diff options
Diffstat (limited to 'include/linux')
974 files changed, 40582 insertions, 17749 deletions
diff --git a/include/linux/a.out.h b/include/linux/a.out.h deleted file mode 100644 index 600cf45645c6..000000000000 --- a/include/linux/a.out.h +++ /dev/null @@ -1,18 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __A_OUT_GNU_H__ -#define __A_OUT_GNU_H__ - -#include <uapi/linux/a.out.h> - -#ifndef __ASSEMBLY__ -#ifdef linux -#include <asm/page.h> -#if defined(__i386__) || defined(__mc68000__) -#else -#ifndef SEGMENT_SIZE -#define SEGMENT_SIZE PAGE_SIZE -#endif -#endif -#endif -#endif /*__ASSEMBLY__ */ -#endif /* __A_OUT_GNU_H__ */ diff --git a/include/linux/acct.h b/include/linux/acct.h index bc70e81895c0..2718c4854815 100644 --- a/include/linux/acct.h +++ b/include/linux/acct.h @@ -21,7 +21,6 @@ #ifdef CONFIG_BSD_PROCESS_ACCT struct pid_namespace; -extern int acct_parm[]; /* for sysctl */ extern void acct_collect(long exitcode, int group_dead); extern void acct_process(void); extern void acct_exit_ns(struct pid_namespace *); diff --git a/include/linux/acpi.h b/include/linux/acpi.h index eaeb4b9255bc..3015235d65e3 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -105,6 +105,7 @@ enum acpi_irq_model_id { ACPI_IRQ_MODEL_IOSAPIC, ACPI_IRQ_MODEL_PLATFORM, ACPI_IRQ_MODEL_GIC, + ACPI_IRQ_MODEL_LPIC, ACPI_IRQ_MODEL_COUNT }; @@ -133,6 +134,7 @@ union acpi_subtable_headers { struct acpi_subtable_header common; struct acpi_hmat_structure hmat; struct acpi_prmt_module_header prmt; + struct acpi_cedt_header cedt; }; typedef int (*acpi_tbl_table_handler)(struct acpi_table_header *table); @@ -140,6 +142,9 @@ typedef int (*acpi_tbl_table_handler)(struct acpi_table_header *table); typedef int (*acpi_tbl_entry_handler)(union acpi_subtable_headers *header, const unsigned long end); +typedef int (*acpi_tbl_entry_handler_arg)(union acpi_subtable_headers *header, + void *arg, const unsigned long end); + /* Debugger support */ struct acpi_debugger_ops { @@ -216,6 +221,8 @@ static inline int acpi_debugger_notify_command_complete(void) struct acpi_subtable_proc { int id; acpi_tbl_entry_handler handler; + acpi_tbl_entry_handler_arg handler_arg; + void *arg; int count; }; @@ -232,17 +239,31 @@ int acpi_locate_initial_tables (void); void acpi_reserve_initial_tables (void); void acpi_table_init_complete (void); int acpi_table_init (void); + +#ifdef CONFIG_ACPI_TABLE_LIB +#define EXPORT_SYMBOL_ACPI_LIB(x) EXPORT_SYMBOL_NS_GPL(x, ACPI) +#define __init_or_acpilib +#define __initdata_or_acpilib +#else +#define EXPORT_SYMBOL_ACPI_LIB(x) +#define __init_or_acpilib __init +#define __initdata_or_acpilib __initdata +#endif + int acpi_table_parse(char *id, acpi_tbl_table_handler handler); -int __init acpi_table_parse_entries(char *id, unsigned long table_size, - int entry_id, - acpi_tbl_entry_handler handler, - unsigned int max_entries); -int __init acpi_table_parse_entries_array(char *id, unsigned long table_size, - struct acpi_subtable_proc *proc, int proc_num, - unsigned int max_entries); +int __init_or_acpilib acpi_table_parse_entries(char *id, + unsigned long table_size, int entry_id, + acpi_tbl_entry_handler handler, unsigned int max_entries); +int __init_or_acpilib acpi_table_parse_entries_array(char *id, + unsigned long table_size, struct acpi_subtable_proc *proc, + int proc_num, unsigned int max_entries); int acpi_table_parse_madt(enum acpi_madt_type id, acpi_tbl_entry_handler handler, unsigned int max_entries); +int __init_or_acpilib +acpi_table_parse_cedt(enum acpi_cedt_type id, + acpi_tbl_entry_handler_arg handler_arg, void *arg); + int acpi_parse_mcfg (struct acpi_table_header *header); void acpi_table_print_madt_entry (struct acpi_subtable_header *madt); @@ -258,14 +279,17 @@ acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *pa) { } void acpi_numa_x2apic_affinity_init(struct acpi_srat_x2apic_cpu_affinity *pa); +#if defined(CONFIG_ARM64) || defined(CONFIG_LOONGARCH) +void acpi_arch_dma_setup(struct device *dev); +#else +static inline void acpi_arch_dma_setup(struct device *dev) { } +#endif + #ifdef CONFIG_ARM64 void acpi_numa_gicc_affinity_init(struct acpi_srat_gicc_affinity *pa); -void acpi_arch_dma_setup(struct device *dev, u64 *dma_addr, u64 *dma_size); #else static inline void acpi_numa_gicc_affinity_init(struct acpi_srat_gicc_affinity *pa) { } -static inline void -acpi_arch_dma_setup(struct device *dev, u64 *dma_addr, u64 *dma_size) { } #endif int acpi_numa_memory_affinity_init (struct acpi_srat_mem_affinity *ma); @@ -336,7 +360,8 @@ int acpi_gsi_to_irq (u32 gsi, unsigned int *irq); int acpi_isa_irq_to_gsi (unsigned isa_irq, u32 *gsi); void acpi_set_irq_model(enum acpi_irq_model_id model, - struct fwnode_handle *fwnode); + struct fwnode_handle *(*)(u32)); +void acpi_set_gsi_to_irq_fallback(u32 (*)(u32)); struct irq_domain *acpi_irq_create_hierarchy(unsigned int flags, unsigned int size, @@ -473,7 +498,7 @@ bool acpi_dev_resource_address_space(struct acpi_resource *ares, struct resource_win *win); bool acpi_dev_resource_ext_address_space(struct acpi_resource *ares, struct resource_win *win); -unsigned long acpi_dev_irq_flags(u8 triggering, u8 polarity, u8 shareable); +unsigned long acpi_dev_irq_flags(u8 triggering, u8 polarity, u8 shareable, u8 wake_capable); unsigned int acpi_dev_get_irq_type(int triggering, int polarity); bool acpi_dev_resource_interrupt(struct acpi_resource *ares, int index, struct resource *res); @@ -484,6 +509,7 @@ int acpi_dev_get_resources(struct acpi_device *adev, struct list_head *list, void *preproc_data); int acpi_dev_get_dma_resources(struct acpi_device *adev, struct list_head *list); +int acpi_dev_get_memory_resources(struct acpi_device *adev, struct list_head *list); int acpi_dev_filter_resource_type(struct acpi_resource *ares, unsigned long types); @@ -500,13 +526,10 @@ int acpi_check_resource_conflict(const struct resource *res); int acpi_check_region(resource_size_t start, resource_size_t n, const char *name); -acpi_status acpi_release_memory(acpi_handle handle, struct resource *res, - u32 level); - int acpi_resources_are_enforced(void); #ifdef CONFIG_HIBERNATION -void __init acpi_check_s4_hw_signature(int check); +extern int acpi_check_s4_hw_signature; #endif #ifdef CONFIG_PM_SLEEP @@ -530,10 +553,16 @@ struct acpi_osc_context { acpi_status acpi_run_osc(acpi_handle handle, struct acpi_osc_context *context); -/* Indexes into _OSC Capabilities Buffer (DWORDs 2 & 3 are device-specific) */ +/* Number of _OSC capability DWORDS depends on bridge type */ +#define OSC_PCI_CAPABILITY_DWORDS 3 +#define OSC_CXL_CAPABILITY_DWORDS 5 + +/* Indexes into _OSC Capabilities Buffer (DWORDs 2 to 5 are device-specific) */ #define OSC_QUERY_DWORD 0 /* DWORD 1 */ #define OSC_SUPPORT_DWORD 1 /* DWORD 2 */ #define OSC_CONTROL_DWORD 2 /* DWORD 3 */ +#define OSC_EXT_SUPPORT_DWORD 3 /* DWORD 4 */ +#define OSC_EXT_CONTROL_DWORD 4 /* DWORD 5 */ /* _OSC Capabilities DWORD 1: Query/Control and Error Returns (generic) */ #define OSC_QUERY_ENABLE 0x00000001 /* input */ @@ -554,12 +583,15 @@ acpi_status acpi_run_osc(acpi_handle handle, struct acpi_osc_context *context); #define OSC_SB_OSLPI_SUPPORT 0x00000100 #define OSC_SB_CPC_DIVERSE_HIGH_SUPPORT 0x00001000 #define OSC_SB_GENERIC_INITIATOR_SUPPORT 0x00002000 +#define OSC_SB_CPC_FLEXIBLE_ADR_SPACE 0x00004000 #define OSC_SB_NATIVE_USB4_SUPPORT 0x00040000 #define OSC_SB_PRM_SUPPORT 0x00200000 extern bool osc_sb_apei_support_acked; extern bool osc_pc_lpi_support_confirmed; extern bool osc_sb_native_usb4_support_confirmed; +extern bool osc_sb_cppc2_support_acked; +extern bool osc_cpc_flexible_adr_space_confirmed; /* USB4 Capabilities */ #define OSC_USB_USB3_TUNNELING 0x00000001 @@ -587,6 +619,29 @@ extern u32 osc_sb_native_usb4_control; #define OSC_PCI_EXPRESS_LTR_CONTROL 0x00000020 #define OSC_PCI_EXPRESS_DPC_CONTROL 0x00000080 +/* CXL _OSC: Capabilities DWORD 4: Support Field */ +#define OSC_CXL_1_1_PORT_REG_ACCESS_SUPPORT 0x00000001 +#define OSC_CXL_2_0_PORT_DEV_REG_ACCESS_SUPPORT 0x00000002 +#define OSC_CXL_PROTOCOL_ERR_REPORTING_SUPPORT 0x00000004 +#define OSC_CXL_NATIVE_HP_SUPPORT 0x00000008 + +/* CXL _OSC: Capabilities DWORD 5: Control Field */ +#define OSC_CXL_ERROR_REPORTING_CONTROL 0x00000001 + +static inline u32 acpi_osc_ctx_get_pci_control(struct acpi_osc_context *context) +{ + u32 *ret = context->ret.pointer; + + return ret[OSC_CONTROL_DWORD]; +} + +static inline u32 acpi_osc_ctx_get_cxl_control(struct acpi_osc_context *context) +{ + u32 *ret = context->ret.pointer; + + return ret[OSC_EXT_CONTROL_DWORD]; +} + #define ACPI_GSB_ACCESS_ATTRIB_QUICK 0x00000002 #define ACPI_GSB_ACCESS_ATTRIB_SEND_RCV 0x00000004 #define ACPI_GSB_ACCESS_ATTRIB_BYTE 0x00000006 @@ -671,7 +726,7 @@ int acpi_device_uevent_modalias(struct device *, struct kobj_uevent_env *); int acpi_device_modalias(struct device *, char *, int); struct platform_device *acpi_create_platform_device(struct acpi_device *, - struct property_entry *); + const struct property_entry *); #define ACPI_PTR(_ptr) (_ptr) static inline void acpi_device_set_enumerated(struct acpi_device *adev) @@ -713,6 +768,7 @@ static inline u64 acpi_arch_get_root_pointer(void) #endif int acpi_get_local_address(acpi_handle handle, u32 *addr); +const char *acpi_get_subsystem_id(acpi_handle handle); #else /* !CONFIG_ACPI */ @@ -746,6 +802,11 @@ acpi_dev_hid_uid_match(struct acpi_device *adev, const char *hid2, const char *u return false; } +static inline int acpi_dev_uid_to_integer(struct acpi_device *adev, u64 *integer) +{ + return -ENODEV; +} + static inline struct acpi_device * acpi_dev_get_first_match_dev(const char *hid, const char *uid, s64 hrv) { @@ -910,7 +971,7 @@ static inline int acpi_device_modalias(struct device *dev, static inline struct platform_device * acpi_create_platform_device(struct acpi_device *adev, - struct property_entry *properties) + const struct property_entry *properties) { return NULL; } @@ -925,8 +986,7 @@ static inline enum dev_dma_attr acpi_get_dma_attr(struct acpi_device *adev) return DEV_DMA_NOT_SUPPORTED; } -static inline int acpi_dma_get_range(struct device *dev, u64 *dma_addr, - u64 *offset, u64 *size) +static inline int acpi_dma_get_range(struct device *dev, const struct bus_dma_region **map) { return -ENODEV; } @@ -974,6 +1034,11 @@ static inline int acpi_get_local_address(acpi_handle handle, u32 *addr) return -ENODEV; } +static inline const char *acpi_get_subsystem_id(acpi_handle handle) +{ + return ERR_PTR(-ENODEV); +} + static inline int acpi_register_wakeup_handler(int wake_irq, bool (*wakeup)(void *context), void *context) { @@ -983,6 +1048,17 @@ static inline int acpi_register_wakeup_handler(int wake_irq, static inline void acpi_unregister_wakeup_handler( bool (*wakeup)(void *context), void *context) { } +struct acpi_osc_context; +static inline u32 acpi_osc_ctx_get_pci_control(struct acpi_osc_context *context) +{ + return 0; +} + +static inline u32 acpi_osc_ctx_get_cxl_control(struct acpi_osc_context *context) +{ + return 0; +} + #endif /* !CONFIG_ACPI */ #ifdef CONFIG_ACPI_HOTPLUG_IOAPIC @@ -1003,7 +1079,16 @@ void acpi_os_set_prepare_extended_sleep(int (*func)(u8 sleep_state, acpi_status acpi_os_prepare_extended_sleep(u8 sleep_state, u32 val_a, u32 val_b); - +#ifdef CONFIG_X86 +struct acpi_s2idle_dev_ops { + struct list_head list_node; + void (*prepare)(void); + void (*check)(void); + void (*restore)(void); +}; +int acpi_register_lps0_dev(struct acpi_s2idle_dev_ops *arg); +void acpi_unregister_lps0_dev(struct acpi_s2idle_dev_ops *arg); +#endif /* CONFIG_X86 */ #ifndef CONFIG_IA64 void arch_reserve_mem_area(acpi_physical_address addr, size_t size); #else @@ -1126,7 +1211,8 @@ bool acpi_gpio_get_irq_resource(struct acpi_resource *ares, struct acpi_resource_gpio **agpio); bool acpi_gpio_get_io_resource(struct acpi_resource *ares, struct acpi_resource_gpio **agpio); -int acpi_dev_gpio_irq_get_by(struct acpi_device *adev, const char *name, int index); +int acpi_dev_gpio_irq_wake_get_by(struct acpi_device *adev, const char *name, int index, + bool *wake_capable); #else static inline bool acpi_gpio_get_irq_resource(struct acpi_resource *ares, struct acpi_resource_gpio **agpio) @@ -1138,16 +1224,28 @@ static inline bool acpi_gpio_get_io_resource(struct acpi_resource *ares, { return false; } -static inline int acpi_dev_gpio_irq_get_by(struct acpi_device *adev, - const char *name, int index) +static inline int acpi_dev_gpio_irq_wake_get_by(struct acpi_device *adev, const char *name, + int index, bool *wake_capable) { return -ENXIO; } #endif +static inline int acpi_dev_gpio_irq_wake_get(struct acpi_device *adev, int index, + bool *wake_capable) +{ + return acpi_dev_gpio_irq_wake_get_by(adev, NULL, index, wake_capable); +} + +static inline int acpi_dev_gpio_irq_get_by(struct acpi_device *adev, const char *name, + int index) +{ + return acpi_dev_gpio_irq_wake_get_by(adev, name, index, NULL); +} + static inline int acpi_dev_gpio_irq_get(struct acpi_device *adev, int index) { - return acpi_dev_gpio_irq_get_by(adev, NULL, index); + return acpi_dev_gpio_irq_wake_get_by(adev, NULL, index, NULL); } /* Device properties */ @@ -1175,7 +1273,7 @@ static inline bool acpi_dev_has_props(const struct acpi_device *adev) struct acpi_device_properties * acpi_data_add_props(struct acpi_device_data *data, const guid_t *guid, - const union acpi_object *properties); + union acpi_object *properties); int acpi_node_prop_get(const struct fwnode_handle *fwnode, const char *propname, void **valptr); @@ -1361,7 +1459,6 @@ int find_acpi_cpu_topology(unsigned int cpu, int level); int find_acpi_cpu_topology_cluster(unsigned int cpu); int find_acpi_cpu_topology_package(unsigned int cpu); int find_acpi_cpu_topology_hetero_id(unsigned int cpu); -int find_acpi_cpu_cache_topology(unsigned int cpu, int level); #else static inline int acpi_pptt_cpu_is_thread(unsigned int cpu) { @@ -1383,10 +1480,6 @@ static inline int find_acpi_cpu_topology_hetero_id(unsigned int cpu) { return -EINVAL; } -static inline int find_acpi_cpu_cache_topology(unsigned int cpu, int level) -{ - return -EINVAL; -} #endif #ifdef CONFIG_ACPI_PCC diff --git a/include/linux/acpi_agdi.h b/include/linux/acpi_agdi.h new file mode 100644 index 000000000000..f477f0b452fa --- /dev/null +++ b/include/linux/acpi_agdi.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef __ACPI_AGDI_H__ +#define __ACPI_AGDI_H__ + +#include <linux/acpi.h> + +#ifdef CONFIG_ACPI_AGDI +void __init acpi_agdi_init(void); +#else +static inline void acpi_agdi_init(void) {} +#endif +#endif /* __ACPI_AGDI_H__ */ diff --git a/include/linux/acpi_iort.h b/include/linux/acpi_iort.h index f1f0842a2cb2..b43be0987b19 100644 --- a/include/linux/acpi_iort.h +++ b/include/linux/acpi_iort.h @@ -33,10 +33,14 @@ struct irq_domain *iort_get_device_domain(struct device *dev, u32 id, enum irq_domain_bus_token bus_token); void acpi_configure_pmsi_domain(struct device *dev); int iort_pmsi_get_dev_id(struct device *dev, u32 *dev_id); +void iort_get_rmr_sids(struct fwnode_handle *iommu_fwnode, + struct list_head *head); +void iort_put_rmr_sids(struct fwnode_handle *iommu_fwnode, + struct list_head *head); /* IOMMU interface */ int iort_dma_get_ranges(struct device *dev, u64 *size); int iort_iommu_configure_id(struct device *dev, const u32 *id_in); -int iort_iommu_msi_get_resv_regions(struct device *dev, struct list_head *head); +void iort_iommu_get_resv_regions(struct device *dev, struct list_head *head); phys_addr_t acpi_iort_dma_get_max_cpu_address(void); #else static inline void acpi_iort_init(void) { } @@ -46,14 +50,18 @@ static inline struct irq_domain *iort_get_device_domain( struct device *dev, u32 id, enum irq_domain_bus_token bus_token) { return NULL; } static inline void acpi_configure_pmsi_domain(struct device *dev) { } +static inline +void iort_get_rmr_sids(struct fwnode_handle *iommu_fwnode, struct list_head *head) { } +static inline +void iort_put_rmr_sids(struct fwnode_handle *iommu_fwnode, struct list_head *head) { } /* IOMMU interface */ static inline int iort_dma_get_ranges(struct device *dev, u64 *size) { return -ENODEV; } static inline int iort_iommu_configure_id(struct device *dev, const u32 *id_in) { return -ENODEV; } static inline -int iort_iommu_msi_get_resv_regions(struct device *dev, struct list_head *head) -{ return 0; } +void iort_iommu_get_resv_regions(struct device *dev, struct list_head *head) +{ } static inline phys_addr_t acpi_iort_dma_get_max_cpu_address(void) { return PHYS_ADDR_MAX; } diff --git a/include/linux/acpi_viot.h b/include/linux/acpi_viot.h index 1eb8ee5b0e5f..a5a122431563 100644 --- a/include/linux/acpi_viot.h +++ b/include/linux/acpi_viot.h @@ -6,9 +6,11 @@ #include <linux/acpi.h> #ifdef CONFIG_ACPI_VIOT +void __init acpi_viot_early_init(void); void __init acpi_viot_init(void); int viot_iommu_configure(struct device *dev); #else +static inline void acpi_viot_early_init(void) {} static inline void acpi_viot_init(void) {} static inline int viot_iommu_configure(struct device *dev) { diff --git a/include/linux/ahci_platform.h b/include/linux/ahci_platform.h index 49e5383d4222..17fa26215292 100644 --- a/include/linux/ahci_platform.h +++ b/include/linux/ahci_platform.h @@ -13,6 +13,7 @@ #include <linux/compiler.h> +struct clk; struct device; struct ata_port_info; struct ahci_host_priv; @@ -21,8 +22,12 @@ struct scsi_host_template; int ahci_platform_enable_phys(struct ahci_host_priv *hpriv); void ahci_platform_disable_phys(struct ahci_host_priv *hpriv); +struct clk *ahci_platform_find_clk(struct ahci_host_priv *hpriv, + const char *con_id); int ahci_platform_enable_clks(struct ahci_host_priv *hpriv); void ahci_platform_disable_clks(struct ahci_host_priv *hpriv); +int ahci_platform_deassert_rsts(struct ahci_host_priv *hpriv); +int ahci_platform_assert_rsts(struct ahci_host_priv *hpriv); int ahci_platform_enable_regulators(struct ahci_host_priv *hpriv); void ahci_platform_disable_regulators(struct ahci_host_priv *hpriv); int ahci_platform_enable_resources(struct ahci_host_priv *hpriv); @@ -41,6 +46,7 @@ int ahci_platform_resume_host(struct device *dev); int ahci_platform_suspend(struct device *dev); int ahci_platform_resume(struct device *dev); -#define AHCI_PLATFORM_GET_RESETS 0x01 +#define AHCI_PLATFORM_GET_RESETS BIT(0) +#define AHCI_PLATFORM_RST_TRIGGER BIT(1) #endif /* _AHCI_PLATFORM_H */ diff --git a/include/linux/aio.h b/include/linux/aio.h index b83e68dd006f..86892a4fe7c8 100644 --- a/include/linux/aio.h +++ b/include/linux/aio.h @@ -20,8 +20,4 @@ static inline void kiocb_set_cancel_fn(struct kiocb *req, kiocb_cancel_fn *cancel) { } #endif /* CONFIG_AIO */ -/* for sysctl: */ -extern unsigned long aio_nr; -extern unsigned long aio_max_nr; - #endif /* __LINUX__AIO_H */ diff --git a/include/linux/amba/bus.h b/include/linux/amba/bus.h index edfcf7a14dcd..5001e14c5c06 100644 --- a/include/linux/amba/bus.h +++ b/include/linux/amba/bus.h @@ -67,10 +67,15 @@ struct amba_device { struct clk *pclk; struct device_dma_parameters dma_parms; unsigned int periphid; + struct mutex periphid_lock; unsigned int cid; struct amba_cs_uci_id uci; unsigned int irq[AMBA_NR_IRQS]; - char *driver_override; + /* + * Driver name to force a match. Do not set directly, because core + * frees it. Use driver_set_override() to set or clear it. + */ + const char *driver_override; }; struct amba_driver { @@ -79,6 +84,14 @@ struct amba_driver { void (*remove)(struct amba_device *); void (*shutdown)(struct amba_device *); const struct amba_id *id_table; + /* + * For most device drivers, no need to care about this flag as long as + * all DMAs are handled through the kernel DMA API. For some special + * ones, for example VFIO drivers, they know how to manage the DMA + * themselves and set this flag so that the IOMMU layer will allow them + * to setup and manage their own I/O address space. + */ + bool driver_managed_dma; }; /* @@ -90,14 +103,8 @@ enum amba_vendor { AMBA_VENDOR_ST = 0x80, AMBA_VENDOR_QCOM = 0x51, AMBA_VENDOR_LSI = 0xb6, - AMBA_VENDOR_LINUX = 0xfe, /* This value is not official */ }; -/* This is used to generate pseudo-ID for AMBA device */ -#define AMBA_LINUX_ID(conf, rev, part) \ - (((conf) & 0xff) << 24 | ((rev) & 0xf) << 20 | \ - AMBA_VENDOR_LINUX << 12 | ((part) & 0xfff)) - extern struct bus_type amba_bustype; #define to_amba_device(d) container_of(d, struct amba_device, dev) @@ -123,30 +130,9 @@ void amba_device_put(struct amba_device *); int amba_device_add(struct amba_device *, struct resource *); int amba_device_register(struct amba_device *, struct resource *); void amba_device_unregister(struct amba_device *); -struct amba_device *amba_find_device(const char *, struct device *, unsigned int, unsigned int); int amba_request_regions(struct amba_device *, const char *); void amba_release_regions(struct amba_device *); -static inline int amba_pclk_enable(struct amba_device *dev) -{ - return clk_enable(dev->pclk); -} - -static inline void amba_pclk_disable(struct amba_device *dev) -{ - clk_disable(dev->pclk); -} - -static inline int amba_pclk_prepare(struct amba_device *dev) -{ - return clk_prepare(dev->pclk); -} - -static inline void amba_pclk_unprepare(struct amba_device *dev) -{ - clk_unprepare(dev->pclk); -} - /* Some drivers don't use the struct amba_device */ #define AMBA_CONFIG_BITS(a) (((a) >> 24) & 0xff) #define AMBA_REV_BITS(a) (((a) >> 20) & 0x0f) diff --git a/include/linux/amba/mmci.h b/include/linux/amba/mmci.h index c92ebc39fc1f..6f96dc2209c0 100644 --- a/include/linux/amba/mmci.h +++ b/include/linux/amba/mmci.h @@ -13,17 +13,11 @@ * @ocr_mask: available voltages on the 4 pins from the block, this * is ignored if a regulator is used, see the MMC_VDD_* masks in * mmc/host.h - * @ios_handler: a callback function to act on specfic ios changes, - * used for example to control a levelshifter - * mask into a value to be binary (or set some other custom bits - * in MMCIPWR) or:ed and written into the MMCIPWR register of the - * block. May also control external power based on the power_mode. * @status: if no GPIO line was given to the block in this function will * be called to determine whether a card is present in the MMC slot or not */ struct mmci_platform_data { unsigned int ocr_mask; - int (*ios_handler)(struct device *, struct mmc_ios *); unsigned int (*status)(struct device *); }; diff --git a/include/linux/amd-iommu.h b/include/linux/amd-iommu.h index 58e6c3806c09..953e6f12fa1c 100644 --- a/include/linux/amd-iommu.h +++ b/include/linux/amd-iommu.h @@ -206,4 +206,8 @@ int amd_iommu_pc_get_reg(struct amd_iommu *iommu, u8 bank, u8 cntr, u8 fxn, u64 *value); struct amd_iommu *get_amd_iommu(unsigned int idx); +#ifdef CONFIG_AMD_MEM_ENCRYPT +int amd_iommu_snp_enable(void); +#endif + #endif /* _ASM_X86_AMD_IOMMU_H */ diff --git a/include/linux/amd-pstate.h b/include/linux/amd-pstate.h new file mode 100644 index 000000000000..1c4b8659f171 --- /dev/null +++ b/include/linux/amd-pstate.h @@ -0,0 +1,77 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * linux/include/linux/amd-pstate.h + * + * Copyright (C) 2022 Advanced Micro Devices, Inc. + * + * Author: Meng Li <li.meng@amd.com> + */ + +#ifndef _LINUX_AMD_PSTATE_H +#define _LINUX_AMD_PSTATE_H + +#include <linux/pm_qos.h> + +/********************************************************************* + * AMD P-state INTERFACE * + *********************************************************************/ +/** + * struct amd_aperf_mperf + * @aperf: actual performance frequency clock count + * @mperf: maximum performance frequency clock count + * @tsc: time stamp counter + */ +struct amd_aperf_mperf { + u64 aperf; + u64 mperf; + u64 tsc; +}; + +/** + * struct amd_cpudata - private CPU data for AMD P-State + * @cpu: CPU number + * @req: constraint request to apply + * @cppc_req_cached: cached performance request hints + * @highest_perf: the maximum performance an individual processor may reach, + * assuming ideal conditions + * @nominal_perf: the maximum sustained performance level of the processor, + * assuming ideal operating conditions + * @lowest_nonlinear_perf: the lowest performance level at which nonlinear power + * savings are achieved + * @lowest_perf: the absolute lowest performance level of the processor + * @max_freq: the frequency that mapped to highest_perf + * @min_freq: the frequency that mapped to lowest_perf + * @nominal_freq: the frequency that mapped to nominal_perf + * @lowest_nonlinear_freq: the frequency that mapped to lowest_nonlinear_perf + * @cur: Difference of Aperf/Mperf/tsc count between last and current sample + * @prev: Last Aperf/Mperf/tsc count value read from register + * @freq: current cpu frequency value + * @boost_supported: check whether the Processor or SBIOS supports boost mode + * + * The amd_cpudata is key private data for each CPU thread in AMD P-State, and + * represents all the attributes and goals that AMD P-State requests at runtime. + */ +struct amd_cpudata { + int cpu; + + struct freq_qos_request req[2]; + u64 cppc_req_cached; + + u32 highest_perf; + u32 nominal_perf; + u32 lowest_nonlinear_perf; + u32 lowest_perf; + + u32 max_freq; + u32 min_freq; + u32 nominal_freq; + u32 lowest_nonlinear_freq; + + struct amd_aperf_mperf cur; + struct amd_aperf_mperf prev; + + u64 freq; + bool boost_supported; +}; + +#endif /* _LINUX_AMD_PSTATE_H */ diff --git a/include/linux/aperture.h b/include/linux/aperture.h new file mode 100644 index 000000000000..442f15a57cad --- /dev/null +++ b/include/linux/aperture.h @@ -0,0 +1,56 @@ +/* SPDX-License-Identifier: MIT */ + +#ifndef _LINUX_APERTURE_H_ +#define _LINUX_APERTURE_H_ + +#include <linux/types.h> + +struct pci_dev; +struct platform_device; + +#if defined(CONFIG_APERTURE_HELPERS) +int devm_aperture_acquire_for_platform_device(struct platform_device *pdev, + resource_size_t base, + resource_size_t size); + +int aperture_remove_conflicting_devices(resource_size_t base, resource_size_t size, + bool primary, const char *name); + +int aperture_remove_conflicting_pci_devices(struct pci_dev *pdev, const char *name); +#else +static inline int devm_aperture_acquire_for_platform_device(struct platform_device *pdev, + resource_size_t base, + resource_size_t size) +{ + return 0; +} + +static inline int aperture_remove_conflicting_devices(resource_size_t base, resource_size_t size, + bool primary, const char *name) +{ + return 0; +} + +static inline int aperture_remove_conflicting_pci_devices(struct pci_dev *pdev, const char *name) +{ + return 0; +} +#endif + +/** + * aperture_remove_all_conflicting_devices - remove all existing framebuffers + * @primary: also kick vga16fb if present; only relevant for VGA devices + * @name: a descriptive name of the requesting driver + * + * This function removes all graphics device drivers. Use this function on systems + * that can have their framebuffer located anywhere in memory. + * + * Returns: + * 0 on success, or a negative errno code otherwise + */ +static inline int aperture_remove_all_conflicting_devices(bool primary, const char *name) +{ + return aperture_remove_conflicting_devices(0, (resource_size_t)-1, primary, name); +} + +#endif diff --git a/include/linux/arch_topology.h b/include/linux/arch_topology.h index cce6136b300a..a07b510e7dc5 100644 --- a/include/linux/arch_topology.h +++ b/include/linux/arch_topology.h @@ -11,6 +11,10 @@ void topology_normalize_cpu_scale(void); int topology_update_cpu_topology(void); +#ifdef CONFIG_ACPI_CPPC_LIB +void topology_init_cpu_capacity_cppc(void); +#endif + struct device_node; bool topology_parse_cpu_capacity(struct device_node *cpu_node, int cpu); @@ -64,7 +68,6 @@ struct cpu_topology { int core_id; int cluster_id; int package_id; - int llc_id; cpumask_t thread_sibling; cpumask_t core_sibling; cpumask_t cluster_sibling; diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h index 63ccb5252190..220c8c60e021 100644 --- a/include/linux/arm-smccc.h +++ b/include/linux/arm-smccc.h @@ -92,6 +92,11 @@ ARM_SMCCC_SMC_32, \ 0, 0x7fff) +#define ARM_SMCCC_ARCH_WORKAROUND_3 \ + ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ + ARM_SMCCC_SMC_32, \ + 0, 0x3fff) + #define ARM_SMCCC_VENDOR_HYP_CALL_UID_FUNC_ID \ ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ ARM_SMCCC_SMC_32, \ diff --git a/include/linux/arm_ffa.h b/include/linux/arm_ffa.h index 85651e41ded8..5f02d2e6b9d9 100644 --- a/include/linux/arm_ffa.h +++ b/include/linux/arm_ffa.h @@ -17,6 +17,7 @@ struct ffa_device { bool mode_32bit; uuid_t uuid; struct device dev; + const struct ffa_ops *ops; }; #define to_ffa_dev(d) container_of(d, struct ffa_device, dev) @@ -38,21 +39,27 @@ struct ffa_driver { static inline void ffa_dev_set_drvdata(struct ffa_device *fdev, void *data) { - fdev->dev.driver_data = data; + dev_set_drvdata(&fdev->dev, data); +} + +static inline void *ffa_dev_get_drvdata(struct ffa_device *fdev) +{ + return dev_get_drvdata(&fdev->dev); } #if IS_REACHABLE(CONFIG_ARM_FFA_TRANSPORT) -struct ffa_device *ffa_device_register(const uuid_t *uuid, int vm_id); +struct ffa_device *ffa_device_register(const uuid_t *uuid, int vm_id, + const struct ffa_ops *ops); void ffa_device_unregister(struct ffa_device *ffa_dev); int ffa_driver_register(struct ffa_driver *driver, struct module *owner, const char *mod_name); void ffa_driver_unregister(struct ffa_driver *driver); bool ffa_device_is_valid(struct ffa_device *ffa_dev); -const struct ffa_dev_ops *ffa_dev_ops_get(struct ffa_device *dev); #else static inline -struct ffa_device *ffa_device_register(const uuid_t *uuid, int vm_id) +struct ffa_device *ffa_device_register(const uuid_t *uuid, int vm_id, + const struct ffa_ops *ops) { return NULL; } @@ -71,11 +78,6 @@ static inline void ffa_driver_unregister(struct ffa_driver *driver) {} static inline bool ffa_device_is_valid(struct ffa_device *ffa_dev) { return false; } -static inline -const struct ffa_dev_ops *ffa_dev_ops_get(struct ffa_device *dev) -{ - return NULL; -} #endif /* CONFIG_ARM_FFA_TRANSPORT */ #define ffa_register(driver) \ @@ -104,7 +106,10 @@ struct ffa_partition_info { #define FFA_PARTITION_DIRECT_SEND BIT(1) /* partition can send and receive indirect messages. */ #define FFA_PARTITION_INDIRECT_MSG BIT(2) +/* partition runs in the AArch64 execution state. */ +#define FFA_PARTITION_AARCH64_EXEC BIT(8) u32 properties; + u32 uuid[4]; }; /* For use with FFA_MSG_SEND_DIRECT_{REQ,RESP} which pass data via registers */ @@ -252,18 +257,28 @@ struct ffa_mem_ops_args { struct ffa_mem_region_attributes *attrs; }; -struct ffa_dev_ops { +struct ffa_info_ops { u32 (*api_version_get)(void); int (*partition_info_get)(const char *uuid_str, struct ffa_partition_info *buffer); +}; + +struct ffa_msg_ops { void (*mode_32bit_set)(struct ffa_device *dev); int (*sync_send_receive)(struct ffa_device *dev, struct ffa_send_direct_data *data); +}; + +struct ffa_mem_ops { int (*memory_reclaim)(u64 g_handle, u32 flags); - int (*memory_share)(struct ffa_device *dev, - struct ffa_mem_ops_args *args); - int (*memory_lend)(struct ffa_device *dev, - struct ffa_mem_ops_args *args); + int (*memory_share)(struct ffa_mem_ops_args *args); + int (*memory_lend)(struct ffa_mem_ops_args *args); +}; + +struct ffa_ops { + const struct ffa_info_ops *info_ops; + const struct ffa_msg_ops *msg_ops; + const struct ffa_mem_ops *mem_ops; }; #endif /* _LINUX_ARM_FFA_H */ diff --git a/include/linux/arm_sdei.h b/include/linux/arm_sdei.h index 0a241c5c911d..14dc461b0e82 100644 --- a/include/linux/arm_sdei.h +++ b/include/linux/arm_sdei.h @@ -46,9 +46,11 @@ int sdei_unregister_ghes(struct ghes *ghes); /* For use by arch code when CPU hotplug notifiers are not appropriate. */ int sdei_mask_local_cpu(void); int sdei_unmask_local_cpu(void); +void __init sdei_init(void); #else static inline int sdei_mask_local_cpu(void) { return 0; } static inline int sdei_unmask_local_cpu(void) { return 0; } +static inline void sdei_init(void) { } #endif /* CONFIG_ARM_SDE_INTERFACE */ diff --git a/include/linux/ata.h b/include/linux/ata.h index 199e47e97d64..e3050e153a71 100644 --- a/include/linux/ata.h +++ b/include/linux/ata.h @@ -324,12 +324,12 @@ enum { ATA_LOG_NCQ_NON_DATA = 0x12, ATA_LOG_NCQ_SEND_RECV = 0x13, ATA_LOG_IDENTIFY_DEVICE = 0x30, + ATA_LOG_CONCURRENT_POSITIONING_RANGES = 0x47, /* Identify device log pages: */ ATA_LOG_SECURITY = 0x06, ATA_LOG_SATA_SETTINGS = 0x08, ATA_LOG_ZONED_INFORMATION = 0x09, - ATA_LOG_CONCURRENT_POSITIONING_RANGES = 0x47, /* Identify device SATA settings log:*/ ATA_LOG_DEVSLP_OFFSET = 0x30, @@ -566,6 +566,18 @@ struct ata_bmdma_prd { ((((id)[ATA_ID_SATA_CAPABILITY] != 0x0000) && \ ((id)[ATA_ID_SATA_CAPABILITY] != 0xffff)) && \ ((id)[ATA_ID_FEATURE_SUPP] & (1 << 2))) +#define ata_id_has_devslp(id) \ + ((((id)[ATA_ID_SATA_CAPABILITY] != 0x0000) && \ + ((id)[ATA_ID_SATA_CAPABILITY] != 0xffff)) && \ + ((id)[ATA_ID_FEATURE_SUPP] & (1 << 8))) +#define ata_id_has_ncq_autosense(id) \ + ((((id)[ATA_ID_SATA_CAPABILITY] != 0x0000) && \ + ((id)[ATA_ID_SATA_CAPABILITY] != 0xffff)) && \ + ((id)[ATA_ID_FEATURE_SUPP] & (1 << 7))) +#define ata_id_has_dipm(id) \ + ((((id)[ATA_ID_SATA_CAPABILITY] != 0x0000) && \ + ((id)[ATA_ID_SATA_CAPABILITY] != 0xffff)) && \ + ((id)[ATA_ID_FEATURE_SUPP] & (1 << 3))) #define ata_id_iordy_disable(id) ((id)[ATA_ID_CAPABILITY] & (1 << 10)) #define ata_id_has_iordy(id) ((id)[ATA_ID_CAPABILITY] & (1 << 11)) #define ata_id_u32(id,n) \ @@ -578,9 +590,6 @@ struct ata_bmdma_prd { #define ata_id_cdb_intr(id) (((id)[ATA_ID_CONFIG] & 0x60) == 0x20) #define ata_id_has_da(id) ((id)[ATA_ID_SATA_CAPABILITY_2] & (1 << 4)) -#define ata_id_has_devslp(id) ((id)[ATA_ID_FEATURE_SUPP] & (1 << 8)) -#define ata_id_has_ncq_autosense(id) \ - ((id)[ATA_ID_FEATURE_SUPP] & (1 << 7)) static inline bool ata_id_has_hipm(const u16 *id) { @@ -592,17 +601,6 @@ static inline bool ata_id_has_hipm(const u16 *id) return val & (1 << 9); } -static inline bool ata_id_has_dipm(const u16 *id) -{ - u16 val = id[ATA_ID_FEATURE_SUPP]; - - if (val == 0 || val == 0xffff) - return false; - - return val & (1 << 3); -} - - static inline bool ata_id_has_fua(const u16 *id) { if ((id[ATA_ID_CFSSE] & 0xC000) != 0x4000) @@ -771,16 +769,21 @@ static inline bool ata_id_has_read_log_dma_ext(const u16 *id) static inline bool ata_id_has_sense_reporting(const u16 *id) { - if (!(id[ATA_ID_CFS_ENABLE_2] & (1 << 15))) + if (!(id[ATA_ID_CFS_ENABLE_2] & BIT(15))) + return false; + if ((id[ATA_ID_COMMAND_SET_3] & (BIT(15) | BIT(14))) != BIT(14)) return false; - return id[ATA_ID_COMMAND_SET_3] & (1 << 6); + return id[ATA_ID_COMMAND_SET_3] & BIT(6); } static inline bool ata_id_sense_reporting_enabled(const u16 *id) { - if (!(id[ATA_ID_CFS_ENABLE_2] & (1 << 15))) + if (!ata_id_has_sense_reporting(id)) + return false; + /* ata_id_has_sense_reporting() == true, word 86 must have bit 15 set */ + if ((id[ATA_ID_COMMAND_SET_4] & (BIT(15) | BIT(14))) != BIT(14)) return false; - return id[ATA_ID_COMMAND_SET_4] & (1 << 6); + return id[ATA_ID_COMMAND_SET_4] & BIT(6); } /** diff --git a/include/linux/atm_tcp.h b/include/linux/atm_tcp.h index c8ecf6f68fb5..2558439d849b 100644 --- a/include/linux/atm_tcp.h +++ b/include/linux/atm_tcp.h @@ -9,6 +9,8 @@ #include <uapi/linux/atm_tcp.h> +struct atm_vcc; +struct module; struct atm_tcp_ops { int (*attach)(struct atm_vcc *vcc,int itf); diff --git a/include/linux/atomic/atomic-arch-fallback.h b/include/linux/atomic/atomic-arch-fallback.h index a3dba31df01e..77bc5522e61c 100644 --- a/include/linux/atomic/atomic-arch-fallback.h +++ b/include/linux/atomic/atomic-arch-fallback.h @@ -147,11 +147,90 @@ #endif /* arch_try_cmpxchg_relaxed */ +#ifndef arch_try_cmpxchg64_relaxed +#ifdef arch_try_cmpxchg64 +#define arch_try_cmpxchg64_acquire arch_try_cmpxchg64 +#define arch_try_cmpxchg64_release arch_try_cmpxchg64 +#define arch_try_cmpxchg64_relaxed arch_try_cmpxchg64 +#endif /* arch_try_cmpxchg64 */ + +#ifndef arch_try_cmpxchg64 +#define arch_try_cmpxchg64(_ptr, _oldp, _new) \ +({ \ + typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ + ___r = arch_cmpxchg64((_ptr), ___o, (_new)); \ + if (unlikely(___r != ___o)) \ + *___op = ___r; \ + likely(___r == ___o); \ +}) +#endif /* arch_try_cmpxchg64 */ + +#ifndef arch_try_cmpxchg64_acquire +#define arch_try_cmpxchg64_acquire(_ptr, _oldp, _new) \ +({ \ + typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ + ___r = arch_cmpxchg64_acquire((_ptr), ___o, (_new)); \ + if (unlikely(___r != ___o)) \ + *___op = ___r; \ + likely(___r == ___o); \ +}) +#endif /* arch_try_cmpxchg64_acquire */ + +#ifndef arch_try_cmpxchg64_release +#define arch_try_cmpxchg64_release(_ptr, _oldp, _new) \ +({ \ + typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ + ___r = arch_cmpxchg64_release((_ptr), ___o, (_new)); \ + if (unlikely(___r != ___o)) \ + *___op = ___r; \ + likely(___r == ___o); \ +}) +#endif /* arch_try_cmpxchg64_release */ + +#ifndef arch_try_cmpxchg64_relaxed +#define arch_try_cmpxchg64_relaxed(_ptr, _oldp, _new) \ +({ \ + typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ + ___r = arch_cmpxchg64_relaxed((_ptr), ___o, (_new)); \ + if (unlikely(___r != ___o)) \ + *___op = ___r; \ + likely(___r == ___o); \ +}) +#endif /* arch_try_cmpxchg64_relaxed */ + +#else /* arch_try_cmpxchg64_relaxed */ + +#ifndef arch_try_cmpxchg64_acquire +#define arch_try_cmpxchg64_acquire(...) \ + __atomic_op_acquire(arch_try_cmpxchg64, __VA_ARGS__) +#endif + +#ifndef arch_try_cmpxchg64_release +#define arch_try_cmpxchg64_release(...) \ + __atomic_op_release(arch_try_cmpxchg64, __VA_ARGS__) +#endif + +#ifndef arch_try_cmpxchg64 +#define arch_try_cmpxchg64(...) \ + __atomic_op_fence(arch_try_cmpxchg64, __VA_ARGS__) +#endif + +#endif /* arch_try_cmpxchg64_relaxed */ + #ifndef arch_atomic_read_acquire static __always_inline int arch_atomic_read_acquire(const atomic_t *v) { - return smp_load_acquire(&(v)->counter); + int ret; + + if (__native_word(atomic_t)) { + ret = smp_load_acquire(&(v)->counter); + } else { + ret = arch_atomic_read(v); + __atomic_acquire_fence(); + } + + return ret; } #define arch_atomic_read_acquire arch_atomic_read_acquire #endif @@ -160,7 +239,12 @@ arch_atomic_read_acquire(const atomic_t *v) static __always_inline void arch_atomic_set_release(atomic_t *v, int i) { - smp_store_release(&(v)->counter, i); + if (__native_word(atomic_t)) { + smp_store_release(&(v)->counter, i); + } else { + __atomic_release_fence(); + arch_atomic_set(v, i); + } } #define arch_atomic_set_release arch_atomic_set_release #endif @@ -1258,7 +1342,16 @@ arch_atomic_dec_if_positive(atomic_t *v) static __always_inline s64 arch_atomic64_read_acquire(const atomic64_t *v) { - return smp_load_acquire(&(v)->counter); + s64 ret; + + if (__native_word(atomic64_t)) { + ret = smp_load_acquire(&(v)->counter); + } else { + ret = arch_atomic64_read(v); + __atomic_acquire_fence(); + } + + return ret; } #define arch_atomic64_read_acquire arch_atomic64_read_acquire #endif @@ -1267,7 +1360,12 @@ arch_atomic64_read_acquire(const atomic64_t *v) static __always_inline void arch_atomic64_set_release(atomic64_t *v, s64 i) { - smp_store_release(&(v)->counter, i); + if (__native_word(atomic64_t)) { + smp_store_release(&(v)->counter, i); + } else { + __atomic_release_fence(); + arch_atomic64_set(v, i); + } } #define arch_atomic64_set_release arch_atomic64_set_release #endif @@ -2358,4 +2456,4 @@ arch_atomic64_dec_if_positive(atomic64_t *v) #endif #endif /* _LINUX_ATOMIC_FALLBACK_H */ -// cca554917d7ea73d5e3e7397dd70c484cad9b2c4 +// b5e87bdd5ede61470c29f7a7e4de781af3770f09 diff --git a/include/linux/atomic/atomic-instrumented.h b/include/linux/atomic/atomic-instrumented.h index 5d69b143c28e..7a139ec030b0 100644 --- a/include/linux/atomic/atomic-instrumented.h +++ b/include/linux/atomic/atomic-instrumented.h @@ -2006,6 +2006,44 @@ atomic_long_dec_if_positive(atomic_long_t *v) arch_try_cmpxchg_relaxed(__ai_ptr, __ai_oldp, __VA_ARGS__); \ }) +#define try_cmpxchg64(ptr, oldp, ...) \ +({ \ + typeof(ptr) __ai_ptr = (ptr); \ + typeof(oldp) __ai_oldp = (oldp); \ + kcsan_mb(); \ + instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \ + arch_try_cmpxchg64(__ai_ptr, __ai_oldp, __VA_ARGS__); \ +}) + +#define try_cmpxchg64_acquire(ptr, oldp, ...) \ +({ \ + typeof(ptr) __ai_ptr = (ptr); \ + typeof(oldp) __ai_oldp = (oldp); \ + instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \ + arch_try_cmpxchg64_acquire(__ai_ptr, __ai_oldp, __VA_ARGS__); \ +}) + +#define try_cmpxchg64_release(ptr, oldp, ...) \ +({ \ + typeof(ptr) __ai_ptr = (ptr); \ + typeof(oldp) __ai_oldp = (oldp); \ + kcsan_release(); \ + instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \ + arch_try_cmpxchg64_release(__ai_ptr, __ai_oldp, __VA_ARGS__); \ +}) + +#define try_cmpxchg64_relaxed(ptr, oldp, ...) \ +({ \ + typeof(ptr) __ai_ptr = (ptr); \ + typeof(oldp) __ai_oldp = (oldp); \ + instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \ + arch_try_cmpxchg64_relaxed(__ai_ptr, __ai_oldp, __VA_ARGS__); \ +}) + #define cmpxchg_local(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ @@ -2045,4 +2083,4 @@ atomic_long_dec_if_positive(atomic_long_t *v) }) #endif /* _LINUX_ATOMIC_INSTRUMENTED_H */ -// 87c974b93032afd42143613434d1a7788fa598f9 +// 764f741eb77a7ad565dc8d99ce2837d5542e8aee diff --git a/include/linux/audit.h b/include/linux/audit.h index d06134ac6245..3608992848d3 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -119,8 +119,6 @@ enum audit_nfcfgop { AUDIT_NFT_OP_INVALID, }; -extern int is_audit_feature_set(int which); - extern int __init audit_register_class(int class, unsigned *list); extern int audit_classify_syscall(int abi, unsigned syscall); extern int audit_classify_arch(int arch); @@ -287,7 +285,6 @@ static inline int audit_signal_info(int sig, struct task_struct *t) /* These are defined in auditsc.c */ /* Public API */ extern int audit_alloc(struct task_struct *task); -extern int audit_alloc_kernel(struct task_struct *task); extern void __audit_free(struct task_struct *task); extern void __audit_uring_entry(u8 op); extern void __audit_uring_exit(int success, long code); @@ -339,7 +336,7 @@ static inline void audit_uring_entry(u8 op) } static inline void audit_uring_exit(int success, long code) { - if (unlikely(!audit_dummy_context())) + if (unlikely(audit_context())) __audit_uring_exit(success, code); } static inline void audit_syscall_entry(int major, unsigned long a0, @@ -580,10 +577,6 @@ static inline int audit_alloc(struct task_struct *task) { return 0; } -static inline int audit_alloc_kernel(struct task_struct *task) -{ - return 0; -} static inline void audit_free(struct task_struct *task) { } static inline void audit_uring_entry(u8 op) diff --git a/include/linux/auxiliary_bus.h b/include/linux/auxiliary_bus.h index fc51d45f106b..de21d9d24a95 100644 --- a/include/linux/auxiliary_bus.h +++ b/include/linux/auxiliary_bus.h @@ -11,12 +11,172 @@ #include <linux/device.h> #include <linux/mod_devicetable.h> +/** + * DOC: DEVICE_LIFESPAN + * + * The registering driver is the entity that allocates memory for the + * auxiliary_device and registers it on the auxiliary bus. It is important to + * note that, as opposed to the platform bus, the registering driver is wholly + * responsible for the management of the memory used for the device object. + * + * To be clear the memory for the auxiliary_device is freed in the release() + * callback defined by the registering driver. The registering driver should + * only call auxiliary_device_delete() and then auxiliary_device_uninit() when + * it is done with the device. The release() function is then automatically + * called if and when other code releases their reference to the devices. + * + * A parent object, defined in the shared header file, contains the + * auxiliary_device. It also contains a pointer to the shared object(s), which + * also is defined in the shared header. Both the parent object and the shared + * object(s) are allocated by the registering driver. This layout allows the + * auxiliary_driver's registering module to perform a container_of() call to go + * from the pointer to the auxiliary_device, that is passed during the call to + * the auxiliary_driver's probe function, up to the parent object, and then + * have access to the shared object(s). + * + * The memory for the shared object(s) must have a lifespan equal to, or + * greater than, the lifespan of the memory for the auxiliary_device. The + * auxiliary_driver should only consider that the shared object is valid as + * long as the auxiliary_device is still registered on the auxiliary bus. It + * is up to the registering driver to manage (e.g. free or keep available) the + * memory for the shared object beyond the life of the auxiliary_device. + * + * The registering driver must unregister all auxiliary devices before its own + * driver.remove() is completed. An easy way to ensure this is to use the + * devm_add_action_or_reset() call to register a function against the parent + * device which unregisters the auxiliary device object(s). + * + * Finally, any operations which operate on the auxiliary devices must continue + * to function (if only to return an error) after the registering driver + * unregisters the auxiliary device. + */ + +/** + * struct auxiliary_device - auxiliary device object. + * @dev: Device, + * The release and parent fields of the device structure must be filled + * in + * @name: Match name found by the auxiliary device driver, + * @id: unique identitier if multiple devices of the same name are exported, + * + * An auxiliary_device represents a part of its parent device's functionality. + * It is given a name that, combined with the registering drivers + * KBUILD_MODNAME, creates a match_name that is used for driver binding, and an + * id that combined with the match_name provide a unique name to register with + * the bus subsystem. For example, a driver registering an auxiliary device is + * named 'foo_mod.ko' and the subdevice is named 'foo_dev'. The match name is + * therefore 'foo_mod.foo_dev'. + * + * Registering an auxiliary_device is a three-step process. + * + * First, a 'struct auxiliary_device' needs to be defined or allocated for each + * sub-device desired. The name, id, dev.release, and dev.parent fields of + * this structure must be filled in as follows. + * + * The 'name' field is to be given a name that is recognized by the auxiliary + * driver. If two auxiliary_devices with the same match_name, eg + * "foo_mod.foo_dev", are registered onto the bus, they must have unique id + * values (e.g. "x" and "y") so that the registered devices names are + * "foo_mod.foo_dev.x" and "foo_mod.foo_dev.y". If match_name + id are not + * unique, then the device_add fails and generates an error message. + * + * The auxiliary_device.dev.type.release or auxiliary_device.dev.release must + * be populated with a non-NULL pointer to successfully register the + * auxiliary_device. This release call is where resources associated with the + * auxiliary device must be free'ed. Because once the device is placed on the + * bus the parent driver can not tell what other code may have a reference to + * this data. + * + * The auxiliary_device.dev.parent should be set. Typically to the registering + * drivers device. + * + * Second, call auxiliary_device_init(), which checks several aspects of the + * auxiliary_device struct and performs a device_initialize(). After this step + * completes, any error state must have a call to auxiliary_device_uninit() in + * its resolution path. + * + * The third and final step in registering an auxiliary_device is to perform a + * call to auxiliary_device_add(), which sets the name of the device and adds + * the device to the bus. + * + * .. code-block:: c + * + * #define MY_DEVICE_NAME "foo_dev" + * + * ... + * + * struct auxiliary_device *my_aux_dev = my_aux_dev_alloc(xxx); + * + * // Step 1: + * my_aux_dev->name = MY_DEVICE_NAME; + * my_aux_dev->id = my_unique_id_alloc(xxx); + * my_aux_dev->dev.release = my_aux_dev_release; + * my_aux_dev->dev.parent = my_dev; + * + * // Step 2: + * if (auxiliary_device_init(my_aux_dev)) + * goto fail; + * + * // Step 3: + * if (auxiliary_device_add(my_aux_dev)) { + * auxiliary_device_uninit(my_aux_dev); + * goto fail; + * } + * + * ... + * + * + * Unregistering an auxiliary_device is a two-step process to mirror the + * register process. First call auxiliary_device_delete(), then call + * auxiliary_device_uninit(). + * + * .. code-block:: c + * + * auxiliary_device_delete(my_dev->my_aux_dev); + * auxiliary_device_uninit(my_dev->my_aux_dev); + */ struct auxiliary_device { struct device dev; const char *name; u32 id; }; +/** + * struct auxiliary_driver - Definition of an auxiliary bus driver + * @probe: Called when a matching device is added to the bus. + * @remove: Called when device is removed from the bus. + * @shutdown: Called at shut-down time to quiesce the device. + * @suspend: Called to put the device to sleep mode. Usually to a power state. + * @resume: Called to bring a device from sleep mode. + * @name: Driver name. + * @driver: Core driver structure. + * @id_table: Table of devices this driver should match on the bus. + * + * Auxiliary drivers follow the standard driver model convention, where + * discovery/enumeration is handled by the core, and drivers provide probe() + * and remove() methods. They support power management and shutdown + * notifications using the standard conventions. + * + * Auxiliary drivers register themselves with the bus by calling + * auxiliary_driver_register(). The id_table contains the match_names of + * auxiliary devices that a driver can bind with. + * + * .. code-block:: c + * + * static const struct auxiliary_device_id my_auxiliary_id_table[] = { + * { .name = "foo_mod.foo_dev" }, + * {}, + * }; + * + * MODULE_DEVICE_TABLE(auxiliary, my_auxiliary_id_table); + * + * struct auxiliary_driver my_drv = { + * .name = "myauxiliarydrv", + * .id_table = my_auxiliary_id_table, + * .probe = my_drv_probe, + * .remove = my_drv_remove + * }; + */ struct auxiliary_driver { int (*probe)(struct auxiliary_device *auxdev, const struct auxiliary_device_id *id); void (*remove)(struct auxiliary_device *auxdev); @@ -28,6 +188,16 @@ struct auxiliary_driver { const struct auxiliary_device_id *id_table; }; +static inline void *auxiliary_get_drvdata(struct auxiliary_device *auxdev) +{ + return dev_get_drvdata(&auxdev->dev); +} + +static inline void auxiliary_set_drvdata(struct auxiliary_device *auxdev, void *data) +{ + dev_set_drvdata(&auxdev->dev, data); +} + static inline struct auxiliary_device *to_auxiliary_dev(struct device *dev) { return container_of(dev, struct auxiliary_device, dev); @@ -66,6 +236,10 @@ void auxiliary_driver_unregister(struct auxiliary_driver *auxdrv); * Helper macro for auxiliary drivers which do not do anything special in * module init/exit. This eliminates a lot of boilerplate. Each module may only * use this macro once, and calling it replaces module_init() and module_exit() + * + * .. code-block:: c + * + * module_auxiliary_driver(my_drv); */ #define module_auxiliary_driver(__auxiliary_driver) \ module_driver(__auxiliary_driver, auxiliary_driver_register, auxiliary_driver_unregister) diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h index 993c5628a726..ae12696ec492 100644 --- a/include/linux/backing-dev-defs.h +++ b/include/linux/backing-dev-defs.h @@ -28,11 +28,6 @@ enum wb_state { WB_start_all, /* nr_pages == 0 (all) work pending */ }; -enum wb_congested_state { - WB_async_congested, /* The async (write) queue is getting full */ - WB_sync_congested, /* The sync queue is getting full */ -}; - enum wb_stat_item { WB_RECLAIMABLE, WB_WRITEBACK, @@ -122,8 +117,6 @@ struct bdi_writeback { atomic_t writeback_inodes; /* number of inodes under writeback */ struct percpu_counter stat[NR_WB_STAT_ITEMS]; - unsigned long congested; /* WB_[a]sync_congested flags */ - unsigned long bw_time_stamp; /* last time write bw is updated */ unsigned long dirtied_stamp; unsigned long written_stamp; /* pages written at bw_time_stamp */ @@ -207,14 +200,6 @@ struct backing_dev_info { #endif }; -enum { - BLK_RW_ASYNC = 0, - BLK_RW_SYNC = 1, -}; - -void clear_bdi_congested(struct backing_dev_info *bdi, int sync); -void set_bdi_congested(struct backing_dev_info *bdi, int sync); - struct wb_lock_cookie { bool locked; unsigned long flags; diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 483979c1b9f4..439815cc1ab9 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -17,8 +17,6 @@ #include <linux/backing-dev-defs.h> #include <linux/slab.h> -struct blkcg; - static inline struct backing_dev_info *bdi_get(struct backing_dev_info *bdi) { kref_get(&bdi->refcnt); @@ -121,6 +119,8 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio); extern struct backing_dev_info noop_backing_dev_info; +int bdi_init(struct backing_dev_info *bdi); + /** * writeback_in_progress - determine whether there is writeback in progress * @wb: bdi_writeback of interest @@ -135,24 +135,11 @@ static inline bool writeback_in_progress(struct bdi_writeback *wb) struct backing_dev_info *inode_to_bdi(struct inode *inode); -static inline int wb_congested(struct bdi_writeback *wb, int cong_bits) -{ - return wb->congested & cong_bits; -} - -long congestion_wait(int sync, long timeout); - static inline bool mapping_can_writeback(struct address_space *mapping) { return inode_to_bdi(mapping->host)->capabilities & BDI_CAP_WRITEBACK; } -static inline int bdi_sched_wait(void *word) -{ - schedule(); - return 0; -} - #ifdef CONFIG_CGROUP_WRITEBACK struct bdi_writeback *wb_get_lookup(struct backing_dev_info *bdi, @@ -161,8 +148,7 @@ struct bdi_writeback *wb_get_create(struct backing_dev_info *bdi, struct cgroup_subsys_state *memcg_css, gfp_t gfp); void wb_memcg_offline(struct mem_cgroup *memcg); -void wb_blkcg_offline(struct blkcg *blkcg); -int inode_congested(struct inode *inode, int cong_bits); +void wb_blkcg_offline(struct cgroup_subsys_state *css); /** * inode_cgwb_enabled - test whether cgroup writeback is enabled on an inode @@ -244,18 +230,6 @@ wb_get_create_current(struct backing_dev_info *bdi, gfp_t gfp) } /** - * inode_to_wb_is_valid - test whether an inode has a wb associated - * @inode: inode of interest - * - * Returns %true if @inode has a wb associated. May be called without any - * locking. - */ -static inline bool inode_to_wb_is_valid(struct inode *inode) -{ - return inode->i_wb; -} - -/** * inode_to_wb - determine the wb of an inode * @inode: inode of interest * @@ -353,11 +327,6 @@ wb_get_create_current(struct backing_dev_info *bdi, gfp_t gfp) return &bdi->wb; } -static inline bool inode_to_wb_is_valid(struct inode *inode) -{ - return true; -} - static inline struct bdi_writeback *inode_to_wb(struct inode *inode) { return &inode_to_bdi(inode)->wb; @@ -386,54 +355,12 @@ static inline void wb_memcg_offline(struct mem_cgroup *memcg) { } -static inline void wb_blkcg_offline(struct blkcg *blkcg) -{ -} - -static inline int inode_congested(struct inode *inode, int cong_bits) +static inline void wb_blkcg_offline(struct cgroup_subsys_state *css) { - return wb_congested(&inode_to_bdi(inode)->wb, cong_bits); } #endif /* CONFIG_CGROUP_WRITEBACK */ -static inline int inode_read_congested(struct inode *inode) -{ - return inode_congested(inode, 1 << WB_sync_congested); -} - -static inline int inode_write_congested(struct inode *inode) -{ - return inode_congested(inode, 1 << WB_async_congested); -} - -static inline int inode_rw_congested(struct inode *inode) -{ - return inode_congested(inode, (1 << WB_sync_congested) | - (1 << WB_async_congested)); -} - -static inline int bdi_congested(struct backing_dev_info *bdi, int cong_bits) -{ - return wb_congested(&bdi->wb, cong_bits); -} - -static inline int bdi_read_congested(struct backing_dev_info *bdi) -{ - return bdi_congested(bdi, 1 << WB_sync_congested); -} - -static inline int bdi_write_congested(struct backing_dev_info *bdi) -{ - return bdi_congested(bdi, 1 << WB_async_congested); -} - -static inline int bdi_rw_congested(struct backing_dev_info *bdi) -{ - return bdi_congested(bdi, (1 << WB_sync_congested) | - (1 << WB_async_congested)); -} - const char *bdi_dev_name(struct backing_dev_info *bdi); #endif /* _LINUX_BACKING_DEV_H */ diff --git a/include/linux/balloon_compaction.h b/include/linux/balloon_compaction.h index 338aa27e4773..5ca2d5699620 100644 --- a/include/linux/balloon_compaction.h +++ b/include/linux/balloon_compaction.h @@ -57,7 +57,6 @@ struct balloon_dev_info { struct list_head pages; /* Pages enqueued & handled to Host */ int (*migratepage)(struct balloon_dev_info *, struct page *newpage, struct page *page, enum migrate_mode mode); - struct inode *inode; }; extern struct page *balloon_page_alloc(void); @@ -75,17 +74,10 @@ static inline void balloon_devinfo_init(struct balloon_dev_info *balloon) spin_lock_init(&balloon->pages_lock); INIT_LIST_HEAD(&balloon->pages); balloon->migratepage = NULL; - balloon->inode = NULL; } #ifdef CONFIG_BALLOON_COMPACTION -extern const struct address_space_operations balloon_aops; -extern bool balloon_page_isolate(struct page *page, - isolate_mode_t mode); -extern void balloon_page_putback(struct page *page); -extern int balloon_page_migrate(struct address_space *mapping, - struct page *newpage, - struct page *page, enum migrate_mode mode); +extern const struct movable_operations balloon_mops; /* * balloon_page_insert - insert a page into the balloon's page list and make @@ -100,7 +92,7 @@ static inline void balloon_page_insert(struct balloon_dev_info *balloon, struct page *page) { __SetPageOffline(page); - __SetPageMovable(page, balloon->inode->i_mapping); + __SetPageMovable(page, &balloon_mops); set_page_private(page, (unsigned long)balloon); list_add(&page->lru, &balloon->pages); } @@ -155,22 +147,6 @@ static inline void balloon_page_delete(struct page *page) list_del(&page->lru); } -static inline bool balloon_page_isolate(struct page *page) -{ - return false; -} - -static inline void balloon_page_putback(struct page *page) -{ - return; -} - -static inline int balloon_page_migrate(struct page *newpage, - struct page *page, enum migrate_mode mode) -{ - return 0; -} - static inline gfp_t balloon_mapping_gfp_mask(void) { return GFP_HIGHUSER; diff --git a/include/linux/base64.h b/include/linux/base64.h new file mode 100644 index 000000000000..660d4cb1ef31 --- /dev/null +++ b/include/linux/base64.h @@ -0,0 +1,16 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * base64 encoding, lifted from fs/crypto/fname.c. + */ + +#ifndef _LINUX_BASE64_H +#define _LINUX_BASE64_H + +#include <linux/types.h> + +#define BASE64_CHARS(nbytes) DIV_ROUND_UP((nbytes) * 4, 3) + +int base64_encode(const u8 *src, int len, char *dst); +int base64_decode(const char *src, int len, u8 *dst); + +#endif /* _LINUX_BASE64_H */ diff --git a/include/linux/bcma/bcma_driver_chipcommon.h b/include/linux/bcma/bcma_driver_chipcommon.h index d35b9206096d..2d94c30ed439 100644 --- a/include/linux/bcma/bcma_driver_chipcommon.h +++ b/include/linux/bcma/bcma_driver_chipcommon.h @@ -3,6 +3,7 @@ #define LINUX_BCMA_DRIVER_CC_H_ #include <linux/platform_device.h> +#include <linux/platform_data/brcmnand.h> #include <linux/gpio.h> /** ChipCommon core registers. **/ @@ -270,6 +271,7 @@ #define BCMA_CC_SROM_CONTROL_OP_WRDIS 0x40000000 #define BCMA_CC_SROM_CONTROL_OP_WREN 0x60000000 #define BCMA_CC_SROM_CONTROL_OTPSEL 0x00000010 +#define BCMA_CC_SROM_CONTROL_OTP_PRESENT 0x00000020 #define BCMA_CC_SROM_CONTROL_LOCK 0x00000008 #define BCMA_CC_SROM_CONTROL_SIZE_MASK 0x00000006 #define BCMA_CC_SROM_CONTROL_SIZE_1K 0x00000000 @@ -599,6 +601,10 @@ struct bcma_sflash { #ifdef CONFIG_BCMA_NFLASH struct bcma_nflash { + /* Must be the fist member for the brcmnand driver to + * de-reference that structure. + */ + struct brcmnand_platform_data brcmnand_info; bool present; bool boot; /* This is the flash the SoC boots from */ }; diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index 049cf9421d83..8d51f69f9f5e 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -8,6 +8,7 @@ #include <uapi/linux/binfmts.h> struct filename; +struct coredump_params; #define CORENAME_MAX_SIZE 128 @@ -42,9 +43,6 @@ struct linux_binprm { * original userspace. */ point_of_no_return:1; -#ifdef __alpha__ - unsigned int taso:1; -#endif struct file *executable; /* Executable to pass to the interpreter */ struct file *interpreter; struct file *file; @@ -77,18 +75,6 @@ struct linux_binprm { #define BINPRM_FLAGS_PRESERVE_ARGV0_BIT 3 #define BINPRM_FLAGS_PRESERVE_ARGV0 (1 << BINPRM_FLAGS_PRESERVE_ARGV0_BIT) -/* Function parameter for binfmt->coredump */ -struct coredump_params { - const kernel_siginfo_t *siginfo; - struct pt_regs *regs; - struct file *file; - unsigned long limit; - unsigned long mm_flags; - loff_t written; - loff_t pos; - loff_t to_skip; -}; - /* * This structure defines the functions that are used to load the binary formats that * linux accepts. @@ -98,8 +84,10 @@ struct linux_binfmt { struct module *module; int (*load_binary)(struct linux_binprm *); int (*load_shlib)(struct file *); +#ifdef CONFIG_COREDUMP int (*core_dump)(struct coredump_params *cprm); unsigned long min_coredump; /* minimal dump size */ +#endif } __randomize_layout; extern void __register_binfmt(struct linux_binfmt *fmt, int insert); diff --git a/include/linux/bio.h b/include/linux/bio.h index fe6bdfbbef66..2c5806997bbf 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -65,7 +65,6 @@ static inline bool bio_no_advance_iter(const struct bio *bio) { return bio_op(bio) == REQ_OP_DISCARD || bio_op(bio) == REQ_OP_SECURE_ERASE || - bio_op(bio) == REQ_OP_WRITE_SAME || bio_op(bio) == REQ_OP_WRITE_ZEROES; } @@ -124,7 +123,7 @@ void __bio_advance(struct bio *, unsigned bytes); /** * bio_advance - increment/complete a bio by some number of bytes * @bio: bio to advance - * @bytes: number of bytes to complete + * @nbytes: number of bytes to complete * * This updates bi_sector, bi_size and bi_idx; if the number of bytes to * complete doesn't align with a bvec boundary, then bv_len and bv_offset will @@ -166,7 +165,7 @@ static inline void bio_advance(struct bio *bio, unsigned int nbytes) */ #define bio_for_each_bvec_all(bvl, bio, i) \ for (i = 0, bvl = bio_first_bvec_all(bio); \ - i < (bio)->bi_vcnt; i++, bvl++) \ + i < (bio)->bi_vcnt; i++, bvl++) #define bio_iter_last(bvec, iter) ((iter).bi_size == (bvec).bv_len) @@ -186,8 +185,6 @@ static inline unsigned bio_segments(struct bio *bio) case REQ_OP_SECURE_ERASE: case REQ_OP_WRITE_ZEROES: return 0; - case REQ_OP_WRITE_SAME: - return 1; default: break; } @@ -260,6 +257,60 @@ static inline struct bio_vec *bio_last_bvec_all(struct bio *bio) return &bio->bi_io_vec[bio->bi_vcnt - 1]; } +/** + * struct folio_iter - State for iterating all folios in a bio. + * @folio: The current folio we're iterating. NULL after the last folio. + * @offset: The byte offset within the current folio. + * @length: The number of bytes in this iteration (will not cross folio + * boundary). + */ +struct folio_iter { + struct folio *folio; + size_t offset; + size_t length; + /* private: for use by the iterator */ + struct folio *_next; + size_t _seg_count; + int _i; +}; + +static inline void bio_first_folio(struct folio_iter *fi, struct bio *bio, + int i) +{ + struct bio_vec *bvec = bio_first_bvec_all(bio) + i; + + fi->folio = page_folio(bvec->bv_page); + fi->offset = bvec->bv_offset + + PAGE_SIZE * (bvec->bv_page - &fi->folio->page); + fi->_seg_count = bvec->bv_len; + fi->length = min(folio_size(fi->folio) - fi->offset, fi->_seg_count); + fi->_next = folio_next(fi->folio); + fi->_i = i; +} + +static inline void bio_next_folio(struct folio_iter *fi, struct bio *bio) +{ + fi->_seg_count -= fi->length; + if (fi->_seg_count) { + fi->folio = fi->_next; + fi->offset = 0; + fi->length = min(folio_size(fi->folio), fi->_seg_count); + fi->_next = folio_next(fi->folio); + } else if (fi->_i + 1 < bio->bi_vcnt) { + bio_first_folio(fi, bio, fi->_i + 1); + } else { + fi->folio = NULL; + } +} + +/** + * bio_for_each_folio_all - Iterate over each folio in a bio. + * @fi: struct folio_iter which is updated for each folio. + * @bio: struct bio to iterate over. + */ +#define bio_for_each_folio_all(fi, bio) \ + for (bio_first_folio(&fi, bio, 0); fi.folio; bio_next_folio(&fi, bio)) + enum bip_flags { BIP_BLOCK_INTEGRITY = 1 << 0, /* block layer owns integrity data */ BIP_MAPPED_INTEGRITY = 1 << 1, /* ref tag has been remapped */ @@ -332,7 +383,7 @@ extern struct bio *bio_split(struct bio *bio, int sectors, * @gfp: gfp mask * @bs: bio set to allocate from * - * Returns a bio representing the next @sectors of @bio - if the bio is smaller + * Return: a bio representing the next @sectors of @bio - if the bio is smaller * than @sectors, returns the original bio unchanged. */ static inline struct bio *bio_next_split(struct bio *bio, int sectors, @@ -352,23 +403,24 @@ enum { extern int bioset_init(struct bio_set *, unsigned int, unsigned int, int flags); extern void bioset_exit(struct bio_set *); extern int biovec_init_pool(mempool_t *pool, int pool_entries); -extern int bioset_init_from_src(struct bio_set *bs, struct bio_set *src); -struct bio *bio_alloc_bioset(gfp_t gfp, unsigned short nr_iovecs, - struct bio_set *bs); -struct bio *bio_alloc_kiocb(struct kiocb *kiocb, unsigned short nr_vecs, - struct bio_set *bs); -struct bio *bio_kmalloc(gfp_t gfp_mask, unsigned short nr_iovecs); +struct bio *bio_alloc_bioset(struct block_device *bdev, unsigned short nr_vecs, + blk_opf_t opf, gfp_t gfp_mask, + struct bio_set *bs); +struct bio *bio_kmalloc(unsigned short nr_vecs, gfp_t gfp_mask); extern void bio_put(struct bio *); -extern void __bio_clone_fast(struct bio *, struct bio *); -extern struct bio *bio_clone_fast(struct bio *, gfp_t, struct bio_set *); +struct bio *bio_alloc_clone(struct block_device *bdev, struct bio *bio_src, + gfp_t gfp, struct bio_set *bs); +int bio_init_clone(struct block_device *bdev, struct bio *bio, + struct bio *bio_src, gfp_t gfp); extern struct bio_set fs_bio_set; -static inline struct bio *bio_alloc(gfp_t gfp_mask, unsigned short nr_iovecs) +static inline struct bio *bio_alloc(struct block_device *bdev, + unsigned short nr_vecs, blk_opf_t opf, gfp_t gfp_mask) { - return bio_alloc_bioset(gfp_mask, nr_iovecs, &fs_bio_set); + return bio_alloc_bioset(bdev, nr_vecs, opf, gfp_mask, &fs_bio_set); } void submit_bio(struct bio *bio); @@ -403,13 +455,14 @@ static inline int bio_iov_vecs_to_alloc(struct iov_iter *iter, int max_segs) struct request_queue; extern int submit_bio_wait(struct bio *bio); -extern void bio_init(struct bio *bio, struct bio_vec *table, - unsigned short max_vecs); +void bio_init(struct bio *bio, struct block_device *bdev, struct bio_vec *table, + unsigned short max_vecs, blk_opf_t opf); extern void bio_uninit(struct bio *); -extern void bio_reset(struct bio *); +void bio_reset(struct bio *bio, struct block_device *bdev, blk_opf_t opf); void bio_chain(struct bio *, struct bio *); -extern int bio_add_page(struct bio *, struct page *, unsigned int,unsigned int); +int bio_add_page(struct bio *, struct page *, unsigned len, unsigned off); +bool bio_add_folio(struct bio *, struct folio *, size_t len, size_t off); extern int bio_add_pc_page(struct request_queue *, struct bio *, struct page *, unsigned int, unsigned int); int bio_add_zone_append_page(struct bio *bio, struct page *page, @@ -435,8 +488,6 @@ static inline void bio_release_pages(struct bio *bio, bool mark_dirty) __bio_release_pages(bio, mark_dirty); } -extern const char *bio_devname(struct bio *bio, char *buffer); - #define bio_dev(bio) \ disk_devt((bio)->bi_bdev->bd_disk) @@ -458,18 +509,11 @@ static inline void bio_set_dev(struct bio *bio, struct block_device *bdev) { bio_clear_flag(bio, BIO_REMAPPED); if (bio->bi_bdev != bdev) - bio_clear_flag(bio, BIO_THROTTLED); + bio_clear_flag(bio, BIO_BPS_THROTTLED); bio->bi_bdev = bdev; bio_associate_blkg(bio); } -static inline void bio_copy_dev(struct bio *dst, struct bio *src) -{ - bio_clear_flag(dst, BIO_REMAPPED); - dst->bi_bdev = src->bi_bdev; - bio_clone_blkg_association(dst, src); -} - /* * BIO list management for use by remapping drivers (e.g. DM or MD) and loop. * @@ -738,6 +782,13 @@ static inline void bio_set_polled(struct bio *bio, struct kiocb *kiocb) bio->bi_opf |= REQ_NOWAIT; } -struct bio *blk_next_bio(struct bio *bio, unsigned int nr_pages, gfp_t gfp); +static inline void bio_clear_polled(struct bio *bio) +{ + /* can't support alloc cache if we turn off polling */ + bio->bi_opf &= ~(REQ_POLLED | REQ_ALLOC_CACHE); +} + +struct bio *blk_next_bio(struct bio *bio, struct block_device *bdev, + unsigned int nr_pages, blk_opf_t opf, gfp_t gfp); #endif /* __LINUX_BIO_H */ diff --git a/include/linux/bitfield.h b/include/linux/bitfield.h index 4e035aca6f7e..c9be1657f03d 100644 --- a/include/linux/bitfield.h +++ b/include/linux/bitfield.h @@ -19,6 +19,9 @@ * * Example: * + * #include <linux/bitfield.h> + * #include <linux/bits.h> + * * #define REG_FIELD_A GENMASK(6, 0) * #define REG_FIELD_B BIT(7) * #define REG_FIELD_C GENMASK(15, 8) @@ -41,6 +44,22 @@ #define __bf_shf(x) (__builtin_ffsll(x) - 1) +#define __scalar_type_to_unsigned_cases(type) \ + unsigned type: (unsigned type)0, \ + signed type: (unsigned type)0 + +#define __unsigned_scalar_typeof(x) typeof( \ + _Generic((x), \ + char: (unsigned char)0, \ + __scalar_type_to_unsigned_cases(char), \ + __scalar_type_to_unsigned_cases(short), \ + __scalar_type_to_unsigned_cases(int), \ + __scalar_type_to_unsigned_cases(long), \ + __scalar_type_to_unsigned_cases(long long), \ + default: (x))) + +#define __bf_cast_unsigned(type, x) ((__unsigned_scalar_typeof(type))(x)) + #define __BF_FIELD_CHECK(_mask, _reg, _val, _pfx) \ ({ \ BUILD_BUG_ON_MSG(!__builtin_constant_p(_mask), \ @@ -49,7 +68,8 @@ BUILD_BUG_ON_MSG(__builtin_constant_p(_val) ? \ ~((_mask) >> __bf_shf(_mask)) & (_val) : 0, \ _pfx "value too large for the field"); \ - BUILD_BUG_ON_MSG((_mask) > (typeof(_reg))~0ull, \ + BUILD_BUG_ON_MSG(__bf_cast_unsigned(_mask, _mask) > \ + __bf_cast_unsigned(_reg, ~0ull), \ _pfx "type of reg too small for mask"); \ __BUILD_BUG_ON_NOT_POWER_OF_2((_mask) + \ (1ULL << __bf_shf(_mask))); \ diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index a241dcf50f39..7d6d73b78147 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -6,6 +6,7 @@ #include <linux/align.h> #include <linux/bitops.h> +#include <linux/find.h> #include <linux/limits.h> #include <linux/string.h> #include <linux/types.h> @@ -50,16 +51,11 @@ struct device; * bitmap_empty(src, nbits) Are all bits zero in *src? * bitmap_full(src, nbits) Are all bits set in *src? * bitmap_weight(src, nbits) Hamming Weight: number set bits + * bitmap_weight_and(src1, src2, nbits) Hamming Weight of and'ed bitmap * bitmap_set(dst, pos, nbits) Set specified bit area * bitmap_clear(dst, pos, nbits) Clear specified bit area * bitmap_find_next_zero_area(buf, len, pos, n, mask) Find bit free area * bitmap_find_next_zero_area_off(buf, len, pos, n, mask, mask_off) as above - * bitmap_next_clear_region(map, &start, &end, nbits) Find next clear region - * bitmap_next_set_region(map, &start, &end, nbits) Find next set region - * bitmap_for_each_clear_region(map, rs, re, start, end) - * Iterate over all clear regions - * bitmap_for_each_set_region(map, rs, re, start, end) - * Iterate over all set regions * bitmap_shift_right(dst, src, n, nbits) *dst = *src >> n * bitmap_shift_left(dst, src, n, nbits) *dst = *src << n * bitmap_cut(dst, src, first, n, nbits) Cut n bits from first, copy rest @@ -76,7 +72,9 @@ struct device; * bitmap_release_region(bitmap, pos, order) Free specified bit region * bitmap_allocate_region(bitmap, pos, order) Allocate specified bit region * bitmap_from_arr32(dst, buf, nbits) Copy nbits from u32[] buf to dst + * bitmap_from_arr64(dst, buf, nbits) Copy nbits from u64[] buf to dst * bitmap_to_arr32(buf, src, nbits) Copy nbits from buf to u32[] dst + * bitmap_to_arr64(buf, src, nbits) Copy nbits from buf to u64[] dst * bitmap_get_value8(map, start) Get 8bit value from map at start * bitmap_set_value8(map, value, start) Set 8bit value to map at start * @@ -137,8 +135,8 @@ unsigned long *devm_bitmap_zalloc(struct device *dev, * lib/bitmap.c provides these functions: */ -int __bitmap_equal(const unsigned long *bitmap1, - const unsigned long *bitmap2, unsigned int nbits); +bool __bitmap_equal(const unsigned long *bitmap1, + const unsigned long *bitmap2, unsigned int nbits); bool __pure __bitmap_or_equal(const unsigned long *src1, const unsigned long *src2, const unsigned long *src3, @@ -151,22 +149,24 @@ void __bitmap_shift_left(unsigned long *dst, const unsigned long *src, unsigned int shift, unsigned int nbits); void bitmap_cut(unsigned long *dst, const unsigned long *src, unsigned int first, unsigned int cut, unsigned int nbits); -int __bitmap_and(unsigned long *dst, const unsigned long *bitmap1, +bool __bitmap_and(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int nbits); void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int nbits); void __bitmap_xor(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int nbits); -int __bitmap_andnot(unsigned long *dst, const unsigned long *bitmap1, +bool __bitmap_andnot(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int nbits); void __bitmap_replace(unsigned long *dst, const unsigned long *old, const unsigned long *new, const unsigned long *mask, unsigned int nbits); -int __bitmap_intersects(const unsigned long *bitmap1, - const unsigned long *bitmap2, unsigned int nbits); -int __bitmap_subset(const unsigned long *bitmap1, - const unsigned long *bitmap2, unsigned int nbits); -int __bitmap_weight(const unsigned long *bitmap, unsigned int nbits); +bool __bitmap_intersects(const unsigned long *bitmap1, + const unsigned long *bitmap2, unsigned int nbits); +bool __bitmap_subset(const unsigned long *bitmap1, + const unsigned long *bitmap2, unsigned int nbits); +unsigned int __bitmap_weight(const unsigned long *bitmap, unsigned int nbits); +unsigned int __bitmap_weight_and(const unsigned long *bitmap1, + const unsigned long *bitmap2, unsigned int nbits); void __bitmap_set(unsigned long *map, unsigned int start, int len); void __bitmap_clear(unsigned long *map, unsigned int start, int len); @@ -225,7 +225,6 @@ void bitmap_copy_le(unsigned long *dst, const unsigned long *src, unsigned int n #else #define bitmap_copy_le bitmap_copy #endif -unsigned int bitmap_ord_to_pos(const unsigned long *bitmap, unsigned int ord, unsigned int nbits); int bitmap_print_to_pagebuf(bool list, char *buf, const unsigned long *maskp, int nmaskbits); @@ -241,20 +240,32 @@ extern int bitmap_print_list_to_buf(char *buf, const unsigned long *maskp, static inline void bitmap_zero(unsigned long *dst, unsigned int nbits) { unsigned int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long); - memset(dst, 0, len); + + if (small_const_nbits(nbits)) + *dst = 0; + else + memset(dst, 0, len); } static inline void bitmap_fill(unsigned long *dst, unsigned int nbits) { unsigned int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long); - memset(dst, 0xff, len); + + if (small_const_nbits(nbits)) + *dst = ~0UL; + else + memset(dst, 0xff, len); } static inline void bitmap_copy(unsigned long *dst, const unsigned long *src, unsigned int nbits) { unsigned int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long); - memcpy(dst, src, len); + + if (small_const_nbits(nbits)) + *dst = *src; + else + memcpy(dst, src, len); } /* @@ -269,8 +280,12 @@ static inline void bitmap_copy_clear_tail(unsigned long *dst, } /* - * On 32-bit systems bitmaps are represented as u32 arrays internally, and - * therefore conversion is not needed when copying data from/to arrays of u32. + * On 32-bit systems bitmaps are represented as u32 arrays internally. On LE64 + * machines the order of hi and lo parts of numbers match the bitmap structure. + * In both cases conversion is not needed when copying data from/to arrays of + * u32. But in LE64 case, typecast in bitmap_copy_clear_tail() may lead + * to out-of-bound access. To avoid that, both LE and BE variants of 64-bit + * architectures are not using bitmap_copy_clear_tail(). */ #if BITS_PER_LONG == 64 void bitmap_from_arr32(unsigned long *bitmap, const u32 *buf, @@ -286,7 +301,23 @@ void bitmap_to_arr32(u32 *buf, const unsigned long *bitmap, (const unsigned long *) (bitmap), (nbits)) #endif -static inline int bitmap_and(unsigned long *dst, const unsigned long *src1, +/* + * On 64-bit systems bitmaps are represented as u64 arrays internally. On LE32 + * machines the order of hi and lo parts of numbers match the bitmap structure. + * In both cases conversion is not needed when copying data from/to arrays of + * u64. + */ +#if (BITS_PER_LONG == 32) && defined(__BIG_ENDIAN) +void bitmap_from_arr64(unsigned long *bitmap, const u64 *buf, unsigned int nbits); +void bitmap_to_arr64(u64 *buf, const unsigned long *bitmap, unsigned int nbits); +#else +#define bitmap_from_arr64(bitmap, buf, nbits) \ + bitmap_copy_clear_tail((unsigned long *)(bitmap), (const unsigned long *)(buf), (nbits)) +#define bitmap_to_arr64(buf, bitmap, nbits) \ + bitmap_copy_clear_tail((unsigned long *)(buf), (const unsigned long *)(bitmap), (nbits)) +#endif + +static inline bool bitmap_and(unsigned long *dst, const unsigned long *src1, const unsigned long *src2, unsigned int nbits) { if (small_const_nbits(nbits)) @@ -312,7 +343,7 @@ static inline void bitmap_xor(unsigned long *dst, const unsigned long *src1, __bitmap_xor(dst, src1, src2, nbits); } -static inline int bitmap_andnot(unsigned long *dst, const unsigned long *src1, +static inline bool bitmap_andnot(unsigned long *dst, const unsigned long *src1, const unsigned long *src2, unsigned int nbits) { if (small_const_nbits(nbits)) @@ -336,8 +367,8 @@ static inline void bitmap_complement(unsigned long *dst, const unsigned long *sr #endif #define BITMAP_MEM_MASK (BITMAP_MEM_ALIGNMENT - 1) -static inline int bitmap_equal(const unsigned long *src1, - const unsigned long *src2, unsigned int nbits) +static inline bool bitmap_equal(const unsigned long *src1, + const unsigned long *src2, unsigned int nbits) { if (small_const_nbits(nbits)) return !((*src1 ^ *src2) & BITMAP_LAST_WORD_MASK(nbits)); @@ -367,8 +398,9 @@ static inline bool bitmap_or_equal(const unsigned long *src1, return !(((*src1 | *src2) ^ *src3) & BITMAP_LAST_WORD_MASK(nbits)); } -static inline int bitmap_intersects(const unsigned long *src1, - const unsigned long *src2, unsigned int nbits) +static inline bool bitmap_intersects(const unsigned long *src1, + const unsigned long *src2, + unsigned int nbits) { if (small_const_nbits(nbits)) return ((*src1 & *src2) & BITMAP_LAST_WORD_MASK(nbits)) != 0; @@ -376,8 +408,8 @@ static inline int bitmap_intersects(const unsigned long *src1, return __bitmap_intersects(src1, src2, nbits); } -static inline int bitmap_subset(const unsigned long *src1, - const unsigned long *src2, unsigned int nbits) +static inline bool bitmap_subset(const unsigned long *src1, + const unsigned long *src2, unsigned int nbits) { if (small_const_nbits(nbits)) return ! ((*src1 & ~(*src2)) & BITMAP_LAST_WORD_MASK(nbits)); @@ -401,18 +433,30 @@ static inline bool bitmap_full(const unsigned long *src, unsigned int nbits) return find_first_zero_bit(src, nbits) == nbits; } -static __always_inline int bitmap_weight(const unsigned long *src, unsigned int nbits) +static __always_inline +unsigned int bitmap_weight(const unsigned long *src, unsigned int nbits) { if (small_const_nbits(nbits)) return hweight_long(*src & BITMAP_LAST_WORD_MASK(nbits)); return __bitmap_weight(src, nbits); } +static __always_inline +unsigned long bitmap_weight_and(const unsigned long *src1, + const unsigned long *src2, unsigned int nbits) +{ + if (small_const_nbits(nbits)) + return hweight_long(*src1 & *src2 & BITMAP_LAST_WORD_MASK(nbits)); + return __bitmap_weight_and(src1, src2, nbits); +} + static __always_inline void bitmap_set(unsigned long *map, unsigned int start, unsigned int nbits) { if (__builtin_constant_p(nbits) && nbits == 1) __set_bit(start, map); + else if (small_const_nbits(start + nbits)) + *map |= GENMASK(start + nbits - 1, start); else if (__builtin_constant_p(start & BITMAP_MEM_MASK) && IS_ALIGNED(start, BITMAP_MEM_ALIGNMENT) && __builtin_constant_p(nbits & BITMAP_MEM_MASK) && @@ -427,6 +471,8 @@ static __always_inline void bitmap_clear(unsigned long *map, unsigned int start, { if (__builtin_constant_p(nbits) && nbits == 1) __clear_bit(start, map); + else if (small_const_nbits(start + nbits)) + *map &= ~GENMASK(start + nbits - 1, start); else if (__builtin_constant_p(start & BITMAP_MEM_MASK) && IS_ALIGNED(start, BITMAP_MEM_ALIGNMENT) && __builtin_constant_p(nbits & BITMAP_MEM_MASK) && @@ -466,14 +512,6 @@ static inline void bitmap_replace(unsigned long *dst, __bitmap_replace(dst, old, new, mask, nbits); } -static inline void bitmap_next_clear_region(unsigned long *bitmap, - unsigned int *rs, unsigned int *re, - unsigned int end) -{ - *rs = find_next_zero_bit(bitmap, end, *rs); - *re = find_next_bit(bitmap, end, *rs + 1); -} - static inline void bitmap_next_set_region(unsigned long *bitmap, unsigned int *rs, unsigned int *re, unsigned int end) @@ -482,25 +520,6 @@ static inline void bitmap_next_set_region(unsigned long *bitmap, *re = find_next_zero_bit(bitmap, end, *rs + 1); } -/* - * Bitmap region iterators. Iterates over the bitmap between [@start, @end). - * @rs and @re should be integer variables and will be set to start and end - * index of the current clear or set region. - */ -#define bitmap_for_each_clear_region(bitmap, rs, re, start, end) \ - for ((rs) = (start), \ - bitmap_next_clear_region((bitmap), &(rs), &(re), (end)); \ - (rs) < (re); \ - (rs) = (re) + 1, \ - bitmap_next_clear_region((bitmap), &(rs), &(re), (end))) - -#define bitmap_for_each_set_region(bitmap, rs, re, start, end) \ - for ((rs) = (start), \ - bitmap_next_set_region((bitmap), &(rs), &(re), (end)); \ - (rs) < (re); \ - (rs) = (re) + 1, \ - bitmap_next_set_region((bitmap), &(rs), &(re), (end))) - /** * BITMAP_FROM_U64() - Represent u64 value in the format suitable for bitmap. * @n: u64 value @@ -546,10 +565,7 @@ static inline void bitmap_next_set_region(unsigned long *bitmap, */ static inline void bitmap_from_u64(unsigned long *dst, u64 mask) { - dst[0] = mask & ULONG_MAX; - - if (sizeof(mask) > sizeof(unsigned long)) - dst[1] = mask >> 32; + bitmap_from_arr64(dst, &mask, 64); } /** diff --git a/include/linux/bitops.h b/include/linux/bitops.h index 5e62e2383b7f..2ba557e067fe 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -27,44 +27,61 @@ extern unsigned int __sw_hweight32(unsigned int w); extern unsigned long __sw_hweight64(__u64 w); /* + * Defined here because those may be needed by architecture-specific static + * inlines. + */ + +#include <asm-generic/bitops/generic-non-atomic.h> + +/* + * Many architecture-specific non-atomic bitops contain inline asm code and due + * to that the compiler can't optimize them to compile-time expressions or + * constants. In contrary, generic_*() helpers are defined in pure C and + * compilers optimize them just well. + * Therefore, to make `unsigned long foo = 0; __set_bit(BAR, &foo)` effectively + * equal to `unsigned long foo = BIT(BAR)`, pick the generic C alternative when + * the arguments can be resolved at compile time. That expression itself is a + * constant and doesn't bring any functional changes to the rest of cases. + * The casts to `uintptr_t` are needed to mitigate `-Waddress` warnings when + * passing a bitmap from .bss or .data (-> `!!addr` is always true). + */ +#define bitop(op, nr, addr) \ + ((__builtin_constant_p(nr) && \ + __builtin_constant_p((uintptr_t)(addr) != (uintptr_t)NULL) && \ + (uintptr_t)(addr) != (uintptr_t)NULL && \ + __builtin_constant_p(*(const unsigned long *)(addr))) ? \ + const##op(nr, addr) : op(nr, addr)) + +#define __set_bit(nr, addr) bitop(___set_bit, nr, addr) +#define __clear_bit(nr, addr) bitop(___clear_bit, nr, addr) +#define __change_bit(nr, addr) bitop(___change_bit, nr, addr) +#define __test_and_set_bit(nr, addr) bitop(___test_and_set_bit, nr, addr) +#define __test_and_clear_bit(nr, addr) bitop(___test_and_clear_bit, nr, addr) +#define __test_and_change_bit(nr, addr) bitop(___test_and_change_bit, nr, addr) +#define test_bit(nr, addr) bitop(_test_bit, nr, addr) +#define test_bit_acquire(nr, addr) bitop(_test_bit_acquire, nr, addr) + +/* * Include this here because some architectures need generic_ffs/fls in * scope */ #include <asm/bitops.h> -#define for_each_set_bit(bit, addr, size) \ - for ((bit) = find_first_bit((addr), (size)); \ - (bit) < (size); \ - (bit) = find_next_bit((addr), (size), (bit) + 1)) - -/* same as for_each_set_bit() but use bit as value to start with */ -#define for_each_set_bit_from(bit, addr, size) \ - for ((bit) = find_next_bit((addr), (size), (bit)); \ - (bit) < (size); \ - (bit) = find_next_bit((addr), (size), (bit) + 1)) - -#define for_each_clear_bit(bit, addr, size) \ - for ((bit) = find_first_zero_bit((addr), (size)); \ - (bit) < (size); \ - (bit) = find_next_zero_bit((addr), (size), (bit) + 1)) +/* Check that the bitops prototypes are sane */ +#define __check_bitop_pr(name) \ + static_assert(__same_type(arch_##name, generic_##name) && \ + __same_type(const_##name, generic_##name) && \ + __same_type(_##name, generic_##name)) -/* same as for_each_clear_bit() but use bit as value to start with */ -#define for_each_clear_bit_from(bit, addr, size) \ - for ((bit) = find_next_zero_bit((addr), (size), (bit)); \ - (bit) < (size); \ - (bit) = find_next_zero_bit((addr), (size), (bit) + 1)) +__check_bitop_pr(__set_bit); +__check_bitop_pr(__clear_bit); +__check_bitop_pr(__change_bit); +__check_bitop_pr(__test_and_set_bit); +__check_bitop_pr(__test_and_clear_bit); +__check_bitop_pr(__test_and_change_bit); +__check_bitop_pr(test_bit); -/** - * for_each_set_clump8 - iterate over bitmap for each 8-bit clump with set bits - * @start: bit offset to start search and to store the current iteration offset - * @clump: location to store copy of current 8-bit clump - * @bits: bitmap address to base the search on - * @size: bitmap size in number of bits - */ -#define for_each_set_clump8(start, clump, bits, size) \ - for ((start) = find_first_clump8(&(clump), (bits), (size)); \ - (start) < (size); \ - (start) = find_next_clump8(&(clump), (bits), (size), (start) + 8)) +#undef __check_bitop_pr static inline int get_bitmask_order(unsigned int count) { @@ -231,6 +248,25 @@ static inline unsigned long __ffs64(u64 word) } /** + * fns - find N'th set bit in a word + * @word: The word to search + * @n: Bit to find + */ +static inline unsigned long fns(unsigned long word, unsigned int n) +{ + unsigned int bit; + + while (word) { + bit = __ffs(word); + if (n-- == 0) + return bit; + __clear_bit(bit, &word); + } + + return BITS_PER_LONG; +} + +/** * assign_bit - Assign value to a bit in memory * @nr: the bit to set * @addr: the address to start counting from @@ -311,10 +347,10 @@ static __always_inline void __assign_bit(long nr, volatile unsigned long *addr, const typeof(*(ptr)) mask__ = (mask), bits__ = (bits); \ typeof(*(ptr)) old__, new__; \ \ + old__ = READ_ONCE(*(ptr)); \ do { \ - old__ = READ_ONCE(*(ptr)); \ new__ = (old__ & ~mask__) | bits__; \ - } while (cmpxchg(ptr, old__, new__) != old__); \ + } while (!try_cmpxchg(ptr, &old__, new__)); \ \ old__; \ }) @@ -326,11 +362,12 @@ static __always_inline void __assign_bit(long nr, volatile unsigned long *addr, const typeof(*(ptr)) clear__ = (clear), test__ = (test);\ typeof(*(ptr)) old__, new__; \ \ + old__ = READ_ONCE(*(ptr)); \ do { \ - old__ = READ_ONCE(*(ptr)); \ + if (old__ & test__) \ + break; \ new__ = old__ & ~clear__; \ - } while (!(old__ & test__) && \ - cmpxchg(ptr, old__, new__) != old__); \ + } while (!try_cmpxchg(ptr, &old__, new__)); \ \ !(old__ & test__); \ }) diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index b4de2010fba5..dd5841a42c33 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -14,713 +14,38 @@ * Nauman Rafique <nauman@google.com> */ -#include <linux/cgroup.h> -#include <linux/percpu.h> -#include <linux/percpu_counter.h> -#include <linux/u64_stats_sync.h> -#include <linux/seq_file.h> -#include <linux/radix-tree.h> -#include <linux/blkdev.h> -#include <linux/atomic.h> -#include <linux/kthread.h> -#include <linux/fs.h> +#include <linux/types.h> -/* percpu_counter batch for blkg_[rw]stats, per-cpu drift doesn't matter */ -#define BLKG_STAT_CPU_BATCH (INT_MAX / 2) +struct bio; +struct cgroup_subsys_state; +struct gendisk; -/* Max limits for throttle policy */ -#define THROTL_IOPS_MAX UINT_MAX #define FC_APPID_LEN 129 - #ifdef CONFIG_BLK_CGROUP - -enum blkg_iostat_type { - BLKG_IOSTAT_READ, - BLKG_IOSTAT_WRITE, - BLKG_IOSTAT_DISCARD, - - BLKG_IOSTAT_NR, -}; - -struct blkcg_gq; - -struct blkcg { - struct cgroup_subsys_state css; - spinlock_t lock; - refcount_t online_pin; - - struct radix_tree_root blkg_tree; - struct blkcg_gq __rcu *blkg_hint; - struct hlist_head blkg_list; - - struct blkcg_policy_data *cpd[BLKCG_MAX_POLS]; - - struct list_head all_blkcgs_node; -#ifdef CONFIG_BLK_CGROUP_FC_APPID - char fc_app_id[FC_APPID_LEN]; -#endif -#ifdef CONFIG_CGROUP_WRITEBACK - struct list_head cgwb_list; -#endif -}; - -struct blkg_iostat { - u64 bytes[BLKG_IOSTAT_NR]; - u64 ios[BLKG_IOSTAT_NR]; -}; - -struct blkg_iostat_set { - struct u64_stats_sync sync; - struct blkg_iostat cur; - struct blkg_iostat last; -}; - -/* - * A blkcg_gq (blkg) is association between a block cgroup (blkcg) and a - * request_queue (q). This is used by blkcg policies which need to track - * information per blkcg - q pair. - * - * There can be multiple active blkcg policies and each blkg:policy pair is - * represented by a blkg_policy_data which is allocated and freed by each - * policy's pd_alloc/free_fn() methods. A policy can allocate private data - * area by allocating larger data structure which embeds blkg_policy_data - * at the beginning. - */ -struct blkg_policy_data { - /* the blkg and policy id this per-policy data belongs to */ - struct blkcg_gq *blkg; - int plid; -}; - -/* - * Policies that need to keep per-blkcg data which is independent from any - * request_queue associated to it should implement cpd_alloc/free_fn() - * methods. A policy can allocate private data area by allocating larger - * data structure which embeds blkcg_policy_data at the beginning. - * cpd_init() is invoked to let each policy handle per-blkcg data. - */ -struct blkcg_policy_data { - /* the blkcg and policy id this per-policy data belongs to */ - struct blkcg *blkcg; - int plid; -}; - -/* association between a blk cgroup and a request queue */ -struct blkcg_gq { - /* Pointer to the associated request_queue */ - struct request_queue *q; - struct list_head q_node; - struct hlist_node blkcg_node; - struct blkcg *blkcg; - - /* all non-root blkcg_gq's are guaranteed to have access to parent */ - struct blkcg_gq *parent; - - /* reference count */ - struct percpu_ref refcnt; - - /* is this blkg online? protected by both blkcg and q locks */ - bool online; - - struct blkg_iostat_set __percpu *iostat_cpu; - struct blkg_iostat_set iostat; - - struct blkg_policy_data *pd[BLKCG_MAX_POLS]; - - spinlock_t async_bio_lock; - struct bio_list async_bios; - struct work_struct async_bio_work; - - atomic_t use_delay; - atomic64_t delay_nsec; - atomic64_t delay_start; - u64 last_delay; - int last_use; - - struct rcu_head rcu_head; -}; - -typedef struct blkcg_policy_data *(blkcg_pol_alloc_cpd_fn)(gfp_t gfp); -typedef void (blkcg_pol_init_cpd_fn)(struct blkcg_policy_data *cpd); -typedef void (blkcg_pol_free_cpd_fn)(struct blkcg_policy_data *cpd); -typedef void (blkcg_pol_bind_cpd_fn)(struct blkcg_policy_data *cpd); -typedef struct blkg_policy_data *(blkcg_pol_alloc_pd_fn)(gfp_t gfp, - struct request_queue *q, struct blkcg *blkcg); -typedef void (blkcg_pol_init_pd_fn)(struct blkg_policy_data *pd); -typedef void (blkcg_pol_online_pd_fn)(struct blkg_policy_data *pd); -typedef void (blkcg_pol_offline_pd_fn)(struct blkg_policy_data *pd); -typedef void (blkcg_pol_free_pd_fn)(struct blkg_policy_data *pd); -typedef void (blkcg_pol_reset_pd_stats_fn)(struct blkg_policy_data *pd); -typedef bool (blkcg_pol_stat_pd_fn)(struct blkg_policy_data *pd, - struct seq_file *s); - -struct blkcg_policy { - int plid; - /* cgroup files for the policy */ - struct cftype *dfl_cftypes; - struct cftype *legacy_cftypes; - - /* operations */ - blkcg_pol_alloc_cpd_fn *cpd_alloc_fn; - blkcg_pol_init_cpd_fn *cpd_init_fn; - blkcg_pol_free_cpd_fn *cpd_free_fn; - blkcg_pol_bind_cpd_fn *cpd_bind_fn; - - blkcg_pol_alloc_pd_fn *pd_alloc_fn; - blkcg_pol_init_pd_fn *pd_init_fn; - blkcg_pol_online_pd_fn *pd_online_fn; - blkcg_pol_offline_pd_fn *pd_offline_fn; - blkcg_pol_free_pd_fn *pd_free_fn; - blkcg_pol_reset_pd_stats_fn *pd_reset_stats_fn; - blkcg_pol_stat_pd_fn *pd_stat_fn; -}; - -extern struct blkcg blkcg_root; extern struct cgroup_subsys_state * const blkcg_root_css; -extern bool blkcg_debug_stats; - -struct blkcg_gq *blkg_lookup_slowpath(struct blkcg *blkcg, - struct request_queue *q, bool update_hint); -int blkcg_init_queue(struct request_queue *q); -void blkcg_exit_queue(struct request_queue *q); - -/* Blkio controller policy registration */ -int blkcg_policy_register(struct blkcg_policy *pol); -void blkcg_policy_unregister(struct blkcg_policy *pol); -int blkcg_activate_policy(struct request_queue *q, - const struct blkcg_policy *pol); -void blkcg_deactivate_policy(struct request_queue *q, - const struct blkcg_policy *pol); - -const char *blkg_dev_name(struct blkcg_gq *blkg); -void blkcg_print_blkgs(struct seq_file *sf, struct blkcg *blkcg, - u64 (*prfill)(struct seq_file *, - struct blkg_policy_data *, int), - const struct blkcg_policy *pol, int data, - bool show_total); -u64 __blkg_prfill_u64(struct seq_file *sf, struct blkg_policy_data *pd, u64 v); - -struct blkg_conf_ctx { - struct block_device *bdev; - struct blkcg_gq *blkg; - char *body; -}; - -struct block_device *blkcg_conf_open_bdev(char **inputp); -int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol, - char *input, struct blkg_conf_ctx *ctx); -void blkg_conf_finish(struct blkg_conf_ctx *ctx); - -/** - * blkcg_css - find the current css - * - * Find the css associated with either the kthread or the current task. - * This may return a dying css, so it is up to the caller to use tryget logic - * to confirm it is alive and well. - */ -static inline struct cgroup_subsys_state *blkcg_css(void) -{ - struct cgroup_subsys_state *css; - - css = kthread_blkcg(); - if (css) - return css; - return task_css(current, io_cgrp_id); -} - -static inline struct blkcg *css_to_blkcg(struct cgroup_subsys_state *css) -{ - return css ? container_of(css, struct blkcg, css) : NULL; -} - -/** - * __bio_blkcg - internal, inconsistent version to get blkcg - * - * DO NOT USE. - * This function is inconsistent and consequently is dangerous to use. The - * first part of the function returns a blkcg where a reference is owned by the - * bio. This means it does not need to be rcu protected as it cannot go away - * with the bio owning a reference to it. However, the latter potentially gets - * it from task_css(). This can race against task migration and the cgroup - * dying. It is also semantically different as it must be called rcu protected - * and is susceptible to failure when trying to get a reference to it. - * Therefore, it is not ok to assume that *_get() will always succeed on the - * blkcg returned here. - */ -static inline struct blkcg *__bio_blkcg(struct bio *bio) -{ - if (bio && bio->bi_blkg) - return bio->bi_blkg->blkcg; - return css_to_blkcg(blkcg_css()); -} -/** - * bio_blkcg - grab the blkcg associated with a bio - * @bio: target bio - * - * This returns the blkcg associated with a bio, %NULL if not associated. - * Callers are expected to either handle %NULL or know association has been - * done prior to calling this. - */ -static inline struct blkcg *bio_blkcg(struct bio *bio) -{ - if (bio && bio->bi_blkg) - return bio->bi_blkg->blkcg; - return NULL; -} - -static inline bool blk_cgroup_congested(void) -{ - struct cgroup_subsys_state *css; - bool ret = false; - - rcu_read_lock(); - css = kthread_blkcg(); - if (!css) - css = task_css(current, io_cgrp_id); - while (css) { - if (atomic_read(&css->cgroup->congestion_count)) { - ret = true; - break; - } - css = css->parent; - } - rcu_read_unlock(); - return ret; -} - -/** - * bio_issue_as_root_blkg - see if this bio needs to be issued as root blkg - * @return: true if this bio needs to be submitted with the root blkg context. - * - * In order to avoid priority inversions we sometimes need to issue a bio as if - * it were attached to the root blkg, and then backcharge to the actual owning - * blkg. The idea is we do bio_blkcg() to look up the actual context for the - * bio and attach the appropriate blkg to the bio. Then we call this helper and - * if it is true run with the root blkg for that queue and then do any - * backcharging to the originating cgroup once the io is complete. - */ -static inline bool bio_issue_as_root_blkg(struct bio *bio) -{ - return (bio->bi_opf & (REQ_META | REQ_SWAP)) != 0; -} - -/** - * blkcg_parent - get the parent of a blkcg - * @blkcg: blkcg of interest - * - * Return the parent blkcg of @blkcg. Can be called anytime. - */ -static inline struct blkcg *blkcg_parent(struct blkcg *blkcg) -{ - return css_to_blkcg(blkcg->css.parent); -} - -/** - * __blkg_lookup - internal version of blkg_lookup() - * @blkcg: blkcg of interest - * @q: request_queue of interest - * @update_hint: whether to update lookup hint with the result or not - * - * This is internal version and shouldn't be used by policy - * implementations. Looks up blkgs for the @blkcg - @q pair regardless of - * @q's bypass state. If @update_hint is %true, the caller should be - * holding @q->queue_lock and lookup hint is updated on success. - */ -static inline struct blkcg_gq *__blkg_lookup(struct blkcg *blkcg, - struct request_queue *q, - bool update_hint) -{ - struct blkcg_gq *blkg; - - if (blkcg == &blkcg_root) - return q->root_blkg; - - blkg = rcu_dereference(blkcg->blkg_hint); - if (blkg && blkg->q == q) - return blkg; - - return blkg_lookup_slowpath(blkcg, q, update_hint); -} - -/** - * blkg_lookup - lookup blkg for the specified blkcg - q pair - * @blkcg: blkcg of interest - * @q: request_queue of interest - * - * Lookup blkg for the @blkcg - @q pair. This function should be called - * under RCU read lock. - */ -static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, - struct request_queue *q) -{ - WARN_ON_ONCE(!rcu_read_lock_held()); - return __blkg_lookup(blkcg, q, false); -} - -/** - * blk_queue_root_blkg - return blkg for the (blkcg_root, @q) pair - * @q: request_queue of interest - * - * Lookup blkg for @q at the root level. See also blkg_lookup(). - */ -static inline struct blkcg_gq *blk_queue_root_blkg(struct request_queue *q) -{ - return q->root_blkg; -} - -/** - * blkg_to_pdata - get policy private data - * @blkg: blkg of interest - * @pol: policy of interest - * - * Return pointer to private data associated with the @blkg-@pol pair. - */ -static inline struct blkg_policy_data *blkg_to_pd(struct blkcg_gq *blkg, - struct blkcg_policy *pol) -{ - return blkg ? blkg->pd[pol->plid] : NULL; -} - -static inline struct blkcg_policy_data *blkcg_to_cpd(struct blkcg *blkcg, - struct blkcg_policy *pol) -{ - return blkcg ? blkcg->cpd[pol->plid] : NULL; -} - -/** - * pdata_to_blkg - get blkg associated with policy private data - * @pd: policy private data of interest - * - * @pd is policy private data. Determine the blkg it's associated with. - */ -static inline struct blkcg_gq *pd_to_blkg(struct blkg_policy_data *pd) -{ - return pd ? pd->blkg : NULL; -} - -static inline struct blkcg *cpd_to_blkcg(struct blkcg_policy_data *cpd) -{ - return cpd ? cpd->blkcg : NULL; -} - -extern void blkcg_destroy_blkgs(struct blkcg *blkcg); - -/** - * blkcg_pin_online - pin online state - * @blkcg: blkcg of interest - * - * While pinned, a blkcg is kept online. This is primarily used to - * impedance-match blkg and cgwb lifetimes so that blkg doesn't go offline - * while an associated cgwb is still active. - */ -static inline void blkcg_pin_online(struct blkcg *blkcg) -{ - refcount_inc(&blkcg->online_pin); -} - -/** - * blkcg_unpin_online - unpin online state - * @blkcg: blkcg of interest - * - * This is primarily used to impedance-match blkg and cgwb lifetimes so - * that blkg doesn't go offline while an associated cgwb is still active. - * When this count goes to zero, all active cgwbs have finished so the - * blkcg can continue destruction by calling blkcg_destroy_blkgs(). - */ -static inline void blkcg_unpin_online(struct blkcg *blkcg) -{ - do { - if (!refcount_dec_and_test(&blkcg->online_pin)) - break; - blkcg_destroy_blkgs(blkcg); - blkcg = blkcg_parent(blkcg); - } while (blkcg); -} - -/** - * blkg_path - format cgroup path of blkg - * @blkg: blkg of interest - * @buf: target buffer - * @buflen: target buffer length - * - * Format the path of the cgroup of @blkg into @buf. - */ -static inline int blkg_path(struct blkcg_gq *blkg, char *buf, int buflen) -{ - return cgroup_path(blkg->blkcg->css.cgroup, buf, buflen); -} - -/** - * blkg_get - get a blkg reference - * @blkg: blkg to get - * - * The caller should be holding an existing reference. - */ -static inline void blkg_get(struct blkcg_gq *blkg) -{ - percpu_ref_get(&blkg->refcnt); -} - -/** - * blkg_tryget - try and get a blkg reference - * @blkg: blkg to get - * - * This is for use when doing an RCU lookup of the blkg. We may be in the midst - * of freeing this blkg, so we can only use it if the refcnt is not zero. - */ -static inline bool blkg_tryget(struct blkcg_gq *blkg) -{ - return blkg && percpu_ref_tryget(&blkg->refcnt); -} - -/** - * blkg_put - put a blkg reference - * @blkg: blkg to put - */ -static inline void blkg_put(struct blkcg_gq *blkg) -{ - percpu_ref_put(&blkg->refcnt); -} - -/** - * blkg_for_each_descendant_pre - pre-order walk of a blkg's descendants - * @d_blkg: loop cursor pointing to the current descendant - * @pos_css: used for iteration - * @p_blkg: target blkg to walk descendants of - * - * Walk @c_blkg through the descendants of @p_blkg. Must be used with RCU - * read locked. If called under either blkcg or queue lock, the iteration - * is guaranteed to include all and only online blkgs. The caller may - * update @pos_css by calling css_rightmost_descendant() to skip subtree. - * @p_blkg is included in the iteration and the first node to be visited. - */ -#define blkg_for_each_descendant_pre(d_blkg, pos_css, p_blkg) \ - css_for_each_descendant_pre((pos_css), &(p_blkg)->blkcg->css) \ - if (((d_blkg) = __blkg_lookup(css_to_blkcg(pos_css), \ - (p_blkg)->q, false))) - -/** - * blkg_for_each_descendant_post - post-order walk of a blkg's descendants - * @d_blkg: loop cursor pointing to the current descendant - * @pos_css: used for iteration - * @p_blkg: target blkg to walk descendants of - * - * Similar to blkg_for_each_descendant_pre() but performs post-order - * traversal instead. Synchronization rules are the same. @p_blkg is - * included in the iteration and the last node to be visited. - */ -#define blkg_for_each_descendant_post(d_blkg, pos_css, p_blkg) \ - css_for_each_descendant_post((pos_css), &(p_blkg)->blkcg->css) \ - if (((d_blkg) = __blkg_lookup(css_to_blkcg(pos_css), \ - (p_blkg)->q, false))) - -bool __blkcg_punt_bio_submit(struct bio *bio); - -static inline bool blkcg_punt_bio_submit(struct bio *bio) -{ - if (bio->bi_opf & REQ_CGROUP_PUNT) - return __blkcg_punt_bio_submit(bio); - else - return false; -} - -static inline void blkcg_bio_issue_init(struct bio *bio) -{ - bio_issue_init(&bio->bi_issue, bio_sectors(bio)); -} - -static inline void blkcg_use_delay(struct blkcg_gq *blkg) -{ - if (WARN_ON_ONCE(atomic_read(&blkg->use_delay) < 0)) - return; - if (atomic_add_return(1, &blkg->use_delay) == 1) - atomic_inc(&blkg->blkcg->css.cgroup->congestion_count); -} - -static inline int blkcg_unuse_delay(struct blkcg_gq *blkg) -{ - int old = atomic_read(&blkg->use_delay); - - if (WARN_ON_ONCE(old < 0)) - return 0; - if (old == 0) - return 0; - - /* - * We do this song and dance because we can race with somebody else - * adding or removing delay. If we just did an atomic_dec we'd end up - * negative and we'd already be in trouble. We need to subtract 1 and - * then check to see if we were the last delay so we can drop the - * congestion count on the cgroup. - */ - while (old) { - int cur = atomic_cmpxchg(&blkg->use_delay, old, old - 1); - if (cur == old) - break; - old = cur; - } - - if (old == 0) - return 0; - if (old == 1) - atomic_dec(&blkg->blkcg->css.cgroup->congestion_count); - return 1; -} - -/** - * blkcg_set_delay - Enable allocator delay mechanism with the specified delay amount - * @blkg: target blkg - * @delay: delay duration in nsecs - * - * When enabled with this function, the delay is not decayed and must be - * explicitly cleared with blkcg_clear_delay(). Must not be mixed with - * blkcg_[un]use_delay() and blkcg_add_delay() usages. - */ -static inline void blkcg_set_delay(struct blkcg_gq *blkg, u64 delay) -{ - int old = atomic_read(&blkg->use_delay); - - /* We only want 1 person setting the congestion count for this blkg. */ - if (!old && atomic_cmpxchg(&blkg->use_delay, old, -1) == old) - atomic_inc(&blkg->blkcg->css.cgroup->congestion_count); - - atomic64_set(&blkg->delay_nsec, delay); -} - -/** - * blkcg_clear_delay - Disable allocator delay mechanism - * @blkg: target blkg - * - * Disable use_delay mechanism. See blkcg_set_delay(). - */ -static inline void blkcg_clear_delay(struct blkcg_gq *blkg) -{ - int old = atomic_read(&blkg->use_delay); - - /* We only want 1 person clearing the congestion count for this blkg. */ - if (old && atomic_cmpxchg(&blkg->use_delay, old, 0) == old) - atomic_dec(&blkg->blkcg->css.cgroup->congestion_count); -} - -void blk_cgroup_bio_start(struct bio *bio); -void blkcg_add_delay(struct blkcg_gq *blkg, u64 now, u64 delta); -void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay); +void blkcg_schedule_throttle(struct gendisk *disk, bool use_memdelay); void blkcg_maybe_throttle_current(void); -#else /* CONFIG_BLK_CGROUP */ - -struct blkcg { -}; - -struct blkg_policy_data { -}; - -struct blkcg_policy_data { -}; +bool blk_cgroup_congested(void); +void blkcg_pin_online(struct cgroup_subsys_state *blkcg_css); +void blkcg_unpin_online(struct cgroup_subsys_state *blkcg_css); +struct list_head *blkcg_get_cgwb_list(struct cgroup_subsys_state *css); +struct cgroup_subsys_state *bio_blkcg_css(struct bio *bio); -struct blkcg_gq { -}; - -struct blkcg_policy { -}; +#else /* CONFIG_BLK_CGROUP */ #define blkcg_root_css ((struct cgroup_subsys_state *)ERR_PTR(-EINVAL)) static inline void blkcg_maybe_throttle_current(void) { } static inline bool blk_cgroup_congested(void) { return false; } - -#ifdef CONFIG_BLOCK - -static inline void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay) { } - -static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, void *key) { return NULL; } -static inline struct blkcg_gq *blk_queue_root_blkg(struct request_queue *q) -{ return NULL; } -static inline int blkcg_init_queue(struct request_queue *q) { return 0; } -static inline void blkcg_exit_queue(struct request_queue *q) { } -static inline int blkcg_policy_register(struct blkcg_policy *pol) { return 0; } -static inline void blkcg_policy_unregister(struct blkcg_policy *pol) { } -static inline int blkcg_activate_policy(struct request_queue *q, - const struct blkcg_policy *pol) { return 0; } -static inline void blkcg_deactivate_policy(struct request_queue *q, - const struct blkcg_policy *pol) { } - -static inline struct blkcg *__bio_blkcg(struct bio *bio) { return NULL; } -static inline struct blkcg *bio_blkcg(struct bio *bio) { return NULL; } - -static inline struct blkg_policy_data *blkg_to_pd(struct blkcg_gq *blkg, - struct blkcg_policy *pol) { return NULL; } -static inline struct blkcg_gq *pd_to_blkg(struct blkg_policy_data *pd) { return NULL; } -static inline char *blkg_path(struct blkcg_gq *blkg) { return NULL; } -static inline void blkg_get(struct blkcg_gq *blkg) { } -static inline void blkg_put(struct blkcg_gq *blkg) { } - -static inline bool blkcg_punt_bio_submit(struct bio *bio) { return false; } -static inline void blkcg_bio_issue_init(struct bio *bio) { } -static inline void blk_cgroup_bio_start(struct bio *bio) { } - -#define blk_queue_for_each_rl(rl, q) \ - for ((rl) = &(q)->root_rl; (rl); (rl) = NULL) - -#endif /* CONFIG_BLOCK */ -#endif /* CONFIG_BLK_CGROUP */ - -#ifdef CONFIG_BLK_CGROUP_FC_APPID -/* - * Sets the fc_app_id field associted to blkcg - * @app_id: application identifier - * @cgrp_id: cgroup id - * @app_id_len: size of application identifier - */ -static inline int blkcg_set_fc_appid(char *app_id, u64 cgrp_id, size_t app_id_len) -{ - struct cgroup *cgrp; - struct cgroup_subsys_state *css; - struct blkcg *blkcg; - int ret = 0; - - if (app_id_len > FC_APPID_LEN) - return -EINVAL; - - cgrp = cgroup_get_from_id(cgrp_id); - if (!cgrp) - return -ENOENT; - css = cgroup_get_e_css(cgrp, &io_cgrp_subsys); - if (!css) { - ret = -ENOENT; - goto out_cgrp_put; - } - blkcg = css_to_blkcg(css); - /* - * There is a slight race condition on setting the appid. - * Worst case an I/O may not find the right id. - * This is no different from the I/O we let pass while obtaining - * the vmid from the fabric. - * Adding the overhead of a lock is not necessary. - */ - strlcpy(blkcg->fc_app_id, app_id, app_id_len); - css_put(css); -out_cgrp_put: - cgroup_put(cgrp); - return ret; -} - -/** - * blkcg_get_fc_appid - get the fc app identifier associated with a bio - * @bio: target bio - * - * On success return the fc_app_id, on failure return NULL - */ -static inline char *blkcg_get_fc_appid(struct bio *bio) +static inline struct cgroup_subsys_state *bio_blkcg_css(struct bio *bio) { - if (bio && bio->bi_blkg && - (bio->bi_blkg->blkcg->fc_app_id[0] != '\0')) - return bio->bi_blkg->blkcg->fc_app_id; return NULL; } -#else -static inline int blkcg_set_fc_appid(char *buf, u64 id, size_t len) { return -EINVAL; } -static inline char *blkcg_get_fc_appid(struct bio *bio) { return NULL; } -#endif /*CONFIG_BLK_CGROUP_FC_APPID*/ +#endif /* CONFIG_BLK_CGROUP */ + +int blkcg_set_fc_appid(char *app_id, u64 cgrp_id, size_t app_id_len); +char *blkcg_get_fc_appid(struct bio *bio); + #endif /* _BLK_CGROUP_H */ diff --git a/include/linux/blk-integrity.h b/include/linux/blk-integrity.h index 8a038ea0717e..378b2459efe2 100644 --- a/include/linux/blk-integrity.h +++ b/include/linux/blk-integrity.h @@ -19,6 +19,7 @@ struct blk_integrity_iter { sector_t seed; unsigned int data_size; unsigned short interval; + unsigned char tuple_size; const char *disk_name; }; diff --git a/include/linux/blk-mq-pci.h b/include/linux/blk-mq-pci.h index 0b1f45c62623..ca544e1d3508 100644 --- a/include/linux/blk-mq-pci.h +++ b/include/linux/blk-mq-pci.h @@ -5,7 +5,7 @@ struct blk_mq_queue_map; struct pci_dev; -int blk_mq_pci_map_queues(struct blk_mq_queue_map *qmap, struct pci_dev *pdev, - int offset); +void blk_mq_pci_map_queues(struct blk_mq_queue_map *qmap, struct pci_dev *pdev, + int offset); #endif /* _LINUX_BLK_MQ_PCI_H */ diff --git a/include/linux/blk-mq-rdma.h b/include/linux/blk-mq-rdma.h index 5cc5f0f36218..53b58c610e76 100644 --- a/include/linux/blk-mq-rdma.h +++ b/include/linux/blk-mq-rdma.h @@ -5,7 +5,7 @@ struct blk_mq_tag_set; struct ib_device; -int blk_mq_rdma_map_queues(struct blk_mq_queue_map *map, +void blk_mq_rdma_map_queues(struct blk_mq_queue_map *map, struct ib_device *dev, int first_vec); #endif /* _LINUX_BLK_MQ_RDMA_H */ diff --git a/include/linux/blk-mq-virtio.h b/include/linux/blk-mq-virtio.h index 687ae287e1dc..13226e9b22dd 100644 --- a/include/linux/blk-mq-virtio.h +++ b/include/linux/blk-mq-virtio.h @@ -5,7 +5,7 @@ struct blk_mq_queue_map; struct virtio_device; -int blk_mq_virtio_map_queues(struct blk_mq_queue_map *qmap, +void blk_mq_virtio_map_queues(struct blk_mq_queue_map *qmap, struct virtio_device *vdev, int first_vec); #endif /* _LINUX_BLK_MQ_VIRTIO_H */ diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 2949d9ac7484..d6119c5d1069 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -4,7 +4,6 @@ #include <linux/blkdev.h> #include <linux/sbitmap.h> -#include <linux/srcu.h> #include <linux/lockdep.h> #include <linux/scatterlist.h> #include <linux/prefetch.h> @@ -15,7 +14,12 @@ struct blk_flush_queue; #define BLKDEV_MIN_RQ 4 #define BLKDEV_DEFAULT_RQ 128 -typedef void (rq_end_io_fn)(struct request *, blk_status_t); +enum rq_end_io_ret { + RQ_END_IO_NONE, + RQ_END_IO_FREE, +}; + +typedef enum rq_end_io_ret (rq_end_io_fn)(struct request *, blk_status_t); /* * request flags */ @@ -58,6 +62,7 @@ typedef __u32 __bitwise req_flags_t; #define RQF_TIMED_OUT ((__force req_flags_t)(1 << 21)) /* queue has elevator attached */ #define RQF_ELV ((__force req_flags_t)(1 << 22)) +#define RQF_RESV ((__force req_flags_t)(1 << 23)) /* flags that prevent us from merging requests: */ #define RQF_NOMERGE_FLAGS \ @@ -80,7 +85,7 @@ struct request { struct blk_mq_ctx *mq_ctx; struct blk_mq_hw_ctx *mq_hctx; - unsigned int cmd_flags; /* op and common flags */ + blk_opf_t cmd_flags; /* op and common flags */ req_flags_t rq_flags; int tag; @@ -100,7 +105,6 @@ struct request { struct request *rq_next; }; - struct gendisk *rq_disk; struct block_device *part; #ifdef CONFIG_BLK_RQ_ALLOC_TIME /* Time that the first bio started allocating this request. */ @@ -140,7 +144,7 @@ struct request { unsigned short ioprio; enum mq_rq_state state; - refcount_t ref; + atomic_t ref; unsigned long deadline; @@ -165,7 +169,6 @@ struct request { struct rb_node rb_node; /* sort/lookup */ struct bio_vec special_vec; void *completion_data; - int error_count; /* for legacy drivers, don't use */ }; @@ -200,8 +203,10 @@ struct request { void *end_io_data; }; -#define req_op(req) \ - ((req)->cmd_flags & REQ_OP_MASK) +static inline enum req_op req_op(const struct request *req) +{ + return req->cmd_flags & REQ_OP_MASK; +} static inline bool blk_rq_is_passthrough(struct request *rq) { @@ -218,9 +223,66 @@ static inline unsigned short req_get_ioprio(struct request *req) #define rq_dma_dir(rq) \ (op_is_write(req_op(rq)) ? DMA_TO_DEVICE : DMA_FROM_DEVICE) +#define rq_list_add(listptr, rq) do { \ + (rq)->rq_next = *(listptr); \ + *(listptr) = rq; \ +} while (0) + +#define rq_list_pop(listptr) \ +({ \ + struct request *__req = NULL; \ + if ((listptr) && *(listptr)) { \ + __req = *(listptr); \ + *(listptr) = __req->rq_next; \ + } \ + __req; \ +}) + +#define rq_list_peek(listptr) \ +({ \ + struct request *__req = NULL; \ + if ((listptr) && *(listptr)) \ + __req = *(listptr); \ + __req; \ +}) + +#define rq_list_for_each(listptr, pos) \ + for (pos = rq_list_peek((listptr)); pos; pos = rq_list_next(pos)) + +#define rq_list_for_each_safe(listptr, pos, nxt) \ + for (pos = rq_list_peek((listptr)), nxt = rq_list_next(pos); \ + pos; pos = nxt, nxt = pos ? rq_list_next(pos) : NULL) + +#define rq_list_next(rq) (rq)->rq_next +#define rq_list_empty(list) ((list) == (struct request *) NULL) + +/** + * rq_list_move() - move a struct request from one list to another + * @src: The source list @rq is currently in + * @dst: The destination list that @rq will be appended to + * @rq: The request to move + * @prev: The request preceding @rq in @src (NULL if @rq is the head) + */ +static inline void rq_list_move(struct request **src, struct request **dst, + struct request *rq, struct request *prev) +{ + if (prev) + prev->rq_next = rq->rq_next; + else + *src = rq->rq_next; + rq_list_add(dst, rq); +} + +/** + * enum blk_eh_timer_return - How the timeout handler should proceed + * @BLK_EH_DONE: The block driver completed the command or will complete it at + * a later time. + * @BLK_EH_RESET_TIMER: Reset the request timer and continue waiting for the + * request to complete. + */ enum blk_eh_timer_return { - BLK_EH_DONE, /* drivers has completed the command */ - BLK_EH_RESET_TIMER, /* reset timer and try again */ + BLK_EH_DONE, + BLK_EH_RESET_TIMER, }; #define BLK_TAG_ALLOC_FIFO 0 /* allocate starting from 0 */ @@ -376,13 +438,6 @@ struct blk_mq_hw_ctx { * q->unused_hctx_list. */ struct list_head hctx_list; - - /** - * @srcu: Sleepable RCU. Use as lock when type of the hardware queue is - * blocking (BLK_MQ_F_BLOCKING). Must be the last member - see also - * blk_mq_hw_ctx_size(). - */ - struct srcu_struct srcu[]; }; /** @@ -479,9 +534,7 @@ struct blk_mq_queue_data { bool last; }; -typedef bool (busy_iter_fn)(struct blk_mq_hw_ctx *, struct request *, void *, - bool); -typedef bool (busy_tag_iter_fn)(struct request *, void *, bool); +typedef bool (busy_tag_iter_fn)(struct request *, void *); /** * struct blk_mq_ops - Callback functions that implements block driver @@ -504,6 +557,14 @@ struct blk_mq_ops { void (*commit_rqs)(struct blk_mq_hw_ctx *); /** + * @queue_rqs: Queue a list of new requests. Driver is guaranteed + * that each request belongs to the same queue. If the driver doesn't + * empty the @rqlist completely, then the rest will be queued + * individually by the block layer upon return. + */ + void (*queue_rqs)(struct request **rqlist); + + /** * @get_budget: Reserve budget before queue request, once .queue_rq is * run, it is driver's responsibility to release the * reserved budget. Also we have to handle failure case @@ -528,7 +589,7 @@ struct blk_mq_ops { /** * @timeout: Called on request timeout. */ - enum blk_eh_timer_return (*timeout)(struct request *, bool); + enum blk_eh_timer_return (*timeout)(struct request *); /** * @poll: Called to poll for completion of a specific tag. @@ -581,7 +642,7 @@ struct blk_mq_ops { * @map_queues: This allows drivers specify their own queue mapping by * overriding the setup-time function that builds the mq_map. */ - int (*map_queues)(struct blk_mq_tag_set *set); + void (*map_queues)(struct blk_mq_tag_set *set); #ifdef CONFIG_BLK_DEBUG_FS /** @@ -640,10 +701,12 @@ struct gendisk *__blk_mq_alloc_disk(struct blk_mq_tag_set *set, void *queuedata, \ __blk_mq_alloc_disk(set, queuedata, &__key); \ }) +struct gendisk *blk_mq_alloc_disk_for_queue(struct request_queue *q, + struct lock_class_key *lkclass); struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *); int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set, struct request_queue *q); -void blk_mq_unregister_dev(struct device *, struct request_queue *); +void blk_mq_destroy_queue(struct request_queue *); int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set); int blk_mq_alloc_sq_tag_set(struct blk_mq_tag_set *set, @@ -664,10 +727,10 @@ enum { BLK_MQ_REQ_PM = (__force blk_mq_req_flags_t)(1 << 2), }; -struct request *blk_mq_alloc_request(struct request_queue *q, unsigned int op, +struct request *blk_mq_alloc_request(struct request_queue *q, blk_opf_t opf, blk_mq_req_flags_t flags); struct request *blk_mq_alloc_request_hctx(struct request_queue *q, - unsigned int op, blk_mq_req_flags_t flags, + blk_opf_t opf, blk_mq_req_flags_t flags, unsigned int hctx_idx); /* @@ -752,6 +815,17 @@ static inline void blk_mq_set_request_complete(struct request *rq) WRITE_ONCE(rq->state, MQ_RQ_COMPLETE); } +/* + * Complete the request directly instead of deferring it to softirq or + * completing it another CPU. Useful in preemptible instead of an interrupt. + */ +static inline void blk_mq_complete_request_direct(struct request *rq, + void (*complete)(struct request *rq)) +{ + WRITE_ONCE(rq->state, MQ_RQ_COMPLETE); + complete(rq); +} + void blk_mq_start_request(struct request *rq); void blk_mq_end_request(struct request *rq, blk_status_t error); void __blk_mq_end_request(struct request *rq, blk_status_t error); @@ -766,6 +840,11 @@ static inline bool blk_mq_need_time_stamp(struct request *rq) return (rq->rq_flags & (RQF_IO_STAT | RQF_STATS | RQF_ELV)); } +static inline bool blk_mq_is_reserved_rq(struct request *rq) +{ + return rq->rq_flags & RQF_RESV; +} + /* * Batched completions only work when there is no I/O error and no special * ->end_io handler. @@ -774,8 +853,10 @@ static inline bool blk_mq_add_to_batch(struct request *req, struct io_comp_batch *iob, int ioerror, void (*complete)(struct io_comp_batch *)) { - if (!iob || (req->rq_flags & RQF_ELV) || req->end_io || ioerror) + if (!iob || (req->rq_flags & RQF_ELV) || ioerror || + (req->end_io && !blk_rq_is_passthrough(req))) return false; + if (!iob->complete) iob->complete = complete; else if (iob->complete != complete) @@ -790,7 +871,6 @@ void blk_mq_kick_requeue_list(struct request_queue *q); void blk_mq_delay_kick_requeue_list(struct request_queue *q, unsigned long msecs); void blk_mq_complete_request(struct request *rq); bool blk_mq_complete_request_remote(struct request *rq); -bool blk_mq_queue_stopped(struct request_queue *q); void blk_mq_stop_hw_queue(struct blk_mq_hw_ctx *hctx); void blk_mq_start_hw_queue(struct blk_mq_hw_ctx *hctx); void blk_mq_stop_hw_queues(struct request_queue *q); @@ -814,7 +894,7 @@ void blk_mq_freeze_queue_wait(struct request_queue *q); int blk_mq_freeze_queue_wait_timeout(struct request_queue *q, unsigned long timeout); -int blk_mq_map_queues(struct blk_mq_queue_map *qmap); +void blk_mq_map_queues(struct blk_mq_queue_map *qmap); void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues); void blk_mq_quiesce_queue_nowait(struct request_queue *q); @@ -859,8 +939,7 @@ static inline void *blk_mq_rq_to_pdu(struct request *rq) } #define queue_for_each_hw_ctx(q, hctx, i) \ - for ((i) = 0; (i) < (q)->nr_hw_queues && \ - ({ hctx = (q)->queue_hw_ctx[i]; 1; }); (i)++) + xa_for_each(&(q)->hctx_table, (i), (hctx)) #define hctx_for_each_ctx(hctx, ctx, i) \ for ((i) = 0; (i) < (hctx)->nr_ctx && \ @@ -879,9 +958,6 @@ static inline void blk_rq_bio_prep(struct request *rq, struct bio *bio, rq->__data_len = bio->bi_iter.bi_size; rq->bio = rq->biotail = bio; rq->ioprio = bio_prio(bio); - - if (bio->bi_bdev) - rq->rq_disk = bio->bi_bdev->bd_disk; } void blk_mq_hctx_set_fq_lock_class(struct blk_mq_hw_ctx *hctx, @@ -897,30 +973,30 @@ int blk_rq_prep_clone(struct request *rq, struct request *rq_src, struct bio_set *bs, gfp_t gfp_mask, int (*bio_ctr)(struct bio *, struct bio *, void *), void *data); void blk_rq_unprep_clone(struct request *rq); -blk_status_t blk_insert_cloned_request(struct request_queue *q, - struct request *rq); +blk_status_t blk_insert_cloned_request(struct request *rq); struct rq_map_data { struct page **pages; - int page_order; - int nr_entries; unsigned long offset; - int null_mapped; - int from_user; + unsigned short page_order; + unsigned short nr_entries; + bool null_mapped; + bool from_user; }; int blk_rq_map_user(struct request_queue *, struct request *, struct rq_map_data *, void __user *, unsigned long, gfp_t); +int blk_rq_map_user_io(struct request *, struct rq_map_data *, + void __user *, unsigned long, gfp_t, bool, int, bool, int); int blk_rq_map_user_iov(struct request_queue *, struct request *, struct rq_map_data *, const struct iov_iter *, gfp_t); int blk_rq_unmap_user(struct bio *); int blk_rq_map_kern(struct request_queue *, struct request *, void *, unsigned int, gfp_t); int blk_rq_append_bio(struct request *rq, struct bio *bio); -void blk_execute_rq_nowait(struct gendisk *, struct request *, int, - rq_end_io_fn *); -blk_status_t blk_execute_rq(struct gendisk *bd_disk, struct request *rq, - int at_head); +void blk_execute_rq_nowait(struct request *rq, bool at_head); +blk_status_t blk_execute_rq(struct request *rq, bool at_head); +bool blk_rq_is_poll(struct request *rq); struct req_iterator { struct bvec_iter iter; @@ -947,7 +1023,6 @@ struct req_iterator { * blk_rq_pos() : the current sector * blk_rq_bytes() : bytes left in the entire request * blk_rq_cur_bytes() : bytes left in the current segment - * blk_rq_err_bytes() : bytes left till the next error boundary * blk_rq_sectors() : sectors left in the entire request * blk_rq_cur_sectors() : sectors left in the current segment * blk_rq_stats_sectors() : sectors of the entire request used for stats @@ -971,8 +1046,6 @@ static inline int blk_rq_cur_bytes(const struct request *rq) return bio_iovec(rq->bio).bv_len; } -unsigned int blk_rq_err_bytes(const struct request *rq); - static inline unsigned int blk_rq_sectors(const struct request *rq) { return blk_rq_bytes(rq) >> SECTOR_SHIFT; @@ -1074,12 +1147,12 @@ void blk_dump_rq_flags(struct request *, char *); #ifdef CONFIG_BLK_DEV_ZONED static inline unsigned int blk_rq_zone_no(struct request *rq) { - return blk_queue_zone_no(rq->q, blk_rq_pos(rq)); + return disk_zone_no(rq->q->disk, blk_rq_pos(rq)); } static inline unsigned int blk_rq_zone_is_seq(struct request *rq) { - return blk_queue_zone_is_seq(rq->q, blk_rq_pos(rq)); + return disk_zone_is_seq(rq->q->disk, blk_rq_pos(rq)); } bool blk_req_needs_zone_write_lock(struct request *rq); @@ -1101,8 +1174,8 @@ static inline void blk_req_zone_write_unlock(struct request *rq) static inline bool blk_req_zone_is_write_locked(struct request *rq) { - return rq->q->seq_zones_wlock && - test_bit(blk_rq_zone_no(rq), rq->q->seq_zones_wlock); + return rq->q->disk->seq_zones_wlock && + test_bit(blk_rq_zone_no(rq), rq->q->disk->seq_zones_wlock); } static inline bool blk_req_can_dispatch_to_zone(struct request *rq) @@ -1135,14 +1208,4 @@ static inline bool blk_req_can_dispatch_to_zone(struct request *rq) } #endif /* CONFIG_BLK_DEV_ZONED */ -#ifndef ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE -# error "You should define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE for your platform" -#endif -#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE -void rq_flush_dcache_pages(struct request *rq); -#else -static inline void rq_flush_dcache_pages(struct request *rq) -{ -} -#endif /* ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE */ #endif /* BLK_MQ_H */ diff --git a/include/linux/blk-pm.h b/include/linux/blk-pm.h index b80c65aba249..2580e05a8ab6 100644 --- a/include/linux/blk-pm.h +++ b/include/linux/blk-pm.h @@ -14,7 +14,7 @@ extern void blk_pm_runtime_init(struct request_queue *q, struct device *dev); extern int blk_pre_runtime_suspend(struct request_queue *q); extern void blk_post_runtime_suspend(struct request_queue *q, int err); extern void blk_pre_runtime_resume(struct request_queue *q); -extern void blk_post_runtime_resume(struct request_queue *q, int err); +extern void blk_post_runtime_resume(struct request_queue *q); extern void blk_set_runtime_active(struct request_queue *q); #else static inline void blk_pm_runtime_init(struct request_queue *q, diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index fe065c394fff..e0b098089ef2 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -44,7 +44,7 @@ struct block_device { unsigned long bd_stamp; bool bd_read_only; /* read-only policy */ dev_t bd_dev; - int bd_openers; + atomic_t bd_openers; struct inode * bd_inode; /* will die */ struct super_block * bd_super; void * bd_claiming; @@ -85,8 +85,10 @@ struct block_device { */ #if defined(CONFIG_ALPHA) && !defined(__alpha_bwx__) typedef u32 __bitwise blk_status_t; +typedef u32 blk_short_t; #else typedef u8 __bitwise blk_status_t; +typedef u16 blk_short_t; #endif #define BLK_STS_OK 0 #define BLK_STS_NOTSUPP ((__force blk_status_t)1) @@ -103,6 +105,10 @@ typedef u8 __bitwise blk_status_t; /* hack for device mapper, don't use elsewhere: */ #define BLK_STS_DM_REQUEUE ((__force blk_status_t)11) +/* + * BLK_STS_AGAIN should only be returned if RQF_NOWAIT is set + * and the bio would block (cf bio_wouldblock_error()) + */ #define BLK_STS_AGAIN ((__force blk_status_t)12) /* @@ -153,6 +159,13 @@ typedef u8 __bitwise blk_status_t; */ #define BLK_STS_ZONE_ACTIVE_RESOURCE ((__force blk_status_t)16) +/* + * BLK_STS_OFFLINE is returned from the driver when the target device is offline + * or is being taken offline. This could help differentiate the case where a + * device is intentionally being shut down from a real I/O error. + */ +#define BLK_STS_OFFLINE ((__force blk_status_t)17) + /** * blk_path_error - returns true if error may be path related * @error: status the request was completed with @@ -227,6 +240,8 @@ static inline void bio_issue_init(struct bio_issue *issue, ((u64)size << BIO_ISSUE_SIZE_SHIFT)); } +typedef __u32 __bitwise blk_opf_t; + typedef unsigned int blk_qc_t; #define BLK_QC_T_NONE -1U @@ -237,13 +252,11 @@ typedef unsigned int blk_qc_t; struct bio { struct bio *bi_next; /* request queue link */ struct block_device *bi_bdev; - unsigned int bi_opf; /* bottom bits req flags, - * top bits REQ_OP. Use - * accessors. + blk_opf_t bi_opf; /* bottom bits REQ_OP, top bits + * req_flags. */ unsigned short bi_flags; /* BIO_* below */ unsigned short bi_ioprio; - unsigned short bi_write_hint; blk_status_t bi_status; atomic_t __bi_remaining; @@ -308,26 +321,29 @@ enum { BIO_NO_PAGE_REF, /* don't put release vec pages */ BIO_CLONED, /* doesn't own data */ BIO_BOUNCED, /* bio is a bounce bio */ - BIO_WORKINGSET, /* contains userspace workingset pages */ BIO_QUIET, /* Make BIO Quiet */ BIO_CHAIN, /* chained bio, ->bi_remaining in effect */ BIO_REFFED, /* bio has elevated ->bi_cnt */ - BIO_THROTTLED, /* This bio has already been subjected to + BIO_BPS_THROTTLED, /* This bio has already been subjected to * throttling rules. Don't do it again. */ BIO_TRACE_COMPLETION, /* bio_endio() should trace the final completion * of this bio. */ BIO_CGROUP_ACCT, /* has been accounted to a cgroup */ - BIO_TRACKED, /* set if bio goes through the rq_qos path */ + BIO_QOS_THROTTLED, /* bio went through rq_qos throttle path */ + BIO_QOS_MERGED, /* but went through rq_qos merge path */ BIO_REMAPPED, BIO_ZONE_WRITE_LOCKED, /* Owns a zoned device zone write lock */ - BIO_PERCPU_CACHE, /* can participate in per-cpu alloc cache */ BIO_FLAG_LAST }; typedef __u32 __bitwise blk_mq_req_flags_t; -/* - * Operations and flags common to the bio and request structures. +#define REQ_OP_BITS 8 +#define REQ_OP_MASK (__force blk_opf_t)((1 << REQ_OP_BITS) - 1) +#define REQ_FLAG_BITS 24 + +/** + * enum req_op - Operations common to the bio and request structures. * We use 8 bits for encoding the operation, and the remaining 24 for flags. * * The least significant bit of the operation number indicates the data @@ -339,43 +355,37 @@ typedef __u32 __bitwise blk_mq_req_flags_t; * If a operation does not transfer data the least significant bit has no * meaning. */ -#define REQ_OP_BITS 8 -#define REQ_OP_MASK ((1 << REQ_OP_BITS) - 1) -#define REQ_FLAG_BITS 24 - -enum req_opf { +enum req_op { /* read sectors from the device */ - REQ_OP_READ = 0, + REQ_OP_READ = (__force blk_opf_t)0, /* write sectors to the device */ - REQ_OP_WRITE = 1, + REQ_OP_WRITE = (__force blk_opf_t)1, /* flush the volatile write cache */ - REQ_OP_FLUSH = 2, + REQ_OP_FLUSH = (__force blk_opf_t)2, /* discard sectors */ - REQ_OP_DISCARD = 3, + REQ_OP_DISCARD = (__force blk_opf_t)3, /* securely erase sectors */ - REQ_OP_SECURE_ERASE = 5, - /* write the same sector many times */ - REQ_OP_WRITE_SAME = 7, + REQ_OP_SECURE_ERASE = (__force blk_opf_t)5, /* write the zero filled sector many times */ - REQ_OP_WRITE_ZEROES = 9, + REQ_OP_WRITE_ZEROES = (__force blk_opf_t)9, /* Open a zone */ - REQ_OP_ZONE_OPEN = 10, + REQ_OP_ZONE_OPEN = (__force blk_opf_t)10, /* Close a zone */ - REQ_OP_ZONE_CLOSE = 11, + REQ_OP_ZONE_CLOSE = (__force blk_opf_t)11, /* Transition a zone to full */ - REQ_OP_ZONE_FINISH = 12, + REQ_OP_ZONE_FINISH = (__force blk_opf_t)12, /* write data at the current zone write pointer */ - REQ_OP_ZONE_APPEND = 13, + REQ_OP_ZONE_APPEND = (__force blk_opf_t)13, /* reset a zone write pointer */ - REQ_OP_ZONE_RESET = 15, + REQ_OP_ZONE_RESET = (__force blk_opf_t)15, /* reset all the zone present on the device */ - REQ_OP_ZONE_RESET_ALL = 17, + REQ_OP_ZONE_RESET_ALL = (__force blk_opf_t)17, /* Driver private requests */ - REQ_OP_DRV_IN = 34, - REQ_OP_DRV_OUT = 35, + REQ_OP_DRV_IN = (__force blk_opf_t)34, + REQ_OP_DRV_OUT = (__force blk_opf_t)35, - REQ_OP_LAST, + REQ_OP_LAST = (__force blk_opf_t)36, }; enum req_flag_bits { @@ -402,39 +412,45 @@ enum req_flag_bits { * work item to avoid such priority inversions. */ __REQ_CGROUP_PUNT, + __REQ_POLLED, /* caller polls for completion using bio_poll */ + __REQ_ALLOC_CACHE, /* allocate IO from cache if available */ + __REQ_SWAP, /* swap I/O */ + __REQ_DRV, /* for driver use */ - /* command specific flags for REQ_OP_WRITE_ZEROES: */ + /* + * Command specific flags, keep last: + */ + /* for REQ_OP_WRITE_ZEROES: */ __REQ_NOUNMAP, /* do not free blocks when zeroing */ - __REQ_POLLED, /* caller polls for completion using bio_poll */ - - /* for driver use */ - __REQ_DRV, - __REQ_SWAP, /* swapping request. */ __REQ_NR_BITS, /* stops here */ }; -#define REQ_FAILFAST_DEV (1ULL << __REQ_FAILFAST_DEV) -#define REQ_FAILFAST_TRANSPORT (1ULL << __REQ_FAILFAST_TRANSPORT) -#define REQ_FAILFAST_DRIVER (1ULL << __REQ_FAILFAST_DRIVER) -#define REQ_SYNC (1ULL << __REQ_SYNC) -#define REQ_META (1ULL << __REQ_META) -#define REQ_PRIO (1ULL << __REQ_PRIO) -#define REQ_NOMERGE (1ULL << __REQ_NOMERGE) -#define REQ_IDLE (1ULL << __REQ_IDLE) -#define REQ_INTEGRITY (1ULL << __REQ_INTEGRITY) -#define REQ_FUA (1ULL << __REQ_FUA) -#define REQ_PREFLUSH (1ULL << __REQ_PREFLUSH) -#define REQ_RAHEAD (1ULL << __REQ_RAHEAD) -#define REQ_BACKGROUND (1ULL << __REQ_BACKGROUND) -#define REQ_NOWAIT (1ULL << __REQ_NOWAIT) -#define REQ_CGROUP_PUNT (1ULL << __REQ_CGROUP_PUNT) - -#define REQ_NOUNMAP (1ULL << __REQ_NOUNMAP) -#define REQ_POLLED (1ULL << __REQ_POLLED) - -#define REQ_DRV (1ULL << __REQ_DRV) -#define REQ_SWAP (1ULL << __REQ_SWAP) +#define REQ_FAILFAST_DEV \ + (__force blk_opf_t)(1ULL << __REQ_FAILFAST_DEV) +#define REQ_FAILFAST_TRANSPORT \ + (__force blk_opf_t)(1ULL << __REQ_FAILFAST_TRANSPORT) +#define REQ_FAILFAST_DRIVER \ + (__force blk_opf_t)(1ULL << __REQ_FAILFAST_DRIVER) +#define REQ_SYNC (__force blk_opf_t)(1ULL << __REQ_SYNC) +#define REQ_META (__force blk_opf_t)(1ULL << __REQ_META) +#define REQ_PRIO (__force blk_opf_t)(1ULL << __REQ_PRIO) +#define REQ_NOMERGE (__force blk_opf_t)(1ULL << __REQ_NOMERGE) +#define REQ_IDLE (__force blk_opf_t)(1ULL << __REQ_IDLE) +#define REQ_INTEGRITY (__force blk_opf_t)(1ULL << __REQ_INTEGRITY) +#define REQ_FUA (__force blk_opf_t)(1ULL << __REQ_FUA) +#define REQ_PREFLUSH (__force blk_opf_t)(1ULL << __REQ_PREFLUSH) +#define REQ_RAHEAD (__force blk_opf_t)(1ULL << __REQ_RAHEAD) +#define REQ_BACKGROUND (__force blk_opf_t)(1ULL << __REQ_BACKGROUND) +#define REQ_NOWAIT (__force blk_opf_t)(1ULL << __REQ_NOWAIT) +#define REQ_CGROUP_PUNT (__force blk_opf_t)(1ULL << __REQ_CGROUP_PUNT) + +#define REQ_NOUNMAP (__force blk_opf_t)(1ULL << __REQ_NOUNMAP) +#define REQ_POLLED (__force blk_opf_t)(1ULL << __REQ_POLLED) +#define REQ_ALLOC_CACHE (__force blk_opf_t)(1ULL << __REQ_ALLOC_CACHE) + +#define REQ_DRV (__force blk_opf_t)(1ULL << __REQ_DRV) +#define REQ_SWAP (__force blk_opf_t)(1ULL << __REQ_SWAP) #define REQ_FAILFAST_MASK \ (REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | REQ_FAILFAST_DRIVER) @@ -451,26 +467,28 @@ enum stat_group { NR_STAT_GROUPS }; -#define bio_op(bio) \ - ((bio)->bi_opf & REQ_OP_MASK) +static inline enum req_op bio_op(const struct bio *bio) +{ + return bio->bi_opf & REQ_OP_MASK; +} /* obsolete, don't use in new code */ -static inline void bio_set_op_attrs(struct bio *bio, unsigned op, - unsigned op_flags) +static inline void bio_set_op_attrs(struct bio *bio, enum req_op op, + blk_opf_t op_flags) { bio->bi_opf = op | op_flags; } -static inline bool op_is_write(unsigned int op) +static inline bool op_is_write(blk_opf_t op) { - return (op & 1); + return !!(op & (__force blk_opf_t)1); } /* * Check if the bio or request is one that needs special treatment in the * flush state machine. */ -static inline bool op_is_flush(unsigned int op) +static inline bool op_is_flush(blk_opf_t op) { return op & (REQ_FUA | REQ_PREFLUSH); } @@ -480,13 +498,13 @@ static inline bool op_is_flush(unsigned int op) * PREFLUSH flag. Other operations may be marked as synchronous using the * REQ_SYNC flag. */ -static inline bool op_is_sync(unsigned int op) +static inline bool op_is_sync(blk_opf_t op) { return (op & REQ_OP_MASK) == REQ_OP_READ || (op & (REQ_SYNC | REQ_FUA | REQ_PREFLUSH)); } -static inline bool op_is_discard(unsigned int op) +static inline bool op_is_discard(blk_opf_t op) { return (op & REQ_OP_MASK) == REQ_OP_DISCARD; } @@ -497,7 +515,7 @@ static inline bool op_is_discard(unsigned int op) * due to its different handling in the block layer and device response in * case of command failure. */ -static inline bool op_is_zone_mgmt(enum req_opf op) +static inline bool op_is_zone_mgmt(enum req_op op) { switch (op & REQ_OP_MASK) { case REQ_OP_ZONE_RESET: @@ -510,7 +528,7 @@ static inline bool op_is_zone_mgmt(enum req_opf op) } } -static inline int op_stat_group(unsigned int op) +static inline int op_stat_group(enum req_op op) { if (op_is_discard(op)) return STAT_DISCARD; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index bd4370baccca..50e358a19d98 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1,9 +1,13 @@ /* SPDX-License-Identifier: GPL-2.0 */ +/* + * Portions Copyright (C) 1992 Drew Eckhardt + */ #ifndef _LINUX_BLKDEV_H #define _LINUX_BLKDEV_H -#include <linux/sched.h> -#include <linux/genhd.h> +#include <linux/types.h> +#include <linux/blk_types.h> +#include <linux/device.h> #include <linux/list.h> #include <linux/llist.h> #include <linux/minmax.h> @@ -12,10 +16,15 @@ #include <linux/wait.h> #include <linux/bio.h> #include <linux/gfp.h> +#include <linux/kdev_t.h> #include <linux/rcupdate.h> #include <linux/percpu-refcount.h> #include <linux/blkzoned.h> +#include <linux/sched.h> #include <linux/sbitmap.h> +#include <linux/srcu.h> +#include <linux/uuid.h> +#include <linux/xarray.h> struct module; struct request_queue; @@ -32,6 +41,10 @@ struct blk_queue_stats; struct blk_stat_callback; struct blk_crypto_profile; +extern const struct device_type disk_type; +extern struct device_type part_type; +extern struct class block_class; + /* Must be consistent with blk_mq_poll_stats_bkt() */ #define BLK_MQ_POLL_STATS_BKTS 16 @@ -44,7 +57,194 @@ struct blk_crypto_profile; */ #define BLKCG_MAX_POLS 6 -static inline int blk_validate_block_size(unsigned int bsize) +#define DISK_MAX_PARTS 256 +#define DISK_NAME_LEN 32 + +#define PARTITION_META_INFO_VOLNAMELTH 64 +/* + * Enough for the string representation of any kind of UUID plus NULL. + * EFI UUID is 36 characters. MSDOS UUID is 11 characters. + */ +#define PARTITION_META_INFO_UUIDLTH (UUID_STRING_LEN + 1) + +struct partition_meta_info { + char uuid[PARTITION_META_INFO_UUIDLTH]; + u8 volname[PARTITION_META_INFO_VOLNAMELTH]; +}; + +/** + * DOC: genhd capability flags + * + * ``GENHD_FL_REMOVABLE``: indicates that the block device gives access to + * removable media. When set, the device remains present even when media is not + * inserted. Shall not be set for devices which are removed entirely when the + * media is removed. + * + * ``GENHD_FL_HIDDEN``: the block device is hidden; it doesn't produce events, + * doesn't appear in sysfs, and can't be opened from userspace or using + * blkdev_get*. Used for the underlying components of multipath devices. + * + * ``GENHD_FL_NO_PART``: partition support is disabled. The kernel will not + * scan for partitions from add_disk, and users can't add partitions manually. + * + */ +enum { + GENHD_FL_REMOVABLE = 1 << 0, + GENHD_FL_HIDDEN = 1 << 1, + GENHD_FL_NO_PART = 1 << 2, +}; + +enum { + DISK_EVENT_MEDIA_CHANGE = 1 << 0, /* media changed */ + DISK_EVENT_EJECT_REQUEST = 1 << 1, /* eject requested */ +}; + +enum { + /* Poll even if events_poll_msecs is unset */ + DISK_EVENT_FLAG_POLL = 1 << 0, + /* Forward events to udev */ + DISK_EVENT_FLAG_UEVENT = 1 << 1, + /* Block event polling when open for exclusive write */ + DISK_EVENT_FLAG_BLOCK_ON_EXCL_WRITE = 1 << 2, +}; + +struct disk_events; +struct badblocks; + +struct blk_integrity { + const struct blk_integrity_profile *profile; + unsigned char flags; + unsigned char tuple_size; + unsigned char interval_exp; + unsigned char tag_size; +}; + +struct gendisk { + /* + * major/first_minor/minors should not be set by any new driver, the + * block core will take care of allocating them automatically. + */ + int major; + int first_minor; + int minors; + + char disk_name[DISK_NAME_LEN]; /* name of major driver */ + + unsigned short events; /* supported events */ + unsigned short event_flags; /* flags related to event processing */ + + struct xarray part_tbl; + struct block_device *part0; + + const struct block_device_operations *fops; + struct request_queue *queue; + void *private_data; + + struct bio_set bio_split; + + int flags; + unsigned long state; +#define GD_NEED_PART_SCAN 0 +#define GD_READ_ONLY 1 +#define GD_DEAD 2 +#define GD_NATIVE_CAPACITY 3 +#define GD_ADDED 4 +#define GD_SUPPRESS_PART_SCAN 5 +#define GD_OWNS_QUEUE 6 + + struct mutex open_mutex; /* open/close mutex */ + unsigned open_partitions; /* number of open partitions */ + + struct backing_dev_info *bdi; + struct kobject *slave_dir; +#ifdef CONFIG_BLOCK_HOLDER_DEPRECATED + struct list_head slave_bdevs; +#endif + struct timer_rand_state *random; + atomic_t sync_io; /* RAID */ + struct disk_events *ev; +#ifdef CONFIG_BLK_DEV_INTEGRITY + struct kobject integrity_kobj; +#endif /* CONFIG_BLK_DEV_INTEGRITY */ + +#ifdef CONFIG_BLK_DEV_ZONED + /* + * Zoned block device information for request dispatch control. + * nr_zones is the total number of zones of the device. This is always + * 0 for regular block devices. conv_zones_bitmap is a bitmap of nr_zones + * bits which indicates if a zone is conventional (bit set) or + * sequential (bit clear). seq_zones_wlock is a bitmap of nr_zones + * bits which indicates if a zone is write locked, that is, if a write + * request targeting the zone was dispatched. + * + * Reads of this information must be protected with blk_queue_enter() / + * blk_queue_exit(). Modifying this information is only allowed while + * no requests are being processed. See also blk_mq_freeze_queue() and + * blk_mq_unfreeze_queue(). + */ + unsigned int nr_zones; + unsigned int max_open_zones; + unsigned int max_active_zones; + unsigned long *conv_zones_bitmap; + unsigned long *seq_zones_wlock; +#endif /* CONFIG_BLK_DEV_ZONED */ + +#if IS_ENABLED(CONFIG_CDROM) + struct cdrom_device_info *cdi; +#endif + int node_id; + struct badblocks *bb; + struct lockdep_map lockdep_map; + u64 diskseq; + + /* + * Independent sector access ranges. This is always NULL for + * devices that do not have multiple independent access ranges. + */ + struct blk_independent_access_ranges *ia_ranges; +}; + +static inline bool disk_live(struct gendisk *disk) +{ + return !inode_unhashed(disk->part0->bd_inode); +} + +/** + * disk_openers - returns how many openers are there for a disk + * @disk: disk to check + * + * This returns the number of openers for a disk. Note that this value is only + * stable if disk->open_mutex is held. + * + * Note: Due to a quirk in the block layer open code, each open partition is + * only counted once even if there are multiple openers. + */ +static inline unsigned int disk_openers(struct gendisk *disk) +{ + return atomic_read(&disk->part0->bd_openers); +} + +/* + * The gendisk is refcounted by the part0 block_device, and the bd_device + * therein is also used for device model presentation in sysfs. + */ +#define dev_to_disk(device) \ + (dev_to_bdev(device)->bd_disk) +#define disk_to_dev(disk) \ + (&((disk)->part0->bd_device)) + +#if IS_REACHABLE(CONFIG_CDROM) +#define disk_to_cdi(disk) ((disk)->cdi) +#else +#define disk_to_cdi(disk) NULL +#endif + +static inline dev_t disk_devt(struct gendisk *disk) +{ + return MKDEV(disk->major, disk->first_minor); +} + +static inline int blk_validate_block_size(unsigned long bsize) { if (bsize < 512 || bsize > PAGE_SIZE || !is_power_of_2(bsize)) return -EINVAL; @@ -52,7 +252,7 @@ static inline int blk_validate_block_size(unsigned int bsize) return 0; } -static inline bool blk_op_is_passthrough(unsigned int op) +static inline bool blk_op_is_passthrough(blk_opf_t op) { op &= REQ_OP_MASK; return op == REQ_OP_DRV_IN || op == REQ_OP_DRV_OUT; @@ -96,7 +296,7 @@ struct queue_limits { unsigned int io_opt; unsigned int max_discard_sectors; unsigned int max_hw_discard_sectors; - unsigned int max_write_same_sectors; + unsigned int max_secure_erase_sectors; unsigned int max_write_zeroes_sectors; unsigned int max_zone_append_sectors; unsigned int discard_granularity; @@ -116,15 +316,15 @@ struct queue_limits { typedef int (*report_zones_cb)(struct blk_zone *zone, unsigned int idx, void *data); -void blk_queue_set_zoned(struct gendisk *disk, enum blk_zoned_model model); +void disk_set_zoned(struct gendisk *disk, enum blk_zoned_model model); #ifdef CONFIG_BLK_DEV_ZONED #define BLK_ALL_ZONES ((unsigned int)-1) int blkdev_report_zones(struct block_device *bdev, sector_t sector, unsigned int nr_zones, report_zones_cb cb, void *data); -unsigned int blkdev_nr_zones(struct gendisk *disk); -extern int blkdev_zone_mgmt(struct block_device *bdev, enum req_opf op, +unsigned int bdev_nr_zones(struct block_device *bdev); +extern int blkdev_zone_mgmt(struct block_device *bdev, enum req_op op, sector_t sectors, sector_t nr_sectors, gfp_t gfp_mask); int blk_revalidate_disk_zones(struct gendisk *disk, @@ -137,7 +337,7 @@ extern int blkdev_zone_mgmt_ioctl(struct block_device *bdev, fmode_t mode, #else /* CONFIG_BLK_DEV_ZONED */ -static inline unsigned int blkdev_nr_zones(struct gendisk *disk) +static inline unsigned int bdev_nr_zones(struct block_device *bdev) { return 0; } @@ -174,7 +374,6 @@ static inline int blkdev_zone_mgmt_ioctl(struct block_device *bdev, */ struct blk_independent_access_range { struct kobject kobj; - struct request_queue *queue; sector_t sector; sector_t nr_sectors; }; @@ -203,7 +402,7 @@ struct request_queue { unsigned int queue_depth; /* hw dispatch queues */ - struct blk_mq_hw_ctx **queue_hw_ctx; + struct xarray hctx_table; unsigned int nr_hw_queues; /* @@ -257,17 +456,23 @@ struct request_queue { unsigned long nr_requests; /* Max # of requests */ unsigned int dma_pad_mask; + /* + * Drivers that set dma_alignment to less than 511 must be prepared to + * handle individual bvec's that are not a multiple of a SECTOR_SIZE + * due to possible offsets. + */ unsigned int dma_alignment; #ifdef CONFIG_BLK_INLINE_ENCRYPTION struct blk_crypto_profile *crypto_profile; + struct kobject *crypto_kobject; #endif unsigned int rq_timeout; int poll_nsec; struct blk_stat_callback *poll_cb; - struct blk_rq_stat poll_stat[BLK_MQ_POLL_STATS_BKTS]; + struct blk_rq_stat *poll_stat; struct timer_list timeout; struct work_struct timeout_work; @@ -287,33 +492,7 @@ struct request_queue { unsigned int required_elevator_features; -#ifdef CONFIG_BLK_DEV_ZONED - /* - * Zoned block device information for request dispatch control. - * nr_zones is the total number of zones of the device. This is always - * 0 for regular block devices. conv_zones_bitmap is a bitmap of nr_zones - * bits which indicates if a zone is conventional (bit set) or - * sequential (bit clear). seq_zones_wlock is a bitmap of nr_zones - * bits which indicates if a zone is write locked, that is, if a write - * request targeting the zone was dispatched. All three fields are - * initialized by the low level device driver (e.g. scsi/sd.c). - * Stacking drivers (device mappers) may or may not initialize - * these fields. - * - * Reads of this information must be protected with blk_queue_enter() / - * blk_queue_exit(). Modifying this information is only allowed while - * no requests are being processed. See also blk_mq_freeze_queue() and - * blk_mq_unfreeze_queue(). - */ - unsigned int nr_zones; - unsigned long *conv_zones_bitmap; - unsigned long *seq_zones_wlock; - unsigned int max_open_zones; - unsigned int max_active_zones; -#endif /* CONFIG_BLK_DEV_ZONED */ - int node; - struct mutex debugfs_mutex; #ifdef CONFIG_BLK_DEV_IO_TRACE struct blk_trace __rcu *blk_trace; #endif @@ -354,42 +533,37 @@ struct request_queue { struct blk_mq_tag_set *tag_set; struct list_head tag_set_list; - struct bio_set bio_split; struct dentry *debugfs_dir; - -#ifdef CONFIG_BLK_DEBUG_FS struct dentry *sched_debugfs_dir; struct dentry *rqos_debugfs_dir; -#endif + /* + * Serializes all debugfs metadata operations using the above dentries. + */ + struct mutex debugfs_mutex; bool mq_sysfs_init_done; -#define BLK_MAX_WRITE_HINTS 5 - u64 write_hints[BLK_MAX_WRITE_HINTS]; - - /* - * Independent sector access ranges. This is always NULL for - * devices that do not have multiple independent access ranges. + /** + * @srcu: Sleepable RCU. Use as lock when type of the request queue + * is blocking (BLK_MQ_F_BLOCKING). Must be the last member */ - struct blk_independent_access_ranges *ia_ranges; + struct srcu_struct srcu[]; }; /* Keep blk_queue_flag_name[] in sync with the definitions below */ #define QUEUE_FLAG_STOPPED 0 /* queue is stopped */ #define QUEUE_FLAG_DYING 1 /* queue being torn down */ +#define QUEUE_FLAG_HAS_SRCU 2 /* SRCU is allocated */ #define QUEUE_FLAG_NOMERGES 3 /* disable merge attempts */ #define QUEUE_FLAG_SAME_COMP 4 /* complete on same CPU-group */ #define QUEUE_FLAG_FAIL_IO 5 /* fake timeout */ #define QUEUE_FLAG_NONROT 6 /* non-rotational device (SSD) */ #define QUEUE_FLAG_VIRT QUEUE_FLAG_NONROT /* paravirt device */ #define QUEUE_FLAG_IO_STAT 7 /* do disk/partitions IO accounting */ -#define QUEUE_FLAG_DISCARD 8 /* supports DISCARD */ #define QUEUE_FLAG_NOXMERGES 9 /* No extended merges */ #define QUEUE_FLAG_ADD_RANDOM 10 /* Contributes to random pool */ -#define QUEUE_FLAG_SECERASE 11 /* supports secure erase */ #define QUEUE_FLAG_SAME_FORCE 12 /* force complete on same CPU */ -#define QUEUE_FLAG_DEAD 13 /* queue tear-down finished */ #define QUEUE_FLAG_INIT_DONE 14 /* queue is initialized */ #define QUEUE_FLAG_STABLE_WRITES 15 /* don't modify blks until WB is done */ #define QUEUE_FLAG_POLL 16 /* IO polling enabled if set */ @@ -397,7 +571,6 @@ struct request_queue { #define QUEUE_FLAG_FUA 18 /* device supports FUA writes */ #define QUEUE_FLAG_DAX 19 /* device supports DAX */ #define QUEUE_FLAG_STATS 20 /* track IO start and completion times */ -#define QUEUE_FLAG_POLL_STATS 21 /* collecting stats for hybrid polling */ #define QUEUE_FLAG_REGISTERED 22 /* queue has been registered to a disk */ #define QUEUE_FLAG_QUIESCED 24 /* queue has been quiesced */ #define QUEUE_FLAG_PCI_P2PDMA 25 /* device supports PCI p2p requests */ @@ -405,10 +578,11 @@ struct request_queue { #define QUEUE_FLAG_RQ_ALLOC_TIME 27 /* record rq->alloc_time_ns */ #define QUEUE_FLAG_HCTX_ACTIVE 28 /* at least one blk-mq hctx is active */ #define QUEUE_FLAG_NOWAIT 29 /* device supports NOWAIT */ +#define QUEUE_FLAG_SQ_SCHED 30 /* single queue style io dispatch */ -#define QUEUE_FLAG_MQ_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \ - (1 << QUEUE_FLAG_SAME_COMP) | \ - (1 << QUEUE_FLAG_NOWAIT)) +#define QUEUE_FLAG_MQ_DEFAULT ((1UL << QUEUE_FLAG_IO_STAT) | \ + (1UL << QUEUE_FLAG_SAME_COMP) | \ + (1UL << QUEUE_FLAG_NOWAIT)) void blk_queue_flag_set(unsigned int flag, struct request_queue *q); void blk_queue_flag_clear(unsigned int flag, struct request_queue *q); @@ -416,7 +590,7 @@ bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q); #define blk_queue_stopped(q) test_bit(QUEUE_FLAG_STOPPED, &(q)->queue_flags) #define blk_queue_dying(q) test_bit(QUEUE_FLAG_DYING, &(q)->queue_flags) -#define blk_queue_dead(q) test_bit(QUEUE_FLAG_DEAD, &(q)->queue_flags) +#define blk_queue_has_srcu(q) test_bit(QUEUE_FLAG_HAS_SRCU, &(q)->queue_flags) #define blk_queue_init_done(q) test_bit(QUEUE_FLAG_INIT_DONE, &(q)->queue_flags) #define blk_queue_nomerges(q) test_bit(QUEUE_FLAG_NOMERGES, &(q)->queue_flags) #define blk_queue_noxmerges(q) \ @@ -426,11 +600,8 @@ bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q); test_bit(QUEUE_FLAG_STABLE_WRITES, &(q)->queue_flags) #define blk_queue_io_stat(q) test_bit(QUEUE_FLAG_IO_STAT, &(q)->queue_flags) #define blk_queue_add_random(q) test_bit(QUEUE_FLAG_ADD_RANDOM, &(q)->queue_flags) -#define blk_queue_discard(q) test_bit(QUEUE_FLAG_DISCARD, &(q)->queue_flags) #define blk_queue_zone_resetall(q) \ test_bit(QUEUE_FLAG_ZONE_RESETALL, &(q)->queue_flags) -#define blk_queue_secure_erase(q) \ - (test_bit(QUEUE_FLAG_SECERASE, &(q)->queue_flags)) #define blk_queue_dax(q) test_bit(QUEUE_FLAG_DAX, &(q)->queue_flags) #define blk_queue_pci_p2pdma(q) \ test_bit(QUEUE_FLAG_PCI_P2PDMA, &(q)->queue_flags) @@ -446,9 +617,8 @@ bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q); REQ_FAILFAST_DRIVER)) #define blk_queue_quiesced(q) test_bit(QUEUE_FLAG_QUIESCED, &(q)->queue_flags) #define blk_queue_pm_only(q) atomic_read(&(q)->pm_only) -#define blk_queue_fua(q) test_bit(QUEUE_FLAG_FUA, &(q)->queue_flags) #define blk_queue_registered(q) test_bit(QUEUE_FLAG_REGISTERED, &(q)->queue_flags) -#define blk_queue_nowait(q) test_bit(QUEUE_FLAG_NOWAIT, &(q)->queue_flags) +#define blk_queue_sq_sched(q) test_bit(QUEUE_FLAG_SQ_SCHED, &(q)->queue_flags) extern void blk_set_pm_only(struct request_queue *q); extern void blk_clear_pm_only(struct request_queue *q); @@ -495,76 +665,69 @@ static inline bool blk_queue_is_zoned(struct request_queue *q) } } -static inline sector_t blk_queue_zone_sectors(struct request_queue *q) -{ - return blk_queue_is_zoned(q) ? q->limits.chunk_sectors : 0; -} - #ifdef CONFIG_BLK_DEV_ZONED -static inline unsigned int blk_queue_nr_zones(struct request_queue *q) +static inline unsigned int disk_nr_zones(struct gendisk *disk) { - return blk_queue_is_zoned(q) ? q->nr_zones : 0; + return blk_queue_is_zoned(disk->queue) ? disk->nr_zones : 0; } -static inline unsigned int blk_queue_zone_no(struct request_queue *q, - sector_t sector) +static inline unsigned int disk_zone_no(struct gendisk *disk, sector_t sector) { - if (!blk_queue_is_zoned(q)) + if (!blk_queue_is_zoned(disk->queue)) return 0; - return sector >> ilog2(q->limits.chunk_sectors); + return sector >> ilog2(disk->queue->limits.chunk_sectors); } -static inline bool blk_queue_zone_is_seq(struct request_queue *q, - sector_t sector) +static inline bool disk_zone_is_seq(struct gendisk *disk, sector_t sector) { - if (!blk_queue_is_zoned(q)) + if (!blk_queue_is_zoned(disk->queue)) return false; - if (!q->conv_zones_bitmap) + if (!disk->conv_zones_bitmap) return true; - return !test_bit(blk_queue_zone_no(q, sector), q->conv_zones_bitmap); + return !test_bit(disk_zone_no(disk, sector), disk->conv_zones_bitmap); } -static inline void blk_queue_max_open_zones(struct request_queue *q, +static inline void disk_set_max_open_zones(struct gendisk *disk, unsigned int max_open_zones) { - q->max_open_zones = max_open_zones; + disk->max_open_zones = max_open_zones; } -static inline unsigned int queue_max_open_zones(const struct request_queue *q) +static inline void disk_set_max_active_zones(struct gendisk *disk, + unsigned int max_active_zones) { - return q->max_open_zones; + disk->max_active_zones = max_active_zones; } -static inline void blk_queue_max_active_zones(struct request_queue *q, - unsigned int max_active_zones) +static inline unsigned int bdev_max_open_zones(struct block_device *bdev) { - q->max_active_zones = max_active_zones; + return bdev->bd_disk->max_open_zones; } -static inline unsigned int queue_max_active_zones(const struct request_queue *q) +static inline unsigned int bdev_max_active_zones(struct block_device *bdev) { - return q->max_active_zones; + return bdev->bd_disk->max_active_zones; } + #else /* CONFIG_BLK_DEV_ZONED */ -static inline unsigned int blk_queue_nr_zones(struct request_queue *q) +static inline unsigned int disk_nr_zones(struct gendisk *disk) { return 0; } -static inline bool blk_queue_zone_is_seq(struct request_queue *q, - sector_t sector) +static inline bool disk_zone_is_seq(struct gendisk *disk, sector_t sector) { return false; } -static inline unsigned int blk_queue_zone_no(struct request_queue *q, - sector_t sector) +static inline unsigned int disk_zone_no(struct gendisk *disk, sector_t sector) { return 0; } -static inline unsigned int queue_max_open_zones(const struct request_queue *q) +static inline unsigned int bdev_max_open_zones(struct block_device *bdev) { return 0; } -static inline unsigned int queue_max_active_zones(const struct request_queue *q) + +static inline unsigned int bdev_max_active_zones(struct block_device *bdev) { return 0; } @@ -588,19 +751,128 @@ static inline unsigned int blk_queue_depth(struct request_queue *q) #define for_each_bio(_bio) \ for (; _bio; _bio = _bio->bi_next) +int __must_check device_add_disk(struct device *parent, struct gendisk *disk, + const struct attribute_group **groups); +static inline int __must_check add_disk(struct gendisk *disk) +{ + return device_add_disk(NULL, disk, NULL); +} +void del_gendisk(struct gendisk *gp); +void invalidate_disk(struct gendisk *disk); +void set_disk_ro(struct gendisk *disk, bool read_only); +void disk_uevent(struct gendisk *disk, enum kobject_action action); + +static inline int get_disk_ro(struct gendisk *disk) +{ + return disk->part0->bd_read_only || + test_bit(GD_READ_ONLY, &disk->state); +} + +static inline int bdev_read_only(struct block_device *bdev) +{ + return bdev->bd_read_only || get_disk_ro(bdev->bd_disk); +} + +bool set_capacity_and_notify(struct gendisk *disk, sector_t size); +bool disk_force_media_change(struct gendisk *disk, unsigned int events); + +void add_disk_randomness(struct gendisk *disk) __latent_entropy; +void rand_initialize_disk(struct gendisk *disk); + +static inline sector_t get_start_sect(struct block_device *bdev) +{ + return bdev->bd_start_sect; +} + +static inline sector_t bdev_nr_sectors(struct block_device *bdev) +{ + return bdev->bd_nr_sectors; +} + +static inline loff_t bdev_nr_bytes(struct block_device *bdev) +{ + return (loff_t)bdev_nr_sectors(bdev) << SECTOR_SHIFT; +} + +static inline sector_t get_capacity(struct gendisk *disk) +{ + return bdev_nr_sectors(disk->part0); +} + +static inline u64 sb_bdev_nr_blocks(struct super_block *sb) +{ + return bdev_nr_sectors(sb->s_bdev) >> + (sb->s_blocksize_bits - SECTOR_SHIFT); +} + +int bdev_disk_changed(struct gendisk *disk, bool invalidate); + +void put_disk(struct gendisk *disk); +struct gendisk *__blk_alloc_disk(int node, struct lock_class_key *lkclass); + +/** + * blk_alloc_disk - allocate a gendisk structure + * @node_id: numa node to allocate on + * + * Allocate and pre-initialize a gendisk structure for use with BIO based + * drivers. + * + * Context: can sleep + */ +#define blk_alloc_disk(node_id) \ +({ \ + static struct lock_class_key __key; \ + \ + __blk_alloc_disk(node_id, &__key); \ +}) + +int __register_blkdev(unsigned int major, const char *name, + void (*probe)(dev_t devt)); +#define register_blkdev(major, name) \ + __register_blkdev(major, name, NULL) +void unregister_blkdev(unsigned int major, const char *name); + +bool bdev_check_media_change(struct block_device *bdev); +int __invalidate_device(struct block_device *bdev, bool kill_dirty); +void set_capacity(struct gendisk *disk, sector_t size); + +#ifdef CONFIG_BLOCK_HOLDER_DEPRECATED +int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk); +void bd_unlink_disk_holder(struct block_device *bdev, struct gendisk *disk); +int bd_register_pending_holders(struct gendisk *disk); +#else +static inline int bd_link_disk_holder(struct block_device *bdev, + struct gendisk *disk) +{ + return 0; +} +static inline void bd_unlink_disk_holder(struct block_device *bdev, + struct gendisk *disk) +{ +} +static inline int bd_register_pending_holders(struct gendisk *disk) +{ + return 0; +} +#endif /* CONFIG_BLOCK_HOLDER_DEPRECATED */ + +dev_t part_devt(struct gendisk *disk, u8 partno); +void inc_diskseq(struct gendisk *disk); +dev_t blk_lookup_devt(const char *name, int partno); +void blk_request_module(dev_t devt); extern int blk_register_queue(struct gendisk *disk); extern void blk_unregister_queue(struct gendisk *disk); void submit_bio_noacct(struct bio *bio); +struct bio *bio_split_to_limits(struct bio *bio); extern int blk_lld_busy(struct request_queue *q); -extern void blk_queue_split(struct bio **); extern int blk_queue_enter(struct request_queue *q, blk_mq_req_flags_t flags); extern void blk_queue_exit(struct request_queue *q); extern void blk_sync_queue(struct request_queue *q); /* Helper to convert REQ_OP_XXX to its string format XXX */ -extern const char *blk_op_str(unsigned int op); +extern const char *blk_op_str(enum req_op op); int blk_status_to_errno(blk_status_t status); blk_status_t errno_to_blk_status(int errno); @@ -618,78 +890,44 @@ static inline struct request_queue *bdev_get_queue(struct block_device *bdev) return bdev->bd_queue; /* this is never NULL */ } -#ifdef CONFIG_BLK_DEV_ZONED - /* Helper to convert BLK_ZONE_ZONE_XXX to its string format XXX */ const char *blk_zone_cond_str(enum blk_zone_cond zone_cond); static inline unsigned int bio_zone_no(struct bio *bio) { - return blk_queue_zone_no(bdev_get_queue(bio->bi_bdev), - bio->bi_iter.bi_sector); + return disk_zone_no(bio->bi_bdev->bd_disk, bio->bi_iter.bi_sector); } static inline unsigned int bio_zone_is_seq(struct bio *bio) { - return blk_queue_zone_is_seq(bdev_get_queue(bio->bi_bdev), - bio->bi_iter.bi_sector); -} -#endif /* CONFIG_BLK_DEV_ZONED */ - -static inline unsigned int blk_queue_get_max_sectors(struct request_queue *q, - int op) -{ - if (unlikely(op == REQ_OP_DISCARD || op == REQ_OP_SECURE_ERASE)) - return min(q->limits.max_discard_sectors, - UINT_MAX >> SECTOR_SHIFT); - - if (unlikely(op == REQ_OP_WRITE_SAME)) - return q->limits.max_write_same_sectors; - - if (unlikely(op == REQ_OP_WRITE_ZEROES)) - return q->limits.max_write_zeroes_sectors; - - return q->limits.max_sectors; + return disk_zone_is_seq(bio->bi_bdev->bd_disk, bio->bi_iter.bi_sector); } /* - * Return maximum size of a request at given offset. Only valid for - * file system requests. + * Return how much of the chunk is left to be used for I/O at a given offset. */ -static inline unsigned int blk_max_size_offset(struct request_queue *q, - sector_t offset, - unsigned int chunk_sectors) -{ - if (!chunk_sectors) { - if (q->limits.chunk_sectors) - chunk_sectors = q->limits.chunk_sectors; - else - return q->limits.max_sectors; - } - - if (likely(is_power_of_2(chunk_sectors))) - chunk_sectors -= offset & (chunk_sectors - 1); - else - chunk_sectors -= sector_div(offset, chunk_sectors); - - return min(q->limits.max_sectors, chunk_sectors); +static inline unsigned int blk_chunk_sectors_left(sector_t offset, + unsigned int chunk_sectors) +{ + if (unlikely(!is_power_of_2(chunk_sectors))) + return chunk_sectors - sector_div(offset, chunk_sectors); + return chunk_sectors - (offset & (chunk_sectors - 1)); } /* * Access functions for manipulating queue properties */ -extern void blk_cleanup_queue(struct request_queue *); void blk_queue_bounce_limit(struct request_queue *q, enum blk_bounce limit); extern void blk_queue_max_hw_sectors(struct request_queue *, unsigned int); extern void blk_queue_chunk_sectors(struct request_queue *, unsigned int); extern void blk_queue_max_segments(struct request_queue *, unsigned short); extern void blk_queue_max_discard_segments(struct request_queue *, unsigned short); +void blk_queue_max_secure_erase_sectors(struct request_queue *q, + unsigned int max_sectors); extern void blk_queue_max_segment_size(struct request_queue *, unsigned int); extern void blk_queue_max_discard_sectors(struct request_queue *q, unsigned int max_discard_sectors); -extern void blk_queue_max_write_same_sectors(struct request_queue *q, - unsigned int max_write_same_sectors); extern void blk_queue_max_write_zeroes_sectors(struct request_queue *q, unsigned int max_write_same_sectors); extern void blk_queue_logical_block_size(struct request_queue *, unsigned int); @@ -730,8 +968,6 @@ void disk_set_independent_access_ranges(struct gendisk *disk, */ /* Supports zoned block devices sequential write constraint */ #define ELEVATOR_F_ZBD_SEQ_WRITE (1U << 0) -/* Supports scheduling on multiple hardware queues */ -#define ELEVATOR_F_MQ_AWARE (1U << 1) extern void blk_queue_required_elevator_features(struct request_queue *q, unsigned int features); @@ -740,7 +976,8 @@ extern bool blk_queue_can_use_dma_map_merging(struct request_queue *q, bool __must_check blk_get_queue(struct request_queue *); extern void blk_put_queue(struct request_queue *); -extern void blk_set_queue_dying(struct request_queue *); + +void blk_mark_disk_dead(struct gendisk *disk); #ifdef CONFIG_BLOCK /* @@ -783,14 +1020,11 @@ extern void blk_start_plug(struct blk_plug *); extern void blk_start_plug_nr_ios(struct blk_plug *, unsigned short); extern void blk_finish_plug(struct blk_plug *); -void blk_flush_plug(struct blk_plug *plug, bool from_schedule); - -static inline bool blk_needs_flush_plug(struct task_struct *tsk) +void __blk_flush_plug(struct blk_plug *plug, bool from_schedule); +static inline void blk_flush_plug(struct blk_plug *plug, bool async) { - struct blk_plug *plug = tsk->plug; - - return plug && - (plug->mq_list || !list_empty(&plug->cb_list)); + if (plug) + __blk_flush_plug(plug, async); } int blkdev_issue_flush(struct block_device *bdev); @@ -816,11 +1050,6 @@ static inline void blk_flush_plug(struct blk_plug *plug, bool async) { } -static inline bool blk_needs_flush_plug(struct task_struct *tsk) -{ - return false; -} - static inline int blkdev_issue_flush(struct block_device *bdev) { return 0; @@ -834,16 +1063,12 @@ static inline long nr_blockdev_pages(void) extern void blk_io_schedule(void); -extern int blkdev_issue_write_same(struct block_device *bdev, sector_t sector, - sector_t nr_sects, gfp_t gfp_mask, struct page *page); - -#define BLKDEV_DISCARD_SECURE (1 << 0) /* issue a secure erase */ - -extern int blkdev_issue_discard(struct block_device *bdev, sector_t sector, - sector_t nr_sects, gfp_t gfp_mask, unsigned long flags); -extern int __blkdev_issue_discard(struct block_device *bdev, sector_t sector, - sector_t nr_sects, gfp_t gfp_mask, int flags, - struct bio **biop); +int blkdev_issue_discard(struct block_device *bdev, sector_t sector, + sector_t nr_sects, gfp_t gfp_mask); +int __blkdev_issue_discard(struct block_device *bdev, sector_t sector, + sector_t nr_sects, gfp_t gfp_mask, struct bio **biop); +int blkdev_issue_secure_erase(struct block_device *bdev, sector_t sector, + sector_t nr_sects, gfp_t gfp); #define BLKDEV_ZERO_NOUNMAP (1 << 0) /* do not free blocks */ #define BLKDEV_ZERO_NOFALLBACK (1 << 1) /* don't write explicit zeroes */ @@ -862,7 +1087,7 @@ static inline int sb_issue_discard(struct super_block *sb, sector_t block, SECTOR_SHIFT), nr_blocks << (sb->s_blocksize_bits - SECTOR_SHIFT), - gfp_mask, flags); + gfp_mask); } static inline int sb_issue_zeroout(struct super_block *sb, sector_t block, sector_t nr_blocks, gfp_t gfp_mask) @@ -936,6 +1161,17 @@ static inline unsigned int queue_max_zone_append_sectors(const struct request_qu return min(l->max_zone_append_sectors, l->max_sectors); } +static inline unsigned int +bdev_max_zone_append_sectors(struct block_device *bdev) +{ + return queue_max_zone_append_sectors(bdev_get_queue(bdev)); +} + +static inline unsigned int bdev_max_segments(struct block_device *bdev) +{ + return queue_max_segments(bdev_get_queue(bdev)); +} + static inline unsigned queue_logical_block_size(const struct request_queue *q) { int retval = 512; @@ -993,94 +1229,59 @@ bdev_zone_write_granularity(struct block_device *bdev) return queue_zone_write_granularity(bdev_get_queue(bdev)); } -static inline int queue_alignment_offset(const struct request_queue *q) -{ - if (q->limits.misaligned) - return -1; +int bdev_alignment_offset(struct block_device *bdev); +unsigned int bdev_discard_alignment(struct block_device *bdev); - return q->limits.alignment_offset; +static inline unsigned int bdev_max_discard_sectors(struct block_device *bdev) +{ + return bdev_get_queue(bdev)->limits.max_discard_sectors; } -static inline int queue_limit_alignment_offset(struct queue_limits *lim, sector_t sector) +static inline unsigned int bdev_discard_granularity(struct block_device *bdev) { - unsigned int granularity = max(lim->physical_block_size, lim->io_min); - unsigned int alignment = sector_div(sector, granularity >> SECTOR_SHIFT) - << SECTOR_SHIFT; + return bdev_get_queue(bdev)->limits.discard_granularity; +} - return (granularity + lim->alignment_offset - alignment) % granularity; +static inline unsigned int +bdev_max_secure_erase_sectors(struct block_device *bdev) +{ + return bdev_get_queue(bdev)->limits.max_secure_erase_sectors; } -static inline int bdev_alignment_offset(struct block_device *bdev) +static inline unsigned int bdev_write_zeroes_sectors(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); - if (q->limits.misaligned) - return -1; - if (bdev_is_partition(bdev)) - return queue_limit_alignment_offset(&q->limits, - bdev->bd_start_sect); - return q->limits.alignment_offset; + if (q) + return q->limits.max_write_zeroes_sectors; + + return 0; } -static inline int queue_discard_alignment(const struct request_queue *q) +static inline bool bdev_nonrot(struct block_device *bdev) { - if (q->limits.discard_misaligned) - return -1; - - return q->limits.discard_alignment; + return blk_queue_nonrot(bdev_get_queue(bdev)); } -static inline int queue_limit_discard_alignment(struct queue_limits *lim, sector_t sector) +static inline bool bdev_stable_writes(struct block_device *bdev) { - unsigned int alignment, granularity, offset; - - if (!lim->max_discard_sectors) - return 0; - - /* Why are these in bytes, not sectors? */ - alignment = lim->discard_alignment >> SECTOR_SHIFT; - granularity = lim->discard_granularity >> SECTOR_SHIFT; - if (!granularity) - return 0; - - /* Offset of the partition start in 'granularity' sectors */ - offset = sector_div(sector, granularity); - - /* And why do we do this modulus *again* in blkdev_issue_discard()? */ - offset = (granularity + alignment - offset) % granularity; - - /* Turn it back into bytes, gaah */ - return offset << SECTOR_SHIFT; + return test_bit(QUEUE_FLAG_STABLE_WRITES, + &bdev_get_queue(bdev)->queue_flags); } -static inline int bdev_discard_alignment(struct block_device *bdev) +static inline bool bdev_write_cache(struct block_device *bdev) { - struct request_queue *q = bdev_get_queue(bdev); - - if (bdev_is_partition(bdev)) - return queue_limit_discard_alignment(&q->limits, - bdev->bd_start_sect); - return q->limits.discard_alignment; + return test_bit(QUEUE_FLAG_WC, &bdev_get_queue(bdev)->queue_flags); } -static inline unsigned int bdev_write_same(struct block_device *bdev) +static inline bool bdev_fua(struct block_device *bdev) { - struct request_queue *q = bdev_get_queue(bdev); - - if (q) - return q->limits.max_write_same_sectors; - - return 0; + return test_bit(QUEUE_FLAG_FUA, &bdev_get_queue(bdev)->queue_flags); } -static inline unsigned int bdev_write_zeroes_sectors(struct block_device *bdev) +static inline bool bdev_nowait(struct block_device *bdev) { - struct request_queue *q = bdev_get_queue(bdev); - - if (q) - return q->limits.max_write_zeroes_sectors; - - return 0; + return test_bit(QUEUE_FLAG_NOWAIT, &bdev_get_queue(bdev)->queue_flags); } static inline enum blk_zoned_model bdev_zoned_model(struct block_device *bdev) @@ -1103,36 +1304,39 @@ static inline bool bdev_is_zoned(struct block_device *bdev) return false; } -static inline sector_t bdev_zone_sectors(struct block_device *bdev) +static inline bool bdev_op_is_zoned_write(struct block_device *bdev, + blk_opf_t op) { - struct request_queue *q = bdev_get_queue(bdev); + if (!bdev_is_zoned(bdev)) + return false; - if (q) - return blk_queue_zone_sectors(q); - return 0; + return op == REQ_OP_WRITE || op == REQ_OP_WRITE_ZEROES; } -static inline unsigned int bdev_max_open_zones(struct block_device *bdev) +static inline sector_t bdev_zone_sectors(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); - if (q) - return queue_max_open_zones(q); - return 0; + if (!blk_queue_is_zoned(q)) + return 0; + return q->limits.chunk_sectors; } -static inline unsigned int bdev_max_active_zones(struct block_device *bdev) +static inline int queue_dma_alignment(const struct request_queue *q) { - struct request_queue *q = bdev_get_queue(bdev); + return q ? q->dma_alignment : 511; +} - if (q) - return queue_max_active_zones(q); - return 0; +static inline unsigned int bdev_dma_alignment(struct block_device *bdev) +{ + return queue_dma_alignment(bdev_get_queue(bdev)); } -static inline int queue_dma_alignment(const struct request_queue *q) +static inline bool bdev_iter_is_aligned(struct block_device *bdev, + struct iov_iter *iter) { - return q ? q->dma_alignment : 511; + return iov_iter_is_aligned(iter, bdev_dma_alignment(bdev), + bdev_logical_block_size(bdev) - 1); } static inline int blk_rq_aligned(struct request_queue *q, unsigned long addr, @@ -1171,8 +1375,6 @@ int kblockd_mod_delayed_work_on(int cpu, struct delayed_work *dwork, unsigned lo bool blk_crypto_register(struct blk_crypto_profile *profile, struct request_queue *q); -void blk_crypto_unregister(struct request_queue *q); - #else /* CONFIG_BLK_INLINE_ENCRYPTION */ static inline bool blk_crypto_register(struct blk_crypto_profile *profile, @@ -1181,8 +1383,6 @@ static inline bool blk_crypto_register(struct blk_crypto_profile *profile, return true; } -static inline void blk_crypto_unregister(struct request_queue *q) { } - #endif /* CONFIG_BLK_INLINE_ENCRYPTION */ enum blk_unique_id { @@ -1196,9 +1396,11 @@ enum blk_unique_id { struct block_device_operations { void (*submit_bio)(struct bio *bio); + int (*poll_bio)(struct bio *bio, struct io_comp_batch *iob, + unsigned int flags); int (*open) (struct block_device *, fmode_t); void (*release) (struct gendisk *, fmode_t); - int (*rw_page)(struct block_device *, sector_t, struct page *, unsigned int); + int (*rw_page)(struct block_device *, sector_t, struct page *, enum req_op); int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); unsigned int (*check_events) (struct gendisk *disk, @@ -1206,6 +1408,7 @@ struct block_device_operations { void (*unlock_native_capacity) (struct gendisk *); int (*getgeo)(struct block_device *, struct hd_geometry *); int (*set_read_only)(struct block_device *bdev, bool ro); + void (*free_disk)(struct gendisk *disk); /* this callback is with swap_lock and sometimes page table lock held */ void (*swap_slot_free_notify) (struct block_device *, unsigned long); int (*report_zones)(struct gendisk *, sector_t sector, @@ -1249,11 +1452,13 @@ static inline void blk_wake_io_task(struct task_struct *waiter) wake_up_process(waiter); } -unsigned long disk_start_io_acct(struct gendisk *disk, unsigned int sectors, - unsigned int op); -void disk_end_io_acct(struct gendisk *disk, unsigned int op, +unsigned long bdev_start_io_acct(struct block_device *bdev, + unsigned int sectors, enum req_op op, + unsigned long start_time); +void bdev_end_io_acct(struct block_device *bdev, enum req_op op, unsigned long start_time); +void bio_start_io_acct_time(struct bio *bio, unsigned long start_time); unsigned long bio_start_io_acct(struct bio *bio); void bio_end_io_acct_remapped(struct bio *bio, unsigned long start_time, struct block_device *orig_bdev); @@ -1261,7 +1466,7 @@ void bio_end_io_acct_remapped(struct bio *bio, unsigned long start_time, /** * bio_end_io_acct - end I/O accounting for bio based drivers * @bio: bio to end account for - * @start: start time returned by bio_start_io_acct() + * @start_time: start time returned by bio_start_io_acct() */ static inline void bio_end_io_acct(struct bio *bio, unsigned long start_time) { @@ -1271,7 +1476,6 @@ static inline void bio_end_io_acct(struct bio *bio, unsigned long start_time) int bdev_read_only(struct block_device *bdev); int set_blocksize(struct block_device *bdev, int size); -const char *bdevname(struct block_device *bdev, char *buffer); int lookup_bdev(const char *pathname, dev_t *dev); void blkdev_show(struct seq_file *seqf, off_t offset); @@ -1304,8 +1508,11 @@ int truncate_bdev_range(struct block_device *bdev, fmode_t mode, loff_t lstart, #ifdef CONFIG_BLOCK void invalidate_bdev(struct block_device *bdev); int sync_blockdev(struct block_device *bdev); +int sync_blockdev_range(struct block_device *bdev, loff_t lstart, loff_t lend); int sync_blockdev_nowait(struct block_device *bdev); void sync_bdevs(bool wait); +void bdev_statx_dioalign(struct inode *inode, struct kstat *stat); +void printk_all_partitions(void); #else static inline void invalidate_bdev(struct block_device *bdev) { @@ -1321,7 +1528,14 @@ static inline int sync_blockdev_nowait(struct block_device *bdev) static inline void sync_bdevs(bool wait) { } -#endif +static inline void bdev_statx_dioalign(struct inode *inode, struct kstat *stat) +{ +} +static inline void printk_all_partitions(void) +{ +} +#endif /* CONFIG_BLOCK */ + int fsync_bdev(struct block_device *bdev); int freeze_bdev(struct block_device *bdev); @@ -1335,33 +1549,4 @@ struct io_comp_batch { #define DEFINE_IO_COMP_BATCH(name) struct io_comp_batch name = { } -#define rq_list_add(listptr, rq) do { \ - (rq)->rq_next = *(listptr); \ - *(listptr) = rq; \ -} while (0) - -#define rq_list_pop(listptr) \ -({ \ - struct request *__req = NULL; \ - if ((listptr) && *(listptr)) { \ - __req = *(listptr); \ - *(listptr) = __req->rq_next; \ - } \ - __req; \ -}) - -#define rq_list_peek(listptr) \ -({ \ - struct request *__req = NULL; \ - if ((listptr) && *(listptr)) \ - __req = *(listptr); \ - __req; \ -}) - -#define rq_list_for_each(listptr, pos) \ - for (pos = rq_list_peek((listptr)); pos; pos = rq_list_next(pos)) \ - -#define rq_list_next(rq) (rq)->rq_next -#define rq_list_empty(list) ((list) == (struct request *) NULL) - #endif /* _LINUX_BLKDEV_H */ diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h index 22501a293fa5..cfbda114348c 100644 --- a/include/linux/blktrace_api.h +++ b/include/linux/blktrace_api.h @@ -7,6 +7,7 @@ #include <linux/compat.h> #include <uapi/linux/blktrace_api.h> #include <linux/list.h> +#include <linux/blk_types.h> #if defined(CONFIG_BLK_DEV_IO_TRACE) @@ -27,12 +28,10 @@ struct blk_trace { atomic_t dropped; }; -struct blkcg; - extern int blk_trace_ioctl(struct block_device *, unsigned, char __user *); extern void blk_trace_shutdown(struct request_queue *); -extern __printf(3, 4) -void __trace_note_message(struct blk_trace *, struct blkcg *blkcg, const char *fmt, ...); +__printf(3, 4) void __blk_trace_note_message(struct blk_trace *bt, + struct cgroup_subsys_state *css, const char *fmt, ...); /** * blk_add_trace_msg - Add a (simple) message to the blktrace stream @@ -47,14 +46,14 @@ void __trace_note_message(struct blk_trace *, struct blkcg *blkcg, const char *f * NOTE: Can not use 'static inline' due to presence of var args... * **/ -#define blk_add_cgroup_trace_msg(q, cg, fmt, ...) \ +#define blk_add_cgroup_trace_msg(q, css, fmt, ...) \ do { \ struct blk_trace *bt; \ \ rcu_read_lock(); \ bt = rcu_dereference((q)->blk_trace); \ if (unlikely(bt)) \ - __trace_note_message(bt, cg, fmt, ##__VA_ARGS__);\ + __blk_trace_note_message(bt, css, fmt, ##__VA_ARGS__);\ rcu_read_unlock(); \ } while (0) #define blk_add_trace_msg(q, fmt, ...) \ @@ -79,10 +78,6 @@ extern int blk_trace_setup(struct request_queue *q, char *name, dev_t dev, char __user *arg); extern int blk_trace_startstop(struct request_queue *q, int start); extern int blk_trace_remove(struct request_queue *q); -extern void blk_trace_remove_sysfs(struct device *dev); -extern int blk_trace_init_sysfs(struct device *dev); - -extern struct attribute_group blk_trace_attr_group; #else /* !CONFIG_BLK_DEV_IO_TRACE */ # define blk_trace_ioctl(bdev, cmd, arg) (-ENOTTY) @@ -93,13 +88,7 @@ extern struct attribute_group blk_trace_attr_group; # define blk_trace_remove(q) (-ENOTTY) # define blk_add_trace_msg(q, fmt, ...) do { } while (0) # define blk_add_cgroup_trace_msg(q, cg, fmt, ...) do { } while (0) -# define blk_trace_remove_sysfs(dev) do { } while (0) # define blk_trace_note_message_enabled(q) (false) -static inline int blk_trace_init_sysfs(struct device *dev) -{ - return 0; -} - #endif /* CONFIG_BLK_DEV_IO_TRACE */ #ifdef CONFIG_COMPAT @@ -117,7 +106,7 @@ struct compat_blk_user_trace_setup { #endif -void blk_fill_rwbs(char *rwbs, unsigned int op); +void blk_fill_rwbs(char *rwbs, blk_opf_t opf); static inline sector_t blk_rq_trace_sector(struct request *rq) { diff --git a/include/linux/bma150.h b/include/linux/bma150.h index 31c9e323a391..4d4a62d49341 100644 --- a/include/linux/bma150.h +++ b/include/linux/bma150.h @@ -33,8 +33,8 @@ struct bma150_cfg { unsigned char lg_hyst; /* Low-G hysterisis */ unsigned char lg_dur; /* Low-G duration */ unsigned char lg_thres; /* Low-G threshold */ - unsigned char range; /* one of BMA0150_RANGE_xxx */ - unsigned char bandwidth; /* one of BMA0150_BW_xxx */ + unsigned char range; /* one of BMA150_RANGE_xxx */ + unsigned char bandwidth; /* one of BMA150_BW_xxx */ }; struct bma150_platform_data { diff --git a/include/linux/bootconfig.h b/include/linux/bootconfig.h index a4665c7ab07c..1611f9db878e 100644 --- a/include/linux/bootconfig.h +++ b/include/linux/bootconfig.h @@ -289,4 +289,14 @@ int __init xbc_get_info(int *node_size, size_t *data_size); /* XBC cleanup data structures */ void __init xbc_exit(void); +/* XBC embedded bootconfig data in kernel */ +#ifdef CONFIG_BOOT_CONFIG_EMBED +const char * __init xbc_get_embedded_bootconfig(size_t *size); +#else +static inline const char *xbc_get_embedded_bootconfig(size_t *size) +{ + return NULL; +} +#endif + #endif diff --git a/include/linux/bpf-cgroup-defs.h b/include/linux/bpf-cgroup-defs.h index 695d1224a71b..7b121bd780eb 100644 --- a/include/linux/bpf-cgroup-defs.h +++ b/include/linux/bpf-cgroup-defs.h @@ -10,6 +10,13 @@ struct bpf_prog_array; +#ifdef CONFIG_BPF_LSM +/* Maximum number of concurrently attachable per-cgroup LSM hooks. */ +#define CGROUP_LSM_NUM 10 +#else +#define CGROUP_LSM_NUM 0 +#endif + enum cgroup_bpf_attach_type { CGROUP_BPF_ATTACH_TYPE_INVALID = -1, CGROUP_INET_INGRESS = 0, @@ -35,6 +42,8 @@ enum cgroup_bpf_attach_type { CGROUP_INET4_GETSOCKNAME, CGROUP_INET6_GETSOCKNAME, CGROUP_INET_SOCK_RELEASE, + CGROUP_LSM_START, + CGROUP_LSM_END = CGROUP_LSM_START + CGROUP_LSM_NUM - 1, MAX_CGROUP_BPF_ATTACH_TYPE }; @@ -47,8 +56,8 @@ struct cgroup_bpf { * have either zero or one element * when BPF_F_ALLOW_MULTI the list can have up to BPF_CGROUP_MAX_PROGS */ - struct list_head progs[MAX_CGROUP_BPF_ATTACH_TYPE]; - u32 flags[MAX_CGROUP_BPF_ATTACH_TYPE]; + struct hlist_head progs[MAX_CGROUP_BPF_ATTACH_TYPE]; + u8 flags[MAX_CGROUP_BPF_ATTACH_TYPE]; /* list of cgroup shared storages */ struct list_head storages; diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index b525d8cdc25b..57e9e109257e 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -8,6 +8,7 @@ #include <linux/jump_label.h> #include <linux/percpu.h> #include <linux/rbtree.h> +#include <net/sock.h> #include <uapi/linux/bpf.h> struct sock; @@ -22,6 +23,13 @@ struct ctl_table; struct ctl_table_header; struct task_struct; +unsigned int __cgroup_bpf_run_lsm_sock(const void *ctx, + const struct bpf_insn *insn); +unsigned int __cgroup_bpf_run_lsm_socket(const void *ctx, + const struct bpf_insn *insn); +unsigned int __cgroup_bpf_run_lsm_current(const void *ctx, + const struct bpf_insn *insn); + #ifdef CONFIG_CGROUP_BPF #define CGROUP_ATYPE(type) \ @@ -94,7 +102,7 @@ struct bpf_cgroup_link { }; struct bpf_prog_list { - struct list_head node; + struct hlist_node node; struct bpf_prog *prog; struct bpf_cgroup_link *link; struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE]; @@ -165,11 +173,23 @@ int bpf_percpu_cgroup_storage_copy(struct bpf_map *map, void *key, void *value); int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, void *value, u64 flags); +/* Opportunistic check to see whether we have any BPF program attached*/ +static inline bool cgroup_bpf_sock_enabled(struct sock *sk, + enum cgroup_bpf_attach_type type) +{ + struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); + struct bpf_prog_array *array; + + array = rcu_access_pointer(cgrp->bpf.effective[type]); + return array != &bpf_empty_prog_array.hdr; +} + /* Wrappers for __cgroup_bpf_run_filter_skb() guarded by cgroup_bpf_enabled. */ #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk, skb) \ ({ \ int __ret = 0; \ - if (cgroup_bpf_enabled(CGROUP_INET_INGRESS)) \ + if (cgroup_bpf_enabled(CGROUP_INET_INGRESS) && \ + cgroup_bpf_sock_enabled(sk, CGROUP_INET_INGRESS)) \ __ret = __cgroup_bpf_run_filter_skb(sk, skb, \ CGROUP_INET_INGRESS); \ \ @@ -181,7 +201,8 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, int __ret = 0; \ if (cgroup_bpf_enabled(CGROUP_INET_EGRESS) && sk && sk == skb->sk) { \ typeof(sk) __sk = sk_to_full_sk(sk); \ - if (sk_fullsock(__sk)) \ + if (sk_fullsock(__sk) && \ + cgroup_bpf_sock_enabled(__sk, CGROUP_INET_EGRESS)) \ __ret = __cgroup_bpf_run_filter_skb(__sk, skb, \ CGROUP_INET_EGRESS); \ } \ @@ -211,24 +232,20 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, #define BPF_CGROUP_RUN_SA_PROG(sk, uaddr, atype) \ ({ \ - u32 __unused_flags; \ int __ret = 0; \ if (cgroup_bpf_enabled(atype)) \ __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, atype, \ - NULL, \ - &__unused_flags); \ + NULL, NULL); \ __ret; \ }) #define BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, atype, t_ctx) \ ({ \ - u32 __unused_flags; \ int __ret = 0; \ if (cgroup_bpf_enabled(atype)) { \ lock_sock(sk); \ __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, atype, \ - t_ctx, \ - &__unused_flags); \ + t_ctx, NULL); \ release_sock(sk); \ } \ __ret; \ @@ -347,7 +364,8 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, kernel_optval) \ ({ \ int __ret = 0; \ - if (cgroup_bpf_enabled(CGROUP_SETSOCKOPT)) \ + if (cgroup_bpf_enabled(CGROUP_SETSOCKOPT) && \ + cgroup_bpf_sock_enabled(sock, CGROUP_SETSOCKOPT)) \ __ret = __cgroup_bpf_run_filter_setsockopt(sock, level, \ optname, optval, \ optlen, \ @@ -367,7 +385,8 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, max_optlen, retval) \ ({ \ int __ret = retval; \ - if (cgroup_bpf_enabled(CGROUP_GETSOCKOPT)) \ + if (cgroup_bpf_enabled(CGROUP_GETSOCKOPT) && \ + cgroup_bpf_sock_enabled(sock, CGROUP_GETSOCKOPT)) \ if (!(sock)->sk_prot->bpf_bypass_getsockopt || \ !INDIRECT_CALL_INET_1((sock)->sk_prot->bpf_bypass_getsockopt, \ tcp_bpf_bypass_getsockopt, \ @@ -395,6 +414,11 @@ int cgroup_bpf_prog_detach(const union bpf_attr *attr, int cgroup_bpf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog); int cgroup_bpf_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr); + +const struct bpf_func_proto * +cgroup_common_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog); +const struct bpf_func_proto * +cgroup_current_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog); #else static inline int cgroup_bpf_inherit(struct cgroup *cgrp) { return 0; } @@ -425,6 +449,18 @@ static inline int cgroup_bpf_prog_query(const union bpf_attr *attr, return -EINVAL; } +static inline const struct bpf_func_proto * +cgroup_common_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) +{ + return NULL; +} + +static inline const struct bpf_func_proto * +cgroup_current_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) +{ + return NULL; +} + static inline int bpf_cgroup_storage_assign(struct bpf_prog_aux *aux, struct bpf_map *map) { return 0; } static inline struct bpf_cgroup_storage *bpf_cgroup_storage_alloc( diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 6e947cd91152..0566705c1d4e 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -5,6 +5,7 @@ #define _LINUX_BPF_H 1 #include <uapi/linux/bpf.h> +#include <uapi/linux/filter.h> #include <linux/workqueue.h> #include <linux/file.h> @@ -22,7 +23,11 @@ #include <linux/sched/mm.h> #include <linux/slab.h> #include <linux/percpu-refcount.h> +#include <linux/stddef.h> #include <linux/bpfptr.h> +#include <linux/btf.h> +#include <linux/rcupdate_trace.h> +#include <linux/init.h> struct bpf_verifier_env; struct bpf_verifier_log; @@ -43,6 +48,8 @@ struct kobject; struct mem_cgroup; struct module; struct bpf_func_state; +struct ftrace_ops; +struct cgroup; extern struct idr btf_idr; extern spinlock_t btf_idr_lock; @@ -52,6 +59,8 @@ typedef u64 (*bpf_callback_t)(u64, u64, u64, u64, u64); typedef int (*bpf_iter_init_seq_priv_t)(void *private_data, struct bpf_iter_aux_info *aux); typedef void (*bpf_iter_fini_seq_priv_t)(void *private_data); +typedef unsigned int (*bpf_func_t)(const void *, + const struct bpf_insn *); struct bpf_iter_seq_info { const struct seq_operations *seq_ops; bpf_iter_init_seq_priv_t init_seq_private; @@ -88,6 +97,7 @@ struct bpf_map_ops { int (*map_push_elem)(struct bpf_map *map, void *value, u64 flags); int (*map_pop_elem)(struct bpf_map *map, void *value); int (*map_peek_elem)(struct bpf_map *map, void *value); + void *(*map_lookup_percpu_elem)(struct bpf_map *map, void *key, u32 cpu); /* funcs called by prog_array and perf_event_array map */ void *(*map_fd_get_ptr)(struct bpf_map *map, struct file *map_file, @@ -147,14 +157,48 @@ struct bpf_map_ops { bpf_callback_t callback_fn, void *callback_ctx, u64 flags); - /* BTF name and id of struct allocated by map_alloc */ - const char * const map_btf_name; + /* BTF id of struct allocated by map_alloc */ int *map_btf_id; /* bpf_iter info used to open a seq_file */ const struct bpf_iter_seq_info *iter_seq_info; }; +enum { + /* Support at most 8 pointers in a BPF map value */ + BPF_MAP_VALUE_OFF_MAX = 8, + BPF_MAP_OFF_ARR_MAX = BPF_MAP_VALUE_OFF_MAX + + 1 + /* for bpf_spin_lock */ + 1, /* for bpf_timer */ +}; + +enum bpf_kptr_type { + BPF_KPTR_UNREF, + BPF_KPTR_REF, +}; + +struct bpf_map_value_off_desc { + u32 offset; + enum bpf_kptr_type type; + struct { + struct btf *btf; + struct module *module; + btf_dtor_kfunc_t dtor; + u32 btf_id; + } kptr; +}; + +struct bpf_map_value_off { + u32 nr_off; + struct bpf_map_value_off_desc off[]; +}; + +struct bpf_map_off_arr { + u32 cnt; + u32 field_off[BPF_MAP_OFF_ARR_MAX]; + u8 field_sz[BPF_MAP_OFF_ARR_MAX]; +}; + struct bpf_map { /* The first two cachelines with read-mostly members of which some * are also accessed in fast-path (e.g. ops, max_entries). @@ -171,6 +215,7 @@ struct bpf_map { u64 map_extra; /* any per-map-type extra fields */ u32 map_flags; int spin_lock_off; /* >=0 valid offset, <0 error */ + struct bpf_map_value_off *kptr_off_tab; int timer_off; /* >=0 valid offset, <0 error */ u32 id; int numa_node; @@ -179,13 +224,10 @@ struct bpf_map { u32 btf_vmlinux_value_type_id; struct btf *btf; #ifdef CONFIG_MEMCG_KMEM - struct mem_cgroup *memcg; + struct obj_cgroup *objcg; #endif char name[BPF_OBJ_NAME_LEN]; - bool bypass_spec_v1; - bool frozen; /* write-once; write-protected by freeze_mutex */ - /* 14 bytes hole */ - + struct bpf_map_off_arr *off_arr; /* The 3rd and 4th cacheline with misc members to avoid false sharing * particularly with refcounting. */ @@ -194,6 +236,19 @@ struct bpf_map { struct work_struct work; struct mutex freeze_mutex; atomic64_t writecnt; + /* 'Ownership' of program-containing map is claimed by the first program + * that is going to use this map or by the first program which FD is + * stored in the map to make sure that all callers and callees have the + * same prog type, JITed flag and xdp_has_frags flag. + */ + struct { + spinlock_t lock; + enum bpf_prog_type type; + bool jited; + bool xdp_has_frags; + } owner; + bool bypass_spec_v1; + bool frozen; /* write-once; write-protected by freeze_mutex */ }; static inline bool map_value_has_spin_lock(const struct bpf_map *map) @@ -206,45 +261,94 @@ static inline bool map_value_has_timer(const struct bpf_map *map) return map->timer_off >= 0; } +static inline bool map_value_has_kptrs(const struct bpf_map *map) +{ + return !IS_ERR_OR_NULL(map->kptr_off_tab); +} + static inline void check_and_init_map_value(struct bpf_map *map, void *dst) { if (unlikely(map_value_has_spin_lock(map))) - *(struct bpf_spin_lock *)(dst + map->spin_lock_off) = - (struct bpf_spin_lock){}; + memset(dst + map->spin_lock_off, 0, sizeof(struct bpf_spin_lock)); if (unlikely(map_value_has_timer(map))) - *(struct bpf_timer *)(dst + map->timer_off) = - (struct bpf_timer){}; + memset(dst + map->timer_off, 0, sizeof(struct bpf_timer)); + if (unlikely(map_value_has_kptrs(map))) { + struct bpf_map_value_off *tab = map->kptr_off_tab; + int i; + + for (i = 0; i < tab->nr_off; i++) + *(u64 *)(dst + tab->off[i].offset) = 0; + } +} + +/* memcpy that is used with 8-byte aligned pointers, power-of-8 size and + * forced to use 'long' read/writes to try to atomically copy long counters. + * Best-effort only. No barriers here, since it _will_ race with concurrent + * updates from BPF programs. Called from bpf syscall and mostly used with + * size 8 or 16 bytes, so ask compiler to inline it. + */ +static inline void bpf_long_memcpy(void *dst, const void *src, u32 size) +{ + const long *lsrc = src; + long *ldst = dst; + + size /= sizeof(long); + while (size--) + *ldst++ = *lsrc++; +} + +/* copy everything but bpf_spin_lock, bpf_timer, and kptrs. There could be one of each. */ +static inline void __copy_map_value(struct bpf_map *map, void *dst, void *src, bool long_memcpy) +{ + u32 curr_off = 0; + int i; + + if (likely(!map->off_arr)) { + if (long_memcpy) + bpf_long_memcpy(dst, src, round_up(map->value_size, 8)); + else + memcpy(dst, src, map->value_size); + return; + } + + for (i = 0; i < map->off_arr->cnt; i++) { + u32 next_off = map->off_arr->field_off[i]; + + memcpy(dst + curr_off, src + curr_off, next_off - curr_off); + curr_off += map->off_arr->field_sz[i]; + } + memcpy(dst + curr_off, src + curr_off, map->value_size - curr_off); } -/* copy everything but bpf_spin_lock and bpf_timer. There could be one of each. */ static inline void copy_map_value(struct bpf_map *map, void *dst, void *src) { - u32 s_off = 0, s_sz = 0, t_off = 0, t_sz = 0; + __copy_map_value(map, dst, src, false); +} + +static inline void copy_map_value_long(struct bpf_map *map, void *dst, void *src) +{ + __copy_map_value(map, dst, src, true); +} - if (unlikely(map_value_has_spin_lock(map))) { - s_off = map->spin_lock_off; - s_sz = sizeof(struct bpf_spin_lock); - } else if (unlikely(map_value_has_timer(map))) { - t_off = map->timer_off; - t_sz = sizeof(struct bpf_timer); +static inline void zero_map_value(struct bpf_map *map, void *dst) +{ + u32 curr_off = 0; + int i; + + if (likely(!map->off_arr)) { + memset(dst, 0, map->value_size); + return; } - if (unlikely(s_sz || t_sz)) { - if (s_off < t_off || !s_sz) { - swap(s_off, t_off); - swap(s_sz, t_sz); - } - memcpy(dst, src, t_off); - memcpy(dst + t_off + t_sz, - src + t_off + t_sz, - s_off - t_off - t_sz); - memcpy(dst + s_off + s_sz, - src + s_off + s_sz, - map->value_size - s_off - s_sz); - } else { - memcpy(dst, src, map->value_size); + for (i = 0; i < map->off_arr->cnt; i++) { + u32 next_off = map->off_arr->field_off[i]; + + memset(dst + curr_off, 0, next_off - curr_off); + curr_off += map->off_arr->field_sz[i]; } + memset(dst + curr_off, 0, map->value_size - curr_off); } + void copy_map_value_locked(struct bpf_map *map, void *dst, void *src, bool lock_src); void bpf_timer_cancel_and_free(void *timer); @@ -316,9 +420,50 @@ enum bpf_type_flag { */ MEM_RDONLY = BIT(1 + BPF_BASE_TYPE_BITS), - __BPF_TYPE_LAST_FLAG = MEM_RDONLY, + /* MEM was "allocated" from a different helper, and cannot be mixed + * with regular non-MEM_ALLOC'ed MEM types. + */ + MEM_ALLOC = BIT(2 + BPF_BASE_TYPE_BITS), + + /* MEM is in user address space. */ + MEM_USER = BIT(3 + BPF_BASE_TYPE_BITS), + + /* MEM is a percpu memory. MEM_PERCPU tags PTR_TO_BTF_ID. When tagged + * with MEM_PERCPU, PTR_TO_BTF_ID _cannot_ be directly accessed. In + * order to drop this tag, it must be passed into bpf_per_cpu_ptr() + * or bpf_this_cpu_ptr(), which will return the pointer corresponding + * to the specified cpu. + */ + MEM_PERCPU = BIT(4 + BPF_BASE_TYPE_BITS), + + /* Indicates that the argument will be released. */ + OBJ_RELEASE = BIT(5 + BPF_BASE_TYPE_BITS), + + /* PTR is not trusted. This is only used with PTR_TO_BTF_ID, to mark + * unreferenced and referenced kptr loaded from map value using a load + * instruction, so that they can only be dereferenced but not escape the + * BPF program into the kernel (i.e. cannot be passed as arguments to + * kfunc or bpf helpers). + */ + PTR_UNTRUSTED = BIT(6 + BPF_BASE_TYPE_BITS), + + MEM_UNINIT = BIT(7 + BPF_BASE_TYPE_BITS), + + /* DYNPTR points to memory local to the bpf program. */ + DYNPTR_TYPE_LOCAL = BIT(8 + BPF_BASE_TYPE_BITS), + + /* DYNPTR points to a kernel-produced ringbuf record. */ + DYNPTR_TYPE_RINGBUF = BIT(9 + BPF_BASE_TYPE_BITS), + + /* Size is known at compile time. */ + MEM_FIXED_SIZE = BIT(10 + BPF_BASE_TYPE_BITS), + + __BPF_TYPE_FLAG_MAX, + __BPF_TYPE_LAST_FLAG = __BPF_TYPE_FLAG_MAX - 1, }; +#define DYNPTR_TYPE_FLAG_MASK (DYNPTR_TYPE_LOCAL | DYNPTR_TYPE_RINGBUF) + /* Max number of base types. */ #define BPF_BASE_TYPE_LIMIT (1UL << BPF_BASE_TYPE_BITS) @@ -335,16 +480,11 @@ enum bpf_arg_type { ARG_CONST_MAP_PTR, /* const argument used as pointer to bpf_map */ ARG_PTR_TO_MAP_KEY, /* pointer to stack used as map key */ ARG_PTR_TO_MAP_VALUE, /* pointer to stack used as map value */ - ARG_PTR_TO_UNINIT_MAP_VALUE, /* pointer to valid memory used to store a map value */ - /* the following constraints used to prototype bpf_memcmp() and other - * functions that access data on eBPF program stack + /* Used to prototype bpf_memcmp() and other functions that access data + * on eBPF program stack */ ARG_PTR_TO_MEM, /* pointer to valid memory (stack, packet, map value) */ - ARG_PTR_TO_UNINIT_MEM, /* pointer to memory does not need to be initialized, - * helper function must fill all bytes or clear - * them in error case. - */ ARG_CONST_SIZE, /* number of bytes accessed from memory */ ARG_CONST_SIZE_OR_ZERO, /* number of bytes accessed from memory or 0 */ @@ -365,6 +505,8 @@ enum bpf_arg_type { ARG_PTR_TO_STACK, /* pointer to stack */ ARG_PTR_TO_CONST_STR, /* pointer to a null terminated read-only string */ ARG_PTR_TO_TIMER, /* pointer to bpf_timer */ + ARG_PTR_TO_KPTR, /* pointer to referenced kptr */ + ARG_PTR_TO_DYNPTR, /* pointer to bpf_dynptr. See bpf_type_flag for dynptr type */ __BPF_ARG_TYPE_MAX, /* Extended arg_types. */ @@ -374,6 +516,13 @@ enum bpf_arg_type { ARG_PTR_TO_SOCKET_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_SOCKET, ARG_PTR_TO_ALLOC_MEM_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_ALLOC_MEM, ARG_PTR_TO_STACK_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_STACK, + ARG_PTR_TO_BTF_ID_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_BTF_ID, + /* pointer to memory does not need to be initialized, helper function must fill + * all bytes or clear them in error case. + */ + ARG_PTR_TO_UNINIT_MEM = MEM_UNINIT | ARG_PTR_TO_MEM, + /* Pointer to valid memory of size known at compile time. */ + ARG_PTR_TO_FIXED_SIZE_MEM = MEM_FIXED_SIZE | ARG_PTR_TO_MEM, /* This must be the last entry. Its purpose is to ensure the enum is * wide enough to hold the higher bits reserved for bpf_type_flag. @@ -400,7 +549,8 @@ enum bpf_return_type { RET_PTR_TO_SOCKET_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_SOCKET, RET_PTR_TO_TCP_SOCK_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_TCP_SOCK, RET_PTR_TO_SOCK_COMMON_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_SOCK_COMMON, - RET_PTR_TO_ALLOC_MEM_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_ALLOC_MEM, + RET_PTR_TO_ALLOC_MEM_OR_NULL = PTR_MAYBE_NULL | MEM_ALLOC | RET_PTR_TO_ALLOC_MEM, + RET_PTR_TO_DYNPTR_MEM_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_ALLOC_MEM, RET_PTR_TO_BTF_ID_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_BTF_ID, /* This must be the last entry. Its purpose is to ensure the enum is @@ -438,6 +588,14 @@ struct bpf_func_proto { u32 *arg5_btf_id; }; u32 *arg_btf_id[5]; + struct { + size_t arg1_size; + size_t arg2_size; + size_t arg3_size; + size_t arg4_size; + size_t arg5_size; + }; + size_t arg_size[5]; }; int *ret_btf_id; /* return value btf_id */ bool (*allowed)(const struct bpf_prog *prog); @@ -498,8 +656,8 @@ enum bpf_reg_type { */ PTR_TO_MEM, /* reg points to valid memory region */ PTR_TO_BUF, /* reg points to a read/write buffer */ - PTR_TO_PERCPU_BTF_ID, /* reg points to a percpu kernel variable */ PTR_TO_FUNC, /* reg points to a bpf program function */ + PTR_TO_DYNPTR, /* reg points to a dynptr */ __BPF_REG_TYPE_MAX, /* Extended reg_types. */ @@ -572,8 +730,7 @@ struct bpf_verifier_ops { const struct btf *btf, const struct btf_type *t, int off, int size, enum bpf_access_type atype, - u32 *next_btf_id); - bool (*check_kfunc_call)(u32 kfunc_btf_id, struct module *owner); + u32 *next_btf_id, enum bpf_type_flag *flag); }; struct bpf_prog_offload_ops { @@ -621,10 +778,14 @@ enum bpf_cgroup_storage_type { */ #define MAX_BPF_FUNC_REG_ARGS 5 +/* The argument is a structure. */ +#define BTF_FMODEL_STRUCT_ARG BIT(0) + struct btf_func_model { u8 ret_size; u8 nr_args; u8 arg_size[MAX_BPF_FUNC_ARGS]; + u8 arg_flags[MAX_BPF_FUNC_ARGS]; }; /* Restore arguments before returning from trampoline to let original function @@ -647,16 +808,28 @@ struct btf_func_model { /* Return the return value of fentry prog. Only used by bpf_struct_ops. */ #define BPF_TRAMP_F_RET_FENTRY_RET BIT(4) +/* Get original function from stack instead of from provided direct address. + * Makes sense for trampolines with fexit or fmod_ret programs. + */ +#define BPF_TRAMP_F_ORIG_STACK BIT(5) + +/* This trampoline is on a function with another ftrace_ops with IPMODIFY, + * e.g., a live patch. This flag is set and cleared by ftrace call backs, + */ +#define BPF_TRAMP_F_SHARE_IPMODIFY BIT(6) + /* Each call __bpf_prog_enter + call bpf_func + call __bpf_prog_exit is ~50 - * bytes on x86. Pick a number to fit into BPF_IMAGE_SIZE / 2 + * bytes on x86. */ -#define BPF_MAX_TRAMP_PROGS 38 +#define BPF_MAX_TRAMP_LINKS 38 -struct bpf_tramp_progs { - struct bpf_prog *progs[BPF_MAX_TRAMP_PROGS]; - int nr_progs; +struct bpf_tramp_links { + struct bpf_tramp_link *links[BPF_MAX_TRAMP_LINKS]; + int nr_links; }; +struct bpf_tramp_run_ctx; + /* Different use cases for BPF trampoline: * 1. replace nop at the function entry (kprobe equivalent) * flags = BPF_TRAMP_F_RESTORE_REGS @@ -680,13 +853,22 @@ struct bpf_tramp_progs { struct bpf_tramp_image; int arch_prepare_bpf_trampoline(struct bpf_tramp_image *tr, void *image, void *image_end, const struct btf_func_model *m, u32 flags, - struct bpf_tramp_progs *tprogs, + struct bpf_tramp_links *tlinks, void *orig_call); /* these two functions are called from generated trampoline */ -u64 notrace __bpf_prog_enter(struct bpf_prog *prog); -void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start); -u64 notrace __bpf_prog_enter_sleepable(struct bpf_prog *prog); -void notrace __bpf_prog_exit_sleepable(struct bpf_prog *prog, u64 start); +u64 notrace __bpf_prog_enter(struct bpf_prog *prog, struct bpf_tramp_run_ctx *run_ctx); +void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start, struct bpf_tramp_run_ctx *run_ctx); +u64 notrace __bpf_prog_enter_sleepable(struct bpf_prog *prog, struct bpf_tramp_run_ctx *run_ctx); +void notrace __bpf_prog_exit_sleepable(struct bpf_prog *prog, u64 start, + struct bpf_tramp_run_ctx *run_ctx); +u64 notrace __bpf_prog_enter_lsm_cgroup(struct bpf_prog *prog, + struct bpf_tramp_run_ctx *run_ctx); +void notrace __bpf_prog_exit_lsm_cgroup(struct bpf_prog *prog, u64 start, + struct bpf_tramp_run_ctx *run_ctx); +u64 notrace __bpf_prog_enter_struct_ops(struct bpf_prog *prog, + struct bpf_tramp_run_ctx *run_ctx); +void notrace __bpf_prog_exit_struct_ops(struct bpf_prog *prog, u64 start, + struct bpf_tramp_run_ctx *run_ctx); void notrace __bpf_tramp_enter(struct bpf_tramp_image *tr); void notrace __bpf_tramp_exit(struct bpf_tramp_image *tr); @@ -722,9 +904,11 @@ struct bpf_tramp_image { struct bpf_trampoline { /* hlist for trampoline_table */ struct hlist_node hlist; + struct ftrace_ops *fops; /* serializes access to fields of this trampoline */ struct mutex mutex; refcount_t refcnt; + u32 flags; u64 key; struct { struct btf_func_model model; @@ -767,6 +951,7 @@ struct bpf_dispatcher { struct bpf_dispatcher_prog progs[BPF_DISPATCHER_MAX]; int num_progs; void *image; + void *rw_image; u32 image_off; struct bpf_ksym ksym; }; @@ -774,18 +959,20 @@ struct bpf_dispatcher { static __always_inline __nocfi unsigned int bpf_dispatcher_nop_func( const void *ctx, const struct bpf_insn *insnsi, - unsigned int (*bpf_func)(const void *, - const struct bpf_insn *)) + bpf_func_t bpf_func) { return bpf_func(ctx, insnsi); } + #ifdef CONFIG_BPF_JIT -int bpf_trampoline_link_prog(struct bpf_prog *prog, struct bpf_trampoline *tr); -int bpf_trampoline_unlink_prog(struct bpf_prog *prog, struct bpf_trampoline *tr); +int bpf_trampoline_link_prog(struct bpf_tramp_link *link, struct bpf_trampoline *tr); +int bpf_trampoline_unlink_prog(struct bpf_tramp_link *link, struct bpf_trampoline *tr); struct bpf_trampoline *bpf_trampoline_get(u64 key, struct bpf_attach_target_info *tgt_info); void bpf_trampoline_put(struct bpf_trampoline *tr); -int arch_prepare_bpf_dispatcher(void *image, s64 *funcs, int num_funcs); +int arch_prepare_bpf_dispatcher(void *image, void *buf, s64 *funcs, int num_funcs); +int __init bpf_arch_init_dispatcher_early(void *ip); + #define BPF_DISPATCHER_INIT(_name) { \ .mutex = __MUTEX_INITIALIZER(_name.mutex), \ .func = &_name##_func, \ @@ -799,45 +986,58 @@ int arch_prepare_bpf_dispatcher(void *image, s64 *funcs, int num_funcs); }, \ } +#define BPF_DISPATCHER_INIT_CALL(_name) \ + static int __init _name##_init(void) \ + { \ + return bpf_arch_init_dispatcher_early(_name##_func); \ + } \ + early_initcall(_name##_init) + +#ifdef CONFIG_X86_64 +#define BPF_DISPATCHER_ATTRIBUTES __attribute__((patchable_function_entry(5))) +#else +#define BPF_DISPATCHER_ATTRIBUTES +#endif + #define DEFINE_BPF_DISPATCHER(name) \ + notrace BPF_DISPATCHER_ATTRIBUTES \ noinline __nocfi unsigned int bpf_dispatcher_##name##_func( \ const void *ctx, \ const struct bpf_insn *insnsi, \ - unsigned int (*bpf_func)(const void *, \ - const struct bpf_insn *)) \ + bpf_func_t bpf_func) \ { \ return bpf_func(ctx, insnsi); \ } \ EXPORT_SYMBOL(bpf_dispatcher_##name##_func); \ struct bpf_dispatcher bpf_dispatcher_##name = \ - BPF_DISPATCHER_INIT(bpf_dispatcher_##name); + BPF_DISPATCHER_INIT(bpf_dispatcher_##name); \ + BPF_DISPATCHER_INIT_CALL(bpf_dispatcher_##name); + #define DECLARE_BPF_DISPATCHER(name) \ unsigned int bpf_dispatcher_##name##_func( \ const void *ctx, \ const struct bpf_insn *insnsi, \ - unsigned int (*bpf_func)(const void *, \ - const struct bpf_insn *)); \ + bpf_func_t bpf_func); \ extern struct bpf_dispatcher bpf_dispatcher_##name; #define BPF_DISPATCHER_FUNC(name) bpf_dispatcher_##name##_func #define BPF_DISPATCHER_PTR(name) (&bpf_dispatcher_##name) void bpf_dispatcher_change_prog(struct bpf_dispatcher *d, struct bpf_prog *from, struct bpf_prog *to); /* Called only from JIT-enabled code, so there's no need for stubs. */ -void *bpf_jit_alloc_exec_page(void); void bpf_image_ksym_add(void *data, struct bpf_ksym *ksym); void bpf_image_ksym_del(struct bpf_ksym *ksym); void bpf_ksym_add(struct bpf_ksym *ksym); void bpf_ksym_del(struct bpf_ksym *ksym); -int bpf_jit_charge_modmem(u32 pages); -void bpf_jit_uncharge_modmem(u32 pages); +int bpf_jit_charge_modmem(u32 size); +void bpf_jit_uncharge_modmem(u32 size); bool bpf_prog_has_trampoline(const struct bpf_prog *prog); #else -static inline int bpf_trampoline_link_prog(struct bpf_prog *prog, +static inline int bpf_trampoline_link_prog(struct bpf_tramp_link *link, struct bpf_trampoline *tr) { return -ENOTSUPP; } -static inline int bpf_trampoline_unlink_prog(struct bpf_prog *prog, +static inline int bpf_trampoline_unlink_prog(struct bpf_tramp_link *link, struct bpf_trampoline *tr) { return -ENOTSUPP; @@ -934,7 +1134,7 @@ struct bpf_prog_aux { bool func_proto_unreliable; bool sleepable; bool tail_call_reachable; - struct hlist_node tramp_hlist; + bool xdp_has_frags; /* BTF_KIND_FUNC_PROTO for valid attach_btf_id */ const struct btf_type *attach_func_proto; /* function name for valid attach_btf_id */ @@ -954,6 +1154,7 @@ struct bpf_prog_aux { struct user_struct *user; u64 load_time; /* ns since boottime */ u32 verified_insns; + int cgroup_atype; /* enum cgroup_bpf_attach_type */ struct bpf_map *cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]; char name[BPF_OBJ_NAME_LEN]; #ifdef CONFIG_SECURITY @@ -993,17 +1194,41 @@ struct bpf_prog_aux { }; }; +struct bpf_prog { + u16 pages; /* Number of allocated pages */ + u16 jited:1, /* Is our filter JIT'ed? */ + jit_requested:1,/* archs need to JIT the prog */ + gpl_compatible:1, /* Is filter GPL compatible? */ + cb_access:1, /* Is control block accessed? */ + dst_needed:1, /* Do we need dst entry? */ + blinding_requested:1, /* needs constant blinding */ + blinded:1, /* Was blinded */ + is_func:1, /* program is a bpf function */ + kprobe_override:1, /* Do we override a kprobe? */ + has_callchain_buf:1, /* callchain buffer allocated? */ + enforce_expected_attach_type:1, /* Enforce expected_attach_type checking at attach time */ + call_get_stack:1, /* Do we call bpf_get_stack() or bpf_get_stackid() */ + call_get_func_ip:1, /* Do we call get_func_ip() */ + tstamp_type_access:1; /* Accessed __sk_buff->tstamp_type */ + enum bpf_prog_type type; /* Type of BPF program */ + enum bpf_attach_type expected_attach_type; /* For some prog types */ + u32 len; /* Number of filter blocks */ + u32 jited_len; /* Size of jited insns in bytes */ + u8 tag[BPF_TAG_SIZE]; + struct bpf_prog_stats __percpu *stats; + int __percpu *active; + unsigned int (*bpf_func)(const void *ctx, + const struct bpf_insn *insn); + struct bpf_prog_aux *aux; /* Auxiliary fields */ + struct sock_fprog_kern *orig_prog; /* Original BPF program */ + /* Instructions for interpreter */ + union { + DECLARE_FLEX_ARRAY(struct sock_filter, insns); + DECLARE_FLEX_ARRAY(struct bpf_insn, insnsi); + }; +}; + struct bpf_array_aux { - /* 'Ownership' of prog array is claimed by the first program that - * is going to use this map or by the first program which FD is - * stored in the map to make sure that all callers and callees have - * the same prog type and JITed flag. - */ - struct { - spinlock_t lock; - enum bpf_prog_type type; - bool jited; - } owner; /* Programs with direct jumps into programs part of this array. */ struct list_head poke_progs; struct bpf_map *map; @@ -1031,6 +1256,24 @@ struct bpf_link_ops { struct bpf_link_info *info); }; +struct bpf_tramp_link { + struct bpf_link link; + struct hlist_node tramp_hlist; + u64 cookie; +}; + +struct bpf_shim_tramp_link { + struct bpf_tramp_link link; + struct bpf_trampoline *trampoline; +}; + +struct bpf_tracing_link { + struct bpf_tramp_link link; + enum bpf_attach_type attach_type; + struct bpf_trampoline *trampoline; + struct bpf_prog *tgt_prog; +}; + struct bpf_link_primer { struct bpf_link *link; struct file *file; @@ -1068,8 +1311,8 @@ bool bpf_struct_ops_get(const void *kdata); void bpf_struct_ops_put(const void *kdata); int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map, void *key, void *value); -int bpf_struct_ops_prepare_trampoline(struct bpf_tramp_progs *tprogs, - struct bpf_prog *prog, +int bpf_struct_ops_prepare_trampoline(struct bpf_tramp_links *tlinks, + struct bpf_tramp_link *link, const struct btf_func_model *model, void *image, void *image_end); static inline bool bpf_try_module_get(const void *data, struct module *owner) @@ -1127,6 +1370,21 @@ static inline int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map, } #endif +#if defined(CONFIG_CGROUP_BPF) && defined(CONFIG_BPF_LSM) +int bpf_trampoline_link_cgroup_shim(struct bpf_prog *prog, + int cgroup_atype); +void bpf_trampoline_unlink_cgroup_shim(struct bpf_prog *prog); +#else +static inline int bpf_trampoline_link_cgroup_shim(struct bpf_prog *prog, + int cgroup_atype) +{ + return -EOPNOTSUPP; +} +static inline void bpf_trampoline_unlink_cgroup_shim(struct bpf_prog *prog) +{ +} +#endif + struct bpf_array { struct bpf_map map; u32 elem_size; @@ -1142,6 +1400,9 @@ struct bpf_array { #define BPF_COMPLEXITY_LIMIT_INSNS 1000000 /* yes. 1M insns */ #define MAX_TAIL_CALL_CNT 33 +/* Maximum number of loops for bpf_loop */ +#define BPF_MAX_LOOPS BIT(23) + #define BPF_F_ACCESS_MASK (BPF_F_RDONLY | \ BPF_F_RDONLY_PROG | \ BPF_F_WRONLY | \ @@ -1150,6 +1411,11 @@ struct bpf_array { #define BPF_MAP_CAN_READ BIT(0) #define BPF_MAP_CAN_WRITE BIT(1) +/* Maximum number of user-producer ring buffer samples that can be drained in + * a call to bpf_user_ringbuf_drain(). + */ +#define BPF_MAX_USER_RINGBUF_SAMPLES (128 * 1024) + static inline u32 bpf_map_flags_to_cap(struct bpf_map *map) { u32 access_flags = map->map_flags & (BPF_F_RDONLY_PROG | BPF_F_WRONLY_PROG); @@ -1178,7 +1444,14 @@ struct bpf_event_entry { struct rcu_head rcu; }; -bool bpf_prog_array_compatible(struct bpf_array *array, const struct bpf_prog *fp); +static inline bool map_type_contains_progs(struct bpf_map *map) +{ + return map->map_type == BPF_MAP_TYPE_PROG_ARRAY || + map->map_type == BPF_MAP_TYPE_DEVMAP || + map->map_type == BPF_MAP_TYPE_CPUMAP; +} + +bool bpf_prog_map_compatible(struct bpf_map *map, const struct bpf_prog *fp); int bpf_prog_calc_tag(struct bpf_prog *fp); const struct bpf_func_proto *bpf_get_trace_printk_proto(void); @@ -1198,7 +1471,7 @@ u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size, /* an array of programs to be executed under rcu_lock. * * Typical usage: - * ret = BPF_PROG_RUN_ARRAY(&bpf_prog_array, ctx, bpf_prog_run); + * ret = bpf_prog_run_array(rcu_dereference(&bpf_prog_array), ctx, bpf_prog_run); * * the structure returned by bpf_prog_array_alloc() should be populated * with program pointers and the last pointer must be NULL. @@ -1220,8 +1493,23 @@ struct bpf_prog_array { struct bpf_prog_array_item items[]; }; +struct bpf_empty_prog_array { + struct bpf_prog_array hdr; + struct bpf_prog *null_prog; +}; + +/* to avoid allocating empty bpf_prog_array for cgroups that + * don't have bpf program attached use one global 'bpf_empty_prog_array' + * It will not be modified the caller of bpf_prog_array_alloc() + * (since caller requested prog_cnt == 0) + * that pointer should be 'freed' by bpf_prog_array_free() + */ +extern struct bpf_empty_prog_array bpf_empty_prog_array; + struct bpf_prog_array *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags); void bpf_prog_array_free(struct bpf_prog_array *progs); +/* Use when traversal over the bpf_prog_array uses tasks_trace rcu */ +void bpf_prog_array_free_sleepable(struct bpf_prog_array *progs); int bpf_prog_array_length(struct bpf_prog_array *progs); bool bpf_prog_array_is_empty(struct bpf_prog_array *array); int bpf_prog_array_copy_to_user(struct bpf_prog_array *progs, @@ -1246,6 +1534,7 @@ struct bpf_run_ctx {}; struct bpf_cg_run_ctx { struct bpf_run_ctx run_ctx; const struct bpf_prog_array_item *prog_item; + int retval; }; struct bpf_trace_run_ctx { @@ -1253,6 +1542,12 @@ struct bpf_trace_run_ctx { u64 bpf_cookie; }; +struct bpf_tramp_run_ctx { + struct bpf_run_ctx run_ctx; + u64 bpf_cookie; + struct bpf_run_ctx *saved_run_ctx; +}; + static inline struct bpf_run_ctx *bpf_set_run_ctx(struct bpf_run_ctx *new_ctx) { struct bpf_run_ctx *old_ctx = NULL; @@ -1279,66 +1574,46 @@ static inline void bpf_reset_run_ctx(struct bpf_run_ctx *old_ctx) typedef u32 (*bpf_prog_run_fn)(const struct bpf_prog *prog, const void *ctx); static __always_inline u32 -BPF_PROG_RUN_ARRAY_CG_FLAGS(const struct bpf_prog_array __rcu *array_rcu, - const void *ctx, bpf_prog_run_fn run_prog, - u32 *ret_flags) +bpf_prog_run_array(const struct bpf_prog_array *array, + const void *ctx, bpf_prog_run_fn run_prog) { const struct bpf_prog_array_item *item; const struct bpf_prog *prog; - const struct bpf_prog_array *array; struct bpf_run_ctx *old_run_ctx; - struct bpf_cg_run_ctx run_ctx; + struct bpf_trace_run_ctx run_ctx; u32 ret = 1; - u32 func_ret; - migrate_disable(); - rcu_read_lock(); - array = rcu_dereference(array_rcu); - item = &array->items[0]; - old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx); - while ((prog = READ_ONCE(item->prog))) { - run_ctx.prog_item = item; - func_ret = run_prog(prog, ctx); - ret &= (func_ret & 1); - *(ret_flags) |= (func_ret >> 1); - item++; - } - bpf_reset_run_ctx(old_run_ctx); - rcu_read_unlock(); - migrate_enable(); - return ret; -} + RCU_LOCKDEP_WARN(!rcu_read_lock_held(), "no rcu lock held"); -static __always_inline u32 -BPF_PROG_RUN_ARRAY_CG(const struct bpf_prog_array __rcu *array_rcu, - const void *ctx, bpf_prog_run_fn run_prog) -{ - const struct bpf_prog_array_item *item; - const struct bpf_prog *prog; - const struct bpf_prog_array *array; - struct bpf_run_ctx *old_run_ctx; - struct bpf_cg_run_ctx run_ctx; - u32 ret = 1; + if (unlikely(!array)) + return ret; migrate_disable(); - rcu_read_lock(); - array = rcu_dereference(array_rcu); - item = &array->items[0]; old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx); + item = &array->items[0]; while ((prog = READ_ONCE(item->prog))) { - run_ctx.prog_item = item; + run_ctx.bpf_cookie = item->bpf_cookie; ret &= run_prog(prog, ctx); item++; } bpf_reset_run_ctx(old_run_ctx); - rcu_read_unlock(); migrate_enable(); return ret; } +/* Notes on RCU design for bpf_prog_arrays containing sleepable programs: + * + * We use the tasks_trace rcu flavor read section to protect the bpf_prog_array + * overall. As a result, we must use the bpf_prog_array_free_sleepable + * in order to use the tasks_trace rcu grace period. + * + * When a non-sleepable program is inside the array, we take the rcu read + * section and disable preemption for that program alone, so it can access + * rcu-protected dynamically sized maps. + */ static __always_inline u32 -BPF_PROG_RUN_ARRAY(const struct bpf_prog_array __rcu *array_rcu, - const void *ctx, bpf_prog_run_fn run_prog) +bpf_prog_run_array_sleepable(const struct bpf_prog_array __rcu *array_rcu, + const void *ctx, bpf_prog_run_fn run_prog) { const struct bpf_prog_array_item *item; const struct bpf_prog *prog; @@ -1347,61 +1622,34 @@ BPF_PROG_RUN_ARRAY(const struct bpf_prog_array __rcu *array_rcu, struct bpf_trace_run_ctx run_ctx; u32 ret = 1; + might_fault(); + + rcu_read_lock_trace(); migrate_disable(); - rcu_read_lock(); - array = rcu_dereference(array_rcu); + + array = rcu_dereference_check(array_rcu, rcu_read_lock_trace_held()); if (unlikely(!array)) goto out; old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx); item = &array->items[0]; while ((prog = READ_ONCE(item->prog))) { + if (!prog->aux->sleepable) + rcu_read_lock(); + run_ctx.bpf_cookie = item->bpf_cookie; ret &= run_prog(prog, ctx); item++; + + if (!prog->aux->sleepable) + rcu_read_unlock(); } bpf_reset_run_ctx(old_run_ctx); out: - rcu_read_unlock(); migrate_enable(); + rcu_read_unlock_trace(); return ret; } -/* To be used by __cgroup_bpf_run_filter_skb for EGRESS BPF progs - * so BPF programs can request cwr for TCP packets. - * - * Current cgroup skb programs can only return 0 or 1 (0 to drop the - * packet. This macro changes the behavior so the low order bit - * indicates whether the packet should be dropped (0) or not (1) - * and the next bit is a congestion notification bit. This could be - * used by TCP to call tcp_enter_cwr() - * - * Hence, new allowed return values of CGROUP EGRESS BPF programs are: - * 0: drop packet - * 1: keep packet - * 2: drop packet and cn - * 3: keep packet and cn - * - * This macro then converts it to one of the NET_XMIT or an error - * code that is then interpreted as drop packet (and no cn): - * 0: NET_XMIT_SUCCESS skb should be transmitted - * 1: NET_XMIT_DROP skb should be dropped and cn - * 2: NET_XMIT_CN skb should be transmitted and cn - * 3: -EPERM skb should be dropped - */ -#define BPF_PROG_CGROUP_INET_EGRESS_RUN_ARRAY(array, ctx, func) \ - ({ \ - u32 _flags = 0; \ - bool _cn; \ - u32 _ret; \ - _ret = BPF_PROG_RUN_ARRAY_CG_FLAGS(array, ctx, func, &_flags); \ - _cn = _flags & BPF_RET_SET_CN; \ - if (_ret) \ - _ret = (_cn ? NET_XMIT_CN : NET_XMIT_SUCCESS); \ - else \ - _ret = (_cn ? NET_XMIT_DROP : -EPERM); \ - _ret; \ - }) - #ifdef CONFIG_BPF_SYSCALL DECLARE_PER_CPU(int, bpf_prog_active); extern struct mutex bpf_stats_enabled_mutex; @@ -1455,6 +1703,12 @@ void bpf_prog_put(struct bpf_prog *prog); void bpf_prog_free_id(struct bpf_prog *prog, bool do_idr_lock); void bpf_map_free_id(struct bpf_map *map, bool do_idr_lock); +struct bpf_map_value_off_desc *bpf_map_kptr_off_contains(struct bpf_map *map, u32 offset); +void bpf_map_free_kptr_off_tab(struct bpf_map *map); +struct bpf_map_value_off *bpf_map_copy_kptr_off_tab(const struct bpf_map *map); +bool bpf_map_equal_kptr_off_tab(const struct bpf_map *map_a, const struct bpf_map *map_b); +void bpf_map_free_kptrs(struct bpf_map *map, void *map_value); + struct bpf_map *bpf_map_get(u32 ufd); struct bpf_map *bpf_map_get_with_uref(u32 ufd); struct bpf_map *__bpf_map_get(struct fd f); @@ -1548,6 +1802,7 @@ void bpf_link_put(struct bpf_link *link); int bpf_link_new_fd(struct bpf_link *link); struct file *bpf_link_new_file(struct bpf_link *link, int *reserved_fd); struct bpf_link *bpf_link_get_from_fd(u32 ufd); +struct bpf_link *bpf_link_get_curr_or_next(u32 *id); int bpf_obj_pin_user(u32 ufd, const char __user *pathname); int bpf_obj_get_user(const char __user *pathname, int flags); @@ -1557,8 +1812,40 @@ int bpf_obj_get_user(const char __user *pathname, int flags); extern int bpf_iter_ ## target(args); \ int __init bpf_iter_ ## target(args) { return 0; } +/* + * The task type of iterators. + * + * For BPF task iterators, they can be parameterized with various + * parameters to visit only some of tasks. + * + * BPF_TASK_ITER_ALL (default) + * Iterate over resources of every task. + * + * BPF_TASK_ITER_TID + * Iterate over resources of a task/tid. + * + * BPF_TASK_ITER_TGID + * Iterate over resources of every task of a process / task group. + */ +enum bpf_iter_task_type { + BPF_TASK_ITER_ALL = 0, + BPF_TASK_ITER_TID, + BPF_TASK_ITER_TGID, +}; + struct bpf_iter_aux_info { + /* for map_elem iter */ struct bpf_map *map; + + /* for cgroup iter */ + struct { + struct cgroup *start; /* starting cgroup */ + enum bpf_cgroup_iter_order order; + } cgroup; + struct { + enum bpf_iter_task_type type; + u32 pid; + } task; }; typedef int (*bpf_iter_attach_target_t)(struct bpf_prog *prog, @@ -1643,22 +1930,6 @@ int bpf_get_file_flag(int flags); int bpf_check_uarg_tail_zero(bpfptr_t uaddr, size_t expected_size, size_t actual_size); -/* memcpy that is used with 8-byte aligned pointers, power-of-8 size and - * forced to use 'long' read/writes to try to atomically copy long counters. - * Best-effort only. No barriers here, since it _will_ race with concurrent - * updates from BPF programs. Called from bpf syscall and mostly used with - * size 8 or 16 bytes, so ask compiler to inline it. - */ -static inline void bpf_long_memcpy(void *dst, const void *src, u32 size) -{ - const long *lsrc = src; - long *ldst = dst; - - size /= sizeof(long); - while (size--) - *ldst++ = *lsrc++; -} - /* verify correctness of eBPF program */ int bpf_check(struct bpf_prog **fp, union bpf_attr *attr, bpfptr_t uattr); @@ -1719,7 +1990,6 @@ int bpf_prog_test_run_raw_tp(struct bpf_prog *prog, int bpf_prog_test_run_sk_lookup(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); -bool bpf_prog_test_check_kfunc_call(u32 kfunc_id, struct module *owner); bool btf_ctx_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info); @@ -1749,10 +2019,11 @@ static inline bool bpf_tracing_btf_ctx_access(int off, int size, int btf_struct_access(struct bpf_verifier_log *log, const struct btf *btf, const struct btf_type *t, int off, int size, enum bpf_access_type atype, - u32 *next_btf_id); + u32 *next_btf_id, enum bpf_type_flag *flag); bool btf_struct_ids_match(struct bpf_verifier_log *log, const struct btf *btf, u32 id, int off, - const struct btf *need_btf, u32 need_type_id); + const struct btf *need_btf, u32 need_type_id, + bool strict); int btf_distill_func_proto(struct bpf_verifier_log *log, struct btf *btf, @@ -1760,12 +2031,22 @@ int btf_distill_func_proto(struct bpf_verifier_log *log, const char *func_name, struct btf_func_model *m); +struct bpf_kfunc_arg_meta { + u64 r0_size; + bool r0_rdonly; + int ref_obj_id; + u32 flags; +}; + struct bpf_reg_state; int btf_check_subprog_arg_match(struct bpf_verifier_env *env, int subprog, struct bpf_reg_state *regs); +int btf_check_subprog_call(struct bpf_verifier_env *env, int subprog, + struct bpf_reg_state *regs); int btf_check_kfunc_arg_match(struct bpf_verifier_env *env, const struct btf *btf, u32 func_id, - struct bpf_reg_state *regs); + struct bpf_reg_state *regs, + struct bpf_kfunc_arg_meta *meta); int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog, struct bpf_reg_state *reg); int btf_check_type_match(struct bpf_verifier_log *log, const struct bpf_prog *prog, @@ -1788,6 +2069,22 @@ struct bpf_core_ctx { int bpf_core_apply(struct bpf_core_ctx *ctx, const struct bpf_core_relo *relo, int relo_idx, void *insn); +static inline bool unprivileged_ebpf_enabled(void) +{ + return !sysctl_unprivileged_bpf_disabled; +} + +/* Not all bpf prog type has the bpf_ctx. + * For the bpf prog type that has initialized the bpf_ctx, + * this function can be used to decide if a kernel function + * is called by a bpf program. + */ +static inline bool has_current_bpf_ctx(void) +{ + return !!current->bpf_ctx; +} + +void notrace bpf_prog_inc_misses_counter(struct bpf_prog *prog); #else /* !CONFIG_BPF_SYSCALL */ static inline struct bpf_prog *bpf_prog_get(u32 ufd) { @@ -1857,11 +2154,6 @@ static inline int bpf_obj_get_user(const char __user *pathname, int flags) return -EOPNOTSUPP; } -static inline bool dev_map_can_have_prog(struct bpf_map *map) -{ - return false; -} - static inline void __dev_flush(void) { } @@ -1925,11 +2217,6 @@ static inline int cpu_map_generic_redirect(struct bpf_cpu_map_entry *rcpu, return -EOPNOTSUPP; } -static inline bool cpu_map_prog_allowed(struct bpf_map *map) -{ - return false; -} - static inline struct bpf_prog *bpf_prog_get_type_path(const char *name, enum bpf_prog_type type) { @@ -1971,12 +2258,6 @@ static inline int bpf_prog_test_run_sk_lookup(struct bpf_prog *prog, return -ENOTSUPP; } -static inline bool bpf_prog_test_check_kfunc_call(u32 kfunc_id, - struct module *owner) -{ - return false; -} - static inline void bpf_map_put(struct bpf_map *map) { } @@ -1986,6 +2267,15 @@ static inline struct bpf_prog *bpf_prog_by_id(u32 id) return ERR_PTR(-ENOTSUPP); } +static inline int btf_struct_access(struct bpf_verifier_log *log, + const struct btf *btf, + const struct btf_type *t, int off, int size, + enum bpf_access_type atype, + u32 *next_btf_id, enum bpf_type_flag *flag) +{ + return -EACCES; +} + static inline const struct bpf_func_proto * bpf_base_func_proto(enum bpf_func_id func_id) { @@ -2007,6 +2297,20 @@ bpf_jit_find_kfunc_model(const struct bpf_prog *prog, { return NULL; } + +static inline bool unprivileged_ebpf_enabled(void) +{ + return false; +} + +static inline bool has_current_bpf_ctx(void) +{ + return false; +} + +static inline void bpf_prog_inc_misses_counter(struct bpf_prog *prog) +{ +} #endif /* CONFIG_BPF_SYSCALL */ void __bpf_free_used_btfs(struct bpf_prog_aux *aux, @@ -2049,6 +2353,8 @@ void bpf_offload_dev_netdev_unregister(struct bpf_offload_dev *offdev, struct net_device *netdev); bool bpf_offload_dev_match(struct bpf_prog *prog, struct net_device *netdev); +void unpriv_ebpf_notify(int new_state); + #if defined(CONFIG_NET) && defined(CONFIG_BPF_SYSCALL) int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr); @@ -2071,7 +2377,11 @@ int bpf_prog_test_run_syscall(struct bpf_prog *prog, int sock_map_get_from_fd(const union bpf_attr *attr, struct bpf_prog *prog); int sock_map_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype); int sock_map_update_elem_sys(struct bpf_map *map, void *key, void *value, u64 flags); +int sock_map_bpf_prog_query(const union bpf_attr *attr, + union bpf_attr __user *uattr); + void sock_map_unhash(struct sock *sk); +void sock_map_destroy(struct sock *sk); void sock_map_close(struct sock *sk, long timeout); #else static inline int bpf_prog_offload_init(struct bpf_prog *prog, @@ -2124,6 +2434,12 @@ static inline int sock_map_update_elem_sys(struct bpf_map *map, void *key, void { return -EOPNOTSUPP; } + +static inline int sock_map_bpf_prog_query(const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + return -EINVAL; +} #endif /* CONFIG_BPF_SYSCALL */ #endif /* CONFIG_NET && CONFIG_BPF_SYSCALL */ @@ -2161,6 +2477,7 @@ extern const struct bpf_func_proto bpf_map_delete_elem_proto; extern const struct bpf_func_proto bpf_map_push_elem_proto; extern const struct bpf_func_proto bpf_map_pop_elem_proto; extern const struct bpf_func_proto bpf_map_peek_elem_proto; +extern const struct bpf_func_proto bpf_map_lookup_percpu_elem_proto; extern const struct bpf_func_proto bpf_get_prandom_u32_proto; extern const struct bpf_func_proto bpf_get_smp_processor_id_proto; @@ -2168,6 +2485,7 @@ extern const struct bpf_func_proto bpf_get_numa_node_id_proto; extern const struct bpf_func_proto bpf_tail_call_proto; extern const struct bpf_func_proto bpf_ktime_get_ns_proto; extern const struct bpf_func_proto bpf_ktime_get_boot_ns_proto; +extern const struct bpf_func_proto bpf_ktime_get_tai_ns_proto; extern const struct bpf_func_proto bpf_get_current_pid_tgid_proto; extern const struct bpf_func_proto bpf_get_current_uid_gid_proto; extern const struct bpf_func_proto bpf_get_current_comm_proto; @@ -2180,6 +2498,7 @@ extern const struct bpf_func_proto bpf_sock_map_update_proto; extern const struct bpf_func_proto bpf_sock_hash_update_proto; extern const struct bpf_func_proto bpf_get_current_cgroup_id_proto; extern const struct bpf_func_proto bpf_get_current_ancestor_cgroup_id_proto; +extern const struct bpf_func_proto bpf_get_cgroup_classid_curr_proto; extern const struct bpf_func_proto bpf_msg_redirect_hash_proto; extern const struct bpf_func_proto bpf_msg_redirect_map_proto; extern const struct bpf_func_proto bpf_sk_redirect_hash_proto; @@ -2198,12 +2517,16 @@ extern const struct bpf_func_proto bpf_ringbuf_reserve_proto; extern const struct bpf_func_proto bpf_ringbuf_submit_proto; extern const struct bpf_func_proto bpf_ringbuf_discard_proto; extern const struct bpf_func_proto bpf_ringbuf_query_proto; +extern const struct bpf_func_proto bpf_ringbuf_reserve_dynptr_proto; +extern const struct bpf_func_proto bpf_ringbuf_submit_dynptr_proto; +extern const struct bpf_func_proto bpf_ringbuf_discard_dynptr_proto; extern const struct bpf_func_proto bpf_skc_to_tcp6_sock_proto; extern const struct bpf_func_proto bpf_skc_to_tcp_sock_proto; extern const struct bpf_func_proto bpf_skc_to_tcp_timewait_sock_proto; extern const struct bpf_func_proto bpf_skc_to_tcp_request_sock_proto; extern const struct bpf_func_proto bpf_skc_to_udp6_sock_proto; extern const struct bpf_func_proto bpf_skc_to_unix_sock_proto; +extern const struct bpf_func_proto bpf_skc_to_mptcp_sock_proto; extern const struct bpf_func_proto bpf_copy_from_user_proto; extern const struct bpf_func_proto bpf_snprintf_btf_proto; extern const struct bpf_func_proto bpf_snprintf_proto; @@ -2218,10 +2541,14 @@ extern const struct bpf_func_proto bpf_for_each_map_elem_proto; extern const struct bpf_func_proto bpf_btf_find_by_name_kind_proto; extern const struct bpf_func_proto bpf_sk_setsockopt_proto; extern const struct bpf_func_proto bpf_sk_getsockopt_proto; -extern const struct bpf_func_proto bpf_kallsyms_lookup_name_proto; +extern const struct bpf_func_proto bpf_unlocked_sk_setsockopt_proto; +extern const struct bpf_func_proto bpf_unlocked_sk_getsockopt_proto; extern const struct bpf_func_proto bpf_find_vma_proto; extern const struct bpf_func_proto bpf_loop_proto; -extern const struct bpf_func_proto bpf_strncmp_proto; +extern const struct bpf_func_proto bpf_copy_from_user_task_proto; +extern const struct bpf_func_proto bpf_set_retval_proto; +extern const struct bpf_func_proto bpf_get_retval_proto; +extern const struct bpf_func_proto bpf_user_ringbuf_drain_proto; const struct bpf_func_proto *tracing_prog_func_proto( enum bpf_func_id func_id, const struct bpf_prog *prog); @@ -2334,6 +2661,9 @@ enum bpf_text_poke_type { int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t, void *addr1, void *addr2); +void *bpf_arch_text_copy(void *dst, void *src, size_t len); +int bpf_arch_text_invalidate(void *dst, size_t len); + struct btf_id_set; bool btf_id_set_contains(const struct btf_id_set *set, u32 id); @@ -2343,4 +2673,50 @@ int bpf_bprintf_prepare(char *fmt, u32 fmt_size, const u64 *raw_args, u32 **bin_buf, u32 num_args); void bpf_bprintf_cleanup(void); +/* the implementation of the opaque uapi struct bpf_dynptr */ +struct bpf_dynptr_kern { + void *data; + /* Size represents the number of usable bytes of dynptr data. + * If for example the offset is at 4 for a local dynptr whose data is + * of type u64, the number of usable bytes is 4. + * + * The upper 8 bits are reserved. It is as follows: + * Bits 0 - 23 = size + * Bits 24 - 30 = dynptr type + * Bit 31 = whether dynptr is read-only + */ + u32 size; + u32 offset; +} __aligned(8); + +enum bpf_dynptr_type { + BPF_DYNPTR_TYPE_INVALID, + /* Points to memory that is local to the bpf program */ + BPF_DYNPTR_TYPE_LOCAL, + /* Underlying data is a kernel-produced ringbuf record */ + BPF_DYNPTR_TYPE_RINGBUF, +}; + +void bpf_dynptr_init(struct bpf_dynptr_kern *ptr, void *data, + enum bpf_dynptr_type type, u32 offset, u32 size); +void bpf_dynptr_set_null(struct bpf_dynptr_kern *ptr); +int bpf_dynptr_check_size(u32 size); +u32 bpf_dynptr_get_size(struct bpf_dynptr_kern *ptr); + +#ifdef CONFIG_BPF_LSM +void bpf_cgroup_atype_get(u32 attach_btf_id, int cgroup_atype); +void bpf_cgroup_atype_put(int cgroup_atype); +#else +static inline void bpf_cgroup_atype_get(u32 attach_btf_id, int cgroup_atype) {} +static inline void bpf_cgroup_atype_put(int cgroup_atype) {} +#endif /* CONFIG_BPF_LSM */ + +struct key; + +#ifdef CONFIG_KEYS +struct bpf_key { + struct key *key; + bool has_ref; +}; +#endif /* CONFIG_KEYS */ #endif /* _LINUX_BPF_H */ diff --git a/include/linux/bpf_local_storage.h b/include/linux/bpf_local_storage.h index 37b3906af8b1..7ea18d4da84b 100644 --- a/include/linux/bpf_local_storage.h +++ b/include/linux/bpf_local_storage.h @@ -143,9 +143,9 @@ void bpf_selem_link_storage_nolock(struct bpf_local_storage *local_storage, bool bpf_selem_unlink_storage_nolock(struct bpf_local_storage *local_storage, struct bpf_local_storage_elem *selem, - bool uncharge_omem); + bool uncharge_omem, bool use_trace_rcu); -void bpf_selem_unlink(struct bpf_local_storage_elem *selem); +void bpf_selem_unlink(struct bpf_local_storage_elem *selem, bool use_trace_rcu); void bpf_selem_link_map(struct bpf_local_storage_map *smap, struct bpf_local_storage_elem *selem); @@ -154,16 +154,17 @@ void bpf_selem_unlink_map(struct bpf_local_storage_elem *selem); struct bpf_local_storage_elem * bpf_selem_alloc(struct bpf_local_storage_map *smap, void *owner, void *value, - bool charge_mem); + bool charge_mem, gfp_t gfp_flags); int bpf_local_storage_alloc(void *owner, struct bpf_local_storage_map *smap, - struct bpf_local_storage_elem *first_selem); + struct bpf_local_storage_elem *first_selem, + gfp_t gfp_flags); struct bpf_local_storage_data * bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap, - void *value, u64 map_flags); + void *value, u64 map_flags, gfp_t gfp_flags); void bpf_local_storage_free_rcu(struct rcu_head *rcu); diff --git a/include/linux/bpf_lsm.h b/include/linux/bpf_lsm.h index 479c101546ad..4bcf76a9bb06 100644 --- a/include/linux/bpf_lsm.h +++ b/include/linux/bpf_lsm.h @@ -42,6 +42,8 @@ extern const struct bpf_func_proto bpf_inode_storage_get_proto; extern const struct bpf_func_proto bpf_inode_storage_delete_proto; void bpf_inode_storage_free(struct inode *inode); +void bpf_lsm_find_cgroup_shim(const struct bpf_prog *prog, bpf_func_t *bpf_func); + #else /* !CONFIG_BPF_LSM */ static inline bool bpf_lsm_is_sleepable_hook(u32 btf_id) @@ -65,6 +67,11 @@ static inline void bpf_inode_storage_free(struct inode *inode) { } +static inline void bpf_lsm_find_cgroup_shim(const struct bpf_prog *prog, + bpf_func_t *bpf_func) +{ +} + #endif /* CONFIG_BPF_LSM */ #endif /* _LINUX_BPF_LSM_H */ diff --git a/include/linux/bpf_mem_alloc.h b/include/linux/bpf_mem_alloc.h new file mode 100644 index 000000000000..3e164b8efaa9 --- /dev/null +++ b/include/linux/bpf_mem_alloc.h @@ -0,0 +1,28 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */ +#ifndef _BPF_MEM_ALLOC_H +#define _BPF_MEM_ALLOC_H +#include <linux/compiler_types.h> +#include <linux/workqueue.h> + +struct bpf_mem_cache; +struct bpf_mem_caches; + +struct bpf_mem_alloc { + struct bpf_mem_caches __percpu *caches; + struct bpf_mem_cache __percpu *cache; + struct work_struct work; +}; + +int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu); +void bpf_mem_alloc_destroy(struct bpf_mem_alloc *ma); + +/* kmalloc/kfree equivalent: */ +void *bpf_mem_alloc(struct bpf_mem_alloc *ma, size_t size); +void bpf_mem_free(struct bpf_mem_alloc *ma, void *ptr); + +/* kmem_cache_alloc/free equivalent: */ +void *bpf_mem_cache_alloc(struct bpf_mem_alloc *ma); +void bpf_mem_cache_free(struct bpf_mem_alloc *ma, void *ptr); + +#endif /* _BPF_MEM_ALLOC_H */ diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index 48a91c51c015..2c6a4f2562a7 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -126,6 +126,7 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_STRUCT_OPS, bpf_struct_ops_map_ops) #endif BPF_MAP_TYPE(BPF_MAP_TYPE_RINGBUF, ringbuf_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_BLOOM_FILTER, bloom_filter_map_ops) +BPF_MAP_TYPE(BPF_MAP_TYPE_USER_RINGBUF, user_ringbuf_map_ops) BPF_LINK_TYPE(BPF_LINK_TYPE_RAW_TRACEPOINT, raw_tracepoint) BPF_LINK_TYPE(BPF_LINK_TYPE_TRACING, tracing) @@ -140,3 +141,5 @@ BPF_LINK_TYPE(BPF_LINK_TYPE_XDP, xdp) #ifdef CONFIG_PERF_EVENTS BPF_LINK_TYPE(BPF_LINK_TYPE_PERF_EVENT, perf) #endif +BPF_LINK_TYPE(BPF_LINK_TYPE_KPROBE_MULTI, kprobe_multi) +BPF_LINK_TYPE(BPF_LINK_TYPE_STRUCT_OPS, struct_ops) diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 143401d4c9d9..9e1e6965f407 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -72,6 +72,18 @@ struct bpf_reg_state { u32 mem_size; /* for PTR_TO_MEM | PTR_TO_MEM_OR_NULL */ + /* For dynptr stack slots */ + struct { + enum bpf_dynptr_type type; + /* A dynptr is 16 bytes so it takes up 2 stack slots. + * We need to track which slot is the first slot + * to protect against cases where the user may try to + * pass in an address starting at the second slot of the + * dynptr. + */ + bool first_slot; + } dynptr; + /* Max size from any of the above. */ struct { unsigned long raw1; @@ -88,6 +100,8 @@ struct bpf_reg_state { * for the purpose of tracking that it's freed. * For PTR_TO_SOCKET this is used to share which pointers retain the * same reference to the socket, to determine proper reference freeing. + * For stack slots that are dynptrs, this is used to track references to + * the dynptr to determine proper reference freeing. */ u32 id; /* PTR_TO_SOCKET and PTR_TO_TCP_SOCK could be a ptr returned @@ -174,9 +188,15 @@ enum bpf_stack_slot_type { STACK_SPILL, /* register spilled into stack */ STACK_MISC, /* BPF program wrote some data into this slot */ STACK_ZERO, /* BPF program wrote constant zero */ + /* A dynptr is stored in this stack slot. The type of dynptr + * is stored in bpf_stack_state->spilled_ptr.dynptr.type + */ + STACK_DYNPTR, }; #define BPF_REG_SIZE 8 /* size of eBPF register in bytes */ +#define BPF_DYNPTR_SIZE sizeof(struct bpf_dynptr_kern) +#define BPF_DYNPTR_NR_SLOTS (BPF_DYNPTR_SIZE / BPF_REG_SIZE) struct bpf_stack_state { struct bpf_reg_state spilled_ptr; @@ -192,6 +212,17 @@ struct bpf_reference_state { * is used purely to inform the user of a reference leak. */ int insn_idx; + /* There can be a case like: + * main (frame 0) + * cb (frame 1) + * func (frame 3) + * cb (frame 4) + * Hence for frame 4, if callback_ref just stored boolean, it would be + * impossible to distinguish nested callback refs. Hence store the + * frameno and compare that to callback_ref in check_reference_leak when + * exiting a callback function. + */ + int callback_ref; }; /* state of the program: @@ -217,6 +248,7 @@ struct bpf_func_state { */ u32 async_entry_cnt; bool in_callback_fn; + struct tnum callback_ret_range; bool in_async_callback_fn; /* The following fields should be last. See copy_func_state() */ @@ -279,7 +311,7 @@ struct bpf_verifier_state { * If is_state_visited() sees a state with branches > 0 it means * there is a loop. If such state is exactly equal to the current state * it's an infinite loop. Note states_equal() checks for states - * equvalency, so two states being 'states_equal' does not mean + * equivalency, so two states being 'states_equal' does not mean * infinite loop. The exact comparison is provided by * states_maybe_looping() function. It's a stronger pre-check and * much faster than states_equal(). @@ -317,6 +349,27 @@ struct bpf_verifier_state { iter < frame->allocated_stack / BPF_REG_SIZE; \ iter++, reg = bpf_get_spilled_reg(iter, frame)) +/* Invoke __expr over regsiters in __vst, setting __state and __reg */ +#define bpf_for_each_reg_in_vstate(__vst, __state, __reg, __expr) \ + ({ \ + struct bpf_verifier_state *___vstate = __vst; \ + int ___i, ___j; \ + for (___i = 0; ___i <= ___vstate->curframe; ___i++) { \ + struct bpf_reg_state *___regs; \ + __state = ___vstate->frame[___i]; \ + ___regs = __state->regs; \ + for (___j = 0; ___j < MAX_BPF_REG; ___j++) { \ + __reg = &___regs[___j]; \ + (void)(__expr); \ + } \ + bpf_for_each_spilled_reg(___j, __state, __reg) { \ + if (!__reg) \ + continue; \ + (void)(__expr); \ + } \ + } \ + }) + /* linked list of verifier states used to prune search */ struct bpf_verifier_state_list { struct bpf_verifier_state state; @@ -324,6 +377,14 @@ struct bpf_verifier_state_list { int miss_cnt, hit_cnt; }; +struct bpf_loop_inline_state { + unsigned int initialized:1; /* set to true upon first entry */ + unsigned int fit_for_inline:1; /* true if callback function is the same + * at each call and flags are always zero + */ + u32 callback_subprogno; /* valid when fit_for_inline is true */ +}; + /* Possible states for alu_state member. */ #define BPF_ALU_SANITIZE_SRC (1U << 0) #define BPF_ALU_SANITIZE_DST (1U << 1) @@ -353,6 +414,10 @@ struct bpf_insn_aux_data { u32 mem_size; /* mem_size for non-struct typed var */ }; } btf_var; + /* if instruction is a call to bpf_loop this field tracks + * the state of the relevant registers to make decision about inlining + */ + struct bpf_loop_inline_state loop_inline_state; }; u64 map_key_state; /* constant (32 bit) key tracking for maps */ int ctx_field_size; /* the ctx field size for load insn, maybe 0 */ @@ -519,10 +584,20 @@ bpf_prog_offload_replace_insn(struct bpf_verifier_env *env, u32 off, void bpf_prog_offload_remove_insns(struct bpf_verifier_env *env, u32 off, u32 cnt); -int check_ctx_reg(struct bpf_verifier_env *env, - const struct bpf_reg_state *reg, int regno); +int check_ptr_off_reg(struct bpf_verifier_env *env, + const struct bpf_reg_state *reg, int regno); +int check_func_arg_reg_off(struct bpf_verifier_env *env, + const struct bpf_reg_state *reg, int regno, + enum bpf_arg_type arg_type); +int check_kfunc_mem_size_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, + u32 regno); int check_mem_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, u32 regno, u32 mem_size); +bool is_dynptr_reg_valid_init(struct bpf_verifier_env *env, + struct bpf_reg_state *reg); +bool is_dynptr_type_expected(struct bpf_verifier_env *env, + struct bpf_reg_state *reg, + enum bpf_arg_type arg_type); /* this lives here instead of in bpf.h because it needs to dereference tgt_prog */ static inline u64 bpf_trampoline_compute_key(const struct bpf_prog *tgt_prog, @@ -550,6 +625,8 @@ int bpf_check_attach_target(struct bpf_verifier_log *log, struct bpf_attach_target_info *tgt_info); void bpf_free_kfunc_btf_tab(struct bpf_kfunc_btf_tab *tab); +int mark_chain_precision(struct bpf_verifier_env *env, int regno); + #define BPF_BASE_TYPE_MASK GENMASK(BPF_BASE_TYPE_BITS - 1, 0) /* extract base type from bpf_{arg, return, reg}_type. */ @@ -564,4 +641,11 @@ static inline u32 type_flag(u32 type) return type & ~BPF_BASE_TYPE_MASK; } +/* only use after check_attach_btf_id() */ +static inline enum bpf_prog_type resolve_prog_type(struct bpf_prog *prog) +{ + return prog->type == BPF_PROG_TYPE_EXT ? + prog->aux->dst_prog->type : prog->type; +} + #endif /* _LINUX_BPF_VERIFIER_H */ diff --git a/include/linux/bpfptr.h b/include/linux/bpfptr.h index 46e1757d06a3..79b2f78eec1a 100644 --- a/include/linux/bpfptr.h +++ b/include/linux/bpfptr.h @@ -49,7 +49,9 @@ static inline void bpfptr_add(bpfptr_t *bpfptr, size_t val) static inline int copy_from_bpfptr_offset(void *dst, bpfptr_t src, size_t offset, size_t size) { - return copy_from_sockptr_offset(dst, (sockptr_t) src, offset, size); + if (!bpfptr_is_kernel(src)) + return copy_from_user(dst, src.user + offset, size); + return copy_from_kernel_nofault(dst, src.kernel + offset, size); } static inline int copy_from_bpfptr(void *dst, bpfptr_t src, size_t size) @@ -78,7 +80,9 @@ static inline void *kvmemdup_bpfptr(bpfptr_t src, size_t len) static inline long strncpy_from_bpfptr(char *dst, bpfptr_t src, size_t count) { - return strncpy_from_sockptr(dst, (sockptr_t) src, count); + if (bpfptr_is_kernel(src)) + return strncpy_from_kernel_nofault(dst, src.kernel, count); + return strncpy_from_user(dst, src.user, count); } #endif /* _LINUX_BPFPTR_H */ diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index 747fad264033..9e77165f3ef6 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -16,6 +16,7 @@ #define PHY_ID_BCM5481 0x0143bca0 #define PHY_ID_BCM5395 0x0143bcf0 #define PHY_ID_BCM53125 0x03625f20 +#define PHY_ID_BCM53128 0x03625e10 #define PHY_ID_BCM54810 0x03625d00 #define PHY_ID_BCM54811 0x03625cc0 #define PHY_ID_BCM5482 0x0143bcb0 @@ -292,6 +293,7 @@ #define MII_BRCM_FET_SHDW_MC_FAME 0x4000 /* Force Auto MDIX enable */ #define MII_BRCM_FET_SHDW_AUXMODE4 0x1a /* Auxiliary mode 4 */ +#define MII_BRCM_FET_SHDW_AM4_STANDBY 0x0008 /* Standby enable */ #define MII_BRCM_FET_SHDW_AM4_LED_MASK 0x0003 #define MII_BRCM_FET_SHDW_AM4_LED_MODE1 0x0001 diff --git a/include/linux/bsg-lib.h b/include/linux/bsg-lib.h index 6b211323a489..9e97ced2896d 100644 --- a/include/linux/bsg-lib.h +++ b/include/linux/bsg-lib.h @@ -10,7 +10,6 @@ #define _BLK_BSG_ #include <linux/blkdev.h> -#include <scsi/scsi_request.h> struct bsg_job; struct request; diff --git a/include/linux/btf.h b/include/linux/btf.h index 0c74348cbc9d..f9aababc5d78 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -12,11 +12,73 @@ #define BTF_TYPE_EMIT(type) ((void)(type *)0) #define BTF_TYPE_EMIT_ENUM(enum_val) ((void)enum_val) +/* These need to be macros, as the expressions are used in assembler input */ +#define KF_ACQUIRE (1 << 0) /* kfunc is an acquire function */ +#define KF_RELEASE (1 << 1) /* kfunc is a release function */ +#define KF_RET_NULL (1 << 2) /* kfunc returns a pointer that may be NULL */ +#define KF_KPTR_GET (1 << 3) /* kfunc returns reference to a kptr */ +/* Trusted arguments are those which are meant to be referenced arguments with + * unchanged offset. It is used to enforce that pointers obtained from acquire + * kfuncs remain unmodified when being passed to helpers taking trusted args. + * + * Consider + * struct foo { + * int data; + * struct foo *next; + * }; + * + * struct bar { + * int data; + * struct foo f; + * }; + * + * struct foo *f = alloc_foo(); // Acquire kfunc + * struct bar *b = alloc_bar(); // Acquire kfunc + * + * If a kfunc set_foo_data() wants to operate only on the allocated object, it + * will set the KF_TRUSTED_ARGS flag, which will prevent unsafe usage like: + * + * set_foo_data(f, 42); // Allowed + * set_foo_data(f->next, 42); // Rejected, non-referenced pointer + * set_foo_data(&f->next, 42);// Rejected, referenced, but wrong type + * set_foo_data(&b->f, 42); // Rejected, referenced, but bad offset + * + * In the final case, usually for the purposes of type matching, it is deduced + * by looking at the type of the member at the offset, but due to the + * requirement of trusted argument, this deduction will be strict and not done + * for this case. + */ +#define KF_TRUSTED_ARGS (1 << 4) /* kfunc only takes trusted pointer arguments */ +#define KF_SLEEPABLE (1 << 5) /* kfunc may sleep */ +#define KF_DESTRUCTIVE (1 << 6) /* kfunc performs destructive actions */ + +/* + * Return the name of the passed struct, if exists, or halt the build if for + * example the structure gets renamed. In this way, developers have to revisit + * the code using that structure name, and update it accordingly. + */ +#define stringify_struct(x) \ + ({ BUILD_BUG_ON(sizeof(struct x) < 0); \ + __stringify(x); }) + struct btf; struct btf_member; struct btf_type; union bpf_attr; struct btf_show; +struct btf_id_set; + +struct btf_kfunc_id_set { + struct module *owner; + struct btf_id_set8 *set; +}; + +struct btf_id_dtor_kfunc { + u32 btf_id; + u32 kfunc_btf_id; +}; + +typedef void (*btf_dtor_kfunc_t)(void *); extern const struct file_operations btf_fops; @@ -101,6 +163,8 @@ bool btf_member_is_reg_int(const struct btf *btf, const struct btf_type *s, u32 expected_offset, u32 expected_size); int btf_find_spin_lock(const struct btf *btf, const struct btf_type *t); int btf_find_timer(const struct btf *btf, const struct btf_type *t); +struct bpf_map_value_off *btf_parse_kptrs(const struct btf *btf, + const struct btf_type *t); bool btf_type_is_void(const struct btf_type *t); s32 btf_find_by_name_kind(const struct btf *btf, const char *name, u8 kind); const struct btf_type *btf_type_skip_modifiers(const struct btf *btf, @@ -144,6 +208,19 @@ static inline bool btf_type_is_enum(const struct btf_type *t) return BTF_INFO_KIND(t->info) == BTF_KIND_ENUM; } +static inline bool btf_is_any_enum(const struct btf_type *t) +{ + return BTF_INFO_KIND(t->info) == BTF_KIND_ENUM || + BTF_INFO_KIND(t->info) == BTF_KIND_ENUM64; +} + +static inline bool btf_kind_core_compat(const struct btf_type *t1, + const struct btf_type *t2) +{ + return BTF_INFO_KIND(t1->info) == BTF_INFO_KIND(t2->info) || + (btf_is_any_enum(t1) && btf_is_any_enum(t2)); +} + static inline bool str_is_empty(const char *s) { return !s || !s[0]; @@ -159,6 +236,16 @@ static inline bool btf_is_enum(const struct btf_type *t) return btf_kind(t) == BTF_KIND_ENUM; } +static inline bool btf_is_enum64(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_ENUM64; +} + +static inline u64 btf_enum64_value(const struct btf_enum64 *e) +{ + return ((u64)e->val_hi32 << 32) | e->val_lo32; +} + static inline bool btf_is_composite(const struct btf_type *t) { u16 kind = btf_kind(t); @@ -216,6 +303,11 @@ static inline bool btf_type_is_var(const struct btf_type *t) return BTF_INFO_KIND(t->info) == BTF_KIND_VAR; } +static inline bool btf_type_is_type_tag(const struct btf_type *t) +{ + return BTF_INFO_KIND(t->info) == BTF_KIND_TYPE_TAG; +} + /* union is only a special case of struct: * all its offsetof(member) == 0 */ @@ -294,12 +386,22 @@ static inline struct btf_enum *btf_enum(const struct btf_type *t) return (struct btf_enum *)(t + 1); } +static inline struct btf_enum64 *btf_enum64(const struct btf_type *t) +{ + return (struct btf_enum64 *)(t + 1); +} + static inline const struct btf_var_secinfo *btf_type_var_secinfo( const struct btf_type *t) { return (const struct btf_var_secinfo *)(t + 1); } +static inline struct btf_param *btf_params(const struct btf_type *t) +{ + return (struct btf_param *)(t + 1); +} + #ifdef CONFIG_BPF_SYSCALL struct bpf_prog; @@ -307,6 +409,14 @@ const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id); const char *btf_name_by_offset(const struct btf *btf, u32 offset); struct btf *btf_parse_vmlinux(void); struct btf *bpf_prog_get_target_btf(const struct bpf_prog *prog); +u32 *btf_kfunc_id_set_contains(const struct btf *btf, + enum bpf_prog_type prog_type, + u32 kfunc_btf_id); +int register_btf_kfunc_id_set(enum bpf_prog_type prog_type, + const struct btf_kfunc_id_set *s); +s32 btf_find_dtor_kfunc(struct btf *btf, u32 btf_id); +int register_btf_id_dtor_kfuncs(const struct btf_id_dtor_kfunc *dtors, u32 add_cnt, + struct module *owner); #else static inline const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id) @@ -318,50 +428,36 @@ static inline const char *btf_name_by_offset(const struct btf *btf, { return NULL; } -#endif - -struct kfunc_btf_id_set { - struct list_head list; - struct btf_id_set *set; - struct module *owner; -}; - -struct kfunc_btf_id_list { - struct list_head list; - struct mutex mutex; -}; - -#ifdef CONFIG_DEBUG_INFO_BTF_MODULES -void register_kfunc_btf_id_set(struct kfunc_btf_id_list *l, - struct kfunc_btf_id_set *s); -void unregister_kfunc_btf_id_set(struct kfunc_btf_id_list *l, - struct kfunc_btf_id_set *s); -bool bpf_check_mod_kfunc_call(struct kfunc_btf_id_list *klist, u32 kfunc_id, - struct module *owner); - -extern struct kfunc_btf_id_list bpf_tcp_ca_kfunc_list; -extern struct kfunc_btf_id_list prog_test_kfunc_list; -#else -static inline void register_kfunc_btf_id_set(struct kfunc_btf_id_list *l, - struct kfunc_btf_id_set *s) +static inline u32 *btf_kfunc_id_set_contains(const struct btf *btf, + enum bpf_prog_type prog_type, + u32 kfunc_btf_id) { + return NULL; } -static inline void unregister_kfunc_btf_id_set(struct kfunc_btf_id_list *l, - struct kfunc_btf_id_set *s) +static inline int register_btf_kfunc_id_set(enum bpf_prog_type prog_type, + const struct btf_kfunc_id_set *s) { + return 0; } -static inline bool bpf_check_mod_kfunc_call(struct kfunc_btf_id_list *klist, - u32 kfunc_id, struct module *owner) +static inline s32 btf_find_dtor_kfunc(struct btf *btf, u32 btf_id) { - return false; + return -ENOENT; +} +static inline int register_btf_id_dtor_kfuncs(const struct btf_id_dtor_kfunc *dtors, + u32 add_cnt, struct module *owner) +{ + return 0; } - -static struct kfunc_btf_id_list bpf_tcp_ca_kfunc_list __maybe_unused; -static struct kfunc_btf_id_list prog_test_kfunc_list __maybe_unused; #endif -#define DEFINE_KFUNC_BTF_ID_SET(set, name) \ - struct kfunc_btf_id_set name = { LIST_HEAD_INIT(name.list), (set), \ - THIS_MODULE } +static inline bool btf_type_is_struct_ptr(struct btf *btf, const struct btf_type *t) +{ + if (!btf_type_is_ptr(t)) + return false; + + t = btf_type_skip_modifiers(btf, t->type, NULL); + + return btf_type_is_struct(t); +} #endif diff --git a/include/linux/btf_ids.h b/include/linux/btf_ids.h index 919c0fde1c51..2aea877d644f 100644 --- a/include/linux/btf_ids.h +++ b/include/linux/btf_ids.h @@ -8,9 +8,19 @@ struct btf_id_set { u32 ids[]; }; +struct btf_id_set8 { + u32 cnt; + u32 flags; + struct { + u32 id; + u32 flags; + } pairs[]; +}; + #ifdef CONFIG_DEBUG_INFO_BTF #include <linux/compiler.h> /* for __PASTE */ +#include <linux/compiler_attributes.h> /* for __maybe_unused */ /* * Following macros help to define lists of BTF IDs placed @@ -24,7 +34,7 @@ struct btf_id_set { #define BTF_IDS_SECTION ".BTF_ids" -#define ____BTF_ID(symbol) \ +#define ____BTF_ID(symbol, word) \ asm( \ ".pushsection " BTF_IDS_SECTION ",\"a\"; \n" \ ".local " #symbol " ; \n" \ @@ -32,10 +42,11 @@ asm( \ ".size " #symbol ", 4; \n" \ #symbol ": \n" \ ".zero 4 \n" \ +word \ ".popsection; \n"); -#define __BTF_ID(symbol) \ - ____BTF_ID(symbol) +#define __BTF_ID(symbol, word) \ + ____BTF_ID(symbol, word) #define __ID(prefix) \ __PASTE(prefix, __COUNTER__) @@ -45,7 +56,14 @@ asm( \ * to 4 zero bytes. */ #define BTF_ID(prefix, name) \ - __BTF_ID(__ID(__BTF_ID__##prefix##__##name##__)) + __BTF_ID(__ID(__BTF_ID__##prefix##__##name##__), "") + +#define ____BTF_ID_FLAGS(prefix, name, flags) \ + __BTF_ID(__ID(__BTF_ID__##prefix##__##name##__), ".long " #flags "\n") +#define __BTF_ID_FLAGS(prefix, name, flags, ...) \ + ____BTF_ID_FLAGS(prefix, name, flags) +#define BTF_ID_FLAGS(prefix, name, ...) \ + __BTF_ID_FLAGS(prefix, name, ##__VA_ARGS__, 0) /* * The BTF_ID_LIST macro defines pure (unsorted) list @@ -144,17 +162,60 @@ asm( \ ".popsection; \n"); \ extern struct btf_id_set name; +/* + * The BTF_SET8_START/END macros pair defines sorted list of + * BTF IDs and their flags plus its members count, with the + * following layout: + * + * BTF_SET8_START(list) + * BTF_ID_FLAGS(type1, name1, flags) + * BTF_ID_FLAGS(type2, name2, flags) + * BTF_SET8_END(list) + * + * __BTF_ID__set8__list: + * .zero 8 + * list: + * __BTF_ID__type1__name1__3: + * .zero 4 + * .word (1 << 0) | (1 << 2) + * __BTF_ID__type2__name2__5: + * .zero 4 + * .word (1 << 3) | (1 << 1) | (1 << 2) + * + */ +#define __BTF_SET8_START(name, scope) \ +asm( \ +".pushsection " BTF_IDS_SECTION ",\"a\"; \n" \ +"." #scope " __BTF_ID__set8__" #name "; \n" \ +"__BTF_ID__set8__" #name ":; \n" \ +".zero 8 \n" \ +".popsection; \n"); + +#define BTF_SET8_START(name) \ +__BTF_ID_LIST(name, local) \ +__BTF_SET8_START(name, local) + +#define BTF_SET8_END(name) \ +asm( \ +".pushsection " BTF_IDS_SECTION ",\"a\"; \n" \ +".size __BTF_ID__set8__" #name ", .-" #name " \n" \ +".popsection; \n"); \ +extern struct btf_id_set8 name; + #else -#define BTF_ID_LIST(name) static u32 name[5]; +#define BTF_ID_LIST(name) static u32 __maybe_unused name[5]; #define BTF_ID(prefix, name) +#define BTF_ID_FLAGS(prefix, name, ...) #define BTF_ID_UNUSED -#define BTF_ID_LIST_GLOBAL(name, n) u32 name[n]; -#define BTF_ID_LIST_SINGLE(name, prefix, typename) static u32 name[1]; -#define BTF_ID_LIST_GLOBAL_SINGLE(name, prefix, typename) u32 name[1]; -#define BTF_SET_START(name) static struct btf_id_set name = { 0 }; -#define BTF_SET_START_GLOBAL(name) static struct btf_id_set name = { 0 }; +#define BTF_ID_LIST_GLOBAL(name, n) u32 __maybe_unused name[n]; +#define BTF_ID_LIST_SINGLE(name, prefix, typename) static u32 __maybe_unused name[1]; +#define BTF_ID_LIST_GLOBAL_SINGLE(name, prefix, typename) u32 __maybe_unused name[1]; +#define BTF_SET_START(name) static struct btf_id_set __maybe_unused name = { 0 }; +#define BTF_SET_START_GLOBAL(name) static struct btf_id_set __maybe_unused name = { 0 }; #define BTF_SET_END(name) +#define BTF_SET8_START(name) static struct btf_id_set8 __maybe_unused name = { 0 }; +#define BTF_SET8_END(name) #endif /* CONFIG_DEBUG_INFO_BTF */ @@ -177,7 +238,9 @@ extern struct btf_id_set name; BTF_SOCK_TYPE(BTF_SOCK_TYPE_TCP6, tcp6_sock) \ BTF_SOCK_TYPE(BTF_SOCK_TYPE_UDP, udp_sock) \ BTF_SOCK_TYPE(BTF_SOCK_TYPE_UDP6, udp6_sock) \ - BTF_SOCK_TYPE(BTF_SOCK_TYPE_UNIX, unix_sock) + BTF_SOCK_TYPE(BTF_SOCK_TYPE_UNIX, unix_sock) \ + BTF_SOCK_TYPE(BTF_SOCK_TYPE_MPTCP, mptcp_sock) \ + BTF_SOCK_TYPE(BTF_SOCK_TYPE_SOCKET, socket) enum { #define BTF_SOCK_TYPE(name, str) name, diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 36f33685c8c0..33fa5e94aa80 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -9,6 +9,7 @@ #define _LINUX_BUFFER_HEAD_H #include <linux/types.h> +#include <linux/blk_types.h> #include <linux/fs.h> #include <linux/linkage.h> #include <linux/pagemap.h> @@ -117,7 +118,6 @@ static __always_inline int test_clear_buffer_##name(struct buffer_head *bh) \ * of the form "mark_buffer_foo()". These are higher-level functions which * do something in addition to setting a b_state bit. */ -BUFFER_FNS(Uptodate, uptodate) BUFFER_FNS(Dirty, dirty) TAS_BUFFER_FNS(Dirty, dirty) BUFFER_FNS(Lock, locked) @@ -135,6 +135,41 @@ BUFFER_FNS(Meta, meta) BUFFER_FNS(Prio, prio) BUFFER_FNS(Defer_Completion, defer_completion) +static __always_inline void set_buffer_uptodate(struct buffer_head *bh) +{ + /* + * If somebody else already set this uptodate, they will + * have done the memory barrier, and a reader will thus + * see *some* valid buffer state. + * + * Any other serialization (with IO errors or whatever that + * might clear the bit) has to come from other state (eg BH_Lock). + */ + if (test_bit(BH_Uptodate, &bh->b_state)) + return; + + /* + * make it consistent with folio_mark_uptodate + * pairs with smp_load_acquire in buffer_uptodate + */ + smp_mb__before_atomic(); + set_bit(BH_Uptodate, &bh->b_state); +} + +static __always_inline void clear_buffer_uptodate(struct buffer_head *bh) +{ + clear_bit(BH_Uptodate, &bh->b_state); +} + +static __always_inline int buffer_uptodate(const struct buffer_head *bh) +{ + /* + * make it consistent with folio_test_uptodate + * pairs with smp_mb__before_atomic in set_buffer_uptodate + */ + return test_bit_acquire(BH_Uptodate, &bh->b_state); +} + #define bh_offset(bh) ((unsigned long)(bh)->b_data & ~PAGE_MASK) /* If we *know* page->private refers to buffer_heads */ @@ -144,8 +179,9 @@ BUFFER_FNS(Defer_Completion, defer_completion) ((struct buffer_head *)page_private(page)); \ }) #define page_has_buffers(page) PagePrivate(page) +#define folio_buffers(folio) folio_get_private(folio) -void buffer_check_dirty_writeback(struct page *page, +void buffer_check_dirty_writeback(struct folio *folio, bool *dirty, bool *writeback); /* @@ -157,7 +193,7 @@ void mark_buffer_write_io_error(struct buffer_head *bh); void touch_buffer(struct buffer_head *bh); void set_bh_page(struct buffer_head *bh, struct page *page, unsigned long offset); -int try_to_free_buffers(struct page *); +bool try_to_free_buffers(struct folio *); struct buffer_head *alloc_page_buffers(struct page *page, unsigned long size, bool retry); void create_empty_buffers(struct page *, unsigned long, @@ -189,8 +225,6 @@ struct buffer_head *__getblk_gfp(struct block_device *bdev, sector_t block, void __brelse(struct buffer_head *); void __bforget(struct buffer_head *); void __breadahead(struct block_device *, sector_t block, unsigned int size); -void __breadahead_gfp(struct block_device *, sector_t block, unsigned int size, - gfp_t gfp); struct buffer_head *__bread_gfp(struct block_device *, sector_t block, unsigned size, gfp_t gfp); void invalidate_bh_lrus(void); @@ -200,15 +234,16 @@ struct buffer_head *alloc_buffer_head(gfp_t gfp_flags); void free_buffer_head(struct buffer_head * bh); void unlock_buffer(struct buffer_head *bh); void __lock_buffer(struct buffer_head *bh); -void ll_rw_block(int, int, int, struct buffer_head * bh[]); int sync_dirty_buffer(struct buffer_head *bh); -int __sync_dirty_buffer(struct buffer_head *bh, int op_flags); -void write_dirty_buffer(struct buffer_head *bh, int op_flags); -int submit_bh(int, int, struct buffer_head *); +int __sync_dirty_buffer(struct buffer_head *bh, blk_opf_t op_flags); +void write_dirty_buffer(struct buffer_head *bh, blk_opf_t op_flags); +void submit_bh(blk_opf_t, struct buffer_head *); void write_boundary_block(struct block_device *bdev, sector_t bblock, unsigned blocksize); int bh_uptodate_or_lock(struct buffer_head *bh); -int bh_submit_read(struct buffer_head *bh); +int __bh_read(struct buffer_head *bh, blk_opf_t op_flags, bool wait); +void __bh_read_batch(int nr, struct buffer_head *bhs[], + blk_opf_t op_flags, bool force_lock); extern int buffer_heads_over_limit; @@ -216,18 +251,16 @@ extern int buffer_heads_over_limit; * Generic address_space_operations implementations for buffer_head-backed * address_spaces. */ -void block_invalidatepage(struct page *page, unsigned int offset, - unsigned int length); +void block_invalidate_folio(struct folio *folio, size_t offset, size_t length); int block_write_full_page(struct page *page, get_block_t *get_block, struct writeback_control *wbc); int __block_write_full_page(struct inode *inode, struct page *page, get_block_t *get_block, struct writeback_control *wbc, bh_end_io_t *handler); -int block_read_full_page(struct page*, get_block_t*); -int block_is_partially_uptodate(struct page *page, unsigned long from, - unsigned long count); +int block_read_full_folio(struct folio *, get_block_t *); +bool block_is_partially_uptodate(struct folio *, size_t from, size_t count); int block_write_begin(struct address_space *mapping, loff_t pos, unsigned len, - unsigned flags, struct page **pagep, get_block_t *get_block); + struct page **pagep, get_block_t *get_block); int __block_write_begin(struct page *page, loff_t pos, unsigned len, get_block_t *get_block); int block_write_end(struct file *, struct address_space *, @@ -239,7 +272,7 @@ int generic_write_end(struct file *, struct address_space *, void page_zero_new_buffers(struct page *page, unsigned from, unsigned to); void clean_page_buffers(struct page *page); int cont_write_begin(struct file *, struct address_space *, loff_t, - unsigned, unsigned, struct page **, void **, + unsigned, struct page **, void **, get_block_t *, loff_t *); int generic_cont_expand_simple(struct inode *inode, loff_t size); int block_commit_write(struct page *page, unsigned from, unsigned to); @@ -259,14 +292,16 @@ static inline vm_fault_t block_page_mkwrite_return(int err) } sector_t generic_block_bmap(struct address_space *, sector_t, get_block_t *); int block_truncate_page(struct address_space *, loff_t, get_block_t *); -int nobh_write_begin(struct address_space *, loff_t, unsigned, unsigned, - struct page **, void **, get_block_t*); -int nobh_write_end(struct file *, struct address_space *, - loff_t, unsigned, unsigned, - struct page *, void *); -int nobh_truncate_page(struct address_space *, loff_t, get_block_t *); -int nobh_writepage(struct page *page, get_block_t *get_block, - struct writeback_control *wbc); + +#ifdef CONFIG_MIGRATION +extern int buffer_migrate_folio(struct address_space *, + struct folio *dst, struct folio *src, enum migrate_mode); +extern int buffer_migrate_folio_norefs(struct address_space *, + struct folio *dst, struct folio *src, enum migrate_mode); +#else +#define buffer_migrate_folio NULL +#define buffer_migrate_folio_norefs NULL +#endif void buffer_init(void); @@ -315,12 +350,6 @@ sb_breadahead(struct super_block *sb, sector_t block) __breadahead(sb->s_bdev, block, sb->s_blocksize); } -static inline void -sb_breadahead_unmovable(struct super_block *sb, sector_t block) -{ - __breadahead_gfp(sb->s_bdev, block, sb->s_blocksize, 0); -} - static inline struct buffer_head * sb_getblk(struct super_block *sb, sector_t block) { @@ -382,6 +411,41 @@ static inline struct buffer_head *__getblk(struct block_device *bdev, return __getblk_gfp(bdev, block, size, __GFP_MOVABLE); } +static inline void bh_readahead(struct buffer_head *bh, blk_opf_t op_flags) +{ + if (!buffer_uptodate(bh) && trylock_buffer(bh)) { + if (!buffer_uptodate(bh)) + __bh_read(bh, op_flags, false); + else + unlock_buffer(bh); + } +} + +static inline void bh_read_nowait(struct buffer_head *bh, blk_opf_t op_flags) +{ + if (!bh_uptodate_or_lock(bh)) + __bh_read(bh, op_flags, false); +} + +/* Returns 1 if buffer uptodated, 0 on success, and -EIO on error. */ +static inline int bh_read(struct buffer_head *bh, blk_opf_t op_flags) +{ + if (bh_uptodate_or_lock(bh)) + return 1; + return __bh_read(bh, op_flags, true); +} + +static inline void bh_read_batch(int nr, struct buffer_head *bhs[]) +{ + __bh_read_batch(nr, bhs, 0, true); +} + +static inline void bh_readahead_batch(int nr, struct buffer_head *bhs[], + blk_opf_t op_flags) +{ + __bh_read_batch(nr, bhs, op_flags, false); +} + /** * __bread() - reads a specified block and returns the bh * @bdev: the block_device to read from @@ -398,12 +462,12 @@ __bread(struct block_device *bdev, sector_t block, unsigned size) return __bread_gfp(bdev, block, size, __GFP_MOVABLE); } -extern int __set_page_dirty_buffers(struct page *page); +bool block_dirty_folio(struct address_space *mapping, struct folio *folio); #else /* CONFIG_BLOCK */ static inline void buffer_init(void) {} -static inline int try_to_free_buffers(struct page *page) { return 1; } +static inline bool try_to_free_buffers(struct folio *folio) { return true; } static inline int inode_has_buffers(struct inode *inode) { return 0; } static inline void invalidate_inode_buffers(struct inode *inode) {} static inline int remove_inode_buffers(struct inode *inode) { return 1; } diff --git a/include/linux/byteorder/generic.h b/include/linux/byteorder/generic.h index 4b13e0a3e15b..c9a4c96c9943 100644 --- a/include/linux/byteorder/generic.h +++ b/include/linux/byteorder/generic.h @@ -190,7 +190,7 @@ static inline void be64_add_cpu(__be64 *var, u64 val) static inline void cpu_to_be32_array(__be32 *dst, const u32 *src, size_t len) { - int i; + size_t i; for (i = 0; i < len; i++) dst[i] = cpu_to_be32(src[i]); @@ -198,7 +198,7 @@ static inline void cpu_to_be32_array(__be32 *dst, const u32 *src, size_t len) static inline void be32_to_cpu_array(u32 *dst, const __be32 *src, size_t len) { - int i; + size_t i; for (i = 0; i < len; i++) dst[i] = be32_to_cpu(src[i]); diff --git a/include/linux/cache.h b/include/linux/cache.h index d742c57eaee5..5da1bbd96154 100644 --- a/include/linux/cache.h +++ b/include/linux/cache.h @@ -85,4 +85,17 @@ #define cache_line_size() L1_CACHE_BYTES #endif +/* + * Helper to add padding within a struct to ensure data fall into separate + * cachelines. + */ +#if defined(CONFIG_SMP) +struct cacheline_padding { + char x[0]; +} ____cacheline_internodealigned_in_smp; +#define CACHELINE_PADDING(name) struct cacheline_padding name +#else +#define CACHELINE_PADDING(name) +#endif + #endif /* __LINUX_CACHE_H */ diff --git a/include/linux/cacheflush.h b/include/linux/cacheflush.h index fef8b607f97e..a6189d21f2ba 100644 --- a/include/linux/cacheflush.h +++ b/include/linux/cacheflush.h @@ -4,6 +4,8 @@ #include <asm/cacheflush.h> +struct folio; + #if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE #ifndef ARCH_IMPLEMENTS_FLUSH_DCACHE_FOLIO void flush_dcache_folio(struct folio *folio); diff --git a/include/linux/cacheinfo.h b/include/linux/cacheinfo.h index 4ff37cb763ae..00b7a6ae8617 100644 --- a/include/linux/cacheinfo.h +++ b/include/linux/cacheinfo.h @@ -82,6 +82,9 @@ struct cpu_cacheinfo *get_cpu_cacheinfo(unsigned int cpu); int init_cache_level(unsigned int cpu); int populate_cache_leaves(unsigned int cpu); int cache_setup_acpi(unsigned int cpu); +bool last_level_cache_is_valid(unsigned int cpu); +bool last_level_cache_is_shared(unsigned int cpu_x, unsigned int cpu_y); +int detect_cache_attributes(unsigned int cpu); #ifndef CONFIG_ACPI_PPTT /* * acpi_find_last_cache_level is only called on ACPI enabled diff --git a/include/linux/can/bittiming.h b/include/linux/can/bittiming.h index a81652d1c6f3..ef0a77173e3c 100644 --- a/include/linux/can/bittiming.h +++ b/include/linux/can/bittiming.h @@ -11,6 +11,8 @@ #define CAN_SYNC_SEG 1 +#define CAN_BITRATE_UNSET 0 +#define CAN_BITRATE_UNKNOWN (-1U) #define CAN_CTRLMODE_TDC_MASK \ (CAN_CTRLMODE_TDC_AUTO | CAN_CTRLMODE_TDC_MANUAL) @@ -113,7 +115,7 @@ struct can_tdc_const { }; #ifdef CONFIG_CAN_CALC_BITTIMING -int can_calc_bittiming(struct net_device *dev, struct can_bittiming *bt, +int can_calc_bittiming(const struct net_device *dev, struct can_bittiming *bt, const struct can_bittiming_const *btc); void can_calc_tdco(struct can_tdc *tdc, const struct can_tdc_const *tdc_const, @@ -121,7 +123,7 @@ void can_calc_tdco(struct can_tdc *tdc, const struct can_tdc_const *tdc_const, u32 *ctrlmode, u32 ctrlmode_supported); #else /* !CONFIG_CAN_CALC_BITTIMING */ static inline int -can_calc_bittiming(struct net_device *dev, struct can_bittiming *bt, +can_calc_bittiming(const struct net_device *dev, struct can_bittiming *bt, const struct can_bittiming_const *btc) { netdev_err(dev, "bit-timing calculation not available\n"); @@ -136,7 +138,7 @@ can_calc_tdco(struct can_tdc *tdc, const struct can_tdc_const *tdc_const, } #endif /* CONFIG_CAN_CALC_BITTIMING */ -int can_get_bittiming(struct net_device *dev, struct can_bittiming *bt, +int can_get_bittiming(const struct net_device *dev, struct can_bittiming *bt, const struct can_bittiming_const *btc, const u32 *bitrate_const, const unsigned int bitrate_const_cnt); diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h index c2ea47f30046..982ba245eb41 100644 --- a/include/linux/can/dev.h +++ b/include/linux/can/dev.h @@ -17,10 +17,10 @@ #include <linux/can.h> #include <linux/can/bittiming.h> #include <linux/can/error.h> -#include <linux/can/led.h> #include <linux/can/length.h> #include <linux/can/netlink.h> #include <linux/can/skb.h> +#include <linux/ethtool.h> #include <linux/netdevice.h> /* @@ -85,15 +85,6 @@ struct can_priv { int (*do_get_berr_counter)(const struct net_device *dev, struct can_berr_counter *bec); int (*do_get_auto_tdcv)(const struct net_device *dev, u32 *tdcv); - -#ifdef CONFIG_CAN_LEDS - struct led_trigger *tx_led_trig; - char tx_led_trig_name[CAN_LED_NAME_SZ]; - struct led_trigger *rx_led_trig; - char rx_led_trig_name[CAN_LED_NAME_SZ]; - struct led_trigger *rxtx_led_trig; - char rxtx_led_trig_name[CAN_LED_NAME_SZ]; -#endif }; static inline bool can_tdc_is_enabled(const struct can_priv *priv) @@ -156,6 +147,27 @@ static inline u32 can_get_static_ctrlmode(struct can_priv *priv) return priv->ctrlmode & ~priv->ctrlmode_supported; } +static inline bool can_is_canxl_dev_mtu(unsigned int mtu) +{ + return (mtu >= CANXL_MIN_MTU && mtu <= CANXL_MAX_MTU); +} + +/* drop skb if it does not contain a valid CAN frame for sending */ +static inline bool can_dev_dropped_skb(struct net_device *dev, struct sk_buff *skb) +{ + struct can_priv *priv = netdev_priv(dev); + + if (priv->ctrlmode & CAN_CTRLMODE_LISTENONLY) { + netdev_info_once(dev, + "interface in listen only mode, dropping skb\n"); + kfree_skb(skb); + dev->stats.tx_dropped++; + return true; + } + + return can_dropped_invalid_skb(dev, skb); +} + void can_setup(struct net_device *dev); struct net_device *alloc_candev_mqs(int sizeof_priv, unsigned int echo_skb_max, @@ -172,6 +184,9 @@ struct can_priv *safe_candev_priv(struct net_device *dev); int open_candev(struct net_device *dev); void close_candev(struct net_device *dev); int can_change_mtu(struct net_device *dev, int new_mtu); +int can_eth_ioctl_hwts(struct net_device *netdev, struct ifreq *ifr, int cmd); +int can_ethtool_op_get_ts_info_hwts(struct net_device *dev, + struct ethtool_ts_info *info); int register_candev(struct net_device *dev); void unregister_candev(struct net_device *dev); diff --git a/include/linux/can/led.h b/include/linux/can/led.h deleted file mode 100644 index 7c3cfd798c56..000000000000 --- a/include/linux/can/led.h +++ /dev/null @@ -1,51 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright 2012, Fabio Baltieri <fabio.baltieri@gmail.com> - */ - -#ifndef _CAN_LED_H -#define _CAN_LED_H - -#include <linux/if.h> -#include <linux/leds.h> -#include <linux/netdevice.h> - -enum can_led_event { - CAN_LED_EVENT_OPEN, - CAN_LED_EVENT_STOP, - CAN_LED_EVENT_TX, - CAN_LED_EVENT_RX, -}; - -#ifdef CONFIG_CAN_LEDS - -/* keep space for interface name + "-tx"/"-rx"/"-rxtx" - * suffix and null terminator - */ -#define CAN_LED_NAME_SZ (IFNAMSIZ + 6) - -void can_led_event(struct net_device *netdev, enum can_led_event event); -void devm_can_led_init(struct net_device *netdev); -int __init can_led_notifier_init(void); -void __exit can_led_notifier_exit(void); - -#else - -static inline void can_led_event(struct net_device *netdev, - enum can_led_event event) -{ -} -static inline void devm_can_led_init(struct net_device *netdev) -{ -} -static inline int can_led_notifier_init(void) -{ - return 0; -} -static inline void can_led_notifier_exit(void) -{ -} - -#endif - -#endif /* !_CAN_LED_H */ diff --git a/include/linux/can/rx-offload.h b/include/linux/can/rx-offload.h index c11477620403..c205c51d79c9 100644 --- a/include/linux/can/rx-offload.h +++ b/include/linux/can/rx-offload.h @@ -42,8 +42,8 @@ int can_rx_offload_add_manual(struct net_device *dev, int can_rx_offload_irq_offload_timestamp(struct can_rx_offload *offload, u64 reg); int can_rx_offload_irq_offload_fifo(struct can_rx_offload *offload); -int can_rx_offload_queue_sorted(struct can_rx_offload *offload, - struct sk_buff *skb, u32 timestamp); +int can_rx_offload_queue_timestamp(struct can_rx_offload *offload, + struct sk_buff *skb, u32 timestamp); unsigned int can_rx_offload_get_echo_skb(struct can_rx_offload *offload, unsigned int idx, u32 timestamp, unsigned int *frame_len_ptr); diff --git a/include/linux/can/skb.h b/include/linux/can/skb.h index fdb22b00674a..1abc25a8d144 100644 --- a/include/linux/can/skb.h +++ b/include/linux/can/skb.h @@ -20,7 +20,8 @@ void can_flush_echo_skb(struct net_device *dev); int can_put_echo_skb(struct sk_buff *skb, struct net_device *dev, unsigned int idx, unsigned int frame_len); struct sk_buff *__can_get_echo_skb(struct net_device *dev, unsigned int idx, - u8 *len_ptr, unsigned int *frame_len_ptr); + unsigned int *len_ptr, + unsigned int *frame_len_ptr); unsigned int __must_check can_get_echo_skb(struct net_device *dev, unsigned int idx, unsigned int *frame_len_ptr); @@ -29,8 +30,12 @@ void can_free_echo_skb(struct net_device *dev, unsigned int idx, struct sk_buff *alloc_can_skb(struct net_device *dev, struct can_frame **cf); struct sk_buff *alloc_canfd_skb(struct net_device *dev, struct canfd_frame **cfd); +struct sk_buff *alloc_canxl_skb(struct net_device *dev, + struct canxl_frame **cxl, + unsigned int data_len); struct sk_buff *alloc_can_err_skb(struct net_device *dev, struct can_frame **cf); +bool can_dropped_invalid_skb(struct net_device *dev, struct sk_buff *skb); /* * The struct can_skb_priv is used to transport additional information along @@ -96,68 +101,59 @@ static inline struct sk_buff *can_create_echo_skb(struct sk_buff *skb) return nskb; } -/* Check for outgoing skbs that have not been created by the CAN subsystem */ -static inline bool can_skb_headroom_valid(struct net_device *dev, - struct sk_buff *skb) +static inline bool can_is_can_skb(const struct sk_buff *skb) { - /* af_packet creates a headroom of HH_DATA_MOD bytes which is fine */ - if (WARN_ON_ONCE(skb_headroom(skb) < sizeof(struct can_skb_priv))) - return false; + struct can_frame *cf = (struct can_frame *)skb->data; - /* af_packet does not apply CAN skb specific settings */ - if (skb->ip_summed == CHECKSUM_NONE) { - /* init headroom */ - can_skb_prv(skb)->ifindex = dev->ifindex; - can_skb_prv(skb)->skbcnt = 0; + /* the CAN specific type of skb is identified by its data length */ + return (skb->len == CAN_MTU && cf->len <= CAN_MAX_DLEN); +} - skb->ip_summed = CHECKSUM_UNNECESSARY; +static inline bool can_is_canfd_skb(const struct sk_buff *skb) +{ + struct canfd_frame *cfd = (struct canfd_frame *)skb->data; - /* perform proper loopback on capable devices */ - if (dev->flags & IFF_ECHO) - skb->pkt_type = PACKET_LOOPBACK; - else - skb->pkt_type = PACKET_HOST; + /* the CAN specific type of skb is identified by its data length */ + return (skb->len == CANFD_MTU && cfd->len <= CANFD_MAX_DLEN); +} - skb_reset_mac_header(skb); - skb_reset_network_header(skb); - skb_reset_transport_header(skb); - } +static inline bool can_is_canxl_skb(const struct sk_buff *skb) +{ + const struct canxl_frame *cxl = (struct canxl_frame *)skb->data; - return true; + if (skb->len < CANXL_HDR_SIZE + CANXL_MIN_DLEN || skb->len > CANXL_MTU) + return false; + + /* this also checks valid CAN XL data length boundaries */ + if (skb->len != CANXL_HDR_SIZE + cxl->len) + return false; + + return cxl->flags & CANXL_XLF; } -/* Drop a given socketbuffer if it does not contain a valid CAN frame. */ -static inline bool can_dropped_invalid_skb(struct net_device *dev, - struct sk_buff *skb) +/* get length element value from can[|fd|xl]_frame structure */ +static inline unsigned int can_skb_get_len_val(struct sk_buff *skb) { + const struct canxl_frame *cxl = (struct canxl_frame *)skb->data; const struct canfd_frame *cfd = (struct canfd_frame *)skb->data; - if (skb->protocol == htons(ETH_P_CAN)) { - if (unlikely(skb->len != CAN_MTU || - cfd->len > CAN_MAX_DLEN)) - goto inval_skb; - } else if (skb->protocol == htons(ETH_P_CANFD)) { - if (unlikely(skb->len != CANFD_MTU || - cfd->len > CANFD_MAX_DLEN)) - goto inval_skb; - } else - goto inval_skb; - - if (!can_skb_headroom_valid(dev, skb)) - goto inval_skb; - - return false; - -inval_skb: - kfree_skb(skb); - dev->stats.tx_dropped++; - return true; + if (can_is_canxl_skb(skb)) + return cxl->len; + + return cfd->len; } -static inline bool can_is_canfd_skb(const struct sk_buff *skb) +/* get needed data length inside CAN frame for all frame types (RTR aware) */ +static inline unsigned int can_skb_get_data_len(struct sk_buff *skb) { - /* the CAN specific type of skb is identified by its data length */ - return skb->len == CANFD_MTU; + unsigned int len = can_skb_get_len_val(skb); + const struct can_frame *cf = (struct can_frame *)skb->data; + + /* RTR frames have an actual length of zero */ + if (can_is_can_skb(skb) && cf->can_id & CAN_RTR_FLAG) + return 0; + + return len; } #endif /* !_CAN_SKB_H */ diff --git a/include/linux/cc_platform.h b/include/linux/cc_platform.h index efd8205282da..cb0d6cd1c12f 100644 --- a/include/linux/cc_platform.h +++ b/include/linux/cc_platform.h @@ -72,6 +72,24 @@ enum cc_attr { * Examples include TDX guest & SEV. */ CC_ATTR_GUEST_UNROLL_STRING_IO, + + /** + * @CC_ATTR_SEV_SNP: Guest SNP is active. + * + * The platform/OS is running as a guest/virtual machine and actively + * using AMD SEV-SNP features. + */ + CC_ATTR_GUEST_SEV_SNP, + + /** + * @CC_ATTR_HOTPLUG_DISABLED: Hotplug is not supported or disabled. + * + * The platform/OS is running as a guest/virtual machine does not + * support CPU hotplug feature. + * + * Examples include TDX Guest. + */ + CC_ATTR_HOTPLUG_DISABLED, }; #ifdef CONFIG_ARCH_HAS_CC_PLATFORM diff --git a/include/linux/cdrom.h b/include/linux/cdrom.h index 0a89f111e00e..67caa909e3e6 100644 --- a/include/linux/cdrom.h +++ b/include/linux/cdrom.h @@ -77,7 +77,6 @@ struct cdrom_device_ops { int (*tray_move) (struct cdrom_device_info *, int); int (*lock_door) (struct cdrom_device_info *, int); int (*select_speed) (struct cdrom_device_info *, int); - int (*select_disc) (struct cdrom_device_info *, int); int (*get_last_session) (struct cdrom_device_info *, struct cdrom_multisession *); int (*get_mcn) (struct cdrom_device_info *, diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h index 7ad6c3d0db7d..49586ff26152 100644 --- a/include/linux/ceph/ceph_fs.h +++ b/include/linux/ceph/ceph_fs.h @@ -28,8 +28,8 @@ #define CEPH_INO_ROOT 1 -#define CEPH_INO_CEPH 2 /* hidden .ceph dir */ -#define CEPH_INO_DOTDOT 3 /* used by ceph fuse for parent (..) */ +#define CEPH_INO_CEPH 2 /* hidden .ceph dir */ +#define CEPH_INO_GLOBAL_SNAPREALM 3 /* global dummy snaprealm */ /* arbitrary limit on max # of monitors (cluster of 3 is typical) */ #define CEPH_MAX_MON 31 @@ -328,6 +328,7 @@ enum { CEPH_MDS_OP_LOOKUPPARENT = 0x00103, CEPH_MDS_OP_LOOKUPINO = 0x00104, CEPH_MDS_OP_LOOKUPNAME = 0x00105, + CEPH_MDS_OP_GETVXATTR = 0x00106, CEPH_MDS_OP_SETXATTR = 0x01105, CEPH_MDS_OP_RMXATTR = 0x01106, @@ -432,9 +433,9 @@ union ceph_mds_request_args { __le32 stripe_unit; /* layout for newly created file */ __le32 stripe_count; /* ... */ __le32 object_size; - __le32 file_replication; - __le32 mask; /* CEPH_CAP_* */ - __le32 old_size; + __le32 pool; + __le32 mask; /* CEPH_CAP_* */ + __le64 old_size; } __attribute__ ((packed)) open; struct { __le32 flags; @@ -767,7 +768,7 @@ struct ceph_mds_caps { __le32 xattr_len; __le64 xattr_version; - /* filelock */ + /* a union of non-export and export bodies. */ __le64 size, max_size, truncate_size; __le32 truncate_seq; struct ceph_timespec mtime, atime, ctime; diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index 409d8c29bc4f..00af2c98da75 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -35,6 +35,7 @@ #define CEPH_OPT_TCP_NODELAY (1<<4) /* TCP_NODELAY on TCP sockets */ #define CEPH_OPT_NOMSGSIGN (1<<5) /* don't sign msgs (msgr1) */ #define CEPH_OPT_ABORT_ON_FULL (1<<6) /* abort w/ ENOSPC when full */ +#define CEPH_OPT_RXBOUNCE (1<<7) /* double-buffer read data */ #define CEPH_OPT_DEFAULT (CEPH_OPT_TCP_NODELAY) @@ -283,6 +284,7 @@ DEFINE_RB_LOOKUP_FUNC(name, type, keyfld, nodefld) extern struct kmem_cache *ceph_inode_cachep; extern struct kmem_cache *ceph_cap_cachep; +extern struct kmem_cache *ceph_cap_snap_cachep; extern struct kmem_cache *ceph_cap_flush_cachep; extern struct kmem_cache *ceph_dentry_cachep; extern struct kmem_cache *ceph_file_cachep; @@ -295,13 +297,13 @@ extern bool libceph_compatible(void *data); extern const char *ceph_msg_type_name(int type); extern int ceph_check_fsid(struct ceph_client *client, struct ceph_fsid *fsid); -extern void *ceph_kvmalloc(size_t size, gfp_t flags); +extern int ceph_parse_fsid(const char *str, struct ceph_fsid *fsid); struct fs_parameter; struct fc_log; struct ceph_options *ceph_alloc_options(void); int ceph_parse_mon_ips(const char *buf, size_t len, struct ceph_options *opt, - struct fc_log *l); + struct fc_log *l, char delim); int ceph_parse_param(struct fs_parameter *param, struct ceph_options *opt, struct fc_log *l); int ceph_print_client_options(struct seq_file *m, struct ceph_client *client, diff --git a/include/linux/ceph/mdsmap.h b/include/linux/ceph/mdsmap.h index 523fd0452856..4c3e0648dc27 100644 --- a/include/linux/ceph/mdsmap.h +++ b/include/linux/ceph/mdsmap.h @@ -25,6 +25,7 @@ struct ceph_mdsmap { u32 m_session_timeout; /* seconds */ u32 m_session_autoclose; /* seconds */ u64 m_max_file_size; + u64 m_max_xattr_size; /* maximum size for xattrs blob */ u32 m_max_mds; /* expected up:active mds number */ u32 m_num_active_mds; /* actual up:active mds number */ u32 possible_max_rank; /* possible max rank index */ diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index 0e6e9ad3c3bf..99c1726be6ee 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -207,7 +207,6 @@ struct ceph_msg_data_cursor { struct ceph_msg_data *data; /* current data item */ size_t resid; /* bytes not yet consumed */ - bool last_piece; /* current is last piece */ bool need_crc; /* crc update needed */ union { #ifdef CONFIG_BLOCK @@ -383,6 +382,10 @@ struct ceph_connection_v2_info { struct ceph_gcm_nonce in_gcm_nonce; struct ceph_gcm_nonce out_gcm_nonce; + struct page **in_enc_pages; + int in_enc_page_cnt; + int in_enc_resid; + int in_enc_i; struct page **out_enc_pages; int out_enc_page_cnt; int out_enc_resid; @@ -457,6 +460,7 @@ struct ceph_connection { struct ceph_msg *out_msg; /* sending message (== tail of out_sent) */ + struct page *bounce_page; u32 in_front_crc, in_middle_crc, in_data_crc; /* calculated crc */ struct timespec64 last_keepalive_ack; /* keepalive2 ack stamp */ @@ -493,8 +497,7 @@ void ceph_con_discard_requeued(struct ceph_connection *con, u64 reconnect_seq); void ceph_msg_data_cursor_init(struct ceph_msg_data_cursor *cursor, struct ceph_msg *msg, size_t length); struct page *ceph_msg_data_next(struct ceph_msg_data_cursor *cursor, - size_t *page_offset, size_t *length, - bool *last_piece); + size_t *page_offset, size_t *length); void ceph_msg_data_advance(struct ceph_msg_data_cursor *cursor, size_t bytes); u32 ceph_crc32c_page(u32 crc, struct page *page, unsigned int page_offset, @@ -532,7 +535,7 @@ extern const char *ceph_pr_addr(const struct ceph_entity_addr *addr); extern int ceph_parse_ips(const char *c, const char *end, struct ceph_entity_addr *addr, - int max_count, int *count); + int max_count, int *count, char delim); extern int ceph_msgr_init(void); extern void ceph_msgr_exit(void); diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 3431011f364d..fb6be72104df 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -287,6 +287,9 @@ struct ceph_osd_linger_request { rados_watcherrcb_t errcb; void *data; + struct ceph_pagelist *request_pl; + struct page **notify_id_pages; + struct page ***preply_pages; size_t *preply_len; }; @@ -504,9 +507,8 @@ extern struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *, extern void ceph_osdc_get_request(struct ceph_osd_request *req); extern void ceph_osdc_put_request(struct ceph_osd_request *req); -extern int ceph_osdc_start_request(struct ceph_osd_client *osdc, - struct ceph_osd_request *req, - bool nofail); +void ceph_osdc_start_request(struct ceph_osd_client *osdc, + struct ceph_osd_request *req); extern void ceph_osdc_cancel_request(struct ceph_osd_request *req); extern int ceph_osdc_wait_request(struct ceph_osd_client *osdc, struct ceph_osd_request *req); diff --git a/include/linux/cfi.h b/include/linux/cfi.h index 879744aaa6e0..5e134f4ce8b7 100644 --- a/include/linux/cfi.h +++ b/include/linux/cfi.h @@ -2,40 +2,38 @@ /* * Clang Control Flow Integrity (CFI) support. * - * Copyright (C) 2021 Google LLC + * Copyright (C) 2022 Google LLC */ #ifndef _LINUX_CFI_H #define _LINUX_CFI_H -#ifdef CONFIG_CFI_CLANG -typedef void (*cfi_check_fn)(uint64_t id, void *ptr, void *diag); - -/* Compiler-generated function in each module, and the kernel */ -extern void __cfi_check(uint64_t id, void *ptr, void *diag); +#include <linux/bug.h> +#include <linux/module.h> -/* - * Force the compiler to generate a CFI jump table entry for a function - * and store the jump table address to __cfi_jt_<function>. - */ -#define __CFI_ADDRESSABLE(fn, __attr) \ - const void *__cfi_jt_ ## fn __visible __attr = (void *)&fn - -#ifdef CONFIG_CFI_CLANG_SHADOW - -extern void cfi_module_add(struct module *mod, unsigned long base_addr); -extern void cfi_module_remove(struct module *mod, unsigned long base_addr); +#ifdef CONFIG_CFI_CLANG +enum bug_trap_type report_cfi_failure(struct pt_regs *regs, unsigned long addr, + unsigned long *target, u32 type); + +static inline enum bug_trap_type report_cfi_failure_noaddr(struct pt_regs *regs, + unsigned long addr) +{ + return report_cfi_failure(regs, addr, NULL, 0); +} + +#ifdef CONFIG_ARCH_USES_CFI_TRAPS +bool is_cfi_trap(unsigned long addr); +#endif +#endif /* CONFIG_CFI_CLANG */ +#ifdef CONFIG_MODULES +#ifdef CONFIG_ARCH_USES_CFI_TRAPS +void module_cfi_finalize(const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs, + struct module *mod); #else - -static inline void cfi_module_add(struct module *mod, unsigned long base_addr) {} -static inline void cfi_module_remove(struct module *mod, unsigned long base_addr) {} - -#endif /* CONFIG_CFI_CLANG_SHADOW */ - -#else /* !CONFIG_CFI_CLANG */ - -#define __CFI_ADDRESSABLE(fn, __attr) - -#endif /* CONFIG_CFI_CLANG */ +static inline void module_cfi_finalize(const Elf_Ehdr *hdr, + const Elf_Shdr *sechdrs, + struct module *mod) {} +#endif /* CONFIG_ARCH_USES_CFI_TRAPS */ +#endif /* CONFIG_MODULES */ #endif /* _LINUX_CFI_H */ diff --git a/include/linux/cfi_types.h b/include/linux/cfi_types.h new file mode 100644 index 000000000000..6b8713675765 --- /dev/null +++ b/include/linux/cfi_types.h @@ -0,0 +1,45 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Clang Control Flow Integrity (CFI) type definitions. + */ +#ifndef _LINUX_CFI_TYPES_H +#define _LINUX_CFI_TYPES_H + +#ifdef __ASSEMBLY__ +#include <linux/linkage.h> + +#ifdef CONFIG_CFI_CLANG +/* + * Use the __kcfi_typeid_<function> type identifier symbol to + * annotate indirectly called assembly functions. The compiler emits + * these symbols for all address-taken function declarations in C + * code. + */ +#ifndef __CFI_TYPE +#define __CFI_TYPE(name) \ + .4byte __kcfi_typeid_##name +#endif + +#define SYM_TYPED_ENTRY(name, linkage, align...) \ + linkage(name) ASM_NL \ + align ASM_NL \ + __CFI_TYPE(name) ASM_NL \ + name: + +#define SYM_TYPED_START(name, linkage, align...) \ + SYM_TYPED_ENTRY(name, linkage, align) + +#else /* CONFIG_CFI_CLANG */ + +#define SYM_TYPED_START(name, linkage, align...) \ + SYM_START(name, linkage, align) + +#endif /* CONFIG_CFI_CLANG */ + +#ifndef SYM_TYPED_FUNC_START +#define SYM_TYPED_FUNC_START(name) \ + SYM_TYPED_START(name, SYM_L_GLOBAL, SYM_A_ALIGN) +#endif + +#endif /* __ASSEMBLY__ */ +#endif /* _LINUX_CFI_TYPES_H */ diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 1bfcfb1af352..6e01f10f0d88 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -89,19 +89,32 @@ enum { CGRP_ROOT_NS_DELEGATE = (1 << 3), /* + * Reduce latencies on dynamic cgroup modifications such as task + * migrations and controller on/offs by disabling percpu operation on + * cgroup_threadgroup_rwsem. This makes hot path operations such as + * forks and exits into the slow path and more expensive. + * + * The static usage pattern of creating a cgroup, enabling controllers, + * and then seeding it with CLONE_INTO_CGROUP doesn't require write + * locking cgroup_threadgroup_rwsem and thus doesn't benefit from + * favordynmod. + */ + CGRP_ROOT_FAVOR_DYNMODS = (1 << 4), + + /* * Enable cpuset controller in v1 cgroup to use v2 behavior. */ - CGRP_ROOT_CPUSET_V2_MODE = (1 << 4), + CGRP_ROOT_CPUSET_V2_MODE = (1 << 16), /* * Enable legacy local memory.events. */ - CGRP_ROOT_MEMORY_LOCAL_EVENTS = (1 << 5), + CGRP_ROOT_MEMORY_LOCAL_EVENTS = (1 << 17), /* * Enable recursive subtree protection */ - CGRP_ROOT_MEMORY_RECURSIVE_PROT = (1 << 6), + CGRP_ROOT_MEMORY_RECURSIVE_PROT = (1 << 18), }; /* cftype->flags */ @@ -113,11 +126,11 @@ enum { CFTYPE_NO_PREFIX = (1 << 3), /* (DON'T USE FOR NEW FILES) no subsys prefix */ CFTYPE_WORLD_WRITABLE = (1 << 4), /* (DON'T USE FOR NEW FILES) S_IWUGO */ CFTYPE_DEBUG = (1 << 5), /* create when cgroup_debug */ - CFTYPE_PRESSURE = (1 << 6), /* only if pressure feature is enabled */ /* internal flags, do not use outside cgroup core proper */ __CFTYPE_ONLY_ON_DFL = (1 << 16), /* only on default hierarchy */ __CFTYPE_NOT_ON_DFL = (1 << 17), /* not on default hierarchy */ + __CFTYPE_ADDED = (1 << 18), }; /* @@ -264,7 +277,8 @@ struct css_set { * List of csets participating in the on-going migration either as * source or destination. Protected by cgroup_mutex. */ - struct list_head mg_preload_node; + struct list_head mg_src_preload_node; + struct list_head mg_dst_preload_node; struct list_head mg_node; /* @@ -287,6 +301,10 @@ struct css_set { struct cgroup_base_stat { struct task_cputime cputime; + +#ifdef CONFIG_SCHED_CORE + u64 forceidle_sum; +#endif }; /* @@ -366,7 +384,7 @@ struct cgroup { /* * The depth this cgroup is at. The root is at depth zero and each * step down the hierarchy increments the level. This along with - * ancestor_ids[] can determine whether a given cgroup is a + * ancestors[] can determine whether a given cgroup is a * descendant of another without traversing the hierarchy. */ int level; @@ -410,6 +428,9 @@ struct cgroup { struct cgroup_file procs_file; /* handle for "cgroup.procs" */ struct cgroup_file events_file; /* handle for "cgroup.events" */ + /* handles for "{cpu,memory,io,irq}.pressure" */ + struct cgroup_file psi_files[NR_PSI_RESOURCES]; + /* * The bitmask of subsystems enabled on the child cgroups. * ->subtree_control is the one configured through @@ -475,7 +496,7 @@ struct cgroup { struct work_struct release_agent_work; /* used to track pressure stalls */ - struct psi_group psi; + struct psi_group *psi; /* used to store eBPF programs */ struct cgroup_bpf bpf; @@ -486,8 +507,8 @@ struct cgroup { /* Used to store internal freezer state */ struct cgroup_freezer_state freezer; - /* ids of the ancestors at each level including self */ - u64 ancestor_ids[]; + /* All ancestors including self */ + struct cgroup *ancestors[]; }; /* @@ -504,11 +525,15 @@ struct cgroup_root { /* Unique id for this hierarchy. */ int hierarchy_id; - /* The root cgroup. Root is destroyed on its release. */ + /* + * The root cgroup. The containing cgroup_root will be destroyed on its + * release. cgrp->ancestors[0] will be used overflowing into the + * following field. cgrp_ancestor_storage must immediately follow. + */ struct cgroup cgrp; - /* for cgrp->ancestor_ids[0] */ - u64 cgrp_ancestor_id_storage; + /* must follow cgrp for cgrp->ancestors[0], see above */ + struct cgroup *cgrp_ancestor_storage; /* Number of cgroups in the hierarchy, used only for /proc/cgroups */ atomic_t nr_cgrps; diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 75c151413fda..528bd44b59e2 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -106,6 +106,7 @@ struct cgroup_subsys_state *css_tryget_online_from_dir(struct dentry *dentry, struct cgroup *cgroup_get_from_path(const char *path); struct cgroup *cgroup_get_from_fd(int fd); +struct cgroup *cgroup_v1v2_get_from_fd(int fd); int cgroup_attach_task_all(struct task_struct *from, struct task_struct *); int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from); @@ -114,6 +115,7 @@ int cgroup_add_dfl_cftypes(struct cgroup_subsys *ss, struct cftype *cfts); int cgroup_add_legacy_cftypes(struct cgroup_subsys *ss, struct cftype *cfts); int cgroup_rm_cftypes(struct cftype *cfts); void cgroup_file_notify(struct cgroup_file *cfile); +void cgroup_file_show(struct cgroup_file *cfile, bool show); int task_cgroup_path(struct task_struct *task, char *buf, size_t buflen); int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry); @@ -432,6 +434,18 @@ static inline void cgroup_put(struct cgroup *cgrp) css_put(&cgrp->self); } +extern struct mutex cgroup_mutex; + +static inline void cgroup_lock(void) +{ + mutex_lock(&cgroup_mutex); +} + +static inline void cgroup_unlock(void) +{ + mutex_unlock(&cgroup_mutex); +} + /** * task_css_set_check - obtain a task's css_set with extra access conditions * @task: the task to obtain css_set for @@ -446,10 +460,10 @@ static inline void cgroup_put(struct cgroup *cgrp) * as locks used during the cgroup_subsys::attach() methods. */ #ifdef CONFIG_PROVE_RCU -extern struct mutex cgroup_mutex; extern spinlock_t css_set_lock; #define task_css_set_check(task, __c) \ rcu_dereference_check((task)->cgroups, \ + rcu_read_lock_sched_held() || \ lockdep_is_held(&cgroup_mutex) || \ lockdep_is_held(&css_set_lock) || \ ((task)->flags & PF_EXITING) || (__c)) @@ -573,7 +587,7 @@ static inline bool cgroup_is_descendant(struct cgroup *cgrp, { if (cgrp->root != ancestor->root || cgrp->level < ancestor->level) return false; - return cgrp->ancestor_ids[ancestor->level] == cgroup_id(ancestor); + return cgrp->ancestors[ancestor->level] == ancestor; } /** @@ -590,11 +604,9 @@ static inline bool cgroup_is_descendant(struct cgroup *cgrp, static inline struct cgroup *cgroup_ancestor(struct cgroup *cgrp, int ancestor_level) { - if (cgrp->level < ancestor_level) + if (ancestor_level < 0 || ancestor_level > cgrp->level) return NULL; - while (cgrp && cgrp->level > ancestor_level) - cgrp = cgroup_parent(cgrp); - return cgrp; + return cgrp->ancestors[ancestor_level]; } /** @@ -671,11 +683,6 @@ static inline void pr_cont_cgroup_path(struct cgroup *cgrp) pr_cont_kernfs_path(cgrp->kn); } -static inline struct psi_group *cgroup_psi(struct cgroup *cgrp) -{ - return &cgrp->psi; -} - bool cgroup_psi_enabled(void); static inline void cgroup_init_kthreadd(void) @@ -707,6 +714,8 @@ struct cgroup; static inline u64 cgroup_id(const struct cgroup *cgrp) { return 1; } static inline void css_get(struct cgroup_subsys_state *css) {} static inline void css_put(struct cgroup_subsys_state *css) {} +static inline void cgroup_lock(void) {} +static inline void cgroup_unlock(void) {} static inline int cgroup_attach_task_all(struct task_struct *from, struct task_struct *t) { return 0; } static inline int cgroupstats_build(struct cgroupstats *stats, @@ -733,11 +742,6 @@ static inline struct cgroup *cgroup_parent(struct cgroup *cgrp) return NULL; } -static inline struct psi_group *cgroup_psi(struct cgroup *cgrp) -{ - return NULL; -} - static inline bool cgroup_psi_enabled(void) { return false; @@ -751,11 +755,6 @@ static inline bool task_under_cgroup_hierarchy(struct task_struct *task, static inline void cgroup_path_from_kernfs_id(u64 id, char *buf, size_t buflen) {} - -static inline struct cgroup *cgroup_get_from_id(u64 id) -{ - return NULL; -} #endif /* !CONFIG_CGROUPS */ #ifdef CONFIG_CGROUPS @@ -791,11 +790,9 @@ static inline void cgroup_account_cputime(struct task_struct *task, cpuacct_charge(task, delta_exec); - rcu_read_lock(); cgrp = task_dfl_cgroup(task); if (cgroup_parent(cgrp)) __cgroup_account_cputime(cgrp, delta_exec); - rcu_read_unlock(); } static inline void cgroup_account_cputime_field(struct task_struct *task, @@ -806,11 +803,9 @@ static inline void cgroup_account_cputime_field(struct task_struct *task, cpuacct_account_field(task, index, delta_exec); - rcu_read_lock(); cgrp = task_dfl_cgroup(task); if (cgroup_parent(cgrp)) __cgroup_account_cputime_field(cgrp, index, delta_exec); - rcu_read_unlock(); } #else /* CONFIG_CGROUPS */ diff --git a/include/linux/cgroup_api.h b/include/linux/cgroup_api.h new file mode 100644 index 000000000000..d0cfe8025111 --- /dev/null +++ b/include/linux/cgroup_api.h @@ -0,0 +1 @@ +#include <linux/cgroup.h> diff --git a/include/linux/cleancache.h b/include/linux/cleancache.h deleted file mode 100644 index 5f5730c1d324..000000000000 --- a/include/linux/cleancache.h +++ /dev/null @@ -1,124 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _LINUX_CLEANCACHE_H -#define _LINUX_CLEANCACHE_H - -#include <linux/fs.h> -#include <linux/exportfs.h> -#include <linux/mm.h> - -#define CLEANCACHE_NO_POOL -1 -#define CLEANCACHE_NO_BACKEND -2 -#define CLEANCACHE_NO_BACKEND_SHARED -3 - -#define CLEANCACHE_KEY_MAX 6 - -/* - * cleancache requires every file with a page in cleancache to have a - * unique key unless/until the file is removed/truncated. For some - * filesystems, the inode number is unique, but for "modern" filesystems - * an exportable filehandle is required (see exportfs.h) - */ -struct cleancache_filekey { - union { - ino_t ino; - __u32 fh[CLEANCACHE_KEY_MAX]; - u32 key[CLEANCACHE_KEY_MAX]; - } u; -}; - -struct cleancache_ops { - int (*init_fs)(size_t); - int (*init_shared_fs)(uuid_t *uuid, size_t); - int (*get_page)(int, struct cleancache_filekey, - pgoff_t, struct page *); - void (*put_page)(int, struct cleancache_filekey, - pgoff_t, struct page *); - void (*invalidate_page)(int, struct cleancache_filekey, pgoff_t); - void (*invalidate_inode)(int, struct cleancache_filekey); - void (*invalidate_fs)(int); -}; - -extern int cleancache_register_ops(const struct cleancache_ops *ops); -extern void __cleancache_init_fs(struct super_block *); -extern void __cleancache_init_shared_fs(struct super_block *); -extern int __cleancache_get_page(struct page *); -extern void __cleancache_put_page(struct page *); -extern void __cleancache_invalidate_page(struct address_space *, struct page *); -extern void __cleancache_invalidate_inode(struct address_space *); -extern void __cleancache_invalidate_fs(struct super_block *); - -#ifdef CONFIG_CLEANCACHE -#define cleancache_enabled (1) -static inline bool cleancache_fs_enabled_mapping(struct address_space *mapping) -{ - return mapping->host->i_sb->cleancache_poolid >= 0; -} -static inline bool cleancache_fs_enabled(struct page *page) -{ - return cleancache_fs_enabled_mapping(page->mapping); -} -#else -#define cleancache_enabled (0) -#define cleancache_fs_enabled(_page) (0) -#define cleancache_fs_enabled_mapping(_page) (0) -#endif - -/* - * The shim layer provided by these inline functions allows the compiler - * to reduce all cleancache hooks to nothingness if CONFIG_CLEANCACHE - * is disabled, to a single global variable check if CONFIG_CLEANCACHE - * is enabled but no cleancache "backend" has dynamically enabled it, - * and, for the most frequent cleancache ops, to a single global variable - * check plus a superblock element comparison if CONFIG_CLEANCACHE is enabled - * and a cleancache backend has dynamically enabled cleancache, but the - * filesystem referenced by that cleancache op has not enabled cleancache. - * As a result, CONFIG_CLEANCACHE can be enabled by default with essentially - * no measurable performance impact. - */ - -static inline void cleancache_init_fs(struct super_block *sb) -{ - if (cleancache_enabled) - __cleancache_init_fs(sb); -} - -static inline void cleancache_init_shared_fs(struct super_block *sb) -{ - if (cleancache_enabled) - __cleancache_init_shared_fs(sb); -} - -static inline int cleancache_get_page(struct page *page) -{ - if (cleancache_enabled && cleancache_fs_enabled(page)) - return __cleancache_get_page(page); - return -1; -} - -static inline void cleancache_put_page(struct page *page) -{ - if (cleancache_enabled && cleancache_fs_enabled(page)) - __cleancache_put_page(page); -} - -static inline void cleancache_invalidate_page(struct address_space *mapping, - struct page *page) -{ - /* careful... page->mapping is NULL sometimes when this is called */ - if (cleancache_enabled && cleancache_fs_enabled_mapping(mapping)) - __cleancache_invalidate_page(mapping, page); -} - -static inline void cleancache_invalidate_inode(struct address_space *mapping) -{ - if (cleancache_enabled && cleancache_fs_enabled_mapping(mapping)) - __cleancache_invalidate_inode(mapping); -} - -static inline void cleancache_invalidate_fs(struct super_block *sb) -{ - if (cleancache_enabled) - __cleancache_invalidate_fs(sb); -} - -#endif /* _LINUX_CLEANCACHE_H */ diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index f59c875271a0..267cd06b54a0 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -42,6 +42,8 @@ struct dentry; * struct clk_rate_request - Structure encoding the clk constraints that * a clock user might require. * + * Should be initialized by calling clk_hw_init_rate_request(). + * * @rate: Requested clock rate. This field will be adjusted by * clock drivers according to hardware capabilities. * @min_rate: Minimum rate imposed by clk users. @@ -60,6 +62,15 @@ struct clk_rate_request { struct clk_hw *best_parent_hw; }; +void clk_hw_init_rate_request(const struct clk_hw *hw, + struct clk_rate_request *req, + unsigned long rate); +void clk_hw_forward_rate_request(const struct clk_hw *core, + const struct clk_rate_request *old_req, + const struct clk_hw *parent, + struct clk_rate_request *req, + unsigned long parent_rate); + /** * struct clk_duty - Struture encoding the duty cycle ratio of a clock * @@ -118,8 +129,9 @@ struct clk_duty { * * @recalc_rate Recalculate the rate of this clock, by querying hardware. The * parent rate is an input parameter. It is up to the caller to - * ensure that the prepare_mutex is held across this call. - * Returns the calculated rate. Optional, but recommended - if + * ensure that the prepare_mutex is held across this call. If the + * driver cannot figure out a rate for this clock, it must return + * 0. Returns the calculated rate. Optional, but recommended - if * this op is not set then clock rate will be initialized to 0. * * @round_rate: Given a target rate as input, returns the closest rate actually @@ -350,7 +362,7 @@ struct clk_hw *__clk_hw_register_fixed_rate(struct device *dev, const char *parent_name, const struct clk_hw *parent_hw, const struct clk_parent_data *parent_data, unsigned long flags, unsigned long fixed_rate, unsigned long fixed_accuracy, - unsigned long clk_fixed_flags); + unsigned long clk_fixed_flags, bool devm); struct clk *clk_register_fixed_rate(struct device *dev, const char *name, const char *parent_name, unsigned long flags, unsigned long fixed_rate); @@ -365,7 +377,20 @@ struct clk *clk_register_fixed_rate(struct device *dev, const char *name, */ #define clk_hw_register_fixed_rate(dev, name, parent_name, flags, fixed_rate) \ __clk_hw_register_fixed_rate((dev), NULL, (name), (parent_name), NULL, \ - NULL, (flags), (fixed_rate), 0, 0) + NULL, (flags), (fixed_rate), 0, 0, false) + +/** + * devm_clk_hw_register_fixed_rate - register fixed-rate clock with the clock + * framework + * @dev: device that is registering this clock + * @name: name of this clock + * @parent_name: name of clock's parent + * @flags: framework-specific flags + * @fixed_rate: non-adjustable clock rate + */ +#define devm_clk_hw_register_fixed_rate(dev, name, parent_name, flags, fixed_rate) \ + __clk_hw_register_fixed_rate((dev), NULL, (name), (parent_name), NULL, \ + NULL, (flags), (fixed_rate), 0, 0, true) /** * clk_hw_register_fixed_rate_parent_hw - register fixed-rate clock with * the clock framework @@ -378,7 +403,7 @@ struct clk *clk_register_fixed_rate(struct device *dev, const char *name, #define clk_hw_register_fixed_rate_parent_hw(dev, name, parent_hw, flags, \ fixed_rate) \ __clk_hw_register_fixed_rate((dev), NULL, (name), NULL, (parent_hw), \ - NULL, (flags), (fixed_rate), 0, 0) + NULL, (flags), (fixed_rate), 0, 0, false) /** * clk_hw_register_fixed_rate_parent_data - register fixed-rate clock with * the clock framework @@ -392,7 +417,7 @@ struct clk *clk_register_fixed_rate(struct device *dev, const char *name, fixed_rate) \ __clk_hw_register_fixed_rate((dev), NULL, (name), NULL, NULL, \ (parent_data), (flags), (fixed_rate), 0, \ - 0) + 0, false) /** * clk_hw_register_fixed_rate_with_accuracy - register fixed-rate clock with * the clock framework @@ -408,7 +433,7 @@ struct clk *clk_register_fixed_rate(struct device *dev, const char *name, fixed_accuracy) \ __clk_hw_register_fixed_rate((dev), NULL, (name), (parent_name), \ NULL, NULL, (flags), (fixed_rate), \ - (fixed_accuracy), 0) + (fixed_accuracy), 0, false) /** * clk_hw_register_fixed_rate_with_accuracy_parent_hw - register fixed-rate * clock with the clock framework @@ -423,7 +448,7 @@ struct clk *clk_register_fixed_rate(struct device *dev, const char *name, parent_hw, flags, fixed_rate, fixed_accuracy) \ __clk_hw_register_fixed_rate((dev), NULL, (name), NULL, (parent_hw) \ NULL, NULL, (flags), (fixed_rate), \ - (fixed_accuracy), 0) + (fixed_accuracy), 0, false) /** * clk_hw_register_fixed_rate_with_accuracy_parent_data - register fixed-rate * clock with the clock framework @@ -438,7 +463,21 @@ struct clk *clk_register_fixed_rate(struct device *dev, const char *name, parent_data, flags, fixed_rate, fixed_accuracy) \ __clk_hw_register_fixed_rate((dev), NULL, (name), NULL, NULL, \ (parent_data), NULL, (flags), \ - (fixed_rate), (fixed_accuracy), 0) + (fixed_rate), (fixed_accuracy), 0, false) +/** + * clk_hw_register_fixed_rate_parent_accuracy - register fixed-rate clock with + * the clock framework + * @dev: device that is registering this clock + * @name: name of this clock + * @parent_name: name of clock's parent + * @flags: framework-specific flags + * @fixed_rate: non-adjustable clock rate + */ +#define clk_hw_register_fixed_rate_parent_accuracy(dev, name, parent_data, \ + flags, fixed_rate) \ + __clk_hw_register_fixed_rate((dev), NULL, (name), NULL, NULL, \ + (parent_data), (flags), (fixed_rate), 0, \ + CLK_FIXED_RATE_PARENT_ACCURACY, false) void clk_unregister_fixed_rate(struct clk *clk); void clk_hw_unregister_fixed_rate(struct clk_hw *hw); @@ -490,6 +529,13 @@ struct clk_hw *__clk_hw_register_gate(struct device *dev, unsigned long flags, void __iomem *reg, u8 bit_idx, u8 clk_gate_flags, spinlock_t *lock); +struct clk_hw *__devm_clk_hw_register_gate(struct device *dev, + struct device_node *np, const char *name, + const char *parent_name, const struct clk_hw *parent_hw, + const struct clk_parent_data *parent_data, + unsigned long flags, + void __iomem *reg, u8 bit_idx, + u8 clk_gate_flags, spinlock_t *lock); struct clk *clk_register_gate(struct device *dev, const char *name, const char *parent_name, unsigned long flags, void __iomem *reg, u8 bit_idx, @@ -544,6 +590,22 @@ struct clk *clk_register_gate(struct device *dev, const char *name, __clk_hw_register_gate((dev), NULL, (name), NULL, NULL, (parent_data), \ (flags), (reg), (bit_idx), \ (clk_gate_flags), (lock)) +/** + * devm_clk_hw_register_gate - register a gate clock with the clock framework + * @dev: device that is registering this clock + * @name: name of this clock + * @parent_name: name of this clock's parent + * @flags: framework-specific flags for this clock + * @reg: register address to control gating of this clock + * @bit_idx: which bit in the register controls gating of this clock + * @clk_gate_flags: gate-specific flags for this clock + * @lock: shared register lock for this clock + */ +#define devm_clk_hw_register_gate(dev, name, parent_name, flags, reg, bit_idx,\ + clk_gate_flags, lock) \ + __devm_clk_hw_register_gate((dev), NULL, (name), (parent_name), NULL, \ + NULL, (flags), (reg), (bit_idx), \ + (clk_gate_flags), (lock)) void clk_unregister_gate(struct clk *clk); void clk_hw_unregister_gate(struct clk_hw *hw); int clk_gate_is_enabled(struct clk_hw *hw); @@ -809,6 +871,25 @@ struct clk *clk_register_divider_table(struct device *dev, const char *name, NULL, (flags), (reg), (shift), (width), \ (clk_divider_flags), NULL, (lock)) /** + * devm_clk_hw_register_divider_parent_hw - register a divider clock with the clock framework + * @dev: device registering this clock + * @name: name of this clock + * @parent_hw: pointer to parent clk + * @flags: framework-specific flags + * @reg: register address to adjust divider + * @shift: number of bits to shift the bitfield + * @width: width of the bitfield + * @clk_divider_flags: divider-specific flags for this clock + * @lock: shared register lock for this clock + */ +#define devm_clk_hw_register_divider_parent_hw(dev, name, parent_hw, flags, \ + reg, shift, width, \ + clk_divider_flags, lock) \ + __devm_clk_hw_register_divider((dev), NULL, (name), NULL, \ + (parent_hw), NULL, (flags), (reg), \ + (shift), (width), (clk_divider_flags), \ + NULL, (lock)) +/** * devm_clk_hw_register_divider_table - register a table based divider clock * with the clock framework (devres variant) * @dev: device registering this clock @@ -865,7 +946,7 @@ void clk_hw_unregister_divider(struct clk_hw *hw); struct clk_mux { struct clk_hw hw; void __iomem *reg; - u32 *table; + const u32 *table; u32 mask; u8 shift; u8 flags; @@ -890,18 +971,18 @@ struct clk_hw *__clk_hw_register_mux(struct device *dev, struct device_node *np, const struct clk_hw **parent_hws, const struct clk_parent_data *parent_data, unsigned long flags, void __iomem *reg, u8 shift, u32 mask, - u8 clk_mux_flags, u32 *table, spinlock_t *lock); + u8 clk_mux_flags, const u32 *table, spinlock_t *lock); struct clk_hw *__devm_clk_hw_register_mux(struct device *dev, struct device_node *np, const char *name, u8 num_parents, const char * const *parent_names, const struct clk_hw **parent_hws, const struct clk_parent_data *parent_data, unsigned long flags, void __iomem *reg, u8 shift, u32 mask, - u8 clk_mux_flags, u32 *table, spinlock_t *lock); + u8 clk_mux_flags, const u32 *table, spinlock_t *lock); struct clk *clk_register_mux_table(struct device *dev, const char *name, const char * const *parent_names, u8 num_parents, unsigned long flags, void __iomem *reg, u8 shift, u32 mask, - u8 clk_mux_flags, u32 *table, spinlock_t *lock); + u8 clk_mux_flags, const u32 *table, spinlock_t *lock); #define clk_register_mux(dev, name, parent_names, num_parents, flags, reg, \ shift, width, clk_mux_flags, lock) \ @@ -915,6 +996,13 @@ struct clk *clk_register_mux_table(struct device *dev, const char *name, (parent_names), NULL, NULL, (flags), (reg), \ (shift), (mask), (clk_mux_flags), (table), \ (lock)) +#define clk_hw_register_mux_table_parent_data(dev, name, parent_data, \ + num_parents, flags, reg, shift, mask, \ + clk_mux_flags, table, lock) \ + __clk_hw_register_mux((dev), NULL, (name), (num_parents), \ + NULL, NULL, (parent_data), (flags), (reg), \ + (shift), (mask), (clk_mux_flags), (table), \ + (lock)) #define clk_hw_register_mux(dev, name, parent_names, num_parents, flags, reg, \ shift, width, clk_mux_flags, lock) \ __clk_hw_register_mux((dev), NULL, (name), (num_parents), \ @@ -932,16 +1020,37 @@ struct clk *clk_register_mux_table(struct device *dev, const char *name, __clk_hw_register_mux((dev), NULL, (name), (num_parents), NULL, NULL, \ (parent_data), (flags), (reg), (shift), \ BIT((width)) - 1, (clk_mux_flags), NULL, (lock)) +#define clk_hw_register_mux_parent_data_table(dev, name, parent_data, \ + num_parents, flags, reg, shift, \ + width, clk_mux_flags, table, \ + lock) \ + __clk_hw_register_mux((dev), NULL, (name), (num_parents), NULL, NULL, \ + (parent_data), (flags), (reg), (shift), \ + BIT((width)) - 1, (clk_mux_flags), table, (lock)) #define devm_clk_hw_register_mux(dev, name, parent_names, num_parents, flags, reg, \ shift, width, clk_mux_flags, lock) \ __devm_clk_hw_register_mux((dev), NULL, (name), (num_parents), \ (parent_names), NULL, NULL, (flags), (reg), \ (shift), BIT((width)) - 1, (clk_mux_flags), \ NULL, (lock)) - -int clk_mux_val_to_index(struct clk_hw *hw, u32 *table, unsigned int flags, +#define devm_clk_hw_register_mux_parent_hws(dev, name, parent_hws, \ + num_parents, flags, reg, shift, \ + width, clk_mux_flags, lock) \ + __devm_clk_hw_register_mux((dev), NULL, (name), (num_parents), NULL, \ + (parent_hws), NULL, (flags), (reg), \ + (shift), BIT((width)) - 1, \ + (clk_mux_flags), NULL, (lock)) +#define devm_clk_hw_register_mux_parent_data_table(dev, name, parent_data, \ + num_parents, flags, reg, shift, \ + width, clk_mux_flags, table, \ + lock) \ + __devm_clk_hw_register_mux((dev), NULL, (name), (num_parents), NULL, \ + NULL, (parent_data), (flags), (reg), (shift), \ + BIT((width)) - 1, (clk_mux_flags), table, (lock)) + +int clk_mux_val_to_index(struct clk_hw *hw, const u32 *table, unsigned int flags, unsigned int val); -unsigned int clk_mux_index_to_val(u32 *table, unsigned int flags, u8 index); +unsigned int clk_mux_index_to_val(const u32 *table, unsigned int flags, u8 index); void clk_unregister_mux(struct clk *clk); void clk_hw_unregister_mux(struct clk_hw *hw); @@ -980,6 +1089,17 @@ void clk_hw_unregister_fixed_factor(struct clk_hw *hw); struct clk_hw *devm_clk_hw_register_fixed_factor(struct device *dev, const char *name, const char *parent_name, unsigned long flags, unsigned int mult, unsigned int div); +struct clk_hw *devm_clk_hw_register_fixed_factor_index(struct device *dev, + const char *name, unsigned int index, unsigned long flags, + unsigned int mult, unsigned int div); + +struct clk_hw *devm_clk_hw_register_fixed_factor_parent_hw(struct device *dev, + const char *name, const struct clk_hw *parent_hw, + unsigned long flags, unsigned int mult, unsigned int div); + +struct clk_hw *clk_hw_register_fixed_factor_parent_hw(struct device *dev, + const char *name, const struct clk_hw *parent_hw, + unsigned long flags, unsigned int mult, unsigned int div); /** * struct clk_fractional_divider - adjustable fractional divider clock * @@ -1150,10 +1270,8 @@ int __must_check devm_clk_hw_register(struct device *dev, struct clk_hw *hw); int __must_check of_clk_hw_register(struct device_node *node, struct clk_hw *hw); void clk_unregister(struct clk *clk); -void devm_clk_unregister(struct device *dev, struct clk *clk); void clk_hw_unregister(struct clk_hw *hw); -void devm_clk_hw_unregister(struct device *dev, struct clk_hw *hw); /* helper functions */ const char *__clk_get_name(const struct clk *clk); @@ -1197,6 +1315,8 @@ int clk_mux_determine_rate_flags(struct clk_hw *hw, struct clk_rate_request *req, unsigned long flags); void clk_hw_reparent(struct clk_hw *hw, struct clk_hw *new_parent); +void clk_hw_get_rate_range(struct clk_hw *hw, unsigned long *min_rate, + unsigned long *max_rate); void clk_hw_set_rate_range(struct clk_hw *hw, unsigned long min_rate, unsigned long max_rate); @@ -1396,7 +1516,7 @@ int devm_of_clk_add_hw_provider(struct device *dev, void *data), void *data); void of_clk_del_provider(struct device_node *np); -void devm_of_clk_del_provider(struct device *dev); + struct clk *of_clk_src_simple_get(struct of_phandle_args *clkspec, void *data); struct clk_hw *of_clk_hw_simple_get(struct of_phandle_args *clkspec, @@ -1433,7 +1553,7 @@ static inline int devm_of_clk_add_hw_provider(struct device *dev, return 0; } static inline void of_clk_del_provider(struct device_node *np) {} -static inline void devm_of_clk_del_provider(struct device *dev) {} + static inline struct clk *of_clk_src_simple_get( struct of_phandle_args *clkspec, void *data) { diff --git a/include/linux/clk.h b/include/linux/clk.h index 266e8de3cb51..1ef013324237 100644 --- a/include/linux/clk.h +++ b/include/linux/clk.h @@ -443,15 +443,16 @@ int __must_check devm_clk_bulk_get_all(struct device *dev, * @dev: device for clock "consumer" * @id: clock consumer ID * - * Returns a struct clk corresponding to the clock producer, or + * Context: May sleep. + * + * Return: a struct clk corresponding to the clock producer, or * valid IS_ERR() condition containing errno. The implementation * uses @dev and @id to determine the clock consumer, and thereby * the clock producer. (IOW, @id may be identical strings, but * clk_get may return different clock producers depending on @dev.) * - * Drivers must assume that the clock source is not enabled. - * - * devm_clk_get should not be called from within interrupt context. + * Drivers must assume that the clock source is neither prepared nor + * enabled. * * The clock will automatically be freed when the device is unbound * from the bus. @@ -459,17 +460,114 @@ int __must_check devm_clk_bulk_get_all(struct device *dev, struct clk *devm_clk_get(struct device *dev, const char *id); /** + * devm_clk_get_prepared - devm_clk_get() + clk_prepare() + * @dev: device for clock "consumer" + * @id: clock consumer ID + * + * Context: May sleep. + * + * Return: a struct clk corresponding to the clock producer, or + * valid IS_ERR() condition containing errno. The implementation + * uses @dev and @id to determine the clock consumer, and thereby + * the clock producer. (IOW, @id may be identical strings, but + * clk_get may return different clock producers depending on @dev.) + * + * The returned clk (if valid) is prepared. Drivers must however assume + * that the clock is not enabled. + * + * The clock will automatically be unprepared and freed when the device + * is unbound from the bus. + */ +struct clk *devm_clk_get_prepared(struct device *dev, const char *id); + +/** + * devm_clk_get_enabled - devm_clk_get() + clk_prepare_enable() + * @dev: device for clock "consumer" + * @id: clock consumer ID + * + * Context: May sleep. + * + * Return: a struct clk corresponding to the clock producer, or + * valid IS_ERR() condition containing errno. The implementation + * uses @dev and @id to determine the clock consumer, and thereby + * the clock producer. (IOW, @id may be identical strings, but + * clk_get may return different clock producers depending on @dev.) + * + * The returned clk (if valid) is prepared and enabled. + * + * The clock will automatically be disabled, unprepared and freed + * when the device is unbound from the bus. + */ +struct clk *devm_clk_get_enabled(struct device *dev, const char *id); + +/** * devm_clk_get_optional - lookup and obtain a managed reference to an optional * clock producer. * @dev: device for clock "consumer" * @id: clock consumer ID * - * Behaves the same as devm_clk_get() except where there is no clock producer. - * In this case, instead of returning -ENOENT, the function returns NULL. + * Context: May sleep. + * + * Return: a struct clk corresponding to the clock producer, or + * valid IS_ERR() condition containing errno. The implementation + * uses @dev and @id to determine the clock consumer, and thereby + * the clock producer. If no such clk is found, it returns NULL + * which serves as a dummy clk. That's the only difference compared + * to devm_clk_get(). + * + * Drivers must assume that the clock source is neither prepared nor + * enabled. + * + * The clock will automatically be freed when the device is unbound + * from the bus. */ struct clk *devm_clk_get_optional(struct device *dev, const char *id); /** + * devm_clk_get_optional_prepared - devm_clk_get_optional() + clk_prepare() + * @dev: device for clock "consumer" + * @id: clock consumer ID + * + * Context: May sleep. + * + * Return: a struct clk corresponding to the clock producer, or + * valid IS_ERR() condition containing errno. The implementation + * uses @dev and @id to determine the clock consumer, and thereby + * the clock producer. If no such clk is found, it returns NULL + * which serves as a dummy clk. That's the only difference compared + * to devm_clk_get_prepared(). + * + * The returned clk (if valid) is prepared. Drivers must however + * assume that the clock is not enabled. + * + * The clock will automatically be unprepared and freed when the + * device is unbound from the bus. + */ +struct clk *devm_clk_get_optional_prepared(struct device *dev, const char *id); + +/** + * devm_clk_get_optional_enabled - devm_clk_get_optional() + + * clk_prepare_enable() + * @dev: device for clock "consumer" + * @id: clock consumer ID + * + * Context: May sleep. + * + * Return: a struct clk corresponding to the clock producer, or + * valid IS_ERR() condition containing errno. The implementation + * uses @dev and @id to determine the clock consumer, and thereby + * the clock producer. If no such clk is found, it returns NULL + * which serves as a dummy clk. That's the only difference compared + * to devm_clk_get_enabled(). + * + * The returned clk (if valid) is prepared and enabled. + * + * The clock will automatically be disabled, unprepared and freed + * when the device is unbound from the bus. + */ +struct clk *devm_clk_get_optional_enabled(struct device *dev, const char *id); + +/** * devm_get_clk_from_child - lookup and obtain a managed reference to a * clock producer from child node. * @dev: device for clock "consumer" @@ -701,7 +799,7 @@ int clk_set_rate_exclusive(struct clk *clk, unsigned long rate); * * Returns true if @parent is a possible parent for @clk, false otherwise. */ -bool clk_has_parent(struct clk *clk, struct clk *parent); +bool clk_has_parent(const struct clk *clk, const struct clk *parent); /** * clk_set_rate_range - set a rate range for a clock source @@ -813,12 +911,36 @@ static inline struct clk *devm_clk_get(struct device *dev, const char *id) return NULL; } +static inline struct clk *devm_clk_get_prepared(struct device *dev, + const char *id) +{ + return NULL; +} + +static inline struct clk *devm_clk_get_enabled(struct device *dev, + const char *id) +{ + return NULL; +} + static inline struct clk *devm_clk_get_optional(struct device *dev, const char *id) { return NULL; } +static inline struct clk *devm_clk_get_optional_prepared(struct device *dev, + const char *id) +{ + return NULL; +} + +static inline struct clk *devm_clk_get_optional_enabled(struct device *dev, + const char *id) +{ + return NULL; +} + static inline int __must_check devm_clk_bulk_get(struct device *dev, int num_clks, struct clk_bulk_data *clks) { @@ -987,6 +1109,17 @@ static inline void clk_bulk_disable_unprepare(int num_clks, } /** + * clk_drop_range - Reset any range set on that clock + * @clk: clock source + * + * Returns success (0) or negative errno. + */ +static inline int clk_drop_range(struct clk *clk) +{ + return clk_set_rate_range(clk, 0, ULONG_MAX); +} + +/** * clk_get_optional - lookup and obtain a reference to an optional clock * producer. * @dev: device for clock "consumer" diff --git a/include/linux/clk/at91_pmc.h b/include/linux/clk/at91_pmc.h index ccb3f034bfa9..7af499bdbecb 100644 --- a/include/linux/clk/at91_pmc.h +++ b/include/linux/clk/at91_pmc.h @@ -12,6 +12,8 @@ #ifndef AT91_PMC_H #define AT91_PMC_H +#include <linux/bits.h> + #define AT91_PMC_V1 (1) /* PMC version 1 */ #define AT91_PMC_V2 (2) /* PMC version 2 [SAM9X60] */ @@ -45,8 +47,8 @@ #define AT91_PMC_PCSR 0x18 /* Peripheral Clock Status Register */ #define AT91_PMC_PLL_ACR 0x18 /* PLL Analog Control Register [for SAM9X60] */ -#define AT91_PMC_PLL_ACR_DEFAULT_UPLL 0x12020010UL /* Default PLL ACR value for UPLL */ -#define AT91_PMC_PLL_ACR_DEFAULT_PLLA 0x00020010UL /* Default PLL ACR value for PLLA */ +#define AT91_PMC_PLL_ACR_DEFAULT_UPLL UL(0x12020010) /* Default PLL ACR value for UPLL */ +#define AT91_PMC_PLL_ACR_DEFAULT_PLLA UL(0x00020010) /* Default PLL ACR value for PLLA */ #define AT91_PMC_PLL_ACR_UTMIVR (1 << 12) /* UPLL Voltage regulator Control */ #define AT91_PMC_PLL_ACR_UTMIBG (1 << 13) /* UPLL Bandgap Control */ @@ -78,6 +80,10 @@ #define AT91_PMC_MAINRDY (1 << 16) /* Main Clock Ready */ #define AT91_CKGR_PLLAR 0x28 /* PLL A Register */ + +#define AT91_PMC_RATIO 0x2c /* Processor clock ratio register [SAMA7G5 only] */ +#define AT91_PMC_RATIO_RATIO (0xf) /* CPU clock ratio. */ + #define AT91_CKGR_PLLBR 0x2c /* PLL B Register */ #define AT91_PMC_DIV (0xff << 0) /* Divider */ #define AT91_PMC_PLLCOUNT (0x3f << 8) /* PLL Counter */ diff --git a/include/linux/clk/davinci.h b/include/linux/clk/davinci.h index 8a7b5cd7eac0..f6ebab6228c2 100644 --- a/include/linux/clk/davinci.h +++ b/include/linux/clk/davinci.h @@ -28,13 +28,5 @@ int dm365_pll1_init(struct device *dev, void __iomem *base, struct regmap *cfgch int dm365_pll2_init(struct device *dev, void __iomem *base, struct regmap *cfgchip); int dm365_psc_init(struct device *dev, void __iomem *base); #endif -#ifdef CONFIG_ARCH_DAVINCI_DM644x -int dm644x_pll1_init(struct device *dev, void __iomem *base, struct regmap *cfgchip); -int dm644x_psc_init(struct device *dev, void __iomem *base); -#endif -#ifdef CONFIG_ARCH_DAVINCI_DM646x -int dm646x_pll1_init(struct device *dev, void __iomem *base, struct regmap *cfgchip); -int dm646x_psc_init(struct device *dev, void __iomem *base); -#endif #endif /* __LINUX_CLK_DAVINCI_PLL_H___ */ diff --git a/include/linux/clk/pxa.h b/include/linux/clk/pxa.h new file mode 100644 index 000000000000..736b8bb91bd7 --- /dev/null +++ b/include/linux/clk/pxa.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#include <linux/compiler.h> +#include <linux/types.h> + +extern int pxa25x_clocks_init(void __iomem *regs); +extern int pxa27x_clocks_init(void __iomem *regs); +extern int pxa3xx_clocks_init(void __iomem *regs, void __iomem *oscc_reg); + +#ifdef CONFIG_PXA3xx +extern unsigned pxa3xx_get_clk_frequency_khz(int); +extern void pxa3xx_clk_update_accr(u32 disable, u32 enable, u32 xclkcfg, u32 mask); +#else +#define pxa3xx_get_clk_frequency_khz(x) (0) +#define pxa3xx_clk_update_accr(disable, enable, xclkcfg, mask) do { } while (0) +#endif diff --git a/include/linux/clk/spear.h b/include/linux/clk/spear.h index a64d034ceddd..eaf95ca656f8 100644 --- a/include/linux/clk/spear.h +++ b/include/linux/clk/spear.h @@ -8,6 +8,20 @@ #ifndef __LINUX_CLK_SPEAR_H #define __LINUX_CLK_SPEAR_H +#ifdef CONFIG_ARCH_SPEAR3XX +void __init spear3xx_clk_init(void __iomem *misc_base, + void __iomem *soc_config_base); +#else +static inline void __init spear3xx_clk_init(void __iomem *misc_base, + void __iomem *soc_config_base) {} +#endif + +#ifdef CONFIG_ARCH_SPEAR6XX +void __init spear6xx_clk_init(void __iomem *misc_base); +#else +static inline void __init spear6xx_clk_init(void __iomem *misc_base) {} +#endif + #ifdef CONFIG_MACH_SPEAR1310 void __init spear1310_clk_init(void __iomem *misc_base, void __iomem *ras_base); #else diff --git a/include/linux/clk/sunxi-ng.h b/include/linux/clk/sunxi-ng.h index 3cd14acde0a1..57c8ec44ab4e 100644 --- a/include/linux/clk/sunxi-ng.h +++ b/include/linux/clk/sunxi-ng.h @@ -6,22 +6,9 @@ #ifndef _LINUX_CLK_SUNXI_NG_H_ #define _LINUX_CLK_SUNXI_NG_H_ -#include <linux/errno.h> - -#ifdef CONFIG_SUNXI_CCU int sunxi_ccu_set_mmc_timing_mode(struct clk *clk, bool new_mode); int sunxi_ccu_get_mmc_timing_mode(struct clk *clk); -#else -static inline int sunxi_ccu_set_mmc_timing_mode(struct clk *clk, - bool new_mode) -{ - return -ENOTSUPP; -} -static inline int sunxi_ccu_get_mmc_timing_mode(struct clk *clk) -{ - return -ENOTSUPP; -} -#endif +int sun6i_rtc_ccu_probe(struct device *dev, void __iomem *reg); #endif diff --git a/include/linux/clk/ti.h b/include/linux/clk/ti.h index 3486f20a3753..cbfcbf186ce3 100644 --- a/include/linux/clk/ti.h +++ b/include/linux/clk/ti.h @@ -1,16 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * TI clock drivers support * * Copyright (C) 2013 Texas Instruments, Inc. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * This program is distributed "as is" WITHOUT ANY WARRANTY of any - * kind, whether express or implied; without even the implied warranty - * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. */ #ifndef __LINUX_CLK_TI_H__ #define __LINUX_CLK_TI_H__ diff --git a/include/linux/clkdev.h b/include/linux/clkdev.h index 8a8423eb8e9a..45570bc21a43 100644 --- a/include/linux/clkdev.h +++ b/include/linux/clkdev.h @@ -46,6 +46,4 @@ int clk_hw_register_clkdev(struct clk_hw *, const char *, const char *); int devm_clk_hw_register_clkdev(struct device *dev, struct clk_hw *hw, const char *con_id, const char *dev_id); -void devm_clk_release_clkdev(struct device *dev, const char *con_id, - const char *dev_id); #endif diff --git a/include/linux/cma.h b/include/linux/cma.h index bd801023504b..63873b93deaa 100644 --- a/include/linux/cma.h +++ b/include/linux/cma.h @@ -12,14 +12,18 @@ */ #ifdef CONFIG_CMA_AREAS #define MAX_CMA_AREAS (1 + CONFIG_CMA_AREAS) - -#else -#define MAX_CMA_AREAS (0) - #endif #define CMA_MAX_NAME 64 +/* + * the buddy -- especially pageblock merging and alloc_contig_range() + * -- can deal with only some pageblocks of a higher-order page being + * MIGRATE_CMA, we can use pageblock_nr_pages. + */ +#define CMA_MIN_ALIGNMENT_PAGES pageblock_nr_pages +#define CMA_MIN_ALIGNMENT_BYTES (PAGE_SIZE * CMA_MIN_ALIGNMENT_PAGES) + struct cma; extern unsigned long totalcma_pages; @@ -50,4 +54,6 @@ extern bool cma_pages_valid(struct cma *cma, const struct page *pages, unsigned extern bool cma_release(struct cma *cma, const struct page *pages, unsigned long count); extern int cma_for_each_area(int (*it)(struct cma *cma, void *data), void *data); + +extern void cma_reserve_pages_on_error(struct cma *cma); #endif diff --git a/include/linux/comedi/comedi_8254.h b/include/linux/comedi/comedi_8254.h new file mode 100644 index 000000000000..d8264417e53c --- /dev/null +++ b/include/linux/comedi/comedi_8254.h @@ -0,0 +1,134 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * comedi_8254.h + * Generic 8254 timer/counter support + * Copyright (C) 2014 H Hartley Sweeten <hsweeten@visionengravers.com> + * + * COMEDI - Linux Control and Measurement Device Interface + * Copyright (C) 2000 David A. Schleef <ds@schleef.org> + */ + +#ifndef _COMEDI_8254_H +#define _COMEDI_8254_H + +#include <linux/types.h> + +struct comedi_device; +struct comedi_insn; +struct comedi_subdevice; + +/* + * Common oscillator base values in nanoseconds + */ +#define I8254_OSC_BASE_10MHZ 100 +#define I8254_OSC_BASE_5MHZ 200 +#define I8254_OSC_BASE_4MHZ 250 +#define I8254_OSC_BASE_2MHZ 500 +#define I8254_OSC_BASE_1MHZ 1000 +#define I8254_OSC_BASE_100KHZ 10000 +#define I8254_OSC_BASE_10KHZ 100000 +#define I8254_OSC_BASE_1KHZ 1000000 + +/* + * I/O access size used to read/write registers + */ +#define I8254_IO8 1 +#define I8254_IO16 2 +#define I8254_IO32 4 + +/* + * Register map for generic 8254 timer (I8254_IO8 with 0 regshift) + */ +#define I8254_COUNTER0_REG 0x00 +#define I8254_COUNTER1_REG 0x01 +#define I8254_COUNTER2_REG 0x02 +#define I8254_CTRL_REG 0x03 +#define I8254_CTRL_SEL_CTR(x) ((x) << 6) +#define I8254_CTRL_READBACK(x) (I8254_CTRL_SEL_CTR(3) | BIT(x)) +#define I8254_CTRL_READBACK_COUNT I8254_CTRL_READBACK(4) +#define I8254_CTRL_READBACK_STATUS I8254_CTRL_READBACK(5) +#define I8254_CTRL_READBACK_SEL_CTR(x) (2 << (x)) +#define I8254_CTRL_RW(x) (((x) & 0x3) << 4) +#define I8254_CTRL_LATCH I8254_CTRL_RW(0) +#define I8254_CTRL_LSB_ONLY I8254_CTRL_RW(1) +#define I8254_CTRL_MSB_ONLY I8254_CTRL_RW(2) +#define I8254_CTRL_LSB_MSB I8254_CTRL_RW(3) + +/* counter maps zero to 0x10000 */ +#define I8254_MAX_COUNT 0x10000 + +/** + * struct comedi_8254 - private data used by this module + * @iobase: PIO base address of the registers (in/out) + * @mmio: MMIO base address of the registers (read/write) + * @iosize: I/O size used to access the registers (b/w/l) + * @regshift: register gap shift + * @osc_base: cascaded oscillator speed in ns + * @divisor: divisor for single counter + * @divisor1: divisor loaded into first cascaded counter + * @divisor2: divisor loaded into second cascaded counter + * #next_div: next divisor for single counter + * @next_div1: next divisor to use for first cascaded counter + * @next_div2: next divisor to use for second cascaded counter + * @clock_src; current clock source for each counter (driver specific) + * @gate_src; current gate source for each counter (driver specific) + * @busy: flags used to indicate that a counter is "busy" + * @insn_config: driver specific (*insn_config) callback + */ +struct comedi_8254 { + unsigned long iobase; + void __iomem *mmio; + unsigned int iosize; + unsigned int regshift; + unsigned int osc_base; + unsigned int divisor; + unsigned int divisor1; + unsigned int divisor2; + unsigned int next_div; + unsigned int next_div1; + unsigned int next_div2; + unsigned int clock_src[3]; + unsigned int gate_src[3]; + bool busy[3]; + + int (*insn_config)(struct comedi_device *dev, + struct comedi_subdevice *s, + struct comedi_insn *insn, unsigned int *data); +}; + +unsigned int comedi_8254_status(struct comedi_8254 *i8254, + unsigned int counter); +unsigned int comedi_8254_read(struct comedi_8254 *i8254, unsigned int counter); +void comedi_8254_write(struct comedi_8254 *i8254, + unsigned int counter, unsigned int val); + +int comedi_8254_set_mode(struct comedi_8254 *i8254, + unsigned int counter, unsigned int mode); +int comedi_8254_load(struct comedi_8254 *i8254, + unsigned int counter, unsigned int val, unsigned int mode); + +void comedi_8254_pacer_enable(struct comedi_8254 *i8254, + unsigned int counter1, unsigned int counter2, + bool enable); +void comedi_8254_update_divisors(struct comedi_8254 *i8254); +void comedi_8254_cascade_ns_to_timer(struct comedi_8254 *i8254, + unsigned int *nanosec, unsigned int flags); +void comedi_8254_ns_to_timer(struct comedi_8254 *i8254, + unsigned int *nanosec, unsigned int flags); + +void comedi_8254_set_busy(struct comedi_8254 *i8254, + unsigned int counter, bool busy); + +void comedi_8254_subdevice_init(struct comedi_subdevice *s, + struct comedi_8254 *i8254); + +struct comedi_8254 *comedi_8254_init(unsigned long iobase, + unsigned int osc_base, + unsigned int iosize, + unsigned int regshift); +struct comedi_8254 *comedi_8254_mm_init(void __iomem *mmio, + unsigned int osc_base, + unsigned int iosize, + unsigned int regshift); + +#endif /* _COMEDI_8254_H */ diff --git a/include/linux/comedi/comedi_8255.h b/include/linux/comedi/comedi_8255.h new file mode 100644 index 000000000000..b2a5bc6b3a49 --- /dev/null +++ b/include/linux/comedi/comedi_8255.h @@ -0,0 +1,42 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * comedi_8255.h + * Generic 8255 digital I/O subdevice support + * + * COMEDI - Linux Control and Measurement Device Interface + * Copyright (C) 1998 David A. Schleef <ds@schleef.org> + */ + +#ifndef _COMEDI_8255_H +#define _COMEDI_8255_H + +#define I8255_SIZE 0x04 + +#define I8255_DATA_A_REG 0x00 +#define I8255_DATA_B_REG 0x01 +#define I8255_DATA_C_REG 0x02 +#define I8255_CTRL_REG 0x03 +#define I8255_CTRL_C_LO_IO BIT(0) +#define I8255_CTRL_B_IO BIT(1) +#define I8255_CTRL_B_MODE BIT(2) +#define I8255_CTRL_C_HI_IO BIT(3) +#define I8255_CTRL_A_IO BIT(4) +#define I8255_CTRL_A_MODE(x) ((x) << 5) +#define I8255_CTRL_CW BIT(7) + +struct comedi_device; +struct comedi_subdevice; + +int subdev_8255_init(struct comedi_device *dev, struct comedi_subdevice *s, + int (*io)(struct comedi_device *dev, int dir, int port, + int data, unsigned long regbase), + unsigned long regbase); + +int subdev_8255_mm_init(struct comedi_device *dev, struct comedi_subdevice *s, + int (*io)(struct comedi_device *dev, int dir, int port, + int data, unsigned long regbase), + unsigned long regbase); + +unsigned long subdev_8255_regbase(struct comedi_subdevice *s); + +#endif diff --git a/include/linux/comedi/comedi_isadma.h b/include/linux/comedi/comedi_isadma.h new file mode 100644 index 000000000000..9d2b12db7e6e --- /dev/null +++ b/include/linux/comedi/comedi_isadma.h @@ -0,0 +1,114 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * COMEDI ISA DMA support functions + * Copyright (c) 2014 H Hartley Sweeten <hsweeten@visionengravers.com> + */ + +#ifndef _COMEDI_ISADMA_H +#define _COMEDI_ISADMA_H + +#include <linux/types.h> + +struct comedi_device; +struct device; + +/* + * These are used to avoid issues when <asm/dma.h> and the DMA_MODE_ + * defines are not available. + */ +#define COMEDI_ISADMA_READ 0 +#define COMEDI_ISADMA_WRITE 1 + +/** + * struct comedi_isadma_desc - cookie for ISA DMA + * @virt_addr: virtual address of buffer + * @hw_addr: hardware (bus) address of buffer + * @chan: DMA channel + * @maxsize: allocated size of buffer (in bytes) + * @size: transfer size (in bytes) + * @mode: DMA_MODE_READ or DMA_MODE_WRITE + */ +struct comedi_isadma_desc { + void *virt_addr; + dma_addr_t hw_addr; + unsigned int chan; + unsigned int maxsize; + unsigned int size; + char mode; +}; + +/** + * struct comedi_isadma - ISA DMA data + * @dev: device to allocate non-coherent memory for + * @desc: cookie for each DMA buffer + * @n_desc: the number of cookies + * @cur_dma: the current cookie in use + * @chan: the first DMA channel requested + * @chan2: the second DMA channel requested + */ +struct comedi_isadma { + struct device *dev; + struct comedi_isadma_desc *desc; + int n_desc; + int cur_dma; + unsigned int chan; + unsigned int chan2; +}; + +#if IS_ENABLED(CONFIG_ISA_DMA_API) + +void comedi_isadma_program(struct comedi_isadma_desc *desc); +unsigned int comedi_isadma_disable(unsigned int dma_chan); +unsigned int comedi_isadma_disable_on_sample(unsigned int dma_chan, + unsigned int size); +unsigned int comedi_isadma_poll(struct comedi_isadma *dma); +void comedi_isadma_set_mode(struct comedi_isadma_desc *desc, char dma_dir); + +struct comedi_isadma *comedi_isadma_alloc(struct comedi_device *dev, + int n_desc, unsigned int dma_chan1, + unsigned int dma_chan2, + unsigned int maxsize, char dma_dir); +void comedi_isadma_free(struct comedi_isadma *dma); + +#else /* !IS_ENABLED(CONFIG_ISA_DMA_API) */ + +static inline void comedi_isadma_program(struct comedi_isadma_desc *desc) +{ +} + +static inline unsigned int comedi_isadma_disable(unsigned int dma_chan) +{ + return 0; +} + +static inline unsigned int +comedi_isadma_disable_on_sample(unsigned int dma_chan, unsigned int size) +{ + return 0; +} + +static inline unsigned int comedi_isadma_poll(struct comedi_isadma *dma) +{ + return 0; +} + +static inline void comedi_isadma_set_mode(struct comedi_isadma_desc *desc, + char dma_dir) +{ +} + +static inline struct comedi_isadma * +comedi_isadma_alloc(struct comedi_device *dev, int n_desc, + unsigned int dma_chan1, unsigned int dma_chan2, + unsigned int maxsize, char dma_dir) +{ + return NULL; +} + +static inline void comedi_isadma_free(struct comedi_isadma *dma) +{ +} + +#endif /* !IS_ENABLED(CONFIG_ISA_DMA_API) */ + +#endif /* #ifndef _COMEDI_ISADMA_H */ diff --git a/include/linux/comedi/comedi_pci.h b/include/linux/comedi/comedi_pci.h new file mode 100644 index 000000000000..2fb50663e3ed --- /dev/null +++ b/include/linux/comedi/comedi_pci.h @@ -0,0 +1,56 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * comedi_pci.h + * header file for Comedi PCI drivers + * + * COMEDI - Linux Control and Measurement Device Interface + * Copyright (C) 1997-2000 David A. Schleef <ds@schleef.org> + */ + +#ifndef _COMEDI_PCI_H +#define _COMEDI_PCI_H + +#include <linux/pci.h> +#include <linux/comedi/comedidev.h> + +/* + * PCI Vendor IDs not in <linux/pci_ids.h> + */ +#define PCI_VENDOR_ID_KOLTER 0x1001 +#define PCI_VENDOR_ID_ICP 0x104c +#define PCI_VENDOR_ID_DT 0x1116 +#define PCI_VENDOR_ID_IOTECH 0x1616 +#define PCI_VENDOR_ID_CONTEC 0x1221 +#define PCI_VENDOR_ID_RTD 0x1435 +#define PCI_VENDOR_ID_HUMUSOFT 0x186c + +struct pci_dev *comedi_to_pci_dev(struct comedi_device *dev); + +int comedi_pci_enable(struct comedi_device *dev); +void comedi_pci_disable(struct comedi_device *dev); +void comedi_pci_detach(struct comedi_device *dev); + +int comedi_pci_auto_config(struct pci_dev *pcidev, struct comedi_driver *driver, + unsigned long context); +void comedi_pci_auto_unconfig(struct pci_dev *pcidev); + +int comedi_pci_driver_register(struct comedi_driver *comedi_driver, + struct pci_driver *pci_driver); +void comedi_pci_driver_unregister(struct comedi_driver *comedi_driver, + struct pci_driver *pci_driver); + +/** + * module_comedi_pci_driver() - Helper macro for registering a comedi PCI driver + * @__comedi_driver: comedi_driver struct + * @__pci_driver: pci_driver struct + * + * Helper macro for comedi PCI drivers which do not do anything special + * in module init/exit. This eliminates a lot of boilerplate. Each + * module may only use this macro once, and calling it replaces + * module_init() and module_exit() + */ +#define module_comedi_pci_driver(__comedi_driver, __pci_driver) \ + module_driver(__comedi_driver, comedi_pci_driver_register, \ + comedi_pci_driver_unregister, &(__pci_driver)) + +#endif /* _COMEDI_PCI_H */ diff --git a/include/linux/comedi/comedi_pcmcia.h b/include/linux/comedi/comedi_pcmcia.h new file mode 100644 index 000000000000..a33dfb65b869 --- /dev/null +++ b/include/linux/comedi/comedi_pcmcia.h @@ -0,0 +1,48 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * comedi_pcmcia.h + * header file for Comedi PCMCIA drivers + * + * COMEDI - Linux Control and Measurement Device Interface + * Copyright (C) 1997-2000 David A. Schleef <ds@schleef.org> + */ + +#ifndef _COMEDI_PCMCIA_H +#define _COMEDI_PCMCIA_H + +#include <pcmcia/cistpl.h> +#include <pcmcia/ds.h> +#include <linux/comedi/comedidev.h> + +struct pcmcia_device *comedi_to_pcmcia_dev(struct comedi_device *dev); + +int comedi_pcmcia_enable(struct comedi_device *dev, + int (*conf_check)(struct pcmcia_device *p_dev, + void *priv_data)); +void comedi_pcmcia_disable(struct comedi_device *dev); + +int comedi_pcmcia_auto_config(struct pcmcia_device *link, + struct comedi_driver *driver); +void comedi_pcmcia_auto_unconfig(struct pcmcia_device *link); + +int comedi_pcmcia_driver_register(struct comedi_driver *comedi_driver, + struct pcmcia_driver *pcmcia_driver); +void comedi_pcmcia_driver_unregister(struct comedi_driver *comedi_driver, + struct pcmcia_driver *pcmcia_driver); + +/** + * module_comedi_pcmcia_driver() - Helper macro for registering a comedi + * PCMCIA driver + * @__comedi_driver: comedi_driver struct + * @__pcmcia_driver: pcmcia_driver struct + * + * Helper macro for comedi PCMCIA drivers which do not do anything special + * in module init/exit. This eliminates a lot of boilerplate. Each + * module may only use this macro once, and calling it replaces + * module_init() and module_exit() + */ +#define module_comedi_pcmcia_driver(__comedi_driver, __pcmcia_driver) \ + module_driver(__comedi_driver, comedi_pcmcia_driver_register, \ + comedi_pcmcia_driver_unregister, &(__pcmcia_driver)) + +#endif /* _COMEDI_PCMCIA_H */ diff --git a/include/linux/comedi/comedi_usb.h b/include/linux/comedi/comedi_usb.h new file mode 100644 index 000000000000..5d17dd425bd2 --- /dev/null +++ b/include/linux/comedi/comedi_usb.h @@ -0,0 +1,41 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* comedi_usb.h + * header file for USB Comedi drivers + * + * COMEDI - Linux Control and Measurement Device Interface + * Copyright (C) 1997-2000 David A. Schleef <ds@schleef.org> + */ + +#ifndef _COMEDI_USB_H +#define _COMEDI_USB_H + +#include <linux/usb.h> +#include <linux/comedi/comedidev.h> + +struct usb_interface *comedi_to_usb_interface(struct comedi_device *dev); +struct usb_device *comedi_to_usb_dev(struct comedi_device *dev); + +int comedi_usb_auto_config(struct usb_interface *intf, + struct comedi_driver *driver, unsigned long context); +void comedi_usb_auto_unconfig(struct usb_interface *intf); + +int comedi_usb_driver_register(struct comedi_driver *comedi_driver, + struct usb_driver *usb_driver); +void comedi_usb_driver_unregister(struct comedi_driver *comedi_driver, + struct usb_driver *usb_driver); + +/** + * module_comedi_usb_driver() - Helper macro for registering a comedi USB driver + * @__comedi_driver: comedi_driver struct + * @__usb_driver: usb_driver struct + * + * Helper macro for comedi USB drivers which do not do anything special + * in module init/exit. This eliminates a lot of boilerplate. Each + * module may only use this macro once, and calling it replaces + * module_init() and module_exit() + */ +#define module_comedi_usb_driver(__comedi_driver, __usb_driver) \ + module_driver(__comedi_driver, comedi_usb_driver_register, \ + comedi_usb_driver_unregister, &(__usb_driver)) + +#endif /* _COMEDI_USB_H */ diff --git a/include/linux/comedi/comedidev.h b/include/linux/comedi/comedidev.h new file mode 100644 index 000000000000..0a1150900ef3 --- /dev/null +++ b/include/linux/comedi/comedidev.h @@ -0,0 +1,1053 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * comedidev.h + * header file for kernel-only structures, variables, and constants + * + * COMEDI - Linux Control and Measurement Device Interface + * Copyright (C) 1997-2000 David A. Schleef <ds@schleef.org> + */ + +#ifndef _COMEDIDEV_H +#define _COMEDIDEV_H + +#include <linux/dma-mapping.h> +#include <linux/mutex.h> +#include <linux/spinlock_types.h> +#include <linux/rwsem.h> +#include <linux/kref.h> +#include <linux/comedi.h> + +#define COMEDI_VERSION(a, b, c) (((a) << 16) + ((b) << 8) + (c)) +#define COMEDI_VERSION_CODE COMEDI_VERSION(COMEDI_MAJORVERSION, \ + COMEDI_MINORVERSION, COMEDI_MICROVERSION) +#define COMEDI_RELEASE VERSION + +#define COMEDI_NUM_BOARD_MINORS 0x30 + +/** + * struct comedi_subdevice - Working data for a COMEDI subdevice + * @device: COMEDI device to which this subdevice belongs. (Initialized by + * comedi_alloc_subdevices().) + * @index: Index of this subdevice within device's array of subdevices. + * (Initialized by comedi_alloc_subdevices().) + * @type: Type of subdevice from &enum comedi_subdevice_type. (Initialized by + * the low-level driver.) + * @n_chan: Number of channels the subdevice supports. (Initialized by the + * low-level driver.) + * @subdev_flags: Various "SDF" flags indicating aspects of the subdevice to + * the COMEDI core and user application. (Initialized by the low-level + * driver.) + * @len_chanlist: Maximum length of a channel list if the subdevice supports + * asynchronous acquisition commands. (Optionally initialized by the + * low-level driver, or changed from 0 to 1 during post-configuration.) + * @private: Private data pointer which is either set by the low-level driver + * itself, or by a call to comedi_alloc_spriv() which allocates storage. + * In the latter case, the storage is automatically freed after the + * low-level driver's "detach" handler is called for the device. + * (Initialized by the low-level driver.) + * @async: Pointer to &struct comedi_async id the subdevice supports + * asynchronous acquisition commands. (Allocated and initialized during + * post-configuration if needed.) + * @lock: Pointer to a file object that performed a %COMEDI_LOCK ioctl on the + * subdevice. (Initially NULL.) + * @busy: Pointer to a file object that is performing an asynchronous + * acquisition command on the subdevice. (Initially NULL.) + * @runflags: Internal flags for use by COMEDI core, mostly indicating whether + * an asynchronous acquisition command is running. + * @spin_lock: Generic spin-lock for use by the COMEDI core and the low-level + * driver. (Initialized by comedi_alloc_subdevices().) + * @io_bits: Bit-mask indicating the channel directions for a DIO subdevice + * with no more than 32 channels. A '1' at a bit position indicates the + * corresponding channel is configured as an output. (Initialized by the + * low-level driver for a DIO subdevice. Forced to all-outputs during + * post-configuration for a digital output subdevice.) + * @maxdata: If non-zero, this is the maximum raw data value of each channel. + * If zero, the maximum data value is channel-specific. (Initialized by + * the low-level driver.) + * @maxdata_list: If the maximum data value is channel-specific, this points + * to an array of maximum data values indexed by channel index. + * (Initialized by the low-level driver.) + * @range_table: If non-NULL, this points to a COMEDI range table for the + * subdevice. If NULL, the range table is channel-specific. (Initialized + * by the low-level driver, will be set to an "invalid" range table during + * post-configuration if @range_table and @range_table_list are both + * NULL.) + * @range_table_list: If the COMEDI range table is channel-specific, this + * points to an array of pointers to COMEDI range tables indexed by + * channel number. (Initialized by the low-level driver.) + * @chanlist: Not used. + * @insn_read: Optional pointer to a handler for the %INSN_READ instruction. + * (Initialized by the low-level driver, or set to a default handler + * during post-configuration.) + * @insn_write: Optional pointer to a handler for the %INSN_WRITE instruction. + * (Initialized by the low-level driver, or set to a default handler + * during post-configuration.) + * @insn_bits: Optional pointer to a handler for the %INSN_BITS instruction + * for a digital input, digital output or digital input/output subdevice. + * (Initialized by the low-level driver, or set to a default handler + * during post-configuration.) + * @insn_config: Optional pointer to a handler for the %INSN_CONFIG + * instruction. (Initialized by the low-level driver, or set to a default + * handler during post-configuration.) + * @do_cmd: If the subdevice supports asynchronous acquisition commands, this + * points to a handler to set it up in hardware. (Initialized by the + * low-level driver.) + * @do_cmdtest: If the subdevice supports asynchronous acquisition commands, + * this points to a handler used to check and possibly tweak a prospective + * acquisition command without setting it up in hardware. (Initialized by + * the low-level driver.) + * @poll: If the subdevice supports asynchronous acquisition commands, this + * is an optional pointer to a handler for the %COMEDI_POLL ioctl which + * instructs the low-level driver to synchronize buffers. (Initialized by + * the low-level driver if needed.) + * @cancel: If the subdevice supports asynchronous acquisition commands, this + * points to a handler used to terminate a running command. (Initialized + * by the low-level driver.) + * @buf_change: If the subdevice supports asynchronous acquisition commands, + * this is an optional pointer to a handler that is called when the data + * buffer for handling asynchronous commands is allocated or reallocated. + * (Initialized by the low-level driver if needed.) + * @munge: If the subdevice supports asynchronous acquisition commands and + * uses DMA to transfer data from the hardware to the acquisition buffer, + * this points to a function used to "munge" the data values from the + * hardware into the format expected by COMEDI. (Initialized by the + * low-level driver if needed.) + * @async_dma_dir: If the subdevice supports asynchronous acquisition commands + * and uses DMA to transfer data from the hardware to the acquisition + * buffer, this sets the DMA direction for the buffer. (initialized to + * %DMA_NONE by comedi_alloc_subdevices() and changed by the low-level + * driver if necessary.) + * @state: Handy bit-mask indicating the output states for a DIO or digital + * output subdevice with no more than 32 channels. (Initialized by the + * low-level driver.) + * @class_dev: If the subdevice supports asynchronous acquisition commands, + * this points to a sysfs comediX_subdY device where X is the minor device + * number of the COMEDI device and Y is the subdevice number. The minor + * device number for the sysfs device is allocated dynamically in the + * range 48 to 255. This is used to allow the COMEDI device to be opened + * with a different default read or write subdevice. (Allocated during + * post-configuration if needed.) + * @minor: If @class_dev is set, this is its dynamically allocated minor + * device number. (Set during post-configuration if necessary.) + * @readback: Optional pointer to memory allocated by + * comedi_alloc_subdev_readback() used to hold the values written to + * analog output channels so they can be read back. The storage is + * automatically freed after the low-level driver's "detach" handler is + * called for the device. (Initialized by the low-level driver.) + * + * This is the main control structure for a COMEDI subdevice. If the subdevice + * supports asynchronous acquisition commands, additional information is stored + * in the &struct comedi_async pointed to by @async. + * + * Most of the subdevice is initialized by the low-level driver's "attach" or + * "auto_attach" handlers but parts of it are initialized by + * comedi_alloc_subdevices(), and other parts are initialized during + * post-configuration on return from that handler. + * + * A low-level driver that sets @insn_bits for a digital input, digital output, + * or DIO subdevice may leave @insn_read and @insn_write uninitialized, in + * which case they will be set to a default handler during post-configuration + * that uses @insn_bits to emulate the %INSN_READ and %INSN_WRITE instructions. + */ +struct comedi_subdevice { + struct comedi_device *device; + int index; + int type; + int n_chan; + int subdev_flags; + int len_chanlist; /* maximum length of channel/gain list */ + + void *private; + + struct comedi_async *async; + + void *lock; + void *busy; + unsigned int runflags; + spinlock_t spin_lock; /* generic spin-lock for COMEDI and drivers */ + + unsigned int io_bits; + + unsigned int maxdata; /* if maxdata==0, use list */ + const unsigned int *maxdata_list; /* list is channel specific */ + + const struct comedi_lrange *range_table; + const struct comedi_lrange *const *range_table_list; + + unsigned int *chanlist; /* driver-owned chanlist (not used) */ + + int (*insn_read)(struct comedi_device *dev, struct comedi_subdevice *s, + struct comedi_insn *insn, unsigned int *data); + int (*insn_write)(struct comedi_device *dev, struct comedi_subdevice *s, + struct comedi_insn *insn, unsigned int *data); + int (*insn_bits)(struct comedi_device *dev, struct comedi_subdevice *s, + struct comedi_insn *insn, unsigned int *data); + int (*insn_config)(struct comedi_device *dev, + struct comedi_subdevice *s, + struct comedi_insn *insn, + unsigned int *data); + + int (*do_cmd)(struct comedi_device *dev, struct comedi_subdevice *s); + int (*do_cmdtest)(struct comedi_device *dev, + struct comedi_subdevice *s, + struct comedi_cmd *cmd); + int (*poll)(struct comedi_device *dev, struct comedi_subdevice *s); + int (*cancel)(struct comedi_device *dev, struct comedi_subdevice *s); + + /* called when the buffer changes */ + int (*buf_change)(struct comedi_device *dev, + struct comedi_subdevice *s); + + void (*munge)(struct comedi_device *dev, struct comedi_subdevice *s, + void *data, unsigned int num_bytes, + unsigned int start_chan_index); + enum dma_data_direction async_dma_dir; + + unsigned int state; + + struct device *class_dev; + int minor; + + unsigned int *readback; +}; + +/** + * struct comedi_buf_page - Describe a page of a COMEDI buffer + * @virt_addr: Kernel address of page. + * @dma_addr: DMA address of page if in DMA coherent memory. + */ +struct comedi_buf_page { + void *virt_addr; + dma_addr_t dma_addr; +}; + +/** + * struct comedi_buf_map - Describe pages in a COMEDI buffer + * @dma_hw_dev: Low-level hardware &struct device pointer copied from the + * COMEDI device's hw_dev member. + * @page_list: Pointer to array of &struct comedi_buf_page, one for each + * page in the buffer. + * @n_pages: Number of pages in the buffer. + * @dma_dir: DMA direction used to allocate pages of DMA coherent memory, + * or %DMA_NONE if pages allocated from regular memory. + * @refcount: &struct kref reference counter used to free the buffer. + * + * A COMEDI data buffer is allocated as individual pages, either in + * conventional memory or DMA coherent memory, depending on the attached, + * low-level hardware device. (The buffer pages also get mapped into the + * kernel's contiguous virtual address space pointed to by the 'prealloc_buf' + * member of &struct comedi_async.) + * + * The buffer is normally freed when the COMEDI device is detached from the + * low-level driver (which may happen due to device removal), but if it happens + * to be mmapped at the time, the pages cannot be freed until the buffer has + * been munmapped. That is what the reference counter is for. (The virtual + * address space pointed by 'prealloc_buf' is freed when the COMEDI device is + * detached.) + */ +struct comedi_buf_map { + struct device *dma_hw_dev; + struct comedi_buf_page *page_list; + unsigned int n_pages; + enum dma_data_direction dma_dir; + struct kref refcount; +}; + +/** + * struct comedi_async - Control data for asynchronous COMEDI commands + * @prealloc_buf: Kernel virtual address of allocated acquisition buffer. + * @prealloc_bufsz: Buffer size (in bytes). + * @buf_map: Map of buffer pages. + * @max_bufsize: Maximum allowed buffer size (in bytes). + * @buf_write_count: "Write completed" count (in bytes, modulo 2**32). + * @buf_write_alloc_count: "Allocated for writing" count (in bytes, + * modulo 2**32). + * @buf_read_count: "Read completed" count (in bytes, modulo 2**32). + * @buf_read_alloc_count: "Allocated for reading" count (in bytes, + * modulo 2**32). + * @buf_write_ptr: Buffer position for writer. + * @buf_read_ptr: Buffer position for reader. + * @cur_chan: Current position in chanlist for scan (for those drivers that + * use it). + * @scans_done: The number of scans completed. + * @scan_progress: Amount received or sent for current scan (in bytes). + * @munge_chan: Current position in chanlist for "munging". + * @munge_count: "Munge" count (in bytes, modulo 2**32). + * @munge_ptr: Buffer position for "munging". + * @events: Bit-vector of events that have occurred. + * @cmd: Details of comedi command in progress. + * @wait_head: Task wait queue for file reader or writer. + * @cb_mask: Bit-vector of events that should wake waiting tasks. + * @inttrig: Software trigger function for command, or NULL. + * + * Note about the ..._count and ..._ptr members: + * + * Think of the _Count values being integers of unlimited size, indexing + * into a buffer of infinite length (though only an advancing portion + * of the buffer of fixed length prealloc_bufsz is accessible at any + * time). Then: + * + * Buf_Read_Count <= Buf_Read_Alloc_Count <= Munge_Count <= + * Buf_Write_Count <= Buf_Write_Alloc_Count <= + * (Buf_Read_Count + prealloc_bufsz) + * + * (Those aren't the actual members, apart from prealloc_bufsz.) When the + * buffer is reset, those _Count values start at 0 and only increase in value, + * maintaining the above inequalities until the next time the buffer is + * reset. The buffer is divided into the following regions by the inequalities: + * + * [0, Buf_Read_Count): + * old region no longer accessible + * + * [Buf_Read_Count, Buf_Read_Alloc_Count): + * filled and munged region allocated for reading but not yet read + * + * [Buf_Read_Alloc_Count, Munge_Count): + * filled and munged region not yet allocated for reading + * + * [Munge_Count, Buf_Write_Count): + * filled region not yet munged + * + * [Buf_Write_Count, Buf_Write_Alloc_Count): + * unfilled region allocated for writing but not yet written + * + * [Buf_Write_Alloc_Count, Buf_Read_Count + prealloc_bufsz): + * unfilled region not yet allocated for writing + * + * [Buf_Read_Count + prealloc_bufsz, infinity): + * unfilled region not yet accessible + * + * Data needs to be written into the buffer before it can be read out, + * and may need to be converted (or "munged") between the two + * operations. Extra unfilled buffer space may need to allocated for + * writing (advancing Buf_Write_Alloc_Count) before new data is written. + * After writing new data, the newly filled space needs to be released + * (advancing Buf_Write_Count). This also results in the new data being + * "munged" (advancing Munge_Count). Before data is read out of the + * buffer, extra space may need to be allocated for reading (advancing + * Buf_Read_Alloc_Count). After the data has been read out, the space + * needs to be released (advancing Buf_Read_Count). + * + * The actual members, buf_read_count, buf_read_alloc_count, + * munge_count, buf_write_count, and buf_write_alloc_count take the + * value of the corresponding capitalized _Count values modulo 2^32 + * (UINT_MAX+1). Subtracting a "higher" _count value from a "lower" + * _count value gives the same answer as subtracting a "higher" _Count + * value from a lower _Count value because prealloc_bufsz < UINT_MAX+1. + * The modulo operation is done implicitly. + * + * The buf_read_ptr, munge_ptr, and buf_write_ptr members take the value + * of the corresponding capitalized _Count values modulo prealloc_bufsz. + * These correspond to byte indices in the physical buffer. The modulo + * operation is done by subtracting prealloc_bufsz when the value + * exceeds prealloc_bufsz (assuming prealloc_bufsz plus the increment is + * less than or equal to UINT_MAX). + */ +struct comedi_async { + void *prealloc_buf; + unsigned int prealloc_bufsz; + struct comedi_buf_map *buf_map; + unsigned int max_bufsize; + unsigned int buf_write_count; + unsigned int buf_write_alloc_count; + unsigned int buf_read_count; + unsigned int buf_read_alloc_count; + unsigned int buf_write_ptr; + unsigned int buf_read_ptr; + unsigned int cur_chan; + unsigned int scans_done; + unsigned int scan_progress; + unsigned int munge_chan; + unsigned int munge_count; + unsigned int munge_ptr; + unsigned int events; + struct comedi_cmd cmd; + wait_queue_head_t wait_head; + unsigned int cb_mask; + int (*inttrig)(struct comedi_device *dev, struct comedi_subdevice *s, + unsigned int x); +}; + +/** + * enum comedi_cb - &struct comedi_async callback "events" + * @COMEDI_CB_EOS: end-of-scan + * @COMEDI_CB_EOA: end-of-acquisition/output + * @COMEDI_CB_BLOCK: data has arrived, wakes up read() / write() + * @COMEDI_CB_EOBUF: DEPRECATED: end of buffer + * @COMEDI_CB_ERROR: card error during acquisition + * @COMEDI_CB_OVERFLOW: buffer overflow/underflow + * @COMEDI_CB_ERROR_MASK: events that indicate an error has occurred + * @COMEDI_CB_CANCEL_MASK: events that will cancel an async command + */ +enum comedi_cb { + COMEDI_CB_EOS = BIT(0), + COMEDI_CB_EOA = BIT(1), + COMEDI_CB_BLOCK = BIT(2), + COMEDI_CB_EOBUF = BIT(3), + COMEDI_CB_ERROR = BIT(4), + COMEDI_CB_OVERFLOW = BIT(5), + /* masks */ + COMEDI_CB_ERROR_MASK = (COMEDI_CB_ERROR | COMEDI_CB_OVERFLOW), + COMEDI_CB_CANCEL_MASK = (COMEDI_CB_EOA | COMEDI_CB_ERROR_MASK) +}; + +/** + * struct comedi_driver - COMEDI driver registration + * @driver_name: Name of driver. + * @module: Owning module. + * @attach: The optional "attach" handler for manually configured COMEDI + * devices. + * @detach: The "detach" handler for deconfiguring COMEDI devices. + * @auto_attach: The optional "auto_attach" handler for automatically + * configured COMEDI devices. + * @num_names: Optional number of "board names" supported. + * @board_name: Optional pointer to a pointer to a board name. The pointer + * to a board name is embedded in an element of a driver-defined array + * of static, read-only board type information. + * @offset: Optional size of each element of the driver-defined array of + * static, read-only board type information, i.e. the offset between each + * pointer to a board name. + * + * This is used with comedi_driver_register() and comedi_driver_unregister() to + * register and unregister a low-level COMEDI driver with the COMEDI core. + * + * If @num_names is non-zero, @board_name should be non-NULL, and @offset + * should be at least sizeof(*board_name). These are used by the handler for + * the %COMEDI_DEVCONFIG ioctl to match a hardware device and its driver by + * board name. If @num_names is zero, the %COMEDI_DEVCONFIG ioctl matches a + * hardware device and its driver by driver name. This is only useful if the + * @attach handler is set. If @num_names is non-zero, the driver's @attach + * handler will be called with the COMEDI device structure's board_ptr member + * pointing to the matched pointer to a board name within the driver's private + * array of static, read-only board type information. + * + * The @detach handler has two roles. If a COMEDI device was successfully + * configured by the @attach or @auto_attach handler, it is called when the + * device is being deconfigured (by the %COMEDI_DEVCONFIG ioctl, or due to + * unloading of the driver, or due to device removal). It is also called when + * the @attach or @auto_attach handler returns an error. Therefore, the + * @attach or @auto_attach handlers can defer clean-up on error until the + * @detach handler is called. If the @attach or @auto_attach handlers free + * any resources themselves, they must prevent the @detach handler from + * freeing the same resources. The @detach handler must not assume that all + * resources requested by the @attach or @auto_attach handler were + * successfully allocated. + */ +struct comedi_driver { + /* private: */ + struct comedi_driver *next; /* Next in list of COMEDI drivers. */ + /* public: */ + const char *driver_name; + struct module *module; + int (*attach)(struct comedi_device *dev, struct comedi_devconfig *it); + void (*detach)(struct comedi_device *dev); + int (*auto_attach)(struct comedi_device *dev, unsigned long context); + unsigned int num_names; + const char *const *board_name; + int offset; +}; + +/** + * struct comedi_device - Working data for a COMEDI device + * @use_count: Number of open file objects. + * @driver: Low-level COMEDI driver attached to this COMEDI device. + * @pacer: Optional pointer to a dynamically allocated acquisition pacer + * control. It is freed automatically after the COMEDI device is + * detached from the low-level driver. + * @private: Optional pointer to private data allocated by the low-level + * driver. It is freed automatically after the COMEDI device is + * detached from the low-level driver. + * @class_dev: Sysfs comediX device. + * @minor: Minor device number of COMEDI char device (0-47). + * @detach_count: Counter incremented every time the COMEDI device is detached. + * Used for checking a previous attachment is still valid. + * @hw_dev: Optional pointer to the low-level hardware &struct device. It is + * required for automatically configured COMEDI devices and optional for + * COMEDI devices configured by the %COMEDI_DEVCONFIG ioctl, although + * the bus-specific COMEDI functions only work if it is set correctly. + * It is also passed to dma_alloc_coherent() for COMEDI subdevices that + * have their 'async_dma_dir' member set to something other than + * %DMA_NONE. + * @board_name: Pointer to a COMEDI board name or a COMEDI driver name. When + * the low-level driver's "attach" handler is called by the handler for + * the %COMEDI_DEVCONFIG ioctl, it either points to a matched board name + * string if the 'num_names' member of the &struct comedi_driver is + * non-zero, otherwise it points to the low-level driver name string. + * When the low-lever driver's "auto_attach" handler is called for an + * automatically configured COMEDI device, it points to the low-level + * driver name string. The low-level driver is free to change it in its + * "attach" or "auto_attach" handler if it wishes. + * @board_ptr: Optional pointer to private, read-only board type information in + * the low-level driver. If the 'num_names' member of the &struct + * comedi_driver is non-zero, the handler for the %COMEDI_DEVCONFIG ioctl + * will point it to a pointer to a matched board name string within the + * driver's private array of static, read-only board type information when + * calling the driver's "attach" handler. The low-level driver is free to + * change it. + * @attached: Flag indicating that the COMEDI device is attached to a low-level + * driver. + * @ioenabled: Flag used to indicate that a PCI device has been enabled and + * its regions requested. + * @spinlock: Generic spin-lock for use by the low-level driver. + * @mutex: Generic mutex for use by the COMEDI core module. + * @attach_lock: &struct rw_semaphore used to guard against the COMEDI device + * being detached while an operation is in progress. The down_write() + * operation is only allowed while @mutex is held and is used when + * changing @attached and @detach_count and calling the low-level driver's + * "detach" handler. The down_read() operation is generally used without + * holding @mutex. + * @refcount: &struct kref reference counter for freeing COMEDI device. + * @n_subdevices: Number of COMEDI subdevices allocated by the low-level + * driver for this device. + * @subdevices: Dynamically allocated array of COMEDI subdevices. + * @mmio: Optional pointer to a remapped MMIO region set by the low-level + * driver. + * @iobase: Optional base of an I/O port region requested by the low-level + * driver. + * @iolen: Length of I/O port region requested at @iobase. + * @irq: Optional IRQ number requested by the low-level driver. + * @read_subdev: Optional pointer to a default COMEDI subdevice operated on by + * the read() file operation. Set by the low-level driver. + * @write_subdev: Optional pointer to a default COMEDI subdevice operated on by + * the write() file operation. Set by the low-level driver. + * @async_queue: Storage for fasync_helper(). + * @open: Optional pointer to a function set by the low-level driver to be + * called when @use_count changes from 0 to 1. + * @close: Optional pointer to a function set by the low-level driver to be + * called when @use_count changed from 1 to 0. + * @insn_device_config: Optional pointer to a handler for all sub-instructions + * except %INSN_DEVICE_CONFIG_GET_ROUTES of the %INSN_DEVICE_CONFIG + * instruction. If this is not initialized by the low-level driver, a + * default handler will be set during post-configuration. + * @get_valid_routes: Optional pointer to a handler for the + * %INSN_DEVICE_CONFIG_GET_ROUTES sub-instruction of the + * %INSN_DEVICE_CONFIG instruction set. If this is not initialized by the + * low-level driver, a default handler that copies zero routes back to the + * user will be used. + * + * This is the main control data structure for a COMEDI device (as far as the + * COMEDI core is concerned). There are two groups of COMEDI devices - + * "legacy" devices that are configured by the handler for the + * %COMEDI_DEVCONFIG ioctl, and automatically configured devices resulting + * from a call to comedi_auto_config() as a result of a bus driver probe in + * a low-level COMEDI driver. The "legacy" COMEDI devices are allocated + * during module initialization if the "comedi_num_legacy_minors" module + * parameter is non-zero and use minor device numbers from 0 to + * comedi_num_legacy_minors minus one. The automatically configured COMEDI + * devices are allocated on demand and use minor device numbers from + * comedi_num_legacy_minors to 47. + */ +struct comedi_device { + int use_count; + struct comedi_driver *driver; + struct comedi_8254 *pacer; + void *private; + + struct device *class_dev; + int minor; + unsigned int detach_count; + struct device *hw_dev; + + const char *board_name; + const void *board_ptr; + unsigned int attached:1; + unsigned int ioenabled:1; + spinlock_t spinlock; /* generic spin-lock for low-level driver */ + struct mutex mutex; /* generic mutex for COMEDI core */ + struct rw_semaphore attach_lock; + struct kref refcount; + + int n_subdevices; + struct comedi_subdevice *subdevices; + + /* dumb */ + void __iomem *mmio; + unsigned long iobase; + unsigned long iolen; + unsigned int irq; + + struct comedi_subdevice *read_subdev; + struct comedi_subdevice *write_subdev; + + struct fasync_struct *async_queue; + + int (*open)(struct comedi_device *dev); + void (*close)(struct comedi_device *dev); + int (*insn_device_config)(struct comedi_device *dev, + struct comedi_insn *insn, unsigned int *data); + unsigned int (*get_valid_routes)(struct comedi_device *dev, + unsigned int n_pairs, + unsigned int *pair_data); +}; + +/* + * function prototypes + */ + +void comedi_event(struct comedi_device *dev, struct comedi_subdevice *s); + +struct comedi_device *comedi_dev_get_from_minor(unsigned int minor); +int comedi_dev_put(struct comedi_device *dev); + +bool comedi_is_subdevice_running(struct comedi_subdevice *s); + +void *comedi_alloc_spriv(struct comedi_subdevice *s, size_t size); +void comedi_set_spriv_auto_free(struct comedi_subdevice *s); + +int comedi_check_chanlist(struct comedi_subdevice *s, + int n, + unsigned int *chanlist); + +/* range stuff */ + +#define RANGE(a, b) {(a) * 1e6, (b) * 1e6, 0} +#define RANGE_ext(a, b) {(a) * 1e6, (b) * 1e6, RF_EXTERNAL} +#define RANGE_mA(a, b) {(a) * 1e6, (b) * 1e6, UNIT_mA} +#define RANGE_unitless(a, b) {(a) * 1e6, (b) * 1e6, 0} +#define BIP_RANGE(a) {-(a) * 1e6, (a) * 1e6, 0} +#define UNI_RANGE(a) {0, (a) * 1e6, 0} + +extern const struct comedi_lrange range_bipolar10; +extern const struct comedi_lrange range_bipolar5; +extern const struct comedi_lrange range_bipolar2_5; +extern const struct comedi_lrange range_unipolar10; +extern const struct comedi_lrange range_unipolar5; +extern const struct comedi_lrange range_unipolar2_5; +extern const struct comedi_lrange range_0_20mA; +extern const struct comedi_lrange range_4_20mA; +extern const struct comedi_lrange range_0_32mA; +extern const struct comedi_lrange range_unknown; + +#define range_digital range_unipolar5 + +/** + * struct comedi_lrange - Describes a COMEDI range table + * @length: Number of entries in the range table. + * @range: Array of &struct comedi_krange, one for each range. + * + * Each element of @range[] describes the minimum and maximum physical range + * and the type of units. Typically, the type of unit is %UNIT_volt + * (i.e. volts) and the minimum and maximum are in millionths of a volt. + * There may also be a flag that indicates the minimum and maximum are merely + * scale factors for an unknown, external reference. + */ +struct comedi_lrange { + int length; + struct comedi_krange range[]; +}; + +/** + * comedi_range_is_bipolar() - Test if subdevice range is bipolar + * @s: COMEDI subdevice. + * @range: Index of range within a range table. + * + * Tests whether a range is bipolar by checking whether its minimum value + * is negative. + * + * Assumes @range is valid. Does not work for subdevices using a + * channel-specific range table list. + * + * Return: + * %true if the range is bipolar. + * %false if the range is unipolar. + */ +static inline bool comedi_range_is_bipolar(struct comedi_subdevice *s, + unsigned int range) +{ + return s->range_table->range[range].min < 0; +} + +/** + * comedi_range_is_unipolar() - Test if subdevice range is unipolar + * @s: COMEDI subdevice. + * @range: Index of range within a range table. + * + * Tests whether a range is unipolar by checking whether its minimum value + * is at least 0. + * + * Assumes @range is valid. Does not work for subdevices using a + * channel-specific range table list. + * + * Return: + * %true if the range is unipolar. + * %false if the range is bipolar. + */ +static inline bool comedi_range_is_unipolar(struct comedi_subdevice *s, + unsigned int range) +{ + return s->range_table->range[range].min >= 0; +} + +/** + * comedi_range_is_external() - Test if subdevice range is external + * @s: COMEDI subdevice. + * @range: Index of range within a range table. + * + * Tests whether a range is externally reference by checking whether its + * %RF_EXTERNAL flag is set. + * + * Assumes @range is valid. Does not work for subdevices using a + * channel-specific range table list. + * + * Return: + * %true if the range is external. + * %false if the range is internal. + */ +static inline bool comedi_range_is_external(struct comedi_subdevice *s, + unsigned int range) +{ + return !!(s->range_table->range[range].flags & RF_EXTERNAL); +} + +/** + * comedi_chan_range_is_bipolar() - Test if channel-specific range is bipolar + * @s: COMEDI subdevice. + * @chan: The channel number. + * @range: Index of range within a range table. + * + * Tests whether a range is bipolar by checking whether its minimum value + * is negative. + * + * Assumes @chan and @range are valid. Only works for subdevices with a + * channel-specific range table list. + * + * Return: + * %true if the range is bipolar. + * %false if the range is unipolar. + */ +static inline bool comedi_chan_range_is_bipolar(struct comedi_subdevice *s, + unsigned int chan, + unsigned int range) +{ + return s->range_table_list[chan]->range[range].min < 0; +} + +/** + * comedi_chan_range_is_unipolar() - Test if channel-specific range is unipolar + * @s: COMEDI subdevice. + * @chan: The channel number. + * @range: Index of range within a range table. + * + * Tests whether a range is unipolar by checking whether its minimum value + * is at least 0. + * + * Assumes @chan and @range are valid. Only works for subdevices with a + * channel-specific range table list. + * + * Return: + * %true if the range is unipolar. + * %false if the range is bipolar. + */ +static inline bool comedi_chan_range_is_unipolar(struct comedi_subdevice *s, + unsigned int chan, + unsigned int range) +{ + return s->range_table_list[chan]->range[range].min >= 0; +} + +/** + * comedi_chan_range_is_external() - Test if channel-specific range is external + * @s: COMEDI subdevice. + * @chan: The channel number. + * @range: Index of range within a range table. + * + * Tests whether a range is externally reference by checking whether its + * %RF_EXTERNAL flag is set. + * + * Assumes @chan and @range are valid. Only works for subdevices with a + * channel-specific range table list. + * + * Return: + * %true if the range is bipolar. + * %false if the range is unipolar. + */ +static inline bool comedi_chan_range_is_external(struct comedi_subdevice *s, + unsigned int chan, + unsigned int range) +{ + return !!(s->range_table_list[chan]->range[range].flags & RF_EXTERNAL); +} + +/** + * comedi_offset_munge() - Convert between offset binary and 2's complement + * @s: COMEDI subdevice. + * @val: Value to be converted. + * + * Toggles the highest bit of a sample value to toggle between offset binary + * and 2's complement. Assumes that @s->maxdata is a power of 2 minus 1. + * + * Return: The converted value. + */ +static inline unsigned int comedi_offset_munge(struct comedi_subdevice *s, + unsigned int val) +{ + return val ^ s->maxdata ^ (s->maxdata >> 1); +} + +/** + * comedi_bytes_per_sample() - Determine subdevice sample size + * @s: COMEDI subdevice. + * + * The sample size will be 4 (sizeof int) or 2 (sizeof short) depending on + * whether the %SDF_LSAMPL subdevice flag is set or not. + * + * Return: The subdevice sample size. + */ +static inline unsigned int comedi_bytes_per_sample(struct comedi_subdevice *s) +{ + return s->subdev_flags & SDF_LSAMPL ? sizeof(int) : sizeof(short); +} + +/** + * comedi_sample_shift() - Determine log2 of subdevice sample size + * @s: COMEDI subdevice. + * + * The sample size will be 4 (sizeof int) or 2 (sizeof short) depending on + * whether the %SDF_LSAMPL subdevice flag is set or not. The log2 of the + * sample size will be 2 or 1 and can be used as the right operand of a + * bit-shift operator to multiply or divide something by the sample size. + * + * Return: log2 of the subdevice sample size. + */ +static inline unsigned int comedi_sample_shift(struct comedi_subdevice *s) +{ + return s->subdev_flags & SDF_LSAMPL ? 2 : 1; +} + +/** + * comedi_bytes_to_samples() - Convert a number of bytes to a number of samples + * @s: COMEDI subdevice. + * @nbytes: Number of bytes + * + * Return: The number of bytes divided by the subdevice sample size. + */ +static inline unsigned int comedi_bytes_to_samples(struct comedi_subdevice *s, + unsigned int nbytes) +{ + return nbytes >> comedi_sample_shift(s); +} + +/** + * comedi_samples_to_bytes() - Convert a number of samples to a number of bytes + * @s: COMEDI subdevice. + * @nsamples: Number of samples. + * + * Return: The number of samples multiplied by the subdevice sample size. + * (Does not check for arithmetic overflow.) + */ +static inline unsigned int comedi_samples_to_bytes(struct comedi_subdevice *s, + unsigned int nsamples) +{ + return nsamples << comedi_sample_shift(s); +} + +/** + * comedi_check_trigger_src() - Trivially validate a comedi_cmd trigger source + * @src: Pointer to the trigger source to validate. + * @flags: Bitmask of valid %TRIG_* for the trigger. + * + * This is used in "step 1" of the do_cmdtest functions of comedi drivers + * to validate the comedi_cmd triggers. The mask of the @src against the + * @flags allows the userspace comedilib to pass all the comedi_cmd + * triggers as %TRIG_ANY and get back a bitmask of the valid trigger sources. + * + * Return: + * 0 if trigger sources in *@src are all supported. + * -EINVAL if any trigger source in *@src is unsupported. + */ +static inline int comedi_check_trigger_src(unsigned int *src, + unsigned int flags) +{ + unsigned int orig_src = *src; + + *src = orig_src & flags; + if (*src == TRIG_INVALID || *src != orig_src) + return -EINVAL; + return 0; +} + +/** + * comedi_check_trigger_is_unique() - Make sure a trigger source is unique + * @src: The trigger source to check. + * + * Return: + * 0 if no more than one trigger source is set. + * -EINVAL if more than one trigger source is set. + */ +static inline int comedi_check_trigger_is_unique(unsigned int src) +{ + /* this test is true if more than one _src bit is set */ + if ((src & (src - 1)) != 0) + return -EINVAL; + return 0; +} + +/** + * comedi_check_trigger_arg_is() - Trivially validate a trigger argument + * @arg: Pointer to the trigger arg to validate. + * @val: The value the argument should be. + * + * Forces *@arg to be @val. + * + * Return: + * 0 if *@arg was already @val. + * -EINVAL if *@arg differed from @val. + */ +static inline int comedi_check_trigger_arg_is(unsigned int *arg, + unsigned int val) +{ + if (*arg != val) { + *arg = val; + return -EINVAL; + } + return 0; +} + +/** + * comedi_check_trigger_arg_min() - Trivially validate a trigger argument min + * @arg: Pointer to the trigger arg to validate. + * @val: The minimum value the argument should be. + * + * Forces *@arg to be at least @val, setting it to @val if necessary. + * + * Return: + * 0 if *@arg was already at least @val. + * -EINVAL if *@arg was less than @val. + */ +static inline int comedi_check_trigger_arg_min(unsigned int *arg, + unsigned int val) +{ + if (*arg < val) { + *arg = val; + return -EINVAL; + } + return 0; +} + +/** + * comedi_check_trigger_arg_max() - Trivially validate a trigger argument max + * @arg: Pointer to the trigger arg to validate. + * @val: The maximum value the argument should be. + * + * Forces *@arg to be no more than @val, setting it to @val if necessary. + * + * Return: + * 0 if*@arg was already no more than @val. + * -EINVAL if *@arg was greater than @val. + */ +static inline int comedi_check_trigger_arg_max(unsigned int *arg, + unsigned int val) +{ + if (*arg > val) { + *arg = val; + return -EINVAL; + } + return 0; +} + +/* + * Must set dev->hw_dev if you wish to dma directly into comedi's buffer. + * Also useful for retrieving a previously configured hardware device of + * known bus type. Set automatically for auto-configured devices. + * Automatically set to NULL when detaching hardware device. + */ +int comedi_set_hw_dev(struct comedi_device *dev, struct device *hw_dev); + +/** + * comedi_buf_n_bytes_ready - Determine amount of unread data in buffer + * @s: COMEDI subdevice. + * + * Determines the number of bytes of unread data in the asynchronous + * acquisition data buffer for a subdevice. The data in question might not + * have been fully "munged" yet. + * + * Returns: The amount of unread data in bytes. + */ +static inline unsigned int comedi_buf_n_bytes_ready(struct comedi_subdevice *s) +{ + return s->async->buf_write_count - s->async->buf_read_count; +} + +unsigned int comedi_buf_write_alloc(struct comedi_subdevice *s, unsigned int n); +unsigned int comedi_buf_write_free(struct comedi_subdevice *s, unsigned int n); + +unsigned int comedi_buf_read_n_available(struct comedi_subdevice *s); +unsigned int comedi_buf_read_alloc(struct comedi_subdevice *s, unsigned int n); +unsigned int comedi_buf_read_free(struct comedi_subdevice *s, unsigned int n); + +unsigned int comedi_buf_write_samples(struct comedi_subdevice *s, + const void *data, unsigned int nsamples); +unsigned int comedi_buf_read_samples(struct comedi_subdevice *s, + void *data, unsigned int nsamples); + +/* drivers.c - general comedi driver functions */ + +#define COMEDI_TIMEOUT_MS 1000 + +int comedi_timeout(struct comedi_device *dev, struct comedi_subdevice *s, + struct comedi_insn *insn, + int (*cb)(struct comedi_device *dev, + struct comedi_subdevice *s, + struct comedi_insn *insn, unsigned long context), + unsigned long context); + +unsigned int comedi_handle_events(struct comedi_device *dev, + struct comedi_subdevice *s); + +int comedi_dio_insn_config(struct comedi_device *dev, + struct comedi_subdevice *s, + struct comedi_insn *insn, unsigned int *data, + unsigned int mask); +unsigned int comedi_dio_update_state(struct comedi_subdevice *s, + unsigned int *data); +unsigned int comedi_bytes_per_scan_cmd(struct comedi_subdevice *s, + struct comedi_cmd *cmd); +unsigned int comedi_bytes_per_scan(struct comedi_subdevice *s); +unsigned int comedi_nscans_left(struct comedi_subdevice *s, + unsigned int nscans); +unsigned int comedi_nsamples_left(struct comedi_subdevice *s, + unsigned int nsamples); +void comedi_inc_scan_progress(struct comedi_subdevice *s, + unsigned int num_bytes); + +void *comedi_alloc_devpriv(struct comedi_device *dev, size_t size); +int comedi_alloc_subdevices(struct comedi_device *dev, int num_subdevices); +int comedi_alloc_subdev_readback(struct comedi_subdevice *s); + +int comedi_readback_insn_read(struct comedi_device *dev, + struct comedi_subdevice *s, + struct comedi_insn *insn, unsigned int *data); + +int comedi_load_firmware(struct comedi_device *dev, struct device *hw_dev, + const char *name, + int (*cb)(struct comedi_device *dev, + const u8 *data, size_t size, + unsigned long context), + unsigned long context); + +int __comedi_request_region(struct comedi_device *dev, + unsigned long start, unsigned long len); +int comedi_request_region(struct comedi_device *dev, + unsigned long start, unsigned long len); +void comedi_legacy_detach(struct comedi_device *dev); + +int comedi_auto_config(struct device *hardware_device, + struct comedi_driver *driver, unsigned long context); +void comedi_auto_unconfig(struct device *hardware_device); + +int comedi_driver_register(struct comedi_driver *driver); +void comedi_driver_unregister(struct comedi_driver *driver); + +/** + * module_comedi_driver() - Helper macro for registering a comedi driver + * @__comedi_driver: comedi_driver struct + * + * Helper macro for comedi drivers which do not do anything special in module + * init/exit. This eliminates a lot of boilerplate. Each module may only use + * this macro once, and calling it replaces module_init() and module_exit(). + */ +#define module_comedi_driver(__comedi_driver) \ + module_driver(__comedi_driver, comedi_driver_register, \ + comedi_driver_unregister) + +#endif /* _COMEDIDEV_H */ diff --git a/include/linux/comedi/comedilib.h b/include/linux/comedi/comedilib.h new file mode 100644 index 000000000000..0223c9cd9215 --- /dev/null +++ b/include/linux/comedi/comedilib.h @@ -0,0 +1,26 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * comedilib.h + * Header file for kcomedilib + * + * COMEDI - Linux Control and Measurement Device Interface + * Copyright (C) 1998-2001 David A. Schleef <ds@schleef.org> + */ + +#ifndef _LINUX_COMEDILIB_H +#define _LINUX_COMEDILIB_H + +struct comedi_device *comedi_open(const char *path); +int comedi_close(struct comedi_device *dev); +int comedi_dio_get_config(struct comedi_device *dev, unsigned int subdev, + unsigned int chan, unsigned int *io); +int comedi_dio_config(struct comedi_device *dev, unsigned int subdev, + unsigned int chan, unsigned int io); +int comedi_dio_bitfield2(struct comedi_device *dev, unsigned int subdev, + unsigned int mask, unsigned int *bits, + unsigned int base_channel); +int comedi_find_subdevice_by_type(struct comedi_device *dev, int type, + unsigned int subd); +int comedi_get_n_channels(struct comedi_device *dev, unsigned int subdevice); + +#endif diff --git a/include/linux/compaction.h b/include/linux/compaction.h index 34bce35c808d..52a9ff65faee 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -177,7 +177,7 @@ static inline bool compaction_withdrawn(enum compact_result result) bool compaction_zonelist_suitable(struct alloc_context *ac, int order, int alloc_flags); -extern int kcompactd_run(int nid); +extern void kcompactd_run(int nid); extern void kcompactd_stop(int nid); extern void wakeup_kcompactd(pg_data_t *pgdat, int order, int highest_zoneidx); @@ -212,9 +212,8 @@ static inline bool compaction_withdrawn(enum compact_result result) return true; } -static inline int kcompactd_run(int nid) +static inline void kcompactd_run(int nid) { - return 0; } static inline void kcompactd_stop(int nid) { diff --git a/include/linux/compat.h b/include/linux/compat.h index 1c758b0e0359..594357881b0b 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -235,6 +235,7 @@ typedef struct compat_siginfo { struct { compat_ulong_t _data; u32 _type; + u32 _flags; } _perf; }; } _sigfault; @@ -258,6 +259,37 @@ struct compat_rlimit { compat_ulong_t rlim_max; }; +#ifdef __ARCH_NEED_COMPAT_FLOCK64_PACKED +#define __ARCH_COMPAT_FLOCK64_PACK __attribute__((packed)) +#else +#define __ARCH_COMPAT_FLOCK64_PACK +#endif + +struct compat_flock { + short l_type; + short l_whence; + compat_off_t l_start; + compat_off_t l_len; +#ifdef __ARCH_COMPAT_FLOCK_EXTRA_SYSID + __ARCH_COMPAT_FLOCK_EXTRA_SYSID +#endif + compat_pid_t l_pid; +#ifdef __ARCH_COMPAT_FLOCK_PAD + __ARCH_COMPAT_FLOCK_PAD +#endif +}; + +struct compat_flock64 { + short l_type; + short l_whence; + compat_loff_t l_start; + compat_loff_t l_len; + compat_pid_t l_pid; +#ifdef __ARCH_COMPAT_FLOCK64_PAD + __ARCH_COMPAT_FLOCK64_PAD +#endif +} __ARCH_COMPAT_FLOCK64_PACK; + struct compat_rusage { struct old_timeval32 ru_utime; struct old_timeval32 ru_stime; @@ -895,6 +927,43 @@ asmlinkage long compat_sys_sigaction(int sig, /* obsolete: net/socket.c */ asmlinkage long compat_sys_socketcall(int call, u32 __user *args); +#ifdef __ARCH_WANT_COMPAT_TRUNCATE64 +asmlinkage long compat_sys_truncate64(const char __user *pathname, compat_arg_u64(len)); +#endif + +#ifdef __ARCH_WANT_COMPAT_FTRUNCATE64 +asmlinkage long compat_sys_ftruncate64(unsigned int fd, compat_arg_u64(len)); +#endif + +#ifdef __ARCH_WANT_COMPAT_FALLOCATE +asmlinkage long compat_sys_fallocate(int fd, int mode, compat_arg_u64(offset), + compat_arg_u64(len)); +#endif + +#ifdef __ARCH_WANT_COMPAT_PREAD64 +asmlinkage long compat_sys_pread64(unsigned int fd, char __user *buf, size_t count, + compat_arg_u64(pos)); +#endif + +#ifdef __ARCH_WANT_COMPAT_PWRITE64 +asmlinkage long compat_sys_pwrite64(unsigned int fd, const char __user *buf, size_t count, + compat_arg_u64(pos)); +#endif + +#ifdef __ARCH_WANT_COMPAT_SYNC_FILE_RANGE +asmlinkage long compat_sys_sync_file_range(int fd, compat_arg_u64(pos), + compat_arg_u64(nbytes), unsigned int flags); +#endif + +#ifdef __ARCH_WANT_COMPAT_FADVISE64_64 +asmlinkage long compat_sys_fadvise64_64(int fd, compat_arg_u64(pos), + compat_arg_u64(len), int advice); +#endif + +#ifdef __ARCH_WANT_COMPAT_READAHEAD +asmlinkage long compat_sys_readahead(int fd, compat_arg_u64(offset), size_t count); +#endif + #endif /* CONFIG_ARCH_HAS_SYSCALL_WRAPPER */ /** diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h index 3c4de9b6c6e3..6cfd6902bd5b 100644 --- a/include/linux/compiler-clang.h +++ b/include/linux/compiler-clang.h @@ -51,6 +51,29 @@ #define __no_sanitize_undefined #endif +#if __has_feature(memory_sanitizer) +#define __SANITIZE_MEMORY__ +/* + * Unlike other sanitizers, KMSAN still inserts code into functions marked with + * no_sanitize("kernel-memory"). Using disable_sanitizer_instrumentation + * provides the behavior consistent with other __no_sanitize_ attributes, + * guaranteeing that __no_sanitize_memory functions remain uninstrumented. + */ +#define __no_sanitize_memory __disable_sanitizer_instrumentation + +/* + * The __no_kmsan_checks attribute ensures that a function does not produce + * false positive reports by: + * - initializing all local variables and memory stores in this function; + * - skipping all shadow checks; + * - passing initialized arguments to this function's callees. + */ +#define __no_kmsan_checks __attribute__((no_sanitize("kernel-memory"))) +#else +#define __no_sanitize_memory +#define __no_kmsan_checks +#endif + /* * Support for __has_feature(coverage_sanitizer) was added in Clang 13 together * with no_sanitize("coverage"). Prior versions of Clang support coverage @@ -66,5 +89,32 @@ # define __noscs __attribute__((__no_sanitize__("shadow-call-stack"))) #endif -#define __nocfi __attribute__((__no_sanitize__("cfi"))) -#define __cficanonical __attribute__((__cfi_canonical_jump_table__)) +#if __has_feature(kcfi) +/* Disable CFI checking inside a function. */ +#define __nocfi __attribute__((__no_sanitize__("kcfi"))) +#endif + +/* + * Turn individual warnings and errors on and off locally, depending + * on version. + */ +#define __diag_clang(version, severity, s) \ + __diag_clang_ ## version(__diag_clang_ ## severity s) + +/* Severity used in pragma directives */ +#define __diag_clang_ignore ignored +#define __diag_clang_warn warning +#define __diag_clang_error error + +#define __diag_str1(s) #s +#define __diag_str(s) __diag_str1(s) +#define __diag(s) _Pragma(__diag_str(clang diagnostic s)) + +#if CONFIG_CLANG_VERSION >= 110000 +#define __diag_clang_11(s) __diag(s) +#else +#define __diag_clang_11(s) +#endif + +#define __diag_ignore_all(option, comment) \ + __diag_clang(11, ignore, option) diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index ccbbd31b3aae..f55a37efdb97 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -66,25 +66,6 @@ __builtin_unreachable(); \ } while (0) -#if defined(RANDSTRUCT_PLUGIN) && !defined(__CHECKER__) -#define __randomize_layout __attribute__((randomize_layout)) -#define __no_randomize_layout __attribute__((no_randomize_layout)) -/* This anon struct can add padding, so only enable it under randstruct. */ -#define randomized_struct_fields_start struct { -#define randomized_struct_fields_end } __randomize_layout; -#endif - -/* - * GCC 'asm goto' miscompiles certain code sequences: - * - * http://gcc.gnu.org/bugzilla/show_bug.cgi?id=58670 - * - * Work it around via a compiler barrier quirk suggested by Jakub Jelinek. - * - * (asm goto is automatically volatile - the naming reflects this.) - */ -#define asm_volatile_goto(x...) do { asm goto(x); asm (""); } while (0) - #if defined(CONFIG_ARCH_USE_BUILTIN_BSWAP) #define __HAVE_BUILTIN_BSWAP32__ #define __HAVE_BUILTIN_BSWAP64__ @@ -97,6 +78,10 @@ #define KASAN_ABI_VERSION 4 #endif +#ifdef CONFIG_SHADOW_CALL_STACK +#define __noscs __attribute__((__no_sanitize__("shadow-call-stack"))) +#endif + #if __has_attribute(__no_sanitize_address__) #define __no_sanitize_address __attribute__((no_sanitize_address)) #else @@ -130,6 +115,12 @@ #endif /* + * GCC does not support KMSAN. + */ +#define __no_sanitize_memory +#define __no_kmsan_checks + +/* * Turn individual warnings and errors on and off locally, depending * on version. */ @@ -151,6 +142,9 @@ #define __diag_GCC_8(s) #endif +#define __diag_ignore_all(option, comment) \ + __diag_GCC(8, ignore, option) + /* * Prior to 9.1, -Wno-alloc-size-larger-than (and therefore the "alloc_size" * attribute) do not work, and must be disabled. diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 429dcebe2b99..973a1bfd7ef5 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -109,7 +109,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, #endif /* Unreachable code */ -#ifdef CONFIG_STACK_VALIDATION +#ifdef CONFIG_OBJTOOL /* * These macros help objtool understand GCC code flow for unreachable code. * The __COUNTER__ based labels are a hack to make each instance of the macros @@ -117,14 +117,6 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, */ #define __stringify_label(n) #n -#define __annotate_reachable(c) ({ \ - asm volatile(__stringify_label(c) ":\n\t" \ - ".pushsection .discard.reachable\n\t" \ - ".long " __stringify_label(c) "b - .\n\t" \ - ".popsection\n\t" : : "i" (c)); \ -}) -#define annotate_reachable() __annotate_reachable(__COUNTER__) - #define __annotate_unreachable(c) ({ \ asm volatile(__stringify_label(c) ":\n\t" \ ".pushsection .discard.unreachable\n\t" \ @@ -133,24 +125,14 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, }) #define annotate_unreachable() __annotate_unreachable(__COUNTER__) -#define ASM_UNREACHABLE \ - "999:\n\t" \ - ".pushsection .discard.unreachable\n\t" \ - ".long 999b - .\n\t" \ - ".popsection\n\t" - /* Annotate a C jump table to allow objtool to follow the code flow */ #define __annotate_jump_table __section(".rodata..c_jump_table") -#else -#define annotate_reachable() +#else /* !CONFIG_OBJTOOL */ #define annotate_unreachable() #define __annotate_jump_table -#endif +#endif /* CONFIG_OBJTOOL */ -#ifndef ASM_UNREACHABLE -# define ASM_UNREACHABLE -#endif #ifndef unreachable # define unreachable() do { \ annotate_unreachable(); \ @@ -221,16 +203,6 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, __v; \ }) -/* - * With CONFIG_CFI_CLANG, the compiler replaces function addresses in - * instrumented C code with jump table addresses. Architectures that - * support CFI can define this macro to return the actual function address - * when needed. - */ -#ifndef function_nocfi -#define function_nocfi(x) (x) -#endif - #endif /* __KERNEL__ */ /* @@ -239,9 +211,11 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, * otherwise, or eliminated entirely due to lack of references that are * visible to the compiler. */ -#define __ADDRESSABLE(sym) \ - static void * __section(".discard.addressable") __used \ +#define ___ADDRESSABLE(sym, __attrs) \ + static void * __used __attrs \ __UNIQUE_ID(__PASTE(__addressable_,sym)) = (void *)&sym; +#define __ADDRESSABLE(sym) \ + ___ADDRESSABLE(sym, __section(".discard.addressable")) /** * offset_to_ptr - convert a relative memory offset to an absolute pointer @@ -258,6 +232,12 @@ static inline void *offset_to_ptr(const int *off) #define __must_be_array(a) BUILD_BUG_ON_ZERO(__same_type((a), &(a)[0])) /* + * Whether 'type' is a signed type or an unsigned type. Supports scalar types, + * bool and also pointer types. + */ +#define is_signed_type(type) (((type)(-1)) < (__force type)1) + +/* * This is needed in functions which generate the stack canary, see * arch/x86/kernel/smpboot.c::start_secondary() for an example. */ diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h index 37e260020221..898b3458b24a 100644 --- a/include/linux/compiler_attributes.h +++ b/include/linux/compiler_attributes.h @@ -35,7 +35,8 @@ /* * Note: do not use this directly. Instead, use __alloc_size() since it is conditionally - * available and includes other attributes. + * available and includes other attributes. For GCC < 9.1, __alloc_size__ gets undefined + * in compiler-gcc.h, due to misbehaviors. * * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-alloc_005fsize-function-attribute * clang: https://clang.llvm.org/docs/AttributeReference.html#alloc-size @@ -101,6 +102,19 @@ #endif /* + * Optional: not supported by gcc + * Optional: only supported since clang >= 14.0 + * Optional: not supported by icc + * + * clang: https://clang.llvm.org/docs/AttributeReference.html#diagnose_as_builtin + */ +#if __has_attribute(__diagnose_as_builtin__) +# define __diagnose_as(builtin...) __attribute__((__diagnose_as_builtin__(builtin))) +#else +# define __diagnose_as(builtin...) +#endif + +/* * Don't. Just don't. See commit 771c035372a0 ("deprecate the '__deprecated' * attribute warnings entirely and for good") for more information. * @@ -258,12 +272,38 @@ #define __noreturn __attribute__((__noreturn__)) /* + * Optional: not supported by gcc. + * Optional: not supported by icc. + * + * clang: https://clang.llvm.org/docs/AttributeReference.html#overloadable + */ +#if __has_attribute(__overloadable__) +# define __overloadable __attribute__((__overloadable__)) +#else +# define __overloadable +#endif + +/* * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Type-Attributes.html#index-packed-type-attribute * clang: https://gcc.gnu.org/onlinedocs/gcc/Common-Variable-Attributes.html#index-packed-variable-attribute */ #define __packed __attribute__((__packed__)) /* + * Note: the "type" argument should match any __builtin_object_size(p, type) usage. + * + * Optional: not supported by gcc. + * Optional: not supported by icc. + * + * clang: https://clang.llvm.org/docs/AttributeReference.html#pass-object-size-pass-dynamic-object-size + */ +#if __has_attribute(__pass_object_size__) +# define __pass_object_size(type) __attribute__((__pass_object_size__(type))) +#else +# define __pass_object_size(type) +#endif + +/* * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-pure-function-attribute */ #define __pure __attribute__((__pure__)) @@ -332,4 +372,11 @@ */ #define __weak __attribute__((__weak__)) +/* + * Used by functions that use '__builtin_return_address'. These function + * don't want to be splited or made inline, which can make + * the '__builtin_return_address' get unexpected address. + */ +#define __fix_address noinline __noclone + #endif /* __LINUX_COMPILER_ATTRIBUTES_H */ diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 3c1795fdb568..eb0466236661 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -4,6 +4,18 @@ #ifndef __ASSEMBLY__ +/* + * Skipped when running bindgen due to a libclang issue; + * see https://github.com/rust-lang/rust-bindgen/issues/2244. + */ +#if defined(CONFIG_DEBUG_INFO_BTF) && defined(CONFIG_PAHOLE_HAS_BTF_TAG) && \ + __has_attribute(btf_type_tag) && !defined(__BINDGEN__) +# define BTF_TYPE_TAG(value) __attribute__((btf_type_tag(#value))) +#else +# define BTF_TYPE_TAG(value) /* nothing */ +#endif + +/* sparse defines __CHECKER__; see Documentation/dev-tools/sparse.rst */ #ifdef __CHECKER__ /* address spaces */ # define __kernel __attribute__((address_space(0))) @@ -16,6 +28,7 @@ static inline void __chk_io_ptr(const volatile void __iomem *ptr) { } /* context/locking */ # define __must_hold(x) __attribute__((context(x,1,1))) # define __acquires(x) __attribute__((context(x,0,1))) +# define __cond_acquires(x) __attribute__((context(x,0,-1))) # define __releases(x) __attribute__((context(x,1,0))) # define __acquire(x) __context__(x,1) # define __release(x) __context__(x,-1) @@ -32,16 +45,17 @@ static inline void __chk_io_ptr(const volatile void __iomem *ptr) { } # ifdef STRUCTLEAK_PLUGIN # define __user __attribute__((user)) # else -# define __user +# define __user BTF_TYPE_TAG(user) # endif # define __iomem -# define __percpu +# define __percpu BTF_TYPE_TAG(percpu) # define __rcu # define __chk_user_ptr(x) (void)0 # define __chk_io_ptr(x) (void)0 /* context/locking */ # define __must_hold(x) # define __acquires(x) +# define __cond_acquires(x) # define __releases(x) # define __acquire(x) (void)0 # define __release(x) (void)0 @@ -137,8 +151,6 @@ struct ftrace_likely_data { */ #define __naked __attribute__((__naked__)) notrace -#define __compiler_offsetof(a, b) __builtin_offsetof(a, b) - /* * Prefer gnu_inline, so that extern inline functions do not emit an * externally visible function. This makes extern inline behave as per gnu89 @@ -221,7 +233,8 @@ struct ftrace_likely_data { /* Section for code which can't be instrumented at all */ #define noinstr \ noinline notrace __attribute((__section__(".noinstr.text"))) \ - __no_kcsan __no_sanitize_address __no_profile __no_sanitize_coverage + __no_kcsan __no_sanitize_address __no_profile __no_sanitize_coverage \ + __no_sanitize_memory #endif /* __KERNEL__ */ @@ -236,15 +249,15 @@ struct ftrace_likely_data { # define __latent_entropy #endif -#ifndef __randomize_layout +#if defined(RANDSTRUCT) && !defined(__CHECKER__) +# define __randomize_layout __designated_init __attribute__((randomize_layout)) +# define __no_randomize_layout __attribute__((no_randomize_layout)) +/* This anon struct can add padding, so only enable it under randstruct. */ +# define randomized_struct_fields_start struct { +# define randomized_struct_fields_end } __randomize_layout; +#else # define __randomize_layout __designated_init -#endif - -#ifndef __no_randomize_layout # define __no_randomize_layout -#endif - -#ifndef randomized_struct_fields_start # define randomized_struct_fields_start # define randomized_struct_fields_end #endif @@ -257,20 +270,18 @@ struct ftrace_likely_data { # define __nocfi #endif -#ifndef __cficanonical -# define __cficanonical -#endif - /* * Any place that could be marked with the "alloc_size" attribute is also - * a place to be marked with the "malloc" attribute. Do this as part of the - * __alloc_size macro to avoid redundant attributes and to avoid missing a - * __malloc marking. + * a place to be marked with the "malloc" attribute, except those that may + * be performing a _reallocation_, as that may alias the existing pointer. + * For these, use __realloc_size(). */ #ifdef __alloc_size__ # define __alloc_size(x, ...) __alloc_size__(x, ## __VA_ARGS__) __malloc +# define __realloc_size(x, ...) __alloc_size__(x, ## __VA_ARGS__) #else # define __alloc_size(x, ...) __malloc +# define __realloc_size(x, ...) #endif #ifndef asm_volatile_goto @@ -368,4 +379,8 @@ struct ftrace_likely_data { #define __diag_error(compiler, version, option, comment) \ __diag_ ## compiler(version, error, option) +#ifndef __diag_ignore_all +#define __diag_ignore_all(option, comment) +#endif + #endif /* __LINUX_COMPILER_TYPES_H */ diff --git a/include/linux/completion.h b/include/linux/completion.h index 51d9ab079629..62b32b19e0a8 100644 --- a/include/linux/completion.h +++ b/include/linux/completion.h @@ -103,6 +103,7 @@ extern void wait_for_completion(struct completion *); extern void wait_for_completion_io(struct completion *); extern int wait_for_completion_interruptible(struct completion *x); extern int wait_for_completion_killable(struct completion *x); +extern int wait_for_completion_state(struct completion *x, unsigned int state); extern unsigned long wait_for_completion_timeout(struct completion *x, unsigned long timeout); extern unsigned long wait_for_completion_io_timeout(struct completion *x, diff --git a/include/linux/component.h b/include/linux/component.h index 16de18f473d7..df4aa75c9e7c 100644 --- a/include/linux/component.h +++ b/include/linux/component.h @@ -38,10 +38,10 @@ int component_add_typed(struct device *dev, const struct component_ops *ops, int subcomponent); void component_del(struct device *, const struct component_ops *); -int component_bind_all(struct device *master, void *master_data); -void component_unbind_all(struct device *master, void *master_data); +int component_bind_all(struct device *parent, void *data); +void component_unbind_all(struct device *parent, void *data); -struct master; +struct aggregate_device; /** * struct component_master_ops - callback for the aggregate driver @@ -82,6 +82,12 @@ struct component_master_ops { void (*unbind)(struct device *master); }; +/* A set helper functions for component compare/release */ +int component_compare_of(struct device *dev, void *data); +void component_release_of(struct device *dev, void *data); +int component_compare_dev(struct device *dev, void *data); +int component_compare_dev_name(struct device *dev, void *data); + void component_master_del(struct device *, const struct component_master_ops *); @@ -89,22 +95,22 @@ struct component_match; int component_master_add_with_match(struct device *, const struct component_master_ops *, struct component_match *); -void component_match_add_release(struct device *master, +void component_match_add_release(struct device *parent, struct component_match **matchptr, void (*release)(struct device *, void *), int (*compare)(struct device *, void *), void *compare_data); -void component_match_add_typed(struct device *master, +void component_match_add_typed(struct device *parent, struct component_match **matchptr, int (*compare_typed)(struct device *, int, void *), void *compare_data); /** * component_match_add - add a component match entry - * @master: device with the aggregate driver + * @parent: device with the aggregate driver * @matchptr: pointer to the list of component matches * @compare: compare function to match against all components * @compare_data: opaque pointer passed to the @compare function * - * Adds a new component match to the list stored in @matchptr, which the @master + * Adds a new component match to the list stored in @matchptr, which the @parent * aggregate driver needs to function. The list of component matches pointed to * by @matchptr must be initialized to NULL before adding the first match. This * only matches against components added with component_add(). @@ -114,11 +120,11 @@ void component_match_add_typed(struct device *master, * * See also component_match_add_release() and component_match_add_typed(). */ -static inline void component_match_add(struct device *master, +static inline void component_match_add(struct device *parent, struct component_match **matchptr, int (*compare)(struct device *, void *), void *compare_data) { - component_match_add_release(master, matchptr, NULL, compare, + component_match_add_release(parent, matchptr, NULL, compare, compare_data); } diff --git a/include/linux/console.h b/include/linux/console.h index 7cd758a4f44e..8c1686e2c233 100644 --- a/include/linux/console.h +++ b/include/linux/console.h @@ -151,6 +151,8 @@ struct console { int cflag; uint ispeed; uint ospeed; + u64 seq; + unsigned long dropped; void *data; struct console *next; }; diff --git a/include/linux/console_struct.h b/include/linux/console_struct.h index d5b9c8d40c18..1518568aaf0f 100644 --- a/include/linux/console_struct.h +++ b/include/linux/console_struct.h @@ -17,7 +17,7 @@ #include <linux/vt.h> #include <linux/workqueue.h> -struct uni_pagedir; +struct uni_pagedict; struct uni_screen; #define NPAR 16 @@ -157,8 +157,8 @@ struct vc_data { unsigned int vc_bell_duration; /* Console bell duration */ unsigned short vc_cur_blink_ms; /* Cursor blink duration */ struct vc_data **vc_display_fg; /* [!] Ptr to var holding fg console for this display */ - struct uni_pagedir *vc_uni_pagedir; - struct uni_pagedir **vc_uni_pagedir_loc; /* [!] Location of uni_pagedir variable for this console */ + struct uni_pagedict *uni_pagedict; + struct uni_pagedict **uni_pagedict_loc; /* [!] Location of uni_pagedict variable for this console */ struct uni_screen *vc_uni_screen; /* unicode screen content */ /* additional information is in vt_kern.h */ }; diff --git a/include/linux/consolemap.h b/include/linux/consolemap.h index bcfce748c9d8..c35db4896c37 100644 --- a/include/linux/consolemap.h +++ b/include/linux/consolemap.h @@ -7,30 +7,56 @@ #ifndef __LINUX_CONSOLEMAP_H__ #define __LINUX_CONSOLEMAP_H__ -#define LAT1_MAP 0 -#define GRAF_MAP 1 -#define IBMPC_MAP 2 -#define USER_MAP 3 +enum translation_map { + LAT1_MAP, + GRAF_MAP, + IBMPC_MAP, + USER_MAP, + + FIRST_MAP = LAT1_MAP, + LAST_MAP = USER_MAP, +}; #include <linux/types.h> -#ifdef CONFIG_CONSOLE_TRANSLATIONS struct vc_data; -extern u16 inverse_translate(const struct vc_data *conp, int glyph, - int use_unicode); -extern unsigned short *set_translate(int m, struct vc_data *vc); -extern int conv_uni_to_pc(struct vc_data *conp, long ucs); -extern u32 conv_8bit_to_uni(unsigned char c); -extern int conv_uni_to_8bit(u32 uni); +#ifdef CONFIG_CONSOLE_TRANSLATIONS +u16 inverse_translate(const struct vc_data *conp, u16 glyph, bool use_unicode); +unsigned short *set_translate(enum translation_map m, struct vc_data *vc); +int conv_uni_to_pc(struct vc_data *conp, long ucs); +u32 conv_8bit_to_uni(unsigned char c); +int conv_uni_to_8bit(u32 uni); void console_map_init(void); #else -#define inverse_translate(conp, glyph, uni) ((uint16_t)glyph) -#define set_translate(m, vc) ((unsigned short *)NULL) -#define conv_uni_to_pc(conp, ucs) ((int) (ucs > 0xff ? -1: ucs)) -#define conv_8bit_to_uni(c) ((uint32_t)(c)) -#define conv_uni_to_8bit(c) ((int) ((c) & 0xff)) -#define console_map_init(c) do { ; } while (0) +static inline u16 inverse_translate(const struct vc_data *conp, u16 glyph, + bool use_unicode) +{ + return glyph; +} + +static inline unsigned short *set_translate(enum translation_map m, + struct vc_data *vc) +{ + return NULL; +} + +static inline int conv_uni_to_pc(struct vc_data *conp, long ucs) +{ + return ucs > 0xff ? -1 : ucs; +} + +static inline u32 conv_8bit_to_uni(unsigned char c) +{ + return c; +} + +static inline int conv_uni_to_8bit(u32 uni) +{ + return uni & 0xff; +} + +static inline void console_map_init(void) { } #endif /* CONFIG_CONSOLE_TRANSLATIONS */ #endif /* __LINUX_CONSOLEMAP_H__ */ diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h index 7a14807c9d1a..dcef4a9e4d63 100644 --- a/include/linux/context_tracking.h +++ b/include/linux/context_tracking.h @@ -10,71 +10,72 @@ #include <asm/ptrace.h> -#ifdef CONFIG_CONTEXT_TRACKING -extern void context_tracking_cpu_set(int cpu); +#ifdef CONFIG_CONTEXT_TRACKING_USER +extern void ct_cpu_track_user(int cpu); /* Called with interrupts disabled. */ -extern void __context_tracking_enter(enum ctx_state state); -extern void __context_tracking_exit(enum ctx_state state); +extern void __ct_user_enter(enum ctx_state state); +extern void __ct_user_exit(enum ctx_state state); -extern void context_tracking_enter(enum ctx_state state); -extern void context_tracking_exit(enum ctx_state state); -extern void context_tracking_user_enter(void); -extern void context_tracking_user_exit(void); +extern void ct_user_enter(enum ctx_state state); +extern void ct_user_exit(enum ctx_state state); + +extern void user_enter_callable(void); +extern void user_exit_callable(void); static inline void user_enter(void) { if (context_tracking_enabled()) - context_tracking_enter(CONTEXT_USER); + ct_user_enter(CONTEXT_USER); } static inline void user_exit(void) { if (context_tracking_enabled()) - context_tracking_exit(CONTEXT_USER); + ct_user_exit(CONTEXT_USER); } /* Called with interrupts disabled. */ static __always_inline void user_enter_irqoff(void) { if (context_tracking_enabled()) - __context_tracking_enter(CONTEXT_USER); + __ct_user_enter(CONTEXT_USER); } static __always_inline void user_exit_irqoff(void) { if (context_tracking_enabled()) - __context_tracking_exit(CONTEXT_USER); + __ct_user_exit(CONTEXT_USER); } static inline enum ctx_state exception_enter(void) { enum ctx_state prev_ctx; - if (IS_ENABLED(CONFIG_HAVE_CONTEXT_TRACKING_OFFSTACK) || + if (IS_ENABLED(CONFIG_HAVE_CONTEXT_TRACKING_USER_OFFSTACK) || !context_tracking_enabled()) return 0; - prev_ctx = this_cpu_read(context_tracking.state); + prev_ctx = __ct_state(); if (prev_ctx != CONTEXT_KERNEL) - context_tracking_exit(prev_ctx); + ct_user_exit(prev_ctx); return prev_ctx; } static inline void exception_exit(enum ctx_state prev_ctx) { - if (!IS_ENABLED(CONFIG_HAVE_CONTEXT_TRACKING_OFFSTACK) && + if (!IS_ENABLED(CONFIG_HAVE_CONTEXT_TRACKING_USER_OFFSTACK) && context_tracking_enabled()) { if (prev_ctx != CONTEXT_KERNEL) - context_tracking_enter(prev_ctx); + ct_user_enter(prev_ctx); } } static __always_inline bool context_tracking_guest_enter(void) { if (context_tracking_enabled()) - __context_tracking_enter(CONTEXT_GUEST); + __ct_user_enter(CONTEXT_GUEST); return context_tracking_enabled_this_cpu(); } @@ -82,40 +83,56 @@ static __always_inline bool context_tracking_guest_enter(void) static __always_inline void context_tracking_guest_exit(void) { if (context_tracking_enabled()) - __context_tracking_exit(CONTEXT_GUEST); + __ct_user_exit(CONTEXT_GUEST); } -/** - * ct_state() - return the current context tracking state if known - * - * Returns the current cpu's context tracking state if context tracking - * is enabled. If context tracking is disabled, returns - * CONTEXT_DISABLED. This should be used primarily for debugging. - */ -static __always_inline enum ctx_state ct_state(void) -{ - return context_tracking_enabled() ? - this_cpu_read(context_tracking.state) : CONTEXT_DISABLED; -} +#define CT_WARN_ON(cond) WARN_ON(context_tracking_enabled() && (cond)) + #else static inline void user_enter(void) { } static inline void user_exit(void) { } static inline void user_enter_irqoff(void) { } static inline void user_exit_irqoff(void) { } -static inline enum ctx_state exception_enter(void) { return 0; } +static inline int exception_enter(void) { return 0; } static inline void exception_exit(enum ctx_state prev_ctx) { } -static inline enum ctx_state ct_state(void) { return CONTEXT_DISABLED; } +static inline int ct_state(void) { return -1; } static __always_inline bool context_tracking_guest_enter(void) { return false; } static inline void context_tracking_guest_exit(void) { } +#define CT_WARN_ON(cond) do { } while (0) +#endif /* !CONFIG_CONTEXT_TRACKING_USER */ -#endif /* !CONFIG_CONTEXT_TRACKING */ - -#define CT_WARN_ON(cond) WARN_ON(context_tracking_enabled() && (cond)) - -#ifdef CONFIG_CONTEXT_TRACKING_FORCE +#ifdef CONFIG_CONTEXT_TRACKING_USER_FORCE extern void context_tracking_init(void); #else static inline void context_tracking_init(void) { } -#endif /* CONFIG_CONTEXT_TRACKING_FORCE */ +#endif /* CONFIG_CONTEXT_TRACKING_USER_FORCE */ + +#ifdef CONFIG_CONTEXT_TRACKING_IDLE +extern void ct_idle_enter(void); +extern void ct_idle_exit(void); + +/* + * Is the current CPU in an extended quiescent state? + * + * No ordering, as we are sampling CPU-local information. + */ +static __always_inline bool rcu_dynticks_curr_cpu_in_eqs(void) +{ + return !(arch_atomic_read(this_cpu_ptr(&context_tracking.state)) & RCU_DYNTICKS_IDX); +} + +/* + * Increment the current CPU's context_tracking structure's ->state field + * with ordering. Return the new value. + */ +static __always_inline unsigned long ct_state_inc(int incby) +{ + return arch_atomic_add_return(incby, this_cpu_ptr(&context_tracking.state)); +} + +#else +static inline void ct_idle_enter(void) { } +static inline void ct_idle_exit(void) { } +#endif /* !CONFIG_CONTEXT_TRACKING_IDLE */ #endif diff --git a/include/linux/context_tracking_irq.h b/include/linux/context_tracking_irq.h new file mode 100644 index 000000000000..c50b5670c4a5 --- /dev/null +++ b/include/linux/context_tracking_irq.h @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_CONTEXT_TRACKING_IRQ_H +#define _LINUX_CONTEXT_TRACKING_IRQ_H + +#ifdef CONFIG_CONTEXT_TRACKING_IDLE +void ct_irq_enter(void); +void ct_irq_exit(void); +void ct_irq_enter_irqson(void); +void ct_irq_exit_irqson(void); +void ct_nmi_enter(void); +void ct_nmi_exit(void); +#else +static inline void ct_irq_enter(void) { } +static inline void ct_irq_exit(void) { } +static inline void ct_irq_enter_irqson(void) { } +static inline void ct_irq_exit_irqson(void) { } +static inline void ct_nmi_enter(void) { } +static inline void ct_nmi_exit(void) { } +#endif + +#endif diff --git a/include/linux/context_tracking_state.h b/include/linux/context_tracking_state.h index 65a60d3313b0..4a4d56f77180 100644 --- a/include/linux/context_tracking_state.h +++ b/include/linux/context_tracking_state.h @@ -4,8 +4,28 @@ #include <linux/percpu.h> #include <linux/static_key.h> +#include <linux/context_tracking_irq.h> + +/* Offset to allow distinguishing irq vs. task-based idle entry/exit. */ +#define DYNTICK_IRQ_NONIDLE ((LONG_MAX / 2) + 1) + +enum ctx_state { + CONTEXT_DISABLED = -1, /* returned by ct_state() if unknown */ + CONTEXT_KERNEL = 0, + CONTEXT_IDLE = 1, + CONTEXT_USER = 2, + CONTEXT_GUEST = 3, + CONTEXT_MAX = 4, +}; + +/* Even value for idle, else odd. */ +#define RCU_DYNTICKS_IDX CONTEXT_MAX + +#define CT_STATE_MASK (CONTEXT_MAX - 1) +#define CT_DYNTICKS_MASK (~CT_STATE_MASK) struct context_tracking { +#ifdef CONFIG_CONTEXT_TRACKING_USER /* * When active is false, probes are unset in order * to minimize overhead: TIF flags are cleared @@ -14,18 +34,73 @@ struct context_tracking { */ bool active; int recursion; - enum ctx_state { - CONTEXT_DISABLED = -1, /* returned by ct_state() if unknown */ - CONTEXT_KERNEL = 0, - CONTEXT_USER, - CONTEXT_GUEST, - } state; +#endif +#ifdef CONFIG_CONTEXT_TRACKING + atomic_t state; +#endif +#ifdef CONFIG_CONTEXT_TRACKING_IDLE + long dynticks_nesting; /* Track process nesting level. */ + long dynticks_nmi_nesting; /* Track irq/NMI nesting level. */ +#endif }; #ifdef CONFIG_CONTEXT_TRACKING -extern struct static_key_false context_tracking_key; DECLARE_PER_CPU(struct context_tracking, context_tracking); +static __always_inline int __ct_state(void) +{ + return arch_atomic_read(this_cpu_ptr(&context_tracking.state)) & CT_STATE_MASK; +} +#endif + +#ifdef CONFIG_CONTEXT_TRACKING_IDLE +static __always_inline int ct_dynticks(void) +{ + return atomic_read(this_cpu_ptr(&context_tracking.state)) & CT_DYNTICKS_MASK; +} + +static __always_inline int ct_dynticks_cpu(int cpu) +{ + struct context_tracking *ct = per_cpu_ptr(&context_tracking, cpu); + + return atomic_read(&ct->state) & CT_DYNTICKS_MASK; +} + +static __always_inline int ct_dynticks_cpu_acquire(int cpu) +{ + struct context_tracking *ct = per_cpu_ptr(&context_tracking, cpu); + + return atomic_read_acquire(&ct->state) & CT_DYNTICKS_MASK; +} + +static __always_inline long ct_dynticks_nesting(void) +{ + return __this_cpu_read(context_tracking.dynticks_nesting); +} + +static __always_inline long ct_dynticks_nesting_cpu(int cpu) +{ + struct context_tracking *ct = per_cpu_ptr(&context_tracking, cpu); + + return ct->dynticks_nesting; +} + +static __always_inline long ct_dynticks_nmi_nesting(void) +{ + return __this_cpu_read(context_tracking.dynticks_nmi_nesting); +} + +static __always_inline long ct_dynticks_nmi_nesting_cpu(int cpu) +{ + struct context_tracking *ct = per_cpu_ptr(&context_tracking, cpu); + + return ct->dynticks_nmi_nesting; +} +#endif /* #ifdef CONFIG_CONTEXT_TRACKING_IDLE */ + +#ifdef CONFIG_CONTEXT_TRACKING_USER +extern struct static_key_false context_tracking_key; + static __always_inline bool context_tracking_enabled(void) { return static_branch_unlikely(&context_tracking_key); @@ -41,15 +116,31 @@ static inline bool context_tracking_enabled_this_cpu(void) return context_tracking_enabled() && __this_cpu_read(context_tracking.active); } -static __always_inline bool context_tracking_in_user(void) +/** + * ct_state() - return the current context tracking state if known + * + * Returns the current cpu's context tracking state if context tracking + * is enabled. If context tracking is disabled, returns + * CONTEXT_DISABLED. This should be used primarily for debugging. + */ +static __always_inline int ct_state(void) { - return __this_cpu_read(context_tracking.state) == CONTEXT_USER; + int ret; + + if (!context_tracking_enabled()) + return CONTEXT_DISABLED; + + preempt_disable(); + ret = __ct_state(); + preempt_enable(); + + return ret; } + #else -static inline bool context_tracking_in_user(void) { return false; } -static inline bool context_tracking_enabled(void) { return false; } -static inline bool context_tracking_enabled_cpu(int cpu) { return false; } -static inline bool context_tracking_enabled_this_cpu(void) { return false; } -#endif /* CONFIG_CONTEXT_TRACKING */ +static __always_inline bool context_tracking_enabled(void) { return false; } +static __always_inline bool context_tracking_enabled_cpu(int cpu) { return false; } +static __always_inline bool context_tracking_enabled_this_cpu(void) { return false; } +#endif /* CONFIG_CONTEXT_TRACKING_USER */ #endif diff --git a/include/linux/coredump.h b/include/linux/coredump.h index 78fcd776b185..08a1d3e7e46d 100644 --- a/include/linux/coredump.h +++ b/include/linux/coredump.h @@ -12,29 +12,43 @@ struct core_vma_metadata { unsigned long start, end; unsigned long flags; unsigned long dump_size; + unsigned long pgoff; + struct file *file; }; -extern int core_uses_pid; -extern char core_pattern[]; -extern unsigned int core_pipe_limit; +struct coredump_params { + const kernel_siginfo_t *siginfo; + struct pt_regs *regs; + struct file *file; + unsigned long limit; + unsigned long mm_flags; + loff_t written; + loff_t pos; + loff_t to_skip; + int vma_count; + size_t vma_data_size; + struct core_vma_metadata *vma_meta; +}; /* * These are the only things you should do on a core-file: use only these * functions to write out all the necessary info. */ -struct coredump_params; extern void dump_skip_to(struct coredump_params *cprm, unsigned long to); extern void dump_skip(struct coredump_params *cprm, size_t nr); extern int dump_emit(struct coredump_params *cprm, const void *addr, int nr); extern int dump_align(struct coredump_params *cprm, int align); int dump_user_range(struct coredump_params *cprm, unsigned long start, unsigned long len); -int dump_vma_snapshot(struct coredump_params *cprm, int *vma_count, - struct core_vma_metadata **vma_meta, - size_t *vma_data_size_ptr); extern void do_coredump(const kernel_siginfo_t *siginfo); #else static inline void do_coredump(const kernel_siginfo_t *siginfo) {} #endif +#if defined(CONFIG_COREDUMP) && defined(CONFIG_SYSCTL) +extern void validate_coredump_safety(void); +#else +static inline void validate_coredump_safety(void) {} +#endif + #endif /* _LINUX_COREDUMP_H */ diff --git a/include/linux/coresight-pmu.h b/include/linux/coresight-pmu.h index 4ac5c081af93..6c2fd6cc5a98 100644 --- a/include/linux/coresight-pmu.h +++ b/include/linux/coresight-pmu.h @@ -18,6 +18,7 @@ * ETMv3.5/PTM doesn't define ETMCR config bits with prefix "ETM3_" and * directly use below macros as config bits. */ +#define ETM_OPT_BRANCH_BROADCAST 8 #define ETM_OPT_CYCACC 12 #define ETM_OPT_CTXTID 14 #define ETM_OPT_CTXTID2 15 @@ -25,6 +26,7 @@ #define ETM_OPT_RETSTK 29 /* ETMv4 CONFIGR programming bits for the ETM OPTs */ +#define ETM4_CFG_BIT_BB 3 #define ETM4_CFG_BIT_CYCACC 4 #define ETM4_CFG_BIT_CTXTID 6 #define ETM4_CFG_BIT_VMID 7 diff --git a/include/linux/coresight.h b/include/linux/coresight.h index 93a2922b7653..1554021231f9 100644 --- a/include/linux/coresight.h +++ b/include/linux/coresight.h @@ -36,7 +36,6 @@ extern struct bus_type coresight_bustype; enum coresight_dev_type { - CORESIGHT_DEV_TYPE_NONE, CORESIGHT_DEV_TYPE_SINK, CORESIGHT_DEV_TYPE_LINK, CORESIGHT_DEV_TYPE_LINKSINK, @@ -46,7 +45,6 @@ enum coresight_dev_type { }; enum coresight_dev_subtype_sink { - CORESIGHT_DEV_SUBTYPE_SINK_NONE, CORESIGHT_DEV_SUBTYPE_SINK_PORT, CORESIGHT_DEV_SUBTYPE_SINK_BUFFER, CORESIGHT_DEV_SUBTYPE_SINK_SYSMEM, @@ -54,21 +52,18 @@ enum coresight_dev_subtype_sink { }; enum coresight_dev_subtype_link { - CORESIGHT_DEV_SUBTYPE_LINK_NONE, CORESIGHT_DEV_SUBTYPE_LINK_MERG, CORESIGHT_DEV_SUBTYPE_LINK_SPLIT, CORESIGHT_DEV_SUBTYPE_LINK_FIFO, }; enum coresight_dev_subtype_source { - CORESIGHT_DEV_SUBTYPE_SOURCE_NONE, CORESIGHT_DEV_SUBTYPE_SOURCE_PROC, CORESIGHT_DEV_SUBTYPE_SOURCE_BUS, CORESIGHT_DEV_SUBTYPE_SOURCE_SOFTWARE, }; enum coresight_dev_subtype_helper { - CORESIGHT_DEV_SUBTYPE_HELPER_NONE, CORESIGHT_DEV_SUBTYPE_HELPER_CATU, }; @@ -377,6 +372,29 @@ static inline u32 csdev_access_relaxed_read32(struct csdev_access *csa, return csa->read(offset, true, false); } +static inline u64 csdev_access_relaxed_read_pair(struct csdev_access *csa, + u32 lo_offset, u32 hi_offset) +{ + if (likely(csa->io_mem)) { + return readl_relaxed(csa->base + lo_offset) | + ((u64)readl_relaxed(csa->base + hi_offset) << 32); + } + + return csa->read(lo_offset, true, false) | (csa->read(hi_offset, true, false) << 32); +} + +static inline void csdev_access_relaxed_write_pair(struct csdev_access *csa, u64 val, + u32 lo_offset, u32 hi_offset) +{ + if (likely(csa->io_mem)) { + writel_relaxed((u32)val, csa->base + lo_offset); + writel_relaxed((u32)(val >> 32), csa->base + hi_offset); + } else { + csa->write((u32)val, lo_offset, true, false); + csa->write((u32)(val >> 32), hi_offset, true, false); + } +} + static inline u32 csdev_access_read32(struct csdev_access *csa, u32 offset) { if (likely(csa->io_mem)) diff --git a/include/linux/counter.h b/include/linux/counter.h index b7d0a00a61cf..b63746637de2 100644 --- a/include/linux/counter.h +++ b/include/linux/counter.h @@ -31,6 +31,8 @@ enum counter_comp_type { COUNTER_COMP_ENUM, COUNTER_COMP_COUNT_DIRECTION, COUNTER_COMP_COUNT_MODE, + COUNTER_COMP_SIGNAL_POLARITY, + COUNTER_COMP_ARRAY, }; /** @@ -38,66 +40,114 @@ enum counter_comp_type { * @type: Counter component data type * @name: device-specific component name * @priv: component-relevant data - * @action_read Synapse action mode read callback. The read value of the + * @action_read: Synapse action mode read callback. The read value of the * respective Synapse action mode should be passed back via * the action parameter. - * @device_u8_read Device u8 component read callback. The read value of the + * @device_u8_read: Device u8 component read callback. The read value of the * respective Device u8 component should be passed back via * the val parameter. - * @count_u8_read Count u8 component read callback. The read value of the + * @count_u8_read: Count u8 component read callback. The read value of the * respective Count u8 component should be passed back via * the val parameter. - * @signal_u8_read Signal u8 component read callback. The read value of the + * @signal_u8_read: Signal u8 component read callback. The read value of the * respective Signal u8 component should be passed back via * the val parameter. - * @device_u32_read Device u32 component read callback. The read value of + * @device_u32_read: Device u32 component read callback. The read value of * the respective Device u32 component should be passed * back via the val parameter. - * @count_u32_read Count u32 component read callback. The read value of the + * @count_u32_read: Count u32 component read callback. The read value of the * respective Count u32 component should be passed back via * the val parameter. - * @signal_u32_read Signal u32 component read callback. The read value of + * @signal_u32_read: Signal u32 component read callback. The read value of * the respective Signal u32 component should be passed * back via the val parameter. - * @device_u64_read Device u64 component read callback. The read value of + * @device_u64_read: Device u64 component read callback. The read value of * the respective Device u64 component should be passed * back via the val parameter. - * @count_u64_read Count u64 component read callback. The read value of the + * @count_u64_read: Count u64 component read callback. The read value of the * respective Count u64 component should be passed back via * the val parameter. - * @signal_u64_read Signal u64 component read callback. The read value of + * @signal_u64_read: Signal u64 component read callback. The read value of * the respective Signal u64 component should be passed * back via the val parameter. - * @action_write Synapse action mode write callback. The write value of + * @signal_array_u32_read: Signal u32 array component read callback. The + * index of the respective Count u32 array + * component element is passed via the idx + * parameter. The read value of the respective + * Count u32 array component element should be + * passed back via the val parameter. + * @device_array_u64_read: Device u64 array component read callback. The + * index of the respective Device u64 array + * component element is passed via the idx + * parameter. The read value of the respective + * Device u64 array component element should be + * passed back via the val parameter. + * @count_array_u64_read: Count u64 array component read callback. The + * index of the respective Count u64 array + * component element is passed via the idx + * parameter. The read value of the respective + * Count u64 array component element should be + * passed back via the val parameter. + * @signal_array_u64_read: Signal u64 array component read callback. The + * index of the respective Count u64 array + * component element is passed via the idx + * parameter. The read value of the respective + * Count u64 array component element should be + * passed back via the val parameter. + * @action_write: Synapse action mode write callback. The write value of * the respective Synapse action mode is passed via the * action parameter. - * @device_u8_write Device u8 component write callback. The write value of + * @device_u8_write: Device u8 component write callback. The write value of * the respective Device u8 component is passed via the val * parameter. - * @count_u8_write Count u8 component write callback. The write value of + * @count_u8_write: Count u8 component write callback. The write value of * the respective Count u8 component is passed via the val * parameter. - * @signal_u8_write Signal u8 component write callback. The write value of + * @signal_u8_write: Signal u8 component write callback. The write value of * the respective Signal u8 component is passed via the val * parameter. - * @device_u32_write Device u32 component write callback. The write value of + * @device_u32_write: Device u32 component write callback. The write value of * the respective Device u32 component is passed via the * val parameter. - * @count_u32_write Count u32 component write callback. The write value of + * @count_u32_write: Count u32 component write callback. The write value of * the respective Count u32 component is passed via the val * parameter. - * @signal_u32_write Signal u32 component write callback. The write value of + * @signal_u32_write: Signal u32 component write callback. The write value of * the respective Signal u32 component is passed via the * val parameter. - * @device_u64_write Device u64 component write callback. The write value of + * @device_u64_write: Device u64 component write callback. The write value of * the respective Device u64 component is passed via the * val parameter. - * @count_u64_write Count u64 component write callback. The write value of + * @count_u64_write: Count u64 component write callback. The write value of * the respective Count u64 component is passed via the val * parameter. - * @signal_u64_write Signal u64 component write callback. The write value of + * @signal_u64_write: Signal u64 component write callback. The write value of * the respective Signal u64 component is passed via the * val parameter. + * @signal_array_u32_write: Signal u32 array component write callback. The + * index of the respective Signal u32 array + * component element is passed via the idx + * parameter. The write value of the respective + * Signal u32 array component element is passed via + * the val parameter. + * @device_array_u64_write: Device u64 array component write callback. The + * index of the respective Device u64 array + * component element is passed via the idx + * parameter. The write value of the respective + * Device u64 array component element is passed via + * the val parameter. + * @count_array_u64_write: Count u64 array component write callback. The + * index of the respective Count u64 array + * component element is passed via the idx + * parameter. The write value of the respective + * Count u64 array component element is passed via + * the val parameter. + * @signal_array_u64_write: Signal u64 array component write callback. The + * index of the respective Signal u64 array + * component element is passed via the idx + * parameter. The write value of the respective + * Signal u64 array component element is passed via + * the val parameter. */ struct counter_comp { enum counter_comp_type type; @@ -125,6 +175,17 @@ struct counter_comp { struct counter_count *count, u64 *val); int (*signal_u64_read)(struct counter_device *counter, struct counter_signal *signal, u64 *val); + int (*signal_array_u32_read)(struct counter_device *counter, + struct counter_signal *signal, + size_t idx, u32 *val); + int (*device_array_u64_read)(struct counter_device *counter, + size_t idx, u64 *val); + int (*count_array_u64_read)(struct counter_device *counter, + struct counter_count *count, + size_t idx, u64 *val); + int (*signal_array_u64_read)(struct counter_device *counter, + struct counter_signal *signal, + size_t idx, u64 *val); }; union { int (*action_write)(struct counter_device *counter, @@ -148,6 +209,17 @@ struct counter_comp { struct counter_count *count, u64 val); int (*signal_u64_write)(struct counter_device *counter, struct counter_signal *signal, u64 val); + int (*signal_array_u32_write)(struct counter_device *counter, + struct counter_signal *signal, + size_t idx, u32 val); + int (*device_array_u64_write)(struct counter_device *counter, + size_t idx, u64 val); + int (*count_array_u64_write)(struct counter_device *counter, + struct counter_count *count, + size_t idx, u64 val); + int (*signal_array_u64_write)(struct counter_device *counter, + struct counter_signal *signal, + size_t idx, u64 val); }; }; @@ -314,8 +386,6 @@ struct counter_device { struct counter_comp *ext; size_t num_ext; - void *priv; - struct device dev; struct cdev chrdev; struct list_head events_list; @@ -329,10 +399,17 @@ struct counter_device { struct mutex ops_exist_lock; }; -int counter_register(struct counter_device *const counter); +void *counter_priv(const struct counter_device *const counter); + +struct counter_device *counter_alloc(size_t sizeof_priv); +void counter_put(struct counter_device *const counter); +int counter_add(struct counter_device *const counter); + void counter_unregister(struct counter_device *const counter); -int devm_counter_register(struct device *dev, - struct counter_device *const counter); +struct counter_device *devm_counter_alloc(struct device *dev, + size_t sizeof_priv); +int devm_counter_add(struct device *dev, + struct counter_device *const counter); void counter_push_event(struct counter_device *const counter, const u8 event, const u8 channel); @@ -447,6 +524,59 @@ struct counter_available { .priv = &(_available), \ } +struct counter_array { + enum counter_comp_type type; + const struct counter_available *avail; + union { + size_t length; + size_t idx; + }; +}; + +#define DEFINE_COUNTER_ARRAY_U64(_name, _length) \ + struct counter_array _name = { \ + .type = COUNTER_COMP_U64, \ + .length = (_length), \ + } + +#define DEFINE_COUNTER_ARRAY_CAPTURE(_name, _length) \ + DEFINE_COUNTER_ARRAY_U64(_name, _length) + +#define DEFINE_COUNTER_ARRAY_POLARITY(_name, _available, _length) \ + struct counter_array _name = { \ + .type = COUNTER_COMP_SIGNAL_POLARITY, \ + .avail = &(_available), \ + .length = (_length), \ + } + +#define COUNTER_COMP_DEVICE_ARRAY_U64(_name, _read, _write, _array) \ +{ \ + .type = COUNTER_COMP_ARRAY, \ + .name = (_name), \ + .device_array_u64_read = (_read), \ + .device_array_u64_write = (_write), \ + .priv = &(_array), \ +} +#define COUNTER_COMP_COUNT_ARRAY_U64(_name, _read, _write, _array) \ +{ \ + .type = COUNTER_COMP_ARRAY, \ + .name = (_name), \ + .count_array_u64_read = (_read), \ + .count_array_u64_write = (_write), \ + .priv = &(_array), \ +} +#define COUNTER_COMP_SIGNAL_ARRAY_U64(_name, _read, _write, _array) \ +{ \ + .type = COUNTER_COMP_ARRAY, \ + .name = (_name), \ + .signal_array_u64_read = (_read), \ + .signal_array_u64_write = (_write), \ + .priv = &(_array), \ +} + +#define COUNTER_COMP_CAPTURE(_read, _write) \ + COUNTER_COMP_COUNT_U64("capture", _read, _write) + #define COUNTER_COMP_CEILING(_read, _write) \ COUNTER_COMP_COUNT_U64("ceiling", _read, _write) @@ -472,10 +602,31 @@ struct counter_available { #define COUNTER_COMP_FLOOR(_read, _write) \ COUNTER_COMP_COUNT_U64("floor", _read, _write) +#define COUNTER_COMP_POLARITY(_read, _write, _available) \ +{ \ + .type = COUNTER_COMP_SIGNAL_POLARITY, \ + .name = "polarity", \ + .signal_u32_read = (_read), \ + .signal_u32_write = (_write), \ + .priv = &(_available), \ +} + #define COUNTER_COMP_PRESET(_read, _write) \ COUNTER_COMP_COUNT_U64("preset", _read, _write) #define COUNTER_COMP_PRESET_ENABLE(_read, _write) \ COUNTER_COMP_COUNT_BOOL("preset_enable", _read, _write) +#define COUNTER_COMP_ARRAY_CAPTURE(_read, _write, _array) \ + COUNTER_COMP_COUNT_ARRAY_U64("capture", _read, _write, _array) + +#define COUNTER_COMP_ARRAY_POLARITY(_read, _write, _array) \ +{ \ + .type = COUNTER_COMP_ARRAY, \ + .name = "polarity", \ + .signal_array_u32_read = (_read), \ + .signal_array_u32_write = (_write), \ + .priv = &(_array), \ +} + #endif /* _COUNTER_H_ */ diff --git a/include/linux/cper.h b/include/linux/cper.h index 6a511a1078ca..eacb7dd7b3af 100644 --- a/include/linux/cper.h +++ b/include/linux/cper.h @@ -558,6 +558,7 @@ extern const char *const cper_proc_error_type_strs[4]; u64 cper_next_record_id(void); const char *cper_severity_str(unsigned int); const char *cper_mem_err_type_str(unsigned int); +const char *cper_mem_err_status_str(u64 status); void cper_print_bits(const char *prefix, unsigned int bits, const char * const strs[], unsigned int strs_size); void cper_mem_err_pack(const struct cper_sec_mem_err *, @@ -568,5 +569,7 @@ void cper_print_proc_arm(const char *pfx, const struct cper_sec_proc_arm *proc); void cper_print_proc_ia(const char *pfx, const struct cper_sec_proc_ia *proc); +int cper_mem_err_location(struct cper_mem_err_compact *mem, char *msg); +int cper_dimm_err_location(struct cper_mem_err_compact *mem, char *msg); #endif diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 9cf51e41e697..314802f98b9d 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -65,6 +65,11 @@ extern ssize_t cpu_show_tsx_async_abort(struct device *dev, extern ssize_t cpu_show_itlb_multihit(struct device *dev, struct device_attribute *attr, char *buf); extern ssize_t cpu_show_srbds(struct device *dev, struct device_attribute *attr, char *buf); +extern ssize_t cpu_show_mmio_stale_data(struct device *dev, + struct device_attribute *attr, + char *buf); +extern ssize_t cpu_show_retbleed(struct device *dev, + struct device_attribute *attr, char *buf); extern __printf(4, 5) struct device *cpu_device_create(struct device *parent, void *drvdata, @@ -167,7 +172,7 @@ static inline int suspend_disable_secondary_cpus(void) { return 0; } static inline void suspend_enable_secondary_cpus(void) { } #endif /* !CONFIG_PM_SLEEP_SMP */ -void cpu_startup_entry(enum cpuhp_state state); +void __noreturn cpu_startup_entry(enum cpuhp_state state); void cpu_idle_poll_ctrl(bool enable); diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 1ab29e61b078..d5595d57f4e5 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -382,6 +382,9 @@ struct cpufreq_driver { int (*suspend)(struct cpufreq_policy *policy); int (*resume)(struct cpufreq_policy *policy); + /* Will be called after the driver is fully initialized */ + void (*ready)(struct cpufreq_policy *policy); + struct freq_attr **attr; /* platform specific boost support code */ @@ -658,6 +661,11 @@ struct gov_attr_set { /* sysfs ops for cpufreq governors */ extern const struct sysfs_ops governor_sysfs_ops; +static inline struct gov_attr_set *to_gov_attr_set(struct kobject *kobj) +{ + return container_of(kobj, struct gov_attr_set, kobj); +} + void gov_attr_set_init(struct gov_attr_set *attr_set, struct list_head *list_node); void gov_attr_set_get(struct gov_attr_set *attr_set, struct list_head *list_node); unsigned int gov_attr_set_put(struct gov_attr_set *attr_set, struct list_head *list_node); @@ -1191,7 +1199,6 @@ static inline void sched_cpufreq_governor_change(struct cpufreq_policy *policy, struct cpufreq_governor *old_gov) { } #endif -extern void arch_freq_prepare_all(void); extern unsigned int arch_freq_get_on_cpu(int cpu); #ifndef arch_set_freq_scale diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 411a428ace4d..f61447913db9 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -100,6 +100,7 @@ enum cpuhp_state { CPUHP_AP_ARM_CACHE_B15_RAC_DEAD, CPUHP_PADATA_DEAD, CPUHP_AP_DTPM_CPU_DEAD, + CPUHP_RANDOM_PREPARE, CPUHP_WORKQUEUE_PREP, CPUHP_POWER_NUMA_PREPARE, CPUHP_HRTIMERS_PREPARE, @@ -149,6 +150,7 @@ enum cpuhp_state { CPUHP_AP_IRQ_BCM2836_STARTING, CPUHP_AP_IRQ_MIPS_GIC_STARTING, CPUHP_AP_IRQ_RISCV_STARTING, + CPUHP_AP_IRQ_LOONGARCH_STARTING, CPUHP_AP_IRQ_SIFIVE_PLIC_STARTING, CPUHP_AP_ARM_MVEBU_COHERENCY, CPUHP_AP_MICROCODE_LOADER, @@ -165,6 +167,7 @@ enum cpuhp_state { CPUHP_AP_PERF_ARM_HW_BREAKPOINT_STARTING, CPUHP_AP_PERF_ARM_ACPI_STARTING, CPUHP_AP_PERF_ARM_STARTING, + CPUHP_AP_PERF_RISCV_STARTING, CPUHP_AP_ARM_L2X0_STARTING, CPUHP_AP_EXYNOS4_MCT_TIMER_STARTING, CPUHP_AP_ARM_ARCH_TIMER_STARTING, @@ -220,17 +223,20 @@ enum cpuhp_state { CPUHP_AP_PERF_S390_SF_ONLINE, CPUHP_AP_PERF_ARM_CCI_ONLINE, CPUHP_AP_PERF_ARM_CCN_ONLINE, + CPUHP_AP_PERF_ARM_HISI_CPA_ONLINE, CPUHP_AP_PERF_ARM_HISI_DDRC_ONLINE, CPUHP_AP_PERF_ARM_HISI_HHA_ONLINE, CPUHP_AP_PERF_ARM_HISI_L3_ONLINE, CPUHP_AP_PERF_ARM_HISI_PA_ONLINE, CPUHP_AP_PERF_ARM_HISI_SLLC_ONLINE, CPUHP_AP_PERF_ARM_HISI_PCIE_PMU_ONLINE, + CPUHP_AP_PERF_ARM_HNS3_PMU_ONLINE, CPUHP_AP_PERF_ARM_L2X0_ONLINE, CPUHP_AP_PERF_ARM_QCOM_L2_ONLINE, CPUHP_AP_PERF_ARM_QCOM_L3_ONLINE, CPUHP_AP_PERF_ARM_APM_XGENE_ONLINE, CPUHP_AP_PERF_ARM_CAVIUM_TX2_UNCORE_ONLINE, + CPUHP_AP_PERF_ARM_MARVELL_CN10K_DDR_ONLINE, CPUHP_AP_PERF_POWERPC_NEST_IMC_ONLINE, CPUHP_AP_PERF_POWERPC_CORE_IMC_ONLINE, CPUHP_AP_PERF_POWERPC_THREAD_IMC_ONLINE, @@ -240,6 +246,7 @@ enum cpuhp_state { CPUHP_AP_PERF_CSKY_ONLINE, CPUHP_AP_WATCHDOG_ONLINE, CPUHP_AP_WORKQUEUE_ONLINE, + CPUHP_AP_RANDOM_ONLINE, CPUHP_AP_RCUTREE_ONLINE, CPUHP_AP_BASE_CACHEINFO_ONLINE, CPUHP_AP_ONLINE_DYN, diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 1e7399fc69c0..c2aa0aa26b45 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -12,6 +12,8 @@ #include <linux/bitmap.h> #include <linux/atomic.h> #include <linux/bug.h> +#include <linux/gfp_types.h> +#include <linux/numa.h> /* Don't assign or return these: may not be this big! */ typedef struct cpumask { DECLARE_BITMAP(bits, NR_CPUS); } cpumask_t; @@ -33,19 +35,23 @@ typedef struct cpumask { DECLARE_BITMAP(bits, NR_CPUS); } cpumask_t; */ #define cpumask_pr_args(maskp) nr_cpu_ids, cpumask_bits(maskp) -#if NR_CPUS == 1 -#define nr_cpu_ids 1U +#if (NR_CPUS == 1) || defined(CONFIG_FORCE_NR_CPUS) +#define nr_cpu_ids ((unsigned int)NR_CPUS) #else extern unsigned int nr_cpu_ids; #endif -#ifdef CONFIG_CPUMASK_OFFSTACK -/* Assuming NR_CPUS is huge, a runtime limit is more efficient. Also, - * not all bits may be allocated. */ -#define nr_cpumask_bits nr_cpu_ids +static inline void set_nr_cpu_ids(unsigned int nr) +{ +#if (NR_CPUS == 1) || defined(CONFIG_FORCE_NR_CPUS) + WARN_ON(nr != nr_cpu_ids); #else -#define nr_cpumask_bits ((unsigned int)NR_CPUS) + nr_cpu_ids = nr; #endif +} + +/* Deprecated. Always use nr_cpu_ids. */ +#define nr_cpumask_bits nr_cpu_ids /* * The following particular system cpumasks and operations manage @@ -65,10 +71,6 @@ extern unsigned int nr_cpu_ids; * cpu_online_mask is the dynamic subset of cpu_present_mask, * indicating those CPUs available for scheduling. * - * If HOTPLUG is enabled, then cpu_possible_mask is forced to have - * all NR_CPUS bits set, otherwise it is just the set of CPUs that - * ACPI reports present at boot. - * * If HOTPLUG is enabled, then cpu_present_mask varies dynamically, * depending on what ACPI reports as currently plugged in, otherwise * cpu_present_mask is just a copy of cpu_possible_mask. @@ -102,7 +104,7 @@ extern atomic_t __num_online_cpus; extern cpumask_t cpus_booted_once_mask; -static inline void cpu_max_bits_warn(unsigned int cpu, unsigned int bits) +static __always_inline void cpu_max_bits_warn(unsigned int cpu, unsigned int bits) { #ifdef CONFIG_DEBUG_PER_CPU_MAPS WARN_ON_ONCE(cpu >= bits); @@ -110,89 +112,45 @@ static inline void cpu_max_bits_warn(unsigned int cpu, unsigned int bits) } /* verify cpu argument to cpumask_* operators */ -static inline unsigned int cpumask_check(unsigned int cpu) +static __always_inline unsigned int cpumask_check(unsigned int cpu) { cpu_max_bits_warn(cpu, nr_cpumask_bits); return cpu; } -#if NR_CPUS == 1 -/* Uniprocessor. Assume all masks are "1". */ +/** + * cpumask_first - get the first cpu in a cpumask + * @srcp: the cpumask pointer + * + * Returns >= nr_cpu_ids if no cpus set. + */ static inline unsigned int cpumask_first(const struct cpumask *srcp) { - return 0; -} - -static inline unsigned int cpumask_last(const struct cpumask *srcp) -{ - return 0; -} - -/* Valid inputs for n are -1 and 0. */ -static inline unsigned int cpumask_next(int n, const struct cpumask *srcp) -{ - return n+1; -} - -static inline unsigned int cpumask_next_zero(int n, const struct cpumask *srcp) -{ - return n+1; -} - -static inline unsigned int cpumask_next_and(int n, - const struct cpumask *srcp, - const struct cpumask *andp) -{ - return n+1; -} - -static inline unsigned int cpumask_next_wrap(int n, const struct cpumask *mask, - int start, bool wrap) -{ - /* cpu0 unless stop condition, wrap and at cpu0, then nr_cpumask_bits */ - return (wrap && n == 0); -} - -/* cpu must be a valid cpu, ie 0, so there's no other choice. */ -static inline unsigned int cpumask_any_but(const struct cpumask *mask, - unsigned int cpu) -{ - return 1; -} - -static inline unsigned int cpumask_local_spread(unsigned int i, int node) -{ - return 0; -} - -static inline int cpumask_any_and_distribute(const struct cpumask *src1p, - const struct cpumask *src2p) { - return cpumask_next_and(-1, src1p, src2p); + return find_first_bit(cpumask_bits(srcp), nr_cpumask_bits); } -static inline int cpumask_any_distribute(const struct cpumask *srcp) +/** + * cpumask_first_zero - get the first unset cpu in a cpumask + * @srcp: the cpumask pointer + * + * Returns >= nr_cpu_ids if all cpus are set. + */ +static inline unsigned int cpumask_first_zero(const struct cpumask *srcp) { - return cpumask_first(srcp); + return find_first_zero_bit(cpumask_bits(srcp), nr_cpumask_bits); } -#define for_each_cpu(cpu, mask) \ - for ((cpu) = 0; (cpu) < 1; (cpu)++, (void)mask) -#define for_each_cpu_not(cpu, mask) \ - for ((cpu) = 0; (cpu) < 1; (cpu)++, (void)mask) -#define for_each_cpu_wrap(cpu, mask, start) \ - for ((cpu) = 0; (cpu) < 1; (cpu)++, (void)mask, (void)(start)) -#define for_each_cpu_and(cpu, mask1, mask2) \ - for ((cpu) = 0; (cpu) < 1; (cpu)++, (void)mask1, (void)mask2) -#else /** - * cpumask_first - get the first cpu in a cpumask - * @srcp: the cpumask pointer + * cpumask_first_and - return the first cpu from *srcp1 & *srcp2 + * @src1p: the first input + * @src2p: the second input * - * Returns >= nr_cpu_ids if no cpus set. + * Returns >= nr_cpu_ids if no cpus set in both. See also cpumask_next_and(). */ -static inline unsigned int cpumask_first(const struct cpumask *srcp) +static inline +unsigned int cpumask_first_and(const struct cpumask *srcp1, const struct cpumask *srcp2) { - return find_first_bit(cpumask_bits(srcp), nr_cpumask_bits); + return find_first_and_bit(cpumask_bits(srcp1), cpumask_bits(srcp2), nr_cpumask_bits); } /** @@ -206,7 +164,21 @@ static inline unsigned int cpumask_last(const struct cpumask *srcp) return find_last_bit(cpumask_bits(srcp), nr_cpumask_bits); } -unsigned int __pure cpumask_next(int n, const struct cpumask *srcp); +/** + * cpumask_next - get the next cpu in a cpumask + * @n: the cpu prior to the place to search (ie. return will be > @n) + * @srcp: the cpumask pointer + * + * Returns >= nr_cpu_ids if no further cpus set. + */ +static inline +unsigned int cpumask_next(int n, const struct cpumask *srcp) +{ + /* -1 is a legal arg here. */ + if (n != -1) + cpumask_check(n); + return find_next_bit(cpumask_bits(srcp), nr_cpumask_bits, n + 1); +} /** * cpumask_next_zero - get the next unset cpu in a cpumask @@ -223,12 +195,48 @@ static inline unsigned int cpumask_next_zero(int n, const struct cpumask *srcp) return find_next_zero_bit(cpumask_bits(srcp), nr_cpumask_bits, n+1); } -int __pure cpumask_next_and(int n, const struct cpumask *, const struct cpumask *); -int __pure cpumask_any_but(const struct cpumask *mask, unsigned int cpu); +#if NR_CPUS == 1 +/* Uniprocessor: there is only one valid CPU */ +static inline unsigned int cpumask_local_spread(unsigned int i, int node) +{ + return 0; +} + +static inline unsigned int cpumask_any_and_distribute(const struct cpumask *src1p, + const struct cpumask *src2p) +{ + return cpumask_first_and(src1p, src2p); +} + +static inline unsigned int cpumask_any_distribute(const struct cpumask *srcp) +{ + return cpumask_first(srcp); +} +#else unsigned int cpumask_local_spread(unsigned int i, int node); -int cpumask_any_and_distribute(const struct cpumask *src1p, +unsigned int cpumask_any_and_distribute(const struct cpumask *src1p, const struct cpumask *src2p); -int cpumask_any_distribute(const struct cpumask *srcp); +unsigned int cpumask_any_distribute(const struct cpumask *srcp); +#endif /* NR_CPUS */ + +/** + * cpumask_next_and - get the next cpu in *src1p & *src2p + * @n: the cpu prior to the place to search (ie. return will be > @n) + * @src1p: the first cpumask pointer + * @src2p: the second cpumask pointer + * + * Returns >= nr_cpu_ids if no further cpus set in both. + */ +static inline +unsigned int cpumask_next_and(int n, const struct cpumask *src1p, + const struct cpumask *src2p) +{ + /* -1 is a legal arg here. */ + if (n != -1) + cpumask_check(n); + return find_next_and_bit(cpumask_bits(src1p), cpumask_bits(src2p), + nr_cpumask_bits, n + 1); +} /** * for_each_cpu - iterate over every cpu in a mask @@ -238,9 +246,7 @@ int cpumask_any_distribute(const struct cpumask *srcp); * After the loop, cpu is >= nr_cpu_ids. */ #define for_each_cpu(cpu, mask) \ - for ((cpu) = -1; \ - (cpu) = cpumask_next((cpu), (mask)), \ - (cpu) < nr_cpu_ids;) + for_each_set_bit(cpu, cpumask_bits(mask), nr_cpumask_bits) /** * for_each_cpu_not - iterate over every cpu in a complemented mask @@ -250,11 +256,28 @@ int cpumask_any_distribute(const struct cpumask *srcp); * After the loop, cpu is >= nr_cpu_ids. */ #define for_each_cpu_not(cpu, mask) \ - for ((cpu) = -1; \ - (cpu) = cpumask_next_zero((cpu), (mask)), \ - (cpu) < nr_cpu_ids;) + for_each_clear_bit(cpu, cpumask_bits(mask), nr_cpumask_bits) + +#if NR_CPUS == 1 +static inline +unsigned int cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool wrap) +{ + cpumask_check(start); + if (n != -1) + cpumask_check(n); -extern int cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool wrap); + /* + * Return the first available CPU when wrapping, or when starting before cpu0, + * since there is only one valid option. + */ + if (wrap && n >= 0) + return nr_cpumask_bits; + + return cpumask_first(mask); +} +#else +unsigned int __pure cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool wrap); +#endif /** * for_each_cpu_wrap - iterate over every cpu in a mask, starting at a specified location @@ -266,10 +289,8 @@ extern int cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool * * After the loop, cpu is >= nr_cpu_ids. */ -#define for_each_cpu_wrap(cpu, mask, start) \ - for ((cpu) = cpumask_next_wrap((start)-1, (mask), (start), false); \ - (cpu) < nr_cpumask_bits; \ - (cpu) = cpumask_next_wrap((cpu), (mask), (start), true)) +#define for_each_cpu_wrap(cpu, mask, start) \ + for_each_set_bit_wrap(cpu, cpumask_bits(mask), nr_cpumask_bits, start) /** * for_each_cpu_and - iterate over every cpu in both masks @@ -286,10 +307,89 @@ extern int cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool * After the loop, cpu is >= nr_cpu_ids. */ #define for_each_cpu_and(cpu, mask1, mask2) \ - for ((cpu) = -1; \ - (cpu) = cpumask_next_and((cpu), (mask1), (mask2)), \ - (cpu) < nr_cpu_ids;) -#endif /* SMP */ + for_each_and_bit(cpu, cpumask_bits(mask1), cpumask_bits(mask2), nr_cpumask_bits) + +/** + * for_each_cpu_andnot - iterate over every cpu present in one mask, excluding + * those present in another. + * @cpu: the (optionally unsigned) integer iterator + * @mask1: the first cpumask pointer + * @mask2: the second cpumask pointer + * + * This saves a temporary CPU mask in many places. It is equivalent to: + * struct cpumask tmp; + * cpumask_andnot(&tmp, &mask1, &mask2); + * for_each_cpu(cpu, &tmp) + * ... + * + * After the loop, cpu is >= nr_cpu_ids. + */ +#define for_each_cpu_andnot(cpu, mask1, mask2) \ + for_each_andnot_bit(cpu, cpumask_bits(mask1), cpumask_bits(mask2), nr_cpumask_bits) + +/** + * cpumask_any_but - return a "random" in a cpumask, but not this one. + * @mask: the cpumask to search + * @cpu: the cpu to ignore. + * + * Often used to find any cpu but smp_processor_id() in a mask. + * Returns >= nr_cpu_ids if no cpus set. + */ +static inline +unsigned int cpumask_any_but(const struct cpumask *mask, unsigned int cpu) +{ + unsigned int i; + + cpumask_check(cpu); + for_each_cpu(i, mask) + if (i != cpu) + break; + return i; +} + +/** + * cpumask_nth - get the first cpu in a cpumask + * @srcp: the cpumask pointer + * @cpu: the N'th cpu to find, starting from 0 + * + * Returns >= nr_cpu_ids if such cpu doesn't exist. + */ +static inline unsigned int cpumask_nth(unsigned int cpu, const struct cpumask *srcp) +{ + return find_nth_bit(cpumask_bits(srcp), nr_cpumask_bits, cpumask_check(cpu)); +} + +/** + * cpumask_nth_and - get the first cpu in 2 cpumasks + * @srcp1: the cpumask pointer + * @srcp2: the cpumask pointer + * @cpu: the N'th cpu to find, starting from 0 + * + * Returns >= nr_cpu_ids if such cpu doesn't exist. + */ +static inline +unsigned int cpumask_nth_and(unsigned int cpu, const struct cpumask *srcp1, + const struct cpumask *srcp2) +{ + return find_nth_and_bit(cpumask_bits(srcp1), cpumask_bits(srcp2), + nr_cpumask_bits, cpumask_check(cpu)); +} + +/** + * cpumask_nth_andnot - get the first cpu set in 1st cpumask, and clear in 2nd. + * @srcp1: the cpumask pointer + * @srcp2: the cpumask pointer + * @cpu: the N'th cpu to find, starting from 0 + * + * Returns >= nr_cpu_ids if such cpu doesn't exist. + */ +static inline +unsigned int cpumask_nth_andnot(unsigned int cpu, const struct cpumask *srcp1, + const struct cpumask *srcp2) +{ + return find_nth_andnot_bit(cpumask_bits(srcp1), cpumask_bits(srcp2), + nr_cpumask_bits, cpumask_check(cpu)); +} #define CPU_BITS_NONE \ { \ @@ -306,12 +406,12 @@ extern int cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool * @cpu: cpu number (< nr_cpu_ids) * @dstp: the cpumask pointer */ -static inline void cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp) +static __always_inline void cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp) { set_bit(cpumask_check(cpu), cpumask_bits(dstp)); } -static inline void __cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp) +static __always_inline void __cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp) { __set_bit(cpumask_check(cpu), cpumask_bits(dstp)); } @@ -322,12 +422,12 @@ static inline void __cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp) * @cpu: cpu number (< nr_cpu_ids) * @dstp: the cpumask pointer */ -static inline void cpumask_clear_cpu(int cpu, struct cpumask *dstp) +static __always_inline void cpumask_clear_cpu(int cpu, struct cpumask *dstp) { clear_bit(cpumask_check(cpu), cpumask_bits(dstp)); } -static inline void __cpumask_clear_cpu(int cpu, struct cpumask *dstp) +static __always_inline void __cpumask_clear_cpu(int cpu, struct cpumask *dstp) { __clear_bit(cpumask_check(cpu), cpumask_bits(dstp)); } @@ -337,9 +437,9 @@ static inline void __cpumask_clear_cpu(int cpu, struct cpumask *dstp) * @cpu: cpu number (< nr_cpu_ids) * @cpumask: the cpumask pointer * - * Returns 1 if @cpu is set in @cpumask, else returns 0 + * Returns true if @cpu is set in @cpumask, else returns false */ -static inline int cpumask_test_cpu(int cpu, const struct cpumask *cpumask) +static __always_inline bool cpumask_test_cpu(int cpu, const struct cpumask *cpumask) { return test_bit(cpumask_check(cpu), cpumask_bits((cpumask))); } @@ -349,11 +449,11 @@ static inline int cpumask_test_cpu(int cpu, const struct cpumask *cpumask) * @cpu: cpu number (< nr_cpu_ids) * @cpumask: the cpumask pointer * - * Returns 1 if @cpu is set in old bitmap of @cpumask, else returns 0 + * Returns true if @cpu is set in old bitmap of @cpumask, else returns false * * test_and_set_bit wrapper for cpumasks. */ -static inline int cpumask_test_and_set_cpu(int cpu, struct cpumask *cpumask) +static __always_inline bool cpumask_test_and_set_cpu(int cpu, struct cpumask *cpumask) { return test_and_set_bit(cpumask_check(cpu), cpumask_bits(cpumask)); } @@ -363,11 +463,11 @@ static inline int cpumask_test_and_set_cpu(int cpu, struct cpumask *cpumask) * @cpu: cpu number (< nr_cpu_ids) * @cpumask: the cpumask pointer * - * Returns 1 if @cpu is set in old bitmap of @cpumask, else returns 0 + * Returns true if @cpu is set in old bitmap of @cpumask, else returns false * * test_and_clear_bit wrapper for cpumasks. */ -static inline int cpumask_test_and_clear_cpu(int cpu, struct cpumask *cpumask) +static __always_inline bool cpumask_test_and_clear_cpu(int cpu, struct cpumask *cpumask) { return test_and_clear_bit(cpumask_check(cpu), cpumask_bits(cpumask)); } @@ -396,9 +496,9 @@ static inline void cpumask_clear(struct cpumask *dstp) * @src1p: the first input * @src2p: the second input * - * If *@dstp is empty, returns 0, else returns 1 + * If *@dstp is empty, returns false, else returns true */ -static inline int cpumask_and(struct cpumask *dstp, +static inline bool cpumask_and(struct cpumask *dstp, const struct cpumask *src1p, const struct cpumask *src2p) { @@ -439,9 +539,9 @@ static inline void cpumask_xor(struct cpumask *dstp, * @src1p: the first input * @src2p: the second input * - * If *@dstp is empty, returns 0, else returns 1 + * If *@dstp is empty, returns false, else returns true */ -static inline int cpumask_andnot(struct cpumask *dstp, +static inline bool cpumask_andnot(struct cpumask *dstp, const struct cpumask *src1p, const struct cpumask *src2p) { @@ -504,9 +604,9 @@ static inline bool cpumask_intersects(const struct cpumask *src1p, * @src1p: the first input * @src2p: the second input * - * Returns 1 if *@src1p is a subset of *@src2p, else returns 0 + * Returns true if *@src1p is a subset of *@src2p, else returns false */ -static inline int cpumask_subset(const struct cpumask *src1p, +static inline bool cpumask_subset(const struct cpumask *src1p, const struct cpumask *src2p) { return bitmap_subset(cpumask_bits(src1p), cpumask_bits(src2p), @@ -541,6 +641,17 @@ static inline unsigned int cpumask_weight(const struct cpumask *srcp) } /** + * cpumask_weight_and - Count of bits in (*srcp1 & *srcp2) + * @srcp1: the cpumask to count bits (< nr_cpu_ids) in. + * @srcp2: the cpumask to count bits (< nr_cpu_ids) in. + */ +static inline unsigned int cpumask_weight_and(const struct cpumask *srcp1, + const struct cpumask *srcp2) +{ + return bitmap_weight_and(cpumask_bits(srcp1), cpumask_bits(srcp2), nr_cpumask_bits); +} + +/** * cpumask_shift_right - *dstp = *srcp >> n * @dstp: the cpumask result * @srcp: the input to shift @@ -586,15 +697,6 @@ static inline void cpumask_copy(struct cpumask *dstp, #define cpumask_any(srcp) cpumask_first(srcp) /** - * cpumask_first_and - return the first cpu from *srcp1 & *srcp2 - * @src1p: the first input - * @src2p: the second input - * - * Returns >= nr_cpu_ids if no cpus set in both. See also cpumask_next_and(). - */ -#define cpumask_first_and(src1p, src2p) cpumask_next_and(-1, (src1p), (src2p)) - -/** * cpumask_any_and - pick a "random" cpu from *mask1 & *mask2 * @mask1: the first input cpumask * @mask2: the second input cpumask @@ -717,9 +819,35 @@ typedef struct cpumask *cpumask_var_t; #define __cpumask_var_read_mostly __read_mostly bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node); -bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags); -bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node); -bool zalloc_cpumask_var(cpumask_var_t *mask, gfp_t flags); + +static inline +bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node) +{ + return alloc_cpumask_var_node(mask, flags | __GFP_ZERO, node); +} + +/** + * alloc_cpumask_var - allocate a struct cpumask + * @mask: pointer to cpumask_var_t where the cpumask is returned + * @flags: GFP_ flags + * + * Only defined when CONFIG_CPUMASK_OFFSTACK=y, otherwise is + * a nop returning a constant 1 (in <linux/cpumask.h>). + * + * See alloc_cpumask_var_node. + */ +static inline +bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) +{ + return alloc_cpumask_var_node(mask, flags, NUMA_NO_NODE); +} + +static inline +bool zalloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) +{ + return alloc_cpumask_var(mask, flags | __GFP_ZERO); +} + void alloc_bootmem_cpumask_var(cpumask_var_t *mask); void free_cpumask_var(cpumask_var_t mask); void free_bootmem_cpumask_var(cpumask_var_t mask); @@ -785,9 +913,16 @@ extern const DECLARE_BITMAP(cpu_all_bits, NR_CPUS); /* First bits of cpu_bit_bitmap are in fact unset. */ #define cpu_none_mask to_cpumask(cpu_bit_bitmap[0]) +#if NR_CPUS == 1 +/* Uniprocessor: the possible/online/present masks are always "1" */ +#define for_each_possible_cpu(cpu) for ((cpu) = 0; (cpu) < 1; (cpu)++) +#define for_each_online_cpu(cpu) for ((cpu) = 0; (cpu) < 1; (cpu)++) +#define for_each_present_cpu(cpu) for ((cpu) = 0; (cpu) < 1; (cpu)++) +#else #define for_each_possible_cpu(cpu) for_each_cpu((cpu), cpu_possible_mask) #define for_each_online_cpu(cpu) for_each_cpu((cpu), cpu_online_mask) #define for_each_present_cpu(cpu) for_each_cpu((cpu), cpu_present_mask) +#endif /* Wrappers for arch boot code to manipulate normally-constant masks */ void init_cpu_present(const struct cpumask *src); @@ -1045,4 +1180,23 @@ cpumap_print_list_to_buf(char *buf, const struct cpumask *mask, [0] = 1UL \ } } +/* + * Provide a valid theoretical max size for cpumap and cpulist sysfs files + * to avoid breaking userspace which may allocate a buffer based on the size + * reported by e.g. fstat. + * + * for cpumap NR_CPUS * 9/32 - 1 should be an exact length. + * + * For cpulist 7 is (ceil(log10(NR_CPUS)) + 1) allowing for NR_CPUS to be up + * to 2 orders of magnitude larger than 8192. And then we divide by 2 to + * cover a worst-case of every other cpu being on one of two nodes for a + * very large NR_CPUS. + * + * Use PAGE_SIZE as a minimum for smaller configurations while avoiding + * unsigned comparison to -1. + */ +#define CPUMAP_FILE_MAX_BYTES (((NR_CPUS * 9)/32 > PAGE_SIZE) \ + ? (NR_CPUS * 9)/32 - 1 : PAGE_SIZE) +#define CPULIST_FILE_MAX_BYTES (((NR_CPUS * 7)/2 > PAGE_SIZE) ? (NR_CPUS * 7)/2 : PAGE_SIZE) + #endif /* __LINUX_CPUMASK_H */ diff --git a/include/linux/cpumask_api.h b/include/linux/cpumask_api.h new file mode 100644 index 000000000000..83bd3ebe82b0 --- /dev/null +++ b/include/linux/cpumask_api.h @@ -0,0 +1 @@ +#include <linux/cpumask.h> diff --git a/include/linux/crash_dump.h b/include/linux/crash_dump.h index 620821549b23..0f3a656293b0 100644 --- a/include/linux/crash_dump.h +++ b/include/linux/crash_dump.h @@ -24,11 +24,10 @@ extern int remap_oldmem_pfn_range(struct vm_area_struct *vma, unsigned long from, unsigned long pfn, unsigned long size, pgprot_t prot); -extern ssize_t copy_oldmem_page(unsigned long, char *, size_t, - unsigned long, int); -extern ssize_t copy_oldmem_page_encrypted(unsigned long pfn, char *buf, - size_t csize, unsigned long offset, - int userbuf); +ssize_t copy_oldmem_page(struct iov_iter *i, unsigned long pfn, size_t csize, + unsigned long offset); +ssize_t copy_oldmem_page_encrypted(struct iov_iter *iter, unsigned long pfn, + size_t csize, unsigned long offset); void vmcore_cleanup(void); @@ -135,13 +134,11 @@ static inline int vmcore_add_device_dump(struct vmcoredd_data *data) #endif /* CONFIG_PROC_VMCORE_DEVICE_DUMP */ #ifdef CONFIG_PROC_VMCORE -ssize_t read_from_oldmem(char *buf, size_t count, - u64 *ppos, int userbuf, - bool encrypted); +ssize_t read_from_oldmem(struct iov_iter *iter, size_t count, + u64 *ppos, bool encrypted); #else -static inline ssize_t read_from_oldmem(char *buf, size_t count, - u64 *ppos, int userbuf, - bool encrypted) +static inline ssize_t read_from_oldmem(struct iov_iter *iter, size_t count, + u64 *ppos, bool encrypted) { return -EOPNOTSUPP; } diff --git a/include/linux/crc-itu-t.h b/include/linux/crc-itu-t.h index a4367051e192..2f991a427ade 100644 --- a/include/linux/crc-itu-t.h +++ b/include/linux/crc-itu-t.h @@ -4,7 +4,7 @@ * * Implements the standard CRC ITU-T V.41: * Width 16 - * Poly 0x1021 (x^16 + x^12 + x^15 + 1) + * Poly 0x1021 (x^16 + x^12 + x^5 + 1) * Init 0 */ diff --git a/include/linux/crc64.h b/include/linux/crc64.h index c756e65a1b58..e044c60d1e61 100644 --- a/include/linux/crc64.h +++ b/include/linux/crc64.h @@ -7,5 +7,12 @@ #include <linux/types.h> +#define CRC64_ROCKSOFT_STRING "crc64-rocksoft" + u64 __pure crc64_be(u64 crc, const void *p, size_t len); +u64 __pure crc64_rocksoft_generic(u64 crc, const void *p, size_t len); + +u64 crc64_rocksoft(const unsigned char *buffer, size_t len); +u64 crc64_rocksoft_update(u64 crc, const unsigned char *buffer, size_t len); + #endif /* _LINUX_CRC64_H */ diff --git a/include/linux/cred.h b/include/linux/cred.h index fcbc6885cc09..9ed9232af934 100644 --- a/include/linux/cred.h +++ b/include/linux/cred.h @@ -176,7 +176,7 @@ extern int set_cred_ucounts(struct cred *); * check for validity of credentials */ #ifdef CONFIG_DEBUG_CREDENTIALS -extern void __invalid_creds(const struct cred *, const char *, unsigned); +extern void __noreturn __invalid_creds(const struct cred *, const char *, unsigned); extern void __validate_process_creds(struct task_struct *, const char *, unsigned); diff --git a/include/linux/crypto.h b/include/linux/crypto.h index 855869e1fd32..2324ab6f1846 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -133,6 +133,15 @@ #define CRYPTO_ALG_ALLOCATES_MEMORY 0x00010000 /* + * Mark an algorithm as a service implementation only usable by a + * template and never by a normal user of the kernel crypto API. + * This is intended to be used by algorithms that are themselves + * not FIPS-approved but may instead be used to implement parts of + * a FIPS-approved algorithm (e.g., dh vs. ffdhe2048(dh)). + */ +#define CRYPTO_ALG_FIPS_INTERNAL 0x00020000 + +/* * Transform masks and values (for crt_flags). */ #define CRYPTO_TFM_NEED_KEY 0x00000001 diff --git a/include/linux/cuda.h b/include/linux/cuda.h index 45bfe9d61271..daf3e6f98444 100644 --- a/include/linux/cuda.h +++ b/include/linux/cuda.h @@ -12,7 +12,7 @@ #include <uapi/linux/cuda.h> -extern int find_via_cuda(void); +extern int __init find_via_cuda(void); extern int cuda_request(struct adb_request *req, void (*done)(struct adb_request *), int nbytes, ...); extern void cuda_poll(void); diff --git a/include/linux/damon.h b/include/linux/damon.h index b4d4be3cc987..620ada094c3b 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -11,12 +11,19 @@ #include <linux/mutex.h> #include <linux/time64.h> #include <linux/types.h> +#include <linux/random.h> /* Minimal region size. Every damon_region is aligned by this. */ #define DAMON_MIN_REGION PAGE_SIZE /* Max priority score for DAMON-based operation schemes */ #define DAMOS_MAX_SCORE (99) +/* Get a random number in [l, r) */ +static inline unsigned long damon_rand(unsigned long l, unsigned long r) +{ + return l + prandom_u32_max(r - l); +} + /** * struct damon_addr_range - Represents an address region of [@start, @end). * @start: Start address of the region (inclusive). @@ -53,19 +60,18 @@ struct damon_region { /** * struct damon_target - Represents a monitoring target. - * @id: Unique identifier for this target. + * @pid: The PID of the virtual address space to monitor. * @nr_regions: Number of monitoring target regions of this target. * @regions_list: Head of the monitoring target regions of this target. * @list: List head for siblings. * * Each monitoring context could have multiple targets. For example, a context * for virtual memory address spaces could have multiple target processes. The - * @id of each target should be unique among the targets of the context. For - * example, in the virtual address monitoring context, it could be a pidfd or - * an address of an mm_struct. + * @pid should be set for appropriate &struct damon_operations including the + * virtual address spaces monitoring operations. */ struct damon_target { - unsigned long id; + struct pid *pid; unsigned int nr_regions; struct list_head regions_list; struct list_head list; @@ -80,7 +86,10 @@ struct damon_target { * @DAMOS_PAGEOUT: Call ``madvise()`` for the region with MADV_PAGEOUT. * @DAMOS_HUGEPAGE: Call ``madvise()`` for the region with MADV_HUGEPAGE. * @DAMOS_NOHUGEPAGE: Call ``madvise()`` for the region with MADV_NOHUGEPAGE. + * @DAMOS_LRU_PRIO: Prioritize the region on its LRU lists. + * @DAMOS_LRU_DEPRIO: Deprioritize the region on its LRU lists. * @DAMOS_STAT: Do nothing but count the stat. + * @NR_DAMOS_ACTIONS: Total number of DAMOS actions */ enum damos_action { DAMOS_WILLNEED, @@ -88,7 +97,10 @@ enum damos_action { DAMOS_PAGEOUT, DAMOS_HUGEPAGE, DAMOS_NOHUGEPAGE, + DAMOS_LRU_PRIO, + DAMOS_LRU_DEPRIO, DAMOS_STAT, /* Do nothing but only record the stat */ + NR_DAMOS_ACTIONS, }; /** @@ -114,9 +126,9 @@ enum damos_action { * uses smaller one as the effective quota. * * For selecting regions within the quota, DAMON prioritizes current scheme's - * target memory regions using the &struct damon_primitive->get_scheme_score. + * target memory regions using the &struct damon_operations->get_scheme_score. * You could customize the prioritization logic by setting &weight_sz, - * &weight_nr_accesses, and &weight_age, because monitoring primitives are + * &weight_nr_accesses, and &weight_age, because monitoring operations are * encouraged to respect those. */ struct damos_quota { @@ -151,10 +163,12 @@ struct damos_quota { * * @DAMOS_WMARK_NONE: Ignore the watermarks of the given scheme. * @DAMOS_WMARK_FREE_MEM_RATE: Free memory rate of the system in [0,1000]. + * @NR_DAMOS_WMARK_METRICS: Total number of DAMOS watermark metrics */ enum damos_wmark_metric { DAMOS_WMARK_NONE, DAMOS_WMARK_FREE_MEM_RATE, + NR_DAMOS_WMARK_METRICS, }; /** @@ -186,25 +200,51 @@ struct damos_watermarks { }; /** - * struct damos - Represents a Data Access Monitoring-based Operation Scheme. + * struct damos_stat - Statistics on a given scheme. + * @nr_tried: Total number of regions that the scheme is tried to be applied. + * @sz_tried: Total size of regions that the scheme is tried to be applied. + * @nr_applied: Total number of regions that the scheme is applied. + * @sz_applied: Total size of regions that the scheme is applied. + * @qt_exceeds: Total number of times the quota of the scheme has exceeded. + */ +struct damos_stat { + unsigned long nr_tried; + unsigned long sz_tried; + unsigned long nr_applied; + unsigned long sz_applied; + unsigned long qt_exceeds; +}; + +/** + * struct damos_access_pattern - Target access pattern of the given scheme. * @min_sz_region: Minimum size of target regions. * @max_sz_region: Maximum size of target regions. * @min_nr_accesses: Minimum ``->nr_accesses`` of target regions. * @max_nr_accesses: Maximum ``->nr_accesses`` of target regions. * @min_age_region: Minimum age of target regions. * @max_age_region: Maximum age of target regions. + */ +struct damos_access_pattern { + unsigned long min_sz_region; + unsigned long max_sz_region; + unsigned int min_nr_accesses; + unsigned int max_nr_accesses; + unsigned int min_age_region; + unsigned int max_age_region; +}; + +/** + * struct damos - Represents a Data Access Monitoring-based Operation Scheme. + * @pattern: Access pattern of target regions. * @action: &damo_action to be applied to the target regions. * @quota: Control the aggressiveness of this scheme. * @wmarks: Watermarks for automated (in)activation of this scheme. - * @stat_count: Total number of regions that this scheme is applied. - * @stat_sz: Total size of regions that this scheme is applied. + * @stat: Statistics of this scheme. * @list: List head for siblings. * * For each aggregation interval, DAMON finds regions which fit in the - * condition (&min_sz_region, &max_sz_region, &min_nr_accesses, - * &max_nr_accesses, &min_age_region, &max_age_region) and applies &action to - * those. To avoid consuming too much CPU time or IO resources for the - * &action, "a is used. + * &pattern and applies &action to those. To avoid consuming too much + * CPU time or IO resources for the &action, "a is used. * * To do the work only when needed, schemes can be activated for specific * system situations using &wmarks. If all schemes that registered to the @@ -219,27 +259,38 @@ struct damos_watermarks { * &action is applied. */ struct damos { - unsigned long min_sz_region; - unsigned long max_sz_region; - unsigned int min_nr_accesses; - unsigned int max_nr_accesses; - unsigned int min_age_region; - unsigned int max_age_region; + struct damos_access_pattern pattern; enum damos_action action; struct damos_quota quota; struct damos_watermarks wmarks; - unsigned long stat_count; - unsigned long stat_sz; + struct damos_stat stat; struct list_head list; }; +/** + * enum damon_ops_id - Identifier for each monitoring operations implementation + * + * @DAMON_OPS_VADDR: Monitoring operations for virtual address spaces + * @DAMON_OPS_FVADDR: Monitoring operations for only fixed ranges of virtual + * address spaces + * @DAMON_OPS_PADDR: Monitoring operations for the physical address space + * @NR_DAMON_OPS: Number of monitoring operations implementations + */ +enum damon_ops_id { + DAMON_OPS_VADDR, + DAMON_OPS_FVADDR, + DAMON_OPS_PADDR, + NR_DAMON_OPS, +}; + struct damon_ctx; /** - * struct damon_primitive - Monitoring primitives for given use cases. + * struct damon_operations - Monitoring operations for given use cases. * - * @init: Initialize primitive-internal data structures. - * @update: Update primitive-internal data structures. + * @id: Identifier of this operations set. + * @init: Initialize operations-related data structures. + * @update: Update operations-related data structures. * @prepare_access_checks: Prepare next access check of target regions. * @check_accesses: Check the accesses to target regions. * @reset_aggregated: Reset aggregated accesses monitoring results. @@ -249,18 +300,20 @@ struct damon_ctx; * @cleanup: Clean up the context. * * DAMON can be extended for various address spaces and usages. For this, - * users should register the low level primitives for their target address - * space and usecase via the &damon_ctx.primitive. Then, the monitoring thread + * users should register the low level operations for their target address + * space and usecase via the &damon_ctx.ops. Then, the monitoring thread * (&damon_ctx.kdamond) calls @init and @prepare_access_checks before starting - * the monitoring, @update after each &damon_ctx.primitive_update_interval, and + * the monitoring, @update after each &damon_ctx.ops_update_interval, and * @check_accesses, @target_valid and @prepare_access_checks after each * &damon_ctx.sample_interval. Finally, @reset_aggregated is called after each * &damon_ctx.aggr_interval. * - * @init should initialize primitive-internal data structures. For example, + * Each &struct damon_operations instance having valid @id can be registered + * via damon_register_ops() and selected by damon_select_ops() later. + * @init should initialize operations-related data structures. For example, * this could be used to construct proper monitoring target regions and link * those to @damon_ctx.adaptive_targets. - * @update should update the primitive-internal data structures. For example, + * @update should update the operations-related data structures. For example, * this could be used to update monitoring target regions for current status. * @prepare_access_checks should manipulate the monitoring regions to be * prepared for the next access check. @@ -274,12 +327,14 @@ struct damon_ctx; * as an integer in [0, &DAMOS_MAX_SCORE]. * @apply_scheme is called from @kdamond when a region for user provided * DAMON-based operation scheme is found. It should apply the scheme's action - * to the region. This is not used for &DAMON_ARBITRARY_TARGET case. + * to the region and return bytes of the region that the action is successfully + * applied. * @target_valid should check whether the target is still valid for the * monitoring. * @cleanup is called from @kdamond just before its termination. */ -struct damon_primitive { +struct damon_operations { + enum damon_ops_id id; void (*init)(struct damon_ctx *context); void (*update)(struct damon_ctx *context); void (*prepare_access_checks)(struct damon_ctx *context); @@ -288,9 +343,10 @@ struct damon_primitive { int (*get_scheme_score)(struct damon_ctx *context, struct damon_target *t, struct damon_region *r, struct damos *scheme); - int (*apply_scheme)(struct damon_ctx *context, struct damon_target *t, - struct damon_region *r, struct damos *scheme); - bool (*target_valid)(void *target); + unsigned long (*apply_scheme)(struct damon_ctx *context, + struct damon_target *t, struct damon_region *r, + struct damos *scheme); + bool (*target_valid)(struct damon_target *t); void (*cleanup)(struct damon_ctx *context); }; @@ -298,6 +354,7 @@ struct damon_primitive { * struct damon_callback - Monitoring events notification callbacks. * * @before_start: Called before starting the monitoring. + * @after_wmarks_check: Called after each schemes' watermarks check. * @after_sampling: Called after each sampling. * @after_aggregation: Called after each aggregation. * @before_terminate: Called before terminating the monitoring. @@ -308,6 +365,11 @@ struct damon_primitive { * respectively. Therefore, those are good places for installing and cleaning * @private. * + * The monitoring thread calls @after_wmarks_check after each DAMON-based + * operation schemes' watermarks check. If users need to make changes to the + * attributes of the monitoring context while it's deactivated due to the + * watermarks, this is the good place to do. + * * The monitoring thread calls @after_sampling and @after_aggregation for each * of the sampling intervals and aggregation intervals, respectively. * Therefore, users can safely access the monitoring results without additional @@ -320,31 +382,47 @@ struct damon_callback { void *private; int (*before_start)(struct damon_ctx *context); + int (*after_wmarks_check)(struct damon_ctx *context); int (*after_sampling)(struct damon_ctx *context); int (*after_aggregation)(struct damon_ctx *context); void (*before_terminate)(struct damon_ctx *context); }; /** - * struct damon_ctx - Represents a context for each monitoring. This is the - * main interface that allows users to set the attributes and get the results - * of the monitoring. + * struct damon_attrs - Monitoring attributes for accuracy/overhead control. * * @sample_interval: The time between access samplings. * @aggr_interval: The time between monitor results aggregations. - * @primitive_update_interval: The time between monitoring primitive updates. + * @ops_update_interval: The time between monitoring operations updates. + * @min_nr_regions: The minimum number of adaptive monitoring + * regions. + * @max_nr_regions: The maximum number of adaptive monitoring + * regions. * * For each @sample_interval, DAMON checks whether each region is accessed or * not. It aggregates and keeps the access information (number of accesses to * each region) for @aggr_interval time. DAMON also checks whether the target * memory regions need update (e.g., by ``mmap()`` calls from the application, * in case of virtual memory monitoring) and applies the changes for each - * @primitive_update_interval. All time intervals are in micro-seconds. - * Please refer to &struct damon_primitive and &struct damon_callback for more + * @ops_update_interval. All time intervals are in micro-seconds. + * Please refer to &struct damon_operations and &struct damon_callback for more * detail. + */ +struct damon_attrs { + unsigned long sample_interval; + unsigned long aggr_interval; + unsigned long ops_update_interval; + unsigned long min_nr_regions; + unsigned long max_nr_regions; +}; + +/** + * struct damon_ctx - Represents a context for each monitoring. This is the + * main interface that allows users to set the attributes and get the results + * of the monitoring. * + * @attrs: Monitoring attributes for accuracy/overhead control. * @kdamond: Kernel thread who does the monitoring. - * @kdamond_stop: Notifies whether kdamond should stop. * @kdamond_lock: Mutex for the synchronizations with @kdamond. * * For each monitoring context, one kernel thread for the monitoring is @@ -352,58 +430,72 @@ struct damon_callback { * * Once started, the monitoring thread runs until explicitly required to be * terminated or every monitoring target is invalid. The validity of the - * targets is checked via the &damon_primitive.target_valid of @primitive. The - * termination can also be explicitly requested by writing non-zero to - * @kdamond_stop. The thread sets @kdamond to NULL when it terminates. - * Therefore, users can know whether the monitoring is ongoing or terminated by - * reading @kdamond. Reads and writes to @kdamond and @kdamond_stop from - * outside of the monitoring thread must be protected by @kdamond_lock. + * targets is checked via the &damon_operations.target_valid of @ops. The + * termination can also be explicitly requested by calling damon_stop(). + * The thread sets @kdamond to NULL when it terminates. Therefore, users can + * know whether the monitoring is ongoing or terminated by reading @kdamond. + * Reads and writes to @kdamond from outside of the monitoring thread must + * be protected by @kdamond_lock. * - * Note that the monitoring thread protects only @kdamond and @kdamond_stop via - * @kdamond_lock. Accesses to other fields must be protected by themselves. + * Note that the monitoring thread protects only @kdamond via @kdamond_lock. + * Accesses to other fields must be protected by themselves. * - * @primitive: Set of monitoring primitives for given use cases. + * @ops: Set of monitoring operations for given use cases. * @callback: Set of callbacks for monitoring events notifications. * - * @min_nr_regions: The minimum number of adaptive monitoring regions. - * @max_nr_regions: The maximum number of adaptive monitoring regions. * @adaptive_targets: Head of monitoring targets (&damon_target) list. * @schemes: Head of schemes (&damos) list. */ struct damon_ctx { - unsigned long sample_interval; - unsigned long aggr_interval; - unsigned long primitive_update_interval; + struct damon_attrs attrs; /* private: internal use only */ struct timespec64 last_aggregation; - struct timespec64 last_primitive_update; + struct timespec64 last_ops_update; /* public: */ struct task_struct *kdamond; struct mutex kdamond_lock; - struct damon_primitive primitive; + struct damon_operations ops; struct damon_callback callback; - unsigned long min_nr_regions; - unsigned long max_nr_regions; struct list_head adaptive_targets; struct list_head schemes; }; -#define damon_next_region(r) \ - (container_of(r->list.next, struct damon_region, list)) +static inline struct damon_region *damon_next_region(struct damon_region *r) +{ + return container_of(r->list.next, struct damon_region, list); +} + +static inline struct damon_region *damon_prev_region(struct damon_region *r) +{ + return container_of(r->list.prev, struct damon_region, list); +} -#define damon_prev_region(r) \ - (container_of(r->list.prev, struct damon_region, list)) +static inline struct damon_region *damon_last_region(struct damon_target *t) +{ + return list_last_entry(&t->regions_list, struct damon_region, list); +} + +static inline struct damon_region *damon_first_region(struct damon_target *t) +{ + return list_first_entry(&t->regions_list, struct damon_region, list); +} + +static inline unsigned long damon_sz_region(struct damon_region *r) +{ + return r->ar.end - r->ar.start; +} -#define damon_last_region(t) \ - (list_last_entry(&t->regions_list, struct damon_region, list)) #define damon_for_each_region(r, t) \ list_for_each_entry(r, &t->regions_list, list) +#define damon_for_each_region_from(r, t) \ + list_for_each_entry_from(r, &t->regions_list, list) + #define damon_for_each_region_safe(r, next, t) \ list_for_each_entry_safe(r, next, &t->regions_list, list) @@ -422,22 +514,30 @@ struct damon_ctx { #ifdef CONFIG_DAMON struct damon_region *damon_new_region(unsigned long start, unsigned long end); -inline void damon_insert_region(struct damon_region *r, + +/* + * Add a region between two other regions + */ +static inline void damon_insert_region(struct damon_region *r, struct damon_region *prev, struct damon_region *next, - struct damon_target *t); + struct damon_target *t) +{ + __list_add(&r->list, &prev->list, &next->list); + t->nr_regions++; +} + void damon_add_region(struct damon_region *r, struct damon_target *t); void damon_destroy_region(struct damon_region *r, struct damon_target *t); +int damon_set_regions(struct damon_target *t, struct damon_addr_range *ranges, + unsigned int nr_ranges); -struct damos *damon_new_scheme( - unsigned long min_sz_region, unsigned long max_sz_region, - unsigned int min_nr_accesses, unsigned int max_nr_accesses, - unsigned int min_age_region, unsigned int max_age_region, - enum damos_action action, struct damos_quota *quota, - struct damos_watermarks *wmarks); +struct damos *damon_new_scheme(struct damos_access_pattern *pattern, + enum damos_action action, struct damos_quota *quota, + struct damos_watermarks *wmarks); void damon_add_scheme(struct damon_ctx *ctx, struct damos *s); void damon_destroy_scheme(struct damos *s); -struct damon_target *damon_new_target(unsigned long id); +struct damon_target *damon_new_target(void); void damon_add_target(struct damon_ctx *ctx, struct damon_target *t); bool damon_targets_empty(struct damon_ctx *ctx); void damon_free_target(struct damon_target *t); @@ -446,49 +546,26 @@ unsigned int damon_nr_regions(struct damon_target *t); struct damon_ctx *damon_new_ctx(void); void damon_destroy_ctx(struct damon_ctx *ctx); -int damon_set_targets(struct damon_ctx *ctx, - unsigned long *ids, ssize_t nr_ids); -int damon_set_attrs(struct damon_ctx *ctx, unsigned long sample_int, - unsigned long aggr_int, unsigned long primitive_upd_int, - unsigned long min_nr_reg, unsigned long max_nr_reg); -int damon_set_schemes(struct damon_ctx *ctx, +int damon_set_attrs(struct damon_ctx *ctx, struct damon_attrs *attrs); +void damon_set_schemes(struct damon_ctx *ctx, struct damos **schemes, ssize_t nr_schemes); int damon_nr_running_ctxs(void); +bool damon_is_registered_ops(enum damon_ops_id id); +int damon_register_ops(struct damon_operations *ops); +int damon_select_ops(struct damon_ctx *ctx, enum damon_ops_id id); + +static inline bool damon_target_has_pid(const struct damon_ctx *ctx) +{ + return ctx->ops.id == DAMON_OPS_VADDR || ctx->ops.id == DAMON_OPS_FVADDR; +} -int damon_start(struct damon_ctx **ctxs, int nr_ctxs); + +int damon_start(struct damon_ctx **ctxs, int nr_ctxs, bool exclusive); int damon_stop(struct damon_ctx **ctxs, int nr_ctxs); -#endif /* CONFIG_DAMON */ +int damon_set_region_biggest_system_ram_default(struct damon_target *t, + unsigned long *start, unsigned long *end); -#ifdef CONFIG_DAMON_VADDR - -/* Monitoring primitives for virtual memory address spaces */ -void damon_va_init(struct damon_ctx *ctx); -void damon_va_update(struct damon_ctx *ctx); -void damon_va_prepare_access_checks(struct damon_ctx *ctx); -unsigned int damon_va_check_accesses(struct damon_ctx *ctx); -bool damon_va_target_valid(void *t); -void damon_va_cleanup(struct damon_ctx *ctx); -int damon_va_apply_scheme(struct damon_ctx *context, struct damon_target *t, - struct damon_region *r, struct damos *scheme); -int damon_va_scheme_score(struct damon_ctx *context, struct damon_target *t, - struct damon_region *r, struct damos *scheme); -void damon_va_set_primitives(struct damon_ctx *ctx); - -#endif /* CONFIG_DAMON_VADDR */ - -#ifdef CONFIG_DAMON_PADDR - -/* Monitoring primitives for the physical memory address space */ -void damon_pa_prepare_access_checks(struct damon_ctx *ctx); -unsigned int damon_pa_check_accesses(struct damon_ctx *ctx); -bool damon_pa_target_valid(void *t); -int damon_pa_apply_scheme(struct damon_ctx *context, struct damon_target *t, - struct damon_region *r, struct damos *scheme); -int damon_pa_scheme_score(struct damon_ctx *context, struct damon_target *t, - struct damon_region *r, struct damos *scheme); -void damon_pa_set_primitives(struct damon_ctx *ctx); - -#endif /* CONFIG_DAMON_PADDR */ +#endif /* CONFIG_DAMON */ #endif /* _DAMON_H */ diff --git a/include/linux/dax.h b/include/linux/dax.h index 8623caa67388..ba985333e26b 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -6,14 +6,19 @@ #include <linux/mm.h> #include <linux/radix-tree.h> -/* Flag for synchronous flush */ -#define DAXDEV_F_SYNC (1UL << 0) - typedef unsigned long dax_entry_t; +struct dax_device; +struct gendisk; struct iomap_ops; +struct iomap_iter; struct iomap; -struct dax_device; + +enum dax_access_mode { + DAX_ACCESS, + DAX_RECOVERY_WRITE, +}; + struct dax_operations { /* * direct_access: translate a device-relative @@ -21,40 +26,46 @@ struct dax_operations { * number of pages available for DAX at that pfn. */ long (*direct_access)(struct dax_device *, pgoff_t, long, - void **, pfn_t *); + enum dax_access_mode, void **, pfn_t *); /* * Validate whether this device is usable as an fsdax backing * device. */ bool (*dax_supported)(struct dax_device *, struct block_device *, int, sector_t, sector_t); - /* copy_from_iter: required operation for fs-dax direct-i/o */ - size_t (*copy_from_iter)(struct dax_device *, pgoff_t, void *, size_t, - struct iov_iter *); - /* copy_to_iter: required operation for fs-dax direct-i/o */ - size_t (*copy_to_iter)(struct dax_device *, pgoff_t, void *, size_t, - struct iov_iter *); /* zero_page_range: required operation. Zero page range */ int (*zero_page_range)(struct dax_device *, pgoff_t, size_t); + /* + * recovery_write: recover a poisoned range by DAX device driver + * capable of clearing poison. + */ + size_t (*recovery_write)(struct dax_device *dax_dev, pgoff_t pgoff, + void *addr, size_t bytes, struct iov_iter *iter); +}; + +struct dax_holder_operations { + /* + * notify_failure - notify memory failure into inner holder device + * @dax_dev: the dax device which contains the holder + * @offset: offset on this dax device where memory failure occurs + * @len: length of this memory failure event + * @flags: action flags for memory failure handler + */ + int (*notify_failure)(struct dax_device *dax_dev, u64 offset, + u64 len, int mf_flags); }; #if IS_ENABLED(CONFIG_DAX) -struct dax_device *alloc_dax(void *private, const char *host, - const struct dax_operations *ops, unsigned long flags); +struct dax_device *alloc_dax(void *private, const struct dax_operations *ops); +void *dax_holder(struct dax_device *dax_dev); void put_dax(struct dax_device *dax_dev); void kill_dax(struct dax_device *dax_dev); void dax_write_cache(struct dax_device *dax_dev, bool wc); bool dax_write_cache_enabled(struct dax_device *dax_dev); -bool __dax_synchronous(struct dax_device *dax_dev); -static inline bool dax_synchronous(struct dax_device *dax_dev) -{ - return __dax_synchronous(dax_dev); -} -void __set_dax_synchronous(struct dax_device *dax_dev); -static inline void set_dax_synchronous(struct dax_device *dax_dev) -{ - __set_dax_synchronous(dax_dev); -} +bool dax_synchronous(struct dax_device *dax_dev); +void set_dax_synchronous(struct dax_device *dax_dev); +size_t dax_recovery_write(struct dax_device *dax_dev, pgoff_t pgoff, + void *addr, size_t bytes, struct iov_iter *i); /* * Check if given mapping is supported by the file / underlying device. */ @@ -68,8 +79,12 @@ static inline bool daxdev_mapping_supported(struct vm_area_struct *vma, return dax_synchronous(dax_dev); } #else -static inline struct dax_device *alloc_dax(void *private, const char *host, - const struct dax_operations *ops, unsigned long flags) +static inline void *dax_holder(struct dax_device *dax_dev) +{ + return NULL; +} +static inline struct dax_device *alloc_dax(void *private, + const struct dax_operations *ops) { /* * Callers should check IS_ENABLED(CONFIG_DAX) to know if this @@ -102,24 +117,43 @@ static inline bool daxdev_mapping_supported(struct vm_area_struct *vma, { return !(vma->vm_flags & VM_SYNC); } +static inline size_t dax_recovery_write(struct dax_device *dax_dev, + pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i) +{ + return 0; +} #endif -struct writeback_control; -int bdev_dax_pgoff(struct block_device *, sector_t, size_t, pgoff_t *pgoff); -#if IS_ENABLED(CONFIG_FS_DAX) -bool generic_fsdax_supported(struct dax_device *dax_dev, - struct block_device *bdev, int blocksize, sector_t start, - sector_t sectors); - -bool dax_supported(struct dax_device *dax_dev, struct block_device *bdev, - int blocksize, sector_t start, sector_t len); +void set_dax_nocache(struct dax_device *dax_dev); +void set_dax_nomc(struct dax_device *dax_dev); -static inline void fs_put_dax(struct dax_device *dax_dev) +struct writeback_control; +#if defined(CONFIG_BLOCK) && defined(CONFIG_FS_DAX) +int dax_add_host(struct dax_device *dax_dev, struct gendisk *disk); +void dax_remove_host(struct gendisk *disk); +struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev, u64 *start_off, + void *holder, const struct dax_holder_operations *ops); +void fs_put_dax(struct dax_device *dax_dev, void *holder); +#else +static inline int dax_add_host(struct dax_device *dax_dev, struct gendisk *disk) +{ + return 0; +} +static inline void dax_remove_host(struct gendisk *disk) +{ +} +static inline struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev, + u64 *start_off, void *holder, + const struct dax_holder_operations *ops) +{ + return NULL; +} +static inline void fs_put_dax(struct dax_device *dax_dev, void *holder) { - put_dax(dax_dev); } +#endif /* CONFIG_BLOCK && CONFIG_FS_DAX */ -struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev); +#if IS_ENABLED(CONFIG_FS_DAX) int dax_writeback_mapping_range(struct address_space *mapping, struct dax_device *dax_dev, struct writeback_control *wbc); @@ -127,25 +161,11 @@ struct page *dax_layout_busy_page(struct address_space *mapping); struct page *dax_layout_busy_page_range(struct address_space *mapping, loff_t start, loff_t end); dax_entry_t dax_lock_page(struct page *page); void dax_unlock_page(struct page *page, dax_entry_t cookie); +dax_entry_t dax_lock_mapping_entry(struct address_space *mapping, + unsigned long index, struct page **page); +void dax_unlock_mapping_entry(struct address_space *mapping, + unsigned long index, dax_entry_t cookie); #else -#define generic_fsdax_supported NULL - -static inline bool dax_supported(struct dax_device *dax_dev, - struct block_device *bdev, int blocksize, sector_t start, - sector_t len) -{ - return false; -} - -static inline void fs_put_dax(struct dax_device *dax_dev) -{ -} - -static inline struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev) -{ - return NULL; -} - static inline struct page *dax_layout_busy_page(struct address_space *mapping) { return NULL; @@ -172,8 +192,24 @@ static inline dax_entry_t dax_lock_page(struct page *page) static inline void dax_unlock_page(struct page *page, dax_entry_t cookie) { } + +static inline dax_entry_t dax_lock_mapping_entry(struct address_space *mapping, + unsigned long index, struct page **page) +{ + return 0; +} + +static inline void dax_unlock_mapping_entry(struct address_space *mapping, + unsigned long index, dax_entry_t cookie) +{ +} #endif +int dax_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero, + const struct iomap_ops *ops); +int dax_truncate_page(struct inode *inode, loff_t pos, bool *did_zero, + const struct iomap_ops *ops); + #if IS_ENABLED(CONFIG_DAX) int dax_read_lock(void); void dax_read_unlock(int id); @@ -190,13 +226,15 @@ static inline void dax_read_unlock(int id) bool dax_alive(struct dax_device *dax_dev); void *dax_get_private(struct dax_device *dax_dev); long dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages, - void **kaddr, pfn_t *pfn); + enum dax_access_mode mode, void **kaddr, pfn_t *pfn); size_t dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i); size_t dax_copy_to_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i); int dax_zero_page_range(struct dax_device *dax_dev, pgoff_t pgoff, size_t nr_pages); +int dax_holder_notify_failure(struct dax_device *dax_dev, u64 off, u64 len, + int mf_flags); void dax_flush(struct dax_device *dax_dev, void *addr, size_t size); ssize_t dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter, @@ -208,7 +246,14 @@ vm_fault_t dax_finish_sync_fault(struct vm_fault *vmf, int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index); int dax_invalidate_mapping_entry_sync(struct address_space *mapping, pgoff_t index); -s64 dax_iomap_zero(loff_t pos, u64 length, struct iomap *iomap); +int dax_dedupe_file_range_compare(struct inode *src, loff_t srcoff, + struct inode *dest, loff_t destoff, + loff_t len, bool *is_same, + const struct iomap_ops *ops); +int dax_remap_file_range_prep(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + loff_t *len, unsigned int remap_flags, + const struct iomap_ops *ops); static inline bool dax_mapping(struct address_space *mapping) { return mapping->host && IS_DAX(mapping->host); diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 9e23d33bb6f1..6b351e009f59 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -16,6 +16,7 @@ #include <linux/wait.h> struct path; +struct file; struct vfsmount; /* @@ -61,16 +62,6 @@ extern const struct qstr empty_name; extern const struct qstr slash_name; extern const struct qstr dotdot_name; -struct dentry_stat_t { - long nr_dentry; - long nr_unused; - long age_limit; /* age in seconds */ - long want_pages; /* pages requested by system */ - long nr_negative; /* # of unused negative dentries */ - long dummy; /* Reserved for future use */ -}; -extern struct dentry_stat_t dentry_stat; - /* * Try to keep struct dentry aligned on 64 byte cachelines (this will * give reasonable cacheline footprint with larger lines without the @@ -243,6 +234,8 @@ extern struct dentry * d_alloc_parallel(struct dentry *, const struct qstr *, wait_queue_head_t *); extern struct dentry * d_splice_alias(struct inode *, struct dentry *); extern struct dentry * d_add_ci(struct dentry *, struct inode *, struct qstr *); +extern bool d_same_name(const struct dentry *dentry, const struct dentry *parent, + const struct qstr *name); extern struct dentry * d_exact_alias(struct dentry *, struct inode *); extern struct dentry *d_find_any_alias(struct inode *inode); extern struct dentry * d_obtain_alias(struct inode *); @@ -258,7 +251,7 @@ extern struct dentry * d_make_root(struct inode *); /* <clickety>-<click> the ramfs-type tree */ extern void d_genocide(struct dentry *); -extern void d_tmpfile(struct dentry *, struct inode *); +extern void d_tmpfile(struct file *, struct inode *); extern struct dentry *d_find_alias(struct inode *); extern void d_prune_aliases(struct inode *); @@ -295,8 +288,8 @@ static inline unsigned d_count(const struct dentry *dentry) /* * helper function for dentry_operations.d_dname() members */ -extern __printf(4, 5) -char *dynamic_dname(struct dentry *, char *, int, const char *, ...); +extern __printf(3, 4) +char *dynamic_dname(char *, int, const char *, ...); extern char *__d_path(const struct path *, const struct path *, char *, int); extern char *d_absolute_path(const struct path *, char *, int); @@ -359,7 +352,7 @@ static inline void dont_mount(struct dentry *dentry) spin_unlock(&dentry->d_lock); } -extern void __d_lookup_done(struct dentry *); +extern void __d_lookup_unhash_wake(struct dentry *dentry); static inline int d_in_lookup(const struct dentry *dentry) { @@ -368,11 +361,8 @@ static inline int d_in_lookup(const struct dentry *dentry) static inline void d_lookup_done(struct dentry *dentry) { - if (unlikely(d_in_lookup(dentry))) { - spin_lock(&dentry->d_lock); - __d_lookup_done(dentry); - spin_unlock(&dentry->d_lock); - } + if (unlikely(d_in_lookup(dentry))) + __d_lookup_unhash_wake(dentry); } extern void dput(struct dentry *); diff --git a/include/linux/debugfs.h b/include/linux/debugfs.h index c869f1e73d75..f60674692d36 100644 --- a/include/linux/debugfs.h +++ b/include/linux/debugfs.h @@ -91,6 +91,8 @@ struct dentry *debugfs_create_automount(const char *name, void debugfs_remove(struct dentry *dentry); #define debugfs_remove_recursive debugfs_remove +void debugfs_lookup_and_remove(const char *name, struct dentry *parent); + const struct file_operations *debugfs_real_fops(const struct file *filp); int debugfs_file_get(struct dentry *dentry); @@ -225,6 +227,10 @@ static inline void debugfs_remove(struct dentry *dentry) static inline void debugfs_remove_recursive(struct dentry *dentry) { } +static inline void debugfs_lookup_and_remove(const char *name, + struct dentry *parent) +{ } + const struct file_operations *debugfs_real_fops(const struct file *filp); static inline int debugfs_file_get(struct dentry *dentry) diff --git a/include/linux/delayacct.h b/include/linux/delayacct.h index af7e6eb50283..0da97dba9ef8 100644 --- a/include/linux/delayacct.h +++ b/include/linux/delayacct.h @@ -9,18 +9,9 @@ #include <uapi/linux/taskstats.h> -/* - * Per-task flags relevant to delay accounting - * maintained privately to avoid exhausting similar flags in sched.h:PF_* - * Used to set current->delays->flags - */ -#define DELAYACCT_PF_SWAPIN 0x00000001 /* I am doing a swapin */ -#define DELAYACCT_PF_BLKIO 0x00000002 /* I am waiting on IO */ - #ifdef CONFIG_TASK_DELAY_ACCT struct task_delay_info { raw_spinlock_t lock; - unsigned int flags; /* Private per-task flags */ /* For each stat XXX, add following, aligned appropriately * @@ -37,13 +28,13 @@ struct task_delay_info { * associated with the operation is added to XXX_delay. * XXX_delay contains the accumulated delay time in nanoseconds. */ - u64 blkio_start; /* Shared by blkio, swapin */ + u64 blkio_start; u64 blkio_delay; /* wait for sync block io completion */ - u64 swapin_delay; /* wait for swapin block io completion */ + u64 swapin_start; + u64 swapin_delay; /* wait for swapin */ u32 blkio_count; /* total count of the number of sync block */ /* io operations performed */ - u32 swapin_count; /* total count of the number of swapin block */ - /* io operations performed */ + u32 swapin_count; /* total count of swapin */ u64 freepages_start; u64 freepages_delay; /* wait for memory reclaim */ @@ -51,8 +42,16 @@ struct task_delay_info { u64 thrashing_start; u64 thrashing_delay; /* wait for thrashing page */ + u64 compact_start; + u64 compact_delay; /* wait for memory compact */ + + u64 wpcopy_start; + u64 wpcopy_delay; /* wait for write-protect copy */ + u32 freepages_count; /* total count of memory reclaim */ u32 thrashing_count; /* total count of thrash waits */ + u32 compact_count; /* total count of memory compact */ + u32 wpcopy_count; /* total count of write-protect copy */ }; #endif @@ -66,9 +65,6 @@ extern int delayacct_on; /* Delay accounting turned on/off */ extern struct kmem_cache *delayacct_cache; extern void delayacct_init(void); -extern int sysctl_delayacct(struct ctl_table *table, int write, void *buffer, - size_t *lenp, loff_t *ppos); - extern void __delayacct_tsk_init(struct task_struct *); extern void __delayacct_tsk_exit(struct task_struct *); extern void __delayacct_blkio_start(void); @@ -77,28 +73,14 @@ extern int delayacct_add_tsk(struct taskstats *, struct task_struct *); extern __u64 __delayacct_blkio_ticks(struct task_struct *); extern void __delayacct_freepages_start(void); extern void __delayacct_freepages_end(void); -extern void __delayacct_thrashing_start(void); -extern void __delayacct_thrashing_end(void); - -static inline int delayacct_is_task_waiting_on_io(struct task_struct *p) -{ - if (p->delays) - return (p->delays->flags & DELAYACCT_PF_BLKIO); - else - return 0; -} - -static inline void delayacct_set_flag(struct task_struct *p, int flag) -{ - if (p->delays) - p->delays->flags |= flag; -} - -static inline void delayacct_clear_flag(struct task_struct *p, int flag) -{ - if (p->delays) - p->delays->flags &= ~flag; -} +extern void __delayacct_thrashing_start(bool *in_thrashing); +extern void __delayacct_thrashing_end(bool *in_thrashing); +extern void __delayacct_swapin_start(void); +extern void __delayacct_swapin_end(void); +extern void __delayacct_compact_start(void); +extern void __delayacct_compact_end(void); +extern void __delayacct_wpcopy_start(void); +extern void __delayacct_wpcopy_end(void); static inline void delayacct_tsk_init(struct task_struct *tsk) { @@ -123,7 +105,6 @@ static inline void delayacct_blkio_start(void) if (!static_branch_unlikely(&delayacct_key)) return; - delayacct_set_flag(current, DELAYACCT_PF_BLKIO); if (current->delays) __delayacct_blkio_start(); } @@ -135,7 +116,6 @@ static inline void delayacct_blkio_end(struct task_struct *p) if (p->delays) __delayacct_blkio_end(p); - delayacct_clear_flag(p, DELAYACCT_PF_BLKIO); } static inline __u64 delayacct_blkio_ticks(struct task_struct *tsk) @@ -147,33 +127,95 @@ static inline __u64 delayacct_blkio_ticks(struct task_struct *tsk) static inline void delayacct_freepages_start(void) { + if (!static_branch_unlikely(&delayacct_key)) + return; + if (current->delays) __delayacct_freepages_start(); } static inline void delayacct_freepages_end(void) { + if (!static_branch_unlikely(&delayacct_key)) + return; + if (current->delays) __delayacct_freepages_end(); } -static inline void delayacct_thrashing_start(void) +static inline void delayacct_thrashing_start(bool *in_thrashing) +{ + if (!static_branch_unlikely(&delayacct_key)) + return; + + if (current->delays) + __delayacct_thrashing_start(in_thrashing); +} + +static inline void delayacct_thrashing_end(bool *in_thrashing) { + if (!static_branch_unlikely(&delayacct_key)) + return; + if (current->delays) - __delayacct_thrashing_start(); + __delayacct_thrashing_end(in_thrashing); } -static inline void delayacct_thrashing_end(void) +static inline void delayacct_swapin_start(void) { + if (!static_branch_unlikely(&delayacct_key)) + return; + if (current->delays) - __delayacct_thrashing_end(); + __delayacct_swapin_start(); +} + +static inline void delayacct_swapin_end(void) +{ + if (!static_branch_unlikely(&delayacct_key)) + return; + + if (current->delays) + __delayacct_swapin_end(); +} + +static inline void delayacct_compact_start(void) +{ + if (!static_branch_unlikely(&delayacct_key)) + return; + + if (current->delays) + __delayacct_compact_start(); +} + +static inline void delayacct_compact_end(void) +{ + if (!static_branch_unlikely(&delayacct_key)) + return; + + if (current->delays) + __delayacct_compact_end(); +} + +static inline void delayacct_wpcopy_start(void) +{ + if (!static_branch_unlikely(&delayacct_key)) + return; + + if (current->delays) + __delayacct_wpcopy_start(); +} + +static inline void delayacct_wpcopy_end(void) +{ + if (!static_branch_unlikely(&delayacct_key)) + return; + + if (current->delays) + __delayacct_wpcopy_end(); } #else -static inline void delayacct_set_flag(struct task_struct *p, int flag) -{} -static inline void delayacct_clear_flag(struct task_struct *p, int flag) -{} static inline void delayacct_init(void) {} static inline void delayacct_tsk_init(struct task_struct *tsk) @@ -195,9 +237,21 @@ static inline void delayacct_freepages_start(void) {} static inline void delayacct_freepages_end(void) {} -static inline void delayacct_thrashing_start(void) +static inline void delayacct_thrashing_start(bool *in_thrashing) +{} +static inline void delayacct_thrashing_end(bool *in_thrashing) +{} +static inline void delayacct_swapin_start(void) +{} +static inline void delayacct_swapin_end(void) +{} +static inline void delayacct_compact_start(void) +{} +static inline void delayacct_compact_end(void) +{} +static inline void delayacct_wpcopy_start(void) {} -static inline void delayacct_thrashing_end(void) +static inline void delayacct_wpcopy_end(void) {} #endif /* CONFIG_TASK_DELAY_ACCT */ diff --git a/include/linux/devfreq.h b/include/linux/devfreq.h index 142474b4af96..34aab4dd336c 100644 --- a/include/linux/devfreq.h +++ b/include/linux/devfreq.h @@ -38,6 +38,7 @@ enum devfreq_timer { struct devfreq; struct devfreq_governor; +struct devfreq_cpu_data; struct thermal_cooling_device; /** @@ -147,6 +148,8 @@ struct devfreq_stats { * reevaluate operable frequencies. Devfreq users may use * devfreq.nb to the corresponding register notifier call chain. * @work: delayed work for load monitoring. + * @freq_table: current frequency table used by the devfreq driver. + * @max_state: count of entry present in the frequency table. * @previous_freq: previously configured frequency value. * @last_status: devfreq user device info, performance statistics * @data: Private data of the governor. The devfreq framework does not @@ -184,6 +187,9 @@ struct devfreq { struct notifier_block nb; struct delayed_work work; + unsigned long *freq_table; + unsigned int max_state; + unsigned long previous_freq; struct devfreq_dev_status last_status; @@ -288,6 +294,11 @@ struct devfreq_simple_ondemand_data { #endif #if IS_ENABLED(CONFIG_DEVFREQ_GOV_PASSIVE) +enum devfreq_parent_dev_type { + DEVFREQ_PARENT_DEV, + CPUFREQ_PARENT_DEV, +}; + /** * struct devfreq_passive_data - ``void *data`` fed to struct devfreq * and devfreq_add_device @@ -299,8 +310,11 @@ struct devfreq_simple_ondemand_data { * using governors except for passive governor. * If the devfreq device has the specific method to decide * the next frequency, should use this callback. - * @this: the devfreq instance of own device. - * @nb: the notifier block for DEVFREQ_TRANSITION_NOTIFIER list + * @parent_type: the parent type of the device. + * @this: the devfreq instance of own device. + * @nb: the notifier block for DEVFREQ_TRANSITION_NOTIFIER or + * CPUFREQ_TRANSITION_NOTIFIER list. + * @cpu_data_list: the list of cpu frequency data for all cpufreq_policy. * * The devfreq_passive_data have to set the devfreq instance of parent * device with governors except for the passive governor. But, don't need to @@ -314,9 +328,13 @@ struct devfreq_passive_data { /* Optional callback to decide the next frequency of passvice device */ int (*get_target_freq)(struct devfreq *this, unsigned long *freq); + /* Should set the type of parent device */ + enum devfreq_parent_dev_type parent_type; + /* For passive governor's internal use. Don't need to set them */ struct devfreq *this; struct notifier_block nb; + struct list_head cpu_data_list; }; #endif diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index a7df155ea49b..04c6acf7faaa 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -20,6 +20,7 @@ struct dm_table; struct dm_report_zones_args; struct mapped_device; struct bio_vec; +enum dax_access_mode; /* * Type of table, mapped_device's mempool and request_queue @@ -146,12 +147,19 @@ typedef int (*dm_busy_fn) (struct dm_target *ti); * >= 0 : the number of bytes accessible at the address */ typedef long (*dm_dax_direct_access_fn) (struct dm_target *ti, pgoff_t pgoff, - long nr_pages, void **kaddr, pfn_t *pfn); -typedef size_t (*dm_dax_copy_iter_fn)(struct dm_target *ti, pgoff_t pgoff, - void *addr, size_t bytes, struct iov_iter *i); + long nr_pages, enum dax_access_mode node, void **kaddr, + pfn_t *pfn); typedef int (*dm_dax_zero_page_range_fn)(struct dm_target *ti, pgoff_t pgoff, size_t nr_pages); +/* + * Returns: + * != 0 : number of bytes transferred + * 0 : recovery write failed + */ +typedef size_t (*dm_dax_recovery_write_fn)(struct dm_target *ti, pgoff_t pgoff, + void *addr, size_t bytes, struct iov_iter *i); + void dm_error(const char *message); struct dm_dev { @@ -200,9 +208,8 @@ struct target_type { dm_iterate_devices_fn iterate_devices; dm_io_hints_fn io_hints; dm_dax_direct_access_fn direct_access; - dm_dax_copy_iter_fn dax_copy_from_iter; - dm_dax_copy_iter_fn dax_copy_to_iter; dm_dax_zero_page_range_fn dax_zero_page_range; + dm_dax_recovery_write_fn dax_recovery_write; /* For internal device-mapper use. */ struct list_head list; @@ -321,12 +328,6 @@ struct dm_target { unsigned num_secure_erase_bios; /* - * The number of WRITE SAME bios that will be submitted to the target. - * The bio number can be accessed with dm_bio_get_target_bio_nr. - */ - unsigned num_write_same_bios; - - /* * The number of WRITE ZEROES bios that will be submitted to the target. * The bio number can be accessed with dm_bio_get_target_bio_nr. */ @@ -362,10 +363,22 @@ struct dm_target { bool limit_swap_bios:1; /* - * Set if this target implements a a zoned device and needs emulation of + * Set if this target implements a zoned device and needs emulation of * zone append operations using regular writes. */ bool emulate_zone_append:1; + + /* + * Set if the target will submit IO using dm_submit_bio_remap() + * after returning DM_MAPIO_SUBMITTED from its map function. + */ + bool accounts_remapped_io:1; + + /* + * Set if the target will submit the DM bio without first calling + * bio_set_dev(). NOTE: ideally a target should _not_ need this. + */ + bool needs_bio_set_dev:1; }; void *dm_per_bio_data(struct bio *bio, size_t data_size); @@ -469,6 +482,7 @@ int dm_suspended(struct dm_target *ti); int dm_post_suspending(struct dm_target *ti); int dm_noflush_suspending(struct dm_target *ti); void dm_accept_partial_bio(struct bio *bio, unsigned n_sectors); +void dm_submit_bio_remap(struct bio *clone, struct bio *tgt_clone); union map_info *dm_get_rq_mapinfo(struct request *rq); #ifdef CONFIG_BLK_DEV_ZONED @@ -553,7 +567,6 @@ void dm_sync_table(struct mapped_device *md); * Queries */ sector_t dm_table_get_size(struct dm_table *t); -unsigned int dm_table_get_num_targets(struct dm_table *t); fmode_t dm_table_get_mode(struct dm_table *t); struct mapped_device *dm_table_get_md(struct dm_table *t); const char *dm_table_device_name(struct dm_table *t); diff --git a/include/linux/device.h b/include/linux/device.h index e270cb740b9e..424b55df0272 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -45,6 +45,7 @@ struct iommu_ops; struct iommu_group; struct dev_pin_info; struct dev_iommu; +struct msi_device_data; /** * struct subsys_interface - interfaces to device functions @@ -372,6 +373,89 @@ struct dev_links_info { }; /** + * struct dev_msi_info - Device data related to MSI + * @domain: The MSI interrupt domain associated to the device + * @data: Pointer to MSI device data + */ +struct dev_msi_info { +#ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN + struct irq_domain *domain; +#endif +#ifdef CONFIG_GENERIC_MSI_IRQ + struct msi_device_data *data; +#endif +}; + +/** + * enum device_physical_location_panel - Describes which panel surface of the + * system's housing the device connection point resides on. + * @DEVICE_PANEL_TOP: Device connection point is on the top panel. + * @DEVICE_PANEL_BOTTOM: Device connection point is on the bottom panel. + * @DEVICE_PANEL_LEFT: Device connection point is on the left panel. + * @DEVICE_PANEL_RIGHT: Device connection point is on the right panel. + * @DEVICE_PANEL_FRONT: Device connection point is on the front panel. + * @DEVICE_PANEL_BACK: Device connection point is on the back panel. + * @DEVICE_PANEL_UNKNOWN: The panel with device connection point is unknown. + */ +enum device_physical_location_panel { + DEVICE_PANEL_TOP, + DEVICE_PANEL_BOTTOM, + DEVICE_PANEL_LEFT, + DEVICE_PANEL_RIGHT, + DEVICE_PANEL_FRONT, + DEVICE_PANEL_BACK, + DEVICE_PANEL_UNKNOWN, +}; + +/** + * enum device_physical_location_vertical_position - Describes vertical + * position of the device connection point on the panel surface. + * @DEVICE_VERT_POS_UPPER: Device connection point is at upper part of panel. + * @DEVICE_VERT_POS_CENTER: Device connection point is at center part of panel. + * @DEVICE_VERT_POS_LOWER: Device connection point is at lower part of panel. + */ +enum device_physical_location_vertical_position { + DEVICE_VERT_POS_UPPER, + DEVICE_VERT_POS_CENTER, + DEVICE_VERT_POS_LOWER, +}; + +/** + * enum device_physical_location_horizontal_position - Describes horizontal + * position of the device connection point on the panel surface. + * @DEVICE_HORI_POS_LEFT: Device connection point is at left part of panel. + * @DEVICE_HORI_POS_CENTER: Device connection point is at center part of panel. + * @DEVICE_HORI_POS_RIGHT: Device connection point is at right part of panel. + */ +enum device_physical_location_horizontal_position { + DEVICE_HORI_POS_LEFT, + DEVICE_HORI_POS_CENTER, + DEVICE_HORI_POS_RIGHT, +}; + +/** + * struct device_physical_location - Device data related to physical location + * of the device connection point. + * @panel: Panel surface of the system's housing that the device connection + * point resides on. + * @vertical_position: Vertical position of the device connection point within + * the panel. + * @horizontal_position: Horizontal position of the device connection point + * within the panel. + * @dock: Set if the device connection point resides in a docking station or + * port replicator. + * @lid: Set if this device connection point resides on the lid of laptop + * system. + */ +struct device_physical_location { + enum device_physical_location_panel panel; + enum device_physical_location_vertical_position vertical_position; + enum device_physical_location_horizontal_position horizontal_position; + bool dock; + bool lid; +}; + +/** * struct device - The basic device structure * @parent: The device's "parent" device, the device to which it is attached. * In most cases, a parent device is some sort of bus or host @@ -385,8 +469,6 @@ struct dev_links_info { * This identifies the device type and carries type-specific * information. * @mutex: Mutex to synchronize calls to its driver. - * @lockdep_mutex: An optional debug lock that a subsystem can use as a - * peer lock to gain localized lockdep coverage of the device_lock. * @bus: Type of bus device is on. * @driver: Which driver has allocated this * @platform_data: Platform data specific to the device. @@ -407,9 +489,7 @@ struct dev_links_info { * @em_pd: device's energy model performance domain * @pins: For device pin management. * See Documentation/driver-api/pin-control.rst for details. - * @msi_lock: Lock to protect MSI mask cache and mask register - * @msi_list: Hosts MSI descriptors - * @msi_domain: The generic MSI domain this device is using. + * @msi: MSI related data * @numa_node: NUMA node this device is close to. * @dma_ops: DMA mapping operations for this device. * @dma_mask: Dma mask (if dma'ble device). @@ -440,6 +520,8 @@ struct dev_links_info { * device (i.e. the bus driver that discovered the device). * @iommu_group: IOMMU group the device belongs to. * @iommu: Per device generic IOMMU runtime data + * @physical_location: Describes physical location of the device connection + * point in the system housing. * @removable: Whether the device can be removed from the system. This * should be set by the subsystem / bus driver that discovered * the device. @@ -486,9 +568,6 @@ struct device { core doesn't touch it */ void *driver_data; /* Driver data, set and get with dev_set_drvdata/dev_get_drvdata */ -#ifdef CONFIG_PROVE_LOCKING - struct mutex lockdep_mutex; -#endif struct mutex mutex; /* mutex to synchronize calls to * its driver. */ @@ -501,16 +580,10 @@ struct device { struct em_perf_domain *em_pd; #endif -#ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN - struct irq_domain *msi_domain; -#endif #ifdef CONFIG_PINCTRL struct dev_pin_info *pins; #endif -#ifdef CONFIG_GENERIC_MSI_IRQ - raw_spinlock_t msi_lock; - struct list_head msi_list; -#endif + struct dev_msi_info msi; #ifdef CONFIG_DMA_OPS const struct dma_map_ops *dma_ops; #endif @@ -560,6 +633,8 @@ struct device { struct iommu_group *iommu_group; struct dev_iommu *iommu; + struct device_physical_location *physical_location; + enum device_removable removable; bool offline_disabled:1; @@ -668,7 +743,7 @@ static inline void set_dev_node(struct device *dev, int node) static inline struct irq_domain *dev_get_msi_domain(const struct device *dev) { #ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN - return dev->msi_domain; + return dev->msi.domain; #else return NULL; #endif @@ -677,7 +752,7 @@ static inline struct irq_domain *dev_get_msi_domain(const struct device *dev) static inline void dev_set_msi_domain(struct device *dev, struct irq_domain *d) { #ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN - dev->msi_domain = d; + dev->msi.domain = d; #endif } @@ -830,6 +905,8 @@ struct device *device_find_child(struct device *dev, void *data, int (*match)(struct device *dev, void *data)); struct device *device_find_child_by_name(struct device *parent, const char *name); +struct device *device_find_any_child(struct device *parent); + int device_rename(struct device *dev, const char *new_name); int device_move(struct device *dev, struct device *new_parent, enum dpm_order dpm_order); @@ -843,6 +920,49 @@ static inline bool device_supports_offline(struct device *dev) return dev->bus && dev->bus->offline && dev->bus->online; } +#define __device_lock_set_class(dev, name, key) \ +do { \ + struct device *__d2 __maybe_unused = dev; \ + lock_set_class(&__d2->mutex.dep_map, name, key, 0, _THIS_IP_); \ +} while (0) + +/** + * device_lock_set_class - Specify a temporary lock class while a device + * is attached to a driver + * @dev: device to modify + * @key: lock class key data + * + * This must be called with the device_lock() already held, for example + * from driver ->probe(). Take care to only override the default + * lockdep_no_validate class. + */ +#ifdef CONFIG_LOCKDEP +#define device_lock_set_class(dev, key) \ +do { \ + struct device *__d = dev; \ + dev_WARN_ONCE(__d, !lockdep_match_class(&__d->mutex, \ + &__lockdep_no_validate__), \ + "overriding existing custom lock class\n"); \ + __device_lock_set_class(__d, #key, key); \ +} while (0) +#else +#define device_lock_set_class(dev, key) __device_lock_set_class(dev, #key, key) +#endif + +/** + * device_lock_reset_class - Return a device to the default lockdep novalidate state + * @dev: device to modify + * + * This must be called with the device_lock() already held, for example + * from driver ->remove(). + */ +#define device_lock_reset_class(dev) \ +do { \ + struct device *__d __maybe_unused = dev; \ + lock_set_novalidate_class(&__d->mutex.dep_map, "&dev->mutex", \ + _THIS_IP_); \ +} while (0) + void lock_device_hotplug(void); void unlock_device_hotplug(void); int lock_device_hotplug_sysfs(void); diff --git a/include/linux/device/bus.h b/include/linux/device/bus.h index a039ab809753..d8b29ccd07e5 100644 --- a/include/linux/device/bus.h +++ b/include/linux/device/bus.h @@ -59,6 +59,8 @@ struct fwnode_handle; * bus supports. * @dma_configure: Called to setup DMA configuration on a device on * this bus. + * @dma_cleanup: Called to cleanup DMA configuration on a device on + * this bus. * @pm: Power management operations of this bus, callback the specific * device driver's pm-ops. * @iommu_ops: IOMMU specific operations for this bus, used to attach IOMMU @@ -103,6 +105,7 @@ struct bus_type { int (*num_vf)(struct device *dev); int (*dma_configure)(struct device *dev); + void (*dma_cleanup)(struct device *dev); const struct dev_pm_ops *pm; diff --git a/include/linux/device/driver.h b/include/linux/device/driver.h index 15e7c5e15d62..2114d65b862f 100644 --- a/include/linux/device/driver.h +++ b/include/linux/device/driver.h @@ -129,6 +129,7 @@ extern struct device_driver *driver_find(const char *name, struct bus_type *bus); extern int driver_probe_done(void); extern void wait_for_device_probe(void); +void __init wait_for_init_devices_probe(void); /* sysfs interface for exporting driver attributes */ @@ -151,6 +152,8 @@ extern int __must_check driver_create_file(struct device_driver *driver, extern void driver_remove_file(struct device_driver *driver, const struct driver_attribute *attr); +int driver_set_override(struct device *dev, const char **override, + const char *s, size_t len); extern int __must_check driver_for_each_device(struct device_driver *drv, struct device *start, void *data, diff --git a/include/linux/dim.h b/include/linux/dim.h index b698266d0035..6c5733981563 100644 --- a/include/linux/dim.h +++ b/include/linux/dim.h @@ -21,7 +21,7 @@ * We consider 10% difference as significant. */ #define IS_SIGNIFICANT_DIFF(val, ref) \ - (((100UL * abs((val) - (ref))) / (ref)) > 10) + ((ref) && (((100UL * abs((val) - (ref))) / (ref)) > 10)) /* * Calculate the gap between two values. diff --git a/include/linux/dlm.h b/include/linux/dlm.h index ff951e9f6f20..c6bc2b5ee7e6 100644 --- a/include/linux/dlm.h +++ b/include/linux/dlm.h @@ -56,9 +56,6 @@ struct dlm_lockspace_ops { * DLM_LSFL_TIMEWARN * The dlm should emit netlink messages if locks have been waiting * for a configurable amount of time. (Unused.) - * DLM_LSFL_FS - * The lockspace user is in the kernel (i.e. filesystem). Enables - * direct bast/cast callbacks. * DLM_LSFL_NEWEXCL * dlm_new_lockspace() should return -EEXIST if the lockspace exists. * @@ -134,7 +131,7 @@ int dlm_lock(dlm_lockspace_t *lockspace, int mode, struct dlm_lksb *lksb, uint32_t flags, - void *name, + const void *name, unsigned int namelen, uint32_t parent_lkid, void (*lockast) (void *astarg), diff --git a/include/linux/dm-bufio.h b/include/linux/dm-bufio.h index 90bd558a17f5..15d9e15ca830 100644 --- a/include/linux/dm-bufio.h +++ b/include/linux/dm-bufio.h @@ -18,13 +18,19 @@ struct dm_bufio_client; struct dm_buffer; /* + * Flags for dm_bufio_client_create + */ +#define DM_BUFIO_CLIENT_NO_SLEEP 0x1 + +/* * Create a buffered IO cache on a given device */ struct dm_bufio_client * dm_bufio_client_create(struct block_device *bdev, unsigned block_size, unsigned reserved_buffers, unsigned aux_size, void (*alloc_callback)(struct dm_buffer *), - void (*write_callback)(struct dm_buffer *)); + void (*write_callback)(struct dm_buffer *), + unsigned int flags); /* * Release a buffered IO cache. diff --git a/include/linux/dm-io.h b/include/linux/dm-io.h index a52c6580cc9a..8e1c4ab5df04 100644 --- a/include/linux/dm-io.h +++ b/include/linux/dm-io.h @@ -13,6 +13,7 @@ #ifdef __KERNEL__ #include <linux/types.h> +#include <linux/blk_types.h> struct dm_io_region { struct block_device *bdev; @@ -57,8 +58,7 @@ struct dm_io_notify { */ struct dm_io_client; struct dm_io_request { - int bi_op; /* REQ_OP */ - int bi_op_flags; /* req_flag_bits */ + blk_opf_t bi_opf; /* Request type and flags */ struct dm_io_memory mem; /* Memory to use for io */ struct dm_io_notify notify; /* Synchronous if notify.fn is NULL */ struct dm_io_client *client; /* Client memory handler */ diff --git a/include/linux/dm-verity-loadpin.h b/include/linux/dm-verity-loadpin.h new file mode 100644 index 000000000000..552b817ab102 --- /dev/null +++ b/include/linux/dm-verity-loadpin.h @@ -0,0 +1,27 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __LINUX_DM_VERITY_LOADPIN_H +#define __LINUX_DM_VERITY_LOADPIN_H + +#include <linux/list.h> + +struct block_device; + +extern struct list_head dm_verity_loadpin_trusted_root_digests; + +struct dm_verity_loadpin_trusted_root_digest { + struct list_head node; + unsigned int len; + u8 data[]; +}; + +#if IS_ENABLED(CONFIG_SECURITY_LOADPIN_VERITY) +bool dm_verity_loadpin_is_bdev_trusted(struct block_device *bdev); +#else +static inline bool dm_verity_loadpin_is_bdev_trusted(struct block_device *bdev) +{ + return false; +} +#endif + +#endif /* __LINUX_DM_VERITY_LOADPIN_H */ diff --git a/include/linux/dma-buf-map.h b/include/linux/dma-buf-map.h deleted file mode 100644 index 278d489e4bdd..000000000000 --- a/include/linux/dma-buf-map.h +++ /dev/null @@ -1,266 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Pointer to dma-buf-mapped memory, plus helpers. - */ - -#ifndef __DMA_BUF_MAP_H__ -#define __DMA_BUF_MAP_H__ - -#include <linux/io.h> -#include <linux/string.h> - -/** - * DOC: overview - * - * Calling dma-buf's vmap operation returns a pointer to the buffer's memory. - * Depending on the location of the buffer, users may have to access it with - * I/O operations or memory load/store operations. For example, copying to - * system memory could be done with memcpy(), copying to I/O memory would be - * done with memcpy_toio(). - * - * .. code-block:: c - * - * void *vaddr = ...; // pointer to system memory - * memcpy(vaddr, src, len); - * - * void *vaddr_iomem = ...; // pointer to I/O memory - * memcpy_toio(vaddr, _iomem, src, len); - * - * When using dma-buf's vmap operation, the returned pointer is encoded as - * :c:type:`struct dma_buf_map <dma_buf_map>`. - * :c:type:`struct dma_buf_map <dma_buf_map>` stores the buffer's address in - * system or I/O memory and a flag that signals the required method of - * accessing the buffer. Use the returned instance and the helper functions - * to access the buffer's memory in the correct way. - * - * The type :c:type:`struct dma_buf_map <dma_buf_map>` and its helpers are - * actually independent from the dma-buf infrastructure. When sharing buffers - * among devices, drivers have to know the location of the memory to access - * the buffers in a safe way. :c:type:`struct dma_buf_map <dma_buf_map>` - * solves this problem for dma-buf and its users. If other drivers or - * sub-systems require similar functionality, the type could be generalized - * and moved to a more prominent header file. - * - * Open-coding access to :c:type:`struct dma_buf_map <dma_buf_map>` is - * considered bad style. Rather then accessing its fields directly, use one - * of the provided helper functions, or implement your own. For example, - * instances of :c:type:`struct dma_buf_map <dma_buf_map>` can be initialized - * statically with DMA_BUF_MAP_INIT_VADDR(), or at runtime with - * dma_buf_map_set_vaddr(). These helpers will set an address in system memory. - * - * .. code-block:: c - * - * struct dma_buf_map map = DMA_BUF_MAP_INIT_VADDR(0xdeadbeaf); - * - * dma_buf_map_set_vaddr(&map. 0xdeadbeaf); - * - * To set an address in I/O memory, use dma_buf_map_set_vaddr_iomem(). - * - * .. code-block:: c - * - * dma_buf_map_set_vaddr_iomem(&map. 0xdeadbeaf); - * - * Instances of struct dma_buf_map do not have to be cleaned up, but - * can be cleared to NULL with dma_buf_map_clear(). Cleared mappings - * always refer to system memory. - * - * .. code-block:: c - * - * dma_buf_map_clear(&map); - * - * Test if a mapping is valid with either dma_buf_map_is_set() or - * dma_buf_map_is_null(). - * - * .. code-block:: c - * - * if (dma_buf_map_is_set(&map) != dma_buf_map_is_null(&map)) - * // always true - * - * Instances of :c:type:`struct dma_buf_map <dma_buf_map>` can be compared - * for equality with dma_buf_map_is_equal(). Mappings the point to different - * memory spaces, system or I/O, are never equal. That's even true if both - * spaces are located in the same address space, both mappings contain the - * same address value, or both mappings refer to NULL. - * - * .. code-block:: c - * - * struct dma_buf_map sys_map; // refers to system memory - * struct dma_buf_map io_map; // refers to I/O memory - * - * if (dma_buf_map_is_equal(&sys_map, &io_map)) - * // always false - * - * A set up instance of struct dma_buf_map can be used to access or manipulate - * the buffer memory. Depending on the location of the memory, the provided - * helpers will pick the correct operations. Data can be copied into the memory - * with dma_buf_map_memcpy_to(). The address can be manipulated with - * dma_buf_map_incr(). - * - * .. code-block:: c - * - * const void *src = ...; // source buffer - * size_t len = ...; // length of src - * - * dma_buf_map_memcpy_to(&map, src, len); - * dma_buf_map_incr(&map, len); // go to first byte after the memcpy - */ - -/** - * struct dma_buf_map - Pointer to vmap'ed dma-buf memory. - * @vaddr_iomem: The buffer's address if in I/O memory - * @vaddr: The buffer's address if in system memory - * @is_iomem: True if the dma-buf memory is located in I/O - * memory, or false otherwise. - */ -struct dma_buf_map { - union { - void __iomem *vaddr_iomem; - void *vaddr; - }; - bool is_iomem; -}; - -/** - * DMA_BUF_MAP_INIT_VADDR - Initializes struct dma_buf_map to an address in system memory - * @vaddr_: A system-memory address - */ -#define DMA_BUF_MAP_INIT_VADDR(vaddr_) \ - { \ - .vaddr = (vaddr_), \ - .is_iomem = false, \ - } - -/** - * dma_buf_map_set_vaddr - Sets a dma-buf mapping structure to an address in system memory - * @map: The dma-buf mapping structure - * @vaddr: A system-memory address - * - * Sets the address and clears the I/O-memory flag. - */ -static inline void dma_buf_map_set_vaddr(struct dma_buf_map *map, void *vaddr) -{ - map->vaddr = vaddr; - map->is_iomem = false; -} - -/** - * dma_buf_map_set_vaddr_iomem - Sets a dma-buf mapping structure to an address in I/O memory - * @map: The dma-buf mapping structure - * @vaddr_iomem: An I/O-memory address - * - * Sets the address and the I/O-memory flag. - */ -static inline void dma_buf_map_set_vaddr_iomem(struct dma_buf_map *map, - void __iomem *vaddr_iomem) -{ - map->vaddr_iomem = vaddr_iomem; - map->is_iomem = true; -} - -/** - * dma_buf_map_is_equal - Compares two dma-buf mapping structures for equality - * @lhs: The dma-buf mapping structure - * @rhs: A dma-buf mapping structure to compare with - * - * Two dma-buf mapping structures are equal if they both refer to the same type of memory - * and to the same address within that memory. - * - * Returns: - * True is both structures are equal, or false otherwise. - */ -static inline bool dma_buf_map_is_equal(const struct dma_buf_map *lhs, - const struct dma_buf_map *rhs) -{ - if (lhs->is_iomem != rhs->is_iomem) - return false; - else if (lhs->is_iomem) - return lhs->vaddr_iomem == rhs->vaddr_iomem; - else - return lhs->vaddr == rhs->vaddr; -} - -/** - * dma_buf_map_is_null - Tests for a dma-buf mapping to be NULL - * @map: The dma-buf mapping structure - * - * Depending on the state of struct dma_buf_map.is_iomem, tests if the - * mapping is NULL. - * - * Returns: - * True if the mapping is NULL, or false otherwise. - */ -static inline bool dma_buf_map_is_null(const struct dma_buf_map *map) -{ - if (map->is_iomem) - return !map->vaddr_iomem; - return !map->vaddr; -} - -/** - * dma_buf_map_is_set - Tests is the dma-buf mapping has been set - * @map: The dma-buf mapping structure - * - * Depending on the state of struct dma_buf_map.is_iomem, tests if the - * mapping has been set. - * - * Returns: - * True if the mapping is been set, or false otherwise. - */ -static inline bool dma_buf_map_is_set(const struct dma_buf_map *map) -{ - return !dma_buf_map_is_null(map); -} - -/** - * dma_buf_map_clear - Clears a dma-buf mapping structure - * @map: The dma-buf mapping structure - * - * Clears all fields to zero; including struct dma_buf_map.is_iomem. So - * mapping structures that were set to point to I/O memory are reset for - * system memory. Pointers are cleared to NULL. This is the default. - */ -static inline void dma_buf_map_clear(struct dma_buf_map *map) -{ - if (map->is_iomem) { - map->vaddr_iomem = NULL; - map->is_iomem = false; - } else { - map->vaddr = NULL; - } -} - -/** - * dma_buf_map_memcpy_to - Memcpy into dma-buf mapping - * @dst: The dma-buf mapping structure - * @src: The source buffer - * @len: The number of byte in src - * - * Copies data into a dma-buf mapping. The source buffer is in system - * memory. Depending on the buffer's location, the helper picks the correct - * method of accessing the memory. - */ -static inline void dma_buf_map_memcpy_to(struct dma_buf_map *dst, const void *src, size_t len) -{ - if (dst->is_iomem) - memcpy_toio(dst->vaddr_iomem, src, len); - else - memcpy(dst->vaddr, src, len); -} - -/** - * dma_buf_map_incr - Increments the address stored in a dma-buf mapping - * @map: The dma-buf mapping structure - * @incr: The number of bytes to increment - * - * Increments the address stored in a dma-buf mapping. Depending on the - * buffer's location, the correct value will be updated. - */ -static inline void dma_buf_map_incr(struct dma_buf_map *map, size_t incr) -{ - if (map->is_iomem) - map->vaddr_iomem += incr; - else - map->vaddr += incr; -} - -#endif /* __DMA_BUF_MAP_H__ */ diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index 7ab50076e7a6..71731796c8c3 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -13,7 +13,7 @@ #ifndef __DMA_BUF_H__ #define __DMA_BUF_H__ -#include <linux/dma-buf-map.h> +#include <linux/iosys-map.h> #include <linux/file.h> #include <linux/err.h> #include <linux/scatterlist.h> @@ -283,8 +283,8 @@ struct dma_buf_ops { */ int (*mmap)(struct dma_buf *, struct vm_area_struct *vma); - int (*vmap)(struct dma_buf *dmabuf, struct dma_buf_map *map); - void (*vunmap)(struct dma_buf *dmabuf, struct dma_buf_map *map); + int (*vmap)(struct dma_buf *dmabuf, struct iosys_map *map); + void (*vunmap)(struct dma_buf *dmabuf, struct iosys_map *map); }; /** @@ -347,7 +347,7 @@ struct dma_buf { * @vmap_ptr: * The current vmap ptr if @vmapping_counter > 0. Protected by @lock. */ - struct dma_buf_map vmap_ptr; + struct iosys_map vmap_ptr; /** * @exp_name: @@ -393,27 +393,30 @@ struct dma_buf { * e.g. exposed in `Implicit Fence Poll Support`_ must follow the * below rules. * - * - Drivers must add a shared fence through dma_resv_add_shared_fence() - * for anything the userspace API considers a read access. This highly - * depends upon the API and window system. + * - Drivers must add a read fence through dma_resv_add_fence() with the + * DMA_RESV_USAGE_READ flag for anything the userspace API considers a + * read access. This highly depends upon the API and window system. * - * - Similarly drivers must set the exclusive fence through - * dma_resv_add_excl_fence() for anything the userspace API considers - * write access. + * - Similarly drivers must add a write fence through + * dma_resv_add_fence() with the DMA_RESV_USAGE_WRITE flag for + * anything the userspace API considers write access. * - * - Drivers may just always set the exclusive fence, since that only + * - Drivers may just always add a write fence, since that only * causes unecessarily synchronization, but no correctness issues. * * - Some drivers only expose a synchronous userspace API with no * pipelining across drivers. These do not set any fences for their * access. An example here is v4l. * + * - Driver should use dma_resv_usage_rw() when retrieving fences as + * dependency for implicit synchronization. + * * DYNAMIC IMPORTER RULES: * * Dynamic importers, see dma_buf_attachment_is_dynamic(), have * additional constraints on how they set up fences: * - * - Dynamic importers must obey the exclusive fence and wait for it to + * - Dynamic importers must obey the write fences and wait for them to * signal before allowing access to the buffer's underlying storage * through the device. * @@ -423,10 +426,9 @@ struct dma_buf { * * IMPORTANT: * - * All drivers must obey the struct dma_resv rules, specifically the - * rules for updating fences, see &dma_resv.fence_excl and - * &dma_resv.fence. If these dependency rules are broken access tracking - * can be lost resulting in use after free issues. + * All drivers and memory management related functions must obey the + * struct dma_resv rules, specifically the rules for updating and + * obeying fences. See enum dma_resv_usage for further descriptions. */ struct dma_resv *resv; @@ -628,6 +630,6 @@ int dma_buf_end_cpu_access(struct dma_buf *dma_buf, int dma_buf_mmap(struct dma_buf *, struct vm_area_struct *, unsigned long); -int dma_buf_vmap(struct dma_buf *dmabuf, struct dma_buf_map *map); -void dma_buf_vunmap(struct dma_buf *dmabuf, struct dma_buf_map *map); +int dma_buf_vmap(struct dma_buf *dmabuf, struct iosys_map *map); +void dma_buf_vunmap(struct dma_buf *dmabuf, struct iosys_map *map); #endif /* __DMA_BUF_H__ */ diff --git a/include/linux/dma-fence-array.h b/include/linux/dma-fence-array.h index 303dd712220f..ec7f25def392 100644 --- a/include/linux/dma-fence-array.h +++ b/include/linux/dma-fence-array.h @@ -45,19 +45,6 @@ struct dma_fence_array { struct irq_work work; }; -extern const struct dma_fence_ops dma_fence_array_ops; - -/** - * dma_fence_is_array - check if a fence is from the array subsclass - * @fence: fence to test - * - * Return true if it is a dma_fence_array and false otherwise. - */ -static inline bool dma_fence_is_array(struct dma_fence *fence) -{ - return fence->ops == &dma_fence_array_ops; -} - /** * to_dma_fence_array - cast a fence to a dma_fence_array * @fence: fence to cast to a dma_fence_array @@ -68,12 +55,27 @@ static inline bool dma_fence_is_array(struct dma_fence *fence) static inline struct dma_fence_array * to_dma_fence_array(struct dma_fence *fence) { - if (fence->ops != &dma_fence_array_ops) + if (!fence || !dma_fence_is_array(fence)) return NULL; return container_of(fence, struct dma_fence_array, base); } +/** + * dma_fence_array_for_each - iterate over all fences in array + * @fence: current fence + * @index: index into the array + * @head: potential dma_fence_array object + * + * Test if @array is a dma_fence_array object and if yes iterate over all fences + * in the array. If not just iterate over the fence in @array itself. + * + * For a deep dive iterator see dma_fence_unwrap_for_each(). + */ +#define dma_fence_array_for_each(fence, index, head) \ + for (index = 0, fence = dma_fence_array_first(head); fence; \ + ++(index), fence = dma_fence_array_next(head, index)) + struct dma_fence_array *dma_fence_array_create(int num_fences, struct dma_fence **fences, u64 context, unsigned seqno, @@ -81,4 +83,8 @@ struct dma_fence_array *dma_fence_array_create(int num_fences, bool dma_fence_match_context(struct dma_fence *fence, u64 context); +struct dma_fence *dma_fence_array_first(struct dma_fence *head); +struct dma_fence *dma_fence_array_next(struct dma_fence *head, + unsigned int index); + #endif /* __LINUX_DMA_FENCE_ARRAY_H */ diff --git a/include/linux/dma-fence-chain.h b/include/linux/dma-fence-chain.h index 54fe3443fd2c..4bdf0b96da28 100644 --- a/include/linux/dma-fence-chain.h +++ b/include/linux/dma-fence-chain.h @@ -49,7 +49,6 @@ struct dma_fence_chain { spinlock_t lock; }; -extern const struct dma_fence_ops dma_fence_chain_ops; /** * to_dma_fence_chain - cast a fence to a dma_fence_chain @@ -61,13 +60,28 @@ extern const struct dma_fence_ops dma_fence_chain_ops; static inline struct dma_fence_chain * to_dma_fence_chain(struct dma_fence *fence) { - if (!fence || fence->ops != &dma_fence_chain_ops) + if (!fence || !dma_fence_is_chain(fence)) return NULL; return container_of(fence, struct dma_fence_chain, base); } /** + * dma_fence_chain_contained - return the contained fence + * @fence: the fence to test + * + * If the fence is a dma_fence_chain the function returns the fence contained + * inside the chain object, otherwise it returns the fence itself. + */ +static inline struct dma_fence * +dma_fence_chain_contained(struct dma_fence *fence) +{ + struct dma_fence_chain *chain = to_dma_fence_chain(fence); + + return chain ? chain->fence : fence; +} + +/** * dma_fence_chain_alloc * * Returns a new struct dma_fence_chain object or NULL on failure. @@ -98,6 +112,8 @@ static inline void dma_fence_chain_free(struct dma_fence_chain *chain) * * Iterate over all fences in the chain. We keep a reference to the current * fence while inside the loop which must be dropped when breaking out. + * + * For a deep dive iterator see dma_fence_unwrap_for_each(). */ #define dma_fence_chain_for_each(iter, head) \ for (iter = dma_fence_get(head); iter; \ diff --git a/include/linux/dma-fence-unwrap.h b/include/linux/dma-fence-unwrap.h new file mode 100644 index 000000000000..66b1e56fbb81 --- /dev/null +++ b/include/linux/dma-fence-unwrap.h @@ -0,0 +1,75 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2022 Advanced Micro Devices, Inc. + * Authors: + * Christian König <christian.koenig@amd.com> + */ + +#ifndef __LINUX_DMA_FENCE_UNWRAP_H +#define __LINUX_DMA_FENCE_UNWRAP_H + +struct dma_fence; + +/** + * struct dma_fence_unwrap - cursor into the container structure + * + * Should be used with dma_fence_unwrap_for_each() iterator macro. + */ +struct dma_fence_unwrap { + /** + * @chain: potential dma_fence_chain, but can be other fence as well + */ + struct dma_fence *chain; + /** + * @array: potential dma_fence_array, but can be other fence as well + */ + struct dma_fence *array; + /** + * @index: last returned index if @array is really a dma_fence_array + */ + unsigned int index; +}; + +struct dma_fence *dma_fence_unwrap_first(struct dma_fence *head, + struct dma_fence_unwrap *cursor); +struct dma_fence *dma_fence_unwrap_next(struct dma_fence_unwrap *cursor); + +/** + * dma_fence_unwrap_for_each - iterate over all fences in containers + * @fence: current fence + * @cursor: current position inside the containers + * @head: starting point for the iterator + * + * Unwrap dma_fence_chain and dma_fence_array containers and deep dive into all + * potential fences in them. If @head is just a normal fence only that one is + * returned. + */ +#define dma_fence_unwrap_for_each(fence, cursor, head) \ + for (fence = dma_fence_unwrap_first(head, cursor); fence; \ + fence = dma_fence_unwrap_next(cursor)) + +struct dma_fence *__dma_fence_unwrap_merge(unsigned int num_fences, + struct dma_fence **fences, + struct dma_fence_unwrap *cursors); + +/** + * dma_fence_unwrap_merge - unwrap and merge fences + * + * All fences given as parameters are unwrapped and merged back together as flat + * dma_fence_array. Useful if multiple containers need to be merged together. + * + * Implemented as a macro to allocate the necessary arrays on the stack and + * account the stack frame size to the caller. + * + * Returns NULL on memory allocation failure, a dma_fence object representing + * all the given fences otherwise. + */ +#define dma_fence_unwrap_merge(...) \ + ({ \ + struct dma_fence *__f[] = { __VA_ARGS__ }; \ + struct dma_fence_unwrap __c[ARRAY_SIZE(__f)]; \ + \ + __dma_fence_unwrap_merge(ARRAY_SIZE(__f), __f, __c); \ + }) + +#endif diff --git a/include/linux/dma-fence.h b/include/linux/dma-fence.h index 1ea691753bd3..775cdc0b4f24 100644 --- a/include/linux/dma-fence.h +++ b/include/linux/dma-fence.h @@ -587,4 +587,42 @@ struct dma_fence *dma_fence_get_stub(void); struct dma_fence *dma_fence_allocate_private_stub(void); u64 dma_fence_context_alloc(unsigned num); +extern const struct dma_fence_ops dma_fence_array_ops; +extern const struct dma_fence_ops dma_fence_chain_ops; + +/** + * dma_fence_is_array - check if a fence is from the array subclass + * @fence: the fence to test + * + * Return true if it is a dma_fence_array and false otherwise. + */ +static inline bool dma_fence_is_array(struct dma_fence *fence) +{ + return fence->ops == &dma_fence_array_ops; +} + +/** + * dma_fence_is_chain - check if a fence is from the chain subclass + * @fence: the fence to test + * + * Return true if it is a dma_fence_chain and false otherwise. + */ +static inline bool dma_fence_is_chain(struct dma_fence *fence) +{ + return fence->ops == &dma_fence_chain_ops; +} + +/** + * dma_fence_is_container - check if a fence is a container for other fences + * @fence: the fence to test + * + * Return true if this fence is a container for other fences, false otherwise. + * This is important since we can't build up large fence structure or otherwise + * we run into recursion during operation on those fences. + */ +static inline bool dma_fence_is_container(struct dma_fence *fence) +{ + return dma_fence_is_array(fence) || dma_fence_is_chain(fence); +} + #endif /* __LINUX_DMA_FENCE_H */ diff --git a/include/linux/dma-iommu.h b/include/linux/dma-iommu.h deleted file mode 100644 index 24607dc3c2ac..000000000000 --- a/include/linux/dma-iommu.h +++ /dev/null @@ -1,93 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) 2014-2015 ARM Ltd. - */ -#ifndef __DMA_IOMMU_H -#define __DMA_IOMMU_H - -#include <linux/errno.h> -#include <linux/types.h> - -#ifdef CONFIG_IOMMU_DMA -#include <linux/dma-mapping.h> -#include <linux/iommu.h> -#include <linux/msi.h> - -/* Domain management interface for IOMMU drivers */ -int iommu_get_dma_cookie(struct iommu_domain *domain); -int iommu_get_msi_cookie(struct iommu_domain *domain, dma_addr_t base); -void iommu_put_dma_cookie(struct iommu_domain *domain); - -/* Setup call for arch DMA mapping code */ -void iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 dma_limit); -int iommu_dma_init_fq(struct iommu_domain *domain); - -/* The DMA API isn't _quite_ the whole story, though... */ -/* - * iommu_dma_prepare_msi() - Map the MSI page in the IOMMU device - * - * The MSI page will be stored in @desc. - * - * Return: 0 on success otherwise an error describing the failure. - */ -int iommu_dma_prepare_msi(struct msi_desc *desc, phys_addr_t msi_addr); - -/* Update the MSI message if required. */ -void iommu_dma_compose_msi_msg(struct msi_desc *desc, - struct msi_msg *msg); - -void iommu_dma_get_resv_regions(struct device *dev, struct list_head *list); - -void iommu_dma_free_cpu_cached_iovas(unsigned int cpu, - struct iommu_domain *domain); - -extern bool iommu_dma_forcedac; - -#else /* CONFIG_IOMMU_DMA */ - -struct iommu_domain; -struct msi_desc; -struct msi_msg; -struct device; - -static inline void iommu_setup_dma_ops(struct device *dev, u64 dma_base, - u64 dma_limit) -{ -} - -static inline int iommu_dma_init_fq(struct iommu_domain *domain) -{ - return -EINVAL; -} - -static inline int iommu_get_dma_cookie(struct iommu_domain *domain) -{ - return -ENODEV; -} - -static inline int iommu_get_msi_cookie(struct iommu_domain *domain, dma_addr_t base) -{ - return -ENODEV; -} - -static inline void iommu_put_dma_cookie(struct iommu_domain *domain) -{ -} - -static inline int iommu_dma_prepare_msi(struct msi_desc *desc, - phys_addr_t msi_addr) -{ - return 0; -} - -static inline void iommu_dma_compose_msi_msg(struct msi_desc *desc, - struct msi_msg *msg) -{ -} - -static inline void iommu_dma_get_resv_regions(struct device *dev, struct list_head *list) -{ -} - -#endif /* CONFIG_IOMMU_DMA */ -#endif /* __DMA_IOMMU_H */ diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h index 0d5b06b3a4a6..d678afeb8a13 100644 --- a/include/linux/dma-map-ops.h +++ b/include/linux/dma-map-ops.h @@ -11,7 +11,17 @@ struct cma; +/* + * Values for struct dma_map_ops.flags: + * + * DMA_F_PCI_P2PDMA_SUPPORTED: Indicates the dma_map_ops implementation can + * handle PCI P2PDMA pages in the map_sg/unmap_sg operation. + */ +#define DMA_F_PCI_P2PDMA_SUPPORTED (1 << 0) + struct dma_map_ops { + unsigned int flags; + void *(*alloc)(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs); @@ -69,6 +79,7 @@ struct dma_map_ops { int (*dma_supported)(struct device *dev, u64 mask); u64 (*get_required_mask)(struct device *dev); size_t (*max_mapping_size)(struct device *dev); + size_t (*opt_mapping_size)(void); unsigned long (*get_merge_boundary)(struct device *dev); }; @@ -166,6 +177,7 @@ static inline void dma_pernuma_cma_reserve(void) { } #ifdef CONFIG_DMA_DECLARE_COHERENT int dma_declare_coherent_memory(struct device *dev, phys_addr_t phys_addr, dma_addr_t device_addr, size_t size); +void dma_release_coherent_memory(struct device *dev); int dma_alloc_from_dev_coherent(struct device *dev, ssize_t size, dma_addr_t *dma_handle, void **ret); int dma_release_from_dev_coherent(struct device *dev, int order, void *vaddr); @@ -177,9 +189,11 @@ static inline int dma_declare_coherent_memory(struct device *dev, { return -ENOSYS; } + #define dma_alloc_from_dev_coherent(dev, size, handle, ret) (0) #define dma_release_from_dev_coherent(dev, order, vaddr) (0) #define dma_mmap_from_dev_coherent(dev, vma, vaddr, order, ret) (0) +static inline void dma_release_coherent_memory(struct device *dev) { } #endif /* CONFIG_DMA_DECLARE_COHERENT */ #ifdef CONFIG_DMA_GLOBAL_POOL @@ -379,4 +393,57 @@ static inline void debug_dma_dump_mappings(struct device *dev) extern const struct dma_map_ops dma_dummy_ops; +enum pci_p2pdma_map_type { + /* + * PCI_P2PDMA_MAP_UNKNOWN: Used internally for indicating the mapping + * type hasn't been calculated yet. Functions that return this enum + * never return this value. + */ + PCI_P2PDMA_MAP_UNKNOWN = 0, + + /* + * PCI_P2PDMA_MAP_NOT_SUPPORTED: Indicates the transaction will + * traverse the host bridge and the host bridge is not in the + * allowlist. DMA Mapping routines should return an error when + * this is returned. + */ + PCI_P2PDMA_MAP_NOT_SUPPORTED, + + /* + * PCI_P2PDMA_BUS_ADDR: Indicates that two devices can talk to + * each other directly through a PCI switch and the transaction will + * not traverse the host bridge. Such a mapping should program + * the DMA engine with PCI bus addresses. + */ + PCI_P2PDMA_MAP_BUS_ADDR, + + /* + * PCI_P2PDMA_MAP_THRU_HOST_BRIDGE: Indicates two devices can talk + * to each other, but the transaction traverses a host bridge on the + * allowlist. In this case, a normal mapping either with CPU physical + * addresses (in the case of dma-direct) or IOVA addresses (in the + * case of IOMMUs) should be used to program the DMA engine. + */ + PCI_P2PDMA_MAP_THRU_HOST_BRIDGE, +}; + +struct pci_p2pdma_map_state { + struct dev_pagemap *pgmap; + int map; + u64 bus_off; +}; + +#ifdef CONFIG_PCI_P2PDMA +enum pci_p2pdma_map_type +pci_p2pdma_map_segment(struct pci_p2pdma_map_state *state, struct device *dev, + struct scatterlist *sg); +#else /* CONFIG_PCI_P2PDMA */ +static inline enum pci_p2pdma_map_type +pci_p2pdma_map_segment(struct pci_p2pdma_map_state *state, struct device *dev, + struct scatterlist *sg) +{ + return PCI_P2PDMA_MAP_NOT_SUPPORTED; +} +#endif /* CONFIG_PCI_P2PDMA */ + #endif /* _LINUX_DMA_MAP_OPS_H */ diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index dca2b1355bb1..0ee20b764000 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -139,11 +139,12 @@ int dma_mmap_attrs(struct device *dev, struct vm_area_struct *vma, void *cpu_addr, dma_addr_t dma_addr, size_t size, unsigned long attrs); bool dma_can_mmap(struct device *dev); -int dma_supported(struct device *dev, u64 mask); +bool dma_pci_p2pdma_supported(struct device *dev); int dma_set_mask(struct device *dev, u64 mask); int dma_set_coherent_mask(struct device *dev, u64 mask); u64 dma_get_required_mask(struct device *dev); size_t dma_max_mapping_size(struct device *dev); +size_t dma_opt_mapping_size(struct device *dev); bool dma_need_sync(struct device *dev, dma_addr_t dma_addr); unsigned long dma_get_merge_boundary(struct device *dev); struct sg_table *dma_alloc_noncontiguous(struct device *dev, size_t size, @@ -246,9 +247,9 @@ static inline bool dma_can_mmap(struct device *dev) { return false; } -static inline int dma_supported(struct device *dev, u64 mask) +static inline bool dma_pci_p2pdma_supported(struct device *dev) { - return 0; + return false; } static inline int dma_set_mask(struct device *dev, u64 mask) { @@ -266,6 +267,10 @@ static inline size_t dma_max_mapping_size(struct device *dev) { return 0; } +static inline size_t dma_opt_mapping_size(struct device *dev) +{ + return 0; +} static inline bool dma_need_sync(struct device *dev, dma_addr_t dma_addr) { return false; diff --git a/include/linux/dma-resv.h b/include/linux/dma-resv.h index eebf04325b34..0637659a702c 100644 --- a/include/linux/dma-resv.h +++ b/include/linux/dma-resv.h @@ -47,24 +47,99 @@ extern struct ww_class reservation_ww_class; +struct dma_resv_list; + /** - * struct dma_resv_list - a list of shared fences - * @rcu: for internal use - * @shared_count: table of shared fences - * @shared_max: for growing shared fence table - * @shared: shared fence table + * enum dma_resv_usage - how the fences from a dma_resv obj are used + * + * This enum describes the different use cases for a dma_resv object and + * controls which fences are returned when queried. + * + * An important fact is that there is the order KERNEL<WRITE<READ<BOOKKEEP and + * when the dma_resv object is asked for fences for one use case the fences + * for the lower use case are returned as well. + * + * For example when asking for WRITE fences then the KERNEL fences are returned + * as well. Similar when asked for READ fences then both WRITE and KERNEL + * fences are returned as well. + * + * Already used fences can be promoted in the sense that a fence with + * DMA_RESV_USAGE_BOOKKEEP could become DMA_RESV_USAGE_READ by adding it again + * with this usage. But fences can never be degraded in the sense that a fence + * with DMA_RESV_USAGE_WRITE could become DMA_RESV_USAGE_READ. */ -struct dma_resv_list { - struct rcu_head rcu; - u32 shared_count, shared_max; - struct dma_fence __rcu *shared[]; +enum dma_resv_usage { + /** + * @DMA_RESV_USAGE_KERNEL: For in kernel memory management only. + * + * This should only be used for things like copying or clearing memory + * with a DMA hardware engine for the purpose of kernel memory + * management. + * + * Drivers *always* must wait for those fences before accessing the + * resource protected by the dma_resv object. The only exception for + * that is when the resource is known to be locked down in place by + * pinning it previously. + */ + DMA_RESV_USAGE_KERNEL, + + /** + * @DMA_RESV_USAGE_WRITE: Implicit write synchronization. + * + * This should only be used for userspace command submissions which add + * an implicit write dependency. + */ + DMA_RESV_USAGE_WRITE, + + /** + * @DMA_RESV_USAGE_READ: Implicit read synchronization. + * + * This should only be used for userspace command submissions which add + * an implicit read dependency. + */ + DMA_RESV_USAGE_READ, + + /** + * @DMA_RESV_USAGE_BOOKKEEP: No implicit sync. + * + * This should be used by submissions which don't want to participate in + * any implicit synchronization. + * + * The most common case are preemption fences, page table updates, TLB + * flushes as well as explicit synced user submissions. + * + * Explicit synced user user submissions can be promoted to + * DMA_RESV_USAGE_READ or DMA_RESV_USAGE_WRITE as needed using + * dma_buf_import_sync_file() when implicit synchronization should + * become necessary after initial adding of the fence. + */ + DMA_RESV_USAGE_BOOKKEEP }; /** + * dma_resv_usage_rw - helper for implicit sync + * @write: true if we create a new implicit sync write + * + * This returns the implicit synchronization usage for write or read accesses, + * see enum dma_resv_usage and &dma_buf.resv. + */ +static inline enum dma_resv_usage dma_resv_usage_rw(bool write) +{ + /* This looks confusing at first sight, but is indeed correct. + * + * The rational is that new write operations needs to wait for the + * existing read and write operations to finish. + * But a new read operation only needs to wait for the existing write + * operations to finish. + */ + return write ? DMA_RESV_USAGE_READ : DMA_RESV_USAGE_WRITE; +} + +/** * struct dma_resv - a reservation object manages fences for a buffer * - * There are multiple uses for this, with sometimes slightly different rules in - * how the fence slots are used. + * This is a container for dma_fence objects which needs to handle multiple use + * cases. * * One use is to synchronize cross-driver access to a struct dma_buf, either for * dynamic buffer management or just to handle implicit synchronization between @@ -91,81 +166,42 @@ struct dma_resv { struct ww_mutex lock; /** - * @seq: + * @fences: * - * Sequence count for managing RCU read-side synchronization, allows - * read-only access to @fence_excl and @fence while ensuring we take a - * consistent snapshot. - */ - seqcount_ww_mutex_t seq; - - /** - * @fence_excl: - * - * The exclusive fence, if there is one currently. - * - * There are two ways to update this fence: - * - * - First by calling dma_resv_add_excl_fence(), which replaces all - * fences attached to the reservation object. To guarantee that no - * fences are lost, this new fence must signal only after all previous - * fences, both shared and exclusive, have signalled. In some cases it - * is convenient to achieve that by attaching a struct dma_fence_array - * with all the new and old fences. - * - * - Alternatively the fence can be set directly, which leaves the - * shared fences unchanged. To guarantee that no fences are lost, this - * new fence must signal only after the previous exclusive fence has - * signalled. Since the shared fences are staying intact, it is not - * necessary to maintain any ordering against those. If semantically - * only a new access is added without actually treating the previous - * one as a dependency the exclusive fences can be strung together - * using struct dma_fence_chain. - * - * Note that actual semantics of what an exclusive or shared fence mean - * is defined by the user, for reservation objects shared across drivers - * see &dma_buf.resv. - */ - struct dma_fence __rcu *fence_excl; - - /** - * @fence: - * - * List of current shared fences. - * - * There are no ordering constraints of shared fences against the - * exclusive fence slot. If a waiter needs to wait for all access, it - * has to wait for both sets of fences to signal. + * Array of fences which where added to the dma_resv object * - * A new fence is added by calling dma_resv_add_shared_fence(). Since - * this often needs to be done past the point of no return in command + * A new fence is added by calling dma_resv_add_fence(). Since this + * often needs to be done past the point of no return in command * submission it cannot fail, and therefore sufficient slots need to be - * reserved by calling dma_resv_reserve_shared(). - * - * Note that actual semantics of what an exclusive or shared fence mean - * is defined by the user, for reservation objects shared across drivers - * see &dma_buf.resv. + * reserved by calling dma_resv_reserve_fences(). */ - struct dma_resv_list __rcu *fence; + struct dma_resv_list __rcu *fences; }; /** * struct dma_resv_iter - current position into the dma_resv fences * * Don't touch this directly in the driver, use the accessor function instead. + * + * IMPORTANT + * + * When using the lockless iterators like dma_resv_iter_next_unlocked() or + * dma_resv_for_each_fence_unlocked() beware that the iterator can be restarted. + * Code which accumulates statistics or similar needs to check for this with + * dma_resv_iter_is_restarted(). */ struct dma_resv_iter { /** @obj: The dma_resv object we iterate over */ struct dma_resv *obj; - /** @all_fences: If all fences should be returned */ - bool all_fences; + /** @usage: Return fences with this usage or lower. */ + enum dma_resv_usage usage; /** @fence: the currently handled fence */ struct dma_fence *fence; - /** @seq: sequence number to check for modifications */ - unsigned int seq; + /** @fence_usage: the usage of the current fence */ + enum dma_resv_usage fence_usage; /** @index: index into the shared fences */ unsigned int index; @@ -173,8 +209,8 @@ struct dma_resv_iter { /** @fences: the shared fences; private, *MUST* not dereference */ struct dma_resv_list *fences; - /** @shared_count: number of shared fences */ - unsigned int shared_count; + /** @num_fences: number of fences */ + unsigned int num_fences; /** @is_restarted: true if this is the first returned fence */ bool is_restarted; @@ -189,14 +225,14 @@ struct dma_fence *dma_resv_iter_next(struct dma_resv_iter *cursor); * dma_resv_iter_begin - initialize a dma_resv_iter object * @cursor: The dma_resv_iter object to initialize * @obj: The dma_resv object which we want to iterate over - * @all_fences: If all fences should be returned or just the exclusive one + * @usage: controls which fences to include, see enum dma_resv_usage. */ static inline void dma_resv_iter_begin(struct dma_resv_iter *cursor, struct dma_resv *obj, - bool all_fences) + enum dma_resv_usage usage) { cursor->obj = obj; - cursor->all_fences = all_fences; + cursor->usage = usage; cursor->fence = NULL; } @@ -213,14 +249,15 @@ static inline void dma_resv_iter_end(struct dma_resv_iter *cursor) } /** - * dma_resv_iter_is_exclusive - test if the current fence is the exclusive one + * dma_resv_iter_usage - Return the usage of the current fence * @cursor: the cursor of the current position * - * Returns true if the currently returned fence is the exclusive one. + * Returns the usage of the currently processed fence. */ -static inline bool dma_resv_iter_is_exclusive(struct dma_resv_iter *cursor) +static inline enum dma_resv_usage +dma_resv_iter_usage(struct dma_resv_iter *cursor) { - return cursor->index == 0; + return cursor->fence_usage; } /** @@ -243,7 +280,11 @@ static inline bool dma_resv_iter_is_restarted(struct dma_resv_iter *cursor) * &dma_resv.lock and using RCU instead. The cursor needs to be initialized * with dma_resv_iter_begin() and cleaned up with dma_resv_iter_end(). Inside * the iterator a reference to the dma_fence is held and the RCU lock dropped. - * When the dma_resv is modified the iteration starts over again. + * + * Beware that the iterator can be restarted when the struct dma_resv for + * @cursor is modified. Code which accumulates statistics or similar needs to + * check for this with dma_resv_iter_is_restarted(). For this reason prefer the + * lock iterator dma_resv_for_each_fence() whenever possible. */ #define dma_resv_for_each_fence_unlocked(cursor, fence) \ for (fence = dma_resv_iter_first_unlocked(cursor); \ @@ -253,7 +294,7 @@ static inline bool dma_resv_iter_is_restarted(struct dma_resv_iter *cursor) * dma_resv_for_each_fence - fence iterator * @cursor: a struct dma_resv_iter pointer * @obj: a dma_resv object pointer - * @all_fences: true if all fences should be returned + * @usage: controls which fences to return * @fence: the current fence * * Iterate over the fences in a struct dma_resv object while holding the @@ -262,8 +303,8 @@ static inline bool dma_resv_iter_is_restarted(struct dma_resv_iter *cursor) * valid as long as the lock is held and so no extra reference to the fence is * taken. */ -#define dma_resv_for_each_fence(cursor, obj, all_fences, fence) \ - for (dma_resv_iter_begin(cursor, obj, all_fences), \ +#define dma_resv_for_each_fence(cursor, obj, usage, fence) \ + for (dma_resv_iter_begin(cursor, obj, usage), \ fence = dma_resv_iter_first(cursor); fence; \ fence = dma_resv_iter_next(cursor)) @@ -271,9 +312,9 @@ static inline bool dma_resv_iter_is_restarted(struct dma_resv_iter *cursor) #define dma_resv_assert_held(obj) lockdep_assert_held(&(obj)->lock.base) #ifdef CONFIG_DEBUG_MUTEXES -void dma_resv_reset_shared_max(struct dma_resv *obj); +void dma_resv_reset_max_fences(struct dma_resv *obj); #else -static inline void dma_resv_reset_shared_max(struct dma_resv *obj) {} +static inline void dma_resv_reset_max_fences(struct dma_resv *obj) {} #endif /** @@ -419,51 +460,26 @@ static inline struct ww_acquire_ctx *dma_resv_locking_ctx(struct dma_resv *obj) */ static inline void dma_resv_unlock(struct dma_resv *obj) { - dma_resv_reset_shared_max(obj); + dma_resv_reset_max_fences(obj); ww_mutex_unlock(&obj->lock); } -/** - * dma_resv_excl_fence - return the object's exclusive fence - * @obj: the reservation object - * - * Returns the exclusive fence (if any). Caller must either hold the objects - * through dma_resv_lock() or the RCU read side lock through rcu_read_lock(), - * or one of the variants of each - * - * RETURNS - * The exclusive fence or NULL - */ -static inline struct dma_fence * -dma_resv_excl_fence(struct dma_resv *obj) -{ - return rcu_dereference_check(obj->fence_excl, dma_resv_held(obj)); -} - -/** - * dma_resv_shared_list - get the reservation object's shared fence list - * @obj: the reservation object - * - * Returns the shared fence list. Caller must either hold the objects - * through dma_resv_lock() or the RCU read side lock through rcu_read_lock(), - * or one of the variants of each - */ -static inline struct dma_resv_list *dma_resv_shared_list(struct dma_resv *obj) -{ - return rcu_dereference_check(obj->fence, dma_resv_held(obj)); -} - void dma_resv_init(struct dma_resv *obj); void dma_resv_fini(struct dma_resv *obj); -int dma_resv_reserve_shared(struct dma_resv *obj, unsigned int num_fences); -void dma_resv_add_shared_fence(struct dma_resv *obj, struct dma_fence *fence); -void dma_resv_add_excl_fence(struct dma_resv *obj, struct dma_fence *fence); -int dma_resv_get_fences(struct dma_resv *obj, struct dma_fence **pfence_excl, - unsigned *pshared_count, struct dma_fence ***pshared); +int dma_resv_reserve_fences(struct dma_resv *obj, unsigned int num_fences); +void dma_resv_add_fence(struct dma_resv *obj, struct dma_fence *fence, + enum dma_resv_usage usage); +void dma_resv_replace_fences(struct dma_resv *obj, uint64_t context, + struct dma_fence *fence, + enum dma_resv_usage usage); +int dma_resv_get_fences(struct dma_resv *obj, enum dma_resv_usage usage, + unsigned int *num_fences, struct dma_fence ***fences); +int dma_resv_get_singleton(struct dma_resv *obj, enum dma_resv_usage usage, + struct dma_fence **fence); int dma_resv_copy_fences(struct dma_resv *dst, struct dma_resv *src); -long dma_resv_wait_timeout(struct dma_resv *obj, bool wait_all, bool intr, - unsigned long timeout); -bool dma_resv_test_signaled(struct dma_resv *obj, bool test_all); +long dma_resv_wait_timeout(struct dma_resv *obj, enum dma_resv_usage usage, + bool intr, unsigned long timeout); +bool dma_resv_test_signaled(struct dma_resv *obj, enum dma_resv_usage usage); void dma_resv_describe(struct dma_resv *obj, struct seq_file *seq); #endif /* _LINUX_RESERVATION_H */ diff --git a/include/linux/dma/edma.h b/include/linux/dma/edma.h index cab6e18773da..7d8062e9c544 100644 --- a/include/linux/dma/edma.h +++ b/include/linux/dma/edma.h @@ -12,19 +12,74 @@ #include <linux/device.h> #include <linux/dmaengine.h> +#define EDMA_MAX_WR_CH 8 +#define EDMA_MAX_RD_CH 8 + struct dw_edma; +struct dw_edma_region { + phys_addr_t paddr; + void __iomem *vaddr; + size_t sz; +}; + +struct dw_edma_core_ops { + int (*irq_vector)(struct device *dev, unsigned int nr); +}; + +enum dw_edma_map_format { + EDMA_MF_EDMA_LEGACY = 0x0, + EDMA_MF_EDMA_UNROLL = 0x1, + EDMA_MF_HDMA_COMPAT = 0x5 +}; + +/** + * enum dw_edma_chip_flags - Flags specific to an eDMA chip + * @DW_EDMA_CHIP_LOCAL: eDMA is used locally by an endpoint + */ +enum dw_edma_chip_flags { + DW_EDMA_CHIP_LOCAL = BIT(0), +}; + /** * struct dw_edma_chip - representation of DesignWare eDMA controller hardware * @dev: struct device of the eDMA controller * @id: instance ID - * @irq: irq line - * @dw: struct dw_edma that is filed by dw_edma_probe() + * @nr_irqs: total number of DMA IRQs + * @ops DMA channel to IRQ number mapping + * @flags dw_edma_chip_flags + * @reg_base DMA register base address + * @ll_wr_cnt DMA write link list count + * @ll_rd_cnt DMA read link list count + * @rg_region DMA register region + * @ll_region_wr DMA descriptor link list memory for write channel + * @ll_region_rd DMA descriptor link list memory for read channel + * @dt_region_wr DMA data memory for write channel + * @dt_region_rd DMA data memory for read channel + * @mf DMA register map format + * @dw: struct dw_edma that is filled by dw_edma_probe() */ struct dw_edma_chip { struct device *dev; int id; - int irq; + int nr_irqs; + const struct dw_edma_core_ops *ops; + u32 flags; + + void __iomem *reg_base; + + u16 ll_wr_cnt; + u16 ll_rd_cnt; + /* link list address */ + struct dw_edma_region ll_region_wr[EDMA_MAX_WR_CH]; + struct dw_edma_region ll_region_rd[EDMA_MAX_RD_CH]; + + /* data region */ + struct dw_edma_region dt_region_wr[EDMA_MAX_WR_CH]; + struct dw_edma_region dt_region_rd[EDMA_MAX_RD_CH]; + + enum dw_edma_map_format mf; + struct dw_edma *dw; }; diff --git a/include/linux/dma/hsu.h b/include/linux/dma/hsu.h index a6b7bc707356..77ea602c287c 100644 --- a/include/linux/dma/hsu.h +++ b/include/linux/dma/hsu.h @@ -8,11 +8,13 @@ #ifndef _DMA_HSU_H #define _DMA_HSU_H -#include <linux/device.h> -#include <linux/interrupt.h> +#include <linux/errno.h> +#include <linux/kconfig.h> +#include <linux/types.h> #include <linux/platform_data/dma-hsu.h> +struct device; struct hsu_dma; /** diff --git a/include/linux/platform_data/dma-imx.h b/include/linux/dma/imx-dma.h index 281adbb26e6b..f487a4fa103a 100644 --- a/include/linux/platform_data/dma-imx.h +++ b/include/linux/dma/imx-dma.h @@ -3,8 +3,8 @@ * Copyright 2004-2009 Freescale Semiconductor, Inc. All Rights Reserved. */ -#ifndef __ASM_ARCH_MXC_DMA_H__ -#define __ASM_ARCH_MXC_DMA_H__ +#ifndef __LINUX_DMA_IMX_H +#define __LINUX_DMA_IMX_H #include <linux/scatterlist.h> #include <linux/device.h> @@ -39,6 +39,7 @@ enum sdma_peripheral_type { IMX_DMATYPE_SSI_DUAL, /* SSI Dual FIFO */ IMX_DMATYPE_ASRC_SP, /* Shared ASRC */ IMX_DMATYPE_SAI, /* SAI */ + IMX_DMATYPE_MULTI_SAI, /* MULTI FIFOs For Audio */ }; enum imx_dma_prio { @@ -65,4 +66,36 @@ static inline int imx_dma_is_general_purpose(struct dma_chan *chan) !strcmp(chan->device->dev->driver->name, "imx-dma"); } -#endif +/** + * struct sdma_peripheral_config - SDMA config for audio + * @n_fifos_src: Number of FIFOs for recording + * @n_fifos_dst: Number of FIFOs for playback + * @stride_fifos_src: FIFO address stride for recording, 0 means all FIFOs are + * continuous, 1 means 1 word stride between FIFOs. All stride + * between FIFOs should be same. + * @stride_fifos_dst: FIFO address stride for playback + * @words_per_fifo: numbers of words per FIFO fetch/fill, 1 means + * one channel per FIFO, 2 means 2 channels per FIFO.. + * If 'n_fifos_src = 4' and 'words_per_fifo = 2', it + * means the first two words(channels) fetch from FIFO0 + * and then jump to FIFO1 for next two words, and so on + * after the last FIFO3 fetched, roll back to FIFO0. + * @sw_done: Use software done. Needed for PDM (micfil) + * + * Some i.MX Audio devices (SAI, micfil) have multiple successive FIFO + * registers. For multichannel recording/playback the SAI/micfil have + * one FIFO register per channel and the SDMA engine has to read/write + * the next channel from/to the next register and wrap around to the + * first register when all channels are handled. The number of active + * channels must be communicated to the SDMA engine using this struct. + */ +struct sdma_peripheral_config { + int n_fifos_src; + int n_fifos_dst; + int stride_fifos_src; + int stride_fifos_dst; + int words_per_fifo; + bool sw_done; +}; + +#endif /* __LINUX_DMA_IMX_H */ diff --git a/include/linux/dma/qcom-gpi-dma.h b/include/linux/dma/qcom-gpi-dma.h index f46dc3372f11..6680dd1a43c6 100644 --- a/include/linux/dma/qcom-gpi-dma.h +++ b/include/linux/dma/qcom-gpi-dma.h @@ -26,7 +26,7 @@ enum spi_transfer_cmd { * @clk_div: source clock divider * @clk_src: serial clock * @cmd: spi cmd - * @fragmentation: keep CS assserted at end of sequence + * @fragmentation: keep CS asserted at end of sequence * @cs: chip select toggle * @set_config: set peripheral config * @rx_len: receive length for buffer diff --git a/include/linux/dma/qcom_adm.h b/include/linux/dma/qcom_adm.h new file mode 100644 index 000000000000..af20df674f0c --- /dev/null +++ b/include/linux/dma/qcom_adm.h @@ -0,0 +1,12 @@ +// SPDX-License-Identifier: GPL-2.0-only +#ifndef __LINUX_DMA_QCOM_ADM_H +#define __LINUX_DMA_QCOM_ADM_H + +#include <linux/types.h> + +struct qcom_adm_peripheral_config { + u32 crci; + u32 mux; +}; + +#endif /* __LINUX_DMA_QCOM_ADM_H */ diff --git a/include/linux/dma/xilinx_dpdma.h b/include/linux/dma/xilinx_dpdma.h new file mode 100644 index 000000000000..02a4adf8921b --- /dev/null +++ b/include/linux/dma/xilinx_dpdma.h @@ -0,0 +1,11 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LINUX_DMA_XILINX_DPDMA_H +#define __LINUX_DMA_XILINX_DPDMA_H + +#include <linux/types.h> + +struct xilinx_dpdma_peripheral_config { + bool video_group; +}; + +#endif /* __LINUX_DMA_XILINX_DPDMA_H */ diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 9000f3ffce8b..c923f4e60f24 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -418,9 +418,6 @@ enum dma_slave_buswidth { * @device_fc: Flow Controller Settings. Only valid for slave channels. Fill * with 'true' if peripheral should be flow controller. Direction will be * selected at Runtime. - * @slave_id: Slave requester id. Only valid for slave channels. The dma - * slave peripheral will have unique id as dma requester which need to be - * pass as slave config. * @peripheral_config: peripheral configuration for programming peripheral * for dmaengine transfer * @peripheral_size: peripheral configuration buffer size @@ -448,7 +445,6 @@ struct dma_slave_config { u32 src_port_window_size; u32 dst_port_window_size; bool device_fc; - unsigned int slave_id; void *peripheral_config; size_t peripheral_size; }; @@ -873,7 +869,6 @@ struct dma_device { struct device *dev; struct module *owner; struct ida chan_ida; - struct mutex chan_mutex; /* to protect chan_ida */ u32 src_addr_widths; u32 dst_addr_widths; @@ -1029,6 +1024,14 @@ static inline struct dma_async_tx_descriptor *dmaengine_prep_interleaved_dma( return chan->device->device_prep_interleaved_dma(chan, xt, flags); } +/** + * dmaengine_prep_dma_memset() - Prepare a DMA memset descriptor. + * @chan: The channel to be used for this descriptor + * @dest: Address of buffer to be set + * @value: Treated as a single byte value that fills the destination buffer + * @len: The total size of dest + * @flags: DMA engine flags + */ static inline struct dma_async_tx_descriptor *dmaengine_prep_dma_memset( struct dma_chan *chan, dma_addr_t dest, int value, size_t len, unsigned long flags) diff --git a/include/linux/dmar.h b/include/linux/dmar.h index 45e903d84733..d81a51978d01 100644 --- a/include/linux/dmar.h +++ b/include/linux/dmar.h @@ -18,11 +18,7 @@ struct acpi_dmar_header; -#ifdef CONFIG_X86 -# define DMAR_UNITS_SUPPORTED MAX_IO_APICS -#else -# define DMAR_UNITS_SUPPORTED 64 -#endif +#define DMAR_UNITS_SUPPORTED 1024 /* DMAR Flags */ #define DMAR_INTR_REMAP 0x1 @@ -121,7 +117,7 @@ extern int dmar_remove_dev_scope(struct dmar_pci_notify_info *info, u16 segment, struct dmar_dev_scope *devices, int count); /* Intel IOMMU detection */ -extern int detect_intel_iommu(void); +void detect_intel_iommu(void); extern int enable_drhd_fault_handling(void); extern int dmar_device_add(acpi_handle handle); extern int dmar_device_remove(acpi_handle handle); @@ -197,6 +193,10 @@ static inline bool dmar_platform_optin(void) return false; } +static inline void detect_intel_iommu(void) +{ +} + #endif /* CONFIG_DMAR_TABLE */ struct irte { diff --git a/include/linux/dnotify.h b/include/linux/dnotify.h index 0aad774beaec..b1d26f9f1c9f 100644 --- a/include/linux/dnotify.h +++ b/include/linux/dnotify.h @@ -26,10 +26,9 @@ struct dnotify_struct { FS_MODIFY | FS_MODIFY_CHILD |\ FS_ACCESS | FS_ACCESS_CHILD |\ FS_ATTRIB | FS_ATTRIB_CHILD |\ - FS_CREATE | FS_DN_RENAME |\ + FS_CREATE | FS_RENAME |\ FS_MOVED_FROM | FS_MOVED_TO) -extern int dir_notify_enable; extern void dnotify_flush(struct file *, fl_owner_t); extern int fcntl_dirnotify(int, struct file *, unsigned long); diff --git a/include/linux/dsa/8021q.h b/include/linux/dsa/8021q.h index 939a1beaddf7..3ed117e299ec 100644 --- a/include/linux/dsa/8021q.h +++ b/include/linux/dsa/8021q.h @@ -32,31 +32,29 @@ int dsa_tag_8021q_register(struct dsa_switch *ds, __be16 proto); void dsa_tag_8021q_unregister(struct dsa_switch *ds); -struct sk_buff *dsa_8021q_xmit(struct sk_buff *skb, struct net_device *netdev, - u16 tpid, u16 tci); +int dsa_tag_8021q_bridge_join(struct dsa_switch *ds, int port, + struct dsa_bridge bridge); -void dsa_8021q_rcv(struct sk_buff *skb, int *source_port, int *switch_id); +void dsa_tag_8021q_bridge_leave(struct dsa_switch *ds, int port, + struct dsa_bridge bridge); -int dsa_tag_8021q_bridge_tx_fwd_offload(struct dsa_switch *ds, int port, - struct dsa_bridge bridge); +struct sk_buff *dsa_8021q_xmit(struct sk_buff *skb, struct net_device *netdev, + u16 tpid, u16 tci); -void dsa_tag_8021q_bridge_tx_fwd_unoffload(struct dsa_switch *ds, int port, - struct dsa_bridge bridge); +void dsa_8021q_rcv(struct sk_buff *skb, int *source_port, int *switch_id, + int *vbid); -u16 dsa_8021q_bridge_tx_fwd_offload_vid(unsigned int bridge_num); +struct net_device *dsa_tag_8021q_find_port_by_vbid(struct net_device *master, + int vbid); -u16 dsa_tag_8021q_tx_vid(const struct dsa_port *dp); +u16 dsa_tag_8021q_bridge_vid(unsigned int bridge_num); -u16 dsa_tag_8021q_rx_vid(const struct dsa_port *dp); +u16 dsa_tag_8021q_standalone_vid(const struct dsa_port *dp); int dsa_8021q_rx_switch_id(u16 vid); int dsa_8021q_rx_source_port(u16 vid); -bool vid_is_dsa_8021q_rxvlan(u16 vid); - -bool vid_is_dsa_8021q_txvlan(u16 vid); - bool vid_is_dsa_8021q(u16 vid); #endif /* _NET_DSA_8021Q_H */ diff --git a/include/linux/dsa/tag_qca.h b/include/linux/dsa/tag_qca.h new file mode 100644 index 000000000000..b1b5720d89a5 --- /dev/null +++ b/include/linux/dsa/tag_qca.h @@ -0,0 +1,87 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __TAG_QCA_H +#define __TAG_QCA_H + +#include <linux/types.h> + +struct dsa_switch; +struct sk_buff; + +#define QCA_HDR_LEN 2 +#define QCA_HDR_VERSION 0x2 + +#define QCA_HDR_RECV_VERSION GENMASK(15, 14) +#define QCA_HDR_RECV_PRIORITY GENMASK(13, 11) +#define QCA_HDR_RECV_TYPE GENMASK(10, 6) +#define QCA_HDR_RECV_FRAME_IS_TAGGED BIT(3) +#define QCA_HDR_RECV_SOURCE_PORT GENMASK(2, 0) + +/* Packet type for recv */ +#define QCA_HDR_RECV_TYPE_NORMAL 0x0 +#define QCA_HDR_RECV_TYPE_MIB 0x1 +#define QCA_HDR_RECV_TYPE_RW_REG_ACK 0x2 + +#define QCA_HDR_XMIT_VERSION GENMASK(15, 14) +#define QCA_HDR_XMIT_PRIORITY GENMASK(13, 11) +#define QCA_HDR_XMIT_CONTROL GENMASK(10, 8) +#define QCA_HDR_XMIT_FROM_CPU BIT(7) +#define QCA_HDR_XMIT_DP_BIT GENMASK(6, 0) + +/* Packet type for xmit */ +#define QCA_HDR_XMIT_TYPE_NORMAL 0x0 +#define QCA_HDR_XMIT_TYPE_RW_REG 0x1 + +/* Check code for a valid mgmt packet. Switch will ignore the packet + * with this wrong. + */ +#define QCA_HDR_MGMT_CHECK_CODE_VAL 0x5 + +/* Specific define for in-band MDIO read/write with Ethernet packet */ +#define QCA_HDR_MGMT_SEQ_LEN 4 /* 4 byte for the seq */ +#define QCA_HDR_MGMT_COMMAND_LEN 4 /* 4 byte for the command */ +#define QCA_HDR_MGMT_DATA1_LEN 4 /* First 4 byte for the mdio data */ +#define QCA_HDR_MGMT_HEADER_LEN (QCA_HDR_MGMT_SEQ_LEN + \ + QCA_HDR_MGMT_COMMAND_LEN + \ + QCA_HDR_MGMT_DATA1_LEN) + +#define QCA_HDR_MGMT_DATA2_LEN 12 /* Other 12 byte for the mdio data */ +#define QCA_HDR_MGMT_PADDING_LEN 34 /* Padding to reach the min Ethernet packet */ + +#define QCA_HDR_MGMT_PKT_LEN (QCA_HDR_MGMT_HEADER_LEN + \ + QCA_HDR_LEN + \ + QCA_HDR_MGMT_DATA2_LEN + \ + QCA_HDR_MGMT_PADDING_LEN) + +#define QCA_HDR_MGMT_SEQ_NUM GENMASK(31, 0) /* 63, 32 */ +#define QCA_HDR_MGMT_CHECK_CODE GENMASK(31, 29) /* 31, 29 */ +#define QCA_HDR_MGMT_CMD BIT(28) /* 28 */ +#define QCA_HDR_MGMT_LENGTH GENMASK(23, 20) /* 23, 20 */ +#define QCA_HDR_MGMT_ADDR GENMASK(18, 0) /* 18, 0 */ + +/* Special struct emulating a Ethernet header */ +struct qca_mgmt_ethhdr { + __le32 command; /* command bit 31:0 */ + __le32 seq; /* seq 63:32 */ + __le32 mdio_data; /* first 4byte mdio */ + __be16 hdr; /* qca hdr */ +} __packed; + +enum mdio_cmd { + MDIO_WRITE = 0x0, + MDIO_READ +}; + +struct mib_ethhdr { + __le32 data[3]; /* first 3 mib counter */ + __be16 hdr; /* qca hdr */ +} __packed; + +struct qca_tagger_data { + void (*rw_reg_ack_handler)(struct dsa_switch *ds, + struct sk_buff *skb); + void (*mib_autocast_handler)(struct dsa_switch *ds, + struct sk_buff *skb); +}; + +#endif /* __TAG_QCA_H */ diff --git a/include/linux/dtpm.h b/include/linux/dtpm.h index d37e5d06a357..a4a13514b730 100644 --- a/include/linux/dtpm.h +++ b/include/linux/dtpm.h @@ -32,28 +32,25 @@ struct dtpm_ops { void (*release)(struct dtpm *); }; -typedef int (*dtpm_init_t)(void); +struct device_node; -struct dtpm_descr { - dtpm_init_t init; +struct dtpm_subsys_ops { + const char *name; + int (*init)(void); + void (*exit)(void); + int (*setup)(struct dtpm *, struct device_node *); }; -/* Init section thermal table */ -extern struct dtpm_descr __dtpm_table[]; -extern struct dtpm_descr __dtpm_table_end[]; - -#define DTPM_TABLE_ENTRY(name, __init) \ - static struct dtpm_descr __dtpm_table_entry_##name \ - __used __section("__dtpm_table") = { \ - .init = __init, \ - } - -#define DTPM_DECLARE(name, init) DTPM_TABLE_ENTRY(name, init) +enum DTPM_NODE_TYPE { + DTPM_NODE_VIRTUAL = 0, + DTPM_NODE_DT, +}; -#define for_each_dtpm_table(__dtpm) \ - for (__dtpm = __dtpm_table; \ - __dtpm < __dtpm_table_end; \ - __dtpm++) +struct dtpm_node { + enum DTPM_NODE_TYPE type; + const char *name; + struct dtpm_node *parent; +}; static inline struct dtpm *to_dtpm(struct powercap_zone *zone) { @@ -70,4 +67,7 @@ void dtpm_unregister(struct dtpm *dtpm); int dtpm_register(const char *name, struct dtpm *dtpm, struct dtpm *parent); +int dtpm_create_hierarchy(struct of_device_id *dtpm_match_table); + +void dtpm_destroy_hierarchy(void); #endif diff --git a/include/linux/dynamic_debug.h b/include/linux/dynamic_debug.h index dce631e678dd..41682278d2e8 100644 --- a/include/linux/dynamic_debug.h +++ b/include/linux/dynamic_debug.h @@ -6,6 +6,8 @@ #include <linux/jump_label.h> #endif +#include <linux/build_bug.h> + /* * An instance of this structure is created in a special * ELF section at every dynamic debug callsite. At runtime, @@ -21,6 +23,9 @@ struct _ddebug { const char *filename; const char *format; unsigned int lineno:18; +#define CLS_BITS 6 + unsigned int class_id:CLS_BITS; +#define _DPRINTK_CLASS_DFLT ((1 << CLS_BITS) - 1) /* * The flags field controls the behaviour at the callsite. * The bits here are changed dynamically when the user @@ -51,15 +56,82 @@ struct _ddebug { #endif } __attribute__((aligned(8))); - +enum class_map_type { + DD_CLASS_TYPE_DISJOINT_BITS, + /** + * DD_CLASS_TYPE_DISJOINT_BITS: classes are independent, one per bit. + * expecting hex input. Built for drm.debug, basis for other types. + */ + DD_CLASS_TYPE_LEVEL_NUM, + /** + * DD_CLASS_TYPE_LEVEL_NUM: input is numeric level, 0-N. + * N turns on just bits N-1 .. 0, so N=0 turns all bits off. + */ + DD_CLASS_TYPE_DISJOINT_NAMES, + /** + * DD_CLASS_TYPE_DISJOINT_NAMES: input is a CSV of [+-]CLASS_NAMES, + * classes are independent, like _DISJOINT_BITS. + */ + DD_CLASS_TYPE_LEVEL_NAMES, + /** + * DD_CLASS_TYPE_LEVEL_NAMES: input is a CSV of [+-]CLASS_NAMES, + * intended for names like: INFO,DEBUG,TRACE, with a module prefix + * avoid EMERG,ALERT,CRIT,ERR,WARNING: they're not debug + */ +}; + +struct ddebug_class_map { + struct list_head link; + struct module *mod; + const char *mod_name; /* needed for builtins */ + const char **class_names; + const int length; + const int base; /* index of 1st .class_id, allows split/shared space */ + enum class_map_type map_type; +}; + +/** + * DECLARE_DYNDBG_CLASSMAP - declare classnames known by a module + * @_var: a struct ddebug_class_map, passed to module_param_cb + * @_type: enum class_map_type, chooses bits/verbose, numeric/symbolic + * @_base: offset of 1st class-name. splits .class_id space + * @classes: class-names used to control class'd prdbgs + */ +#define DECLARE_DYNDBG_CLASSMAP(_var, _maptype, _base, ...) \ + static const char *_var##_classnames[] = { __VA_ARGS__ }; \ + static struct ddebug_class_map __aligned(8) __used \ + __section("__dyndbg_classes") _var = { \ + .mod = THIS_MODULE, \ + .mod_name = KBUILD_MODNAME, \ + .base = _base, \ + .map_type = _maptype, \ + .length = NUM_TYPE_ARGS(char*, __VA_ARGS__), \ + .class_names = _var##_classnames, \ + } +#define NUM_TYPE_ARGS(eltype, ...) \ + (sizeof((eltype[]){__VA_ARGS__}) / sizeof(eltype)) + +/* encapsulate linker provided built-in (or module) dyndbg data */ +struct _ddebug_info { + struct _ddebug *descs; + struct ddebug_class_map *classes; + unsigned int num_descs; + unsigned int num_classes; +}; + +struct ddebug_class_param { + union { + unsigned long *bits; + unsigned int *lvl; + }; + char flags[8]; + const struct ddebug_class_map *map; +}; #if defined(CONFIG_DYNAMIC_DEBUG_CORE) -/* exported for module authors to exercise >control */ -int dynamic_debug_exec_queries(const char *query, const char *modname); +int ddebug_add_module(struct _ddebug_info *dyndbg, const char *modname); -int ddebug_add_module(struct _ddebug *tab, unsigned int n, - const char *modname); extern int ddebug_remove_module(const char *mod_name); extern __printf(2, 3) void __dynamic_pr_debug(struct _ddebug *descriptor, const char *fmt, ...); @@ -87,7 +159,7 @@ void __dynamic_ibdev_dbg(struct _ddebug *descriptor, const struct ib_device *ibdev, const char *fmt, ...); -#define DEFINE_DYNAMIC_DEBUG_METADATA(name, fmt) \ +#define DEFINE_DYNAMIC_DEBUG_METADATA_CLS(name, cls, fmt) \ static struct _ddebug __aligned(8) \ __section("__dyndbg") name = { \ .modname = KBUILD_MODNAME, \ @@ -96,8 +168,14 @@ void __dynamic_ibdev_dbg(struct _ddebug *descriptor, .format = (fmt), \ .lineno = __LINE__, \ .flags = _DPRINTK_FLAGS_DEFAULT, \ + .class_id = cls, \ _DPRINTK_KEY_INIT \ - } + }; \ + BUILD_BUG_ON_MSG(cls > _DPRINTK_CLASS_DFLT, \ + "classid value overflow") + +#define DEFINE_DYNAMIC_DEBUG_METADATA(name, fmt) \ + DEFINE_DYNAMIC_DEBUG_METADATA_CLS(name, _DPRINTK_CLASS_DFLT, fmt) #ifdef CONFIG_JUMP_LABEL @@ -128,17 +206,34 @@ void __dynamic_ibdev_dbg(struct _ddebug *descriptor, #endif /* CONFIG_JUMP_LABEL */ -#define __dynamic_func_call(id, fmt, func, ...) do { \ - DEFINE_DYNAMIC_DEBUG_METADATA(id, fmt); \ - if (DYNAMIC_DEBUG_BRANCH(id)) \ - func(&id, ##__VA_ARGS__); \ -} while (0) - -#define __dynamic_func_call_no_desc(id, fmt, func, ...) do { \ - DEFINE_DYNAMIC_DEBUG_METADATA(id, fmt); \ +/* + * Factory macros: ($prefix)dynamic_func_call($suffix) + * + * Lower layer (with __ prefix) gets the callsite metadata, and wraps + * the func inside a debug-branch/static-key construct. Upper layer + * (with _ prefix) does the UNIQUE_ID once, so that lower can ref the + * name/label multiple times, and tie the elements together. + * Multiple flavors: + * (|_cls): adds in _DPRINT_CLASS_DFLT as needed + * (|_no_desc): former gets callsite descriptor as 1st arg (for prdbgs) + */ +#define __dynamic_func_call_cls(id, cls, fmt, func, ...) do { \ + DEFINE_DYNAMIC_DEBUG_METADATA_CLS(id, cls, fmt); \ if (DYNAMIC_DEBUG_BRANCH(id)) \ - func(__VA_ARGS__); \ + func(&id, ##__VA_ARGS__); \ +} while (0) +#define __dynamic_func_call(id, fmt, func, ...) \ + __dynamic_func_call_cls(id, _DPRINTK_CLASS_DFLT, fmt, \ + func, ##__VA_ARGS__) + +#define __dynamic_func_call_cls_no_desc(id, cls, fmt, func, ...) do { \ + DEFINE_DYNAMIC_DEBUG_METADATA_CLS(id, cls, fmt); \ + if (DYNAMIC_DEBUG_BRANCH(id)) \ + func(__VA_ARGS__); \ } while (0) +#define __dynamic_func_call_no_desc(id, fmt, func, ...) \ + __dynamic_func_call_cls_no_desc(id, _DPRINTK_CLASS_DFLT, \ + fmt, func, ##__VA_ARGS__) /* * "Factory macro" for generating a call to func, guarded by a @@ -148,22 +243,33 @@ void __dynamic_ibdev_dbg(struct _ddebug *descriptor, * the varargs. Note that fmt is repeated in invocations of this * macro. */ +#define _dynamic_func_call_cls(cls, fmt, func, ...) \ + __dynamic_func_call_cls(__UNIQUE_ID(ddebug), cls, fmt, func, ##__VA_ARGS__) #define _dynamic_func_call(fmt, func, ...) \ - __dynamic_func_call(__UNIQUE_ID(ddebug), fmt, func, ##__VA_ARGS__) + _dynamic_func_call_cls(_DPRINTK_CLASS_DFLT, fmt, func, ##__VA_ARGS__) + /* * A variant that does the same, except that the descriptor is not * passed as the first argument to the function; it is only called * with precisely the macro's varargs. */ -#define _dynamic_func_call_no_desc(fmt, func, ...) \ - __dynamic_func_call_no_desc(__UNIQUE_ID(ddebug), fmt, func, ##__VA_ARGS__) +#define _dynamic_func_call_cls_no_desc(cls, fmt, func, ...) \ + __dynamic_func_call_cls_no_desc(__UNIQUE_ID(ddebug), cls, fmt, \ + func, ##__VA_ARGS__) +#define _dynamic_func_call_no_desc(fmt, func, ...) \ + _dynamic_func_call_cls_no_desc(_DPRINTK_CLASS_DFLT, fmt, \ + func, ##__VA_ARGS__) + +#define dynamic_pr_debug_cls(cls, fmt, ...) \ + _dynamic_func_call_cls(cls, fmt, __dynamic_pr_debug, \ + pr_fmt(fmt), ##__VA_ARGS__) #define dynamic_pr_debug(fmt, ...) \ - _dynamic_func_call(fmt, __dynamic_pr_debug, \ + _dynamic_func_call(fmt, __dynamic_pr_debug, \ pr_fmt(fmt), ##__VA_ARGS__) #define dynamic_dev_dbg(dev, fmt, ...) \ - _dynamic_func_call(fmt,__dynamic_dev_dbg, \ + _dynamic_func_call(fmt, __dynamic_dev_dbg, \ dev, fmt, ##__VA_ARGS__) #define dynamic_netdev_dbg(dev, fmt, ...) \ @@ -181,14 +287,24 @@ void __dynamic_ibdev_dbg(struct _ddebug *descriptor, KERN_DEBUG, prefix_str, prefix_type, \ rowsize, groupsize, buf, len, ascii) +struct kernel_param; +int param_set_dyndbg_classes(const char *instr, const struct kernel_param *kp); +int param_get_dyndbg_classes(char *buffer, const struct kernel_param *kp); + +/* for test only, generally expect drm.debug style macro wrappers */ +#define __pr_debug_cls(cls, fmt, ...) do { \ + BUILD_BUG_ON_MSG(!__builtin_constant_p(cls), \ + "expecting constant class int/enum"); \ + dynamic_pr_debug_cls(cls, fmt, ##__VA_ARGS__); \ + } while (0) + #else /* !CONFIG_DYNAMIC_DEBUG_CORE */ #include <linux/string.h> #include <linux/errno.h> #include <linux/printk.h> -static inline int ddebug_add_module(struct _ddebug *tab, unsigned int n, - const char *modname) +static inline int ddebug_add_module(struct _ddebug_info *dinfo, const char *modname) { return 0; } @@ -201,7 +317,7 @@ static inline int ddebug_remove_module(const char *mod) static inline int ddebug_dyndbg_module_param_cb(char *param, char *val, const char *modname) { - if (strstr(param, "dyndbg")) { + if (!strcmp(param, "dyndbg")) { /* avoid pr_warn(), which wants pr_fmt() fully defined */ printk(KERN_WARNING "dyndbg param is supported only in " "CONFIG_DYNAMIC_DEBUG builds\n"); @@ -221,12 +337,14 @@ static inline int ddebug_dyndbg_module_param_cb(char *param, char *val, rowsize, groupsize, buf, len, ascii); \ } while (0) -static inline int dynamic_debug_exec_queries(const char *query, const char *modname) -{ - pr_warn("kernel not built with CONFIG_DYNAMIC_DEBUG_CORE\n"); - return 0; -} +struct kernel_param; +static inline int param_set_dyndbg_classes(const char *instr, const struct kernel_param *kp) +{ return 0; } +static inline int param_get_dyndbg_classes(char *buffer, const struct kernel_param *kp) +{ return 0; } #endif /* !CONFIG_DYNAMIC_DEBUG_CORE */ +extern const struct kernel_param_ops param_ops_dyndbg_classes; + #endif diff --git a/include/linux/edac.h b/include/linux/edac.h index e730b3468719..fa4bda2a70f6 100644 --- a/include/linux/edac.h +++ b/include/linux/edac.h @@ -231,21 +231,21 @@ enum mem_type { #define MEM_FLAG_DDR BIT(MEM_DDR) #define MEM_FLAG_RDDR BIT(MEM_RDDR) #define MEM_FLAG_RMBS BIT(MEM_RMBS) -#define MEM_FLAG_DDR2 BIT(MEM_DDR2) -#define MEM_FLAG_FB_DDR2 BIT(MEM_FB_DDR2) -#define MEM_FLAG_RDDR2 BIT(MEM_RDDR2) -#define MEM_FLAG_XDR BIT(MEM_XDR) -#define MEM_FLAG_DDR3 BIT(MEM_DDR3) -#define MEM_FLAG_RDDR3 BIT(MEM_RDDR3) -#define MEM_FLAG_LPDDR3 BIT(MEM_LPDDR3) -#define MEM_FLAG_DDR4 BIT(MEM_DDR4) -#define MEM_FLAG_RDDR4 BIT(MEM_RDDR4) -#define MEM_FLAG_LRDDR4 BIT(MEM_LRDDR4) -#define MEM_FLAG_LPDDR4 BIT(MEM_LPDDR4) -#define MEM_FLAG_DDR5 BIT(MEM_DDR5) -#define MEM_FLAG_RDDR5 BIT(MEM_RDDR5) -#define MEM_FLAG_LRDDR5 BIT(MEM_LRDDR5) -#define MEM_FLAG_NVDIMM BIT(MEM_NVDIMM) +#define MEM_FLAG_DDR2 BIT(MEM_DDR2) +#define MEM_FLAG_FB_DDR2 BIT(MEM_FB_DDR2) +#define MEM_FLAG_RDDR2 BIT(MEM_RDDR2) +#define MEM_FLAG_XDR BIT(MEM_XDR) +#define MEM_FLAG_DDR3 BIT(MEM_DDR3) +#define MEM_FLAG_RDDR3 BIT(MEM_RDDR3) +#define MEM_FLAG_LPDDR3 BIT(MEM_LPDDR3) +#define MEM_FLAG_DDR4 BIT(MEM_DDR4) +#define MEM_FLAG_RDDR4 BIT(MEM_RDDR4) +#define MEM_FLAG_LRDDR4 BIT(MEM_LRDDR4) +#define MEM_FLAG_LPDDR4 BIT(MEM_LPDDR4) +#define MEM_FLAG_DDR5 BIT(MEM_DDR5) +#define MEM_FLAG_RDDR5 BIT(MEM_RDDR5) +#define MEM_FLAG_LRDDR5 BIT(MEM_LRDDR5) +#define MEM_FLAG_NVDIMM BIT(MEM_NVDIMM) #define MEM_FLAG_WIO2 BIT(MEM_WIO2) #define MEM_FLAG_HBM2 BIT(MEM_HBM2) diff --git a/include/linux/efi.h b/include/linux/efi.h index 0de9fb1fdc5a..7603fc58c47c 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -148,6 +148,52 @@ typedef struct { u32 imagesize; } efi_capsule_header_t; +/* EFI_FIRMWARE_MANAGEMENT_CAPSULE_HEADER */ +struct efi_manage_capsule_header { + u32 ver; + u16 emb_drv_cnt; + u16 payload_cnt; + /* + * Variable-size array of the size given by the sum of + * emb_drv_cnt and payload_cnt. + */ + u64 offset_list[]; +} __packed; + +/* EFI_FIRMWARE_MANAGEMENT_CAPSULE_IMAGE_HEADER */ +struct efi_manage_capsule_image_header { + u32 ver; + efi_guid_t image_type_id; + u8 image_index; + u8 reserved_bytes[3]; + u32 image_size; + u32 vendor_code_size; + /* hw_ins was introduced in version 2 */ + u64 hw_ins; + /* capsule_support was introduced in version 3 */ + u64 capsule_support; +} __packed; + +/* WIN_CERTIFICATE */ +struct win_cert { + u32 len; + u16 rev; + u16 cert_type; +}; + +/* WIN_CERTIFICATE_UEFI_GUID */ +struct win_cert_uefi_guid { + struct win_cert hdr; + efi_guid_t cert_type; + u8 cert_data[]; +}; + +/* EFI_FIRMWARE_IMAGE_AUTHENTICATION */ +struct efi_image_auth { + u64 mon_count; + struct win_cert_uefi_guid auth_info; +}; + /* * EFI capsule flags */ @@ -167,6 +213,8 @@ struct capsule_info { size_t page_bytes_remain; }; +int efi_capsule_setup_info(struct capsule_info *cap_info, void *kbuff, + size_t hdr_bytes); int __efi_capsule_setup_info(struct capsule_info *cap_info); /* @@ -320,6 +368,9 @@ void efi_native_runtime_setup(void); #define UV_SYSTEM_TABLE_GUID EFI_GUID(0x3b13a7d4, 0x633e, 0x11dd, 0x93, 0xec, 0xda, 0x25, 0x56, 0xd8, 0x95, 0x93) #define LINUX_EFI_CRASH_GUID EFI_GUID(0xcfc8fc79, 0xbe2e, 0x4ddc, 0x97, 0xf0, 0x9f, 0x98, 0xbf, 0xe2, 0x98, 0xa0) #define LOADED_IMAGE_PROTOCOL_GUID EFI_GUID(0x5b1b31a1, 0x9562, 0x11d2, 0x8e, 0x3f, 0x00, 0xa0, 0xc9, 0x69, 0x72, 0x3b) +#define LOADED_IMAGE_DEVICE_PATH_PROTOCOL_GUID EFI_GUID(0xbc62157e, 0x3e33, 0x4fec, 0x99, 0x20, 0x2d, 0x3b, 0x36, 0xd7, 0x50, 0xdf) +#define EFI_DEVICE_PATH_PROTOCOL_GUID EFI_GUID(0x09576e91, 0x6d3f, 0x11d2, 0x8e, 0x39, 0x00, 0xa0, 0xc9, 0x69, 0x72, 0x3b) +#define EFI_DEVICE_PATH_TO_TEXT_PROTOCOL_GUID EFI_GUID(0x8b843e20, 0x8132, 0x4852, 0x90, 0xcc, 0x55, 0x1a, 0x4e, 0x4a, 0x7f, 0x1c) #define EFI_GRAPHICS_OUTPUT_PROTOCOL_GUID EFI_GUID(0x9042a9de, 0x23dc, 0x4a38, 0x96, 0xfb, 0x7a, 0xde, 0xd0, 0x80, 0x51, 0x6a) #define EFI_UGA_PROTOCOL_GUID EFI_GUID(0x982c298b, 0xf4fa, 0x41cb, 0xb8, 0x38, 0x77, 0xaa, 0x68, 0x8f, 0xb8, 0x39) #define EFI_PCI_IO_PROTOCOL_GUID EFI_GUID(0x4cf5b200, 0x68b8, 0x4ca5, 0x9e, 0xec, 0xb2, 0x3e, 0x3f, 0x50, 0x02, 0x9a) @@ -337,6 +388,8 @@ void efi_native_runtime_setup(void); #define EFI_LOAD_FILE_PROTOCOL_GUID EFI_GUID(0x56ec3091, 0x954c, 0x11d2, 0x8e, 0x3f, 0x00, 0xa0, 0xc9, 0x69, 0x72, 0x3b) #define EFI_LOAD_FILE2_PROTOCOL_GUID EFI_GUID(0x4006c0c1, 0xfcb3, 0x403e, 0x99, 0x6d, 0x4a, 0x6c, 0x87, 0x24, 0xe0, 0x6d) #define EFI_RT_PROPERTIES_TABLE_GUID EFI_GUID(0xeb66918a, 0x7eef, 0x402a, 0x84, 0x2e, 0x93, 0x1d, 0x21, 0xc3, 0x8a, 0xe9) +#define EFI_DXE_SERVICES_TABLE_GUID EFI_GUID(0x05ad34ba, 0x6f02, 0x4214, 0x95, 0x2e, 0x4d, 0xa0, 0x39, 0x8e, 0x2b, 0xb9) +#define EFI_SMBIOS_PROTOCOL_GUID EFI_GUID(0x03583ff6, 0xcb36, 0x4940, 0x94, 0x7e, 0xb9, 0xb3, 0x9f, 0x4a, 0xfa, 0xf7) #define EFI_IMAGE_SECURITY_DATABASE_GUID EFI_GUID(0xd719b2cb, 0x3d3a, 0x4596, 0xa3, 0xbc, 0xda, 0xd0, 0x0e, 0x67, 0x65, 0x6f) #define EFI_SHIM_LOCK_GUID EFI_GUID(0x605dab50, 0xe046, 0x4300, 0xab, 0xb6, 0x3d, 0xd8, 0x10, 0xdd, 0x8b, 0x23) @@ -344,6 +397,7 @@ void efi_native_runtime_setup(void); #define EFI_CERT_SHA256_GUID EFI_GUID(0xc1c41626, 0x504c, 0x4092, 0xac, 0xa9, 0x41, 0xf9, 0x36, 0x93, 0x43, 0x28) #define EFI_CERT_X509_GUID EFI_GUID(0xa5c059a1, 0x94e4, 0x4aa7, 0x87, 0xb5, 0xab, 0x15, 0x5c, 0x2b, 0xf0, 0x72) #define EFI_CERT_X509_SHA256_GUID EFI_GUID(0x3bd2a492, 0x96c0, 0x4079, 0xb4, 0x20, 0xfc, 0xf9, 0x8e, 0xf1, 0x03, 0xed) +#define EFI_CC_BLOB_GUID EFI_GUID(0x067b1f5f, 0xcf26, 0x44c5, 0x85, 0x54, 0x93, 0xd7, 0x77, 0x91, 0x2d, 0x42) /* * This GUID is used to pass to the kernel proper the struct screen_info @@ -358,7 +412,23 @@ void efi_native_runtime_setup(void); #define LINUX_EFI_TPM_FINAL_LOG_GUID EFI_GUID(0x1e2ed096, 0x30e2, 0x4254, 0xbd, 0x89, 0x86, 0x3b, 0xbe, 0xf8, 0x23, 0x25) #define LINUX_EFI_MEMRESERVE_TABLE_GUID EFI_GUID(0x888eb0c6, 0x8ede, 0x4ff5, 0xa8, 0xf0, 0x9a, 0xee, 0x5c, 0xb9, 0x77, 0xc2) #define LINUX_EFI_INITRD_MEDIA_GUID EFI_GUID(0x5568e427, 0x68fc, 0x4f3d, 0xac, 0x74, 0xca, 0x55, 0x52, 0x31, 0xcc, 0x68) +#define LINUX_EFI_ZBOOT_MEDIA_GUID EFI_GUID(0xe565a30d, 0x47da, 0x4dbd, 0xb3, 0x54, 0x9b, 0xb5, 0xc8, 0x4f, 0x8b, 0xe2) #define LINUX_EFI_MOK_VARIABLE_TABLE_GUID EFI_GUID(0xc451ed2b, 0x9694, 0x45d3, 0xba, 0xba, 0xed, 0x9f, 0x89, 0x88, 0xa3, 0x89) +#define LINUX_EFI_COCO_SECRET_AREA_GUID EFI_GUID(0xadf956ad, 0xe98c, 0x484c, 0xae, 0x11, 0xb5, 0x1c, 0x7d, 0x33, 0x64, 0x47) +#define LINUX_EFI_BOOT_MEMMAP_GUID EFI_GUID(0x800f683f, 0xd08b, 0x423a, 0xa2, 0x93, 0x96, 0x5c, 0x3c, 0x6f, 0xe2, 0xb4) + +#define RISCV_EFI_BOOT_PROTOCOL_GUID EFI_GUID(0xccd15fec, 0x6f73, 0x4eec, 0x83, 0x95, 0x3e, 0x69, 0xe4, 0xb9, 0x40, 0xbf) + +/* + * This GUID may be installed onto the kernel image's handle as a NULL protocol + * to signal to the stub that the placement of the image should be respected, + * and moving the image in physical memory is undesirable. To ensure + * compatibility with 64k pages kernels with virtually mapped stacks, and to + * avoid defeating physical randomization, this protocol should only be + * installed if the image was placed at a randomized 128k aligned address in + * memory. + */ +#define LINUX_EFI_LOADED_IMAGE_FIXED_GUID EFI_GUID(0xf5a37b6d, 0x3344, 0x42a5, 0xb6, 0xbb, 0x97, 0x86, 0x48, 0xc1, 0x89, 0x0a) /* OEM GUIDs */ #define DELLEMC_EFI_RCI2_TABLE_GUID EFI_GUID(0x2d9f28a2, 0xa886, 0x456a, 0x97, 0xa8, 0xf1, 0x1e, 0xf2, 0x4f, 0xf4, 0x55) @@ -389,6 +459,7 @@ typedef struct { } efi_config_table_type_t; #define EFI_SYSTEM_TABLE_SIGNATURE ((u64)0x5453595320494249ULL) +#define EFI_DXE_SERVICES_TABLE_SIGNATURE ((u64)0x565245535f455844ULL) #define EFI_2_30_SYSTEM_TABLE_REVISION ((2 << 16) | (30)) #define EFI_2_20_SYSTEM_TABLE_REVISION ((2 << 16) | (20)) @@ -453,6 +524,15 @@ typedef union { efi_system_table_32_t mixed_mode; } efi_system_table_t; +struct efi_boot_memmap { + unsigned long map_size; + unsigned long desc_size; + u32 desc_ver; + unsigned long map_key; + unsigned long buff_size; + efi_memory_desc_t map[]; +}; + /* * Architecture independent structure for describing a memory map for the * benefit of efi_memmap_init_early(), and for passing context between @@ -550,6 +630,7 @@ extern struct efi { unsigned long tpm_log; /* TPM2 Event Log table */ unsigned long tpm_final_log; /* TPM2 Final Events Log table */ unsigned long mokvar_table; /* MOK variable config table */ + unsigned long coco_secret; /* Confidential computing secret table */ efi_get_time_t *get_time; efi_set_time_t *set_time; @@ -806,6 +887,7 @@ static inline bool efi_rt_services_supported(unsigned int mask) { return (efi.runtime_supported_mask & mask) == mask; } +extern void efi_find_mirror(void); #else static inline bool efi_enabled(int feature) { @@ -823,6 +905,8 @@ static inline bool efi_rt_services_supported(unsigned int mask) { return false; } + +static inline void efi_find_mirror(void) {} #endif extern int efi_status_to_err(efi_status_t status); @@ -883,6 +967,7 @@ extern int efi_status_to_err(efi_status_t status); #define EFI_DEV_MEDIA_VENDOR 3 #define EFI_DEV_MEDIA_FILE 4 #define EFI_DEV_MEDIA_PROTOCOL 5 +#define EFI_DEV_MEDIA_REL_OFFSET 8 #define EFI_DEV_BIOS_BOOT 0x05 #define EFI_DEV_END_PATH 0x7F #define EFI_DEV_END_PATH2 0xFF @@ -913,12 +998,27 @@ struct efi_vendor_dev_path { u8 vendordata[]; } __packed; +struct efi_rel_offset_dev_path { + struct efi_generic_dev_path header; + u32 reserved; + u64 starting_offset; + u64 ending_offset; +} __packed; + +struct efi_mem_mapped_dev_path { + struct efi_generic_dev_path header; + u32 memory_type; + u64 starting_addr; + u64 ending_addr; +} __packed; + struct efi_dev_path { union { struct efi_generic_dev_path header; struct efi_acpi_dev_path acpi; struct efi_pci_dev_path pci; struct efi_vendor_dev_path vendor; + struct efi_rel_offset_dev_path rel_offset; }; } __packed; @@ -961,29 +1061,6 @@ struct efivars { #define EFI_VAR_NAME_LEN 1024 -struct efi_variable { - efi_char16_t VariableName[EFI_VAR_NAME_LEN/sizeof(efi_char16_t)]; - efi_guid_t VendorGuid; - unsigned long DataSize; - __u8 Data[1024]; - efi_status_t Status; - __u32 Attributes; -} __attribute__((packed)); - -struct efivar_entry { - struct efi_variable var; - struct list_head list; - struct kobject kobj; - bool scanning; - bool deleting; -}; - -static inline void -efivar_unregister(struct efivar_entry *var) -{ - kobject_put(&var->kobj); -} - int efivars_register(struct efivars *efivars, const struct efivar_operations *ops, struct kobject *kobject); @@ -991,43 +1068,23 @@ int efivars_unregister(struct efivars *efivars); struct kobject *efivars_kobject(void); int efivar_supports_writes(void); -int efivar_init(int (*func)(efi_char16_t *, efi_guid_t, unsigned long, void *), - void *data, bool duplicates, struct list_head *head); - -int efivar_entry_add(struct efivar_entry *entry, struct list_head *head); -int efivar_entry_remove(struct efivar_entry *entry); - -int __efivar_entry_delete(struct efivar_entry *entry); -int efivar_entry_delete(struct efivar_entry *entry); - -int efivar_entry_size(struct efivar_entry *entry, unsigned long *size); -int __efivar_entry_get(struct efivar_entry *entry, u32 *attributes, - unsigned long *size, void *data); -int efivar_entry_get(struct efivar_entry *entry, u32 *attributes, - unsigned long *size, void *data); -int efivar_entry_set(struct efivar_entry *entry, u32 attributes, - unsigned long size, void *data, struct list_head *head); -int efivar_entry_set_get_size(struct efivar_entry *entry, u32 attributes, - unsigned long *size, void *data, bool *set); -int efivar_entry_set_safe(efi_char16_t *name, efi_guid_t vendor, u32 attributes, - bool block, unsigned long size, void *data); - -int efivar_entry_iter_begin(void); -void efivar_entry_iter_end(void); - -int __efivar_entry_iter(int (*func)(struct efivar_entry *, void *), - struct list_head *head, void *data, - struct efivar_entry **prev); -int efivar_entry_iter(int (*func)(struct efivar_entry *, void *), - struct list_head *head, void *data); - -struct efivar_entry *efivar_entry_find(efi_char16_t *name, efi_guid_t guid, - struct list_head *head, bool remove); - -bool efivar_validate(efi_guid_t vendor, efi_char16_t *var_name, u8 *data, - unsigned long data_size); -bool efivar_variable_is_removable(efi_guid_t vendor, const char *name, - size_t len); + +int efivar_lock(void); +int efivar_trylock(void); +void efivar_unlock(void); + +efi_status_t efivar_get_variable(efi_char16_t *name, efi_guid_t *vendor, + u32 *attr, unsigned long *size, void *data); + +efi_status_t efivar_get_next_variable(unsigned long *name_size, + efi_char16_t *name, efi_guid_t *vendor); + +efi_status_t efivar_set_variable_locked(efi_char16_t *name, efi_guid_t *vendor, + u32 attr, unsigned long data_size, + void *data, bool nonblocking); + +efi_status_t efivar_set_variable(efi_char16_t *name, efi_guid_t *vendor, + u32 attr, unsigned long data_size, void *data); #if IS_ENABLED(CONFIG_EFI_CAPSULE_LOADER) extern bool efi_capsule_pending(int *reset_type); @@ -1115,6 +1172,8 @@ static inline void efi_check_for_embedded_firmwares(void) { } efi_status_t efi_random_get_seed(void); +#define arch_efi_call_virt(p, f, args...) ((p)->f(args)) + /* * Arch code can implement the following three template macros, avoiding * reptition for the void/non-void return cases of {__,}efi_call_virt(): @@ -1164,7 +1223,7 @@ efi_status_t efi_random_get_seed(void); arch_efi_call_virt_teardown(); \ }) -#define EFI_RANDOM_SEED_SIZE 64U +#define EFI_RANDOM_SEED_SIZE 32U // BLAKE2S_HASH_SIZE struct linux_efi_random_seed { u32 size; @@ -1283,10 +1342,19 @@ static inline struct efi_mokvar_table_entry *efi_mokvar_entry_find( } #endif -#ifdef CONFIG_SYSFB extern void efifb_setup_from_dmi(struct screen_info *si, const char *opt); -#else -static inline void efifb_setup_from_dmi(struct screen_info *si, const char *opt) { } -#endif + +struct linux_efi_coco_secret_area { + u64 base_pa; + u64 size; +}; + +struct linux_efi_initrd { + unsigned long base; + unsigned long size; +}; + +/* Header of a populated EFI secret area */ +#define EFI_SECRET_TABLE_HEADER_GUID EFI_GUID(0x1e74f542, 0x71dd, 0x4d66, 0x96, 0x3e, 0xef, 0x42, 0x87, 0xff, 0x17, 0x3b) #endif /* _LINUX_EFI_H */ diff --git a/include/linux/elfcore-compat.h b/include/linux/elfcore-compat.h index e272c3d452ce..54feb64e9b5d 100644 --- a/include/linux/elfcore-compat.h +++ b/include/linux/elfcore-compat.h @@ -43,6 +43,11 @@ struct compat_elf_prpsinfo __compat_uid_t pr_uid; __compat_gid_t pr_gid; compat_pid_t pr_pid, pr_ppid, pr_pgrp, pr_sid; + /* + * The hard-coded 16 is derived from TASK_COMM_LEN, but it can't be + * changed as it is exposed to userspace. We'd better make it hard-coded + * here. + */ char pr_fname[16]; char pr_psargs[ELF_PRARGSZ]; }; diff --git a/include/linux/elfcore.h b/include/linux/elfcore.h index 957ebec35aad..346a8b56cdc8 100644 --- a/include/linux/elfcore.h +++ b/include/linux/elfcore.h @@ -65,6 +65,11 @@ struct elf_prpsinfo __kernel_gid_t pr_gid; pid_t pr_pid, pr_ppid, pr_pgrp, pr_sid; /* Lots missing */ + /* + * The hard-coded 16 is derived from TASK_COMM_LEN, but it can't be + * changed as it is exposed to userspace. We'd better make it hard-coded + * here. + */ char pr_fname[16]; /* filename of executable */ char pr_psargs[ELF_PRARGSZ]; /* initial part of arg list */ }; @@ -79,15 +84,6 @@ static inline void elf_core_copy_regs(elf_gregset_t *elfregs, struct pt_regs *re #endif } -static inline void elf_core_copy_kernel_regs(elf_gregset_t *elfregs, struct pt_regs *regs) -{ -#ifdef ELF_CORE_COPY_KERNEL_REGS - ELF_CORE_COPY_KERNEL_REGS((*elfregs), regs); -#else - elf_core_copy_regs(elfregs, regs); -#endif -} - static inline int elf_core_copy_task_regs(struct task_struct *t, elf_gregset_t* elfregs) { #if defined (ELF_CORE_COPY_TASK_REGS) @@ -109,7 +105,7 @@ static inline int elf_core_copy_task_fpregs(struct task_struct *t, struct pt_reg #endif } -#if (defined(CONFIG_UML) && defined(CONFIG_X86_32)) || defined(CONFIG_IA64) +#ifdef CONFIG_ARCH_BINFMT_ELF_EXTRA_PHDRS /* * These functions parameterize elf_core_dump in fs/binfmt_elf.c to write out * extra segments containing the gate DSO contents. Dumping its @@ -144,6 +140,6 @@ static inline size_t elf_core_extra_data_size(void) { return 0; } -#endif +#endif /* CONFIG_ARCH_BINFMT_ELF_EXTRA_PHDRS */ #endif /* _LINUX_ELFCORE_H */ diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h index 6377adc3b78d..b9caa01dfac4 100644 --- a/include/linux/energy_model.h +++ b/include/linux/energy_model.h @@ -62,66 +62,115 @@ struct em_perf_domain { /* * em_perf_domain flags: * - * EM_PERF_DOMAIN_MILLIWATTS: The power values are in milli-Watts or some + * EM_PERF_DOMAIN_MICROWATTS: The power values are in micro-Watts or some * other scale. * * EM_PERF_DOMAIN_SKIP_INEFFICIENCIES: Skip inefficient states when estimating * energy consumption. + * + * EM_PERF_DOMAIN_ARTIFICIAL: The power values are artificial and might be + * created by platform missing real power information */ -#define EM_PERF_DOMAIN_MILLIWATTS BIT(0) +#define EM_PERF_DOMAIN_MICROWATTS BIT(0) #define EM_PERF_DOMAIN_SKIP_INEFFICIENCIES BIT(1) +#define EM_PERF_DOMAIN_ARTIFICIAL BIT(2) #define em_span_cpus(em) (to_cpumask((em)->cpus)) +#define em_is_artificial(em) ((em)->flags & EM_PERF_DOMAIN_ARTIFICIAL) #ifdef CONFIG_ENERGY_MODEL -#define EM_MAX_POWER 0xFFFF +/* + * The max power value in micro-Watts. The limit of 64 Watts is set as + * a safety net to not overflow multiplications on 32bit platforms. The + * 32bit value limit for total Perf Domain power implies a limit of + * maximum CPUs in such domain to 64. + */ +#define EM_MAX_POWER (64000000) /* 64 Watts */ + +/* + * To avoid possible energy estimation overflow on 32bit machines add + * limits to number of CPUs in the Perf. Domain. + * We are safe on 64bit machine, thus some big number. + */ +#ifdef CONFIG_64BIT +#define EM_MAX_NUM_CPUS 4096 +#else +#define EM_MAX_NUM_CPUS 16 +#endif /* - * Increase resolution of energy estimation calculations for 64-bit - * architectures. The extra resolution improves decision made by EAS for the - * task placement when two Performance Domains might provide similar energy - * estimation values (w/o better resolution the values could be equal). + * To avoid an overflow on 32bit machines while calculating the energy + * use a different order in the operation. First divide by the 'cpu_scale' + * which would reduce big value stored in the 'cost' field, then multiply by + * the 'sum_util'. This would allow to handle existing platforms, which have + * e.g. power ~1.3 Watt at max freq, so the 'cost' value > 1mln micro-Watts. + * In such scenario, where there are 4 CPUs in the Perf. Domain the 'sum_util' + * could be 4096, then multiplication: 'cost' * 'sum_util' would overflow. + * This reordering of operations has some limitations, we lose small + * precision in the estimation (comparing to 64bit platform w/o reordering). * - * We increase resolution only if we have enough bits to allow this increased - * resolution (i.e. 64-bit). The costs for increasing resolution when 32-bit - * are pretty high and the returns do not justify the increased costs. + * We are safe on 64bit machine. */ #ifdef CONFIG_64BIT -#define em_scale_power(p) ((p) * 1000) +#define em_estimate_energy(cost, sum_util, scale_cpu) \ + (((cost) * (sum_util)) / (scale_cpu)) #else -#define em_scale_power(p) (p) +#define em_estimate_energy(cost, sum_util, scale_cpu) \ + (((cost) / (scale_cpu)) * (sum_util)) #endif struct em_data_callback { /** * active_power() - Provide power at the next performance state of * a device + * @dev : Device for which we do this operation (can be a CPU) * @power : Active power at the performance state * (modified) * @freq : Frequency at the performance state in kHz * (modified) - * @dev : Device for which we do this operation (can be a CPU) * * active_power() must find the lowest performance state of 'dev' above * 'freq' and update 'power' and 'freq' to the matching active power * and frequency. * * In case of CPUs, the power is the one of a single CPU in the domain, - * expressed in milli-Watts or an abstract scale. It is expected to + * expressed in micro-Watts or an abstract scale. It is expected to * fit in the [0, EM_MAX_POWER] range. * * Return 0 on success. */ - int (*active_power)(unsigned long *power, unsigned long *freq, - struct device *dev); + int (*active_power)(struct device *dev, unsigned long *power, + unsigned long *freq); + + /** + * get_cost() - Provide the cost at the given performance state of + * a device + * @dev : Device for which we do this operation (can be a CPU) + * @freq : Frequency at the performance state in kHz + * @cost : The cost value for the performance state + * (modified) + * + * In case of CPUs, the cost is the one of a single CPU in the domain. + * It is expected to fit in the [0, EM_MAX_POWER] range due to internal + * usage in EAS calculation. + * + * Return 0 on success, or appropriate error value in case of failure. + */ + int (*get_cost)(struct device *dev, unsigned long freq, + unsigned long *cost); }; -#define EM_DATA_CB(_active_power_cb) { .active_power = &_active_power_cb } +#define EM_SET_ACTIVE_POWER_CB(em_cb, cb) ((em_cb).active_power = cb) +#define EM_ADV_DATA_CB(_active_power_cb, _cost_cb) \ + { .active_power = _active_power_cb, \ + .get_cost = _cost_cb } +#define EM_DATA_CB(_active_power_cb) \ + EM_ADV_DATA_CB(_active_power_cb, NULL) struct em_perf_domain *em_cpu_get(int cpu); struct em_perf_domain *em_pd_get(struct device *dev); int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states, struct em_data_callback *cb, cpumask_t *span, - bool milliwatts); + bool microwatts); void em_dev_unregister_perf_domain(struct device *dev); /** @@ -246,7 +295,7 @@ static inline unsigned long em_cpu_energy(struct em_perf_domain *pd, * pd_nrg = ------------------------ (4) * scale_cpu */ - return ps->cost * sum_util / scale_cpu; + return em_estimate_energy(ps->cost, sum_util, scale_cpu); } /** @@ -263,12 +312,14 @@ static inline int em_pd_nr_perf_states(struct em_perf_domain *pd) #else struct em_data_callback {}; +#define EM_ADV_DATA_CB(_active_power_cb, _cost_cb) { } #define EM_DATA_CB(_active_power_cb) { } +#define EM_SET_ACTIVE_POWER_CB(em_cb, cb) do { } while (0) static inline int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states, struct em_data_callback *cb, cpumask_t *span, - bool milliwatts) + bool microwatts) { return -EINVAL; } diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h index 2e2b8d6140ed..d95ab85f96ba 100644 --- a/include/linux/entry-common.h +++ b/include/linux/entry-common.h @@ -3,7 +3,7 @@ #define __LINUX_ENTRYCOMMON_H #include <linux/static_call_types.h> -#include <linux/tracehook.h> +#include <linux/ptrace.h> #include <linux/syscalls.h> #include <linux/seccomp.h> #include <linux/sched.h> @@ -63,7 +63,7 @@ ARCH_EXIT_TO_USER_MODE_WORK) /** - * arch_check_user_regs - Architecture specific sanity check for user mode regs + * arch_enter_from_user_mode - Architecture specific sanity check for user mode regs * @regs: Pointer to currents pt_regs * * Defaults to an empty implementation. Can be replaced by architecture @@ -73,30 +73,10 @@ * section. Use __always_inline so the compiler cannot push it out of line * and make it instrumentable. */ -static __always_inline void arch_check_user_regs(struct pt_regs *regs); +static __always_inline void arch_enter_from_user_mode(struct pt_regs *regs); -#ifndef arch_check_user_regs -static __always_inline void arch_check_user_regs(struct pt_regs *regs) {} -#endif - -/** - * arch_syscall_enter_tracehook - Wrapper around tracehook_report_syscall_entry() - * @regs: Pointer to currents pt_regs - * - * Returns: 0 on success or an error code to skip the syscall. - * - * Defaults to tracehook_report_syscall_entry(). Can be replaced by - * architecture specific code. - * - * Invoked from syscall_enter_from_user_mode() - */ -static inline __must_check int arch_syscall_enter_tracehook(struct pt_regs *regs); - -#ifndef arch_syscall_enter_tracehook -static inline __must_check int arch_syscall_enter_tracehook(struct pt_regs *regs) -{ - return tracehook_report_syscall_entry(regs); -} +#ifndef arch_enter_from_user_mode +static __always_inline void arch_enter_from_user_mode(struct pt_regs *regs) {} #endif /** @@ -157,7 +137,7 @@ void syscall_enter_from_user_mode_prepare(struct pt_regs *regs); * It handles the following work items: * * 1) syscall_work flag dependent invocations of - * arch_syscall_enter_tracehook(), __secure_computing(), trace_sys_enter() + * ptrace_report_syscall_entry(), __secure_computing(), trace_sys_enter() * 2) Invocation of audit_syscall_entry() */ long syscall_enter_from_user_mode_work(struct pt_regs *regs, long syscall); @@ -273,30 +253,10 @@ static __always_inline void arch_exit_to_user_mode(void) { } /** * arch_do_signal_or_restart - Architecture specific signal delivery function * @regs: Pointer to currents pt_regs - * @has_signal: actual signal to handle * * Invoked from exit_to_user_mode_loop(). */ -void arch_do_signal_or_restart(struct pt_regs *regs, bool has_signal); - -/** - * arch_syscall_exit_tracehook - Wrapper around tracehook_report_syscall_exit() - * @regs: Pointer to currents pt_regs - * @step: Indicator for single step - * - * Defaults to tracehook_report_syscall_exit(). Can be replaced by - * architecture specific code. - * - * Invoked from syscall_exit_to_user_mode() - */ -static inline void arch_syscall_exit_tracehook(struct pt_regs *regs, bool step); - -#ifndef arch_syscall_exit_tracehook -static inline void arch_syscall_exit_tracehook(struct pt_regs *regs, bool step) -{ - tracehook_report_syscall_exit(regs, step); -} -#endif +void arch_do_signal_or_restart(struct pt_regs *regs); /** * exit_to_user_mode - Fixup state when exiting to user mode @@ -347,7 +307,7 @@ void syscall_exit_to_user_mode_work(struct pt_regs *regs); * - rseq syscall exit * - audit * - syscall tracing - * - tracehook (single stepping) + * - ptrace (single stepping) * * 2) Preparatory work * - Exit to user mode loop (common TIF handling). Invokes @@ -396,7 +356,7 @@ void irqentry_exit_to_user_mode(struct pt_regs *regs); /** * struct irqentry_state - Opaque object for exception state storage * @exit_rcu: Used exclusively in the irqentry_*() calls; signals whether the - * exit path has to invoke rcu_irq_exit(). + * exit path has to invoke ct_irq_exit(). * @lockdep: Used exclusively in the irqentry_nmi_*() calls; ensures that * lockdep state is restored correctly on exit from nmi. * @@ -434,12 +394,12 @@ typedef struct irqentry_state { * * For kernel mode entries RCU handling is done conditional. If RCU is * watching then the only RCU requirement is to check whether the tick has - * to be restarted. If RCU is not watching then rcu_irq_enter() has to be - * invoked on entry and rcu_irq_exit() on exit. + * to be restarted. If RCU is not watching then ct_irq_enter() has to be + * invoked on entry and ct_irq_exit() on exit. * - * Avoiding the rcu_irq_enter/exit() calls is an optimization but also + * Avoiding the ct_irq_enter/exit() calls is an optimization but also * solves the problem of kernel mode pagefaults which can schedule, which - * is not possible after invoking rcu_irq_enter() without undoing it. + * is not possible after invoking ct_irq_enter() without undoing it. * * For user mode entries irqentry_enter_from_user_mode() is invoked to * establish the proper context for NOHZ_FULL. Otherwise scheduling on exit @@ -454,10 +414,21 @@ irqentry_state_t noinstr irqentry_enter(struct pt_regs *regs); * * Conditional reschedule with additional sanity checks. */ -void irqentry_exit_cond_resched(void); +void raw_irqentry_exit_cond_resched(void); #ifdef CONFIG_PREEMPT_DYNAMIC -DECLARE_STATIC_CALL(irqentry_exit_cond_resched, irqentry_exit_cond_resched); +#if defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL) +#define irqentry_exit_cond_resched_dynamic_enabled raw_irqentry_exit_cond_resched +#define irqentry_exit_cond_resched_dynamic_disabled NULL +DECLARE_STATIC_CALL(irqentry_exit_cond_resched, raw_irqentry_exit_cond_resched); +#define irqentry_exit_cond_resched() static_call(irqentry_exit_cond_resched)() +#elif defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY) +DECLARE_STATIC_KEY_TRUE(sk_dynamic_irqentry_exit_cond_resched); +void dynamic_irqentry_exit_cond_resched(void); +#define irqentry_exit_cond_resched() dynamic_irqentry_exit_cond_resched() #endif +#else /* CONFIG_PREEMPT_DYNAMIC */ +#define irqentry_exit_cond_resched() raw_irqentry_exit_cond_resched() +#endif /* CONFIG_PREEMPT_DYNAMIC */ /** * irqentry_exit - Handle return from exception that used irqentry_enter() diff --git a/include/linux/entry-kvm.h b/include/linux/entry-kvm.h index 07c878d6e323..6813171afccb 100644 --- a/include/linux/entry-kvm.h +++ b/include/linux/entry-kvm.h @@ -3,7 +3,7 @@ #define __LINUX_ENTRYKVM_H #include <linux/static_call_types.h> -#include <linux/tracehook.h> +#include <linux/resume_user_mode.h> #include <linux/syscalls.h> #include <linux/seccomp.h> #include <linux/sched.h> diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index 2ad71cc90b37..a541f0c4f146 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -134,7 +134,7 @@ static inline bool is_multicast_ether_addr(const u8 *addr) #endif } -static inline bool is_multicast_ether_addr_64bits(const u8 addr[6+2]) +static inline bool is_multicast_ether_addr_64bits(const u8 *addr) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 #ifdef __BIG_ENDIAN @@ -372,8 +372,7 @@ static inline bool ether_addr_equal(const u8 *addr1, const u8 *addr2) * Please note that alignment of addr1 & addr2 are only guaranteed to be 16 bits. */ -static inline bool ether_addr_equal_64bits(const u8 addr1[6+2], - const u8 addr2[6+2]) +static inline bool ether_addr_equal_64bits(const u8 *addr1, const u8 *addr2) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 u64 fold = (*(const u64 *)addr1) ^ (*(const u64 *)addr2); @@ -429,6 +428,28 @@ static inline bool ether_addr_equal_masked(const u8 *addr1, const u8 *addr2, return true; } +static inline bool ether_addr_is_ipv4_mcast(const u8 *addr) +{ + u8 base[ETH_ALEN] = { 0x01, 0x00, 0x5e, 0x00, 0x00, 0x00 }; + u8 mask[ETH_ALEN] = { 0xff, 0xff, 0xff, 0x80, 0x00, 0x00 }; + + return ether_addr_equal_masked(addr, base, mask); +} + +static inline bool ether_addr_is_ipv6_mcast(const u8 *addr) +{ + u8 base[ETH_ALEN] = { 0x33, 0x33, 0x00, 0x00, 0x00, 0x00 }; + u8 mask[ETH_ALEN] = { 0xff, 0xff, 0x00, 0x00, 0x00, 0x00 }; + + return ether_addr_equal_masked(addr, base, mask); +} + +static inline bool ether_addr_is_ip_mcast(const u8 *addr) +{ + return ether_addr_is_ipv4_mcast(addr) || + ether_addr_is_ipv6_mcast(addr); +} + /** * ether_addr_to_u64 - Convert an Ethernet address into a u64 value. * @addr: Pointer to a six-byte array containing the Ethernet address diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index a26f37a27167..99dc7bfbcd3c 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -70,17 +70,27 @@ enum { /** * struct kernel_ethtool_ringparam - RX/TX ring configuration * @rx_buf_len: Current length of buffers on the rx ring. + * @tcp_data_split: Scatter packet headers and data to separate buffers + * @tx_push: The flag of tx push mode + * @cqe_size: Size of TX/RX completion queue event */ struct kernel_ethtool_ringparam { u32 rx_buf_len; + u8 tcp_data_split; + u8 tx_push; + u32 cqe_size; }; /** * enum ethtool_supported_ring_param - indicator caps for setting ring params * @ETHTOOL_RING_USE_RX_BUF_LEN: capture for setting rx_buf_len + * @ETHTOOL_RING_USE_CQE_SIZE: capture for setting cqe_size + * @ETHTOOL_RING_USE_TX_PUSH: capture for setting tx_push */ enum ethtool_supported_ring_param { ETHTOOL_RING_USE_RX_BUF_LEN = BIT(0), + ETHTOOL_RING_USE_CQE_SIZE = BIT(1), + ETHTOOL_RING_USE_TX_PUSH = BIT(2), }; #define __ETH_RSS_HASH_BIT(bit) ((u32)1 << (bit)) @@ -111,7 +121,7 @@ struct ethtool_link_ext_state_info { enum ethtool_link_ext_substate_bad_signal_integrity bad_signal_integrity; enum ethtool_link_ext_substate_cable_issue cable_issue; enum ethtool_link_ext_substate_module module; - u8 __link_ext_substate; + u32 __link_ext_substate; }; }; diff --git a/include/linux/eventfd.h b/include/linux/eventfd.h index 305d5f19093b..30eb30d6909b 100644 --- a/include/linux/eventfd.h +++ b/include/linux/eventfd.h @@ -46,7 +46,7 @@ void eventfd_ctx_do_read(struct eventfd_ctx *ctx, __u64 *cnt); static inline bool eventfd_signal_allowed(void) { - return !current->in_eventfd_signal; + return !current->in_eventfd; } #else /* CONFIG_EVENTFD */ diff --git a/include/linux/evm.h b/include/linux/evm.h index 4c374be70247..aa63e0b3c0a2 100644 --- a/include/linux/evm.h +++ b/include/linux/evm.h @@ -21,7 +21,8 @@ extern enum integrity_status evm_verifyxattr(struct dentry *dentry, void *xattr_value, size_t xattr_value_len, struct integrity_iint_cache *iint); -extern int evm_inode_setattr(struct dentry *dentry, struct iattr *attr); +extern int evm_inode_setattr(struct user_namespace *mnt_userns, + struct dentry *dentry, struct iattr *attr); extern void evm_inode_post_setattr(struct dentry *dentry, int ia_valid); extern int evm_inode_setxattr(struct user_namespace *mnt_userns, struct dentry *dentry, const char *name, @@ -68,7 +69,8 @@ static inline enum integrity_status evm_verifyxattr(struct dentry *dentry, } #endif -static inline int evm_inode_setattr(struct dentry *dentry, struct iattr *attr) +static inline int evm_inode_setattr(struct user_namespace *mnt_userns, + struct dentry *dentry, struct iattr *attr) { return 0; } diff --git a/include/linux/export-internal.h b/include/linux/export-internal.h new file mode 100644 index 000000000000..fe7e6ba918f1 --- /dev/null +++ b/include/linux/export-internal.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Please do not include this explicitly. + * This is used by C files generated by modpost. + */ + +#ifndef __LINUX_EXPORT_INTERNAL_H__ +#define __LINUX_EXPORT_INTERNAL_H__ + +#include <linux/compiler.h> +#include <linux/types.h> + +#define SYMBOL_CRC(sym, crc, sec) \ + asm(".section \"___kcrctab" sec "+" #sym "\",\"a\"" "\n" \ + "__crc_" #sym ":" "\n" \ + ".long " #crc "\n" \ + ".previous" "\n") + +#endif /* __LINUX_EXPORT_INTERNAL_H__ */ diff --git a/include/linux/export.h b/include/linux/export.h index 27d848712b90..3f31ced0d977 100644 --- a/include/linux/export.h +++ b/include/linux/export.h @@ -2,6 +2,8 @@ #ifndef _LINUX_EXPORT_H #define _LINUX_EXPORT_H +#include <linux/stringify.h> + /* * Export symbols from the kernel to modules. Forked from module.h * to reduce the amount of pointless cruft we feed to gcc when only @@ -11,6 +13,14 @@ * hackers place grumpy comments in header files. */ +/* + * This comment block is used by fixdep. Please do not remove. + * + * When CONFIG_MODVERSIONS is changed from n to y, all source files having + * EXPORT_SYMBOL variants must be re-compiled because genksyms is run as a + * side effect of the *.o build rule. + */ + #ifndef __ASSEMBLY__ #ifdef MODULE extern struct module __this_module; @@ -19,26 +29,6 @@ extern struct module __this_module; #define THIS_MODULE ((struct module *)0) #endif -#ifdef CONFIG_MODVERSIONS -/* Mark the CRC weak since genksyms apparently decides not to - * generate a checksums for some symbols */ -#if defined(CONFIG_MODULE_REL_CRCS) -#define __CRC_SYMBOL(sym, sec) \ - asm(" .section \"___kcrctab" sec "+" #sym "\", \"a\" \n" \ - " .weak __crc_" #sym " \n" \ - " .long __crc_" #sym " - . \n" \ - " .previous \n") -#else -#define __CRC_SYMBOL(sym, sec) \ - asm(" .section \"___kcrctab" sec "+" #sym "\", \"a\" \n" \ - " .weak __crc_" #sym " \n" \ - " .long __crc_" #sym " \n" \ - " .previous \n") -#endif -#else -#define __CRC_SYMBOL(sym, sec) -#endif - #ifdef CONFIG_HAVE_ARCH_PREL32_RELOCATIONS #include <linux/compiler.h> /* @@ -85,7 +75,6 @@ struct kernel_symbol { /* * For every exported symbol, do the following: * - * - If applicable, place a CRC entry in the __kcrctab section. * - Put the name of the symbol and namespace (empty string "" for none) in * __ksymtab_strings. * - Place a struct kernel_symbol entry in the __ksymtab section. @@ -98,7 +87,6 @@ struct kernel_symbol { extern typeof(sym) sym; \ extern const char __kstrtab_##sym[]; \ extern const char __kstrtabns_##sym[]; \ - __CRC_SYMBOL(sym, sec); \ asm(" .section \"__ksymtab_strings\",\"aMS\",%progbits,1 \n" \ "__kstrtab_" #sym ": \n" \ " .asciz \"" #sym "\" \n" \ @@ -154,7 +142,6 @@ struct kernel_symbol { #endif /* CONFIG_MODULES */ #ifdef DEFAULT_SYMBOL_NAMESPACE -#include <linux/stringify.h> #define _EXPORT_SYMBOL(sym, sec) __EXPORT_SYMBOL(sym, sec, __stringify(DEFAULT_SYMBOL_NAMESPACE)) #else #define _EXPORT_SYMBOL(sym, sec) __EXPORT_SYMBOL(sym, sec, "") @@ -162,8 +149,8 @@ struct kernel_symbol { #define EXPORT_SYMBOL(sym) _EXPORT_SYMBOL(sym, "") #define EXPORT_SYMBOL_GPL(sym) _EXPORT_SYMBOL(sym, "_gpl") -#define EXPORT_SYMBOL_NS(sym, ns) __EXPORT_SYMBOL(sym, "", #ns) -#define EXPORT_SYMBOL_NS_GPL(sym, ns) __EXPORT_SYMBOL(sym, "_gpl", #ns) +#define EXPORT_SYMBOL_NS(sym, ns) __EXPORT_SYMBOL(sym, "", __stringify(ns)) +#define EXPORT_SYMBOL_NS_GPL(sym, ns) __EXPORT_SYMBOL(sym, "_gpl", __stringify(ns)) #endif /* !__ASSEMBLY__ */ diff --git a/include/linux/exportfs.h b/include/linux/exportfs.h index 3260fe714846..fe848901fcc3 100644 --- a/include/linux/exportfs.h +++ b/include/linux/exportfs.h @@ -221,8 +221,6 @@ struct export_operations { #define EXPORT_OP_NOATOMIC_ATTR (0x10) /* Filesystem cannot supply atomic attribute updates */ -#define EXPORT_OP_SYNC_LOCKS (0x20) /* Filesystem can't do - asychronous blocking locks */ unsigned long flags; }; diff --git a/include/linux/extcon.h b/include/linux/extcon.h index 0c19010da77f..3c45c3846fe9 100644 --- a/include/linux/extcon.h +++ b/include/linux/extcon.h @@ -76,6 +76,8 @@ #define EXTCON_DISP_VGA 43 /* Video Graphics Array */ #define EXTCON_DISP_DP 44 /* Display Port */ #define EXTCON_DISP_HMD 45 /* Head-Mounted Display */ +#define EXTCON_DISP_CVBS 46 /* Composite Video Broadcast Signal */ +#define EXTCON_DISP_EDP 47 /* Embedded Display Port */ /* Miscellaneous external connector */ #define EXTCON_DOCK 60 @@ -296,7 +298,7 @@ static inline void devm_extcon_unregister_notifier_all(struct device *dev, static inline struct extcon_dev *extcon_get_extcon_dev(const char *extcon_name) { - return ERR_PTR(-ENODEV); + return NULL; } static inline struct extcon_dev *extcon_find_edev_by_node(struct device_node *node) diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index d445150c5350..ee0d75d9a302 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -73,6 +73,42 @@ struct f2fs_device { __le32 total_segments; } __packed; +/* reason of stop_checkpoint */ +enum stop_cp_reason { + STOP_CP_REASON_SHUTDOWN, + STOP_CP_REASON_FAULT_INJECT, + STOP_CP_REASON_META_PAGE, + STOP_CP_REASON_WRITE_FAIL, + STOP_CP_REASON_CORRUPTED_SUMMARY, + STOP_CP_REASON_UPDATE_INODE, + STOP_CP_REASON_FLUSH_FAIL, + STOP_CP_REASON_MAX, +}; + +#define MAX_STOP_REASON 32 + +/* detail reason for EFSCORRUPTED */ +enum f2fs_error { + ERROR_CORRUPTED_CLUSTER, + ERROR_FAIL_DECOMPRESSION, + ERROR_INVALID_BLKADDR, + ERROR_CORRUPTED_DIRENT, + ERROR_CORRUPTED_INODE, + ERROR_INCONSISTENT_SUMMARY, + ERROR_INCONSISTENT_FOOTER, + ERROR_INCONSISTENT_SUM_TYPE, + ERROR_CORRUPTED_JOURNAL, + ERROR_INCONSISTENT_NODE_COUNT, + ERROR_INCONSISTENT_BLOCK_COUNT, + ERROR_INVALID_CURSEG, + ERROR_INCONSISTENT_SIT, + ERROR_CORRUPTED_VERITY_XATTR, + ERROR_CORRUPTED_XATTR, + ERROR_MAX, +}; + +#define MAX_F2FS_ERRORS 16 + struct f2fs_super_block { __le32 magic; /* Magic Number */ __le16 major_ver; /* Major Version */ @@ -116,7 +152,9 @@ struct f2fs_super_block { __u8 hot_ext_count; /* # of hot file extension */ __le16 s_encoding; /* Filename charset encoding */ __le16 s_encoding_flags; /* Filename charset encoding flags */ - __u8 reserved[306]; /* valid reserved region */ + __u8 s_stop_reason[MAX_STOP_REASON]; /* stop checkpoint reason */ + __u8 s_errors[MAX_F2FS_ERRORS]; /* reason of image corrupts */ + __u8 reserved[258]; /* valid reserved region */ __le32 crc; /* checksum of superblock */ } __packed; diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h index 616af2ea20f3..8ad743def6f3 100644 --- a/include/linux/fanotify.h +++ b/include/linux/fanotify.h @@ -5,8 +5,6 @@ #include <linux/sysctl.h> #include <uapi/linux/fanotify.h> -extern struct ctl_table fanotify_table[]; /* for sysctl */ - #define FAN_GROUP_FLAG(group, flag) \ ((group)->fanotify_data.flags & (flag)) @@ -25,7 +23,7 @@ extern struct ctl_table fanotify_table[]; /* for sysctl */ #define FANOTIFY_CLASS_BITS (FAN_CLASS_NOTIF | FANOTIFY_PERM_CLASSES) -#define FANOTIFY_FID_BITS (FAN_REPORT_FID | FAN_REPORT_DFID_NAME) +#define FANOTIFY_FID_BITS (FAN_REPORT_DFID_NAME_TARGET) #define FANOTIFY_INFO_MODES (FANOTIFY_FID_BITS | FAN_REPORT_PIDFD) @@ -61,14 +59,19 @@ extern struct ctl_table fanotify_table[]; /* for sysctl */ #define FANOTIFY_MARK_TYPE_BITS (FAN_MARK_INODE | FAN_MARK_MOUNT | \ FAN_MARK_FILESYSTEM) +#define FANOTIFY_MARK_CMD_BITS (FAN_MARK_ADD | FAN_MARK_REMOVE | \ + FAN_MARK_FLUSH) + +#define FANOTIFY_MARK_IGNORE_BITS (FAN_MARK_IGNORED_MASK | \ + FAN_MARK_IGNORE) + #define FANOTIFY_MARK_FLAGS (FANOTIFY_MARK_TYPE_BITS | \ - FAN_MARK_ADD | \ - FAN_MARK_REMOVE | \ + FANOTIFY_MARK_CMD_BITS | \ + FANOTIFY_MARK_IGNORE_BITS | \ FAN_MARK_DONT_FOLLOW | \ FAN_MARK_ONLYDIR | \ - FAN_MARK_IGNORED_MASK | \ FAN_MARK_IGNORED_SURV_MODIFY | \ - FAN_MARK_FLUSH) + FAN_MARK_EVICTABLE) /* * Events that can be reported with data type FSNOTIFY_EVENT_PATH. @@ -82,7 +85,8 @@ extern struct ctl_table fanotify_table[]; /* for sysctl */ * Directory entry modification events - reported only to directory * where entry is modified and not to a watching parent. */ -#define FANOTIFY_DIRENT_EVENTS (FAN_MOVE | FAN_CREATE | FAN_DELETE) +#define FANOTIFY_DIRENT_EVENTS (FAN_MOVE | FAN_CREATE | FAN_DELETE | \ + FAN_RENAME) /* Events that can be reported with event->fd */ #define FANOTIFY_FD_EVENTS (FANOTIFY_PATH_EVENTS | FANOTIFY_PERM_EVENTS) @@ -111,6 +115,10 @@ extern struct ctl_table fanotify_table[]; /* for sysctl */ FANOTIFY_PERM_EVENTS | \ FAN_Q_OVERFLOW | FAN_ONDIR) +/* Events and flags relevant only for directories */ +#define FANOTIFY_DIRONLY_EVENT_BITS (FANOTIFY_DIRENT_EVENTS | \ + FAN_EVENT_ON_CHILD | FAN_ONDIR) + #define ALL_FANOTIFY_EVENT_BITS (FANOTIFY_OUTGOING_EVENTS | \ FANOTIFY_EVENT_FLAGS) diff --git a/include/linux/fault-inject.h b/include/linux/fault-inject.h index e525f6957c49..9f6e25467844 100644 --- a/include/linux/fault-inject.h +++ b/include/linux/fault-inject.h @@ -20,6 +20,7 @@ struct fault_attr { atomic_t space; unsigned long verbose; bool task_filter; + bool no_warn; unsigned long stacktrace_depth; unsigned long require_start; unsigned long require_end; @@ -39,6 +40,7 @@ struct fault_attr { .ratelimit_state = RATELIMIT_STATE_INIT_DISABLED, \ .verbose = 2, \ .dname = NULL, \ + .no_warn = false, \ } #define DECLARE_FAULT_ATTR(name) struct fault_attr name = FAULT_ATTR_INITIALIZER @@ -64,6 +66,8 @@ static inline struct dentry *fault_create_debugfs_attr(const char *name, struct kmem_cache; +bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order); + int should_failslab(struct kmem_cache *s, gfp_t gfpflags); #ifdef CONFIG_FAILSLAB extern bool __should_failslab(struct kmem_cache *s, gfp_t gfpflags); diff --git a/include/linux/fb.h b/include/linux/fb.h index 3da95842b207..bcb8658f5b64 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -201,11 +201,19 @@ struct fb_pixmap { }; #ifdef CONFIG_FB_DEFERRED_IO +struct fb_deferred_io_pageref { + struct page *page; + unsigned long offset; + /* private */ + struct list_head list; +}; + struct fb_deferred_io { /* delay between mkwrite and deferred handler */ unsigned long delay; - struct mutex lock; /* mutex that protects the page list */ - struct list_head pagelist; /* list of touched pages */ + bool sort_pagereflist; /* sort pagelist by offset */ + struct mutex lock; /* mutex that protects the pageref list */ + struct list_head pagereflist; /* list of pagerefs for touched pages */ /* callback */ void (*first_io)(struct fb_info *info); void (*deferred_io)(struct fb_info *info, struct list_head *pagelist); @@ -262,7 +270,7 @@ struct fb_ops { /* Draws a rectangle */ void (*fb_fillrect) (struct fb_info *info, const struct fb_fillrect *rect); - /* Copy data from area to another. Obsolete. */ + /* Copy data from area to another */ void (*fb_copyarea) (struct fb_info *info, const struct fb_copyarea *region); /* Draws a image to the display */ void (*fb_imageblit) (struct fb_info *info, const struct fb_image *image); @@ -449,7 +457,6 @@ struct fb_info { struct fb_var_screeninfo var; /* Current var */ struct fb_fix_screeninfo fix; /* Current fix */ struct fb_monspecs monspecs; /* Current Monitor specs */ - struct work_struct queue; /* Framebuffer event queue */ struct fb_pixmap pixmap; /* Image hardware mapper */ struct fb_pixmap sprite; /* Cursor hardware mapper */ struct fb_cmap cmap; /* Current cmap */ @@ -468,6 +475,8 @@ struct fb_info { #endif #ifdef CONFIG_FB_DEFERRED_IO struct delayed_work deferred_work; + unsigned long npagerefs; + struct fb_deferred_io_pageref *pagerefs; struct fb_deferred_io *fbdefio; #endif @@ -546,7 +555,7 @@ static inline struct apertures_struct *alloc_apertures(unsigned int max_num) { #elif defined(__i386__) || defined(__alpha__) || defined(__x86_64__) || \ defined(__hppa__) || defined(__sh__) || defined(__powerpc__) || \ - defined(__arm__) || defined(__aarch64__) + defined(__arm__) || defined(__aarch64__) || defined(__mips__) #define fb_readb __raw_readb #define fb_readw __raw_readw @@ -606,11 +615,6 @@ extern ssize_t fb_sys_write(struct fb_info *info, const char __user *buf, /* drivers/video/fbmem.c */ extern int register_framebuffer(struct fb_info *fb_info); extern void unregister_framebuffer(struct fb_info *fb_info); -extern int remove_conflicting_pci_framebuffers(struct pci_dev *pdev, - const char *name); -extern int remove_conflicting_framebuffers(struct apertures_struct *a, - const char *name, bool primary); -extern bool is_firmware_framebuffer(struct apertures_struct *a); extern int fb_prepare_logo(struct fb_info *fb_info, int rotate); extern int fb_show_logo(struct fb_info *fb_info, int rotate); extern char* fb_get_buffer_offset(struct fb_info *info, struct fb_pixmap *buf, u32 size); @@ -623,16 +627,10 @@ extern int fb_get_color_depth(struct fb_var_screeninfo *var, extern int fb_get_options(const char *name, char **option); extern int fb_new_modelist(struct fb_info *info); -extern struct fb_info *registered_fb[FB_MAX]; -extern int num_registered_fb; extern bool fb_center_logo; extern int fb_logo_count; extern struct class *fb_class; -#define for_each_registered_fb(i) \ - for (i = 0; i < FB_MAX; i++) \ - if (!registered_fb[i]) {} else - static inline void lock_fb_info(struct fb_info *info) { mutex_lock(&info->lock); @@ -660,7 +658,7 @@ static inline void __fb_pad_aligned_buffer(u8 *dst, u32 d_pitch, /* drivers/video/fb_defio.c */ int fb_deferred_io_mmap(struct fb_info *info, struct vm_area_struct *vma); -extern void fb_deferred_io_init(struct fb_info *info); +extern int fb_deferred_io_init(struct fb_info *info); extern void fb_deferred_io_open(struct fb_info *info, struct inode *inode, struct file *file); diff --git a/include/linux/fbcon.h b/include/linux/fbcon.h index ff5596dd30f8..2382dec6d6ab 100644 --- a/include/linux/fbcon.h +++ b/include/linux/fbcon.h @@ -15,6 +15,8 @@ void fbcon_new_modelist(struct fb_info *info); void fbcon_get_requirement(struct fb_info *info, struct fb_blit_caps *caps); void fbcon_fb_blanked(struct fb_info *info, int blank); +int fbcon_modechange_possible(struct fb_info *info, + struct fb_var_screeninfo *var); void fbcon_update_vcs(struct fb_info *info, bool all); void fbcon_remap_all(struct fb_info *info); int fbcon_set_con2fb_map_ioctl(void __user *argp); @@ -33,6 +35,8 @@ static inline void fbcon_new_modelist(struct fb_info *info) {} static inline void fbcon_get_requirement(struct fb_info *info, struct fb_blit_caps *caps) {} static inline void fbcon_fb_blanked(struct fb_info *info, int blank) {} +static inline int fbcon_modechange_possible(struct fb_info *info, + struct fb_var_screeninfo *var) { return 0; } static inline void fbcon_update_vcs(struct fb_info *info, bool all) {} static inline void fbcon_remap_all(struct fb_info *info) {} static inline int fbcon_set_con2fb_map_ioctl(void __user *argp) { return 0; } diff --git a/include/linux/fdtable.h b/include/linux/fdtable.h index d0e78174874a..e066816f3519 100644 --- a/include/linux/fdtable.h +++ b/include/linux/fdtable.h @@ -125,7 +125,7 @@ int iterate_fd(struct files_struct *, unsigned, extern int close_fd(unsigned int fd); extern int __close_range(unsigned int fd, unsigned int max_fd, unsigned int flags); -extern int close_fd_get_file(unsigned int fd, struct file **res); +extern struct file *close_fd_get_file(unsigned int fd); extern int unshare_fd(unsigned long unshare_flags, unsigned int max_fds, struct files_struct **new_fdp); diff --git a/include/linux/file.h b/include/linux/file.h index 51e830b4fe3a..39704eae83e2 100644 --- a/include/linux/file.h +++ b/include/linux/file.h @@ -14,7 +14,6 @@ struct file; extern void fput(struct file *); -extern void fput_many(struct file *, unsigned int); struct file_operations; struct task_struct; @@ -47,7 +46,6 @@ static inline void fdput(struct fd fd) } extern struct file *fget(unsigned int fd); -extern struct file *fget_many(unsigned int fd, unsigned int refs); extern struct file *fget_raw(unsigned int fd); extern struct file *fget_task(struct task_struct *task, unsigned int fd); extern unsigned long __fdget(unsigned int fd); diff --git a/include/linux/filter.h b/include/linux/filter.h index 71fa57b88bfc..efc42a6e3aed 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -548,7 +548,7 @@ struct sock_fprog_kern { #define BPF_IMAGE_ALIGNMENT 8 struct bpf_binary_header { - u32 pages; + u32 size; u8 image[] __aligned(BPF_IMAGE_ALIGNMENT); }; @@ -559,38 +559,6 @@ struct bpf_prog_stats { struct u64_stats_sync syncp; } __aligned(2 * sizeof(u64)); -struct bpf_prog { - u16 pages; /* Number of allocated pages */ - u16 jited:1, /* Is our filter JIT'ed? */ - jit_requested:1,/* archs need to JIT the prog */ - gpl_compatible:1, /* Is filter GPL compatible? */ - cb_access:1, /* Is control block accessed? */ - dst_needed:1, /* Do we need dst entry? */ - blinded:1, /* Was blinded */ - is_func:1, /* program is a bpf function */ - kprobe_override:1, /* Do we override a kprobe? */ - has_callchain_buf:1, /* callchain buffer allocated? */ - enforce_expected_attach_type:1, /* Enforce expected_attach_type checking at attach time */ - call_get_stack:1, /* Do we call bpf_get_stack() or bpf_get_stackid() */ - call_get_func_ip:1; /* Do we call get_func_ip() */ - enum bpf_prog_type type; /* Type of BPF program */ - enum bpf_attach_type expected_attach_type; /* For some prog types */ - u32 len; /* Number of filter blocks */ - u32 jited_len; /* Size of jited insns in bytes */ - u8 tag[BPF_TAG_SIZE]; - struct bpf_prog_stats __percpu *stats; - int __percpu *active; - unsigned int (*bpf_func)(const void *ctx, - const struct bpf_insn *insn); - struct bpf_prog_aux *aux; /* Auxiliary fields */ - struct sock_fprog_kern *orig_prog; /* Original BPF program */ - /* Instructions for interpreter */ - union { - DECLARE_FLEX_ARRAY(struct sock_filter, insns); - DECLARE_FLEX_ARRAY(struct bpf_insn, insnsi); - }; -}; - struct sk_filter { refcount_t refcnt; struct rcu_head rcu; @@ -599,6 +567,12 @@ struct sk_filter { DECLARE_STATIC_KEY_FALSE(bpf_stats_enabled_key); +extern struct mutex nf_conn_btf_access_lock; +extern int (*nfct_btf_struct_access)(struct bpf_verifier_log *log, const struct btf *btf, + const struct btf_type *t, int off, int size, + enum bpf_access_type atype, u32 *next_btf_id, + enum bpf_type_flag *flag); + typedef unsigned int (*bpf_dispatcher_fn)(const void *ctx, const struct bpf_insn *insnsi, unsigned int (*bpf_func)(const void *, @@ -886,17 +860,8 @@ static inline void bpf_prog_lock_ro(struct bpf_prog *fp) static inline void bpf_jit_binary_lock_ro(struct bpf_binary_header *hdr) { set_vm_flush_reset_perms(hdr); - set_memory_ro((unsigned long)hdr, hdr->pages); - set_memory_x((unsigned long)hdr, hdr->pages); -} - -static inline struct bpf_binary_header * -bpf_jit_binary_hdr(const struct bpf_prog *fp) -{ - unsigned long real_start = (unsigned long)fp->bpf_func; - unsigned long addr = real_start & PAGE_MASK; - - return (void *)addr; + set_memory_ro((unsigned long)hdr, hdr->size >> PAGE_SHIFT); + set_memory_x((unsigned long)hdr, hdr->size >> PAGE_SHIFT); } int sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, unsigned int cap); @@ -941,8 +906,7 @@ int sk_reuseport_attach_filter(struct sock_fprog *fprog, struct sock *sk); int sk_reuseport_attach_bpf(u32 ufd, struct sock *sk); void sk_reuseport_prog_free(struct bpf_prog *prog); int sk_detach_filter(struct sock *sk); -int sk_get_filter(struct sock *sk, struct sock_filter __user *filter, - unsigned int len); +int sk_get_filter(struct sock *sk, sockptr_t optval, unsigned int len); bool sk_filter_charge(struct sock *sk, struct sk_filter *fp); void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp); @@ -955,6 +919,7 @@ u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog); void bpf_jit_compile(struct bpf_prog *prog); bool bpf_jit_needs_zext(void); +bool bpf_jit_supports_subprog_tailcalls(void); bool bpf_jit_supports_kfunc_call(void); bool bpf_helper_changes_pkt_data(void *func); @@ -1058,6 +1023,8 @@ extern long bpf_jit_limit_max; typedef void (*bpf_jit_fill_hole_t)(void *area, unsigned int size); +void bpf_jit_fill_hole_with_zero(void *area, unsigned int size); + struct bpf_binary_header * bpf_jit_binary_alloc(unsigned int proglen, u8 **image_ptr, unsigned int alignment, @@ -1067,6 +1034,29 @@ u64 bpf_jit_alloc_exec_limit(void); void *bpf_jit_alloc_exec(unsigned long size); void bpf_jit_free_exec(void *addr); void bpf_jit_free(struct bpf_prog *fp); +struct bpf_binary_header * +bpf_jit_binary_pack_hdr(const struct bpf_prog *fp); + +void *bpf_prog_pack_alloc(u32 size, bpf_jit_fill_hole_t bpf_fill_ill_insns); +void bpf_prog_pack_free(struct bpf_binary_header *hdr); + +static inline bool bpf_prog_kallsyms_verify_off(const struct bpf_prog *fp) +{ + return list_empty(&fp->aux->ksym.lnode) || + fp->aux->ksym.lnode.prev == LIST_POISON2; +} + +struct bpf_binary_header * +bpf_jit_binary_pack_alloc(unsigned int proglen, u8 **ro_image, + unsigned int alignment, + struct bpf_binary_header **rw_hdr, + u8 **rw_image, + bpf_jit_fill_hole_t bpf_fill_ill_insns); +int bpf_jit_binary_pack_finalize(struct bpf_prog *prog, + struct bpf_binary_header *ro_header, + struct bpf_binary_header *rw_header); +void bpf_jit_binary_pack_free(struct bpf_binary_header *ro_header, + struct bpf_binary_header *rw_header); int bpf_jit_add_poke_descriptor(struct bpf_prog *prog, struct bpf_jit_poke_descriptor *poke); @@ -1120,7 +1110,7 @@ static inline bool bpf_jit_blinding_enabled(struct bpf_prog *prog) return false; if (!bpf_jit_harden) return false; - if (bpf_jit_harden == 1 && capable(CAP_SYS_ADMIN)) + if (bpf_jit_harden == 1 && bpf_capable()) return false; return true; @@ -1356,7 +1346,10 @@ struct bpf_sockopt_kern { s32 level; s32 optname; s32 optlen; - s32 retval; + /* for retval in struct bpf_cg_run_ctx */ + struct task_struct *current_task; + /* Temporary "register" for indirect stores to ppos. */ + u64 tmp_reg; }; int copy_bpf_fprog_from_user(struct sock_fprog *dst, sockptr_t src, int len); diff --git a/include/linux/find.h b/include/linux/find.h new file mode 100644 index 000000000000..ccaf61a0f5fd --- /dev/null +++ b/include/linux/find.h @@ -0,0 +1,600 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LINUX_FIND_H_ +#define __LINUX_FIND_H_ + +#ifndef __LINUX_BITMAP_H +#error only <linux/bitmap.h> can be included directly +#endif + +#include <linux/bitops.h> + +unsigned long _find_next_bit(const unsigned long *addr1, unsigned long nbits, + unsigned long start); +unsigned long _find_next_and_bit(const unsigned long *addr1, const unsigned long *addr2, + unsigned long nbits, unsigned long start); +unsigned long _find_next_andnot_bit(const unsigned long *addr1, const unsigned long *addr2, + unsigned long nbits, unsigned long start); +unsigned long _find_next_zero_bit(const unsigned long *addr, unsigned long nbits, + unsigned long start); +extern unsigned long _find_first_bit(const unsigned long *addr, unsigned long size); +unsigned long __find_nth_bit(const unsigned long *addr, unsigned long size, unsigned long n); +unsigned long __find_nth_and_bit(const unsigned long *addr1, const unsigned long *addr2, + unsigned long size, unsigned long n); +unsigned long __find_nth_andnot_bit(const unsigned long *addr1, const unsigned long *addr2, + unsigned long size, unsigned long n); +extern unsigned long _find_first_and_bit(const unsigned long *addr1, + const unsigned long *addr2, unsigned long size); +extern unsigned long _find_first_zero_bit(const unsigned long *addr, unsigned long size); +extern unsigned long _find_last_bit(const unsigned long *addr, unsigned long size); + +#ifdef __BIG_ENDIAN +unsigned long _find_first_zero_bit_le(const unsigned long *addr, unsigned long size); +unsigned long _find_next_zero_bit_le(const unsigned long *addr, unsigned + long size, unsigned long offset); +unsigned long _find_next_bit_le(const unsigned long *addr, unsigned + long size, unsigned long offset); +#endif + +#ifndef find_next_bit +/** + * find_next_bit - find the next set bit in a memory region + * @addr: The address to base the search on + * @size: The bitmap size in bits + * @offset: The bitnumber to start searching at + * + * Returns the bit number for the next set bit + * If no bits are set, returns @size. + */ +static inline +unsigned long find_next_bit(const unsigned long *addr, unsigned long size, + unsigned long offset) +{ + if (small_const_nbits(size)) { + unsigned long val; + + if (unlikely(offset >= size)) + return size; + + val = *addr & GENMASK(size - 1, offset); + return val ? __ffs(val) : size; + } + + return _find_next_bit(addr, size, offset); +} +#endif + +#ifndef find_next_and_bit +/** + * find_next_and_bit - find the next set bit in both memory regions + * @addr1: The first address to base the search on + * @addr2: The second address to base the search on + * @size: The bitmap size in bits + * @offset: The bitnumber to start searching at + * + * Returns the bit number for the next set bit + * If no bits are set, returns @size. + */ +static inline +unsigned long find_next_and_bit(const unsigned long *addr1, + const unsigned long *addr2, unsigned long size, + unsigned long offset) +{ + if (small_const_nbits(size)) { + unsigned long val; + + if (unlikely(offset >= size)) + return size; + + val = *addr1 & *addr2 & GENMASK(size - 1, offset); + return val ? __ffs(val) : size; + } + + return _find_next_and_bit(addr1, addr2, size, offset); +} +#endif + +#ifndef find_next_andnot_bit +/** + * find_next_andnot_bit - find the next set bit in *addr1 excluding all the bits + * in *addr2 + * @addr1: The first address to base the search on + * @addr2: The second address to base the search on + * @size: The bitmap size in bits + * @offset: The bitnumber to start searching at + * + * Returns the bit number for the next set bit + * If no bits are set, returns @size. + */ +static inline +unsigned long find_next_andnot_bit(const unsigned long *addr1, + const unsigned long *addr2, unsigned long size, + unsigned long offset) +{ + if (small_const_nbits(size)) { + unsigned long val; + + if (unlikely(offset >= size)) + return size; + + val = *addr1 & ~*addr2 & GENMASK(size - 1, offset); + return val ? __ffs(val) : size; + } + + return _find_next_andnot_bit(addr1, addr2, size, offset); +} +#endif + +#ifndef find_next_zero_bit +/** + * find_next_zero_bit - find the next cleared bit in a memory region + * @addr: The address to base the search on + * @size: The bitmap size in bits + * @offset: The bitnumber to start searching at + * + * Returns the bit number of the next zero bit + * If no bits are zero, returns @size. + */ +static inline +unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size, + unsigned long offset) +{ + if (small_const_nbits(size)) { + unsigned long val; + + if (unlikely(offset >= size)) + return size; + + val = *addr | ~GENMASK(size - 1, offset); + return val == ~0UL ? size : ffz(val); + } + + return _find_next_zero_bit(addr, size, offset); +} +#endif + +#ifndef find_first_bit +/** + * find_first_bit - find the first set bit in a memory region + * @addr: The address to start the search at + * @size: The maximum number of bits to search + * + * Returns the bit number of the first set bit. + * If no bits are set, returns @size. + */ +static inline +unsigned long find_first_bit(const unsigned long *addr, unsigned long size) +{ + if (small_const_nbits(size)) { + unsigned long val = *addr & GENMASK(size - 1, 0); + + return val ? __ffs(val) : size; + } + + return _find_first_bit(addr, size); +} +#endif + +/** + * find_nth_bit - find N'th set bit in a memory region + * @addr: The address to start the search at + * @size: The maximum number of bits to search + * @n: The number of set bit, which position is needed, counting from 0 + * + * The following is semantically equivalent: + * idx = find_nth_bit(addr, size, 0); + * idx = find_first_bit(addr, size); + * + * Returns the bit number of the N'th set bit. + * If no such, returns @size. + */ +static inline +unsigned long find_nth_bit(const unsigned long *addr, unsigned long size, unsigned long n) +{ + if (n >= size) + return size; + + if (small_const_nbits(size)) { + unsigned long val = *addr & GENMASK(size - 1, 0); + + return val ? fns(val, n) : size; + } + + return __find_nth_bit(addr, size, n); +} + +/** + * find_nth_and_bit - find N'th set bit in 2 memory regions + * @addr1: The 1st address to start the search at + * @addr2: The 2nd address to start the search at + * @size: The maximum number of bits to search + * @n: The number of set bit, which position is needed, counting from 0 + * + * Returns the bit number of the N'th set bit. + * If no such, returns @size. + */ +static inline +unsigned long find_nth_and_bit(const unsigned long *addr1, const unsigned long *addr2, + unsigned long size, unsigned long n) +{ + if (n >= size) + return size; + + if (small_const_nbits(size)) { + unsigned long val = *addr1 & *addr2 & GENMASK(size - 1, 0); + + return val ? fns(val, n) : size; + } + + return __find_nth_and_bit(addr1, addr2, size, n); +} + +/** + * find_nth_andnot_bit - find N'th set bit in 2 memory regions, + * flipping bits in 2nd region + * @addr1: The 1st address to start the search at + * @addr2: The 2nd address to start the search at + * @size: The maximum number of bits to search + * @n: The number of set bit, which position is needed, counting from 0 + * + * Returns the bit number of the N'th set bit. + * If no such, returns @size. + */ +static inline +unsigned long find_nth_andnot_bit(const unsigned long *addr1, const unsigned long *addr2, + unsigned long size, unsigned long n) +{ + if (n >= size) + return size; + + if (small_const_nbits(size)) { + unsigned long val = *addr1 & (~*addr2) & GENMASK(size - 1, 0); + + return val ? fns(val, n) : size; + } + + return __find_nth_andnot_bit(addr1, addr2, size, n); +} + +#ifndef find_first_and_bit +/** + * find_first_and_bit - find the first set bit in both memory regions + * @addr1: The first address to base the search on + * @addr2: The second address to base the search on + * @size: The bitmap size in bits + * + * Returns the bit number for the next set bit + * If no bits are set, returns @size. + */ +static inline +unsigned long find_first_and_bit(const unsigned long *addr1, + const unsigned long *addr2, + unsigned long size) +{ + if (small_const_nbits(size)) { + unsigned long val = *addr1 & *addr2 & GENMASK(size - 1, 0); + + return val ? __ffs(val) : size; + } + + return _find_first_and_bit(addr1, addr2, size); +} +#endif + +#ifndef find_first_zero_bit +/** + * find_first_zero_bit - find the first cleared bit in a memory region + * @addr: The address to start the search at + * @size: The maximum number of bits to search + * + * Returns the bit number of the first cleared bit. + * If no bits are zero, returns @size. + */ +static inline +unsigned long find_first_zero_bit(const unsigned long *addr, unsigned long size) +{ + if (small_const_nbits(size)) { + unsigned long val = *addr | ~GENMASK(size - 1, 0); + + return val == ~0UL ? size : ffz(val); + } + + return _find_first_zero_bit(addr, size); +} +#endif + +#ifndef find_last_bit +/** + * find_last_bit - find the last set bit in a memory region + * @addr: The address to start the search at + * @size: The number of bits to search + * + * Returns the bit number of the last set bit, or size. + */ +static inline +unsigned long find_last_bit(const unsigned long *addr, unsigned long size) +{ + if (small_const_nbits(size)) { + unsigned long val = *addr & GENMASK(size - 1, 0); + + return val ? __fls(val) : size; + } + + return _find_last_bit(addr, size); +} +#endif + +/** + * find_next_and_bit_wrap - find the next set bit in both memory regions + * @addr1: The first address to base the search on + * @addr2: The second address to base the search on + * @size: The bitmap size in bits + * @offset: The bitnumber to start searching at + * + * Returns the bit number for the next set bit, or first set bit up to @offset + * If no bits are set, returns @size. + */ +static inline +unsigned long find_next_and_bit_wrap(const unsigned long *addr1, + const unsigned long *addr2, + unsigned long size, unsigned long offset) +{ + unsigned long bit = find_next_and_bit(addr1, addr2, size, offset); + + if (bit < size) + return bit; + + bit = find_first_and_bit(addr1, addr2, offset); + return bit < offset ? bit : size; +} + +/** + * find_next_bit_wrap - find the next set bit in both memory regions + * @addr: The first address to base the search on + * @size: The bitmap size in bits + * @offset: The bitnumber to start searching at + * + * Returns the bit number for the next set bit, or first set bit up to @offset + * If no bits are set, returns @size. + */ +static inline +unsigned long find_next_bit_wrap(const unsigned long *addr, + unsigned long size, unsigned long offset) +{ + unsigned long bit = find_next_bit(addr, size, offset); + + if (bit < size) + return bit; + + bit = find_first_bit(addr, offset); + return bit < offset ? bit : size; +} + +/* + * Helper for for_each_set_bit_wrap(). Make sure you're doing right thing + * before using it alone. + */ +static inline +unsigned long __for_each_wrap(const unsigned long *bitmap, unsigned long size, + unsigned long start, unsigned long n) +{ + unsigned long bit; + + /* If not wrapped around */ + if (n > start) { + /* and have a bit, just return it. */ + bit = find_next_bit(bitmap, size, n); + if (bit < size) + return bit; + + /* Otherwise, wrap around and ... */ + n = 0; + } + + /* Search the other part. */ + bit = find_next_bit(bitmap, start, n); + return bit < start ? bit : size; +} + +/** + * find_next_clump8 - find next 8-bit clump with set bits in a memory region + * @clump: location to store copy of found clump + * @addr: address to base the search on + * @size: bitmap size in number of bits + * @offset: bit offset at which to start searching + * + * Returns the bit offset for the next set clump; the found clump value is + * copied to the location pointed by @clump. If no bits are set, returns @size. + */ +extern unsigned long find_next_clump8(unsigned long *clump, + const unsigned long *addr, + unsigned long size, unsigned long offset); + +#define find_first_clump8(clump, bits, size) \ + find_next_clump8((clump), (bits), (size), 0) + +#if defined(__LITTLE_ENDIAN) + +static inline unsigned long find_next_zero_bit_le(const void *addr, + unsigned long size, unsigned long offset) +{ + return find_next_zero_bit(addr, size, offset); +} + +static inline unsigned long find_next_bit_le(const void *addr, + unsigned long size, unsigned long offset) +{ + return find_next_bit(addr, size, offset); +} + +static inline unsigned long find_first_zero_bit_le(const void *addr, + unsigned long size) +{ + return find_first_zero_bit(addr, size); +} + +#elif defined(__BIG_ENDIAN) + +#ifndef find_next_zero_bit_le +static inline +unsigned long find_next_zero_bit_le(const void *addr, unsigned + long size, unsigned long offset) +{ + if (small_const_nbits(size)) { + unsigned long val = *(const unsigned long *)addr; + + if (unlikely(offset >= size)) + return size; + + val = swab(val) | ~GENMASK(size - 1, offset); + return val == ~0UL ? size : ffz(val); + } + + return _find_next_zero_bit_le(addr, size, offset); +} +#endif + +#ifndef find_first_zero_bit_le +static inline +unsigned long find_first_zero_bit_le(const void *addr, unsigned long size) +{ + if (small_const_nbits(size)) { + unsigned long val = swab(*(const unsigned long *)addr) | ~GENMASK(size - 1, 0); + + return val == ~0UL ? size : ffz(val); + } + + return _find_first_zero_bit_le(addr, size); +} +#endif + +#ifndef find_next_bit_le +static inline +unsigned long find_next_bit_le(const void *addr, unsigned + long size, unsigned long offset) +{ + if (small_const_nbits(size)) { + unsigned long val = *(const unsigned long *)addr; + + if (unlikely(offset >= size)) + return size; + + val = swab(val) & GENMASK(size - 1, offset); + return val ? __ffs(val) : size; + } + + return _find_next_bit_le(addr, size, offset); +} +#endif + +#else +#error "Please fix <asm/byteorder.h>" +#endif + +#define for_each_set_bit(bit, addr, size) \ + for ((bit) = 0; (bit) = find_next_bit((addr), (size), (bit)), (bit) < (size); (bit)++) + +#define for_each_and_bit(bit, addr1, addr2, size) \ + for ((bit) = 0; \ + (bit) = find_next_and_bit((addr1), (addr2), (size), (bit)), (bit) < (size);\ + (bit)++) + +#define for_each_andnot_bit(bit, addr1, addr2, size) \ + for ((bit) = 0; \ + (bit) = find_next_andnot_bit((addr1), (addr2), (size), (bit)), (bit) < (size);\ + (bit)++) + +/* same as for_each_set_bit() but use bit as value to start with */ +#define for_each_set_bit_from(bit, addr, size) \ + for (; (bit) = find_next_bit((addr), (size), (bit)), (bit) < (size); (bit)++) + +#define for_each_clear_bit(bit, addr, size) \ + for ((bit) = 0; \ + (bit) = find_next_zero_bit((addr), (size), (bit)), (bit) < (size); \ + (bit)++) + +/* same as for_each_clear_bit() but use bit as value to start with */ +#define for_each_clear_bit_from(bit, addr, size) \ + for (; (bit) = find_next_zero_bit((addr), (size), (bit)), (bit) < (size); (bit)++) + +/** + * for_each_set_bitrange - iterate over all set bit ranges [b; e) + * @b: bit offset of start of current bitrange (first set bit) + * @e: bit offset of end of current bitrange (first unset bit) + * @addr: bitmap address to base the search on + * @size: bitmap size in number of bits + */ +#define for_each_set_bitrange(b, e, addr, size) \ + for ((b) = 0; \ + (b) = find_next_bit((addr), (size), b), \ + (e) = find_next_zero_bit((addr), (size), (b) + 1), \ + (b) < (size); \ + (b) = (e) + 1) + +/** + * for_each_set_bitrange_from - iterate over all set bit ranges [b; e) + * @b: bit offset of start of current bitrange (first set bit); must be initialized + * @e: bit offset of end of current bitrange (first unset bit) + * @addr: bitmap address to base the search on + * @size: bitmap size in number of bits + */ +#define for_each_set_bitrange_from(b, e, addr, size) \ + for (; \ + (b) = find_next_bit((addr), (size), (b)), \ + (e) = find_next_zero_bit((addr), (size), (b) + 1), \ + (b) < (size); \ + (b) = (e) + 1) + +/** + * for_each_clear_bitrange - iterate over all unset bit ranges [b; e) + * @b: bit offset of start of current bitrange (first unset bit) + * @e: bit offset of end of current bitrange (first set bit) + * @addr: bitmap address to base the search on + * @size: bitmap size in number of bits + */ +#define for_each_clear_bitrange(b, e, addr, size) \ + for ((b) = 0; \ + (b) = find_next_zero_bit((addr), (size), (b)), \ + (e) = find_next_bit((addr), (size), (b) + 1), \ + (b) < (size); \ + (b) = (e) + 1) + +/** + * for_each_clear_bitrange_from - iterate over all unset bit ranges [b; e) + * @b: bit offset of start of current bitrange (first set bit); must be initialized + * @e: bit offset of end of current bitrange (first unset bit) + * @addr: bitmap address to base the search on + * @size: bitmap size in number of bits + */ +#define for_each_clear_bitrange_from(b, e, addr, size) \ + for (; \ + (b) = find_next_zero_bit((addr), (size), (b)), \ + (e) = find_next_bit((addr), (size), (b) + 1), \ + (b) < (size); \ + (b) = (e) + 1) + +/** + * for_each_set_bit_wrap - iterate over all set bits starting from @start, and + * wrapping around the end of bitmap. + * @bit: offset for current iteration + * @addr: bitmap address to base the search on + * @size: bitmap size in number of bits + * @start: Starting bit for bitmap traversing, wrapping around the bitmap end + */ +#define for_each_set_bit_wrap(bit, addr, size, start) \ + for ((bit) = find_next_bit_wrap((addr), (size), (start)); \ + (bit) < (size); \ + (bit) = __for_each_wrap((addr), (size), (start), (bit) + 1)) + +/** + * for_each_set_clump8 - iterate over bitmap for each 8-bit clump with set bits + * @start: bit offset to start search and to store the current iteration offset + * @clump: location to store copy of current 8-bit clump + * @bits: bitmap address to base the search on + * @size: bitmap size in number of bits + */ +#define for_each_set_clump8(start, clump, bits, size) \ + for ((start) = find_first_clump8(&(clump), (bits), (size)); \ + (start) < (size); \ + (start) = find_next_clump8(&(clump), (bits), (size), (start) + 8)) + +#endif /*__LINUX_FIND_H_ */ diff --git a/include/linux/firewire.h b/include/linux/firewire.h index 07967a450eaa..980019053e54 100644 --- a/include/linux/firewire.h +++ b/include/linux/firewire.h @@ -150,6 +150,8 @@ static inline void fw_card_put(struct fw_card *card) kref_put(&card->kref, fw_card_release); } +int fw_card_read_cycle_time(struct fw_card *card, u32 *cycle_time); + struct fw_attribute_group { struct attribute_group *groups[2]; struct attribute_group group; @@ -352,6 +354,7 @@ void fw_core_remove_address_handler(struct fw_address_handler *handler); void fw_send_response(struct fw_card *card, struct fw_request *request, int rcode); int fw_get_request_speed(struct fw_request *request); +u32 fw_request_get_timestamp(const struct fw_request *request); void fw_send_request(struct fw_card *card, struct fw_transaction *t, int tcode, int destination_id, int generation, int speed, unsigned long long offset, void *payload, size_t length, diff --git a/include/linux/firmware.h b/include/linux/firmware.h index 3b057dfc8284..de7fea3bca51 100644 --- a/include/linux/firmware.h +++ b/include/linux/firmware.h @@ -17,6 +17,64 @@ struct firmware { void *priv; }; +/** + * enum fw_upload_err - firmware upload error codes + * @FW_UPLOAD_ERR_NONE: returned to indicate success + * @FW_UPLOAD_ERR_HW_ERROR: error signalled by hardware, see kernel log + * @FW_UPLOAD_ERR_TIMEOUT: SW timed out on handshake with HW/firmware + * @FW_UPLOAD_ERR_CANCELED: upload was cancelled by the user + * @FW_UPLOAD_ERR_BUSY: there is an upload operation already in progress + * @FW_UPLOAD_ERR_INVALID_SIZE: invalid firmware image size + * @FW_UPLOAD_ERR_RW_ERROR: read or write to HW failed, see kernel log + * @FW_UPLOAD_ERR_WEAROUT: FLASH device is approaching wear-out, wait & retry + * @FW_UPLOAD_ERR_MAX: Maximum error code marker + */ +enum fw_upload_err { + FW_UPLOAD_ERR_NONE, + FW_UPLOAD_ERR_HW_ERROR, + FW_UPLOAD_ERR_TIMEOUT, + FW_UPLOAD_ERR_CANCELED, + FW_UPLOAD_ERR_BUSY, + FW_UPLOAD_ERR_INVALID_SIZE, + FW_UPLOAD_ERR_RW_ERROR, + FW_UPLOAD_ERR_WEAROUT, + FW_UPLOAD_ERR_MAX +}; + +struct fw_upload { + void *dd_handle; /* reference to parent driver */ + void *priv; /* firmware loader private fields */ +}; + +/** + * struct fw_upload_ops - device specific operations to support firmware upload + * @prepare: Required: Prepare secure update + * @write: Required: The write() op receives the remaining + * size to be written and must return the actual + * size written or a negative error code. The write() + * op will be called repeatedly until all data is + * written. + * @poll_complete: Required: Check for the completion of the + * HW authentication/programming process. + * @cancel: Required: Request cancellation of update. This op + * is called from the context of a different kernel + * thread, so race conditions need to be considered. + * @cleanup: Optional: Complements the prepare() + * function and is called at the completion + * of the update, on success or failure, if the + * prepare function succeeded. + */ +struct fw_upload_ops { + enum fw_upload_err (*prepare)(struct fw_upload *fw_upload, + const u8 *data, u32 size); + enum fw_upload_err (*write)(struct fw_upload *fw_upload, + const u8 *data, u32 offset, + u32 size, u32 *written); + enum fw_upload_err (*poll_complete)(struct fw_upload *fw_upload); + void (*cancel)(struct fw_upload *fw_upload); + void (*cleanup)(struct fw_upload *fw_upload); +}; + struct module; struct device; @@ -34,7 +92,7 @@ static inline bool firmware_request_builtin(struct firmware *fw, } #endif -#if defined(CONFIG_FW_LOADER) || (defined(CONFIG_FW_LOADER_MODULE) && defined(MODULE)) +#if IS_REACHABLE(CONFIG_FW_LOADER) int request_firmware(const struct firmware **fw, const char *name, struct device *device); int firmware_request_nowarn(const struct firmware **fw, const char *name, @@ -112,6 +170,30 @@ static inline int request_partial_firmware_into_buf #endif +#ifdef CONFIG_FW_UPLOAD + +struct fw_upload * +firmware_upload_register(struct module *module, struct device *parent, + const char *name, const struct fw_upload_ops *ops, + void *dd_handle); +void firmware_upload_unregister(struct fw_upload *fw_upload); + +#else + +static inline struct fw_upload * +firmware_upload_register(struct module *module, struct device *parent, + const char *name, const struct fw_upload_ops *ops, + void *dd_handle) +{ + return ERR_PTR(-EINVAL); +} + +static inline void firmware_upload_unregister(struct fw_upload *fw_upload) +{ +} + +#endif + int firmware_request_cache(struct device *device, const char *name); #endif diff --git a/include/linux/firmware/cirrus/cs_dsp.h b/include/linux/firmware/cirrus/cs_dsp.h index 9ad9eaaaa552..cad828e21c72 100644 --- a/include/linux/firmware/cirrus/cs_dsp.h +++ b/include/linux/firmware/cirrus/cs_dsp.h @@ -11,6 +11,12 @@ #ifndef __CS_DSP_H #define __CS_DSP_H +#include <linux/bits.h> +#include <linux/device.h> +#include <linux/firmware.h> +#include <linux/list.h> +#include <linux/regmap.h> + #define CS_ADSP2_REGION_0 BIT(0) #define CS_ADSP2_REGION_1 BIT(1) #define CS_ADSP2_REGION_2 BIT(2) @@ -29,6 +35,7 @@ #define CS_ADSP2_REGION_ALL (CS_ADSP2_REGION_0 | CS_ADSP2_REGION_1_9) #define CS_DSP_DATA_WORD_SIZE 3 +#define CS_DSP_DATA_WORD_BITS (3 * BITS_PER_BYTE) #define CS_DSP_ACKED_CTL_TIMEOUT_MS 100 #define CS_DSP_ACKED_CTL_N_QUICKPOLLS 10 @@ -49,48 +56,50 @@ struct cs_dsp_region { * struct cs_dsp_alg_region - Describes a logical algorithm region in DSP address space * @list: List node for internal use * @alg: Algorithm id + * @ver: Expected algorithm version * @type: Memory region type * @base: Address of region */ struct cs_dsp_alg_region { struct list_head list; unsigned int alg; + unsigned int ver; int type; unsigned int base; }; /** * struct cs_dsp_coeff_ctl - Describes a coefficient control + * @list: List node for internal use + * @dsp: DSP instance associated with this control + * @cache: Cached value of the control * @fw_name: Name of the firmware * @subname: Name of the control parsed from the WMFW * @subname_len: Length of subname - * @alg_region: Logical region associated with this control - * @dsp: DSP instance associated with this control - * @enabled: Flag indicating whether control is enabled - * @list: List node for internal use - * @cache: Cached value of the control - * @offset: Offset of control within alg_region - * @len: Length of the cached value - * @set: Flag indicating the value has been written by the user - * @flags: Bitfield of WMFW_CTL_FLAG_ control flags defined in wmfw.h + * @offset: Offset of control within alg_region in words + * @len: Length of the cached value in bytes * @type: One of the WMFW_CTL_TYPE_ control types defined in wmfw.h + * @flags: Bitfield of WMFW_CTL_FLAG_ control flags defined in wmfw.h + * @set: Flag indicating the value has been written by the user + * @enabled: Flag indicating whether control is enabled + * @alg_region: Logical region associated with this control * @priv: For use by the client */ struct cs_dsp_coeff_ctl { + struct list_head list; + struct cs_dsp *dsp; + void *cache; const char *fw_name; /* Subname is needed to match with firmware */ const char *subname; unsigned int subname_len; - struct cs_dsp_alg_region alg_region; - struct cs_dsp *dsp; - unsigned int enabled:1; - struct list_head list; - void *cache; unsigned int offset; size_t len; - unsigned int set:1; - unsigned int flags; unsigned int type; + unsigned int flags; + unsigned int set:1; + unsigned int enabled:1; + struct cs_dsp_alg_region alg_region; void *priv; }; @@ -180,8 +189,10 @@ struct cs_dsp { * struct cs_dsp_client_ops - client callbacks * @control_add: Called under the pwr_lock when a control is created * @control_remove: Called under the pwr_lock when a control is destroyed - * @post_run: Called under the pwr_lock by cs_dsp_run() - * @post_stop: Called under the pwr_lock by cs_dsp_stop() + * @pre_run: Called under the pwr_lock by cs_dsp_run() before the core is started + * @post_run: Called under the pwr_lock by cs_dsp_run() after the core is started + * @pre_stop: Called under the pwr_lock by cs_dsp_stop() before the core is stopped + * @post_stop: Called under the pwr_lock by cs_dsp_stop() after the core is stopped * @watchdog_expired: Called when a watchdog expiry is detected * * These callbacks give the cs_dsp client an opportunity to respond to events @@ -190,7 +201,9 @@ struct cs_dsp { struct cs_dsp_client_ops { int (*control_add)(struct cs_dsp_coeff_ctl *ctl); void (*control_remove)(struct cs_dsp_coeff_ctl *ctl); + int (*pre_run)(struct cs_dsp *dsp); int (*post_run)(struct cs_dsp *dsp); + void (*pre_stop)(struct cs_dsp *dsp); void (*post_stop)(struct cs_dsp *dsp); void (*watchdog_expired)(struct cs_dsp *dsp); }; @@ -223,8 +236,10 @@ void cs_dsp_init_debugfs(struct cs_dsp *dsp, struct dentry *debugfs_root); void cs_dsp_cleanup_debugfs(struct cs_dsp *dsp); int cs_dsp_coeff_write_acked_control(struct cs_dsp_coeff_ctl *ctl, unsigned int event_id); -int cs_dsp_coeff_write_ctrl(struct cs_dsp_coeff_ctl *ctl, const void *buf, size_t len); -int cs_dsp_coeff_read_ctrl(struct cs_dsp_coeff_ctl *ctl, void *buf, size_t len); +int cs_dsp_coeff_write_ctrl(struct cs_dsp_coeff_ctl *ctl, unsigned int off, + const void *buf, size_t len); +int cs_dsp_coeff_read_ctrl(struct cs_dsp_coeff_ctl *ctl, unsigned int off, + void *buf, size_t len); struct cs_dsp_coeff_ctl *cs_dsp_get_ctl(struct cs_dsp *dsp, const char *name, int type, unsigned int alg); @@ -239,4 +254,75 @@ struct cs_dsp_alg_region *cs_dsp_find_alg_region(struct cs_dsp *dsp, const char *cs_dsp_mem_region_name(unsigned int type); +/** + * struct cs_dsp_chunk - Describes a buffer holding data formatted for the DSP + * @data: Pointer to underlying buffer memory + * @max: Pointer to end of the buffer memory + * @bytes: Number of bytes read/written into the memory chunk + * @cache: Temporary holding data as it is formatted + * @cachebits: Number of bits of data currently in cache + */ +struct cs_dsp_chunk { + u8 *data; + u8 *max; + int bytes; + + u32 cache; + int cachebits; +}; + +/** + * cs_dsp_chunk() - Create a DSP memory chunk + * @data: Pointer to the buffer that will be used to store data + * @size: Size of the buffer in bytes + * + * Return: A cs_dsp_chunk structure + */ +static inline struct cs_dsp_chunk cs_dsp_chunk(void *data, int size) +{ + struct cs_dsp_chunk ch = { + .data = data, + .max = data + size, + }; + + return ch; +} + +/** + * cs_dsp_chunk_end() - Check if a DSP memory chunk is full + * @ch: Pointer to the chunk structure + * + * Return: True if the whole buffer has been read/written + */ +static inline bool cs_dsp_chunk_end(struct cs_dsp_chunk *ch) +{ + return ch->data == ch->max; +} + +/** + * cs_dsp_chunk_bytes() - Number of bytes written/read from a DSP memory chunk + * @ch: Pointer to the chunk structure + * + * Return: Number of bytes read/written to the buffer + */ +static inline int cs_dsp_chunk_bytes(struct cs_dsp_chunk *ch) +{ + return ch->bytes; +} + +/** + * cs_dsp_chunk_valid_addr() - Check if an address is in a DSP memory chunk + * @ch: Pointer to the chunk structure + * + * Return: True if the given address is within the buffer + */ +static inline bool cs_dsp_chunk_valid_addr(struct cs_dsp_chunk *ch, void *addr) +{ + return (u8 *)addr >= ch->data && (u8 *)addr < ch->max; +} + +int cs_dsp_chunk_write(struct cs_dsp_chunk *ch, int nbits, u32 val); +int cs_dsp_chunk_flush(struct cs_dsp_chunk *ch); +int cs_dsp_chunk_read(struct cs_dsp_chunk *ch, int nbits); + #endif diff --git a/include/linux/firmware/cirrus/wmfw.h b/include/linux/firmware/cirrus/wmfw.h index a19bf7c6fc8b..74e5a4f6c13a 100644 --- a/include/linux/firmware/cirrus/wmfw.h +++ b/include/linux/firmware/cirrus/wmfw.h @@ -29,6 +29,7 @@ #define WMFW_CTL_TYPE_ACKED 0x1000 /* acked control */ #define WMFW_CTL_TYPE_HOSTEVENT 0x1001 /* event control */ #define WMFW_CTL_TYPE_HOST_BUFFER 0x1002 /* host buffer pointer */ +#define WMFW_CTL_TYPE_FWEVENT 0x1004 /* firmware event control */ struct wmfw_header { char magic[4]; diff --git a/include/linux/firmware/imx/svc/rm.h b/include/linux/firmware/imx/svc/rm.h index 456b6a59d29b..31456f897aa9 100644 --- a/include/linux/firmware/imx/svc/rm.h +++ b/include/linux/firmware/imx/svc/rm.h @@ -59,11 +59,16 @@ enum imx_sc_rm_func { #if IS_ENABLED(CONFIG_IMX_SCU) bool imx_sc_rm_is_resource_owned(struct imx_sc_ipc *ipc, u16 resource); +int imx_sc_rm_get_resource_owner(struct imx_sc_ipc *ipc, u16 resource, u8 *pt); #else static inline bool imx_sc_rm_is_resource_owned(struct imx_sc_ipc *ipc, u16 resource) { return true; } +static inline int imx_sc_rm_get_resource_owner(struct imx_sc_ipc *ipc, u16 resource, u8 *pt) +{ + return -EOPNOTSUPP; +} #endif #endif diff --git a/include/linux/firmware/intel/stratix10-smc.h b/include/linux/firmware/intel/stratix10-smc.h index c3e5ab014caf..a718f853d457 100644 --- a/include/linux/firmware/intel/stratix10-smc.h +++ b/include/linux/firmware/intel/stratix10-smc.h @@ -321,8 +321,6 @@ INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_FPGA_CONFIG_COMPLETED_WRITE) #define INTEL_SIP_SMC_ECC_DBE \ INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_ECC_DBE) -#endif - /** * Request INTEL_SIP_SMC_RSU_NOTIFY * @@ -404,3 +402,197 @@ INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_FPGA_CONFIG_COMPLETED_WRITE) #define INTEL_SIP_SMC_FUNCID_RSU_MAX_RETRY 18 #define INTEL_SIP_SMC_RSU_MAX_RETRY \ INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_RSU_MAX_RETRY) + +/** + * Request INTEL_SIP_SMC_RSU_DCMF_STATUS + * + * Sync call used by service driver at EL1 to query DCMF status from FW + * + * Call register usage: + * a0 INTEL_SIP_SMC_RSU_DCMF_STATUS + * a1-7 not used + * + * Return status + * a0 INTEL_SIP_SMC_STATUS_OK + * a1 dcmf3 | dcmf2 | dcmf1 | dcmf0 + * + * Or + * + * a0 INTEL_SIP_SMC_RSU_ERROR + */ +#define INTEL_SIP_SMC_FUNCID_RSU_DCMF_STATUS 20 +#define INTEL_SIP_SMC_RSU_DCMF_STATUS \ + INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_RSU_DCMF_STATUS) + +/** + * Request INTEL_SIP_SMC_SERVICE_COMPLETED + * Sync call to check if the secure world have completed service request + * or not. + * + * Call register usage: + * a0: INTEL_SIP_SMC_SERVICE_COMPLETED + * a1: this register is optional. If used, it is the physical address for + * secure firmware to put output data + * a2: this register is optional. If used, it is the size of output data + * a3-a7: not used + * + * Return status: + * a0: INTEL_SIP_SMC_STATUS_OK, INTEL_SIP_SMC_STATUS_ERROR, + * INTEL_SIP_SMC_REJECTED or INTEL_SIP_SMC_STATUS_BUSY + * a1: mailbox error if a0 is INTEL_SIP_SMC_STATUS_ERROR + * a2: physical address containing the process info + * for FCS certificate -- the data contains the certificate status + * for FCS cryption -- the data contains the actual data size FW processes + * a3: output data size + */ +#define INTEL_SIP_SMC_FUNCID_SERVICE_COMPLETED 30 +#define INTEL_SIP_SMC_SERVICE_COMPLETED \ + INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_SERVICE_COMPLETED) + +/** + * Request INTEL_SIP_SMC_FIRMWARE_VERSION + * + * Sync call used to query the version of running firmware + * + * Call register usage: + * a0 INTEL_SIP_SMC_FIRMWARE_VERSION + * a1-a7 not used + * + * Return status: + * a0 INTEL_SIP_SMC_STATUS_OK or INTEL_SIP_SMC_STATUS_ERROR + * a1 running firmware version + */ +#define INTEL_SIP_SMC_FUNCID_FIRMWARE_VERSION 31 +#define INTEL_SIP_SMC_FIRMWARE_VERSION \ + INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_FIRMWARE_VERSION) + +/** + * Request INTEL_SIP_SMC_SVC_VERSION + * + * Sync call used to query the SIP SMC API Version + * + * Call register usage: + * a0 INTEL_SIP_SMC_SVC_VERSION + * a1-a7 not used + * + * Return status: + * a0 INTEL_SIP_SMC_STATUS_OK + * a1 Major + * a2 Minor + */ +#define INTEL_SIP_SMC_SVC_FUNCID_VERSION 512 +#define INTEL_SIP_SMC_SVC_VERSION \ + INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_SVC_FUNCID_VERSION) + +/** + * SMC call protocol for FPGA Crypto Service (FCS) + * FUNCID starts from 90 + */ + +/** + * Request INTEL_SIP_SMC_FCS_RANDOM_NUMBER + * + * Sync call used to query the random number generated by the firmware + * + * Call register usage: + * a0 INTEL_SIP_SMC_FCS_RANDOM_NUMBER + * a1 the physical address for firmware to write generated random data + * a2-a7 not used + * + * Return status: + * a0 INTEL_SIP_SMC_STATUS_OK, INTEL_SIP_SMC_FCS_ERROR or + * INTEL_SIP_SMC_FCS_REJECTED + * a1 mailbox error + * a2 the physical address of generated random number + * a3 size + */ +#define INTEL_SIP_SMC_FUNCID_FCS_RANDOM_NUMBER 90 +#define INTEL_SIP_SMC_FCS_RANDOM_NUMBER \ + INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_FCS_RANDOM_NUMBER) + +/** + * Request INTEL_SIP_SMC_FCS_CRYPTION + * Async call for data encryption and HMAC signature generation, or for + * data decryption and HMAC verification. + * + * Call INTEL_SIP_SMC_SERVICE_COMPLETED to get the output encrypted or + * decrypted data + * + * Call register usage: + * a0 INTEL_SIP_SMC_FCS_CRYPTION + * a1 cryption mode (1 for encryption and 0 for decryption) + * a2 physical address which stores to be encrypted or decrypted data + * a3 input data size + * a4 physical address which will hold the encrypted or decrypted output data + * a5 output data size + * a6-a7 not used + * + * Return status: + * a0 INTEL_SIP_SMC_STATUS_OK, INTEL_SIP_SMC_STATUS_ERROR or + * INTEL_SIP_SMC_STATUS_REJECTED + * a1-3 not used + */ +#define INTEL_SIP_SMC_FUNCID_FCS_CRYPTION 91 +#define INTEL_SIP_SMC_FCS_CRYPTION \ + INTEL_SIP_SMC_STD_CALL_VAL(INTEL_SIP_SMC_FUNCID_FCS_CRYPTION) + +/** + * Request INTEL_SIP_SMC_FCS_SERVICE_REQUEST + * Async call for authentication service of HPS software + * + * Call register usage: + * a0 INTEL_SIP_SMC_FCS_SERVICE_REQUEST + * a1 the physical address of data block + * a2 size of data block + * a3-a7 not used + * + * Return status: + * a0 INTEL_SIP_SMC_STATUS_OK, INTEL_SIP_SMC_ERROR or + * INTEL_SIP_SMC_REJECTED + * a1-a3 not used + */ +#define INTEL_SIP_SMC_FUNCID_FCS_SERVICE_REQUEST 92 +#define INTEL_SIP_SMC_FCS_SERVICE_REQUEST \ + INTEL_SIP_SMC_STD_CALL_VAL(INTEL_SIP_SMC_FUNCID_FCS_SERVICE_REQUEST) + +/** + * Request INTEL_SIP_SMC_FUNCID_FCS_SEND_CERTIFICATE + * Sync call to send a signed certificate + * + * Call register usage: + * a0 INTEL_SIP_SMC_FCS_SEND_CERTIFICATE + * a1 the physical address of CERTIFICATE block + * a2 size of data block + * a3-a7 not used + * + * Return status: + * a0 INTEL_SIP_SMC_STATUS_OK or INTEL_SIP_SMC_FCS_REJECTED + * a1-a3 not used + */ +#define INTEL_SIP_SMC_FUNCID_FCS_SEND_CERTIFICATE 93 +#define INTEL_SIP_SMC_FCS_SEND_CERTIFICATE \ + INTEL_SIP_SMC_STD_CALL_VAL(INTEL_SIP_SMC_FUNCID_FCS_SEND_CERTIFICATE) + +/** + * Request INTEL_SIP_SMC_FCS_GET_PROVISION_DATA + * Sync call to dump all the fuses and key hashes + * + * Call register usage: + * a0 INTEL_SIP_SMC_FCS_GET_PROVISION_DATA + * a1 the physical address for firmware to write structure of fuse and + * key hashes + * a2-a7 not used + * + * Return status: + * a0 INTEL_SIP_SMC_STATUS_OK, INTEL_SIP_SMC_FCS_ERROR or + * INTEL_SIP_SMC_FCS_REJECTED + * a1 mailbox error + * a2 physical address for the structure of fuse and key hashes + * a3 the size of structure + * + */ +#define INTEL_SIP_SMC_FUNCID_FCS_GET_PROVISION_DATA 94 +#define INTEL_SIP_SMC_FCS_GET_PROVISION_DATA \ + INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_FCS_GET_PROVISION_DATA) + +#endif diff --git a/include/linux/firmware/intel/stratix10-svc-client.h b/include/linux/firmware/intel/stratix10-svc-client.h index 19781b0f6429..0c16037fd08d 100644 --- a/include/linux/firmware/intel/stratix10-svc-client.h +++ b/include/linux/firmware/intel/stratix10-svc-client.h @@ -14,6 +14,7 @@ */ #define SVC_CLIENT_FPGA "fpga" #define SVC_CLIENT_RSU "rsu" +#define SVC_CLIENT_FCS "fcs" /* * Status of the sent command, in bit number @@ -49,6 +50,7 @@ #define SVC_STATUS_BUSY 4 #define SVC_STATUS_ERROR 5 #define SVC_STATUS_NO_SUPPORT 6 +#define SVC_STATUS_INVALID_PARAM 7 /* * Flag bit for COMMAND_RECONFIG @@ -66,6 +68,8 @@ #define SVC_RECONFIG_REQUEST_TIMEOUT_MS 300 #define SVC_RECONFIG_BUFFER_TIMEOUT_MS 720 #define SVC_RSU_REQUEST_TIMEOUT_MS 300 +#define SVC_FCS_REQUEST_TIMEOUT_MS 2000 +#define SVC_COMPLETED_TIMEOUT_MS 30000 struct stratix10_svc_chan; @@ -104,31 +108,80 @@ struct stratix10_svc_chan; * * @COMMAND_RSU_DCMF_VERSION: query firmware for the DCMF version, return status * is SVC_STATUS_OK or SVC_STATUS_ERROR + * + * @COMMAND_POLL_SERVICE_STATUS: poll if the service request is complete, + * return statis is SVC_STATUS_OK, SVC_STATUS_ERROR or SVC_STATUS_BUSY + * + * @COMMAND_FIRMWARE_VERSION: query running firmware version, return status + * is SVC_STATUS_OK or SVC_STATUS_ERROR + * + * @COMMAND_SMC_SVC_VERSION: Non-mailbox SMC SVC API Version, + * return status is SVC_STATUS_OK + * + * @COMMAND_RSU_DCMF_STATUS: query firmware for the DCMF status + * return status is SVC_STATUS_OK or SVC_STATUS_ERROR + * + * @COMMAND_FCS_REQUEST_SERVICE: request validation of image from firmware, + * return status is SVC_STATUS_OK, SVC_STATUS_INVALID_PARAM + * + * @COMMAND_FCS_SEND_CERTIFICATE: send a certificate, return status is + * SVC_STATUS_OK, SVC_STATUS_INVALID_PARAM, SVC_STATUS_ERROR + * + * @COMMAND_FCS_GET_PROVISION_DATA: read the provisioning data, return status is + * SVC_STATUS_OK, SVC_STATUS_INVALID_PARAM, SVC_STATUS_ERROR + * + * @COMMAND_FCS_DATA_ENCRYPTION: encrypt the data, return status is + * SVC_STATUS_OK, SVC_STATUS_INVALID_PARAM, SVC_STATUS_ERROR + * + * @COMMAND_FCS_DATA_DECRYPTION: decrypt the data, return status is + * SVC_STATUS_OK, SVC_STATUS_INVALID_PARAM, SVC_STATUS_ERROR + * + * @COMMAND_FCS_RANDOM_NUMBER_GEN: generate a random number, return status + * is SVC_STATUS_OK, SVC_STATUS_ERROR */ enum stratix10_svc_command_code { + /* for FPGA */ COMMAND_NOOP = 0, COMMAND_RECONFIG, COMMAND_RECONFIG_DATA_SUBMIT, COMMAND_RECONFIG_DATA_CLAIM, COMMAND_RECONFIG_STATUS, - COMMAND_RSU_STATUS, + /* for RSU */ + COMMAND_RSU_STATUS = 10, COMMAND_RSU_UPDATE, COMMAND_RSU_NOTIFY, COMMAND_RSU_RETRY, COMMAND_RSU_MAX_RETRY, COMMAND_RSU_DCMF_VERSION, + COMMAND_RSU_DCMF_STATUS, + COMMAND_FIRMWARE_VERSION, + /* for FCS */ + COMMAND_FCS_REQUEST_SERVICE = 20, + COMMAND_FCS_SEND_CERTIFICATE, + COMMAND_FCS_GET_PROVISION_DATA, + COMMAND_FCS_DATA_ENCRYPTION, + COMMAND_FCS_DATA_DECRYPTION, + COMMAND_FCS_RANDOM_NUMBER_GEN, + /* for general status poll */ + COMMAND_POLL_SERVICE_STATUS = 40, + /* Non-mailbox SMC Call */ + COMMAND_SMC_SVC_VERSION = 200, }; /** * struct stratix10_svc_client_msg - message sent by client to service * @payload: starting address of data need be processed - * @payload_length: data size in bytes + * @payload_length: to be processed data size in bytes + * @payload_output: starting address of processed data + * @payload_length_output: processed data size in bytes * @command: service command * @arg: args to be passed via registers and not physically mapped buffers */ struct stratix10_svc_client_msg { void *payload; size_t payload_length; + void *payload_output; + size_t payload_length_output; enum stratix10_svc_command_code command; u64 arg[3]; }; diff --git a/include/linux/firmware/mediatek/mtk-adsp-ipc.h b/include/linux/firmware/mediatek/mtk-adsp-ipc.h new file mode 100644 index 000000000000..28fd313340b8 --- /dev/null +++ b/include/linux/firmware/mediatek/mtk-adsp-ipc.h @@ -0,0 +1,65 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2022 MediaTek Inc. + */ + +#ifndef MTK_ADSP_IPC_H +#define MTK_ADSP_IPC_H + +#include <linux/device.h> +#include <linux/types.h> +#include <linux/mailbox_controller.h> +#include <linux/mailbox_client.h> + +#define MTK_ADSP_IPC_REQ 0 +#define MTK_ADSP_IPC_RSP 1 +#define MTK_ADSP_IPC_OP_REQ 0x1 +#define MTK_ADSP_IPC_OP_RSP 0x2 + +enum { + MTK_ADSP_MBOX_REPLY, + MTK_ADSP_MBOX_REQUEST, + MTK_ADSP_MBOX_NUM, +}; + +struct mtk_adsp_ipc; + +struct mtk_adsp_ipc_ops { + void (*handle_reply)(struct mtk_adsp_ipc *ipc); + void (*handle_request)(struct mtk_adsp_ipc *ipc); +}; + +struct mtk_adsp_chan { + struct mtk_adsp_ipc *ipc; + struct mbox_client cl; + struct mbox_chan *ch; + char *name; + int idx; +}; + +struct mtk_adsp_ipc { + struct mtk_adsp_chan chans[MTK_ADSP_MBOX_NUM]; + struct device *dev; + struct mtk_adsp_ipc_ops *ops; + void *private_data; +}; + +static inline void mtk_adsp_ipc_set_data(struct mtk_adsp_ipc *ipc, void *data) +{ + if (!ipc) + return; + + ipc->private_data = data; +} + +static inline void *mtk_adsp_ipc_get_data(struct mtk_adsp_ipc *ipc) +{ + if (!ipc) + return NULL; + + return ipc->private_data; +} + +int mtk_adsp_ipc_send(struct mtk_adsp_ipc *ipc, unsigned int idx, uint32_t op); + +#endif /* MTK_ADSP_IPC_H */ diff --git a/include/linux/firmware/trusted_foundations.h b/include/linux/firmware/trusted_foundations.h index be5984bda592..931b6c5c72df 100644 --- a/include/linux/firmware/trusted_foundations.h +++ b/include/linux/firmware/trusted_foundations.h @@ -71,12 +71,16 @@ static inline void register_trusted_foundations( static inline void of_register_trusted_foundations(void) { + struct device_node *np = of_find_compatible_node(NULL, NULL, "tlm,trusted-foundations"); + + if (!np) + return; + of_node_put(np); /* * If we find the target should enable TF but does not support it, * fail as the system won't be able to do much anyway */ - if (of_find_compatible_node(NULL, NULL, "tlm,trusted-foundations")) - register_trusted_foundations(NULL); + register_trusted_foundations(NULL); } static inline bool trusted_foundations_registered(void) diff --git a/include/linux/firmware/xlnx-event-manager.h b/include/linux/firmware/xlnx-event-manager.h new file mode 100644 index 000000000000..82e8254b0f80 --- /dev/null +++ b/include/linux/firmware/xlnx-event-manager.h @@ -0,0 +1,36 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _FIRMWARE_XLNX_EVENT_MANAGER_H_ +#define _FIRMWARE_XLNX_EVENT_MANAGER_H_ + +#include <linux/firmware/xlnx-zynqmp.h> + +#define CB_MAX_PAYLOAD_SIZE (4U) /*In payload maximum 32bytes */ + +/************************** Exported Function *****************************/ + +typedef void (*event_cb_func_t)(const u32 *payload, void *data); + +#if IS_REACHABLE(CONFIG_XLNX_EVENT_MANAGER) +int xlnx_register_event(const enum pm_api_cb_id cb_type, const u32 node_id, + const u32 event, const bool wake, + event_cb_func_t cb_fun, void *data); + +int xlnx_unregister_event(const enum pm_api_cb_id cb_type, const u32 node_id, + const u32 event, event_cb_func_t cb_fun, void *data); +#else +static inline int xlnx_register_event(const enum pm_api_cb_id cb_type, const u32 node_id, + const u32 event, const bool wake, + event_cb_func_t cb_fun, void *data) +{ + return -ENODEV; +} + +static inline int xlnx_unregister_event(const enum pm_api_cb_id cb_type, const u32 node_id, + const u32 event, event_cb_func_t cb_fun, void *data) +{ + return -ENODEV; +} +#endif + +#endif /* _FIRMWARE_XLNX_EVENT_MANAGER_H_ */ diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index 47fd4e52a423..76d2b3ebad84 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -2,7 +2,7 @@ /* * Xilinx Zynq MPSoC Firmware layer * - * Copyright (C) 2014-2019 Xilinx + * Copyright (C) 2014-2021 Xilinx * * Michal Simek <michal.simek@xilinx.com> * Davorin Mista <davorin.mista@aggios.com> @@ -29,6 +29,12 @@ /* SMC SIP service Call Function Identifier Prefix */ #define PM_SIP_SVC 0xC2000000 + +/* PM API versions */ +#define PM_API_VERSION_2 2 + +/* ATF only commands */ +#define TF_A_PM_REGISTER_SGI 0xa04 #define PM_GET_TRUSTZONE_VERSION 0xa03 #define PM_SET_SUSPEND_MODE 0xa02 #define GET_CALLBACK_DATA 0xa01 @@ -64,8 +70,23 @@ #define XILINX_ZYNQMP_PM_FPGA_FULL 0x0U #define XILINX_ZYNQMP_PM_FPGA_PARTIAL BIT(0) +/* + * Node IDs for the Error Events. + */ +#define EVENT_ERROR_PMC_ERR1 (0x28100000U) +#define EVENT_ERROR_PMC_ERR2 (0x28104000U) +#define EVENT_ERROR_PSM_ERR1 (0x28108000U) +#define EVENT_ERROR_PSM_ERR2 (0x2810C000U) + +enum pm_api_cb_id { + PM_INIT_SUSPEND_CB = 30, + PM_ACKNOWLEDGE_CB = 31, + PM_NOTIFY_CB = 32, +}; + enum pm_api_id { PM_GET_API_VERSION = 1, + PM_REGISTER_NOTIFIER = 5, PM_SYSTEM_SHUTDOWN = 12, PM_REQUEST_NODE = 13, PM_RELEASE_NODE = 14, @@ -78,6 +99,7 @@ enum pm_api_id { PM_FPGA_LOAD = 22, PM_FPGA_GET_STATUS = 23, PM_GET_CHIPID = 24, + PM_SECURE_SHA = 26, PM_PINCTRL_REQUEST = 28, PM_PINCTRL_RELEASE = 29, PM_PINCTRL_GET_FUNCTION = 30, @@ -126,6 +148,14 @@ enum pm_ioctl_id { /* Set healthy bit value */ IOCTL_SET_BOOT_HEALTH_STATUS = 17, IOCTL_OSPI_MUX_SELECT = 21, + /* Register SGI to ATF */ + IOCTL_REGISTER_SGI = 25, + /* Runtime feature configuration */ + IOCTL_SET_FEATURE_CONFIG = 26, + IOCTL_GET_FEATURE_CONFIG = 27, + /* Dynamic SD/GEM configuration */ + IOCTL_SET_SD_CONFIG = 30, + IOCTL_SET_GEM_CONFIG = 31, }; enum pm_query_id { @@ -342,6 +372,11 @@ enum pm_pinctrl_drive_strength { PM_PINCTRL_DRIVE_STRENGTH_12MA = 3, }; +enum pm_pinctrl_tri_state { + PM_PINCTRL_TRI_STATE_DISABLE = 0, + PM_PINCTRL_TRI_STATE_ENABLE = 1, +}; + enum zynqmp_pm_shutdown_type { ZYNQMP_PM_SHUTDOWN_TYPE_SHUTDOWN = 0, ZYNQMP_PM_SHUTDOWN_TYPE_RESET = 1, @@ -359,6 +394,38 @@ enum ospi_mux_select_type { PM_OSPI_MUX_SEL_LINEAR = 1, }; +enum pm_feature_config_id { + PM_FEATURE_INVALID = 0, + PM_FEATURE_OVERTEMP_STATUS = 1, + PM_FEATURE_OVERTEMP_VALUE = 2, + PM_FEATURE_EXTWDT_STATUS = 3, + PM_FEATURE_EXTWDT_VALUE = 4, +}; + +/** + * enum pm_sd_config_type - PM SD configuration. + * @SD_CONFIG_EMMC_SEL: To set SD_EMMC_SEL in CTRL_REG_SD and SD_SLOTTYPE + * @SD_CONFIG_BASECLK: To set SD_BASECLK in SD_CONFIG_REG1 + * @SD_CONFIG_8BIT: To set SD_8BIT in SD_CONFIG_REG2 + * @SD_CONFIG_FIXED: To set fixed config registers + */ +enum pm_sd_config_type { + SD_CONFIG_EMMC_SEL = 1, + SD_CONFIG_BASECLK = 2, + SD_CONFIG_8BIT = 3, + SD_CONFIG_FIXED = 4, +}; + +/** + * enum pm_gem_config_type - PM GEM configuration. + * @GEM_CONFIG_SGMII_MODE: To set GEM_SGMII_MODE in GEM_CLK_CTRL register + * @GEM_CONFIG_FIXED: To set fixed config registers + */ +enum pm_gem_config_type { + GEM_CONFIG_SGMII_MODE = 1, + GEM_CONFIG_FIXED = 2, +}; + /** * struct zynqmp_pm_query_data - PM query data * @qid: query ID @@ -410,6 +477,7 @@ int zynqmp_pm_set_requirement(const u32 node, const u32 capabilities, const u32 qos, const enum zynqmp_pm_request_ack ack); int zynqmp_pm_aes_engine(const u64 address, u32 *out); +int zynqmp_pm_sha_hash(const u64 address, const u32 size, const u32 flags); int zynqmp_pm_fpga_load(const u64 address, const u32 size, const u32 flags); int zynqmp_pm_fpga_get_status(u32 *value); int zynqmp_pm_write_ggs(u32 index, u32 value); @@ -427,6 +495,16 @@ int zynqmp_pm_pinctrl_get_config(const u32 pin, const u32 param, int zynqmp_pm_pinctrl_set_config(const u32 pin, const u32 param, u32 value); int zynqmp_pm_load_pdi(const u32 src, const u64 address); +int zynqmp_pm_register_notifier(const u32 node, const u32 event, + const u32 wake, const u32 enable); +int zynqmp_pm_feature(const u32 api_id); +int zynqmp_pm_is_function_supported(const u32 api_id, const u32 id); +int zynqmp_pm_set_feature_config(enum pm_feature_config_id id, u32 value); +int zynqmp_pm_get_feature_config(enum pm_feature_config_id id, u32 *payload); +int zynqmp_pm_register_sgi(u32 sgi_num, u32 reset); +int zynqmp_pm_set_sd_config(u32 node, enum pm_sd_config_type config, u32 value); +int zynqmp_pm_set_gem_config(u32 node, enum pm_gem_config_type config, + u32 value); #else static inline int zynqmp_pm_get_api_version(u32 *version) { @@ -581,6 +659,12 @@ static inline int zynqmp_pm_aes_engine(const u64 address, u32 *out) return -ENODEV; } +static inline int zynqmp_pm_sha_hash(const u64 address, const u32 size, + const u32 flags) +{ + return -ENODEV; +} + static inline int zynqmp_pm_fpga_load(const u64 address, const u32 size, const u32 flags) { @@ -637,6 +721,11 @@ static inline int zynqmp_pm_pinctrl_get_function(const u32 pin, u32 *id) return -ENODEV; } +static inline int zynqmp_pm_is_function_supported(const u32 api_id, const u32 id) +{ + return -ENODEV; +} + static inline int zynqmp_pm_pinctrl_set_function(const u32 pin, const u32 id) { return -ENODEV; @@ -658,6 +747,49 @@ static inline int zynqmp_pm_load_pdi(const u32 src, const u64 address) { return -ENODEV; } + +static inline int zynqmp_pm_register_notifier(const u32 node, const u32 event, + const u32 wake, const u32 enable) +{ + return -ENODEV; +} + +static inline int zynqmp_pm_feature(const u32 api_id) +{ + return -ENODEV; +} + +static inline int zynqmp_pm_set_feature_config(enum pm_feature_config_id id, + u32 value) +{ + return -ENODEV; +} + +static inline int zynqmp_pm_get_feature_config(enum pm_feature_config_id id, + u32 *payload) +{ + return -ENODEV; +} + +static inline int zynqmp_pm_register_sgi(u32 sgi_num, u32 reset) +{ + return -ENODEV; +} + +static inline int zynqmp_pm_set_sd_config(u32 node, + enum pm_sd_config_type config, + u32 value) +{ + return -ENODEV; +} + +static inline int zynqmp_pm_set_gem_config(u32 node, + enum pm_gem_config_type config, + u32 value) +{ + return -ENODEV; +} + #endif #endif /* __FIRMWARE_ZYNQMP_H__ */ diff --git a/include/linux/fortify-string.h b/include/linux/fortify-string.h index a6cd6815f249..1067a8450826 100644 --- a/include/linux/fortify-string.h +++ b/include/linux/fortify-string.h @@ -2,20 +2,27 @@ #ifndef _LINUX_FORTIFY_STRING_H_ #define _LINUX_FORTIFY_STRING_H_ -#define __FORTIFY_INLINE extern __always_inline __attribute__((gnu_inline)) +#include <linux/bug.h> +#include <linux/const.h> +#include <linux/limits.h> + +#define __FORTIFY_INLINE extern __always_inline __gnu_inline __overloadable #define __RENAME(x) __asm__(#x) void fortify_panic(const char *name) __noreturn __cold; void __read_overflow(void) __compiletime_error("detected read beyond size of object (1st parameter)"); void __read_overflow2(void) __compiletime_error("detected read beyond size of object (2nd parameter)"); +void __read_overflow2_field(size_t avail, size_t wanted) __compiletime_warning("detected read beyond size of field (2nd parameter); maybe use struct_group()?"); void __write_overflow(void) __compiletime_error("detected write beyond size of object (1st parameter)"); +void __write_overflow_field(size_t avail, size_t wanted) __compiletime_warning("detected write beyond size of field (1st parameter); maybe use struct_group()?"); #define __compiletime_strlen(p) \ ({ \ unsigned char *__p = (unsigned char *)(p); \ - size_t __ret = (size_t)-1; \ - size_t __p_size = __builtin_object_size(p, 1); \ - if (__p_size != (size_t)-1) { \ + size_t __ret = SIZE_MAX; \ + size_t __p_size = __member_size(p); \ + if (__p_size != SIZE_MAX && \ + __builtin_constant_p(*__p)) { \ size_t __p_len = __p_size - 1; \ if (__builtin_constant_p(__p[__p_len]) && \ __p[__p_len] == '\0') \ @@ -36,11 +43,24 @@ extern __kernel_size_t __underlying_strlen(const char *p) __RENAME(strlen); extern char *__underlying_strncat(char *p, const char *q, __kernel_size_t count) __RENAME(strncat); extern char *__underlying_strncpy(char *p, const char *q, __kernel_size_t size) __RENAME(strncpy); #else -#define __underlying_memchr __builtin_memchr -#define __underlying_memcmp __builtin_memcmp + +#if defined(__SANITIZE_MEMORY__) +/* + * For KMSAN builds all memcpy/memset/memmove calls should be replaced by the + * corresponding __msan_XXX functions. + */ +#include <linux/kmsan_string.h> +#define __underlying_memcpy __msan_memcpy +#define __underlying_memmove __msan_memmove +#define __underlying_memset __msan_memset +#else #define __underlying_memcpy __builtin_memcpy #define __underlying_memmove __builtin_memmove #define __underlying_memset __builtin_memset +#endif + +#define __underlying_memchr __builtin_memchr +#define __underlying_memcmp __builtin_memcmp #define __underlying_strcat __builtin_strcat #define __underlying_strcpy __builtin_strcpy #define __underlying_strlen __builtin_strlen @@ -48,22 +68,88 @@ extern char *__underlying_strncpy(char *p, const char *q, __kernel_size_t size) #define __underlying_strncpy __builtin_strncpy #endif -__FORTIFY_INLINE char *strncpy(char *p, const char *q, __kernel_size_t size) +/** + * unsafe_memcpy - memcpy implementation with no FORTIFY bounds checking + * + * @dst: Destination memory address to write to + * @src: Source memory address to read from + * @bytes: How many bytes to write to @dst from @src + * @justification: Free-form text or comment describing why the use is needed + * + * This should be used for corner cases where the compiler cannot do the + * right thing, or during transitions between APIs, etc. It should be used + * very rarely, and includes a place for justification detailing where bounds + * checking has happened, and why existing solutions cannot be employed. + */ +#define unsafe_memcpy(dst, src, bytes, justification) \ + __underlying_memcpy(dst, src, bytes) + +/* + * Clang's use of __builtin_*object_size() within inlines needs hinting via + * __pass_*object_size(). The preference is to only ever use type 1 (member + * size, rather than struct size), but there remain some stragglers using + * type 0 that will be converted in the future. + */ +#define POS __pass_object_size(1) +#define POS0 __pass_object_size(0) +#define __struct_size(p) __builtin_object_size(p, 0) +#define __member_size(p) __builtin_object_size(p, 1) + +#define __compiletime_lessthan(bounds, length) ( \ + __builtin_constant_p((bounds) < (length)) && \ + (bounds) < (length) \ +) + +/** + * strncpy - Copy a string to memory with non-guaranteed NUL padding + * + * @p: pointer to destination of copy + * @q: pointer to NUL-terminated source string to copy + * @size: bytes to write at @p + * + * If strlen(@q) >= @size, the copy of @q will stop after @size bytes, + * and @p will NOT be NUL-terminated + * + * If strlen(@q) < @size, following the copy of @q, trailing NUL bytes + * will be written to @p until @size total bytes have been written. + * + * Do not use this function. While FORTIFY_SOURCE tries to avoid + * over-reads of @q, it cannot defend against writing unterminated + * results to @p. Using strncpy() remains ambiguous and fragile. + * Instead, please choose an alternative, so that the expectation + * of @p's contents is unambiguous: + * + * +--------------------+-----------------+------------+ + * | @p needs to be: | padded to @size | not padded | + * +====================+=================+============+ + * | NUL-terminated | strscpy_pad() | strscpy() | + * +--------------------+-----------------+------------+ + * | not NUL-terminated | strtomem_pad() | strtomem() | + * +--------------------+-----------------+------------+ + * + * Note strscpy*()'s differing return values for detecting truncation, + * and strtomem*()'s expectation that the destination is marked with + * __nonstring when it is a character array. + * + */ +__FORTIFY_INLINE __diagnose_as(__builtin_strncpy, 1, 2, 3) +char *strncpy(char * const POS p, const char *q, __kernel_size_t size) { - size_t p_size = __builtin_object_size(p, 1); + size_t p_size = __member_size(p); - if (__builtin_constant_p(size) && p_size < size) + if (__compiletime_lessthan(p_size, size)) __write_overflow(); if (p_size < size) fortify_panic(__func__); return __underlying_strncpy(p, q, size); } -__FORTIFY_INLINE char *strcat(char *p, const char *q) +__FORTIFY_INLINE __diagnose_as(__builtin_strcat, 1, 2) +char *strcat(char * const POS p, const char *q) { - size_t p_size = __builtin_object_size(p, 1); + size_t p_size = __member_size(p); - if (p_size == (size_t)-1) + if (p_size == SIZE_MAX) return __underlying_strcat(p, q); if (strlcat(p, q, p_size) >= p_size) fortify_panic(__func__); @@ -71,14 +157,14 @@ __FORTIFY_INLINE char *strcat(char *p, const char *q) } extern __kernel_size_t __real_strnlen(const char *, __kernel_size_t) __RENAME(strnlen); -__FORTIFY_INLINE __kernel_size_t strnlen(const char *p, __kernel_size_t maxlen) +__FORTIFY_INLINE __kernel_size_t strnlen(const char * const POS p, __kernel_size_t maxlen) { - size_t p_size = __builtin_object_size(p, 1); + size_t p_size = __member_size(p); size_t p_len = __compiletime_strlen(p); size_t ret; /* We can take compile-time actions when maxlen is const. */ - if (__builtin_constant_p(maxlen) && p_len != (size_t)-1) { + if (__builtin_constant_p(maxlen) && p_len != SIZE_MAX) { /* If p is const, we can use its compile-time-known len. */ if (maxlen >= p_size) return p_len; @@ -91,14 +177,22 @@ __FORTIFY_INLINE __kernel_size_t strnlen(const char *p, __kernel_size_t maxlen) return ret; } -/* defined after fortified strnlen to reuse it. */ -__FORTIFY_INLINE __kernel_size_t strlen(const char *p) +/* + * Defined after fortified strnlen to reuse it. However, it must still be + * possible for strlen() to be used on compile-time strings for use in + * static initializers (i.e. as a constant expression). + */ +#define strlen(p) \ + __builtin_choose_expr(__is_constexpr(__builtin_strlen(p)), \ + __builtin_strlen(p), __fortify_strlen(p)) +__FORTIFY_INLINE __diagnose_as(__builtin_strlen, 1) +__kernel_size_t __fortify_strlen(const char * const POS p) { __kernel_size_t ret; - size_t p_size = __builtin_object_size(p, 1); + size_t p_size = __member_size(p); /* Give up if we don't know how large p is. */ - if (p_size == (size_t)-1) + if (p_size == SIZE_MAX) return __underlying_strlen(p); ret = strnlen(p, p_size); if (p_size <= ret) @@ -108,14 +202,14 @@ __FORTIFY_INLINE __kernel_size_t strlen(const char *p) /* defined after fortified strlen to reuse it */ extern size_t __real_strlcpy(char *, const char *, size_t) __RENAME(strlcpy); -__FORTIFY_INLINE size_t strlcpy(char *p, const char *q, size_t size) +__FORTIFY_INLINE size_t strlcpy(char * const POS p, const char * const POS q, size_t size) { - size_t p_size = __builtin_object_size(p, 1); - size_t q_size = __builtin_object_size(q, 1); + size_t p_size = __member_size(p); + size_t q_size = __member_size(q); size_t q_len; /* Full count of source string length. */ size_t len; /* Count of characters going into destination. */ - if (p_size == (size_t)-1 && q_size == (size_t)-1) + if (p_size == SIZE_MAX && q_size == SIZE_MAX) return __real_strlcpy(p, q, size); q_len = strlen(q); len = (q_len >= size) ? size - 1 : q_len; @@ -135,22 +229,22 @@ __FORTIFY_INLINE size_t strlcpy(char *p, const char *q, size_t size) /* defined after fortified strnlen to reuse it */ extern ssize_t __real_strscpy(char *, const char *, size_t) __RENAME(strscpy); -__FORTIFY_INLINE ssize_t strscpy(char *p, const char *q, size_t size) +__FORTIFY_INLINE ssize_t strscpy(char * const POS p, const char * const POS q, size_t size) { size_t len; /* Use string size rather than possible enclosing struct size. */ - size_t p_size = __builtin_object_size(p, 1); - size_t q_size = __builtin_object_size(q, 1); + size_t p_size = __member_size(p); + size_t q_size = __member_size(q); /* If we cannot get size of p and q default to call strscpy. */ - if (p_size == (size_t) -1 && q_size == (size_t) -1) + if (p_size == SIZE_MAX && q_size == SIZE_MAX) return __real_strscpy(p, q, size); /* * If size can be known at compile time and is greater than * p_size, generate a compile time write overflow error. */ - if (__builtin_constant_p(size) && size > p_size) + if (__compiletime_lessthan(p_size, size)) __write_overflow(); /* @@ -181,13 +275,14 @@ __FORTIFY_INLINE ssize_t strscpy(char *p, const char *q, size_t size) } /* defined after fortified strlen and strnlen to reuse them */ -__FORTIFY_INLINE char *strncat(char *p, const char *q, __kernel_size_t count) +__FORTIFY_INLINE __diagnose_as(__builtin_strncat, 1, 2, 3) +char *strncat(char * const POS p, const char * const POS q, __kernel_size_t count) { size_t p_len, copy_len; - size_t p_size = __builtin_object_size(p, 1); - size_t q_size = __builtin_object_size(q, 1); + size_t p_size = __member_size(p); + size_t q_size = __member_size(q); - if (p_size == (size_t)-1 && q_size == (size_t)-1) + if (p_size == SIZE_MAX && q_size == SIZE_MAX) return __underlying_strncat(p, q, count); p_len = strlen(p); copy_len = strnlen(q, count); @@ -198,70 +293,255 @@ __FORTIFY_INLINE char *strncat(char *p, const char *q, __kernel_size_t count) return p; } -__FORTIFY_INLINE void *memset(void *p, int c, __kernel_size_t size) -{ - size_t p_size = __builtin_object_size(p, 0); - - if (__builtin_constant_p(size) && p_size < size) - __write_overflow(); - if (p_size < size) - fortify_panic(__func__); - return __underlying_memset(p, c, size); -} - -__FORTIFY_INLINE void *memcpy(void *p, const void *q, __kernel_size_t size) +__FORTIFY_INLINE void fortify_memset_chk(__kernel_size_t size, + const size_t p_size, + const size_t p_size_field) { - size_t p_size = __builtin_object_size(p, 0); - size_t q_size = __builtin_object_size(q, 0); - if (__builtin_constant_p(size)) { - if (p_size < size) + /* + * Length argument is a constant expression, so we + * can perform compile-time bounds checking where + * buffer sizes are also known at compile time. + */ + + /* Error when size is larger than enclosing struct. */ + if (__compiletime_lessthan(p_size_field, p_size) && + __compiletime_lessthan(p_size, size)) __write_overflow(); - if (q_size < size) - __read_overflow2(); + + /* Warn when write size is larger than dest field. */ + if (__compiletime_lessthan(p_size_field, size)) + __write_overflow_field(p_size_field, size); } - if (p_size < size || q_size < size) - fortify_panic(__func__); - return __underlying_memcpy(p, q, size); + /* + * At this point, length argument may not be a constant expression, + * so run-time bounds checking can be done where buffer sizes are + * known. (This is not an "else" because the above checks may only + * be compile-time warnings, and we want to still warn for run-time + * overflows.) + */ + + /* + * Always stop accesses beyond the struct that contains the + * field, when the buffer's remaining size is known. + * (The SIZE_MAX test is to optimize away checks where the buffer + * lengths are unknown.) + */ + if (p_size != SIZE_MAX && p_size < size) + fortify_panic("memset"); } -__FORTIFY_INLINE void *memmove(void *p, const void *q, __kernel_size_t size) -{ - size_t p_size = __builtin_object_size(p, 0); - size_t q_size = __builtin_object_size(q, 0); +#define __fortify_memset_chk(p, c, size, p_size, p_size_field) ({ \ + size_t __fortify_size = (size_t)(size); \ + fortify_memset_chk(__fortify_size, p_size, p_size_field), \ + __underlying_memset(p, c, __fortify_size); \ +}) + +/* + * __struct_size() vs __member_size() must be captured here to avoid + * evaluating argument side-effects further into the macro layers. + */ +#ifndef CONFIG_KMSAN +#define memset(p, c, s) __fortify_memset_chk(p, c, s, \ + __struct_size(p), __member_size(p)) +#endif +/* + * To make sure the compiler can enforce protection against buffer overflows, + * memcpy(), memmove(), and memset() must not be used beyond individual + * struct members. If you need to copy across multiple members, please use + * struct_group() to create a named mirror of an anonymous struct union. + * (e.g. see struct sk_buff.) Read overflow checking is currently only + * done when a write overflow is also present, or when building with W=1. + * + * Mitigation coverage matrix + * Bounds checking at: + * +-------+-------+-------+-------+ + * | Compile time | Run time | + * memcpy() argument sizes: | write | read | write | read | + * dest source length +-------+-------+-------+-------+ + * memcpy(known, known, constant) | y | y | n/a | n/a | + * memcpy(known, unknown, constant) | y | n | n/a | V | + * memcpy(known, known, dynamic) | n | n | B | B | + * memcpy(known, unknown, dynamic) | n | n | B | V | + * memcpy(unknown, known, constant) | n | y | V | n/a | + * memcpy(unknown, unknown, constant) | n | n | V | V | + * memcpy(unknown, known, dynamic) | n | n | V | B | + * memcpy(unknown, unknown, dynamic) | n | n | V | V | + * +-------+-------+-------+-------+ + * + * y = perform deterministic compile-time bounds checking + * n = cannot perform deterministic compile-time bounds checking + * n/a = no run-time bounds checking needed since compile-time deterministic + * B = can perform run-time bounds checking (currently unimplemented) + * V = vulnerable to run-time overflow (will need refactoring to solve) + * + */ +__FORTIFY_INLINE bool fortify_memcpy_chk(__kernel_size_t size, + const size_t p_size, + const size_t q_size, + const size_t p_size_field, + const size_t q_size_field, + const char *func) +{ if (__builtin_constant_p(size)) { - if (p_size < size) + /* + * Length argument is a constant expression, so we + * can perform compile-time bounds checking where + * buffer sizes are also known at compile time. + */ + + /* Error when size is larger than enclosing struct. */ + if (__compiletime_lessthan(p_size_field, p_size) && + __compiletime_lessthan(p_size, size)) __write_overflow(); - if (q_size < size) + if (__compiletime_lessthan(q_size_field, q_size) && + __compiletime_lessthan(q_size, size)) __read_overflow2(); + + /* Warn when write size argument larger than dest field. */ + if (__compiletime_lessthan(p_size_field, size)) + __write_overflow_field(p_size_field, size); + /* + * Warn for source field over-read when building with W=1 + * or when an over-write happened, so both can be fixed at + * the same time. + */ + if ((IS_ENABLED(KBUILD_EXTRA_WARN1) || + __compiletime_lessthan(p_size_field, size)) && + __compiletime_lessthan(q_size_field, size)) + __read_overflow2_field(q_size_field, size); } - if (p_size < size || q_size < size) - fortify_panic(__func__); - return __underlying_memmove(p, q, size); + /* + * At this point, length argument may not be a constant expression, + * so run-time bounds checking can be done where buffer sizes are + * known. (This is not an "else" because the above checks may only + * be compile-time warnings, and we want to still warn for run-time + * overflows.) + */ + + /* + * Always stop accesses beyond the struct that contains the + * field, when the buffer's remaining size is known. + * (The SIZE_MAX test is to optimize away checks where the buffer + * lengths are unknown.) + */ + if ((p_size != SIZE_MAX && p_size < size) || + (q_size != SIZE_MAX && q_size < size)) + fortify_panic(func); + + /* + * Warn when writing beyond destination field size. + * + * We must ignore p_size_field == 0 for existing 0-element + * fake flexible arrays, until they are all converted to + * proper flexible arrays. + * + * The implementation of __builtin_*object_size() behaves + * like sizeof() when not directly referencing a flexible + * array member, which means there will be many bounds checks + * that will appear at run-time, without a way for them to be + * detected at compile-time (as can be done when the destination + * is specifically the flexible array member). + * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=101832 + */ + if (p_size_field != 0 && p_size_field != SIZE_MAX && + p_size != p_size_field && p_size_field < size) + return true; + + return false; } +#define __fortify_memcpy_chk(p, q, size, p_size, q_size, \ + p_size_field, q_size_field, op) ({ \ + const size_t __fortify_size = (size_t)(size); \ + const size_t __p_size = (p_size); \ + const size_t __q_size = (q_size); \ + const size_t __p_size_field = (p_size_field); \ + const size_t __q_size_field = (q_size_field); \ + WARN_ONCE(fortify_memcpy_chk(__fortify_size, __p_size, \ + __q_size, __p_size_field, \ + __q_size_field, #op), \ + #op ": detected field-spanning write (size %zu) of single %s (size %zu)\n", \ + __fortify_size, \ + "field \"" #p "\" at " __FILE__ ":" __stringify(__LINE__), \ + __p_size_field); \ + __underlying_##op(p, q, __fortify_size); \ +}) + +/* + * Notes about compile-time buffer size detection: + * + * With these types... + * + * struct middle { + * u16 a; + * u8 middle_buf[16]; + * int b; + * }; + * struct end { + * u16 a; + * u8 end_buf[16]; + * }; + * struct flex { + * int a; + * u8 flex_buf[]; + * }; + * + * void func(TYPE *ptr) { ... } + * + * Cases where destination size cannot be currently detected: + * - the size of ptr's object (seemingly by design, gcc & clang fail): + * __builtin_object_size(ptr, 1) == SIZE_MAX + * - the size of flexible arrays in ptr's obj (by design, dynamic size): + * __builtin_object_size(ptr->flex_buf, 1) == SIZE_MAX + * - the size of ANY array at the end of ptr's obj (gcc and clang bug): + * __builtin_object_size(ptr->end_buf, 1) == SIZE_MAX + * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=101836 + * + * Cases where destination size is currently detected: + * - the size of non-array members within ptr's object: + * __builtin_object_size(ptr->a, 1) == 2 + * - the size of non-flexible-array in the middle of ptr's obj: + * __builtin_object_size(ptr->middle_buf, 1) == 16 + * + */ + +/* + * __struct_size() vs __member_size() must be captured here to avoid + * evaluating argument side-effects further into the macro layers. + */ +#define memcpy(p, q, s) __fortify_memcpy_chk(p, q, s, \ + __struct_size(p), __struct_size(q), \ + __member_size(p), __member_size(q), \ + memcpy) +#define memmove(p, q, s) __fortify_memcpy_chk(p, q, s, \ + __struct_size(p), __struct_size(q), \ + __member_size(p), __member_size(q), \ + memmove) + extern void *__real_memscan(void *, int, __kernel_size_t) __RENAME(memscan); -__FORTIFY_INLINE void *memscan(void *p, int c, __kernel_size_t size) +__FORTIFY_INLINE void *memscan(void * const POS0 p, int c, __kernel_size_t size) { - size_t p_size = __builtin_object_size(p, 0); + size_t p_size = __struct_size(p); - if (__builtin_constant_p(size) && p_size < size) + if (__compiletime_lessthan(p_size, size)) __read_overflow(); if (p_size < size) fortify_panic(__func__); return __real_memscan(p, c, size); } -__FORTIFY_INLINE int memcmp(const void *p, const void *q, __kernel_size_t size) +__FORTIFY_INLINE __diagnose_as(__builtin_memcmp, 1, 2, 3) +int memcmp(const void * const POS0 p, const void * const POS0 q, __kernel_size_t size) { - size_t p_size = __builtin_object_size(p, 0); - size_t q_size = __builtin_object_size(q, 0); + size_t p_size = __struct_size(p); + size_t q_size = __struct_size(q); if (__builtin_constant_p(size)) { - if (p_size < size) + if (__compiletime_lessthan(p_size, size)) __read_overflow(); - if (q_size < size) + if (__compiletime_lessthan(q_size, size)) __read_overflow2(); } if (p_size < size || q_size < size) @@ -269,11 +549,12 @@ __FORTIFY_INLINE int memcmp(const void *p, const void *q, __kernel_size_t size) return __underlying_memcmp(p, q, size); } -__FORTIFY_INLINE void *memchr(const void *p, int c, __kernel_size_t size) +__FORTIFY_INLINE __diagnose_as(__builtin_memchr, 1, 2, 3) +void *memchr(const void * const POS0 p, int c, __kernel_size_t size) { - size_t p_size = __builtin_object_size(p, 0); + size_t p_size = __struct_size(p); - if (__builtin_constant_p(size) && p_size < size) + if (__compiletime_lessthan(p_size, size)) __read_overflow(); if (p_size < size) fortify_panic(__func__); @@ -281,11 +562,11 @@ __FORTIFY_INLINE void *memchr(const void *p, int c, __kernel_size_t size) } void *__real_memchr_inv(const void *s, int c, size_t n) __RENAME(memchr_inv); -__FORTIFY_INLINE void *memchr_inv(const void *p, int c, size_t size) +__FORTIFY_INLINE void *memchr_inv(const void * const POS0 p, int c, size_t size) { - size_t p_size = __builtin_object_size(p, 0); + size_t p_size = __struct_size(p); - if (__builtin_constant_p(size) && p_size < size) + if (__compiletime_lessthan(p_size, size)) __read_overflow(); if (p_size < size) fortify_panic(__func__); @@ -293,47 +574,51 @@ __FORTIFY_INLINE void *memchr_inv(const void *p, int c, size_t size) } extern void *__real_kmemdup(const void *src, size_t len, gfp_t gfp) __RENAME(kmemdup); -__FORTIFY_INLINE void *kmemdup(const void *p, size_t size, gfp_t gfp) +__FORTIFY_INLINE void *kmemdup(const void * const POS0 p, size_t size, gfp_t gfp) { - size_t p_size = __builtin_object_size(p, 0); + size_t p_size = __struct_size(p); - if (__builtin_constant_p(size) && p_size < size) + if (__compiletime_lessthan(p_size, size)) __read_overflow(); if (p_size < size) fortify_panic(__func__); return __real_kmemdup(p, size, gfp); } -/* defined after fortified strlen and memcpy to reuse them */ -__FORTIFY_INLINE char *strcpy(char *p, const char *q) +/* Defined after fortified strlen to reuse it. */ +__FORTIFY_INLINE __diagnose_as(__builtin_strcpy, 1, 2) +char *strcpy(char * const POS p, const char * const POS q) { - size_t p_size = __builtin_object_size(p, 1); - size_t q_size = __builtin_object_size(q, 1); + size_t p_size = __member_size(p); + size_t q_size = __member_size(q); size_t size; - if (p_size == (size_t)-1 && q_size == (size_t)-1) + /* If neither buffer size is known, immediately give up. */ + if (__builtin_constant_p(p_size) && + __builtin_constant_p(q_size) && + p_size == SIZE_MAX && q_size == SIZE_MAX) return __underlying_strcpy(p, q); size = strlen(q) + 1; /* Compile-time check for const size overflow. */ - if (__builtin_constant_p(size) && p_size < size) + if (__compiletime_lessthan(p_size, size)) __write_overflow(); /* Run-time check for dynamic size overflow. */ if (p_size < size) fortify_panic(__func__); - memcpy(p, q, size); + __underlying_memcpy(p, q, size); return p; } /* Don't use these outside the FORITFY_SOURCE implementation */ #undef __underlying_memchr #undef __underlying_memcmp -#undef __underlying_memcpy -#undef __underlying_memmove -#undef __underlying_memset #undef __underlying_strcat #undef __underlying_strcpy #undef __underlying_strlen #undef __underlying_strncat #undef __underlying_strncpy +#undef POS +#undef POS0 + #endif /* _LINUX_FORTIFY_STRING_H_ */ diff --git a/include/linux/fpga/fpga-bridge.h b/include/linux/fpga/fpga-bridge.h index 6c3c28806ff1..223da48a6d18 100644 --- a/include/linux/fpga/fpga-bridge.h +++ b/include/linux/fpga/fpga-bridge.h @@ -23,6 +23,23 @@ struct fpga_bridge_ops { }; /** + * struct fpga_bridge_info - collection of parameters an FPGA Bridge + * @name: fpga bridge name + * @br_ops: pointer to structure of fpga bridge ops + * @priv: fpga bridge private data + * + * fpga_bridge_info contains parameters for the register function. These + * are separated into an info structure because they some are optional + * others could be added to in the future. The info structure facilitates + * maintaining a stable API. + */ +struct fpga_bridge_info { + const char *name; + const struct fpga_bridge_ops *br_ops; + void *priv; +}; + +/** * struct fpga_bridge - FPGA bridge structure * @name: name of low level FPGA bridge * @dev: FPGA bridge device @@ -62,15 +79,10 @@ int of_fpga_bridge_get_to_list(struct device_node *np, struct fpga_image_info *info, struct list_head *bridge_list); -struct fpga_bridge *fpga_bridge_create(struct device *dev, const char *name, - const struct fpga_bridge_ops *br_ops, - void *priv); -void fpga_bridge_free(struct fpga_bridge *br); -int fpga_bridge_register(struct fpga_bridge *br); +struct fpga_bridge * +fpga_bridge_register(struct device *parent, const char *name, + const struct fpga_bridge_ops *br_ops, + void *priv); void fpga_bridge_unregister(struct fpga_bridge *br); -struct fpga_bridge -*devm_fpga_bridge_create(struct device *dev, const char *name, - const struct fpga_bridge_ops *br_ops, void *priv); - #endif /* _LINUX_FPGA_BRIDGE_H */ diff --git a/include/linux/fpga/fpga-mgr.h b/include/linux/fpga/fpga-mgr.h index 474c1f506307..54f63459efd6 100644 --- a/include/linux/fpga/fpga-mgr.h +++ b/include/linux/fpga/fpga-mgr.h @@ -22,6 +22,8 @@ struct sg_table; * @FPGA_MGR_STATE_RESET: FPGA in reset state * @FPGA_MGR_STATE_FIRMWARE_REQ: firmware request in progress * @FPGA_MGR_STATE_FIRMWARE_REQ_ERR: firmware request failed + * @FPGA_MGR_STATE_PARSE_HEADER: parse FPGA image header + * @FPGA_MGR_STATE_PARSE_HEADER_ERR: Error during PARSE_HEADER stage * @FPGA_MGR_STATE_WRITE_INIT: preparing FPGA for programming * @FPGA_MGR_STATE_WRITE_INIT_ERR: Error during WRITE_INIT stage * @FPGA_MGR_STATE_WRITE: writing image to FPGA @@ -41,7 +43,9 @@ enum fpga_mgr_states { FPGA_MGR_STATE_FIRMWARE_REQ, FPGA_MGR_STATE_FIRMWARE_REQ_ERR, - /* write sequence: init, write, complete */ + /* write sequence: parse header, init, write, complete */ + FPGA_MGR_STATE_PARSE_HEADER, + FPGA_MGR_STATE_PARSE_HEADER_ERR, FPGA_MGR_STATE_WRITE_INIT, FPGA_MGR_STATE_WRITE_INIT_ERR, FPGA_MGR_STATE_WRITE, @@ -85,6 +89,9 @@ enum fpga_mgr_states { * @sgt: scatter/gather table containing FPGA image * @buf: contiguous buffer containing FPGA image * @count: size of buf + * @header_size: size of image header. + * @data_size: size of image data to be sent to the device. If not specified, + * whole image will be used. Header may be skipped in either case. * @region_id: id of target region * @dev: device that owns this * @overlay: Device Tree overlay @@ -98,6 +105,8 @@ struct fpga_image_info { struct sg_table *sgt; const char *buf; size_t count; + size_t header_size; + size_t data_size; int region_id; struct device *dev; #ifdef CONFIG_OF @@ -106,10 +115,47 @@ struct fpga_image_info { }; /** + * struct fpga_compat_id - id for compatibility check + * + * @id_h: high 64bit of the compat_id + * @id_l: low 64bit of the compat_id + */ +struct fpga_compat_id { + u64 id_h; + u64 id_l; +}; + +/** + * struct fpga_manager_info - collection of parameters for an FPGA Manager + * @name: fpga manager name + * @compat_id: FPGA manager id for compatibility check. + * @mops: pointer to structure of fpga manager ops + * @priv: fpga manager private data + * + * fpga_manager_info contains parameters for the register_full function. + * These are separated into an info structure because they some are optional + * others could be added to in the future. The info structure facilitates + * maintaining a stable API. + */ +struct fpga_manager_info { + const char *name; + struct fpga_compat_id *compat_id; + const struct fpga_manager_ops *mops; + void *priv; +}; + +/** * struct fpga_manager_ops - ops for low level fpga manager drivers - * @initial_header_size: Maximum number of bytes that should be passed into write_init + * @initial_header_size: minimum number of bytes that should be passed into + * parse_header and write_init. + * @skip_header: bool flag to tell fpga-mgr core whether it should skip + * info->header_size part at the beginning of the image when invoking + * write callback. * @state: returns an enum value of the FPGA's state * @status: returns status of the FPGA, including reconfiguration error code + * @parse_header: parse FPGA image header to set info->header_size and + * info->data_size. In case the input buffer is not large enough, set + * required size to info->header_size and return -EAGAIN. * @write_init: prepare the FPGA to receive configuration data * @write: write count bytes of configuration data to the FPGA * @write_sg: write the scatter list of configuration data to the FPGA @@ -123,8 +169,12 @@ struct fpga_image_info { */ struct fpga_manager_ops { size_t initial_header_size; + bool skip_header; enum fpga_mgr_states (*state)(struct fpga_manager *mgr); u64 (*status)(struct fpga_manager *mgr); + int (*parse_header)(struct fpga_manager *mgr, + struct fpga_image_info *info, + const char *buf, size_t count); int (*write_init)(struct fpga_manager *mgr, struct fpga_image_info *info, const char *buf, size_t count); @@ -144,17 +194,6 @@ struct fpga_manager_ops { #define FPGA_MGR_STATUS_FIFO_OVERFLOW_ERR BIT(4) /** - * struct fpga_compat_id - id for compatibility check - * - * @id_h: high 64bit of the compat_id - * @id_l: low 64bit of the compat_id - */ -struct fpga_compat_id { - u64 id_h; - u64 id_l; -}; - -/** * struct fpga_manager - fpga manager structure * @name: name of low level fpga manager * @dev: fpga manager device @@ -191,17 +230,18 @@ struct fpga_manager *fpga_mgr_get(struct device *dev); void fpga_mgr_put(struct fpga_manager *mgr); -struct fpga_manager *fpga_mgr_create(struct device *dev, const char *name, - const struct fpga_manager_ops *mops, - void *priv); -void fpga_mgr_free(struct fpga_manager *mgr); -int fpga_mgr_register(struct fpga_manager *mgr); -void fpga_mgr_unregister(struct fpga_manager *mgr); +struct fpga_manager * +fpga_mgr_register_full(struct device *parent, const struct fpga_manager_info *info); -int devm_fpga_mgr_register(struct device *dev, struct fpga_manager *mgr); +struct fpga_manager * +fpga_mgr_register(struct device *parent, const char *name, + const struct fpga_manager_ops *mops, void *priv); +void fpga_mgr_unregister(struct fpga_manager *mgr); -struct fpga_manager *devm_fpga_mgr_create(struct device *dev, const char *name, - const struct fpga_manager_ops *mops, - void *priv); +struct fpga_manager * +devm_fpga_mgr_register_full(struct device *parent, const struct fpga_manager_info *info); +struct fpga_manager * +devm_fpga_mgr_register(struct device *parent, const char *name, + const struct fpga_manager_ops *mops, void *priv); #endif /*_LINUX_FPGA_MGR_H */ diff --git a/include/linux/fpga/fpga-region.h b/include/linux/fpga/fpga-region.h index 27cb706275db..9d4d32909340 100644 --- a/include/linux/fpga/fpga-region.h +++ b/include/linux/fpga/fpga-region.h @@ -7,6 +7,27 @@ #include <linux/fpga/fpga-mgr.h> #include <linux/fpga/fpga-bridge.h> +struct fpga_region; + +/** + * struct fpga_region_info - collection of parameters an FPGA Region + * @mgr: fpga region manager + * @compat_id: FPGA region id for compatibility check. + * @priv: fpga region private data + * @get_bridges: optional function to get bridges to a list + * + * fpga_region_info contains parameters for the register_full function. + * These are separated into an info structure because they some are optional + * others could be added to in the future. The info structure facilitates + * maintaining a stable API. + */ +struct fpga_region_info { + struct fpga_manager *mgr; + struct fpga_compat_id *compat_id; + void *priv; + int (*get_bridges)(struct fpga_region *region); +}; + /** * struct fpga_region - FPGA Region structure * @dev: FPGA Region device @@ -31,21 +52,18 @@ struct fpga_region { #define to_fpga_region(d) container_of(d, struct fpga_region, dev) -struct fpga_region *fpga_region_class_find( - struct device *start, const void *data, - int (*match)(struct device *, const void *)); +struct fpga_region * +fpga_region_class_find(struct device *start, const void *data, + int (*match)(struct device *, const void *)); int fpga_region_program_fpga(struct fpga_region *region); -struct fpga_region -*fpga_region_create(struct device *dev, struct fpga_manager *mgr, - int (*get_bridges)(struct fpga_region *)); -void fpga_region_free(struct fpga_region *region); -int fpga_region_register(struct fpga_region *region); -void fpga_region_unregister(struct fpga_region *region); +struct fpga_region * +fpga_region_register_full(struct device *parent, const struct fpga_region_info *info); -struct fpga_region -*devm_fpga_region_create(struct device *dev, struct fpga_manager *mgr, - int (*get_bridges)(struct fpga_region *)); +struct fpga_region * +fpga_region_register(struct device *parent, struct fpga_manager *mgr, + int (*get_bridges)(struct fpga_region *)); +void fpga_region_unregister(struct fpga_region *region); #endif /* _FPGA_REGION_H */ diff --git a/include/linux/fprobe.h b/include/linux/fprobe.h new file mode 100644 index 000000000000..1c2bde0ead73 --- /dev/null +++ b/include/linux/fprobe.h @@ -0,0 +1,105 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Simple ftrace probe wrapper */ +#ifndef _LINUX_FPROBE_H +#define _LINUX_FPROBE_H + +#include <linux/compiler.h> +#include <linux/ftrace.h> +#include <linux/rethook.h> + +/** + * struct fprobe - ftrace based probe. + * @ops: The ftrace_ops. + * @nmissed: The counter for missing events. + * @flags: The status flag. + * @rethook: The rethook data structure. (internal data) + * @entry_handler: The callback function for function entry. + * @exit_handler: The callback function for function exit. + */ +struct fprobe { +#ifdef CONFIG_FUNCTION_TRACER + /* + * If CONFIG_FUNCTION_TRACER is not set, CONFIG_FPROBE is disabled too. + * But user of fprobe may keep embedding the struct fprobe on their own + * code. To avoid build error, this will keep the fprobe data structure + * defined here, but remove ftrace_ops data structure. + */ + struct ftrace_ops ops; +#endif + unsigned long nmissed; + unsigned int flags; + struct rethook *rethook; + + void (*entry_handler)(struct fprobe *fp, unsigned long entry_ip, struct pt_regs *regs); + void (*exit_handler)(struct fprobe *fp, unsigned long entry_ip, struct pt_regs *regs); +}; + +/* This fprobe is soft-disabled. */ +#define FPROBE_FL_DISABLED 1 + +/* + * This fprobe handler will be shared with kprobes. + * This flag must be set before registering. + */ +#define FPROBE_FL_KPROBE_SHARED 2 + +static inline bool fprobe_disabled(struct fprobe *fp) +{ + return (fp) ? fp->flags & FPROBE_FL_DISABLED : false; +} + +static inline bool fprobe_shared_with_kprobes(struct fprobe *fp) +{ + return (fp) ? fp->flags & FPROBE_FL_KPROBE_SHARED : false; +} + +#ifdef CONFIG_FPROBE +int register_fprobe(struct fprobe *fp, const char *filter, const char *notfilter); +int register_fprobe_ips(struct fprobe *fp, unsigned long *addrs, int num); +int register_fprobe_syms(struct fprobe *fp, const char **syms, int num); +int unregister_fprobe(struct fprobe *fp); +#else +static inline int register_fprobe(struct fprobe *fp, const char *filter, const char *notfilter) +{ + return -EOPNOTSUPP; +} +static inline int register_fprobe_ips(struct fprobe *fp, unsigned long *addrs, int num) +{ + return -EOPNOTSUPP; +} +static inline int register_fprobe_syms(struct fprobe *fp, const char **syms, int num) +{ + return -EOPNOTSUPP; +} +static inline int unregister_fprobe(struct fprobe *fp) +{ + return -EOPNOTSUPP; +} +#endif + +/** + * disable_fprobe() - Disable fprobe + * @fp: The fprobe to be disabled. + * + * This will soft-disable @fp. Note that this doesn't remove the ftrace + * hooks from the function entry. + */ +static inline void disable_fprobe(struct fprobe *fp) +{ + if (fp) + fp->flags |= FPROBE_FL_DISABLED; +} + +/** + * enable_fprobe() - Enable fprobe + * @fp: The fprobe to be enabled. + * + * This will soft-enable @fp. + */ +static inline void enable_fprobe(struct fprobe *fp) +{ + if (fp) + fp->flags &= ~FPROBE_FL_DISABLED; +} + +#endif diff --git a/include/linux/freezer.h b/include/linux/freezer.h index 0621c5f86c39..b303472255be 100644 --- a/include/linux/freezer.h +++ b/include/linux/freezer.h @@ -8,9 +8,11 @@ #include <linux/sched.h> #include <linux/wait.h> #include <linux/atomic.h> +#include <linux/jump_label.h> #ifdef CONFIG_FREEZER -extern atomic_t system_freezing_cnt; /* nr of freezing conds in effect */ +DECLARE_STATIC_KEY_FALSE(freezer_active); + extern bool pm_freezing; /* PM freezing in effect */ extern bool pm_nosig_freezing; /* PM nosig freezing in effect */ @@ -22,10 +24,7 @@ extern unsigned int freeze_timeout_msecs; /* * Check if a process has been frozen */ -static inline bool frozen(struct task_struct *p) -{ - return p->flags & PF_FROZEN; -} +extern bool frozen(struct task_struct *p); extern bool freezing_slow_path(struct task_struct *p); @@ -34,9 +33,10 @@ extern bool freezing_slow_path(struct task_struct *p); */ static inline bool freezing(struct task_struct *p) { - if (likely(!atomic_read(&system_freezing_cnt))) - return false; - return freezing_slow_path(p); + if (static_branch_unlikely(&freezer_active)) + return freezing_slow_path(p); + + return false; } /* Takes and releases task alloc lock using task_lock() */ @@ -48,23 +48,14 @@ extern int freeze_kernel_threads(void); extern void thaw_processes(void); extern void thaw_kernel_threads(void); -/* - * DO NOT ADD ANY NEW CALLERS OF THIS FUNCTION - * If try_to_freeze causes a lockdep warning it means the caller may deadlock - */ -static inline bool try_to_freeze_unsafe(void) +static inline bool try_to_freeze(void) { might_sleep(); if (likely(!freezing(current))) return false; - return __refrigerator(false); -} - -static inline bool try_to_freeze(void) -{ if (!(current->flags & PF_NOFREEZE)) debug_check_no_locks_held(); - return try_to_freeze_unsafe(); + return __refrigerator(false); } extern bool freeze_task(struct task_struct *p); @@ -79,195 +70,6 @@ static inline bool cgroup_freezing(struct task_struct *task) } #endif /* !CONFIG_CGROUP_FREEZER */ -/* - * The PF_FREEZER_SKIP flag should be set by a vfork parent right before it - * calls wait_for_completion(&vfork) and reset right after it returns from this - * function. Next, the parent should call try_to_freeze() to freeze itself - * appropriately in case the child has exited before the freezing of tasks is - * complete. However, we don't want kernel threads to be frozen in unexpected - * places, so we allow them to block freeze_processes() instead or to set - * PF_NOFREEZE if needed. Fortunately, in the ____call_usermodehelper() case the - * parent won't really block freeze_processes(), since ____call_usermodehelper() - * (the child) does a little before exec/exit and it can't be frozen before - * waking up the parent. - */ - - -/** - * freezer_do_not_count - tell freezer to ignore %current - * - * Tell freezers to ignore the current task when determining whether the - * target frozen state is reached. IOW, the current task will be - * considered frozen enough by freezers. - * - * The caller shouldn't do anything which isn't allowed for a frozen task - * until freezer_cont() is called. Usually, freezer[_do_not]_count() pair - * wrap a scheduling operation and nothing much else. - */ -static inline void freezer_do_not_count(void) -{ - current->flags |= PF_FREEZER_SKIP; -} - -/** - * freezer_count - tell freezer to stop ignoring %current - * - * Undo freezer_do_not_count(). It tells freezers that %current should be - * considered again and tries to freeze if freezing condition is already in - * effect. - */ -static inline void freezer_count(void) -{ - current->flags &= ~PF_FREEZER_SKIP; - /* - * If freezing is in progress, the following paired with smp_mb() - * in freezer_should_skip() ensures that either we see %true - * freezing() or freezer_should_skip() sees !PF_FREEZER_SKIP. - */ - smp_mb(); - try_to_freeze(); -} - -/* DO NOT ADD ANY NEW CALLERS OF THIS FUNCTION */ -static inline void freezer_count_unsafe(void) -{ - current->flags &= ~PF_FREEZER_SKIP; - smp_mb(); - try_to_freeze_unsafe(); -} - -/** - * freezer_should_skip - whether to skip a task when determining frozen - * state is reached - * @p: task in quesion - * - * This function is used by freezers after establishing %true freezing() to - * test whether a task should be skipped when determining the target frozen - * state is reached. IOW, if this function returns %true, @p is considered - * frozen enough. - */ -static inline bool freezer_should_skip(struct task_struct *p) -{ - /* - * The following smp_mb() paired with the one in freezer_count() - * ensures that either freezer_count() sees %true freezing() or we - * see cleared %PF_FREEZER_SKIP and return %false. This makes it - * impossible for a task to slip frozen state testing after - * clearing %PF_FREEZER_SKIP. - */ - smp_mb(); - return p->flags & PF_FREEZER_SKIP; -} - -/* - * These functions are intended to be used whenever you want allow a sleeping - * task to be frozen. Note that neither return any clear indication of - * whether a freeze event happened while in this function. - */ - -/* Like schedule(), but should not block the freezer. */ -static inline void freezable_schedule(void) -{ - freezer_do_not_count(); - schedule(); - freezer_count(); -} - -/* DO NOT ADD ANY NEW CALLERS OF THIS FUNCTION */ -static inline void freezable_schedule_unsafe(void) -{ - freezer_do_not_count(); - schedule(); - freezer_count_unsafe(); -} - -/* - * Like schedule_timeout(), but should not block the freezer. Do not - * call this with locks held. - */ -static inline long freezable_schedule_timeout(long timeout) -{ - long __retval; - freezer_do_not_count(); - __retval = schedule_timeout(timeout); - freezer_count(); - return __retval; -} - -/* - * Like schedule_timeout_interruptible(), but should not block the freezer. Do not - * call this with locks held. - */ -static inline long freezable_schedule_timeout_interruptible(long timeout) -{ - long __retval; - freezer_do_not_count(); - __retval = schedule_timeout_interruptible(timeout); - freezer_count(); - return __retval; -} - -/* DO NOT ADD ANY NEW CALLERS OF THIS FUNCTION */ -static inline long freezable_schedule_timeout_interruptible_unsafe(long timeout) -{ - long __retval; - - freezer_do_not_count(); - __retval = schedule_timeout_interruptible(timeout); - freezer_count_unsafe(); - return __retval; -} - -/* Like schedule_timeout_killable(), but should not block the freezer. */ -static inline long freezable_schedule_timeout_killable(long timeout) -{ - long __retval; - freezer_do_not_count(); - __retval = schedule_timeout_killable(timeout); - freezer_count(); - return __retval; -} - -/* DO NOT ADD ANY NEW CALLERS OF THIS FUNCTION */ -static inline long freezable_schedule_timeout_killable_unsafe(long timeout) -{ - long __retval; - freezer_do_not_count(); - __retval = schedule_timeout_killable(timeout); - freezer_count_unsafe(); - return __retval; -} - -/* - * Like schedule_hrtimeout_range(), but should not block the freezer. Do not - * call this with locks held. - */ -static inline int freezable_schedule_hrtimeout_range(ktime_t *expires, - u64 delta, const enum hrtimer_mode mode) -{ - int __retval; - freezer_do_not_count(); - __retval = schedule_hrtimeout_range(expires, delta, mode); - freezer_count(); - return __retval; -} - -/* - * Freezer-friendly wrappers around wait_event_interruptible(), - * wait_event_killable() and wait_event_interruptible_timeout(), originally - * defined in <linux/wait.h> - */ - -/* DO NOT ADD ANY NEW CALLERS OF THIS FUNCTION */ -#define wait_event_freezekillable_unsafe(wq, condition) \ -({ \ - int __retval; \ - freezer_do_not_count(); \ - __retval = wait_event_killable(wq, (condition)); \ - freezer_count_unsafe(); \ - __retval; \ -}) - #else /* !CONFIG_FREEZER */ static inline bool frozen(struct task_struct *p) { return false; } static inline bool freezing(struct task_struct *p) { return false; } @@ -281,35 +83,8 @@ static inline void thaw_kernel_threads(void) {} static inline bool try_to_freeze(void) { return false; } -static inline void freezer_do_not_count(void) {} -static inline void freezer_count(void) {} -static inline int freezer_should_skip(struct task_struct *p) { return 0; } static inline void set_freezable(void) {} -#define freezable_schedule() schedule() - -#define freezable_schedule_unsafe() schedule() - -#define freezable_schedule_timeout(timeout) schedule_timeout(timeout) - -#define freezable_schedule_timeout_interruptible(timeout) \ - schedule_timeout_interruptible(timeout) - -#define freezable_schedule_timeout_interruptible_unsafe(timeout) \ - schedule_timeout_interruptible(timeout) - -#define freezable_schedule_timeout_killable(timeout) \ - schedule_timeout_killable(timeout) - -#define freezable_schedule_timeout_killable_unsafe(timeout) \ - schedule_timeout_killable(timeout) - -#define freezable_schedule_hrtimeout_range(expires, delta, mode) \ - schedule_hrtimeout_range(expires, delta, mode) - -#define wait_event_freezekillable_unsafe(wq, condition) \ - wait_event_killable(wq, condition) - #endif /* !CONFIG_FREEZER */ #endif /* FREEZER_H_INCLUDED */ diff --git a/include/linux/frontswap.h b/include/linux/frontswap.h index b07d88c92bb2..a631bac12220 100644 --- a/include/linux/frontswap.h +++ b/include/linux/frontswap.h @@ -7,31 +7,17 @@ #include <linux/bitops.h> #include <linux/jump_label.h> -/* - * Return code to denote that requested number of - * frontswap pages are unused(moved to page cache). - * Used in shmem_unuse and try_to_unuse. - */ -#define FRONTSWAP_PAGES_UNUSED 2 - struct frontswap_ops { void (*init)(unsigned); /* this swap type was just swapon'ed */ int (*store)(unsigned, pgoff_t, struct page *); /* store a page */ int (*load)(unsigned, pgoff_t, struct page *); /* load a page */ void (*invalidate_page)(unsigned, pgoff_t); /* page no longer needed */ void (*invalidate_area)(unsigned); /* swap type just swapoff'ed */ - struct frontswap_ops *next; /* private pointer to next ops */ }; -extern void frontswap_register_ops(struct frontswap_ops *ops); -extern void frontswap_shrink(unsigned long); -extern unsigned long frontswap_curr_pages(void); -extern void frontswap_writethrough(bool); -#define FRONTSWAP_HAS_EXCLUSIVE_GETS -extern void frontswap_tmem_exclusive_gets(bool); +int frontswap_register_ops(const struct frontswap_ops *ops); -extern bool __frontswap_test(struct swap_info_struct *, pgoff_t); -extern void __frontswap_init(unsigned type, unsigned long *map); +extern void frontswap_init(unsigned type, unsigned long *map); extern int __frontswap_store(struct page *page); extern int __frontswap_load(struct page *page); extern void __frontswap_invalidate_page(unsigned, pgoff_t); @@ -45,11 +31,6 @@ static inline bool frontswap_enabled(void) return static_branch_unlikely(&frontswap_enabled_key); } -static inline bool frontswap_test(struct swap_info_struct *sis, pgoff_t offset) -{ - return __frontswap_test(sis, offset); -} - static inline void frontswap_map_set(struct swap_info_struct *p, unsigned long *map) { @@ -68,11 +49,6 @@ static inline bool frontswap_enabled(void) return false; } -static inline bool frontswap_test(struct swap_info_struct *sis, pgoff_t offset) -{ - return false; -} - static inline void frontswap_map_set(struct swap_info_struct *p, unsigned long *map) { @@ -112,11 +88,4 @@ static inline void frontswap_invalidate_area(unsigned type) __frontswap_invalidate_area(type); } -static inline void frontswap_init(unsigned type, unsigned long *map) -{ -#ifdef CONFIG_FRONTSWAP - __frontswap_init(type, map); -#endif -} - #endif /* _LINUX_FRONTSWAP_H */ diff --git a/include/linux/fs.h b/include/linux/fs.h index 493b87e3616b..e654435f1651 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -42,6 +42,7 @@ #include <linux/mount.h> #include <linux/cred.h> #include <linux/mnt_idmapping.h> +#include <linux/slab.h> #include <asm/byteorder.h> #include <uapi/linux/fs.h> @@ -73,21 +74,15 @@ struct fsverity_operations; struct fs_context; struct fs_parameter_spec; struct fileattr; +struct iomap_ops; extern void __init inode_init(void); extern void __init inode_init_early(void); extern void __init files_init(void); extern void __init files_maxfiles_init(void); -extern struct files_stat_struct files_stat; extern unsigned long get_max_files(void); extern unsigned int sysctl_nr_open; -extern struct inodes_stat_t inodes_stat; -extern int leases_enable, lease_break_time; -extern int sysctl_protected_symlinks; -extern int sysctl_protected_hardlinks; -extern int sysctl_protected_fifos; -extern int sysctl_protected_regular; typedef __kernel_rwf_t rwf_t; @@ -168,6 +163,9 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, /* File is stream-like */ #define FMODE_STREAM ((__force fmode_t)0x200000) +/* File supports DIRECT IO */ +#define FMODE_CAN_ODIRECT ((__force fmode_t)0x400000) + /* File was opened by fanotify and shouldn't generate fanotify events */ #define FMODE_NONOTIFY ((__force fmode_t)0x4000000) @@ -183,6 +181,9 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, /* File supports async buffered reads */ #define FMODE_BUF_RASYNC ((__force fmode_t)0x40000000) +/* File supports async nowait buffered writes */ +#define FMODE_BUF_WASYNC ((__force fmode_t)0x80000000) + /* * Attribute flags. These should be or-ed together to figure out what * has been changed! @@ -224,8 +225,26 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, struct iattr { unsigned int ia_valid; umode_t ia_mode; - kuid_t ia_uid; - kgid_t ia_gid; + /* + * The two anonymous unions wrap structures with the same member. + * + * Filesystems raising FS_ALLOW_IDMAP need to use ia_vfs{g,u}id which + * are a dedicated type requiring the filesystem to use the dedicated + * helpers. Other filesystem can continue to use ia_{g,u}id until they + * have been ported. + * + * They always contain the same value. In other words FS_ALLOW_IDMAP + * pass down the same value on idmapped mounts as they would on regular + * mounts. + */ + union { + kuid_t ia_uid; + vfsuid_t ia_vfsuid; + }; + union { + kgid_t ia_gid; + vfsgid_t ia_vfsgid; + }; loff_t ia_size; struct timespec64 ia_atime; struct timespec64 ia_mtime; @@ -268,7 +287,7 @@ struct iattr { * trying again. The aop will be taking reasonable * precautions not to livelock. If the caller held a page * reference, it should drop it before retrying. Returned - * by readpage(). + * by read_folio(). * * address_space_operation functions return these large constants to indicate * special semantics to the caller. These are much larger than the bytes in a @@ -281,11 +300,6 @@ enum positive_aop_returns { AOP_TRUNCATED_PAGE = 0x80001, }; -#define AOP_FLAG_CONT_EXPAND 0x0001 /* called from cont_expand */ -#define AOP_FLAG_NOFS 0x0002 /* used by filesystem to direct - * helper code (eg buffer layer) - * to clear GFP_FS from alloc */ - /* * oh the beauties of C type declarations. */ @@ -326,18 +340,12 @@ enum rw_hint { struct kiocb { struct file *ki_filp; - - /* The 'ki_filp' pointer is shared in a union for aio */ - randomized_struct_fields_start - loff_t ki_pos; void (*ki_complete)(struct kiocb *iocb, long ret); void *private; int ki_flags; - u16 ki_hint; u16 ki_ioprio; /* See linux/ioprio.h */ struct wait_page_queue *ki_waitq; /* for async buffered IO */ - randomized_struct_fields_end }; static inline bool is_sync_kiocb(struct kiocb *kiocb) @@ -345,48 +353,20 @@ static inline bool is_sync_kiocb(struct kiocb *kiocb) return kiocb->ki_complete == NULL; } -/* - * "descriptor" for what we're up to with a read. - * This allows us to use the same read code yet - * have multiple different users of the data that - * we read from a file. - * - * The simplest case just copies the data to user - * mode. - */ -typedef struct { - size_t written; - size_t count; - union { - char __user *buf; - void *data; - } arg; - int error; -} read_descriptor_t; - -typedef int (*read_actor_t)(read_descriptor_t *, struct page *, - unsigned long, unsigned long); - struct address_space_operations { int (*writepage)(struct page *page, struct writeback_control *wbc); - int (*readpage)(struct file *, struct page *); + int (*read_folio)(struct file *, struct folio *); /* Write back some dirty pages from this mapping. */ int (*writepages)(struct address_space *, struct writeback_control *); - /* Set a page dirty. Return true if this dirtied it */ - int (*set_page_dirty)(struct page *page); + /* Mark a folio dirty. Return true if this dirtied it */ + bool (*dirty_folio)(struct address_space *, struct folio *); - /* - * Reads in the requested pages. Unlike ->readpage(), this is - * PURELY used for read-ahead!. - */ - int (*readpages)(struct file *filp, struct address_space *mapping, - struct list_head *pages, unsigned nr_pages); void (*readahead)(struct readahead_control *); int (*write_begin)(struct file *, struct address_space *mapping, - loff_t pos, unsigned len, unsigned flags, + loff_t pos, unsigned len, struct page **pagep, void **fsdata); int (*write_end)(struct file *, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, @@ -394,44 +374,31 @@ struct address_space_operations { /* Unfortunately this kludge is needed for FIBMAP. Don't use it */ sector_t (*bmap)(struct address_space *, sector_t); - void (*invalidatepage) (struct page *, unsigned int, unsigned int); - int (*releasepage) (struct page *, gfp_t); - void (*freepage)(struct page *); + void (*invalidate_folio) (struct folio *, size_t offset, size_t len); + bool (*release_folio)(struct folio *, gfp_t); + void (*free_folio)(struct folio *folio); ssize_t (*direct_IO)(struct kiocb *, struct iov_iter *iter); /* - * migrate the contents of a page to the specified target. If + * migrate the contents of a folio to the specified target. If * migrate_mode is MIGRATE_ASYNC, it must not block. */ - int (*migratepage) (struct address_space *, - struct page *, struct page *, enum migrate_mode); - bool (*isolate_page)(struct page *, isolate_mode_t); - void (*putback_page)(struct page *); - int (*launder_page) (struct page *); - int (*is_partially_uptodate) (struct page *, unsigned long, - unsigned long); - void (*is_dirty_writeback) (struct page *, bool *, bool *); + int (*migrate_folio)(struct address_space *, struct folio *dst, + struct folio *src, enum migrate_mode); + int (*launder_folio)(struct folio *); + bool (*is_partially_uptodate) (struct folio *, size_t from, + size_t count); + void (*is_dirty_writeback) (struct folio *, bool *dirty, bool *wb); int (*error_remove_page)(struct address_space *, struct page *); /* swapfile support */ int (*swap_activate)(struct swap_info_struct *sis, struct file *file, sector_t *span); void (*swap_deactivate)(struct file *file); + int (*swap_rw)(struct kiocb *iocb, struct iov_iter *iter); }; extern const struct address_space_operations empty_aops; -/* - * pagecache_write_begin/pagecache_write_end must be used by general code - * to write into the pagecache. - */ -int pagecache_write_begin(struct file *, struct address_space *mapping, - loff_t pos, unsigned len, unsigned flags, - struct page **pagep, void **fsdata); - -int pagecache_write_end(struct file *, struct address_space *mapping, - loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata); - /** * struct address_space - Contents of a cacheable, mappable object. * @host: Owner, either the inode or the block_device. @@ -509,6 +476,11 @@ static inline void i_mmap_unlock_write(struct address_space *mapping) up_write(&mapping->i_mmap_rwsem); } +static inline int i_mmap_trylock_read(struct address_space *mapping) +{ + return down_read_trylock(&mapping->i_mmap_rwsem); +} + static inline void i_mmap_lock_read(struct address_space *mapping) { down_read(&mapping->i_mmap_rwsem); @@ -937,10 +909,15 @@ struct fown_struct { * struct file_ra_state - Track a file's readahead state. * @start: Where the most recent readahead started. * @size: Number of pages read in the most recent readahead. - * @async_size: Start next readahead when this many pages are left. - * @ra_pages: Maximum size of a readahead request. + * @async_size: Numer of pages that were/are not needed immediately + * and so were/are genuinely "ahead". Start next readahead when + * the first of these pages is accessed. + * @ra_pages: Maximum size of a readahead request, copied from the bdi. * @mmap_miss: How many mmap accesses missed in the page cache. * @prev_pos: The last byte in the most recent read request. + * + * When this structure is passed to ->readahead(), the "most recent" + * readahead means the current readahead. */ struct file_ra_state { pgoff_t start; @@ -962,9 +939,10 @@ static inline int ra_has_index(struct file_ra_state *ra, pgoff_t index) struct file { union { - struct llist_node fu_llist; - struct rcu_head fu_rcuhead; - } f_u; + struct llist_node f_llist; + struct rcu_head f_rcuhead; + unsigned int f_iocb_flags; + }; struct path f_path; struct inode *f_inode; /* cached value */ const struct file_operations *f_op; @@ -974,7 +952,6 @@ struct file { * Must not be taken from IRQ context. */ spinlock_t f_lock; - enum rw_hint f_write_hint; atomic_long_t f_count; unsigned int f_flags; fmode_t f_mode; @@ -1013,9 +990,7 @@ static inline struct file *get_file(struct file *f) atomic_long_inc(&f->f_count); return f; } -#define get_file_rcu_many(x, cnt) \ - atomic_long_add_unless(&(x)->f_count, (cnt), 0) -#define get_file_rcu(x) get_file_rcu_many((x), 1) +#define get_file_rcu(x) atomic_long_inc_not_zero(&(x)->f_count) #define file_count(x) atomic_long_read(&(x)->f_count) #define MAX_NON_LFS ((1UL<<31) - 1) @@ -1061,6 +1036,7 @@ struct file_lock_operations { }; struct lock_manager_operations { + void *lm_mod_owner; fl_owner_t (*lm_get_owner)(fl_owner_t); void (*lm_put_owner)(fl_owner_t); void (*lm_notify)(struct file_lock *); /* unblock callback */ @@ -1069,6 +1045,8 @@ struct lock_manager_operations { int (*lm_change)(struct file_lock *, int, struct list_head *); void (*lm_setup)(struct file_lock *, void **); bool (*lm_breaker_owns_lease)(struct file_lock *); + bool (*lm_lock_expirable)(struct file_lock *cfl); + void (*lm_expire_lock)(void); }; struct lock_manager { @@ -1206,6 +1184,8 @@ extern void lease_unregister_notifier(struct notifier_block *); struct files_struct; extern void show_fd_locks(struct seq_file *f, struct file *filp, struct files_struct *files); +extern bool locks_owner_has_blockers(struct file_lock_context *flctx, + fl_owner_t owner); #else /* !CONFIG_FILE_LOCKING */ static inline int fcntl_getlk(struct file *file, unsigned int cmd, struct flock __user *user) @@ -1221,13 +1201,13 @@ static inline int fcntl_setlk(unsigned int fd, struct file *file, #if BITS_PER_LONG == 32 static inline int fcntl_getlk64(struct file *file, unsigned int cmd, - struct flock64 __user *user) + struct flock64 *user) { return -EINVAL; } static inline int fcntl_setlk64(unsigned int fd, struct file *file, - unsigned int cmd, struct flock64 __user *user) + unsigned int cmd, struct flock64 *user) { return -EACCES; } @@ -1341,6 +1321,11 @@ static inline int lease_modify(struct file_lock *fl, int arg, struct files_struct; static inline void show_fd_locks(struct seq_file *f, struct file *filp, struct files_struct *files) {} +static inline bool locks_owner_has_blockers(struct file_lock_context *flctx, + fl_owner_t owner) +{ + return false; +} #endif /* !CONFIG_FILE_LOCKING */ static inline struct inode *file_inode(const struct file *f) @@ -1442,6 +1427,8 @@ extern int send_sigurg(struct fown_struct *fown); #define SB_I_SKIP_SYNC 0x00000100 /* Skip superblock at global sync */ #define SB_I_PERSB_BDI 0x00000200 /* has a per-sb bdi */ +#define SB_I_TS_EXPIRY_WARNED 0x00000400 /* warned about timestamp range expiry */ +#define SB_I_RETIRED 0x00000800 /* superblock shouldn't be reused */ /* Possible states of 'frozen' field */ enum { @@ -1485,12 +1472,12 @@ struct super_block { const struct xattr_handler **s_xattr; #ifdef CONFIG_FS_ENCRYPTION const struct fscrypt_operations *s_cop; - struct key *s_master_keys; /* master crypto keys in use */ + struct fscrypt_keyring *s_master_keys; /* master crypto keys in use */ #endif #ifdef CONFIG_FS_VERITY const struct fsverity_operations *s_vop; #endif -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) struct unicode_map *s_encoding; __u16 s_encoding_flags; #endif @@ -1542,11 +1529,6 @@ struct super_block { const struct dentry_operations *s_d_op; /* default d_op for dentries */ - /* - * Saved pool identifier for cleancache (-1 means none) - */ - int cleancache_poolid; - struct shrinker s_shrink; /* per-sb shrinker handle */ /* Number of inodes with nlink == 0 but still referenced */ @@ -1635,13 +1617,68 @@ static inline void i_gid_write(struct inode *inode, gid_t gid) * @mnt_userns: user namespace of the mount the inode was found from * @inode: inode to map * + * Note, this will eventually be removed completely in favor of the type-safe + * i_uid_into_vfsuid(). + * * Return: the inode's i_uid mapped down according to @mnt_userns. * If the inode's i_uid has no mapping INVALID_UID is returned. */ static inline kuid_t i_uid_into_mnt(struct user_namespace *mnt_userns, const struct inode *inode) { - return mapped_kuid_fs(mnt_userns, i_user_ns(inode), inode->i_uid); + return AS_KUIDT(make_vfsuid(mnt_userns, i_user_ns(inode), inode->i_uid)); +} + +/** + * i_uid_into_vfsuid - map an inode's i_uid down into a mnt_userns + * @mnt_userns: user namespace of the mount the inode was found from + * @inode: inode to map + * + * Return: whe inode's i_uid mapped down according to @mnt_userns. + * If the inode's i_uid has no mapping INVALID_VFSUID is returned. + */ +static inline vfsuid_t i_uid_into_vfsuid(struct user_namespace *mnt_userns, + const struct inode *inode) +{ + return make_vfsuid(mnt_userns, i_user_ns(inode), inode->i_uid); +} + +/** + * i_uid_needs_update - check whether inode's i_uid needs to be updated + * @mnt_userns: user namespace of the mount the inode was found from + * @attr: the new attributes of @inode + * @inode: the inode to update + * + * Check whether the $inode's i_uid field needs to be updated taking idmapped + * mounts into account if the filesystem supports it. + * + * Return: true if @inode's i_uid field needs to be updated, false if not. + */ +static inline bool i_uid_needs_update(struct user_namespace *mnt_userns, + const struct iattr *attr, + const struct inode *inode) +{ + return ((attr->ia_valid & ATTR_UID) && + !vfsuid_eq(attr->ia_vfsuid, + i_uid_into_vfsuid(mnt_userns, inode))); +} + +/** + * i_uid_update - update @inode's i_uid field + * @mnt_userns: user namespace of the mount the inode was found from + * @attr: the new attributes of @inode + * @inode: the inode to update + * + * Safely update @inode's i_uid field translating the vfsuid of any idmapped + * mount into the filesystem kuid. + */ +static inline void i_uid_update(struct user_namespace *mnt_userns, + const struct iattr *attr, + struct inode *inode) +{ + if (attr->ia_valid & ATTR_UID) + inode->i_uid = from_vfsuid(mnt_userns, i_user_ns(inode), + attr->ia_vfsuid); } /** @@ -1649,13 +1686,68 @@ static inline kuid_t i_uid_into_mnt(struct user_namespace *mnt_userns, * @mnt_userns: user namespace of the mount the inode was found from * @inode: inode to map * + * Note, this will eventually be removed completely in favor of the type-safe + * i_gid_into_vfsgid(). + * * Return: the inode's i_gid mapped down according to @mnt_userns. * If the inode's i_gid has no mapping INVALID_GID is returned. */ static inline kgid_t i_gid_into_mnt(struct user_namespace *mnt_userns, const struct inode *inode) { - return mapped_kgid_fs(mnt_userns, i_user_ns(inode), inode->i_gid); + return AS_KGIDT(make_vfsgid(mnt_userns, i_user_ns(inode), inode->i_gid)); +} + +/** + * i_gid_into_vfsgid - map an inode's i_gid down into a mnt_userns + * @mnt_userns: user namespace of the mount the inode was found from + * @inode: inode to map + * + * Return: the inode's i_gid mapped down according to @mnt_userns. + * If the inode's i_gid has no mapping INVALID_VFSGID is returned. + */ +static inline vfsgid_t i_gid_into_vfsgid(struct user_namespace *mnt_userns, + const struct inode *inode) +{ + return make_vfsgid(mnt_userns, i_user_ns(inode), inode->i_gid); +} + +/** + * i_gid_needs_update - check whether inode's i_gid needs to be updated + * @mnt_userns: user namespace of the mount the inode was found from + * @attr: the new attributes of @inode + * @inode: the inode to update + * + * Check whether the $inode's i_gid field needs to be updated taking idmapped + * mounts into account if the filesystem supports it. + * + * Return: true if @inode's i_gid field needs to be updated, false if not. + */ +static inline bool i_gid_needs_update(struct user_namespace *mnt_userns, + const struct iattr *attr, + const struct inode *inode) +{ + return ((attr->ia_valid & ATTR_GID) && + !vfsgid_eq(attr->ia_vfsgid, + i_gid_into_vfsgid(mnt_userns, inode))); +} + +/** + * i_gid_update - update @inode's i_gid field + * @mnt_userns: user namespace of the mount the inode was found from + * @attr: the new attributes of @inode + * @inode: the inode to update + * + * Safely update @inode's i_gid field translating the vfsgid of any idmapped + * mount into the filesystem kgid. + */ +static inline void i_gid_update(struct user_namespace *mnt_userns, + const struct iattr *attr, + struct inode *inode) +{ + if (attr->ia_valid & ATTR_GID) + inode->i_gid = from_vfsgid(mnt_userns, i_user_ns(inode), + attr->ia_vfsgid); } /** @@ -1744,6 +1836,11 @@ static inline bool __sb_start_write_trylock(struct super_block *sb, int level) #define __sb_writers_release(sb, lev) \ percpu_rwsem_release(&(sb)->s_writers.rw_sem[(lev)-1], 1, _THIS_IP_) +static inline bool sb_write_started(const struct super_block *sb) +{ + return lockdep_is_held_type(sb->s_writers.rw_sem + SB_FREEZE_WRITE - 1, 1); +} + /** * sb_end_write - drop write access to a superblock * @sb: the super we wrote to @@ -1907,8 +2004,9 @@ static inline int vfs_whiteout(struct user_namespace *mnt_userns, WHITEOUT_DEV); } -struct dentry *vfs_tmpfile(struct user_namespace *mnt_userns, - struct dentry *dentry, umode_t mode, int open_flag); +struct file *vfs_tmpfile_open(struct user_namespace *mnt_userns, + const struct path *parentpath, + umode_t mode, int open_flag, const struct cred *cred); int vfs_mkobj(struct dentry *, umode_t, int (*f)(struct dentry *, umode_t, void *), @@ -1933,15 +2031,18 @@ extern long compat_ptr_ioctl(struct file *file, unsigned int cmd, void inode_init_owner(struct user_namespace *mnt_userns, struct inode *inode, const struct inode *dir, umode_t mode); extern bool may_open_dev(const struct path *path); +umode_t mode_strip_sgid(struct user_namespace *mnt_userns, + const struct inode *dir, umode_t mode); /* * This is the "filldir" function type, used by readdir() to let * the kernel specify what kind of dirent layout it wants to have. * This allows the kernel to read directories into kernel space or * to have different dirent layouts depending on the binary type. + * Return 'true' to keep going and 'false' if there are no more entries. */ struct dir_context; -typedef int (*filldir_t)(struct dir_context *, const char *, int, loff_t, u64, +typedef bool (*filldir_t)(struct dir_context *, const char *, int, loff_t, u64, unsigned); struct dir_context { @@ -1989,6 +2090,7 @@ struct dir_context { #define REMAP_FILE_ADVISORY (REMAP_FILE_CAN_SHORTEN) struct iov_iter; +struct io_uring_cmd; struct file_operations { struct module *owner; @@ -2031,6 +2133,9 @@ struct file_operations { struct file *file_out, loff_t pos_out, loff_t len, unsigned int remap_flags); int (*fadvise)(struct file *, loff_t, loff_t, int); + int (*uring_cmd)(struct io_uring_cmd *ioucmd, unsigned int issue_flags); + int (*uring_cmd_iopoll)(struct io_uring_cmd *, struct io_comp_batch *, + unsigned int poll_flags); } __randomize_layout; struct inode_operations { @@ -2066,7 +2171,7 @@ struct inode_operations { struct file *, unsigned open_flag, umode_t create_mode); int (*tmpfile) (struct user_namespace *, struct inode *, - struct dentry *, umode_t); + struct file *, umode_t); int (*set_acl)(struct user_namespace *, struct inode *, struct posix_acl *, int); int (*fileattr_set)(struct user_namespace *mnt_userns, @@ -2098,10 +2203,13 @@ extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *, extern ssize_t generic_copy_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, size_t len, unsigned int flags); -extern int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, - struct file *file_out, loff_t pos_out, - loff_t *count, - unsigned int remap_flags); +int __generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + loff_t *len, unsigned int remap_flags, + const struct iomap_ops *dax_read_ops); +int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + loff_t *count, unsigned int remap_flags); extern loff_t do_clone_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t len, unsigned int remap_flags); @@ -2173,6 +2281,7 @@ struct super_operations { #define S_ENCRYPTED (1 << 14) /* Encrypted file (using fs/crypto/) */ #define S_CASEFOLD (1 << 15) /* Casefolded file */ #define S_VERITY (1 << 16) /* Verity file (using fs/verity/) */ +#define S_KERNEL_FILE (1 << 17) /* File is in use by the kernel (eg. fs/cachefiles) */ /* * Note that nosuid etc flags are inode-specific: setting some file-system @@ -2222,35 +2331,15 @@ static inline bool sb_rdonly(const struct super_block *sb) { return sb->s_flags static inline bool HAS_UNMAPPED_ID(struct user_namespace *mnt_userns, struct inode *inode) { - return !uid_valid(i_uid_into_mnt(mnt_userns, inode)) || - !gid_valid(i_gid_into_mnt(mnt_userns, inode)); -} - -static inline enum rw_hint file_write_hint(struct file *file) -{ - if (file->f_write_hint != WRITE_LIFE_NOT_SET) - return file->f_write_hint; - - return file_inode(file)->i_write_hint; -} - -static inline int iocb_flags(struct file *file); - -static inline u16 ki_hint_validate(enum rw_hint hint) -{ - typeof(((struct kiocb *)0)->ki_hint) max_hint = -1; - - if (hint <= max_hint) - return hint; - return 0; + return !vfsuid_valid(i_uid_into_vfsuid(mnt_userns, inode)) || + !vfsgid_valid(i_gid_into_vfsgid(mnt_userns, inode)); } static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp) { *kiocb = (struct kiocb) { .ki_filp = filp, - .ki_flags = iocb_flags(filp), - .ki_hint = ki_hint_validate(file_write_hint(filp)), + .ki_flags = filp->f_iocb_flags, .ki_ioprio = get_current_ioprio(), }; } @@ -2261,7 +2350,6 @@ static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src, *kiocb = (struct kiocb) { .ki_filp = filp, .ki_flags = kiocb_src->ki_flags, - .ki_hint = kiocb_src->ki_hint, .ki_ioprio = kiocb_src->ki_ioprio, .ki_pos = kiocb_src->ki_pos, }; @@ -2287,13 +2375,14 @@ static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src, * don't have to write inode on fdatasync() when only * e.g. the timestamps have changed. * I_DIRTY_PAGES Inode has dirty pages. Inode itself may be clean. - * I_DIRTY_TIME The inode itself only has dirty timestamps, and the + * I_DIRTY_TIME The inode itself has dirty timestamps, and the * lazytime mount option is enabled. We keep track of this * separately from I_DIRTY_SYNC in order to implement * lazytime. This gets cleared if I_DIRTY_INODE - * (I_DIRTY_SYNC and/or I_DIRTY_DATASYNC) gets set. I.e. - * either I_DIRTY_TIME *or* I_DIRTY_INODE can be set in - * i_state, but not both. I_DIRTY_PAGES may still be set. + * (I_DIRTY_SYNC and/or I_DIRTY_DATASYNC) gets set. But + * I_DIRTY_TIME can still be set if I_DIRTY_SYNC is already + * in place because writeback might already be in progress + * and we don't want to lose the time update * I_NEW Serves as both a mutex and completion notification. * New inodes set I_NEW. If two processes both create * the same inode, one of them will release its inode and @@ -2342,6 +2431,8 @@ static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src, * Used to detect that mark_inode_dirty() should not move * inode between dirty lists. * + * I_PINNING_FSCACHE_WB Inode is pinning an fscache object for writeback. + * * Q: What is the difference between I_WILL_FREE and I_FREEING? */ #define I_DIRTY_SYNC (1 << 0) @@ -2364,6 +2455,7 @@ static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src, #define I_CREATING (1 << 15) #define I_DONTCACHE (1 << 16) #define I_SYNC_QUEUED (1 << 17) +#define I_PINNING_FSCACHE_WB (1 << 18) #define I_DIRTY_INODE (I_DIRTY_SYNC | I_DIRTY_DATASYNC) #define I_DIRTY (I_DIRTY_INODE | I_DIRTY_PAGES) @@ -2430,6 +2522,7 @@ static inline void file_accessed(struct file *file) } extern int file_modified(struct file *file); +int kiocb_modified(struct kiocb *iocb); int sync_inode_metadata(struct inode *inode, int wait); @@ -2475,6 +2568,7 @@ extern struct dentry *mount_nodev(struct file_system_type *fs_type, int flags, void *data, int (*fill_super)(struct super_block *, void *, int)); extern struct dentry *mount_subtree(struct vfsmount *mnt, const char *path); +void retire_super(struct super_block *sb); void generic_shutdown_super(struct super_block *sb); void kill_block_super(struct super_block *sb); void kill_anon_super(struct super_block *sb); @@ -2512,22 +2606,11 @@ struct super_block *sget(struct file_system_type *type, extern int register_filesystem(struct file_system_type *); extern int unregister_filesystem(struct file_system_type *); -extern struct vfsmount *kern_mount(struct file_system_type *); -extern void kern_unmount(struct vfsmount *mnt); -extern int may_umount_tree(struct vfsmount *); -extern int may_umount(struct vfsmount *); -extern long do_mount(const char *, const char __user *, - const char *, unsigned long, void *); -extern struct vfsmount *collect_mounts(const struct path *); -extern void drop_collected_mounts(struct vfsmount *); -extern int iterate_mounts(int (*)(struct vfsmount *, void *), void *, - struct vfsmount *); extern int vfs_statfs(const struct path *, struct kstatfs *); extern int user_statfs(const char __user *, struct kstatfs *); extern int fd_statfs(int, struct kstatfs *); extern int freeze_super(struct super_block *super); extern int thaw_super(struct super_block *super); -extern bool our_mnt(struct vfsmount *mnt); extern __printf(2, 3) int super_setup_bdi_name(struct super_block *sb, char *fmt, ...); extern int super_setup_bdi(struct super_block *sb); @@ -2681,6 +2764,8 @@ static inline struct file *file_open_root_mnt(struct vfsmount *mnt, name, flags, mode); } extern struct file * dentry_open(const struct path *, int, const struct cred *); +extern struct file *dentry_create(const struct path *path, int flags, + umode_t mode, const struct cred *cred); extern struct file * open_with_fake_path(const struct path *, int, struct inode*, const struct cred *); static inline struct file *file_clone_open(struct file *file) @@ -2699,6 +2784,15 @@ extern int finish_open(struct file *file, struct dentry *dentry, int (*open)(struct inode *, struct file *)); extern int finish_no_open(struct file *file, struct dentry *dentry); +/* Helper for the simple case when original dentry is used */ +static inline int finish_open_simple(struct file *file, int error) +{ + if (error) + return error; + + return finish_open(file, file->f_path.dentry, NULL); +} + /* fs/dcache.c */ extern void __init vfs_caches_init_early(void); extern void __init vfs_caches_init(void); @@ -2754,56 +2848,6 @@ extern void init_special_inode(struct inode *, umode_t, dev_t); extern void make_bad_inode(struct inode *); extern bool is_bad_inode(struct inode *); -unsigned long invalidate_mapping_pages(struct address_space *mapping, - pgoff_t start, pgoff_t end); - -void invalidate_mapping_pagevec(struct address_space *mapping, - pgoff_t start, pgoff_t end, - unsigned long *nr_pagevec); - -static inline void invalidate_remote_inode(struct inode *inode) -{ - if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || - S_ISLNK(inode->i_mode)) - invalidate_mapping_pages(inode->i_mapping, 0, -1); -} -extern int invalidate_inode_pages2(struct address_space *mapping); -extern int invalidate_inode_pages2_range(struct address_space *mapping, - pgoff_t start, pgoff_t end); -extern int write_inode_now(struct inode *, int); -extern int filemap_fdatawrite(struct address_space *); -extern int filemap_flush(struct address_space *); -extern int filemap_fdatawait_keep_errors(struct address_space *mapping); -extern int filemap_fdatawait_range(struct address_space *, loff_t lstart, - loff_t lend); -extern int filemap_fdatawait_range_keep_errors(struct address_space *mapping, - loff_t start_byte, loff_t end_byte); - -static inline int filemap_fdatawait(struct address_space *mapping) -{ - return filemap_fdatawait_range(mapping, 0, LLONG_MAX); -} - -extern bool filemap_range_has_page(struct address_space *, loff_t lstart, - loff_t lend); -extern bool filemap_range_needs_writeback(struct address_space *, - loff_t lstart, loff_t lend); -extern int filemap_write_and_wait_range(struct address_space *mapping, - loff_t lstart, loff_t lend); -extern int __filemap_fdatawrite_range(struct address_space *mapping, - loff_t start, loff_t end, int sync_mode); -extern int filemap_fdatawrite_range(struct address_space *mapping, - loff_t start, loff_t end); -extern int filemap_check_errors(struct address_space *mapping); -extern void __filemap_set_wb_err(struct address_space *mapping, int err); -int filemap_fdatawrite_wbc(struct address_space *mapping, - struct writeback_control *wbc); - -static inline int filemap_write_and_wait(struct address_space *mapping) -{ - return filemap_write_and_wait_range(mapping, 0, LLONG_MAX); -} - extern int __must_check file_fdatawait_range(struct file *file, loff_t lstart, loff_t lend); extern int __must_check file_check_and_advance_wb_err(struct file *file); @@ -2815,67 +2859,6 @@ static inline int file_write_and_wait(struct file *file) return file_write_and_wait_range(file, 0, LLONG_MAX); } -/** - * filemap_set_wb_err - set a writeback error on an address_space - * @mapping: mapping in which to set writeback error - * @err: error to be set in mapping - * - * When writeback fails in some way, we must record that error so that - * userspace can be informed when fsync and the like are called. We endeavor - * to report errors on any file that was open at the time of the error. Some - * internal callers also need to know when writeback errors have occurred. - * - * When a writeback error occurs, most filesystems will want to call - * filemap_set_wb_err to record the error in the mapping so that it will be - * automatically reported whenever fsync is called on the file. - */ -static inline void filemap_set_wb_err(struct address_space *mapping, int err) -{ - /* Fastpath for common case of no error */ - if (unlikely(err)) - __filemap_set_wb_err(mapping, err); -} - -/** - * filemap_check_wb_err - has an error occurred since the mark was sampled? - * @mapping: mapping to check for writeback errors - * @since: previously-sampled errseq_t - * - * Grab the errseq_t value from the mapping, and see if it has changed "since" - * the given value was sampled. - * - * If it has then report the latest error set, otherwise return 0. - */ -static inline int filemap_check_wb_err(struct address_space *mapping, - errseq_t since) -{ - return errseq_check(&mapping->wb_err, since); -} - -/** - * filemap_sample_wb_err - sample the current errseq_t to test for later errors - * @mapping: mapping to be sampled - * - * Writeback errors are always reported relative to a particular sample point - * in the past. This function provides those sample points. - */ -static inline errseq_t filemap_sample_wb_err(struct address_space *mapping) -{ - return errseq_sample(&mapping->wb_err); -} - -/** - * file_sample_sb_err - sample the current errseq_t to test for later errors - * @file: file pointer to be sampled - * - * Grab the most current superblock-level errseq_t value for the given - * struct file. - */ -static inline errseq_t file_sample_sb_err(struct file *file) -{ - return errseq_sample(&file->f_path.dentry->d_sb->s_wb_err); -} - extern int vfs_fsync_range(struct file *file, loff_t start, loff_t end, int datasync); extern int vfs_fsync(struct file *file, int datasync); @@ -2883,6 +2866,12 @@ extern int vfs_fsync(struct file *file, int datasync); extern int sync_file_range(struct file *file, loff_t offset, loff_t nbytes, unsigned int flags); +static inline bool iocb_is_dsync(const struct kiocb *iocb) +{ + return (iocb->ki_flags & IOCB_DSYNC) || + IS_SYNC(iocb->ki_filp->f_mapping->host); +} + /* * Sync the bytes written if this was a synchronous write. Expect ki_pos * to already be updated for the write, and will return either the amount @@ -2890,7 +2879,7 @@ extern int sync_file_range(struct file *file, loff_t offset, loff_t nbytes, */ static inline ssize_t generic_write_sync(struct kiocb *iocb, ssize_t count) { - if (iocb->ki_flags & IOCB_DSYNC) { + if (iocb_is_dsync(iocb)) { int ret = vfs_fsync_range(iocb->ki_filp, iocb->ki_pos - count, iocb->ki_pos - 1, (iocb->ki_flags & IOCB_SYNC) ? 0 : 1); @@ -3091,6 +3080,7 @@ extern void unlock_new_inode(struct inode *); extern void discard_new_inode(struct inode *); extern unsigned int get_next_ino(void); extern void evict_inodes(struct super_block *sb); +void dump_mapping(const struct address_space *); /* * Userspace may rely on the the inode number being non-zero. For example, glibc @@ -3117,6 +3107,16 @@ extern void free_inode_nonrcu(struct inode *inode); extern int should_remove_suid(struct dentry *); extern int file_remove_privs(struct file *); +/* + * This must be used for allocating filesystems specific inodes to set + * up the inode reclaim context correctly. + */ +static inline void * +alloc_inode_sb(struct super_block *sb, struct kmem_cache *cache, gfp_t gfp) +{ + return kmem_cache_alloc_lru(cache, &sb->s_inode_lru, gfp); +} + extern void __insert_inode_hash(struct inode *, unsigned long hashval); static inline void insert_inode_hash(struct inode *inode) { @@ -3139,6 +3139,7 @@ extern int sb_min_blocksize(struct super_block *, int); extern int generic_file_mmap(struct file *, struct vm_area_struct *); extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *); extern ssize_t generic_write_checks(struct kiocb *, struct iov_iter *); +int generic_write_checks_count(struct kiocb *iocb, loff_t *count); extern int generic_write_check_limits(struct file *file, loff_t pos, loff_t *count); extern int generic_file_rw_checks(struct file *file_in, struct file *file_out); @@ -3148,7 +3149,7 @@ extern ssize_t generic_file_read_iter(struct kiocb *, struct iov_iter *); extern ssize_t __generic_file_write_iter(struct kiocb *, struct iov_iter *); extern ssize_t generic_file_write_iter(struct kiocb *, struct iov_iter *); extern ssize_t generic_file_direct_write(struct kiocb *, struct iov_iter *); -extern ssize_t generic_perform_write(struct file *, struct iov_iter *, loff_t); +ssize_t generic_perform_write(struct kiocb *, struct iov_iter *); ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos, rwf_t flags); @@ -3173,7 +3174,7 @@ extern long do_splice_direct(struct file *in, loff_t *ppos, struct file *out, extern void file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping); extern loff_t noop_llseek(struct file *file, loff_t offset, int whence); -extern loff_t no_llseek(struct file *file, loff_t offset, int whence); +#define no_llseek NULL extern loff_t vfs_setpos(struct file *file, loff_t offset, loff_t maxsize); extern loff_t generic_file_llseek(struct file *file, loff_t offset, int whence); extern loff_t generic_file_llseek_size(struct file *file, loff_t offset, @@ -3182,6 +3183,7 @@ extern loff_t fixed_size_llseek(struct file *file, loff_t offset, int whence, loff_t size); extern loff_t no_seek_end_llseek_size(struct file *, loff_t, int, loff_t); extern loff_t no_seek_end_llseek(struct file *, loff_t, int); +int rw_verify_area(int, struct file *, const loff_t *, size_t); extern int generic_file_open(struct inode * inode, struct file * filp); extern int nonseekable_open(struct inode * inode, struct file * filp); extern int stream_open(struct inode * inode, struct file * filp); @@ -3258,8 +3260,6 @@ extern int page_readlink(struct dentry *, char __user *, int); extern const char *page_get_link(struct dentry *, struct inode *, struct delayed_call *); extern void page_put_link(void *); -extern int __page_symlink(struct inode *inode, const char *symname, int len, - int nofs); extern int page_symlink(struct inode *inode, const char *symname, int len); extern const struct inode_operations page_symlink_inode_operations; extern void kfree_link(void *); @@ -3331,12 +3331,10 @@ extern int simple_rename(struct user_namespace *, struct inode *, extern void simple_recursive_removal(struct dentry *, void (*callback)(struct dentry *)); extern int noop_fsync(struct file *, loff_t, loff_t, int); -extern void noop_invalidatepage(struct page *page, unsigned int offset, - unsigned int length); extern ssize_t noop_direct_IO(struct kiocb *iocb, struct iov_iter *iter); extern int simple_empty(struct dentry *); extern int simple_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned flags, + loff_t pos, unsigned len, struct page **pagep, void **fsdata); extern const struct address_space_operations ram_aops; extern int always_delete_dentry(const struct dentry *); @@ -3369,18 +3367,6 @@ extern int generic_check_addressable(unsigned, u64); extern void generic_set_encrypted_ci_d_ops(struct dentry *dentry); -#ifdef CONFIG_MIGRATION -extern int buffer_migrate_page(struct address_space *, - struct page *, struct page *, - enum migrate_mode); -extern int buffer_migrate_page_norefs(struct address_space *, - struct page *, struct page *, - enum migrate_mode); -#else -#define buffer_migrate_page NULL -#define buffer_migrate_page_norefs NULL -#endif - int may_setattr(struct user_namespace *mnt_userns, struct inode *inode, unsigned int ia_valid); int setattr_prepare(struct user_namespace *, struct dentry *, struct iattr *); @@ -3416,7 +3402,7 @@ static inline int iocb_flags(struct file *file) res |= IOCB_APPEND; if (file->f_flags & O_DIRECT) res |= IOCB_DIRECT; - if ((file->f_flags & O_DSYNC) || IS_SYNC(file->f_mapping->host)) + if (file->f_flags & O_DSYNC) res |= IOCB_DSYNC; if (file->f_flags & __O_SYNC) res |= IOCB_SYNC; @@ -3530,12 +3516,6 @@ ssize_t simple_attr_write(struct file *file, const char __user *buf, size_t len, loff_t *ppos); struct ctl_table; -int proc_nr_files(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos); -int proc_nr_dentry(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos); -int proc_nr_inodes(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos); int __init list_bdev_fs_names(char *buf, size_t size); #define __FMODE_EXEC ((__force int) FMODE_EXEC) @@ -3574,17 +3554,17 @@ static inline bool dir_emit(struct dir_context *ctx, const char *name, int namelen, u64 ino, unsigned type) { - return ctx->actor(ctx, name, namelen, ctx->pos, ino, type) == 0; + return ctx->actor(ctx, name, namelen, ctx->pos, ino, type); } static inline bool dir_emit_dot(struct file *file, struct dir_context *ctx) { return ctx->actor(ctx, ".", 1, ctx->pos, - file->f_path.dentry->d_inode->i_ino, DT_DIR) == 0; + file->f_path.dentry->d_inode->i_ino, DT_DIR); } static inline bool dir_emit_dotdot(struct file *file, struct dir_context *ctx) { return ctx->actor(ctx, "..", 2, ctx->pos, - parent_ino(file->f_path.dentry), DT_DIR) == 0; + parent_ino(file->f_path.dentry), DT_DIR); } static inline bool dir_emit_dots(struct file *file, struct dir_context *ctx) { @@ -3623,15 +3603,4 @@ extern int vfs_fadvise(struct file *file, loff_t offset, loff_t len, extern int generic_fadvise(struct file *file, loff_t offset, loff_t len, int advice); -/* - * Flush file data before changing attributes. Caller must hold any locks - * required to prevent further writes to this file until we're done setting - * flags. - */ -static inline int inode_drain_writes(struct inode *inode) -{ - inode_dio_wait(inode); - return filemap_write_and_wait(inode->i_mapping); -} - #endif /* _LINUX_FS_H */ diff --git a/include/linux/fs_api.h b/include/linux/fs_api.h new file mode 100644 index 000000000000..83be38d6d413 --- /dev/null +++ b/include/linux/fs_api.h @@ -0,0 +1 @@ +#include <linux/fs.h> diff --git a/include/linux/fs_context.h b/include/linux/fs_context.h index 6b54982fc5f3..13fa6f3df8e4 100644 --- a/include/linux/fs_context.h +++ b/include/linux/fs_context.h @@ -142,6 +142,8 @@ extern void put_fs_context(struct fs_context *fc); extern int vfs_parse_fs_param_source(struct fs_context *fc, struct fs_parameter *param); extern void fc_drop_locked(struct fs_context *fc); +int reconfigure_single(struct super_block *s, + int flags, void *data); /* * sget() wrappers to be called from the ->get_tree() op. diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h index 8d39491c5f9f..a174cedf4d90 100644 --- a/include/linux/fscache-cache.h +++ b/include/linux/fscache-cache.h @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0-or-later */ /* General filesystem caching backing cache interface * - * Copyright (C) 2004-2007 Red Hat, Inc. All Rights Reserved. + * Copyright (C) 2021 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) * * NOTE!!! See: @@ -15,207 +15,34 @@ #define _LINUX_FSCACHE_CACHE_H #include <linux/fscache.h> -#include <linux/sched.h> -#include <linux/workqueue.h> -#define NR_MAXCACHES BITS_PER_LONG - -struct fscache_cache; -struct fscache_cache_ops; -struct fscache_object; -struct fscache_operation; - -enum fscache_obj_ref_trace { - fscache_obj_get_add_to_deps, - fscache_obj_get_queue, - fscache_obj_put_alloc_fail, - fscache_obj_put_attach_fail, - fscache_obj_put_drop_obj, - fscache_obj_put_enq_dep, - fscache_obj_put_queue, - fscache_obj_put_work, - fscache_obj_ref__nr_traces +enum fscache_cache_trace; +enum fscache_cookie_trace; +enum fscache_access_trace; + +enum fscache_cache_state { + FSCACHE_CACHE_IS_NOT_PRESENT, /* No cache is present for this name */ + FSCACHE_CACHE_IS_PREPARING, /* A cache is preparing to come live */ + FSCACHE_CACHE_IS_ACTIVE, /* Attached cache is active and can be used */ + FSCACHE_CACHE_GOT_IOERROR, /* Attached cache stopped on I/O error */ + FSCACHE_CACHE_IS_WITHDRAWN, /* Attached cache is being withdrawn */ +#define NR__FSCACHE_CACHE_STATE (FSCACHE_CACHE_IS_WITHDRAWN + 1) }; /* - * cache tag definition - */ -struct fscache_cache_tag { - struct list_head link; - struct fscache_cache *cache; /* cache referred to by this tag */ - unsigned long flags; -#define FSCACHE_TAG_RESERVED 0 /* T if tag is reserved for a cache */ - atomic_t usage; - char name[]; /* tag name */ -}; - -/* - * cache definition + * Cache cookie. */ struct fscache_cache { const struct fscache_cache_ops *ops; - struct fscache_cache_tag *tag; /* tag representing this cache */ - struct kobject *kobj; /* system representation of this cache */ - struct list_head link; /* link in list of caches */ - size_t max_index_size; /* maximum size of index data */ - char identifier[36]; /* cache label */ - - /* node management */ - struct work_struct op_gc; /* operation garbage collector */ - struct list_head object_list; /* list of data/index objects */ - struct list_head op_gc_list; /* list of ops to be deleted */ - spinlock_t object_list_lock; - spinlock_t op_gc_list_lock; + struct list_head cache_link; /* Link in cache list */ + void *cache_priv; /* Private cache data (or NULL) */ + refcount_t ref; + atomic_t n_volumes; /* Number of active volumes; */ + atomic_t n_accesses; /* Number of in-progress accesses on the cache */ atomic_t object_count; /* no. of live objects in this cache */ - struct fscache_object *fsdef; /* object for the fsdef index */ - unsigned long flags; -#define FSCACHE_IOERROR 0 /* cache stopped on I/O error */ -#define FSCACHE_CACHE_WITHDRAWN 1 /* cache has been withdrawn */ -}; - -extern wait_queue_head_t fscache_cache_cleared_wq; - -/* - * operation to be applied to a cache object - * - retrieval initiation operations are done in the context of the process - * that issued them, and not in an async thread pool - */ -typedef void (*fscache_operation_release_t)(struct fscache_operation *op); -typedef void (*fscache_operation_processor_t)(struct fscache_operation *op); -typedef void (*fscache_operation_cancel_t)(struct fscache_operation *op); - -enum fscache_operation_state { - FSCACHE_OP_ST_BLANK, /* Op is not yet submitted */ - FSCACHE_OP_ST_INITIALISED, /* Op is initialised */ - FSCACHE_OP_ST_PENDING, /* Op is blocked from running */ - FSCACHE_OP_ST_IN_PROGRESS, /* Op is in progress */ - FSCACHE_OP_ST_COMPLETE, /* Op is complete */ - FSCACHE_OP_ST_CANCELLED, /* Op has been cancelled */ - FSCACHE_OP_ST_DEAD /* Op is now dead */ -}; - -struct fscache_operation { - struct work_struct work; /* record for async ops */ - struct list_head pend_link; /* link in object->pending_ops */ - struct fscache_object *object; /* object to be operated upon */ - - unsigned long flags; -#define FSCACHE_OP_TYPE 0x000f /* operation type */ -#define FSCACHE_OP_ASYNC 0x0001 /* - async op, processor may sleep for disk */ -#define FSCACHE_OP_MYTHREAD 0x0002 /* - processing is done be issuing thread, not pool */ -#define FSCACHE_OP_WAITING 4 /* cleared when op is woken */ -#define FSCACHE_OP_EXCLUSIVE 5 /* exclusive op, other ops must wait */ -#define FSCACHE_OP_DEC_READ_CNT 6 /* decrement object->n_reads on destruction */ -#define FSCACHE_OP_UNUSE_COOKIE 7 /* call fscache_unuse_cookie() on completion */ -#define FSCACHE_OP_KEEP_FLAGS 0x00f0 /* flags to keep when repurposing an op */ - - enum fscache_operation_state state; - atomic_t usage; - unsigned debug_id; /* debugging ID */ - - /* operation processor callback - * - can be NULL if FSCACHE_OP_WAITING is going to be used to perform - * the op in a non-pool thread */ - fscache_operation_processor_t processor; - - /* Operation cancellation cleanup (optional) */ - fscache_operation_cancel_t cancel; - - /* operation releaser */ - fscache_operation_release_t release; -}; - -extern atomic_t fscache_op_debug_id; -extern void fscache_op_work_func(struct work_struct *work); - -extern void fscache_enqueue_operation(struct fscache_operation *); -extern void fscache_op_complete(struct fscache_operation *, bool); -extern void fscache_put_operation(struct fscache_operation *); -extern void fscache_operation_init(struct fscache_cookie *, - struct fscache_operation *, - fscache_operation_processor_t, - fscache_operation_cancel_t, - fscache_operation_release_t); - -/* - * data read operation - */ -struct fscache_retrieval { - struct fscache_operation op; - struct fscache_cookie *cookie; /* The netfs cookie */ - struct address_space *mapping; /* netfs pages */ - fscache_rw_complete_t end_io_func; /* function to call on I/O completion */ - void *context; /* netfs read context (pinned) */ - struct list_head to_do; /* list of things to be done by the backend */ - atomic_t n_pages; /* number of pages to be retrieved */ -}; - -typedef int (*fscache_page_retrieval_func_t)(struct fscache_retrieval *op, - struct page *page, - gfp_t gfp); - -typedef int (*fscache_pages_retrieval_func_t)(struct fscache_retrieval *op, - struct list_head *pages, - unsigned *nr_pages, - gfp_t gfp); - -/** - * fscache_get_retrieval - Get an extra reference on a retrieval operation - * @op: The retrieval operation to get a reference on - * - * Get an extra reference on a retrieval operation. - */ -static inline -struct fscache_retrieval *fscache_get_retrieval(struct fscache_retrieval *op) -{ - atomic_inc(&op->op.usage); - return op; -} - -/** - * fscache_enqueue_retrieval - Enqueue a retrieval operation for processing - * @op: The retrieval operation affected - * - * Enqueue a retrieval operation for processing by the FS-Cache thread pool. - */ -static inline void fscache_enqueue_retrieval(struct fscache_retrieval *op) -{ - fscache_enqueue_operation(&op->op); -} - -/** - * fscache_retrieval_complete - Record (partial) completion of a retrieval - * @op: The retrieval operation affected - * @n_pages: The number of pages to account for - */ -static inline void fscache_retrieval_complete(struct fscache_retrieval *op, - int n_pages) -{ - if (atomic_sub_return_relaxed(n_pages, &op->n_pages) <= 0) - fscache_op_complete(&op->op, false); -} - -/** - * fscache_put_retrieval - Drop a reference to a retrieval operation - * @op: The retrieval operation affected - * - * Drop a reference to a retrieval operation. - */ -static inline void fscache_put_retrieval(struct fscache_retrieval *op) -{ - fscache_put_operation(&op->op); -} - -/* - * cached page storage work item - * - used to do three things: - * - batch writes to the cache - * - do cache writes asynchronously - * - defer writes until cache object lookup completion - */ -struct fscache_storage { - struct fscache_operation op; - pgoff_t store_limit; /* don't write more than this */ + unsigned int debug_id; + enum fscache_cache_state state; + char *name; }; /* @@ -225,341 +52,154 @@ struct fscache_cache_ops { /* name of cache provider */ const char *name; - /* allocate an object record for a cookie */ - struct fscache_object *(*alloc_object)(struct fscache_cache *cache, - struct fscache_cookie *cookie); - - /* look up the object for a cookie - * - return -ETIMEDOUT to be requeued - */ - int (*lookup_object)(struct fscache_object *object); - - /* finished looking up */ - void (*lookup_complete)(struct fscache_object *object); - - /* increment the usage count on this object (may fail if unmounting) */ - struct fscache_object *(*grab_object)(struct fscache_object *object, - enum fscache_obj_ref_trace why); + /* Acquire a volume */ + void (*acquire_volume)(struct fscache_volume *volume); - /* pin an object in the cache */ - int (*pin_object)(struct fscache_object *object); + /* Free the cache's data attached to a volume */ + void (*free_volume)(struct fscache_volume *volume); - /* unpin an object in the cache */ - void (*unpin_object)(struct fscache_object *object); + /* Look up a cookie in the cache */ + bool (*lookup_cookie)(struct fscache_cookie *cookie); - /* check the consistency between the backing cache and the FS-Cache - * cookie */ - int (*check_consistency)(struct fscache_operation *op); + /* Withdraw an object without any cookie access counts held */ + void (*withdraw_cookie)(struct fscache_cookie *cookie); - /* store the updated auxiliary data on an object */ - void (*update_object)(struct fscache_object *object); + /* Change the size of a data object */ + void (*resize_cookie)(struct netfs_cache_resources *cres, + loff_t new_size); /* Invalidate an object */ - void (*invalidate_object)(struct fscache_operation *op); - - /* discard the resources pinned by an object and effect retirement if - * necessary */ - void (*drop_object)(struct fscache_object *object); - - /* dispose of a reference to an object */ - void (*put_object)(struct fscache_object *object, - enum fscache_obj_ref_trace why); - - /* sync a cache */ - void (*sync_cache)(struct fscache_cache *cache); - - /* notification that the attributes of a non-index object (such as - * i_size) have changed */ - int (*attr_changed)(struct fscache_object *object); - - /* reserve space for an object's data and associated metadata */ - int (*reserve_space)(struct fscache_object *object, loff_t i_size); - - /* request a backing block for a page be read or allocated in the - * cache */ - fscache_page_retrieval_func_t read_or_alloc_page; - - /* request backing blocks for a list of pages be read or allocated in - * the cache */ - fscache_pages_retrieval_func_t read_or_alloc_pages; - - /* request a backing block for a page be allocated in the cache so that - * it can be written directly */ - fscache_page_retrieval_func_t allocate_page; - - /* request backing blocks for pages be allocated in the cache so that - * they can be written directly */ - fscache_pages_retrieval_func_t allocate_pages; - - /* write a page to its backing block in the cache */ - int (*write_page)(struct fscache_storage *op, struct page *page); - - /* detach backing block from a page (optional) - * - must release the cookie lock before returning - * - may sleep - */ - void (*uncache_page)(struct fscache_object *object, - struct page *page); - - /* dissociate a cache from all the pages it was backing */ - void (*dissociate_pages)(struct fscache_cache *cache); + bool (*invalidate_cookie)(struct fscache_cookie *cookie); - /* Begin a read operation for the netfs lib */ - int (*begin_read_operation)(struct netfs_read_request *rreq, - struct fscache_retrieval *op); -}; - -extern struct fscache_cookie fscache_fsdef_index; + /* Begin an operation for the netfs lib */ + bool (*begin_operation)(struct netfs_cache_resources *cres, + enum fscache_want_state want_state); -/* - * Event list for fscache_object::{event_mask,events} - */ -enum { - FSCACHE_OBJECT_EV_NEW_CHILD, /* T if object has a new child */ - FSCACHE_OBJECT_EV_PARENT_READY, /* T if object's parent is ready */ - FSCACHE_OBJECT_EV_UPDATE, /* T if object should be updated */ - FSCACHE_OBJECT_EV_INVALIDATE, /* T if cache requested object invalidation */ - FSCACHE_OBJECT_EV_CLEARED, /* T if accessors all gone */ - FSCACHE_OBJECT_EV_ERROR, /* T if fatal error occurred during processing */ - FSCACHE_OBJECT_EV_KILL, /* T if netfs relinquished or cache withdrew object */ - NR_FSCACHE_OBJECT_EVENTS -}; - -#define FSCACHE_OBJECT_EVENTS_MASK ((1UL << NR_FSCACHE_OBJECT_EVENTS) - 1) - -/* - * States for object state machine. - */ -struct fscache_transition { - unsigned long events; - const struct fscache_state *transit_to; + /* Prepare to write to a live cache object */ + void (*prepare_to_write)(struct fscache_cookie *cookie); }; -struct fscache_state { - char name[24]; - char short_name[8]; - const struct fscache_state *(*work)(struct fscache_object *object, - int event); - const struct fscache_transition transitions[]; -}; +extern struct workqueue_struct *fscache_wq; +extern wait_queue_head_t fscache_clearance_waiters; /* - * on-disk cache file or index handle + * out-of-line cache backend functions */ -struct fscache_object { - const struct fscache_state *state; /* Object state machine state */ - const struct fscache_transition *oob_table; /* OOB state transition table */ - int debug_id; /* debugging ID */ - int n_children; /* number of child objects */ - int n_ops; /* number of extant ops on object */ - int n_obj_ops; /* number of object ops outstanding on object */ - int n_in_progress; /* number of ops in progress */ - int n_exclusive; /* number of exclusive ops queued or in progress */ - atomic_t n_reads; /* number of read ops in progress */ - spinlock_t lock; /* state and operations lock */ - - unsigned long lookup_jif; /* time at which lookup started */ - unsigned long oob_event_mask; /* OOB events this object is interested in */ - unsigned long event_mask; /* events this object is interested in */ - unsigned long events; /* events to be processed by this object - * (order is important - using fls) */ - - unsigned long flags; -#define FSCACHE_OBJECT_LOCK 0 /* T if object is busy being processed */ -#define FSCACHE_OBJECT_PENDING_WRITE 1 /* T if object has pending write */ -#define FSCACHE_OBJECT_WAITING 2 /* T if object is waiting on its parent */ -#define FSCACHE_OBJECT_IS_LIVE 3 /* T if object is not withdrawn or relinquished */ -#define FSCACHE_OBJECT_IS_LOOKED_UP 4 /* T if object has been looked up */ -#define FSCACHE_OBJECT_IS_AVAILABLE 5 /* T if object has become active */ -#define FSCACHE_OBJECT_RETIRED 6 /* T if object was retired on relinquishment */ -#define FSCACHE_OBJECT_KILLED_BY_CACHE 7 /* T if object was killed by the cache */ -#define FSCACHE_OBJECT_RUN_AFTER_DEAD 8 /* T if object has been dispatched after death */ - - struct list_head cache_link; /* link in cache->object_list */ - struct hlist_node cookie_link; /* link in cookie->backing_objects */ - struct fscache_cache *cache; /* cache that supplied this object */ - struct fscache_cookie *cookie; /* netfs's file/index object */ - struct fscache_object *parent; /* parent object */ - struct work_struct work; /* attention scheduling record */ - struct list_head dependents; /* FIFO of dependent objects */ - struct list_head dep_link; /* link in parent's dependents list */ - struct list_head pending_ops; /* unstarted operations on this object */ - pgoff_t store_limit; /* current storage limit */ - loff_t store_limit_l; /* current storage limit */ -}; - -extern void fscache_object_init(struct fscache_object *, struct fscache_cookie *, - struct fscache_cache *); -extern void fscache_object_destroy(struct fscache_object *); - -extern void fscache_object_lookup_negative(struct fscache_object *object); -extern void fscache_obtained_object(struct fscache_object *object); - -static inline bool fscache_object_is_live(struct fscache_object *object) -{ - return test_bit(FSCACHE_OBJECT_IS_LIVE, &object->flags); -} - -static inline bool fscache_object_is_dying(struct fscache_object *object) -{ - return !fscache_object_is_live(object); -} - -static inline bool fscache_object_is_available(struct fscache_object *object) -{ - return test_bit(FSCACHE_OBJECT_IS_AVAILABLE, &object->flags); -} +extern struct rw_semaphore fscache_addremove_sem; +extern struct fscache_cache *fscache_acquire_cache(const char *name); +extern void fscache_relinquish_cache(struct fscache_cache *cache); +extern int fscache_add_cache(struct fscache_cache *cache, + const struct fscache_cache_ops *ops, + void *cache_priv); +extern void fscache_withdraw_cache(struct fscache_cache *cache); +extern void fscache_withdraw_volume(struct fscache_volume *volume); +extern void fscache_withdraw_cookie(struct fscache_cookie *cookie); -static inline bool fscache_cache_is_broken(struct fscache_object *object) -{ - return test_bit(FSCACHE_IOERROR, &object->cache->flags); -} +extern void fscache_io_error(struct fscache_cache *cache); -static inline bool fscache_object_is_active(struct fscache_object *object) -{ - return fscache_object_is_available(object) && - fscache_object_is_live(object) && - !fscache_cache_is_broken(object); -} +extern void fscache_end_volume_access(struct fscache_volume *volume, + struct fscache_cookie *cookie, + enum fscache_access_trace why); + +extern struct fscache_cookie *fscache_get_cookie(struct fscache_cookie *cookie, + enum fscache_cookie_trace where); +extern void fscache_put_cookie(struct fscache_cookie *cookie, + enum fscache_cookie_trace where); +extern void fscache_end_cookie_access(struct fscache_cookie *cookie, + enum fscache_access_trace why); +extern void fscache_cookie_lookup_negative(struct fscache_cookie *cookie); +extern void fscache_resume_after_invalidation(struct fscache_cookie *cookie); +extern void fscache_caching_failed(struct fscache_cookie *cookie); +extern bool fscache_wait_for_operation(struct netfs_cache_resources *cred, + enum fscache_want_state state); /** - * fscache_object_destroyed - Note destruction of an object in a cache - * @cache: The cache from which the object came + * fscache_cookie_state - Read the state of a cookie + * @cookie: The cookie to query * - * Note the destruction and deallocation of an object record in a cache. + * Get the state of a cookie, imposing an ordering between the cookie contents + * and the state value. Paired with fscache_set_cookie_state(). */ -static inline void fscache_object_destroyed(struct fscache_cache *cache) +static inline +enum fscache_cookie_state fscache_cookie_state(struct fscache_cookie *cookie) { - if (atomic_dec_and_test(&cache->object_count)) - wake_up_all(&fscache_cache_cleared_wq); + return smp_load_acquire(&cookie->state); } /** - * fscache_object_lookup_error - Note an object encountered an error - * @object: The object on which the error was encountered + * fscache_get_key - Get a pointer to the cookie key + * @cookie: The cookie to query * - * Note that an object encountered a fatal error (usually an I/O error) and - * that it should be withdrawn as soon as possible. + * Return a pointer to the where a cookie's key is stored. */ -static inline void fscache_object_lookup_error(struct fscache_object *object) +static inline void *fscache_get_key(struct fscache_cookie *cookie) { - set_bit(FSCACHE_OBJECT_EV_ERROR, &object->events); + if (cookie->key_len <= sizeof(cookie->inline_key)) + return cookie->inline_key; + else + return cookie->key; } -/** - * fscache_set_store_limit - Set the maximum size to be stored in an object - * @object: The object to set the maximum on - * @i_size: The limit to set in bytes - * - * Set the maximum size an object is permitted to reach, implying the highest - * byte that may be written. Intended to be called by the attr_changed() op. - * - * See Documentation/filesystems/caching/backend-api.rst for a complete - * description. - */ -static inline -void fscache_set_store_limit(struct fscache_object *object, loff_t i_size) +static inline struct fscache_cookie *fscache_cres_cookie(struct netfs_cache_resources *cres) { - object->store_limit_l = i_size; - object->store_limit = i_size >> PAGE_SHIFT; - if (i_size & ~PAGE_MASK) - object->store_limit++; + return cres->cache_priv; } /** - * fscache_end_io - End a retrieval operation on a page - * @op: The FS-Cache operation covering the retrieval - * @page: The page that was to be fetched - * @error: The error code (0 if successful) + * fscache_count_object - Tell fscache that an object has been added + * @cache: The cache to account to * - * Note the end of an operation to retrieve a page, as covered by a particular - * operation record. + * Tell fscache that an object has been added to the cache. This prevents the + * cache from tearing down the cache structure until the object is uncounted. */ -static inline void fscache_end_io(struct fscache_retrieval *op, - struct page *page, int error) +static inline void fscache_count_object(struct fscache_cache *cache) { - op->end_io_func(page, op->context, error); -} - -static inline void __fscache_use_cookie(struct fscache_cookie *cookie) -{ - atomic_inc(&cookie->n_active); + atomic_inc(&cache->object_count); } /** - * fscache_use_cookie - Request usage of cookie attached to an object - * @object: Object description - * - * Request usage of the cookie attached to an object. NULL is returned if the - * relinquishment had reduced the cookie usage count to 0. + * fscache_uncount_object - Tell fscache that an object has been removed + * @cache: The cache to account to + * + * Tell fscache that an object has been removed from the cache and will no + * longer be accessed. After this point, the cache cookie may be destroyed. */ -static inline bool fscache_use_cookie(struct fscache_object *object) -{ - struct fscache_cookie *cookie = object->cookie; - return atomic_inc_not_zero(&cookie->n_active) != 0; -} - -static inline bool __fscache_unuse_cookie(struct fscache_cookie *cookie) -{ - return atomic_dec_and_test(&cookie->n_active); -} - -static inline void __fscache_wake_unused_cookie(struct fscache_cookie *cookie) +static inline void fscache_uncount_object(struct fscache_cache *cache) { - wake_up_var(&cookie->n_active); + if (atomic_dec_and_test(&cache->object_count)) + wake_up_all(&fscache_clearance_waiters); } /** - * fscache_unuse_cookie - Cease usage of cookie attached to an object - * @object: Object description - * - * Cease usage of the cookie attached to an object. When the users count - * reaches zero then the cookie relinquishment will be permitted to proceed. - */ -static inline void fscache_unuse_cookie(struct fscache_object *object) -{ - struct fscache_cookie *cookie = object->cookie; - if (__fscache_unuse_cookie(cookie)) - __fscache_wake_unused_cookie(cookie); -} - -/* - * out-of-line cache backend functions - */ -extern __printf(3, 4) -void fscache_init_cache(struct fscache_cache *cache, - const struct fscache_cache_ops *ops, - const char *idfmt, ...); - -extern int fscache_add_cache(struct fscache_cache *cache, - struct fscache_object *fsdef, - const char *tagname); -extern void fscache_withdraw_cache(struct fscache_cache *cache); - -extern void fscache_io_error(struct fscache_cache *cache); - -extern void fscache_mark_page_cached(struct fscache_retrieval *op, - struct page *page); - -extern void fscache_mark_pages_cached(struct fscache_retrieval *op, - struct pagevec *pagevec); - -extern bool fscache_object_sleep_till_congested(signed long *timeoutp); - -extern enum fscache_checkaux fscache_check_aux(struct fscache_object *object, - const void *data, - uint16_t datalen, - loff_t object_size); - -extern void fscache_object_retrying_stale(struct fscache_object *object); - -enum fscache_why_object_killed { - FSCACHE_OBJECT_IS_STALE, - FSCACHE_OBJECT_NO_SPACE, - FSCACHE_OBJECT_WAS_RETIRED, - FSCACHE_OBJECT_WAS_CULLED, -}; -extern void fscache_object_mark_killed(struct fscache_object *object, - enum fscache_why_object_killed why); + * fscache_wait_for_objects - Wait for all objects to be withdrawn + * @cache: The cache to query + * + * Wait for all extant objects in a cache to finish being withdrawn + * and go away. + */ +static inline void fscache_wait_for_objects(struct fscache_cache *cache) +{ + wait_event(fscache_clearance_waiters, + atomic_read(&cache->object_count) == 0); +} + +#ifdef CONFIG_FSCACHE_STATS +extern atomic_t fscache_n_read; +extern atomic_t fscache_n_write; +extern atomic_t fscache_n_no_write_space; +extern atomic_t fscache_n_no_create_space; +extern atomic_t fscache_n_culled; +#define fscache_count_read() atomic_inc(&fscache_n_read) +#define fscache_count_write() atomic_inc(&fscache_n_write) +#define fscache_count_no_write_space() atomic_inc(&fscache_n_no_write_space) +#define fscache_count_no_create_space() atomic_inc(&fscache_n_no_create_space) +#define fscache_count_culled() atomic_inc(&fscache_n_culled) +#else +#define fscache_count_read() do {} while(0) +#define fscache_count_write() do {} while(0) +#define fscache_count_no_write_space() do {} while(0) +#define fscache_count_no_create_space() do {} while(0) +#define fscache_count_culled() do {} while(0) +#endif #endif /* _LINUX_FSCACHE_CACHE_H */ diff --git a/include/linux/fscache.h b/include/linux/fscache.h index 3b2282c157f7..36e5dd84cf59 100644 --- a/include/linux/fscache.h +++ b/include/linux/fscache.h @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0-or-later */ /* General filesystem caching interface * - * Copyright (C) 2004-2007 Red Hat, Inc. All Rights Reserved. + * Copyright (C) 2021 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) * * NOTE!!! See: @@ -15,146 +15,128 @@ #define _LINUX_FSCACHE_H #include <linux/fs.h> -#include <linux/list.h> -#include <linux/pagemap.h> -#include <linux/pagevec.h> -#include <linux/list_bl.h> #include <linux/netfs.h> +#include <linux/writeback.h> #if defined(CONFIG_FSCACHE) || defined(CONFIG_FSCACHE_MODULE) +#define __fscache_available (1) #define fscache_available() (1) +#define fscache_volume_valid(volume) (volume) #define fscache_cookie_valid(cookie) (cookie) +#define fscache_resources_valid(cres) ((cres)->cache_priv) +#define fscache_cookie_enabled(cookie) (cookie && !test_bit(FSCACHE_COOKIE_DISABLED, &cookie->flags)) #else +#define __fscache_available (0) #define fscache_available() (0) +#define fscache_volume_valid(volume) (0) #define fscache_cookie_valid(cookie) (0) +#define fscache_resources_valid(cres) (false) +#define fscache_cookie_enabled(cookie) (0) #endif - -/* pattern used to fill dead space in an index entry */ -#define FSCACHE_INDEX_DEADFILL_PATTERN 0x79 - -struct pagevec; -struct fscache_cache_tag; struct fscache_cookie; -struct fscache_netfs; -struct netfs_read_request; - -typedef void (*fscache_rw_complete_t)(struct page *page, - void *context, - int error); - -/* result of index entry consultation */ -enum fscache_checkaux { - FSCACHE_CHECKAUX_OKAY, /* entry okay as is */ - FSCACHE_CHECKAUX_NEEDS_UPDATE, /* entry requires update */ - FSCACHE_CHECKAUX_OBSOLETE, /* entry requires deletion */ -}; -/* - * fscache cookie definition - */ -struct fscache_cookie_def { - /* name of cookie type */ - char name[16]; - - /* cookie type */ - uint8_t type; -#define FSCACHE_COOKIE_TYPE_INDEX 0 -#define FSCACHE_COOKIE_TYPE_DATAFILE 1 - - /* select the cache into which to insert an entry in this index - * - optional - * - should return a cache identifier or NULL to cause the cache to be - * inherited from the parent if possible or the first cache picked - * for a non-index file if not - */ - struct fscache_cache_tag *(*select_cache)( - const void *parent_netfs_data, - const void *cookie_netfs_data); - - /* consult the netfs about the state of an object - * - this function can be absent if the index carries no state data - * - the netfs data from the cookie being used as the target is - * presented, as is the auxiliary data and the object size - */ - enum fscache_checkaux (*check_aux)(void *cookie_netfs_data, - const void *data, - uint16_t datalen, - loff_t object_size); - - /* get an extra reference on a read context - * - this function can be absent if the completion function doesn't - * require a context - */ - void (*get_context)(void *cookie_netfs_data, void *context); +#define FSCACHE_ADV_SINGLE_CHUNK 0x01 /* The object is a single chunk of data */ +#define FSCACHE_ADV_WRITE_CACHE 0x00 /* Do cache if written to locally */ +#define FSCACHE_ADV_WRITE_NOCACHE 0x02 /* Don't cache if written to locally */ +#define FSCACHE_ADV_WANT_CACHE_SIZE 0x04 /* Retrieve cache size at runtime */ - /* release an extra reference on a read context - * - this function can be absent if the completion function doesn't - * require a context - */ - void (*put_context)(void *cookie_netfs_data, void *context); +#define FSCACHE_INVAL_DIO_WRITE 0x01 /* Invalidate due to DIO write */ - /* indicate page that now have cache metadata retained - * - this function should mark the specified page as now being cached - * - the page will have been marked with PG_fscache before this is - * called, so this is optional - */ - void (*mark_page_cached)(void *cookie_netfs_data, - struct address_space *mapping, - struct page *page); +enum fscache_want_state { + FSCACHE_WANT_PARAMS, + FSCACHE_WANT_WRITE, + FSCACHE_WANT_READ, }; /* - * fscache cached network filesystem type - * - name, version and ops must be filled in before registration - * - all other fields will be set during registration + * Data object state. + */ +enum fscache_cookie_state { + FSCACHE_COOKIE_STATE_QUIESCENT, /* The cookie is uncached */ + FSCACHE_COOKIE_STATE_LOOKING_UP, /* The cache object is being looked up */ + FSCACHE_COOKIE_STATE_CREATING, /* The cache object is being created */ + FSCACHE_COOKIE_STATE_ACTIVE, /* The cache is active, readable and writable */ + FSCACHE_COOKIE_STATE_INVALIDATING, /* The cache is being invalidated */ + FSCACHE_COOKIE_STATE_FAILED, /* The cache failed, withdraw to clear */ + FSCACHE_COOKIE_STATE_LRU_DISCARDING, /* The cookie is being discarded by the LRU */ + FSCACHE_COOKIE_STATE_WITHDRAWING, /* The cookie is being withdrawn */ + FSCACHE_COOKIE_STATE_RELINQUISHING, /* The cookie is being relinquished */ + FSCACHE_COOKIE_STATE_DROPPED, /* The cookie has been dropped */ +#define FSCACHE_COOKIE_STATE__NR (FSCACHE_COOKIE_STATE_DROPPED + 1) +} __attribute__((mode(byte))); + +/* + * Volume representation cookie. */ -struct fscache_netfs { - uint32_t version; /* indexing version */ - const char *name; /* filesystem name */ - struct fscache_cookie *primary_index; +struct fscache_volume { + refcount_t ref; + atomic_t n_cookies; /* Number of data cookies in volume */ + atomic_t n_accesses; /* Number of cache accesses in progress */ + unsigned int debug_id; + unsigned int key_hash; /* Hash of key string */ + char *key; /* Volume ID, eg. "afs@example.com@1234" */ + struct list_head proc_link; /* Link in /proc/fs/fscache/volumes */ + struct hlist_bl_node hash_link; /* Link in hash table */ + struct work_struct work; + struct fscache_cache *cache; /* The cache in which this resides */ + void *cache_priv; /* Cache private data */ + spinlock_t lock; + unsigned long flags; +#define FSCACHE_VOLUME_RELINQUISHED 0 /* Volume is being cleaned up */ +#define FSCACHE_VOLUME_INVALIDATE 1 /* Volume was invalidated */ +#define FSCACHE_VOLUME_COLLIDED_WITH 2 /* Volume was collided with */ +#define FSCACHE_VOLUME_ACQUIRE_PENDING 3 /* Volume is waiting to complete acquisition */ +#define FSCACHE_VOLUME_CREATING 4 /* Volume is being created on disk */ + u8 coherency_len; /* Length of the coherency data */ + u8 coherency[]; /* Coherency data */ }; /* - * data file or index object cookie + * Data file representation cookie. * - a file will only appear in one cache * - a request to cache a file may or may not be honoured, subject to * constraints such as disk space * - indices are created on disk just-in-time */ struct fscache_cookie { - refcount_t ref; /* number of users of this cookie */ - atomic_t n_children; /* number of children of this cookie */ - atomic_t n_active; /* number of active users of netfs ptrs */ + refcount_t ref; + atomic_t n_active; /* number of active users of cookie */ + atomic_t n_accesses; /* Number of cache accesses in progress */ unsigned int debug_id; + unsigned int inval_counter; /* Number of invalidations made */ spinlock_t lock; - spinlock_t stores_lock; /* lock on page store tree */ - struct hlist_head backing_objects; /* object(s) backing this file/index */ - const struct fscache_cookie_def *def; /* definition */ - struct fscache_cookie *parent; /* parent of this entry */ + struct fscache_volume *volume; /* Parent volume of this file. */ + void *cache_priv; /* Cache-side representation */ struct hlist_bl_node hash_link; /* Link in hash table */ struct list_head proc_link; /* Link in proc list */ - void *netfs_data; /* back pointer to netfs */ - struct radix_tree_root stores; /* pages to be stored on this cookie */ -#define FSCACHE_COOKIE_PENDING_TAG 0 /* pages tag: pending write to cache */ -#define FSCACHE_COOKIE_STORING_TAG 1 /* pages tag: writing to cache */ - + struct list_head commit_link; /* Link in commit queue */ + struct work_struct work; /* Commit/relinq/withdraw work */ + loff_t object_size; /* Size of the netfs object */ + unsigned long unused_at; /* Time at which unused (jiffies) */ unsigned long flags; -#define FSCACHE_COOKIE_LOOKING_UP 0 /* T if non-index cookie being looked up still */ -#define FSCACHE_COOKIE_NO_DATA_YET 1 /* T if new object with no cached data yet */ -#define FSCACHE_COOKIE_UNAVAILABLE 2 /* T if cookie is unavailable (error, etc) */ -#define FSCACHE_COOKIE_INVALIDATING 3 /* T if cookie is being invalidated */ -#define FSCACHE_COOKIE_RELINQUISHED 4 /* T if cookie has been relinquished */ -#define FSCACHE_COOKIE_ENABLED 5 /* T if cookie is enabled */ -#define FSCACHE_COOKIE_ENABLEMENT_LOCK 6 /* T if cookie is being en/disabled */ -#define FSCACHE_COOKIE_AUX_UPDATED 8 /* T if the auxiliary data was updated */ -#define FSCACHE_COOKIE_ACQUIRED 9 /* T if cookie is in use */ -#define FSCACHE_COOKIE_RELINQUISHING 10 /* T if cookie is being relinquished */ - - u8 type; /* Type of object */ +#define FSCACHE_COOKIE_RELINQUISHED 0 /* T if cookie has been relinquished */ +#define FSCACHE_COOKIE_RETIRED 1 /* T if this cookie has retired on relinq */ +#define FSCACHE_COOKIE_IS_CACHING 2 /* T if this cookie is cached */ +#define FSCACHE_COOKIE_NO_DATA_TO_READ 3 /* T if this cookie has nothing to read */ +#define FSCACHE_COOKIE_NEEDS_UPDATE 4 /* T if attrs have been updated */ +#define FSCACHE_COOKIE_HAS_BEEN_CACHED 5 /* T if cookie needs withdraw-on-relinq */ +#define FSCACHE_COOKIE_DISABLED 6 /* T if cookie has been disabled */ +#define FSCACHE_COOKIE_LOCAL_WRITE 7 /* T if cookie has been modified locally */ +#define FSCACHE_COOKIE_NO_ACCESS_WAKE 8 /* T if no wake when n_accesses goes 0 */ +#define FSCACHE_COOKIE_DO_RELINQUISH 9 /* T if this cookie needs relinquishment */ +#define FSCACHE_COOKIE_DO_WITHDRAW 10 /* T if this cookie needs withdrawing */ +#define FSCACHE_COOKIE_DO_LRU_DISCARD 11 /* T if this cookie needs LRU discard */ +#define FSCACHE_COOKIE_DO_PREP_TO_WRITE 12 /* T if cookie needs write preparation */ +#define FSCACHE_COOKIE_HAVE_DATA 13 /* T if this cookie has data stored */ +#define FSCACHE_COOKIE_IS_HASHED 14 /* T if this cookie is hashed */ +#define FSCACHE_COOKIE_DO_INVALIDATE 15 /* T if cookie needs invalidation */ + + enum fscache_cookie_state state; + u8 advice; /* FSCACHE_ADV_* */ u8 key_len; /* Length of index key */ u8 aux_len; /* Length of auxiliary data */ - u32 key_hash; /* Hash of parent, type, key, len */ + u32 key_hash; /* Hash of volume, key, len */ union { void *key; /* Index key */ u8 inline_key[16]; /* - If the key is short enough */ @@ -165,11 +147,6 @@ struct fscache_cookie { }; }; -static inline bool fscache_cookie_enabled(struct fscache_cookie *cookie) -{ - return fscache_cookie_valid(cookie) && test_bit(FSCACHE_COOKIE_ENABLED, &cookie->flags); -} - /* * slow-path functions for when there is actually caching available, and the * netfs does actually have a valid token @@ -177,699 +154,542 @@ static inline bool fscache_cookie_enabled(struct fscache_cookie *cookie) * - these are undefined symbols when FS-Cache is not configured and the * optimiser takes care of not using them */ -extern int __fscache_register_netfs(struct fscache_netfs *); -extern void __fscache_unregister_netfs(struct fscache_netfs *); -extern struct fscache_cache_tag *__fscache_lookup_cache_tag(const char *); -extern void __fscache_release_cache_tag(struct fscache_cache_tag *); +extern struct fscache_volume *__fscache_acquire_volume(const char *, const char *, + const void *, size_t); +extern void __fscache_relinquish_volume(struct fscache_volume *, const void *, bool); extern struct fscache_cookie *__fscache_acquire_cookie( - struct fscache_cookie *, - const struct fscache_cookie_def *, + struct fscache_volume *, + u8, const void *, size_t, const void *, size_t, - void *, loff_t, bool); -extern void __fscache_relinquish_cookie(struct fscache_cookie *, const void *, bool); -extern int __fscache_check_consistency(struct fscache_cookie *, const void *); -extern void __fscache_update_cookie(struct fscache_cookie *, const void *); -extern int __fscache_attr_changed(struct fscache_cookie *); -extern void __fscache_invalidate(struct fscache_cookie *); -extern void __fscache_wait_on_invalidate(struct fscache_cookie *); - -#ifdef FSCACHE_USE_NEW_IO_API -extern int __fscache_begin_read_operation(struct netfs_read_request *, struct fscache_cookie *); -#else -extern int __fscache_read_or_alloc_page(struct fscache_cookie *, - struct page *, - fscache_rw_complete_t, - void *, - gfp_t); -extern int __fscache_read_or_alloc_pages(struct fscache_cookie *, - struct address_space *, - struct list_head *, - unsigned *, - fscache_rw_complete_t, - void *, - gfp_t); -extern int __fscache_alloc_page(struct fscache_cookie *, struct page *, gfp_t); -extern int __fscache_write_page(struct fscache_cookie *, struct page *, loff_t, gfp_t); -extern void __fscache_uncache_page(struct fscache_cookie *, struct page *); -extern bool __fscache_check_page_write(struct fscache_cookie *, struct page *); -extern void __fscache_wait_on_page_write(struct fscache_cookie *, struct page *); -extern bool __fscache_maybe_release_page(struct fscache_cookie *, struct page *, - gfp_t); -extern void __fscache_uncache_all_inode_pages(struct fscache_cookie *, - struct inode *); -extern void __fscache_readpages_cancel(struct fscache_cookie *cookie, - struct list_head *pages); -#endif /* FSCACHE_USE_NEW_IO_API */ - -extern void __fscache_disable_cookie(struct fscache_cookie *, const void *, bool); -extern void __fscache_enable_cookie(struct fscache_cookie *, const void *, loff_t, - bool (*)(void *), void *); + loff_t); +extern void __fscache_use_cookie(struct fscache_cookie *, bool); +extern void __fscache_unuse_cookie(struct fscache_cookie *, const void *, const loff_t *); +extern void __fscache_relinquish_cookie(struct fscache_cookie *, bool); +extern void __fscache_resize_cookie(struct fscache_cookie *, loff_t); +extern void __fscache_invalidate(struct fscache_cookie *, const void *, loff_t, unsigned int); +extern int __fscache_begin_read_operation(struct netfs_cache_resources *, struct fscache_cookie *); +extern int __fscache_begin_write_operation(struct netfs_cache_resources *, struct fscache_cookie *); + +extern void __fscache_write_to_cache(struct fscache_cookie *, struct address_space *, + loff_t, size_t, loff_t, netfs_io_terminated_t, void *, + bool); +extern void __fscache_clear_page_bits(struct address_space *, loff_t, size_t); /** - * fscache_register_netfs - Register a filesystem as desiring caching services - * @netfs: The description of the filesystem + * fscache_acquire_volume - Register a volume as desiring caching services + * @volume_key: An identification string for the volume + * @cache_name: The name of the cache to use (or NULL for the default) + * @coherency_data: Piece of arbitrary coherency data to check (or NULL) + * @coherency_len: The size of the coherency data * - * Register a filesystem as desiring caching services if they're available. + * Register a volume as desiring caching services if they're available. The + * caller must provide an identifier for the volume and may also indicate which + * cache it should be in. If a preexisting volume entry is found in the cache, + * the coherency data must match otherwise the entry will be invalidated. * - * See Documentation/filesystems/caching/netfs-api.rst for a complete - * description. + * Returns a cookie pointer on success, -ENOMEM if out of memory or -EBUSY if a + * cache volume of that name is already acquired. Note that "NULL" is a valid + * cookie pointer and can be returned if caching is refused. */ static inline -int fscache_register_netfs(struct fscache_netfs *netfs) +struct fscache_volume *fscache_acquire_volume(const char *volume_key, + const char *cache_name, + const void *coherency_data, + size_t coherency_len) { - if (fscache_available()) - return __fscache_register_netfs(netfs); - else - return 0; + if (!fscache_available()) + return NULL; + return __fscache_acquire_volume(volume_key, cache_name, + coherency_data, coherency_len); } /** - * fscache_unregister_netfs - Indicate that a filesystem no longer desires - * caching services - * @netfs: The description of the filesystem + * fscache_relinquish_volume - Cease caching a volume + * @volume: The volume cookie + * @coherency_data: Piece of arbitrary coherency data to set (or NULL) + * @invalidate: True if the volume should be invalidated * - * Indicate that a filesystem no longer desires caching services for the - * moment. - * - * See Documentation/filesystems/caching/netfs-api.rst for a complete - * description. + * Indicate that a filesystem no longer desires caching services for a volume. + * The caller must have relinquished all file cookies prior to calling this. + * The stored coherency data is updated. */ static inline -void fscache_unregister_netfs(struct fscache_netfs *netfs) +void fscache_relinquish_volume(struct fscache_volume *volume, + const void *coherency_data, + bool invalidate) { - if (fscache_available()) - __fscache_unregister_netfs(netfs); + if (fscache_volume_valid(volume)) + __fscache_relinquish_volume(volume, coherency_data, invalidate); } /** - * fscache_lookup_cache_tag - Look up a cache tag - * @name: The name of the tag to search for + * fscache_acquire_cookie - Acquire a cookie to represent a cache object + * @volume: The volume in which to locate/create this cookie + * @advice: Advice flags (FSCACHE_COOKIE_ADV_*) + * @index_key: The index key for this cookie + * @index_key_len: Size of the index key + * @aux_data: The auxiliary data for the cookie (may be NULL) + * @aux_data_len: Size of the auxiliary data buffer + * @object_size: The initial size of object * - * Acquire a specific cache referral tag that can be used to select a specific - * cache in which to cache an index. + * Acquire a cookie to represent a data file within the given cache volume. * * See Documentation/filesystems/caching/netfs-api.rst for a complete * description. */ static inline -struct fscache_cache_tag *fscache_lookup_cache_tag(const char *name) +struct fscache_cookie *fscache_acquire_cookie(struct fscache_volume *volume, + u8 advice, + const void *index_key, + size_t index_key_len, + const void *aux_data, + size_t aux_data_len, + loff_t object_size) { - if (fscache_available()) - return __fscache_lookup_cache_tag(name); - else + if (!fscache_volume_valid(volume)) return NULL; + return __fscache_acquire_cookie(volume, advice, + index_key, index_key_len, + aux_data, aux_data_len, + object_size); } /** - * fscache_release_cache_tag - Release a cache tag - * @tag: The tag to release - * - * Release a reference to a cache referral tag previously looked up. + * fscache_use_cookie - Request usage of cookie attached to an object + * @cookie: The cookie representing the cache object + * @will_modify: If cache is expected to be modified locally * - * See Documentation/filesystems/caching/netfs-api.rst for a complete - * description. + * Request usage of the cookie attached to an object. The caller should tell + * the cache if the object's contents are about to be modified locally and then + * the cache can apply the policy that has been set to handle this case. */ -static inline -void fscache_release_cache_tag(struct fscache_cache_tag *tag) +static inline void fscache_use_cookie(struct fscache_cookie *cookie, + bool will_modify) { - if (fscache_available()) - __fscache_release_cache_tag(tag); + if (fscache_cookie_valid(cookie)) + __fscache_use_cookie(cookie, will_modify); } /** - * fscache_acquire_cookie - Acquire a cookie to represent a cache object - * @parent: The cookie that's to be the parent of this one - * @def: A description of the cache object, including callback operations - * @index_key: The index key for this cookie - * @index_key_len: Size of the index key - * @aux_data: The auxiliary data for the cookie (may be NULL) - * @aux_data_len: Size of the auxiliary data buffer - * @netfs_data: An arbitrary piece of data to be kept in the cookie to - * represent the cache object to the netfs - * @object_size: The initial size of object - * @enable: Whether or not to enable a data cookie immediately - * - * This function is used to inform FS-Cache about part of an index hierarchy - * that can be used to locate files. This is done by requesting a cookie for - * each index in the path to the file. + * fscache_unuse_cookie - Cease usage of cookie attached to an object + * @cookie: The cookie representing the cache object + * @aux_data: Updated auxiliary data (or NULL) + * @object_size: Revised size of the object (or NULL) * - * See Documentation/filesystems/caching/netfs-api.rst for a complete - * description. + * Cease usage of the cookie attached to an object. When the users count + * reaches zero then the cookie relinquishment will be permitted to proceed. */ -static inline -struct fscache_cookie *fscache_acquire_cookie( - struct fscache_cookie *parent, - const struct fscache_cookie_def *def, - const void *index_key, - size_t index_key_len, - const void *aux_data, - size_t aux_data_len, - void *netfs_data, - loff_t object_size, - bool enable) +static inline void fscache_unuse_cookie(struct fscache_cookie *cookie, + const void *aux_data, + const loff_t *object_size) { - if (fscache_cookie_valid(parent) && fscache_cookie_enabled(parent)) - return __fscache_acquire_cookie(parent, def, - index_key, index_key_len, - aux_data, aux_data_len, - netfs_data, object_size, enable); - else - return NULL; + if (fscache_cookie_valid(cookie)) + __fscache_unuse_cookie(cookie, aux_data, object_size); } /** * fscache_relinquish_cookie - Return the cookie to the cache, maybe discarding * it * @cookie: The cookie being returned - * @aux_data: The updated auxiliary data for the cookie (may be NULL) * @retire: True if the cache object the cookie represents is to be discarded * * This function returns a cookie to the cache, forcibly discarding the - * associated cache object if retire is set to true. The opportunity is - * provided to update the auxiliary data in the cache before the object is - * disconnected. + * associated cache object if retire is set to true. * * See Documentation/filesystems/caching/netfs-api.rst for a complete * description. */ static inline -void fscache_relinquish_cookie(struct fscache_cookie *cookie, - const void *aux_data, - bool retire) +void fscache_relinquish_cookie(struct fscache_cookie *cookie, bool retire) { if (fscache_cookie_valid(cookie)) - __fscache_relinquish_cookie(cookie, aux_data, retire); + __fscache_relinquish_cookie(cookie, retire); } -/** - * fscache_check_consistency - Request validation of a cache's auxiliary data - * @cookie: The cookie representing the cache object - * @aux_data: The updated auxiliary data for the cookie (may be NULL) - * - * Request an consistency check from fscache, which passes the request to the - * backing cache. The auxiliary data on the cookie will be updated first if - * @aux_data is set. - * - * Returns 0 if consistent and -ESTALE if inconsistent. May also - * return -ENOMEM and -ERESTARTSYS. +/* + * Find the auxiliary data on a cookie. */ -static inline -int fscache_check_consistency(struct fscache_cookie *cookie, - const void *aux_data) +static inline void *fscache_get_aux(struct fscache_cookie *cookie) { - if (fscache_cookie_valid(cookie) && fscache_cookie_enabled(cookie)) - return __fscache_check_consistency(cookie, aux_data); + if (cookie->aux_len <= sizeof(cookie->inline_aux)) + return cookie->inline_aux; else - return 0; + return cookie->aux; } -/** - * fscache_update_cookie - Request that a cache object be updated - * @cookie: The cookie representing the cache object - * @aux_data: The updated auxiliary data for the cookie (may be NULL) - * - * Request an update of the index data for the cache object associated with the - * cookie. The auxiliary data on the cookie will be updated first if @aux_data - * is set. - * - * See Documentation/filesystems/caching/netfs-api.rst for a complete - * description. +/* + * Update the auxiliary data on a cookie. */ static inline -void fscache_update_cookie(struct fscache_cookie *cookie, const void *aux_data) +void fscache_update_aux(struct fscache_cookie *cookie, + const void *aux_data, const loff_t *object_size) { - if (fscache_cookie_valid(cookie) && fscache_cookie_enabled(cookie)) - __fscache_update_cookie(cookie, aux_data); + void *p = fscache_get_aux(cookie); + + if (aux_data && p) + memcpy(p, aux_data, cookie->aux_len); + if (object_size) + cookie->object_size = *object_size; } -/** - * fscache_pin_cookie - Pin a data-storage cache object in its cache - * @cookie: The cookie representing the cache object - * - * Permit data-storage cache objects to be pinned in the cache. - * - * See Documentation/filesystems/caching/netfs-api.rst for a complete - * description. - */ +#ifdef CONFIG_FSCACHE_STATS +extern atomic_t fscache_n_updates; +#endif + static inline -int fscache_pin_cookie(struct fscache_cookie *cookie) +void __fscache_update_cookie(struct fscache_cookie *cookie, const void *aux_data, + const loff_t *object_size) { - return -ENOBUFS; +#ifdef CONFIG_FSCACHE_STATS + atomic_inc(&fscache_n_updates); +#endif + fscache_update_aux(cookie, aux_data, object_size); + smp_wmb(); + set_bit(FSCACHE_COOKIE_NEEDS_UPDATE, &cookie->flags); } /** - * fscache_pin_cookie - Unpin a data-storage cache object in its cache + * fscache_update_cookie - Request that a cache object be updated * @cookie: The cookie representing the cache object + * @aux_data: The updated auxiliary data for the cookie (may be NULL) + * @object_size: The current size of the object (may be NULL) * - * Permit data-storage cache objects to be unpinned from the cache. + * Request an update of the index data for the cache object associated with the + * cookie. The auxiliary data on the cookie will be updated first if @aux_data + * is set and the object size will be updated and the object possibly trimmed + * if @object_size is set. * * See Documentation/filesystems/caching/netfs-api.rst for a complete * description. */ static inline -void fscache_unpin_cookie(struct fscache_cookie *cookie) +void fscache_update_cookie(struct fscache_cookie *cookie, const void *aux_data, + const loff_t *object_size) { + if (fscache_cookie_enabled(cookie)) + __fscache_update_cookie(cookie, aux_data, object_size); } /** - * fscache_attr_changed - Notify cache that an object's attributes changed + * fscache_resize_cookie - Request that a cache object be resized * @cookie: The cookie representing the cache object + * @new_size: The new size of the object (may be NULL) * - * Send a notification to the cache indicating that an object's attributes have - * changed. This includes the data size. These attributes will be obtained - * through the get_attr() cookie definition op. + * Request that the size of an object be changed. * * See Documentation/filesystems/caching/netfs-api.rst for a complete * description. */ static inline -int fscache_attr_changed(struct fscache_cookie *cookie) +void fscache_resize_cookie(struct fscache_cookie *cookie, loff_t new_size) { - if (fscache_cookie_valid(cookie) && fscache_cookie_enabled(cookie)) - return __fscache_attr_changed(cookie); - else - return -ENOBUFS; + if (fscache_cookie_enabled(cookie)) + __fscache_resize_cookie(cookie, new_size); } /** * fscache_invalidate - Notify cache that an object needs invalidation * @cookie: The cookie representing the cache object + * @aux_data: The updated auxiliary data for the cookie (may be NULL) + * @size: The revised size of the object. + * @flags: Invalidation flags (FSCACHE_INVAL_*) * * Notify the cache that an object is needs to be invalidated and that it - * should abort any retrievals or stores it is doing on the cache. The object - * is then marked non-caching until such time as the invalidation is complete. + * should abort any retrievals or stores it is doing on the cache. This + * increments inval_counter on the cookie which can be used by the caller to + * reconsider I/O requests as they complete. * - * This can be called with spinlocks held. + * If @flags has FSCACHE_INVAL_DIO_WRITE set, this indicates that this is due + * to a direct I/O write and will cause caching to be disabled on this cookie + * until it is completely unused. * * See Documentation/filesystems/caching/netfs-api.rst for a complete * description. */ static inline -void fscache_invalidate(struct fscache_cookie *cookie) +void fscache_invalidate(struct fscache_cookie *cookie, + const void *aux_data, loff_t size, unsigned int flags) { - if (fscache_cookie_valid(cookie) && fscache_cookie_enabled(cookie)) - __fscache_invalidate(cookie); + if (fscache_cookie_enabled(cookie)) + __fscache_invalidate(cookie, aux_data, size, flags); } /** - * fscache_wait_on_invalidate - Wait for invalidation to complete - * @cookie: The cookie representing the cache object - * - * Wait for the invalidation of an object to complete. + * fscache_operation_valid - Return true if operations resources are usable + * @cres: The resources to check. * - * See Documentation/filesystems/caching/netfs-api.rst for a complete - * description. + * Returns a pointer to the operations table if usable or NULL if not. */ static inline -void fscache_wait_on_invalidate(struct fscache_cookie *cookie) +const struct netfs_cache_ops *fscache_operation_valid(const struct netfs_cache_resources *cres) { - if (fscache_cookie_valid(cookie)) - __fscache_wait_on_invalidate(cookie); + return fscache_resources_valid(cres) ? cres->ops : NULL; } /** - * fscache_reserve_space - Reserve data space for a cached object - * @cookie: The cookie representing the cache object - * @i_size: The amount of space to be reserved - * - * Reserve an amount of space in the cache for the cache object attached to a - * cookie so that a write to that object within the space can always be - * honoured. - * - * See Documentation/filesystems/caching/netfs-api.rst for a complete - * description. - */ -static inline -int fscache_reserve_space(struct fscache_cookie *cookie, loff_t size) -{ - return -ENOBUFS; -} - -#ifdef FSCACHE_USE_NEW_IO_API - -/** * fscache_begin_read_operation - Begin a read operation for the netfs lib - * @rreq: The read request being undertaken + * @cres: The cache resources for the read being performed * @cookie: The cookie representing the cache object * - * Begin a read operation on behalf of the netfs helper library. @rreq - * indicates the read request to which the operation state should be attached; - * @cookie indicates the cache object that will be accessed. + * Begin a read operation on behalf of the netfs helper library. @cres + * indicates the cache resources to which the operation state should be + * attached; @cookie indicates the cache object that will be accessed. * * This is intended to be called from the ->begin_cache_operation() netfs lib * operation as implemented by the network filesystem. * + * @cres->inval_counter is set from @cookie->inval_counter for comparison at + * the end of the operation. This allows invalidation during the operation to + * be detected by the caller. + * * Returns: * * 0 - Success * * -ENOBUFS - No caching available * * Other error code from the cache, such as -ENOMEM. */ static inline -int fscache_begin_read_operation(struct netfs_read_request *rreq, +int fscache_begin_read_operation(struct netfs_cache_resources *cres, struct fscache_cookie *cookie) { - if (fscache_cookie_valid(cookie) && fscache_cookie_enabled(cookie)) - return __fscache_begin_read_operation(rreq, cookie); + if (fscache_cookie_enabled(cookie)) + return __fscache_begin_read_operation(cres, cookie); return -ENOBUFS; } -#else /* FSCACHE_USE_NEW_IO_API */ - /** - * fscache_read_or_alloc_page - Read a page from the cache or allocate a block - * in which to store it - * @cookie: The cookie representing the cache object - * @page: The netfs page to fill if possible - * @end_io_func: The callback to invoke when and if the page is filled - * @context: An arbitrary piece of data to pass on to end_io_func() - * @gfp: The conditions under which memory allocation should be made - * - * Read a page from the cache, or if that's not possible make a potential - * one-block reservation in the cache into which the page may be stored once - * fetched from the server. - * - * If the page is not backed by the cache object, or if it there's some reason - * it can't be, -ENOBUFS will be returned and nothing more will be done for - * that page. - * - * Else, if that page is backed by the cache, a read will be initiated directly - * to the netfs's page and 0 will be returned by this function. The - * end_io_func() callback will be invoked when the operation terminates on a - * completion or failure. Note that the callback may be invoked before the - * return. - * - * Else, if the page is unbacked, -ENODATA is returned and a block may have - * been allocated in the cache. + * fscache_end_operation - End the read operation for the netfs lib + * @cres: The cache resources for the read operation * - * See Documentation/filesystems/caching/netfs-api.rst for a complete - * description. + * Clean up the resources at the end of the read request. */ -static inline -int fscache_read_or_alloc_page(struct fscache_cookie *cookie, - struct page *page, - fscache_rw_complete_t end_io_func, - void *context, - gfp_t gfp) +static inline void fscache_end_operation(struct netfs_cache_resources *cres) { - if (fscache_cookie_valid(cookie) && fscache_cookie_enabled(cookie)) - return __fscache_read_or_alloc_page(cookie, page, end_io_func, - context, gfp); - else - return -ENOBUFS; -} + const struct netfs_cache_ops *ops = fscache_operation_valid(cres); -/** - * fscache_read_or_alloc_pages - Read pages from the cache and/or allocate - * blocks in which to store them - * @cookie: The cookie representing the cache object - * @mapping: The netfs inode mapping to which the pages will be attached - * @pages: A list of potential netfs pages to be filled - * @nr_pages: Number of pages to be read and/or allocated - * @end_io_func: The callback to invoke when and if each page is filled - * @context: An arbitrary piece of data to pass on to end_io_func() - * @gfp: The conditions under which memory allocation should be made - * - * Read a set of pages from the cache, or if that's not possible, attempt to - * make a potential one-block reservation for each page in the cache into which - * that page may be stored once fetched from the server. - * - * If some pages are not backed by the cache object, or if it there's some - * reason they can't be, -ENOBUFS will be returned and nothing more will be - * done for that pages. - * - * Else, if some of the pages are backed by the cache, a read will be initiated - * directly to the netfs's page and 0 will be returned by this function. The - * end_io_func() callback will be invoked when the operation terminates on a - * completion or failure. Note that the callback may be invoked before the - * return. - * - * Else, if a page is unbacked, -ENODATA is returned and a block may have - * been allocated in the cache. - * - * Because the function may want to return all of -ENOBUFS, -ENODATA and 0 in - * regard to different pages, the return values are prioritised in that order. - * Any pages submitted for reading are removed from the pages list. - * - * See Documentation/filesystems/caching/netfs-api.rst for a complete - * description. - */ -static inline -int fscache_read_or_alloc_pages(struct fscache_cookie *cookie, - struct address_space *mapping, - struct list_head *pages, - unsigned *nr_pages, - fscache_rw_complete_t end_io_func, - void *context, - gfp_t gfp) -{ - if (fscache_cookie_valid(cookie) && fscache_cookie_enabled(cookie)) - return __fscache_read_or_alloc_pages(cookie, mapping, pages, - nr_pages, end_io_func, - context, gfp); - else - return -ENOBUFS; + if (ops) + ops->end_operation(cres); } /** - * fscache_alloc_page - Allocate a block in which to store a page - * @cookie: The cookie representing the cache object - * @page: The netfs page to allocate a page for - * @gfp: The conditions under which memory allocation should be made + * fscache_read - Start a read from the cache. + * @cres: The cache resources to use + * @start_pos: The beginning file offset in the cache file + * @iter: The buffer to fill - and also the length + * @read_hole: How to handle a hole in the data. + * @term_func: The function to call upon completion + * @term_func_priv: The private data for @term_func * - * Request Allocation a block in the cache in which to store a netfs page - * without retrieving any contents from the cache. + * Start a read from the cache. @cres indicates the cache object to read from + * and must be obtained by a call to fscache_begin_operation() beforehand. * - * If the page is not backed by a file then -ENOBUFS will be returned and - * nothing more will be done, and no reservation will be made. + * The data is read into the iterator, @iter, and that also indicates the size + * of the operation. @start_pos is the start position in the file, though if + * @seek_data is set appropriately, the cache can use SEEK_DATA to find the + * next piece of data, writing zeros for the hole into the iterator. * - * Else, a block will be allocated if one wasn't already, and 0 will be - * returned + * Upon termination of the operation, @term_func will be called and supplied + * with @term_func_priv plus the amount of data written, if successful, or the + * error code otherwise. * - * See Documentation/filesystems/caching/netfs-api.rst for a complete - * description. - */ -static inline -int fscache_alloc_page(struct fscache_cookie *cookie, - struct page *page, - gfp_t gfp) -{ - if (fscache_cookie_valid(cookie) && fscache_cookie_enabled(cookie)) - return __fscache_alloc_page(cookie, page, gfp); - else - return -ENOBUFS; -} - -/** - * fscache_readpages_cancel - Cancel read/alloc on pages - * @cookie: The cookie representing the inode's cache object. - * @pages: The netfs pages that we canceled write on in readpages() + * @read_hole indicates how a partially populated region in the cache should be + * handled. It can be one of a number of settings: * - * Uncache/unreserve the pages reserved earlier in readpages() via - * fscache_readpages_or_alloc() and similar. In most successful caches in - * readpages() this doesn't do anything. In cases when the underlying netfs's - * readahead failed we need to clean up the pagelist (unmark and uncache). + * NETFS_READ_HOLE_IGNORE - Just try to read (may return a short read). * - * This function may sleep as it may have to clean up disk state. + * NETFS_READ_HOLE_CLEAR - Seek for data, clearing the part of the buffer + * skipped over, then do as for IGNORE. + * + * NETFS_READ_HOLE_FAIL - Give ENODATA if we encounter a hole. */ static inline -void fscache_readpages_cancel(struct fscache_cookie *cookie, - struct list_head *pages) +int fscache_read(struct netfs_cache_resources *cres, + loff_t start_pos, + struct iov_iter *iter, + enum netfs_read_from_hole read_hole, + netfs_io_terminated_t term_func, + void *term_func_priv) { - if (fscache_cookie_valid(cookie)) - __fscache_readpages_cancel(cookie, pages); + const struct netfs_cache_ops *ops = fscache_operation_valid(cres); + return ops->read(cres, start_pos, iter, read_hole, + term_func, term_func_priv); } /** - * fscache_write_page - Request storage of a page in the cache + * fscache_begin_write_operation - Begin a write operation for the netfs lib + * @cres: The cache resources for the write being performed * @cookie: The cookie representing the cache object - * @page: The netfs page to store - * @object_size: Updated size of object - * @gfp: The conditions under which memory allocation should be made * - * Request the contents of the netfs page be written into the cache. This - * request may be ignored if no cache block is currently allocated, in which - * case it will return -ENOBUFS. + * Begin a write operation on behalf of the netfs helper library. @cres + * indicates the cache resources to which the operation state should be + * attached; @cookie indicates the cache object that will be accessed. * - * If a cache block was already allocated, a write will be initiated and 0 will - * be returned. The PG_fscache_write page bit is set immediately and will then - * be cleared at the completion of the write to indicate the success or failure - * of the operation. Note that the completion may happen before the return. + * @cres->inval_counter is set from @cookie->inval_counter for comparison at + * the end of the operation. This allows invalidation during the operation to + * be detected by the caller. * - * See Documentation/filesystems/caching/netfs-api.rst for a complete - * description. + * Returns: + * * 0 - Success + * * -ENOBUFS - No caching available + * * Other error code from the cache, such as -ENOMEM. */ static inline -int fscache_write_page(struct fscache_cookie *cookie, - struct page *page, - loff_t object_size, - gfp_t gfp) +int fscache_begin_write_operation(struct netfs_cache_resources *cres, + struct fscache_cookie *cookie) { - if (fscache_cookie_valid(cookie) && fscache_cookie_enabled(cookie)) - return __fscache_write_page(cookie, page, object_size, gfp); - else - return -ENOBUFS; + if (fscache_cookie_enabled(cookie)) + return __fscache_begin_write_operation(cres, cookie); + return -ENOBUFS; } /** - * fscache_uncache_page - Indicate that caching is no longer required on a page - * @cookie: The cookie representing the cache object - * @page: The netfs page that was being cached. + * fscache_write - Start a write to the cache. + * @cres: The cache resources to use + * @start_pos: The beginning file offset in the cache file + * @iter: The data to write - and also the length + * @term_func: The function to call upon completion + * @term_func_priv: The private data for @term_func * - * Tell the cache that we no longer want a page to be cached and that it should - * remove any knowledge of the netfs page it may have. + * Start a write to the cache. @cres indicates the cache object to write to and + * must be obtained by a call to fscache_begin_operation() beforehand. * - * Note that this cannot cancel any outstanding I/O operations between this - * page and the cache. + * The data to be written is obtained from the iterator, @iter, and that also + * indicates the size of the operation. @start_pos is the start position in + * the file. * - * See Documentation/filesystems/caching/netfs-api.rst for a complete - * description. + * Upon termination of the operation, @term_func will be called and supplied + * with @term_func_priv plus the amount of data written, if successful, or the + * error code otherwise. */ static inline -void fscache_uncache_page(struct fscache_cookie *cookie, - struct page *page) +int fscache_write(struct netfs_cache_resources *cres, + loff_t start_pos, + struct iov_iter *iter, + netfs_io_terminated_t term_func, + void *term_func_priv) { - if (fscache_cookie_valid(cookie)) - __fscache_uncache_page(cookie, page); + const struct netfs_cache_ops *ops = fscache_operation_valid(cres); + return ops->write(cres, start_pos, iter, term_func, term_func_priv); } /** - * fscache_check_page_write - Ask if a page is being writing to the cache - * @cookie: The cookie representing the cache object - * @page: The netfs page that is being cached. - * - * Ask the cache if a page is being written to the cache. - * - * See Documentation/filesystems/caching/netfs-api.rst for a complete - * description. - */ -static inline -bool fscache_check_page_write(struct fscache_cookie *cookie, - struct page *page) + * fscache_clear_page_bits - Clear the PG_fscache bits from a set of pages + * @mapping: The netfs inode to use as the source + * @start: The start position in @mapping + * @len: The amount of data to unlock + * @caching: If PG_fscache has been set + * + * Clear the PG_fscache flag from a sequence of pages and wake up anyone who's + * waiting. + */ +static inline void fscache_clear_page_bits(struct address_space *mapping, + loff_t start, size_t len, + bool caching) { - if (fscache_cookie_valid(cookie)) - return __fscache_check_page_write(cookie, page); - return false; + if (caching) + __fscache_clear_page_bits(mapping, start, len); } /** - * fscache_wait_on_page_write - Wait for a page to complete writing to the cache + * fscache_write_to_cache - Save a write to the cache and clear PG_fscache * @cookie: The cookie representing the cache object - * @page: The netfs page that is being cached. - * - * Ask the cache to wake us up when a page is no longer being written to the - * cache. - * - * See Documentation/filesystems/caching/netfs-api.rst for a complete - * description. - */ -static inline -void fscache_wait_on_page_write(struct fscache_cookie *cookie, - struct page *page) + * @mapping: The netfs inode to use as the source + * @start: The start position in @mapping + * @len: The amount of data to write back + * @i_size: The new size of the inode + * @term_func: The function to call upon completion + * @term_func_priv: The private data for @term_func + * @caching: If PG_fscache has been set + * + * Helper function for a netfs to write dirty data from an inode into the cache + * object that's backing it. + * + * @start and @len describe the range of the data. This does not need to be + * page-aligned, but to satisfy DIO requirements, the cache may expand it up to + * the page boundaries on either end. All the pages covering the range must be + * marked with PG_fscache. + * + * If given, @term_func will be called upon completion and supplied with + * @term_func_priv. Note that the PG_fscache flags will have been cleared by + * this point, so the netfs must retain its own pin on the mapping. + */ +static inline void fscache_write_to_cache(struct fscache_cookie *cookie, + struct address_space *mapping, + loff_t start, size_t len, loff_t i_size, + netfs_io_terminated_t term_func, + void *term_func_priv, + bool caching) { - if (fscache_cookie_valid(cookie)) - __fscache_wait_on_page_write(cookie, page); -} + if (caching) + __fscache_write_to_cache(cookie, mapping, start, len, i_size, + term_func, term_func_priv, caching); + else if (term_func) + term_func(term_func_priv, -ENOBUFS, false); -/** - * fscache_maybe_release_page - Consider releasing a page, cancelling a store - * @cookie: The cookie representing the cache object - * @page: The netfs page that is being cached. - * @gfp: The gfp flags passed to releasepage() - * - * Consider releasing a page for the vmscan algorithm, on behalf of the netfs's - * releasepage() call. A storage request on the page may cancelled if it is - * not currently being processed. - * - * The function returns true if the page no longer has a storage request on it, - * and false if a storage request is left in place. If true is returned, the - * page will have been passed to fscache_uncache_page(). If false is returned - * the page cannot be freed yet. - */ -static inline -bool fscache_maybe_release_page(struct fscache_cookie *cookie, - struct page *page, - gfp_t gfp) -{ - if (fscache_cookie_valid(cookie) && PageFsCache(page)) - return __fscache_maybe_release_page(cookie, page, gfp); - return true; } +#if __fscache_available +bool fscache_dirty_folio(struct address_space *mapping, struct folio *folio, + struct fscache_cookie *cookie); +#else +#define fscache_dirty_folio(MAPPING, FOLIO, COOKIE) \ + filemap_dirty_folio(MAPPING, FOLIO) +#endif + /** - * fscache_uncache_all_inode_pages - Uncache all an inode's pages - * @cookie: The cookie representing the inode's cache object. - * @inode: The inode to uncache pages from. - * - * Uncache all the pages in an inode that are marked PG_fscache, assuming them - * to be associated with the given cookie. + * fscache_unpin_writeback - Unpin writeback resources + * @wbc: The writeback control + * @cookie: The cookie referring to the cache object * - * This function may sleep. It will wait for pages that are being written out - * and will wait whilst the PG_fscache mark is removed by the cache. + * Unpin the writeback resources pinned by fscache_dirty_folio(). This is + * intended to be called by the netfs's ->write_inode() method. */ -static inline -void fscache_uncache_all_inode_pages(struct fscache_cookie *cookie, - struct inode *inode) +static inline void fscache_unpin_writeback(struct writeback_control *wbc, + struct fscache_cookie *cookie) { - if (fscache_cookie_valid(cookie)) - __fscache_uncache_all_inode_pages(cookie, inode); + if (wbc->unpinned_fscache_wb) + fscache_unuse_cookie(cookie, NULL, NULL); } -#endif /* FSCACHE_USE_NEW_IO_API */ - /** - * fscache_disable_cookie - Disable a cookie - * @cookie: The cookie representing the cache object - * @aux_data: The updated auxiliary data for the cookie (may be NULL) - * @invalidate: Invalidate the backing object - * - * Disable a cookie from accepting further alloc, read, write, invalidate, - * update or acquire operations. Outstanding operations can still be waited - * upon and pages can still be uncached and the cookie relinquished. - * - * This will not return until all outstanding operations have completed. + * fscache_clear_inode_writeback - Clear writeback resources pinned by an inode + * @cookie: The cookie referring to the cache object + * @inode: The inode to clean up + * @aux: Auxiliary data to apply to the inode * - * If @invalidate is set, then the backing object will be invalidated and - * detached, otherwise it will just be detached. - * - * If @aux_data is set, then auxiliary data will be updated from that. + * Clear any writeback resources held by an inode when the inode is evicted. + * This must be called before clear_inode() is called. */ -static inline -void fscache_disable_cookie(struct fscache_cookie *cookie, - const void *aux_data, - bool invalidate) +static inline void fscache_clear_inode_writeback(struct fscache_cookie *cookie, + struct inode *inode, + const void *aux) { - if (fscache_cookie_valid(cookie) && fscache_cookie_enabled(cookie)) - __fscache_disable_cookie(cookie, aux_data, invalidate); + if (inode->i_state & I_PINNING_FSCACHE_WB) { + loff_t i_size = i_size_read(inode); + fscache_unuse_cookie(cookie, aux, &i_size); + } } /** - * fscache_enable_cookie - Reenable a cookie - * @cookie: The cookie representing the cache object - * @aux_data: The updated auxiliary data for the cookie (may be NULL) - * @object_size: Current size of object - * @can_enable: A function to permit enablement once lock is held - * @data: Data for can_enable() - * - * Reenable a previously disabled cookie, allowing it to accept further alloc, - * read, write, invalidate, update or acquire operations. An attempt will be - * made to immediately reattach the cookie to a backing object. If @aux_data - * is set, the auxiliary data attached to the cookie will be updated. + * fscache_note_page_release - Note that a netfs page got released + * @cookie: The cookie corresponding to the file * - * The can_enable() function is called (if not NULL) once the enablement lock - * is held to rule on whether enablement is still permitted to go ahead. + * Note that a page that has been copied to the cache has been released. This + * means that future reads will need to look in the cache to see if it's there. */ static inline -void fscache_enable_cookie(struct fscache_cookie *cookie, - const void *aux_data, - loff_t object_size, - bool (*can_enable)(void *data), - void *data) +void fscache_note_page_release(struct fscache_cookie *cookie) { - if (fscache_cookie_valid(cookie) && !fscache_cookie_enabled(cookie)) - __fscache_enable_cookie(cookie, aux_data, object_size, - can_enable, data); + /* If we've written data to the cache (HAVE_DATA) and there wasn't any + * data in the cache when we started (NO_DATA_TO_READ), it may no + * longer be true that we can skip reading from the cache - so clear + * the flag that causes reads to be skipped. + */ + if (cookie && + test_bit(FSCACHE_COOKIE_HAVE_DATA, &cookie->flags) && + test_bit(FSCACHE_COOKIE_NO_DATA_TO_READ, &cookie->flags)) + clear_bit(FSCACHE_COOKIE_NO_DATA_TO_READ, &cookie->flags); } #endif /* _LINUX_FSCACHE_H */ diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h index 91ea9477e9bd..4f5f8a651213 100644 --- a/include/linux/fscrypt.h +++ b/include/linux/fscrypt.h @@ -18,10 +18,21 @@ #include <linux/slab.h> #include <uapi/linux/fscrypt.h> -#define FS_CRYPTO_BLOCK_SIZE 16 +/* + * The lengths of all file contents blocks must be divisible by this value. + * This is needed to ensure that all contents encryption modes will work, as + * some of the supported modes don't support arbitrarily byte-aligned messages. + * + * Since the needed alignment is 16 bytes, most filesystems will meet this + * requirement naturally, as typical block sizes are powers of 2. However, if a + * filesystem can generate arbitrarily byte-aligned block lengths (e.g., via + * compression), then it will need to pad to this alignment before encryption. + */ +#define FSCRYPT_CONTENTS_ALIGNMENT 16 union fscrypt_policy; struct fscrypt_info; +struct fs_parameter; struct seq_file; struct fscrypt_str { @@ -150,24 +161,21 @@ struct fscrypt_operations { int *ino_bits_ret, int *lblk_bits_ret); /* - * Return the number of block devices to which the filesystem may write - * encrypted file contents. + * Return an array of pointers to the block devices to which the + * filesystem may write encrypted file contents, NULL if the filesystem + * only has a single such block device, or an ERR_PTR() on error. + * + * On successful non-NULL return, *num_devs is set to the number of + * devices in the returned array. The caller must free the returned + * array using kfree(). * * If the filesystem can use multiple block devices (other than block * devices that aren't used for encrypted file contents, such as * external journal devices), and wants to support inline encryption, * then it must implement this function. Otherwise it's not needed. */ - int (*get_num_devices)(struct super_block *sb); - - /* - * If ->get_num_devices() returns a value greater than 1, then this - * function is called to get the array of request_queues that the - * filesystem is using -- one per block device. (There may be duplicate - * entries in this array, as block devices can share a request_queue.) - */ - void (*get_devices)(struct super_block *sb, - struct request_queue **devs); + struct block_device **(*get_devices)(struct super_block *sb, + unsigned int *num_devs); }; static inline struct fscrypt_info *fscrypt_get_info(const struct inode *inode) @@ -273,16 +281,24 @@ int fscrypt_ioctl_get_policy(struct file *filp, void __user *arg); int fscrypt_ioctl_get_policy_ex(struct file *filp, void __user *arg); int fscrypt_ioctl_get_nonce(struct file *filp, void __user *arg); int fscrypt_has_permitted_context(struct inode *parent, struct inode *child); +int fscrypt_context_for_new_inode(void *ctx, struct inode *inode); int fscrypt_set_context(struct inode *inode, void *fs_data); struct fscrypt_dummy_policy { const union fscrypt_policy *policy; }; -int fscrypt_set_test_dummy_encryption(struct super_block *sb, const char *arg, - struct fscrypt_dummy_policy *dummy_policy); +int fscrypt_parse_test_dummy_encryption(const struct fs_parameter *param, + struct fscrypt_dummy_policy *dummy_policy); +bool fscrypt_dummy_policies_equal(const struct fscrypt_dummy_policy *p1, + const struct fscrypt_dummy_policy *p2); void fscrypt_show_test_dummy_encryption(struct seq_file *seq, char sep, struct super_block *sb); +static inline bool +fscrypt_is_dummy_policy_set(const struct fscrypt_dummy_policy *dummy_policy) +{ + return dummy_policy->policy != NULL; +} static inline void fscrypt_free_dummy_policy(struct fscrypt_dummy_policy *dummy_policy) { @@ -291,8 +307,10 @@ fscrypt_free_dummy_policy(struct fscrypt_dummy_policy *dummy_policy) } /* keyring.c */ -void fscrypt_sb_free(struct super_block *sb); +void fscrypt_destroy_keyring(struct super_block *sb); int fscrypt_ioctl_add_key(struct file *filp, void __user *arg); +int fscrypt_add_test_dummy_key(struct super_block *sb, + const struct fscrypt_dummy_policy *dummy_policy); int fscrypt_ioctl_remove_key(struct file *filp, void __user *arg); int fscrypt_ioctl_remove_key_all_users(struct file *filp, void __user *arg); int fscrypt_ioctl_get_key_status(struct file *filp, void __user *arg); @@ -305,6 +323,10 @@ void fscrypt_free_inode(struct inode *inode); int fscrypt_drop_inode(struct inode *inode); /* fname.c */ +int fscrypt_fname_encrypt(const struct inode *inode, const struct qstr *iname, + u8 *out, unsigned int olen); +bool fscrypt_fname_encrypted_size(const struct inode *inode, u32 orig_len, + u32 max_len, u32 *encrypted_len_ret); int fscrypt_setup_filename(struct inode *inode, const struct qstr *iname, int lookup, struct fscrypt_name *fname); @@ -326,7 +348,7 @@ u64 fscrypt_fname_siphash(const struct inode *dir, const struct qstr *name); int fscrypt_d_revalidate(struct dentry *dentry, unsigned int flags); /* bio.c */ -void fscrypt_decrypt_bio(struct bio *bio); +bool fscrypt_decrypt_bio(struct bio *bio); int fscrypt_zeroout_range(const struct inode *inode, pgoff_t lblk, sector_t pblk, unsigned int len); @@ -467,19 +489,39 @@ static inline int fscrypt_set_context(struct inode *inode, void *fs_data) struct fscrypt_dummy_policy { }; +static inline int +fscrypt_parse_test_dummy_encryption(const struct fs_parameter *param, + struct fscrypt_dummy_policy *dummy_policy) +{ + return -EINVAL; +} + +static inline bool +fscrypt_dummy_policies_equal(const struct fscrypt_dummy_policy *p1, + const struct fscrypt_dummy_policy *p2) +{ + return true; +} + static inline void fscrypt_show_test_dummy_encryption(struct seq_file *seq, char sep, struct super_block *sb) { } +static inline bool +fscrypt_is_dummy_policy_set(const struct fscrypt_dummy_policy *dummy_policy) +{ + return false; +} + static inline void fscrypt_free_dummy_policy(struct fscrypt_dummy_policy *dummy_policy) { } /* keyring.c */ -static inline void fscrypt_sb_free(struct super_block *sb) +static inline void fscrypt_destroy_keyring(struct super_block *sb) { } @@ -488,6 +530,13 @@ static inline int fscrypt_ioctl_add_key(struct file *filp, void __user *arg) return -EOPNOTSUPP; } +static inline int +fscrypt_add_test_dummy_key(struct super_block *sb, + const struct fscrypt_dummy_policy *dummy_policy) +{ + return 0; +} + static inline int fscrypt_ioctl_remove_key(struct file *filp, void __user *arg) { return -EOPNOTSUPP; @@ -592,8 +641,9 @@ static inline int fscrypt_d_revalidate(struct dentry *dentry, } /* bio.c */ -static inline void fscrypt_decrypt_bio(struct bio *bio) +static inline bool fscrypt_decrypt_bio(struct bio *bio) { + return true; } static inline int fscrypt_zeroout_range(const struct inode *inode, pgoff_t lblk, @@ -714,6 +764,10 @@ bool fscrypt_mergeable_bio(struct bio *bio, const struct inode *inode, bool fscrypt_mergeable_bio_bh(struct bio *bio, const struct buffer_head *next_bh); +bool fscrypt_dio_supported(struct inode *inode); + +u64 fscrypt_limit_io_blocks(const struct inode *inode, u64 lblk, u64 nr_blocks); + #else /* CONFIG_FS_ENCRYPTION_INLINE_CRYPT */ static inline bool __fscrypt_inode_uses_inline_crypto(const struct inode *inode) @@ -742,6 +796,17 @@ static inline bool fscrypt_mergeable_bio_bh(struct bio *bio, { return true; } + +static inline bool fscrypt_dio_supported(struct inode *inode) +{ + return !fscrypt_needs_contents_encryption(inode); +} + +static inline u64 fscrypt_limit_io_blocks(const struct inode *inode, u64 lblk, + u64 nr_blocks) +{ + return nr_blocks; +} #endif /* !CONFIG_FS_ENCRYPTION_INLINE_CRYPT */ /** diff --git a/include/linux/fsl/mc.h b/include/linux/fsl/mc.h index e026f6c48b49..a86115bc799c 100644 --- a/include/linux/fsl/mc.h +++ b/include/linux/fsl/mc.h @@ -32,6 +32,13 @@ struct fsl_mc_io; * @shutdown: Function called at shutdown time to quiesce the device * @suspend: Function called when a device is stopped * @resume: Function called when a device is resumed + * @driver_managed_dma: Device driver doesn't use kernel DMA API for DMA. + * For most device drivers, no need to care about this flag + * as long as all DMAs are handled through the kernel DMA API. + * For some special ones, for example VFIO drivers, they know + * how to manage the DMA themselves and set this flag so that + * the IOMMU layer will allow them to setup and manage their + * own I/O address space. * * Generic DPAA device driver object for device drivers that are registered * with a DPRC bus. This structure is to be embedded in each device-specific @@ -45,6 +52,7 @@ struct fsl_mc_driver { void (*shutdown)(struct fsl_mc_device *dev); int (*suspend)(struct fsl_mc_device *dev, pm_message_t state); int (*resume)(struct fsl_mc_device *dev); + bool driver_managed_dma; }; #define to_fsl_mc_driver(_drv) \ @@ -91,13 +99,13 @@ struct fsl_mc_resource { /** * struct fsl_mc_device_irq - MC object device message-based interrupt - * @msi_desc: pointer to MSI descriptor allocated by fsl_mc_msi_alloc_descs() + * @virq: Linux virtual interrupt number * @mc_dev: MC object device that owns this interrupt * @dev_irq_index: device-relative IRQ index * @resource: MC generic resource associated with the interrupt */ struct fsl_mc_device_irq { - struct msi_desc *msi_desc; + unsigned int virq; struct fsl_mc_device *mc_dev; u8 dev_irq_index; struct fsl_mc_resource resource; @@ -170,7 +178,9 @@ struct fsl_mc_obj_desc { * @regions: pointer to array of MMIO region entries * @irqs: pointer to array of pointers to interrupts allocated to this device * @resource: generic resource associated with this MC object device, if any. - * @driver_override: driver name to force a match + * @driver_override: driver name to force a match; do not set directly, + * because core frees it; use driver_set_override() to + * set or clear it. * * Generic device object for MC object devices that are "attached" to a * MC bus. @@ -204,7 +214,7 @@ struct fsl_mc_device { struct fsl_mc_device_irq **irqs; struct fsl_mc_resource *resource; struct device_link *consumer_link; - char *driver_override; + const char *driver_override; }; #define to_fsl_mc_device(_dev) \ diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index 787545e87eeb..bb8467cd11ae 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -144,16 +144,19 @@ static inline void fsnotify_move(struct inode *old_dir, struct inode *new_dir, u32 fs_cookie = fsnotify_get_cookie(); __u32 old_dir_mask = FS_MOVED_FROM; __u32 new_dir_mask = FS_MOVED_TO; + __u32 rename_mask = FS_RENAME; const struct qstr *new_name = &moved->d_name; - if (old_dir == new_dir) - old_dir_mask |= FS_DN_RENAME; - if (isdir) { old_dir_mask |= FS_ISDIR; new_dir_mask |= FS_ISDIR; + rename_mask |= FS_ISDIR; } + /* Event with information about both old and new parent+name */ + fsnotify_name(rename_mask, moved, FSNOTIFY_EVENT_DENTRY, + old_dir, old_name, 0); + fsnotify_name(old_dir_mask, source, FSNOTIFY_EVENT_INODE, old_dir, old_name, fs_cookie); fsnotify_name(new_dir_mask, source, FSNOTIFY_EVENT_INODE, @@ -222,16 +225,53 @@ static inline void fsnotify_link(struct inode *dir, struct inode *inode, } /* + * fsnotify_delete - @dentry was unlinked and unhashed + * + * Caller must make sure that dentry->d_name is stable. + * + * Note: unlike fsnotify_unlink(), we have to pass also the unlinked inode + * as this may be called after d_delete() and old_dentry may be negative. + */ +static inline void fsnotify_delete(struct inode *dir, struct inode *inode, + struct dentry *dentry) +{ + __u32 mask = FS_DELETE; + + if (S_ISDIR(inode->i_mode)) + mask |= FS_ISDIR; + + fsnotify_name(mask, inode, FSNOTIFY_EVENT_INODE, dir, &dentry->d_name, + 0); +} + +/** + * d_delete_notify - delete a dentry and call fsnotify_delete() + * @dentry: The dentry to delete + * + * This helper is used to guaranty that the unlinked inode cannot be found + * by lookup of this name after fsnotify_delete() event has been delivered. + */ +static inline void d_delete_notify(struct inode *dir, struct dentry *dentry) +{ + struct inode *inode = d_inode(dentry); + + ihold(inode); + d_delete(dentry); + fsnotify_delete(dir, inode, dentry); + iput(inode); +} + +/* * fsnotify_unlink - 'name' was unlinked * * Caller must make sure that dentry->d_name is stable. */ static inline void fsnotify_unlink(struct inode *dir, struct dentry *dentry) { - /* Expected to be called before d_delete() */ - WARN_ON_ONCE(d_is_negative(dentry)); + if (WARN_ON_ONCE(d_is_negative(dentry))) + return; - fsnotify_dirent(dir, dentry, FS_DELETE); + fsnotify_delete(dir, d_inode(dentry), dentry); } /* @@ -255,10 +295,10 @@ static inline void fsnotify_mkdir(struct inode *dir, struct dentry *dentry) */ static inline void fsnotify_rmdir(struct inode *dir, struct dentry *dentry) { - /* Expected to be called before d_delete() */ - WARN_ON_ONCE(d_is_negative(dentry)); + if (WARN_ON_ONCE(d_is_negative(dentry))) + return; - fsnotify_dirent(dir, dentry, FS_DELETE | FS_ISDIR); + fsnotify_delete(dir, d_inode(dentry), dentry); } /* diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 51ef2b079bfa..d7d96c806bff 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -20,6 +20,7 @@ #include <linux/user_namespace.h> #include <linux/refcount.h> #include <linux/mempool.h> +#include <linux/sched/mm.h> /* * IN_* from inotfy.h lines up EXACTLY with FS_*, this is so we can easily @@ -55,7 +56,6 @@ #define FS_ACCESS_PERM 0x00020000 /* access event in a permissions hook */ #define FS_OPEN_EXEC_PERM 0x00040000 /* open/exec event in a permission hook */ -#define FS_EXCL_UNLINK 0x04000000 /* do not send events if object is unlinked */ /* * Set on inode mark that cares about things that happen to its children. * Always set for dnotify and inotify. @@ -63,10 +63,9 @@ */ #define FS_EVENT_ON_CHILD 0x08000000 -#define FS_DN_RENAME 0x10000000 /* file renamed */ +#define FS_RENAME 0x10000000 /* File was renamed */ #define FS_DN_MULTISHOT 0x20000000 /* dnotify multishot */ #define FS_ISDIR 0x40000000 /* event occurred against dir */ -#define FS_IN_ONESHOT 0x80000000 /* only send event once */ #define FS_MOVE (FS_MOVED_FROM | FS_MOVED_TO) @@ -76,7 +75,7 @@ * The watching parent may get an FS_ATTRIB|FS_EVENT_ON_CHILD event * when a directory entry inside a child subdir changes. */ -#define ALL_FSNOTIFY_DIRENT_EVENTS (FS_CREATE | FS_DELETE | FS_MOVE) +#define ALL_FSNOTIFY_DIRENT_EVENTS (FS_CREATE | FS_DELETE | FS_MOVE | FS_RENAME) #define ALL_FSNOTIFY_PERM_EVENTS (FS_OPEN_PERM | FS_ACCESS_PERM | \ FS_OPEN_EXEC_PERM) @@ -101,13 +100,12 @@ /* Events that can be reported to backends */ #define ALL_FSNOTIFY_EVENTS (ALL_FSNOTIFY_DIRENT_EVENTS | \ FS_EVENTS_POSS_ON_CHILD | \ - FS_DELETE_SELF | FS_MOVE_SELF | FS_DN_RENAME | \ + FS_DELETE_SELF | FS_MOVE_SELF | \ FS_UNMOUNT | FS_Q_OVERFLOW | FS_IN_IGNORED | \ FS_ERROR) /* Extra flags that may be reported with event or control handling of events */ -#define ALL_FSNOTIFY_FLAGS (FS_EXCL_UNLINK | FS_ISDIR | FS_IN_ONESHOT | \ - FS_DN_MULTISHOT | FS_EVENT_ON_CHILD) +#define ALL_FSNOTIFY_FLAGS (FS_ISDIR | FS_EVENT_ON_CHILD | FS_DN_MULTISHOT) #define ALL_FSNOTIFY_BITS (ALL_FSNOTIFY_EVENTS | ALL_FSNOTIFY_FLAGS) @@ -213,6 +211,12 @@ struct fsnotify_group { unsigned int priority; bool shutdown; /* group is being shut down, don't queue more events */ +#define FSNOTIFY_GROUP_USER 0x01 /* user allocated group */ +#define FSNOTIFY_GROUP_DUPS 0x02 /* allow multiple marks per object */ +#define FSNOTIFY_GROUP_NOFS 0x04 /* group lock is not direct reclaim safe */ + int flags; + unsigned int owner_flags; /* stored flags of mark_mutex owner */ + /* stores all fastpath marks assoc with this group so they can be cleaned on unregister */ struct mutex mark_mutex; /* protect marks_list */ atomic_t user_waits; /* Number of tasks waiting for user @@ -253,6 +257,31 @@ struct fsnotify_group { }; }; +/* + * These helpers are used to prevent deadlock when reclaiming inodes with + * evictable marks of the same group that is allocating a new mark. + */ +static inline void fsnotify_group_lock(struct fsnotify_group *group) +{ + mutex_lock(&group->mark_mutex); + if (group->flags & FSNOTIFY_GROUP_NOFS) + group->owner_flags = memalloc_nofs_save(); +} + +static inline void fsnotify_group_unlock(struct fsnotify_group *group) +{ + if (group->flags & FSNOTIFY_GROUP_NOFS) + memalloc_nofs_restore(group->owner_flags); + mutex_unlock(&group->mark_mutex); +} + +static inline void fsnotify_group_assert_locked(struct fsnotify_group *group) +{ + WARN_ON_ONCE(!mutex_is_locked(&group->mark_mutex)); + if (group->flags & FSNOTIFY_GROUP_NOFS) + WARN_ON_ONCE(!(current->flags & PF_MEMALLOC_NOFS)); +} + /* When calling fsnotify tell it if the data is a path or inode */ enum fsnotify_data_type { FSNOTIFY_EVENT_NONE, @@ -337,58 +366,81 @@ static inline struct fs_error_report *fsnotify_data_error_report( } } +/* + * Index to merged marks iterator array that correlates to a type of watch. + * The type of watched object can be deduced from the iterator type, but not + * the other way around, because an event can match different watched objects + * of the same object type. + * For example, both parent and child are watching an object of type inode. + */ +enum fsnotify_iter_type { + FSNOTIFY_ITER_TYPE_INODE, + FSNOTIFY_ITER_TYPE_VFSMOUNT, + FSNOTIFY_ITER_TYPE_SB, + FSNOTIFY_ITER_TYPE_PARENT, + FSNOTIFY_ITER_TYPE_INODE2, + FSNOTIFY_ITER_TYPE_COUNT +}; + +/* The type of object that a mark is attached to */ enum fsnotify_obj_type { + FSNOTIFY_OBJ_TYPE_ANY = -1, FSNOTIFY_OBJ_TYPE_INODE, - FSNOTIFY_OBJ_TYPE_PARENT, FSNOTIFY_OBJ_TYPE_VFSMOUNT, FSNOTIFY_OBJ_TYPE_SB, FSNOTIFY_OBJ_TYPE_COUNT, FSNOTIFY_OBJ_TYPE_DETACHED = FSNOTIFY_OBJ_TYPE_COUNT }; -#define FSNOTIFY_OBJ_TYPE_INODE_FL (1U << FSNOTIFY_OBJ_TYPE_INODE) -#define FSNOTIFY_OBJ_TYPE_PARENT_FL (1U << FSNOTIFY_OBJ_TYPE_PARENT) -#define FSNOTIFY_OBJ_TYPE_VFSMOUNT_FL (1U << FSNOTIFY_OBJ_TYPE_VFSMOUNT) -#define FSNOTIFY_OBJ_TYPE_SB_FL (1U << FSNOTIFY_OBJ_TYPE_SB) -#define FSNOTIFY_OBJ_ALL_TYPES_MASK ((1U << FSNOTIFY_OBJ_TYPE_COUNT) - 1) - -static inline bool fsnotify_valid_obj_type(unsigned int type) +static inline bool fsnotify_valid_obj_type(unsigned int obj_type) { - return (type < FSNOTIFY_OBJ_TYPE_COUNT); + return (obj_type < FSNOTIFY_OBJ_TYPE_COUNT); } struct fsnotify_iter_info { - struct fsnotify_mark *marks[FSNOTIFY_OBJ_TYPE_COUNT]; + struct fsnotify_mark *marks[FSNOTIFY_ITER_TYPE_COUNT]; + struct fsnotify_group *current_group; unsigned int report_mask; int srcu_idx; }; static inline bool fsnotify_iter_should_report_type( - struct fsnotify_iter_info *iter_info, int type) + struct fsnotify_iter_info *iter_info, int iter_type) { - return (iter_info->report_mask & (1U << type)); + return (iter_info->report_mask & (1U << iter_type)); } static inline void fsnotify_iter_set_report_type( - struct fsnotify_iter_info *iter_info, int type) + struct fsnotify_iter_info *iter_info, int iter_type) +{ + iter_info->report_mask |= (1U << iter_type); +} + +static inline struct fsnotify_mark *fsnotify_iter_mark( + struct fsnotify_iter_info *iter_info, int iter_type) { - iter_info->report_mask |= (1U << type); + if (fsnotify_iter_should_report_type(iter_info, iter_type)) + return iter_info->marks[iter_type]; + return NULL; } -static inline void fsnotify_iter_set_report_type_mark( - struct fsnotify_iter_info *iter_info, int type, - struct fsnotify_mark *mark) +static inline int fsnotify_iter_step(struct fsnotify_iter_info *iter, int type, + struct fsnotify_mark **markp) { - iter_info->marks[type] = mark; - iter_info->report_mask |= (1U << type); + while (type < FSNOTIFY_ITER_TYPE_COUNT) { + *markp = fsnotify_iter_mark(iter, type); + if (*markp) + break; + type++; + } + return type; } #define FSNOTIFY_ITER_FUNCS(name, NAME) \ static inline struct fsnotify_mark *fsnotify_iter_##name##_mark( \ struct fsnotify_iter_info *iter_info) \ { \ - return (iter_info->report_mask & FSNOTIFY_OBJ_TYPE_##NAME##_FL) ? \ - iter_info->marks[FSNOTIFY_OBJ_TYPE_##NAME] : NULL; \ + return fsnotify_iter_mark(iter_info, FSNOTIFY_ITER_TYPE_##NAME); \ } FSNOTIFY_ITER_FUNCS(inode, INODE) @@ -396,8 +448,13 @@ FSNOTIFY_ITER_FUNCS(parent, PARENT) FSNOTIFY_ITER_FUNCS(vfsmount, VFSMOUNT) FSNOTIFY_ITER_FUNCS(sb, SB) -#define fsnotify_foreach_obj_type(type) \ - for (type = 0; type < FSNOTIFY_OBJ_TYPE_COUNT; type++) +#define fsnotify_foreach_iter_type(type) \ + for (type = 0; type < FSNOTIFY_ITER_TYPE_COUNT; type++) +#define fsnotify_foreach_iter_mark_type(iter, mark, type) \ + for (type = 0; \ + type = fsnotify_iter_step(iter, type, &mark), \ + type < FSNOTIFY_ITER_TYPE_COUNT; \ + type++) /* * fsnotify_connp_t is what we embed in objects which connector can be attached @@ -416,6 +473,7 @@ struct fsnotify_mark_connector { spinlock_t lock; unsigned short type; /* Type of object [lock] */ #define FSNOTIFY_CONN_FLAG_HAS_FSID 0x01 +#define FSNOTIFY_CONN_FLAG_HAS_IREF 0x02 unsigned short flags; /* flags [lock] */ __kernel_fsid_t fsid; /* fsid of filesystem containing object */ union { @@ -460,11 +518,18 @@ struct fsnotify_mark { struct hlist_node obj_list; /* Head of list of marks for an object [mark ref] */ struct fsnotify_mark_connector *connector; - /* Events types to ignore [mark->lock, group->mark_mutex] */ - __u32 ignored_mask; -#define FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY 0x01 -#define FSNOTIFY_MARK_FLAG_ALIVE 0x02 -#define FSNOTIFY_MARK_FLAG_ATTACHED 0x04 + /* Events types and flags to ignore [mark->lock, group->mark_mutex] */ + __u32 ignore_mask; + /* General fsnotify mark flags */ +#define FSNOTIFY_MARK_FLAG_ALIVE 0x0001 +#define FSNOTIFY_MARK_FLAG_ATTACHED 0x0002 + /* inotify mark flags */ +#define FSNOTIFY_MARK_FLAG_EXCL_UNLINK 0x0010 +#define FSNOTIFY_MARK_FLAG_IN_ONESHOT 0x0020 + /* fanotify mark flags */ +#define FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY 0x0100 +#define FSNOTIFY_MARK_FLAG_NO_IREF 0x0200 +#define FSNOTIFY_MARK_FLAG_HAS_IGNORE_FLAGS 0x0400 unsigned int flags; /* flags [mark->lock] */ }; @@ -530,8 +595,9 @@ static inline void fsnotify_update_flags(struct dentry *dentry) /* called from fsnotify listeners, such as fanotify or dnotify */ /* create a new group */ -extern struct fsnotify_group *fsnotify_alloc_group(const struct fsnotify_ops *ops); -extern struct fsnotify_group *fsnotify_alloc_user_group(const struct fsnotify_ops *ops); +extern struct fsnotify_group *fsnotify_alloc_group( + const struct fsnotify_ops *ops, + int flags); /* get reference to a group */ extern void fsnotify_get_group(struct fsnotify_group *group); /* drop reference on a group from fsnotify_alloc_group */ @@ -590,6 +656,101 @@ extern void fsnotify_remove_queued_event(struct fsnotify_group *group, /* functions used to manipulate the marks attached to inodes */ +/* + * Canonical "ignore mask" including event flags. + * + * Note the subtle semantic difference from the legacy ->ignored_mask. + * ->ignored_mask traditionally only meant which events should be ignored, + * while ->ignore_mask also includes flags regarding the type of objects on + * which events should be ignored. + */ +static inline __u32 fsnotify_ignore_mask(struct fsnotify_mark *mark) +{ + __u32 ignore_mask = mark->ignore_mask; + + /* The event flags in ignore mask take effect */ + if (mark->flags & FSNOTIFY_MARK_FLAG_HAS_IGNORE_FLAGS) + return ignore_mask; + + /* + * Legacy behavior: + * - Always ignore events on dir + * - Ignore events on child if parent is watching children + */ + ignore_mask |= FS_ISDIR; + ignore_mask &= ~FS_EVENT_ON_CHILD; + ignore_mask |= mark->mask & FS_EVENT_ON_CHILD; + + return ignore_mask; +} + +/* Legacy ignored_mask - only event types to ignore */ +static inline __u32 fsnotify_ignored_events(struct fsnotify_mark *mark) +{ + return mark->ignore_mask & ALL_FSNOTIFY_EVENTS; +} + +/* + * Check if mask (or ignore mask) should be applied depending if victim is a + * directory and whether it is reported to a watching parent. + */ +static inline bool fsnotify_mask_applicable(__u32 mask, bool is_dir, + int iter_type) +{ + /* Should mask be applied to a directory? */ + if (is_dir && !(mask & FS_ISDIR)) + return false; + + /* Should mask be applied to a child? */ + if (iter_type == FSNOTIFY_ITER_TYPE_PARENT && + !(mask & FS_EVENT_ON_CHILD)) + return false; + + return true; +} + +/* + * Effective ignore mask taking into account if event victim is a + * directory and whether it is reported to a watching parent. + */ +static inline __u32 fsnotify_effective_ignore_mask(struct fsnotify_mark *mark, + bool is_dir, int iter_type) +{ + __u32 ignore_mask = fsnotify_ignored_events(mark); + + if (!ignore_mask) + return 0; + + /* For non-dir and non-child, no need to consult the event flags */ + if (!is_dir && iter_type != FSNOTIFY_ITER_TYPE_PARENT) + return ignore_mask; + + ignore_mask = fsnotify_ignore_mask(mark); + if (!fsnotify_mask_applicable(ignore_mask, is_dir, iter_type)) + return 0; + + return ignore_mask & ALL_FSNOTIFY_EVENTS; +} + +/* Get mask for calculating object interest taking ignore mask into account */ +static inline __u32 fsnotify_calc_mask(struct fsnotify_mark *mark) +{ + __u32 mask = mark->mask; + + if (!fsnotify_ignored_events(mark)) + return mask; + + /* Interest in FS_MODIFY may be needed for clearing ignore mask */ + if (!(mark->flags & FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY)) + mask |= FS_MODIFY; + + /* + * If mark is interested in ignoring events on children, the object must + * show interest in those events for fsnotify_parent() to notice it. + */ + return mask | mark->ignore_mask; +} + /* Get mask of events for a list of marks */ extern __u32 fsnotify_conn_mask(struct fsnotify_mark_connector *conn); /* Calculate mask of events for a list of marks */ @@ -604,27 +765,27 @@ extern int fsnotify_get_conn_fsid(const struct fsnotify_mark_connector *conn, __kernel_fsid_t *fsid); /* attach the mark to the object */ extern int fsnotify_add_mark(struct fsnotify_mark *mark, - fsnotify_connp_t *connp, unsigned int type, - int allow_dups, __kernel_fsid_t *fsid); + fsnotify_connp_t *connp, unsigned int obj_type, + int add_flags, __kernel_fsid_t *fsid); extern int fsnotify_add_mark_locked(struct fsnotify_mark *mark, fsnotify_connp_t *connp, - unsigned int type, int allow_dups, + unsigned int obj_type, int add_flags, __kernel_fsid_t *fsid); /* attach the mark to the inode */ static inline int fsnotify_add_inode_mark(struct fsnotify_mark *mark, struct inode *inode, - int allow_dups) + int add_flags) { return fsnotify_add_mark(mark, &inode->i_fsnotify_marks, - FSNOTIFY_OBJ_TYPE_INODE, allow_dups, NULL); + FSNOTIFY_OBJ_TYPE_INODE, add_flags, NULL); } static inline int fsnotify_add_inode_mark_locked(struct fsnotify_mark *mark, struct inode *inode, - int allow_dups) + int add_flags) { return fsnotify_add_mark_locked(mark, &inode->i_fsnotify_marks, - FSNOTIFY_OBJ_TYPE_INODE, allow_dups, + FSNOTIFY_OBJ_TYPE_INODE, add_flags, NULL); } @@ -637,22 +798,23 @@ extern void fsnotify_detach_mark(struct fsnotify_mark *mark); extern void fsnotify_free_mark(struct fsnotify_mark *mark); /* Wait until all marks queued for destruction are destroyed */ extern void fsnotify_wait_marks_destroyed(void); -/* run all the marks in a group, and clear all of the marks attached to given object type */ -extern void fsnotify_clear_marks_by_group(struct fsnotify_group *group, unsigned int type); +/* Clear all of the marks of a group attached to a given object type */ +extern void fsnotify_clear_marks_by_group(struct fsnotify_group *group, + unsigned int obj_type); /* run all the marks in a group, and clear all of the vfsmount marks */ static inline void fsnotify_clear_vfsmount_marks_by_group(struct fsnotify_group *group) { - fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_VFSMOUNT_FL); + fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_VFSMOUNT); } /* run all the marks in a group, and clear all of the inode marks */ static inline void fsnotify_clear_inode_marks_by_group(struct fsnotify_group *group) { - fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_INODE_FL); + fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_INODE); } /* run all the marks in a group, and clear all of the sn marks */ static inline void fsnotify_clear_sb_marks_by_group(struct fsnotify_group *group) { - fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_SB_FL); + fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_SB); } extern void fsnotify_get_mark(struct fsnotify_mark *mark); extern void fsnotify_put_mark(struct fsnotify_mark *mark); diff --git a/include/linux/fsverity.h b/include/linux/fsverity.h index b568b3c7d095..40f14e5fed9d 100644 --- a/include/linux/fsverity.h +++ b/include/linux/fsverity.h @@ -12,8 +12,19 @@ #define _LINUX_FSVERITY_H #include <linux/fs.h> +#include <crypto/hash_info.h> +#include <crypto/sha2.h> #include <uapi/linux/fsverity.h> +/* + * Largest digest size among all hash algorithms supported by fs-verity. + * Currently assumed to be <= size of fsverity_descriptor::root_hash. + */ +#define FS_VERITY_MAX_DIGEST_SIZE SHA512_DIGEST_SIZE + +/* Arbitrary limit to bound the kmalloc() size. Can be changed. */ +#define FS_VERITY_MAX_DESCRIPTOR_SIZE 16384 + /* Verity operations for filesystems */ struct fsverity_operations { @@ -131,6 +142,9 @@ int fsverity_ioctl_enable(struct file *filp, const void __user *arg); /* measure.c */ int fsverity_ioctl_measure(struct file *filp, void __user *arg); +int fsverity_get_digest(struct inode *inode, + u8 digest[FS_VERITY_MAX_DIGEST_SIZE], + enum hash_algo *alg); /* open.c */ @@ -170,6 +184,13 @@ static inline int fsverity_ioctl_measure(struct file *filp, void __user *arg) return -EOPNOTSUPP; } +static inline int fsverity_get_digest(struct inode *inode, + u8 digest[FS_VERITY_MAX_DIGEST_SIZE], + enum hash_algo *alg) +{ + return -EOPNOTSUPP; +} + /* open.c */ static inline int fsverity_file_open(struct inode *inode, struct file *filp) @@ -221,7 +242,7 @@ static inline void fsverity_enqueue_verify_work(struct work_struct *work) * * This checks whether ->i_verity_info has been set. * - * Filesystems call this from ->readpages() to check whether the pages need to + * Filesystems call this from ->readahead() to check whether the pages need to * be verified or not. Don't use IS_VERITY() for this purpose; it's subject to * a race condition where the file is being read concurrently with * FS_IOC_ENABLE_VERITY completing. (S_VERITY is set before ->i_verity_info.) diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 9999e29187de..62557d4bffc2 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -9,6 +9,7 @@ #include <linux/trace_recursion.h> #include <linux/trace_clock.h> +#include <linux/jump_label.h> #include <linux/kallsyms.h> #include <linux/linkage.h> #include <linux/bitops.h> @@ -30,6 +31,12 @@ #define ARCH_SUPPORTS_FTRACE_OPS 0 #endif +#ifdef CONFIG_TRACING +extern void ftrace_boot_snapshot(void); +#else +static inline void ftrace_boot_snapshot(void) { } +#endif + #ifdef CONFIG_FUNCTION_TRACER struct ftrace_ops; struct ftrace_regs; @@ -94,9 +101,6 @@ static inline int ftrace_mod_get_kallsym(unsigned int symnum, unsigned long *val #ifdef CONFIG_FUNCTION_TRACER extern int ftrace_enabled; -extern int -ftrace_enable_sysctl(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos); #ifndef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS @@ -204,6 +208,43 @@ enum { FTRACE_OPS_FL_DIRECT = BIT(17), }; +/* + * FTRACE_OPS_CMD_* commands allow the ftrace core logic to request changes + * to a ftrace_ops. Note, the requests may fail. + * + * ENABLE_SHARE_IPMODIFY_SELF - enable a DIRECT ops to work on the same + * function as an ops with IPMODIFY. Called + * when the DIRECT ops is being registered. + * This is called with both direct_mutex and + * ftrace_lock are locked. + * + * ENABLE_SHARE_IPMODIFY_PEER - enable a DIRECT ops to work on the same + * function as an ops with IPMODIFY. Called + * when the other ops (the one with IPMODIFY) + * is being registered. + * This is called with direct_mutex locked. + * + * DISABLE_SHARE_IPMODIFY_PEER - disable a DIRECT ops to work on the same + * function as an ops with IPMODIFY. Called + * when the other ops (the one with IPMODIFY) + * is being unregistered. + * This is called with direct_mutex locked. + */ +enum ftrace_ops_cmd { + FTRACE_OPS_CMD_ENABLE_SHARE_IPMODIFY_SELF, + FTRACE_OPS_CMD_ENABLE_SHARE_IPMODIFY_PEER, + FTRACE_OPS_CMD_DISABLE_SHARE_IPMODIFY_PEER, +}; + +/* + * For most ftrace_ops_cmd, + * Returns: + * 0 - Success. + * Negative on failure. The return value is dependent on the + * callback. + */ +typedef int (*ftrace_ops_func_t)(struct ftrace_ops *op, enum ftrace_ops_cmd cmd); + #ifdef CONFIG_DYNAMIC_FTRACE /* The hash used to know what functions callbacks trace */ struct ftrace_ops_hash { @@ -215,7 +256,10 @@ struct ftrace_ops_hash { void ftrace_free_init_mem(void); void ftrace_free_mem(struct module *mod, void *start, void *end); #else -static inline void ftrace_free_init_mem(void) { } +static inline void ftrace_free_init_mem(void) +{ + ftrace_boot_snapshot(); +} static inline void ftrace_free_mem(struct module *mod, void *start, void *end) { } #endif @@ -243,6 +287,7 @@ struct ftrace_ops { unsigned long trampoline; unsigned long trampoline_size; struct list_head list; + ftrace_ops_func_t ops_func; #endif }; @@ -293,6 +338,8 @@ int unregister_ftrace_function(struct ftrace_ops *ops); extern void ftrace_stub(unsigned long a0, unsigned long a1, struct ftrace_ops *op, struct ftrace_regs *fregs); + +int ftrace_lookup_symbols(const char **sorted_syms, size_t cnt, unsigned long *addrs); #else /* !CONFIG_FUNCTION_TRACER */ /* * (un)register_ftrace_function must be a macro since the ops parameter @@ -303,6 +350,10 @@ extern void ftrace_stub(unsigned long a0, unsigned long a1, static inline void ftrace_kill(void) { } static inline void ftrace_free_init_mem(void) { } static inline void ftrace_free_mem(struct module *mod, void *start, void *end) { } +static inline int ftrace_lookup_symbols(const char **sorted_syms, size_t cnt, unsigned long *addrs) +{ + return -EOPNOTSUPP; +} #endif /* CONFIG_FUNCTION_TRACER */ struct ftrace_func_entry { @@ -327,6 +378,7 @@ unsigned long ftrace_find_rec_direct(unsigned long ip); int register_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr); int unregister_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr); int modify_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr); +int modify_ftrace_direct_multi_nolock(struct ftrace_ops *ops, unsigned long addr); #else struct ftrace_ops; @@ -371,6 +423,10 @@ static inline int modify_ftrace_direct_multi(struct ftrace_ops *ops, unsigned lo { return -ENODEV; } +static inline int modify_ftrace_direct_multi_nolock(struct ftrace_ops *ops, unsigned long addr) +{ + return -ENODEV; +} #endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */ #ifndef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS @@ -439,8 +495,8 @@ static inline void stack_tracer_enable(void) { } #ifdef CONFIG_DYNAMIC_FTRACE -int ftrace_arch_code_modify_prepare(void); -int ftrace_arch_code_modify_post_process(void); +void ftrace_arch_code_modify_prepare(void); +void ftrace_arch_code_modify_post_process(void); enum ftrace_bug_type { FTRACE_BUG_UNKNOWN, @@ -512,6 +568,8 @@ struct dyn_ftrace { int ftrace_set_filter_ip(struct ftrace_ops *ops, unsigned long ip, int remove, int reset); +int ftrace_set_filter_ips(struct ftrace_ops *ops, unsigned long *ips, + unsigned int cnt, int remove, int reset); int ftrace_set_filter(struct ftrace_ops *ops, unsigned char *buf, int len, int reset); int ftrace_set_notrace(struct ftrace_ops *ops, unsigned char *buf, @@ -802,6 +860,7 @@ static inline unsigned long ftrace_location(unsigned long ip) #define ftrace_regex_open(ops, flag, inod, file) ({ -ENODEV; }) #define ftrace_set_early_filter(ops, buf, enable) do { } while (0) #define ftrace_set_filter_ip(ops, ip, remove, reset) ({ -ENODEV; }) +#define ftrace_set_filter_ips(ops, ips, cnt, remove, reset) ({ -ENODEV; }) #define ftrace_set_filter(ops, buf, len, reset) ({ -ENODEV; }) #define ftrace_set_notrace(ops, buf, len, reset) ({ -ENODEV; }) #define ftrace_free_filter(ops) do { } while (0) @@ -1006,7 +1065,20 @@ unsigned long ftrace_graph_ret_addr(struct task_struct *task, int *idx, extern int register_ftrace_graph(struct fgraph_ops *ops); extern void unregister_ftrace_graph(struct fgraph_ops *ops); -extern bool ftrace_graph_is_dead(void); +/** + * ftrace_graph_is_dead - returns true if ftrace_graph_stop() was called + * + * ftrace_graph_stop() is called when a severe error is detected in + * the function graph tracing. This function is called by the critical + * paths of function graph to keep those paths from doing any more harm. + */ +DECLARE_STATIC_KEY_FALSE(kill_ftrace_graph); + +static inline bool ftrace_graph_is_dead(void) +{ + return static_branch_unlikely(&kill_ftrace_graph); +} + extern void ftrace_graph_stop(void); /* The current handlers in use */ @@ -1050,47 +1122,6 @@ static inline void unpause_graph_tracing(void) { } #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ #ifdef CONFIG_TRACING - -/* flags for current->trace */ -enum { - TSK_TRACE_FL_TRACE_BIT = 0, - TSK_TRACE_FL_GRAPH_BIT = 1, -}; -enum { - TSK_TRACE_FL_TRACE = 1 << TSK_TRACE_FL_TRACE_BIT, - TSK_TRACE_FL_GRAPH = 1 << TSK_TRACE_FL_GRAPH_BIT, -}; - -static inline void set_tsk_trace_trace(struct task_struct *tsk) -{ - set_bit(TSK_TRACE_FL_TRACE_BIT, &tsk->trace); -} - -static inline void clear_tsk_trace_trace(struct task_struct *tsk) -{ - clear_bit(TSK_TRACE_FL_TRACE_BIT, &tsk->trace); -} - -static inline int test_tsk_trace_trace(struct task_struct *tsk) -{ - return tsk->trace & TSK_TRACE_FL_TRACE; -} - -static inline void set_tsk_trace_graph(struct task_struct *tsk) -{ - set_bit(TSK_TRACE_FL_GRAPH_BIT, &tsk->trace); -} - -static inline void clear_tsk_trace_graph(struct task_struct *tsk) -{ - clear_bit(TSK_TRACE_FL_GRAPH_BIT, &tsk->trace); -} - -static inline int test_tsk_trace_graph(struct task_struct *tsk) -{ - return tsk->trace & TSK_TRACE_FL_GRAPH; -} - enum ftrace_dump_mode; extern enum ftrace_dump_mode ftrace_dump_on_oops; diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h index 3a532ba66f6c..89b9bdfca925 100644 --- a/include/linux/fwnode.h +++ b/include/linux/fwnode.h @@ -27,11 +27,15 @@ struct device; * driver needs its child devices to be bound with * their respective drivers as soon as they are * added. + * BEST_EFFORT: The fwnode/device needs to probe early and might be missing some + * suppliers. Only enforce ordering with suppliers that have + * drivers. */ #define FWNODE_FLAG_LINKS_ADDED BIT(0) #define FWNODE_FLAG_NOT_DEVICE BIT(1) #define FWNODE_FLAG_INITIALIZED BIT(2) #define FWNODE_FLAG_NEEDS_CHILD_BOUND_ON_ADD BIT(3) +#define FWNODE_FLAG_BEST_EFFORT BIT(4) struct fwnode_handle { struct fwnode_handle *secondary; @@ -113,6 +117,9 @@ struct fwnode_operations { bool (*device_is_available)(const struct fwnode_handle *fwnode); const void *(*device_get_match_data)(const struct fwnode_handle *fwnode, const struct device *dev); + bool (*device_dma_supported)(const struct fwnode_handle *fwnode); + enum dev_dma_attr + (*device_get_dma_attr)(const struct fwnode_handle *fwnode); bool (*property_present)(const struct fwnode_handle *fwnode, const char *propname); int (*property_read_int_array)(const struct fwnode_handle *fwnode, @@ -145,15 +152,17 @@ struct fwnode_operations { (*graph_get_port_parent)(struct fwnode_handle *fwnode); int (*graph_parse_endpoint)(const struct fwnode_handle *fwnode, struct fwnode_endpoint *endpoint); + void __iomem *(*iomap)(struct fwnode_handle *fwnode, int index); + int (*irq_get)(const struct fwnode_handle *fwnode, unsigned int index); int (*add_links)(struct fwnode_handle *fwnode); }; -#define fwnode_has_op(fwnode, op) \ - ((fwnode) && (fwnode)->ops && (fwnode)->ops->op) +#define fwnode_has_op(fwnode, op) \ + (!IS_ERR_OR_NULL(fwnode) && (fwnode)->ops && (fwnode)->ops->op) + #define fwnode_call_int_op(fwnode, op, ...) \ - (fwnode ? (fwnode_has_op(fwnode, op) ? \ - (fwnode)->ops->op(fwnode, ## __VA_ARGS__) : -ENXIO) : \ - -EINVAL) + (fwnode_has_op(fwnode, op) ? \ + (fwnode)->ops->op(fwnode, ## __VA_ARGS__) : (IS_ERR_OR_NULL(fwnode) ? -EINVAL : -ENXIO)) #define fwnode_call_bool_op(fwnode, op, ...) \ (fwnode_has_op(fwnode, op) ? \ diff --git a/include/linux/gameport.h b/include/linux/gameport.h index 69081d899492..8c2f00018e89 100644 --- a/include/linux/gameport.h +++ b/include/linux/gameport.h @@ -110,7 +110,7 @@ static inline void gameport_free_port(struct gameport *gameport) static inline void gameport_set_name(struct gameport *gameport, const char *name) { - strlcpy(gameport->name, name, sizeof(gameport->name)); + strscpy(gameport->name, name, sizeof(gameport->name)); } /* diff --git a/include/linux/genhd.h b/include/linux/genhd.h deleted file mode 100644 index 74c410263113..000000000000 --- a/include/linux/genhd.h +++ /dev/null @@ -1,334 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _LINUX_GENHD_H -#define _LINUX_GENHD_H - -/* - * genhd.h Copyright (C) 1992 Drew Eckhardt - * Generic hard disk header file by - * Drew Eckhardt - * - * <drew@colorado.edu> - */ - -#include <linux/types.h> -#include <linux/kdev_t.h> -#include <linux/uuid.h> -#include <linux/blk_types.h> -#include <linux/device.h> -#include <linux/xarray.h> - -extern const struct device_type disk_type; -extern struct device_type part_type; -extern struct class block_class; - -#define DISK_MAX_PARTS 256 -#define DISK_NAME_LEN 32 - -#define PARTITION_META_INFO_VOLNAMELTH 64 -/* - * Enough for the string representation of any kind of UUID plus NULL. - * EFI UUID is 36 characters. MSDOS UUID is 11 characters. - */ -#define PARTITION_META_INFO_UUIDLTH (UUID_STRING_LEN + 1) - -struct partition_meta_info { - char uuid[PARTITION_META_INFO_UUIDLTH]; - u8 volname[PARTITION_META_INFO_VOLNAMELTH]; -}; - -/** - * DOC: genhd capability flags - * - * ``GENHD_FL_REMOVABLE`` (0x0001): indicates that the block device - * gives access to removable media. - * When set, the device remains present even when media is not - * inserted. - * Must not be set for devices which are removed entirely when the - * media is removed. - * - * ``GENHD_FL_CD`` (0x0008): the block device is a CD-ROM-style - * device. - * Affects responses to the ``CDROM_GET_CAPABILITY`` ioctl. - * - * ``GENHD_FL_SUPPRESS_PARTITION_INFO`` (0x0020): don't include - * partition information in ``/proc/partitions`` or in the output of - * printk_all_partitions(). - * Used for the null block device and some MMC devices. - * - * ``GENHD_FL_EXT_DEVT`` (0x0040): the driver supports extended - * dynamic ``dev_t``, i.e. it wants extended device numbers - * (``BLOCK_EXT_MAJOR``). - * This affects the maximum number of partitions. - * - * ``GENHD_FL_NATIVE_CAPACITY`` (0x0080): based on information in the - * partition table, the device's capacity has been extended to its - * native capacity; i.e. the device has hidden capacity used by one - * of the partitions (this is a flag used so that native capacity is - * only ever unlocked once). - * - * ``GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE`` (0x0100): event polling is - * blocked whenever a writer holds an exclusive lock. - * - * ``GENHD_FL_NO_PART_SCAN`` (0x0200): partition scanning is disabled. - * Used for loop devices in their default settings and some MMC - * devices. - * - * ``GENHD_FL_HIDDEN`` (0x0400): the block device is hidden; it - * doesn't produce events, doesn't appear in sysfs, and doesn't have - * an associated ``bdev``. - * Implies ``GENHD_FL_SUPPRESS_PARTITION_INFO`` and - * ``GENHD_FL_NO_PART_SCAN``. - * Used for multipath devices. - */ -#define GENHD_FL_REMOVABLE 0x0001 -/* 2 is unused (used to be GENHD_FL_DRIVERFS) */ -/* 4 is unused (used to be GENHD_FL_MEDIA_CHANGE_NOTIFY) */ -#define GENHD_FL_CD 0x0008 -#define GENHD_FL_SUPPRESS_PARTITION_INFO 0x0020 -#define GENHD_FL_EXT_DEVT 0x0040 -#define GENHD_FL_NATIVE_CAPACITY 0x0080 -#define GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE 0x0100 -#define GENHD_FL_NO_PART_SCAN 0x0200 -#define GENHD_FL_HIDDEN 0x0400 - -enum { - DISK_EVENT_MEDIA_CHANGE = 1 << 0, /* media changed */ - DISK_EVENT_EJECT_REQUEST = 1 << 1, /* eject requested */ -}; - -enum { - /* Poll even if events_poll_msecs is unset */ - DISK_EVENT_FLAG_POLL = 1 << 0, - /* Forward events to udev */ - DISK_EVENT_FLAG_UEVENT = 1 << 1, -}; - -struct disk_events; -struct badblocks; - -struct blk_integrity { - const struct blk_integrity_profile *profile; - unsigned char flags; - unsigned char tuple_size; - unsigned char interval_exp; - unsigned char tag_size; -}; - -struct gendisk { - /* major, first_minor and minors are input parameters only, - * don't use directly. Use disk_devt() and disk_max_parts(). - */ - int major; /* major number of driver */ - int first_minor; - int minors; /* maximum number of minors, =1 for - * disks that can't be partitioned. */ - - char disk_name[DISK_NAME_LEN]; /* name of major driver */ - - unsigned short events; /* supported events */ - unsigned short event_flags; /* flags related to event processing */ - - struct xarray part_tbl; - struct block_device *part0; - - const struct block_device_operations *fops; - struct request_queue *queue; - void *private_data; - - int flags; - unsigned long state; -#define GD_NEED_PART_SCAN 0 -#define GD_READ_ONLY 1 -#define GD_DEAD 2 - - struct mutex open_mutex; /* open/close mutex */ - unsigned open_partitions; /* number of open partitions */ - - struct backing_dev_info *bdi; - struct kobject *slave_dir; -#ifdef CONFIG_BLOCK_HOLDER_DEPRECATED - struct list_head slave_bdevs; -#endif - struct timer_rand_state *random; - atomic_t sync_io; /* RAID */ - struct disk_events *ev; -#ifdef CONFIG_BLK_DEV_INTEGRITY - struct kobject integrity_kobj; -#endif /* CONFIG_BLK_DEV_INTEGRITY */ -#if IS_ENABLED(CONFIG_CDROM) - struct cdrom_device_info *cdi; -#endif - int node_id; - struct badblocks *bb; - struct lockdep_map lockdep_map; - u64 diskseq; -}; - -static inline bool disk_live(struct gendisk *disk) -{ - return !inode_unhashed(disk->part0->bd_inode); -} - -/* - * The gendisk is refcounted by the part0 block_device, and the bd_device - * therein is also used for device model presentation in sysfs. - */ -#define dev_to_disk(device) \ - (dev_to_bdev(device)->bd_disk) -#define disk_to_dev(disk) \ - (&((disk)->part0->bd_device)) - -#if IS_REACHABLE(CONFIG_CDROM) -#define disk_to_cdi(disk) ((disk)->cdi) -#else -#define disk_to_cdi(disk) NULL -#endif - -static inline int disk_max_parts(struct gendisk *disk) -{ - if (disk->flags & GENHD_FL_EXT_DEVT) - return DISK_MAX_PARTS; - return disk->minors; -} - -static inline bool disk_part_scan_enabled(struct gendisk *disk) -{ - return disk_max_parts(disk) > 1 && - !(disk->flags & GENHD_FL_NO_PART_SCAN); -} - -static inline dev_t disk_devt(struct gendisk *disk) -{ - return MKDEV(disk->major, disk->first_minor); -} - -void disk_uevent(struct gendisk *disk, enum kobject_action action); - -/* block/genhd.c */ -int __must_check device_add_disk(struct device *parent, struct gendisk *disk, - const struct attribute_group **groups); -static inline int __must_check add_disk(struct gendisk *disk) -{ - return device_add_disk(NULL, disk, NULL); -} -extern void del_gendisk(struct gendisk *gp); - -void invalidate_disk(struct gendisk *disk); - -void set_disk_ro(struct gendisk *disk, bool read_only); - -static inline int get_disk_ro(struct gendisk *disk) -{ - return disk->part0->bd_read_only || - test_bit(GD_READ_ONLY, &disk->state); -} - -static inline int bdev_read_only(struct block_device *bdev) -{ - return bdev->bd_read_only || get_disk_ro(bdev->bd_disk); -} - -extern void disk_block_events(struct gendisk *disk); -extern void disk_unblock_events(struct gendisk *disk); -extern void disk_flush_events(struct gendisk *disk, unsigned int mask); -bool set_capacity_and_notify(struct gendisk *disk, sector_t size); -bool disk_force_media_change(struct gendisk *disk, unsigned int events); - -/* drivers/char/random.c */ -extern void add_disk_randomness(struct gendisk *disk) __latent_entropy; -extern void rand_initialize_disk(struct gendisk *disk); - -static inline sector_t get_start_sect(struct block_device *bdev) -{ - return bdev->bd_start_sect; -} - -static inline sector_t bdev_nr_sectors(struct block_device *bdev) -{ - return bdev->bd_nr_sectors; -} - -static inline loff_t bdev_nr_bytes(struct block_device *bdev) -{ - return (loff_t)bdev_nr_sectors(bdev) << SECTOR_SHIFT; -} - -static inline sector_t get_capacity(struct gendisk *disk) -{ - return bdev_nr_sectors(disk->part0); -} - -static inline u64 sb_bdev_nr_blocks(struct super_block *sb) -{ - return bdev_nr_sectors(sb->s_bdev) >> - (sb->s_blocksize_bits - SECTOR_SHIFT); -} - -int bdev_disk_changed(struct gendisk *disk, bool invalidate); -void blk_drop_partitions(struct gendisk *disk); - -struct gendisk *__alloc_disk_node(struct request_queue *q, int node_id, - struct lock_class_key *lkclass); -extern void put_disk(struct gendisk *disk); -struct gendisk *__blk_alloc_disk(int node, struct lock_class_key *lkclass); - -/** - * blk_alloc_disk - allocate a gendisk structure - * @node_id: numa node to allocate on - * - * Allocate and pre-initialize a gendisk structure for use with BIO based - * drivers. - * - * Context: can sleep - */ -#define blk_alloc_disk(node_id) \ -({ \ - static struct lock_class_key __key; \ - \ - __blk_alloc_disk(node_id, &__key); \ -}) -void blk_cleanup_disk(struct gendisk *disk); - -int __register_blkdev(unsigned int major, const char *name, - void (*probe)(dev_t devt)); -#define register_blkdev(major, name) \ - __register_blkdev(major, name, NULL) -void unregister_blkdev(unsigned int major, const char *name); - -bool bdev_check_media_change(struct block_device *bdev); -int __invalidate_device(struct block_device *bdev, bool kill_dirty); -void set_capacity(struct gendisk *disk, sector_t size); - -#ifdef CONFIG_BLOCK_HOLDER_DEPRECATED -int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk); -void bd_unlink_disk_holder(struct block_device *bdev, struct gendisk *disk); -int bd_register_pending_holders(struct gendisk *disk); -#else -static inline int bd_link_disk_holder(struct block_device *bdev, - struct gendisk *disk) -{ - return 0; -} -static inline void bd_unlink_disk_holder(struct block_device *bdev, - struct gendisk *disk) -{ -} -static inline int bd_register_pending_holders(struct gendisk *disk) -{ - return 0; -} -#endif /* CONFIG_BLOCK_HOLDER_DEPRECATED */ - -dev_t part_devt(struct gendisk *disk, u8 partno); -void inc_diskseq(struct gendisk *disk); -dev_t blk_lookup_devt(const char *name, int partno); -void blk_request_module(dev_t devt); -#ifdef CONFIG_BLOCK -void printk_all_partitions(void); -#else /* CONFIG_BLOCK */ -static inline void printk_all_partitions(void) -{ -} -#endif /* CONFIG_BLOCK */ - -#endif /* _LINUX_GENHD_H */ diff --git a/include/linux/genl_magic_func.h b/include/linux/genl_magic_func.h index 939b1a8f571b..4a4b387181ad 100644 --- a/include/linux/genl_magic_func.h +++ b/include/linux/genl_magic_func.h @@ -294,6 +294,7 @@ static struct genl_family ZZZ_genl_family __ro_after_init = { .ops = ZZZ_genl_ops, .n_ops = ARRAY_SIZE(ZZZ_genl_ops), .mcgrps = ZZZ_genl_mcgrps, + .resv_start_op = 42, /* drbd is currently the only user */ .n_mcgrps = ARRAY_SIZE(ZZZ_genl_mcgrps), .module = THIS_MODULE, }; diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 8fcc38467af6..ef4aea3b356e 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -2,340 +2,13 @@ #ifndef __LINUX_GFP_H #define __LINUX_GFP_H -#include <linux/mmdebug.h> +#include <linux/gfp_types.h> + #include <linux/mmzone.h> -#include <linux/stddef.h> -#include <linux/linkage.h> #include <linux/topology.h> -/* The typedef is in types.h but we want the documentation here */ -#if 0 -/** - * typedef gfp_t - Memory allocation flags. - * - * GFP flags are commonly used throughout Linux to indicate how memory - * should be allocated. The GFP acronym stands for get_free_pages(), - * the underlying memory allocation function. Not every GFP flag is - * supported by every function which may allocate memory. Most users - * will want to use a plain ``GFP_KERNEL``. - */ -typedef unsigned int __bitwise gfp_t; -#endif - struct vm_area_struct; -/* - * In case of changes, please don't forget to update - * include/trace/events/mmflags.h and tools/perf/builtin-kmem.c - */ - -/* Plain integer GFP bitmasks. Do not use this directly. */ -#define ___GFP_DMA 0x01u -#define ___GFP_HIGHMEM 0x02u -#define ___GFP_DMA32 0x04u -#define ___GFP_MOVABLE 0x08u -#define ___GFP_RECLAIMABLE 0x10u -#define ___GFP_HIGH 0x20u -#define ___GFP_IO 0x40u -#define ___GFP_FS 0x80u -#define ___GFP_ZERO 0x100u -#define ___GFP_ATOMIC 0x200u -#define ___GFP_DIRECT_RECLAIM 0x400u -#define ___GFP_KSWAPD_RECLAIM 0x800u -#define ___GFP_WRITE 0x1000u -#define ___GFP_NOWARN 0x2000u -#define ___GFP_RETRY_MAYFAIL 0x4000u -#define ___GFP_NOFAIL 0x8000u -#define ___GFP_NORETRY 0x10000u -#define ___GFP_MEMALLOC 0x20000u -#define ___GFP_COMP 0x40000u -#define ___GFP_NOMEMALLOC 0x80000u -#define ___GFP_HARDWALL 0x100000u -#define ___GFP_THISNODE 0x200000u -#define ___GFP_ACCOUNT 0x400000u -#define ___GFP_ZEROTAGS 0x800000u -#define ___GFP_SKIP_KASAN_POISON 0x1000000u -#ifdef CONFIG_LOCKDEP -#define ___GFP_NOLOCKDEP 0x2000000u -#else -#define ___GFP_NOLOCKDEP 0 -#endif -/* If the above are modified, __GFP_BITS_SHIFT may need updating */ - -/* - * Physical address zone modifiers (see linux/mmzone.h - low four bits) - * - * Do not put any conditional on these. If necessary modify the definitions - * without the underscores and use them consistently. The definitions here may - * be used in bit comparisons. - */ -#define __GFP_DMA ((__force gfp_t)___GFP_DMA) -#define __GFP_HIGHMEM ((__force gfp_t)___GFP_HIGHMEM) -#define __GFP_DMA32 ((__force gfp_t)___GFP_DMA32) -#define __GFP_MOVABLE ((__force gfp_t)___GFP_MOVABLE) /* ZONE_MOVABLE allowed */ -#define GFP_ZONEMASK (__GFP_DMA|__GFP_HIGHMEM|__GFP_DMA32|__GFP_MOVABLE) - -/** - * DOC: Page mobility and placement hints - * - * Page mobility and placement hints - * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - * - * These flags provide hints about how mobile the page is. Pages with similar - * mobility are placed within the same pageblocks to minimise problems due - * to external fragmentation. - * - * %__GFP_MOVABLE (also a zone modifier) indicates that the page can be - * moved by page migration during memory compaction or can be reclaimed. - * - * %__GFP_RECLAIMABLE is used for slab allocations that specify - * SLAB_RECLAIM_ACCOUNT and whose pages can be freed via shrinkers. - * - * %__GFP_WRITE indicates the caller intends to dirty the page. Where possible, - * these pages will be spread between local zones to avoid all the dirty - * pages being in one zone (fair zone allocation policy). - * - * %__GFP_HARDWALL enforces the cpuset memory allocation policy. - * - * %__GFP_THISNODE forces the allocation to be satisfied from the requested - * node with no fallbacks or placement policy enforcements. - * - * %__GFP_ACCOUNT causes the allocation to be accounted to kmemcg. - */ -#define __GFP_RECLAIMABLE ((__force gfp_t)___GFP_RECLAIMABLE) -#define __GFP_WRITE ((__force gfp_t)___GFP_WRITE) -#define __GFP_HARDWALL ((__force gfp_t)___GFP_HARDWALL) -#define __GFP_THISNODE ((__force gfp_t)___GFP_THISNODE) -#define __GFP_ACCOUNT ((__force gfp_t)___GFP_ACCOUNT) - -/** - * DOC: Watermark modifiers - * - * Watermark modifiers -- controls access to emergency reserves - * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - * - * %__GFP_HIGH indicates that the caller is high-priority and that granting - * the request is necessary before the system can make forward progress. - * For example, creating an IO context to clean pages. - * - * %__GFP_ATOMIC indicates that the caller cannot reclaim or sleep and is - * high priority. Users are typically interrupt handlers. This may be - * used in conjunction with %__GFP_HIGH - * - * %__GFP_MEMALLOC allows access to all memory. This should only be used when - * the caller guarantees the allocation will allow more memory to be freed - * very shortly e.g. process exiting or swapping. Users either should - * be the MM or co-ordinating closely with the VM (e.g. swap over NFS). - * Users of this flag have to be extremely careful to not deplete the reserve - * completely and implement a throttling mechanism which controls the - * consumption of the reserve based on the amount of freed memory. - * Usage of a pre-allocated pool (e.g. mempool) should be always considered - * before using this flag. - * - * %__GFP_NOMEMALLOC is used to explicitly forbid access to emergency reserves. - * This takes precedence over the %__GFP_MEMALLOC flag if both are set. - */ -#define __GFP_ATOMIC ((__force gfp_t)___GFP_ATOMIC) -#define __GFP_HIGH ((__force gfp_t)___GFP_HIGH) -#define __GFP_MEMALLOC ((__force gfp_t)___GFP_MEMALLOC) -#define __GFP_NOMEMALLOC ((__force gfp_t)___GFP_NOMEMALLOC) - -/** - * DOC: Reclaim modifiers - * - * Reclaim modifiers - * ~~~~~~~~~~~~~~~~~ - * Please note that all the following flags are only applicable to sleepable - * allocations (e.g. %GFP_NOWAIT and %GFP_ATOMIC will ignore them). - * - * %__GFP_IO can start physical IO. - * - * %__GFP_FS can call down to the low-level FS. Clearing the flag avoids the - * allocator recursing into the filesystem which might already be holding - * locks. - * - * %__GFP_DIRECT_RECLAIM indicates that the caller may enter direct reclaim. - * This flag can be cleared to avoid unnecessary delays when a fallback - * option is available. - * - * %__GFP_KSWAPD_RECLAIM indicates that the caller wants to wake kswapd when - * the low watermark is reached and have it reclaim pages until the high - * watermark is reached. A caller may wish to clear this flag when fallback - * options are available and the reclaim is likely to disrupt the system. The - * canonical example is THP allocation where a fallback is cheap but - * reclaim/compaction may cause indirect stalls. - * - * %__GFP_RECLAIM is shorthand to allow/forbid both direct and kswapd reclaim. - * - * The default allocator behavior depends on the request size. We have a concept - * of so called costly allocations (with order > %PAGE_ALLOC_COSTLY_ORDER). - * !costly allocations are too essential to fail so they are implicitly - * non-failing by default (with some exceptions like OOM victims might fail so - * the caller still has to check for failures) while costly requests try to be - * not disruptive and back off even without invoking the OOM killer. - * The following three modifiers might be used to override some of these - * implicit rules - * - * %__GFP_NORETRY: The VM implementation will try only very lightweight - * memory direct reclaim to get some memory under memory pressure (thus - * it can sleep). It will avoid disruptive actions like OOM killer. The - * caller must handle the failure which is quite likely to happen under - * heavy memory pressure. The flag is suitable when failure can easily be - * handled at small cost, such as reduced throughput - * - * %__GFP_RETRY_MAYFAIL: The VM implementation will retry memory reclaim - * procedures that have previously failed if there is some indication - * that progress has been made else where. It can wait for other - * tasks to attempt high level approaches to freeing memory such as - * compaction (which removes fragmentation) and page-out. - * There is still a definite limit to the number of retries, but it is - * a larger limit than with %__GFP_NORETRY. - * Allocations with this flag may fail, but only when there is - * genuinely little unused memory. While these allocations do not - * directly trigger the OOM killer, their failure indicates that - * the system is likely to need to use the OOM killer soon. The - * caller must handle failure, but can reasonably do so by failing - * a higher-level request, or completing it only in a much less - * efficient manner. - * If the allocation does fail, and the caller is in a position to - * free some non-essential memory, doing so could benefit the system - * as a whole. - * - * %__GFP_NOFAIL: The VM implementation _must_ retry infinitely: the caller - * cannot handle allocation failures. The allocation could block - * indefinitely but will never return with failure. Testing for - * failure is pointless. - * New users should be evaluated carefully (and the flag should be - * used only when there is no reasonable failure policy) but it is - * definitely preferable to use the flag rather than opencode endless - * loop around allocator. - * Using this flag for costly allocations is _highly_ discouraged. - */ -#define __GFP_IO ((__force gfp_t)___GFP_IO) -#define __GFP_FS ((__force gfp_t)___GFP_FS) -#define __GFP_DIRECT_RECLAIM ((__force gfp_t)___GFP_DIRECT_RECLAIM) /* Caller can reclaim */ -#define __GFP_KSWAPD_RECLAIM ((__force gfp_t)___GFP_KSWAPD_RECLAIM) /* kswapd can wake */ -#define __GFP_RECLAIM ((__force gfp_t)(___GFP_DIRECT_RECLAIM|___GFP_KSWAPD_RECLAIM)) -#define __GFP_RETRY_MAYFAIL ((__force gfp_t)___GFP_RETRY_MAYFAIL) -#define __GFP_NOFAIL ((__force gfp_t)___GFP_NOFAIL) -#define __GFP_NORETRY ((__force gfp_t)___GFP_NORETRY) - -/** - * DOC: Action modifiers - * - * Action modifiers - * ~~~~~~~~~~~~~~~~ - * - * %__GFP_NOWARN suppresses allocation failure reports. - * - * %__GFP_COMP address compound page metadata. - * - * %__GFP_ZERO returns a zeroed page on success. - * - * %__GFP_ZEROTAGS returns a page with zeroed memory tags on success, if - * __GFP_ZERO is set. - * - * %__GFP_SKIP_KASAN_POISON returns a page which does not need to be poisoned - * on deallocation. Typically used for userspace pages. Currently only has an - * effect in HW tags mode. - */ -#define __GFP_NOWARN ((__force gfp_t)___GFP_NOWARN) -#define __GFP_COMP ((__force gfp_t)___GFP_COMP) -#define __GFP_ZERO ((__force gfp_t)___GFP_ZERO) -#define __GFP_ZEROTAGS ((__force gfp_t)___GFP_ZEROTAGS) -#define __GFP_SKIP_KASAN_POISON ((__force gfp_t)___GFP_SKIP_KASAN_POISON) - -/* Disable lockdep for GFP context tracking */ -#define __GFP_NOLOCKDEP ((__force gfp_t)___GFP_NOLOCKDEP) - -/* Room for N __GFP_FOO bits */ -#define __GFP_BITS_SHIFT (25 + IS_ENABLED(CONFIG_LOCKDEP)) -#define __GFP_BITS_MASK ((__force gfp_t)((1 << __GFP_BITS_SHIFT) - 1)) - -/** - * DOC: Useful GFP flag combinations - * - * Useful GFP flag combinations - * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - * - * Useful GFP flag combinations that are commonly used. It is recommended - * that subsystems start with one of these combinations and then set/clear - * %__GFP_FOO flags as necessary. - * - * %GFP_ATOMIC users can not sleep and need the allocation to succeed. A lower - * watermark is applied to allow access to "atomic reserves". - * The current implementation doesn't support NMI and few other strict - * non-preemptive contexts (e.g. raw_spin_lock). The same applies to %GFP_NOWAIT. - * - * %GFP_KERNEL is typical for kernel-internal allocations. The caller requires - * %ZONE_NORMAL or a lower zone for direct access but can direct reclaim. - * - * %GFP_KERNEL_ACCOUNT is the same as GFP_KERNEL, except the allocation is - * accounted to kmemcg. - * - * %GFP_NOWAIT is for kernel allocations that should not stall for direct - * reclaim, start physical IO or use any filesystem callback. - * - * %GFP_NOIO will use direct reclaim to discard clean pages or slab pages - * that do not require the starting of any physical IO. - * Please try to avoid using this flag directly and instead use - * memalloc_noio_{save,restore} to mark the whole scope which cannot - * perform any IO with a short explanation why. All allocation requests - * will inherit GFP_NOIO implicitly. - * - * %GFP_NOFS will use direct reclaim but will not use any filesystem interfaces. - * Please try to avoid using this flag directly and instead use - * memalloc_nofs_{save,restore} to mark the whole scope which cannot/shouldn't - * recurse into the FS layer with a short explanation why. All allocation - * requests will inherit GFP_NOFS implicitly. - * - * %GFP_USER is for userspace allocations that also need to be directly - * accessibly by the kernel or hardware. It is typically used by hardware - * for buffers that are mapped to userspace (e.g. graphics) that hardware - * still must DMA to. cpuset limits are enforced for these allocations. - * - * %GFP_DMA exists for historical reasons and should be avoided where possible. - * The flags indicates that the caller requires that the lowest zone be - * used (%ZONE_DMA or 16M on x86-64). Ideally, this would be removed but - * it would require careful auditing as some users really require it and - * others use the flag to avoid lowmem reserves in %ZONE_DMA and treat the - * lowest zone as a type of emergency reserve. - * - * %GFP_DMA32 is similar to %GFP_DMA except that the caller requires a 32-bit - * address. - * - * %GFP_HIGHUSER is for userspace allocations that may be mapped to userspace, - * do not need to be directly accessible by the kernel but that cannot - * move once in use. An example may be a hardware allocation that maps - * data directly into userspace but has no addressing limitations. - * - * %GFP_HIGHUSER_MOVABLE is for userspace allocations that the kernel does not - * need direct access to but can use kmap() when access is required. They - * are expected to be movable via page reclaim or page migration. Typically, - * pages on the LRU would also be allocated with %GFP_HIGHUSER_MOVABLE. - * - * %GFP_TRANSHUGE and %GFP_TRANSHUGE_LIGHT are used for THP allocations. They - * are compound allocations that will generally fail quickly if memory is not - * available and will not wake kswapd/kcompactd on failure. The _LIGHT - * version does not attempt reclaim/compaction at all and is by default used - * in page fault path, while the non-light is used by khugepaged. - */ -#define GFP_ATOMIC (__GFP_HIGH|__GFP_ATOMIC|__GFP_KSWAPD_RECLAIM) -#define GFP_KERNEL (__GFP_RECLAIM | __GFP_IO | __GFP_FS) -#define GFP_KERNEL_ACCOUNT (GFP_KERNEL | __GFP_ACCOUNT) -#define GFP_NOWAIT (__GFP_KSWAPD_RECLAIM) -#define GFP_NOIO (__GFP_RECLAIM) -#define GFP_NOFS (__GFP_RECLAIM | __GFP_IO) -#define GFP_USER (__GFP_RECLAIM | __GFP_IO | __GFP_FS | __GFP_HARDWALL) -#define GFP_DMA __GFP_DMA -#define GFP_DMA32 __GFP_DMA32 -#define GFP_HIGHUSER (GFP_USER | __GFP_HIGHMEM) -#define GFP_HIGHUSER_MOVABLE (GFP_HIGHUSER | __GFP_MOVABLE | \ - __GFP_SKIP_KASAN_POISON) -#define GFP_TRANSHUGE_LIGHT ((GFP_HIGHUSER_MOVABLE | __GFP_COMP | \ - __GFP_NOMEMALLOC | __GFP_NOWARN) & ~__GFP_RECLAIM) -#define GFP_TRANSHUGE (GFP_TRANSHUGE_LIGHT | __GFP_DIRECT_RECLAIM) - /* Convert GFP flags to their corresponding migrate type */ #define GFP_MOVABLE_MASK (__GFP_RECLAIMABLE|__GFP_MOVABLE) #define GFP_MOVABLE_SHIFT 3 @@ -345,12 +18,15 @@ static inline int gfp_migratetype(const gfp_t gfp_flags) VM_WARN_ON((gfp_flags & GFP_MOVABLE_MASK) == GFP_MOVABLE_MASK); BUILD_BUG_ON((1UL << GFP_MOVABLE_SHIFT) != ___GFP_MOVABLE); BUILD_BUG_ON((___GFP_MOVABLE >> GFP_MOVABLE_SHIFT) != MIGRATE_MOVABLE); + BUILD_BUG_ON((___GFP_RECLAIMABLE >> GFP_MOVABLE_SHIFT) != MIGRATE_RECLAIMABLE); + BUILD_BUG_ON(((___GFP_MOVABLE | ___GFP_RECLAIMABLE) >> + GFP_MOVABLE_SHIFT) != MIGRATE_HIGHATOMIC); if (unlikely(page_group_by_mobility_disabled)) return MIGRATE_UNMOVABLE; /* Group based on mobility */ - return (gfp_flags & GFP_MOVABLE_MASK) >> GFP_MOVABLE_SHIFT; + return (__force unsigned long)(gfp_flags & GFP_MOVABLE_MASK) >> GFP_MOVABLE_SHIFT; } #undef GFP_MOVABLE_MASK #undef GFP_MOVABLE_SHIFT @@ -360,29 +36,6 @@ static inline bool gfpflags_allow_blocking(const gfp_t gfp_flags) return !!(gfp_flags & __GFP_DIRECT_RECLAIM); } -/** - * gfpflags_normal_context - is gfp_flags a normal sleepable context? - * @gfp_flags: gfp_flags to test - * - * Test whether @gfp_flags indicates that the allocation is from the - * %current context and allowed to sleep. - * - * An allocation being allowed to block doesn't mean it owns the %current - * context. When direct reclaim path tries to allocate memory, the - * allocation context is nested inside whatever %current was doing at the - * time of the original allocation. The nested allocation may be allowed - * to block but modifying anything %current owns can corrupt the outer - * context's expectations. - * - * %true result from this function indicates that the allocation context - * can sleep and use anything that's associated with %current. - */ -static inline bool gfpflags_normal_context(const gfp_t gfp_flags) -{ - return (gfp_flags & (__GFP_DIRECT_RECLAIM | __GFP_MEMALLOC)) == - __GFP_DIRECT_RECLAIM; -} - #ifdef CONFIG_HIGHMEM #define OPT_ZONE_HIGHMEM ZONE_HIGHMEM #else @@ -596,11 +249,8 @@ static inline struct page *alloc_pages_node(int nid, gfp_t gfp_mask, #ifdef CONFIG_NUMA struct page *alloc_pages(gfp_t gfp, unsigned int order); struct folio *folio_alloc(gfp_t gfp, unsigned order); -extern struct page *alloc_pages_vma(gfp_t gfp_mask, int order, - struct vm_area_struct *vma, unsigned long addr, - int node, bool hugepage); -#define alloc_hugepage_vma(gfp_mask, vma, addr, order) \ - alloc_pages_vma(gfp_mask, order, vma, addr, numa_node_id(), true) +struct folio *vma_alloc_folio(gfp_t gfp, int order, struct vm_area_struct *vma, + unsigned long addr, bool hugepage); #else static inline struct page *alloc_pages(gfp_t gfp_mask, unsigned int order) { @@ -610,14 +260,17 @@ static inline struct folio *folio_alloc(gfp_t gfp, unsigned int order) { return __folio_alloc_node(gfp, order, numa_node_id()); } -#define alloc_pages_vma(gfp_mask, order, vma, addr, node, false)\ - alloc_pages(gfp_mask, order) -#define alloc_hugepage_vma(gfp_mask, vma, addr, order) \ - alloc_pages(gfp_mask, order) +#define vma_alloc_folio(gfp, order, vma, addr, hugepage) \ + folio_alloc(gfp, order) #endif #define alloc_page(gfp_mask) alloc_pages(gfp_mask, 0) -#define alloc_page_vma(gfp_mask, vma, addr) \ - alloc_pages_vma(gfp_mask, 0, vma, addr, numa_node_id(), false) +static inline struct page *alloc_page_vma(gfp_t gfp, + struct vm_area_struct *vma, unsigned long addr) +{ + struct folio *folio = vma_alloc_folio(gfp, 0, vma, addr, false); + + return &folio->page; +} extern unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order); extern unsigned long get_zeroed_page(gfp_t gfp_mask); diff --git a/include/linux/gfp_api.h b/include/linux/gfp_api.h new file mode 100644 index 000000000000..5a05a2764a86 --- /dev/null +++ b/include/linux/gfp_api.h @@ -0,0 +1 @@ +#include <linux/gfp.h> diff --git a/include/linux/gfp_types.h b/include/linux/gfp_types.h new file mode 100644 index 000000000000..d88c46ca82e1 --- /dev/null +++ b/include/linux/gfp_types.h @@ -0,0 +1,348 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LINUX_GFP_TYPES_H +#define __LINUX_GFP_TYPES_H + +/* The typedef is in types.h but we want the documentation here */ +#if 0 +/** + * typedef gfp_t - Memory allocation flags. + * + * GFP flags are commonly used throughout Linux to indicate how memory + * should be allocated. The GFP acronym stands for get_free_pages(), + * the underlying memory allocation function. Not every GFP flag is + * supported by every function which may allocate memory. Most users + * will want to use a plain ``GFP_KERNEL``. + */ +typedef unsigned int __bitwise gfp_t; +#endif + +/* + * In case of changes, please don't forget to update + * include/trace/events/mmflags.h and tools/perf/builtin-kmem.c + */ + +/* Plain integer GFP bitmasks. Do not use this directly. */ +#define ___GFP_DMA 0x01u +#define ___GFP_HIGHMEM 0x02u +#define ___GFP_DMA32 0x04u +#define ___GFP_MOVABLE 0x08u +#define ___GFP_RECLAIMABLE 0x10u +#define ___GFP_HIGH 0x20u +#define ___GFP_IO 0x40u +#define ___GFP_FS 0x80u +#define ___GFP_ZERO 0x100u +#define ___GFP_ATOMIC 0x200u +#define ___GFP_DIRECT_RECLAIM 0x400u +#define ___GFP_KSWAPD_RECLAIM 0x800u +#define ___GFP_WRITE 0x1000u +#define ___GFP_NOWARN 0x2000u +#define ___GFP_RETRY_MAYFAIL 0x4000u +#define ___GFP_NOFAIL 0x8000u +#define ___GFP_NORETRY 0x10000u +#define ___GFP_MEMALLOC 0x20000u +#define ___GFP_COMP 0x40000u +#define ___GFP_NOMEMALLOC 0x80000u +#define ___GFP_HARDWALL 0x100000u +#define ___GFP_THISNODE 0x200000u +#define ___GFP_ACCOUNT 0x400000u +#define ___GFP_ZEROTAGS 0x800000u +#ifdef CONFIG_KASAN_HW_TAGS +#define ___GFP_SKIP_ZERO 0x1000000u +#define ___GFP_SKIP_KASAN_UNPOISON 0x2000000u +#define ___GFP_SKIP_KASAN_POISON 0x4000000u +#else +#define ___GFP_SKIP_ZERO 0 +#define ___GFP_SKIP_KASAN_UNPOISON 0 +#define ___GFP_SKIP_KASAN_POISON 0 +#endif +#ifdef CONFIG_LOCKDEP +#define ___GFP_NOLOCKDEP 0x8000000u +#else +#define ___GFP_NOLOCKDEP 0 +#endif +/* If the above are modified, __GFP_BITS_SHIFT may need updating */ + +/* + * Physical address zone modifiers (see linux/mmzone.h - low four bits) + * + * Do not put any conditional on these. If necessary modify the definitions + * without the underscores and use them consistently. The definitions here may + * be used in bit comparisons. + */ +#define __GFP_DMA ((__force gfp_t)___GFP_DMA) +#define __GFP_HIGHMEM ((__force gfp_t)___GFP_HIGHMEM) +#define __GFP_DMA32 ((__force gfp_t)___GFP_DMA32) +#define __GFP_MOVABLE ((__force gfp_t)___GFP_MOVABLE) /* ZONE_MOVABLE allowed */ +#define GFP_ZONEMASK (__GFP_DMA|__GFP_HIGHMEM|__GFP_DMA32|__GFP_MOVABLE) + +/** + * DOC: Page mobility and placement hints + * + * Page mobility and placement hints + * --------------------------------- + * + * These flags provide hints about how mobile the page is. Pages with similar + * mobility are placed within the same pageblocks to minimise problems due + * to external fragmentation. + * + * %__GFP_MOVABLE (also a zone modifier) indicates that the page can be + * moved by page migration during memory compaction or can be reclaimed. + * + * %__GFP_RECLAIMABLE is used for slab allocations that specify + * SLAB_RECLAIM_ACCOUNT and whose pages can be freed via shrinkers. + * + * %__GFP_WRITE indicates the caller intends to dirty the page. Where possible, + * these pages will be spread between local zones to avoid all the dirty + * pages being in one zone (fair zone allocation policy). + * + * %__GFP_HARDWALL enforces the cpuset memory allocation policy. + * + * %__GFP_THISNODE forces the allocation to be satisfied from the requested + * node with no fallbacks or placement policy enforcements. + * + * %__GFP_ACCOUNT causes the allocation to be accounted to kmemcg. + */ +#define __GFP_RECLAIMABLE ((__force gfp_t)___GFP_RECLAIMABLE) +#define __GFP_WRITE ((__force gfp_t)___GFP_WRITE) +#define __GFP_HARDWALL ((__force gfp_t)___GFP_HARDWALL) +#define __GFP_THISNODE ((__force gfp_t)___GFP_THISNODE) +#define __GFP_ACCOUNT ((__force gfp_t)___GFP_ACCOUNT) + +/** + * DOC: Watermark modifiers + * + * Watermark modifiers -- controls access to emergency reserves + * ------------------------------------------------------------ + * + * %__GFP_HIGH indicates that the caller is high-priority and that granting + * the request is necessary before the system can make forward progress. + * For example, creating an IO context to clean pages. + * + * %__GFP_ATOMIC indicates that the caller cannot reclaim or sleep and is + * high priority. Users are typically interrupt handlers. This may be + * used in conjunction with %__GFP_HIGH + * + * %__GFP_MEMALLOC allows access to all memory. This should only be used when + * the caller guarantees the allocation will allow more memory to be freed + * very shortly e.g. process exiting or swapping. Users either should + * be the MM or co-ordinating closely with the VM (e.g. swap over NFS). + * Users of this flag have to be extremely careful to not deplete the reserve + * completely and implement a throttling mechanism which controls the + * consumption of the reserve based on the amount of freed memory. + * Usage of a pre-allocated pool (e.g. mempool) should be always considered + * before using this flag. + * + * %__GFP_NOMEMALLOC is used to explicitly forbid access to emergency reserves. + * This takes precedence over the %__GFP_MEMALLOC flag if both are set. + */ +#define __GFP_ATOMIC ((__force gfp_t)___GFP_ATOMIC) +#define __GFP_HIGH ((__force gfp_t)___GFP_HIGH) +#define __GFP_MEMALLOC ((__force gfp_t)___GFP_MEMALLOC) +#define __GFP_NOMEMALLOC ((__force gfp_t)___GFP_NOMEMALLOC) + +/** + * DOC: Reclaim modifiers + * + * Reclaim modifiers + * ----------------- + * Please note that all the following flags are only applicable to sleepable + * allocations (e.g. %GFP_NOWAIT and %GFP_ATOMIC will ignore them). + * + * %__GFP_IO can start physical IO. + * + * %__GFP_FS can call down to the low-level FS. Clearing the flag avoids the + * allocator recursing into the filesystem which might already be holding + * locks. + * + * %__GFP_DIRECT_RECLAIM indicates that the caller may enter direct reclaim. + * This flag can be cleared to avoid unnecessary delays when a fallback + * option is available. + * + * %__GFP_KSWAPD_RECLAIM indicates that the caller wants to wake kswapd when + * the low watermark is reached and have it reclaim pages until the high + * watermark is reached. A caller may wish to clear this flag when fallback + * options are available and the reclaim is likely to disrupt the system. The + * canonical example is THP allocation where a fallback is cheap but + * reclaim/compaction may cause indirect stalls. + * + * %__GFP_RECLAIM is shorthand to allow/forbid both direct and kswapd reclaim. + * + * The default allocator behavior depends on the request size. We have a concept + * of so called costly allocations (with order > %PAGE_ALLOC_COSTLY_ORDER). + * !costly allocations are too essential to fail so they are implicitly + * non-failing by default (with some exceptions like OOM victims might fail so + * the caller still has to check for failures) while costly requests try to be + * not disruptive and back off even without invoking the OOM killer. + * The following three modifiers might be used to override some of these + * implicit rules + * + * %__GFP_NORETRY: The VM implementation will try only very lightweight + * memory direct reclaim to get some memory under memory pressure (thus + * it can sleep). It will avoid disruptive actions like OOM killer. The + * caller must handle the failure which is quite likely to happen under + * heavy memory pressure. The flag is suitable when failure can easily be + * handled at small cost, such as reduced throughput + * + * %__GFP_RETRY_MAYFAIL: The VM implementation will retry memory reclaim + * procedures that have previously failed if there is some indication + * that progress has been made else where. It can wait for other + * tasks to attempt high level approaches to freeing memory such as + * compaction (which removes fragmentation) and page-out. + * There is still a definite limit to the number of retries, but it is + * a larger limit than with %__GFP_NORETRY. + * Allocations with this flag may fail, but only when there is + * genuinely little unused memory. While these allocations do not + * directly trigger the OOM killer, their failure indicates that + * the system is likely to need to use the OOM killer soon. The + * caller must handle failure, but can reasonably do so by failing + * a higher-level request, or completing it only in a much less + * efficient manner. + * If the allocation does fail, and the caller is in a position to + * free some non-essential memory, doing so could benefit the system + * as a whole. + * + * %__GFP_NOFAIL: The VM implementation _must_ retry infinitely: the caller + * cannot handle allocation failures. The allocation could block + * indefinitely but will never return with failure. Testing for + * failure is pointless. + * New users should be evaluated carefully (and the flag should be + * used only when there is no reasonable failure policy) but it is + * definitely preferable to use the flag rather than opencode endless + * loop around allocator. + * Using this flag for costly allocations is _highly_ discouraged. + */ +#define __GFP_IO ((__force gfp_t)___GFP_IO) +#define __GFP_FS ((__force gfp_t)___GFP_FS) +#define __GFP_DIRECT_RECLAIM ((__force gfp_t)___GFP_DIRECT_RECLAIM) /* Caller can reclaim */ +#define __GFP_KSWAPD_RECLAIM ((__force gfp_t)___GFP_KSWAPD_RECLAIM) /* kswapd can wake */ +#define __GFP_RECLAIM ((__force gfp_t)(___GFP_DIRECT_RECLAIM|___GFP_KSWAPD_RECLAIM)) +#define __GFP_RETRY_MAYFAIL ((__force gfp_t)___GFP_RETRY_MAYFAIL) +#define __GFP_NOFAIL ((__force gfp_t)___GFP_NOFAIL) +#define __GFP_NORETRY ((__force gfp_t)___GFP_NORETRY) + +/** + * DOC: Action modifiers + * + * Action modifiers + * ---------------- + * + * %__GFP_NOWARN suppresses allocation failure reports. + * + * %__GFP_COMP address compound page metadata. + * + * %__GFP_ZERO returns a zeroed page on success. + * + * %__GFP_ZEROTAGS zeroes memory tags at allocation time if the memory itself + * is being zeroed (either via __GFP_ZERO or via init_on_alloc, provided that + * __GFP_SKIP_ZERO is not set). This flag is intended for optimization: setting + * memory tags at the same time as zeroing memory has minimal additional + * performace impact. + * + * %__GFP_SKIP_KASAN_UNPOISON makes KASAN skip unpoisoning on page allocation. + * Only effective in HW_TAGS mode. + * + * %__GFP_SKIP_KASAN_POISON makes KASAN skip poisoning on page deallocation. + * Typically, used for userspace pages. Only effective in HW_TAGS mode. + */ +#define __GFP_NOWARN ((__force gfp_t)___GFP_NOWARN) +#define __GFP_COMP ((__force gfp_t)___GFP_COMP) +#define __GFP_ZERO ((__force gfp_t)___GFP_ZERO) +#define __GFP_ZEROTAGS ((__force gfp_t)___GFP_ZEROTAGS) +#define __GFP_SKIP_ZERO ((__force gfp_t)___GFP_SKIP_ZERO) +#define __GFP_SKIP_KASAN_UNPOISON ((__force gfp_t)___GFP_SKIP_KASAN_UNPOISON) +#define __GFP_SKIP_KASAN_POISON ((__force gfp_t)___GFP_SKIP_KASAN_POISON) + +/* Disable lockdep for GFP context tracking */ +#define __GFP_NOLOCKDEP ((__force gfp_t)___GFP_NOLOCKDEP) + +/* Room for N __GFP_FOO bits */ +#define __GFP_BITS_SHIFT (27 + IS_ENABLED(CONFIG_LOCKDEP)) +#define __GFP_BITS_MASK ((__force gfp_t)((1 << __GFP_BITS_SHIFT) - 1)) + +/** + * DOC: Useful GFP flag combinations + * + * Useful GFP flag combinations + * ---------------------------- + * + * Useful GFP flag combinations that are commonly used. It is recommended + * that subsystems start with one of these combinations and then set/clear + * %__GFP_FOO flags as necessary. + * + * %GFP_ATOMIC users can not sleep and need the allocation to succeed. A lower + * watermark is applied to allow access to "atomic reserves". + * The current implementation doesn't support NMI and few other strict + * non-preemptive contexts (e.g. raw_spin_lock). The same applies to %GFP_NOWAIT. + * + * %GFP_KERNEL is typical for kernel-internal allocations. The caller requires + * %ZONE_NORMAL or a lower zone for direct access but can direct reclaim. + * + * %GFP_KERNEL_ACCOUNT is the same as GFP_KERNEL, except the allocation is + * accounted to kmemcg. + * + * %GFP_NOWAIT is for kernel allocations that should not stall for direct + * reclaim, start physical IO or use any filesystem callback. + * + * %GFP_NOIO will use direct reclaim to discard clean pages or slab pages + * that do not require the starting of any physical IO. + * Please try to avoid using this flag directly and instead use + * memalloc_noio_{save,restore} to mark the whole scope which cannot + * perform any IO with a short explanation why. All allocation requests + * will inherit GFP_NOIO implicitly. + * + * %GFP_NOFS will use direct reclaim but will not use any filesystem interfaces. + * Please try to avoid using this flag directly and instead use + * memalloc_nofs_{save,restore} to mark the whole scope which cannot/shouldn't + * recurse into the FS layer with a short explanation why. All allocation + * requests will inherit GFP_NOFS implicitly. + * + * %GFP_USER is for userspace allocations that also need to be directly + * accessibly by the kernel or hardware. It is typically used by hardware + * for buffers that are mapped to userspace (e.g. graphics) that hardware + * still must DMA to. cpuset limits are enforced for these allocations. + * + * %GFP_DMA exists for historical reasons and should be avoided where possible. + * The flags indicates that the caller requires that the lowest zone be + * used (%ZONE_DMA or 16M on x86-64). Ideally, this would be removed but + * it would require careful auditing as some users really require it and + * others use the flag to avoid lowmem reserves in %ZONE_DMA and treat the + * lowest zone as a type of emergency reserve. + * + * %GFP_DMA32 is similar to %GFP_DMA except that the caller requires a 32-bit + * address. Note that kmalloc(..., GFP_DMA32) does not return DMA32 memory + * because the DMA32 kmalloc cache array is not implemented. + * (Reason: there is no such user in kernel). + * + * %GFP_HIGHUSER is for userspace allocations that may be mapped to userspace, + * do not need to be directly accessible by the kernel but that cannot + * move once in use. An example may be a hardware allocation that maps + * data directly into userspace but has no addressing limitations. + * + * %GFP_HIGHUSER_MOVABLE is for userspace allocations that the kernel does not + * need direct access to but can use kmap() when access is required. They + * are expected to be movable via page reclaim or page migration. Typically, + * pages on the LRU would also be allocated with %GFP_HIGHUSER_MOVABLE. + * + * %GFP_TRANSHUGE and %GFP_TRANSHUGE_LIGHT are used for THP allocations. They + * are compound allocations that will generally fail quickly if memory is not + * available and will not wake kswapd/kcompactd on failure. The _LIGHT + * version does not attempt reclaim/compaction at all and is by default used + * in page fault path, while the non-light is used by khugepaged. + */ +#define GFP_ATOMIC (__GFP_HIGH|__GFP_ATOMIC|__GFP_KSWAPD_RECLAIM) +#define GFP_KERNEL (__GFP_RECLAIM | __GFP_IO | __GFP_FS) +#define GFP_KERNEL_ACCOUNT (GFP_KERNEL | __GFP_ACCOUNT) +#define GFP_NOWAIT (__GFP_KSWAPD_RECLAIM) +#define GFP_NOIO (__GFP_RECLAIM) +#define GFP_NOFS (__GFP_RECLAIM | __GFP_IO) +#define GFP_USER (__GFP_RECLAIM | __GFP_IO | __GFP_FS | __GFP_HARDWALL) +#define GFP_DMA __GFP_DMA +#define GFP_DMA32 __GFP_DMA32 +#define GFP_HIGHUSER (GFP_USER | __GFP_HIGHMEM) +#define GFP_HIGHUSER_MOVABLE (GFP_HIGHUSER | __GFP_MOVABLE | \ + __GFP_SKIP_KASAN_POISON | __GFP_SKIP_KASAN_UNPOISON) +#define GFP_TRANSHUGE_LIGHT ((GFP_HIGHUSER_MOVABLE | __GFP_COMP | \ + __GFP_NOMEMALLOC | __GFP_NOWARN) & ~__GFP_RECLAIM) +#define GFP_TRANSHUGE (GFP_TRANSHUGE_LIGHT | __GFP_DIRECT_RECLAIM) + +#endif /* __LINUX_GFP_TYPES_H */ diff --git a/include/linux/goldfish.h b/include/linux/goldfish.h index 12be1601fd84..bcc17f95b906 100644 --- a/include/linux/goldfish.h +++ b/include/linux/goldfish.h @@ -8,14 +8,21 @@ /* Helpers for Goldfish virtual platform */ +#ifndef gf_ioread32 +#define gf_ioread32 ioread32 +#endif +#ifndef gf_iowrite32 +#define gf_iowrite32 iowrite32 +#endif + static inline void gf_write_ptr(const void *ptr, void __iomem *portl, void __iomem *porth) { const unsigned long addr = (unsigned long)ptr; - __raw_writel(lower_32_bits(addr), portl); + gf_iowrite32(lower_32_bits(addr), portl); #ifdef CONFIG_64BIT - __raw_writel(upper_32_bits(addr), porth); + gf_iowrite32(upper_32_bits(addr), porth); #endif } @@ -23,9 +30,9 @@ static inline void gf_write_dma_addr(const dma_addr_t addr, void __iomem *portl, void __iomem *porth) { - __raw_writel(lower_32_bits(addr), portl); + gf_iowrite32(lower_32_bits(addr), portl); #ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT - __raw_writel(upper_32_bits(addr), porth); + gf_iowrite32(upper_32_bits(addr), porth); #endif } diff --git a/include/linux/gpio.h b/include/linux/gpio.h index 008ad3ee56b7..a370387fa406 100644 --- a/include/linux/gpio.h +++ b/include/linux/gpio.h @@ -95,7 +95,6 @@ struct device; int devm_gpio_request(struct device *dev, unsigned gpio, const char *label); int devm_gpio_request_one(struct device *dev, unsigned gpio, unsigned long flags, const char *label); -void devm_gpio_free(struct device *dev, unsigned int gpio); #else /* ! CONFIG_GPIOLIB */ @@ -240,11 +239,6 @@ static inline int devm_gpio_request_one(struct device *dev, unsigned gpio, return -EINVAL; } -static inline void devm_gpio_free(struct device *dev, unsigned int gpio) -{ - WARN_ON(1); -} - #endif /* ! CONFIG_GPIOLIB */ #endif /* __LINUX_GPIO_H */ diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h index 3ad67b4a72be..36460ced060b 100644 --- a/include/linux/gpio/consumer.h +++ b/include/linux/gpio/consumer.h @@ -8,27 +8,16 @@ #include <linux/err.h> struct device; - -/** - * Opaque descriptor for a GPIO. These are obtained using gpiod_get() and are - * preferable to the old integer-based handles. - * - * Contrary to integers, a pointer to a gpio_desc is guaranteed to be valid - * until the GPIO is released. - */ struct gpio_desc; - -/** - * Opaque descriptor for a structure of GPIO array attributes. This structure - * is attached to struct gpiod_descs obtained from gpiod_get_array() and can be - * passed back to get/set array functions in order to activate fast processing - * path if applicable. - */ struct gpio_array; /** - * Struct containing an array of descriptors that can be obtained using - * gpiod_get_array(). + * struct gpio_descs - Struct containing an array of descriptors that can be + * obtained using gpiod_get_array() + * + * @info: Pointer to the opaque gpio_array structure + * @ndescs: Number of held descriptors + * @desc: Array of pointers to GPIO descriptors */ struct gpio_descs { struct gpio_array *info; @@ -43,8 +32,16 @@ struct gpio_descs { #define GPIOD_FLAGS_BIT_NONEXCLUSIVE BIT(4) /** - * Optional flags that can be passed to one of gpiod_* to configure direction - * and output value. These values cannot be OR'd. + * enum gpiod_flags - Optional flags that can be passed to one of gpiod_* to + * configure direction and output value. These values + * cannot be OR'd. + * + * @GPIOD_ASIS: Don't change anything + * @GPIOD_IN: Set lines to input mode + * @GPIOD_OUT_LOW: Set lines to output and drive them low + * @GPIOD_OUT_HIGH: Set lines to output and drive them high + * @GPIOD_OUT_LOW_OPEN_DRAIN: Set lines to open-drain output and drive them low + * @GPIOD_OUT_HIGH_OPEN_DRAIN: Set lines to open-drain output and drive them high */ enum gpiod_flags { GPIOD_ASIS = 0, @@ -112,6 +109,8 @@ int gpiod_get_direction(struct gpio_desc *desc); int gpiod_direction_input(struct gpio_desc *desc); int gpiod_direction_output(struct gpio_desc *desc, int value); int gpiod_direction_output_raw(struct gpio_desc *desc, int value); +int gpiod_enable_hw_timestamp_ns(struct gpio_desc *desc, unsigned long flags); +int gpiod_disable_hw_timestamp_ns(struct gpio_desc *desc, unsigned long flags); /* Value get/set from non-sleeping context */ int gpiod_get_value(const struct gpio_desc *desc); @@ -175,10 +174,6 @@ int desc_to_gpio(const struct gpio_desc *desc); /* Child properties interface */ struct fwnode_handle; -struct gpio_desc *fwnode_get_named_gpiod(struct fwnode_handle *fwnode, - const char *propname, int index, - enum gpiod_flags dflags, - const char *label); struct gpio_desc *fwnode_gpiod_get_index(struct fwnode_handle *fwnode, const char *con_id, int index, enum gpiod_flags flags, @@ -353,8 +348,18 @@ static inline int gpiod_direction_output_raw(struct gpio_desc *desc, int value) WARN_ON(desc); return -ENOSYS; } - - +static inline int gpiod_enable_hw_timestamp_ns(struct gpio_desc *desc, + unsigned long flags) +{ + WARN_ON(desc); + return -ENOSYS; +} +static inline int gpiod_disable_hw_timestamp_ns(struct gpio_desc *desc, + unsigned long flags) +{ + WARN_ON(desc); + return -ENOSYS; +} static inline int gpiod_get_value(const struct gpio_desc *desc) { /* GPIO can never have been requested */ @@ -545,15 +550,6 @@ static inline int desc_to_gpio(const struct gpio_desc *desc) struct fwnode_handle; static inline -struct gpio_desc *fwnode_get_named_gpiod(struct fwnode_handle *fwnode, - const char *propname, int index, - enum gpiod_flags dflags, - const char *label) -{ - return ERR_PTR(-ENOSYS); -} - -static inline struct gpio_desc *fwnode_gpiod_get_index(struct fwnode_handle *fwnode, const char *con_id, int index, enum gpiod_flags flags, @@ -691,7 +687,7 @@ void acpi_dev_remove_driver_gpios(struct acpi_device *adev); int devm_acpi_dev_add_driver_gpios(struct device *dev, const struct acpi_gpio_mapping *gpios); -struct gpio_desc *acpi_get_and_request_gpiod(char *path, int pin, char *label); +struct gpio_desc *acpi_get_and_request_gpiod(char *path, unsigned int pin, char *label); #else /* CONFIG_GPIOLIB && CONFIG_ACPI */ @@ -708,6 +704,12 @@ static inline int devm_acpi_dev_add_driver_gpios(struct device *dev, return -ENXIO; } +static inline struct gpio_desc *acpi_get_and_request_gpiod(char *path, unsigned int pin, + char *label) +{ + return ERR_PTR(-ENOSYS); +} + #endif /* CONFIG_GPIOLIB && CONFIG_ACPI */ diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index b0728c8ad90c..6aeea1071b1b 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -3,13 +3,16 @@ #define __LINUX_GPIO_DRIVER_H #include <linux/device.h> -#include <linux/types.h> #include <linux/irq.h> #include <linux/irqchip/chained_irq.h> #include <linux/irqdomain.h> #include <linux/lockdep.h> #include <linux/pinctrl/pinctrl.h> #include <linux/pinctrl/pinconf-generic.h> +#include <linux/property.h> +#include <linux/types.h> + +#include <asm/msi.h> struct gpio_desc; struct of_phandle_args; @@ -22,6 +25,13 @@ enum gpio_lookup_flags; struct gpio_chip; +union gpio_irq_fwspec { + struct irq_fwspec fwspec; +#ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN + msi_alloc_info_t msiinfo; +#endif +}; + #define GPIO_LINE_DIRECTION_IN 1 #define GPIO_LINE_DIRECTION_OUT 0 @@ -102,9 +112,10 @@ struct gpio_irq_chip { * variant named &gpiochip_populate_parent_fwspec_fourcell is also * available. */ - void *(*populate_parent_alloc_arg)(struct gpio_chip *gc, - unsigned int parent_hwirq, - unsigned int parent_type); + int (*populate_parent_alloc_arg)(struct gpio_chip *gc, + union gpio_irq_fwspec *fwspec, + unsigned int parent_hwirq, + unsigned int parent_type); /** * @child_offset_to_irq: @@ -166,18 +177,24 @@ struct gpio_irq_chip { */ irq_flow_handler_t parent_handler; - /** - * @parent_handler_data: - * @parent_handler_data_array: - * - * Data associated, and passed to, the handler for the parent - * interrupt. Can either be a single pointer if @per_parent_data - * is false, or an array of @num_parents pointers otherwise. If - * @per_parent_data is true, @parent_handler_data_array cannot be - * NULL. - */ union { + /** + * @parent_handler_data: + * + * If @per_parent_data is false, @parent_handler_data is a + * single pointer used as the data associated with every + * parent interrupt. + */ void *parent_handler_data; + + /** + * @parent_handler_data_array: + * + * If @per_parent_data is true, @parent_handler_data_array is + * an array of @num_parents pointers, and is used to associate + * different data for each parent. This cannot be NULL if + * @per_parent_data is true. + */ void **parent_handler_data_array; }; @@ -219,6 +236,15 @@ struct gpio_irq_chip { bool per_parent_data; /** + * @initialized: + * + * Flag to track GPIO chip irq member's initialization. + * This flag will make sure GPIO chip irq members are not used + * before they are initialized. + */ + bool initialized; + + /** * @init_hw: optional routine to initialize hardware before * an IRQ chip will be added. This is quite useful when * a particular driver wants to clear IRQ related registers @@ -320,6 +346,10 @@ struct gpio_irq_chip { * @add_pin_ranges: optional routine to initialize pin ranges, to be used when * requires special mapping of the pins that provides GPIO functionality. * It is called after adding GPIO chip and before adding IRQ chip. + * @en_hw_timestamp: Dependent on GPIO chip, an optional routine to + * enable hardware timestamp. + * @dis_hw_timestamp: Dependent on GPIO chip, an optional routine to + * disable hardware timestamp. * @base: identifies the first GPIO number handled by this chip; * or, if negative during registration, requests dynamic ID allocation. * DEPRECATION: providing anything non-negative and nailing the base @@ -416,6 +446,12 @@ struct gpio_chip { int (*add_pin_ranges)(struct gpio_chip *gc); + int (*en_hw_timestamp)(struct gpio_chip *gc, + u32 offset, + unsigned long flags); + int (*dis_hw_timestamp)(struct gpio_chip *gc, + u32 offset, + unsigned long flags); int base; u16 ngpio; u16 offset; @@ -433,7 +469,7 @@ struct gpio_chip { void __iomem *reg_dir_in; bool bgpio_dir_unreadable; int bgpio_bits; - spinlock_t bgpio_lock; + raw_spinlock_t bgpio_lock; unsigned long bgpio_data; unsigned long bgpio_dir; #endif /* CONFIG_GPIO_GENERIC */ @@ -489,6 +525,18 @@ struct gpio_chip { */ int (*of_xlate)(struct gpio_chip *gc, const struct of_phandle_args *gpiospec, u32 *flags); + + /** + * @of_gpio_ranges_fallback: + * + * Optional hook for the case that no gpio-ranges property is defined + * within the device tree node "np" (usually DT before introduction + * of gpio-ranges). So this callback is helpful to provide the + * necessary backward compatibility for the pin ranges. + */ + int (*of_gpio_ranges_fallback)(struct gpio_chip *gc, + struct device_node *np); + #endif /* CONFIG_OF_GPIO */ }; @@ -576,6 +624,22 @@ void gpiochip_relres_irq(struct gpio_chip *gc, unsigned int offset); void gpiochip_disable_irq(struct gpio_chip *gc, unsigned int offset); void gpiochip_enable_irq(struct gpio_chip *gc, unsigned int offset); +/* irq_data versions of the above */ +int gpiochip_irq_reqres(struct irq_data *data); +void gpiochip_irq_relres(struct irq_data *data); + +/* Paste this in your irq_chip structure */ +#define GPIOCHIP_IRQ_RESOURCE_HELPERS \ + .irq_request_resources = gpiochip_irq_reqres, \ + .irq_release_resources = gpiochip_irq_relres + +static inline void gpio_irq_chip_set_chip(struct gpio_irq_chip *girq, + const struct irq_chip *chip) +{ + /* Yes, dropping const is ugly, but it isn't like we have a choice */ + girq->chip = (struct irq_chip *)chip; +} + /* Line status inquiry for drivers */ bool gpiochip_line_is_open_drain(struct gpio_chip *gc, unsigned int offset); bool gpiochip_line_is_open_source(struct gpio_chip *gc, unsigned int offset); @@ -595,28 +659,14 @@ struct bgpio_pdata { #ifdef CONFIG_IRQ_DOMAIN_HIERARCHY -void *gpiochip_populate_parent_fwspec_twocell(struct gpio_chip *gc, +int gpiochip_populate_parent_fwspec_twocell(struct gpio_chip *gc, + union gpio_irq_fwspec *gfwspec, + unsigned int parent_hwirq, + unsigned int parent_type); +int gpiochip_populate_parent_fwspec_fourcell(struct gpio_chip *gc, + union gpio_irq_fwspec *gfwspec, unsigned int parent_hwirq, unsigned int parent_type); -void *gpiochip_populate_parent_fwspec_fourcell(struct gpio_chip *gc, - unsigned int parent_hwirq, - unsigned int parent_type); - -#else - -static inline void *gpiochip_populate_parent_fwspec_twocell(struct gpio_chip *gc, - unsigned int parent_hwirq, - unsigned int parent_type) -{ - return NULL; -} - -static inline void *gpiochip_populate_parent_fwspec_fourcell(struct gpio_chip *gc, - unsigned int parent_hwirq, - unsigned int parent_type) -{ - return NULL; -} #endif /* CONFIG_IRQ_DOMAIN_HIERARCHY */ @@ -747,4 +797,29 @@ static inline void gpiochip_unlock_as_irq(struct gpio_chip *gc, } #endif /* CONFIG_GPIOLIB */ +#define for_each_gpiochip_node(dev, child) \ + device_for_each_child_node(dev, child) \ + if (!fwnode_property_present(child, "gpio-controller")) {} else + +static inline unsigned int gpiochip_node_count(struct device *dev) +{ + struct fwnode_handle *child; + unsigned int count = 0; + + for_each_gpiochip_node(dev, child) + count++; + + return count; +} + +static inline struct fwnode_handle *gpiochip_node_get_first(struct device *dev) +{ + struct fwnode_handle *fwnode; + + for_each_gpiochip_node(dev, fwnode) + return fwnode; + + return NULL; +} + #endif /* __LINUX_GPIO_DRIVER_H */ diff --git a/include/linux/gpio/machine.h b/include/linux/gpio/machine.h index 2647dd10b541..0b619eb7ae83 100644 --- a/include/linux/gpio/machine.h +++ b/include/linux/gpio/machine.h @@ -14,6 +14,7 @@ enum gpio_lookup_flags { GPIO_TRANSITORY = (1 << 3), GPIO_PULL_UP = (1 << 4), GPIO_PULL_DOWN = (1 << 5), + GPIO_PULL_DISABLE = (1 << 6), GPIO_LOOKUP_FLAGS_DEFAULT = GPIO_ACTIVE_HIGH | GPIO_PERSISTENT, }; @@ -64,6 +65,18 @@ struct gpiod_hog { }; /* + * Helper for lookup tables with just one single lookup for a device. + */ +#define GPIO_LOOKUP_SINGLE(_name, _dev_id, _key, _chip_hwnum, _con_id, _flags) \ +static struct gpiod_lookup_table _name = { \ + .dev_id = _dev_id, \ + .table = { \ + GPIO_LOOKUP(_key, _chip_hwnum, _con_id, _flags), \ + {}, \ + }, \ +} + +/* * Simple definition of a single GPIO under a con_id */ #define GPIO_LOOKUP(_key, _chip_hwnum, _con_id, _flags) \ diff --git a/include/linux/greybus/greybus_manifest.h b/include/linux/greybus/greybus_manifest.h index 6e62fe478712..bef9eb2093e9 100644 --- a/include/linux/greybus/greybus_manifest.h +++ b/include/linux/greybus/greybus_manifest.h @@ -100,7 +100,7 @@ enum { struct greybus_descriptor_string { __u8 length; __u8 id; - __u8 string[0]; + __u8 string[]; } __packed; /* @@ -175,7 +175,7 @@ struct greybus_manifest_header { struct greybus_manifest { struct greybus_manifest_header header; - struct greybus_descriptor descriptors[0]; + struct greybus_descriptor descriptors[]; } __packed; #endif /* __GREYBUS_MANIFEST_H */ diff --git a/include/linux/greybus/hd.h b/include/linux/greybus/hd.h index d3faf0c1a569..718e2857054e 100644 --- a/include/linux/greybus/hd.h +++ b/include/linux/greybus/hd.h @@ -58,7 +58,7 @@ struct gb_host_device { struct gb_svc *svc; /* Private data for the host driver */ - unsigned long hd_priv[0] __aligned(sizeof(s64)); + unsigned long hd_priv[] __aligned(sizeof(s64)); }; #define to_gb_host_device(d) container_of(d, struct gb_host_device, dev) diff --git a/include/linux/greybus/module.h b/include/linux/greybus/module.h index 47b839af145d..3efe2133acfd 100644 --- a/include/linux/greybus/module.h +++ b/include/linux/greybus/module.h @@ -23,7 +23,7 @@ struct gb_module { bool disconnected; - struct gb_interface *interfaces[0]; + struct gb_interface *interfaces[]; }; #define to_gb_module(d) container_of(d, struct gb_module, dev) diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h index 76878b357ffa..d57cab4d4c06 100644 --- a/include/linux/hardirq.h +++ b/include/linux/hardirq.h @@ -92,14 +92,6 @@ void irq_exit_rcu(void); #define arch_nmi_exit() do { } while (0) #endif -#ifdef CONFIG_TINY_RCU -static inline void rcu_nmi_enter(void) { } -static inline void rcu_nmi_exit(void) { } -#else -extern void rcu_nmi_enter(void); -extern void rcu_nmi_exit(void); -#endif - /* * NMI vs Tracing * -------------- @@ -124,7 +116,7 @@ extern void rcu_nmi_exit(void); do { \ __nmi_enter(); \ lockdep_hardirq_enter(); \ - rcu_nmi_enter(); \ + ct_nmi_enter(); \ instrumentation_begin(); \ ftrace_nmi_enter(); \ instrumentation_end(); \ @@ -143,7 +135,7 @@ extern void rcu_nmi_exit(void); instrumentation_begin(); \ ftrace_nmi_exit(); \ instrumentation_end(); \ - rcu_nmi_exit(); \ + ct_nmi_exit(); \ lockdep_hardirq_exit(); \ __nmi_exit(); \ } while (0) diff --git a/include/linux/hash.h b/include/linux/hash.h index ad6fa21d977b..38edaa08f862 100644 --- a/include/linux/hash.h +++ b/include/linux/hash.h @@ -62,10 +62,7 @@ static inline u32 __hash_32_generic(u32 val) return val * GOLDEN_RATIO_32; } -#ifndef HAVE_ARCH_HASH_32 -#define hash_32 hash_32_generic -#endif -static inline u32 hash_32_generic(u32 val, unsigned int bits) +static inline u32 hash_32(u32 val, unsigned int bits) { /* High bits are more random, so use them. */ return __hash_32(val) >> (32 - bits); diff --git a/include/linux/hashtable_api.h b/include/linux/hashtable_api.h new file mode 100644 index 000000000000..c268ac2c5c0e --- /dev/null +++ b/include/linux/hashtable_api.h @@ -0,0 +1 @@ +#include <linux/hashtable.h> diff --git a/include/linux/hdmi.h b/include/linux/hdmi.h index c8ec982ff498..2f4dcc8d060e 100644 --- a/include/linux/hdmi.h +++ b/include/linux/hdmi.h @@ -336,7 +336,12 @@ ssize_t hdmi_audio_infoframe_pack(struct hdmi_audio_infoframe *frame, void *buffer, size_t size); ssize_t hdmi_audio_infoframe_pack_only(const struct hdmi_audio_infoframe *frame, void *buffer, size_t size); -int hdmi_audio_infoframe_check(struct hdmi_audio_infoframe *frame); +int hdmi_audio_infoframe_check(const struct hdmi_audio_infoframe *frame); + +struct dp_sdp; +ssize_t +hdmi_audio_infoframe_pack_for_dp(const struct hdmi_audio_infoframe *frame, + struct dp_sdp *sdp, u8 dp_version); enum hdmi_3d_structure { HDMI_3D_STRUCTURE_INVALID = -1, diff --git a/include/linux/hid.h b/include/linux/hid.h index 7487b0586fe6..8677ae38599e 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -314,15 +314,6 @@ struct hid_item { #define HID_BAT_ABSOLUTESTATEOFCHARGE 0x00850065 #define HID_VD_ASUS_CUSTOM_MEDIA_KEYS 0xff310076 -/* - * HID report types --- Ouch! HID spec says 1 2 3! - */ - -#define HID_INPUT_REPORT 0 -#define HID_OUTPUT_REPORT 1 -#define HID_FEATURE_REPORT 2 - -#define HID_REPORT_TYPES 3 /* * HID connect requests @@ -342,12 +333,12 @@ struct hid_item { * HID device quirks. */ -/* +/* * Increase this if you need to configure more HID quirks at module load time */ #define MAX_USBHID_BOOT_QUIRKS 4 -#define HID_QUIRK_INVERT BIT(0) +/* BIT(0) reserved for backward compatibility, was HID_QUIRK_INVERT */ #define HID_QUIRK_NOTOUCH BIT(1) #define HID_QUIRK_IGNORE BIT(2) #define HID_QUIRK_NOGET BIT(3) @@ -476,31 +467,50 @@ struct hid_field { unsigned report_count; /* number of this field in the report */ unsigned report_type; /* (input,output,feature) */ __s32 *value; /* last known value(s) */ + __s32 *new_value; /* newly read value(s) */ + __s32 *usages_priorities; /* priority of each usage when reading the report + * bits 8-16 are reserved for hid-input usage + */ __s32 logical_minimum; __s32 logical_maximum; __s32 physical_minimum; __s32 physical_maximum; __s32 unit_exponent; unsigned unit; + bool ignored; /* this field is ignored in this event */ struct hid_report *report; /* associated report */ unsigned index; /* index into report->field[] */ /* hidinput data */ struct hid_input *hidinput; /* associated input structure */ __u16 dpad; /* dpad input code */ + unsigned int slot_idx; /* slot index in a report */ }; #define HID_MAX_FIELDS 256 +struct hid_field_entry { + struct list_head list; + struct hid_field *field; + unsigned int index; + __s32 priority; +}; + struct hid_report { struct list_head list; struct list_head hidinput_list; + struct list_head field_entry_list; /* ordered list of input fields */ unsigned int id; /* id of this report */ - unsigned int type; /* report type */ + enum hid_report_type type; /* report type */ unsigned int application; /* application usage for this report */ struct hid_field *field[HID_MAX_FIELDS]; /* fields of the report */ + struct hid_field_entry *field_entries; /* allocated memory of input field_entry */ unsigned maxfield; /* maximum valid field index */ unsigned size; /* size of the report (bits) */ struct hid_device *device; /* associated device */ + + /* tool related state */ + bool tool_active; /* whether the current tool is active */ + unsigned int tool; /* BTN_TOOL_* */ }; #define HID_MAX_IDS 256 @@ -639,6 +649,8 @@ struct hid_device { /* device report descriptor */ struct list_head debug_list; spinlock_t debug_list_lock; wait_queue_head_t debug_wait; + + unsigned int id; /* system unique id */ }; #define to_hid_device(pdev) \ @@ -905,20 +917,21 @@ extern int hidinput_connect(struct hid_device *hid, unsigned int force); extern void hidinput_disconnect(struct hid_device *); int hid_set_field(struct hid_field *, unsigned, __s32); -int hid_input_report(struct hid_device *, int type, u8 *, u32, int); +int hid_input_report(struct hid_device *hid, enum hid_report_type type, u8 *data, u32 size, + int interrupt); struct hid_field *hidinput_get_led_field(struct hid_device *hid); unsigned int hidinput_count_leds(struct hid_device *hid); __s32 hidinput_calc_abs_res(const struct hid_field *field, __u16 code); void hid_output_report(struct hid_report *report, __u8 *data); -int __hid_request(struct hid_device *hid, struct hid_report *rep, int reqtype); +int __hid_request(struct hid_device *hid, struct hid_report *rep, enum hid_class_request reqtype); u8 *hid_alloc_report_buf(struct hid_report *report, gfp_t flags); struct hid_device *hid_allocate_device(void); struct hid_report *hid_register_report(struct hid_device *device, - unsigned int type, unsigned int id, + enum hid_report_type type, unsigned int id, unsigned int application); int hid_parse_report(struct hid_device *hid, __u8 *start, unsigned size); struct hid_report *hid_validate_values(struct hid_device *hid, - unsigned int type, unsigned int id, + enum hid_report_type type, unsigned int id, unsigned int field_index, unsigned int report_counts); @@ -1087,10 +1100,11 @@ void hid_hw_stop(struct hid_device *hdev); int __must_check hid_hw_open(struct hid_device *hdev); void hid_hw_close(struct hid_device *hdev); void hid_hw_request(struct hid_device *hdev, - struct hid_report *report, int reqtype); + struct hid_report *report, enum hid_class_request reqtype); int hid_hw_raw_request(struct hid_device *hdev, unsigned char reportnum, __u8 *buf, - size_t len, unsigned char rtype, int reqtype); + size_t len, enum hid_report_type rtype, + enum hid_class_request reqtype); int hid_hw_output_report(struct hid_device *hdev, __u8 *buf, size_t len); /** @@ -1118,7 +1132,7 @@ static inline int hid_hw_power(struct hid_device *hdev, int level) * @reqtype: hid request type */ static inline int hid_hw_idle(struct hid_device *hdev, int report, int idle, - int reqtype) + enum hid_class_request reqtype) { if (hdev->ll_driver->idle) return hdev->ll_driver->idle(hdev, report, idle, reqtype); @@ -1163,8 +1177,8 @@ static inline u32 hid_report_len(struct hid_report *report) return DIV_ROUND_UP(report->size, 8) + (report->id > 0); } -int hid_report_raw_event(struct hid_device *hid, int type, u8 *data, u32 size, - int interrupt); +int hid_report_raw_event(struct hid_device *hid, enum hid_report_type type, u8 *data, u32 size, + int interrupt); /* HID quirks API */ unsigned long hid_lookup_quirk(const struct hid_device *hdev); diff --git a/include/linux/highmem-internal.h b/include/linux/highmem-internal.h index 0a0b2b09b1b8..034b1106d022 100644 --- a/include/linux/highmem-internal.h +++ b/include/linux/highmem-internal.h @@ -8,7 +8,7 @@ #ifdef CONFIG_KMAP_LOCAL void *__kmap_local_pfn_prot(unsigned long pfn, pgprot_t prot); void *__kmap_local_page_prot(struct page *page, pgprot_t prot); -void kunmap_local_indexed(void *vaddr); +void kunmap_local_indexed(const void *vaddr); void kmap_local_fork(struct task_struct *tsk); void __kmap_local_sched_out(void); void __kmap_local_sched_in(void); @@ -89,7 +89,7 @@ static inline void *kmap_local_pfn(unsigned long pfn) return __kmap_local_pfn_prot(pfn, kmap_prot); } -static inline void __kunmap_local(void *vaddr) +static inline void __kunmap_local(const void *vaddr) { kunmap_local_indexed(vaddr); } @@ -121,7 +121,7 @@ static inline void *kmap_atomic_pfn(unsigned long pfn) return __kmap_local_pfn_prot(pfn, kmap_prot); } -static inline void __kunmap_atomic(void *addr) +static inline void __kunmap_atomic(const void *addr) { kunmap_local_indexed(addr); pagefault_enable(); @@ -149,6 +149,11 @@ static inline void totalhigh_pages_add(long count) atomic_long_add(count, &_totalhigh_pages); } +static inline bool is_kmap_addr(const void *x) +{ + unsigned long addr = (unsigned long)x; + return addr >= PKMAP_ADDR(0) && addr < PKMAP_ADDR(LAST_PKMAP); +} #else /* CONFIG_HIGHMEM */ static inline struct page *kmap_to_page(void *addr) @@ -192,7 +197,7 @@ static inline void *kmap_local_pfn(unsigned long pfn) return kmap_local_page(pfn_to_page(pfn)); } -static inline void __kunmap_local(void *addr) +static inline void __kunmap_local(const void *addr) { #ifdef ARCH_HAS_FLUSH_ON_KUNMAP kunmap_flush_on_unmap(addr); @@ -219,7 +224,7 @@ static inline void *kmap_atomic_pfn(unsigned long pfn) return kmap_atomic(pfn_to_page(pfn)); } -static inline void __kunmap_atomic(void *addr) +static inline void __kunmap_atomic(const void *addr) { #ifdef ARCH_HAS_FLUSH_ON_KUNMAP kunmap_flush_on_unmap(addr); @@ -234,11 +239,28 @@ static inline void __kunmap_atomic(void *addr) static inline unsigned int nr_free_highpages(void) { return 0; } static inline unsigned long totalhigh_pages(void) { return 0UL; } +static inline bool is_kmap_addr(const void *x) +{ + return false; +} + #endif /* CONFIG_HIGHMEM */ -/* - * Prevent people trying to call kunmap_atomic() as if it were kunmap() - * kunmap_atomic() should get the return value of kmap_atomic, not the page. +/** + * kunmap_atomic - Unmap the virtual address mapped by kmap_atomic() - deprecated! + * @__addr: Virtual address to be unmapped + * + * Unmaps an address previously mapped by kmap_atomic() and re-enables + * pagefaults. Depending on PREEMP_RT configuration, re-enables also + * migration and preemption. Users should not count on these side effects. + * + * Mappings should be unmapped in the reverse order that they were mapped. + * See kmap_local_page() for details on nesting. + * + * @__addr can be any address within the mapped page, so there is no need + * to subtract any offset that has been added. In contrast to kunmap(), + * this function takes the address returned from kmap_atomic(), not the + * page passed to it. The compiler will warn you if you pass the page. */ #define kunmap_atomic(__addr) \ do { \ @@ -246,6 +268,16 @@ do { \ __kunmap_atomic(__addr); \ } while (0) +/** + * kunmap_local - Unmap a page mapped via kmap_local_page(). + * @__addr: An address within the page mapped + * + * @__addr can be any address within the mapped page. Commonly it is the + * address return from kmap_local_page(), but it can also include offsets. + * + * Unmapping should be done in the reverse order of the mapping. See + * kmap_local_page() for details. + */ #define kunmap_local(__addr) \ do { \ BUILD_BUG_ON(__same_type((__addr), struct page *)); \ diff --git a/include/linux/highmem.h b/include/linux/highmem.h index 39bb9b47fa9c..e9912da5441b 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -6,6 +6,7 @@ #include <linux/kernel.h> #include <linux/bug.h> #include <linux/cacheflush.h> +#include <linux/kmsan.h> #include <linux/mm.h> #include <linux/uaccess.h> #include <linux/hardirq.h> @@ -37,7 +38,7 @@ static inline void *kmap(struct page *page); /** * kunmap - Unmap the virtual address mapped by kmap() - * @addr: Virtual address to be unmapped + * @page: Pointer to the page which was mapped by kmap() * * Counterpart to kmap(). A NOOP for CONFIG_HIGHMEM=n and for mappings of * pages in the low memory area. @@ -60,11 +61,11 @@ static inline void kmap_flush_unused(void); /** * kmap_local_page - Map a page for temporary usage - * @page: Pointer to the page to be mapped + * @page: Pointer to the page to be mapped * * Returns: The virtual address of the mapping * - * Can be invoked from any context. + * Can be invoked from any context, including interrupts. * * Requires careful handling when nesting multiple mappings because the map * management is stack based. The unmap has to be in the reverse order of @@ -86,8 +87,7 @@ static inline void kmap_flush_unused(void); * temporarily mapped. * * While it is significantly faster than kmap() for the higmem case it - * comes with restrictions about the pointer validity. Only use when really - * necessary. + * comes with restrictions about the pointer validity. * * On HIGHMEM enabled systems mapping a highmem page has the side effect of * disabling migration in order to keep the virtual address stable across @@ -138,23 +138,46 @@ static inline void *kmap_local_folio(struct folio *folio, size_t offset); * * Returns: The virtual address of the mapping * - * Effectively a wrapper around kmap_local_page() which disables pagefaults - * and preemption. + * In fact a wrapper around kmap_local_page() which also disables pagefaults + * and, depending on PREEMPT_RT configuration, also CPU migration and + * preemption. Therefore users should not count on the latter two side effects. + * + * Mappings should always be released by kunmap_atomic(). * * Do not use in new code. Use kmap_local_page() instead. - */ -static inline void *kmap_atomic(struct page *page); - -/** - * kunmap_atomic - Unmap the virtual address mapped by kmap_atomic() - * @addr: Virtual address to be unmapped * - * Counterpart to kmap_atomic(). + * It is used in atomic context when code wants to access the contents of a + * page that might be allocated from high memory (see __GFP_HIGHMEM), for + * example a page in the pagecache. The API has two functions, and they + * can be used in a manner similar to the following:: + * + * // Find the page of interest. + * struct page *page = find_get_page(mapping, offset); * - * Effectively a wrapper around kunmap_local() which additionally undoes - * the side effects of kmap_atomic(), i.e. reenabling pagefaults and - * preemption. + * // Gain access to the contents of that page. + * void *vaddr = kmap_atomic(page); + * + * // Do something to the contents of that page. + * memset(vaddr, 0, PAGE_SIZE); + * + * // Unmap that page. + * kunmap_atomic(vaddr); + * + * Note that the kunmap_atomic() call takes the result of the kmap_atomic() + * call, not the argument. + * + * If you need to map two pages because you want to copy from one page to + * another you need to keep the kmap_atomic calls strictly nested, like: + * + * vaddr1 = kmap_atomic(page1); + * vaddr2 = kmap_atomic(page2); + * + * memcpy(vaddr1, vaddr2, PAGE_SIZE); + * + * kunmap_atomic(vaddr2); + * kunmap_atomic(vaddr1); */ +static inline void *kmap_atomic(struct page *page); /* Highmem related interfaces for management code */ static inline unsigned int nr_free_highpages(void); @@ -191,6 +214,8 @@ static inline void clear_user_highpage(struct page *page, unsigned long vaddr) * @vma: The VMA the page is to be allocated for * @vaddr: The virtual address the page will be inserted into * + * Returns: The allocated and zeroed HIGHMEM page + * * This function will allocate a page for a VMA that the caller knows will * be able to migrate in the future using move_pages() or reclaimed * @@ -218,6 +243,16 @@ static inline void clear_highpage(struct page *page) kunmap_local(kaddr); } +static inline void clear_highpage_kasan_tagged(struct page *page) +{ + u8 tag; + + tag = page_kasan_tag(page); + page_kasan_tag_reset(page); + clear_highpage(page); + page_kasan_tag_set(page, tag); +} + #ifndef __HAVE_ARCH_TAG_CLEAR_HIGHPAGE static inline void tag_clear_highpage(struct page *page) @@ -277,6 +312,7 @@ static inline void copy_user_highpage(struct page *to, struct page *from, vfrom = kmap_local_page(from); vto = kmap_local_page(to); copy_user_page(vto, vfrom, vaddr, to); + kmsan_unpoison_memory(page_address(to), PAGE_SIZE); kunmap_local(vto); kunmap_local(vfrom); } @@ -292,6 +328,7 @@ static inline void copy_highpage(struct page *to, struct page *from) vfrom = kmap_local_page(from); vto = kmap_local_page(to); copy_page(vto, vfrom); + kmsan_copy_page_meta(to, from); kunmap_local(vto); kunmap_local(vfrom); } @@ -311,19 +348,6 @@ static inline void memcpy_page(struct page *dst_page, size_t dst_off, kunmap_local(dst); } -static inline void memmove_page(struct page *dst_page, size_t dst_off, - struct page *src_page, size_t src_off, - size_t len) -{ - char *dst = kmap_local_page(dst_page); - char *src = kmap_local_page(src_page); - - VM_BUG_ON(dst_off + len > PAGE_SIZE || src_off + len > PAGE_SIZE); - memmove(dst + dst_off, src + src_off, len); - kunmap_local(src); - kunmap_local(dst); -} - static inline void memset_page(struct page *page, size_t offset, int val, size_t len) { @@ -358,6 +382,8 @@ static inline void memcpy_to_page(struct page *page, size_t offset, static inline void memzero_page(struct page *page, size_t offset, size_t len) { char *addr = kmap_local_page(page); + + VM_BUG_ON(offset + len > PAGE_SIZE); memset(addr + offset, 0, len); flush_dcache_page(page); kunmap_local(addr); diff --git a/include/linux/hippidevice.h b/include/linux/hippidevice.h index 9dc01f7ab5b4..07414c241e65 100644 --- a/include/linux/hippidevice.h +++ b/include/linux/hippidevice.h @@ -23,6 +23,10 @@ #ifdef __KERNEL__ +struct neigh_parms; +struct net_device; +struct sk_buff; + struct hippi_cb { __u32 ifield; }; diff --git a/include/linux/hisi_acc_qm.h b/include/linux/hisi_acc_qm.h new file mode 100644 index 000000000000..e230c7c46110 --- /dev/null +++ b/include/linux/hisi_acc_qm.h @@ -0,0 +1,520 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2019 HiSilicon Limited. */ +#ifndef HISI_ACC_QM_H +#define HISI_ACC_QM_H + +#include <linux/bitfield.h> +#include <linux/debugfs.h> +#include <linux/iopoll.h> +#include <linux/module.h> +#include <linux/pci.h> + +#define QM_QNUM_V1 4096 +#define QM_QNUM_V2 1024 +#define QM_MAX_VFS_NUM_V2 63 + +/* qm user domain */ +#define QM_ARUSER_M_CFG_1 0x100088 +#define AXUSER_SNOOP_ENABLE BIT(30) +#define AXUSER_CMD_TYPE GENMASK(14, 12) +#define AXUSER_CMD_SMMU_NORMAL 1 +#define AXUSER_NS BIT(6) +#define AXUSER_NO BIT(5) +#define AXUSER_FP BIT(4) +#define AXUSER_SSV BIT(0) +#define AXUSER_BASE (AXUSER_SNOOP_ENABLE | \ + FIELD_PREP(AXUSER_CMD_TYPE, \ + AXUSER_CMD_SMMU_NORMAL) | \ + AXUSER_NS | AXUSER_NO | AXUSER_FP) +#define QM_ARUSER_M_CFG_ENABLE 0x100090 +#define ARUSER_M_CFG_ENABLE 0xfffffffe +#define QM_AWUSER_M_CFG_1 0x100098 +#define QM_AWUSER_M_CFG_ENABLE 0x1000a0 +#define AWUSER_M_CFG_ENABLE 0xfffffffe +#define QM_WUSER_M_CFG_ENABLE 0x1000a8 +#define WUSER_M_CFG_ENABLE 0xffffffff + +/* mailbox */ +#define QM_MB_CMD_SQC 0x0 +#define QM_MB_CMD_CQC 0x1 +#define QM_MB_CMD_EQC 0x2 +#define QM_MB_CMD_AEQC 0x3 +#define QM_MB_CMD_SQC_BT 0x4 +#define QM_MB_CMD_CQC_BT 0x5 +#define QM_MB_CMD_SQC_VFT_V2 0x6 +#define QM_MB_CMD_STOP_QP 0x8 +#define QM_MB_CMD_SRC 0xc +#define QM_MB_CMD_DST 0xd + +#define QM_MB_CMD_SEND_BASE 0x300 +#define QM_MB_EVENT_SHIFT 8 +#define QM_MB_BUSY_SHIFT 13 +#define QM_MB_OP_SHIFT 14 +#define QM_MB_CMD_DATA_ADDR_L 0x304 +#define QM_MB_CMD_DATA_ADDR_H 0x308 +#define QM_MB_MAX_WAIT_CNT 6000 + +/* doorbell */ +#define QM_DOORBELL_CMD_SQ 0 +#define QM_DOORBELL_CMD_CQ 1 +#define QM_DOORBELL_CMD_EQ 2 +#define QM_DOORBELL_CMD_AEQ 3 + +#define QM_DOORBELL_SQ_CQ_BASE_V2 0x1000 +#define QM_DOORBELL_EQ_AEQ_BASE_V2 0x2000 +#define QM_QP_MAX_NUM_SHIFT 11 +#define QM_DB_CMD_SHIFT_V2 12 +#define QM_DB_RAND_SHIFT_V2 16 +#define QM_DB_INDEX_SHIFT_V2 32 +#define QM_DB_PRIORITY_SHIFT_V2 48 +#define QM_VF_STATE 0x60 + +/* qm cache */ +#define QM_CACHE_CTL 0x100050 +#define SQC_CACHE_ENABLE BIT(0) +#define CQC_CACHE_ENABLE BIT(1) +#define SQC_CACHE_WB_ENABLE BIT(4) +#define SQC_CACHE_WB_THRD GENMASK(10, 5) +#define CQC_CACHE_WB_ENABLE BIT(11) +#define CQC_CACHE_WB_THRD GENMASK(17, 12) +#define QM_AXI_M_CFG 0x1000ac +#define AXI_M_CFG 0xffff +#define QM_AXI_M_CFG_ENABLE 0x1000b0 +#define AM_CFG_SINGLE_PORT_MAX_TRANS 0x300014 +#define AXI_M_CFG_ENABLE 0xffffffff +#define QM_PEH_AXUSER_CFG 0x1000cc +#define QM_PEH_AXUSER_CFG_ENABLE 0x1000d0 +#define PEH_AXUSER_CFG 0x401001 +#define PEH_AXUSER_CFG_ENABLE 0xffffffff + +#define QM_MIN_QNUM 2 +#define HISI_ACC_SGL_SGE_NR_MAX 255 +#define QM_SHAPER_CFG 0x100164 +#define QM_SHAPER_ENABLE BIT(30) +#define QM_SHAPER_TYPE1_OFFSET 10 + +/* page number for queue file region */ +#define QM_DOORBELL_PAGE_NR 1 + +/* uacce mode of the driver */ +#define UACCE_MODE_NOUACCE 0 /* don't use uacce */ +#define UACCE_MODE_SVA 1 /* use uacce sva mode */ +#define UACCE_MODE_DESC "0(default) means only register to crypto, 1 means both register to crypto and uacce" + +enum qm_stop_reason { + QM_NORMAL, + QM_SOFT_RESET, + QM_FLR, +}; + +enum qm_state { + QM_INIT = 0, + QM_START, + QM_CLOSE, + QM_STOP, +}; + +enum qp_state { + QP_INIT = 1, + QP_START, + QP_STOP, + QP_CLOSE, +}; + +enum qm_hw_ver { + QM_HW_UNKNOWN = -1, + QM_HW_V1 = 0x20, + QM_HW_V2 = 0x21, + QM_HW_V3 = 0x30, +}; + +enum qm_fun_type { + QM_HW_PF, + QM_HW_VF, +}; + +enum qm_debug_file { + CURRENT_QM, + CURRENT_Q, + CLEAR_ENABLE, + DEBUG_FILE_NUM, +}; + +enum qm_vf_state { + QM_READY = 0, + QM_NOT_READY, +}; + +enum qm_cap_bits { + QM_SUPPORT_DB_ISOLATION = 0x0, + QM_SUPPORT_FUNC_QOS, + QM_SUPPORT_STOP_QP, + QM_SUPPORT_MB_COMMAND, + QM_SUPPORT_SVA_PREFETCH, + QM_SUPPORT_RPM, +}; + +struct dfx_diff_registers { + u32 *regs; + u32 reg_offset; + u32 reg_len; +}; + +struct qm_dfx { + atomic64_t err_irq_cnt; + atomic64_t aeq_irq_cnt; + atomic64_t abnormal_irq_cnt; + atomic64_t create_qp_err_cnt; + atomic64_t mb_err_cnt; +}; + +struct debugfs_file { + enum qm_debug_file index; + struct mutex lock; + struct qm_debug *debug; +}; + +struct qm_debug { + u32 curr_qm_qp_num; + u32 sqe_mask_offset; + u32 sqe_mask_len; + struct qm_dfx dfx; + struct dentry *debug_root; + struct dentry *qm_d; + struct debugfs_file files[DEBUG_FILE_NUM]; + unsigned int *qm_last_words; + /* ACC engines recoreding last regs */ + unsigned int *last_words; + struct dfx_diff_registers *qm_diff_regs; + struct dfx_diff_registers *acc_diff_regs; +}; + +struct qm_shaper_factor { + u32 func_qos; + u64 cir_b; + u64 cir_u; + u64 cir_s; + u64 cbs_s; +}; + +struct qm_dma { + void *va; + dma_addr_t dma; + size_t size; +}; + +struct hisi_qm_status { + u32 eq_head; + bool eqc_phase; + u32 aeq_head; + bool aeqc_phase; + atomic_t flags; + int stop_reason; +}; + +struct hisi_qm; + +struct hisi_qm_err_info { + char *acpi_rst; + u32 msi_wr_port; + u32 ecc_2bits_mask; + u32 qm_shutdown_mask; + u32 dev_shutdown_mask; + u32 qm_reset_mask; + u32 dev_reset_mask; + u32 ce; + u32 nfe; + u32 fe; +}; + +struct hisi_qm_err_status { + u32 is_qm_ecc_mbit; + u32 is_dev_ecc_mbit; +}; + +struct hisi_qm_err_ini { + int (*hw_init)(struct hisi_qm *qm); + void (*hw_err_enable)(struct hisi_qm *qm); + void (*hw_err_disable)(struct hisi_qm *qm); + u32 (*get_dev_hw_err_status)(struct hisi_qm *qm); + void (*clear_dev_hw_err_status)(struct hisi_qm *qm, u32 err_sts); + void (*open_axi_master_ooo)(struct hisi_qm *qm); + void (*close_axi_master_ooo)(struct hisi_qm *qm); + void (*open_sva_prefetch)(struct hisi_qm *qm); + void (*close_sva_prefetch)(struct hisi_qm *qm); + void (*log_dev_hw_err)(struct hisi_qm *qm, u32 err_sts); + void (*show_last_dfx_regs)(struct hisi_qm *qm); + void (*err_info_init)(struct hisi_qm *qm); +}; + +struct hisi_qm_cap_info { + u32 type; + /* Register offset */ + u32 offset; + /* Bit offset in register */ + u32 shift; + u32 mask; + u32 v1_val; + u32 v2_val; + u32 v3_val; +}; + +struct hisi_qm_list { + struct mutex lock; + struct list_head list; + int (*register_to_crypto)(struct hisi_qm *qm); + void (*unregister_from_crypto)(struct hisi_qm *qm); +}; + +struct hisi_qm_poll_data { + struct hisi_qm *qm; + struct work_struct work; + u16 *qp_finish_id; +}; + +struct hisi_qm { + enum qm_hw_ver ver; + enum qm_fun_type fun_type; + const char *dev_name; + struct pci_dev *pdev; + void __iomem *io_base; + void __iomem *db_io_base; + + /* Capbility version, 0: not supports */ + u32 cap_ver; + u32 sqe_size; + u32 qp_base; + u32 qp_num; + u32 qp_in_used; + u32 ctrl_qp_num; + u32 max_qp_num; + u32 vfs_num; + u32 db_interval; + u16 eq_depth; + u16 aeq_depth; + struct list_head list; + struct hisi_qm_list *qm_list; + + struct qm_dma qdma; + struct qm_sqc *sqc; + struct qm_cqc *cqc; + struct qm_eqe *eqe; + struct qm_aeqe *aeqe; + dma_addr_t sqc_dma; + dma_addr_t cqc_dma; + dma_addr_t eqe_dma; + dma_addr_t aeqe_dma; + + struct hisi_qm_status status; + const struct hisi_qm_err_ini *err_ini; + struct hisi_qm_err_info err_info; + struct hisi_qm_err_status err_status; + unsigned long misc_ctl; /* driver removing and reset sched */ + /* Device capability bit */ + unsigned long caps; + + struct rw_semaphore qps_lock; + struct idr qp_idr; + struct hisi_qp *qp_array; + struct hisi_qm_poll_data *poll_data; + + struct mutex mailbox_lock; + + const struct hisi_qm_hw_ops *ops; + + struct qm_debug debug; + + u32 error_mask; + + struct workqueue_struct *wq; + struct work_struct rst_work; + struct work_struct cmd_process; + + const char *algs; + bool use_sva; + bool is_frozen; + + resource_size_t phys_base; + resource_size_t db_phys_base; + struct uacce_device *uacce; + int mode; + struct qm_shaper_factor *factor; + u32 mb_qos; + u32 type_rate; +}; + +struct hisi_qp_status { + atomic_t used; + u16 sq_tail; + u16 cq_head; + bool cqc_phase; + atomic_t flags; +}; + +struct hisi_qp_ops { + int (*fill_sqe)(void *sqe, void *q_parm, void *d_parm); +}; + +struct hisi_qp { + u32 qp_id; + u16 sq_depth; + u16 cq_depth; + u8 alg_type; + u8 req_type; + + struct qm_dma qdma; + void *sqe; + struct qm_cqe *cqe; + dma_addr_t sqe_dma; + dma_addr_t cqe_dma; + + struct hisi_qp_status qp_status; + struct hisi_qp_ops *hw_ops; + void *qp_ctx; + void (*req_cb)(struct hisi_qp *qp, void *data); + void (*event_cb)(struct hisi_qp *qp); + + struct hisi_qm *qm; + bool is_resetting; + bool is_in_kernel; + u16 pasid; + struct uacce_queue *uacce_q; +}; + +static inline int q_num_set(const char *val, const struct kernel_param *kp, + unsigned int device) +{ + struct pci_dev *pdev = pci_get_device(PCI_VENDOR_ID_HUAWEI, + device, NULL); + u32 n, q_num; + int ret; + + if (!val) + return -EINVAL; + + if (!pdev) { + q_num = min_t(u32, QM_QNUM_V1, QM_QNUM_V2); + pr_info("No device found currently, suppose queue number is %u\n", + q_num); + } else { + if (pdev->revision == QM_HW_V1) + q_num = QM_QNUM_V1; + else + q_num = QM_QNUM_V2; + } + + ret = kstrtou32(val, 10, &n); + if (ret || n < QM_MIN_QNUM || n > q_num) + return -EINVAL; + + return param_set_int(val, kp); +} + +static inline int vfs_num_set(const char *val, const struct kernel_param *kp) +{ + u32 n; + int ret; + + if (!val) + return -EINVAL; + + ret = kstrtou32(val, 10, &n); + if (ret < 0) + return ret; + + if (n > QM_MAX_VFS_NUM_V2) + return -EINVAL; + + return param_set_int(val, kp); +} + +static inline int mode_set(const char *val, const struct kernel_param *kp) +{ + u32 n; + int ret; + + if (!val) + return -EINVAL; + + ret = kstrtou32(val, 10, &n); + if (ret != 0 || (n != UACCE_MODE_SVA && + n != UACCE_MODE_NOUACCE)) + return -EINVAL; + + return param_set_int(val, kp); +} + +static inline int uacce_mode_set(const char *val, const struct kernel_param *kp) +{ + return mode_set(val, kp); +} + +static inline void hisi_qm_init_list(struct hisi_qm_list *qm_list) +{ + INIT_LIST_HEAD(&qm_list->list); + mutex_init(&qm_list->lock); +} + +int hisi_qm_init(struct hisi_qm *qm); +void hisi_qm_uninit(struct hisi_qm *qm); +int hisi_qm_start(struct hisi_qm *qm); +int hisi_qm_stop(struct hisi_qm *qm, enum qm_stop_reason r); +int hisi_qm_start_qp(struct hisi_qp *qp, unsigned long arg); +int hisi_qm_stop_qp(struct hisi_qp *qp); +int hisi_qp_send(struct hisi_qp *qp, const void *msg); +void hisi_qm_debug_init(struct hisi_qm *qm); +void hisi_qm_debug_regs_clear(struct hisi_qm *qm); +int hisi_qm_sriov_enable(struct pci_dev *pdev, int max_vfs); +int hisi_qm_sriov_disable(struct pci_dev *pdev, bool is_frozen); +int hisi_qm_sriov_configure(struct pci_dev *pdev, int num_vfs); +void hisi_qm_dev_err_init(struct hisi_qm *qm); +void hisi_qm_dev_err_uninit(struct hisi_qm *qm); +int hisi_qm_diff_regs_init(struct hisi_qm *qm, + struct dfx_diff_registers *dregs, int reg_len); +void hisi_qm_diff_regs_uninit(struct hisi_qm *qm, int reg_len); +void hisi_qm_acc_diff_regs_dump(struct hisi_qm *qm, struct seq_file *s, + struct dfx_diff_registers *dregs, int regs_len); + +pci_ers_result_t hisi_qm_dev_err_detected(struct pci_dev *pdev, + pci_channel_state_t state); +pci_ers_result_t hisi_qm_dev_slot_reset(struct pci_dev *pdev); +void hisi_qm_reset_prepare(struct pci_dev *pdev); +void hisi_qm_reset_done(struct pci_dev *pdev); + +int hisi_qm_wait_mb_ready(struct hisi_qm *qm); +int hisi_qm_mb(struct hisi_qm *qm, u8 cmd, dma_addr_t dma_addr, u16 queue, + bool op); + +struct hisi_acc_sgl_pool; +struct hisi_acc_hw_sgl *hisi_acc_sg_buf_map_to_hw_sgl(struct device *dev, + struct scatterlist *sgl, struct hisi_acc_sgl_pool *pool, + u32 index, dma_addr_t *hw_sgl_dma); +void hisi_acc_sg_buf_unmap(struct device *dev, struct scatterlist *sgl, + struct hisi_acc_hw_sgl *hw_sgl); +struct hisi_acc_sgl_pool *hisi_acc_create_sgl_pool(struct device *dev, + u32 count, u32 sge_nr); +void hisi_acc_free_sgl_pool(struct device *dev, + struct hisi_acc_sgl_pool *pool); +int hisi_qm_alloc_qps_node(struct hisi_qm_list *qm_list, int qp_num, + u8 alg_type, int node, struct hisi_qp **qps); +void hisi_qm_free_qps(struct hisi_qp **qps, int qp_num); +void hisi_qm_dev_shutdown(struct pci_dev *pdev); +void hisi_qm_wait_task_finish(struct hisi_qm *qm, struct hisi_qm_list *qm_list); +int hisi_qm_alg_register(struct hisi_qm *qm, struct hisi_qm_list *qm_list); +void hisi_qm_alg_unregister(struct hisi_qm *qm, struct hisi_qm_list *qm_list); +int hisi_qm_resume(struct device *dev); +int hisi_qm_suspend(struct device *dev); +void hisi_qm_pm_uninit(struct hisi_qm *qm); +void hisi_qm_pm_init(struct hisi_qm *qm); +int hisi_qm_get_dfx_access(struct hisi_qm *qm); +void hisi_qm_put_dfx_access(struct hisi_qm *qm); +void hisi_qm_regs_dump(struct seq_file *s, struct debugfs_regset32 *regset); +u32 hisi_qm_get_hw_info(struct hisi_qm *qm, + const struct hisi_qm_cap_info *info_table, + u32 index, bool is_read); + +/* Used by VFIO ACC live migration driver */ +struct pci_driver *hisi_sec_get_pf_driver(void); +struct pci_driver *hisi_hpre_get_pf_driver(void); +struct pci_driver *hisi_zip_get_pf_driver(void); +#endif diff --git a/include/linux/hmm.h b/include/linux/hmm.h index 2fd2e91d5107..126a36571667 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -4,19 +4,14 @@ * * Authors: Jérôme Glisse <jglisse@redhat.com> * - * See Documentation/vm/hmm.rst for reasons and overview of what HMM is. + * See Documentation/mm/hmm.rst for reasons and overview of what HMM is. */ #ifndef LINUX_HMM_H #define LINUX_HMM_H -#include <linux/kconfig.h> -#include <linux/pgtable.h> +#include <linux/mm.h> -#include <linux/device.h> -#include <linux/migrate.h> -#include <linux/memremap.h> -#include <linux/completion.h> -#include <linux/mmu_notifier.h> +struct mmu_interval_notifier; /* * On output: @@ -105,7 +100,7 @@ struct hmm_range { }; /* - * Please see Documentation/vm/hmm.rst for how to use the range API. + * Please see Documentation/mm/hmm.rst for how to use the range API. */ int hmm_range_fault(struct hmm_range *range); diff --git a/include/linux/host1x.h b/include/linux/host1x.h index e8dc5bc41f79..cb2100d9b0ff 100644 --- a/include/linux/host1x.h +++ b/include/linux/host1x.h @@ -31,6 +31,11 @@ u64 host1x_get_dma_mask(struct host1x *host1x); * struct host1x_bo_cache - host1x buffer object cache * @mappings: list of mappings * @lock: synchronizes accesses to the list of mappings + * + * Note that entries are not periodically evicted from this cache and instead need to be + * explicitly released. This is used primarily for DRM/KMS where the cache's reference is + * released when the last reference to a buffer object represented by a mapping in this + * cache is dropped. */ struct host1x_bo_cache { struct list_head mappings; @@ -81,6 +86,7 @@ struct host1x_client_ops { * @parent: pointer to parent structure * @usecount: reference count for this structure * @lock: mutex for mutually exclusive concurrency + * @cache: host1x buffer object cache */ struct host1x_client { struct list_head list; @@ -321,6 +327,14 @@ struct host1x_job { /* Whether host1x-side firewall should be ran for this job or not */ bool enable_firewall; + + /* Options for configuring engine data stream ID */ + /* Context device to use for job */ + struct host1x_memory_context *memory_context; + /* Stream ID to use if context isolation is disabled (!memory_context) */ + u32 engine_fallback_streamid; + /* Engine offset to program stream ID to */ + u32 engine_streamid_offset; }; struct host1x_job *host1x_job_alloc(struct host1x_channel *ch, @@ -440,4 +454,38 @@ int tegra_mipi_disable(struct tegra_mipi_device *device); int tegra_mipi_start_calibration(struct tegra_mipi_device *device); int tegra_mipi_finish_calibration(struct tegra_mipi_device *device); +/* host1x memory contexts */ + +struct host1x_memory_context { + struct host1x *host; + + refcount_t ref; + struct pid *owner; + + struct device dev; + u64 dma_mask; + u32 stream_id; +}; + +#ifdef CONFIG_IOMMU_API +struct host1x_memory_context *host1x_memory_context_alloc(struct host1x *host1x, + struct pid *pid); +void host1x_memory_context_get(struct host1x_memory_context *cd); +void host1x_memory_context_put(struct host1x_memory_context *cd); +#else +static inline struct host1x_memory_context *host1x_memory_context_alloc(struct host1x *host1x, + struct pid *pid) +{ + return NULL; +} + +static inline void host1x_memory_context_get(struct host1x_memory_context *cd) +{ +} + +static inline void host1x_memory_context_put(struct host1x_memory_context *cd) +{ +} +#endif + #endif diff --git a/include/linux/host1x_context_bus.h b/include/linux/host1x_context_bus.h new file mode 100644 index 000000000000..72462737a6db --- /dev/null +++ b/include/linux/host1x_context_bus.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright (c) 2021, NVIDIA Corporation. All rights reserved. + */ + +#ifndef __LINUX_HOST1X_CONTEXT_BUS_H +#define __LINUX_HOST1X_CONTEXT_BUS_H + +#include <linux/device.h> + +#ifdef CONFIG_TEGRA_HOST1X_CONTEXT_BUS +extern struct bus_type host1x_context_device_bus_type; +#endif + +#endif diff --git a/include/linux/hp_sdc.h b/include/linux/hp_sdc.h index 6f1dee7e67e0..9be8704e2d38 100644 --- a/include/linux/hp_sdc.h +++ b/include/linux/hp_sdc.h @@ -180,7 +180,7 @@ switch (val) { \ #define HP_SDC_CMD_SET_IM 0x40 /* 010xxxxx == set irq mask */ -/* The documents provided do not explicitly state that all registers betweem +/* The documents provided do not explicitly state that all registers between * 0x01 and 0x1f inclusive can be read by sending their register index as a * command, but this is implied and appears to be the case. */ diff --git a/include/linux/hrtimer_api.h b/include/linux/hrtimer_api.h new file mode 100644 index 000000000000..8d9700894468 --- /dev/null +++ b/include/linux/hrtimer_api.h @@ -0,0 +1 @@ +#include <linux/hrtimer.h> diff --git a/include/linux/htcpld.h b/include/linux/htcpld.h index 842fce69ac06..5f8ac9b1d724 100644 --- a/include/linux/htcpld.h +++ b/include/linux/htcpld.h @@ -13,8 +13,6 @@ struct htcpld_chip_platform_data { }; struct htcpld_core_platform_data { - unsigned int int_reset_gpio_hi; - unsigned int int_reset_gpio_lo; unsigned int i2c_adapter_id; struct htcpld_chip_platform_data *chip; diff --git a/include/linux/hte.h b/include/linux/hte.h new file mode 100644 index 000000000000..8289055061ab --- /dev/null +++ b/include/linux/hte.h @@ -0,0 +1,271 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __LINUX_HTE_H +#define __LINUX_HTE_H + +#include <linux/errno.h> + +struct hte_chip; +struct hte_device; +struct of_phandle_args; + +/** + * enum hte_edge - HTE line edge flags. + * + * @HTE_EDGE_NO_SETUP: No edge setup. In this case consumer will setup edges, + * for example during request irq call. + * @HTE_RISING_EDGE_TS: Rising edge. + * @HTE_FALLING_EDGE_TS: Falling edge. + * + */ +enum hte_edge { + HTE_EDGE_NO_SETUP = 1U << 0, + HTE_RISING_EDGE_TS = 1U << 1, + HTE_FALLING_EDGE_TS = 1U << 2, +}; + +/** + * enum hte_return - HTE subsystem return values used during callback. + * + * @HTE_CB_HANDLED: The consumer handled the data. + * @HTE_RUN_SECOND_CB: The consumer needs further processing, in that case + * HTE subsystem calls secondary callback provided by the consumer where it + * is allowed to sleep. + */ +enum hte_return { + HTE_CB_HANDLED, + HTE_RUN_SECOND_CB, +}; + +/** + * struct hte_ts_data - HTE timestamp data. + * + * @tsc: Timestamp value. + * @seq: Sequence counter of the timestamps. + * @raw_level: Level of the line at the timestamp if provider supports it, + * -1 otherwise. + */ +struct hte_ts_data { + u64 tsc; + u64 seq; + int raw_level; +}; + +/** + * struct hte_clk_info - Clock source info that HTE provider uses to timestamp. + * + * @hz: Supported clock rate in HZ, for example 1KHz clock = 1000. + * @type: Supported clock type. + */ +struct hte_clk_info { + u64 hz; + clockid_t type; +}; + +/** + * typedef hte_ts_cb_t - HTE timestamp data processing primary callback. + * + * The callback is used to push timestamp data to the client and it is + * not allowed to sleep. + * + * @ts: HW timestamp data. + * @data: Client supplied data. + */ +typedef enum hte_return (*hte_ts_cb_t)(struct hte_ts_data *ts, void *data); + +/** + * typedef hte_ts_sec_cb_t - HTE timestamp data processing secondary callback. + * + * This is used when the client needs further processing where it is + * allowed to sleep. + * + * @data: Client supplied data. + * + */ +typedef enum hte_return (*hte_ts_sec_cb_t)(void *data); + +/** + * struct hte_line_attr - Line attributes. + * + * @line_id: The logical ID understood by the consumers and providers. + * @line_data: Line data related to line_id. + * @edge_flags: Edge setup flags. + * @name: Descriptive name of the entity that is being monitored for the + * hardware timestamping. If null, HTE core will construct the name. + * + */ +struct hte_line_attr { + u32 line_id; + void *line_data; + unsigned long edge_flags; + const char *name; +}; + +/** + * struct hte_ts_desc - HTE timestamp descriptor. + * + * This structure is a communication token between consumers to subsystem + * and subsystem to providers. + * + * @attr: The line attributes. + * @hte_data: Subsystem's private data, set by HTE subsystem. + */ +struct hte_ts_desc { + struct hte_line_attr attr; + void *hte_data; +}; + +/** + * struct hte_ops - HTE operations set by providers. + * + * @request: Hook for requesting a HTE timestamp. Returns 0 on success, + * non-zero for failures. + * @release: Hook for releasing a HTE timestamp. Returns 0 on success, + * non-zero for failures. + * @enable: Hook to enable the specified timestamp. Returns 0 on success, + * non-zero for failures. + * @disable: Hook to disable specified timestamp. Returns 0 on success, + * non-zero for failures. + * @get_clk_src_info: Hook to get the clock information the provider uses + * to timestamp. Returns 0 for success and negative error code for failure. On + * success HTE subsystem fills up provided struct hte_clk_info. + * + * xlated_id parameter is used to communicate between HTE subsystem and the + * providers and is translated by the provider. + */ +struct hte_ops { + int (*request)(struct hte_chip *chip, struct hte_ts_desc *desc, + u32 xlated_id); + int (*release)(struct hte_chip *chip, struct hte_ts_desc *desc, + u32 xlated_id); + int (*enable)(struct hte_chip *chip, u32 xlated_id); + int (*disable)(struct hte_chip *chip, u32 xlated_id); + int (*get_clk_src_info)(struct hte_chip *chip, + struct hte_clk_info *ci); +}; + +/** + * struct hte_chip - Abstract HTE chip. + * + * @name: functional name of the HTE IP block. + * @dev: device providing the HTE. + * @ops: callbacks for this HTE. + * @nlines: number of lines/signals supported by this chip. + * @xlate_of: Callback which translates consumer supplied logical ids to + * physical ids, return 0 for the success and negative for the failures. + * It stores (between 0 to @nlines) in xlated_id parameter for the success. + * @xlate_plat: Same as above but for the consumers with no DT node. + * @match_from_linedata: Match HTE device using the line_data. + * @of_hte_n_cells: Number of cells used to form the HTE specifier. + * @gdev: HTE subsystem abstract device, internal to the HTE subsystem. + * @data: chip specific private data. + */ +struct hte_chip { + const char *name; + struct device *dev; + const struct hte_ops *ops; + u32 nlines; + int (*xlate_of)(struct hte_chip *gc, + const struct of_phandle_args *args, + struct hte_ts_desc *desc, u32 *xlated_id); + int (*xlate_plat)(struct hte_chip *gc, struct hte_ts_desc *desc, + u32 *xlated_id); + bool (*match_from_linedata)(const struct hte_chip *chip, + const struct hte_ts_desc *hdesc); + u8 of_hte_n_cells; + + struct hte_device *gdev; + void *data; +}; + +#if IS_ENABLED(CONFIG_HTE) +/* HTE APIs for the providers */ +int devm_hte_register_chip(struct hte_chip *chip); +int hte_push_ts_ns(const struct hte_chip *chip, u32 xlated_id, + struct hte_ts_data *data); + +/* HTE APIs for the consumers */ +int hte_init_line_attr(struct hte_ts_desc *desc, u32 line_id, + unsigned long edge_flags, const char *name, + void *data); +int hte_ts_get(struct device *dev, struct hte_ts_desc *desc, int index); +int hte_ts_put(struct hte_ts_desc *desc); +int hte_request_ts_ns(struct hte_ts_desc *desc, hte_ts_cb_t cb, + hte_ts_sec_cb_t tcb, void *data); +int devm_hte_request_ts_ns(struct device *dev, struct hte_ts_desc *desc, + hte_ts_cb_t cb, hte_ts_sec_cb_t tcb, void *data); +int of_hte_req_count(struct device *dev); +int hte_enable_ts(struct hte_ts_desc *desc); +int hte_disable_ts(struct hte_ts_desc *desc); +int hte_get_clk_src_info(const struct hte_ts_desc *desc, + struct hte_clk_info *ci); + +#else /* !CONFIG_HTE */ +static inline int devm_hte_register_chip(struct hte_chip *chip) +{ + return -EOPNOTSUPP; +} + +static inline int hte_push_ts_ns(const struct hte_chip *chip, + u32 xlated_id, + const struct hte_ts_data *data) +{ + return -EOPNOTSUPP; +} + +static inline int hte_init_line_attr(struct hte_ts_desc *desc, u32 line_id, + unsigned long edge_flags, + const char *name, void *data) +{ + return -EOPNOTSUPP; +} + +static inline int hte_ts_get(struct device *dev, struct hte_ts_desc *desc, + int index) +{ + return -EOPNOTSUPP; +} + +static inline int hte_ts_put(struct hte_ts_desc *desc) +{ + return -EOPNOTSUPP; +} + +static inline int hte_request_ts_ns(struct hte_ts_desc *desc, hte_ts_cb_t cb, + hte_ts_sec_cb_t tcb, void *data) +{ + return -EOPNOTSUPP; +} + +static inline int devm_hte_request_ts_ns(struct device *dev, + struct hte_ts_desc *desc, + hte_ts_cb_t cb, + hte_ts_sec_cb_t tcb, + void *data) +{ + return -EOPNOTSUPP; +} + +static inline int of_hte_req_count(struct device *dev) +{ + return -EOPNOTSUPP; +} + +static inline int hte_enable_ts(struct hte_ts_desc *desc) +{ + return -EOPNOTSUPP; +} + +static inline int hte_disable_ts(struct hte_ts_desc *desc) +{ + return -EOPNOTSUPP; +} + +static inline int hte_get_clk_src_info(const struct hte_ts_desc *desc, + struct hte_clk_info *ci) +{ + return -EOPNOTSUPP; +} +#endif /* !CONFIG_HTE */ + +#endif diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index f280f33ff223..a1341fdcf666 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -36,8 +36,9 @@ int zap_huge_pud(struct mmu_gather *tlb, struct vm_area_struct *vma, pud_t *pud, unsigned long addr); bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr, unsigned long new_addr, pmd_t *old_pmd, pmd_t *new_pmd); -int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, - pgprot_t newprot, unsigned long cp_flags); +int change_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, + pmd_t *pmd, unsigned long addr, pgprot_t newprot, + unsigned long cp_flags); vm_fault_t vmf_insert_pfn_pmd_prot(struct vm_fault *vmf, pfn_t pfn, pgprot_t pgprot, bool write); @@ -115,9 +116,30 @@ extern struct kobj_attribute shmem_enabled_attr; extern unsigned long transparent_hugepage_flags; +#define hugepage_flags_enabled() \ + (transparent_hugepage_flags & \ + ((1<<TRANSPARENT_HUGEPAGE_FLAG) | \ + (1<<TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG))) +#define hugepage_flags_always() \ + (transparent_hugepage_flags & \ + (1<<TRANSPARENT_HUGEPAGE_FLAG)) + +/* + * Do the below checks: + * - For file vma, check if the linear page offset of vma is + * HPAGE_PMD_NR aligned within the file. The hugepage is + * guaranteed to be hugepage-aligned within the file, but we must + * check that the PMD-aligned addresses in the VMA map to + * PMD-aligned offsets within the file, else the hugepage will + * not be PMD-mappable. + * - For all vmas, check if the haddr is in an aligned HPAGE_PMD_SIZE + * area. + */ static inline bool transhuge_vma_suitable(struct vm_area_struct *vma, - unsigned long haddr) + unsigned long addr) { + unsigned long haddr; + /* Don't have to check pgoff for anonymous vma */ if (!vma_is_anonymous(vma)) { if (!IS_ALIGNED((vma->vm_start >> PAGE_SHIFT) - vma->vm_pgoff, @@ -125,54 +147,29 @@ static inline bool transhuge_vma_suitable(struct vm_area_struct *vma, return false; } - if (haddr < vma->vm_start || haddr + HPAGE_PMD_SIZE > vma->vm_end) - return false; - return true; -} + haddr = addr & HPAGE_PMD_MASK; -static inline bool transhuge_vma_enabled(struct vm_area_struct *vma, - unsigned long vm_flags) -{ - /* Explicitly disabled through madvise. */ - if ((vm_flags & VM_NOHUGEPAGE) || - test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags)) + if (haddr < vma->vm_start || haddr + HPAGE_PMD_SIZE > vma->vm_end) return false; return true; } -/* - * to be used on vmas which are known to support THP. - * Use transparent_hugepage_active otherwise - */ -static inline bool __transparent_hugepage_enabled(struct vm_area_struct *vma) +static inline bool file_thp_enabled(struct vm_area_struct *vma) { + struct inode *inode; - /* - * If the hardware/firmware marked hugepage support disabled. - */ - if (transparent_hugepage_flags & (1 << TRANSPARENT_HUGEPAGE_NEVER_DAX)) + if (!vma->vm_file) return false; - if (!transhuge_vma_enabled(vma, vma->vm_flags)) - return false; + inode = vma->vm_file->f_inode; - if (vma_is_temporary_stack(vma)) - return false; - - if (transparent_hugepage_flags & (1 << TRANSPARENT_HUGEPAGE_FLAG)) - return true; - - if (vma_is_dax(vma)) - return true; - - if (transparent_hugepage_flags & - (1 << TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG)) - return !!(vma->vm_flags & VM_HUGEPAGE); - - return false; + return (IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS)) && + (vma->vm_flags & VM_EXEC) && + !inode_is_open_for_write(inode) && S_ISREG(inode->i_mode); } -bool transparent_hugepage_active(struct vm_area_struct *vma); +bool hugepage_vma_check(struct vm_area_struct *vma, unsigned long vm_flags, + bool smaps, bool in_pf, bool enforce_sysfs); #define transparent_hugepage_use_zero_page() \ (transparent_hugepage_flags & \ @@ -183,9 +180,8 @@ unsigned long thp_get_unmapped_area(struct file *filp, unsigned long addr, void prep_transhuge_page(struct page *page); void free_transhuge_page(struct page *page); -bool is_transparent_hugepage(struct page *page); -bool can_split_huge_page(struct page *page, int *pextra_pins); +bool can_split_folio(struct folio *folio, int *pextra_pins); int split_huge_page_to_list(struct page *page, struct list_head *list); static inline int split_huge_page(struct page *page) { @@ -194,7 +190,7 @@ static inline int split_huge_page(struct page *page) void deferred_split_huge_page(struct page *page); void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, - unsigned long address, bool freeze, struct page *page); + unsigned long address, bool freeze, struct folio *folio); #define split_huge_pmd(__vma, __pmd, __address) \ do { \ @@ -207,7 +203,7 @@ void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, void split_huge_pmd_address(struct vm_area_struct *vma, unsigned long address, - bool freeze, struct page *page); + bool freeze, struct folio *folio); void __split_huge_pud(struct vm_area_struct *vma, pud_t *pud, unsigned long address); @@ -222,6 +218,9 @@ void __split_huge_pud(struct vm_area_struct *vma, pud_t *pud, int hugepage_madvise(struct vm_area_struct *vma, unsigned long *vm_flags, int advice); +int madvise_collapse(struct vm_area_struct *vma, + struct vm_area_struct **prev, + unsigned long start, unsigned long end); void vma_adjust_trans_huge(struct vm_area_struct *vma, unsigned long start, unsigned long end, long adjust_next); spinlock_t *__pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma); @@ -251,27 +250,12 @@ static inline spinlock_t *pud_trans_huge_lock(pud_t *pud, } /** - * thp_order - Order of a transparent huge page. - * @page: Head page of a transparent huge page. - */ -static inline unsigned int thp_order(struct page *page) -{ - VM_BUG_ON_PGFLAGS(PageTail(page), page); - if (PageHead(page)) - return HPAGE_PMD_ORDER; - return 0; -} - -/** - * thp_nr_pages - The number of regular pages in this huge page. - * @page: The head page of a huge page. + * folio_test_pmd_mappable - Can we map this folio with a PMD? + * @folio: The folio to test */ -static inline int thp_nr_pages(struct page *page) +static inline bool folio_test_pmd_mappable(struct folio *folio) { - VM_BUG_ON_PGFLAGS(PageTail(page), page); - if (PageHead(page)) - return HPAGE_PMD_NR; - return 1; + return folio_order(folio) >= HPAGE_PMD_ORDER; } struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr, @@ -291,7 +275,7 @@ static inline bool is_huge_zero_page(struct page *page) static inline bool is_huge_zero_pmd(pmd_t pmd) { - return READ_ONCE(huge_zero_pfn) == pmd_pfn(pmd) && pmd_present(pmd); + return pmd_present(pmd) && READ_ONCE(huge_zero_pfn) == pmd_pfn(pmd); } static inline bool is_huge_zero_pud(pud_t pud) @@ -312,8 +296,8 @@ static inline bool thp_migration_supported(void) static inline struct list_head *page_deferred_list(struct page *page) { /* - * Global or memcg deferred list in the second tail pages is - * occupied by compound_head. + * See organization of tail pages of compound page in + * "struct page" definition. */ return &page[2].deferred_list; } @@ -327,55 +311,33 @@ static inline struct list_head *page_deferred_list(struct page *page) #define HPAGE_PUD_MASK ({ BUILD_BUG(); 0; }) #define HPAGE_PUD_SIZE ({ BUILD_BUG(); 0; }) -static inline unsigned int thp_order(struct page *page) -{ - VM_BUG_ON_PGFLAGS(PageTail(page), page); - return 0; -} - -static inline int thp_nr_pages(struct page *page) -{ - VM_BUG_ON_PGFLAGS(PageTail(page), page); - return 1; -} - -static inline bool __transparent_hugepage_enabled(struct vm_area_struct *vma) -{ - return false; -} - -static inline bool transparent_hugepage_active(struct vm_area_struct *vma) +static inline bool folio_test_pmd_mappable(struct folio *folio) { return false; } static inline bool transhuge_vma_suitable(struct vm_area_struct *vma, - unsigned long haddr) + unsigned long addr) { return false; } -static inline bool transhuge_vma_enabled(struct vm_area_struct *vma, - unsigned long vm_flags) +static inline bool hugepage_vma_check(struct vm_area_struct *vma, + unsigned long vm_flags, bool smaps, + bool in_pf, bool enforce_sysfs) { return false; } static inline void prep_transhuge_page(struct page *page) {} -static inline bool is_transparent_hugepage(struct page *page) -{ - return false; -} - #define transparent_hugepage_flags 0UL #define thp_get_unmapped_area NULL static inline bool -can_split_huge_page(struct page *page, int *pextra_pins) +can_split_folio(struct folio *folio, int *pextra_pins) { - BUILD_BUG(); return false; } static inline int @@ -392,9 +354,9 @@ static inline void deferred_split_huge_page(struct page *page) {} do { } while (0) static inline void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, - unsigned long address, bool freeze, struct page *page) {} + unsigned long address, bool freeze, struct folio *folio) {} static inline void split_huge_pmd_address(struct vm_area_struct *vma, - unsigned long address, bool freeze, struct page *page) {} + unsigned long address, bool freeze, struct folio *folio) {} #define split_huge_pud(__vma, __pmd, __address) \ do { } while (0) @@ -402,9 +364,16 @@ static inline void split_huge_pmd_address(struct vm_area_struct *vma, static inline int hugepage_madvise(struct vm_area_struct *vma, unsigned long *vm_flags, int advice) { - BUG(); - return 0; + return -EINVAL; } + +static inline int madvise_collapse(struct vm_area_struct *vma, + struct vm_area_struct **prev, + unsigned long start, unsigned long end) +{ + return -EINVAL; +} + static inline void vma_adjust_trans_huge(struct vm_area_struct *vma, unsigned long start, unsigned long end, @@ -469,15 +438,27 @@ static inline bool thp_migration_supported(void) } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ -/** - * thp_size - Size of a transparent huge page. - * @page: Head page of a transparent huge page. - * - * Return: Number of bytes in this page. +static inline int split_folio_to_list(struct folio *folio, + struct list_head *list) +{ + return split_huge_page_to_list(&folio->page, list); +} + +static inline int split_folio(struct folio *folio) +{ + return split_folio_to_list(folio, NULL); +} + +/* + * archs that select ARCH_WANTS_THP_SWAP but don't support THP_SWP due to + * limitations in the implementation like arm64 MTE can override this to + * false */ -static inline unsigned long thp_size(struct page *page) +#ifndef arch_thp_swp_supported +static inline bool arch_thp_swp_supported(void) { - return PAGE_SIZE << thp_order(page); + return true; } +#endif #endif /* _LINUX_HUGE_MM_H */ diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 00351ccb49a3..8b4f93e84868 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -16,8 +16,9 @@ struct ctl_table; struct user_struct; struct mmu_gather; +struct node; -#ifndef is_hugepd +#ifndef CONFIG_ARCH_HAS_HUGEPD typedef struct { unsigned long pd; } hugepd_t; #define is_hugepd(hugepd) (0) #define __hugepd(x) ((hugepd_t) { (x) }) @@ -43,6 +44,9 @@ enum { SUBPAGE_INDEX_CGROUP_RSVD, /* reuse page->private */ __MAX_CGROUP_SUBPAGE_INDEX = SUBPAGE_INDEX_CGROUP_RSVD, #endif +#ifdef CONFIG_MEMORY_FAILURE + SUBPAGE_INDEX_HWPOISON, +#endif __NR_USED_SUBPAGE, }; @@ -111,6 +115,12 @@ struct file_region { #endif }; +struct hugetlb_vma_lock { + struct kref refs; + struct rw_semaphore rw_sema; + struct vm_area_struct *vma; +}; + extern struct resv_map *resv_map_alloc(void); void resv_map_release(struct kref *ref); @@ -123,7 +133,7 @@ struct hugepage_subpool *hugepage_new_subpool(struct hstate *h, long max_hpages, long min_hpages); void hugepage_put_subpool(struct hugepage_subpool *spool); -void reset_vma_resv_huge_pages(struct vm_area_struct *vma); +void hugetlb_dup_vma_private(struct vm_area_struct *vma); void clear_vma_resv_huge_pages(struct vm_area_struct *vma); int hugetlb_sysctl_handler(struct ctl_table *, int, void *, size_t *, loff_t *); int hugetlb_overcommit_handler(struct ctl_table *, int, void *, size_t *, @@ -137,20 +147,22 @@ int move_hugetlb_page_tables(struct vm_area_struct *vma, struct vm_area_struct *new_vma, unsigned long old_addr, unsigned long new_addr, unsigned long len); -int copy_hugetlb_page_range(struct mm_struct *, struct mm_struct *, struct vm_area_struct *); +int copy_hugetlb_page_range(struct mm_struct *, struct mm_struct *, + struct vm_area_struct *, struct vm_area_struct *); long follow_hugetlb_page(struct mm_struct *, struct vm_area_struct *, struct page **, struct vm_area_struct **, unsigned long *, unsigned long *, long, unsigned int, int *); void unmap_hugepage_range(struct vm_area_struct *, - unsigned long, unsigned long, struct page *); + unsigned long, unsigned long, struct page *, + zap_flags_t); void __unmap_hugepage_range_final(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start, unsigned long end, - struct page *ref_page); + struct page *ref_page, zap_flags_t zap_flags); void hugetlb_report_meminfo(struct seq_file *); int hugetlb_report_node_meminfo(char *buf, int len, int nid); -void hugetlb_show_meminfo(void); +void hugetlb_show_meminfo_node(int nid); unsigned long hugetlb_total_pages(void); vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, unsigned int flags); @@ -160,15 +172,17 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, pte_t *dst_pte, unsigned long dst_addr, unsigned long src_addr, enum mcopy_atomic_mode mode, - struct page **pagep); + struct page **pagep, + bool wp_copy); #endif /* CONFIG_USERFAULTFD */ bool hugetlb_reserve_pages(struct inode *inode, long from, long to, struct vm_area_struct *vma, vm_flags_t vm_flags); long hugetlb_unreserve_pages(struct inode *inode, long start, long end, long freed); -bool isolate_huge_page(struct page *page, struct list_head *list); +int isolate_hugetlb(struct page *page, struct list_head *list); int get_hwpoison_huge_page(struct page *page, bool *hugetlb); +int get_huge_page_for_hwpoison(unsigned long pfn, int flags); void putback_active_hugepage(struct page *page); void move_hugetlb_state(struct page *oldpage, struct page *newpage, int reason); void free_huge_page(struct page *page); @@ -190,8 +204,9 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, unsigned long sz); pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, unsigned long sz); +unsigned long hugetlb_mask_last_page(struct hstate *h); int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long *addr, pte_t *ptep); + unsigned long addr, pte_t *ptep); void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma, unsigned long *start, unsigned long *end); struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address, @@ -199,24 +214,33 @@ struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address, struct page *follow_huge_pd(struct vm_area_struct *vma, unsigned long address, hugepd_t hpd, int flags, int pdshift); -struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address, - pmd_t *pmd, int flags); +struct page *follow_huge_pmd_pte(struct vm_area_struct *vma, unsigned long address, + int flags); struct page *follow_huge_pud(struct mm_struct *mm, unsigned long address, pud_t *pud, int flags); struct page *follow_huge_pgd(struct mm_struct *mm, unsigned long address, pgd_t *pgd, int flags); +void hugetlb_vma_lock_read(struct vm_area_struct *vma); +void hugetlb_vma_unlock_read(struct vm_area_struct *vma); +void hugetlb_vma_lock_write(struct vm_area_struct *vma); +void hugetlb_vma_unlock_write(struct vm_area_struct *vma); +int hugetlb_vma_trylock_write(struct vm_area_struct *vma); +void hugetlb_vma_assert_locked(struct vm_area_struct *vma); +void hugetlb_vma_lock_release(struct kref *kref); + int pmd_huge(pmd_t pmd); int pud_huge(pud_t pud); unsigned long hugetlb_change_protection(struct vm_area_struct *vma, - unsigned long address, unsigned long end, pgprot_t newprot); + unsigned long address, unsigned long end, pgprot_t newprot, + unsigned long cp_flags); bool is_hugetlb_entry_migration(pte_t pte); void hugetlb_unshare_all_pmds(struct vm_area_struct *vma); #else /* !CONFIG_HUGETLB_PAGE */ -static inline void reset_vma_resv_huge_pages(struct vm_area_struct *vma) +static inline void hugetlb_dup_vma_private(struct vm_area_struct *vma) { } @@ -237,7 +261,7 @@ static inline struct address_space *hugetlb_page_mapping_lock_write( static inline int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long *addr, pte_t *ptep) + unsigned long addr, pte_t *ptep) { return 0; } @@ -265,7 +289,9 @@ static inline struct page *follow_huge_addr(struct mm_struct *mm, } static inline int copy_hugetlb_page_range(struct mm_struct *dst, - struct mm_struct *src, struct vm_area_struct *vma) + struct mm_struct *src, + struct vm_area_struct *dst_vma, + struct vm_area_struct *src_vma) { BUG(); return 0; @@ -290,7 +316,7 @@ static inline int hugetlb_report_node_meminfo(char *buf, int len, int nid) return 0; } -static inline void hugetlb_show_meminfo(void) +static inline void hugetlb_show_meminfo_node(int nid) { } @@ -301,8 +327,8 @@ static inline struct page *follow_huge_pd(struct vm_area_struct *vma, return NULL; } -static inline struct page *follow_huge_pmd(struct mm_struct *mm, - unsigned long address, pmd_t *pmd, int flags) +static inline struct page *follow_huge_pmd_pte(struct vm_area_struct *vma, + unsigned long address, int flags) { return NULL; } @@ -325,6 +351,31 @@ static inline int prepare_hugepage_range(struct file *file, return -EINVAL; } +static inline void hugetlb_vma_lock_read(struct vm_area_struct *vma) +{ +} + +static inline void hugetlb_vma_unlock_read(struct vm_area_struct *vma) +{ +} + +static inline void hugetlb_vma_lock_write(struct vm_area_struct *vma) +{ +} + +static inline void hugetlb_vma_unlock_write(struct vm_area_struct *vma) +{ +} + +static inline int hugetlb_vma_trylock_write(struct vm_area_struct *vma) +{ + return 1; +} + +static inline void hugetlb_vma_assert_locked(struct vm_area_struct *vma) +{ +} + static inline int pmd_huge(pmd_t pmd) { return 0; @@ -355,7 +406,8 @@ static inline int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, unsigned long dst_addr, unsigned long src_addr, enum mcopy_atomic_mode mode, - struct page **pagep) + struct page **pagep, + bool wp_copy) { BUG(); return 0; @@ -368,9 +420,9 @@ static inline pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, return NULL; } -static inline bool isolate_huge_page(struct page *page, struct list_head *list) +static inline int isolate_hugetlb(struct page *page, struct list_head *list) { - return false; + return -EBUSY; } static inline int get_hwpoison_huge_page(struct page *page, bool *hugetlb) @@ -378,6 +430,11 @@ static inline int get_hwpoison_huge_page(struct page *page, bool *hugetlb) return 0; } +static inline int get_huge_page_for_hwpoison(unsigned long pfn, int flags) +{ + return 0; +} + static inline void putback_active_hugepage(struct page *page) { } @@ -389,14 +446,16 @@ static inline void move_hugetlb_state(struct page *oldpage, static inline unsigned long hugetlb_change_protection( struct vm_area_struct *vma, unsigned long address, - unsigned long end, pgprot_t newprot) + unsigned long end, pgprot_t newprot, + unsigned long cp_flags) { return 0; } static inline void __unmap_hugepage_range_final(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start, - unsigned long end, struct page *ref_page) + unsigned long end, struct page *ref_page, + zap_flags_t zap_flags) { BUG(); } @@ -513,6 +572,11 @@ unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr, unsigned long flags); #endif /* HAVE_ARCH_HUGETLB_UNMAPPED_AREA */ +unsigned long +generic_hugetlb_get_unmapped_area(struct file *file, unsigned long addr, + unsigned long len, unsigned long pgoff, + unsigned long flags); + /* * huegtlb page specific state flags. These flags are located in page.private * of the hugetlb head page. Functions created via the below macros should be @@ -530,7 +594,7 @@ unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr, * Synchronization: Initially set after new page allocation with no * locking. When examined and modified during migration processing * (isolate, migrate, putback) the hugetlb_lock is held. - * HPG_temporary - - Set on a page that is temporarily allocated from the buddy + * HPG_temporary - Set on a page that is temporarily allocated from the buddy * allocator. Typically used for migration target pages when no pages * are available in the pool. The hugetlb free page path will * immediately free pages with this flag set to the buddy allocator. @@ -540,6 +604,8 @@ unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr, * HPG_freed - Set when page is on the free lists. * Synchronization: hugetlb_lock held for examination and modification. * HPG_vmemmap_optimized - Set when the vmemmap pages of the page are freed. + * HPG_raw_hwp_unreliable - Set when the hugetlb page has a hwpoison sub-page + * that is not tracked by raw_hwp_page list. */ enum hugetlb_page_flags { HPG_restore_reserve = 0, @@ -547,6 +613,7 @@ enum hugetlb_page_flags { HPG_temporary, HPG_freed, HPG_vmemmap_optimized, + HPG_raw_hwp_unreliable, __NR_HPAGEFLAGS, }; @@ -593,6 +660,7 @@ HPAGEFLAG(Migratable, migratable) HPAGEFLAG(Temporary, temporary) HPAGEFLAG(Freed, freed) HPAGEFLAG(VmemmapOptimized, vmemmap_optimized) +HPAGEFLAG(RawHwpUnreliable, raw_hwp_unreliable) #ifdef CONFIG_HUGETLB_PAGE @@ -617,13 +685,10 @@ struct hstate { unsigned int nr_huge_pages_node[MAX_NUMNODES]; unsigned int free_huge_pages_node[MAX_NUMNODES]; unsigned int surplus_huge_pages_node[MAX_NUMNODES]; -#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP - unsigned int nr_free_vmemmap_pages; -#endif #ifdef CONFIG_CGROUP_HUGETLB /* cgroup control files */ - struct cftype cgroup_files_dfl[7]; - struct cftype cgroup_files_legacy[9]; + struct cftype cgroup_files_dfl[8]; + struct cftype cgroup_files_legacy[10]; #endif char name[HSTATE_NAME_LEN]; }; @@ -640,7 +705,7 @@ struct page *alloc_huge_page_nodemask(struct hstate *h, int preferred_nid, nodemask_t *nmask, gfp_t gfp_mask); struct page *alloc_huge_page_vma(struct hstate *h, struct vm_area_struct *vma, unsigned long address); -int huge_add_to_page_cache(struct page *page, struct address_space *mapping, +int hugetlb_add_to_page_cache(struct page *page, struct address_space *mapping, pgoff_t idx); void restore_reserve_on_error(struct hstate *h, struct vm_area_struct *vma, unsigned long address, struct page *page); @@ -695,7 +760,7 @@ static inline struct hstate *hstate_vma(struct vm_area_struct *vma) return hstate_file(vma->vm_file); } -static inline unsigned long huge_page_size(struct hstate *h) +static inline unsigned long huge_page_size(const struct hstate *h) { return (unsigned long)PAGE_SIZE << h->order; } @@ -724,7 +789,7 @@ static inline bool hstate_is_gigantic(struct hstate *h) return huge_page_order(h) >= MAX_ORDER; } -static inline unsigned int pages_per_huge_page(struct hstate *h) +static inline unsigned int pages_per_huge_page(const struct hstate *h) { return 1 << h->order; } @@ -754,7 +819,7 @@ static inline void arch_clear_hugepage_flags(struct page *page) { } static inline pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, vm_flags_t flags) { - return entry; + return pte_mkhuge(entry); } #endif @@ -778,6 +843,14 @@ extern int dissolve_free_huge_page(struct page *page); extern int dissolve_free_huge_pages(unsigned long start_pfn, unsigned long end_pfn); +#ifdef CONFIG_MEMORY_FAILURE +extern void hugetlb_clear_page_hwpoison(struct page *hpage); +#else +static inline void hugetlb_clear_page_hwpoison(struct page *hpage) +{ +} +#endif + #ifdef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION #ifndef arch_hugetlb_migration_supported static inline bool arch_hugetlb_migration_supported(struct hstate *h) @@ -883,14 +956,6 @@ static inline void hugetlb_count_sub(long l, struct mm_struct *mm) atomic_long_sub(l, &mm->hugetlb_usage); } -#ifndef set_huge_swap_pte_at -static inline void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr, - pte_t *ptep, pte_t pte, unsigned long sz) -{ - set_huge_pte_at(mm, addr, ptep, pte); -} -#endif - #ifndef huge_ptep_modify_prot_start #define huge_ptep_modify_prot_start huge_ptep_modify_prot_start static inline pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma, @@ -910,6 +975,11 @@ static inline void huge_ptep_modify_prot_commit(struct vm_area_struct *vma, } #endif +#ifdef CONFIG_NUMA +void hugetlb_register_node(struct node *node); +void hugetlb_unregister_node(struct node *node); +#endif + #else /* CONFIG_HUGETLB_PAGE */ struct hstate {}; @@ -970,6 +1040,11 @@ static inline struct hstate *page_hstate(struct page *page) return NULL; } +static inline struct hstate *size_to_hstate(unsigned long size) +{ + return NULL; +} + static inline unsigned long huge_page_size(struct hstate *h) { return PAGE_SIZE; @@ -1069,17 +1144,25 @@ static inline void hugetlb_count_sub(long l, struct mm_struct *mm) { } -static inline void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr, - pte_t *ptep, pte_t pte, unsigned long sz) +static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep) { + return *ptep; } -#endif /* CONFIG_HUGETLB_PAGE */ -#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP -extern bool hugetlb_free_vmemmap_enabled; -#else -#define hugetlb_free_vmemmap_enabled false -#endif +static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t pte) +{ +} + +static inline void hugetlb_register_node(struct node *node) +{ +} + +static inline void hugetlb_unregister_node(struct node *node) +{ +} +#endif /* CONFIG_HUGETLB_PAGE */ static inline spinlock_t *huge_pte_lock(struct hstate *h, struct mm_struct *mm, pte_t *pte) @@ -1093,14 +1176,10 @@ static inline spinlock_t *huge_pte_lock(struct hstate *h, #if defined(CONFIG_HUGETLB_PAGE) && defined(CONFIG_CMA) extern void __init hugetlb_cma_reserve(int order); -extern void __init hugetlb_cma_check(void); #else static inline __init void hugetlb_cma_reserve(int order) { } -static inline __init void hugetlb_cma_check(void) -{ -} #endif bool want_pmd_share(struct vm_area_struct *vma, unsigned long addr); diff --git a/include/linux/hugetlb_cgroup.h b/include/linux/hugetlb_cgroup.h index ba025ae27882..630cd255d0cf 100644 --- a/include/linux/hugetlb_cgroup.h +++ b/include/linux/hugetlb_cgroup.h @@ -36,6 +36,11 @@ enum hugetlb_memory_event { HUGETLB_NR_MEMORY_EVENTS, }; +struct hugetlb_cgroup_per_node { + /* hugetlb usage in pages over all hstates. */ + unsigned long usage[HUGE_MAX_HSTATE]; +}; + struct hugetlb_cgroup { struct cgroup_subsys_state css; @@ -57,6 +62,8 @@ struct hugetlb_cgroup { /* Handle for "hugetlb.events.local" */ struct cgroup_file events_local_file[HUGE_MAX_HSTATE]; + + struct hugetlb_cgroup_per_node *nodeinfo[]; }; static inline struct hugetlb_cgroup * @@ -83,32 +90,31 @@ hugetlb_cgroup_from_page_rsvd(struct page *page) return __hugetlb_cgroup_from_page(page, true); } -static inline int __set_hugetlb_cgroup(struct page *page, +static inline void __set_hugetlb_cgroup(struct page *page, struct hugetlb_cgroup *h_cg, bool rsvd) { VM_BUG_ON_PAGE(!PageHuge(page), page); if (compound_order(page) < HUGETLB_CGROUP_MIN_ORDER) - return -1; + return; if (rsvd) set_page_private(page + SUBPAGE_INDEX_CGROUP_RSVD, (unsigned long)h_cg); else set_page_private(page + SUBPAGE_INDEX_CGROUP, (unsigned long)h_cg); - return 0; } -static inline int set_hugetlb_cgroup(struct page *page, +static inline void set_hugetlb_cgroup(struct page *page, struct hugetlb_cgroup *h_cg) { - return __set_hugetlb_cgroup(page, h_cg, false); + __set_hugetlb_cgroup(page, h_cg, false); } -static inline int set_hugetlb_cgroup_rsvd(struct page *page, +static inline void set_hugetlb_cgroup_rsvd(struct page *page, struct hugetlb_cgroup *h_cg) { - return __set_hugetlb_cgroup(page, h_cg, true); + __set_hugetlb_cgroup(page, h_cg, true); } static inline bool hugetlb_cgroup_disabled(void) @@ -192,16 +198,14 @@ hugetlb_cgroup_from_page_rsvd(struct page *page) return NULL; } -static inline int set_hugetlb_cgroup(struct page *page, +static inline void set_hugetlb_cgroup(struct page *page, struct hugetlb_cgroup *h_cg) { - return 0; } -static inline int set_hugetlb_cgroup_rsvd(struct page *page, +static inline void set_hugetlb_cgroup_rsvd(struct page *page, struct hugetlb_cgroup *h_cg) { - return 0; } static inline bool hugetlb_cgroup_disabled(void) diff --git a/include/linux/hw_breakpoint.h b/include/linux/hw_breakpoint.h index 78dd7035d1e5..f319bd26b030 100644 --- a/include/linux/hw_breakpoint.h +++ b/include/linux/hw_breakpoint.h @@ -74,12 +74,12 @@ register_wide_hw_breakpoint(struct perf_event_attr *attr, extern int register_perf_hw_breakpoint(struct perf_event *bp); extern void unregister_hw_breakpoint(struct perf_event *bp); extern void unregister_wide_hw_breakpoint(struct perf_event * __percpu *cpu_events); +extern bool hw_breakpoint_is_used(void); extern int dbg_reserve_bp_slot(struct perf_event *bp); extern int dbg_release_bp_slot(struct perf_event *bp); extern int reserve_bp_slot(struct perf_event *bp); extern void release_bp_slot(struct perf_event *bp); -int hw_breakpoint_weight(struct perf_event *bp); int arch_reserve_bp_slot(struct perf_event *bp); void arch_release_bp_slot(struct perf_event *bp); void arch_unregister_hw_breakpoint(struct perf_event *bp); @@ -121,6 +121,8 @@ register_perf_hw_breakpoint(struct perf_event *bp) { return -ENOSYS; } static inline void unregister_hw_breakpoint(struct perf_event *bp) { } static inline void unregister_wide_hw_breakpoint(struct perf_event * __percpu *cpu_events) { } +static inline bool hw_breakpoint_is_used(void) { return false; } + static inline int reserve_bp_slot(struct perf_event *bp) {return -ENOSYS; } static inline void release_bp_slot(struct perf_event *bp) { } diff --git a/include/linux/hw_random.h b/include/linux/hw_random.h index 8e6dd908da21..77c2885c4c13 100644 --- a/include/linux/hw_random.h +++ b/include/linux/hw_random.h @@ -50,6 +50,7 @@ struct hwrng { struct list_head list; struct kref ref; struct completion cleanup_done; + struct completion dying; }; struct device; @@ -60,7 +61,7 @@ extern int devm_hwrng_register(struct device *dev, struct hwrng *rng); /** Unregister a Hardware Random Number Generator driver. */ extern void hwrng_unregister(struct hwrng *rng); extern void devm_hwrng_unregister(struct device *dve, struct hwrng *rng); -/** Feed random bits into the pool. */ -extern void add_hwgenerator_randomness(const char *buffer, size_t count, size_t entropy); + +extern long hwrng_msleep(struct hwrng *rng, unsigned int msecs); #endif /* LINUX_HWRANDOM_H_ */ diff --git a/include/linux/hwmon.h b/include/linux/hwmon.h index fad1f1df26df..14325f93c6b2 100644 --- a/include/linux/hwmon.h +++ b/include/linux/hwmon.h @@ -332,12 +332,14 @@ enum hwmon_pwm_attributes { hwmon_pwm_enable, hwmon_pwm_mode, hwmon_pwm_freq, + hwmon_pwm_auto_channels_temp, }; #define HWMON_PWM_INPUT BIT(hwmon_pwm_input) #define HWMON_PWM_ENABLE BIT(hwmon_pwm_enable) #define HWMON_PWM_MODE BIT(hwmon_pwm_mode) #define HWMON_PWM_FREQ BIT(hwmon_pwm_freq) +#define HWMON_PWM_AUTO_CHANNELS_TEMP BIT(hwmon_pwm_auto_channels_temp) enum hwmon_intrusion_attributes { hwmon_intrusion_alarm, @@ -448,6 +450,9 @@ hwmon_device_register_with_info(struct device *dev, const struct hwmon_chip_info *info, const struct attribute_group **extra_groups); struct device * +hwmon_device_register_for_thermal(struct device *dev, const char *name, + void *drvdata); +struct device * devm_hwmon_device_register_with_info(struct device *dev, const char *name, void *drvdata, const struct hwmon_chip_info *info, @@ -459,6 +464,9 @@ void devm_hwmon_device_unregister(struct device *dev); int hwmon_notify_event(struct device *dev, enum hwmon_sensor_types type, u32 attr, int channel); +char *hwmon_sanitize_name(const char *name); +char *devm_hwmon_sanitize_name(struct device *dev, const char *name); + /** * hwmon_is_bad_char - Is the char invalid in a hwmon name * @ch: the char to be considered diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index b823311eac79..3b42264333ef 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -230,15 +230,19 @@ static inline u32 hv_get_avail_to_write_percent( * two 16 bit quantities: major_number. minor_number. * * 0 . 13 (Windows Server 2008) - * 1 . 1 (Windows 7) - * 2 . 4 (Windows 8) - * 3 . 0 (Windows 8 R2) + * 1 . 1 (Windows 7, WS2008 R2) + * 2 . 4 (Windows 8, WS2012) + * 3 . 0 (Windows 8.1, WS2012 R2) * 4 . 0 (Windows 10) * 4 . 1 (Windows 10 RS3) * 5 . 0 (Newer Windows 10) * 5 . 1 (Windows 10 RS4) * 5 . 2 (Windows Server 2019, RS5) * 5 . 3 (Windows Server 2022) + * + * The WS2008 and WIN7 versions are listed here for + * completeness but are no longer supported in the + * Linux kernel. */ #define VERSION_WS2008 ((0 << 16) | (13)) @@ -788,6 +792,7 @@ struct vmbus_requestor { #define VMBUS_NO_RQSTOR U64_MAX #define VMBUS_RQST_ERROR (U64_MAX - 1) +#define VMBUS_RQST_ADDR_ANY U64_MAX /* NetVSC-specific */ #define VMBUS_RQST_ID_NO_RESPONSE (U64_MAX - 2) /* StorVSC-specific */ @@ -1041,13 +1046,36 @@ struct vmbus_channel { u32 max_pkt_size; }; +#define lock_requestor(channel, flags) \ +do { \ + struct vmbus_requestor *rqstor = &(channel)->requestor; \ + \ + spin_lock_irqsave(&rqstor->req_lock, flags); \ +} while (0) + +static __always_inline void unlock_requestor(struct vmbus_channel *channel, + unsigned long flags) +{ + struct vmbus_requestor *rqstor = &channel->requestor; + + spin_unlock_irqrestore(&rqstor->req_lock, flags); +} + u64 vmbus_next_request_id(struct vmbus_channel *channel, u64 rqst_addr); +u64 __vmbus_request_addr_match(struct vmbus_channel *channel, u64 trans_id, + u64 rqst_addr); +u64 vmbus_request_addr_match(struct vmbus_channel *channel, u64 trans_id, + u64 rqst_addr); u64 vmbus_request_addr(struct vmbus_channel *channel, u64 trans_id); +static inline bool is_hvsock_offer(const struct vmbus_channel_offer_channel *o) +{ + return !!(o->offer.chn_flags & VMBUS_CHANNEL_TLNPI_PROVIDER_OFFER); +} + static inline bool is_hvsock_channel(const struct vmbus_channel *c) { - return !!(c->offermsg.offer.chn_flags & - VMBUS_CHANNEL_TLNPI_PROVIDER_OFFER); + return is_hvsock_offer(&c->offermsg); } static inline bool is_sub_channel(const struct vmbus_channel *c) @@ -1161,6 +1189,13 @@ extern int vmbus_open(struct vmbus_channel *channel, extern void vmbus_close(struct vmbus_channel *channel); +extern int vmbus_sendpacket_getid(struct vmbus_channel *channel, + void *buffer, + u32 bufferLen, + u64 requestid, + u64 *trans_id, + enum vmbus_packet_type type, + u32 flags); extern int vmbus_sendpacket(struct vmbus_channel *channel, void *buffer, u32 bufferLen, @@ -1257,10 +1292,16 @@ struct hv_device { u16 device_id; struct device device; - char *driver_override; /* Driver name to force a match */ + /* + * Driver name to force a match. Do not set directly, because core + * frees it. Use driver_set_override() to set or clear it. + */ + const char *driver_override; struct vmbus_channel *channel; struct kset *channels_kset; + struct device_dma_parameters dma_parms; + u64 dma_mask; /* place holder to keep track of the dir for hv device in debugfs */ struct dentry *debug_dir; @@ -1449,12 +1490,14 @@ void vmbus_free_mmio(resource_size_t start, resource_size_t size); 0x80, 0x2e, 0x27, 0xed, 0xe1, 0x9f) /* - * Linux doesn't support the 3 devices: the first two are for - * Automatic Virtual Machine Activation, and the third is for - * Remote Desktop Virtualization. + * Linux doesn't support these 4 devices: the first two are for + * Automatic Virtual Machine Activation, the third is for + * Remote Desktop Virtualization, and the fourth is Initial + * Machine Configuration (IMC) used only by Windows guests. * {f8e65716-3cb3-4a06-9a60-1889c5cccab5} * {3375baf4-9e15-4b30-b765-67acb10d607b} * {276aacf4-ac15-426c-98dd-7521ad3f01fe} + * {c376c1c3-d276-48d2-90a9-c04748072c60} */ #define HV_AVMA1_GUID \ @@ -1469,6 +1512,10 @@ void vmbus_free_mmio(resource_size_t start, resource_size_t size); .guid = GUID_INIT(0x276aacf4, 0xac15, 0x426c, 0x98, 0xdd, \ 0x75, 0x21, 0xad, 0x3f, 0x01, 0xfe) +#define HV_IMC_GUID \ + .guid = GUID_INIT(0xc376c1c3, 0xd276, 0x48d2, 0x90, 0xa9, \ + 0xc0, 0x47, 0x48, 0x07, 0x2c, 0x60) + /* * Common header for Hyper-V ICs */ @@ -1583,6 +1630,11 @@ struct hyperv_service_callback { void (*callback)(void *context); }; +struct hv_dma_range { + dma_addr_t dma; + u32 mapping_size; +}; + #define MAX_SRV_VER 0x7ffffff extern bool vmbus_prep_negotiate_resp(struct icmsg_hdr *icmsghdrp, u8 *buf, u32 buflen, const int *fw_version, int fw_vercnt, @@ -1656,56 +1708,34 @@ static inline u32 hv_pkt_datalen(const struct vmpacket_descriptor *desc) return (desc->len8 << 3) - (desc->offset8 << 3); } - -struct vmpacket_descriptor * -hv_pkt_iter_first_raw(struct vmbus_channel *channel); +/* Get packet length associated with descriptor */ +static inline u32 hv_pkt_len(const struct vmpacket_descriptor *desc) +{ + return desc->len8 << 3; +} struct vmpacket_descriptor * hv_pkt_iter_first(struct vmbus_channel *channel); struct vmpacket_descriptor * __hv_pkt_iter_next(struct vmbus_channel *channel, - const struct vmpacket_descriptor *pkt, - bool copy); + const struct vmpacket_descriptor *pkt); void hv_pkt_iter_close(struct vmbus_channel *channel); static inline struct vmpacket_descriptor * -hv_pkt_iter_next_pkt(struct vmbus_channel *channel, - const struct vmpacket_descriptor *pkt, - bool copy) +hv_pkt_iter_next(struct vmbus_channel *channel, + const struct vmpacket_descriptor *pkt) { struct vmpacket_descriptor *nxt; - nxt = __hv_pkt_iter_next(channel, pkt, copy); + nxt = __hv_pkt_iter_next(channel, pkt); if (!nxt) hv_pkt_iter_close(channel); return nxt; } -/* - * Get next packet descriptor without copying it out of the ring buffer - * If at end of list, return NULL and update host. - */ -static inline struct vmpacket_descriptor * -hv_pkt_iter_next_raw(struct vmbus_channel *channel, - const struct vmpacket_descriptor *pkt) -{ - return hv_pkt_iter_next_pkt(channel, pkt, false); -} - -/* - * Get next packet descriptor from iterator - * If at end of list, return NULL and update host. - */ -static inline struct vmpacket_descriptor * -hv_pkt_iter_next(struct vmbus_channel *channel, - const struct vmpacket_descriptor *pkt) -{ - return hv_pkt_iter_next_pkt(channel, pkt, true); -} - #define foreach_vmbus_pkt(pkt, channel) \ for (pkt = hv_pkt_iter_first(channel); pkt; \ pkt = hv_pkt_iter_next(channel, pkt)) diff --git a/include/linux/hypervisor.h b/include/linux/hypervisor.h index fc08b433c856..9efbc54e35e5 100644 --- a/include/linux/hypervisor.h +++ b/include/linux/hypervisor.h @@ -32,4 +32,12 @@ static inline bool jailhouse_paravirt(void) #endif /* !CONFIG_X86 */ +static inline bool hypervisor_isolated_pci_functions(void) +{ + if (IS_ENABLED(CONFIG_S390)) + return true; + + return jailhouse_paravirt(); +} + #endif /* __LINUX_HYPEVISOR_H */ diff --git a/include/linux/i2c-smbus.h b/include/linux/i2c-smbus.h index 1ef421818d3a..ced1c6ead52a 100644 --- a/include/linux/i2c-smbus.h +++ b/include/linux/i2c-smbus.h @@ -30,14 +30,6 @@ struct i2c_client *i2c_new_smbus_alert_device(struct i2c_adapter *adapter, struct i2c_smbus_alert_setup *setup); int i2c_handle_smbus_alert(struct i2c_client *ara); -#if IS_ENABLED(CONFIG_I2C_SMBUS) && IS_ENABLED(CONFIG_OF) -int of_i2c_setup_smbus_alert(struct i2c_adapter *adap); -#else -static inline int of_i2c_setup_smbus_alert(struct i2c_adapter *adap) -{ - return 0; -} -#endif #if IS_ENABLED(CONFIG_I2C_SMBUS) && IS_ENABLED(CONFIG_I2C_SLAVE) struct i2c_client *i2c_new_slave_host_notify_device(struct i2c_adapter *adapter); void i2c_free_slave_host_notify_device(struct i2c_client *client); diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 7d4f52ceb7b5..f7c49bbdb8a1 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -273,7 +273,7 @@ struct i2c_driver { /* Standard driver model interfaces */ int (*probe)(struct i2c_client *client, const struct i2c_device_id *id); - int (*remove)(struct i2c_client *client); + void (*remove)(struct i2c_client *client); /* New driver model interface to aid the seamless removal of the * current probe()'s, more commonly unused than used second parameter. @@ -392,12 +392,8 @@ enum i2c_slave_event { int i2c_slave_register(struct i2c_client *client, i2c_slave_cb_t slave_cb); int i2c_slave_unregister(struct i2c_client *client); bool i2c_detect_slave_mode(struct device *dev); - -static inline int i2c_slave_event(struct i2c_client *client, - enum i2c_slave_event event, u8 *val) -{ - return client->slave_cb(client, event, val); -} +int i2c_slave_event(struct i2c_client *client, + enum i2c_slave_event event, u8 *val); #else static inline bool i2c_detect_slave_mode(struct device *dev) { return false; } #endif @@ -541,7 +537,8 @@ i2c_register_board_info(int busnum, struct i2c_board_info const *info, * * The return codes from the ``master_xfer{_atomic}`` fields should indicate the * type of error code that occurred during the transfer, as documented in the - * Kernel Documentation file Documentation/i2c/fault-codes.rst. + * Kernel Documentation file Documentation/i2c/fault-codes.rst. Otherwise, the + * number of messages executed should be returned. */ struct i2c_algorithm { /* diff --git a/include/linux/i3c/ccc.h b/include/linux/i3c/ccc.h index 73b0982cc519..ad59a4ae60d1 100644 --- a/include/linux/i3c/ccc.h +++ b/include/linux/i3c/ccc.h @@ -132,7 +132,7 @@ struct i3c_ccc_dev_desc { struct i3c_ccc_defslvs { u8 count; struct i3c_ccc_dev_desc master; - struct i3c_ccc_dev_desc slaves[0]; + struct i3c_ccc_dev_desc slaves[]; } __packed; /** @@ -240,7 +240,7 @@ struct i3c_ccc_bridged_slave_desc { */ struct i3c_ccc_setbrgtgt { u8 count; - struct i3c_ccc_bridged_slave_desc bslaves[0]; + struct i3c_ccc_bridged_slave_desc bslaves[]; } __packed; /** @@ -318,7 +318,7 @@ enum i3c_ccc_setxtime_subcmd { */ struct i3c_ccc_setxtime { u8 subcmd; - u8 data[0]; + u8 data[]; } __packed; #define I3C_CCC_GETXTIME_SYNC_MODE BIT(0) diff --git a/include/linux/i3c/master.h b/include/linux/i3c/master.h index 9cb39d901cd5..604a126b78c8 100644 --- a/include/linux/i3c/master.h +++ b/include/linux/i3c/master.h @@ -85,7 +85,6 @@ struct i2c_dev_boardinfo { */ struct i2c_dev_desc { struct i3c_i2c_dev_desc common; - const struct i2c_dev_boardinfo *boardinfo; struct i2c_client *dev; u16 addr; u8 lvr; diff --git a/include/linux/icmpv6.h b/include/linux/icmpv6.h index 9055cb380ee2..db0f4fcfdaf4 100644 --- a/include/linux/icmpv6.h +++ b/include/linux/icmpv6.h @@ -79,8 +79,9 @@ extern int icmpv6_init(void); extern int icmpv6_err_convert(u8 type, u8 code, int *err); extern void icmpv6_cleanup(void); -extern void icmpv6_param_prob(struct sk_buff *skb, - u8 code, int pos); +extern void icmpv6_param_prob_reason(struct sk_buff *skb, + u8 code, int pos, + enum skb_drop_reason reason); struct flowi6; struct in6_addr; @@ -91,6 +92,12 @@ extern void icmpv6_flow_init(struct sock *sk, const struct in6_addr *daddr, int oif); +static inline void icmpv6_param_prob(struct sk_buff *skb, u8 code, int pos) +{ + icmpv6_param_prob_reason(skb, code, pos, + SKB_DROP_REASON_NOT_SPECIFIED); +} + static inline bool icmpv6_is_err(int type) { switch (type) { diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 559b6c644938..79690938d9a2 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -9,7 +9,7 @@ * Copyright (c) 2006, Michael Wu <flamingice@sourmilk.net> * Copyright (c) 2013 - 2014 Intel Mobile Communications GmbH * Copyright (c) 2016 - 2017 Intel Deutschland GmbH - * Copyright (c) 2018 - 2021 Intel Corporation + * Copyright (c) 2018 - 2022 Intel Corporation */ #ifndef LINUX_IEEE80211_H @@ -18,6 +18,7 @@ #include <linux/types.h> #include <linux/if_ether.h> #include <linux/etherdevice.h> +#include <linux/bitfield.h> #include <asm/byteorder.h> #include <asm/unaligned.h> @@ -75,6 +76,7 @@ #define IEEE80211_STYPE_ACTION 0x00D0 /* control */ +#define IEEE80211_STYPE_TRIGGER 0x0020 #define IEEE80211_STYPE_CTL_EXT 0x0060 #define IEEE80211_STYPE_BACK_REQ 0x0080 #define IEEE80211_STYPE_BACK 0x0090 @@ -294,12 +296,25 @@ static inline u16 ieee80211_sn_sub(u16 sn1, u16 sn2) #define IEEE80211_HT_CTL_LEN 4 +/* trigger type within common_info of trigger frame */ +#define IEEE80211_TRIGGER_TYPE_MASK 0xf +#define IEEE80211_TRIGGER_TYPE_BASIC 0x0 +#define IEEE80211_TRIGGER_TYPE_BFRP 0x1 +#define IEEE80211_TRIGGER_TYPE_MU_BAR 0x2 +#define IEEE80211_TRIGGER_TYPE_MU_RTS 0x3 +#define IEEE80211_TRIGGER_TYPE_BSRP 0x4 +#define IEEE80211_TRIGGER_TYPE_GCR_MU_BAR 0x5 +#define IEEE80211_TRIGGER_TYPE_BQRP 0x6 +#define IEEE80211_TRIGGER_TYPE_NFRP 0x7 + struct ieee80211_hdr { __le16 frame_control; __le16 duration_id; - u8 addr1[ETH_ALEN]; - u8 addr2[ETH_ALEN]; - u8 addr3[ETH_ALEN]; + struct_group(addrs, + u8 addr1[ETH_ALEN]; + u8 addr2[ETH_ALEN]; + u8 addr3[ETH_ALEN]; + ); __le16 seq_ctrl; u8 addr4[ETH_ALEN]; } __packed __aligned(2); @@ -323,6 +338,15 @@ struct ieee80211_qos_hdr { __le16 qos_ctrl; } __packed __aligned(2); +struct ieee80211_trigger { + __le16 frame_control; + __le16 duration; + u8 ra[ETH_ALEN]; + u8 ta[ETH_ALEN]; + __le64 common_info; + u8 variable[]; +} __packed __aligned(2); + /** * ieee80211_has_tods - check if IEEE80211_FCTL_TODS is set * @fc: frame control bytes in little-endian byteorder @@ -729,6 +753,16 @@ static inline bool ieee80211_is_qos_nullfunc(__le16 fc) } /** + * ieee80211_is_trigger - check if frame is trigger frame + * @fc: frame control field in little-endian byteorder + */ +static inline bool ieee80211_is_trigger(__le16 fc) +{ + return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == + cpu_to_le16(IEEE80211_FTYPE_CTL | IEEE80211_STYPE_TRIGGER); +} + +/** * ieee80211_is_any_nullfunc - check if frame is regular or QoS nullfunc frame * @fc: frame control bytes in little-endian byteorder */ @@ -1023,6 +1057,8 @@ struct ieee80211_tpc_report_ie { #define IEEE80211_ADDBA_EXT_FRAG_LEVEL_MASK GENMASK(2, 1) #define IEEE80211_ADDBA_EXT_FRAG_LEVEL_SHIFT 1 #define IEEE80211_ADDBA_EXT_NO_FRAG BIT(0) +#define IEEE80211_ADDBA_EXT_BUF_SIZE_MASK GENMASK(7, 5) +#define IEEE80211_ADDBA_EXT_BUF_SIZE_SHIFT 10 struct ieee80211_addba_ext_ie { u8 data; @@ -1298,6 +1334,15 @@ struct ieee80211_mgmt { u8 action_code; u8 variable[]; } __packed s1g; + struct { + u8 action_code; + u8 dialog_token; + u8 follow_up; + u32 tod; + u32 toa; + u8 max_tod_error; + u8 max_toa_error; + } __packed wnm_timing_msr; } u; } __packed action; } u; @@ -1697,10 +1742,12 @@ struct ieee80211_ht_operation { * A-MPDU buffer sizes * According to HT size varies from 8 to 64 frames * HE adds the ability to have up to 256 frames. + * EHT adds the ability to have up to 1K frames. */ #define IEEE80211_MIN_AMPDU_BUF 0x8 #define IEEE80211_MAX_AMPDU_BUF_HT 0x40 -#define IEEE80211_MAX_AMPDU_BUF 0x100 +#define IEEE80211_MAX_AMPDU_BUF_HE 0x100 +#define IEEE80211_MAX_AMPDU_BUF_EHT 0x400 /* Spatial Multiplexing Power Save Modes (for capability) */ @@ -1925,6 +1972,131 @@ struct ieee80211_mu_edca_param_set { struct ieee80211_he_mu_edca_param_ac_rec ac_vo; } __packed; +#define IEEE80211_EHT_MCS_NSS_RX 0x0f +#define IEEE80211_EHT_MCS_NSS_TX 0xf0 + +/** + * struct ieee80211_eht_mcs_nss_supp_20mhz_only - EHT 20MHz only station max + * supported NSS for per MCS. + * + * For each field below, bits 0 - 3 indicate the maximal number of spatial + * streams for Rx, and bits 4 - 7 indicate the maximal number of spatial streams + * for Tx. + * + * @rx_tx_mcs7_max_nss: indicates the maximum number of spatial streams + * supported for reception and the maximum number of spatial streams + * supported for transmission for MCS 0 - 7. + * @rx_tx_mcs9_max_nss: indicates the maximum number of spatial streams + * supported for reception and the maximum number of spatial streams + * supported for transmission for MCS 8 - 9. + * @rx_tx_mcs11_max_nss: indicates the maximum number of spatial streams + * supported for reception and the maximum number of spatial streams + * supported for transmission for MCS 10 - 11. + * @rx_tx_mcs13_max_nss: indicates the maximum number of spatial streams + * supported for reception and the maximum number of spatial streams + * supported for transmission for MCS 12 - 13. + */ +struct ieee80211_eht_mcs_nss_supp_20mhz_only { + u8 rx_tx_mcs7_max_nss; + u8 rx_tx_mcs9_max_nss; + u8 rx_tx_mcs11_max_nss; + u8 rx_tx_mcs13_max_nss; +}; + +/** + * struct ieee80211_eht_mcs_nss_supp_bw - EHT max supported NSS per MCS (except + * 20MHz only stations). + * + * For each field below, bits 0 - 3 indicate the maximal number of spatial + * streams for Rx, and bits 4 - 7 indicate the maximal number of spatial streams + * for Tx. + * + * @rx_tx_mcs9_max_nss: indicates the maximum number of spatial streams + * supported for reception and the maximum number of spatial streams + * supported for transmission for MCS 0 - 9. + * @rx_tx_mcs11_max_nss: indicates the maximum number of spatial streams + * supported for reception and the maximum number of spatial streams + * supported for transmission for MCS 10 - 11. + * @rx_tx_mcs13_max_nss: indicates the maximum number of spatial streams + * supported for reception and the maximum number of spatial streams + * supported for transmission for MCS 12 - 13. + */ +struct ieee80211_eht_mcs_nss_supp_bw { + u8 rx_tx_mcs9_max_nss; + u8 rx_tx_mcs11_max_nss; + u8 rx_tx_mcs13_max_nss; +}; + +/** + * struct ieee80211_eht_cap_elem_fixed - EHT capabilities fixed data + * + * This structure is the "EHT Capabilities element" fixed fields as + * described in P802.11be_D2.0 section 9.4.2.313. + * + * @mac_cap_info: MAC capabilities, see IEEE80211_EHT_MAC_CAP* + * @phy_cap_info: PHY capabilities, see IEEE80211_EHT_PHY_CAP* + */ +struct ieee80211_eht_cap_elem_fixed { + u8 mac_cap_info[2]; + u8 phy_cap_info[9]; +} __packed; + +/** + * struct ieee80211_eht_cap_elem - EHT capabilities element + * @fixed: fixed parts, see &ieee80211_eht_cap_elem_fixed + * @optional: optional parts + */ +struct ieee80211_eht_cap_elem { + struct ieee80211_eht_cap_elem_fixed fixed; + + /* + * Followed by: + * Supported EHT-MCS And NSS Set field: 4, 3, 6 or 9 octets. + * EHT PPE Thresholds field: variable length. + */ + u8 optional[]; +} __packed; + +#define IEEE80211_EHT_OPER_INFO_PRESENT 0x01 +#define IEEE80211_EHT_OPER_DISABLED_SUBCHANNEL_BITMAP_PRESENT 0x02 +#define IEEE80211_EHT_OPER_EHT_DEF_PE_DURATION 0x04 +#define IEEE80211_EHT_OPER_GROUP_ADDRESSED_BU_IND_LIMIT 0x08 +#define IEEE80211_EHT_OPER_GROUP_ADDRESSED_BU_IND_EXP_MASK 0x30 + +/** + * struct ieee80211_eht_operation - eht operation element + * + * This structure is the "EHT Operation Element" fields as + * described in P802.11be_D2.0 section 9.4.2.311 + * + * @params: EHT operation element parameters. See &IEEE80211_EHT_OPER_* + * @basic_mcs_nss: indicates the EHT-MCSs for each number of spatial streams in + * EHT PPDUs that are supported by all EHT STAs in the BSS in transmit and + * receive. + * @optional: optional parts + */ +struct ieee80211_eht_operation { + u8 params; + __le32 basic_mcs_nss; + u8 optional[]; +} __packed; + +/** + * struct ieee80211_eht_operation_info - eht operation information + * + * @control: EHT operation information control. + * @ccfs0: defines a channel center frequency for a 20, 40, 80, 160, or 320 MHz + * EHT BSS. + * @ccfs1: defines a channel center frequency for a 160 or 320 MHz EHT BSS. + * @optional: optional parts + */ +struct ieee80211_eht_operation_info { + u8 control; + u8 ccfs0; + u8 ccfs1; + u8 optional[]; +} __packed; + /* 802.11ac VHT Capabilities */ #define IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_3895 0x00000000 #define IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_7991 0x00000001 @@ -2129,6 +2301,8 @@ enum ieee80211_client_reg_power { #define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G 0x04 #define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G 0x08 #define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_80PLUS80_MHZ_IN_5G 0x10 +#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_MASK_ALL 0x1e + #define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_RU_MAPPING_IN_2G 0x20 #define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_RU_MAPPING_IN_5G 0x40 #define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_MASK 0xfe @@ -2309,6 +2483,7 @@ ieee80211_he_mcs_nss_size(const struct ieee80211_he_cap_elem *he_cap) #define IEEE80211_PPE_THRES_RU_INDEX_BITMASK_MASK 0x78 #define IEEE80211_PPE_THRES_RU_INDEX_BITMASK_POS (3) #define IEEE80211_PPE_THRES_INFO_PPET_SIZE (3) +#define IEEE80211_HE_PPE_THRES_INFO_HEADER_SIZE (7) /* * Calculate 802.11ax HE capabilities IE PPE field size @@ -2338,6 +2513,29 @@ ieee80211_he_ppe_size(u8 ppe_thres_hdr, const u8 *phy_cap_info) return n; } +static inline bool ieee80211_he_capa_size_ok(const u8 *data, u8 len) +{ + const struct ieee80211_he_cap_elem *he_cap_ie_elem = (const void *)data; + u8 needed = sizeof(*he_cap_ie_elem); + + if (len < needed) + return false; + + needed += ieee80211_he_mcs_nss_size(he_cap_ie_elem); + if (len < needed) + return false; + + if (he_cap_ie_elem->phy_cap_info[6] & + IEEE80211_HE_PHY_CAP6_PPE_THRESHOLD_PRESENT) { + if (len < needed + 1) + return false; + needed += ieee80211_he_ppe_size(data[needed], + he_cap_ie_elem->phy_cap_info); + } + + return len >= needed; +} + /* HE Operation defines */ #define IEEE80211_HE_OPERATION_DFLT_PE_DURATION_MASK 0x00000007 #define IEEE80211_HE_OPERATION_TWT_REQUIRED 0x00000008 @@ -2427,7 +2625,7 @@ struct ieee80211_tx_pwr_env { static inline u8 ieee80211_he_oper_size(const u8 *he_oper_ie) { - struct ieee80211_he_operation *he_oper = (void *)he_oper_ie; + const struct ieee80211_he_operation *he_oper = (const void *)he_oper_ie; u8 oper_len = sizeof(struct ieee80211_he_operation); u32 he_oper_params; @@ -2460,7 +2658,7 @@ ieee80211_he_oper_size(const u8 *he_oper_ie) static inline const struct ieee80211_he_6ghz_oper * ieee80211_he_6ghz_oper(const struct ieee80211_he_operation *he_oper) { - const u8 *ret = (void *)&he_oper->optional; + const u8 *ret = (const void *)&he_oper->optional; u32 he_oper_params; if (!he_oper) @@ -2475,7 +2673,7 @@ ieee80211_he_6ghz_oper(const struct ieee80211_he_operation *he_oper) if (he_oper_params & IEEE80211_HE_OPERATION_CO_HOSTED_BSS) ret++; - return (void *)ret; + return (const void *)ret; } /* HE Spatial Reuse defines */ @@ -2496,7 +2694,7 @@ ieee80211_he_6ghz_oper(const struct ieee80211_he_operation *he_oper) static inline u8 ieee80211_he_spr_size(const u8 *he_spr_ie) { - struct ieee80211_he_spr *he_spr = (void *)he_spr_ie; + const struct ieee80211_he_spr *he_spr = (const void *)he_spr_ie; u8 spr_len = sizeof(struct ieee80211_he_spr); u8 he_spr_params; @@ -2599,6 +2797,207 @@ ieee80211_he_spr_size(const u8 *he_spr_ie) #define S1G_OPER_CH_WIDTH_PRIMARY_1MHZ BIT(0) #define S1G_OPER_CH_WIDTH_OPER GENMASK(4, 1) +/* EHT MAC capabilities as defined in P802.11be_D2.0 section 9.4.2.313.2 */ +#define IEEE80211_EHT_MAC_CAP0_EPCS_PRIO_ACCESS 0x01 +#define IEEE80211_EHT_MAC_CAP0_OM_CONTROL 0x02 +#define IEEE80211_EHT_MAC_CAP0_TRIG_TXOP_SHARING_MODE1 0x04 +#define IEEE80211_EHT_MAC_CAP0_TRIG_TXOP_SHARING_MODE2 0x08 +#define IEEE80211_EHT_MAC_CAP0_RESTRICTED_TWT 0x10 +#define IEEE80211_EHT_MAC_CAP0_SCS_TRAFFIC_DESC 0x20 +#define IEEE80211_EHT_MAC_CAP0_MAX_MPDU_LEN_MASK 0xc0 +#define IEEE80211_EHT_MAC_CAP0_MAX_MPDU_LEN_3895 0 +#define IEEE80211_EHT_MAC_CAP0_MAX_MPDU_LEN_7991 1 +#define IEEE80211_EHT_MAC_CAP0_MAX_MPDU_LEN_11454 2 + +#define IEEE80211_EHT_MAC_CAP1_MAX_AMPDU_LEN_MASK 0x01 + +/* EHT PHY capabilities as defined in P802.11be_D2.0 section 9.4.2.313.3 */ +#define IEEE80211_EHT_PHY_CAP0_320MHZ_IN_6GHZ 0x02 +#define IEEE80211_EHT_PHY_CAP0_242_TONE_RU_GT20MHZ 0x04 +#define IEEE80211_EHT_PHY_CAP0_NDP_4_EHT_LFT_32_GI 0x08 +#define IEEE80211_EHT_PHY_CAP0_PARTIAL_BW_UL_MU_MIMO 0x10 +#define IEEE80211_EHT_PHY_CAP0_SU_BEAMFORMER 0x20 +#define IEEE80211_EHT_PHY_CAP0_SU_BEAMFORMEE 0x40 + +/* EHT beamformee number of spatial streams <= 80MHz is split */ +#define IEEE80211_EHT_PHY_CAP0_BEAMFORMEE_SS_80MHZ_MASK 0x80 +#define IEEE80211_EHT_PHY_CAP1_BEAMFORMEE_SS_80MHZ_MASK 0x03 + +#define IEEE80211_EHT_PHY_CAP1_BEAMFORMEE_SS_160MHZ_MASK 0x1c +#define IEEE80211_EHT_PHY_CAP1_BEAMFORMEE_SS_320MHZ_MASK 0xe0 + +#define IEEE80211_EHT_PHY_CAP2_SOUNDING_DIM_80MHZ_MASK 0x07 +#define IEEE80211_EHT_PHY_CAP2_SOUNDING_DIM_160MHZ_MASK 0x38 + +/* EHT number of sounding dimensions for 320MHz is split */ +#define IEEE80211_EHT_PHY_CAP2_SOUNDING_DIM_320MHZ_MASK 0xc0 +#define IEEE80211_EHT_PHY_CAP3_SOUNDING_DIM_320MHZ_MASK 0x01 +#define IEEE80211_EHT_PHY_CAP3_NG_16_SU_FEEDBACK 0x02 +#define IEEE80211_EHT_PHY_CAP3_NG_16_MU_FEEDBACK 0x04 +#define IEEE80211_EHT_PHY_CAP3_CODEBOOK_4_2_SU_FDBK 0x08 +#define IEEE80211_EHT_PHY_CAP3_CODEBOOK_7_5_MU_FDBK 0x10 +#define IEEE80211_EHT_PHY_CAP3_TRIG_SU_BF_FDBK 0x20 +#define IEEE80211_EHT_PHY_CAP3_TRIG_MU_BF_PART_BW_FDBK 0x40 +#define IEEE80211_EHT_PHY_CAP3_TRIG_CQI_FDBK 0x80 + +#define IEEE80211_EHT_PHY_CAP4_PART_BW_DL_MU_MIMO 0x01 +#define IEEE80211_EHT_PHY_CAP4_PSR_SR_SUPP 0x02 +#define IEEE80211_EHT_PHY_CAP4_POWER_BOOST_FACT_SUPP 0x04 +#define IEEE80211_EHT_PHY_CAP4_EHT_MU_PPDU_4_EHT_LTF_08_GI 0x08 +#define IEEE80211_EHT_PHY_CAP4_MAX_NC_MASK 0xf0 + +#define IEEE80211_EHT_PHY_CAP5_NON_TRIG_CQI_FEEDBACK 0x01 +#define IEEE80211_EHT_PHY_CAP5_TX_LESS_242_TONE_RU_SUPP 0x02 +#define IEEE80211_EHT_PHY_CAP5_RX_LESS_242_TONE_RU_SUPP 0x04 +#define IEEE80211_EHT_PHY_CAP5_PPE_THRESHOLD_PRESENT 0x08 +#define IEEE80211_EHT_PHY_CAP5_COMMON_NOMINAL_PKT_PAD_MASK 0x30 +#define IEEE80211_EHT_PHY_CAP5_COMMON_NOMINAL_PKT_PAD_0US 0 +#define IEEE80211_EHT_PHY_CAP5_COMMON_NOMINAL_PKT_PAD_8US 1 +#define IEEE80211_EHT_PHY_CAP5_COMMON_NOMINAL_PKT_PAD_16US 2 +#define IEEE80211_EHT_PHY_CAP5_COMMON_NOMINAL_PKT_PAD_20US 3 + +/* Maximum number of supported EHT LTF is split */ +#define IEEE80211_EHT_PHY_CAP5_MAX_NUM_SUPP_EHT_LTF_MASK 0xc0 +#define IEEE80211_EHT_PHY_CAP6_MAX_NUM_SUPP_EHT_LTF_MASK 0x07 + +#define IEEE80211_EHT_PHY_CAP6_MCS15_SUPP_MASK 0x78 +#define IEEE80211_EHT_PHY_CAP6_EHT_DUP_6GHZ_SUPP 0x80 + +#define IEEE80211_EHT_PHY_CAP7_20MHZ_STA_RX_NDP_WIDER_BW 0x01 +#define IEEE80211_EHT_PHY_CAP7_NON_OFDMA_UL_MU_MIMO_80MHZ 0x02 +#define IEEE80211_EHT_PHY_CAP7_NON_OFDMA_UL_MU_MIMO_160MHZ 0x04 +#define IEEE80211_EHT_PHY_CAP7_NON_OFDMA_UL_MU_MIMO_320MHZ 0x08 +#define IEEE80211_EHT_PHY_CAP7_MU_BEAMFORMER_80MHZ 0x10 +#define IEEE80211_EHT_PHY_CAP7_MU_BEAMFORMER_160MHZ 0x20 +#define IEEE80211_EHT_PHY_CAP7_MU_BEAMFORMER_320MHZ 0x40 +#define IEEE80211_EHT_PHY_CAP7_TB_SOUNDING_FDBK_RATE_LIMIT 0x80 + +#define IEEE80211_EHT_PHY_CAP8_RX_1024QAM_WIDER_BW_DL_OFDMA 0x01 +#define IEEE80211_EHT_PHY_CAP8_RX_4096QAM_WIDER_BW_DL_OFDMA 0x02 + +/* + * EHT operation channel width as defined in P802.11be_D2.0 section 9.4.2.311 + */ +#define IEEE80211_EHT_OPER_CHAN_WIDTH 0x7 +#define IEEE80211_EHT_OPER_CHAN_WIDTH_20MHZ 0 +#define IEEE80211_EHT_OPER_CHAN_WIDTH_40MHZ 1 +#define IEEE80211_EHT_OPER_CHAN_WIDTH_80MHZ 2 +#define IEEE80211_EHT_OPER_CHAN_WIDTH_160MHZ 3 +#define IEEE80211_EHT_OPER_CHAN_WIDTH_320MHZ 4 + +/* Calculate 802.11be EHT capabilities IE Tx/Rx EHT MCS NSS Support Field size */ +static inline u8 +ieee80211_eht_mcs_nss_size(const struct ieee80211_he_cap_elem *he_cap, + const struct ieee80211_eht_cap_elem_fixed *eht_cap, + bool from_ap) +{ + u8 count = 0; + + /* on 2.4 GHz, if it supports 40 MHz, the result is 3 */ + if (he_cap->phy_cap_info[0] & + IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_IN_2G) + return 3; + + /* on 2.4 GHz, these three bits are reserved, so should be 0 */ + if (he_cap->phy_cap_info[0] & + IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G) + count += 3; + + if (he_cap->phy_cap_info[0] & + IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G) + count += 3; + + if (eht_cap->phy_cap_info[0] & IEEE80211_EHT_PHY_CAP0_320MHZ_IN_6GHZ) + count += 3; + + if (count) + return count; + + return from_ap ? 3 : 4; +} + +/* 802.11be EHT PPE Thresholds */ +#define IEEE80211_EHT_PPE_THRES_NSS_POS 0 +#define IEEE80211_EHT_PPE_THRES_NSS_MASK 0xf +#define IEEE80211_EHT_PPE_THRES_RU_INDEX_BITMASK_MASK 0x1f0 +#define IEEE80211_EHT_PPE_THRES_INFO_PPET_SIZE 3 +#define IEEE80211_EHT_PPE_THRES_INFO_HEADER_SIZE 9 + +/* + * Calculate 802.11be EHT capabilities IE EHT field size + */ +static inline u8 +ieee80211_eht_ppe_size(u16 ppe_thres_hdr, const u8 *phy_cap_info) +{ + u32 n; + + if (!(phy_cap_info[5] & + IEEE80211_EHT_PHY_CAP5_PPE_THRESHOLD_PRESENT)) + return 0; + + n = hweight16(ppe_thres_hdr & + IEEE80211_EHT_PPE_THRES_RU_INDEX_BITMASK_MASK); + n *= 1 + u16_get_bits(ppe_thres_hdr, IEEE80211_EHT_PPE_THRES_NSS_MASK); + + /* + * Each pair is 6 bits, and we need to add the 9 "header" bits to the + * total size. + */ + n = n * IEEE80211_EHT_PPE_THRES_INFO_PPET_SIZE * 2 + + IEEE80211_EHT_PPE_THRES_INFO_HEADER_SIZE; + return DIV_ROUND_UP(n, 8); +} + +static inline bool +ieee80211_eht_capa_size_ok(const u8 *he_capa, const u8 *data, u8 len, + bool from_ap) +{ + const struct ieee80211_eht_cap_elem_fixed *elem = (const void *)data; + u8 needed = sizeof(struct ieee80211_eht_cap_elem_fixed); + + if (len < needed || !he_capa) + return false; + + needed += ieee80211_eht_mcs_nss_size((const void *)he_capa, + (const void *)data, + from_ap); + if (len < needed) + return false; + + if (elem->phy_cap_info[5] & + IEEE80211_EHT_PHY_CAP5_PPE_THRESHOLD_PRESENT) { + u16 ppe_thres_hdr; + + if (len < needed + sizeof(ppe_thres_hdr)) + return false; + + ppe_thres_hdr = get_unaligned_le16(data + needed); + needed += ieee80211_eht_ppe_size(ppe_thres_hdr, + elem->phy_cap_info); + } + + return len >= needed; +} + +static inline bool +ieee80211_eht_oper_size_ok(const u8 *data, u8 len) +{ + const struct ieee80211_eht_operation *elem = (const void *)data; + u8 needed = sizeof(*elem); + + if (len < needed) + return false; + + if (elem->params & IEEE80211_EHT_OPER_INFO_PRESENT) { + needed += 3; + + if (elem->params & + IEEE80211_EHT_OPER_DISABLED_SUBCHANNEL_BITMAP_PRESENT) + needed += 2; + } + + return len >= needed; +} #define LISTEN_INT_USF GENMASK(15, 14) #define LISTEN_INT_UI GENMASK(13, 0) @@ -3054,6 +3453,9 @@ enum ieee80211_eid_ext { WLAN_EID_EXT_SHORT_SSID_LIST = 58, WLAN_EID_EXT_HE_6GHZ_CAPA = 59, WLAN_EID_EXT_UL_MU_POWER_CAPA = 60, + WLAN_EID_EXT_EHT_OPERATION = 106, + WLAN_EID_EXT_EHT_MULTI_LINK = 107, + WLAN_EID_EXT_EHT_CAPABILITY = 108, }; /* Action category code */ @@ -3137,6 +3539,17 @@ enum ieee80211_mesh_actioncode { WLAN_MESH_ACTION_TBTT_ADJUSTMENT_RESPONSE, }; +/* Unprotected WNM action codes */ +enum ieee80211_unprotected_wnm_actioncode { + WLAN_UNPROTECTED_WNM_ACTION_TIM = 0, + WLAN_UNPROTECTED_WNM_ACTION_TIMING_MEASUREMENT_RESPONSE = 1, +}; + +/* Public action codes */ +enum ieee80211_public_actioncode { + WLAN_PUBLIC_ACTION_FTM_RESPONSE = 33, +}; + /* Security key length */ enum ieee80211_key_len { WLAN_KEY_LEN_WEP40 = 5, @@ -3736,6 +4149,7 @@ static inline bool _ieee80211_is_robust_mgmt_frame(struct ieee80211_hdr *hdr) *category != WLAN_CATEGORY_SELF_PROTECTED && *category != WLAN_CATEGORY_UNPROT_DMG && *category != WLAN_CATEGORY_VHT && + *category != WLAN_CATEGORY_S1G && *category != WLAN_CATEGORY_VENDOR_SPECIFIC; } @@ -3925,6 +4339,40 @@ static inline bool ieee80211_action_contains_tpc(struct sk_buff *skb) return true; } +static inline bool ieee80211_is_timing_measurement(struct sk_buff *skb) +{ + struct ieee80211_mgmt *mgmt = (void *)skb->data; + + if (skb->len < IEEE80211_MIN_ACTION_SIZE) + return false; + + if (!ieee80211_is_action(mgmt->frame_control)) + return false; + + if (mgmt->u.action.category == WLAN_CATEGORY_WNM_UNPROTECTED && + mgmt->u.action.u.wnm_timing_msr.action_code == + WLAN_UNPROTECTED_WNM_ACTION_TIMING_MEASUREMENT_RESPONSE && + skb->len >= offsetofend(typeof(*mgmt), u.action.u.wnm_timing_msr)) + return true; + + return false; +} + +static inline bool ieee80211_is_ftm(struct sk_buff *skb) +{ + struct ieee80211_mgmt *mgmt = (void *)skb->data; + + if (!ieee80211_is_public_action((void *)mgmt, skb->len)) + return false; + + if (mgmt->u.action.u.ftm.action_code == + WLAN_PUBLIC_ACTION_FTM_RESPONSE && + skb->len >= offsetofend(typeof(*mgmt), u.action.u.ftm)) + return true; + + return false; +} + struct element { u8 id; u8 datalen; @@ -4005,10 +4453,10 @@ static inline bool for_each_element_completed(const struct element *element, #define IEEE80211_RNR_TBTT_PARAMS_COLOC_AP 0x40 struct ieee80211_neighbor_ap_info { - u8 tbtt_info_hdr; - u8 tbtt_info_len; - u8 op_class; - u8 channel; + u8 tbtt_info_hdr; + u8 tbtt_info_len; + u8 op_class; + u8 channel; } __packed; enum ieee80211_range_params_max_total_ltf { @@ -4018,4 +4466,229 @@ enum ieee80211_range_params_max_total_ltf { IEEE80211_RANGE_PARAMS_MAX_TOTAL_LTF_UNSPECIFIED, }; +/* multi-link device */ +#define IEEE80211_MLD_MAX_NUM_LINKS 15 + +#define IEEE80211_ML_CONTROL_TYPE 0x0007 +#define IEEE80211_ML_CONTROL_TYPE_BASIC 0 +#define IEEE80211_ML_CONTROL_TYPE_PREQ 1 +#define IEEE80211_ML_CONTROL_TYPE_RECONF 2 +#define IEEE80211_ML_CONTROL_TYPE_TDLS 3 +#define IEEE80211_ML_CONTROL_TYPE_PRIO_ACCESS 4 +#define IEEE80211_ML_CONTROL_PRESENCE_MASK 0xfff0 + +struct ieee80211_multi_link_elem { + __le16 control; + u8 variable[]; +} __packed; + +#define IEEE80211_MLC_BASIC_PRES_LINK_ID 0x0010 +#define IEEE80211_MLC_BASIC_PRES_BSS_PARAM_CH_CNT 0x0020 +#define IEEE80211_MLC_BASIC_PRES_MED_SYNC_DELAY 0x0040 +#define IEEE80211_MLC_BASIC_PRES_EML_CAPA 0x0080 +#define IEEE80211_MLC_BASIC_PRES_MLD_CAPA_OP 0x0100 +#define IEEE80211_MLC_BASIC_PRES_MLD_ID 0x0200 + +#define IEEE80211_MED_SYNC_DELAY_DURATION 0x00ff +#define IEEE80211_MED_SYNC_DELAY_SYNC_OFDM_ED_THRESH 0x0f00 +#define IEEE80211_MED_SYNC_DELAY_SYNC_MAX_NUM_TXOPS 0xf000 + +#define IEEE80211_EML_CAP_EMLSR_SUPP 0x0001 +#define IEEE80211_EML_CAP_EMLSR_PADDING_DELAY 0x000e +#define IEEE80211_EML_CAP_EMLSR_PADDING_DELAY_0US 0 +#define IEEE80211_EML_CAP_EMLSR_PADDING_DELAY_32US 1 +#define IEEE80211_EML_CAP_EMLSR_PADDING_DELAY_64US 2 +#define IEEE80211_EML_CAP_EMLSR_PADDING_DELAY_128US 3 +#define IEEE80211_EML_CAP_EMLSR_PADDING_DELAY_256US 4 +#define IEEE80211_EML_CAP_EMLSR_TRANSITION_DELAY 0x0070 +#define IEEE80211_EML_CAP_EMLSR_TRANSITION_DELAY_0US 0 +#define IEEE80211_EML_CAP_EMLSR_TRANSITION_DELAY_16US 1 +#define IEEE80211_EML_CAP_EMLSR_TRANSITION_DELAY_32US 2 +#define IEEE80211_EML_CAP_EMLSR_TRANSITION_DELAY_64US 3 +#define IEEE80211_EML_CAP_EMLSR_TRANSITION_DELAY_128US 4 +#define IEEE80211_EML_CAP_EMLSR_TRANSITION_DELAY_256US 5 +#define IEEE80211_EML_CAP_EMLMR_SUPPORT 0x0080 +#define IEEE80211_EML_CAP_EMLMR_DELAY 0x0700 +#define IEEE80211_EML_CAP_EMLMR_DELAY_0US 0 +#define IEEE80211_EML_CAP_EMLMR_DELAY_32US 1 +#define IEEE80211_EML_CAP_EMLMR_DELAY_64US 2 +#define IEEE80211_EML_CAP_EMLMR_DELAY_128US 3 +#define IEEE80211_EML_CAP_EMLMR_DELAY_256US 4 +#define IEEE80211_EML_CAP_TRANSITION_TIMEOUT 0x7800 +#define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_0 0 +#define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_128US 1 +#define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_256US 2 +#define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_512US 3 +#define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_1TU 4 +#define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_2TU 5 +#define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_4TU 6 +#define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_8TU 7 +#define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_16TU 8 +#define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_32TU 9 +#define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_64TU 10 +#define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_128TU 11 + +#define IEEE80211_MLD_CAP_OP_MAX_SIMUL_LINKS 0x000f +#define IEEE80211_MLD_CAP_OP_SRS_SUPPORT 0x0010 +#define IEEE80211_MLD_CAP_OP_TID_TO_LINK_MAP_NEG_SUPP 0x0060 +#define IEEE80211_MLD_CAP_OP_FREQ_SEP_TYPE_IND 0x0f80 +#define IEEE80211_MLD_CAP_OP_AAR_SUPPORT 0x1000 + +struct ieee80211_mle_basic_common_info { + u8 len; + u8 mld_mac_addr[ETH_ALEN]; + u8 variable[]; +} __packed; + +#define IEEE80211_MLC_PREQ_PRES_MLD_ID 0x0010 + +struct ieee80211_mle_preq_common_info { + u8 len; + u8 variable[]; +} __packed; + +#define IEEE80211_MLC_RECONF_PRES_MLD_MAC_ADDR 0x0010 + +/* no fixed fields in RECONF */ + +struct ieee80211_mle_tdls_common_info { + u8 len; + u8 ap_mld_mac_addr[ETH_ALEN]; +} __packed; + +#define IEEE80211_MLC_PRIO_ACCESS_PRES_AP_MLD_MAC_ADDR 0x0010 + +/* no fixed fields in PRIO_ACCESS */ + +/** + * ieee80211_mle_common_size - check multi-link element common size + * @data: multi-link element, must already be checked for size using + * ieee80211_mle_size_ok() + */ +static inline u8 ieee80211_mle_common_size(const u8 *data) +{ + const struct ieee80211_multi_link_elem *mle = (const void *)data; + u16 control = le16_to_cpu(mle->control); + u8 common = 0; + + switch (u16_get_bits(control, IEEE80211_ML_CONTROL_TYPE)) { + case IEEE80211_ML_CONTROL_TYPE_BASIC: + common += sizeof(struct ieee80211_mle_basic_common_info); + break; + case IEEE80211_ML_CONTROL_TYPE_PREQ: + common += sizeof(struct ieee80211_mle_preq_common_info); + break; + case IEEE80211_ML_CONTROL_TYPE_RECONF: + if (control & IEEE80211_MLC_RECONF_PRES_MLD_MAC_ADDR) + common += ETH_ALEN; + return common; + case IEEE80211_ML_CONTROL_TYPE_TDLS: + common += sizeof(struct ieee80211_mle_tdls_common_info); + break; + case IEEE80211_ML_CONTROL_TYPE_PRIO_ACCESS: + if (control & IEEE80211_MLC_PRIO_ACCESS_PRES_AP_MLD_MAC_ADDR) + common += ETH_ALEN; + return common; + default: + WARN_ON(1); + return 0; + } + + return common + mle->variable[0]; +} + +/** + * ieee80211_mle_size_ok - validate multi-link element size + * @data: pointer to the element data + * @len: length of the containing element + */ +static inline bool ieee80211_mle_size_ok(const u8 *data, u8 len) +{ + const struct ieee80211_multi_link_elem *mle = (const void *)data; + u8 fixed = sizeof(*mle); + u8 common = 0; + bool check_common_len = false; + u16 control; + + if (len < fixed) + return false; + + control = le16_to_cpu(mle->control); + + switch (u16_get_bits(control, IEEE80211_ML_CONTROL_TYPE)) { + case IEEE80211_ML_CONTROL_TYPE_BASIC: + common += sizeof(struct ieee80211_mle_basic_common_info); + check_common_len = true; + if (control & IEEE80211_MLC_BASIC_PRES_LINK_ID) + common += 1; + if (control & IEEE80211_MLC_BASIC_PRES_BSS_PARAM_CH_CNT) + common += 1; + if (control & IEEE80211_MLC_BASIC_PRES_MED_SYNC_DELAY) + common += 2; + if (control & IEEE80211_MLC_BASIC_PRES_EML_CAPA) + common += 2; + if (control & IEEE80211_MLC_BASIC_PRES_MLD_CAPA_OP) + common += 2; + if (control & IEEE80211_MLC_BASIC_PRES_MLD_ID) + common += 1; + break; + case IEEE80211_ML_CONTROL_TYPE_PREQ: + common += sizeof(struct ieee80211_mle_preq_common_info); + if (control & IEEE80211_MLC_PREQ_PRES_MLD_ID) + common += 1; + check_common_len = true; + break; + case IEEE80211_ML_CONTROL_TYPE_RECONF: + if (control & IEEE80211_MLC_RECONF_PRES_MLD_MAC_ADDR) + common += ETH_ALEN; + break; + case IEEE80211_ML_CONTROL_TYPE_TDLS: + common += sizeof(struct ieee80211_mle_tdls_common_info); + check_common_len = true; + break; + case IEEE80211_ML_CONTROL_TYPE_PRIO_ACCESS: + if (control & IEEE80211_MLC_PRIO_ACCESS_PRES_AP_MLD_MAC_ADDR) + common += ETH_ALEN; + break; + default: + /* we don't know this type */ + return true; + } + + if (len < fixed + common) + return false; + + if (!check_common_len) + return true; + + /* if present, common length is the first octet there */ + return mle->variable[0] >= common; +} + +enum ieee80211_mle_subelems { + IEEE80211_MLE_SUBELEM_PER_STA_PROFILE = 0, +}; + +#define IEEE80211_MLE_STA_CONTROL_LINK_ID 0x000f +#define IEEE80211_MLE_STA_CONTROL_COMPLETE_PROFILE 0x0010 +#define IEEE80211_MLE_STA_CONTROL_STA_MAC_ADDR_PRESENT 0x0020 +#define IEEE80211_MLE_STA_CONTROL_BEACON_INT_PRESENT 0x0040 +#define IEEE80211_MLE_STA_CONTROL_TSF_OFFS_PRESENT 0x0080 +#define IEEE80211_MLE_STA_CONTROL_DTIM_INFO_PRESENT 0x0100 +#define IEEE80211_MLE_STA_CONTROL_NSTR_LINK_PAIR_PRESENT 0x0200 +#define IEEE80211_MLE_STA_CONTROL_NSTR_BITMAP_SIZE 0x0400 +#define IEEE80211_MLE_STA_CONTROL_BSS_PARAM_CHANGE_CNT_PRESENT 0x0800 + +struct ieee80211_mle_per_sta_profile { + __le16 control; + u8 sta_info_len; + u8 variable[]; +} __packed; + +#define for_each_mle_subelement(_elem, _data, _len) \ + if (ieee80211_mle_size_ok(_data, _len)) \ + for_each_element(_elem, \ + _data + ieee80211_mle_common_size(_data),\ + _len - ieee80211_mle_common_size(_data)) + #endif /* LINUX_IEEE80211_H */ diff --git a/include/linux/ieee802154.h b/include/linux/ieee802154.h index 95c831162212..f1f9412b6ac6 100644 --- a/include/linux/ieee802154.h +++ b/include/linux/ieee802154.h @@ -134,18 +134,46 @@ enum { * a successful transmission. */ IEEE802154_SUCCESS = 0x0, - + /* The requested operation failed. */ + IEEE802154_MAC_ERROR = 0x1, + /* The requested operation has been cancelled. */ + IEEE802154_CANCELLED = 0x2, + /* + * Device is ready to poll the coordinator for data in a non beacon + * enabled PAN. + */ + IEEE802154_READY_FOR_POLL = 0x3, + /* Wrong frame counter. */ + IEEE802154_COUNTER_ERROR = 0xdb, + /* + * The frame does not conforms to the incoming key usage policy checking + * procedure. + */ + IEEE802154_IMPROPER_KEY_TYPE = 0xdc, + /* + * The frame does not conforms to the incoming security level usage + * policy checking procedure. + */ + IEEE802154_IMPROPER_SECURITY_LEVEL = 0xdd, + /* Secured frame received with an empty Frame Version field. */ + IEEE802154_UNSUPPORTED_LEGACY = 0xde, + /* + * A secured frame is received or must be sent but security is not + * enabled in the device. Or, the Auxiliary Security Header has security + * level of zero in it. + */ + IEEE802154_UNSUPPORTED_SECURITY = 0xdf, /* The beacon was lost following a synchronization request. */ - IEEE802154_BEACON_LOSS = 0xe0, + IEEE802154_BEACON_LOST = 0xe0, /* * A transmission could not take place due to activity on the * channel, i.e., the CSMA-CA mechanism has failed. */ - IEEE802154_CHNL_ACCESS_FAIL = 0xe1, + IEEE802154_CHANNEL_ACCESS_FAILURE = 0xe1, /* The GTS request has been denied by the PAN coordinator. */ - IEEE802154_DENINED = 0xe2, + IEEE802154_DENIED = 0xe2, /* The attempt to disable the transceiver has failed. */ - IEEE802154_DISABLE_TRX_FAIL = 0xe3, + IEEE802154_DISABLE_TRX_FAILURE = 0xe3, /* * The received frame induces a failed security check according to * the security suite. @@ -185,9 +213,9 @@ enum { * A PAN identifier conflict has been detected and communicated to the * PAN coordinator. */ - IEEE802154_PANID_CONFLICT = 0xee, + IEEE802154_PAN_ID_CONFLICT = 0xee, /* A coordinator realignment command has been received. */ - IEEE802154_REALIGMENT = 0xef, + IEEE802154_REALIGNMENT = 0xef, /* The transaction has expired and its information discarded. */ IEEE802154_TRANSACTION_EXPIRED = 0xf0, /* There is no capacity to store the transaction. */ @@ -203,12 +231,49 @@ enum { * A SET/GET request was issued with the identifier of a PIB attribute * that is not supported. */ - IEEE802154_UNSUPPORTED_ATTR = 0xf4, + IEEE802154_UNSUPPORTED_ATTRIBUTE = 0xf4, + /* Missing source or destination address or address mode. */ + IEEE802154_INVALID_ADDRESS = 0xf5, + /* + * MLME asked to turn the receiver on, but the on time duration is too + * big compared to the macBeaconOrder. + */ + IEEE802154_ON_TIME_TOO_LONG = 0xf6, + /* + * MLME asaked to turn the receiver on, but the request was delayed for + * too long before getting processed. + */ + IEEE802154_PAST_TIME = 0xf7, + /* + * The StartTime parameter is nonzero, and the MLME is not currently + * tracking the beacon of the coordinator through which it is + * associated. + */ + IEEE802154_TRACKING_OFF = 0xf8, + /* + * The index inside the hierarchical values in PIBAttribute is out of + * range. + */ + IEEE802154_INVALID_INDEX = 0xf9, + /* + * The number of PAN descriptors discovered during a scan has been + * reached. + */ + IEEE802154_LIMIT_REACHED = 0xfa, + /* + * The PIBAttribute parameter specifies an attribute that is a read-only + * attribute. + */ + IEEE802154_READ_ONLY = 0xfb, /* * A request to perform a scan operation failed because the MLME was * in the process of performing a previously initiated scan operation. */ IEEE802154_SCAN_IN_PROGRESS = 0xfc, + /* The outgoing superframe overlaps the incoming superframe. */ + IEEE802154_SUPERFRAME_OVERLAP = 0xfd, + /* Any other error situation. */ + IEEE802154_SYSTEM_ERROR = 0xff, }; /* frame control handling */ diff --git a/include/linux/if_arp.h b/include/linux/if_arp.h index b712217f7030..1ed52441972f 100644 --- a/include/linux/if_arp.h +++ b/include/linux/if_arp.h @@ -52,6 +52,7 @@ static inline bool dev_is_mac_header_xmit(const struct net_device *dev) case ARPHRD_VOID: case ARPHRD_NONE: case ARPHRD_RAWIP: + case ARPHRD_PIMREG: return false; default: return true; diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h index 509e18c7e740..d62ef428e3aa 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -58,6 +58,7 @@ struct br_ip_list { #define BR_MRP_LOST_CONT BIT(18) #define BR_MRP_LOST_IN_CONT BIT(19) #define BR_TX_FWD_OFFLOAD BIT(20) +#define BR_PORT_LOCKED BIT(21) #define BR_DEFAULT_AGEING_TIME (300 * HZ) @@ -118,6 +119,9 @@ int br_vlan_get_info(const struct net_device *dev, u16 vid, struct bridge_vlan_info *p_vinfo); int br_vlan_get_info_rcu(const struct net_device *dev, u16 vid, struct bridge_vlan_info *p_vinfo); +bool br_mst_enabled(const struct net_device *dev); +int br_mst_get_info(const struct net_device *dev, u16 msti, unsigned long *vids); +int br_mst_get_state(const struct net_device *dev, u16 msti, u8 *state); #else static inline bool br_vlan_enabled(const struct net_device *dev) { @@ -150,6 +154,22 @@ static inline int br_vlan_get_info_rcu(const struct net_device *dev, u16 vid, { return -EINVAL; } + +static inline bool br_mst_enabled(const struct net_device *dev) +{ + return false; +} + +static inline int br_mst_get_info(const struct net_device *dev, u16 msti, + unsigned long *vids) +{ + return -EINVAL; +} +static inline int br_mst_get_state(const struct net_device *dev, u16 msti, + u8 *state) +{ + return -EINVAL; +} #endif #if IS_ENABLED(CONFIG_BRIDGE) diff --git a/include/linux/if_eql.h b/include/linux/if_eql.h index d75601d613cc..07f9b660b741 100644 --- a/include/linux/if_eql.h +++ b/include/linux/if_eql.h @@ -21,6 +21,7 @@ #include <linux/timer.h> #include <linux/spinlock.h> +#include <net/net_trackers.h> #include <uapi/linux/if_eql.h> typedef struct slave { diff --git a/include/linux/if_hsr.h b/include/linux/if_hsr.h index 38bbc537d4e4..0404f5bf4f30 100644 --- a/include/linux/if_hsr.h +++ b/include/linux/if_hsr.h @@ -2,6 +2,10 @@ #ifndef _LINUX_IF_HSR_H_ #define _LINUX_IF_HSR_H_ +#include <linux/types.h> + +struct net_device; + /* used to differentiate various protocols */ enum hsr_version { HSR_V0 = 0, @@ -9,6 +13,22 @@ enum hsr_version { PRP_V1, }; +/* HSR Tag. + * As defined in IEC-62439-3:2010, the HSR tag is really { ethertype = 0x88FB, + * path, LSDU_size, sequence Nr }. But we let eth_header() create { h_dest, + * h_source, h_proto = 0x88FB }, and add { path, LSDU_size, sequence Nr, + * encapsulated protocol } instead. + * + * Field names as defined in the IEC:2010 standard for HSR. + */ +struct hsr_tag { + __be16 path_and_LSDU_size; + __be16 sequence_nr; + __be16 encap_proto; +} __packed; + +#define HSR_HLEN 6 + #if IS_ENABLED(CONFIG_HSR) extern bool is_hsr_master(struct net_device *dev); extern int hsr_get_version(struct net_device *dev, enum hsr_version *ver); diff --git a/include/linux/if_macvlan.h b/include/linux/if_macvlan.h index 10c94a3936ca..523025106a64 100644 --- a/include/linux/if_macvlan.h +++ b/include/linux/if_macvlan.h @@ -21,6 +21,7 @@ struct macvlan_dev { struct hlist_node hlist; struct macvlan_port *port; struct net_device *lowerdev; + netdevice_tracker dev_tracker; void *accel_priv; struct vlan_pcpu_stats __percpu *pcpu_stats; @@ -45,10 +46,10 @@ static inline void macvlan_count_rx(const struct macvlan_dev *vlan, pcpu_stats = get_cpu_ptr(vlan->pcpu_stats); u64_stats_update_begin(&pcpu_stats->syncp); - pcpu_stats->rx_packets++; - pcpu_stats->rx_bytes += len; + u64_stats_inc(&pcpu_stats->rx_packets); + u64_stats_add(&pcpu_stats->rx_bytes, len); if (multicast) - pcpu_stats->rx_multicast++; + u64_stats_inc(&pcpu_stats->rx_multicast); u64_stats_update_end(&pcpu_stats->syncp); put_cpu_ptr(vlan->pcpu_stats); } else { diff --git a/include/linux/if_pppol2tp.h b/include/linux/if_pppol2tp.h index 96d40942e5a3..c87efd333faa 100644 --- a/include/linux/if_pppol2tp.h +++ b/include/linux/if_pppol2tp.h @@ -4,8 +4,6 @@ * * This file supplies definitions required by the PPP over L2TP driver * (l2tp_ppp.c). All version information wrt this file is located in l2tp_ppp.c - * - * License: */ #ifndef __LINUX_IF_PPPOL2TP_H #define __LINUX_IF_PPPOL2TP_H diff --git a/include/linux/if_pppox.h b/include/linux/if_pppox.h index 69e813bcb947..ff3beda1312c 100644 --- a/include/linux/if_pppox.h +++ b/include/linux/if_pppox.h @@ -5,8 +5,6 @@ * * This file supplies definitions required by the PPP over Ethernet driver * (pppox.c). All version information wrt this file is located in pppox.c - * - * License: */ #ifndef __LINUX_IF_PPPOX_H #define __LINUX_IF_PPPOX_H diff --git a/include/linux/if_rmnet.h b/include/linux/if_rmnet.h index 10e7521ecb6c..839d1e48b85e 100644 --- a/include/linux/if_rmnet.h +++ b/include/linux/if_rmnet.h @@ -5,6 +5,8 @@ #ifndef _LINUX_IF_RMNET_H_ #define _LINUX_IF_RMNET_H_ +#include <linux/types.h> + struct rmnet_map_header { u8 flags; /* MAP_CMD_FLAG, MAP_PAD_LEN_MASK */ u8 mux_id; diff --git a/include/linux/if_tap.h b/include/linux/if_tap.h index 915a187cfabd..553552fa635c 100644 --- a/include/linux/if_tap.h +++ b/include/linux/if_tap.h @@ -2,14 +2,18 @@ #ifndef _LINUX_IF_TAP_H_ #define _LINUX_IF_TAP_H_ +#include <net/sock.h> +#include <linux/skb_array.h> + +struct file; +struct socket; + #if IS_ENABLED(CONFIG_TAP) struct socket *tap_get_socket(struct file *); struct ptr_ring *tap_get_ptr_ring(struct file *file); #else #include <linux/err.h> #include <linux/errno.h> -struct file; -struct socket; static inline struct socket *tap_get_socket(struct file *f) { return ERR_PTR(-EINVAL); @@ -20,9 +24,6 @@ static inline struct ptr_ring *tap_get_ptr_ring(struct file *f) } #endif /* CONFIG_TAP */ -#include <net/sock.h> -#include <linux/skb_array.h> - /* * Maximum times a tap device can be opened. This can be used to * configure the number of receive queue, e.g. for multiqueue virtio. diff --git a/include/linux/if_team.h b/include/linux/if_team.h index add607943c95..fc985e5c739d 100644 --- a/include/linux/if_team.h +++ b/include/linux/if_team.h @@ -12,11 +12,11 @@ #include <uapi/linux/if_team.h> struct team_pcpu_stats { - u64 rx_packets; - u64 rx_bytes; - u64 rx_multicast; - u64 tx_packets; - u64 tx_bytes; + u64_stats_t rx_packets; + u64_stats_t rx_bytes; + u64_stats_t rx_multicast; + u64_stats_t tx_packets; + u64_stats_t tx_bytes; struct u64_stats_sync syncp; u32 rx_dropped; u32 tx_dropped; diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 8420fe504927..e00c4ee81ff7 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -46,8 +46,10 @@ struct vlan_hdr { * @h_vlan_encapsulated_proto: packet type ID or len */ struct vlan_ethhdr { - unsigned char h_dest[ETH_ALEN]; - unsigned char h_source[ETH_ALEN]; + struct_group(addrs, + unsigned char h_dest[ETH_ALEN]; + unsigned char h_source[ETH_ALEN]; + ); __be16 h_vlan_proto; __be16 h_vlan_TCI; __be16 h_vlan_encapsulated_proto; @@ -116,11 +118,11 @@ static inline void vlan_drop_rx_stag_filter_info(struct net_device *dev) * @tx_dropped: number of tx drops */ struct vlan_pcpu_stats { - u64 rx_packets; - u64 rx_bytes; - u64 rx_multicast; - u64 tx_packets; - u64 tx_bytes; + u64_stats_t rx_packets; + u64_stats_t rx_bytes; + u64_stats_t rx_multicast; + u64_stats_t tx_packets; + u64_stats_t tx_bytes; struct u64_stats_sync syncp; u32 rx_errors; u32 tx_dropped; diff --git a/include/linux/igmp.h b/include/linux/igmp.h index 93c262ecbdc9..78890143f079 100644 --- a/include/linux/igmp.h +++ b/include/linux/igmp.h @@ -118,9 +118,9 @@ extern int ip_mc_source(int add, int omode, struct sock *sk, struct ip_mreq_source *mreqs, int ifindex); extern int ip_mc_msfilter(struct sock *sk, struct ip_msfilter *msf,int ifindex); extern int ip_mc_msfget(struct sock *sk, struct ip_msfilter *msf, - struct ip_msfilter __user *optval, int __user *optlen); + sockptr_t optval, sockptr_t optlen); extern int ip_mc_gsfget(struct sock *sk, struct group_filter *gsf, - struct sockaddr_storage __user *p); + sockptr_t optval, size_t offset); extern int ip_mc_sf_allow(struct sock *sk, __be32 local, __be32 rmt, int dif, int sdif); extern void ip_mc_init_dev(struct in_device *); diff --git a/include/linux/iio/adc/ad_sigma_delta.h b/include/linux/iio/adc/ad_sigma_delta.h index c525fd51652f..7852f6c9a714 100644 --- a/include/linux/iio/adc/ad_sigma_delta.h +++ b/include/linux/iio/adc/ad_sigma_delta.h @@ -32,26 +32,34 @@ struct iio_dev; /** * struct ad_sigma_delta_info - Sigma Delta driver specific callbacks and options * @set_channel: Will be called to select the current channel, may be NULL. + * @append_status: Will be called to enable status append at the end of the sample, may be NULL. * @set_mode: Will be called to select the current mode, may be NULL. + * @disable_all: Will be called to disable all channels, may be NULL. * @postprocess_sample: Is called for each sampled data word, can be used to * modify or drop the sample data, it, may be NULL. * @has_registers: true if the device has writable and readable registers, false * if there is just one read-only sample data shift register. * @addr_shift: Shift of the register address in the communications register. * @read_mask: Mask for the communications register having the read bit set. + * @status_ch_mask: Mask for the channel number stored in status register. * @data_reg: Address of the data register, if 0 the default address of 0x3 will * be used. * @irq_flags: flags for the interrupt used by the triggered buffer + * @num_slots: Number of sequencer slots */ struct ad_sigma_delta_info { int (*set_channel)(struct ad_sigma_delta *, unsigned int channel); + int (*append_status)(struct ad_sigma_delta *, bool append); int (*set_mode)(struct ad_sigma_delta *, enum ad_sigma_delta_mode mode); + int (*disable_all)(struct ad_sigma_delta *); int (*postprocess_sample)(struct ad_sigma_delta *, unsigned int raw_sample); bool has_registers; unsigned int addr_shift; unsigned int read_mask; + unsigned int status_ch_mask; unsigned int data_reg; unsigned long irq_flags; + unsigned int num_slots; }; /** @@ -76,6 +84,13 @@ struct ad_sigma_delta { uint8_t comm; const struct ad_sigma_delta_info *info; + unsigned int active_slots; + unsigned int current_slot; + unsigned int num_slots; + bool status_appended; + /* map slots to channels in order to know what to expect from devices */ + unsigned int *slots; + uint8_t *samples_buf; /* * DMA (thus cache coherency maintenance) requires the @@ -97,6 +112,29 @@ static inline int ad_sigma_delta_set_channel(struct ad_sigma_delta *sd, return 0; } +static inline int ad_sigma_delta_append_status(struct ad_sigma_delta *sd, bool append) +{ + int ret; + + if (sd->info->append_status) { + ret = sd->info->append_status(sd, append); + if (ret < 0) + return ret; + + sd->status_appended = append; + } + + return 0; +} + +static inline int ad_sigma_delta_disable_all(struct ad_sigma_delta *sd) +{ + if (sd->info->disable_all) + return sd->info->disable_all(sd); + + return 0; +} + static inline int ad_sigma_delta_set_mode(struct ad_sigma_delta *sd, unsigned int mode) { diff --git a/include/linux/iio/adc/qcom-vadc-common.h b/include/linux/iio/adc/qcom-vadc-common.h index 33f60f43e1aa..aa21b032e861 100644 --- a/include/linux/iio/adc/qcom-vadc-common.h +++ b/include/linux/iio/adc/qcom-vadc-common.h @@ -6,6 +6,7 @@ #ifndef QCOM_VADC_COMMON_H #define QCOM_VADC_COMMON_H +#include <linux/math.h> #include <linux/types.h> #define VADC_CONV_TIME_MIN_US 2000 @@ -80,16 +81,6 @@ struct vadc_linear_graph { }; /** - * struct vadc_prescale_ratio - Represent scaling ratio for ADC input. - * @num: the inverse numerator of the gain applied to the input channel. - * @den: the inverse denominator of the gain applied to the input channel. - */ -struct vadc_prescale_ratio { - u32 num; - u32 den; -}; - -/** * enum vadc_scale_fn_type - Scaling function to convert ADC code to * physical scaled units for the channel. * SCALE_DEFAULT: Default scaling to convert raw adc code to voltage (uV). @@ -144,12 +135,12 @@ struct adc5_data { int qcom_vadc_scale(enum vadc_scale_fn_type scaletype, const struct vadc_linear_graph *calib_graph, - const struct vadc_prescale_ratio *prescale, + const struct u32_fract *prescale, bool absolute, u16 adc_code, int *result_mdec); struct qcom_adc5_scale_type { - int (*scale_fn)(const struct vadc_prescale_ratio *prescale, + int (*scale_fn)(const struct u32_fract *prescale, const struct adc5_data *data, u16 adc_code, int *result); }; @@ -161,6 +152,8 @@ int qcom_adc5_hw_scale(enum vadc_scale_fn_type scaletype, u16 qcom_adc_tm5_temp_volt_scale(unsigned int prescale_ratio, u32 full_scale_code_volt, int temp); +u16 qcom_adc_tm5_gen2_temp_res_scale(int temp); + int qcom_adc5_prescaling_from_dt(u32 num, u32 den); int qcom_adc5_hw_settle_time_from_dt(u32 value, const unsigned int *hw_settle); diff --git a/include/linux/iio/afe/rescale.h b/include/linux/iio/afe/rescale.h new file mode 100644 index 000000000000..6eecb435488f --- /dev/null +++ b/include/linux/iio/afe/rescale.h @@ -0,0 +1,36 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2018 Axentia Technologies AB + */ + +#ifndef __IIO_RESCALE_H__ +#define __IIO_RESCALE_H__ + +#include <linux/types.h> +#include <linux/iio/iio.h> + +struct device; +struct rescale; + +struct rescale_cfg { + enum iio_chan_type type; + int (*props)(struct device *dev, struct rescale *rescale); +}; + +struct rescale { + const struct rescale_cfg *cfg; + struct iio_channel *source; + struct iio_chan_spec chan; + struct iio_chan_spec_ext_info *ext_info; + bool chan_processed; + s32 numerator; + s32 denominator; + s32 offset; +}; + +int rescale_process_scale(struct rescale *rescale, int scale_type, + int *val, int *val2); +int rescale_process_offset(struct rescale *rescale, int scale_type, + int scale, int scale2, int schan_off, + int *val, int *val2); +#endif /* __IIO_RESCALE_H__ */ diff --git a/include/linux/iio/buffer-dma.h b/include/linux/iio/buffer-dma.h index ff15c61bf319..6564bdcdac66 100644 --- a/include/linux/iio/buffer-dma.h +++ b/include/linux/iio/buffer-dma.h @@ -17,11 +17,6 @@ struct iio_dma_buffer_queue; struct iio_dma_buffer_ops; struct device; -struct iio_buffer_block { - u32 size; - u32 bytes_used; -}; - /** * enum iio_block_state - State of a struct iio_dma_buffer_block * @IIO_BLOCK_STATE_DEQUEUED: Block is not queued diff --git a/include/linux/iio/common/cros_ec_sensors_core.h b/include/linux/iio/common/cros_ec_sensors_core.h index c582e1a14232..e72167b96d27 100644 --- a/include/linux/iio/common/cros_ec_sensors_core.h +++ b/include/linux/iio/common/cros_ec_sensors_core.h @@ -41,7 +41,6 @@ typedef irqreturn_t (*cros_ec_sensors_capture_t)(int irq, void *p); * @param: motion sensor parameters structure * @resp: motion sensor response structure * @type: type of motion sensor - * @loc: location where the motion sensor is placed * @range_updated: True if the range of the sensor has been * updated. * @curr_range: If updated, the current range value. @@ -67,7 +66,6 @@ struct cros_ec_sensors_core_state { struct ec_response_motion_sense *resp; enum motionsensor_type type; - enum motionsensor_location loc; bool range_updated; int curr_range; @@ -95,8 +93,11 @@ int cros_ec_sensors_read_cmd(struct iio_dev *indio_dev, unsigned long scan_mask, struct platform_device; int cros_ec_sensors_core_init(struct platform_device *pdev, struct iio_dev *indio_dev, bool physical_device, - cros_ec_sensors_capture_t trigger_capture, - cros_ec_sensorhub_push_data_cb_t push_data); + cros_ec_sensors_capture_t trigger_capture); + +int cros_ec_sensors_core_register(struct device *dev, + struct iio_dev *indio_dev, + cros_ec_sensorhub_push_data_cb_t push_data); irqreturn_t cros_ec_sensors_capture(int irq, void *p); int cros_ec_sensors_push_data(struct iio_dev *indio_dev, diff --git a/include/linux/iio/common/st_sensors.h b/include/linux/iio/common/st_sensors.h index 22f67845cdd3..db4a1b260348 100644 --- a/include/linux/iio/common/st_sensors.h +++ b/include/linux/iio/common/st_sensors.h @@ -237,6 +237,7 @@ struct st_sensor_settings { * @hw_irq_trigger: if we're using the hardware interrupt on the sensor. * @hw_timestamp: Latest timestamp from the interrupt handler, when in use. * @buffer_data: Data used by buffer part. + * @odr_lock: Local lock for preventing concurrent ODR accesses/changes */ struct st_sensor_data { struct iio_trigger *trig; @@ -261,6 +262,8 @@ struct st_sensor_data { s64 hw_timestamp; char buffer_data[ST_SENSORS_MAX_BUFFER_SIZE] ____cacheline_aligned; + + struct mutex odr_lock; }; #ifdef CONFIG_IIO_BUFFER diff --git a/include/linux/iio/consumer.h b/include/linux/iio/consumer.h index 5fa5957586cf..6802596b017c 100644 --- a/include/linux/iio/consumer.h +++ b/include/linux/iio/consumer.h @@ -13,7 +13,7 @@ struct iio_dev; struct iio_chan_spec; struct device; -struct device_node; +struct fwnode_handle; /** * struct iio_channel - everything needed for a consumer to use a channel @@ -99,26 +99,20 @@ void iio_channel_release_all(struct iio_channel *chan); struct iio_channel *devm_iio_channel_get_all(struct device *dev); /** - * of_iio_channel_get_by_name() - get description of all that is needed to access channel. - * @np: Pointer to consumer device tree node + * fwnode_iio_channel_get_by_name() - get description of all that is needed to access channel. + * @fwnode: Pointer to consumer Firmware node * @consumer_channel: Unique name to identify the channel on the consumer * side. This typically describes the channels use within * the consumer. E.g. 'battery_voltage' */ -#ifdef CONFIG_OF -struct iio_channel *of_iio_channel_get_by_name(struct device_node *np, const char *name); -#else -static inline struct iio_channel * -of_iio_channel_get_by_name(struct device_node *np, const char *name) -{ - return NULL; -} -#endif +struct iio_channel *fwnode_iio_channel_get_by_name(struct fwnode_handle *fwnode, + const char *name); /** - * devm_of_iio_channel_get_by_name() - Resource managed version of of_iio_channel_get_by_name(). + * devm_fwnode_iio_channel_get_by_name() - Resource managed version of + * fwnode_iio_channel_get_by_name(). * @dev: Pointer to consumer device. - * @np: Pointer to consumer device tree node + * @fwnode: Pointer to consumer Firmware node * @consumer_channel: Unique name to identify the channel on the consumer * side. This typically describes the channels use within * the consumer. E.g. 'battery_voltage' @@ -129,9 +123,9 @@ of_iio_channel_get_by_name(struct device_node *np, const char *name) * The allocated iio channel is automatically released when the device is * unbound. */ -struct iio_channel *devm_of_iio_channel_get_by_name(struct device *dev, - struct device_node *np, - const char *consumer_channel); +struct iio_channel *devm_fwnode_iio_channel_get_by_name(struct device *dev, + struct fwnode_handle *fwnode, + const char *consumer_channel); struct iio_cb_buffer; /** diff --git a/include/linux/iio/iio-opaque.h b/include/linux/iio/iio-opaque.h index 2be12b7b5dc5..d1f8b30a7c8b 100644 --- a/include/linux/iio/iio-opaque.h +++ b/include/linux/iio/iio-opaque.h @@ -7,7 +7,11 @@ * struct iio_dev_opaque - industrial I/O device opaque information * @indio_dev: public industrial I/O device information * @id: used to identify device internally + * @currentmode: operating mode currently in use, may be eventually + * checked by device drivers but should be considered + * read-only as this is a core internal bit * @driver_module: used to make it harder to undercut users + * @mlock_key: lockdep class for iio_dev lock * @info_exist_lock: lock to prevent use during removal * @trig_readonly: mark the current trigger immutable * @event_interface: event chrdevs associated with interrupt lines @@ -36,8 +40,10 @@ */ struct iio_dev_opaque { struct iio_dev indio_dev; + int currentmode; int id; struct module *driver_module; + struct lock_class_key mlock_key; struct mutex info_exist_lock; bool trig_readonly; struct iio_event_interface *event_interface; diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index 324561b7a5e8..f0ec8a5e5a7a 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -9,14 +9,16 @@ #include <linux/device.h> #include <linux/cdev.h> +#include <linux/slab.h> #include <linux/iio/types.h> -#include <linux/of.h> /* IIO TODO LIST */ /* * Provide means of adjusting timer accuracy. * Currently assumes nano seconds. */ +struct fwnode_reference_args; + enum iio_shared_by { IIO_SEPARATE, IIO_SHARED_BY_TYPE, @@ -103,15 +105,16 @@ ssize_t iio_enum_write(struct iio_dev *indio_dev, /** * IIO_ENUM_AVAILABLE() - Initialize enum available extended channel attribute * @_name: Attribute name ("_available" will be appended to the name) + * @_shared: Whether the attribute is shared between all channels * @_e: Pointer to an iio_enum struct * * Creates a read only attribute which lists all the available enum items in a * space separated list. This should usually be used together with IIO_ENUM() */ -#define IIO_ENUM_AVAILABLE(_name, _e) \ +#define IIO_ENUM_AVAILABLE(_name, _shared, _e) \ { \ .name = (_name "_available"), \ - .shared = IIO_SHARED_BY_TYPE, \ + .shared = _shared, \ .read = iio_enum_available_read, \ .private = (uintptr_t)(_e), \ } @@ -312,9 +315,55 @@ static inline bool iio_channel_has_available(const struct iio_chan_spec *chan, } s64 iio_get_time_ns(const struct iio_dev *indio_dev); -unsigned int iio_get_time_res(const struct iio_dev *indio_dev); -/* Device operating modes */ +/* + * Device operating modes + * @INDIO_DIRECT_MODE: There is an access to either: + * a) The last single value available for devices that do not provide + * on-demand reads. + * b) A new value after performing an on-demand read otherwise. + * On most devices, this is a single-shot read. On some devices with data + * streams without an 'on-demand' function, this might also be the 'last value' + * feature. Above all, this mode internally means that we are not in any of the + * other modes, and sysfs reads should work. + * Device drivers should inform the core if they support this mode. + * @INDIO_BUFFER_TRIGGERED: Common mode when dealing with kfifo buffers. + * It indicates that an explicit trigger is required. This requests the core to + * attach a poll function when enabling the buffer, which is indicated by the + * _TRIGGERED suffix. + * The core will ensure this mode is set when registering a triggered buffer + * with iio_triggered_buffer_setup(). + * @INDIO_BUFFER_SOFTWARE: Another kfifo buffer mode, but not event triggered. + * No poll function can be attached because there is no triggered infrastructure + * we can use to cause capture. There is a kfifo that the driver will fill, but + * not "only one scan at a time". Typically, hardware will have a buffer that + * can hold multiple scans. Software may read one or more scans at a single time + * and push the available data to a Kfifo. This means the core will not attach + * any poll function when enabling the buffer. + * The core will ensure this mode is set when registering a simple kfifo buffer + * with devm_iio_kfifo_buffer_setup(). + * @INDIO_BUFFER_HARDWARE: For specific hardware, if unsure do not use this mode. + * Same as above but this time the buffer is not a kfifo where we have direct + * access to the data. Instead, the consumer driver must access the data through + * non software visible channels (or DMA when there is no demux possible in + * software) + * The core will ensure this mode is set when registering a dmaengine buffer + * with devm_iio_dmaengine_buffer_setup(). + * @INDIO_EVENT_TRIGGERED: Very unusual mode. + * Triggers usually refer to an external event which will start data capture. + * Here it is kind of the opposite as, a particular state of the data might + * produce an event which can be considered as an event. We don't necessarily + * have access to the data itself, but to the event produced. For example, this + * can be a threshold detector. The internal path of this mode is very close to + * the INDIO_BUFFER_TRIGGERED mode. + * The core will ensure this mode is set when registering a triggered event. + * @INDIO_HARDWARE_TRIGGERED: Very unusual mode. + * Here, triggers can result in data capture and can be routed to multiple + * hardware components, which make them close to regular triggers in the way + * they must be managed by the core, but without the entire interrupts/poll + * functions burden. Interrupts are irrelevant as the data flow is hardware + * mediated and distributed. + */ #define INDIO_DIRECT_MODE 0x01 #define INDIO_BUFFER_TRIGGERED 0x02 #define INDIO_BUFFER_SOFTWARE 0x04 @@ -380,6 +429,8 @@ struct iio_trigger; /* forward declaration */ * provide a custom of_xlate function that reads the * *args* and returns the appropriate index in registered * IIO channels array. + * @fwnode_xlate: fwnode based function pointer to obtain channel specifier index. + * Functionally the same as @of_xlate. * @hwfifo_set_watermark: function pointer to set the current hardware * fifo watermark level; see hwfifo_* entries in * Documentation/ABI/testing/sysfs-bus-iio for details on @@ -459,8 +510,8 @@ struct iio_info { int (*debugfs_reg_access)(struct iio_dev *indio_dev, unsigned reg, unsigned writeval, unsigned *readval); - int (*of_xlate)(struct iio_dev *indio_dev, - const struct of_phandle_args *iiospec); + int (*fwnode_xlate)(struct iio_dev *indio_dev, + const struct fwnode_reference_args *iiospec); int (*hwfifo_set_watermark)(struct iio_dev *indio_dev, unsigned val); int (*hwfifo_flush_to_buffer)(struct iio_dev *indio_dev, unsigned count); @@ -487,8 +538,12 @@ struct iio_buffer_setup_ops { /** * struct iio_dev - industrial I/O device - * @modes: [DRIVER] operating modes supported by device - * @currentmode: [DRIVER] current operating mode + * @modes: [DRIVER] bitmask listing all the operating modes + * supported by the IIO device. This list should be + * initialized before registering the IIO device. It can + * also be filed up by the IIO core, as a result of + * enabling particular features in the driver + * (see iio_triggered_event_setup()). * @dev: [DRIVER] device structure, should be assigned a parent * and owner * @buffer: [DRIVER] any buffer present @@ -515,7 +570,6 @@ struct iio_buffer_setup_ops { */ struct iio_dev { int modes; - int currentmode; struct device dev; struct iio_buffer *buffer; @@ -542,6 +596,8 @@ struct iio_dev { }; int iio_device_id(struct iio_dev *indio_dev); +int iio_device_get_current_mode(struct iio_dev *indio_dev); +bool iio_buffer_enabled(struct iio_dev *indio_dev); const struct iio_chan_spec *iio_find_channel_from_si(struct iio_dev *indio_dev, int si); @@ -656,8 +712,13 @@ static inline void *iio_device_get_drvdata(const struct iio_dev *indio_dev) return dev_get_drvdata(&indio_dev->dev); } -/* Can we make this smaller? */ -#define IIO_ALIGN L1_CACHE_BYTES +/* + * Used to ensure the iio_priv() structure is aligned to allow that structure + * to in turn include IIO_DMA_MINALIGN'd elements such as buffers which + * must not share cachelines with the rest of the structure, thus making + * them safe for use with non-coherent DMA. + */ +#define IIO_DMA_MINALIGN ARCH_KMALLOC_MINALIGN struct iio_dev *iio_device_alloc(struct device *parent, int sizeof_priv); /* The information at the returned address is guaranteed to be cacheline aligned */ @@ -668,20 +729,13 @@ static inline void *iio_priv(const struct iio_dev *indio_dev) void iio_device_free(struct iio_dev *indio_dev); struct iio_dev *devm_iio_device_alloc(struct device *parent, int sizeof_priv); -__printf(2, 3) -struct iio_trigger *devm_iio_trigger_alloc(struct device *parent, - const char *fmt, ...); -/** - * iio_buffer_enabled() - helper function to test if the buffer is enabled - * @indio_dev: IIO device structure for device - **/ -static inline bool iio_buffer_enabled(struct iio_dev *indio_dev) -{ - return indio_dev->currentmode - & (INDIO_BUFFER_TRIGGERED | INDIO_BUFFER_HARDWARE | - INDIO_BUFFER_SOFTWARE); -} +#define devm_iio_trigger_alloc(parent, fmt, ...) \ + __devm_iio_trigger_alloc((parent), THIS_MODULE, (fmt), ##__VA_ARGS__) +__printf(3, 4) +struct iio_trigger *__devm_iio_trigger_alloc(struct device *parent, + struct module *this_mod, + const char *fmt, ...); /** * iio_get_debugfs_dentry() - helper function to get the debugfs_dentry * @indio_dev: IIO device structure for device diff --git a/include/linux/iio/imu/adis.h b/include/linux/iio/imu/adis.h index 7c02f5292eea..515ca09764fe 100644 --- a/include/linux/iio/imu/adis.h +++ b/include/linux/iio/imu/adis.h @@ -32,6 +32,7 @@ struct adis_timeout { u16 sw_reset_ms; u16 self_test_ms; }; + /** * struct adis_data - ADIS chip variant specific data * @read_delay: SPI delay for read operations in us @@ -45,7 +46,7 @@ struct adis_timeout { * @self_test_mask: Bitmask of supported self-test operations * @self_test_reg: Register address to request self test command * @self_test_no_autoclear: True if device's self-test needs clear of ctrl reg - * @status_error_msgs: Array of error messgaes + * @status_error_msgs: Array of error messages * @status_error_mask: Bitmask of errors supported by the device * @timeouts: Chip specific delays * @enable_irq: Hook for ADIS devices that have a special IRQ enable/disable @@ -130,12 +131,12 @@ struct adis { unsigned long irq_flag; void *buffer; - uint8_t tx[10] ____cacheline_aligned; - uint8_t rx[4]; + u8 tx[10] ____cacheline_aligned; + u8 rx[4]; }; int adis_init(struct adis *adis, struct iio_dev *indio_dev, - struct spi_device *spi, const struct adis_data *data); + struct spi_device *spi, const struct adis_data *data); int __adis_reset(struct adis *adis); /** @@ -156,9 +157,9 @@ static inline int adis_reset(struct adis *adis) } int __adis_write_reg(struct adis *adis, unsigned int reg, - unsigned int val, unsigned int size); + unsigned int val, unsigned int size); int __adis_read_reg(struct adis *adis, unsigned int reg, - unsigned int *val, unsigned int size); + unsigned int *val, unsigned int size); /** * __adis_write_reg_8() - Write single byte to a register (unlocked) @@ -167,7 +168,7 @@ int __adis_read_reg(struct adis *adis, unsigned int reg, * @value: The value to write */ static inline int __adis_write_reg_8(struct adis *adis, unsigned int reg, - uint8_t val) + u8 val) { return __adis_write_reg(adis, reg, val, 1); } @@ -179,7 +180,7 @@ static inline int __adis_write_reg_8(struct adis *adis, unsigned int reg, * @value: Value to be written */ static inline int __adis_write_reg_16(struct adis *adis, unsigned int reg, - uint16_t val) + u16 val) { return __adis_write_reg(adis, reg, val, 2); } @@ -191,7 +192,7 @@ static inline int __adis_write_reg_16(struct adis *adis, unsigned int reg, * @value: Value to be written */ static inline int __adis_write_reg_32(struct adis *adis, unsigned int reg, - uint32_t val) + u32 val) { return __adis_write_reg(adis, reg, val, 4); } @@ -203,7 +204,7 @@ static inline int __adis_write_reg_32(struct adis *adis, unsigned int reg, * @val: The value read back from the device */ static inline int __adis_read_reg_16(struct adis *adis, unsigned int reg, - uint16_t *val) + u16 *val) { unsigned int tmp; int ret; @@ -222,7 +223,7 @@ static inline int __adis_read_reg_16(struct adis *adis, unsigned int reg, * @val: The value read back from the device */ static inline int __adis_read_reg_32(struct adis *adis, unsigned int reg, - uint32_t *val) + u32 *val) { unsigned int tmp; int ret; @@ -242,7 +243,7 @@ static inline int __adis_read_reg_32(struct adis *adis, unsigned int reg, * @size: The size of the @value (in bytes) */ static inline int adis_write_reg(struct adis *adis, unsigned int reg, - unsigned int val, unsigned int size) + unsigned int val, unsigned int size) { int ret; @@ -261,7 +262,7 @@ static inline int adis_write_reg(struct adis *adis, unsigned int reg, * @size: The size of the @val buffer */ static int adis_read_reg(struct adis *adis, unsigned int reg, - unsigned int *val, unsigned int size) + unsigned int *val, unsigned int size) { int ret; @@ -279,7 +280,7 @@ static int adis_read_reg(struct adis *adis, unsigned int reg, * @value: The value to write */ static inline int adis_write_reg_8(struct adis *adis, unsigned int reg, - uint8_t val) + u8 val) { return adis_write_reg(adis, reg, val, 1); } @@ -291,7 +292,7 @@ static inline int adis_write_reg_8(struct adis *adis, unsigned int reg, * @value: Value to be written */ static inline int adis_write_reg_16(struct adis *adis, unsigned int reg, - uint16_t val) + u16 val) { return adis_write_reg(adis, reg, val, 2); } @@ -303,7 +304,7 @@ static inline int adis_write_reg_16(struct adis *adis, unsigned int reg, * @value: Value to be written */ static inline int adis_write_reg_32(struct adis *adis, unsigned int reg, - uint32_t val) + u32 val) { return adis_write_reg(adis, reg, val, 4); } @@ -315,7 +316,7 @@ static inline int adis_write_reg_32(struct adis *adis, unsigned int reg, * @val: The value read back from the device */ static inline int adis_read_reg_16(struct adis *adis, unsigned int reg, - uint16_t *val) + u16 *val) { unsigned int tmp; int ret; @@ -334,7 +335,7 @@ static inline int adis_read_reg_16(struct adis *adis, unsigned int reg, * @val: The value read back from the device */ static inline int adis_read_reg_32(struct adis *adis, unsigned int reg, - uint32_t *val) + u32 *val) { unsigned int tmp; int ret; @@ -381,10 +382,8 @@ static inline int adis_update_bits_base(struct adis *adis, unsigned int reg, * @val can lead to undesired behavior if the register to update is 16bit. */ #define adis_update_bits(adis, reg, mask, val) ({ \ - BUILD_BUG_ON(sizeof(val) == 1 || sizeof(val) == 8); \ - __builtin_choose_expr(sizeof(val) == 4, \ - adis_update_bits_base(adis, reg, mask, val, 4), \ - adis_update_bits_base(adis, reg, mask, val, 2)); \ + BUILD_BUG_ON(sizeof(val) != 2 && sizeof(val) != 4); \ + adis_update_bits_base(adis, reg, mask, val, sizeof(val)); \ }) /** @@ -399,10 +398,8 @@ static inline int adis_update_bits_base(struct adis *adis, unsigned int reg, * @val can lead to undesired behavior if the register to update is 16bit. */ #define __adis_update_bits(adis, reg, mask, val) ({ \ - BUILD_BUG_ON(sizeof(val) == 1 || sizeof(val) == 8); \ - __builtin_choose_expr(sizeof(val) == 4, \ - __adis_update_bits_base(adis, reg, mask, val, 4), \ - __adis_update_bits_base(adis, reg, mask, val, 2)); \ + BUILD_BUG_ON(sizeof(val) != 2 && sizeof(val) != 4); \ + __adis_update_bits_base(adis, reg, mask, val, sizeof(val)); \ }) int adis_enable_irq(struct adis *adis, bool enable); @@ -443,8 +440,8 @@ static inline void adis_dev_unlock(struct adis *adis) } int adis_single_conversion(struct iio_dev *indio_dev, - const struct iio_chan_spec *chan, unsigned int error_mask, - int *val); + const struct iio_chan_spec *chan, + unsigned int error_mask, int *val); #define ADIS_VOLTAGE_CHAN(addr, si, chan, name, info_all, bits) { \ .type = IIO_VOLTAGE, \ @@ -493,7 +490,7 @@ int adis_single_conversion(struct iio_dev *indio_dev, .modified = 1, \ .channel2 = IIO_MOD_ ## mod, \ .info_mask_separate = BIT(IIO_CHAN_INFO_RAW) | \ - info_sep, \ + (info_sep), \ .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE), \ .info_mask_shared_by_all = info_all, \ .address = (addr), \ @@ -527,7 +524,7 @@ devm_adis_setup_buffer_and_trigger(struct adis *adis, struct iio_dev *indio_dev, int devm_adis_probe_trigger(struct adis *adis, struct iio_dev *indio_dev); int adis_update_scan_mode(struct iio_dev *indio_dev, - const unsigned long *scan_mask); + const unsigned long *scan_mask); #else /* CONFIG_IIO_BUFFER */ @@ -551,7 +548,8 @@ static inline int devm_adis_probe_trigger(struct adis *adis, #ifdef CONFIG_DEBUG_FS int adis_debugfs_reg_access(struct iio_dev *indio_dev, - unsigned int reg, unsigned int writeval, unsigned int *readval); + unsigned int reg, unsigned int writeval, + unsigned int *readval); #else diff --git a/include/linux/iio/kfifo_buf.h b/include/linux/iio/kfifo_buf.h index ccd2ceae7b25..8a83fb58232d 100644 --- a/include/linux/iio/kfifo_buf.h +++ b/include/linux/iio/kfifo_buf.h @@ -12,11 +12,10 @@ void iio_kfifo_free(struct iio_buffer *r); int devm_iio_kfifo_buffer_setup_ext(struct device *dev, struct iio_dev *indio_dev, - int mode_flags, const struct iio_buffer_setup_ops *setup_ops, const struct attribute **buffer_attrs); -#define devm_iio_kfifo_buffer_setup(dev, indio_dev, mode_flags, setup_ops) \ - devm_iio_kfifo_buffer_setup_ext((dev), (indio_dev), (mode_flags), (setup_ops), NULL) +#define devm_iio_kfifo_buffer_setup(dev, indio_dev, setup_ops) \ + devm_iio_kfifo_buffer_setup_ext((dev), (indio_dev), (setup_ops), NULL) #endif diff --git a/include/linux/iio/trigger.h b/include/linux/iio/trigger.h index 096f68dd2e0c..f6360d9a492d 100644 --- a/include/linux/iio/trigger.h +++ b/include/linux/iio/trigger.h @@ -55,6 +55,7 @@ struct iio_trigger_ops { * @attached_own_device:[INTERN] if we are using our own device as trigger, * i.e. if we registered a poll function to the same * device as the one providing the trigger. + * @reenable_work: [INTERN] work item used to ensure reenable can sleep. **/ struct iio_trigger { const struct iio_trigger_ops *ops; @@ -74,6 +75,7 @@ struct iio_trigger { unsigned long pool[BITS_TO_LONGS(CONFIG_IIO_CONSUMERS_PER_TRIGGER)]; struct mutex pool_lock; bool attached_own_device; + struct work_struct reenable_work; }; @@ -91,6 +93,11 @@ static inline void iio_trigger_put(struct iio_trigger *trig) static inline struct iio_trigger *iio_trigger_get(struct iio_trigger *trig) { get_device(&trig->dev); + + WARN_ONCE(list_empty(&trig->list), + "Getting non-registered iio trigger %s is prohibited\n", + trig->name); + __module_get(trig->owner); return trig; @@ -124,16 +131,10 @@ static inline void *iio_trigger_get_drvdata(struct iio_trigger *trig) * iio_trigger_register() - register a trigger with the IIO core * @trig_info: trigger to be registered **/ -#define iio_trigger_register(trig_info) \ - __iio_trigger_register((trig_info), THIS_MODULE) -int __iio_trigger_register(struct iio_trigger *trig_info, - struct module *this_mod); +int iio_trigger_register(struct iio_trigger *trig_info); -#define devm_iio_trigger_register(dev, trig_info) \ - __devm_iio_trigger_register((dev), (trig_info), THIS_MODULE) -int __devm_iio_trigger_register(struct device *dev, - struct iio_trigger *trig_info, - struct module *this_mod); +int devm_iio_trigger_register(struct device *dev, + struct iio_trigger *trig_info); /** * iio_trigger_unregister() - unregister a trigger from the core @@ -161,8 +162,13 @@ void iio_trigger_poll_chained(struct iio_trigger *trig); irqreturn_t iio_trigger_generic_data_rdy_poll(int irq, void *private); -__printf(2, 3) -struct iio_trigger *iio_trigger_alloc(struct device *parent, const char *fmt, ...); +#define iio_trigger_alloc(parent, fmt, ...) \ + __iio_trigger_alloc((parent), THIS_MODULE, (fmt), ##__VA_ARGS__) + +__printf(3, 4) +struct iio_trigger *__iio_trigger_alloc(struct device *parent, + struct module *this_mod, + const char *fmt, ...); void iio_trigger_free(struct iio_trigger *trig); /** diff --git a/include/linux/iio/types.h b/include/linux/iio/types.h index 84b3f8175cc6..82faa98c719a 100644 --- a/include/linux/iio/types.h +++ b/include/linux/iio/types.h @@ -17,6 +17,8 @@ enum iio_event_info { IIO_EV_INFO_HIGH_PASS_FILTER_3DB, IIO_EV_INFO_LOW_PASS_FILTER_3DB, IIO_EV_INFO_TIMEOUT, + IIO_EV_INFO_RESET_TIMEOUT, + IIO_EV_INFO_TAP2_MIN_DELAY, }; #define IIO_VAL_INT 1 @@ -24,6 +26,7 @@ enum iio_event_info { #define IIO_VAL_INT_PLUS_NANO 3 #define IIO_VAL_INT_PLUS_MICRO_DB 4 #define IIO_VAL_INT_MULTIPLE 5 +#define IIO_VAL_INT_64 6 /* 64-bit data, val is lower 32 bits */ #define IIO_VAL_FRACTIONAL 10 #define IIO_VAL_FRACTIONAL_LOG2 11 #define IIO_VAL_CHAR 12 @@ -62,6 +65,7 @@ enum iio_chan_info_enum { IIO_CHAN_INFO_OVERSAMPLING_RATIO, IIO_CHAN_INFO_THERMOCOUPLE_TYPE, IIO_CHAN_INFO_CALIBAMBIENT, + IIO_CHAN_INFO_ZEROPOINT, }; #endif /* _IIO_TYPES_H_ */ diff --git a/include/linux/ima.h b/include/linux/ima.h index 426b1744215e..81708ca0ebc7 100644 --- a/include/linux/ima.h +++ b/include/linux/ima.h @@ -140,6 +140,11 @@ static inline int ima_measure_critical_data(const char *event_label, #endif /* CONFIG_IMA */ +#ifdef CONFIG_HAVE_IMA_KEXEC +int __init ima_free_kexec_buffer(void); +int __init ima_get_kexec_buffer(void **addr, size_t *size); +#endif + #ifdef CONFIG_IMA_SECURE_AND_OR_TRUSTED_BOOT extern bool arch_ima_get_secureboot(void); extern const char * const *arch_get_ima_policy(void); diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index 674aeead6260..ddb27fc0ee8c 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -131,7 +131,7 @@ static inline void ipv4_devconf_setall(struct in_device *in_dev) IN_DEV_ORCONF((in_dev), IGNORE_ROUTES_WITH_LINKDOWN) #define IN_DEV_ARPFILTER(in_dev) IN_DEV_ORCONF((in_dev), ARPFILTER) -#define IN_DEV_ARP_ACCEPT(in_dev) IN_DEV_ORCONF((in_dev), ARP_ACCEPT) +#define IN_DEV_ARP_ACCEPT(in_dev) IN_DEV_MAXCONF((in_dev), ARP_ACCEPT) #define IN_DEV_ARP_ANNOUNCE(in_dev) IN_DEV_MAXCONF((in_dev), ARP_ANNOUNCE) #define IN_DEV_ARP_IGNORE(in_dev) IN_DEV_MAXCONF((in_dev), ARP_IGNORE) #define IN_DEV_ARP_NOTIFY(in_dev) IN_DEV_MAXCONF((in_dev), ARP_NOTIFY) @@ -150,6 +150,7 @@ struct in_ifaddr { __be32 ifa_broadcast; unsigned char ifa_scope; unsigned char ifa_prefixlen; + unsigned char ifa_proto; __u32 ifa_flags; char ifa_label[IFNAMSIZ]; diff --git a/include/linux/init.h b/include/linux/init.h index d82b4b2e1d25..077d7f93b402 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -47,7 +47,7 @@ /* These are for everybody (although not all archs will actually discard it in modules) */ -#define __init __section(".init.text") __cold __latent_entropy __noinitretpoline __nocfi +#define __init __section(".init.text") __cold __latent_entropy __noinitretpoline #define __initdata __section(".init.data") #define __initconst __section(".init.rodata") #define __exitdata __section(".exit.data") @@ -134,7 +134,7 @@ static inline initcall_t initcall_from_entry(initcall_entry_t *entry) extern initcall_entry_t __con_initcall_start[], __con_initcall_end[]; -/* Used for contructor calls. */ +/* Used for constructor calls. */ typedef void (*ctor_fn_t)(void); struct file_system_type; @@ -220,8 +220,8 @@ extern bool initcall_debug; __initcall_name(initstub, __iid, id) #define __define_initcall_stub(__stub, fn) \ - int __init __cficanonical __stub(void); \ - int __init __cficanonical __stub(void) \ + int __init __stub(void); \ + int __init __stub(void) \ { \ return fn(); \ } \ @@ -320,12 +320,19 @@ struct obs_kernel_param { __aligned(__alignof__(struct obs_kernel_param)) \ = { __setup_str_##unique_id, fn, early } +/* + * NOTE: __setup functions return values: + * @fn returns 1 (or non-zero) if the option argument is "handled" + * and returns 0 if the option argument is "not handled". + */ #define __setup(str, fn) \ __setup_param(str, fn, fn, 0) /* - * NOTE: fn is as per module_param, not __setup! - * Emits warning if fn returns non-zero. + * NOTE: @fn is as per module_param, not __setup! + * I.e., @fn returns 0 for no error or non-zero for error + * (possibly @fn returns a -errno value, but it does not matter). + * Emits warning if @fn returns non-zero. */ #define early_param(str, fn) \ __setup_param(str, fn, fn, 1) diff --git a/include/linux/initrd.h b/include/linux/initrd.h index 1bbe9af48dc3..f1a1f4c92ded 100644 --- a/include/linux/initrd.h +++ b/include/linux/initrd.h @@ -29,8 +29,6 @@ static inline void wait_for_initramfs(void) {} extern phys_addr_t phys_initrd_start; extern unsigned long phys_initrd_size; -extern unsigned int real_root_dev; - extern char __initramfs_start[]; extern unsigned long __initramfs_size; diff --git a/include/linux/inotify.h b/include/linux/inotify.h index 6a24905f6e1e..8d20caa1b268 100644 --- a/include/linux/inotify.h +++ b/include/linux/inotify.h @@ -7,11 +7,8 @@ #ifndef _LINUX_INOTIFY_H #define _LINUX_INOTIFY_H -#include <linux/sysctl.h> #include <uapi/linux/inotify.h> -extern struct ctl_table inotify_table[]; /* for sysctl */ - #define ALL_INOTIFY_BITS (IN_ACCESS | IN_MODIFY | IN_ATTRIB | IN_CLOSE_WRITE | \ IN_CLOSE_NOWRITE | IN_OPEN | IN_MOVED_FROM | \ IN_MOVED_TO | IN_CREATE | IN_DELETE | \ diff --git a/include/linux/input.h b/include/linux/input.h index 0354b298d874..49790c1bd2c4 100644 --- a/include/linux/input.h +++ b/include/linux/input.h @@ -475,6 +475,8 @@ static inline void input_set_events_per_packet(struct input_dev *dev, int n_even void input_alloc_absinfo(struct input_dev *dev); void input_set_abs_params(struct input_dev *dev, unsigned int axis, int min, int max, int fuzz, int flat); +void input_copy_abs(struct input_dev *dst, unsigned int dst_axis, + const struct input_dev *src, unsigned int src_axis); #define INPUT_GENERATE_ABS_ACCESSORS(_suffix, _item) \ static inline int input_abs_get_##_suffix(struct input_dev *dev, \ diff --git a/include/linux/input/auo-pixcir-ts.h b/include/linux/input/auo-pixcir-ts.h deleted file mode 100644 index ed0776997a7a..000000000000 --- a/include/linux/input/auo-pixcir-ts.h +++ /dev/null @@ -1,44 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Driver for AUO in-cell touchscreens - * - * Copyright (c) 2011 Heiko Stuebner <heiko@sntech.de> - * - * based on auo_touch.h from Dell Streak kernel - * - * Copyright (c) 2008 QUALCOMM Incorporated. - * Copyright (c) 2008 QUALCOMM USA, INC. - */ - -#ifndef __AUO_PIXCIR_TS_H__ -#define __AUO_PIXCIR_TS_H__ - -/* - * Interrupt modes: - * periodical: interrupt is asserted periodicaly - * compare coordinates: interrupt is asserted when coordinates change - * indicate touch: interrupt is asserted during touch - */ -#define AUO_PIXCIR_INT_PERIODICAL 0x00 -#define AUO_PIXCIR_INT_COMP_COORD 0x01 -#define AUO_PIXCIR_INT_TOUCH_IND 0x02 - -/* - * @gpio_int interrupt gpio - * @int_setting one of AUO_PIXCIR_INT_* - * @init_hw hardwarespecific init - * @exit_hw hardwarespecific shutdown - * @x_max x-resolution - * @y_max y-resolution - */ -struct auo_pixcir_ts_platdata { - int gpio_int; - int gpio_rst; - - int int_setting; - - unsigned int x_max; - unsigned int y_max; -}; - -#endif diff --git a/include/linux/input/elan-i2c-ids.h b/include/linux/input/elan-i2c-ids.h index 520858d12680..51cca17ee94c 100644 --- a/include/linux/input/elan-i2c-ids.h +++ b/include/linux/input/elan-i2c-ids.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * Elan I2C/SMBus Touchpad device whitelist * @@ -11,10 +12,6 @@ * copyright (c) 2011-2012 Cypress Semiconductor, Inc. * copyright (c) 2011-2012 Google, Inc. * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License version 2 as published - * by the Free Software Foundation. - * * Trademarks are the property of their respective owners. */ diff --git a/include/linux/input/vivaldi-fmap.h b/include/linux/input/vivaldi-fmap.h new file mode 100644 index 000000000000..7e4b7023bf04 --- /dev/null +++ b/include/linux/input/vivaldi-fmap.h @@ -0,0 +1,27 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _VIVALDI_FMAP_H +#define _VIVALDI_FMAP_H + +#include <linux/types.h> + +#define VIVALDI_MAX_FUNCTION_ROW_KEYS 24 + +/** + * struct vivaldi_data - Function row map data for ChromeOS Vivaldi keyboards + * @function_row_physmap: An array of scancodes or their equivalent (HID usage + * codes, encoded rows/columns, etc) for the top + * row function keys, in an order from left to right + * @num_function_row_keys: The number of top row keys in a custom keyboard + * + * This structure is supposed to be used by ChromeOS keyboards using + * the Vivaldi keyboard function row design. + */ +struct vivaldi_data { + u32 function_row_physmap[VIVALDI_MAX_FUNCTION_ROW_KEYS]; + unsigned int num_function_row_keys; +}; + +ssize_t vivaldi_function_row_physmap_show(const struct vivaldi_data *data, + char *buf); + +#endif /* _VIVALDI_FMAP_H */ diff --git a/include/linux/instrumentation.h b/include/linux/instrumentation.h index 24359b4a9605..bc7babe91b2e 100644 --- a/include/linux/instrumentation.h +++ b/include/linux/instrumentation.h @@ -2,7 +2,7 @@ #ifndef __LINUX_INSTRUMENTATION_H #define __LINUX_INSTRUMENTATION_H -#if defined(CONFIG_DEBUG_ENTRY) && defined(CONFIG_STACK_VALIDATION) +#ifdef CONFIG_NOINSTR_VALIDATION #include <linux/stringify.h> @@ -53,9 +53,9 @@ ".popsection\n\t" : : "i" (c)); \ }) #define instrumentation_end() __instrumentation_end(__COUNTER__) -#else +#else /* !CONFIG_NOINSTR_VALIDATION */ # define instrumentation_begin() do { } while(0) # define instrumentation_end() do { } while(0) -#endif +#endif /* CONFIG_NOINSTR_VALIDATION */ #endif /* __LINUX_INSTRUMENTATION_H */ diff --git a/include/linux/instrumented.h b/include/linux/instrumented.h index 42faebbaa202..501fa8486749 100644 --- a/include/linux/instrumented.h +++ b/include/linux/instrumented.h @@ -2,7 +2,7 @@ /* * This header provides generic wrappers for memory access instrumentation that - * the compiler cannot emit for: KASAN, KCSAN. + * the compiler cannot emit for: KASAN, KCSAN, KMSAN. */ #ifndef _LINUX_INSTRUMENTED_H #define _LINUX_INSTRUMENTED_H @@ -10,6 +10,7 @@ #include <linux/compiler.h> #include <linux/kasan-checks.h> #include <linux/kcsan-checks.h> +#include <linux/kmsan-checks.h> #include <linux/types.h> /** @@ -117,10 +118,11 @@ instrument_copy_to_user(void __user *to, const void *from, unsigned long n) { kasan_check_read(from, n); kcsan_check_read(from, n); + kmsan_copy_to_user(to, from, n, 0); } /** - * instrument_copy_from_user - instrument writes of copy_from_user + * instrument_copy_from_user_before - add instrumentation before copy_from_user * * Instrument writes to kernel memory, that are due to copy_from_user (and * variants). The instrumentation should be inserted before the accesses. @@ -130,10 +132,61 @@ instrument_copy_to_user(void __user *to, const void *from, unsigned long n) * @n number of bytes to copy */ static __always_inline void -instrument_copy_from_user(const void *to, const void __user *from, unsigned long n) +instrument_copy_from_user_before(const void *to, const void __user *from, unsigned long n) { kasan_check_write(to, n); kcsan_check_write(to, n); } +/** + * instrument_copy_from_user_after - add instrumentation after copy_from_user + * + * Instrument writes to kernel memory, that are due to copy_from_user (and + * variants). The instrumentation should be inserted after the accesses. + * + * @to destination address + * @from source address + * @n number of bytes to copy + * @left number of bytes not copied (as returned by copy_from_user) + */ +static __always_inline void +instrument_copy_from_user_after(const void *to, const void __user *from, + unsigned long n, unsigned long left) +{ + kmsan_unpoison_memory(to, n - left); +} + +/** + * instrument_get_user() - add instrumentation to get_user()-like macros + * + * get_user() and friends are fragile, so it may depend on the implementation + * whether the instrumentation happens before or after the data is copied from + * the userspace. + * + * @to destination variable, may not be address-taken + */ +#define instrument_get_user(to) \ +({ \ + u64 __tmp = (u64)(to); \ + kmsan_unpoison_memory(&__tmp, sizeof(__tmp)); \ + to = __tmp; \ +}) + + +/** + * instrument_put_user() - add instrumentation to put_user()-like macros + * + * put_user() and friends are fragile, so it may depend on the implementation + * whether the instrumentation happens before or after the data is copied from + * the userspace. + * + * @from source address + * @ptr userspace pointer to copy to + * @size number of bytes to copy + */ +#define instrument_put_user(from, ptr, size) \ +({ \ + kmsan_copy_to_user(ptr, &from, sizeof(from), 0); \ +}) + #endif /* _LINUX_INSTRUMENTED_H */ diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h deleted file mode 100644 index 69230fd695ea..000000000000 --- a/include/linux/intel-iommu.h +++ /dev/null @@ -1,863 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright © 2006-2015, Intel Corporation. - * - * Authors: Ashok Raj <ashok.raj@intel.com> - * Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com> - * David Woodhouse <David.Woodhouse@intel.com> - */ - -#ifndef _INTEL_IOMMU_H_ -#define _INTEL_IOMMU_H_ - -#include <linux/types.h> -#include <linux/iova.h> -#include <linux/io.h> -#include <linux/idr.h> -#include <linux/mmu_notifier.h> -#include <linux/list.h> -#include <linux/iommu.h> -#include <linux/io-64-nonatomic-lo-hi.h> -#include <linux/dmar.h> -#include <linux/ioasid.h> -#include <linux/bitfield.h> - -#include <asm/cacheflush.h> -#include <asm/iommu.h> - -/* - * VT-d hardware uses 4KiB page size regardless of host page size. - */ -#define VTD_PAGE_SHIFT (12) -#define VTD_PAGE_SIZE (1UL << VTD_PAGE_SHIFT) -#define VTD_PAGE_MASK (((u64)-1) << VTD_PAGE_SHIFT) -#define VTD_PAGE_ALIGN(addr) (((addr) + VTD_PAGE_SIZE - 1) & VTD_PAGE_MASK) - -#define VTD_STRIDE_SHIFT (9) -#define VTD_STRIDE_MASK (((u64)-1) << VTD_STRIDE_SHIFT) - -#define DMA_PTE_READ BIT_ULL(0) -#define DMA_PTE_WRITE BIT_ULL(1) -#define DMA_PTE_LARGE_PAGE BIT_ULL(7) -#define DMA_PTE_SNP BIT_ULL(11) - -#define DMA_FL_PTE_PRESENT BIT_ULL(0) -#define DMA_FL_PTE_US BIT_ULL(2) -#define DMA_FL_PTE_ACCESS BIT_ULL(5) -#define DMA_FL_PTE_DIRTY BIT_ULL(6) -#define DMA_FL_PTE_XD BIT_ULL(63) - -#define ADDR_WIDTH_5LEVEL (57) -#define ADDR_WIDTH_4LEVEL (48) - -#define CONTEXT_TT_MULTI_LEVEL 0 -#define CONTEXT_TT_DEV_IOTLB 1 -#define CONTEXT_TT_PASS_THROUGH 2 -#define CONTEXT_PASIDE BIT_ULL(3) - -/* - * Intel IOMMU register specification per version 1.0 public spec. - */ -#define DMAR_VER_REG 0x0 /* Arch version supported by this IOMMU */ -#define DMAR_CAP_REG 0x8 /* Hardware supported capabilities */ -#define DMAR_ECAP_REG 0x10 /* Extended capabilities supported */ -#define DMAR_GCMD_REG 0x18 /* Global command register */ -#define DMAR_GSTS_REG 0x1c /* Global status register */ -#define DMAR_RTADDR_REG 0x20 /* Root entry table */ -#define DMAR_CCMD_REG 0x28 /* Context command reg */ -#define DMAR_FSTS_REG 0x34 /* Fault Status register */ -#define DMAR_FECTL_REG 0x38 /* Fault control register */ -#define DMAR_FEDATA_REG 0x3c /* Fault event interrupt data register */ -#define DMAR_FEADDR_REG 0x40 /* Fault event interrupt addr register */ -#define DMAR_FEUADDR_REG 0x44 /* Upper address register */ -#define DMAR_AFLOG_REG 0x58 /* Advanced Fault control */ -#define DMAR_PMEN_REG 0x64 /* Enable Protected Memory Region */ -#define DMAR_PLMBASE_REG 0x68 /* PMRR Low addr */ -#define DMAR_PLMLIMIT_REG 0x6c /* PMRR low limit */ -#define DMAR_PHMBASE_REG 0x70 /* pmrr high base addr */ -#define DMAR_PHMLIMIT_REG 0x78 /* pmrr high limit */ -#define DMAR_IQH_REG 0x80 /* Invalidation queue head register */ -#define DMAR_IQT_REG 0x88 /* Invalidation queue tail register */ -#define DMAR_IQ_SHIFT 4 /* Invalidation queue head/tail shift */ -#define DMAR_IQA_REG 0x90 /* Invalidation queue addr register */ -#define DMAR_ICS_REG 0x9c /* Invalidation complete status register */ -#define DMAR_IQER_REG 0xb0 /* Invalidation queue error record register */ -#define DMAR_IRTA_REG 0xb8 /* Interrupt remapping table addr register */ -#define DMAR_PQH_REG 0xc0 /* Page request queue head register */ -#define DMAR_PQT_REG 0xc8 /* Page request queue tail register */ -#define DMAR_PQA_REG 0xd0 /* Page request queue address register */ -#define DMAR_PRS_REG 0xdc /* Page request status register */ -#define DMAR_PECTL_REG 0xe0 /* Page request event control register */ -#define DMAR_PEDATA_REG 0xe4 /* Page request event interrupt data register */ -#define DMAR_PEADDR_REG 0xe8 /* Page request event interrupt addr register */ -#define DMAR_PEUADDR_REG 0xec /* Page request event Upper address register */ -#define DMAR_MTRRCAP_REG 0x100 /* MTRR capability register */ -#define DMAR_MTRRDEF_REG 0x108 /* MTRR default type register */ -#define DMAR_MTRR_FIX64K_00000_REG 0x120 /* MTRR Fixed range registers */ -#define DMAR_MTRR_FIX16K_80000_REG 0x128 -#define DMAR_MTRR_FIX16K_A0000_REG 0x130 -#define DMAR_MTRR_FIX4K_C0000_REG 0x138 -#define DMAR_MTRR_FIX4K_C8000_REG 0x140 -#define DMAR_MTRR_FIX4K_D0000_REG 0x148 -#define DMAR_MTRR_FIX4K_D8000_REG 0x150 -#define DMAR_MTRR_FIX4K_E0000_REG 0x158 -#define DMAR_MTRR_FIX4K_E8000_REG 0x160 -#define DMAR_MTRR_FIX4K_F0000_REG 0x168 -#define DMAR_MTRR_FIX4K_F8000_REG 0x170 -#define DMAR_MTRR_PHYSBASE0_REG 0x180 /* MTRR Variable range registers */ -#define DMAR_MTRR_PHYSMASK0_REG 0x188 -#define DMAR_MTRR_PHYSBASE1_REG 0x190 -#define DMAR_MTRR_PHYSMASK1_REG 0x198 -#define DMAR_MTRR_PHYSBASE2_REG 0x1a0 -#define DMAR_MTRR_PHYSMASK2_REG 0x1a8 -#define DMAR_MTRR_PHYSBASE3_REG 0x1b0 -#define DMAR_MTRR_PHYSMASK3_REG 0x1b8 -#define DMAR_MTRR_PHYSBASE4_REG 0x1c0 -#define DMAR_MTRR_PHYSMASK4_REG 0x1c8 -#define DMAR_MTRR_PHYSBASE5_REG 0x1d0 -#define DMAR_MTRR_PHYSMASK5_REG 0x1d8 -#define DMAR_MTRR_PHYSBASE6_REG 0x1e0 -#define DMAR_MTRR_PHYSMASK6_REG 0x1e8 -#define DMAR_MTRR_PHYSBASE7_REG 0x1f0 -#define DMAR_MTRR_PHYSMASK7_REG 0x1f8 -#define DMAR_MTRR_PHYSBASE8_REG 0x200 -#define DMAR_MTRR_PHYSMASK8_REG 0x208 -#define DMAR_MTRR_PHYSBASE9_REG 0x210 -#define DMAR_MTRR_PHYSMASK9_REG 0x218 -#define DMAR_VCCAP_REG 0xe30 /* Virtual command capability register */ -#define DMAR_VCMD_REG 0xe00 /* Virtual command register */ -#define DMAR_VCRSP_REG 0xe10 /* Virtual command response register */ - -#define DMAR_IQER_REG_IQEI(reg) FIELD_GET(GENMASK_ULL(3, 0), reg) -#define DMAR_IQER_REG_ITESID(reg) FIELD_GET(GENMASK_ULL(47, 32), reg) -#define DMAR_IQER_REG_ICESID(reg) FIELD_GET(GENMASK_ULL(63, 48), reg) - -#define OFFSET_STRIDE (9) - -#define dmar_readq(a) readq(a) -#define dmar_writeq(a,v) writeq(v,a) -#define dmar_readl(a) readl(a) -#define dmar_writel(a, v) writel(v, a) - -#define DMAR_VER_MAJOR(v) (((v) & 0xf0) >> 4) -#define DMAR_VER_MINOR(v) ((v) & 0x0f) - -/* - * Decoding Capability Register - */ -#define cap_5lp_support(c) (((c) >> 60) & 1) -#define cap_pi_support(c) (((c) >> 59) & 1) -#define cap_fl1gp_support(c) (((c) >> 56) & 1) -#define cap_read_drain(c) (((c) >> 55) & 1) -#define cap_write_drain(c) (((c) >> 54) & 1) -#define cap_max_amask_val(c) (((c) >> 48) & 0x3f) -#define cap_num_fault_regs(c) ((((c) >> 40) & 0xff) + 1) -#define cap_pgsel_inv(c) (((c) >> 39) & 1) - -#define cap_super_page_val(c) (((c) >> 34) & 0xf) -#define cap_super_offset(c) (((find_first_bit(&cap_super_page_val(c), 4)) \ - * OFFSET_STRIDE) + 21) - -#define cap_fault_reg_offset(c) ((((c) >> 24) & 0x3ff) * 16) -#define cap_max_fault_reg_offset(c) \ - (cap_fault_reg_offset(c) + cap_num_fault_regs(c) * 16) - -#define cap_zlr(c) (((c) >> 22) & 1) -#define cap_isoch(c) (((c) >> 23) & 1) -#define cap_mgaw(c) ((((c) >> 16) & 0x3f) + 1) -#define cap_sagaw(c) (((c) >> 8) & 0x1f) -#define cap_caching_mode(c) (((c) >> 7) & 1) -#define cap_phmr(c) (((c) >> 6) & 1) -#define cap_plmr(c) (((c) >> 5) & 1) -#define cap_rwbf(c) (((c) >> 4) & 1) -#define cap_afl(c) (((c) >> 3) & 1) -#define cap_ndoms(c) (((unsigned long)1) << (4 + 2 * ((c) & 0x7))) -/* - * Extended Capability Register - */ - -#define ecap_rps(e) (((e) >> 49) & 0x1) -#define ecap_smpwc(e) (((e) >> 48) & 0x1) -#define ecap_flts(e) (((e) >> 47) & 0x1) -#define ecap_slts(e) (((e) >> 46) & 0x1) -#define ecap_slads(e) (((e) >> 45) & 0x1) -#define ecap_vcs(e) (((e) >> 44) & 0x1) -#define ecap_smts(e) (((e) >> 43) & 0x1) -#define ecap_dit(e) (((e) >> 41) & 0x1) -#define ecap_pds(e) (((e) >> 42) & 0x1) -#define ecap_pasid(e) (((e) >> 40) & 0x1) -#define ecap_pss(e) (((e) >> 35) & 0x1f) -#define ecap_eafs(e) (((e) >> 34) & 0x1) -#define ecap_nwfs(e) (((e) >> 33) & 0x1) -#define ecap_srs(e) (((e) >> 31) & 0x1) -#define ecap_ers(e) (((e) >> 30) & 0x1) -#define ecap_prs(e) (((e) >> 29) & 0x1) -#define ecap_broken_pasid(e) (((e) >> 28) & 0x1) -#define ecap_dis(e) (((e) >> 27) & 0x1) -#define ecap_nest(e) (((e) >> 26) & 0x1) -#define ecap_mts(e) (((e) >> 25) & 0x1) -#define ecap_ecs(e) (((e) >> 24) & 0x1) -#define ecap_iotlb_offset(e) ((((e) >> 8) & 0x3ff) * 16) -#define ecap_max_iotlb_offset(e) (ecap_iotlb_offset(e) + 16) -#define ecap_coherent(e) ((e) & 0x1) -#define ecap_qis(e) ((e) & 0x2) -#define ecap_pass_through(e) (((e) >> 6) & 0x1) -#define ecap_eim_support(e) (((e) >> 4) & 0x1) -#define ecap_ir_support(e) (((e) >> 3) & 0x1) -#define ecap_dev_iotlb_support(e) (((e) >> 2) & 0x1) -#define ecap_max_handle_mask(e) (((e) >> 20) & 0xf) -#define ecap_sc_support(e) (((e) >> 7) & 0x1) /* Snooping Control */ - -/* Virtual command interface capability */ -#define vccap_pasid(v) (((v) & DMA_VCS_PAS)) /* PASID allocation */ - -/* IOTLB_REG */ -#define DMA_TLB_FLUSH_GRANU_OFFSET 60 -#define DMA_TLB_GLOBAL_FLUSH (((u64)1) << 60) -#define DMA_TLB_DSI_FLUSH (((u64)2) << 60) -#define DMA_TLB_PSI_FLUSH (((u64)3) << 60) -#define DMA_TLB_IIRG(type) ((type >> 60) & 3) -#define DMA_TLB_IAIG(val) (((val) >> 57) & 3) -#define DMA_TLB_READ_DRAIN (((u64)1) << 49) -#define DMA_TLB_WRITE_DRAIN (((u64)1) << 48) -#define DMA_TLB_DID(id) (((u64)((id) & 0xffff)) << 32) -#define DMA_TLB_IVT (((u64)1) << 63) -#define DMA_TLB_IH_NONLEAF (((u64)1) << 6) -#define DMA_TLB_MAX_SIZE (0x3f) - -/* INVALID_DESC */ -#define DMA_CCMD_INVL_GRANU_OFFSET 61 -#define DMA_ID_TLB_GLOBAL_FLUSH (((u64)1) << 4) -#define DMA_ID_TLB_DSI_FLUSH (((u64)2) << 4) -#define DMA_ID_TLB_PSI_FLUSH (((u64)3) << 4) -#define DMA_ID_TLB_READ_DRAIN (((u64)1) << 7) -#define DMA_ID_TLB_WRITE_DRAIN (((u64)1) << 6) -#define DMA_ID_TLB_DID(id) (((u64)((id & 0xffff) << 16))) -#define DMA_ID_TLB_IH_NONLEAF (((u64)1) << 6) -#define DMA_ID_TLB_ADDR(addr) (addr) -#define DMA_ID_TLB_ADDR_MASK(mask) (mask) - -/* PMEN_REG */ -#define DMA_PMEN_EPM (((u32)1)<<31) -#define DMA_PMEN_PRS (((u32)1)<<0) - -/* GCMD_REG */ -#define DMA_GCMD_TE (((u32)1) << 31) -#define DMA_GCMD_SRTP (((u32)1) << 30) -#define DMA_GCMD_SFL (((u32)1) << 29) -#define DMA_GCMD_EAFL (((u32)1) << 28) -#define DMA_GCMD_WBF (((u32)1) << 27) -#define DMA_GCMD_QIE (((u32)1) << 26) -#define DMA_GCMD_SIRTP (((u32)1) << 24) -#define DMA_GCMD_IRE (((u32) 1) << 25) -#define DMA_GCMD_CFI (((u32) 1) << 23) - -/* GSTS_REG */ -#define DMA_GSTS_TES (((u32)1) << 31) -#define DMA_GSTS_RTPS (((u32)1) << 30) -#define DMA_GSTS_FLS (((u32)1) << 29) -#define DMA_GSTS_AFLS (((u32)1) << 28) -#define DMA_GSTS_WBFS (((u32)1) << 27) -#define DMA_GSTS_QIES (((u32)1) << 26) -#define DMA_GSTS_IRTPS (((u32)1) << 24) -#define DMA_GSTS_IRES (((u32)1) << 25) -#define DMA_GSTS_CFIS (((u32)1) << 23) - -/* DMA_RTADDR_REG */ -#define DMA_RTADDR_RTT (((u64)1) << 11) -#define DMA_RTADDR_SMT (((u64)1) << 10) - -/* CCMD_REG */ -#define DMA_CCMD_ICC (((u64)1) << 63) -#define DMA_CCMD_GLOBAL_INVL (((u64)1) << 61) -#define DMA_CCMD_DOMAIN_INVL (((u64)2) << 61) -#define DMA_CCMD_DEVICE_INVL (((u64)3) << 61) -#define DMA_CCMD_FM(m) (((u64)((m) & 0x3)) << 32) -#define DMA_CCMD_MASK_NOBIT 0 -#define DMA_CCMD_MASK_1BIT 1 -#define DMA_CCMD_MASK_2BIT 2 -#define DMA_CCMD_MASK_3BIT 3 -#define DMA_CCMD_SID(s) (((u64)((s) & 0xffff)) << 16) -#define DMA_CCMD_DID(d) ((u64)((d) & 0xffff)) - -/* FECTL_REG */ -#define DMA_FECTL_IM (((u32)1) << 31) - -/* FSTS_REG */ -#define DMA_FSTS_PFO (1 << 0) /* Primary Fault Overflow */ -#define DMA_FSTS_PPF (1 << 1) /* Primary Pending Fault */ -#define DMA_FSTS_IQE (1 << 4) /* Invalidation Queue Error */ -#define DMA_FSTS_ICE (1 << 5) /* Invalidation Completion Error */ -#define DMA_FSTS_ITE (1 << 6) /* Invalidation Time-out Error */ -#define DMA_FSTS_PRO (1 << 7) /* Page Request Overflow */ -#define dma_fsts_fault_record_index(s) (((s) >> 8) & 0xff) - -/* FRCD_REG, 32 bits access */ -#define DMA_FRCD_F (((u32)1) << 31) -#define dma_frcd_type(d) ((d >> 30) & 1) -#define dma_frcd_fault_reason(c) (c & 0xff) -#define dma_frcd_source_id(c) (c & 0xffff) -#define dma_frcd_pasid_value(c) (((c) >> 8) & 0xfffff) -#define dma_frcd_pasid_present(c) (((c) >> 31) & 1) -/* low 64 bit */ -#define dma_frcd_page_addr(d) (d & (((u64)-1) << PAGE_SHIFT)) - -/* PRS_REG */ -#define DMA_PRS_PPR ((u32)1) -#define DMA_PRS_PRO ((u32)2) - -#define DMA_VCS_PAS ((u64)1) - -#define IOMMU_WAIT_OP(iommu, offset, op, cond, sts) \ -do { \ - cycles_t start_time = get_cycles(); \ - while (1) { \ - sts = op(iommu->reg + offset); \ - if (cond) \ - break; \ - if (DMAR_OPERATION_TIMEOUT < (get_cycles() - start_time))\ - panic("DMAR hardware is malfunctioning\n"); \ - cpu_relax(); \ - } \ -} while (0) - -#define QI_LENGTH 256 /* queue length */ - -enum { - QI_FREE, - QI_IN_USE, - QI_DONE, - QI_ABORT -}; - -#define QI_CC_TYPE 0x1 -#define QI_IOTLB_TYPE 0x2 -#define QI_DIOTLB_TYPE 0x3 -#define QI_IEC_TYPE 0x4 -#define QI_IWD_TYPE 0x5 -#define QI_EIOTLB_TYPE 0x6 -#define QI_PC_TYPE 0x7 -#define QI_DEIOTLB_TYPE 0x8 -#define QI_PGRP_RESP_TYPE 0x9 -#define QI_PSTRM_RESP_TYPE 0xa - -#define QI_IEC_SELECTIVE (((u64)1) << 4) -#define QI_IEC_IIDEX(idx) (((u64)(idx & 0xffff) << 32)) -#define QI_IEC_IM(m) (((u64)(m & 0x1f) << 27)) - -#define QI_IWD_STATUS_DATA(d) (((u64)d) << 32) -#define QI_IWD_STATUS_WRITE (((u64)1) << 5) -#define QI_IWD_FENCE (((u64)1) << 6) -#define QI_IWD_PRQ_DRAIN (((u64)1) << 7) - -#define QI_IOTLB_DID(did) (((u64)did) << 16) -#define QI_IOTLB_DR(dr) (((u64)dr) << 7) -#define QI_IOTLB_DW(dw) (((u64)dw) << 6) -#define QI_IOTLB_GRAN(gran) (((u64)gran) >> (DMA_TLB_FLUSH_GRANU_OFFSET-4)) -#define QI_IOTLB_ADDR(addr) (((u64)addr) & VTD_PAGE_MASK) -#define QI_IOTLB_IH(ih) (((u64)ih) << 6) -#define QI_IOTLB_AM(am) (((u8)am) & 0x3f) - -#define QI_CC_FM(fm) (((u64)fm) << 48) -#define QI_CC_SID(sid) (((u64)sid) << 32) -#define QI_CC_DID(did) (((u64)did) << 16) -#define QI_CC_GRAN(gran) (((u64)gran) >> (DMA_CCMD_INVL_GRANU_OFFSET-4)) - -#define QI_DEV_IOTLB_SID(sid) ((u64)((sid) & 0xffff) << 32) -#define QI_DEV_IOTLB_QDEP(qdep) (((qdep) & 0x1f) << 16) -#define QI_DEV_IOTLB_ADDR(addr) ((u64)(addr) & VTD_PAGE_MASK) -#define QI_DEV_IOTLB_PFSID(pfsid) (((u64)(pfsid & 0xf) << 12) | \ - ((u64)((pfsid >> 4) & 0xfff) << 52)) -#define QI_DEV_IOTLB_SIZE 1 -#define QI_DEV_IOTLB_MAX_INVS 32 - -#define QI_PC_PASID(pasid) (((u64)pasid) << 32) -#define QI_PC_DID(did) (((u64)did) << 16) -#define QI_PC_GRAN(gran) (((u64)gran) << 4) - -/* PASID cache invalidation granu */ -#define QI_PC_ALL_PASIDS 0 -#define QI_PC_PASID_SEL 1 -#define QI_PC_GLOBAL 3 - -#define QI_EIOTLB_ADDR(addr) ((u64)(addr) & VTD_PAGE_MASK) -#define QI_EIOTLB_IH(ih) (((u64)ih) << 6) -#define QI_EIOTLB_AM(am) (((u64)am) & 0x3f) -#define QI_EIOTLB_PASID(pasid) (((u64)pasid) << 32) -#define QI_EIOTLB_DID(did) (((u64)did) << 16) -#define QI_EIOTLB_GRAN(gran) (((u64)gran) << 4) - -/* QI Dev-IOTLB inv granu */ -#define QI_DEV_IOTLB_GRAN_ALL 1 -#define QI_DEV_IOTLB_GRAN_PASID_SEL 0 - -#define QI_DEV_EIOTLB_ADDR(a) ((u64)(a) & VTD_PAGE_MASK) -#define QI_DEV_EIOTLB_SIZE (((u64)1) << 11) -#define QI_DEV_EIOTLB_PASID(p) ((u64)((p) & 0xfffff) << 32) -#define QI_DEV_EIOTLB_SID(sid) ((u64)((sid) & 0xffff) << 16) -#define QI_DEV_EIOTLB_QDEP(qd) ((u64)((qd) & 0x1f) << 4) -#define QI_DEV_EIOTLB_PFSID(pfsid) (((u64)(pfsid & 0xf) << 12) | \ - ((u64)((pfsid >> 4) & 0xfff) << 52)) -#define QI_DEV_EIOTLB_MAX_INVS 32 - -/* Page group response descriptor QW0 */ -#define QI_PGRP_PASID_P(p) (((u64)(p)) << 4) -#define QI_PGRP_PDP(p) (((u64)(p)) << 5) -#define QI_PGRP_RESP_CODE(res) (((u64)(res)) << 12) -#define QI_PGRP_DID(rid) (((u64)(rid)) << 16) -#define QI_PGRP_PASID(pasid) (((u64)(pasid)) << 32) - -/* Page group response descriptor QW1 */ -#define QI_PGRP_LPIG(x) (((u64)(x)) << 2) -#define QI_PGRP_IDX(idx) (((u64)(idx)) << 3) - - -#define QI_RESP_SUCCESS 0x0 -#define QI_RESP_INVALID 0x1 -#define QI_RESP_FAILURE 0xf - -#define QI_GRAN_NONG_PASID 2 -#define QI_GRAN_PSI_PASID 3 - -#define qi_shift(iommu) (DMAR_IQ_SHIFT + !!ecap_smts((iommu)->ecap)) - -struct qi_desc { - u64 qw0; - u64 qw1; - u64 qw2; - u64 qw3; -}; - -struct q_inval { - raw_spinlock_t q_lock; - void *desc; /* invalidation queue */ - int *desc_status; /* desc status */ - int free_head; /* first free entry */ - int free_tail; /* last free entry */ - int free_cnt; -}; - -struct dmar_pci_notify_info; - -#ifdef CONFIG_IRQ_REMAP -/* 1MB - maximum possible interrupt remapping table size */ -#define INTR_REMAP_PAGE_ORDER 8 -#define INTR_REMAP_TABLE_REG_SIZE 0xf -#define INTR_REMAP_TABLE_REG_SIZE_MASK 0xf - -#define INTR_REMAP_TABLE_ENTRIES 65536 - -struct irq_domain; - -struct ir_table { - struct irte *base; - unsigned long *bitmap; -}; - -void intel_irq_remap_add_device(struct dmar_pci_notify_info *info); -#else -static inline void -intel_irq_remap_add_device(struct dmar_pci_notify_info *info) { } -#endif - -struct iommu_flush { - void (*flush_context)(struct intel_iommu *iommu, u16 did, u16 sid, - u8 fm, u64 type); - void (*flush_iotlb)(struct intel_iommu *iommu, u16 did, u64 addr, - unsigned int size_order, u64 type); -}; - -enum { - SR_DMAR_FECTL_REG, - SR_DMAR_FEDATA_REG, - SR_DMAR_FEADDR_REG, - SR_DMAR_FEUADDR_REG, - MAX_SR_DMAR_REGS -}; - -#define VTD_FLAG_TRANS_PRE_ENABLED (1 << 0) -#define VTD_FLAG_IRQ_REMAP_PRE_ENABLED (1 << 1) -#define VTD_FLAG_SVM_CAPABLE (1 << 2) - -extern int intel_iommu_sm; -extern spinlock_t device_domain_lock; - -#define sm_supported(iommu) (intel_iommu_sm && ecap_smts((iommu)->ecap)) -#define pasid_supported(iommu) (sm_supported(iommu) && \ - ecap_pasid((iommu)->ecap)) - -struct pasid_entry; -struct pasid_state_entry; -struct page_req_dsc; - -/* - * 0: Present - * 1-11: Reserved - * 12-63: Context Ptr (12 - (haw-1)) - * 64-127: Reserved - */ -struct root_entry { - u64 lo; - u64 hi; -}; - -/* - * low 64 bits: - * 0: present - * 1: fault processing disable - * 2-3: translation type - * 12-63: address space root - * high 64 bits: - * 0-2: address width - * 3-6: aval - * 8-23: domain id - */ -struct context_entry { - u64 lo; - u64 hi; -}; - -/* - * When VT-d works in the scalable mode, it allows DMA translation to - * happen through either first level or second level page table. This - * bit marks that the DMA translation for the domain goes through the - * first level page table, otherwise, it goes through the second level. - */ -#define DOMAIN_FLAG_USE_FIRST_LEVEL BIT(1) - -/* - * Domain represents a virtual machine which demands iommu nested - * translation mode support. - */ -#define DOMAIN_FLAG_NESTING_MODE BIT(2) - -struct dmar_domain { - int nid; /* node id */ - - unsigned int iommu_refcnt[DMAR_UNITS_SUPPORTED]; - /* Refcount of devices per iommu */ - - - u16 iommu_did[DMAR_UNITS_SUPPORTED]; - /* Domain ids per IOMMU. Use u16 since - * domain ids are 16 bit wide according - * to VT-d spec, section 9.3 */ - - u8 has_iotlb_device: 1; - u8 iommu_coherency: 1; /* indicate coherency of iommu access */ - u8 iommu_snooping: 1; /* indicate snooping control feature */ - - struct list_head devices; /* all devices' list */ - struct list_head subdevices; /* all subdevices' list */ - struct iova_domain iovad; /* iova's that belong to this domain */ - - struct dma_pte *pgd; /* virtual address */ - int gaw; /* max guest address width */ - - /* adjusted guest address width, 0 is level 2 30-bit */ - int agaw; - - int flags; /* flags to find out type of domain */ - int iommu_superpage;/* Level of superpages supported: - 0 == 4KiB (no superpages), 1 == 2MiB, - 2 == 1GiB, 3 == 512GiB, 4 == 1TiB */ - u64 max_addr; /* maximum mapped address */ - - u32 default_pasid; /* - * The default pasid used for non-SVM - * traffic on mediated devices. - */ - - struct iommu_domain domain; /* generic domain data structure for - iommu core */ -}; - -struct intel_iommu { - void __iomem *reg; /* Pointer to hardware regs, virtual addr */ - u64 reg_phys; /* physical address of hw register set */ - u64 reg_size; /* size of hw register set */ - u64 cap; - u64 ecap; - u64 vccap; - u32 gcmd; /* Holds TE, EAFL. Don't need SRTP, SFL, WBF */ - raw_spinlock_t register_lock; /* protect register handling */ - int seq_id; /* sequence id of the iommu */ - int agaw; /* agaw of this iommu */ - int msagaw; /* max sagaw of this iommu */ - unsigned int irq, pr_irq; - u16 segment; /* PCI segment# */ - unsigned char name[13]; /* Device Name */ - -#ifdef CONFIG_INTEL_IOMMU - unsigned long *domain_ids; /* bitmap of domains */ - struct dmar_domain ***domains; /* ptr to domains */ - spinlock_t lock; /* protect context, domain ids */ - struct root_entry *root_entry; /* virtual address */ - - struct iommu_flush flush; -#endif -#ifdef CONFIG_INTEL_IOMMU_SVM - struct page_req_dsc *prq; - unsigned char prq_name[16]; /* Name for PRQ interrupt */ - struct completion prq_complete; - struct ioasid_allocator_ops pasid_allocator; /* Custom allocator for PASIDs */ -#endif - struct iopf_queue *iopf_queue; - unsigned char iopfq_name[16]; - struct q_inval *qi; /* Queued invalidation info */ - u32 *iommu_state; /* Store iommu states between suspend and resume.*/ - -#ifdef CONFIG_IRQ_REMAP - struct ir_table *ir_table; /* Interrupt remapping info */ - struct irq_domain *ir_domain; - struct irq_domain *ir_msi_domain; -#endif - struct iommu_device iommu; /* IOMMU core code handle */ - int node; - u32 flags; /* Software defined flags */ - - struct dmar_drhd_unit *drhd; - void *perf_statistic; -}; - -/* Per subdevice private data */ -struct subdev_domain_info { - struct list_head link_phys; /* link to phys device siblings */ - struct list_head link_domain; /* link to domain siblings */ - struct device *pdev; /* physical device derived from */ - struct dmar_domain *domain; /* aux-domain */ - int users; /* user count */ -}; - -/* PCI domain-device relationship */ -struct device_domain_info { - struct list_head link; /* link to domain siblings */ - struct list_head global; /* link to global list */ - struct list_head table; /* link to pasid table */ - struct list_head subdevices; /* subdevices sibling */ - u32 segment; /* PCI segment number */ - u8 bus; /* PCI bus number */ - u8 devfn; /* PCI devfn number */ - u16 pfsid; /* SRIOV physical function source ID */ - u8 pasid_supported:3; - u8 pasid_enabled:1; - u8 pri_supported:1; - u8 pri_enabled:1; - u8 ats_supported:1; - u8 ats_enabled:1; - u8 auxd_enabled:1; /* Multiple domains per device */ - u8 ats_qdep; - struct device *dev; /* it's NULL for PCIe-to-PCI bridge */ - struct intel_iommu *iommu; /* IOMMU used by this device */ - struct dmar_domain *domain; /* pointer to domain */ - struct pasid_table *pasid_table; /* pasid table */ -}; - -static inline void __iommu_flush_cache( - struct intel_iommu *iommu, void *addr, int size) -{ - if (!ecap_coherent(iommu->ecap)) - clflush_cache_range(addr, size); -} - -/* Convert generic struct iommu_domain to private struct dmar_domain */ -static inline struct dmar_domain *to_dmar_domain(struct iommu_domain *dom) -{ - return container_of(dom, struct dmar_domain, domain); -} - -/* - * 0: readable - * 1: writable - * 2-6: reserved - * 7: super page - * 8-10: available - * 11: snoop behavior - * 12-63: Host physical address - */ -struct dma_pte { - u64 val; -}; - -static inline void dma_clear_pte(struct dma_pte *pte) -{ - pte->val = 0; -} - -static inline u64 dma_pte_addr(struct dma_pte *pte) -{ -#ifdef CONFIG_64BIT - return pte->val & VTD_PAGE_MASK & (~DMA_FL_PTE_XD); -#else - /* Must have a full atomic 64-bit read */ - return __cmpxchg64(&pte->val, 0ULL, 0ULL) & - VTD_PAGE_MASK & (~DMA_FL_PTE_XD); -#endif -} - -static inline bool dma_pte_present(struct dma_pte *pte) -{ - return (pte->val & 3) != 0; -} - -static inline bool dma_pte_superpage(struct dma_pte *pte) -{ - return (pte->val & DMA_PTE_LARGE_PAGE); -} - -static inline bool first_pte_in_page(struct dma_pte *pte) -{ - return IS_ALIGNED((unsigned long)pte, VTD_PAGE_SIZE); -} - -static inline int nr_pte_to_next_page(struct dma_pte *pte) -{ - return first_pte_in_page(pte) ? BIT_ULL(VTD_STRIDE_SHIFT) : - (struct dma_pte *)ALIGN((unsigned long)pte, VTD_PAGE_SIZE) - pte; -} - -extern struct dmar_drhd_unit * dmar_find_matched_drhd_unit(struct pci_dev *dev); -extern int dmar_find_matched_atsr_unit(struct pci_dev *dev); - -extern int dmar_enable_qi(struct intel_iommu *iommu); -extern void dmar_disable_qi(struct intel_iommu *iommu); -extern int dmar_reenable_qi(struct intel_iommu *iommu); -extern void qi_global_iec(struct intel_iommu *iommu); - -extern void qi_flush_context(struct intel_iommu *iommu, u16 did, u16 sid, - u8 fm, u64 type); -extern void qi_flush_iotlb(struct intel_iommu *iommu, u16 did, u64 addr, - unsigned int size_order, u64 type); -extern void qi_flush_dev_iotlb(struct intel_iommu *iommu, u16 sid, u16 pfsid, - u16 qdep, u64 addr, unsigned mask); - -void qi_flush_piotlb(struct intel_iommu *iommu, u16 did, u32 pasid, u64 addr, - unsigned long npages, bool ih); - -void qi_flush_dev_iotlb_pasid(struct intel_iommu *iommu, u16 sid, u16 pfsid, - u32 pasid, u16 qdep, u64 addr, - unsigned int size_order); -void qi_flush_pasid_cache(struct intel_iommu *iommu, u16 did, u64 granu, - u32 pasid); - -int qi_submit_sync(struct intel_iommu *iommu, struct qi_desc *desc, - unsigned int count, unsigned long options); -/* - * Options used in qi_submit_sync: - * QI_OPT_WAIT_DRAIN - Wait for PRQ drain completion, spec 6.5.2.8. - */ -#define QI_OPT_WAIT_DRAIN BIT(0) - -extern int dmar_ir_support(void); - -void *alloc_pgtable_page(int node); -void free_pgtable_page(void *vaddr); -struct intel_iommu *domain_get_iommu(struct dmar_domain *domain); -int for_each_device_domain(int (*fn)(struct device_domain_info *info, - void *data), void *data); -void iommu_flush_write_buffer(struct intel_iommu *iommu); -int intel_iommu_enable_pasid(struct intel_iommu *iommu, struct device *dev); -struct dmar_domain *find_domain(struct device *dev); -struct device_domain_info *get_domain_info(struct device *dev); -struct intel_iommu *device_to_iommu(struct device *dev, u8 *bus, u8 *devfn); - -#ifdef CONFIG_INTEL_IOMMU_SVM -extern void intel_svm_check(struct intel_iommu *iommu); -extern int intel_svm_enable_prq(struct intel_iommu *iommu); -extern int intel_svm_finish_prq(struct intel_iommu *iommu); -int intel_svm_bind_gpasid(struct iommu_domain *domain, struct device *dev, - struct iommu_gpasid_bind_data *data); -int intel_svm_unbind_gpasid(struct device *dev, u32 pasid); -struct iommu_sva *intel_svm_bind(struct device *dev, struct mm_struct *mm, - void *drvdata); -void intel_svm_unbind(struct iommu_sva *handle); -u32 intel_svm_get_pasid(struct iommu_sva *handle); -int intel_svm_page_response(struct device *dev, struct iommu_fault_event *evt, - struct iommu_page_response *msg); - -struct intel_svm_dev { - struct list_head list; - struct rcu_head rcu; - struct device *dev; - struct intel_iommu *iommu; - struct iommu_sva sva; - unsigned long prq_seq_number; - u32 pasid; - int users; - u16 did; - u16 dev_iotlb:1; - u16 sid, qdep; -}; - -struct intel_svm { - struct mmu_notifier notifier; - struct mm_struct *mm; - - unsigned int flags; - u32 pasid; - int gpasid; /* In case that guest PASID is different from host PASID */ - struct list_head devs; -}; -#else -static inline void intel_svm_check(struct intel_iommu *iommu) {} -#endif - -#ifdef CONFIG_INTEL_IOMMU_DEBUGFS -void intel_iommu_debugfs_init(void); -#else -static inline void intel_iommu_debugfs_init(void) {} -#endif /* CONFIG_INTEL_IOMMU_DEBUGFS */ - -extern const struct attribute_group *intel_iommu_groups[]; -bool context_present(struct context_entry *context); -struct context_entry *iommu_context_addr(struct intel_iommu *iommu, u8 bus, - u8 devfn, int alloc); - -#ifdef CONFIG_INTEL_IOMMU -extern int iommu_calculate_agaw(struct intel_iommu *iommu); -extern int iommu_calculate_max_sagaw(struct intel_iommu *iommu); -extern int dmar_disabled; -extern int intel_iommu_enabled; -extern int intel_iommu_gfx_mapped; -#else -static inline int iommu_calculate_agaw(struct intel_iommu *iommu) -{ - return 0; -} -static inline int iommu_calculate_max_sagaw(struct intel_iommu *iommu) -{ - return 0; -} -#define dmar_disabled (1) -#define intel_iommu_enabled (0) -#endif - -static inline const char *decode_prq_descriptor(char *str, size_t size, - u64 dw0, u64 dw1, u64 dw2, u64 dw3) -{ - char *buf = str; - int bytes; - - bytes = snprintf(buf, size, - "rid=0x%llx addr=0x%llx %c%c%c%c%c pasid=0x%llx index=0x%llx", - FIELD_GET(GENMASK_ULL(31, 16), dw0), - FIELD_GET(GENMASK_ULL(63, 12), dw1), - dw1 & BIT_ULL(0) ? 'r' : '-', - dw1 & BIT_ULL(1) ? 'w' : '-', - dw0 & BIT_ULL(52) ? 'x' : '-', - dw0 & BIT_ULL(53) ? 'p' : '-', - dw1 & BIT_ULL(2) ? 'l' : '-', - FIELD_GET(GENMASK_ULL(51, 32), dw0), - FIELD_GET(GENMASK_ULL(11, 3), dw1)); - - /* Private Data */ - if (dw0 & BIT_ULL(9)) { - size -= bytes; - buf += bytes; - snprintf(buf, size, " private=0x%llx/0x%llx\n", dw2, dw3); - } - - return str; -} - -#endif diff --git a/include/linux/intel-svm.h b/include/linux/intel-svm.h index 57cceecbe37f..207ef06ba3e1 100644 --- a/include/linux/intel-svm.h +++ b/include/linux/intel-svm.h @@ -8,14 +8,8 @@ #ifndef __INTEL_SVM_H__ #define __INTEL_SVM_H__ -/* Values for rxwp in fault_cb callback */ -#define SVM_REQ_READ (1<<3) -#define SVM_REQ_WRITE (1<<2) -#define SVM_REQ_EXEC (1<<1) -#define SVM_REQ_PRIV (1<<0) - /* Page Request Queue depth */ -#define PRQ_ORDER 2 +#define PRQ_ORDER 4 #define PRQ_RING_MASK ((0x1000 << PRQ_ORDER) - 0x20) #define PRQ_DEPTH ((0x1000 << PRQ_ORDER) >> 5) @@ -31,17 +25,5 @@ * do such IOTLB flushes automatically. */ #define SVM_FLAG_SUPERVISOR_MODE BIT(0) -/* - * The SVM_FLAG_GUEST_MODE flag is used when a PASID bind is for guest - * processes. Compared to the host bind, the primary differences are: - * 1. mm life cycle management - * 2. fault reporting - */ -#define SVM_FLAG_GUEST_MODE BIT(1) -/* - * The SVM_FLAG_GUEST_PASID flag is used when a guest has its own PASID space, - * which requires guest and host PASID translation at both directions. - */ -#define SVM_FLAG_GUEST_PASID BIT(2) #endif /* __INTEL_SVM_H__ */ diff --git a/include/linux/interconnect-provider.h b/include/linux/interconnect-provider.h index 6bd01f7159c6..cd5c5a27557f 100644 --- a/include/linux/interconnect-provider.h +++ b/include/linux/interconnect-provider.h @@ -123,7 +123,7 @@ void icc_node_add(struct icc_node *node, struct icc_provider *provider); void icc_node_del(struct icc_node *node); int icc_nodes_remove(struct icc_provider *provider); int icc_provider_add(struct icc_provider *provider); -int icc_provider_del(struct icc_provider *provider); +void icc_provider_del(struct icc_provider *provider); struct icc_node_data *of_icc_get_from_provider(struct of_phandle_args *spec); void icc_sync_state(struct device *dev); @@ -172,9 +172,8 @@ static inline int icc_provider_add(struct icc_provider *provider) return -ENOTSUPP; } -static inline int icc_provider_del(struct icc_provider *provider) +static inline void icc_provider_del(struct icc_provider *provider) { - return -ENOTSUPP; } static inline struct icc_node_data *of_icc_get_from_provider(struct of_phandle_args *spec) diff --git a/include/linux/interconnect.h b/include/linux/interconnect.h index f2dd2fc8d3cd..2b0e784ba771 100644 --- a/include/linux/interconnect.h +++ b/include/linux/interconnect.h @@ -38,19 +38,13 @@ struct icc_bulk_data { u32 peak_bw; }; -int __must_check of_icc_bulk_get(struct device *dev, int num_paths, - struct icc_bulk_data *paths); -void icc_bulk_put(int num_paths, struct icc_bulk_data *paths); -int icc_bulk_set_bw(int num_paths, const struct icc_bulk_data *paths); -int icc_bulk_enable(int num_paths, const struct icc_bulk_data *paths); -void icc_bulk_disable(int num_paths, const struct icc_bulk_data *paths); - #if IS_ENABLED(CONFIG_INTERCONNECT) struct icc_path *icc_get(struct device *dev, const int src_id, const int dst_id); struct icc_path *of_icc_get(struct device *dev, const char *name); struct icc_path *devm_of_icc_get(struct device *dev, const char *name); +int devm_of_icc_bulk_get(struct device *dev, int num_paths, struct icc_bulk_data *paths); struct icc_path *of_icc_get_by_index(struct device *dev, int idx); void icc_put(struct icc_path *path); int icc_enable(struct icc_path *path); @@ -58,6 +52,12 @@ int icc_disable(struct icc_path *path); int icc_set_bw(struct icc_path *path, u32 avg_bw, u32 peak_bw); void icc_set_tag(struct icc_path *path, u32 tag); const char *icc_get_name(struct icc_path *path); +int __must_check of_icc_bulk_get(struct device *dev, int num_paths, + struct icc_bulk_data *paths); +void icc_bulk_put(int num_paths, struct icc_bulk_data *paths); +int icc_bulk_set_bw(int num_paths, const struct icc_bulk_data *paths); +int icc_bulk_enable(int num_paths, const struct icc_bulk_data *paths); +void icc_bulk_disable(int num_paths, const struct icc_bulk_data *paths); #else @@ -112,6 +112,35 @@ static inline const char *icc_get_name(struct icc_path *path) return NULL; } +static inline int of_icc_bulk_get(struct device *dev, int num_paths, struct icc_bulk_data *paths) +{ + return 0; +} + +static inline int devm_of_icc_bulk_get(struct device *dev, int num_paths, + struct icc_bulk_data *paths) +{ + return 0; +} + +static inline void icc_bulk_put(int num_paths, struct icc_bulk_data *paths) +{ +} + +static inline int icc_bulk_set_bw(int num_paths, const struct icc_bulk_data *paths) +{ + return 0; +} + +static inline int icc_bulk_enable(int num_paths, const struct icc_bulk_data *paths) +{ + return 0; +} + +static inline void icc_bulk_disable(int num_paths, const struct icc_bulk_data *paths) +{ +} + #endif /* CONFIG_INTERCONNECT */ #endif /* __LINUX_INTERCONNECT_H */ diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 1f22a30c0963..a92bce40b04b 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -222,24 +222,6 @@ devm_request_any_context_irq(struct device *dev, unsigned int irq, extern void devm_free_irq(struct device *dev, unsigned int irq, void *dev_id); -/* - * On lockdep we dont want to enable hardirqs in hardirq - * context. Use local_irq_enable_in_hardirq() to annotate - * kernel code that has to do this nevertheless (pretty much - * the only valid case is for old/broken hardware that is - * insanely slow). - * - * NOTE: in theory this might break fragile code that relies - * on hardirq delivery - in practice we dont seem to have such - * places left. So the only effect should be slightly increased - * irqs-off latencies. - */ -#ifdef CONFIG_LOCKDEP -# define local_irq_enable_in_hardirq() do { } while (0) -#else -# define local_irq_enable_in_hardirq() local_irq_enable() -#endif - bool irq_has_action(unsigned int irq); extern void disable_irq_nosync(unsigned int irq); extern bool disable_hardirq(unsigned int irq); @@ -329,7 +311,46 @@ extern int irq_force_affinity(unsigned int irq, const struct cpumask *cpumask); extern int irq_can_set_affinity(unsigned int irq); extern int irq_select_affinity(unsigned int irq); -extern int irq_set_affinity_hint(unsigned int irq, const struct cpumask *m); +extern int __irq_apply_affinity_hint(unsigned int irq, const struct cpumask *m, + bool setaffinity); + +/** + * irq_update_affinity_hint - Update the affinity hint + * @irq: Interrupt to update + * @m: cpumask pointer (NULL to clear the hint) + * + * Updates the affinity hint, but does not change the affinity of the interrupt. + */ +static inline int +irq_update_affinity_hint(unsigned int irq, const struct cpumask *m) +{ + return __irq_apply_affinity_hint(irq, m, false); +} + +/** + * irq_set_affinity_and_hint - Update the affinity hint and apply the provided + * cpumask to the interrupt + * @irq: Interrupt to update + * @m: cpumask pointer (NULL to clear the hint) + * + * Updates the affinity hint and if @m is not NULL it applies it as the + * affinity of that interrupt. + */ +static inline int +irq_set_affinity_and_hint(unsigned int irq, const struct cpumask *m) +{ + return __irq_apply_affinity_hint(irq, m, true); +} + +/* + * Deprecated. Use irq_update_affinity_hint() or irq_set_affinity_and_hint() + * instead. + */ +static inline int irq_set_affinity_hint(unsigned int irq, const struct cpumask *m) +{ + return irq_set_affinity_and_hint(irq, m); +} + extern int irq_update_affinity_desc(unsigned int irq, struct irq_affinity_desc *affinity); @@ -361,6 +382,18 @@ static inline int irq_can_set_affinity(unsigned int irq) static inline int irq_select_affinity(unsigned int irq) { return 0; } +static inline int irq_update_affinity_hint(unsigned int irq, + const struct cpumask *m) +{ + return -EINVAL; +} + +static inline int irq_set_affinity_and_hint(unsigned int irq, + const struct cpumask *m) +{ + return -EINVAL; +} + static inline int irq_set_affinity_hint(unsigned int irq, const struct cpumask *m) { @@ -528,7 +561,16 @@ enum NR_SOFTIRQS }; -#define SOFTIRQ_STOP_IDLE_MASK (~(1 << RCU_SOFTIRQ)) +/* + * The following vectors can be safely ignored after ksoftirqd is parked: + * + * _ RCU: + * 1) rcutree_migrate_callbacks() migrates the queue. + * 2) rcu_report_dead() reports the final quiescent states. + * + * _ IRQ_POLL: irq_poll_cpu_dead() migrates the queue + */ +#define SOFTIRQ_HOTPLUG_SAFE_MASK (BIT(RCU_SOFTIRQ) | BIT(IRQ_POLL_SOFTIRQ)) /* map softirq index to softirq name. update 'softirq_to_name' in * kernel/softirq.c when adding a new softirq. @@ -547,6 +589,15 @@ struct softirq_action asmlinkage void do_softirq(void); asmlinkage void __do_softirq(void); +#ifdef CONFIG_PREEMPT_RT +extern void do_softirq_post_smp_call_flush(unsigned int was_pending); +#else +static inline void do_softirq_post_smp_call_flush(unsigned int unused) +{ + do_softirq(); +} +#endif + extern void open_softirq(int nr, void (*action)(struct softirq_action *)); extern void softirq_init(void); extern void __raise_softirq_irqoff(unsigned int nr); diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h index 86af6f0a00a2..1f068dfdb140 100644 --- a/include/linux/io-pgtable.h +++ b/include/linux/io-pgtable.h @@ -16,7 +16,9 @@ enum io_pgtable_fmt { ARM_V7S, ARM_MALI_LPAE, AMD_IOMMU_V1, + AMD_IOMMU_V2, APPLE_DART, + APPLE_DART2, IO_PGTABLE_NUM_FMTS, }; @@ -74,17 +76,22 @@ struct io_pgtable_cfg { * to support up to 35 bits PA where the bit32, bit33 and bit34 are * encoded in the bit9, bit4 and bit5 of the PTE respectively. * + * IO_PGTABLE_QUIRK_ARM_MTK_TTBR_EXT: (ARM v7s format) MediaTek IOMMUs + * extend the translation table base support up to 35 bits PA, the + * encoding format is same with IO_PGTABLE_QUIRK_ARM_MTK_EXT. + * * IO_PGTABLE_QUIRK_ARM_TTBR1: (ARM LPAE format) Configure the table * for use in the upper half of a split address space. * * IO_PGTABLE_QUIRK_ARM_OUTER_WBWA: Override the outer-cacheability * attributes set in the TCR for a non-coherent page-table walker. */ - #define IO_PGTABLE_QUIRK_ARM_NS BIT(0) - #define IO_PGTABLE_QUIRK_NO_PERMS BIT(1) - #define IO_PGTABLE_QUIRK_ARM_MTK_EXT BIT(3) - #define IO_PGTABLE_QUIRK_ARM_TTBR1 BIT(5) - #define IO_PGTABLE_QUIRK_ARM_OUTER_WBWA BIT(6) + #define IO_PGTABLE_QUIRK_ARM_NS BIT(0) + #define IO_PGTABLE_QUIRK_NO_PERMS BIT(1) + #define IO_PGTABLE_QUIRK_ARM_MTK_EXT BIT(3) + #define IO_PGTABLE_QUIRK_ARM_MTK_TTBR_EXT BIT(4) + #define IO_PGTABLE_QUIRK_ARM_TTBR1 BIT(5) + #define IO_PGTABLE_QUIRK_ARM_OUTER_WBWA BIT(6) unsigned long quirks; unsigned long pgsize_bitmap; unsigned int ias; @@ -255,6 +262,7 @@ extern struct io_pgtable_init_fns io_pgtable_arm_64_lpae_s2_init_fns; extern struct io_pgtable_init_fns io_pgtable_arm_v7s_init_fns; extern struct io_pgtable_init_fns io_pgtable_arm_mali_lpae_init_fns; extern struct io_pgtable_init_fns io_pgtable_amd_iommu_v1_init_fns; +extern struct io_pgtable_init_fns io_pgtable_amd_iommu_v2_init_fns; extern struct io_pgtable_init_fns io_pgtable_apple_dart_init_fns; #endif /* __IO_PGTABLE_H */ diff --git a/include/linux/io.h b/include/linux/io.h index 5fc800390fe4..308f4f0cfb93 100644 --- a/include/linux/io.h +++ b/include/linux/io.h @@ -59,8 +59,6 @@ void __iomem *devm_ioremap_uc(struct device *dev, resource_size_t offset, resource_size_t size); void __iomem *devm_ioremap_wc(struct device *dev, resource_size_t offset, resource_size_t size); -void __iomem *devm_ioremap_np(struct device *dev, resource_size_t offset, - resource_size_t size); void devm_iounmap(struct device *dev, void __iomem *addr); int check_signature(const volatile void __iomem *io_addr, const unsigned char *signature, int length); diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h index 649a4d7c241b..43bc8a2edccf 100644 --- a/include/linux/io_uring.h +++ b/include/linux/io_uring.h @@ -4,16 +4,52 @@ #include <linux/sched.h> #include <linux/xarray.h> +#include <uapi/linux/io_uring.h> + +enum io_uring_cmd_flags { + IO_URING_F_COMPLETE_DEFER = 1, + IO_URING_F_UNLOCKED = 2, + /* int's last bit, sign checks are usually faster than a bit test */ + IO_URING_F_NONBLOCK = INT_MIN, + + /* ctx state flags, for URING_CMD */ + IO_URING_F_SQE128 = 4, + IO_URING_F_CQE32 = 8, + IO_URING_F_IOPOLL = 16, +}; + +struct io_uring_cmd { + struct file *file; + const void *cmd; + union { + /* callback to defer completions to task context */ + void (*task_work_cb)(struct io_uring_cmd *cmd); + /* used for polled completion */ + void *cookie; + }; + u32 cmd_op; + u32 flags; + u8 pdu[32]; /* available inline for free use */ +}; #if defined(CONFIG_IO_URING) +int io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw, + struct iov_iter *iter, void *ioucmd); +void io_uring_cmd_done(struct io_uring_cmd *cmd, ssize_t ret, ssize_t res2); +void io_uring_cmd_complete_in_task(struct io_uring_cmd *ioucmd, + void (*task_work_cb)(struct io_uring_cmd *)); struct sock *io_uring_get_socket(struct file *file); void __io_uring_cancel(bool cancel_all); void __io_uring_free(struct task_struct *tsk); +void io_uring_unreg_ringfd(void); +const char *io_uring_get_opcode(u8 opcode); static inline void io_uring_files_cancel(void) { - if (current->io_uring) + if (current->io_uring) { + io_uring_unreg_ringfd(); __io_uring_cancel(false); + } } static inline void io_uring_task_cancel(void) { @@ -26,6 +62,19 @@ static inline void io_uring_free(struct task_struct *tsk) __io_uring_free(tsk); } #else +static inline int io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw, + struct iov_iter *iter, void *ioucmd) +{ + return -EOPNOTSUPP; +} +static inline void io_uring_cmd_done(struct io_uring_cmd *cmd, ssize_t ret, + ssize_t ret2) +{ +} +static inline void io_uring_cmd_complete_in_task(struct io_uring_cmd *ioucmd, + void (*task_work_cb)(struct io_uring_cmd *)) +{ +} static inline struct sock *io_uring_get_socket(struct file *file) { return NULL; @@ -39,6 +88,10 @@ static inline void io_uring_files_cancel(void) static inline void io_uring_free(struct task_struct *tsk) { } +static inline const char *io_uring_get_opcode(u8 opcode) +{ + return ""; +} #endif #endif diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h new file mode 100644 index 000000000000..f5b687a787a3 --- /dev/null +++ b/include/linux/io_uring_types.h @@ -0,0 +1,580 @@ +#ifndef IO_URING_TYPES_H +#define IO_URING_TYPES_H + +#include <linux/blkdev.h> +#include <linux/task_work.h> +#include <linux/bitmap.h> +#include <linux/llist.h> +#include <uapi/linux/io_uring.h> + +struct io_wq_work_node { + struct io_wq_work_node *next; +}; + +struct io_wq_work_list { + struct io_wq_work_node *first; + struct io_wq_work_node *last; +}; + +struct io_wq_work { + struct io_wq_work_node list; + unsigned flags; + /* place it here instead of io_kiocb as it fills padding and saves 4B */ + int cancel_seq; +}; + +struct io_fixed_file { + /* file * with additional FFS_* flags */ + unsigned long file_ptr; +}; + +struct io_file_table { + struct io_fixed_file *files; + unsigned long *bitmap; + unsigned int alloc_hint; +}; + +struct io_hash_bucket { + spinlock_t lock; + struct hlist_head list; +} ____cacheline_aligned_in_smp; + +struct io_hash_table { + struct io_hash_bucket *hbs; + unsigned hash_bits; +}; + +/* + * Arbitrary limit, can be raised if need be + */ +#define IO_RINGFD_REG_MAX 16 + +struct io_uring_task { + /* submission side */ + int cached_refs; + const struct io_ring_ctx *last; + struct io_wq *io_wq; + struct file *registered_rings[IO_RINGFD_REG_MAX]; + + struct xarray xa; + struct wait_queue_head wait; + atomic_t in_idle; + atomic_t inflight_tracked; + struct percpu_counter inflight; + + struct { /* task_work */ + struct llist_head task_list; + struct callback_head task_work; + } ____cacheline_aligned_in_smp; +}; + +struct io_uring { + u32 head ____cacheline_aligned_in_smp; + u32 tail ____cacheline_aligned_in_smp; +}; + +/* + * This data is shared with the application through the mmap at offsets + * IORING_OFF_SQ_RING and IORING_OFF_CQ_RING. + * + * The offsets to the member fields are published through struct + * io_sqring_offsets when calling io_uring_setup. + */ +struct io_rings { + /* + * Head and tail offsets into the ring; the offsets need to be + * masked to get valid indices. + * + * The kernel controls head of the sq ring and the tail of the cq ring, + * and the application controls tail of the sq ring and the head of the + * cq ring. + */ + struct io_uring sq, cq; + /* + * Bitmasks to apply to head and tail offsets (constant, equals + * ring_entries - 1) + */ + u32 sq_ring_mask, cq_ring_mask; + /* Ring sizes (constant, power of 2) */ + u32 sq_ring_entries, cq_ring_entries; + /* + * Number of invalid entries dropped by the kernel due to + * invalid index stored in array + * + * Written by the kernel, shouldn't be modified by the + * application (i.e. get number of "new events" by comparing to + * cached value). + * + * After a new SQ head value was read by the application this + * counter includes all submissions that were dropped reaching + * the new SQ head (and possibly more). + */ + u32 sq_dropped; + /* + * Runtime SQ flags + * + * Written by the kernel, shouldn't be modified by the + * application. + * + * The application needs a full memory barrier before checking + * for IORING_SQ_NEED_WAKEUP after updating the sq tail. + */ + atomic_t sq_flags; + /* + * Runtime CQ flags + * + * Written by the application, shouldn't be modified by the + * kernel. + */ + u32 cq_flags; + /* + * Number of completion events lost because the queue was full; + * this should be avoided by the application by making sure + * there are not more requests pending than there is space in + * the completion queue. + * + * Written by the kernel, shouldn't be modified by the + * application (i.e. get number of "new events" by comparing to + * cached value). + * + * As completion events come in out of order this counter is not + * ordered with any other data. + */ + u32 cq_overflow; + /* + * Ring buffer of completion events. + * + * The kernel writes completion events fresh every time they are + * produced, so the application is allowed to modify pending + * entries. + */ + struct io_uring_cqe cqes[] ____cacheline_aligned_in_smp; +}; + +struct io_restriction { + DECLARE_BITMAP(register_op, IORING_REGISTER_LAST); + DECLARE_BITMAP(sqe_op, IORING_OP_LAST); + u8 sqe_flags_allowed; + u8 sqe_flags_required; + bool registered; +}; + +struct io_submit_link { + struct io_kiocb *head; + struct io_kiocb *last; +}; + +struct io_submit_state { + /* inline/task_work completion list, under ->uring_lock */ + struct io_wq_work_node free_list; + /* batch completion logic */ + struct io_wq_work_list compl_reqs; + struct io_submit_link link; + + bool plug_started; + bool need_plug; + unsigned short submit_nr; + struct blk_plug plug; +}; + +struct io_ev_fd { + struct eventfd_ctx *cq_ev_fd; + unsigned int eventfd_async: 1; + struct rcu_head rcu; + atomic_t refs; + atomic_t ops; +}; + +struct io_alloc_cache { + struct hlist_head list; + unsigned int nr_cached; +}; + +struct io_ring_ctx { + /* const or read-mostly hot data */ + struct { + struct percpu_ref refs; + + struct io_rings *rings; + unsigned int flags; + enum task_work_notify_mode notify_method; + unsigned int compat: 1; + unsigned int drain_next: 1; + unsigned int restricted: 1; + unsigned int off_timeout_used: 1; + unsigned int drain_active: 1; + unsigned int drain_disabled: 1; + unsigned int has_evfd: 1; + unsigned int syscall_iopoll: 1; + } ____cacheline_aligned_in_smp; + + /* submission data */ + struct { + struct mutex uring_lock; + + /* + * Ring buffer of indices into array of io_uring_sqe, which is + * mmapped by the application using the IORING_OFF_SQES offset. + * + * This indirection could e.g. be used to assign fixed + * io_uring_sqe entries to operations and only submit them to + * the queue when needed. + * + * The kernel modifies neither the indices array nor the entries + * array. + */ + u32 *sq_array; + struct io_uring_sqe *sq_sqes; + unsigned cached_sq_head; + unsigned sq_entries; + + /* + * Fixed resources fast path, should be accessed only under + * uring_lock, and updated through io_uring_register(2) + */ + struct io_rsrc_node *rsrc_node; + int rsrc_cached_refs; + atomic_t cancel_seq; + struct io_file_table file_table; + unsigned nr_user_files; + unsigned nr_user_bufs; + struct io_mapped_ubuf **user_bufs; + + struct io_submit_state submit_state; + + struct io_buffer_list *io_bl; + struct xarray io_bl_xa; + struct list_head io_buffers_cache; + + struct io_hash_table cancel_table_locked; + struct list_head cq_overflow_list; + struct io_alloc_cache apoll_cache; + struct io_alloc_cache netmsg_cache; + } ____cacheline_aligned_in_smp; + + /* IRQ completion list, under ->completion_lock */ + struct io_wq_work_list locked_free_list; + unsigned int locked_free_nr; + + const struct cred *sq_creds; /* cred used for __io_sq_thread() */ + struct io_sq_data *sq_data; /* if using sq thread polling */ + + struct wait_queue_head sqo_sq_wait; + struct list_head sqd_list; + + unsigned long check_cq; + + unsigned int file_alloc_start; + unsigned int file_alloc_end; + + struct xarray personalities; + u32 pers_next; + + struct { + /* + * We cache a range of free CQEs we can use, once exhausted it + * should go through a slower range setup, see __io_get_cqe() + */ + struct io_uring_cqe *cqe_cached; + struct io_uring_cqe *cqe_sentinel; + + unsigned cached_cq_tail; + unsigned cq_entries; + struct io_ev_fd __rcu *io_ev_fd; + struct wait_queue_head cq_wait; + unsigned cq_extra; + } ____cacheline_aligned_in_smp; + + struct { + spinlock_t completion_lock; + + /* + * ->iopoll_list is protected by the ctx->uring_lock for + * io_uring instances that don't use IORING_SETUP_SQPOLL. + * For SQPOLL, only the single threaded io_sq_thread() will + * manipulate the list, hence no extra locking is needed there. + */ + struct io_wq_work_list iopoll_list; + struct io_hash_table cancel_table; + bool poll_multi_queue; + + struct llist_head work_llist; + + struct list_head io_buffers_comp; + } ____cacheline_aligned_in_smp; + + /* timeouts */ + struct { + spinlock_t timeout_lock; + atomic_t cq_timeouts; + struct list_head timeout_list; + struct list_head ltimeout_list; + unsigned cq_last_tm_flush; + } ____cacheline_aligned_in_smp; + + /* Keep this last, we don't need it for the fast path */ + + struct io_restriction restrictions; + struct task_struct *submitter_task; + + /* slow path rsrc auxilary data, used by update/register */ + struct io_rsrc_node *rsrc_backup_node; + struct io_mapped_ubuf *dummy_ubuf; + struct io_rsrc_data *file_data; + struct io_rsrc_data *buf_data; + + struct delayed_work rsrc_put_work; + struct llist_head rsrc_put_llist; + struct list_head rsrc_ref_list; + spinlock_t rsrc_ref_lock; + + struct list_head io_buffers_pages; + + #if defined(CONFIG_UNIX) + struct socket *ring_sock; + #endif + /* hashed buffered write serialization */ + struct io_wq_hash *hash_map; + + /* Only used for accounting purposes */ + struct user_struct *user; + struct mm_struct *mm_account; + + /* ctx exit and cancelation */ + struct llist_head fallback_llist; + struct delayed_work fallback_work; + struct work_struct exit_work; + struct list_head tctx_list; + struct completion ref_comp; + + /* io-wq management, e.g. thread count */ + u32 iowq_limits[2]; + bool iowq_limits_set; + + struct list_head defer_list; + unsigned sq_thread_idle; + /* protected by ->completion_lock */ + unsigned evfd_last_cq_tail; +}; + +enum { + REQ_F_FIXED_FILE_BIT = IOSQE_FIXED_FILE_BIT, + REQ_F_IO_DRAIN_BIT = IOSQE_IO_DRAIN_BIT, + REQ_F_LINK_BIT = IOSQE_IO_LINK_BIT, + REQ_F_HARDLINK_BIT = IOSQE_IO_HARDLINK_BIT, + REQ_F_FORCE_ASYNC_BIT = IOSQE_ASYNC_BIT, + REQ_F_BUFFER_SELECT_BIT = IOSQE_BUFFER_SELECT_BIT, + REQ_F_CQE_SKIP_BIT = IOSQE_CQE_SKIP_SUCCESS_BIT, + + /* first byte is taken by user flags, shift it to not overlap */ + REQ_F_FAIL_BIT = 8, + REQ_F_INFLIGHT_BIT, + REQ_F_CUR_POS_BIT, + REQ_F_NOWAIT_BIT, + REQ_F_LINK_TIMEOUT_BIT, + REQ_F_NEED_CLEANUP_BIT, + REQ_F_POLLED_BIT, + REQ_F_BUFFER_SELECTED_BIT, + REQ_F_BUFFER_RING_BIT, + REQ_F_REISSUE_BIT, + REQ_F_CREDS_BIT, + REQ_F_REFCOUNT_BIT, + REQ_F_ARM_LTIMEOUT_BIT, + REQ_F_ASYNC_DATA_BIT, + REQ_F_SKIP_LINK_CQES_BIT, + REQ_F_SINGLE_POLL_BIT, + REQ_F_DOUBLE_POLL_BIT, + REQ_F_PARTIAL_IO_BIT, + REQ_F_CQE32_INIT_BIT, + REQ_F_APOLL_MULTISHOT_BIT, + REQ_F_CLEAR_POLLIN_BIT, + REQ_F_HASH_LOCKED_BIT, + /* keep async read/write and isreg together and in order */ + REQ_F_SUPPORT_NOWAIT_BIT, + REQ_F_ISREG_BIT, + + /* not a real bit, just to check we're not overflowing the space */ + __REQ_F_LAST_BIT, +}; + +enum { + /* ctx owns file */ + REQ_F_FIXED_FILE = BIT(REQ_F_FIXED_FILE_BIT), + /* drain existing IO first */ + REQ_F_IO_DRAIN = BIT(REQ_F_IO_DRAIN_BIT), + /* linked sqes */ + REQ_F_LINK = BIT(REQ_F_LINK_BIT), + /* doesn't sever on completion < 0 */ + REQ_F_HARDLINK = BIT(REQ_F_HARDLINK_BIT), + /* IOSQE_ASYNC */ + REQ_F_FORCE_ASYNC = BIT(REQ_F_FORCE_ASYNC_BIT), + /* IOSQE_BUFFER_SELECT */ + REQ_F_BUFFER_SELECT = BIT(REQ_F_BUFFER_SELECT_BIT), + /* IOSQE_CQE_SKIP_SUCCESS */ + REQ_F_CQE_SKIP = BIT(REQ_F_CQE_SKIP_BIT), + + /* fail rest of links */ + REQ_F_FAIL = BIT(REQ_F_FAIL_BIT), + /* on inflight list, should be cancelled and waited on exit reliably */ + REQ_F_INFLIGHT = BIT(REQ_F_INFLIGHT_BIT), + /* read/write uses file position */ + REQ_F_CUR_POS = BIT(REQ_F_CUR_POS_BIT), + /* must not punt to workers */ + REQ_F_NOWAIT = BIT(REQ_F_NOWAIT_BIT), + /* has or had linked timeout */ + REQ_F_LINK_TIMEOUT = BIT(REQ_F_LINK_TIMEOUT_BIT), + /* needs cleanup */ + REQ_F_NEED_CLEANUP = BIT(REQ_F_NEED_CLEANUP_BIT), + /* already went through poll handler */ + REQ_F_POLLED = BIT(REQ_F_POLLED_BIT), + /* buffer already selected */ + REQ_F_BUFFER_SELECTED = BIT(REQ_F_BUFFER_SELECTED_BIT), + /* buffer selected from ring, needs commit */ + REQ_F_BUFFER_RING = BIT(REQ_F_BUFFER_RING_BIT), + /* caller should reissue async */ + REQ_F_REISSUE = BIT(REQ_F_REISSUE_BIT), + /* supports async reads/writes */ + REQ_F_SUPPORT_NOWAIT = BIT(REQ_F_SUPPORT_NOWAIT_BIT), + /* regular file */ + REQ_F_ISREG = BIT(REQ_F_ISREG_BIT), + /* has creds assigned */ + REQ_F_CREDS = BIT(REQ_F_CREDS_BIT), + /* skip refcounting if not set */ + REQ_F_REFCOUNT = BIT(REQ_F_REFCOUNT_BIT), + /* there is a linked timeout that has to be armed */ + REQ_F_ARM_LTIMEOUT = BIT(REQ_F_ARM_LTIMEOUT_BIT), + /* ->async_data allocated */ + REQ_F_ASYNC_DATA = BIT(REQ_F_ASYNC_DATA_BIT), + /* don't post CQEs while failing linked requests */ + REQ_F_SKIP_LINK_CQES = BIT(REQ_F_SKIP_LINK_CQES_BIT), + /* single poll may be active */ + REQ_F_SINGLE_POLL = BIT(REQ_F_SINGLE_POLL_BIT), + /* double poll may active */ + REQ_F_DOUBLE_POLL = BIT(REQ_F_DOUBLE_POLL_BIT), + /* request has already done partial IO */ + REQ_F_PARTIAL_IO = BIT(REQ_F_PARTIAL_IO_BIT), + /* fast poll multishot mode */ + REQ_F_APOLL_MULTISHOT = BIT(REQ_F_APOLL_MULTISHOT_BIT), + /* ->extra1 and ->extra2 are initialised */ + REQ_F_CQE32_INIT = BIT(REQ_F_CQE32_INIT_BIT), + /* recvmsg special flag, clear EPOLLIN */ + REQ_F_CLEAR_POLLIN = BIT(REQ_F_CLEAR_POLLIN_BIT), + /* hashed into ->cancel_hash_locked, protected by ->uring_lock */ + REQ_F_HASH_LOCKED = BIT(REQ_F_HASH_LOCKED_BIT), +}; + +typedef void (*io_req_tw_func_t)(struct io_kiocb *req, bool *locked); + +struct io_task_work { + struct llist_node node; + io_req_tw_func_t func; +}; + +struct io_cqe { + __u64 user_data; + __s32 res; + /* fd initially, then cflags for completion */ + union { + __u32 flags; + int fd; + }; +}; + +/* + * Each request type overlays its private data structure on top of this one. + * They must not exceed this one in size. + */ +struct io_cmd_data { + struct file *file; + /* each command gets 56 bytes of data */ + __u8 data[56]; +}; + +static inline void io_kiocb_cmd_sz_check(size_t cmd_sz) +{ + BUILD_BUG_ON(cmd_sz > sizeof(struct io_cmd_data)); +} +#define io_kiocb_to_cmd(req, cmd_type) ( \ + io_kiocb_cmd_sz_check(sizeof(cmd_type)) , \ + ((cmd_type *)&(req)->cmd) \ +) +#define cmd_to_io_kiocb(ptr) ((struct io_kiocb *) ptr) + +struct io_kiocb { + union { + /* + * NOTE! Each of the io_kiocb union members has the file pointer + * as the first entry in their struct definition. So you can + * access the file pointer through any of the sub-structs, + * or directly as just 'file' in this struct. + */ + struct file *file; + struct io_cmd_data cmd; + }; + + u8 opcode; + /* polled IO has completed */ + u8 iopoll_completed; + /* + * Can be either a fixed buffer index, or used with provided buffers. + * For the latter, before issue it points to the buffer group ID, + * and after selection it points to the buffer ID itself. + */ + u16 buf_index; + unsigned int flags; + + struct io_cqe cqe; + + struct io_ring_ctx *ctx; + struct task_struct *task; + + struct io_rsrc_node *rsrc_node; + + union { + /* store used ubuf, so we can prevent reloading */ + struct io_mapped_ubuf *imu; + + /* stores selected buf, valid IFF REQ_F_BUFFER_SELECTED is set */ + struct io_buffer *kbuf; + + /* + * stores buffer ID for ring provided buffers, valid IFF + * REQ_F_BUFFER_RING is set. + */ + struct io_buffer_list *buf_list; + }; + + union { + /* used by request caches, completion batching and iopoll */ + struct io_wq_work_node comp_list; + /* cache ->apoll->events */ + __poll_t apoll_events; + }; + atomic_t refs; + atomic_t poll_refs; + struct io_task_work io_task_work; + /* for polled requests, i.e. IORING_OP_POLL_ADD and async armed poll */ + union { + struct hlist_node hash_node; + struct { + u64 extra1; + u64 extra2; + }; + }; + /* internal polling, see IORING_FEAT_FAST_POLL */ + struct async_poll *apoll; + /* opcode allocated if it needs to store data for async defer */ + void *async_data; + /* linked requests, IFF REQ_F_HARDLINK or REQ_F_LINK are set */ + struct io_kiocb *link; + /* custom credentials, valid IFF REQ_F_CREDS is set */ + const struct cred *creds; + struct io_wq_work work; +}; + +struct io_overflow_cqe { + struct list_head list; + struct io_uring_cqe cqe; +}; + +#endif diff --git a/include/linux/ioasid.h b/include/linux/ioasid.h index e9dacd4b9f6b..af1c9d62e642 100644 --- a/include/linux/ioasid.h +++ b/include/linux/ioasid.h @@ -34,13 +34,16 @@ struct ioasid_allocator_ops { #if IS_ENABLED(CONFIG_IOASID) ioasid_t ioasid_alloc(struct ioasid_set *set, ioasid_t min, ioasid_t max, void *private); -void ioasid_get(ioasid_t ioasid); -bool ioasid_put(ioasid_t ioasid); +void ioasid_free(ioasid_t ioasid); void *ioasid_find(struct ioasid_set *set, ioasid_t ioasid, bool (*getter)(void *)); int ioasid_register_allocator(struct ioasid_allocator_ops *allocator); void ioasid_unregister_allocator(struct ioasid_allocator_ops *allocator); int ioasid_set_data(ioasid_t ioasid, void *data); +static inline bool pasid_valid(ioasid_t ioasid) +{ + return ioasid != INVALID_IOASID; +} #else /* !CONFIG_IOASID */ static inline ioasid_t ioasid_alloc(struct ioasid_set *set, ioasid_t min, @@ -49,14 +52,7 @@ static inline ioasid_t ioasid_alloc(struct ioasid_set *set, ioasid_t min, return INVALID_IOASID; } -static inline void ioasid_get(ioasid_t ioasid) -{ -} - -static inline bool ioasid_put(ioasid_t ioasid) -{ - return false; -} +static inline void ioasid_free(ioasid_t ioasid) { } static inline void *ioasid_find(struct ioasid_set *set, ioasid_t ioasid, bool (*getter)(void *)) @@ -78,5 +74,10 @@ static inline int ioasid_set_data(ioasid_t ioasid, void *data) return -ENOTSUPP; } +static inline bool pasid_valid(ioasid_t ioasid) +{ + return false; +} + #endif /* CONFIG_IOASID */ #endif /* __LINUX_IOASID_H */ diff --git a/include/linux/iocontext.h b/include/linux/iocontext.h index 0a9dc40b7be8..14f7eaf1b443 100644 --- a/include/linux/iocontext.h +++ b/include/linux/iocontext.h @@ -99,55 +99,40 @@ struct io_cq { struct io_context { atomic_long_t refcount; atomic_t active_ref; - atomic_t nr_tasks; + unsigned short ioprio; + +#ifdef CONFIG_BLK_ICQ /* all the fields below are protected by this lock */ spinlock_t lock; - unsigned short ioprio; - struct radix_tree_root icq_tree; struct io_cq __rcu *icq_hint; struct hlist_head icq_list; struct work_struct release_work; +#endif /* CONFIG_BLK_ICQ */ }; -/** - * get_io_context_active - get active reference on ioc - * @ioc: ioc of interest - * - * Only iocs with active reference can issue new IOs. This function - * acquires an active reference on @ioc. The caller must already have an - * active reference on @ioc. - */ -static inline void get_io_context_active(struct io_context *ioc) -{ - WARN_ON_ONCE(atomic_long_read(&ioc->refcount) <= 0); - WARN_ON_ONCE(atomic_read(&ioc->active_ref) <= 0); - atomic_long_inc(&ioc->refcount); - atomic_inc(&ioc->active_ref); -} - -static inline void ioc_task_link(struct io_context *ioc) -{ - get_io_context_active(ioc); - - WARN_ON_ONCE(atomic_read(&ioc->nr_tasks) <= 0); - atomic_inc(&ioc->nr_tasks); -} - struct task_struct; #ifdef CONFIG_BLOCK void put_io_context(struct io_context *ioc); -void put_io_context_active(struct io_context *ioc); void exit_io_context(struct task_struct *task); -struct io_context *get_task_io_context(struct task_struct *task, - gfp_t gfp_flags, int node); +int __copy_io(unsigned long clone_flags, struct task_struct *tsk); +static inline int copy_io(unsigned long clone_flags, struct task_struct *tsk) +{ + if (!current->io_context) + return 0; + return __copy_io(clone_flags, tsk); +} #else struct io_context; static inline void put_io_context(struct io_context *ioc) { } static inline void exit_io_context(struct task_struct *task) { } -#endif +static inline int copy_io(unsigned long clone_flags, struct task_struct *tsk) +{ + return 0; +} +#endif /* CONFIG_BLOCK */ -#endif +#endif /* IOCONTEXT_H */ diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 6d1b08d0ae93..238a03087e17 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -141,6 +141,11 @@ struct iomap_page_ops { #define IOMAP_NOWAIT (1 << 5) /* do not block */ #define IOMAP_OVERWRITE_ONLY (1 << 6) /* only pure overwrites allowed */ #define IOMAP_UNSHARE (1 << 7) /* unshare_file_range */ +#ifdef CONFIG_FS_DAX +#define IOMAP_DAX (1 << 8) /* DAX mapping */ +#else +#define IOMAP_DAX 0 +#endif /* CONFIG_FS_DAX */ struct iomap_ops { /* @@ -183,6 +188,7 @@ struct iomap_iter { unsigned flags; struct iomap iomap; struct iomap srcmap; + void *private; }; int iomap_iter(struct iomap_iter *iter, const struct iomap_ops *ops); @@ -220,19 +226,11 @@ static inline const struct iomap *iomap_iter_srcmap(const struct iomap_iter *i) ssize_t iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *from, const struct iomap_ops *ops); -int iomap_readpage(struct page *page, const struct iomap_ops *ops); +int iomap_read_folio(struct folio *folio, const struct iomap_ops *ops); void iomap_readahead(struct readahead_control *, const struct iomap_ops *ops); -int iomap_is_partially_uptodate(struct page *page, unsigned long from, - unsigned long count); -int iomap_releasepage(struct page *page, gfp_t gfp_mask); -void iomap_invalidatepage(struct page *page, unsigned int offset, - unsigned int len); -#ifdef CONFIG_MIGRATION -int iomap_migrate_page(struct address_space *mapping, struct page *newpage, - struct page *page, enum migrate_mode mode); -#else -#define iomap_migrate_page NULL -#endif +bool iomap_is_partially_uptodate(struct folio *, size_t from, size_t count); +bool iomap_release_folio(struct folio *folio, gfp_t gfp_flags); +void iomap_invalidate_folio(struct folio *folio, size_t offset, size_t len); int iomap_file_unshare(struct inode *inode, loff_t pos, loff_t len, const struct iomap_ops *ops); int iomap_zero_range(struct inode *inode, loff_t pos, loff_t len, @@ -257,9 +255,11 @@ struct iomap_ioend { struct list_head io_list; /* next ioend in chain */ u16 io_type; u16 io_flags; /* IOMAP_F_* */ + u32 io_folios; /* folios added to ioend */ struct inode *io_inode; /* file being written to */ size_t io_size; /* size of the extent */ loff_t io_offset; /* offset in the file */ + sector_t io_sector; /* start sector of ioend */ struct bio *io_bio; /* bio being built */ struct bio io_inline_bio; /* MUST BE LAST! */ }; @@ -284,7 +284,7 @@ struct iomap_writeback_ops { * Optional, allows the file system to discard state on a page where * we failed to submit any I/O. */ - void (*discard_page)(struct page *page, loff_t fileoff); + void (*discard_folio)(struct folio *folio, loff_t pos); }; struct iomap_writepage_ctx { @@ -297,9 +297,6 @@ void iomap_finish_ioends(struct iomap_ioend *ioend, int error); void iomap_ioend_try_merge(struct iomap_ioend *ioend, struct list_head *more_ioends); void iomap_sort_ioends(struct list_head *ioend_list); -int iomap_writepage(struct page *page, struct writeback_control *wbc, - struct iomap_writepage_ctx *wpc, - const struct iomap_writeback_ops *ops); int iomap_writepages(struct address_space *mapping, struct writeback_control *wbc, struct iomap_writepage_ctx *wpc, const struct iomap_writeback_ops *ops); @@ -315,6 +312,16 @@ struct iomap_dio_ops { unsigned flags); void (*submit_io)(const struct iomap_iter *iter, struct bio *bio, loff_t file_offset); + + /* + * Filesystems wishing to attach private information to a direct io bio + * must provide a ->submit_io method that attaches the additional + * information to the bio and changes the ->bi_end_io callback to a + * custom function. This function should, at a minimum, perform any + * relevant post-processing of the bio and end with a call to + * iomap_dio_bio_end_io. + */ + struct bio_set *bio_set; }; /* @@ -337,13 +344,20 @@ struct iomap_dio_ops { */ #define IOMAP_DIO_PARTIAL (1 << 2) +/* + * The caller will sync the write if needed; do not sync it within + * iomap_dio_rw. Overrides IOMAP_DIO_FORCE_WAIT. + */ +#define IOMAP_DIO_NOSYNC (1 << 3) + ssize_t iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, const struct iomap_ops *ops, const struct iomap_dio_ops *dops, - unsigned int dio_flags, size_t done_before); + unsigned int dio_flags, void *private, size_t done_before); struct iomap_dio *__iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, const struct iomap_ops *ops, const struct iomap_dio_ops *dops, - unsigned int dio_flags, size_t done_before); + unsigned int dio_flags, void *private, size_t done_before); ssize_t iomap_dio_complete(struct iomap_dio *dio); +void iomap_dio_bio_end_io(struct bio *bio); #ifdef CONFIG_SWAP struct file; diff --git a/include/linux/iommu.h b/include/linux/iommu.h index d2f3435e7d17..3c9da1f8979e 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -37,6 +37,7 @@ struct iommu_group; struct bus_type; struct device; struct iommu_domain; +struct iommu_domain_ops; struct notifier_block; struct iommu_sva; struct iommu_fault_event; @@ -88,7 +89,7 @@ struct iommu_domain_geometry { struct iommu_domain { unsigned type; - const struct iommu_ops *ops; + const struct iommu_domain_ops *ops; unsigned long pgsize_bitmap; /* Bitmap of page sizes in use */ iommu_fault_handler_t handler; void *handler_token; @@ -102,10 +103,11 @@ static inline bool iommu_is_dma_domain(struct iommu_domain *domain) } enum iommu_cap { - IOMMU_CAP_CACHE_COHERENCY, /* IOMMU can enforce cache coherent DMA - transactions */ + IOMMU_CAP_CACHE_COHERENCY, /* IOMMU_CACHE is supported */ IOMMU_CAP_INTR_REMAP, /* IOMMU supports interrupt isolation */ IOMMU_CAP_NOEXEC, /* IOMMU_NOEXEC flag */ + IOMMU_CAP_PRE_BOOT_PROTECTION, /* Firmware says it used the IOMMU for + DMA protection and we should too */ }; /* These are the possible reserved region types */ @@ -133,6 +135,7 @@ enum iommu_resv_type { * @length: Length of the region in bytes * @prot: IOMMU Protection flags (READ/WRITE/...) * @type: Type of the reserved region + * @free: Callback to free associated memory allocations */ struct iommu_resv_region { struct list_head list; @@ -140,11 +143,19 @@ struct iommu_resv_region { size_t length; int prot; enum iommu_resv_type type; + void (*free)(struct device *dev, struct iommu_resv_region *region); +}; + +struct iommu_iort_rmr_data { + struct iommu_resv_region rr; + + /* Stream IDs associated with IORT RMR entry */ + const u32 *sids; + u32 num_sids; }; /** * enum iommu_dev_features - Per device IOMMU features - * @IOMMU_DEV_FEAT_AUX: Auxiliary domain feature * @IOMMU_DEV_FEAT_SVA: Shared Virtual Addresses * @IOMMU_DEV_FEAT_IOPF: I/O Page Faults such as PRI or Stall. Generally * enabling %IOMMU_DEV_FEAT_SVA requires @@ -153,11 +164,9 @@ struct iommu_resv_region { * supported, this feature must be enabled before and * disabled after %IOMMU_DEV_FEAT_SVA. * - * Device drivers query whether a feature is supported using - * iommu_dev_has_feature(), and enable it using iommu_dev_enable_feature(). + * Device drivers enable a feature using iommu_dev_enable_feature(). */ enum iommu_dev_features { - IOMMU_DEV_FEAT_AUX, IOMMU_DEV_FEAT_SVA, IOMMU_DEV_FEAT_IOPF, }; @@ -186,7 +195,7 @@ struct iommu_iotlb_gather { unsigned long start; unsigned long end; size_t pgsize; - struct page *freelist; + struct list_head freelist; bool queued; }; @@ -194,105 +203,50 @@ struct iommu_iotlb_gather { * struct iommu_ops - iommu ops and capabilities * @capable: check capability * @domain_alloc: allocate iommu domain - * @domain_free: free iommu domain - * @attach_dev: attach device to an iommu domain - * @detach_dev: detach device from an iommu domain - * @map: map a physically contiguous memory region to an iommu domain - * @map_pages: map a physically contiguous set of pages of the same size to - * an iommu domain. - * @unmap: unmap a physically contiguous memory region from an iommu domain - * @unmap_pages: unmap a number of pages of the same size from an iommu domain - * @flush_iotlb_all: Synchronously flush all hardware TLBs for this domain - * @iotlb_sync_map: Sync mappings created recently using @map to the hardware - * @iotlb_sync: Flush all queued ranges from the hardware TLBs and empty flush - * queue - * @iova_to_phys: translate iova to physical address * @probe_device: Add device to iommu driver handling * @release_device: Remove device from iommu driver handling * @probe_finalize: Do final setup work after the device is added to an IOMMU * group and attached to the groups domain * @device_group: find iommu group for a particular device - * @enable_nesting: Enable nesting - * @set_pgtable_quirks: Set io page table quirks (IO_PGTABLE_QUIRK_*) * @get_resv_regions: Request list of reserved regions for a device - * @put_resv_regions: Free list of reserved regions for a device - * @apply_resv_region: Temporary helper call-back for iova reserved ranges * @of_xlate: add OF master IDs to iommu grouping * @is_attach_deferred: Check if domain attach should be deferred from iommu * driver init to device driver init (default no) - * @dev_has/enable/disable_feat: per device entries to check/enable/disable + * @dev_enable/disable_feat: per device entries to enable/disable * iommu specific features. - * @dev_feat_enabled: check enabled feature - * @aux_attach/detach_dev: aux-domain specific attach/detach entries. - * @aux_get_pasid: get the pasid given an aux-domain * @sva_bind: Bind process address space to device * @sva_unbind: Unbind process address space from device * @sva_get_pasid: Get PASID associated to a SVA handle * @page_response: handle page request response - * @cache_invalidate: invalidate translation caches - * @sva_bind_gpasid: bind guest pasid and mm - * @sva_unbind_gpasid: unbind guest pasid and mm * @def_domain_type: device default domain type, return value: * - IOMMU_DOMAIN_IDENTITY: must use an identity domain * - IOMMU_DOMAIN_DMA: must use a dma domain * - 0: use the default setting + * @default_domain_ops: the default ops for domains * @pgsize_bitmap: bitmap of all possible supported page sizes * @owner: Driver module providing these ops */ struct iommu_ops { - bool (*capable)(enum iommu_cap); + bool (*capable)(struct device *dev, enum iommu_cap); /* Domain allocation and freeing by the iommu driver */ struct iommu_domain *(*domain_alloc)(unsigned iommu_domain_type); - void (*domain_free)(struct iommu_domain *); - int (*attach_dev)(struct iommu_domain *domain, struct device *dev); - void (*detach_dev)(struct iommu_domain *domain, struct device *dev); - int (*map)(struct iommu_domain *domain, unsigned long iova, - phys_addr_t paddr, size_t size, int prot, gfp_t gfp); - int (*map_pages)(struct iommu_domain *domain, unsigned long iova, - phys_addr_t paddr, size_t pgsize, size_t pgcount, - int prot, gfp_t gfp, size_t *mapped); - size_t (*unmap)(struct iommu_domain *domain, unsigned long iova, - size_t size, struct iommu_iotlb_gather *iotlb_gather); - size_t (*unmap_pages)(struct iommu_domain *domain, unsigned long iova, - size_t pgsize, size_t pgcount, - struct iommu_iotlb_gather *iotlb_gather); - void (*flush_iotlb_all)(struct iommu_domain *domain); - void (*iotlb_sync_map)(struct iommu_domain *domain, unsigned long iova, - size_t size); - void (*iotlb_sync)(struct iommu_domain *domain, - struct iommu_iotlb_gather *iotlb_gather); - phys_addr_t (*iova_to_phys)(struct iommu_domain *domain, dma_addr_t iova); struct iommu_device *(*probe_device)(struct device *dev); void (*release_device)(struct device *dev); void (*probe_finalize)(struct device *dev); struct iommu_group *(*device_group)(struct device *dev); - int (*enable_nesting)(struct iommu_domain *domain); - int (*set_pgtable_quirks)(struct iommu_domain *domain, - unsigned long quirks); /* Request/Free a list of reserved regions for a device */ void (*get_resv_regions)(struct device *dev, struct list_head *list); - void (*put_resv_regions)(struct device *dev, struct list_head *list); - void (*apply_resv_region)(struct device *dev, - struct iommu_domain *domain, - struct iommu_resv_region *region); int (*of_xlate)(struct device *dev, struct of_phandle_args *args); - bool (*is_attach_deferred)(struct iommu_domain *domain, struct device *dev); + bool (*is_attach_deferred)(struct device *dev); /* Per device IOMMU features */ - bool (*dev_has_feat)(struct device *dev, enum iommu_dev_features f); - bool (*dev_feat_enabled)(struct device *dev, enum iommu_dev_features f); int (*dev_enable_feat)(struct device *dev, enum iommu_dev_features f); int (*dev_disable_feat)(struct device *dev, enum iommu_dev_features f); - /* Aux-domain specific attach/detach entries */ - int (*aux_attach_dev)(struct iommu_domain *domain, struct device *dev); - void (*aux_detach_dev)(struct iommu_domain *domain, struct device *dev); - int (*aux_get_pasid)(struct iommu_domain *domain, struct device *dev); - struct iommu_sva *(*sva_bind)(struct device *dev, struct mm_struct *mm, void *drvdata); void (*sva_unbind)(struct iommu_sva *handle); @@ -301,20 +255,68 @@ struct iommu_ops { int (*page_response)(struct device *dev, struct iommu_fault_event *evt, struct iommu_page_response *msg); - int (*cache_invalidate)(struct iommu_domain *domain, struct device *dev, - struct iommu_cache_invalidate_info *inv_info); - int (*sva_bind_gpasid)(struct iommu_domain *domain, - struct device *dev, struct iommu_gpasid_bind_data *data); - - int (*sva_unbind_gpasid)(struct device *dev, u32 pasid); int (*def_domain_type)(struct device *dev); + const struct iommu_domain_ops *default_domain_ops; unsigned long pgsize_bitmap; struct module *owner; }; /** + * struct iommu_domain_ops - domain specific operations + * @attach_dev: attach an iommu domain to a device + * @detach_dev: detach an iommu domain from a device + * @map: map a physically contiguous memory region to an iommu domain + * @map_pages: map a physically contiguous set of pages of the same size to + * an iommu domain. + * @unmap: unmap a physically contiguous memory region from an iommu domain + * @unmap_pages: unmap a number of pages of the same size from an iommu domain + * @flush_iotlb_all: Synchronously flush all hardware TLBs for this domain + * @iotlb_sync_map: Sync mappings created recently using @map to the hardware + * @iotlb_sync: Flush all queued ranges from the hardware TLBs and empty flush + * queue + * @iova_to_phys: translate iova to physical address + * @enforce_cache_coherency: Prevent any kind of DMA from bypassing IOMMU_CACHE, + * including no-snoop TLPs on PCIe or other platform + * specific mechanisms. + * @enable_nesting: Enable nesting + * @set_pgtable_quirks: Set io page table quirks (IO_PGTABLE_QUIRK_*) + * @free: Release the domain after use. + */ +struct iommu_domain_ops { + int (*attach_dev)(struct iommu_domain *domain, struct device *dev); + void (*detach_dev)(struct iommu_domain *domain, struct device *dev); + + int (*map)(struct iommu_domain *domain, unsigned long iova, + phys_addr_t paddr, size_t size, int prot, gfp_t gfp); + int (*map_pages)(struct iommu_domain *domain, unsigned long iova, + phys_addr_t paddr, size_t pgsize, size_t pgcount, + int prot, gfp_t gfp, size_t *mapped); + size_t (*unmap)(struct iommu_domain *domain, unsigned long iova, + size_t size, struct iommu_iotlb_gather *iotlb_gather); + size_t (*unmap_pages)(struct iommu_domain *domain, unsigned long iova, + size_t pgsize, size_t pgcount, + struct iommu_iotlb_gather *iotlb_gather); + + void (*flush_iotlb_all)(struct iommu_domain *domain); + void (*iotlb_sync_map)(struct iommu_domain *domain, unsigned long iova, + size_t size); + void (*iotlb_sync)(struct iommu_domain *domain, + struct iommu_iotlb_gather *iotlb_gather); + + phys_addr_t (*iova_to_phys)(struct iommu_domain *domain, + dma_addr_t iova); + + bool (*enforce_cache_coherency)(struct iommu_domain *domain); + int (*enable_nesting)(struct iommu_domain *domain); + int (*set_pgtable_quirks)(struct iommu_domain *domain, + unsigned long quirks); + + void (*free)(struct iommu_domain *domain); +}; + +/** * struct iommu_device - IOMMU core representation of one IOMMU hardware * instance * @list: Used by the iommu-core to keep a list of registered iommus @@ -399,20 +401,24 @@ static inline void iommu_iotlb_gather_init(struct iommu_iotlb_gather *gather) { *gather = (struct iommu_iotlb_gather) { .start = ULONG_MAX, + .freelist = LIST_HEAD_INIT(gather->freelist), }; } -#define IOMMU_GROUP_NOTIFY_ADD_DEVICE 1 /* Device added */ -#define IOMMU_GROUP_NOTIFY_DEL_DEVICE 2 /* Pre Device removed */ -#define IOMMU_GROUP_NOTIFY_BIND_DRIVER 3 /* Pre Driver bind */ -#define IOMMU_GROUP_NOTIFY_BOUND_DRIVER 4 /* Post Driver bind */ -#define IOMMU_GROUP_NOTIFY_UNBIND_DRIVER 5 /* Pre Driver unbind */ -#define IOMMU_GROUP_NOTIFY_UNBOUND_DRIVER 6 /* Post Driver unbind */ +static inline const struct iommu_ops *dev_iommu_ops(struct device *dev) +{ + /* + * Assume that valid ops must be installed if iommu_probe_device() + * has succeeded. The device ops are essentially for internal use + * within the IOMMU subsystem itself, so we should be able to trust + * ourselves not to misuse the helper. + */ + return dev->iommu->iommu_dev->ops; +} -extern int bus_set_iommu(struct bus_type *bus, const struct iommu_ops *ops); extern int bus_iommu_probe(struct bus_type *bus); extern bool iommu_present(struct bus_type *bus); -extern bool iommu_capable(struct bus_type *bus, enum iommu_cap cap); +extern bool device_iommu_capable(struct device *dev, enum iommu_cap cap); extern struct iommu_domain *iommu_domain_alloc(struct bus_type *bus); extern struct iommu_group *iommu_group_get_by_id(int id); extern void iommu_domain_free(struct iommu_domain *domain); @@ -420,14 +426,6 @@ extern int iommu_attach_device(struct iommu_domain *domain, struct device *dev); extern void iommu_detach_device(struct iommu_domain *domain, struct device *dev); -extern int iommu_uapi_cache_invalidate(struct iommu_domain *domain, - struct device *dev, - void __user *uinfo); - -extern int iommu_uapi_sva_bind_gpasid(struct iommu_domain *domain, - struct device *dev, void __user *udata); -extern int iommu_uapi_sva_unbind_gpasid(struct iommu_domain *domain, - struct device *dev, void __user *udata); extern int iommu_sva_unbind_gpasid(struct iommu_domain *domain, struct device *dev, ioasid_t pasid); extern struct iommu_domain *iommu_get_domain_for_dev(struct device *dev); @@ -452,14 +450,12 @@ extern void iommu_set_fault_handler(struct iommu_domain *domain, extern void iommu_get_resv_regions(struct device *dev, struct list_head *list); extern void iommu_put_resv_regions(struct device *dev, struct list_head *list); -extern void generic_iommu_put_resv_regions(struct device *dev, - struct list_head *list); extern void iommu_set_default_passthrough(bool cmd_line); extern void iommu_set_default_translated(bool cmd_line); extern bool iommu_default_passthrough(void); extern struct iommu_resv_region * iommu_alloc_resv_region(phys_addr_t start, size_t length, int prot, - enum iommu_resv_type type); + enum iommu_resv_type type, gfp_t gfp); extern int iommu_get_group_resv_regions(struct iommu_group *group, struct list_head *head); @@ -481,10 +477,6 @@ extern int iommu_group_for_each_dev(struct iommu_group *group, void *data, extern struct iommu_group *iommu_group_get(struct device *dev); extern struct iommu_group *iommu_group_ref_get(struct iommu_group *group); extern void iommu_group_put(struct iommu_group *group); -extern int iommu_group_register_notifier(struct iommu_group *group, - struct notifier_block *nb); -extern int iommu_group_unregister_notifier(struct iommu_group *group, - struct notifier_block *nb); extern int iommu_register_device_fault_handler(struct device *dev, iommu_dev_fault_handler_t handler, void *data); @@ -670,10 +662,6 @@ void iommu_release_device(struct device *dev); int iommu_dev_enable_feature(struct device *dev, enum iommu_dev_features f); int iommu_dev_disable_feature(struct device *dev, enum iommu_dev_features f); -bool iommu_dev_feature_enabled(struct device *dev, enum iommu_dev_features f); -int iommu_aux_attach_device(struct iommu_domain *domain, struct device *dev); -void iommu_aux_detach_device(struct iommu_domain *domain, struct device *dev); -int iommu_aux_get_pasid(struct iommu_domain *domain, struct device *dev); struct iommu_sva *iommu_sva_bind_device(struct device *dev, struct mm_struct *mm, @@ -681,6 +669,13 @@ struct iommu_sva *iommu_sva_bind_device(struct device *dev, void iommu_sva_unbind_device(struct iommu_sva *handle); u32 iommu_sva_get_pasid(struct iommu_sva *handle); +int iommu_device_use_default_domain(struct device *dev); +void iommu_device_unuse_default_domain(struct device *dev); + +int iommu_group_claim_dma_owner(struct iommu_group *group, void *owner); +void iommu_group_release_dma_owner(struct iommu_group *group); +bool iommu_group_dma_owner_claimed(struct iommu_group *group); + #else /* CONFIG_IOMMU_API */ struct iommu_ops {}; @@ -695,7 +690,7 @@ static inline bool iommu_present(struct bus_type *bus) return false; } -static inline bool iommu_capable(struct bus_type *bus, enum iommu_cap cap) +static inline bool device_iommu_capable(struct device *dev, enum iommu_cap cap) { return false; } @@ -877,18 +872,6 @@ static inline void iommu_group_put(struct iommu_group *group) { } -static inline int iommu_group_register_notifier(struct iommu_group *group, - struct notifier_block *nb) -{ - return -ENODEV; -} - -static inline int iommu_group_unregister_notifier(struct iommu_group *group, - struct notifier_block *nb) -{ - return 0; -} - static inline int iommu_register_device_fault_handler(struct device *dev, iommu_dev_fault_handler_t handler, @@ -1000,12 +983,6 @@ const struct iommu_ops *iommu_ops_from_fwnode(struct fwnode_handle *fwnode) return NULL; } -static inline bool -iommu_dev_feature_enabled(struct device *dev, enum iommu_dev_features feat) -{ - return false; -} - static inline int iommu_dev_enable_feature(struct device *dev, enum iommu_dev_features feat) { @@ -1018,23 +995,6 @@ iommu_dev_disable_feature(struct device *dev, enum iommu_dev_features feat) return -ENODEV; } -static inline int -iommu_aux_attach_device(struct iommu_domain *domain, struct device *dev) -{ - return -ENODEV; -} - -static inline void -iommu_aux_detach_device(struct iommu_domain *domain, struct device *dev) -{ -} - -static inline int -iommu_aux_get_pasid(struct iommu_domain *domain, struct device *dev) -{ - return -ENODEV; -} - static inline struct iommu_sva * iommu_sva_bind_device(struct device *dev, struct mm_struct *mm, void *drvdata) { @@ -1050,36 +1010,33 @@ static inline u32 iommu_sva_get_pasid(struct iommu_sva *handle) return IOMMU_PASID_INVALID; } -static inline int -iommu_uapi_cache_invalidate(struct iommu_domain *domain, - struct device *dev, - struct iommu_cache_invalidate_info *inv_info) +static inline struct iommu_fwspec *dev_iommu_fwspec_get(struct device *dev) { - return -ENODEV; + return NULL; } -static inline int iommu_uapi_sva_bind_gpasid(struct iommu_domain *domain, - struct device *dev, void __user *udata) +static inline int iommu_device_use_default_domain(struct device *dev) { - return -ENODEV; + return 0; } -static inline int iommu_uapi_sva_unbind_gpasid(struct iommu_domain *domain, - struct device *dev, void __user *udata) +static inline void iommu_device_unuse_default_domain(struct device *dev) { - return -ENODEV; } -static inline int iommu_sva_unbind_gpasid(struct iommu_domain *domain, - struct device *dev, - ioasid_t pasid) +static inline int +iommu_group_claim_dma_owner(struct iommu_group *group, void *owner) { return -ENODEV; } -static inline struct iommu_fwspec *dev_iommu_fwspec_get(struct device *dev) +static inline void iommu_group_release_dma_owner(struct iommu_group *group) { - return NULL; +} + +static inline bool iommu_group_dma_owner_claimed(struct iommu_group *group) +{ + return false; } #endif /* CONFIG_IOMMU_API */ @@ -1106,4 +1063,40 @@ void iommu_debugfs_setup(void); static inline void iommu_debugfs_setup(void) {} #endif +#ifdef CONFIG_IOMMU_DMA +#include <linux/msi.h> + +/* Setup call for arch DMA mapping code */ +void iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 dma_limit); + +int iommu_get_msi_cookie(struct iommu_domain *domain, dma_addr_t base); + +int iommu_dma_prepare_msi(struct msi_desc *desc, phys_addr_t msi_addr); +void iommu_dma_compose_msi_msg(struct msi_desc *desc, struct msi_msg *msg); + +#else /* CONFIG_IOMMU_DMA */ + +struct msi_desc; +struct msi_msg; + +static inline void iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 dma_limit) +{ +} + +static inline int iommu_get_msi_cookie(struct iommu_domain *domain, dma_addr_t base) +{ + return -ENODEV; +} + +static inline int iommu_dma_prepare_msi(struct msi_desc *desc, phys_addr_t msi_addr) +{ + return 0; +} + +static inline void iommu_dma_compose_msi_msg(struct msi_desc *desc, struct msi_msg *msg) +{ +} + +#endif /* CONFIG_IOMMU_DMA */ + #endif /* __LINUX_IOMMU_H */ diff --git a/include/linux/ioport.h b/include/linux/ioport.h index 8359c50f9988..27642ca15d93 100644 --- a/include/linux/ioport.h +++ b/include/linux/ioport.h @@ -79,7 +79,8 @@ struct resource { #define IORESOURCE_IRQ_HIGHLEVEL (1<<2) #define IORESOURCE_IRQ_LOWLEVEL (1<<3) #define IORESOURCE_IRQ_SHAREABLE (1<<4) -#define IORESOURCE_IRQ_OPTIONAL (1<<5) +#define IORESOURCE_IRQ_OPTIONAL (1<<5) +#define IORESOURCE_IRQ_WAKECAPABLE (1<<6) /* PnP DMA specific bits (IORESOURCE_BITS) */ #define IORESOURCE_DMA_TYPE_MASK (3<<0) @@ -141,6 +142,7 @@ enum { IORES_DESC_DEVICE_PRIVATE_MEMORY = 6, IORES_DESC_RESERVED = 7, IORES_DESC_SOFT_RESERVED = 8, + IORES_DESC_CXL = 9, }; /* @@ -171,6 +173,11 @@ enum { #define DEFINE_RES_MEM(_start, _size) \ DEFINE_RES_MEM_NAMED((_start), (_size), NULL) +#define DEFINE_RES_REG_NAMED(_start, _size, _name) \ + DEFINE_RES_NAMED((_start), (_size), (_name), IORESOURCE_REG) +#define DEFINE_RES_REG(_start, _size) \ + DEFINE_RES_REG_NAMED((_start), (_size), NULL) + #define DEFINE_RES_IRQ_NAMED(_irq, _name) \ DEFINE_RES_NAMED((_irq), 1, (_name), IORESOURCE_IRQ) #define DEFINE_RES_IRQ(_irq) \ @@ -262,6 +269,8 @@ resource_union(struct resource *r1, struct resource *r2, struct resource *r) #define request_muxed_region(start,n,name) __request_region(&ioport_resource, (start), (n), (name), IORESOURCE_MUXED) #define __request_mem_region(start,n,name, excl) __request_region(&iomem_resource, (start), (n), (name), excl) #define request_mem_region(start,n,name) __request_region(&iomem_resource, (start), (n), (name), 0) +#define request_mem_region_muxed(start, n, name) \ + __request_region(&iomem_resource, (start), (n), (name), IORESOURCE_MUXED) #define request_mem_region_exclusive(start,n,name) \ __request_region(&iomem_resource, (start), (n), (name), IORESOURCE_EXCLUSIVE) #define rename_region(region, newname) do { (region)->name = (newname); } while (0) @@ -327,6 +336,8 @@ struct resource *devm_request_free_mem_region(struct device *dev, struct resource *base, unsigned long size); struct resource *request_free_mem_region(struct resource *base, unsigned long size, const char *name); +struct resource *alloc_free_mem_region(struct resource *base, + unsigned long size, unsigned long align, const char *name); static inline void irqresource_disabled(struct resource *res, u32 irq) { diff --git a/include/linux/ioprio.h b/include/linux/ioprio.h index 3f53bc27a19b..7578d4f6a969 100644 --- a/include/linux/ioprio.h +++ b/include/linux/ioprio.h @@ -11,7 +11,7 @@ /* * Default IO priority. */ -#define IOPRIO_DEFAULT IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, IOPRIO_BE_NORM) +#define IOPRIO_DEFAULT IOPRIO_PRIO_VALUE(IOPRIO_CLASS_NONE, 0) /* * Check that a priority value has a valid class. @@ -46,23 +46,19 @@ static inline int task_nice_ioclass(struct task_struct *task) return IOPRIO_CLASS_BE; } -/* - * If the calling process has set an I/O priority, use that. Otherwise, return - * the default I/O priority. - */ -static inline int get_current_ioprio(void) +#ifdef CONFIG_BLOCK +int __get_task_ioprio(struct task_struct *p); +#else +static inline int __get_task_ioprio(struct task_struct *p) { - struct io_context *ioc = current->io_context; - - if (ioc) - return ioc->ioprio; return IOPRIO_DEFAULT; } +#endif /* CONFIG_BLOCK */ -/* - * For inheritance, return the highest of the two given priorities - */ -extern int ioprio_best(unsigned short aprio, unsigned short bprio); +static inline int get_current_ioprio(void) +{ + return __get_task_ioprio(current); +} extern int set_task_ioprio(struct task_struct *task, int ioprio); diff --git a/include/linux/iosys-map.h b/include/linux/iosys-map.h new file mode 100644 index 000000000000..cb71aa616bd3 --- /dev/null +++ b/include/linux/iosys-map.h @@ -0,0 +1,516 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Pointer abstraction for IO/system memory + */ + +#ifndef __IOSYS_MAP_H__ +#define __IOSYS_MAP_H__ + +#include <linux/compiler_types.h> +#include <linux/io.h> +#include <linux/string.h> + +/** + * DOC: overview + * + * When accessing a memory region, depending on its location, users may have to + * access it with I/O operations or memory load/store operations. For example, + * copying to system memory could be done with memcpy(), copying to I/O memory + * would be done with memcpy_toio(). + * + * .. code-block:: c + * + * void *vaddr = ...; // pointer to system memory + * memcpy(vaddr, src, len); + * + * void *vaddr_iomem = ...; // pointer to I/O memory + * memcpy_toio(vaddr_iomem, src, len); + * + * The user of such pointer may not have information about the mapping of that + * region or may want to have a single code path to handle operations on that + * buffer, regardless if it's located in system or IO memory. The type + * :c:type:`struct iosys_map <iosys_map>` and its helpers abstract that so the + * buffer can be passed around to other drivers or have separate duties inside + * the same driver for allocation, read and write operations. + * + * Open-coding access to :c:type:`struct iosys_map <iosys_map>` is considered + * bad style. Rather then accessing its fields directly, use one of the provided + * helper functions, or implement your own. For example, instances of + * :c:type:`struct iosys_map <iosys_map>` can be initialized statically with + * IOSYS_MAP_INIT_VADDR(), or at runtime with iosys_map_set_vaddr(). These + * helpers will set an address in system memory. + * + * .. code-block:: c + * + * struct iosys_map map = IOSYS_MAP_INIT_VADDR(0xdeadbeaf); + * + * iosys_map_set_vaddr(&map, 0xdeadbeaf); + * + * To set an address in I/O memory, use IOSYS_MAP_INIT_VADDR_IOMEM() or + * iosys_map_set_vaddr_iomem(). + * + * .. code-block:: c + * + * struct iosys_map map = IOSYS_MAP_INIT_VADDR_IOMEM(0xdeadbeaf); + * + * iosys_map_set_vaddr_iomem(&map, 0xdeadbeaf); + * + * Instances of struct iosys_map do not have to be cleaned up, but + * can be cleared to NULL with iosys_map_clear(). Cleared mappings + * always refer to system memory. + * + * .. code-block:: c + * + * iosys_map_clear(&map); + * + * Test if a mapping is valid with either iosys_map_is_set() or + * iosys_map_is_null(). + * + * .. code-block:: c + * + * if (iosys_map_is_set(&map) != iosys_map_is_null(&map)) + * // always true + * + * Instances of :c:type:`struct iosys_map <iosys_map>` can be compared for + * equality with iosys_map_is_equal(). Mappings that point to different memory + * spaces, system or I/O, are never equal. That's even true if both spaces are + * located in the same address space, both mappings contain the same address + * value, or both mappings refer to NULL. + * + * .. code-block:: c + * + * struct iosys_map sys_map; // refers to system memory + * struct iosys_map io_map; // refers to I/O memory + * + * if (iosys_map_is_equal(&sys_map, &io_map)) + * // always false + * + * A set up instance of struct iosys_map can be used to access or manipulate the + * buffer memory. Depending on the location of the memory, the provided helpers + * will pick the correct operations. Data can be copied into the memory with + * iosys_map_memcpy_to(). The address can be manipulated with iosys_map_incr(). + * + * .. code-block:: c + * + * const void *src = ...; // source buffer + * size_t len = ...; // length of src + * + * iosys_map_memcpy_to(&map, src, len); + * iosys_map_incr(&map, len); // go to first byte after the memcpy + */ + +/** + * struct iosys_map - Pointer to IO/system memory + * @vaddr_iomem: The buffer's address if in I/O memory + * @vaddr: The buffer's address if in system memory + * @is_iomem: True if the buffer is located in I/O memory, or false + * otherwise. + */ +struct iosys_map { + union { + void __iomem *vaddr_iomem; + void *vaddr; + }; + bool is_iomem; +}; + +/** + * IOSYS_MAP_INIT_VADDR - Initializes struct iosys_map to an address in system memory + * @vaddr_: A system-memory address + */ +#define IOSYS_MAP_INIT_VADDR(vaddr_) \ + { \ + .vaddr = (vaddr_), \ + .is_iomem = false, \ + } + +/** + * IOSYS_MAP_INIT_VADDR_IOMEM - Initializes struct iosys_map to an address in I/O memory + * @vaddr_iomem_: An I/O-memory address + */ +#define IOSYS_MAP_INIT_VADDR_IOMEM(vaddr_iomem_) \ + { \ + .vaddr_iomem = (vaddr_iomem_), \ + .is_iomem = true, \ + } + +/** + * IOSYS_MAP_INIT_OFFSET - Initializes struct iosys_map from another iosys_map + * @map_: The dma-buf mapping structure to copy from + * @offset_: Offset to add to the other mapping + * + * Initializes a new iosys_map struct based on another passed as argument. It + * does a shallow copy of the struct so it's possible to update the back storage + * without changing where the original map points to. It is the equivalent of + * doing: + * + * .. code-block:: c + * + * iosys_map map = other_map; + * iosys_map_incr(&map, &offset); + * + * Example usage: + * + * .. code-block:: c + * + * void foo(struct device *dev, struct iosys_map *base_map) + * { + * ... + * struct iosys_map map = IOSYS_MAP_INIT_OFFSET(base_map, FIELD_OFFSET); + * ... + * } + * + * The advantage of using the initializer over just increasing the offset with + * iosys_map_incr() like above is that the new map will always point to the + * right place of the buffer during its scope. It reduces the risk of updating + * the wrong part of the buffer and having no compiler warning about that. If + * the assignment to IOSYS_MAP_INIT_OFFSET() is forgotten, the compiler can warn + * about the use of uninitialized variable. + */ +#define IOSYS_MAP_INIT_OFFSET(map_, offset_) ({ \ + struct iosys_map copy = *map_; \ + iosys_map_incr(©, offset_); \ + copy; \ +}) + +/** + * iosys_map_set_vaddr - Sets a iosys mapping structure to an address in system memory + * @map: The iosys_map structure + * @vaddr: A system-memory address + * + * Sets the address and clears the I/O-memory flag. + */ +static inline void iosys_map_set_vaddr(struct iosys_map *map, void *vaddr) +{ + map->vaddr = vaddr; + map->is_iomem = false; +} + +/** + * iosys_map_set_vaddr_iomem - Sets a iosys mapping structure to an address in I/O memory + * @map: The iosys_map structure + * @vaddr_iomem: An I/O-memory address + * + * Sets the address and the I/O-memory flag. + */ +static inline void iosys_map_set_vaddr_iomem(struct iosys_map *map, + void __iomem *vaddr_iomem) +{ + map->vaddr_iomem = vaddr_iomem; + map->is_iomem = true; +} + +/** + * iosys_map_is_equal - Compares two iosys mapping structures for equality + * @lhs: The iosys_map structure + * @rhs: A iosys_map structure to compare with + * + * Two iosys mapping structures are equal if they both refer to the same type of memory + * and to the same address within that memory. + * + * Returns: + * True is both structures are equal, or false otherwise. + */ +static inline bool iosys_map_is_equal(const struct iosys_map *lhs, + const struct iosys_map *rhs) +{ + if (lhs->is_iomem != rhs->is_iomem) + return false; + else if (lhs->is_iomem) + return lhs->vaddr_iomem == rhs->vaddr_iomem; + else + return lhs->vaddr == rhs->vaddr; +} + +/** + * iosys_map_is_null - Tests for a iosys mapping to be NULL + * @map: The iosys_map structure + * + * Depending on the state of struct iosys_map.is_iomem, tests if the + * mapping is NULL. + * + * Returns: + * True if the mapping is NULL, or false otherwise. + */ +static inline bool iosys_map_is_null(const struct iosys_map *map) +{ + if (map->is_iomem) + return !map->vaddr_iomem; + return !map->vaddr; +} + +/** + * iosys_map_is_set - Tests if the iosys mapping has been set + * @map: The iosys_map structure + * + * Depending on the state of struct iosys_map.is_iomem, tests if the + * mapping has been set. + * + * Returns: + * True if the mapping is been set, or false otherwise. + */ +static inline bool iosys_map_is_set(const struct iosys_map *map) +{ + return !iosys_map_is_null(map); +} + +/** + * iosys_map_clear - Clears a iosys mapping structure + * @map: The iosys_map structure + * + * Clears all fields to zero, including struct iosys_map.is_iomem, so + * mapping structures that were set to point to I/O memory are reset for + * system memory. Pointers are cleared to NULL. This is the default. + */ +static inline void iosys_map_clear(struct iosys_map *map) +{ + if (map->is_iomem) { + map->vaddr_iomem = NULL; + map->is_iomem = false; + } else { + map->vaddr = NULL; + } +} + +/** + * iosys_map_memcpy_to - Memcpy into offset of iosys_map + * @dst: The iosys_map structure + * @dst_offset: The offset from which to copy + * @src: The source buffer + * @len: The number of byte in src + * + * Copies data into a iosys_map with an offset. The source buffer is in + * system memory. Depending on the buffer's location, the helper picks the + * correct method of accessing the memory. + */ +static inline void iosys_map_memcpy_to(struct iosys_map *dst, size_t dst_offset, + const void *src, size_t len) +{ + if (dst->is_iomem) + memcpy_toio(dst->vaddr_iomem + dst_offset, src, len); + else + memcpy(dst->vaddr + dst_offset, src, len); +} + +/** + * iosys_map_memcpy_from - Memcpy from iosys_map into system memory + * @dst: Destination in system memory + * @src: The iosys_map structure + * @src_offset: The offset from which to copy + * @len: The number of byte in src + * + * Copies data from a iosys_map with an offset. The dest buffer is in + * system memory. Depending on the mapping location, the helper picks the + * correct method of accessing the memory. + */ +static inline void iosys_map_memcpy_from(void *dst, const struct iosys_map *src, + size_t src_offset, size_t len) +{ + if (src->is_iomem) + memcpy_fromio(dst, src->vaddr_iomem + src_offset, len); + else + memcpy(dst, src->vaddr + src_offset, len); +} + +/** + * iosys_map_incr - Increments the address stored in a iosys mapping + * @map: The iosys_map structure + * @incr: The number of bytes to increment + * + * Increments the address stored in a iosys mapping. Depending on the + * buffer's location, the correct value will be updated. + */ +static inline void iosys_map_incr(struct iosys_map *map, size_t incr) +{ + if (map->is_iomem) + map->vaddr_iomem += incr; + else + map->vaddr += incr; +} + +/** + * iosys_map_memset - Memset iosys_map + * @dst: The iosys_map structure + * @offset: Offset from dst where to start setting value + * @value: The value to set + * @len: The number of bytes to set in dst + * + * Set value in iosys_map. Depending on the buffer's location, the helper + * picks the correct method of accessing the memory. + */ +static inline void iosys_map_memset(struct iosys_map *dst, size_t offset, + int value, size_t len) +{ + if (dst->is_iomem) + memset_io(dst->vaddr_iomem + offset, value, len); + else + memset(dst->vaddr + offset, value, len); +} + +#ifdef CONFIG_64BIT +#define __iosys_map_rd_io_u64_case(val_, vaddr_iomem_) \ + u64: val_ = readq(vaddr_iomem_) +#define __iosys_map_wr_io_u64_case(val_, vaddr_iomem_) \ + u64: writeq(val_, vaddr_iomem_) +#else +#define __iosys_map_rd_io_u64_case(val_, vaddr_iomem_) \ + u64: memcpy_fromio(&(val_), vaddr_iomem_, sizeof(u64)) +#define __iosys_map_wr_io_u64_case(val_, vaddr_iomem_) \ + u64: memcpy_toio(vaddr_iomem_, &(val_), sizeof(u64)) +#endif + +#define __iosys_map_rd_io(val__, vaddr_iomem__, type__) _Generic(val__, \ + u8: val__ = readb(vaddr_iomem__), \ + u16: val__ = readw(vaddr_iomem__), \ + u32: val__ = readl(vaddr_iomem__), \ + __iosys_map_rd_io_u64_case(val__, vaddr_iomem__)) + +#define __iosys_map_rd_sys(val__, vaddr__, type__) \ + val__ = READ_ONCE(*(type__ *)(vaddr__)) + +#define __iosys_map_wr_io(val__, vaddr_iomem__, type__) _Generic(val__, \ + u8: writeb(val__, vaddr_iomem__), \ + u16: writew(val__, vaddr_iomem__), \ + u32: writel(val__, vaddr_iomem__), \ + __iosys_map_wr_io_u64_case(val__, vaddr_iomem__)) + +#define __iosys_map_wr_sys(val__, vaddr__, type__) \ + WRITE_ONCE(*(type__ *)(vaddr__), val__) + +/** + * iosys_map_rd - Read a C-type value from the iosys_map + * + * @map__: The iosys_map structure + * @offset__: The offset from which to read + * @type__: Type of the value being read + * + * Read a C type value (u8, u16, u32 and u64) from iosys_map. For other types or + * if pointer may be unaligned (and problematic for the architecture supported), + * use iosys_map_memcpy_from(). + * + * Returns: + * The value read from the mapping. + */ +#define iosys_map_rd(map__, offset__, type__) ({ \ + type__ val; \ + if ((map__)->is_iomem) { \ + __iosys_map_rd_io(val, (map__)->vaddr_iomem + (offset__), type__);\ + } else { \ + __iosys_map_rd_sys(val, (map__)->vaddr + (offset__), type__); \ + } \ + val; \ +}) + +/** + * iosys_map_wr - Write a C-type value to the iosys_map + * + * @map__: The iosys_map structure + * @offset__: The offset from the mapping to write to + * @type__: Type of the value being written + * @val__: Value to write + * + * Write a C type value (u8, u16, u32 and u64) to the iosys_map. For other types + * or if pointer may be unaligned (and problematic for the architecture + * supported), use iosys_map_memcpy_to() + */ +#define iosys_map_wr(map__, offset__, type__, val__) ({ \ + type__ val = (val__); \ + if ((map__)->is_iomem) { \ + __iosys_map_wr_io(val, (map__)->vaddr_iomem + (offset__), type__);\ + } else { \ + __iosys_map_wr_sys(val, (map__)->vaddr + (offset__), type__); \ + } \ +}) + +/** + * iosys_map_rd_field - Read a member from a struct in the iosys_map + * + * @map__: The iosys_map structure + * @struct_offset__: Offset from the beggining of the map, where the struct + * is located + * @struct_type__: The struct describing the layout of the mapping + * @field__: Member of the struct to read + * + * Read a value from iosys_map considering its layout is described by a C struct + * starting at @struct_offset__. The field offset and size is calculated and its + * value read. If the field access would incur in un-aligned access, then either + * iosys_map_memcpy_from() needs to be used or the architecture must support it. + * For example: suppose there is a @struct foo defined as below and the value + * ``foo.field2.inner2`` needs to be read from the iosys_map: + * + * .. code-block:: c + * + * struct foo { + * int field1; + * struct { + * int inner1; + * int inner2; + * } field2; + * int field3; + * } __packed; + * + * This is the expected memory layout of a buffer using iosys_map_rd_field(): + * + * +------------------------------+--------------------------+ + * | Address | Content | + * +==============================+==========================+ + * | buffer + 0000 | start of mmapped buffer | + * | | pointed by iosys_map | + * +------------------------------+--------------------------+ + * | ... | ... | + * +------------------------------+--------------------------+ + * | buffer + ``struct_offset__`` | start of ``struct foo`` | + * +------------------------------+--------------------------+ + * | ... | ... | + * +------------------------------+--------------------------+ + * | buffer + wwww | ``foo.field2.inner2`` | + * +------------------------------+--------------------------+ + * | ... | ... | + * +------------------------------+--------------------------+ + * | buffer + yyyy | end of ``struct foo`` | + * +------------------------------+--------------------------+ + * | ... | ... | + * +------------------------------+--------------------------+ + * | buffer + zzzz | end of mmaped buffer | + * +------------------------------+--------------------------+ + * + * Values automatically calculated by this macro or not needed are denoted by + * wwww, yyyy and zzzz. This is the code to read that value: + * + * .. code-block:: c + * + * x = iosys_map_rd_field(&map, offset, struct foo, field2.inner2); + * + * Returns: + * The value read from the mapping. + */ +#define iosys_map_rd_field(map__, struct_offset__, struct_type__, field__) ({ \ + struct_type__ *s; \ + iosys_map_rd(map__, struct_offset__ + offsetof(struct_type__, field__), \ + typeof(s->field__)); \ +}) + +/** + * iosys_map_wr_field - Write to a member of a struct in the iosys_map + * + * @map__: The iosys_map structure + * @struct_offset__: Offset from the beggining of the map, where the struct + * is located + * @struct_type__: The struct describing the layout of the mapping + * @field__: Member of the struct to read + * @val__: Value to write + * + * Write a value to the iosys_map considering its layout is described by a C + * struct starting at @struct_offset__. The field offset and size is calculated + * and the @val__ is written. If the field access would incur in un-aligned + * access, then either iosys_map_memcpy_to() needs to be used or the + * architecture must support it. Refer to iosys_map_rd_field() for expected + * usage and memory layout. + */ +#define iosys_map_wr_field(map__, struct_offset__, struct_type__, field__, val__) ({ \ + struct_type__ *s; \ + iosys_map_wr(map__, struct_offset__ + offsetof(struct_type__, field__), \ + typeof(s->field__), val__); \ +}) + +#endif /* __IOSYS_MAP_H__ */ diff --git a/include/linux/iova.h b/include/linux/iova.h index 71d8a2de6635..83c00fac2acb 100644 --- a/include/linux/iova.h +++ b/include/linux/iova.h @@ -12,7 +12,6 @@ #include <linux/types.h> #include <linux/kernel.h> #include <linux/rbtree.h> -#include <linux/atomic.h> #include <linux/dma-mapping.h> /* iova structure */ @@ -22,47 +21,8 @@ struct iova { unsigned long pfn_lo; /* Lowest allocated pfn */ }; -struct iova_magazine; -struct iova_cpu_rcache; -#define IOVA_RANGE_CACHE_MAX_SIZE 6 /* log of max cached IOVA range size (in pages) */ -#define MAX_GLOBAL_MAGS 32 /* magazines per bin */ - -struct iova_rcache { - spinlock_t lock; - unsigned long depot_size; - struct iova_magazine *depot[MAX_GLOBAL_MAGS]; - struct iova_cpu_rcache __percpu *cpu_rcaches; -}; - -struct iova_domain; - -/* Call-Back from IOVA code into IOMMU drivers */ -typedef void (* iova_flush_cb)(struct iova_domain *domain); - -/* Destructor for per-entry data */ -typedef void (* iova_entry_dtor)(unsigned long data); - -/* Number of entries per Flush Queue */ -#define IOVA_FQ_SIZE 256 - -/* Timeout (in ms) after which entries are flushed from the Flush-Queue */ -#define IOVA_FQ_TIMEOUT 10 - -/* Flush Queue entry for defered flushing */ -struct iova_fq_entry { - unsigned long iova_pfn; - unsigned long pages; - unsigned long data; - u64 counter; /* Flush counter when this entrie was added */ -}; - -/* Per-CPU Flush Queue structure */ -struct iova_fq { - struct iova_fq_entry entries[IOVA_FQ_SIZE]; - unsigned head, tail; - spinlock_t lock; -}; +struct iova_rcache; /* holds all the iova translations for a domain */ struct iova_domain { @@ -74,27 +34,9 @@ struct iova_domain { unsigned long start_pfn; /* Lower limit for this domain */ unsigned long dma_32bit_pfn; unsigned long max32_alloc_size; /* Size of last failed allocation */ - struct iova_fq __percpu *fq; /* Flush Queue */ - - atomic64_t fq_flush_start_cnt; /* Number of TLB flushes that - have been started */ - - atomic64_t fq_flush_finish_cnt; /* Number of TLB flushes that - have been finished */ - struct iova anchor; /* rbtree lookup anchor */ - struct iova_rcache rcaches[IOVA_RANGE_CACHE_MAX_SIZE]; /* IOVA range caches */ - - iova_flush_cb flush_cb; /* Call-Back function to flush IOMMU - TLBs */ - iova_entry_dtor entry_dtor; /* IOMMU driver specific destructor for - iova entry */ - - struct timer_list fq_timer; /* Timer to regularily empty the - flush-queues */ - atomic_t fq_timer_on; /* 1 when timer is active, 0 - when not */ + struct iova_rcache *rcaches; struct hlist_node cpuhp_dead; }; @@ -133,10 +75,12 @@ static inline unsigned long iova_pfn(struct iova_domain *iovad, dma_addr_t iova) return iova >> iova_shift(iovad); } -#if IS_ENABLED(CONFIG_IOMMU_IOVA) +#if IS_REACHABLE(CONFIG_IOMMU_IOVA) int iova_cache_get(void); void iova_cache_put(void); +unsigned long iova_rcache_range(void); + void free_iova(struct iova_domain *iovad, unsigned long pfn); void __free_iova(struct iova_domain *iovad, struct iova *iova); struct iova *alloc_iova(struct iova_domain *iovad, unsigned long size, @@ -144,17 +88,13 @@ struct iova *alloc_iova(struct iova_domain *iovad, unsigned long size, bool size_aligned); void free_iova_fast(struct iova_domain *iovad, unsigned long pfn, unsigned long size); -void queue_iova(struct iova_domain *iovad, - unsigned long pfn, unsigned long pages, - unsigned long data); unsigned long alloc_iova_fast(struct iova_domain *iovad, unsigned long size, unsigned long limit_pfn, bool flush_rcache); struct iova *reserve_iova(struct iova_domain *iovad, unsigned long pfn_lo, unsigned long pfn_hi); void init_iova_domain(struct iova_domain *iovad, unsigned long granule, unsigned long start_pfn); -int init_iova_flush_queue(struct iova_domain *iovad, - iova_flush_cb flush_cb, iova_entry_dtor entry_dtor); +int iova_domain_init_rcaches(struct iova_domain *iovad); struct iova *find_iova(struct iova_domain *iovad, unsigned long pfn); void put_iova_domain(struct iova_domain *iovad); #else @@ -189,12 +129,6 @@ static inline void free_iova_fast(struct iova_domain *iovad, { } -static inline void queue_iova(struct iova_domain *iovad, - unsigned long pfn, unsigned long pages, - unsigned long data) -{ -} - static inline unsigned long alloc_iova_fast(struct iova_domain *iovad, unsigned long size, unsigned long limit_pfn, @@ -216,13 +150,6 @@ static inline void init_iova_domain(struct iova_domain *iovad, { } -static inline int init_iova_flush_queue(struct iova_domain *iovad, - iova_flush_cb flush_cb, - iova_entry_dtor entry_dtor) -{ - return -ENODEV; -} - static inline struct iova *find_iova(struct iova_domain *iovad, unsigned long pfn) { diff --git a/include/linux/iova_bitmap.h b/include/linux/iova_bitmap.h new file mode 100644 index 000000000000..c006cf0a25f3 --- /dev/null +++ b/include/linux/iova_bitmap.h @@ -0,0 +1,26 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2022, Oracle and/or its affiliates. + * Copyright (c) 2022, NVIDIA CORPORATION & AFFILIATES. All rights reserved + */ +#ifndef _IOVA_BITMAP_H_ +#define _IOVA_BITMAP_H_ + +#include <linux/types.h> + +struct iova_bitmap; + +typedef int (*iova_bitmap_fn_t)(struct iova_bitmap *bitmap, + unsigned long iova, size_t length, + void *opaque); + +struct iova_bitmap *iova_bitmap_alloc(unsigned long iova, size_t length, + unsigned long page_size, + u64 __user *data); +void iova_bitmap_free(struct iova_bitmap *bitmap); +int iova_bitmap_for_each(struct iova_bitmap *bitmap, void *opaque, + iova_bitmap_fn_t fn); +void iova_bitmap_set(struct iova_bitmap *bitmap, + unsigned long iova, size_t length); + +#endif diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h index b75395ec8d52..e8240cf2611a 100644 --- a/include/linux/ipc_namespace.h +++ b/include/linux/ipc_namespace.h @@ -10,6 +10,8 @@ #include <linux/ns_common.h> #include <linux/refcount.h> #include <linux/rhashtable-types.h> +#include <linux/sysctl.h> +#include <linux/percpu_counter.h> struct user_namespace; @@ -35,8 +37,8 @@ struct ipc_namespace { unsigned int msg_ctlmax; unsigned int msg_ctlmnb; unsigned int msg_ctlmni; - atomic_t msg_bytes; - atomic_t msg_hdrs; + struct percpu_counter percpu_msg_bytes; + struct percpu_counter percpu_msg_hdrs; size_t shm_ctlmax; size_t shm_ctlall; @@ -63,6 +65,12 @@ struct ipc_namespace { unsigned int mq_msg_default; unsigned int mq_msgsize_default; + struct ctl_table_set mq_set; + struct ctl_table_header *mq_sysctls; + + struct ctl_table_set ipc_set; + struct ctl_table_header *ipc_sysctls; + /* user_ns which owns the ipc ns */ struct user_namespace *user_ns; struct ucounts *ucounts; @@ -169,15 +177,37 @@ static inline void put_ipc_ns(struct ipc_namespace *ns) #ifdef CONFIG_POSIX_MQUEUE_SYSCTL -struct ctl_table_header; -extern struct ctl_table_header *mq_register_sysctl_table(void); +void retire_mq_sysctls(struct ipc_namespace *ns); +bool setup_mq_sysctls(struct ipc_namespace *ns); #else /* CONFIG_POSIX_MQUEUE_SYSCTL */ -static inline struct ctl_table_header *mq_register_sysctl_table(void) +static inline void retire_mq_sysctls(struct ipc_namespace *ns) { - return NULL; +} + +static inline bool setup_mq_sysctls(struct ipc_namespace *ns) +{ + return true; } #endif /* CONFIG_POSIX_MQUEUE_SYSCTL */ + +#ifdef CONFIG_SYSVIPC_SYSCTL + +bool setup_ipc_sysctls(struct ipc_namespace *ns); +void retire_ipc_sysctls(struct ipc_namespace *ns); + +#else /* CONFIG_SYSVIPC_SYSCTL */ + +static inline void retire_ipc_sysctls(struct ipc_namespace *ns) +{ +} + +static inline bool setup_ipc_sysctls(struct ipc_namespace *ns) +{ + return true; +} + +#endif /* CONFIG_SYSVIPC_SYSCTL */ #endif diff --git a/include/linux/ipmi.h b/include/linux/ipmi.h index 163831a087ef..a1c9c0d48ebf 100644 --- a/include/linux/ipmi.h +++ b/include/linux/ipmi.h @@ -72,6 +72,11 @@ struct ipmi_recv_msg { unsigned char msg_data[IPMI_MAX_MSG_LENGTH]; }; +#define INIT_IPMI_RECV_MSG(done_handler) \ +{ \ + .done = done_handler \ +} + /* Allocate and free the receive message. */ void ipmi_free_recv_msg(struct ipmi_recv_msg *msg); diff --git a/include/linux/ipmi_smi.h b/include/linux/ipmi_smi.h index 9277d21c2690..5d69820d8b02 100644 --- a/include/linux/ipmi_smi.h +++ b/include/linux/ipmi_smi.h @@ -125,6 +125,12 @@ struct ipmi_smi_msg { void (*done)(struct ipmi_smi_msg *msg); }; +#define INIT_IPMI_SMI_MSG(done_handler) \ +{ \ + .done = done_handler, \ + .type = IPMI_SMI_MSG_TYPE_NORMAL \ +} + struct ipmi_smi_handlers { struct module *owner; diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index a59d25f19385..37dfdcfcdd54 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -51,7 +51,7 @@ struct ipv6_devconf { __s32 use_optimistic; #endif #ifdef CONFIG_IPV6_MROUTE - __s32 mc_forwarding; + atomic_t mc_forwarding; #endif __s32 disable_ipv6; __s32 drop_unicast_in_l2_multicast; @@ -61,6 +61,7 @@ struct ipv6_devconf { __s32 suppress_frag_ndisc; __s32 accept_ra_mtu; __s32 drop_unsolicited_na; + __s32 accept_untracked_na; struct ipv6_stable_secret { bool initialized; struct in6_addr secret; @@ -144,6 +145,7 @@ struct inet6_skb_parm { #define IP6SKB_L3SLAVE 64 #define IP6SKB_JUMBOGRAM 128 #define IP6SKB_SEG6 256 +#define IP6SKB_FAKEJUMBO 512 }; #if defined(CONFIG_NET_L3_MASTER_DEV) @@ -339,8 +341,7 @@ static inline struct raw6_sock *raw6_sk(const struct sock *sk) return (struct raw6_sock *)sk; } -#define __ipv6_only_sock(sk) (sk->sk_ipv6only) -#define ipv6_only_sock(sk) (__ipv6_only_sock(sk)) +#define ipv6_only_sock(sk) (sk->sk_ipv6only) #define ipv6_sk_rxinfo(sk) ((sk)->sk_family == PF_INET6 && \ inet6_sk(sk)->rxopt.bits.rxinfo) @@ -357,7 +358,6 @@ static inline int inet_v6_ipv6only(const struct sock *sk) return ipv6_only_sock(sk); } #else -#define __ipv6_only_sock(sk) 0 #define ipv6_only_sock(sk) 0 #define ipv6_sk_rxinfo(sk) 0 @@ -371,19 +371,12 @@ static inline struct ipv6_pinfo * inet6_sk(const struct sock *__sk) return NULL; } -static inline struct inet6_request_sock * - inet6_rsk(const struct request_sock *rsk) -{ - return NULL; -} - static inline struct raw6_sock *raw6_sk(const struct sock *sk) { return NULL; } #define inet6_rcv_saddr(__sk) NULL -#define tcp_twsk_ipv6only(__sk) 0 #define inet_v6_ipv6only(__sk) 0 #endif /* IS_ENABLED(CONFIG_IPV6) */ #endif /* _IPV6_H */ diff --git a/include/linux/irq.h b/include/linux/irq.h index 848e1e12c5c6..c3eb89606c2b 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -151,7 +151,9 @@ struct irq_common_data { #endif void *handler_data; struct msi_desc *msi_desc; +#ifdef CONFIG_SMP cpumask_var_t affinity; +#endif #ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK cpumask_var_t effective_affinity; #endif @@ -456,7 +458,6 @@ static inline irq_hw_number_t irqd_to_hwirq(struct irq_data *d) /** * struct irq_chip - hardware interrupt chip descriptor * - * @parent_device: pointer to parent device for irqchip * @name: name for /proc/interrupts * @irq_startup: start up the interrupt (defaults to ->enable if NULL) * @irq_shutdown: shut down the interrupt (defaults to ->disable if NULL) @@ -503,7 +504,6 @@ static inline irq_hw_number_t irqd_to_hwirq(struct irq_data *d) * @flags: chip specific flags */ struct irq_chip { - struct device *parent_device; const char *name; unsigned int (*irq_startup)(struct irq_data *data); void (*irq_shutdown)(struct irq_data *data); @@ -571,6 +571,7 @@ struct irq_chip { * IRQCHIP_ENABLE_WAKEUP_ON_SUSPEND: Invokes __enable_irq()/__disable_irq() for wake irqs * in the suspend path if they are in disabled state * IRQCHIP_AFFINITY_PRE_STARTUP: Default affinity update before startup + * IRQCHIP_IMMUTABLE: Don't ever change anything in this chip */ enum { IRQCHIP_SET_TYPE_MASKED = (1 << 0), @@ -584,6 +585,7 @@ enum { IRQCHIP_SUPPORTS_NMI = (1 << 8), IRQCHIP_ENABLE_WAKEUP_ON_SUSPEND = (1 << 9), IRQCHIP_AFFINITY_PRE_STARTUP = (1 << 10), + IRQCHIP_IMMUTABLE = (1 << 11), }; #include <linux/irqdesc.h> @@ -712,10 +714,11 @@ extern struct irq_chip no_irq_chip; extern struct irq_chip dummy_irq_chip; extern void -irq_set_chip_and_handler_name(unsigned int irq, struct irq_chip *chip, +irq_set_chip_and_handler_name(unsigned int irq, const struct irq_chip *chip, irq_flow_handler_t handle, const char *name); -static inline void irq_set_chip_and_handler(unsigned int irq, struct irq_chip *chip, +static inline void irq_set_chip_and_handler(unsigned int irq, + const struct irq_chip *chip, irq_flow_handler_t handle) { irq_set_chip_and_handler_name(irq, chip, handle, NULL); @@ -805,7 +808,7 @@ static inline void irq_set_percpu_devid_flags(unsigned int irq) } /* Set/get chip/data for an IRQ: */ -extern int irq_set_chip(unsigned int irq, struct irq_chip *chip); +extern int irq_set_chip(unsigned int irq, const struct irq_chip *chip); extern int irq_set_handler_data(unsigned int irq, void *data); extern int irq_set_chip_data(unsigned int irq, void *data); extern int irq_set_irq_type(unsigned int irq, unsigned int type); @@ -878,21 +881,34 @@ static inline int irq_data_get_node(struct irq_data *d) return irq_common_data_get_node(d->common); } -static inline struct cpumask *irq_get_affinity_mask(int irq) +static inline +const struct cpumask *irq_data_get_affinity_mask(struct irq_data *d) { - struct irq_data *d = irq_get_irq_data(irq); +#ifdef CONFIG_SMP + return d->common->affinity; +#else + return cpumask_of(0); +#endif +} - return d ? d->common->affinity : NULL; +static inline void irq_data_update_affinity(struct irq_data *d, + const struct cpumask *m) +{ +#ifdef CONFIG_SMP + cpumask_copy(d->common->affinity, m); +#endif } -static inline struct cpumask *irq_data_get_affinity_mask(struct irq_data *d) +static inline const struct cpumask *irq_get_affinity_mask(int irq) { - return d->common->affinity; + struct irq_data *d = irq_get_irq_data(irq); + + return d ? irq_data_get_affinity_mask(d) : NULL; } #ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK static inline -struct cpumask *irq_data_get_effective_affinity_mask(struct irq_data *d) +const struct cpumask *irq_data_get_effective_affinity_mask(struct irq_data *d) { return d->common->effective_affinity; } @@ -907,13 +923,14 @@ static inline void irq_data_update_effective_affinity(struct irq_data *d, { } static inline -struct cpumask *irq_data_get_effective_affinity_mask(struct irq_data *d) +const struct cpumask *irq_data_get_effective_affinity_mask(struct irq_data *d) { - return d->common->affinity; + return irq_data_get_affinity_mask(d); } #endif -static inline struct cpumask *irq_get_effective_affinity_mask(unsigned int irq) +static inline +const struct cpumask *irq_get_effective_affinity_mask(unsigned int irq) { struct irq_data *d = irq_get_irq_data(irq); @@ -1120,6 +1137,7 @@ int irq_gc_set_wake(struct irq_data *d, unsigned int on); /* Setup functions for irq_chip_generic */ int irq_map_generic_chip(struct irq_domain *d, unsigned int virq, irq_hw_number_t hw_irq); +void irq_unmap_generic_chip(struct irq_domain *d, unsigned int virq); struct irq_chip_generic * irq_alloc_generic_chip(const char *name, int nr_ct, unsigned int irq_base, void __iomem *reg_base, irq_flow_handler_t handler); diff --git a/include/linux/irqchip.h b/include/linux/irqchip.h index 3a091d0710ae..d5e6024cb2a8 100644 --- a/include/linux/irqchip.h +++ b/include/linux/irqchip.h @@ -44,7 +44,8 @@ static const struct of_device_id drv_name##_irqchip_match_table[] = { #define IRQCHIP_MATCH(compat, fn) { .compatible = compat, \ .data = typecheck_irq_init_cb(fn), }, -#define IRQCHIP_PLATFORM_DRIVER_END(drv_name) \ + +#define IRQCHIP_PLATFORM_DRIVER_END(drv_name, ...) \ {}, \ }; \ MODULE_DEVICE_TABLE(of, drv_name##_irqchip_match_table); \ @@ -56,6 +57,7 @@ static struct platform_driver drv_name##_driver = { \ .owner = THIS_MODULE, \ .of_match_table = drv_name##_irqchip_match_table, \ .suppress_bind_attrs = true, \ + __VA_ARGS__ \ }, \ }; \ builtin_platform_driver(drv_name##_driver) diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index 81cbf85f73de..728691365464 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -127,6 +127,8 @@ #define GICR_PIDR2 GICD_PIDR2 #define GICR_CTLR_ENABLE_LPIS (1UL << 0) +#define GICR_CTLR_CES (1UL << 1) +#define GICR_CTLR_IR (1UL << 2) #define GICR_CTLR_RWP (1UL << 3) #define GICR_TYPER_CPU_NUMBER(r) (((r) >> 8) & 0xffff) @@ -615,7 +617,7 @@ struct rdists { void __iomem *rd_base; struct page *pend_page; phys_addr_t phys_base; - bool lpi_enabled; + u64 flags; cpumask_t *vpe_table_mask; void *vpe_l1_base; } __percpu *rdist; @@ -624,6 +626,7 @@ struct rdists { u64 flags; u32 gicd_typer; u32 gicd_typer2; + int cpuhp_memreserve_state; bool has_vlpis; bool has_rvpeid; bool has_direct_lpi; @@ -632,6 +635,7 @@ struct rdists { struct irq_domain; struct fwnode_handle; +int __init its_lpi_memreserve_init(void); int its_cpu_init(void); int its_init(struct fwnode_handle *handle, struct rdists *rdists, struct irq_domain *domain); diff --git a/include/linux/irqchip/irq-ixp4xx.h b/include/linux/irqchip/irq-ixp4xx.h deleted file mode 100644 index 9395917d6936..000000000000 --- a/include/linux/irqchip/irq-ixp4xx.h +++ /dev/null @@ -1,12 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __IRQ_IXP4XX_H -#define __IRQ_IXP4XX_H - -#include <linux/ioport.h> -struct irq_domain; - -void ixp4xx_irq_init(resource_size_t irqbase, - bool is_356); -struct irq_domain *ixp4xx_get_irq_domain(void); - -#endif /* __IRQ_IXP4XX_H */ diff --git a/include/linux/irqchip/mmp.h b/include/linux/irqchip/mmp.h index cb8455c87c8a..aa1813749a4f 100644 --- a/include/linux/irqchip/mmp.h +++ b/include/linux/irqchip/mmp.h @@ -4,4 +4,7 @@ extern struct irq_chip icu_irq_chip; +extern void icu_init_irq(void); +extern void mmp2_init_icu(void); + #endif /* __IRQCHIP_MMP_H */ diff --git a/include/linux/irqchip/versatile-fpga.h b/include/linux/irqchip/versatile-fpga.h deleted file mode 100644 index a978fc8c7996..000000000000 --- a/include/linux/irqchip/versatile-fpga.h +++ /dev/null @@ -1,14 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef PLAT_FPGA_IRQ_H -#define PLAT_FPGA_IRQ_H - -struct device_node; -struct pt_regs; - -void fpga_handle_irq(struct pt_regs *regs); -void fpga_irq_init(void __iomem *, const char *, int, int, u32, - struct device_node *node); -int fpga_irq_of_init(struct device_node *node, - struct device_node *parent); - -#endif diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h index 93d270ca0c56..844a8e30e6de 100644 --- a/include/linux/irqdesc.h +++ b/include/linux/irqdesc.h @@ -160,6 +160,7 @@ static inline void generic_handle_irq_desc(struct irq_desc *desc) int handle_irq_desc(struct irq_desc *desc); int generic_handle_irq(unsigned int irq); +int generic_handle_irq_safe(unsigned int irq); #ifdef CONFIG_IRQ_DOMAIN /* @@ -168,6 +169,7 @@ int generic_handle_irq(unsigned int irq); * conversion failed. */ int generic_handle_domain_irq(struct irq_domain *domain, unsigned int hwirq); +int generic_handle_domain_irq_safe(struct irq_domain *domain, unsigned int hwirq); int generic_handle_domain_nmi(struct irq_domain *domain, unsigned int hwirq); #endif @@ -208,14 +210,15 @@ static inline void irq_set_handler_locked(struct irq_data *data, * Must be called with irq_desc locked and valid parameters. */ static inline void -irq_set_chip_handler_name_locked(struct irq_data *data, struct irq_chip *chip, +irq_set_chip_handler_name_locked(struct irq_data *data, + const struct irq_chip *chip, irq_flow_handler_t handler, const char *name) { struct irq_desc *desc = irq_data_to_desc(data); desc->handle_irq = handler; desc->name = name; - data->chip = chip; + data->chip = (struct irq_chip *)chip; } bool irq_check_status_bit(unsigned int irq, unsigned int bitmask); diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index 553da4899f55..00d577f90883 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -131,7 +131,7 @@ struct irq_domain_ops { #endif }; -extern struct irq_domain_ops irq_generic_chip_ops; +extern const struct irq_domain_ops irq_generic_chip_ops; struct irq_domain_chip_generic; @@ -151,6 +151,8 @@ struct irq_domain_chip_generic; * @gc: Pointer to a list of generic chips. There is a helper function for * setting up one or more generic chips for interrupt controllers * drivers using the generic chip library which uses this pointer. + * @dev: Pointer to a device that the domain represent, and that will be + * used for power management purposes. * @parent: Pointer to parent irq_domain to support hierarchy irq_domains * * Revmap data, used internally by irq_domain @@ -171,6 +173,7 @@ struct irq_domain { struct fwnode_handle *fwnode; enum irq_domain_bus_token bus_token; struct irq_domain_chip_generic *gc; + struct device *dev; #ifdef CONFIG_IRQ_DOMAIN_HIERARCHY struct irq_domain *parent; #endif @@ -226,6 +229,13 @@ static inline struct device_node *irq_domain_get_of_node(struct irq_domain *d) return to_of_node(d->fwnode); } +static inline void irq_domain_set_pm_device(struct irq_domain *d, + struct device *dev) +{ + if (d) + d->dev = dev; +} + #ifdef CONFIG_IRQ_DOMAIN struct fwnode_handle *__irq_domain_alloc_fwnode(unsigned int type, int id, const char *name, phys_addr_t *pa); @@ -469,7 +479,8 @@ int irq_destroy_ipi(unsigned int irq, const struct cpumask *dest); extern struct irq_data *irq_domain_get_irq_data(struct irq_domain *domain, unsigned int virq); extern void irq_domain_set_info(struct irq_domain *domain, unsigned int virq, - irq_hw_number_t hwirq, struct irq_chip *chip, + irq_hw_number_t hwirq, + const struct irq_chip *chip, void *chip_data, irq_flow_handler_t handler, void *handler_data, const char *handler_name); extern void irq_domain_reset_irq_data(struct irq_data *irq_data); @@ -512,7 +523,7 @@ extern int irq_domain_alloc_irqs_hierarchy(struct irq_domain *domain, extern int irq_domain_set_hwirq_and_chip(struct irq_domain *domain, unsigned int virq, irq_hw_number_t hwirq, - struct irq_chip *chip, + const struct irq_chip *chip, void *chip_data); extern void irq_domain_free_irqs_common(struct irq_domain *domain, unsigned int virq, diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h index 600c10da321a..5ec0fa71399e 100644 --- a/include/linux/irqflags.h +++ b/include/linux/irqflags.h @@ -20,13 +20,13 @@ #ifdef CONFIG_PROVE_LOCKING extern void lockdep_softirqs_on(unsigned long ip); extern void lockdep_softirqs_off(unsigned long ip); - extern void lockdep_hardirqs_on_prepare(unsigned long ip); + extern void lockdep_hardirqs_on_prepare(void); extern void lockdep_hardirqs_on(unsigned long ip); extern void lockdep_hardirqs_off(unsigned long ip); #else static inline void lockdep_softirqs_on(unsigned long ip) { } static inline void lockdep_softirqs_off(unsigned long ip) { } - static inline void lockdep_hardirqs_on_prepare(unsigned long ip) { } + static inline void lockdep_hardirqs_on_prepare(void) { } static inline void lockdep_hardirqs_on(unsigned long ip) { } static inline void lockdep_hardirqs_off(unsigned long ip) { } #endif @@ -71,14 +71,6 @@ do { \ do { \ __this_cpu_dec(hardirq_context); \ } while (0) -# define lockdep_softirq_enter() \ -do { \ - current->softirq_context++; \ -} while (0) -# define lockdep_softirq_exit() \ -do { \ - current->softirq_context--; \ -} while (0) # define lockdep_hrtimer_enter(__hrtimer) \ ({ \ @@ -140,6 +132,21 @@ do { \ # define lockdep_irq_work_exit(__work) do { } while (0) #endif +#if defined(CONFIG_TRACE_IRQFLAGS) && !defined(CONFIG_PREEMPT_RT) +# define lockdep_softirq_enter() \ +do { \ + current->softirq_context++; \ +} while (0) +# define lockdep_softirq_exit() \ +do { \ + current->softirq_context--; \ +} while (0) + +#else +# define lockdep_softirq_enter() do { } while (0) +# define lockdep_softirq_exit() do { } while (0) +#endif + #if defined(CONFIG_IRQSOFF_TRACER) || \ defined(CONFIG_PREEMPT_TRACER) extern void stop_critical_timings(void); diff --git a/include/linux/isa-dma.h b/include/linux/isa-dma.h new file mode 100644 index 000000000000..61504a8c1b9e --- /dev/null +++ b/include/linux/isa-dma.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __LINUX_ISA_DMA_H +#define __LINUX_ISA_DMA_H + +#include <asm/dma.h> + +#if defined(CONFIG_PCI) && defined(CONFIG_X86_32) +extern int isa_dma_bridge_buggy; +#else +#define isa_dma_bridge_buggy (0) +#endif + +#endif /* __LINUX_ISA_DMA_H */ diff --git a/include/linux/isa.h b/include/linux/isa.h index e30963190968..4fbbf5e36e08 100644 --- a/include/linux/isa.h +++ b/include/linux/isa.h @@ -38,6 +38,32 @@ static inline void isa_unregister_driver(struct isa_driver *d) } #endif +#define module_isa_driver_init(__isa_driver, __num_isa_dev) \ +static int __init __isa_driver##_init(void) \ +{ \ + return isa_register_driver(&(__isa_driver), __num_isa_dev); \ +} \ +module_init(__isa_driver##_init) + +#define module_isa_driver_with_irq_init(__isa_driver, __num_isa_dev, __num_irq) \ +static int __init __isa_driver##_init(void) \ +{ \ + if (__num_irq != __num_isa_dev) { \ + pr_err("%s: Number of irq (%u) does not match number of base (%u)\n", \ + __isa_driver.driver.name, __num_irq, __num_isa_dev); \ + return -EINVAL; \ + } \ + return isa_register_driver(&(__isa_driver), __num_isa_dev); \ +} \ +module_init(__isa_driver##_init) + +#define module_isa_driver_exit(__isa_driver) \ +static void __exit __isa_driver##_exit(void) \ +{ \ + isa_unregister_driver(&(__isa_driver)); \ +} \ +module_exit(__isa_driver##_exit) + /** * module_isa_driver() - Helper macro for registering a ISA driver * @__isa_driver: isa_driver struct @@ -48,16 +74,22 @@ static inline void isa_unregister_driver(struct isa_driver *d) * use this macro once, and calling it replaces module_init and module_exit. */ #define module_isa_driver(__isa_driver, __num_isa_dev) \ -static int __init __isa_driver##_init(void) \ -{ \ - return isa_register_driver(&(__isa_driver), __num_isa_dev); \ -} \ -module_init(__isa_driver##_init); \ -static void __exit __isa_driver##_exit(void) \ -{ \ - isa_unregister_driver(&(__isa_driver)); \ -} \ -module_exit(__isa_driver##_exit); +module_isa_driver_init(__isa_driver, __num_isa_dev); \ +module_isa_driver_exit(__isa_driver) + +/** + * module_isa_driver_with_irq() - Helper macro for registering an ISA driver with irq + * @__isa_driver: isa_driver struct + * @__num_isa_dev: number of devices to register + * @__num_irq: number of IRQ to register + * + * Helper macro for ISA drivers with irq that do not do anything special in + * module init/exit. Each module may only use this macro once, and calling it + * replaces module_init and module_exit. + */ +#define module_isa_driver_with_irq(__isa_driver, __num_isa_dev, __num_irq) \ +module_isa_driver_with_irq_init(__isa_driver, __num_isa_dev, __num_irq); \ +module_isa_driver_exit(__isa_driver) /** * max_num_isa_dev() - Maximum possible number registered of an ISA device diff --git a/include/linux/iversion.h b/include/linux/iversion.h index 3bfebde5a1a6..e27bd4f55d84 100644 --- a/include/linux/iversion.h +++ b/include/linux/iversion.h @@ -123,17 +123,12 @@ inode_peek_iversion_raw(const struct inode *inode) static inline void inode_set_max_iversion_raw(struct inode *inode, u64 val) { - u64 cur, old; + u64 cur = inode_peek_iversion_raw(inode); - cur = inode_peek_iversion_raw(inode); - for (;;) { + do { if (cur > val) break; - old = atomic64_cmpxchg(&inode->i_version, cur, val); - if (likely(old == cur)) - break; - cur = old; - } + } while (!atomic64_try_cmpxchg(&inode->i_version, &cur, val)); } /** @@ -177,56 +172,7 @@ inode_set_iversion_queried(struct inode *inode, u64 val) I_VERSION_QUERIED); } -/** - * inode_maybe_inc_iversion - increments i_version - * @inode: inode with the i_version that should be updated - * @force: increment the counter even if it's not necessary? - * - * Every time the inode is modified, the i_version field must be seen to have - * changed by any observer. - * - * If "force" is set or the QUERIED flag is set, then ensure that we increment - * the value, and clear the queried flag. - * - * In the common case where neither is set, then we can return "false" without - * updating i_version. - * - * If this function returns false, and no other metadata has changed, then we - * can avoid logging the metadata. - */ -static inline bool -inode_maybe_inc_iversion(struct inode *inode, bool force) -{ - u64 cur, old, new; - - /* - * The i_version field is not strictly ordered with any other inode - * information, but the legacy inode_inc_iversion code used a spinlock - * to serialize increments. - * - * Here, we add full memory barriers to ensure that any de-facto - * ordering with other info is preserved. - * - * This barrier pairs with the barrier in inode_query_iversion() - */ - smp_mb(); - cur = inode_peek_iversion_raw(inode); - for (;;) { - /* If flag is clear then we needn't do anything */ - if (!force && !(cur & I_VERSION_QUERIED)) - return false; - - /* Since lowest bit is flag, add 2 to avoid it */ - new = (cur & ~I_VERSION_QUERIED) + I_VERSION_INCREMENT; - - old = atomic64_cmpxchg(&inode->i_version, cur, new); - if (likely(old == cur)) - break; - cur = old; - } - return true; -} - +bool inode_maybe_inc_iversion(struct inode *inode, bool force); /** * inode_inc_iversion - forcibly increment i_version @@ -304,10 +250,10 @@ inode_peek_iversion(const struct inode *inode) static inline u64 inode_query_iversion(struct inode *inode) { - u64 cur, old, new; + u64 cur, new; cur = inode_peek_iversion_raw(inode); - for (;;) { + do { /* If flag is already set, then no need to swap */ if (cur & I_VERSION_QUERIED) { /* @@ -320,11 +266,7 @@ inode_query_iversion(struct inode *inode) } new = cur | I_VERSION_QUERIED; - old = atomic64_cmpxchg(&inode->i_version, cur, new); - if (likely(old == cur)) - break; - cur = old; - } + } while (!atomic64_try_cmpxchg(&inode->i_version, &cur, new)); return cur >> I_VERSION_QUERIED_SHIFT; } diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index fd933c45281a..0b7242370b56 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -54,14 +54,13 @@ * CONFIG_JBD2_DEBUG is on. */ #define JBD2_EXPENSIVE_CHECKING -extern ushort jbd2_journal_enable_debug; void __jbd2_debug(int level, const char *file, const char *func, unsigned int line, const char *fmt, ...); -#define jbd_debug(n, fmt, a...) \ +#define jbd2_debug(n, fmt, a...) \ __jbd2_debug((n), __FILE__, __func__, __LINE__, (fmt), ##a) #else -#define jbd_debug(n, fmt, a...) no_printk(fmt, ##a) +#define jbd2_debug(n, fmt, a...) no_printk(fmt, ##a) #endif extern void *jbd2_alloc(size_t size, gfp_t flags); @@ -554,9 +553,6 @@ struct transaction_chp_stats_s { * ->j_list_lock * * j_state_lock - * ->t_handle_lock - * - * j_state_lock * ->j_list_lock (journal_unmap_buffer) * */ @@ -594,7 +590,7 @@ struct transaction_s */ unsigned long t_log_start; - /* + /* * Number of buffers on the t_buffers list [j_list_lock, no locks * needed for jbd2 thread] */ @@ -1295,7 +1291,7 @@ struct journal_s * Clean-up after fast commit or full commit. JBD2 calls this function * after every commit operation. */ - void (*j_fc_cleanup_callback)(struct journal_s *journal, int); + void (*j_fc_cleanup_callback)(struct journal_s *journal, int full, tid_t tid); /** * @j_fc_replay_callback: @@ -1419,9 +1415,7 @@ extern void jbd2_journal_unfile_buffer(journal_t *, struct journal_head *); extern bool __jbd2_journal_refile_buffer(struct journal_head *); extern void jbd2_journal_refile_buffer(journal_t *, struct journal_head *); extern void __jbd2_journal_file_buffer(struct journal_head *, transaction_t *, int); -extern void __journal_free_buffer(struct journal_head *bh); extern void jbd2_journal_file_buffer(struct journal_head *, transaction_t *, int); -extern void __journal_clean_data_list(transaction_t *transaction); static inline void jbd2_file_log_bh(struct list_head *head, struct buffer_head *bh) { list_add_tail(&bh->b_assoc_buffers, head); @@ -1486,9 +1480,6 @@ extern int jbd2_journal_write_metadata_buffer(transaction_t *transaction, struct buffer_head **bh_out, sector_t blocknr); -/* Transaction locking */ -extern void __wait_on_journal (journal_t *); - /* Transaction cache support */ extern void jbd2_journal_destroy_transaction_cache(void); extern int __init jbd2_journal_init_transaction_cache(void); @@ -1535,14 +1526,16 @@ void jbd2_journal_set_triggers(struct buffer_head *, struct jbd2_buffer_trigger_type *type); extern int jbd2_journal_dirty_metadata (handle_t *, struct buffer_head *); extern int jbd2_journal_forget (handle_t *, struct buffer_head *); -extern int jbd2_journal_invalidatepage(journal_t *, - struct page *, unsigned int, unsigned int); -extern int jbd2_journal_try_to_free_buffers(journal_t *journal, struct page *page); +int jbd2_journal_invalidate_folio(journal_t *, struct folio *, + size_t offset, size_t length); +bool jbd2_journal_try_to_free_buffers(journal_t *journal, struct folio *folio); extern int jbd2_journal_stop(handle_t *); extern int jbd2_journal_flush(journal_t *journal, unsigned int flags); extern void jbd2_journal_lock_updates (journal_t *); extern void jbd2_journal_unlock_updates (journal_t *); +void jbd2_journal_wait_updates(journal_t *); + extern journal_t * jbd2_journal_init_dev(struct block_device *bdev, struct block_device *fs_dev, unsigned long long start, int len, int bsize); @@ -1563,7 +1556,7 @@ extern int jbd2_journal_wipe (journal_t *, int); extern int jbd2_journal_skip_recovery (journal_t *); extern void jbd2_journal_update_sb_errno(journal_t *); extern int jbd2_journal_update_sb_log_tail (journal_t *, tid_t, - unsigned long, int); + unsigned long, blk_opf_t); extern void jbd2_journal_abort (journal_t *, int); extern int jbd2_journal_errno (journal_t *); extern void jbd2_journal_ack_err (journal_t *); @@ -1653,7 +1646,6 @@ extern void jbd2_clear_buffer_revoked_flags(journal_t *journal); */ int jbd2_log_start_commit(journal_t *journal, tid_t tid); -int __jbd2_log_start_commit(journal_t *journal, tid_t tid); int jbd2_journal_start_commit(journal_t *journal, tid_t *tid); int jbd2_log_wait_commit(journal_t *journal, tid_t tid); int jbd2_transaction_committed(journal_t *journal, tid_t tid); @@ -1774,8 +1766,6 @@ static inline unsigned long jbd2_log_space_left(journal_t *journal) #define BJ_Reserved 4 /* Buffer is reserved for access by journal */ #define BJ_Types 5 -extern int jbd_blocks_per_page(struct inode *inode); - /* JBD uses a CRC32 checksum */ #define JBD_MAX_CHECKSUM_SIZE 4 diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h index 48b9b2a82767..570831ca9951 100644 --- a/include/linux/jump_label.h +++ b/include/linux/jump_label.h @@ -82,10 +82,9 @@ extern bool static_key_initialized; "%s(): static key '%pS' used before call to jump_label_init()", \ __func__, (key)) -#ifdef CONFIG_JUMP_LABEL - struct static_key { atomic_t enabled; +#ifdef CONFIG_JUMP_LABEL /* * Note: * To make anonymous unions work with old compilers, the static @@ -104,13 +103,9 @@ struct static_key { struct jump_entry *entries; struct static_key_mod *next; }; +#endif /* CONFIG_JUMP_LABEL */ }; -#else -struct static_key { - atomic_t enabled; -}; -#endif /* CONFIG_JUMP_LABEL */ #endif /* __ASSEMBLY__ */ #ifdef CONFIG_JUMP_LABEL @@ -225,8 +220,6 @@ extern void jump_label_lock(void); extern void jump_label_unlock(void); extern void arch_jump_label_transform(struct jump_entry *entry, enum jump_label_type type); -extern void arch_jump_label_transform_static(struct jump_entry *entry, - enum jump_label_type type); extern bool arch_jump_label_transform_queue(struct jump_entry *entry, enum jump_label_type type); extern void arch_jump_label_transform_apply(void); @@ -235,12 +228,12 @@ extern void static_key_slow_inc(struct static_key *key); extern void static_key_slow_dec(struct static_key *key); extern void static_key_slow_inc_cpuslocked(struct static_key *key); extern void static_key_slow_dec_cpuslocked(struct static_key *key); -extern void jump_label_apply_nops(struct module *mod); extern int static_key_count(struct static_key *key); extern void static_key_enable(struct static_key *key); extern void static_key_disable(struct static_key *key); extern void static_key_enable_cpuslocked(struct static_key *key); extern void static_key_disable_cpuslocked(struct static_key *key); +extern enum jump_label_type jump_label_init_type(struct jump_entry *entry); /* * We should be using ATOMIC_INIT() for initializing .enabled, but @@ -251,19 +244,19 @@ extern void static_key_disable_cpuslocked(struct static_key *key); */ #define STATIC_KEY_INIT_TRUE \ { .enabled = { 1 }, \ - { .entries = (void *)JUMP_TYPE_TRUE } } + { .type = JUMP_TYPE_TRUE } } #define STATIC_KEY_INIT_FALSE \ { .enabled = { 0 }, \ - { .entries = (void *)JUMP_TYPE_FALSE } } + { .type = JUMP_TYPE_FALSE } } #else /* !CONFIG_JUMP_LABEL */ #include <linux/atomic.h> #include <linux/bug.h> -static inline int static_key_count(struct static_key *key) +static __always_inline int static_key_count(struct static_key *key) { - return atomic_read(&key->enabled); + return arch_atomic_read(&key->enabled); } static __always_inline void jump_label_init(void) @@ -308,11 +301,6 @@ static inline int jump_label_text_reserved(void *start, void *end) static inline void jump_label_lock(void) {} static inline void jump_label_unlock(void) {} -static inline int jump_label_apply_nops(struct module *mod) -{ - return 0; -} - static inline void static_key_enable(struct static_key *key) { STATIC_KEY_CHECK_USE(key); diff --git a/include/linux/kallsyms.h b/include/linux/kallsyms.h index 4176c7eca7b5..649faac31ddb 100644 --- a/include/linux/kallsyms.h +++ b/include/linux/kallsyms.h @@ -15,7 +15,7 @@ #include <asm/sections.h> -#define KSYM_NAME_LEN 128 +#define KSYM_NAME_LEN 512 #define KSYM_SYMBOL_LEN (sizeof("%s+%#lx/%#lx [%s %s]") + \ (KSYM_NAME_LEN - 1) + \ 2*(BITS_PER_LONG*3/10) + (MODULE_NAME_LEN - 1) + \ @@ -48,7 +48,7 @@ static inline int is_ksym_addr(unsigned long addr) static inline void *dereference_symbol_descriptor(void *ptr) { -#ifdef HAVE_DEREFERENCE_FUNCTION_DESCRIPTOR +#ifdef CONFIG_HAVE_FUNCTION_DESCRIPTORS struct module *mod; ptr = dereference_kernel_function_descriptor(ptr); @@ -65,11 +65,11 @@ static inline void *dereference_symbol_descriptor(void *ptr) return ptr; } +#ifdef CONFIG_KALLSYMS int kallsyms_on_each_symbol(int (*fn)(void *, const char *, struct module *, unsigned long), void *data); -#ifdef CONFIG_KALLSYMS /* Lookup the address for a symbol. Returns 0 if not found. */ unsigned long kallsyms_lookup_name(const char *name); @@ -163,6 +163,11 @@ static inline bool kallsyms_show_value(const struct cred *cred) return false; } +static inline int kallsyms_on_each_symbol(int (*fn)(void *, const char *, struct module *, + unsigned long), void *data) +{ + return -EOPNOTSUPP; +} #endif /*CONFIG_KALLSYMS*/ static inline void print_ip_sym(const char *loglvl, unsigned long ip) diff --git a/include/linux/kasan-enabled.h b/include/linux/kasan-enabled.h new file mode 100644 index 000000000000..6f612d69ea0c --- /dev/null +++ b/include/linux/kasan-enabled.h @@ -0,0 +1,35 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_KASAN_ENABLED_H +#define _LINUX_KASAN_ENABLED_H + +#include <linux/static_key.h> + +#ifdef CONFIG_KASAN_HW_TAGS + +DECLARE_STATIC_KEY_FALSE(kasan_flag_enabled); + +static __always_inline bool kasan_enabled(void) +{ + return static_branch_likely(&kasan_flag_enabled); +} + +static inline bool kasan_hw_tags_enabled(void) +{ + return kasan_enabled(); +} + +#else /* CONFIG_KASAN_HW_TAGS */ + +static inline bool kasan_enabled(void) +{ + return IS_ENABLED(CONFIG_KASAN); +} + +static inline bool kasan_hw_tags_enabled(void) +{ + return false; +} + +#endif /* CONFIG_KASAN_HW_TAGS */ + +#endif /* LINUX_KASAN_ENABLED_H */ diff --git a/include/linux/kasan.h b/include/linux/kasan.h index fb78108d694e..d811b3d7d2a1 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -3,6 +3,7 @@ #define _LINUX_KASAN_H #include <linux/bug.h> +#include <linux/kasan-enabled.h> #include <linux/kernel.h> #include <linux/static_key.h> #include <linux/types.h> @@ -18,13 +19,15 @@ struct task_struct; #include <linux/linkage.h> #include <asm/kasan.h> -/* kasan_data struct is used in KUnit tests for KASAN expected failures */ -struct kunit_kasan_expectation { - bool report_found; -}; - #endif +typedef unsigned int __bitwise kasan_vmalloc_flags_t; + +#define KASAN_VMALLOC_NONE ((__force kasan_vmalloc_flags_t)0x00u) +#define KASAN_VMALLOC_INIT ((__force kasan_vmalloc_flags_t)0x01u) +#define KASAN_VMALLOC_VM_ALLOC ((__force kasan_vmalloc_flags_t)0x02u) +#define KASAN_VMALLOC_PROT_NORMAL ((__force kasan_vmalloc_flags_t)0x04u) + #if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) #include <linux/pgtable.h> @@ -83,47 +86,8 @@ static inline void kasan_disable_current(void) {} #ifdef CONFIG_KASAN_HW_TAGS -DECLARE_STATIC_KEY_FALSE(kasan_flag_enabled); - -static __always_inline bool kasan_enabled(void) -{ - return static_branch_likely(&kasan_flag_enabled); -} - -static inline bool kasan_hw_tags_enabled(void) -{ - return kasan_enabled(); -} - -void kasan_alloc_pages(struct page *page, unsigned int order, gfp_t flags); -void kasan_free_pages(struct page *page, unsigned int order); - #else /* CONFIG_KASAN_HW_TAGS */ -static inline bool kasan_enabled(void) -{ - return IS_ENABLED(CONFIG_KASAN); -} - -static inline bool kasan_hw_tags_enabled(void) -{ - return false; -} - -static __always_inline void kasan_alloc_pages(struct page *page, - unsigned int order, gfp_t flags) -{ - /* Only available for integrated init. */ - BUILD_BUG(); -} - -static __always_inline void kasan_free_pages(struct page *page, - unsigned int order) -{ - /* Only available for integrated init. */ - BUILD_BUG(); -} - #endif /* CONFIG_KASAN_HW_TAGS */ static inline bool kasan_has_integrated_init(void) @@ -134,19 +98,13 @@ static inline bool kasan_has_integrated_init(void) #ifdef CONFIG_KASAN struct kasan_cache { +#ifdef CONFIG_KASAN_GENERIC int alloc_meta_offset; int free_meta_offset; +#endif bool is_kmalloc; }; -slab_flags_t __kasan_never_merge(void); -static __always_inline slab_flags_t kasan_never_merge(void) -{ - if (kasan_enabled()) - return __kasan_never_merge(); - return 0; -} - void __kasan_unpoison_range(const void *addr, size_t size); static __always_inline void kasan_unpoison_range(const void *addr, size_t size) { @@ -170,15 +128,6 @@ static __always_inline void kasan_unpoison_pages(struct page *page, __kasan_unpoison_pages(page, order, init); } -void __kasan_cache_create(struct kmem_cache *cache, unsigned int *size, - slab_flags_t *flags); -static __always_inline void kasan_cache_create(struct kmem_cache *cache, - unsigned int *size, slab_flags_t *flags) -{ - if (kasan_enabled()) - __kasan_cache_create(cache, size, flags); -} - void __kasan_cache_create_kmalloc(struct kmem_cache *cache); static __always_inline void kasan_cache_create_kmalloc(struct kmem_cache *cache) { @@ -186,14 +135,6 @@ static __always_inline void kasan_cache_create_kmalloc(struct kmem_cache *cache) __kasan_cache_create_kmalloc(cache); } -size_t __kasan_metadata_size(struct kmem_cache *cache); -static __always_inline size_t kasan_metadata_size(struct kmem_cache *cache) -{ - if (kasan_enabled()) - return __kasan_metadata_size(cache); - return 0; -} - void __kasan_poison_slab(struct slab *slab); static __always_inline void kasan_poison_slab(struct slab *slab) { @@ -303,26 +244,14 @@ static __always_inline bool kasan_check_byte(const void *addr) return true; } - -bool kasan_save_enable_multi_shot(void); -void kasan_restore_multi_shot(bool enabled); - #else /* CONFIG_KASAN */ -static inline slab_flags_t kasan_never_merge(void) -{ - return 0; -} static inline void kasan_unpoison_range(const void *address, size_t size) {} static inline void kasan_poison_pages(struct page *page, unsigned int order, bool init) {} static inline void kasan_unpoison_pages(struct page *page, unsigned int order, bool init) {} -static inline void kasan_cache_create(struct kmem_cache *cache, - unsigned int *size, - slab_flags_t *flags) {} static inline void kasan_cache_create_kmalloc(struct kmem_cache *cache) {} -static inline size_t kasan_metadata_size(struct kmem_cache *cache) { return 0; } static inline void kasan_poison_slab(struct slab *slab) {} static inline void kasan_unpoison_object_data(struct kmem_cache *cache, void *object) {} @@ -373,6 +302,11 @@ static inline void kasan_unpoison_task_stack(struct task_struct *task) {} #ifdef CONFIG_KASAN_GENERIC +size_t kasan_metadata_size(struct kmem_cache *cache); +slab_flags_t kasan_never_merge(void); +void kasan_cache_create(struct kmem_cache *cache, unsigned int *size, + slab_flags_t *flags); + void kasan_cache_shrink(struct kmem_cache *cache); void kasan_cache_shutdown(struct kmem_cache *cache); void kasan_record_aux_stack(void *ptr); @@ -380,6 +314,21 @@ void kasan_record_aux_stack_noalloc(void *ptr); #else /* CONFIG_KASAN_GENERIC */ +/* Tag-based KASAN modes do not use per-object metadata. */ +static inline size_t kasan_metadata_size(struct kmem_cache *cache) +{ + return 0; +} +/* And thus nothing prevents cache merging. */ +static inline slab_flags_t kasan_never_merge(void) +{ + return 0; +} +/* And no cache-related metadata initialization is required. */ +static inline void kasan_cache_create(struct kmem_cache *cache, + unsigned int *size, + slab_flags_t *flags) {} + static inline void kasan_cache_shrink(struct kmem_cache *cache) {} static inline void kasan_cache_shutdown(struct kmem_cache *cache) {} static inline void kasan_record_aux_stack(void *ptr) {} @@ -435,34 +384,71 @@ static inline void kasan_init_hw_tags(void) { } #ifdef CONFIG_KASAN_VMALLOC +#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) + +void kasan_populate_early_vm_area_shadow(void *start, unsigned long size); int kasan_populate_vmalloc(unsigned long addr, unsigned long size); -void kasan_poison_vmalloc(const void *start, unsigned long size); -void kasan_unpoison_vmalloc(const void *start, unsigned long size); void kasan_release_vmalloc(unsigned long start, unsigned long end, unsigned long free_region_start, unsigned long free_region_end); -void kasan_populate_early_vm_area_shadow(void *start, unsigned long size); +#else /* CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS */ + +static inline void kasan_populate_early_vm_area_shadow(void *start, + unsigned long size) +{ } +static inline int kasan_populate_vmalloc(unsigned long start, + unsigned long size) +{ + return 0; +} +static inline void kasan_release_vmalloc(unsigned long start, + unsigned long end, + unsigned long free_region_start, + unsigned long free_region_end) { } + +#endif /* CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS */ + +void *__kasan_unpoison_vmalloc(const void *start, unsigned long size, + kasan_vmalloc_flags_t flags); +static __always_inline void *kasan_unpoison_vmalloc(const void *start, + unsigned long size, + kasan_vmalloc_flags_t flags) +{ + if (kasan_enabled()) + return __kasan_unpoison_vmalloc(start, size, flags); + return (void *)start; +} + +void __kasan_poison_vmalloc(const void *start, unsigned long size); +static __always_inline void kasan_poison_vmalloc(const void *start, + unsigned long size) +{ + if (kasan_enabled()) + __kasan_poison_vmalloc(start, size); +} #else /* CONFIG_KASAN_VMALLOC */ +static inline void kasan_populate_early_vm_area_shadow(void *start, + unsigned long size) { } static inline int kasan_populate_vmalloc(unsigned long start, unsigned long size) { return 0; } - -static inline void kasan_poison_vmalloc(const void *start, unsigned long size) -{ } -static inline void kasan_unpoison_vmalloc(const void *start, unsigned long size) -{ } static inline void kasan_release_vmalloc(unsigned long start, unsigned long end, unsigned long free_region_start, - unsigned long free_region_end) {} + unsigned long free_region_end) { } -static inline void kasan_populate_early_vm_area_shadow(void *start, - unsigned long size) +static inline void *kasan_unpoison_vmalloc(const void *start, + unsigned long size, + kasan_vmalloc_flags_t flags) +{ + return (void *)start; +} +static inline void kasan_poison_vmalloc(const void *start, unsigned long size) { } #endif /* CONFIG_KASAN_VMALLOC */ @@ -471,17 +457,17 @@ static inline void kasan_populate_early_vm_area_shadow(void *start, !defined(CONFIG_KASAN_VMALLOC) /* - * These functions provide a special case to support backing module - * allocations with real shadow memory. With KASAN vmalloc, the special - * case is unnecessary, as the work is handled in the generic case. + * These functions allocate and free shadow memory for kernel modules. + * They are only required when KASAN_VMALLOC is not supported, as otherwise + * shadow memory is allocated by the generic vmalloc handlers. */ -int kasan_module_alloc(void *addr, size_t size); -void kasan_free_shadow(const struct vm_struct *vm); +int kasan_alloc_module_shadow(void *addr, size_t size, gfp_t gfp_mask); +void kasan_free_module_shadow(const struct vm_struct *vm); #else /* (CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS) && !CONFIG_KASAN_VMALLOC */ -static inline int kasan_module_alloc(void *addr, size_t size) { return 0; } -static inline void kasan_free_shadow(const struct vm_struct *vm) {} +static inline int kasan_alloc_module_shadow(void *addr, size_t size, gfp_t gfp_mask) { return 0; } +static inline void kasan_free_module_shadow(const struct vm_struct *vm) {} #endif /* (CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS) && !CONFIG_KASAN_VMALLOC */ diff --git a/include/linux/kdb.h b/include/linux/kdb.h index ea0f5e580fac..07dfb6a20a1c 100644 --- a/include/linux/kdb.h +++ b/include/linux/kdb.h @@ -222,5 +222,6 @@ enum { extern int kdbgetintenv(const char *, int *); extern int kdb_set(int, const char **); +int kdb_lsmod(int argc, const char **argv); #endif /* !_KDB_H */ diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 77755ac3e189..fe6efb24d151 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -1,4 +1,13 @@ /* SPDX-License-Identifier: GPL-2.0 */ +/* + * NOTE: + * + * This header has combined a lot of unrelated to each other stuff. + * The process of splitting its content is in progress while keeping + * backward compatibility. That's why it's highly recommended NOT to + * include this header inside another header file, especially under + * generic or architectural include/ directory. + */ #ifndef _LINUX_KERNEL_H #define _LINUX_KERNEL_H @@ -90,7 +99,7 @@ struct user; extern int __cond_resched(void); # define might_resched() __cond_resched() -#elif defined(CONFIG_PREEMPT_DYNAMIC) +#elif defined(CONFIG_PREEMPT_DYNAMIC) && defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL) extern int __cond_resched(void); @@ -101,6 +110,11 @@ static __always_inline void might_resched(void) static_call_mod(might_resched)(); } +#elif defined(CONFIG_PREEMPT_DYNAMIC) && defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY) + +extern int dynamic_might_resched(void); +# define might_resched() dynamic_might_resched() + #else # define might_resched() do { } while (0) @@ -187,7 +201,6 @@ static inline void might_fault(void) { } #endif void do_exit(long error_code) __noreturn; -void complete_and_exit(struct completion *, long) __noreturn; extern int num_to_str(char *buf, int size, unsigned long long num, unsigned int width); @@ -272,7 +285,7 @@ static inline char *hex_byte_pack_upper(char *buf, u8 byte) return buf; } -extern int hex_to_bin(char ch); +extern int hex_to_bin(unsigned char ch); extern int __must_check hex2bin(u8 *dst, const char *src, size_t count); extern char *bin2hex(char *dst, const void *src, size_t count); diff --git a/include/linux/kernel_read_file.h b/include/linux/kernel_read_file.h index 575ffa1031d3..90451e2e12bd 100644 --- a/include/linux/kernel_read_file.h +++ b/include/linux/kernel_read_file.h @@ -35,21 +35,21 @@ static inline const char *kernel_read_file_id_str(enum kernel_read_file_id id) return kernel_read_file_str[id]; } -int kernel_read_file(struct file *file, loff_t offset, - void **buf, size_t buf_size, - size_t *file_size, - enum kernel_read_file_id id); -int kernel_read_file_from_path(const char *path, loff_t offset, - void **buf, size_t buf_size, - size_t *file_size, - enum kernel_read_file_id id); -int kernel_read_file_from_path_initns(const char *path, loff_t offset, - void **buf, size_t buf_size, - size_t *file_size, - enum kernel_read_file_id id); -int kernel_read_file_from_fd(int fd, loff_t offset, - void **buf, size_t buf_size, - size_t *file_size, - enum kernel_read_file_id id); +ssize_t kernel_read_file(struct file *file, loff_t offset, + void **buf, size_t buf_size, + size_t *file_size, + enum kernel_read_file_id id); +ssize_t kernel_read_file_from_path(const char *path, loff_t offset, + void **buf, size_t buf_size, + size_t *file_size, + enum kernel_read_file_id id); +ssize_t kernel_read_file_from_path_initns(const char *path, loff_t offset, + void **buf, size_t buf_size, + size_t *file_size, + enum kernel_read_file_id id); +ssize_t kernel_read_file_from_fd(int fd, loff_t offset, + void **buf, size_t buf_size, + size_t *file_size, + enum kernel_read_file_id id); #endif /* _LINUX_KERNEL_READ_FILE_H */ diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h index 69ae6b278464..ddb5a358fd82 100644 --- a/include/linux/kernel_stat.h +++ b/include/linux/kernel_stat.h @@ -28,6 +28,9 @@ enum cpu_usage_stat { CPUTIME_STEAL, CPUTIME_GUEST, CPUTIME_GUEST_NICE, +#ifdef CONFIG_SCHED_CORE + CPUTIME_FORCEIDLE, +#endif NR_STATS, }; @@ -115,4 +118,8 @@ extern void account_process_tick(struct task_struct *, int user); extern void account_idle_ticks(unsigned long ticks); +#ifdef CONFIG_SCHED_CORE +extern void __account_forceidle_time(struct task_struct *tsk, u64 delta); +#endif + #endif /* _LINUX_KERNEL_STAT_H */ diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h index 3ccce6f24548..73f5c120def8 100644 --- a/include/linux/kernfs.h +++ b/include/linux/kernfs.h @@ -6,7 +6,6 @@ #ifndef __LINUX_KERNFS_H #define __LINUX_KERNFS_H -#include <linux/kernel.h> #include <linux/err.h> #include <linux/list.h> #include <linux/mutex.h> @@ -14,14 +13,19 @@ #include <linux/lockdep.h> #include <linux/rbtree.h> #include <linux/atomic.h> +#include <linux/bug.h> +#include <linux/types.h> #include <linux/uidgid.h> #include <linux/wait.h> +#include <linux/rwsem.h> +#include <linux/cache.h> struct file; struct dentry; struct iattr; struct seq_file; struct vm_area_struct; +struct vm_operations_struct; struct super_block; struct file_system_type; struct poll_table_struct; @@ -31,6 +35,62 @@ struct kernfs_fs_context; struct kernfs_open_node; struct kernfs_iattrs; +/* + * NR_KERNFS_LOCK_BITS determines size (NR_KERNFS_LOCKS) of hash + * table of locks. + * Having a small hash table would impact scalability, since + * more and more kernfs_node objects will end up using same lock + * and having a very large hash table would waste memory. + * + * At the moment size of hash table of locks is being set based on + * the number of CPUs as follows: + * + * NR_CPU NR_KERNFS_LOCK_BITS NR_KERNFS_LOCKS + * 1 1 2 + * 2-3 2 4 + * 4-7 4 16 + * 8-15 6 64 + * 16-31 8 256 + * 32 and more 10 1024 + * + * The above relation between NR_CPU and number of locks is based + * on some internal experimentation which involved booting qemu + * with different values of smp, performing some sysfs operations + * on all CPUs and observing how increase in number of locks impacts + * completion time of these sysfs operations on each CPU. + */ +#ifdef CONFIG_SMP +#define NR_KERNFS_LOCK_BITS (2 * (ilog2(NR_CPUS < 32 ? NR_CPUS : 32))) +#else +#define NR_KERNFS_LOCK_BITS 1 +#endif + +#define NR_KERNFS_LOCKS (1 << NR_KERNFS_LOCK_BITS) + +/* + * There's one kernfs_open_file for each open file and one kernfs_open_node + * for each kernfs_node with one or more open files. + * + * filp->private_data points to seq_file whose ->private points to + * kernfs_open_file. + * + * kernfs_open_files are chained at kernfs_open_node->files, which is + * protected by kernfs_global_locks.open_file_mutex[i]. + * + * To reduce possible contention in sysfs access, arising due to single + * locks, use an array of locks (e.g. open_file_mutex) and use kernfs_node + * object address as hash keys to get the index of these locks. + * + * Hashed mutexes are safe to use here because operations using these don't + * rely on global exclusion. + * + * In future we intend to replace other global locks with hashed ones as well. + * kernfs_global_locks acts as a holder for all such hash tables. + */ +struct kernfs_global_locks { + struct mutex open_file_mutex[NR_KERNFS_LOCKS]; +}; + enum kernfs_node_type { KERNFS_DIR = 0x0001, KERNFS_FILE = 0x0002, @@ -48,10 +108,12 @@ enum kernfs_node_flag { KERNFS_HAS_SEQ_SHOW = 0x0040, KERNFS_HAS_MMAP = 0x0080, KERNFS_LOCKDEP = 0x0100, + KERNFS_HIDDEN = 0x0200, KERNFS_SUICIDAL = 0x0400, KERNFS_SUICIDED = 0x0800, KERNFS_EMPTY_DIR = 0x1000, KERNFS_HAS_RELEASE = 0x2000, + KERNFS_REMOVING = 0x4000, }; /* @flags for kernfs_create_root() */ @@ -111,7 +173,7 @@ struct kernfs_elem_symlink { struct kernfs_elem_attr { const struct kernfs_ops *ops; - struct kernfs_open_node *open; + struct kernfs_open_node __rcu *open; loff_t size; struct kernfs_node *notify_next; /* for kernfs_notify() */ }; @@ -182,22 +244,7 @@ struct kernfs_syscall_ops { struct kernfs_root *root); }; -struct kernfs_root { - /* published fields */ - struct kernfs_node *kn; - unsigned int flags; /* KERNFS_ROOT_* flags */ - - /* private fields, do not use outside kernfs proper */ - struct idr ino_idr; - u32 last_id_lowbits; - u32 id_highbits; - struct kernfs_syscall_ops *syscall_ops; - - /* list of kernfs_super_info of this root, protected by kernfs_rwsem */ - struct list_head supers; - - wait_queue_head_t deactivate_waitq; -}; +struct kernfs_node *kernfs_root_to_node(struct kernfs_root *root); struct kernfs_open_file { /* published fields */ @@ -384,6 +431,7 @@ struct kernfs_node *kernfs_create_link(struct kernfs_node *parent, const char *name, struct kernfs_node *target); void kernfs_activate(struct kernfs_node *kn); +void kernfs_show(struct kernfs_node *kn, bool show); void kernfs_remove(struct kernfs_node *kn); void kernfs_break_active_protection(struct kernfs_node *kn); void kernfs_unbreak_active_protection(struct kernfs_node *kn); diff --git a/include/linux/kexec.h b/include/linux/kexec.h index 0c994ae37729..41a686996aaa 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -19,6 +19,13 @@ #include <asm/io.h> #include <uapi/linux/kexec.h> +#include <linux/verification.h> + +/* Location of a reserved region to hold the crash kernel. + */ +extern struct resource crashk_res; +extern struct resource crashk_low_res; +extern note_buf_t __percpu *crash_notes; #ifdef CONFIG_KEXEC_CORE #include <linux/list.h> @@ -182,29 +189,54 @@ int kexec_purgatory_get_set_symbol(struct kimage *image, const char *name, void *buf, unsigned int size, bool get_value); void *kexec_purgatory_get_symbol_addr(struct kimage *image, const char *name); +void *kexec_image_load_default(struct kimage *image); + +#ifndef arch_kexec_kernel_image_probe +static inline int +arch_kexec_kernel_image_probe(struct kimage *image, void *buf, unsigned long buf_len) +{ + return kexec_image_probe_default(image, buf, buf_len); +} +#endif + +#ifndef arch_kimage_file_post_load_cleanup +static inline int arch_kimage_file_post_load_cleanup(struct kimage *image) +{ + return kexec_image_post_load_cleanup_default(image); +} +#endif + +#ifndef arch_kexec_kernel_image_load +static inline void *arch_kexec_kernel_image_load(struct kimage *image) +{ + return kexec_image_load_default(image); +} +#endif -/* Architectures may override the below functions */ -int arch_kexec_kernel_image_probe(struct kimage *image, void *buf, - unsigned long buf_len); -void *arch_kexec_kernel_image_load(struct kimage *image); -int arch_kexec_apply_relocations_add(struct purgatory_info *pi, - Elf_Shdr *section, - const Elf_Shdr *relsec, - const Elf_Shdr *symtab); -int arch_kexec_apply_relocations(struct purgatory_info *pi, - Elf_Shdr *section, - const Elf_Shdr *relsec, - const Elf_Shdr *symtab); -int arch_kimage_file_post_load_cleanup(struct kimage *image); #ifdef CONFIG_KEXEC_SIG -int arch_kexec_kernel_verify_sig(struct kimage *image, void *buf, - unsigned long buf_len); +#ifdef CONFIG_SIGNED_PE_FILE_VERIFICATION +int kexec_kernel_verify_pe_sig(const char *kernel, unsigned long kernel_len); +#endif #endif -int arch_kexec_locate_mem_hole(struct kexec_buf *kbuf); extern int kexec_add_buffer(struct kexec_buf *kbuf); int kexec_locate_mem_hole(struct kexec_buf *kbuf); +#ifndef arch_kexec_locate_mem_hole +/** + * arch_kexec_locate_mem_hole - Find free memory to place the segments. + * @kbuf: Parameters for the memory search. + * + * On success, kbuf->mem will have the start address of the memory region found. + * + * Return: 0 on success, negative errno on error. + */ +static inline int arch_kexec_locate_mem_hole(struct kexec_buf *kbuf) +{ + return kexec_locate_mem_hole(kbuf); +} +#endif + /* Alignment required for elf header segment */ #define ELF_CORE_HEADER_ALIGN 4096 @@ -221,8 +253,46 @@ struct crash_mem { extern int crash_exclude_mem_range(struct crash_mem *mem, unsigned long long mstart, unsigned long long mend); -extern int crash_prepare_elf64_headers(struct crash_mem *mem, int kernel_map, +extern int crash_prepare_elf64_headers(struct crash_mem *mem, int need_kernel_map, void **addr, unsigned long *sz); + +#ifndef arch_kexec_apply_relocations_add +/* + * arch_kexec_apply_relocations_add - apply relocations of type RELA + * @pi: Purgatory to be relocated. + * @section: Section relocations applying to. + * @relsec: Section containing RELAs. + * @symtab: Corresponding symtab. + * + * Return: 0 on success, negative errno on error. + */ +static inline int +arch_kexec_apply_relocations_add(struct purgatory_info *pi, Elf_Shdr *section, + const Elf_Shdr *relsec, const Elf_Shdr *symtab) +{ + pr_err("RELA relocation unsupported.\n"); + return -ENOEXEC; +} +#endif + +#ifndef arch_kexec_apply_relocations +/* + * arch_kexec_apply_relocations - apply relocations of type REL + * @pi: Purgatory to be relocated. + * @section: Section relocations applying to. + * @relsec: Section containing RELs. + * @symtab: Corresponding symtab. + * + * Return: 0 on success, negative errno on error. + */ +static inline int +arch_kexec_apply_relocations(struct purgatory_info *pi, Elf_Shdr *section, + const Elf_Shdr *relsec, const Elf_Shdr *symtab) +{ + pr_err("REL relocation unsupported.\n"); + return -ENOEXEC; +} +#endif #endif /* CONFIG_KEXEC_FILE */ #ifdef CONFIG_KEXEC_ELF @@ -322,7 +392,10 @@ extern void machine_kexec_cleanup(struct kimage *image); extern int kernel_kexec(void); extern struct page *kimage_alloc_control_pages(struct kimage *image, unsigned int order); -int machine_kexec_post_load(struct kimage *image); + +#ifndef machine_kexec_post_load +static inline int machine_kexec_post_load(struct kimage *image) { return 0; } +#endif extern void __crash_kexec(struct pt_regs *); extern void crash_kexec(struct pt_regs *); @@ -350,21 +423,26 @@ extern int kexec_load_disabled; #define KEXEC_FILE_FLAGS (KEXEC_FILE_UNLOAD | KEXEC_FILE_ON_CRASH | \ KEXEC_FILE_NO_INITRAMFS) -/* Location of a reserved region to hold the crash kernel. - */ -extern struct resource crashk_res; -extern struct resource crashk_low_res; -extern note_buf_t __percpu *crash_notes; - /* flag to track if kexec reboot is in progress */ extern bool kexec_in_progress; int crash_shrink_memory(unsigned long new_size); -size_t crash_get_memory_size(void); -void crash_free_reserved_phys_range(unsigned long begin, unsigned long end); +ssize_t crash_get_memory_size(void); -void arch_kexec_protect_crashkres(void); -void arch_kexec_unprotect_crashkres(void); +#ifndef arch_kexec_protect_crashkres +/* + * Protection mechanism for crashkernel reserved memory after + * the kdump kernel is loaded. + * + * Provide an empty default implementation here -- architecture + * code may override this + */ +static inline void arch_kexec_protect_crashkres(void) { } +#endif + +#ifndef arch_kexec_unprotect_crashkres +static inline void arch_kexec_unprotect_crashkres(void) { } +#endif #ifndef page_to_boot_pfn static inline unsigned long page_to_boot_pfn(struct page *page) @@ -394,6 +472,16 @@ static inline phys_addr_t boot_phys_to_phys(unsigned long boot_phys) } #endif +#ifndef crash_free_reserved_phys_range +static inline void crash_free_reserved_phys_range(unsigned long begin, unsigned long end) +{ + unsigned long addr; + + for (addr = begin; addr < end; addr += PAGE_SIZE) + free_reserved_page(boot_pfn_to_page(addr >> PAGE_SHIFT)); +} +#endif + static inline unsigned long virt_to_boot_phys(void *addr) { return phys_to_boot_phys(__pa((unsigned long)addr)); @@ -422,6 +510,12 @@ static inline int kexec_crash_loaded(void) { return 0; } #define kexec_in_progress false #endif /* CONFIG_KEXEC_CORE */ +#ifdef CONFIG_KEXEC_SIG +void set_kexec_sig_enforced(void); +#else +static inline void set_kexec_sig_enforced(void) {} +#endif + #endif /* !defined(__ASSEBMLY__) */ #endif /* LINUX_KEXEC_H */ diff --git a/include/linux/key.h b/include/linux/key.h index 7febc4881363..d27477faf00d 100644 --- a/include/linux/key.h +++ b/include/linux/key.h @@ -88,6 +88,12 @@ enum key_need_perm { KEY_DEFER_PERM_CHECK, /* Special: permission check is deferred */ }; +enum key_lookup_flag { + KEY_LOOKUP_CREATE = 0x01, + KEY_LOOKUP_PARTIAL = 0x02, + KEY_LOOKUP_ALL = (KEY_LOOKUP_CREATE | KEY_LOOKUP_PARTIAL), +}; + struct seq_file; struct user_struct; struct signal_struct; diff --git a/include/linux/kfence.h b/include/linux/kfence.h index 4b5e3679a72c..726857a4b680 100644 --- a/include/linux/kfence.h +++ b/include/linux/kfence.h @@ -17,6 +17,8 @@ #include <linux/atomic.h> #include <linux/static_key.h> +extern unsigned long kfence_sample_interval; + /* * We allocate an even number of pages, as it simplifies calculations to map * address to metadata indices; effectively, the very first page serves as an @@ -202,6 +204,22 @@ static __always_inline __must_check bool kfence_free(void *addr) */ bool __must_check kfence_handle_page_fault(unsigned long addr, bool is_write, struct pt_regs *regs); +#ifdef CONFIG_PRINTK +struct kmem_obj_info; +/** + * __kfence_obj_info() - fill kmem_obj_info struct + * @kpp: kmem_obj_info to be filled + * @object: the object + * + * Return: + * * false - not a KFENCE object + * * true - a KFENCE object, filled @kpp + * + * Copies information to @kpp for KFENCE objects. + */ +bool __kfence_obj_info(struct kmem_obj_info *kpp, void *object, struct slab *slab); +#endif + #else /* CONFIG_KFENCE */ static inline bool is_kfence_address(const void *addr) { return false; } @@ -219,6 +237,14 @@ static inline bool __must_check kfence_handle_page_fault(unsigned long addr, boo return false; } +#ifdef CONFIG_PRINTK +struct kmem_obj_info; +static inline bool __kfence_obj_info(struct kmem_obj_info *kpp, void *object, struct slab *slab) +{ + return false; +} +#endif + #endif #endif /* _LINUX_KFENCE_H */ diff --git a/include/linux/kfifo.h b/include/linux/kfifo.h index 86249476b57f..0b35a41440ff 100644 --- a/include/linux/kfifo.h +++ b/include/linux/kfifo.h @@ -688,7 +688,7 @@ __kfifo_uint_must_check_helper( \ * writer, you don't need extra locking to use these macro. */ #define kfifo_to_user(fifo, to, len, copied) \ -__kfifo_uint_must_check_helper( \ +__kfifo_int_must_check_helper( \ ({ \ typeof((fifo) + 1) __tmp = (fifo); \ void __user *__to = (to); \ diff --git a/include/linux/khugepaged.h b/include/linux/khugepaged.h index 2fcc01891b47..70162d707caf 100644 --- a/include/linux/khugepaged.h +++ b/include/linux/khugepaged.h @@ -3,8 +3,6 @@ #define _LINUX_KHUGEPAGED_H #include <linux/sched/coredump.h> /* MMF_VM_HUGEPAGE */ -#include <linux/shmem_fs.h> - #ifdef CONFIG_TRANSPARENT_HUGEPAGE extern struct attribute_group khugepaged_attr_group; @@ -12,39 +10,26 @@ extern struct attribute_group khugepaged_attr_group; extern int khugepaged_init(void); extern void khugepaged_destroy(void); extern int start_stop_khugepaged(void); -extern int __khugepaged_enter(struct mm_struct *mm); +extern void __khugepaged_enter(struct mm_struct *mm); extern void __khugepaged_exit(struct mm_struct *mm); -extern int khugepaged_enter_vma_merge(struct vm_area_struct *vma, - unsigned long vm_flags); +extern void khugepaged_enter_vma(struct vm_area_struct *vma, + unsigned long vm_flags); extern void khugepaged_min_free_kbytes_update(void); #ifdef CONFIG_SHMEM -extern void collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr); +extern int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr, + bool install_pmd); #else -static inline void collapse_pte_mapped_thp(struct mm_struct *mm, - unsigned long addr) +static inline int collapse_pte_mapped_thp(struct mm_struct *mm, + unsigned long addr, bool install_pmd) { + return 0; } #endif -#define khugepaged_enabled() \ - (transparent_hugepage_flags & \ - ((1<<TRANSPARENT_HUGEPAGE_FLAG) | \ - (1<<TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG))) -#define khugepaged_always() \ - (transparent_hugepage_flags & \ - (1<<TRANSPARENT_HUGEPAGE_FLAG)) -#define khugepaged_req_madv() \ - (transparent_hugepage_flags & \ - (1<<TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG)) -#define khugepaged_defrag() \ - (transparent_hugepage_flags & \ - (1<<TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG)) - -static inline int khugepaged_fork(struct mm_struct *mm, struct mm_struct *oldmm) +static inline void khugepaged_fork(struct mm_struct *mm, struct mm_struct *oldmm) { if (test_bit(MMF_VM_HUGEPAGE, &oldmm->flags)) - return __khugepaged_enter(mm); - return 0; + __khugepaged_enter(mm); } static inline void khugepaged_exit(struct mm_struct *mm) @@ -52,42 +37,22 @@ static inline void khugepaged_exit(struct mm_struct *mm) if (test_bit(MMF_VM_HUGEPAGE, &mm->flags)) __khugepaged_exit(mm); } - -static inline int khugepaged_enter(struct vm_area_struct *vma, - unsigned long vm_flags) -{ - if (!test_bit(MMF_VM_HUGEPAGE, &vma->vm_mm->flags)) - if ((khugepaged_always() || - (shmem_file(vma->vm_file) && shmem_huge_enabled(vma)) || - (khugepaged_req_madv() && (vm_flags & VM_HUGEPAGE))) && - !(vm_flags & VM_NOHUGEPAGE) && - !test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags)) - if (__khugepaged_enter(vma->vm_mm)) - return -ENOMEM; - return 0; -} #else /* CONFIG_TRANSPARENT_HUGEPAGE */ -static inline int khugepaged_fork(struct mm_struct *mm, struct mm_struct *oldmm) +static inline void khugepaged_fork(struct mm_struct *mm, struct mm_struct *oldmm) { - return 0; } static inline void khugepaged_exit(struct mm_struct *mm) { } -static inline int khugepaged_enter(struct vm_area_struct *vma, - unsigned long vm_flags) +static inline void khugepaged_enter_vma(struct vm_area_struct *vma, + unsigned long vm_flags) { - return 0; } -static inline int khugepaged_enter_vma_merge(struct vm_area_struct *vma, - unsigned long vm_flags) +static inline int collapse_pte_mapped_thp(struct mm_struct *mm, + unsigned long addr, bool install_pmd) { return 0; } -static inline void collapse_pte_mapped_thp(struct mm_struct *mm, - unsigned long addr) -{ -} static inline void khugepaged_min_free_kbytes_update(void) { diff --git a/include/linux/kmemleak.h b/include/linux/kmemleak.h index 34684b2026ab..6a3cd1bf4680 100644 --- a/include/linux/kmemleak.h +++ b/include/linux/kmemleak.h @@ -29,10 +29,9 @@ extern void kmemleak_not_leak(const void *ptr) __ref; extern void kmemleak_ignore(const void *ptr) __ref; extern void kmemleak_scan_area(const void *ptr, size_t size, gfp_t gfp) __ref; extern void kmemleak_no_scan(const void *ptr) __ref; -extern void kmemleak_alloc_phys(phys_addr_t phys, size_t size, int min_count, +extern void kmemleak_alloc_phys(phys_addr_t phys, size_t size, gfp_t gfp) __ref; extern void kmemleak_free_part_phys(phys_addr_t phys, size_t size) __ref; -extern void kmemleak_not_leak_phys(phys_addr_t phys) __ref; extern void kmemleak_ignore_phys(phys_addr_t phys) __ref; static inline void kmemleak_alloc_recursive(const void *ptr, size_t size, @@ -107,15 +106,12 @@ static inline void kmemleak_no_scan(const void *ptr) { } static inline void kmemleak_alloc_phys(phys_addr_t phys, size_t size, - int min_count, gfp_t gfp) + gfp_t gfp) { } static inline void kmemleak_free_part_phys(phys_addr_t phys, size_t size) { } -static inline void kmemleak_not_leak_phys(phys_addr_t phys) -{ -} static inline void kmemleak_ignore_phys(phys_addr_t phys) { } diff --git a/include/linux/kmsan-checks.h b/include/linux/kmsan-checks.h new file mode 100644 index 000000000000..c4cae333deec --- /dev/null +++ b/include/linux/kmsan-checks.h @@ -0,0 +1,83 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * KMSAN checks to be used for one-off annotations in subsystems. + * + * Copyright (C) 2017-2022 Google LLC + * Author: Alexander Potapenko <glider@google.com> + * + */ + +#ifndef _LINUX_KMSAN_CHECKS_H +#define _LINUX_KMSAN_CHECKS_H + +#include <linux/types.h> + +#ifdef CONFIG_KMSAN + +/** + * kmsan_poison_memory() - Mark the memory range as uninitialized. + * @address: address to start with. + * @size: size of buffer to poison. + * @flags: GFP flags for allocations done by this function. + * + * Until other data is written to this range, KMSAN will treat it as + * uninitialized. Error reports for this memory will reference the call site of + * kmsan_poison_memory() as origin. + */ +void kmsan_poison_memory(const void *address, size_t size, gfp_t flags); + +/** + * kmsan_unpoison_memory() - Mark the memory range as initialized. + * @address: address to start with. + * @size: size of buffer to unpoison. + * + * Until other data is written to this range, KMSAN will treat it as + * initialized. + */ +void kmsan_unpoison_memory(const void *address, size_t size); + +/** + * kmsan_check_memory() - Check the memory range for being initialized. + * @address: address to start with. + * @size: size of buffer to check. + * + * If any piece of the given range is marked as uninitialized, KMSAN will report + * an error. + */ +void kmsan_check_memory(const void *address, size_t size); + +/** + * kmsan_copy_to_user() - Notify KMSAN about a data transfer to userspace. + * @to: destination address in the userspace. + * @from: source address in the kernel. + * @to_copy: number of bytes to copy. + * @left: number of bytes not copied. + * + * If this is a real userspace data transfer, KMSAN checks the bytes that were + * actually copied to ensure there was no information leak. If @to belongs to + * the kernel space (which is possible for compat syscalls), KMSAN just copies + * the metadata. + */ +void kmsan_copy_to_user(void __user *to, const void *from, size_t to_copy, + size_t left); + +#else + +static inline void kmsan_poison_memory(const void *address, size_t size, + gfp_t flags) +{ +} +static inline void kmsan_unpoison_memory(const void *address, size_t size) +{ +} +static inline void kmsan_check_memory(const void *address, size_t size) +{ +} +static inline void kmsan_copy_to_user(void __user *to, const void *from, + size_t to_copy, size_t left) +{ +} + +#endif + +#endif /* _LINUX_KMSAN_CHECKS_H */ diff --git a/include/linux/kmsan.h b/include/linux/kmsan.h new file mode 100644 index 000000000000..e38ae3c34618 --- /dev/null +++ b/include/linux/kmsan.h @@ -0,0 +1,330 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * KMSAN API for subsystems. + * + * Copyright (C) 2017-2022 Google LLC + * Author: Alexander Potapenko <glider@google.com> + * + */ +#ifndef _LINUX_KMSAN_H +#define _LINUX_KMSAN_H + +#include <linux/dma-direction.h> +#include <linux/gfp.h> +#include <linux/kmsan-checks.h> +#include <linux/types.h> + +struct page; +struct kmem_cache; +struct task_struct; +struct scatterlist; +struct urb; + +#ifdef CONFIG_KMSAN + +/** + * kmsan_task_create() - Initialize KMSAN state for the task. + * @task: task to initialize. + */ +void kmsan_task_create(struct task_struct *task); + +/** + * kmsan_task_exit() - Notify KMSAN that a task has exited. + * @task: task about to finish. + */ +void kmsan_task_exit(struct task_struct *task); + +/** + * kmsan_init_shadow() - Initialize KMSAN shadow at boot time. + * + * Allocate and initialize KMSAN metadata for early allocations. + */ +void __init kmsan_init_shadow(void); + +/** + * kmsan_init_runtime() - Initialize KMSAN state and enable KMSAN. + */ +void __init kmsan_init_runtime(void); + +/** + * kmsan_memblock_free_pages() - handle freeing of memblock pages. + * @page: struct page to free. + * @order: order of @page. + * + * Freed pages are either returned to buddy allocator or held back to be used + * as metadata pages. + */ +bool __init kmsan_memblock_free_pages(struct page *page, unsigned int order); + +/** + * kmsan_alloc_page() - Notify KMSAN about an alloc_pages() call. + * @page: struct page pointer returned by alloc_pages(). + * @order: order of allocated struct page. + * @flags: GFP flags used by alloc_pages() + * + * KMSAN marks 1<<@order pages starting at @page as uninitialized, unless + * @flags contain __GFP_ZERO. + */ +void kmsan_alloc_page(struct page *page, unsigned int order, gfp_t flags); + +/** + * kmsan_free_page() - Notify KMSAN about a free_pages() call. + * @page: struct page pointer passed to free_pages(). + * @order: order of deallocated struct page. + * + * KMSAN marks freed memory as uninitialized. + */ +void kmsan_free_page(struct page *page, unsigned int order); + +/** + * kmsan_copy_page_meta() - Copy KMSAN metadata between two pages. + * @dst: destination page. + * @src: source page. + * + * KMSAN copies the contents of metadata pages for @src into the metadata pages + * for @dst. If @dst has no associated metadata pages, nothing happens. + * If @src has no associated metadata pages, @dst metadata pages are unpoisoned. + */ +void kmsan_copy_page_meta(struct page *dst, struct page *src); + +/** + * kmsan_slab_alloc() - Notify KMSAN about a slab allocation. + * @s: slab cache the object belongs to. + * @object: object pointer. + * @flags: GFP flags passed to the allocator. + * + * Depending on cache flags and GFP flags, KMSAN sets up the metadata of the + * newly created object, marking it as initialized or uninitialized. + */ +void kmsan_slab_alloc(struct kmem_cache *s, void *object, gfp_t flags); + +/** + * kmsan_slab_free() - Notify KMSAN about a slab deallocation. + * @s: slab cache the object belongs to. + * @object: object pointer. + * + * KMSAN marks the freed object as uninitialized. + */ +void kmsan_slab_free(struct kmem_cache *s, void *object); + +/** + * kmsan_kmalloc_large() - Notify KMSAN about a large slab allocation. + * @ptr: object pointer. + * @size: object size. + * @flags: GFP flags passed to the allocator. + * + * Similar to kmsan_slab_alloc(), but for large allocations. + */ +void kmsan_kmalloc_large(const void *ptr, size_t size, gfp_t flags); + +/** + * kmsan_kfree_large() - Notify KMSAN about a large slab deallocation. + * @ptr: object pointer. + * + * Similar to kmsan_slab_free(), but for large allocations. + */ +void kmsan_kfree_large(const void *ptr); + +/** + * kmsan_map_kernel_range_noflush() - Notify KMSAN about a vmap. + * @start: start of vmapped range. + * @end: end of vmapped range. + * @prot: page protection flags used for vmap. + * @pages: array of pages. + * @page_shift: page_shift passed to vmap_range_noflush(). + * + * KMSAN maps shadow and origin pages of @pages into contiguous ranges in + * vmalloc metadata address range. + */ +void kmsan_vmap_pages_range_noflush(unsigned long start, unsigned long end, + pgprot_t prot, struct page **pages, + unsigned int page_shift); + +/** + * kmsan_vunmap_kernel_range_noflush() - Notify KMSAN about a vunmap. + * @start: start of vunmapped range. + * @end: end of vunmapped range. + * + * KMSAN unmaps the contiguous metadata ranges created by + * kmsan_map_kernel_range_noflush(). + */ +void kmsan_vunmap_range_noflush(unsigned long start, unsigned long end); + +/** + * kmsan_ioremap_page_range() - Notify KMSAN about a ioremap_page_range() call. + * @addr: range start. + * @end: range end. + * @phys_addr: physical range start. + * @prot: page protection flags used for ioremap_page_range(). + * @page_shift: page_shift argument passed to vmap_range_noflush(). + * + * KMSAN creates new metadata pages for the physical pages mapped into the + * virtual memory. + */ +void kmsan_ioremap_page_range(unsigned long addr, unsigned long end, + phys_addr_t phys_addr, pgprot_t prot, + unsigned int page_shift); + +/** + * kmsan_iounmap_page_range() - Notify KMSAN about a iounmap_page_range() call. + * @start: range start. + * @end: range end. + * + * KMSAN unmaps the metadata pages for the given range and, unlike for + * vunmap_page_range(), also deallocates them. + */ +void kmsan_iounmap_page_range(unsigned long start, unsigned long end); + +/** + * kmsan_handle_dma() - Handle a DMA data transfer. + * @page: first page of the buffer. + * @offset: offset of the buffer within the first page. + * @size: buffer size. + * @dir: one of possible dma_data_direction values. + * + * Depending on @direction, KMSAN: + * * checks the buffer, if it is copied to device; + * * initializes the buffer, if it is copied from device; + * * does both, if this is a DMA_BIDIRECTIONAL transfer. + */ +void kmsan_handle_dma(struct page *page, size_t offset, size_t size, + enum dma_data_direction dir); + +/** + * kmsan_handle_dma_sg() - Handle a DMA transfer using scatterlist. + * @sg: scatterlist holding DMA buffers. + * @nents: number of scatterlist entries. + * @dir: one of possible dma_data_direction values. + * + * Depending on @direction, KMSAN: + * * checks the buffers in the scatterlist, if they are copied to device; + * * initializes the buffers, if they are copied from device; + * * does both, if this is a DMA_BIDIRECTIONAL transfer. + */ +void kmsan_handle_dma_sg(struct scatterlist *sg, int nents, + enum dma_data_direction dir); + +/** + * kmsan_handle_urb() - Handle a USB data transfer. + * @urb: struct urb pointer. + * @is_out: data transfer direction (true means output to hardware). + * + * If @is_out is true, KMSAN checks the transfer buffer of @urb. Otherwise, + * KMSAN initializes the transfer buffer. + */ +void kmsan_handle_urb(const struct urb *urb, bool is_out); + +/** + * kmsan_unpoison_entry_regs() - Handle pt_regs in low-level entry code. + * @regs: struct pt_regs pointer received from assembly code. + * + * KMSAN unpoisons the contents of the passed pt_regs, preventing potential + * false positive reports. Unlike kmsan_unpoison_memory(), + * kmsan_unpoison_entry_regs() can be called from the regions where + * kmsan_in_runtime() returns true, which is the case in early entry code. + */ +void kmsan_unpoison_entry_regs(const struct pt_regs *regs); + +#else + +static inline void kmsan_init_shadow(void) +{ +} + +static inline void kmsan_init_runtime(void) +{ +} + +static inline bool kmsan_memblock_free_pages(struct page *page, + unsigned int order) +{ + return true; +} + +static inline void kmsan_task_create(struct task_struct *task) +{ +} + +static inline void kmsan_task_exit(struct task_struct *task) +{ +} + +static inline int kmsan_alloc_page(struct page *page, unsigned int order, + gfp_t flags) +{ + return 0; +} + +static inline void kmsan_free_page(struct page *page, unsigned int order) +{ +} + +static inline void kmsan_copy_page_meta(struct page *dst, struct page *src) +{ +} + +static inline void kmsan_slab_alloc(struct kmem_cache *s, void *object, + gfp_t flags) +{ +} + +static inline void kmsan_slab_free(struct kmem_cache *s, void *object) +{ +} + +static inline void kmsan_kmalloc_large(const void *ptr, size_t size, + gfp_t flags) +{ +} + +static inline void kmsan_kfree_large(const void *ptr) +{ +} + +static inline void kmsan_vmap_pages_range_noflush(unsigned long start, + unsigned long end, + pgprot_t prot, + struct page **pages, + unsigned int page_shift) +{ +} + +static inline void kmsan_vunmap_range_noflush(unsigned long start, + unsigned long end) +{ +} + +static inline void kmsan_ioremap_page_range(unsigned long start, + unsigned long end, + phys_addr_t phys_addr, + pgprot_t prot, + unsigned int page_shift) +{ +} + +static inline void kmsan_iounmap_page_range(unsigned long start, + unsigned long end) +{ +} + +static inline void kmsan_handle_dma(struct page *page, size_t offset, + size_t size, enum dma_data_direction dir) +{ +} + +static inline void kmsan_handle_dma_sg(struct scatterlist *sg, int nents, + enum dma_data_direction dir) +{ +} + +static inline void kmsan_handle_urb(const struct urb *urb, bool is_out) +{ +} + +static inline void kmsan_unpoison_entry_regs(const struct pt_regs *regs) +{ +} + +#endif + +#endif /* _LINUX_KMSAN_H */ diff --git a/include/linux/kmsan_string.h b/include/linux/kmsan_string.h new file mode 100644 index 000000000000..7287da6f52ef --- /dev/null +++ b/include/linux/kmsan_string.h @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * KMSAN string functions API used in other headers. + * + * Copyright (C) 2022 Google LLC + * Author: Alexander Potapenko <glider@google.com> + * + */ +#ifndef _LINUX_KMSAN_STRING_H +#define _LINUX_KMSAN_STRING_H + +/* + * KMSAN overrides the default memcpy/memset/memmove implementations in the + * kernel, which requires having __msan_XXX function prototypes in several other + * headers. Keep them in one place instead of open-coding. + */ +void *__msan_memcpy(void *dst, const void *src, size_t size); +void *__msan_memset(void *s, int c, size_t n); +void *__msan_memmove(void *dest, const void *src, size_t len); + +#endif /* _LINUX_KMSAN_STRING_H */ diff --git a/include/linux/kmsan_types.h b/include/linux/kmsan_types.h new file mode 100644 index 000000000000..8bfa6c98176d --- /dev/null +++ b/include/linux/kmsan_types.h @@ -0,0 +1,35 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * A minimal header declaring types added by KMSAN to existing kernel structs. + * + * Copyright (C) 2017-2022 Google LLC + * Author: Alexander Potapenko <glider@google.com> + * + */ +#ifndef _LINUX_KMSAN_TYPES_H +#define _LINUX_KMSAN_TYPES_H + +/* These constants are defined in the MSan LLVM instrumentation pass. */ +#define KMSAN_RETVAL_SIZE 800 +#define KMSAN_PARAM_SIZE 800 + +struct kmsan_context_state { + char param_tls[KMSAN_PARAM_SIZE]; + char retval_tls[KMSAN_RETVAL_SIZE]; + char va_arg_tls[KMSAN_PARAM_SIZE]; + char va_arg_origin_tls[KMSAN_PARAM_SIZE]; + u64 va_arg_overflow_size_tls; + char param_origin_tls[KMSAN_PARAM_SIZE]; + u32 retval_origin_tls; +}; + +#undef KMSAN_PARAM_SIZE +#undef KMSAN_RETVAL_SIZE + +struct kmsan_ctx { + struct kmsan_context_state cstate; + int kmsan_in_runtime; + bool allow_reporting; +}; + +#endif /* _LINUX_KMSAN_TYPES_H */ diff --git a/include/linux/kobject.h b/include/linux/kobject.h index efd56f990a46..57fb972fea05 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -19,10 +19,10 @@ #include <linux/list.h> #include <linux/sysfs.h> #include <linux/compiler.h> +#include <linux/container_of.h> #include <linux/spinlock.h> #include <linux/kref.h> #include <linux/kobject_ns.h> -#include <linux/kernel.h> #include <linux/wait.h> #include <linux/atomic.h> #include <linux/workqueue.h> @@ -66,7 +66,7 @@ struct kobject { struct list_head entry; struct kobject *parent; struct kset *kset; - struct kobj_type *ktype; + const struct kobj_type *ktype; struct kernfs_node *sd; /* sysfs directory entry */ struct kref kref; #ifdef CONFIG_DEBUG_KOBJECT_RELEASE @@ -90,13 +90,13 @@ static inline const char *kobject_name(const struct kobject *kobj) return kobj->name; } -extern void kobject_init(struct kobject *kobj, struct kobj_type *ktype); +extern void kobject_init(struct kobject *kobj, const struct kobj_type *ktype); extern __printf(3, 4) __must_check int kobject_add(struct kobject *kobj, struct kobject *parent, const char *fmt, ...); extern __printf(4, 5) __must_check int kobject_init_and_add(struct kobject *kobj, - struct kobj_type *ktype, struct kobject *parent, + const struct kobj_type *ktype, struct kobject *parent, const char *fmt, ...); extern void kobject_del(struct kobject *kobj); @@ -117,27 +117,9 @@ extern void kobject_get_ownership(struct kobject *kobj, kuid_t *uid, kgid_t *gid); extern char *kobject_get_path(struct kobject *kobj, gfp_t flag); -/** - * kobject_has_children - Returns whether a kobject has children. - * @kobj: the object to test - * - * This will return whether a kobject has other kobjects as children. - * - * It does NOT account for the presence of attribute files, only sub - * directories. It also assumes there is no concurrent addition or - * removal of such children, and thus relies on external locking. - */ -static inline bool kobject_has_children(struct kobject *kobj) -{ - WARN_ON_ONCE(kref_read(&kobj->kref) == 0); - - return kobj->sd && kobj->sd->dir.subdirs; -} - struct kobj_type { void (*release)(struct kobject *kobj); const struct sysfs_ops *sysfs_ops; - struct attribute **default_attrs; /* use default_groups instead */ const struct attribute_group **default_groups; const struct kobj_ns_type_operations *(*child_ns_type)(struct kobject *kobj); const void *(*namespace)(struct kobject *kobj); @@ -153,10 +135,9 @@ struct kobj_uevent_env { }; struct kset_uevent_ops { - int (* const filter)(struct kset *kset, struct kobject *kobj); - const char *(* const name)(struct kset *kset, struct kobject *kobj); - int (* const uevent)(struct kset *kset, struct kobject *kobj, - struct kobj_uevent_env *env); + int (* const filter)(struct kobject *kobj); + const char *(* const name)(struct kobject *kobj); + int (* const uevent)(struct kobject *kobj, struct kobj_uevent_env *env); }; struct kobj_attribute { @@ -217,7 +198,7 @@ static inline void kset_put(struct kset *k) kobject_put(&k->kobj); } -static inline struct kobj_type *get_ktype(struct kobject *kobj) +static inline const struct kobj_type *get_ktype(struct kobject *kobj) { return kobj->ktype; } diff --git a/include/linux/kobject_api.h b/include/linux/kobject_api.h new file mode 100644 index 000000000000..6e36a054c2d6 --- /dev/null +++ b/include/linux/kobject_api.h @@ -0,0 +1 @@ +#include <linux/kobject.h> diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 8c8f7a4d93af..a0b92be98984 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -28,6 +28,7 @@ #include <linux/ftrace.h> #include <linux/refcount.h> #include <linux/freelist.h> +#include <linux/rethook.h> #include <asm/kprobes.h> #ifdef CONFIG_KPROBES @@ -102,6 +103,7 @@ struct kprobe { * this flag is only for optimized_kprobe. */ #define KPROBE_FLAG_FTRACE 8 /* probe is using ftrace */ +#define KPROBE_FLAG_ON_FUNC_ENTRY 16 /* probe is on the function entry */ /* Has this kprobe gone ? */ static inline bool kprobe_gone(struct kprobe *p) @@ -149,13 +151,20 @@ struct kretprobe { int maxactive; int nmissed; size_t data_size; +#ifdef CONFIG_KRETPROBE_ON_RETHOOK + struct rethook *rh; +#else struct freelist_head freelist; struct kretprobe_holder *rph; +#endif }; #define KRETPROBE_MAX_DATA_SIZE 4096 struct kretprobe_instance { +#ifdef CONFIG_KRETPROBE_ON_RETHOOK + struct rethook_node node; +#else union { struct freelist_node freelist; struct rcu_head rcu; @@ -164,6 +173,7 @@ struct kretprobe_instance { struct kretprobe_holder *rph; kprobe_opcode_t *ret_addr; void *fp; +#endif char data[]; }; @@ -186,10 +196,24 @@ extern void kprobe_busy_begin(void); extern void kprobe_busy_end(void); #ifdef CONFIG_KRETPROBES -extern void arch_prepare_kretprobe(struct kretprobe_instance *ri, - struct pt_regs *regs); +/* Check whether @p is used for implementing a trampoline. */ extern int arch_trampoline_kprobe(struct kprobe *p); +#ifdef CONFIG_KRETPROBE_ON_RETHOOK +static nokprobe_inline struct kretprobe *get_kretprobe(struct kretprobe_instance *ri) +{ + RCU_LOCKDEP_WARN(!rcu_read_lock_any_held(), + "Kretprobe is accessed from instance under preemptive context"); + + return (struct kretprobe *)READ_ONCE(ri->node.rethook->data); +} +static nokprobe_inline unsigned long get_kretprobe_retaddr(struct kretprobe_instance *ri) +{ + return ri->node.ret_addr; +} +#else +extern void arch_prepare_kretprobe(struct kretprobe_instance *ri, + struct pt_regs *regs); void arch_kretprobe_fixup_return(struct pt_regs *regs, kprobe_opcode_t *correct_ret_addr); @@ -232,6 +256,12 @@ static nokprobe_inline struct kretprobe *get_kretprobe(struct kretprobe_instance return READ_ONCE(ri->rph->rp); } +static nokprobe_inline unsigned long get_kretprobe_retaddr(struct kretprobe_instance *ri) +{ + return (unsigned long)ri->ret_addr; +} +#endif /* CONFIG_KRETPROBE_ON_RETHOOK */ + #else /* !CONFIG_KRETPROBES */ static inline void arch_prepare_kretprobe(struct kretprobe *rp, struct pt_regs *regs) @@ -265,7 +295,6 @@ extern int arch_init_kprobes(void); extern void kprobes_inc_nmissed_count(struct kprobe *p); extern bool arch_within_kprobe_blacklist(unsigned long addr); extern int arch_populate_kprobe_blacklist(void); -extern bool arch_kprobe_on_func_entry(unsigned long offset); extern int kprobe_on_func_entry(kprobe_opcode_t *addr, const char *sym, unsigned long offset); extern bool within_kprobe_blacklist(unsigned long addr); @@ -348,12 +377,6 @@ extern void opt_pre_handler(struct kprobe *p, struct pt_regs *regs); DEFINE_INSN_CACHE_OPS(optinsn); -#ifdef CONFIG_SYSCTL -extern int sysctl_kprobes_optimization; -extern int proc_kprobes_optimization_handler(struct ctl_table *table, - int write, void *buffer, - size_t *length, loff_t *ppos); -#endif /* CONFIG_SYSCTL */ extern void wait_for_kprobe_optimizer(void); #else /* !CONFIG_OPTPROBES */ static inline void wait_for_kprobe_optimizer(void) { } @@ -390,6 +413,8 @@ static inline struct kprobe_ctlblk *get_kprobe_ctlblk(void) } kprobe_opcode_t *kprobe_lookup_name(const char *name, unsigned int offset); +kprobe_opcode_t *arch_adjust_kprobe_addr(unsigned long addr, unsigned long offset, bool *on_func_entry); + int register_kprobe(struct kprobe *p); void unregister_kprobe(struct kprobe *p); int register_kprobes(struct kprobe **kps, int num); @@ -400,7 +425,11 @@ void unregister_kretprobe(struct kretprobe *rp); int register_kretprobes(struct kretprobe **rps, int num); void unregister_kretprobes(struct kretprobe **rps, int num); +#if defined(CONFIG_KRETPROBE_ON_RETHOOK) || !defined(CONFIG_KRETPROBES) +#define kprobe_flush_task(tk) do {} while (0) +#else void kprobe_flush_task(struct task_struct *tk); +#endif void kprobe_free_init_mem(void); @@ -433,6 +462,9 @@ static inline struct kprobe *kprobe_running(void) { return NULL; } +#define kprobe_busy_begin() do {} while (0) +#define kprobe_busy_end() do {} while (0) + static inline int register_kprobe(struct kprobe *p) { return -EOPNOTSUPP; @@ -511,6 +543,19 @@ static inline bool is_kprobe_optinsn_slot(unsigned long addr) #endif /* !CONFIG_OPTPROBES */ #ifdef CONFIG_KRETPROBES +#ifdef CONFIG_KRETPROBE_ON_RETHOOK +static nokprobe_inline bool is_kretprobe_trampoline(unsigned long addr) +{ + return is_rethook_trampoline(addr); +} + +static nokprobe_inline +unsigned long kretprobe_find_ret_addr(struct task_struct *tsk, void *fp, + struct llist_node **cur) +{ + return rethook_find_ret_addr(tsk, (unsigned long)fp, cur); +} +#else static nokprobe_inline bool is_kretprobe_trampoline(unsigned long addr) { return (void *)addr == kretprobe_trampoline_addr(); @@ -518,6 +563,7 @@ static nokprobe_inline bool is_kretprobe_trampoline(unsigned long addr) unsigned long kretprobe_find_ret_addr(struct task_struct *tsk, void *fp, struct llist_node **cur); +#endif #else static nokprobe_inline bool is_kretprobe_trampoline(unsigned long addr) { diff --git a/include/linux/kref_api.h b/include/linux/kref_api.h new file mode 100644 index 000000000000..d67e554721d2 --- /dev/null +++ b/include/linux/kref_api.h @@ -0,0 +1 @@ +#include <linux/kref.h> diff --git a/include/linux/ksm.h b/include/linux/ksm.h index a38a5bca1ba5..7e232ba59b86 100644 --- a/include/linux/ksm.h +++ b/include/linux/ksm.h @@ -15,9 +15,6 @@ #include <linux/sched.h> #include <linux/sched/coredump.h> -struct stable_node; -struct mem_cgroup; - #ifdef CONFIG_KSM int ksm_madvise(struct vm_area_struct *vma, unsigned long start, unsigned long end, int advice, unsigned long *vm_flags); @@ -51,7 +48,7 @@ static inline void ksm_exit(struct mm_struct *mm) struct page *ksm_might_need_to_copy(struct page *page, struct vm_area_struct *vma, unsigned long address); -void rmap_walk_ksm(struct page *page, struct rmap_walk_control *rwc); +void rmap_walk_ksm(struct folio *folio, struct rmap_walk_control *rwc); void folio_migrate_ksm(struct folio *newfolio, struct folio *folio); #else /* !CONFIG_KSM */ @@ -78,7 +75,7 @@ static inline struct page *ksm_might_need_to_copy(struct page *page, return page; } -static inline void rmap_walk_ksm(struct page *page, +static inline void rmap_walk_ksm(struct folio *folio, struct rmap_walk_control *rwc) { } diff --git a/include/linux/kthread.h b/include/linux/kthread.h index 346b0f269161..30e5bec81d2b 100644 --- a/include/linux/kthread.h +++ b/include/linux/kthread.h @@ -33,7 +33,8 @@ struct task_struct *kthread_create_on_cpu(int (*threadfn)(void *data), unsigned int cpu, const char *namefmt); -void set_kthread_struct(struct task_struct *p); +void get_kthread_comm(char *buf, size_t buf_size, struct task_struct *tsk); +bool set_kthread_struct(struct task_struct *p); void kthread_set_per_cpu(struct task_struct *k, int cpu); bool kthread_is_per_cpu(struct task_struct *k); @@ -56,6 +57,31 @@ bool kthread_is_per_cpu(struct task_struct *k); __k; \ }) +/** + * kthread_run_on_cpu - create and wake a cpu bound thread. + * @threadfn: the function to run until signal_pending(current). + * @data: data ptr for @threadfn. + * @cpu: The cpu on which the thread should be bound, + * @namefmt: printf-style name for the thread. Format is restricted + * to "name.*%u". Code fills in cpu number. + * + * Description: Convenient wrapper for kthread_create_on_cpu() + * followed by wake_up_process(). Returns the kthread or + * ERR_PTR(-ENOMEM). + */ +static inline struct task_struct * +kthread_run_on_cpu(int (*threadfn)(void *data), void *data, + unsigned int cpu, const char *namefmt) +{ + struct task_struct *p; + + p = kthread_create_on_cpu(threadfn, data, cpu, namefmt); + if (!IS_ERR(p)) + wake_up_process(p); + + return p; +} + void free_kthread_struct(struct task_struct *k); void kthread_bind(struct task_struct *k, unsigned int cpu); void kthread_bind_mask(struct task_struct *k, const struct cpumask *mask); @@ -70,6 +96,8 @@ void *kthread_probe_data(struct task_struct *k); int kthread_park(struct task_struct *k); void kthread_unpark(struct task_struct *k); void kthread_parkme(void); +void kthread_exit(long result) __noreturn; +void kthread_complete_and_exit(struct completion *, long) __noreturn; int kthreadd(void *unused); extern struct task_struct *kthreadd_task; @@ -113,12 +141,6 @@ struct kthread_delayed_work { struct timer_list timer; }; -#define KTHREAD_WORKER_INIT(worker) { \ - .lock = __RAW_SPIN_LOCK_UNLOCKED((worker).lock), \ - .work_list = LIST_HEAD_INIT((worker).work_list), \ - .delayed_work_list = LIST_HEAD_INIT((worker).delayed_work_list),\ - } - #define KTHREAD_WORK_INIT(work, fn) { \ .node = LIST_HEAD_INIT((work).node), \ .func = (fn), \ @@ -130,9 +152,6 @@ struct kthread_delayed_work { TIMER_IRQSAFE), \ } -#define DEFINE_KTHREAD_WORKER(worker) \ - struct kthread_worker worker = KTHREAD_WORKER_INIT(worker) - #define DEFINE_KTHREAD_WORK(work, fn) \ struct kthread_work work = KTHREAD_WORK_INIT(work, fn) @@ -140,19 +159,6 @@ struct kthread_delayed_work { struct kthread_delayed_work dwork = \ KTHREAD_DELAYED_WORK_INIT(dwork, fn) -/* - * kthread_worker.lock needs its own lockdep class key when defined on - * stack with lockdep enabled. Use the following macros in such cases. - */ -#ifdef CONFIG_LOCKDEP -# define KTHREAD_WORKER_INIT_ONSTACK(worker) \ - ({ kthread_init_worker(&worker); worker; }) -# define DEFINE_KTHREAD_WORKER_ONSTACK(worker) \ - struct kthread_worker worker = KTHREAD_WORKER_INIT_ONSTACK(worker) -#else -# define DEFINE_KTHREAD_WORKER_ONSTACK(worker) DEFINE_KTHREAD_WORKER(worker) -#endif - extern void __kthread_init_worker(struct kthread_worker *worker, const char *name, struct lock_class_key *key); @@ -216,9 +222,5 @@ void kthread_associate_blkcg(struct cgroup_subsys_state *css); struct cgroup_subsys_state *kthread_blkcg(void); #else static inline void kthread_associate_blkcg(struct cgroup_subsys_state *css) { } -static inline struct cgroup_subsys_state *kthread_blkcg(void) -{ - return NULL; -} #endif #endif /* _LINUX_KTHREAD_H */ diff --git a/include/linux/ktime_api.h b/include/linux/ktime_api.h new file mode 100644 index 000000000000..f697d493960f --- /dev/null +++ b/include/linux/ktime_api.h @@ -0,0 +1 @@ +#include <linux/ktime.h> diff --git a/include/linux/kvm_dirty_ring.h b/include/linux/kvm_dirty_ring.h index 120e5e90fa1d..906f899813dc 100644 --- a/include/linux/kvm_dirty_ring.h +++ b/include/linux/kvm_dirty_ring.h @@ -27,9 +27,9 @@ struct kvm_dirty_ring { int index; }; -#if (KVM_DIRTY_LOG_PAGE_OFFSET == 0) +#ifndef CONFIG_HAVE_KVM_DIRTY_RING /* - * If KVM_DIRTY_LOG_PAGE_OFFSET not defined, kvm_dirty_ring.o should + * If CONFIG_HAVE_HVM_DIRTY_RING not defined, kvm_dirty_ring.o should * not be included as well, so define these nop functions for the arch. */ static inline u32 kvm_dirty_ring_get_rsvd_entries(void) @@ -43,11 +43,6 @@ static inline int kvm_dirty_ring_alloc(struct kvm_dirty_ring *ring, return 0; } -static inline struct kvm_dirty_ring *kvm_dirty_ring_get(struct kvm *kvm) -{ - return NULL; -} - static inline int kvm_dirty_ring_reset(struct kvm *kvm, struct kvm_dirty_ring *ring) { @@ -74,11 +69,10 @@ static inline bool kvm_dirty_ring_soft_full(struct kvm_dirty_ring *ring) return true; } -#else /* KVM_DIRTY_LOG_PAGE_OFFSET == 0 */ +#else /* CONFIG_HAVE_KVM_DIRTY_RING */ u32 kvm_dirty_ring_get_rsvd_entries(void); int kvm_dirty_ring_alloc(struct kvm_dirty_ring *ring, int index, u32 size); -struct kvm_dirty_ring *kvm_dirty_ring_get(struct kvm *kvm); /* * called with kvm->slots_lock held, returns the number of @@ -98,6 +92,6 @@ struct page *kvm_dirty_ring_get_page(struct kvm_dirty_ring *ring, u32 offset); void kvm_dirty_ring_free(struct kvm_dirty_ring *ring); bool kvm_dirty_ring_soft_full(struct kvm_dirty_ring *ring); -#endif /* KVM_DIRTY_LOG_PAGE_OFFSET == 0 */ +#endif /* CONFIG_HAVE_KVM_DIRTY_RING */ #endif /* KVM_DIRTY_RING_H */ diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index c310648cc8f1..18592bdf4c1b 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -29,6 +29,12 @@ #include <linux/refcount.h> #include <linux/nospec.h> #include <linux/notifier.h> +#include <linux/ftrace.h> +#include <linux/hashtable.h> +#include <linux/instrumentation.h> +#include <linux/interval_tree.h> +#include <linux/rbtree.h> +#include <linux/xarray.h> #include <asm/signal.h> #include <linux/kvm.h> @@ -142,17 +148,26 @@ static inline bool is_error_page(struct page *page) #define KVM_REQUEST_MASK GENMASK(7,0) #define KVM_REQUEST_NO_WAKEUP BIT(8) #define KVM_REQUEST_WAIT BIT(9) +#define KVM_REQUEST_NO_ACTION BIT(10) /* * Architecture-independent vcpu->requests bit members - * Bits 4-7 are reserved for more arch-independent bits. + * Bits 3-7 are reserved for more arch-independent bits. */ #define KVM_REQ_TLB_FLUSH (0 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) -#define KVM_REQ_MMU_RELOAD (1 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) +#define KVM_REQ_VM_DEAD (1 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQ_UNBLOCK 2 -#define KVM_REQ_UNHALT 3 -#define KVM_REQ_VM_DEAD (4 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQUEST_ARCH_BASE 8 +/* + * KVM_REQ_OUTSIDE_GUEST_MODE exists is purely as way to force the vCPU to + * OUTSIDE_GUEST_MODE. KVM_REQ_OUTSIDE_GUEST_MODE differs from a vCPU "kick" + * in that it ensures the vCPU has reached OUTSIDE_GUEST_MODE before continuing + * on. A kick only guarantees that the vCPU is on its way out, e.g. a previous + * kick may have set vcpu->mode to EXITING_GUEST_MODE, and so there's no + * guarantee the vCPU received an IPI and has actually exited guest mode. + */ +#define KVM_REQ_OUTSIDE_GUEST_MODE (KVM_REQUEST_NO_ACTION | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) + #define KVM_ARCH_REQ_FLAGS(nr, flags) ({ \ BUILD_BUG_ON((unsigned)(nr) >= (sizeof_field(struct kvm_vcpu, requests) * 8) - KVM_REQUEST_ARCH_BASE); \ (unsigned)(((nr) + KVM_REQUEST_ARCH_BASE) | (flags)); \ @@ -299,18 +314,20 @@ struct kvm_vcpu { int cpu; int vcpu_id; /* id given by userspace at creation */ int vcpu_idx; /* index in kvm->vcpus array */ - int srcu_idx; + int ____srcu_idx; /* Don't use this directly. You've been warned. */ +#ifdef CONFIG_PROVE_RCU + int srcu_depth; +#endif int mode; u64 requests; unsigned long guest_debug; - int pre_pcpu; - struct list_head blocked_vcpu_list; - struct mutex mutex; struct kvm_run *run; +#ifndef __KVM_HAVE_ARCH_WQP struct rcuwait wait; +#endif struct pid __rcu *pid; int sigset_active; sigset_t sigset; @@ -355,15 +372,20 @@ struct kvm_vcpu { struct kvm_dirty_ring dirty_ring; /* - * The index of the most recently used memslot by this vCPU. It's ok - * if this becomes stale due to memslot changes since we always check - * it is a valid slot. + * The most recently used memslot by this vCPU and the slots generation + * for which it is valid. + * No wraparound protection is needed since generations won't overflow in + * thousands of years, even assuming 1M memslot operations per second. */ - int last_used_slot; + struct kvm_memory_slot *last_used_slot; + u64 last_used_slot_gen; }; -/* must be called with irqs disabled */ -static __always_inline void guest_enter_irqoff(void) +/* + * Start accounting time towards a guest. + * Must be called before entering guest context. + */ +static __always_inline void guest_timing_enter_irqoff(void) { /* * This is running in ioctl context so its safe to assume that it's the @@ -372,7 +394,18 @@ static __always_inline void guest_enter_irqoff(void) instrumentation_begin(); vtime_account_guest_enter(); instrumentation_end(); +} +/* + * Enter guest context and enter an RCU extended quiescent state. + * + * Between guest_context_enter_irqoff() and guest_context_exit_irqoff() it is + * unsafe to use any code which may directly or indirectly use RCU, tracing + * (including IRQ flag tracing), or lockdep. All code in this period must be + * non-instrumentable. + */ +static __always_inline void guest_context_enter_irqoff(void) +{ /* * KVM does not hold any references to rcu protected data when it * switches CPU into a guest mode. In fact switching to a guest mode @@ -388,16 +421,79 @@ static __always_inline void guest_enter_irqoff(void) } } -static __always_inline void guest_exit_irqoff(void) +/* + * Deprecated. Architectures should move to guest_timing_enter_irqoff() and + * guest_state_enter_irqoff(). + */ +static __always_inline void guest_enter_irqoff(void) +{ + guest_timing_enter_irqoff(); + guest_context_enter_irqoff(); +} + +/** + * guest_state_enter_irqoff - Fixup state when entering a guest + * + * Entry to a guest will enable interrupts, but the kernel state is interrupts + * disabled when this is invoked. Also tell RCU about it. + * + * 1) Trace interrupts on state + * 2) Invoke context tracking if enabled to adjust RCU state + * 3) Tell lockdep that interrupts are enabled + * + * Invoked from architecture specific code before entering a guest. + * Must be called with interrupts disabled and the caller must be + * non-instrumentable. + * The caller has to invoke guest_timing_enter_irqoff() before this. + * + * Note: this is analogous to exit_to_user_mode(). + */ +static __always_inline void guest_state_enter_irqoff(void) +{ + instrumentation_begin(); + trace_hardirqs_on_prepare(); + lockdep_hardirqs_on_prepare(); + instrumentation_end(); + + guest_context_enter_irqoff(); + lockdep_hardirqs_on(CALLER_ADDR0); +} + +/* + * Exit guest context and exit an RCU extended quiescent state. + * + * Between guest_context_enter_irqoff() and guest_context_exit_irqoff() it is + * unsafe to use any code which may directly or indirectly use RCU, tracing + * (including IRQ flag tracing), or lockdep. All code in this period must be + * non-instrumentable. + */ +static __always_inline void guest_context_exit_irqoff(void) { context_tracking_guest_exit(); +} +/* + * Stop accounting time towards a guest. + * Must be called after exiting guest context. + */ +static __always_inline void guest_timing_exit_irqoff(void) +{ instrumentation_begin(); /* Flush the guest cputime we spent on the guest */ vtime_account_guest_exit(); instrumentation_end(); } +/* + * Deprecated. Architectures should move to guest_state_exit_irqoff() and + * guest_timing_exit_irqoff(). + */ +static __always_inline void guest_exit_irqoff(void) +{ + guest_context_exit_irqoff(); + guest_timing_exit_irqoff(); +} + static inline void guest_exit(void) { unsigned long flags; @@ -407,6 +503,33 @@ static inline void guest_exit(void) local_irq_restore(flags); } +/** + * guest_state_exit_irqoff - Establish state when returning from guest mode + * + * Entry from a guest disables interrupts, but guest mode is traced as + * interrupts enabled. Also with NO_HZ_FULL RCU might be idle. + * + * 1) Tell lockdep that interrupts are disabled + * 2) Invoke context tracking if enabled to reactivate RCU + * 3) Trace interrupts off state + * + * Invoked from architecture specific code after exiting a guest. + * Must be invoked with interrupts disabled and the caller must be + * non-instrumentable. + * The caller has to invoke guest_timing_exit_irqoff() after this. + * + * Note: this is analogous to enter_from_user_mode(). + */ +static __always_inline void guest_state_exit_irqoff(void) +{ + lockdep_hardirqs_off(CALLER_ADDR0); + guest_context_exit_irqoff(); + + instrumentation_begin(); + trace_hardirqs_off_finish(); + instrumentation_end(); +} + static inline int kvm_vcpu_exiting_guest_mode(struct kvm_vcpu *vcpu) { /* @@ -424,7 +547,26 @@ static inline int kvm_vcpu_exiting_guest_mode(struct kvm_vcpu *vcpu) */ #define KVM_MEM_MAX_NR_PAGES ((1UL << 31) - 1) +/* + * Since at idle each memslot belongs to two memslot sets it has to contain + * two embedded nodes for each data structure that it forms a part of. + * + * Two memslot sets (one active and one inactive) are necessary so the VM + * continues to run on one memslot set while the other is being modified. + * + * These two memslot sets normally point to the same set of memslots. + * They can, however, be desynchronized when performing a memslot management + * operation by replacing the memslot to be modified by its copy. + * After the operation is complete, both memslot sets once again point to + * the same, common set of memslot data. + * + * The memslots themselves are independent of each other so they can be + * individually added or deleted. + */ struct kvm_memory_slot { + struct hlist_node id_node[2]; + struct interval_tree_node hva_node[2]; + struct rb_node gfn_node[2]; gfn_t base_gfn; unsigned long npages; unsigned long *dirty_bitmap; @@ -435,7 +577,7 @@ struct kvm_memory_slot { u16 as_id; }; -static inline bool kvm_slot_dirty_track_enabled(struct kvm_memory_slot *slot) +static inline bool kvm_slot_dirty_track_enabled(const struct kvm_memory_slot *slot) { return slot->flags & KVM_MEM_LOG_DIRTY_PAGES; } @@ -469,6 +611,13 @@ struct kvm_hv_sint { u32 sint; }; +struct kvm_xen_evtchn { + u32 port; + u32 vcpu_id; + int vcpu_idx; + u32 priority; +}; + struct kvm_kernel_irq_routing_entry { u32 gsi; u32 type; @@ -489,6 +638,7 @@ struct kvm_kernel_irq_routing_entry { } msi; struct kvm_s390_adapter_int adapter; struct kvm_hv_sint hv_sint; + struct kvm_xen_evtchn xen_evtchn; }; struct hlist_node link; }; @@ -505,12 +655,12 @@ struct kvm_irq_routing_table { }; #endif -#ifndef KVM_PRIVATE_MEM_SLOTS -#define KVM_PRIVATE_MEM_SLOTS 0 +#ifndef KVM_INTERNAL_MEM_SLOTS +#define KVM_INTERNAL_MEM_SLOTS 0 #endif #define KVM_MEM_SLOTS_NUM SHRT_MAX -#define KVM_USER_MEM_SLOTS (KVM_MEM_SLOTS_NUM - KVM_PRIVATE_MEM_SLOTS) +#define KVM_USER_MEM_SLOTS (KVM_MEM_SLOTS_NUM - KVM_INTERNAL_MEM_SLOTS) #ifndef __KVM_VCPU_MULTIPLE_ADDRESS_SPACE static inline int kvm_arch_vcpu_memslots_id(struct kvm_vcpu *vcpu) @@ -519,18 +669,21 @@ static inline int kvm_arch_vcpu_memslots_id(struct kvm_vcpu *vcpu) } #endif -/* - * Note: - * memslots are not sorted by id anymore, please use id_to_memslot() - * to get the memslot by its id. - */ struct kvm_memslots { u64 generation; - /* The mapping table from slot id to the index in memslots[]. */ - short id_to_index[KVM_MEM_SLOTS_NUM]; - atomic_t last_used_slot; - int used_slots; - struct kvm_memory_slot memslots[]; + atomic_long_t last_used_slot; + struct rb_root_cached hva_tree; + struct rb_root gfn_tree; + /* + * The mapping table from slot id to memslot. + * + * 7-bit bucket count matches the size of the old id to index array for + * 512 slots, while giving good performance with this slot count. + * Higher bucket counts bring only small performance improvements but + * always result in higher memory usage (even for lower memslot counts). + */ + DECLARE_HASHTABLE(id_hash, 7); + int node_idx; }; struct kvm { @@ -551,14 +704,22 @@ struct kvm { */ struct mutex slots_arch_lock; struct mm_struct *mm; /* userspace tied to this vm */ + unsigned long nr_memslot_pages; + /* The two memslot sets - active and inactive (per address space) */ + struct kvm_memslots __memslots[KVM_ADDRESS_SPACE_NUM][2]; + /* The current active memslot set for each address space */ struct kvm_memslots __rcu *memslots[KVM_ADDRESS_SPACE_NUM]; - struct kvm_vcpu *vcpus[KVM_MAX_VCPUS]; + struct xarray vcpu_array; /* Used to wait for completion of MMU notifiers. */ spinlock_t mn_invalidate_lock; unsigned long mn_active_invalidate_count; struct rcuwait mn_memslots_update_rcuwait; + /* For management / invalidation of gfn_to_pfn_caches */ + spinlock_t gpc_lock; + struct list_head gpc_list; + /* * created_vcpus is protected by kvm->lock, and is incremented * at the beginning of KVM_CREATE_VCPU. online_vcpus is only @@ -566,6 +727,7 @@ struct kvm { * and is accessed atomically. */ atomic_t online_vcpus; + int max_vcpus; int created_vcpus; int last_boosted_vcpu; struct list_head vm_list; @@ -602,10 +764,10 @@ struct kvm { #if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER) struct mmu_notifier mmu_notifier; - unsigned long mmu_notifier_seq; - long mmu_notifier_count; - unsigned long mmu_notifier_range_start; - unsigned long mmu_notifier_range_end; + unsigned long mmu_invalidate_seq; + long mmu_invalidate_in_progress; + unsigned long mmu_invalidate_range_start; + unsigned long mmu_invalidate_range_end; #endif struct list_head devices; u64 manual_dirty_log_protect; @@ -682,6 +844,25 @@ static inline void kvm_vm_bugged(struct kvm *kvm) unlikely(__ret); \ }) +static inline void kvm_vcpu_srcu_read_lock(struct kvm_vcpu *vcpu) +{ +#ifdef CONFIG_PROVE_RCU + WARN_ONCE(vcpu->srcu_depth++, + "KVM: Illegal vCPU srcu_idx LOCK, depth=%d", vcpu->srcu_depth - 1); +#endif + vcpu->____srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); +} + +static inline void kvm_vcpu_srcu_read_unlock(struct kvm_vcpu *vcpu) +{ + srcu_read_unlock(&vcpu->kvm->srcu, vcpu->____srcu_idx); + +#ifdef CONFIG_PROVE_RCU + WARN_ONCE(--vcpu->srcu_depth, + "KVM: Illegal vCPU srcu_idx UNLOCK, depth=%d", vcpu->srcu_depth); +#endif +} + static inline bool kvm_dirty_log_manual_protect_and_init_set(struct kvm *kvm) { return !!(kvm->manual_dirty_log_protect & KVM_DIRTY_LOG_INITIALLY_SET); @@ -701,19 +882,17 @@ static inline struct kvm_vcpu *kvm_get_vcpu(struct kvm *kvm, int i) /* Pairs with smp_wmb() in kvm_vm_ioctl_create_vcpu. */ smp_rmb(); - return kvm->vcpus[i]; + return xa_load(&kvm->vcpu_array, i); } -#define kvm_for_each_vcpu(idx, vcpup, kvm) \ - for (idx = 0; \ - idx < atomic_read(&kvm->online_vcpus) && \ - (vcpup = kvm_get_vcpu(kvm, idx)) != NULL; \ - idx++) +#define kvm_for_each_vcpu(idx, vcpup, kvm) \ + xa_for_each_range(&kvm->vcpu_array, idx, vcpup, 0, \ + (atomic_read(&kvm->online_vcpus) - 1)) static inline struct kvm_vcpu *kvm_get_vcpu_by_id(struct kvm *kvm, int id) { struct kvm_vcpu *vcpu = NULL; - int i; + unsigned long i; if (id < 0) return NULL; @@ -727,13 +906,7 @@ static inline struct kvm_vcpu *kvm_get_vcpu_by_id(struct kvm *kvm, int id) return NULL; } -#define kvm_for_each_memslot(memslot, slots) \ - for (memslot = &slots->memslots[0]; \ - memslot < slots->memslots + slots->used_slots; memslot++) \ - if (WARN_ON_ONCE(!memslot->npages)) { \ - } else - -void kvm_vcpu_destroy(struct kvm_vcpu *vcpu); +void kvm_destroy_vcpus(struct kvm *kvm); void vcpu_load(struct kvm_vcpu *vcpu); void vcpu_put(struct kvm_vcpu *vcpu); @@ -793,21 +966,124 @@ static inline struct kvm_memslots *kvm_vcpu_memslots(struct kvm_vcpu *vcpu) return __kvm_memslots(vcpu->kvm, as_id); } +static inline bool kvm_memslots_empty(struct kvm_memslots *slots) +{ + return RB_EMPTY_ROOT(&slots->gfn_tree); +} + +#define kvm_for_each_memslot(memslot, bkt, slots) \ + hash_for_each(slots->id_hash, bkt, memslot, id_node[slots->node_idx]) \ + if (WARN_ON_ONCE(!memslot->npages)) { \ + } else + static inline struct kvm_memory_slot *id_to_memslot(struct kvm_memslots *slots, int id) { - int index = slots->id_to_index[id]; struct kvm_memory_slot *slot; + int idx = slots->node_idx; - if (index < 0) - return NULL; + hash_for_each_possible(slots->id_hash, slot, id_node[idx], id) { + if (slot->id == id) + return slot; + } - slot = &slots->memslots[index]; + return NULL; +} + +/* Iterator used for walking memslots that overlap a gfn range. */ +struct kvm_memslot_iter { + struct kvm_memslots *slots; + struct rb_node *node; + struct kvm_memory_slot *slot; +}; + +static inline void kvm_memslot_iter_next(struct kvm_memslot_iter *iter) +{ + iter->node = rb_next(iter->node); + if (!iter->node) + return; - WARN_ON(slot->id != id); - return slot; + iter->slot = container_of(iter->node, struct kvm_memory_slot, gfn_node[iter->slots->node_idx]); } +static inline void kvm_memslot_iter_start(struct kvm_memslot_iter *iter, + struct kvm_memslots *slots, + gfn_t start) +{ + int idx = slots->node_idx; + struct rb_node *tmp; + struct kvm_memory_slot *slot; + + iter->slots = slots; + + /* + * Find the so called "upper bound" of a key - the first node that has + * its key strictly greater than the searched one (the start gfn in our case). + */ + iter->node = NULL; + for (tmp = slots->gfn_tree.rb_node; tmp; ) { + slot = container_of(tmp, struct kvm_memory_slot, gfn_node[idx]); + if (start < slot->base_gfn) { + iter->node = tmp; + tmp = tmp->rb_left; + } else { + tmp = tmp->rb_right; + } + } + + /* + * Find the slot with the lowest gfn that can possibly intersect with + * the range, so we'll ideally have slot start <= range start + */ + if (iter->node) { + /* + * A NULL previous node means that the very first slot + * already has a higher start gfn. + * In this case slot start > range start. + */ + tmp = rb_prev(iter->node); + if (tmp) + iter->node = tmp; + } else { + /* a NULL node below means no slots */ + iter->node = rb_last(&slots->gfn_tree); + } + + if (iter->node) { + iter->slot = container_of(iter->node, struct kvm_memory_slot, gfn_node[idx]); + + /* + * It is possible in the slot start < range start case that the + * found slot ends before or at range start (slot end <= range start) + * and so it does not overlap the requested range. + * + * In such non-overlapping case the next slot (if it exists) will + * already have slot start > range start, otherwise the logic above + * would have found it instead of the current slot. + */ + if (iter->slot->base_gfn + iter->slot->npages <= start) + kvm_memslot_iter_next(iter); + } +} + +static inline bool kvm_memslot_iter_is_valid(struct kvm_memslot_iter *iter, gfn_t end) +{ + if (!iter->node) + return false; + + /* + * If this slot starts beyond or at the end of the range so does + * every next one + */ + return iter->slot->base_gfn < end; +} + +/* Iterate over each memslot at least partially intersecting [start, end) range */ +#define kvm_for_each_memslot_in_gfn_range(iter, slots, start, end) \ + for (kvm_memslot_iter_start(iter, slots, start); \ + kvm_memslot_iter_is_valid(iter, end); \ + kvm_memslot_iter_next(iter)) + /* * KVM_SET_USER_MEMORY_REGION ioctl allows the following operations: * - create a new memory slot @@ -833,11 +1109,10 @@ int __kvm_set_memory_region(struct kvm *kvm, void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot); void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen); int kvm_arch_prepare_memory_region(struct kvm *kvm, - struct kvm_memory_slot *memslot, - const struct kvm_userspace_memory_region *mem, + const struct kvm_memory_slot *old, + struct kvm_memory_slot *new, enum kvm_mr_change change); void kvm_arch_commit_memory_region(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem, struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change); @@ -858,14 +1133,13 @@ unsigned long gfn_to_hva_memslot_prot(struct kvm_memory_slot *slot, gfn_t gfn, bool *writable); void kvm_release_page_clean(struct page *page); void kvm_release_page_dirty(struct page *page); -void kvm_set_page_accessed(struct page *page); kvm_pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn); kvm_pfn_t gfn_to_pfn_prot(struct kvm *kvm, gfn_t gfn, bool write_fault, bool *writable); -kvm_pfn_t gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn); -kvm_pfn_t gfn_to_pfn_memslot_atomic(struct kvm_memory_slot *slot, gfn_t gfn); -kvm_pfn_t __gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn, +kvm_pfn_t gfn_to_pfn_memslot(const struct kvm_memory_slot *slot, gfn_t gfn); +kvm_pfn_t gfn_to_pfn_memslot_atomic(const struct kvm_memory_slot *slot, gfn_t gfn); +kvm_pfn_t __gfn_to_pfn_memslot(const struct kvm_memory_slot *slot, gfn_t gfn, bool atomic, bool *async, bool write_fault, bool *writable, hva_t *hva); @@ -942,7 +1216,7 @@ struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn); bool kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn); bool kvm_vcpu_is_visible_gfn(struct kvm_vcpu *vcpu, gfn_t gfn); unsigned long kvm_host_page_size(struct kvm_vcpu *vcpu, gfn_t gfn); -void mark_page_dirty_in_slot(struct kvm *kvm, struct kvm_memory_slot *memslot, gfn_t gfn); +void mark_page_dirty_in_slot(struct kvm *kvm, const struct kvm_memory_slot *memslot, gfn_t gfn); void mark_page_dirty(struct kvm *kvm, gfn_t gfn); struct kvm_memslots *kvm_vcpu_memslots(struct kvm_vcpu *vcpu); @@ -950,7 +1224,6 @@ struct kvm_memory_slot *kvm_vcpu_gfn_to_memslot(struct kvm_vcpu *vcpu, gfn_t gfn kvm_pfn_t kvm_vcpu_gfn_to_pfn_atomic(struct kvm_vcpu *vcpu, gfn_t gfn); kvm_pfn_t kvm_vcpu_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn); int kvm_vcpu_map(struct kvm_vcpu *vcpu, gpa_t gpa, struct kvm_host_map *map); -struct page *kvm_vcpu_gfn_to_page(struct kvm_vcpu *vcpu, gfn_t gfn); void kvm_vcpu_unmap(struct kvm_vcpu *vcpu, struct kvm_host_map *map, bool dirty); unsigned long kvm_vcpu_gfn_to_hva(struct kvm_vcpu *vcpu, gfn_t gfn); unsigned long kvm_vcpu_gfn_to_hva_prot(struct kvm_vcpu *vcpu, gfn_t gfn, bool *writable); @@ -966,10 +1239,116 @@ int kvm_vcpu_write_guest(struct kvm_vcpu *vcpu, gpa_t gpa, const void *data, unsigned long len); void kvm_vcpu_mark_page_dirty(struct kvm_vcpu *vcpu, gfn_t gfn); +/** + * kvm_gpc_init - initialize gfn_to_pfn_cache. + * + * @gpc: struct gfn_to_pfn_cache object. + * + * This sets up a gfn_to_pfn_cache by initializing locks. Note, the cache must + * be zero-allocated (or zeroed by the caller before init). + */ +void kvm_gpc_init(struct gfn_to_pfn_cache *gpc); + +/** + * kvm_gpc_activate - prepare a cached kernel mapping and HPA for a given guest + * physical address. + * + * @kvm: pointer to kvm instance. + * @gpc: struct gfn_to_pfn_cache object. + * @vcpu: vCPU to be used for marking pages dirty and to be woken on + * invalidation. + * @usage: indicates if the resulting host physical PFN is used while + * the @vcpu is IN_GUEST_MODE (in which case invalidation of + * the cache from MMU notifiers---but not for KVM memslot + * changes!---will also force @vcpu to exit the guest and + * refresh the cache); and/or if the PFN used directly + * by KVM (and thus needs a kernel virtual mapping). + * @gpa: guest physical address to map. + * @len: sanity check; the range being access must fit a single page. + * + * @return: 0 for success. + * -EINVAL for a mapping which would cross a page boundary. + * -EFAULT for an untranslatable guest physical address. + * + * This primes a gfn_to_pfn_cache and links it into the @kvm's list for + * invalidations to be processed. Callers are required to use + * kvm_gfn_to_pfn_cache_check() to ensure that the cache is valid before + * accessing the target page. + */ +int kvm_gpc_activate(struct kvm *kvm, struct gfn_to_pfn_cache *gpc, + struct kvm_vcpu *vcpu, enum pfn_cache_usage usage, + gpa_t gpa, unsigned long len); + +/** + * kvm_gfn_to_pfn_cache_check - check validity of a gfn_to_pfn_cache. + * + * @kvm: pointer to kvm instance. + * @gpc: struct gfn_to_pfn_cache object. + * @gpa: current guest physical address to map. + * @len: sanity check; the range being access must fit a single page. + * + * @return: %true if the cache is still valid and the address matches. + * %false if the cache is not valid. + * + * Callers outside IN_GUEST_MODE context should hold a read lock on @gpc->lock + * while calling this function, and then continue to hold the lock until the + * access is complete. + * + * Callers in IN_GUEST_MODE may do so without locking, although they should + * still hold a read lock on kvm->scru for the memslot checks. + */ +bool kvm_gfn_to_pfn_cache_check(struct kvm *kvm, struct gfn_to_pfn_cache *gpc, + gpa_t gpa, unsigned long len); + +/** + * kvm_gfn_to_pfn_cache_refresh - update a previously initialized cache. + * + * @kvm: pointer to kvm instance. + * @gpc: struct gfn_to_pfn_cache object. + * @gpa: updated guest physical address to map. + * @len: sanity check; the range being access must fit a single page. + * + * @return: 0 for success. + * -EINVAL for a mapping which would cross a page boundary. + * -EFAULT for an untranslatable guest physical address. + * + * This will attempt to refresh a gfn_to_pfn_cache. Note that a successful + * returm from this function does not mean the page can be immediately + * accessed because it may have raced with an invalidation. Callers must + * still lock and check the cache status, as this function does not return + * with the lock still held to permit access. + */ +int kvm_gfn_to_pfn_cache_refresh(struct kvm *kvm, struct gfn_to_pfn_cache *gpc, + gpa_t gpa, unsigned long len); + +/** + * kvm_gfn_to_pfn_cache_unmap - temporarily unmap a gfn_to_pfn_cache. + * + * @kvm: pointer to kvm instance. + * @gpc: struct gfn_to_pfn_cache object. + * + * This unmaps the referenced page. The cache is left in the invalid state + * but at least the mapping from GPA to userspace HVA will remain cached + * and can be reused on a subsequent refresh. + */ +void kvm_gfn_to_pfn_cache_unmap(struct kvm *kvm, struct gfn_to_pfn_cache *gpc); + +/** + * kvm_gpc_deactivate - deactivate and unlink a gfn_to_pfn_cache. + * + * @kvm: pointer to kvm instance. + * @gpc: struct gfn_to_pfn_cache object. + * + * This removes a cache from the @kvm's list to be processed on MMU notifier + * invocation. + */ +void kvm_gpc_deactivate(struct kvm *kvm, struct gfn_to_pfn_cache *gpc); + void kvm_sigset_activate(struct kvm_vcpu *vcpu); void kvm_sigset_deactivate(struct kvm_vcpu *vcpu); -void kvm_vcpu_block(struct kvm_vcpu *vcpu); +void kvm_vcpu_halt(struct kvm_vcpu *vcpu); +bool kvm_vcpu_block(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu); bool kvm_vcpu_wake_up(struct kvm_vcpu *vcpu); @@ -978,19 +1357,19 @@ int kvm_vcpu_yield_to(struct kvm_vcpu *target); void kvm_vcpu_on_spin(struct kvm_vcpu *vcpu, bool usermode_vcpu_not_eligible); void kvm_flush_remote_tlbs(struct kvm *kvm); -void kvm_reload_remote_mmus(struct kvm *kvm); #ifdef KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE int kvm_mmu_topup_memory_cache(struct kvm_mmu_memory_cache *mc, int min); +int __kvm_mmu_topup_memory_cache(struct kvm_mmu_memory_cache *mc, int capacity, int min); int kvm_mmu_memory_cache_nr_free_objects(struct kvm_mmu_memory_cache *mc); void kvm_mmu_free_memory_cache(struct kvm_mmu_memory_cache *mc); void *kvm_mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc); #endif -void kvm_inc_notifier_count(struct kvm *kvm, unsigned long start, - unsigned long end); -void kvm_dec_notifier_count(struct kvm *kvm, unsigned long start, - unsigned long end); +void kvm_mmu_invalidate_begin(struct kvm *kvm, unsigned long start, + unsigned long end); +void kvm_mmu_invalidate_end(struct kvm *kvm, unsigned long start, + unsigned long end); long kvm_arch_dev_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg); @@ -1021,6 +1400,8 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap); long kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg); +long kvm_arch_vm_compat_ioctl(struct file *filp, unsigned int ioctl, + unsigned long arg); int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu); int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu); @@ -1060,6 +1441,8 @@ int kvm_arch_pm_notifier(struct kvm *kvm, unsigned long state); #ifdef __KVM_HAVE_ARCH_VCPU_DEBUGFS void kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu, struct dentry *debugfs_dentry); +#else +static inline void kvm_create_vcpu_debugfs(struct kvm_vcpu *vcpu) {} #endif int kvm_arch_hardware_enable(void); @@ -1137,7 +1520,7 @@ static inline void kvm_arch_end_assignment(struct kvm *kvm) { } -static inline bool kvm_arch_has_assigned_device(struct kvm *kvm) +static __always_inline bool kvm_arch_has_assigned_device(struct kvm *kvm) { return false; } @@ -1152,6 +1535,20 @@ static inline struct rcuwait *kvm_arch_vcpu_get_wait(struct kvm_vcpu *vcpu) #endif } +/* + * Wake a vCPU if necessary, but don't do any stats/metadata updates. Returns + * true if the vCPU was blocking and was awakened, false otherwise. + */ +static inline bool __kvm_vcpu_wake_up(struct kvm_vcpu *vcpu) +{ + return !!rcuwait_wake_up(kvm_arch_vcpu_get_wait(vcpu)); +} + +static inline bool kvm_vcpu_is_blocking(struct kvm_vcpu *vcpu) +{ + return rcuwait_active(kvm_arch_vcpu_get_wait(vcpu)); +} + #ifdef __KVM_HAVE_ARCH_INTC_INITIALIZED /* * returns true if the virtual interrupt controller is initialized and @@ -1166,15 +1563,24 @@ static inline bool kvm_arch_intc_initialized(struct kvm *kvm) } #endif +#ifdef CONFIG_GUEST_PERF_EVENTS +unsigned long kvm_arch_vcpu_get_ip(struct kvm_vcpu *vcpu); + +void kvm_register_perf_callbacks(unsigned int (*pt_intr_handler)(void)); +void kvm_unregister_perf_callbacks(void); +#else +static inline void kvm_register_perf_callbacks(void *ign) {} +static inline void kvm_unregister_perf_callbacks(void) {} +#endif /* CONFIG_GUEST_PERF_EVENTS */ + int kvm_arch_init_vm(struct kvm *kvm, unsigned long type); void kvm_arch_destroy_vm(struct kvm *kvm); void kvm_arch_sync_events(struct kvm *kvm); int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu); -bool kvm_is_reserved_pfn(kvm_pfn_t pfn); -bool kvm_is_zone_device_pfn(kvm_pfn_t pfn); -bool kvm_is_transparent_hugepage(kvm_pfn_t pfn); +struct page *kvm_pfn_to_refcounted_page(kvm_pfn_t pfn); +bool kvm_is_zone_device_page(struct page *page); struct kvm_irq_ack_notifier { struct hlist_node link; @@ -1205,25 +1611,15 @@ void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id); bool kvm_arch_irqfd_allowed(struct kvm *kvm, struct kvm_irqfd *args); /* - * Returns a pointer to the memslot at slot_index if it contains gfn. + * Returns a pointer to the memslot if it contains gfn. * Otherwise returns NULL. */ static inline struct kvm_memory_slot * -try_get_memslot(struct kvm_memslots *slots, int slot_index, gfn_t gfn) +try_get_memslot(struct kvm_memory_slot *slot, gfn_t gfn) { - struct kvm_memory_slot *slot; - - if (slot_index < 0 || slot_index >= slots->used_slots) + if (!slot) return NULL; - /* - * slot_index can come from vcpu->last_used_slot which is not kept - * in sync with userspace-controllable memslot deletion. So use nospec - * to prevent the CPU from speculating past the end of memslots[]. - */ - slot_index = array_index_nospec(slot_index, slots->used_slots); - slot = &slots->memslots[slot_index]; - if (gfn >= slot->base_gfn && gfn < slot->base_gfn + slot->npages) return slot; else @@ -1231,63 +1627,63 @@ try_get_memslot(struct kvm_memslots *slots, int slot_index, gfn_t gfn) } /* - * Returns a pointer to the memslot that contains gfn and records the index of - * the slot in index. Otherwise returns NULL. + * Returns a pointer to the memslot that contains gfn. Otherwise returns NULL. * - * IMPORTANT: Slots are sorted from highest GFN to lowest GFN! + * With "approx" set returns the memslot also when the address falls + * in a hole. In that case one of the memslots bordering the hole is + * returned. */ static inline struct kvm_memory_slot * -search_memslots(struct kvm_memslots *slots, gfn_t gfn, int *index) +search_memslots(struct kvm_memslots *slots, gfn_t gfn, bool approx) { - int start = 0, end = slots->used_slots; - struct kvm_memory_slot *memslots = slots->memslots; struct kvm_memory_slot *slot; - - if (unlikely(!slots->used_slots)) - return NULL; - - while (start < end) { - int slot = start + (end - start) / 2; - - if (gfn >= memslots[slot].base_gfn) - end = slot; - else - start = slot + 1; - } - - slot = try_get_memslot(slots, start, gfn); - if (slot) { - *index = start; - return slot; + struct rb_node *node; + int idx = slots->node_idx; + + slot = NULL; + for (node = slots->gfn_tree.rb_node; node; ) { + slot = container_of(node, struct kvm_memory_slot, gfn_node[idx]); + if (gfn >= slot->base_gfn) { + if (gfn < slot->base_gfn + slot->npages) + return slot; + node = node->rb_right; + } else + node = node->rb_left; } - return NULL; + return approx ? slot : NULL; } -/* - * __gfn_to_memslot() and its descendants are here because it is called from - * non-modular code in arch/powerpc/kvm/book3s_64_vio{,_hv}.c. gfn_to_memslot() - * itself isn't here as an inline because that would bloat other code too much. - */ static inline struct kvm_memory_slot * -__gfn_to_memslot(struct kvm_memslots *slots, gfn_t gfn) +____gfn_to_memslot(struct kvm_memslots *slots, gfn_t gfn, bool approx) { struct kvm_memory_slot *slot; - int slot_index = atomic_read(&slots->last_used_slot); - slot = try_get_memslot(slots, slot_index, gfn); + slot = (struct kvm_memory_slot *)atomic_long_read(&slots->last_used_slot); + slot = try_get_memslot(slot, gfn); if (slot) return slot; - slot = search_memslots(slots, gfn, &slot_index); + slot = search_memslots(slots, gfn, approx); if (slot) { - atomic_set(&slots->last_used_slot, slot_index); + atomic_long_set(&slots->last_used_slot, (unsigned long)slot); return slot; } return NULL; } +/* + * __gfn_to_memslot() and its descendants are here to allow arch code to inline + * the lookups in hot paths. gfn_to_memslot() itself isn't here as an inline + * because that would bloat other code too much. + */ +static inline struct kvm_memory_slot * +__gfn_to_memslot(struct kvm_memslots *slots, gfn_t gfn) +{ + return ____gfn_to_memslot(slots, gfn, false); +} + static inline unsigned long __gfn_to_hva_memslot(const struct kvm_memory_slot *slot, gfn_t gfn) { @@ -1330,12 +1726,6 @@ static inline hpa_t pfn_to_hpa(kvm_pfn_t pfn) return (hpa_t)pfn << PAGE_SHIFT; } -static inline struct page *kvm_vcpu_gpa_to_page(struct kvm_vcpu *vcpu, - gpa_t gpa) -{ - return kvm_vcpu_gfn_to_page(vcpu, gpa_to_gfn(gpa)); -} - static inline bool kvm_is_error_gpa(struct kvm *kvm, gpa_t gpa) { unsigned long hva = gfn_to_hva(kvm, gpa_to_gfn(gpa)); @@ -1433,6 +1823,15 @@ struct _kvm_stats_desc { STATS_DESC_PEAK(SCOPE, name, KVM_STATS_UNIT_NONE, \ KVM_STATS_BASE_POW10, 0) +/* Instantaneous boolean value, read only */ +#define STATS_DESC_IBOOLEAN(SCOPE, name) \ + STATS_DESC_INSTANT(SCOPE, name, KVM_STATS_UNIT_BOOLEAN, \ + KVM_STATS_BASE_POW10, 0) +/* Peak (sticky) boolean value, read/write */ +#define STATS_DESC_PBOOLEAN(SCOPE, name) \ + STATS_DESC_PEAK(SCOPE, name, KVM_STATS_UNIT_BOOLEAN, \ + KVM_STATS_BASE_POW10, 0) + /* Cumulative time in nanosecond */ #define STATS_DESC_TIME_NSEC(SCOPE, name) \ STATS_DESC_CUMULATIVE(SCOPE, name, KVM_STATS_UNIT_SECONDS, \ @@ -1463,7 +1862,8 @@ struct _kvm_stats_desc { STATS_DESC_LOGHIST_TIME_NSEC(VCPU_GENERIC, halt_poll_fail_hist, \ HALT_POLL_HIST_COUNT), \ STATS_DESC_LOGHIST_TIME_NSEC(VCPU_GENERIC, halt_wait_hist, \ - HALT_POLL_HIST_COUNT) + HALT_POLL_HIST_COUNT), \ + STATS_DESC_IBOOLEAN(VCPU_GENERIC, blocking) extern struct dentry *kvm_debugfs_dir; @@ -1518,42 +1918,44 @@ extern const struct kvm_stats_header kvm_vcpu_stats_header; extern const struct _kvm_stats_desc kvm_vcpu_stats_desc[]; #if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER) -static inline int mmu_notifier_retry(struct kvm *kvm, unsigned long mmu_seq) +static inline int mmu_invalidate_retry(struct kvm *kvm, unsigned long mmu_seq) { - if (unlikely(kvm->mmu_notifier_count)) + if (unlikely(kvm->mmu_invalidate_in_progress)) return 1; /* - * Ensure the read of mmu_notifier_count happens before the read - * of mmu_notifier_seq. This interacts with the smp_wmb() in - * mmu_notifier_invalidate_range_end to make sure that the caller - * either sees the old (non-zero) value of mmu_notifier_count or - * the new (incremented) value of mmu_notifier_seq. - * PowerPC Book3s HV KVM calls this under a per-page lock - * rather than under kvm->mmu_lock, for scalability, so - * can't rely on kvm->mmu_lock to keep things ordered. + * Ensure the read of mmu_invalidate_in_progress happens before + * the read of mmu_invalidate_seq. This interacts with the + * smp_wmb() in mmu_notifier_invalidate_range_end to make sure + * that the caller either sees the old (non-zero) value of + * mmu_invalidate_in_progress or the new (incremented) value of + * mmu_invalidate_seq. + * + * PowerPC Book3s HV KVM calls this under a per-page lock rather + * than under kvm->mmu_lock, for scalability, so can't rely on + * kvm->mmu_lock to keep things ordered. */ smp_rmb(); - if (kvm->mmu_notifier_seq != mmu_seq) + if (kvm->mmu_invalidate_seq != mmu_seq) return 1; return 0; } -static inline int mmu_notifier_retry_hva(struct kvm *kvm, - unsigned long mmu_seq, - unsigned long hva) +static inline int mmu_invalidate_retry_hva(struct kvm *kvm, + unsigned long mmu_seq, + unsigned long hva) { lockdep_assert_held(&kvm->mmu_lock); /* - * If mmu_notifier_count is non-zero, then the range maintained by - * kvm_mmu_notifier_invalidate_range_start contains all addresses that - * might be being invalidated. Note that it may include some false + * If mmu_invalidate_in_progress is non-zero, then the range maintained + * by kvm_mmu_notifier_invalidate_range_start contains all addresses + * that might be being invalidated. Note that it may include some false * positives, due to shortcuts when handing concurrent invalidations. */ - if (unlikely(kvm->mmu_notifier_count) && - hva >= kvm->mmu_notifier_range_start && - hva < kvm->mmu_notifier_range_end) + if (unlikely(kvm->mmu_invalidate_in_progress) && + hva >= kvm->mmu_invalidate_range_start && + hva < kvm->mmu_invalidate_range_end) return 1; - if (kvm->mmu_notifier_seq != mmu_seq) + if (kvm->mmu_invalidate_seq != mmu_seq) return 1; return 0; } @@ -1625,7 +2027,7 @@ static inline int kvm_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args) void kvm_arch_irq_routing_update(struct kvm *kvm); -static inline void kvm_make_request(int req, struct kvm_vcpu *vcpu) +static inline void __kvm_make_request(int req, struct kvm_vcpu *vcpu) { /* * Ensure the rest of the request is published to kvm_check_request's @@ -1635,6 +2037,19 @@ static inline void kvm_make_request(int req, struct kvm_vcpu *vcpu) set_bit(req & KVM_REQUEST_MASK, (void *)&vcpu->requests); } +static __always_inline void kvm_make_request(int req, struct kvm_vcpu *vcpu) +{ + /* + * Request that don't require vCPU action should never be logged in + * vcpu->requests. The vCPU won't clear the request, so it will stay + * logged indefinitely and prevent the vCPU from entering the guest. + */ + BUILD_BUG_ON(!__builtin_constant_p(req) || + (req & KVM_REQUEST_NO_ACTION)); + + __kvm_make_request(req, vcpu); +} + static inline bool kvm_request_pending(struct kvm_vcpu *vcpu) { return READ_ONCE(vcpu->requests); @@ -1818,6 +2233,8 @@ static inline long kvm_arch_vcpu_async_ioctl(struct file *filp, void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm, unsigned long start, unsigned long end); +void kvm_arch_guest_memory_reclaimed(struct kvm *kvm); + #ifdef CONFIG_HAVE_KVM_VCPU_RUN_PID_CHANGE int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu); #else @@ -1842,6 +2259,19 @@ static inline void kvm_handle_signal_exit(struct kvm_vcpu *vcpu) #endif /* CONFIG_KVM_XFER_TO_GUEST_WORK */ /* + * If more than one page is being (un)accounted, @virt must be the address of + * the first page of a block of pages what were allocated together (i.e + * accounted together). + * + * kvm_account_pgtable_pages() is thread-safe because mod_lruvec_page_state() + * is thread-safe. + */ +static inline void kvm_account_pgtable_pages(void *virt, int nr) +{ + mod_lruvec_page_state(virt_to_page(virt), NR_SECONDARY_PAGETABLE, nr); +} + +/* * This defines how many reserved entries we want to keep before we * kick the vcpu to the userspace to avoid dirty ring full. This * value can be tuned to higher if e.g. PML is enabled on the host. diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h index 234eab059839..3ca3db020e0e 100644 --- a/include/linux/kvm_types.h +++ b/include/linux/kvm_types.h @@ -18,7 +18,10 @@ struct kvm_memslots; enum kvm_mr_change; +#include <linux/bits.h> +#include <linux/mutex.h> #include <linux/types.h> +#include <linux/spinlock_types.h> #include <asm/kvm_types.h> @@ -45,6 +48,12 @@ typedef u64 hfn_t; typedef hfn_t kvm_pfn_t; +enum pfn_cache_usage { + KVM_GUEST_USES_PFN = BIT(0), + KVM_HOST_USES_PFN = BIT(1), + KVM_GUEST_AND_HOST_USE_PFN = KVM_GUEST_USES_PFN | KVM_HOST_USES_PFN, +}; + struct gfn_to_hva_cache { u64 generation; gpa_t gpa; @@ -53,6 +62,22 @@ struct gfn_to_hva_cache { struct kvm_memory_slot *memslot; }; +struct gfn_to_pfn_cache { + u64 generation; + gpa_t gpa; + unsigned long uhva; + struct kvm_memory_slot *memslot; + struct kvm_vcpu *vcpu; + struct list_head list; + rwlock_t lock; + struct mutex refresh_lock; + void *khva; + kvm_pfn_t pfn; + enum pfn_cache_usage usage; + bool active; + bool valid; +}; + #ifdef KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE /* * Memory caches are used to preallocate memory ahead of various MMU flows, @@ -60,12 +85,17 @@ struct gfn_to_hva_cache { * MMU flows is problematic, as is triggering reclaim, I/O, etc... while * holding MMU locks. Note, these caches act more like prefetch buffers than * classical caches, i.e. objects are not returned to the cache on being freed. + * + * The @capacity field and @objects array are lazily initialized when the cache + * is topped up (__kvm_mmu_topup_memory_cache()). */ struct kvm_mmu_memory_cache { int nobjs; gfp_t gfp_zero; + gfp_t gfp_custom; struct kmem_cache *kmem_cache; - void *objects[KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE]; + int capacity; + void **objects; }; #endif @@ -87,6 +117,7 @@ struct kvm_vcpu_stat_generic { u64 halt_poll_success_hist[HALT_POLL_HIST_COUNT]; u64 halt_poll_fail_hist[HALT_POLL_HIST_COUNT]; u64 halt_wait_hist[HALT_POLL_HIST_COUNT]; + u64 blocking; }; #define KVM_STATS_NAME_SIZE 48 diff --git a/include/linux/lapb.h b/include/linux/lapb.h index eb56472f23b2..b5333f9413dc 100644 --- a/include/linux/lapb.h +++ b/include/linux/lapb.h @@ -6,6 +6,11 @@ #ifndef LAPB_KERNEL_H #define LAPB_KERNEL_H +#include <linux/skbuff.h> +#include <linux/timer.h> + +struct net_device; + #define LAPB_OK 0 #define LAPB_BADTOKEN 1 #define LAPB_INVALUE 2 diff --git a/include/linux/latencytop.h b/include/linux/latencytop.h index abe3d95f795b..84f1053cf2a8 100644 --- a/include/linux/latencytop.h +++ b/include/linux/latencytop.h @@ -38,9 +38,6 @@ account_scheduler_latency(struct task_struct *task, int usecs, int inter) void clear_tsk_latency_tracing(struct task_struct *p); -int sysctl_latencytop(struct ctl_table *table, int write, void *buffer, - size_t *lenp, loff_t *ppos); - #else static inline void diff --git a/include/linux/libata.h b/include/linux/libata.h index 2a8404b26083..fe990176e6ee 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -39,25 +39,9 @@ * compile-time options: to be removed as soon as all the drivers are * converted to the new debugging mechanism */ -#undef ATA_DEBUG /* debugging output */ -#undef ATA_VERBOSE_DEBUG /* yet more debugging output */ #undef ATA_IRQ_TRAP /* define to ack screaming irqs */ -#undef ATA_NDEBUG /* define to disable quick runtime checks */ -/* note: prints function name for you */ -#ifdef ATA_DEBUG -#define DPRINTK(fmt, args...) printk(KERN_ERR "%s: " fmt, __func__, ## args) -#ifdef ATA_VERBOSE_DEBUG -#define VPRINTK(fmt, args...) printk(KERN_ERR "%s: " fmt, __func__, ## args) -#else -#define VPRINTK(fmt, args...) -#endif /* ATA_VERBOSE_DEBUG */ -#else -#define DPRINTK(fmt, args...) -#define VPRINTK(fmt, args...) -#endif /* ATA_DEBUG */ - #define ata_print_version_once(dev, version) \ ({ \ static bool __print_once; \ @@ -68,38 +52,6 @@ } \ }) -/* NEW: debug levels */ -#define HAVE_LIBATA_MSG 1 - -enum { - ATA_MSG_DRV = 0x0001, - ATA_MSG_INFO = 0x0002, - ATA_MSG_PROBE = 0x0004, - ATA_MSG_WARN = 0x0008, - ATA_MSG_MALLOC = 0x0010, - ATA_MSG_CTL = 0x0020, - ATA_MSG_INTR = 0x0040, - ATA_MSG_ERR = 0x0080, -}; - -#define ata_msg_drv(p) ((p)->msg_enable & ATA_MSG_DRV) -#define ata_msg_info(p) ((p)->msg_enable & ATA_MSG_INFO) -#define ata_msg_probe(p) ((p)->msg_enable & ATA_MSG_PROBE) -#define ata_msg_warn(p) ((p)->msg_enable & ATA_MSG_WARN) -#define ata_msg_malloc(p) ((p)->msg_enable & ATA_MSG_MALLOC) -#define ata_msg_ctl(p) ((p)->msg_enable & ATA_MSG_CTL) -#define ata_msg_intr(p) ((p)->msg_enable & ATA_MSG_INTR) -#define ata_msg_err(p) ((p)->msg_enable & ATA_MSG_ERR) - -static inline u32 ata_msg_init(int dval, int default_msg_enable_bits) -{ - if (dval < 0 || dval >= (sizeof(u32) * 8)) - return default_msg_enable_bits; /* should be 0x1 - only driver info msgs */ - if (!dval) - return 0; - return (1 << dval) - 1; -} - /* defines only for the constants which don't work well as enums */ #define ATA_TAG_POISON 0xfafbfcfdU @@ -149,7 +101,7 @@ enum { ATA_DFLAG_UNLOCK_HPA = (1 << 18), /* unlock HPA */ ATA_DFLAG_NCQ_SEND_RECV = (1 << 19), /* device supports NCQ SEND and RECV */ ATA_DFLAG_NCQ_PRIO = (1 << 20), /* device supports NCQ priority */ - ATA_DFLAG_NCQ_PRIO_ENABLE = (1 << 21), /* Priority cmds sent to dev */ + ATA_DFLAG_NCQ_PRIO_ENABLED = (1 << 21), /* Priority cmds sent to dev */ ATA_DFLAG_INIT_MASK = (1 << 24) - 1, ATA_DFLAG_DETACH = (1 << 24), @@ -191,7 +143,7 @@ enum { ATA_LFLAG_NO_LPM = (1 << 8), /* disable LPM on this link */ ATA_LFLAG_RST_ONCE = (1 << 9), /* limit recovery to one reset */ ATA_LFLAG_CHANGED = (1 << 10), /* LPM state changed on this link */ - ATA_LFLAG_NO_DB_DELAY = (1 << 11), /* no debounce delay on link resume */ + ATA_LFLAG_NO_DEBOUNCE_DELAY = (1 << 11), /* no debounce delay on link resume */ /* struct ata_port flags */ ATA_FLAG_SLAVE_POSS = (1 << 0), /* host supports slave dev */ @@ -323,7 +275,7 @@ enum { PORT_DISABLED = 2, /* encoding various smaller bitmaps into a single - * unsigned long bitmap + * unsigned int bitmap */ ATA_NR_PIO_MODES = 7, ATA_NR_MWDMA_MODES = 5, @@ -428,6 +380,7 @@ enum { ATA_HORKAGE_MAX_TRIM_128M = (1 << 26), /* Limit max trim size to 128M */ ATA_HORKAGE_NO_NCQ_ON_ATI = (1 << 27), /* Disable NCQ on ATI chipset */ ATA_HORKAGE_NO_ID_DEV_LOG = (1 << 28), /* Identify device log missing */ + ATA_HORKAGE_NO_LOG_DIR = (1 << 29), /* Do not read log directory */ /* DMA mask for user DMA control: User visible values; DO NOT renumber */ @@ -473,12 +426,9 @@ enum { }; enum ata_xfer_mask { - ATA_MASK_PIO = ((1LU << ATA_NR_PIO_MODES) - 1) - << ATA_SHIFT_PIO, - ATA_MASK_MWDMA = ((1LU << ATA_NR_MWDMA_MODES) - 1) - << ATA_SHIFT_MWDMA, - ATA_MASK_UDMA = ((1LU << ATA_NR_UDMA_MODES) - 1) - << ATA_SHIFT_UDMA, + ATA_MASK_PIO = ((1U << ATA_NR_PIO_MODES) - 1) << ATA_SHIFT_PIO, + ATA_MASK_MWDMA = ((1U << ATA_NR_MWDMA_MODES) - 1) << ATA_SHIFT_MWDMA, + ATA_MASK_UDMA = ((1U << ATA_NR_UDMA_MODES) - 1) << ATA_SHIFT_UDMA, }; enum hsm_task_states { @@ -566,7 +516,10 @@ struct ata_taskfile { u8 hob_lbam; u8 hob_lbah; - u8 feature; + union { + u8 error; + u8 feature; + }; u8 nsect; u8 lbal; u8 lbam; @@ -574,7 +527,10 @@ struct ata_taskfile { u8 device; - u8 command; /* IO operation */ + union { + u8 status; + u8 command; + }; u32 auxiliary; /* auxiliary field */ /* from SATA 3.1 and */ @@ -721,9 +677,9 @@ struct ata_device { unsigned int cdb_len; /* per-dev xfer mask */ - unsigned long pio_mask; - unsigned long mwdma_mask; - unsigned long udma_mask; + unsigned int pio_mask; + unsigned int mwdma_mask; + unsigned int udma_mask; /* for CHS addressing */ u16 cylinders; /* Number of cylinders */ @@ -861,10 +817,8 @@ struct ata_port { unsigned int cbl; /* cable type; ATA_CBL_xxx */ struct ata_queued_cmd qcmd[ATA_MAX_QUEUE + 1]; - unsigned long sas_tag_allocated; /* for sas tag allocation only */ u64 qc_active; int nr_active_links; /* #links with active qcs */ - unsigned int sas_last_tag; /* track next tag hw expects */ struct ata_link link; /* host default link */ struct ata_link *slave_link; /* see ata_slave_link_init() */ @@ -884,7 +838,6 @@ struct ata_port { unsigned int hsm_task_state; - u32 msg_enable; struct list_head eh_done_q; wait_queue_head_t eh_wait_q; int eh_tries; @@ -894,7 +847,7 @@ struct ata_port { enum ata_lpm_policy target_lpm_policy; struct timer_list fastdrain_timer; - unsigned long fastdrain_cnt; + unsigned int fastdrain_cnt; async_cookie_t cookie; @@ -929,11 +882,12 @@ struct ata_port_operations { * Configuration and exception handling */ int (*cable_detect)(struct ata_port *ap); - unsigned long (*mode_filter)(struct ata_device *dev, unsigned long xfer_mask); + unsigned int (*mode_filter)(struct ata_device *dev, unsigned int xfer_mask); void (*set_piomode)(struct ata_port *ap, struct ata_device *dev); void (*set_dmamode)(struct ata_port *ap, struct ata_device *dev); int (*set_mode)(struct ata_link *link, struct ata_device **r_failed_dev); - unsigned int (*read_id)(struct ata_device *dev, struct ata_taskfile *tf, u16 *id); + unsigned int (*read_id)(struct ata_device *dev, struct ata_taskfile *tf, + __le16 *id); void (*dev_config)(struct ata_device *dev); @@ -1024,9 +978,9 @@ struct ata_port_operations { struct ata_port_info { unsigned long flags; unsigned long link_flags; - unsigned long pio_mask; - unsigned long mwdma_mask; - unsigned long udma_mask; + unsigned int pio_mask; + unsigned int mwdma_mask; + unsigned int udma_mask; struct ata_port_operations *port_ops; void *private_data; }; @@ -1128,7 +1082,7 @@ extern int ata_sas_scsi_ioctl(struct ata_port *ap, struct scsi_device *dev, extern bool ata_link_online(struct ata_link *link); extern bool ata_link_offline(struct ata_link *link); #ifdef CONFIG_PM -extern int ata_host_suspend(struct ata_host *host, pm_message_t mesg); +extern void ata_host_suspend(struct ata_host *host, pm_message_t mesg); extern void ata_host_resume(struct ata_host *host); extern void ata_sas_port_suspend(struct ata_port *ap); extern void ata_sas_port_resume(struct ata_port *ap); @@ -1145,28 +1099,32 @@ extern void ata_msleep(struct ata_port *ap, unsigned int msecs); extern u32 ata_wait_register(struct ata_port *ap, void __iomem *reg, u32 mask, u32 val, unsigned long interval, unsigned long timeout); extern int atapi_cmd_type(u8 opcode); -extern unsigned long ata_pack_xfermask(unsigned long pio_mask, - unsigned long mwdma_mask, unsigned long udma_mask); -extern void ata_unpack_xfermask(unsigned long xfer_mask, - unsigned long *pio_mask, unsigned long *mwdma_mask, - unsigned long *udma_mask); -extern u8 ata_xfer_mask2mode(unsigned long xfer_mask); -extern unsigned long ata_xfer_mode2mask(u8 xfer_mode); -extern int ata_xfer_mode2shift(unsigned long xfer_mode); -extern const char *ata_mode_string(unsigned long xfer_mask); -extern unsigned long ata_id_xfermask(const u16 *id); +extern unsigned int ata_pack_xfermask(unsigned int pio_mask, + unsigned int mwdma_mask, + unsigned int udma_mask); +extern void ata_unpack_xfermask(unsigned int xfer_mask, + unsigned int *pio_mask, + unsigned int *mwdma_mask, + unsigned int *udma_mask); +extern u8 ata_xfer_mask2mode(unsigned int xfer_mask); +extern unsigned int ata_xfer_mode2mask(u8 xfer_mode); +extern int ata_xfer_mode2shift(u8 xfer_mode); +extern const char *ata_mode_string(unsigned int xfer_mask); +extern unsigned int ata_id_xfermask(const u16 *id); extern int ata_std_qc_defer(struct ata_queued_cmd *qc); extern enum ata_completion_errors ata_noop_qc_prep(struct ata_queued_cmd *qc); extern void ata_sg_init(struct ata_queued_cmd *qc, struct scatterlist *sg, unsigned int n_elem); extern unsigned int ata_dev_classify(const struct ata_taskfile *tf); +extern unsigned int ata_port_classify(struct ata_port *ap, + const struct ata_taskfile *tf); extern void ata_dev_disable(struct ata_device *adev); extern void ata_id_string(const u16 *id, unsigned char *s, unsigned int ofs, unsigned int len); extern void ata_id_c_string(const u16 *id, unsigned char *s, unsigned int ofs, unsigned int len); extern unsigned int ata_do_dev_read_id(struct ata_device *dev, - struct ata_taskfile *tf, u16 *id); + struct ata_taskfile *tf, __le16 *id); extern void ata_qc_complete(struct ata_queued_cmd *qc); extern u64 ata_qc_get_active(struct ata_port *ap); extern void ata_scsi_simulate(struct ata_device *dev, struct scsi_cmnd *cmd); @@ -1178,8 +1136,8 @@ extern int ata_scsi_slave_config(struct scsi_device *sdev); extern void ata_scsi_slave_destroy(struct scsi_device *sdev); extern int ata_scsi_change_queue_depth(struct scsi_device *sdev, int queue_depth); -extern int __ata_change_queue_depth(struct ata_port *ap, struct scsi_device *sdev, - int queue_depth); +extern int ata_change_queue_depth(struct ata_port *ap, struct ata_device *dev, + struct scsi_device *sdev, int queue_depth); extern struct ata_device *ata_dev_pair(struct ata_device *adev); extern int ata_do_set_mode(struct ata_link *link, struct ata_device **r_failed_dev); extern void ata_scsi_port_error_handler(struct Scsi_Host *host, struct ata_port *ap); @@ -1324,8 +1282,8 @@ static inline const struct ata_acpi_gtm *ata_acpi_init_gtm(struct ata_port *ap) } int ata_acpi_stm(struct ata_port *ap, const struct ata_acpi_gtm *stm); int ata_acpi_gtm(struct ata_port *ap, struct ata_acpi_gtm *stm); -unsigned long ata_acpi_gtm_xfermask(struct ata_device *dev, - const struct ata_acpi_gtm *gtm); +unsigned int ata_acpi_gtm_xfermask(struct ata_device *dev, + const struct ata_acpi_gtm *gtm); int ata_acpi_cbl_80wire(struct ata_port *ap, const struct ata_acpi_gtm *gtm); #else static inline const struct ata_acpi_gtm *ata_acpi_init_gtm(struct ata_port *ap) @@ -1424,7 +1382,8 @@ extern const struct attribute_group *ata_common_sdev_groups[]; .proc_name = drv_name, \ .slave_destroy = ata_scsi_slave_destroy, \ .bios_param = ata_std_bios_param, \ - .unlock_native_capacity = ata_scsi_unlock_native_capacity + .unlock_native_capacity = ata_scsi_unlock_native_capacity,\ + .max_sectors = ATA_MAX_SECTORS_LBA48 #define ATA_SUBBASE_SHT(drv_name) \ __ATA_BASE_SHT(drv_name), \ @@ -1432,6 +1391,12 @@ extern const struct attribute_group *ata_common_sdev_groups[]; .tag_alloc_policy = BLK_TAG_ALLOC_RR, \ .slave_configure = ata_scsi_slave_config +#define ATA_SUBBASE_SHT_QD(drv_name, drv_qd) \ + __ATA_BASE_SHT(drv_name), \ + .can_queue = drv_qd, \ + .tag_alloc_policy = BLK_TAG_ALLOC_RR, \ + .slave_configure = ata_scsi_slave_config + #define ATA_BASE_SHT(drv_name) \ ATA_SUBBASE_SHT(drv_name), \ .sdev_groups = ata_common_sdev_groups @@ -1443,6 +1408,11 @@ extern const struct attribute_group *ata_ncq_sdev_groups[]; ATA_SUBBASE_SHT(drv_name), \ .sdev_groups = ata_ncq_sdev_groups, \ .change_queue_depth = ata_scsi_change_queue_depth + +#define ATA_NCQ_SHT_QD(drv_name, drv_qd) \ + ATA_SUBBASE_SHT_QD(drv_name, drv_qd), \ + .sdev_groups = ata_ncq_sdev_groups, \ + .change_queue_depth = ata_scsi_change_queue_depth #endif /* @@ -1487,51 +1457,61 @@ static inline int sata_srst_pmp(struct ata_link *link) return link->pmp; } -/* - * printk helpers - */ -__printf(3, 4) -void ata_port_printk(const struct ata_port *ap, const char *level, - const char *fmt, ...); -__printf(3, 4) -void ata_link_printk(const struct ata_link *link, const char *level, - const char *fmt, ...); -__printf(3, 4) -void ata_dev_printk(const struct ata_device *dev, const char *level, - const char *fmt, ...); +#define ata_port_printk(level, ap, fmt, ...) \ + pr_ ## level ("ata%u: " fmt, (ap)->print_id, ##__VA_ARGS__) #define ata_port_err(ap, fmt, ...) \ - ata_port_printk(ap, KERN_ERR, fmt, ##__VA_ARGS__) + ata_port_printk(err, ap, fmt, ##__VA_ARGS__) #define ata_port_warn(ap, fmt, ...) \ - ata_port_printk(ap, KERN_WARNING, fmt, ##__VA_ARGS__) + ata_port_printk(warn, ap, fmt, ##__VA_ARGS__) #define ata_port_notice(ap, fmt, ...) \ - ata_port_printk(ap, KERN_NOTICE, fmt, ##__VA_ARGS__) + ata_port_printk(notice, ap, fmt, ##__VA_ARGS__) #define ata_port_info(ap, fmt, ...) \ - ata_port_printk(ap, KERN_INFO, fmt, ##__VA_ARGS__) + ata_port_printk(info, ap, fmt, ##__VA_ARGS__) #define ata_port_dbg(ap, fmt, ...) \ - ata_port_printk(ap, KERN_DEBUG, fmt, ##__VA_ARGS__) + ata_port_printk(debug, ap, fmt, ##__VA_ARGS__) + +#define ata_link_printk(level, link, fmt, ...) \ +do { \ + if (sata_pmp_attached((link)->ap) || \ + (link)->ap->slave_link) \ + pr_ ## level ("ata%u.%02u: " fmt, \ + (link)->ap->print_id, \ + (link)->pmp, \ + ##__VA_ARGS__); \ + else \ + pr_ ## level ("ata%u: " fmt, \ + (link)->ap->print_id, \ + ##__VA_ARGS__); \ +} while (0) #define ata_link_err(link, fmt, ...) \ - ata_link_printk(link, KERN_ERR, fmt, ##__VA_ARGS__) + ata_link_printk(err, link, fmt, ##__VA_ARGS__) #define ata_link_warn(link, fmt, ...) \ - ata_link_printk(link, KERN_WARNING, fmt, ##__VA_ARGS__) + ata_link_printk(warn, link, fmt, ##__VA_ARGS__) #define ata_link_notice(link, fmt, ...) \ - ata_link_printk(link, KERN_NOTICE, fmt, ##__VA_ARGS__) + ata_link_printk(notice, link, fmt, ##__VA_ARGS__) #define ata_link_info(link, fmt, ...) \ - ata_link_printk(link, KERN_INFO, fmt, ##__VA_ARGS__) + ata_link_printk(info, link, fmt, ##__VA_ARGS__) #define ata_link_dbg(link, fmt, ...) \ - ata_link_printk(link, KERN_DEBUG, fmt, ##__VA_ARGS__) + ata_link_printk(debug, link, fmt, ##__VA_ARGS__) + +#define ata_dev_printk(level, dev, fmt, ...) \ + pr_ ## level("ata%u.%02u: " fmt, \ + (dev)->link->ap->print_id, \ + (dev)->link->pmp + (dev)->devno, \ + ##__VA_ARGS__) #define ata_dev_err(dev, fmt, ...) \ - ata_dev_printk(dev, KERN_ERR, fmt, ##__VA_ARGS__) + ata_dev_printk(err, dev, fmt, ##__VA_ARGS__) #define ata_dev_warn(dev, fmt, ...) \ - ata_dev_printk(dev, KERN_WARNING, fmt, ##__VA_ARGS__) + ata_dev_printk(warn, dev, fmt, ##__VA_ARGS__) #define ata_dev_notice(dev, fmt, ...) \ - ata_dev_printk(dev, KERN_NOTICE, fmt, ##__VA_ARGS__) + ata_dev_printk(notice, dev, fmt, ##__VA_ARGS__) #define ata_dev_info(dev, fmt, ...) \ - ata_dev_printk(dev, KERN_INFO, fmt, ##__VA_ARGS__) + ata_dev_printk(info, dev, fmt, ##__VA_ARGS__) #define ata_dev_dbg(dev, fmt, ...) \ - ata_dev_printk(dev, KERN_DEBUG, fmt, ##__VA_ARGS__) + ata_dev_printk(debug, dev, fmt, ##__VA_ARGS__) void ata_print_version(const struct device *dev, const char *version); @@ -2065,11 +2045,8 @@ static inline u8 ata_wait_idle(struct ata_port *ap) { u8 status = ata_sff_busy_wait(ap, ATA_BUSY | ATA_DRQ, 1000); -#ifdef ATA_DEBUG if (status != 0xff && (status & (ATA_BUSY | ATA_DRQ))) - ata_port_printk(ap, KERN_DEBUG, "abnormal Status 0x%X\n", - status); -#endif + ata_port_dbg(ap, "abnormal Status 0x%X\n", status); return status; } diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h index 7074aa9af525..c74acfa1a3fe 100644 --- a/include/linux/libnvdimm.h +++ b/include/linux/libnvdimm.h @@ -25,8 +25,6 @@ struct badrange { }; enum { - /* when a dimm supports both PMEM and BLK access a label is required */ - NDD_ALIASING = 0, /* unarmed memory devices may not persist writes */ NDD_UNARMED = 1, /* locked memory devices should not be accessed */ @@ -35,8 +33,6 @@ enum { NDD_SECURITY_OVERWRITE = 3, /* tracking whether or not there is a pending device reference */ NDD_WORK_PENDING = 4, - /* ignore / filter NSLABEL_FLAG_LOCAL for this DIMM, i.e. no aliasing */ - NDD_NOBLK = 5, /* dimm supports namespace labels */ NDD_LABELING = 6, @@ -63,6 +59,9 @@ enum { /* Platform provides asynchronous flush mechanism */ ND_REGION_ASYNC = 3, + /* Region was created by CXL subsystem */ + ND_REGION_CXL = 4, + /* mark newly adjusted resources as requiring a label update */ DPA_RESOURCE_ADJUSTED = 1 << 0, }; @@ -126,6 +125,7 @@ struct nd_region_desc { int numa_node; int target_node; unsigned long flags; + int memregion; struct device_node *of_node; int (*flush)(struct nd_region *nd_region, struct bio *bio); }; @@ -140,21 +140,6 @@ static inline void __iomem *devm_nvdimm_ioremap(struct device *dev, } struct nvdimm_bus; -struct module; -struct nd_blk_region; -struct nd_blk_region_desc { - int (*enable)(struct nvdimm_bus *nvdimm_bus, struct device *dev); - int (*do_io)(struct nd_blk_region *ndbr, resource_size_t dpa, - void *iobuf, u64 len, int rw); - struct nd_region_desc ndr_desc; -}; - -static inline struct nd_blk_region_desc *to_blk_region_desc( - struct nd_region_desc *ndr_desc) -{ - return container_of(ndr_desc, struct nd_blk_region_desc, ndr_desc); - -} /* * Note that separate bits for locked + unlocked are defined so that @@ -257,7 +242,6 @@ struct nvdimm_bus *nvdimm_to_bus(struct nvdimm *nvdimm); struct nvdimm *to_nvdimm(struct device *dev); struct nd_region *to_nd_region(struct device *dev); struct device *nd_region_dev(struct nd_region *nd_region); -struct nd_blk_region *to_nd_blk_region(struct device *dev); struct nvdimm_bus_descriptor *to_nd_desc(struct nvdimm_bus *nvdimm_bus); struct device *to_nvdimm_bus_dev(struct nvdimm_bus *nvdimm_bus); const char *nvdimm_name(struct nvdimm *nvdimm); @@ -279,6 +263,7 @@ static inline struct nvdimm *nvdimm_create(struct nvdimm_bus *nvdimm_bus, cmd_mask, num_flush, flush_wpq, NULL, NULL, NULL); } void nvdimm_delete(struct nvdimm *nvdimm); +void nvdimm_region_delete(struct nd_region *nd_region); const struct nd_cmd_desc *nd_cmd_dimm_desc(int cmd); const struct nd_cmd_desc *nd_cmd_bus_desc(int cmd); @@ -295,10 +280,6 @@ struct nd_region *nvdimm_blk_region_create(struct nvdimm_bus *nvdimm_bus, struct nd_region *nvdimm_volatile_region_create(struct nvdimm_bus *nvdimm_bus, struct nd_region_desc *ndr_desc); void *nd_region_provider_data(struct nd_region *nd_region); -void *nd_blk_region_provider_data(struct nd_blk_region *ndbr); -void nd_blk_region_set_provider_data(struct nd_blk_region *ndbr, void *data); -struct nvdimm *nd_blk_region_to_dimm(struct nd_blk_region *ndbr); -unsigned long nd_blk_memremap_flags(struct nd_blk_region *ndbr); unsigned int nd_region_acquire_lane(struct nd_region *nd_region); void nd_region_release_lane(struct nd_region *nd_region, unsigned int lane); u64 nd_fletcher64(void *addr, size_t len, bool le); diff --git a/include/linux/limits.h b/include/linux/limits.h index b568b9c30bbf..f6bcc9369010 100644 --- a/include/linux/limits.h +++ b/include/linux/limits.h @@ -7,6 +7,7 @@ #include <vdso/limits.h> #define SIZE_MAX (~(size_t)0) +#define SSIZE_MAX ((ssize_t)(SIZE_MAX >> 1)) #define PHYS_ADDR_MAX (~(phys_addr_t)0) #define U8_MAX ((u8)~0U) diff --git a/include/linux/linear_range.h b/include/linux/linear_range.h index fd3d0b358f22..2e4f4c3539c0 100644 --- a/include/linux/linear_range.h +++ b/include/linux/linear_range.h @@ -26,6 +26,17 @@ struct linear_range { unsigned int step; }; +#define LINEAR_RANGE(_min, _min_sel, _max_sel, _step) \ + { \ + .min = _min, \ + .min_sel = _min_sel, \ + .max_sel = _max_sel, \ + .step = _step, \ + } + +#define LINEAR_RANGE_IDX(_idx, _min, _min_sel, _max_sel, _step) \ + [_idx] = LINEAR_RANGE(_min, _min_sel, _max_sel, _step) + unsigned int linear_range_values_in_range(const struct linear_range *r); unsigned int linear_range_values_in_range_array(const struct linear_range *r, int ranges); diff --git a/include/linux/linkage.h b/include/linux/linkage.h index dbf8506decca..1feab6136b5b 100644 --- a/include/linux/linkage.h +++ b/include/linux/linkage.h @@ -165,7 +165,15 @@ #ifndef SYM_END #define SYM_END(name, sym_type) \ .type name sym_type ASM_NL \ - .size name, .-name + .set .L__sym_size_##name, .-name ASM_NL \ + .size name, .L__sym_size_##name +#endif + +/* SYM_ALIAS -- use only if you have to */ +#ifndef SYM_ALIAS +#define SYM_ALIAS(alias, name, linkage) \ + linkage(alias) ASM_NL \ + .set alias, name ASM_NL #endif /* === code annotations === */ @@ -200,30 +208,8 @@ SYM_ENTRY(name, linkage, SYM_A_NONE) #endif -/* - * SYM_FUNC_START_LOCAL_ALIAS -- use where there are two local names for one - * function - */ -#ifndef SYM_FUNC_START_LOCAL_ALIAS -#define SYM_FUNC_START_LOCAL_ALIAS(name) \ - SYM_START(name, SYM_L_LOCAL, SYM_A_ALIGN) -#endif - -/* - * SYM_FUNC_START_ALIAS -- use where there are two global names for one - * function - */ -#ifndef SYM_FUNC_START_ALIAS -#define SYM_FUNC_START_ALIAS(name) \ - SYM_START(name, SYM_L_GLOBAL, SYM_A_ALIGN) -#endif - /* SYM_FUNC_START -- use for global functions */ #ifndef SYM_FUNC_START -/* - * The same as SYM_FUNC_START_ALIAS, but we will need to distinguish these two - * later. - */ #define SYM_FUNC_START(name) \ SYM_START(name, SYM_L_GLOBAL, SYM_A_ALIGN) #endif @@ -236,7 +222,6 @@ /* SYM_FUNC_START_LOCAL -- use for local functions */ #ifndef SYM_FUNC_START_LOCAL -/* the same as SYM_FUNC_START_LOCAL_ALIAS, see comment near SYM_FUNC_START */ #define SYM_FUNC_START_LOCAL(name) \ SYM_START(name, SYM_L_LOCAL, SYM_A_ALIGN) #endif @@ -259,22 +244,39 @@ SYM_START(name, SYM_L_WEAK, SYM_A_NONE) #endif -/* SYM_FUNC_END_ALIAS -- the end of LOCAL_ALIASed or ALIASed function */ -#ifndef SYM_FUNC_END_ALIAS -#define SYM_FUNC_END_ALIAS(name) \ - SYM_END(name, SYM_T_FUNC) -#endif - /* * SYM_FUNC_END -- the end of SYM_FUNC_START_LOCAL, SYM_FUNC_START, * SYM_FUNC_START_WEAK, ... */ #ifndef SYM_FUNC_END -/* the same as SYM_FUNC_END_ALIAS, see comment near SYM_FUNC_START */ #define SYM_FUNC_END(name) \ SYM_END(name, SYM_T_FUNC) #endif +/* + * SYM_FUNC_ALIAS -- define a global alias for an existing function + */ +#ifndef SYM_FUNC_ALIAS +#define SYM_FUNC_ALIAS(alias, name) \ + SYM_ALIAS(alias, name, SYM_L_GLOBAL) +#endif + +/* + * SYM_FUNC_ALIAS_LOCAL -- define a local alias for an existing function + */ +#ifndef SYM_FUNC_ALIAS_LOCAL +#define SYM_FUNC_ALIAS_LOCAL(alias, name) \ + SYM_ALIAS(alias, name, SYM_L_LOCAL) +#endif + +/* + * SYM_FUNC_ALIAS_WEAK -- define a weak global alias for an existing function + */ +#ifndef SYM_FUNC_ALIAS_WEAK +#define SYM_FUNC_ALIAS_WEAK(alias, name) \ + SYM_ALIAS(alias, name, SYM_L_WEAK) +#endif + /* SYM_CODE_START -- use for non-C (special) functions */ #ifndef SYM_CODE_START #define SYM_CODE_START(name) \ diff --git a/include/linux/linkmode.h b/include/linux/linkmode.h index f8397f300fcd..15e0e0209da4 100644 --- a/include/linux/linkmode.h +++ b/include/linux/linkmode.h @@ -66,11 +66,6 @@ static inline void linkmode_mod_bit(int nr, volatile unsigned long *addr, linkmode_clear_bit(nr, addr); } -static inline void linkmode_change_bit(int nr, volatile unsigned long *addr) -{ - __change_bit(nr, addr); -} - static inline int linkmode_test_bit(int nr, const volatile unsigned long *addr) { return test_bit(nr, addr); diff --git a/include/linux/list.h b/include/linux/list.h index 6636fc07f918..61762054b4be 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -35,7 +35,7 @@ static inline void INIT_LIST_HEAD(struct list_head *list) { WRITE_ONCE(list->next, list); - list->prev = list; + WRITE_ONCE(list->prev, list); } #ifdef CONFIG_DEBUG_LIST @@ -258,8 +258,7 @@ static inline void list_bulk_move_tail(struct list_head *head, * @list: the entry to test * @head: the head of the list */ -static inline int list_is_first(const struct list_head *list, - const struct list_head *head) +static inline int list_is_first(const struct list_head *list, const struct list_head *head) { return list->prev == head; } @@ -269,13 +268,22 @@ static inline int list_is_first(const struct list_head *list, * @list: the entry to test * @head: the head of the list */ -static inline int list_is_last(const struct list_head *list, - const struct list_head *head) +static inline int list_is_last(const struct list_head *list, const struct list_head *head) { return list->next == head; } /** + * list_is_head - tests whether @list is the list @head + * @list: the entry to test + * @head: the head of the list + */ +static inline int list_is_head(const struct list_head *list, const struct list_head *head) +{ + return list == head; +} + +/** * list_empty - tests whether a list is empty * @head: the list to test. */ @@ -298,7 +306,7 @@ static inline int list_empty(const struct list_head *head) static inline void list_del_init_careful(struct list_head *entry) { __list_del_entry(entry); - entry->prev = entry; + WRITE_ONCE(entry->prev, entry); smp_store_release(&entry->next, entry); } @@ -318,7 +326,7 @@ static inline void list_del_init_careful(struct list_head *entry) static inline int list_empty_careful(const struct list_head *head) { struct list_head *next = smp_load_acquire(&head->next); - return (next == head) && (next == head->prev); + return list_is_head(next, head) && (next == READ_ONCE(head->prev)); } /** @@ -393,10 +401,9 @@ static inline void list_cut_position(struct list_head *list, { if (list_empty(head)) return; - if (list_is_singular(head) && - (head->next != entry && head != entry)) + if (list_is_singular(head) && !list_is_head(entry, head) && (entry != head->next)) return; - if (entry == head) + if (list_is_head(entry, head)) INIT_LIST_HEAD(list); else __list_cut_position(list, head, entry); @@ -557,6 +564,19 @@ static inline void list_splice_tail_init(struct list_head *list, list_entry((pos)->member.next, typeof(*(pos)), member) /** + * list_next_entry_circular - get the next element in list + * @pos: the type * to cursor. + * @head: the list head to take the element from. + * @member: the name of the list_head within the struct. + * + * Wraparound if pos is the last element (return the first element). + * Note, that list is expected to be not empty. + */ +#define list_next_entry_circular(pos, head, member) \ + (list_is_last(&(pos)->member, head) ? \ + list_first_entry(head, typeof(*(pos)), member) : list_next_entry(pos, member)) + +/** * list_prev_entry - get the prev element in list * @pos: the type * to cursor * @member: the name of the list_head within the struct. @@ -565,12 +585,35 @@ static inline void list_splice_tail_init(struct list_head *list, list_entry((pos)->member.prev, typeof(*(pos)), member) /** + * list_prev_entry_circular - get the prev element in list + * @pos: the type * to cursor. + * @head: the list head to take the element from. + * @member: the name of the list_head within the struct. + * + * Wraparound if pos is the first element (return the last element). + * Note, that list is expected to be not empty. + */ +#define list_prev_entry_circular(pos, head, member) \ + (list_is_first(&(pos)->member, head) ? \ + list_last_entry(head, typeof(*(pos)), member) : list_prev_entry(pos, member)) + +/** * list_for_each - iterate over a list * @pos: the &struct list_head to use as a loop cursor. * @head: the head for your list. */ #define list_for_each(pos, head) \ - for (pos = (head)->next; pos != (head); pos = pos->next) + for (pos = (head)->next; !list_is_head(pos, (head)); pos = pos->next) + +/** + * list_for_each_rcu - Iterate over a list in an RCU-safe fashion + * @pos: the &struct list_head to use as a loop cursor. + * @head: the head for your list. + */ +#define list_for_each_rcu(pos, head) \ + for (pos = rcu_dereference((head)->next); \ + !list_is_head(pos, (head)); \ + pos = rcu_dereference(pos->next)) /** * list_for_each_continue - continue iteration over a list @@ -580,7 +623,7 @@ static inline void list_splice_tail_init(struct list_head *list, * Continue to iterate over a list, continuing after the current position. */ #define list_for_each_continue(pos, head) \ - for (pos = pos->next; pos != (head); pos = pos->next) + for (pos = pos->next; !list_is_head(pos, (head)); pos = pos->next) /** * list_for_each_prev - iterate over a list backwards @@ -588,7 +631,7 @@ static inline void list_splice_tail_init(struct list_head *list, * @head: the head for your list. */ #define list_for_each_prev(pos, head) \ - for (pos = (head)->prev; pos != (head); pos = pos->prev) + for (pos = (head)->prev; !list_is_head(pos, (head)); pos = pos->prev) /** * list_for_each_safe - iterate over a list safe against removal of list entry @@ -597,8 +640,9 @@ static inline void list_splice_tail_init(struct list_head *list, * @head: the head for your list. */ #define list_for_each_safe(pos, n, head) \ - for (pos = (head)->next, n = pos->next; pos != (head); \ - pos = n, n = pos->next) + for (pos = (head)->next, n = pos->next; \ + !list_is_head(pos, (head)); \ + pos = n, n = pos->next) /** * list_for_each_prev_safe - iterate over a list backwards safe against removal of list entry @@ -608,7 +652,7 @@ static inline void list_splice_tail_init(struct list_head *list, */ #define list_for_each_prev_safe(pos, n, head) \ for (pos = (head)->prev, n = pos->prev; \ - pos != (head); \ + !list_is_head(pos, (head)); \ pos = n, n = pos->prev) /** diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h index 1b5fceb565df..b35968ee9fb5 100644 --- a/include/linux/list_lru.h +++ b/include/linux/list_lru.h @@ -11,6 +11,7 @@ #include <linux/list.h> #include <linux/nodemask.h> #include <linux/shrinker.h> +#include <linux/xarray.h> struct mem_cgroup; @@ -33,8 +34,8 @@ struct list_lru_one { struct list_lru_memcg { struct rcu_head rcu; - /* array of per cgroup lists, indexed by memcg_cache_id */ - struct list_lru_one *lru[]; + /* array of per cgroup per node lists, indexed by node id */ + struct list_lru_one node[]; }; struct list_lru_node { @@ -42,11 +43,7 @@ struct list_lru_node { spinlock_t lock; /* global list, used for the root cgroup in cgroup aware lrus */ struct list_lru_one lru; -#ifdef CONFIG_MEMCG_KMEM - /* for cgroup aware lrus points to per cgroup lists, otherwise NULL */ - struct list_lru_memcg __rcu *memcg_lrus; -#endif - long nr_items; + long nr_items; } ____cacheline_aligned_in_smp; struct list_lru { @@ -55,6 +52,7 @@ struct list_lru { struct list_head list; int shrinker_id; bool memcg_aware; + struct xarray xa; #endif }; @@ -69,8 +67,9 @@ int __list_lru_init(struct list_lru *lru, bool memcg_aware, #define list_lru_init_memcg(lru, shrinker) \ __list_lru_init((lru), true, NULL, shrinker) -int memcg_update_all_list_lrus(int num_memcgs); -void memcg_drain_all_list_lrus(int src_idx, struct mem_cgroup *dst_memcg); +int memcg_list_lru_alloc(struct mem_cgroup *memcg, struct list_lru *lru, + gfp_t gfp); +void memcg_reparent_list_lrus(struct mem_cgroup *memcg, struct mem_cgroup *parent); /** * list_lru_add: add an element to the lru list's tail diff --git a/include/linux/livepatch.h b/include/linux/livepatch.h index 2614247a9781..293e29960c6e 100644 --- a/include/linux/livepatch.h +++ b/include/linux/livepatch.h @@ -16,8 +16,6 @@ #if IS_ENABLED(CONFIG_LIVEPATCH) -#include <asm/livepatch.h> - /* task patch states */ #define KLP_UNDEFINED -1 #define KLP_UNPATCHED 0 diff --git a/include/linux/llist_api.h b/include/linux/llist_api.h new file mode 100644 index 000000000000..625bec0393a1 --- /dev/null +++ b/include/linux/llist_api.h @@ -0,0 +1 @@ +#include <linux/llist.h> diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h index c4ae6506b8b3..70ce419e2709 100644 --- a/include/linux/lockd/lockd.h +++ b/include/linux/lockd/lockd.h @@ -292,6 +292,7 @@ void nlmsvc_locks_init_private(struct file_lock *, struct nlm_host *, pid_t); __be32 nlm_lookup_file(struct svc_rqst *, struct nlm_file **, struct nlm_lock *); void nlm_release_file(struct nlm_file *); +void nlmsvc_put_lockowner(struct nlm_lockowner *); void nlmsvc_release_lockowner(struct nlm_lock *); void nlmsvc_mark_resources(struct net *); void nlmsvc_free_host_resources(struct nlm_host *); @@ -303,10 +304,15 @@ void nlmsvc_invalidate_all(void); int nlmsvc_unlock_all_by_sb(struct super_block *sb); int nlmsvc_unlock_all_by_ip(struct sockaddr *server_addr); +static inline struct file *nlmsvc_file_file(struct nlm_file *file) +{ + return file->f_file[O_RDONLY] ? + file->f_file[O_RDONLY] : file->f_file[O_WRONLY]; +} + static inline struct inode *nlmsvc_file_inode(struct nlm_file *file) { - return locks_inode(file->f_file[O_RDONLY] ? - file->f_file[O_RDONLY] : file->f_file[O_WRONLY]); + return locks_inode(nlmsvc_file_file(file)); } static inline int __nlm_privileged_request4(const struct sockaddr *sap) diff --git a/include/linux/lockd/xdr.h b/include/linux/lockd/xdr.h index 398f70093cd3..67e4a2c5500b 100644 --- a/include/linux/lockd/xdr.h +++ b/include/linux/lockd/xdr.h @@ -41,6 +41,8 @@ struct nlm_lock { struct nfs_fh fh; struct xdr_netobj oh; u32 svid; + u64 lock_start; + u64 lock_len; struct file_lock fl; }; diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 467b94257105..1f1099dac3f0 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -16,10 +16,6 @@ struct task_struct; -/* for sysctl */ -extern int prove_locking; -extern int lock_stat; - #ifdef CONFIG_LOCKDEP #include <linux/linkage.h> @@ -192,7 +188,7 @@ static inline void lockdep_init_map_waits(struct lockdep_map *lock, const char *name, struct lock_class_key *key, int subclass, u8 inner, u8 outer) { - lockdep_init_map_type(lock, name, key, subclass, inner, LD_WAIT_INV, LD_LOCK_NORMAL); + lockdep_init_map_type(lock, name, key, subclass, inner, outer, LD_LOCK_NORMAL); } static inline void @@ -215,24 +211,28 @@ static inline void lockdep_init_map(struct lockdep_map *lock, const char *name, * or they are too narrow (they suffer from a false class-split): */ #define lockdep_set_class(lock, key) \ - lockdep_init_map_waits(&(lock)->dep_map, #key, key, 0, \ - (lock)->dep_map.wait_type_inner, \ - (lock)->dep_map.wait_type_outer) + lockdep_init_map_type(&(lock)->dep_map, #key, key, 0, \ + (lock)->dep_map.wait_type_inner, \ + (lock)->dep_map.wait_type_outer, \ + (lock)->dep_map.lock_type) #define lockdep_set_class_and_name(lock, key, name) \ - lockdep_init_map_waits(&(lock)->dep_map, name, key, 0, \ - (lock)->dep_map.wait_type_inner, \ - (lock)->dep_map.wait_type_outer) + lockdep_init_map_type(&(lock)->dep_map, name, key, 0, \ + (lock)->dep_map.wait_type_inner, \ + (lock)->dep_map.wait_type_outer, \ + (lock)->dep_map.lock_type) #define lockdep_set_class_and_subclass(lock, key, sub) \ - lockdep_init_map_waits(&(lock)->dep_map, #key, key, sub,\ - (lock)->dep_map.wait_type_inner, \ - (lock)->dep_map.wait_type_outer) + lockdep_init_map_type(&(lock)->dep_map, #key, key, sub, \ + (lock)->dep_map.wait_type_inner, \ + (lock)->dep_map.wait_type_outer, \ + (lock)->dep_map.lock_type) #define lockdep_set_subclass(lock, sub) \ - lockdep_init_map_waits(&(lock)->dep_map, #lock, (lock)->dep_map.key, sub,\ - (lock)->dep_map.wait_type_inner, \ - (lock)->dep_map.wait_type_outer) + lockdep_init_map_type(&(lock)->dep_map, #lock, (lock)->dep_map.key, sub,\ + (lock)->dep_map.wait_type_inner, \ + (lock)->dep_map.wait_type_outer, \ + (lock)->dep_map.lock_type) #define lockdep_set_novalidate_class(lock) \ lockdep_set_class_and_name(lock, &__lockdep_no_validate__, #lock) @@ -290,6 +290,9 @@ extern void lock_set_class(struct lockdep_map *lock, const char *name, struct lock_class_key *key, unsigned int subclass, unsigned long ip); +#define lock_set_novalidate_class(l, n, i) \ + lock_set_class(l, n, &__lockdep_no_validate__, 0, i) + static inline void lock_set_subclass(struct lockdep_map *lock, unsigned int subclass, unsigned long ip) { @@ -357,7 +360,8 @@ static inline void lockdep_set_selftest_task(struct task_struct *task) # define lock_acquire(l, s, t, r, c, n, i) do { } while (0) # define lock_release(l, i) do { } while (0) # define lock_downgrade(l, i) do { } while (0) -# define lock_set_class(l, n, k, s, i) do { } while (0) +# define lock_set_class(l, n, key, s, i) do { (void)(key); } while (0) +# define lock_set_novalidate_class(l, n, i) do { } while (0) # define lock_set_subclass(l, s, i) do { } while (0) # define lockdep_init() do { } while (0) # define lockdep_init_map_type(lock, name, key, sub, inner, outer, type) \ diff --git a/include/linux/lockdep_api.h b/include/linux/lockdep_api.h new file mode 100644 index 000000000000..907e66979ab2 --- /dev/null +++ b/include/linux/lockdep_api.h @@ -0,0 +1 @@ +#include <linux/lockdep.h> diff --git a/include/linux/lockref.h b/include/linux/lockref.h index 99f17cc8e163..c3a1f78bc884 100644 --- a/include/linux/lockref.h +++ b/include/linux/lockref.h @@ -38,7 +38,6 @@ extern void lockref_get(struct lockref *); extern int lockref_put_return(struct lockref *); extern int lockref_get_not_zero(struct lockref *); extern int lockref_put_not_zero(struct lockref *); -extern int lockref_get_or_lock(struct lockref *); extern int lockref_put_or_lock(struct lockref *); extern void lockref_mark_dead(struct lockref *); diff --git a/include/linux/log2.h b/include/linux/log2.h index df0b155c2141..9f30d087a128 100644 --- a/include/linux/log2.h +++ b/include/linux/log2.h @@ -18,7 +18,7 @@ * - the arch is not required to handle n==0 if implementing the fallback */ #ifndef CONFIG_ARCH_HAS_ILOG2_U32 -static inline __attribute__((const)) +static __always_inline __attribute__((const)) int __ilog2_u32(u32 n) { return fls(n) - 1; @@ -26,7 +26,7 @@ int __ilog2_u32(u32 n) #endif #ifndef CONFIG_ARCH_HAS_ILOG2_U64 -static inline __attribute__((const)) +static __always_inline __attribute__((const)) int __ilog2_u64(u64 n) { return fls64(n) - 1; diff --git a/include/linux/lsm_audit.h b/include/linux/lsm_audit.h index 17d02eda9538..97a8b21eb033 100644 --- a/include/linux/lsm_audit.h +++ b/include/linux/lsm_audit.h @@ -76,6 +76,7 @@ struct common_audit_data { #define LSM_AUDIT_DATA_IBENDPORT 14 #define LSM_AUDIT_DATA_LOCKDOWN 15 #define LSM_AUDIT_DATA_NOTIFICATION 16 +#define LSM_AUDIT_DATA_ANONINODE 17 union { struct path path; struct dentry *dentry; @@ -96,6 +97,7 @@ struct common_audit_data { struct lsm_ibpkey_audit *ibpkey; struct lsm_ibendport_audit *ibendport; int reason; + const char *anonclass; } u; /* this union contains LSM specific data */ union { diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index a5a724c308d8..ec119da1d89b 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -80,7 +80,7 @@ LSM_HOOK(int, 0, sb_clone_mnt_opts, const struct super_block *oldsb, unsigned long *set_kern_flags) LSM_HOOK(int, 0, move_mount, const struct path *from_path, const struct path *to_path) -LSM_HOOK(int, 0, dentry_init_security, struct dentry *dentry, +LSM_HOOK(int, -EOPNOTSUPP, dentry_init_security, struct dentry *dentry, int mode, const struct qstr *name, const char **xattr_name, void **ctx, u32 *ctxlen) LSM_HOOK(int, 0, dentry_create_files_as, struct dentry *dentry, int mode, @@ -100,7 +100,7 @@ LSM_HOOK(int, 0, path_link, struct dentry *old_dentry, const struct path *new_dir, struct dentry *new_dentry) LSM_HOOK(int, 0, path_rename, const struct path *old_dir, struct dentry *old_dentry, const struct path *new_dir, - struct dentry *new_dentry) + struct dentry *new_dentry, unsigned int flags) LSM_HOOK(int, 0, path_chmod, const struct path *path, umode_t mode) LSM_HOOK(int, 0, path_chown, const struct path *path, kuid_t uid, kgid_t gid) LSM_HOOK(int, 0, path_chroot, const struct path *path) @@ -201,6 +201,7 @@ LSM_HOOK(int, 0, task_fix_setuid, struct cred *new, const struct cred *old, int flags) LSM_HOOK(int, 0, task_fix_setgid, struct cred *new, const struct cred * old, int flags) +LSM_HOOK(int, 0, task_fix_setgroups, struct cred *new, const struct cred * old) LSM_HOOK(int, 0, task_setpgid, struct task_struct *p, pid_t pgid) LSM_HOOK(int, 0, task_getpgid, struct task_struct *p) LSM_HOOK(int, 0, task_getsid, struct task_struct *p) @@ -223,6 +224,7 @@ LSM_HOOK(int, -ENOSYS, task_prctl, int option, unsigned long arg2, unsigned long arg3, unsigned long arg4, unsigned long arg5) LSM_HOOK(void, LSM_RET_VOID, task_to_inode, struct task_struct *p, struct inode *inode) +LSM_HOOK(int, 0, userns_create, const struct cred *cred) LSM_HOOK(int, 0, ipc_permission, struct kern_ipc_perm *ipcp, short flag) LSM_HOOK(void, LSM_RET_VOID, ipc_getsecid, struct kern_ipc_perm *ipcp, u32 *secid) @@ -252,7 +254,7 @@ LSM_HOOK(int, 0, sem_semop, struct kern_ipc_perm *perm, struct sembuf *sops, LSM_HOOK(int, 0, netlink_send, struct sock *sk, struct sk_buff *skb) LSM_HOOK(void, LSM_RET_VOID, d_instantiate, struct dentry *dentry, struct inode *inode) -LSM_HOOK(int, -EINVAL, getprocattr, struct task_struct *p, char *name, +LSM_HOOK(int, -EINVAL, getprocattr, struct task_struct *p, const char *name, char **value) LSM_HOOK(int, -EINVAL, setprocattr, const char *name, void *value, size_t size) LSM_HOOK(int, 0, ismaclabel, const char *name) @@ -332,6 +334,8 @@ LSM_HOOK(int, 0, sctp_bind_connect, struct sock *sk, int optname, struct sockaddr *address, int addrlen) LSM_HOOK(void, LSM_RET_VOID, sctp_sk_clone, struct sctp_association *asoc, struct sock *sk, struct sock *newsk) +LSM_HOOK(int, 0, sctp_assoc_established, struct sctp_association *asoc, + struct sk_buff *skb) #endif /* CONFIG_SECURITY_NETWORK */ #ifdef CONFIG_SECURITY_INFINIBAND @@ -404,4 +408,5 @@ LSM_HOOK(int, 0, perf_event_write, struct perf_event *event) #ifdef CONFIG_IO_URING LSM_HOOK(int, 0, uring_override_creds, const struct cred *new) LSM_HOOK(int, 0, uring_sqpoll, void) +LSM_HOOK(int, 0, uring_cmd, struct io_uring_cmd *ioucmd) #endif /* CONFIG_IO_URING */ diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 3bf5c658bc44..4ec80b96c22e 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -358,6 +358,7 @@ * @old_dentry contains the dentry structure of the old link. * @new_dir contains the path structure for parent of the new link. * @new_dentry contains the dentry structure of the new link. + * @flags may contain rename options such as RENAME_EXCHANGE. * Return 0 if permission is granted. * @path_chmod: * Check for permission to change a mode of the file @path. The new @@ -701,6 +702,13 @@ * @old is the set of credentials that are being replaced. * @flags contains one of the LSM_SETID_* values. * Return 0 on success. + * @task_fix_setgroups: + * Update the module's state after setting the supplementary group + * identity attributes of the current process. + * @new is the set of credentials that will be installed. Modifications + * should be made to this rather than to @current->cred. + * @old is the set of credentials that are being replaced. + * Return 0 on success. * @task_setpgid: * Check permission before setting the process group identifier of the * process @p to @pgid. @@ -798,6 +806,10 @@ * security attributes, e.g. for /proc/pid inodes. * @p contains the task_struct for the task. * @inode contains the inode structure for the inode. + * @userns_create: + * Check permission prior to creating a new user namespace. + * @cred points to prepared creds. + * Return 0 if successful, otherwise < 0 error code. * * Security hooks for Netlink messaging. * @@ -1046,6 +1058,11 @@ * @asoc pointer to current sctp association structure. * @sk pointer to current sock structure. * @newsk pointer to new sock structure. + * @sctp_assoc_established: + * Passes the @asoc and @chunk->skb of the association COOKIE_ACK packet + * to the security module. + * @asoc pointer to sctp association structure. + * @skb pointer to skbuff of association packet. * * Security hooks for Infiniband * @@ -1569,6 +1586,9 @@ * Check whether the current task is allowed to spawn a io_uring polling * thread (IORING_SETUP_SQPOLL). * + * @uring_cmd: + * Check whether the file_operations uring_cmd is allowed to run. + * */ union security_list_options { #define LSM_HOOK(RET, DEFAULT, NAME, ...) RET (*NAME)(__VA_ARGS__); @@ -1590,7 +1610,7 @@ struct security_hook_list { struct hlist_node list; struct hlist_head *head; union security_list_options hook; - char *lsm; + const char *lsm; } __randomize_layout; /* @@ -1625,7 +1645,7 @@ extern struct security_hook_heads security_hook_heads; extern char *lsm_names; extern void security_add_hooks(struct security_hook_list *hooks, int count, - char *lsm); + const char *lsm); #define LSM_FLAG_LEGACY_MAJOR BIT(0) #define LSM_FLAG_EXCLUSIVE BIT(1) diff --git a/include/linux/mailbox/mtk-cmdq-mailbox.h b/include/linux/mailbox/mtk-cmdq-mailbox.h index 44365aab043c..a8f0070c7aa9 100644 --- a/include/linux/mailbox/mtk-cmdq-mailbox.h +++ b/include/linux/mailbox/mtk-cmdq-mailbox.h @@ -67,24 +67,14 @@ enum cmdq_code { struct cmdq_cb_data { int sta; - void *data; struct cmdq_pkt *pkt; }; -typedef void (*cmdq_async_flush_cb)(struct cmdq_cb_data data); - -struct cmdq_task_cb { - cmdq_async_flush_cb cb; - void *data; -}; - struct cmdq_pkt { void *va_base; dma_addr_t pa_base; size_t cmd_buf_size; /* command occupied size */ size_t buf_size; /* real buffer size */ - struct cmdq_task_cb cb; - struct cmdq_task_cb async_cb; void *cl; }; diff --git a/include/linux/mailbox_controller.h b/include/linux/mailbox_controller.h index 36d6ce673503..6fee33cb52f5 100644 --- a/include/linux/mailbox_controller.h +++ b/include/linux/mailbox_controller.h @@ -83,6 +83,7 @@ struct mbox_controller { const struct of_phandle_args *sp); /* Internal to API */ struct hrtimer poll_hrt; + spinlock_t poll_hrt_lock; struct list_head node; }; diff --git a/include/linux/map_benchmark.h b/include/linux/map_benchmark.h new file mode 100644 index 000000000000..62674c83bde4 --- /dev/null +++ b/include/linux/map_benchmark.h @@ -0,0 +1,31 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2022 HiSilicon Limited. + */ + +#ifndef _KERNEL_DMA_BENCHMARK_H +#define _KERNEL_DMA_BENCHMARK_H + +#define DMA_MAP_BENCHMARK _IOWR('d', 1, struct map_benchmark) +#define DMA_MAP_MAX_THREADS 1024 +#define DMA_MAP_MAX_SECONDS 300 +#define DMA_MAP_MAX_TRANS_DELAY (10 * NSEC_PER_MSEC) + +#define DMA_MAP_BIDIRECTIONAL 0 +#define DMA_MAP_TO_DEVICE 1 +#define DMA_MAP_FROM_DEVICE 2 + +struct map_benchmark { + __u64 avg_map_100ns; /* average map latency in 100ns */ + __u64 map_stddev; /* standard deviation of map latency */ + __u64 avg_unmap_100ns; /* as above */ + __u64 unmap_stddev; + __u32 threads; /* how many threads will do map/unmap in parallel */ + __u32 seconds; /* how long the test will last */ + __s32 node; /* which numa node this benchmark will run on */ + __u32 dma_bits; /* DMA addressing capability */ + __u32 dma_dir; /* DMA data direction */ + __u32 dma_trans_ns; /* time for DMA transmission in ns */ + __u32 granule; /* how many PAGE_SIZE will do map/unmap once a time */ +}; +#endif /* _KERNEL_DMA_BENCHMARK_H */ diff --git a/include/linux/maple_tree.h b/include/linux/maple_tree.h new file mode 100644 index 000000000000..e594db58a0f1 --- /dev/null +++ b/include/linux/maple_tree.h @@ -0,0 +1,692 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +#ifndef _LINUX_MAPLE_TREE_H +#define _LINUX_MAPLE_TREE_H +/* + * Maple Tree - An RCU-safe adaptive tree for storing ranges + * Copyright (c) 2018-2022 Oracle + * Authors: Liam R. Howlett <Liam.Howlett@Oracle.com> + * Matthew Wilcox <willy@infradead.org> + */ + +#include <linux/kernel.h> +#include <linux/rcupdate.h> +#include <linux/spinlock.h> +/* #define CONFIG_MAPLE_RCU_DISABLED */ +/* #define CONFIG_DEBUG_MAPLE_TREE_VERBOSE */ + +/* + * Allocated nodes are mutable until they have been inserted into the tree, + * at which time they cannot change their type until they have been removed + * from the tree and an RCU grace period has passed. + * + * Removed nodes have their ->parent set to point to themselves. RCU readers + * check ->parent before relying on the value that they loaded from the + * slots array. This lets us reuse the slots array for the RCU head. + * + * Nodes in the tree point to their parent unless bit 0 is set. + */ +#if defined(CONFIG_64BIT) || defined(BUILD_VDSO32_64) +/* 64bit sizes */ +#define MAPLE_NODE_SLOTS 31 /* 256 bytes including ->parent */ +#define MAPLE_RANGE64_SLOTS 16 /* 256 bytes */ +#define MAPLE_ARANGE64_SLOTS 10 /* 240 bytes */ +#define MAPLE_ARANGE64_META_MAX 15 /* Out of range for metadata */ +#define MAPLE_ALLOC_SLOTS (MAPLE_NODE_SLOTS - 1) +#else +/* 32bit sizes */ +#define MAPLE_NODE_SLOTS 63 /* 256 bytes including ->parent */ +#define MAPLE_RANGE64_SLOTS 32 /* 256 bytes */ +#define MAPLE_ARANGE64_SLOTS 21 /* 240 bytes */ +#define MAPLE_ARANGE64_META_MAX 31 /* Out of range for metadata */ +#define MAPLE_ALLOC_SLOTS (MAPLE_NODE_SLOTS - 2) +#endif /* defined(CONFIG_64BIT) || defined(BUILD_VDSO32_64) */ + +#define MAPLE_NODE_MASK 255UL + +/* + * The node->parent of the root node has bit 0 set and the rest of the pointer + * is a pointer to the tree itself. No more bits are available in this pointer + * (on m68k, the data structure may only be 2-byte aligned). + * + * Internal non-root nodes can only have maple_range_* nodes as parents. The + * parent pointer is 256B aligned like all other tree nodes. When storing a 32 + * or 64 bit values, the offset can fit into 4 bits. The 16 bit values need an + * extra bit to store the offset. This extra bit comes from a reuse of the last + * bit in the node type. This is possible by using bit 1 to indicate if bit 2 + * is part of the type or the slot. + * + * Once the type is decided, the decision of an allocation range type or a range + * type is done by examining the immutable tree flag for the MAPLE_ALLOC_RANGE + * flag. + * + * Node types: + * 0x??1 = Root + * 0x?00 = 16 bit nodes + * 0x010 = 32 bit nodes + * 0x110 = 64 bit nodes + * + * Slot size and location in the parent pointer: + * type : slot location + * 0x??1 : Root + * 0x?00 : 16 bit values, type in 0-1, slot in 2-6 + * 0x010 : 32 bit values, type in 0-2, slot in 3-6 + * 0x110 : 64 bit values, type in 0-2, slot in 3-6 + */ + +/* + * This metadata is used to optimize the gap updating code and in reverse + * searching for gaps or any other code that needs to find the end of the data. + */ +struct maple_metadata { + unsigned char end; + unsigned char gap; +}; + +/* + * Leaf nodes do not store pointers to nodes, they store user data. Users may + * store almost any bit pattern. As noted above, the optimisation of storing an + * entry at 0 in the root pointer cannot be done for data which have the bottom + * two bits set to '10'. We also reserve values with the bottom two bits set to + * '10' which are below 4096 (ie 2, 6, 10 .. 4094) for internal use. Some APIs + * return errnos as a negative errno shifted right by two bits and the bottom + * two bits set to '10', and while choosing to store these values in the array + * is not an error, it may lead to confusion if you're testing for an error with + * mas_is_err(). + * + * Non-leaf nodes store the type of the node pointed to (enum maple_type in bits + * 3-6), bit 2 is reserved. That leaves bits 0-1 unused for now. + * + * In regular B-Tree terms, pivots are called keys. The term pivot is used to + * indicate that the tree is specifying ranges, Pivots may appear in the + * subtree with an entry attached to the value whereas keys are unique to a + * specific position of a B-tree. Pivot values are inclusive of the slot with + * the same index. + */ + +struct maple_range_64 { + struct maple_pnode *parent; + unsigned long pivot[MAPLE_RANGE64_SLOTS - 1]; + union { + void __rcu *slot[MAPLE_RANGE64_SLOTS]; + struct { + void __rcu *pad[MAPLE_RANGE64_SLOTS - 1]; + struct maple_metadata meta; + }; + }; +}; + +/* + * At tree creation time, the user can specify that they're willing to trade off + * storing fewer entries in a tree in return for storing more information in + * each node. + * + * The maple tree supports recording the largest range of NULL entries available + * in this node, also called gaps. This optimises the tree for allocating a + * range. + */ +struct maple_arange_64 { + struct maple_pnode *parent; + unsigned long pivot[MAPLE_ARANGE64_SLOTS - 1]; + void __rcu *slot[MAPLE_ARANGE64_SLOTS]; + unsigned long gap[MAPLE_ARANGE64_SLOTS]; + struct maple_metadata meta; +}; + +struct maple_alloc { + unsigned long total; + unsigned char node_count; + unsigned int request_count; + struct maple_alloc *slot[MAPLE_ALLOC_SLOTS]; +}; + +struct maple_topiary { + struct maple_pnode *parent; + struct maple_enode *next; /* Overlaps the pivot */ +}; + +enum maple_type { + maple_dense, + maple_leaf_64, + maple_range_64, + maple_arange_64, +}; + + +/** + * DOC: Maple tree flags + * + * * MT_FLAGS_ALLOC_RANGE - Track gaps in this tree + * * MT_FLAGS_USE_RCU - Operate in RCU mode + * * MT_FLAGS_HEIGHT_OFFSET - The position of the tree height in the flags + * * MT_FLAGS_HEIGHT_MASK - The mask for the maple tree height value + * * MT_FLAGS_LOCK_MASK - How the mt_lock is used + * * MT_FLAGS_LOCK_IRQ - Acquired irq-safe + * * MT_FLAGS_LOCK_BH - Acquired bh-safe + * * MT_FLAGS_LOCK_EXTERN - mt_lock is not used + * + * MAPLE_HEIGHT_MAX The largest height that can be stored + */ +#define MT_FLAGS_ALLOC_RANGE 0x01 +#define MT_FLAGS_USE_RCU 0x02 +#define MT_FLAGS_HEIGHT_OFFSET 0x02 +#define MT_FLAGS_HEIGHT_MASK 0x7C +#define MT_FLAGS_LOCK_MASK 0x300 +#define MT_FLAGS_LOCK_IRQ 0x100 +#define MT_FLAGS_LOCK_BH 0x200 +#define MT_FLAGS_LOCK_EXTERN 0x300 + +#define MAPLE_HEIGHT_MAX 31 + + +#define MAPLE_NODE_TYPE_MASK 0x0F +#define MAPLE_NODE_TYPE_SHIFT 0x03 + +#define MAPLE_RESERVED_RANGE 4096 + +#ifdef CONFIG_LOCKDEP +typedef struct lockdep_map *lockdep_map_p; +#define mt_lock_is_held(mt) lock_is_held(mt->ma_external_lock) +#define mt_set_external_lock(mt, lock) \ + (mt)->ma_external_lock = &(lock)->dep_map +#else +typedef struct { /* nothing */ } lockdep_map_p; +#define mt_lock_is_held(mt) 1 +#define mt_set_external_lock(mt, lock) do { } while (0) +#endif + +/* + * If the tree contains a single entry at index 0, it is usually stored in + * tree->ma_root. To optimise for the page cache, an entry which ends in '00', + * '01' or '11' is stored in the root, but an entry which ends in '10' will be + * stored in a node. Bits 3-6 are used to store enum maple_type. + * + * The flags are used both to store some immutable information about this tree + * (set at tree creation time) and dynamic information set under the spinlock. + * + * Another use of flags are to indicate global states of the tree. This is the + * case with the MAPLE_USE_RCU flag, which indicates the tree is currently in + * RCU mode. This mode was added to allow the tree to reuse nodes instead of + * re-allocating and RCU freeing nodes when there is a single user. + */ +struct maple_tree { + union { + spinlock_t ma_lock; + lockdep_map_p ma_external_lock; + }; + void __rcu *ma_root; + unsigned int ma_flags; +}; + +/** + * MTREE_INIT() - Initialize a maple tree + * @name: The maple tree name + * @__flags: The maple tree flags + * + */ +#define MTREE_INIT(name, __flags) { \ + .ma_lock = __SPIN_LOCK_UNLOCKED((name).ma_lock), \ + .ma_flags = __flags, \ + .ma_root = NULL, \ +} + +/** + * MTREE_INIT_EXT() - Initialize a maple tree with an external lock. + * @name: The tree name + * @__flags: The maple tree flags + * @__lock: The external lock + */ +#ifdef CONFIG_LOCKDEP +#define MTREE_INIT_EXT(name, __flags, __lock) { \ + .ma_external_lock = &(__lock).dep_map, \ + .ma_flags = (__flags), \ + .ma_root = NULL, \ +} +#else +#define MTREE_INIT_EXT(name, __flags, __lock) MTREE_INIT(name, __flags) +#endif + +#define DEFINE_MTREE(name) \ + struct maple_tree name = MTREE_INIT(name, 0) + +#define mtree_lock(mt) spin_lock((&(mt)->ma_lock)) +#define mtree_unlock(mt) spin_unlock((&(mt)->ma_lock)) + +/* + * The Maple Tree squeezes various bits in at various points which aren't + * necessarily obvious. Usually, this is done by observing that pointers are + * N-byte aligned and thus the bottom log_2(N) bits are available for use. We + * don't use the high bits of pointers to store additional information because + * we don't know what bits are unused on any given architecture. + * + * Nodes are 256 bytes in size and are also aligned to 256 bytes, giving us 8 + * low bits for our own purposes. Nodes are currently of 4 types: + * 1. Single pointer (Range is 0-0) + * 2. Non-leaf Allocation Range nodes + * 3. Non-leaf Range nodes + * 4. Leaf Range nodes All nodes consist of a number of node slots, + * pivots, and a parent pointer. + */ + +struct maple_node { + union { + struct { + struct maple_pnode *parent; + void __rcu *slot[MAPLE_NODE_SLOTS]; + }; + struct { + void *pad; + struct rcu_head rcu; + struct maple_enode *piv_parent; + unsigned char parent_slot; + enum maple_type type; + unsigned char slot_len; + unsigned int ma_flags; + }; + struct maple_range_64 mr64; + struct maple_arange_64 ma64; + struct maple_alloc alloc; + }; +}; + +/* + * More complicated stores can cause two nodes to become one or three and + * potentially alter the height of the tree. Either half of the tree may need + * to be rebalanced against the other. The ma_topiary struct is used to track + * which nodes have been 'cut' from the tree so that the change can be done + * safely at a later date. This is done to support RCU. + */ +struct ma_topiary { + struct maple_enode *head; + struct maple_enode *tail; + struct maple_tree *mtree; +}; + +void *mtree_load(struct maple_tree *mt, unsigned long index); + +int mtree_insert(struct maple_tree *mt, unsigned long index, + void *entry, gfp_t gfp); +int mtree_insert_range(struct maple_tree *mt, unsigned long first, + unsigned long last, void *entry, gfp_t gfp); +int mtree_alloc_range(struct maple_tree *mt, unsigned long *startp, + void *entry, unsigned long size, unsigned long min, + unsigned long max, gfp_t gfp); +int mtree_alloc_rrange(struct maple_tree *mt, unsigned long *startp, + void *entry, unsigned long size, unsigned long min, + unsigned long max, gfp_t gfp); + +int mtree_store_range(struct maple_tree *mt, unsigned long first, + unsigned long last, void *entry, gfp_t gfp); +int mtree_store(struct maple_tree *mt, unsigned long index, + void *entry, gfp_t gfp); +void *mtree_erase(struct maple_tree *mt, unsigned long index); + +void mtree_destroy(struct maple_tree *mt); +void __mt_destroy(struct maple_tree *mt); + +/** + * mtree_empty() - Determine if a tree has any present entries. + * @mt: Maple Tree. + * + * Context: Any context. + * Return: %true if the tree contains only NULL pointers. + */ +static inline bool mtree_empty(const struct maple_tree *mt) +{ + return mt->ma_root == NULL; +} + +/* Advanced API */ + +/* + * The maple state is defined in the struct ma_state and is used to keep track + * of information during operations, and even between operations when using the + * advanced API. + * + * If state->node has bit 0 set then it references a tree location which is not + * a node (eg the root). If bit 1 is set, the rest of the bits are a negative + * errno. Bit 2 (the 'unallocated slots' bit) is clear. Bits 3-6 indicate the + * node type. + * + * state->alloc either has a request number of nodes or an allocated node. If + * stat->alloc has a requested number of nodes, the first bit will be set (0x1) + * and the remaining bits are the value. If state->alloc is a node, then the + * node will be of type maple_alloc. maple_alloc has MAPLE_NODE_SLOTS - 1 for + * storing more allocated nodes, a total number of nodes allocated, and the + * node_count in this node. node_count is the number of allocated nodes in this + * node. The scaling beyond MAPLE_NODE_SLOTS - 1 is handled by storing further + * nodes into state->alloc->slot[0]'s node. Nodes are taken from state->alloc + * by removing a node from the state->alloc node until state->alloc->node_count + * is 1, when state->alloc is returned and the state->alloc->slot[0] is promoted + * to state->alloc. Nodes are pushed onto state->alloc by putting the current + * state->alloc into the pushed node's slot[0]. + * + * The state also contains the implied min/max of the state->node, the depth of + * this search, and the offset. The implied min/max are either from the parent + * node or are 0-oo for the root node. The depth is incremented or decremented + * every time a node is walked down or up. The offset is the slot/pivot of + * interest in the node - either for reading or writing. + * + * When returning a value the maple state index and last respectively contain + * the start and end of the range for the entry. Ranges are inclusive in the + * Maple Tree. + */ +struct ma_state { + struct maple_tree *tree; /* The tree we're operating in */ + unsigned long index; /* The index we're operating on - range start */ + unsigned long last; /* The last index we're operating on - range end */ + struct maple_enode *node; /* The node containing this entry */ + unsigned long min; /* The minimum index of this node - implied pivot min */ + unsigned long max; /* The maximum index of this node - implied pivot max */ + struct maple_alloc *alloc; /* Allocated nodes for this operation */ + unsigned char depth; /* depth of tree descent during write */ + unsigned char offset; + unsigned char mas_flags; +}; + +struct ma_wr_state { + struct ma_state *mas; + struct maple_node *node; /* Decoded mas->node */ + unsigned long r_min; /* range min */ + unsigned long r_max; /* range max */ + enum maple_type type; /* mas->node type */ + unsigned char offset_end; /* The offset where the write ends */ + unsigned char node_end; /* mas->node end */ + unsigned long *pivots; /* mas->node->pivots pointer */ + unsigned long end_piv; /* The pivot at the offset end */ + void __rcu **slots; /* mas->node->slots pointer */ + void *entry; /* The entry to write */ + void *content; /* The existing entry that is being overwritten */ +}; + +#define mas_lock(mas) spin_lock(&((mas)->tree->ma_lock)) +#define mas_unlock(mas) spin_unlock(&((mas)->tree->ma_lock)) + + +/* + * Special values for ma_state.node. + * MAS_START means we have not searched the tree. + * MAS_ROOT means we have searched the tree and the entry we found lives in + * the root of the tree (ie it has index 0, length 1 and is the only entry in + * the tree). + * MAS_NONE means we have searched the tree and there is no node in the + * tree for this entry. For example, we searched for index 1 in an empty + * tree. Or we have a tree which points to a full leaf node and we + * searched for an entry which is larger than can be contained in that + * leaf node. + * MA_ERROR represents an errno. After dropping the lock and attempting + * to resolve the error, the walk would have to be restarted from the + * top of the tree as the tree may have been modified. + */ +#define MAS_START ((struct maple_enode *)1UL) +#define MAS_ROOT ((struct maple_enode *)5UL) +#define MAS_NONE ((struct maple_enode *)9UL) +#define MAS_PAUSE ((struct maple_enode *)17UL) +#define MA_ERROR(err) \ + ((struct maple_enode *)(((unsigned long)err << 2) | 2UL)) + +#define MA_STATE(name, mt, first, end) \ + struct ma_state name = { \ + .tree = mt, \ + .index = first, \ + .last = end, \ + .node = MAS_START, \ + .min = 0, \ + .max = ULONG_MAX, \ + .alloc = NULL, \ + } + +#define MA_WR_STATE(name, ma_state, wr_entry) \ + struct ma_wr_state name = { \ + .mas = ma_state, \ + .content = NULL, \ + .entry = wr_entry, \ + } + +#define MA_TOPIARY(name, tree) \ + struct ma_topiary name = { \ + .head = NULL, \ + .tail = NULL, \ + .mtree = tree, \ + } + +void *mas_walk(struct ma_state *mas); +void *mas_store(struct ma_state *mas, void *entry); +void *mas_erase(struct ma_state *mas); +int mas_store_gfp(struct ma_state *mas, void *entry, gfp_t gfp); +void mas_store_prealloc(struct ma_state *mas, void *entry); +void *mas_find(struct ma_state *mas, unsigned long max); +void *mas_find_rev(struct ma_state *mas, unsigned long min); +int mas_preallocate(struct ma_state *mas, void *entry, gfp_t gfp); +bool mas_is_err(struct ma_state *mas); + +bool mas_nomem(struct ma_state *mas, gfp_t gfp); +void mas_pause(struct ma_state *mas); +void maple_tree_init(void); +void mas_destroy(struct ma_state *mas); +int mas_expected_entries(struct ma_state *mas, unsigned long nr_entries); + +void *mas_prev(struct ma_state *mas, unsigned long min); +void *mas_next(struct ma_state *mas, unsigned long max); + +int mas_empty_area(struct ma_state *mas, unsigned long min, unsigned long max, + unsigned long size); + +/* Checks if a mas has not found anything */ +static inline bool mas_is_none(struct ma_state *mas) +{ + return mas->node == MAS_NONE; +} + +/* Checks if a mas has been paused */ +static inline bool mas_is_paused(struct ma_state *mas) +{ + return mas->node == MAS_PAUSE; +} + +void mas_dup_tree(struct ma_state *oldmas, struct ma_state *mas); +void mas_dup_store(struct ma_state *mas, void *entry); + +/* + * This finds an empty area from the highest address to the lowest. + * AKA "Topdown" version, + */ +int mas_empty_area_rev(struct ma_state *mas, unsigned long min, + unsigned long max, unsigned long size); +/** + * mas_reset() - Reset a Maple Tree operation state. + * @mas: Maple Tree operation state. + * + * Resets the error or walk state of the @mas so future walks of the + * array will start from the root. Use this if you have dropped the + * lock and want to reuse the ma_state. + * + * Context: Any context. + */ +static inline void mas_reset(struct ma_state *mas) +{ + mas->node = MAS_START; +} + +/** + * mas_for_each() - Iterate over a range of the maple tree. + * @__mas: Maple Tree operation state (maple_state) + * @__entry: Entry retrieved from the tree + * @__max: maximum index to retrieve from the tree + * + * When returned, mas->index and mas->last will hold the entire range for the + * entry. + * + * Note: may return the zero entry. + * + */ +#define mas_for_each(__mas, __entry, __max) \ + while (((__entry) = mas_find((__mas), (__max))) != NULL) + + +/** + * mas_set_range() - Set up Maple Tree operation state for a different index. + * @mas: Maple Tree operation state. + * @start: New start of range in the Maple Tree. + * @last: New end of range in the Maple Tree. + * + * Move the operation state to refer to a different range. This will + * have the effect of starting a walk from the top; see mas_next() + * to move to an adjacent index. + */ +static inline +void mas_set_range(struct ma_state *mas, unsigned long start, unsigned long last) +{ + mas->index = start; + mas->last = last; + mas->node = MAS_START; +} + +/** + * mas_set() - Set up Maple Tree operation state for a different index. + * @mas: Maple Tree operation state. + * @index: New index into the Maple Tree. + * + * Move the operation state to refer to a different index. This will + * have the effect of starting a walk from the top; see mas_next() + * to move to an adjacent index. + */ +static inline void mas_set(struct ma_state *mas, unsigned long index) +{ + + mas_set_range(mas, index, index); +} + +static inline bool mt_external_lock(const struct maple_tree *mt) +{ + return (mt->ma_flags & MT_FLAGS_LOCK_MASK) == MT_FLAGS_LOCK_EXTERN; +} + +/** + * mt_init_flags() - Initialise an empty maple tree with flags. + * @mt: Maple Tree + * @flags: maple tree flags. + * + * If you need to initialise a Maple Tree with special flags (eg, an + * allocation tree), use this function. + * + * Context: Any context. + */ +static inline void mt_init_flags(struct maple_tree *mt, unsigned int flags) +{ + mt->ma_flags = flags; + if (!mt_external_lock(mt)) + spin_lock_init(&mt->ma_lock); + rcu_assign_pointer(mt->ma_root, NULL); +} + +/** + * mt_init() - Initialise an empty maple tree. + * @mt: Maple Tree + * + * An empty Maple Tree. + * + * Context: Any context. + */ +static inline void mt_init(struct maple_tree *mt) +{ + mt_init_flags(mt, 0); +} + +static inline bool mt_in_rcu(struct maple_tree *mt) +{ +#ifdef CONFIG_MAPLE_RCU_DISABLED + return false; +#endif + return mt->ma_flags & MT_FLAGS_USE_RCU; +} + +/** + * mt_clear_in_rcu() - Switch the tree to non-RCU mode. + * @mt: The Maple Tree + */ +static inline void mt_clear_in_rcu(struct maple_tree *mt) +{ + if (!mt_in_rcu(mt)) + return; + + if (mt_external_lock(mt)) { + BUG_ON(!mt_lock_is_held(mt)); + mt->ma_flags &= ~MT_FLAGS_USE_RCU; + } else { + mtree_lock(mt); + mt->ma_flags &= ~MT_FLAGS_USE_RCU; + mtree_unlock(mt); + } +} + +/** + * mt_set_in_rcu() - Switch the tree to RCU safe mode. + * @mt: The Maple Tree + */ +static inline void mt_set_in_rcu(struct maple_tree *mt) +{ + if (mt_in_rcu(mt)) + return; + + if (mt_external_lock(mt)) { + BUG_ON(!mt_lock_is_held(mt)); + mt->ma_flags |= MT_FLAGS_USE_RCU; + } else { + mtree_lock(mt); + mt->ma_flags |= MT_FLAGS_USE_RCU; + mtree_unlock(mt); + } +} + +static inline unsigned int mt_height(const struct maple_tree *mt) + +{ + return (mt->ma_flags & MT_FLAGS_HEIGHT_MASK) >> MT_FLAGS_HEIGHT_OFFSET; +} + +void *mt_find(struct maple_tree *mt, unsigned long *index, unsigned long max); +void *mt_find_after(struct maple_tree *mt, unsigned long *index, + unsigned long max); +void *mt_prev(struct maple_tree *mt, unsigned long index, unsigned long min); +void *mt_next(struct maple_tree *mt, unsigned long index, unsigned long max); + +/** + * mt_for_each - Iterate over each entry starting at index until max. + * @__tree: The Maple Tree + * @__entry: The current entry + * @__index: The index to update to track the location in the tree + * @__max: The maximum limit for @index + * + * Note: Will not return the zero entry. + */ +#define mt_for_each(__tree, __entry, __index, __max) \ + for (__entry = mt_find(__tree, &(__index), __max); \ + __entry; __entry = mt_find_after(__tree, &(__index), __max)) + + +#ifdef CONFIG_DEBUG_MAPLE_TREE +extern atomic_t maple_tree_tests_run; +extern atomic_t maple_tree_tests_passed; + +void mt_dump(const struct maple_tree *mt); +void mt_validate(struct maple_tree *mt); +void mt_cache_shrink(void); +#define MT_BUG_ON(__tree, __x) do { \ + atomic_inc(&maple_tree_tests_run); \ + if (__x) { \ + pr_info("BUG at %s:%d (%u)\n", \ + __func__, __LINE__, __x); \ + mt_dump(__tree); \ + pr_info("Pass: %u Run:%u\n", \ + atomic_read(&maple_tree_tests_passed), \ + atomic_read(&maple_tree_tests_run)); \ + dump_stack(); \ + } else { \ + atomic_inc(&maple_tree_tests_passed); \ + } \ +} while (0) +#else +#define MT_BUG_ON(__tree, __x) BUG_ON(__x) +#endif /* CONFIG_DEBUG_MAPLE_TREE */ + +#endif /*_LINUX_MAPLE_TREE_H */ diff --git a/include/linux/math.h b/include/linux/math.h index 53674a327e39..439b8f0b9ebd 100644 --- a/include/linux/math.h +++ b/include/linux/math.h @@ -2,6 +2,7 @@ #ifndef _LINUX_MATH_H #define _LINUX_MATH_H +#include <linux/types.h> #include <asm/div64.h> #include <uapi/linux/kernel.h> @@ -106,6 +107,17 @@ } \ ) +#define __STRUCT_FRACT(type) \ +struct type##_fract { \ + __##type numerator; \ + __##type denominator; \ +}; +__STRUCT_FRACT(s16) +__STRUCT_FRACT(u16) +__STRUCT_FRACT(s32) +__STRUCT_FRACT(u32) +#undef __STRUCT_FRACT + /* * Multiplies an integer by a fraction, while avoiding unnecessary * overflow or loss of precision. diff --git a/include/linux/math64.h b/include/linux/math64.h index 2928f03d6d46..a14f40de1dca 100644 --- a/include/linux/math64.h +++ b/include/linux/math64.h @@ -301,6 +301,19 @@ u64 mul_u64_u64_div_u64(u64 a, u64 mul, u64 div); ({ u64 _tmp = (divisor); div64_u64((dividend) + _tmp / 2, _tmp); }) /* + * DIV_U64_ROUND_CLOSEST - unsigned 64bit divide with 32bit divisor rounded to nearest integer + * @dividend: unsigned 64bit dividend + * @divisor: unsigned 32bit divisor + * + * Divide unsigned 64bit dividend by unsigned 32bit divisor + * and round to closest integer. + * + * Return: dividend / divisor rounded to nearest integer + */ +#define DIV_U64_ROUND_CLOSEST(dividend, divisor) \ + ({ u32 _tmp = (divisor); div_u64((u64)(dividend) + _tmp / 2, _tmp); }) + +/* * DIV_S64_ROUND_CLOSEST - signed 64bit divide with 32bit divisor rounded to nearest integer * @dividend: signed 64bit dividend * @divisor: signed 32bit divisor diff --git a/include/linux/mbcache.h b/include/linux/mbcache.h index 20f1e3ff6013..2da63fd7b98f 100644 --- a/include/linux/mbcache.h +++ b/include/linux/mbcache.h @@ -13,8 +13,16 @@ struct mb_cache; struct mb_cache_entry { /* List of entries in cache - protected by cache->c_list_lock */ struct list_head e_list; - /* Hash table list - protected by hash chain bitlock */ + /* + * Hash table list - protected by hash chain bitlock. The entry is + * guaranteed to be hashed while e_refcnt > 0. + */ struct hlist_bl_node e_hash_list; + /* + * Entry refcount. Once it reaches zero, entry is unhashed and freed. + * While refcount > 0, the entry is guaranteed to stay in the hash and + * e.g. mb_cache_entry_try_delete() will fail. + */ atomic_t e_refcnt; /* Key in hash - stable during lifetime of the entry */ u32 e_key; @@ -29,17 +37,24 @@ void mb_cache_destroy(struct mb_cache *cache); int mb_cache_entry_create(struct mb_cache *cache, gfp_t mask, u32 key, u64 value, bool reusable); -void __mb_cache_entry_free(struct mb_cache_entry *entry); -static inline int mb_cache_entry_put(struct mb_cache *cache, - struct mb_cache_entry *entry) +void __mb_cache_entry_free(struct mb_cache *cache, + struct mb_cache_entry *entry); +void mb_cache_entry_wait_unused(struct mb_cache_entry *entry); +static inline void mb_cache_entry_put(struct mb_cache *cache, + struct mb_cache_entry *entry) { - if (!atomic_dec_and_test(&entry->e_refcnt)) - return 0; - __mb_cache_entry_free(entry); - return 1; + unsigned int cnt = atomic_dec_return(&entry->e_refcnt); + + if (cnt > 0) { + if (cnt <= 2) + wake_up_var(&entry->e_refcnt); + return; + } + __mb_cache_entry_free(cache, entry); } -void mb_cache_entry_delete(struct mb_cache *cache, u32 key, u64 value); +struct mb_cache_entry *mb_cache_entry_delete_or_get(struct mb_cache *cache, + u32 key, u64 value); struct mb_cache_entry *mb_cache_entry_get(struct mb_cache *cache, u32 key, u64 value); struct mb_cache_entry *mb_cache_entry_find_first(struct mb_cache *cache, diff --git a/include/linux/mc146818rtc.h b/include/linux/mc146818rtc.h index 0661af17a758..b0da04fe087b 100644 --- a/include/linux/mc146818rtc.h +++ b/include/linux/mc146818rtc.h @@ -86,6 +86,8 @@ struct cmos_rtc_board_info { /* 2 values for divider stage reset, others for "testing purposes only" */ # define RTC_DIV_RESET1 0x60 # define RTC_DIV_RESET2 0x70 + /* In AMD BKDG bit 5 and 6 are reserved, bit 4 is for select dv0 bank */ +# define RTC_AMD_BANK_SELECT 0x10 /* Periodic intr. / Square wave rate select. 0=none, 1=32.8kHz,... 15=2Hz */ # define RTC_RATE_SELECT 0x0F @@ -123,7 +125,11 @@ struct cmos_rtc_board_info { #define RTC_IO_EXTENT_USED RTC_IO_EXTENT #endif /* ARCH_RTC_LOCATION */ -unsigned int mc146818_get_time(struct rtc_time *time); +bool mc146818_does_rtc_work(void); +int mc146818_get_time(struct rtc_time *time); int mc146818_set_time(struct rtc_time *time); +bool mc146818_avoid_UIP(void (*callback)(unsigned char seconds, void *param), + void *param); + #endif /* _MC146818RTC_H */ diff --git a/include/linux/mdev.h b/include/linux/mdev.h index 15d03f6532d0..139d05b26f82 100644 --- a/include/linux/mdev.h +++ b/include/linux/mdev.h @@ -10,156 +10,80 @@ #ifndef MDEV_H #define MDEV_H +#include <linux/device.h> +#include <linux/uuid.h> + struct mdev_type; struct mdev_device { struct device dev; guid_t uuid; - void *driver_data; struct list_head next; struct mdev_type *type; bool active; }; -static inline struct mdev_device *to_mdev_device(struct device *dev) -{ - return container_of(dev, struct mdev_device, dev); -} - -unsigned int mdev_get_type_group_id(struct mdev_device *mdev); -unsigned int mtype_get_type_group_id(struct mdev_type *mtype); -struct device *mtype_get_parent_dev(struct mdev_type *mtype); +struct mdev_type { + /* set by the driver before calling mdev_register parent: */ + const char *sysfs_name; + const char *pretty_name; -/** - * struct mdev_parent_ops - Structure to be registered for each parent device to - * register the device to mdev module. - * - * @owner: The module owner. - * @device_driver: Which device driver to probe() on newly created devices - * @dev_attr_groups: Attributes of the parent device. - * @mdev_attr_groups: Attributes of the mediated device. - * @supported_type_groups: Attributes to define supported types. It is mandatory - * to provide supported types. - * @create: Called to allocate basic resources in parent device's - * driver for a particular mediated device. It is - * mandatory to provide create ops. - * @mdev: mdev_device structure on of mediated device - * that is being created - * Returns integer: success (0) or error (< 0) - * @remove: Called to free resources in parent device's driver for - * a mediated device. It is mandatory to provide 'remove' - * ops. - * @mdev: mdev_device device structure which is being - * destroyed - * Returns integer: success (0) or error (< 0) - * @read: Read emulation callback - * @mdev: mediated device structure - * @buf: read buffer - * @count: number of bytes to read - * @ppos: address. - * Retuns number on bytes read on success or error. - * @write: Write emulation callback - * @mdev: mediated device structure - * @buf: write buffer - * @count: number of bytes to be written - * @ppos: address. - * Retuns number on bytes written on success or error. - * @ioctl: IOCTL callback - * @mdev: mediated device structure - * @cmd: ioctl command - * @arg: arguments to ioctl - * @mmap: mmap callback - * @mdev: mediated device structure - * @vma: vma structure - * @request: request callback to release device - * @mdev: mediated device structure - * @count: request sequence number - * Parent device that support mediated device should be registered with mdev - * module with mdev_parent_ops structure. - **/ -struct mdev_parent_ops { - struct module *owner; - struct mdev_driver *device_driver; - const struct attribute_group **dev_attr_groups; - const struct attribute_group **mdev_attr_groups; - struct attribute_group **supported_type_groups; + /* set by the core, can be used drivers */ + struct mdev_parent *parent; - int (*create)(struct mdev_device *mdev); - int (*remove)(struct mdev_device *mdev); - int (*open_device)(struct mdev_device *mdev); - void (*close_device)(struct mdev_device *mdev); - ssize_t (*read)(struct mdev_device *mdev, char __user *buf, - size_t count, loff_t *ppos); - ssize_t (*write)(struct mdev_device *mdev, const char __user *buf, - size_t count, loff_t *ppos); - long (*ioctl)(struct mdev_device *mdev, unsigned int cmd, - unsigned long arg); - int (*mmap)(struct mdev_device *mdev, struct vm_area_struct *vma); - void (*request)(struct mdev_device *mdev, unsigned int count); + /* internal only */ + struct kobject kobj; + struct kobject *devices_kobj; }; -/* interface for exporting mdev supported type attributes */ -struct mdev_type_attribute { - struct attribute attr; - ssize_t (*show)(struct mdev_type *mtype, - struct mdev_type_attribute *attr, char *buf); - ssize_t (*store)(struct mdev_type *mtype, - struct mdev_type_attribute *attr, const char *buf, - size_t count); +/* embedded into the struct device that the mdev devices hang off */ +struct mdev_parent { + struct device *dev; + struct mdev_driver *mdev_driver; + struct kset *mdev_types_kset; + /* Synchronize device creation/removal with parent unregistration */ + struct rw_semaphore unreg_sem; + struct mdev_type **types; + unsigned int nr_types; + atomic_t available_instances; }; -#define MDEV_TYPE_ATTR(_name, _mode, _show, _store) \ -struct mdev_type_attribute mdev_type_attr_##_name = \ - __ATTR(_name, _mode, _show, _store) -#define MDEV_TYPE_ATTR_RW(_name) \ - struct mdev_type_attribute mdev_type_attr_##_name = __ATTR_RW(_name) -#define MDEV_TYPE_ATTR_RO(_name) \ - struct mdev_type_attribute mdev_type_attr_##_name = __ATTR_RO(_name) -#define MDEV_TYPE_ATTR_WO(_name) \ - struct mdev_type_attribute mdev_type_attr_##_name = __ATTR_WO(_name) +static inline struct mdev_device *to_mdev_device(struct device *dev) +{ + return container_of(dev, struct mdev_device, dev); +} /** * struct mdev_driver - Mediated device driver + * @device_api: string to return for the device_api sysfs + * @max_instances: maximum number of instances supported (optional) * @probe: called when new device created * @remove: called when device removed + * @get_available: Return the max number of instances that can be created + * @show_description: Print a description of the mtype * @driver: device driver structure - * **/ struct mdev_driver { + const char *device_api; + unsigned int max_instances; int (*probe)(struct mdev_device *dev); void (*remove)(struct mdev_device *dev); + unsigned int (*get_available)(struct mdev_type *mtype); + ssize_t (*show_description)(struct mdev_type *mtype, char *buf); struct device_driver driver; }; -static inline void *mdev_get_drvdata(struct mdev_device *mdev) -{ - return mdev->driver_data; -} -static inline void mdev_set_drvdata(struct mdev_device *mdev, void *data) -{ - mdev->driver_data = data; -} -static inline const guid_t *mdev_uuid(struct mdev_device *mdev) -{ - return &mdev->uuid; -} - -extern struct bus_type mdev_bus_type; - -int mdev_register_device(struct device *dev, const struct mdev_parent_ops *ops); -void mdev_unregister_device(struct device *dev); +int mdev_register_parent(struct mdev_parent *parent, struct device *dev, + struct mdev_driver *mdev_driver, struct mdev_type **types, + unsigned int nr_types); +void mdev_unregister_parent(struct mdev_parent *parent); int mdev_register_driver(struct mdev_driver *drv); void mdev_unregister_driver(struct mdev_driver *drv); -struct device *mdev_parent_dev(struct mdev_device *mdev); static inline struct device *mdev_dev(struct mdev_device *mdev) { return &mdev->dev; } -static inline struct mdev_device *mdev_from_dev(struct device *dev) -{ - return dev->bus == &mdev_bus_type ? to_mdev_device(dev) : NULL; -} #endif /* MDEV_H */ diff --git a/include/linux/mdio.h b/include/linux/mdio.h index ecac96d52e01..00177567cfef 100644 --- a/include/linux/mdio.h +++ b/include/linux/mdio.h @@ -340,6 +340,76 @@ static inline void mii_10gbt_stat_mod_linkmode_lpa_t(unsigned long *advertising, advertising, lpa & MDIO_AN_10GBT_STAT_LP10G); } +/** + * mii_t1_adv_l_mod_linkmode_t + * @advertising: target the linkmode advertisement settings + * @lpa: value of the BASE-T1 Autonegotiation Advertisement [15:0] Register + * + * A small helper function that translates BASE-T1 Autonegotiation + * Advertisement [15:0] Register bits to linkmode advertisement settings. + * Other bits in advertising aren't changed. + */ +static inline void mii_t1_adv_l_mod_linkmode_t(unsigned long *advertising, u32 lpa) +{ + linkmode_mod_bit(ETHTOOL_LINK_MODE_Pause_BIT, advertising, + lpa & MDIO_AN_T1_ADV_L_PAUSE_CAP); + linkmode_mod_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, advertising, + lpa & MDIO_AN_T1_ADV_L_PAUSE_ASYM); +} + +/** + * mii_t1_adv_m_mod_linkmode_t + * @advertising: target the linkmode advertisement settings + * @lpa: value of the BASE-T1 Autonegotiation Advertisement [31:16] Register + * + * A small helper function that translates BASE-T1 Autonegotiation + * Advertisement [31:16] Register bits to linkmode advertisement settings. + * Other bits in advertising aren't changed. + */ +static inline void mii_t1_adv_m_mod_linkmode_t(unsigned long *advertising, u32 lpa) +{ + linkmode_mod_bit(ETHTOOL_LINK_MODE_10baseT1L_Full_BIT, + advertising, lpa & MDIO_AN_T1_ADV_M_B10L); +} + +/** + * linkmode_adv_to_mii_t1_adv_l_t + * @advertising: the linkmode advertisement settings + * + * A small helper function that translates linkmode advertisement + * settings to phy autonegotiation advertisements for the + * BASE-T1 Autonegotiation Advertisement [15:0] Register. + */ +static inline u32 linkmode_adv_to_mii_t1_adv_l_t(unsigned long *advertising) +{ + u32 result = 0; + + if (linkmode_test_bit(ETHTOOL_LINK_MODE_Pause_BIT, advertising)) + result |= MDIO_AN_T1_ADV_L_PAUSE_CAP; + if (linkmode_test_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, advertising)) + result |= MDIO_AN_T1_ADV_L_PAUSE_ASYM; + + return result; +} + +/** + * linkmode_adv_to_mii_t1_adv_m_t + * @advertising: the linkmode advertisement settings + * + * A small helper function that translates linkmode advertisement + * settings to phy autonegotiation advertisements for the + * BASE-T1 Autonegotiation Advertisement [31:16] Register. + */ +static inline u32 linkmode_adv_to_mii_t1_adv_m_t(unsigned long *advertising) +{ + u32 result = 0; + + if (linkmode_test_bit(ETHTOOL_LINK_MODE_10baseT1L_Full_BIT, advertising)) + result |= MDIO_AN_T1_ADV_M_B10L; + + return result; +} + int __mdiobus_read(struct mii_bus *bus, int addr, u32 regnum); int __mdiobus_write(struct mii_bus *bus, int addr, u32 regnum, u16 val); int __mdiobus_modify_changed(struct mii_bus *bus, int addr, u32 regnum, diff --git a/include/linux/mdio/mdio-i2c.h b/include/linux/mdio/mdio-i2c.h index b1d27f7cd23f..65b550a6fc32 100644 --- a/include/linux/mdio/mdio-i2c.h +++ b/include/linux/mdio/mdio-i2c.h @@ -11,6 +11,14 @@ struct device; struct i2c_adapter; struct mii_bus; -struct mii_bus *mdio_i2c_alloc(struct device *parent, struct i2c_adapter *i2c); +enum mdio_i2c_proto { + MDIO_I2C_NONE, + MDIO_I2C_MARVELL_C22, + MDIO_I2C_C45, + MDIO_I2C_ROLLBALL, +}; + +struct mii_bus *mdio_i2c_alloc(struct device *parent, struct i2c_adapter *i2c, + enum mdio_i2c_proto protocol); #endif diff --git a/include/linux/mdio/mdio-xgene.h b/include/linux/mdio/mdio-xgene.h index 8af93ada8b64..9e588965dc83 100644 --- a/include/linux/mdio/mdio-xgene.h +++ b/include/linux/mdio/mdio-xgene.h @@ -8,6 +8,10 @@ #ifndef __MDIO_XGENE_H__ #define __MDIO_XGENE_H__ +#include <linux/bits.h> +#include <linux/spinlock.h> +#include <linux/types.h> + #define BLOCK_XG_MDIO_CSR_OFFSET 0x5000 #define BLOCK_DIAG_CSR_OFFSET 0xd000 #define XGENET_CONFIG_REG_ADDR 0x20 diff --git a/include/linux/mei_aux.h b/include/linux/mei_aux.h new file mode 100644 index 000000000000..506912ad363b --- /dev/null +++ b/include/linux/mei_aux.h @@ -0,0 +1,31 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2022, Intel Corporation. All rights reserved. + */ +#ifndef _LINUX_MEI_AUX_H +#define _LINUX_MEI_AUX_H + +#include <linux/auxiliary_bus.h> + +/** + * struct mei_aux_device - mei auxiliary device + * @aux_dev: - auxiliary device object + * @irq: interrupt driving the mei auxiliary device + * @bar: mmio resource bar reserved to mei auxiliary device + * @ext_op_mem: resource for extend operational memory + * used in graphics PXP mode. + * @slow_firmware: The device has slow underlying firmware. + * Such firmware will require to use larger operation timeouts. + */ +struct mei_aux_device { + struct auxiliary_device aux_dev; + int irq; + struct resource bar; + struct resource ext_op_mem; + bool slow_firmware; +}; + +#define auxiliary_dev_to_mei_aux_dev(auxiliary_dev) \ + container_of(auxiliary_dev, struct mei_aux_device, aux_dev) + +#endif /* _LINUX_MEI_AUX_H */ diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 9dc7cb239d21..50ad19662a32 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -1,7 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0-or-later */ #ifndef _LINUX_MEMBLOCK_H #define _LINUX_MEMBLOCK_H -#ifdef __KERNEL__ /* * Logical memory blocks. @@ -605,6 +604,5 @@ static inline void early_memtest(phys_addr_t start, phys_addr_t end) } #endif -#endif /* __KERNEL__ */ #endif /* _LINUX_MEMBLOCK_H */ diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index e34112f6a369..e1644a24009c 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -33,6 +33,10 @@ enum memcg_stat_item { MEMCG_SWAP = NR_VM_NODE_STAT_ITEMS, MEMCG_SOCK, MEMCG_PERCPU_B, + MEMCG_VMALLOC, + MEMCG_KMEM, + MEMCG_ZSWAP_B, + MEMCG_ZSWAPPED, MEMCG_NR_STAT, }; @@ -42,6 +46,7 @@ enum memcg_memory_event { MEMCG_MAX, MEMCG_OOM, MEMCG_OOM_KILL, + MEMCG_OOM_GROUP_KILL, MEMCG_SWAP_HIGH, MEMCG_SWAP_MAX, MEMCG_SWAP_FAIL, @@ -75,29 +80,8 @@ enum mem_cgroup_events_target { MEM_CGROUP_NTARGETS, }; -struct memcg_vmstats_percpu { - /* Local (CPU and cgroup) page state & events */ - long state[MEMCG_NR_STAT]; - unsigned long events[NR_VM_EVENT_ITEMS]; - - /* Delta calculation for lockless upward propagation */ - long state_prev[MEMCG_NR_STAT]; - unsigned long events_prev[NR_VM_EVENT_ITEMS]; - - /* Cgroup1: threshold notifications & softlimit tree updates */ - unsigned long nr_page_events; - unsigned long targets[MEM_CGROUP_NTARGETS]; -}; - -struct memcg_vmstats { - /* Aggregated (CPU and subtree) page state & events */ - long state[MEMCG_NR_STAT]; - unsigned long events[NR_VM_EVENT_ITEMS]; - - /* Pending child counts during tree propagation */ - long state_pending[MEMCG_NR_STAT]; - unsigned long events_pending[NR_VM_EVENT_ITEMS]; -}; +struct memcg_vmstats_percpu; +struct memcg_vmstats; struct mem_cgroup_reclaim_iter { struct mem_cgroup *position; @@ -180,15 +164,6 @@ struct mem_cgroup_thresholds { struct mem_cgroup_threshold_ary *spare; }; -#if defined(CONFIG_SMP) -struct memcg_padding { - char x[0]; -} ____cacheline_internodealigned_in_smp; -#define MEMCG_PADDING(name) struct memcg_padding name -#else -#define MEMCG_PADDING(name) -#endif - /* * Remember four most recent foreign writebacks with dirty pages in this * cgroup. Inode sharing is expected to be uncommon and, even if we miss @@ -217,7 +192,7 @@ struct obj_cgroup { struct mem_cgroup *memcg; atomic_t nr_charged_bytes; union { - struct list_head list; + struct list_head list; /* protected by objcg_lock */ struct rcu_head rcu; }; }; @@ -249,6 +224,10 @@ struct mem_cgroup { /* Range enforcement for interrupt charges */ struct work_struct high_work; +#if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_ZSWAP) + unsigned long zswap_max; +#endif + unsigned long soft_limit; /* vmpressure notifications */ @@ -295,10 +274,10 @@ struct mem_cgroup { spinlock_t move_lock; unsigned long move_lock_flags; - MEMCG_PADDING(_pad1_); + CACHELINE_PADDING(_pad1_); /* memory.stat */ - struct memcg_vmstats vmstats; + struct memcg_vmstats *vmstats; /* memory.events */ atomic_long_t memory_events[MEMCG_NR_MEMORY_EVENTS]; @@ -313,10 +292,11 @@ struct mem_cgroup { #ifdef CONFIG_MEMCG_KMEM int kmemcg_id; struct obj_cgroup __rcu *objcg; - struct list_head objcg_list; /* list of inherited objcgs */ + /* list of inherited objcgs, protected by objcg_lock */ + struct list_head objcg_list; #endif - MEMCG_PADDING(_pad2_); + CACHELINE_PADDING(_pad2_); /* * set > 0 if pages under this cgroup are moving to other cgroup. @@ -340,14 +320,20 @@ struct mem_cgroup { struct deferred_split deferred_split_queue; #endif +#ifdef CONFIG_LRU_GEN + /* per-memcg mm_struct list */ + struct lru_gen_mm_list mm_list; +#endif + struct mem_cgroup_per_node *nodeinfo[]; }; /* - * size of first charge trial. "32" comes from vmscan.c's magic value. - * TODO: maybe necessary to use big numbers in big irons. + * size of first charge trial. + * TODO: maybe necessary to use big numbers in big irons or dynamic based of the + * workload. */ -#define MEMCG_CHARGE_BATCH 32U +#define MEMCG_CHARGE_BATCH 64U extern struct mem_cgroup *root_mem_cgroup; @@ -434,6 +420,7 @@ static inline struct obj_cgroup *__folio_objcg(struct folio *folio) * - LRU isolation * - lock_page_memcg() * - exclusive reference + * - mem_cgroup_trylock_pages() * * For a kmem folio a caller should hold an rcu read lock to protect memcg * associated with a kmem folio from being released. @@ -495,6 +482,7 @@ static inline struct mem_cgroup *folio_memcg_rcu(struct folio *folio) * - LRU isolation * - lock_page_memcg() * - exclusive reference + * - mem_cgroup_trylock_pages() * * For a kmem page a caller should hold an rcu read lock to protect memcg * associated with a kmem page from being released. @@ -520,6 +508,20 @@ static inline struct mem_cgroup *page_memcg_check(struct page *page) return (struct mem_cgroup *)(memcg_data & ~MEMCG_DATA_FLAGS_MASK); } +static inline struct mem_cgroup *get_mem_cgroup_from_objcg(struct obj_cgroup *objcg) +{ + struct mem_cgroup *memcg; + + rcu_read_lock(); +retry: + memcg = obj_cgroup_memcg(objcg); + if (unlikely(!css_tryget(&memcg->css))) + goto retry; + rcu_read_unlock(); + + return memcg; +} + #ifdef CONFIG_MEMCG_KMEM /* * folio_memcg_kmem - Check if the folio has the memcg_kmem flag set. @@ -665,7 +667,7 @@ static inline int mem_cgroup_charge(struct folio *folio, struct mm_struct *mm, return __mem_cgroup_charge(folio, mm, gfp); } -int mem_cgroup_swapin_charge_page(struct page *page, struct mm_struct *mm, +int mem_cgroup_swapin_charge_folio(struct folio *folio, struct mm_struct *mm, gfp_t gfp, swp_entry_t entry); void mem_cgroup_swapin_uncharge_swap(swp_entry_t entry); @@ -813,6 +815,15 @@ static inline unsigned short mem_cgroup_id(struct mem_cgroup *memcg) } struct mem_cgroup *mem_cgroup_from_id(unsigned short id); +#ifdef CONFIG_SHRINKER_DEBUG +static inline unsigned long mem_cgroup_ino(struct mem_cgroup *memcg) +{ + return memcg ? cgroup_ino(memcg->css.cgroup) : 0; +} + +struct mem_cgroup *mem_cgroup_get_from_ino(unsigned long ino); +#endif + static inline struct mem_cgroup *mem_cgroup_from_seq(struct seq_file *m) { return mem_cgroup_from_css(seq_css(m)); @@ -838,9 +849,7 @@ static inline struct mem_cgroup *lruvec_memcg(struct lruvec *lruvec) */ static inline struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg) { - if (!memcg->memory.parent) - return NULL; - return mem_cgroup_from_counter(memcg->memory.parent, memory); + return mem_cgroup_from_css(memcg->css.parent); } static inline bool mem_cgroup_is_descendant(struct mem_cgroup *memcg, @@ -921,10 +930,6 @@ struct mem_cgroup *mem_cgroup_get_oom_group(struct task_struct *victim, struct mem_cgroup *oom_domain); void mem_cgroup_print_oom_group(struct mem_cgroup *memcg); -#ifdef CONFIG_MEMCG_SWAP -extern bool cgroup_memory_noswap; -#endif - void folio_memcg_lock(struct folio *folio); void folio_memcg_unlock(struct folio *folio); void lock_page_memcg(struct page *page); @@ -932,6 +937,23 @@ void unlock_page_memcg(struct page *page); void __mod_memcg_state(struct mem_cgroup *memcg, int idx, int val); +/* try to stablize folio_memcg() for all the pages in a memcg */ +static inline bool mem_cgroup_trylock_pages(struct mem_cgroup *memcg) +{ + rcu_read_lock(); + + if (mem_cgroup_disabled() || !atomic_read(&memcg->moving_account)) + return true; + + rcu_read_unlock(); + return false; +} + +static inline void mem_cgroup_unlock_pages(void) +{ + rcu_read_unlock(); +} + /* idx can be of type enum memcg_stat_item or node_stat_item */ static inline void mod_memcg_state(struct mem_cgroup *memcg, int idx, int val) @@ -943,21 +965,39 @@ static inline void mod_memcg_state(struct mem_cgroup *memcg, local_irq_restore(flags); } -static inline unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx) +static inline void mod_memcg_page_state(struct page *page, + int idx, int val) { - return READ_ONCE(memcg->vmstats.state[idx]); + struct mem_cgroup *memcg; + + if (mem_cgroup_disabled()) + return; + + rcu_read_lock(); + memcg = page_memcg(page); + if (memcg) + mod_memcg_state(memcg, idx, val); + rcu_read_unlock(); } +unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx); + static inline unsigned long lruvec_page_state(struct lruvec *lruvec, enum node_stat_item idx) { struct mem_cgroup_per_node *pn; + long x; if (mem_cgroup_disabled()) return node_page_state(lruvec_pgdat(lruvec), idx); pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec); - return READ_ONCE(pn->lruvec_stats.state[idx]); + x = READ_ONCE(pn->lruvec_stats.state[idx]); +#ifdef CONFIG_SMP + if (x < 0) + x = 0; +#endif + return x; } static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec, @@ -981,6 +1021,7 @@ static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec, } void mem_cgroup_flush_stats(void); +void mem_cgroup_flush_stats_delayed(void); void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val); @@ -1029,6 +1070,15 @@ static inline void count_memcg_page_event(struct page *page, count_memcg_events(memcg, idx, 1); } +static inline void count_memcg_folio_events(struct folio *folio, + enum vm_event_item idx, unsigned long nr) +{ + struct mem_cgroup *memcg = folio_memcg(folio); + + if (memcg) + count_memcg_events(memcg, idx, nr); +} + static inline void count_memcg_event_mm(struct mm_struct *mm, enum vm_event_item idx) { @@ -1175,7 +1225,7 @@ static inline int mem_cgroup_charge(struct folio *folio, return 0; } -static inline int mem_cgroup_swapin_charge_page(struct page *page, +static inline int mem_cgroup_swapin_charge_folio(struct folio *folio, struct mm_struct *mm, gfp_t gfp, swp_entry_t entry) { return 0; @@ -1236,6 +1286,10 @@ struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css) return NULL; } +static inline void obj_cgroup_put(struct obj_cgroup *objcg) +{ +} + static inline void mem_cgroup_put(struct mem_cgroup *memcg) { } @@ -1296,6 +1350,18 @@ static inline struct mem_cgroup *mem_cgroup_from_id(unsigned short id) return NULL; } +#ifdef CONFIG_SHRINKER_DEBUG +static inline unsigned long mem_cgroup_ino(struct mem_cgroup *memcg) +{ + return 0; +} + +static inline struct mem_cgroup *mem_cgroup_get_from_ino(unsigned long ino) +{ + return NULL; +} +#endif + static inline struct mem_cgroup *mem_cgroup_from_seq(struct seq_file *m) { return NULL; @@ -1354,6 +1420,18 @@ static inline void folio_memcg_unlock(struct folio *folio) { } +static inline bool mem_cgroup_trylock_pages(struct mem_cgroup *memcg) +{ + /* to match folio_memcg_rcu() */ + rcu_read_lock(); + return true; +} + +static inline void mem_cgroup_unlock_pages(void) +{ + rcu_read_unlock(); +} + static inline void mem_cgroup_handle_over_high(void) { } @@ -1398,6 +1476,11 @@ static inline void mod_memcg_state(struct mem_cgroup *memcg, { } +static inline void mod_memcg_page_state(struct page *page, + int idx, int val) +{ +} + static inline unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx) { return 0; @@ -1419,6 +1502,10 @@ static inline void mem_cgroup_flush_stats(void) { } +static inline void mem_cgroup_flush_stats_delayed(void) +{ +} + static inline void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val) { @@ -1457,6 +1544,11 @@ static inline void count_memcg_page_event(struct page *page, { } +static inline void count_memcg_folio_events(struct folio *folio, + enum vm_event_item idx, unsigned long nr) +{ +} + static inline void count_memcg_event_mm(struct mm_struct *mm, enum vm_event_item idx) { @@ -1643,24 +1735,13 @@ int __memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order); void __memcg_kmem_uncharge_page(struct page *page, int order); struct obj_cgroup *get_obj_cgroup_from_current(void); +struct obj_cgroup *get_obj_cgroup_from_page(struct page *page); int obj_cgroup_charge(struct obj_cgroup *objcg, gfp_t gfp, size_t size); void obj_cgroup_uncharge(struct obj_cgroup *objcg, size_t size); extern struct static_key_false memcg_kmem_enabled_key; -extern int memcg_nr_cache_ids; -void memcg_get_cache_ids(void); -void memcg_put_cache_ids(void); - -/* - * Helper macro to loop through all memcg-specific caches. Callers must still - * check if the cache is valid (it is either valid or NULL). - * the slab_mutex must be held when looping through those caches - */ -#define for_each_memcg_cache_index(_idx) \ - for ((_idx) = 0; (_idx) < memcg_nr_cache_ids; (_idx)++) - static inline bool memcg_kmem_enabled(void) { return static_branch_likely(&memcg_kmem_enabled_key); @@ -1684,12 +1765,27 @@ static inline void memcg_kmem_uncharge_page(struct page *page, int order) * A helper for accessing memcg's kmem_id, used for getting * corresponding LRU lists. */ -static inline int memcg_cache_id(struct mem_cgroup *memcg) +static inline int memcg_kmem_id(struct mem_cgroup *memcg) { return memcg ? memcg->kmemcg_id : -1; } struct mem_cgroup *mem_cgroup_from_obj(void *p); +struct mem_cgroup *mem_cgroup_from_slab_obj(void *p); + +static inline void count_objcg_event(struct obj_cgroup *objcg, + enum vm_event_item idx) +{ + struct mem_cgroup *memcg; + + if (!memcg_kmem_enabled()) + return; + + rcu_read_lock(); + memcg = obj_cgroup_memcg(objcg); + count_memcg_events(memcg, idx, 1); + rcu_read_unlock(); +} #else static inline bool mem_cgroup_kmem_disabled(void) @@ -1717,32 +1813,55 @@ static inline void __memcg_kmem_uncharge_page(struct page *page, int order) { } -#define for_each_memcg_cache_index(_idx) \ - for (; NULL; ) +static inline struct obj_cgroup *get_obj_cgroup_from_page(struct page *page) +{ + return NULL; +} static inline bool memcg_kmem_enabled(void) { return false; } -static inline int memcg_cache_id(struct mem_cgroup *memcg) +static inline int memcg_kmem_id(struct mem_cgroup *memcg) { return -1; } -static inline void memcg_get_cache_ids(void) +static inline struct mem_cgroup *mem_cgroup_from_obj(void *p) { + return NULL; } -static inline void memcg_put_cache_ids(void) +static inline struct mem_cgroup *mem_cgroup_from_slab_obj(void *p) { + return NULL; } -static inline struct mem_cgroup *mem_cgroup_from_obj(void *p) +static inline void count_objcg_event(struct obj_cgroup *objcg, + enum vm_event_item idx) { - return NULL; } #endif /* CONFIG_MEMCG_KMEM */ +#if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_ZSWAP) +bool obj_cgroup_may_zswap(struct obj_cgroup *objcg); +void obj_cgroup_charge_zswap(struct obj_cgroup *objcg, size_t size); +void obj_cgroup_uncharge_zswap(struct obj_cgroup *objcg, size_t size); +#else +static inline bool obj_cgroup_may_zswap(struct obj_cgroup *objcg) +{ + return true; +} +static inline void obj_cgroup_charge_zswap(struct obj_cgroup *objcg, + size_t size) +{ +} +static inline void obj_cgroup_uncharge_zswap(struct obj_cgroup *objcg, + size_t size) +{ +} +#endif + #endif /* _LINUX_MEMCONTROL_H */ diff --git a/include/linux/memory-tiers.h b/include/linux/memory-tiers.h new file mode 100644 index 000000000000..965009aa01d7 --- /dev/null +++ b/include/linux/memory-tiers.h @@ -0,0 +1,102 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_MEMORY_TIERS_H +#define _LINUX_MEMORY_TIERS_H + +#include <linux/types.h> +#include <linux/nodemask.h> +#include <linux/kref.h> +#include <linux/mmzone.h> +/* + * Each tier cover a abstrace distance chunk size of 128 + */ +#define MEMTIER_CHUNK_BITS 7 +#define MEMTIER_CHUNK_SIZE (1 << MEMTIER_CHUNK_BITS) +/* + * Smaller abstract distance values imply faster (higher) memory tiers. Offset + * the DRAM adistance so that we can accommodate devices with a slightly lower + * adistance value (slightly faster) than default DRAM adistance to be part of + * the same memory tier. + */ +#define MEMTIER_ADISTANCE_DRAM ((4 * MEMTIER_CHUNK_SIZE) + (MEMTIER_CHUNK_SIZE >> 1)) +#define MEMTIER_HOTPLUG_PRIO 100 + +struct memory_tier; +struct memory_dev_type { + /* list of memory types that are part of same tier as this type */ + struct list_head tier_sibiling; + /* abstract distance for this specific memory type */ + int adistance; + /* Nodes of same abstract distance */ + nodemask_t nodes; + struct kref kref; +}; + +#ifdef CONFIG_NUMA +extern bool numa_demotion_enabled; +struct memory_dev_type *alloc_memory_type(int adistance); +void destroy_memory_type(struct memory_dev_type *memtype); +void init_node_memory_type(int node, struct memory_dev_type *default_type); +void clear_node_memory_type(int node, struct memory_dev_type *memtype); +#ifdef CONFIG_MIGRATION +int next_demotion_node(int node); +void node_get_allowed_targets(pg_data_t *pgdat, nodemask_t *targets); +bool node_is_toptier(int node); +#else +static inline int next_demotion_node(int node) +{ + return NUMA_NO_NODE; +} + +static inline void node_get_allowed_targets(pg_data_t *pgdat, nodemask_t *targets) +{ + *targets = NODE_MASK_NONE; +} + +static inline bool node_is_toptier(int node) +{ + return true; +} +#endif + +#else + +#define numa_demotion_enabled false +/* + * CONFIG_NUMA implementation returns non NULL error. + */ +static inline struct memory_dev_type *alloc_memory_type(int adistance) +{ + return NULL; +} + +static inline void destroy_memory_type(struct memory_dev_type *memtype) +{ + +} + +static inline void init_node_memory_type(int node, struct memory_dev_type *default_type) +{ + +} + +static inline void clear_node_memory_type(int node, struct memory_dev_type *memtype) +{ + +} + +static inline int next_demotion_node(int node) +{ + return NUMA_NO_NODE; +} + +static inline void node_get_allowed_targets(pg_data_t *pgdat, nodemask_t *targets) +{ + *targets = NODE_MASK_NONE; +} + +static inline bool node_is_toptier(int node) +{ + return true; +} +#endif /* CONFIG_NUMA */ +#endif /* _LINUX_MEMORY_TIERS_H */ diff --git a/include/linux/memory.h b/include/linux/memory.h index 88eb587b5143..aa619464a1df 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -70,6 +70,13 @@ struct memory_block { unsigned long state; /* serialized by the dev->lock */ int online_type; /* for passing data to online routine */ int nid; /* NID for this memory block */ + /* + * The single zone of this memory block if all PFNs of this memory block + * that are System RAM (not a memory hole, not ZONE_DEVICE ranges) are + * managed by a single zone. NULL if multiple zones (including nodes) + * apply. + */ + struct zone *zone; struct device dev; /* * Number of vmemmap pages. These pages @@ -161,6 +168,11 @@ int walk_dynamic_memory_groups(int nid, walk_memory_groups_func_t func, }) #define register_hotmemory_notifier(nb) register_memory_notifier(nb) #define unregister_hotmemory_notifier(nb) unregister_memory_notifier(nb) + +#ifdef CONFIG_NUMA +void memory_block_add_nid(struct memory_block *mem, int nid, + enum meminit_context context); +#endif /* CONFIG_NUMA */ #endif /* CONFIG_MEMORY_HOTPLUG */ /* diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index be48e003a518..9fcbf5706595 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -11,10 +11,58 @@ struct page; struct zone; struct pglist_data; struct mem_section; -struct memory_block; struct memory_group; struct resource; struct vmem_altmap; +struct dev_pagemap; + +#ifdef CONFIG_HAVE_ARCH_NODEDATA_EXTENSION +/* + * For supporting node-hotadd, we have to allocate a new pgdat. + * + * If an arch has generic style NODE_DATA(), + * node_data[nid] = kzalloc() works well. But it depends on the architecture. + * + * In general, generic_alloc_nodedata() is used. + * + */ +extern pg_data_t *arch_alloc_nodedata(int nid); +extern void arch_refresh_nodedata(int nid, pg_data_t *pgdat); + +#else /* CONFIG_HAVE_ARCH_NODEDATA_EXTENSION */ + +#define arch_alloc_nodedata(nid) generic_alloc_nodedata(nid) + +#ifdef CONFIG_NUMA +/* + * XXX: node aware allocation can't work well to get new node's memory at this time. + * Because, pgdat for the new node is not allocated/initialized yet itself. + * To use new node's memory, more consideration will be necessary. + */ +#define generic_alloc_nodedata(nid) \ +({ \ + memblock_alloc(sizeof(*pgdat), SMP_CACHE_BYTES); \ +}) + +extern pg_data_t *node_data[]; +static inline void arch_refresh_nodedata(int nid, pg_data_t *pgdat) +{ + node_data[nid] = pgdat; +} + +#else /* !CONFIG_NUMA */ + +/* never called */ +static inline pg_data_t *generic_alloc_nodedata(int nid) +{ + BUG(); + return NULL; +} +static inline void arch_refresh_nodedata(int nid, pg_data_t *pgdat) +{ +} +#endif /* CONFIG_NUMA */ +#endif /* CONFIG_HAVE_ARCH_NODEDATA_EXTENSION */ #ifdef CONFIG_MEMORY_HOTPLUG struct page *pfn_to_online_page(unsigned long pfn); @@ -66,6 +114,7 @@ typedef int __bitwise mhp_t; struct mhp_params { struct vmem_altmap *altmap; pgprot_t pgprot; + struct dev_pagemap *pgmap; }; bool mhp_range_allowed(u64 start, u64 size, bool need_mapping); @@ -107,8 +156,6 @@ extern int mhp_init_memmap_on_memory(unsigned long pfn, unsigned long nr_pages, extern void mhp_deinit_memmap_on_memory(unsigned long pfn, unsigned long nr_pages); extern int online_pages(unsigned long pfn, unsigned long nr_pages, struct zone *zone, struct memory_group *group); -extern struct zone *test_pages_in_a_zone(unsigned long start_pfn, - unsigned long end_pfn); extern void __offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn); @@ -154,71 +201,27 @@ int add_pages(int nid, unsigned long start_pfn, unsigned long nr_pages, struct mhp_params *params); #endif /* ARCH_HAS_ADD_PAGES */ -#ifdef CONFIG_HAVE_ARCH_NODEDATA_EXTENSION -/* - * For supporting node-hotadd, we have to allocate a new pgdat. - * - * If an arch has generic style NODE_DATA(), - * node_data[nid] = kzalloc() works well. But it depends on the architecture. - * - * In general, generic_alloc_nodedata() is used. - * Now, arch_free_nodedata() is just defined for error path of node_hot_add. - * - */ -extern pg_data_t *arch_alloc_nodedata(int nid); -extern void arch_free_nodedata(pg_data_t *pgdat); -extern void arch_refresh_nodedata(int nid, pg_data_t *pgdat); - -#else /* CONFIG_HAVE_ARCH_NODEDATA_EXTENSION */ - -#define arch_alloc_nodedata(nid) generic_alloc_nodedata(nid) -#define arch_free_nodedata(pgdat) generic_free_nodedata(pgdat) +void get_online_mems(void); +void put_online_mems(void); -#ifdef CONFIG_NUMA -/* - * If ARCH_HAS_NODEDATA_EXTENSION=n, this func is used to allocate pgdat. - * XXX: kmalloc_node() can't work well to get new node's memory at this time. - * Because, pgdat for the new node is not allocated/initialized yet itself. - * To use new node's memory, more consideration will be necessary. - */ -#define generic_alloc_nodedata(nid) \ -({ \ - kzalloc(sizeof(pg_data_t), GFP_KERNEL); \ -}) -/* - * This definition is just for error path in node hotadd. - * For node hotremove, we have to replace this. - */ -#define generic_free_nodedata(pgdat) kfree(pgdat) +void mem_hotplug_begin(void); +void mem_hotplug_done(void); -extern pg_data_t *node_data[]; -static inline void arch_refresh_nodedata(int nid, pg_data_t *pgdat) +/* See kswapd_is_running() */ +static inline void pgdat_kswapd_lock(pg_data_t *pgdat) { - node_data[nid] = pgdat; + mutex_lock(&pgdat->kswapd_lock); } -#else /* !CONFIG_NUMA */ - -/* never called */ -static inline pg_data_t *generic_alloc_nodedata(int nid) -{ - BUG(); - return NULL; -} -static inline void generic_free_nodedata(pg_data_t *pgdat) +static inline void pgdat_kswapd_unlock(pg_data_t *pgdat) { + mutex_unlock(&pgdat->kswapd_lock); } -static inline void arch_refresh_nodedata(int nid, pg_data_t *pgdat) + +static inline void pgdat_kswapd_lock_init(pg_data_t *pgdat) { + mutex_init(&pgdat->kswapd_lock); } -#endif /* CONFIG_NUMA */ -#endif /* CONFIG_HAVE_ARCH_NODEDATA_EXTENSION */ - -void get_online_mems(void); -void put_online_mems(void); - -void mem_hotplug_begin(void); -void mem_hotplug_done(void); #else /* ! CONFIG_MEMORY_HOTPLUG */ #define pfn_to_online_page(pfn) \ @@ -256,6 +259,10 @@ static inline bool movable_node_is_enabled(void) { return false; } + +static inline void pgdat_kswapd_lock(pg_data_t *pgdat) {} +static inline void pgdat_kswapd_unlock(pg_data_t *pgdat) {} +static inline void pgdat_kswapd_lock_init(pg_data_t *pgdat) {} #endif /* ! CONFIG_MEMORY_HOTPLUG */ /* @@ -297,7 +304,7 @@ static inline void pgdat_resize_init(struct pglist_data *pgdat) {} extern void try_offline_node(int nid); extern int offline_pages(unsigned long start_pfn, unsigned long nr_pages, - struct memory_group *group); + struct zone *zone, struct memory_group *group); extern int remove_memory(u64 start, u64 size); extern void __remove_memory(u64 start, u64 size); extern int offline_and_remove_memory(u64 start, u64 size); @@ -306,7 +313,7 @@ extern int offline_and_remove_memory(u64 start, u64 size); static inline void try_offline_node(int nid) {} static inline int offline_pages(unsigned long start_pfn, unsigned long nr_pages, - struct memory_group *group) + struct zone *zone, struct memory_group *group) { return -EINVAL; } @@ -323,7 +330,7 @@ extern void set_zone_contiguous(struct zone *zone); extern void clear_zone_contiguous(struct zone *zone); #ifdef CONFIG_MEMORY_HOTPLUG -extern void __ref free_area_init_core_hotplug(int nid); +extern void __ref free_area_init_core_hotplug(struct pglist_data *pgdat); extern int __add_memory(int nid, u64 start, u64 size, mhp_t mhp_flags); extern int add_memory(int nid, u64 start, u64 size, mhp_t mhp_flags); extern int add_memory_resource(int nid, struct resource *resource, @@ -337,9 +344,9 @@ extern void move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn, extern void remove_pfn_range_from_zone(struct zone *zone, unsigned long start_pfn, unsigned long nr_pages); -extern bool is_memblock_offlined(struct memory_block *mem); extern int sparse_add_section(int nid, unsigned long pfn, - unsigned long nr_pages, struct vmem_altmap *altmap); + unsigned long nr_pages, struct vmem_altmap *altmap, + struct dev_pagemap *pgmap); extern void sparse_remove_section(struct mem_section *ms, unsigned long pfn, unsigned long nr_pages, unsigned long map_offset, struct vmem_altmap *altmap); diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h index 3c7595e81150..d232de7cdc56 100644 --- a/include/linux/mempolicy.h +++ b/include/linux/mempolicy.h @@ -46,6 +46,7 @@ struct mempolicy { unsigned short mode; /* See MPOL_* above */ unsigned short flags; /* See set_mempolicy() MPOL_F_* above */ nodemask_t nodes; /* interleave/bind/perfer */ + int home_node; /* Home node to use for MPOL_BIND and MPOL_PREFERRED_MANY */ union { nodemask_t cpuset_mems_allowed; /* relative to these nodes */ @@ -150,13 +151,6 @@ extern bool mempolicy_in_oom_domain(struct task_struct *tsk, const nodemask_t *mask); extern nodemask_t *policy_nodemask(gfp_t gfp, struct mempolicy *policy); -static inline nodemask_t *policy_nodemask_current(gfp_t gfp) -{ - struct mempolicy *mpol = get_task_policy(current); - - return policy_nodemask(gfp, mpol); -} - extern unsigned int mempolicy_slab_node(void); extern enum zone_type policy_zone; @@ -188,6 +182,7 @@ static inline bool mpol_is_preferred_many(struct mempolicy *pol) return (pol->mode == MPOL_PREFERRED_MANY); } +extern bool apply_policy_zone(struct mempolicy *policy, enum zone_type zone); #else @@ -293,11 +288,6 @@ static inline void mpol_put_task_policy(struct task_struct *task) { } -static inline nodemask_t *policy_nodemask_current(gfp_t gfp) -{ - return NULL; -} - static inline bool mpol_is_preferred_many(struct mempolicy *pol) { return false; diff --git a/include/linux/memregion.h b/include/linux/memregion.h index e11595256cac..c04c4fd2e209 100644 --- a/include/linux/memregion.h +++ b/include/linux/memregion.h @@ -16,7 +16,7 @@ static inline int memregion_alloc(gfp_t gfp) { return -ENOMEM; } -void memregion_free(int id) +static inline void memregion_free(int id) { } #endif diff --git a/include/linux/memremap.h b/include/linux/memremap.h index c0e9d35889e8..7fcaf3180a5b 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -1,6 +1,8 @@ /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_MEMREMAP_H_ #define _LINUX_MEMREMAP_H_ + +#include <linux/mmzone.h> #include <linux/range.h> #include <linux/ioport.h> #include <linux/percpu-refcount.h> @@ -37,7 +39,14 @@ struct vmem_altmap { * must be treated as an opaque object, rather than a "normal" struct page. * * A more complete discussion of unaddressable memory may be found in - * include/linux/hmm.h and Documentation/vm/hmm.rst. + * include/linux/hmm.h and Documentation/mm/hmm.rst. + * + * MEMORY_DEVICE_COHERENT: + * Device memory that is cache coherent from device and CPU point of view. This + * is used on platforms that have an advanced system bus (like CAPI or CXL). A + * driver can hotplug the device memory using ZONE_DEVICE and with that memory + * type. Any page of a process can be migrated to such memory. However no one + * should be allowed to pin such memory so that it can always be evicted. * * MEMORY_DEVICE_FS_DAX: * Host memory that has similar access semantics as System RAM i.e. DMA @@ -59,6 +68,7 @@ struct vmem_altmap { enum memory_type { /* 0 is reserved to catch uninitialized type fields */ MEMORY_DEVICE_PRIVATE = 1, + MEMORY_DEVICE_COHERENT, MEMORY_DEVICE_FS_DAX, MEMORY_DEVICE_GENERIC, MEMORY_DEVICE_PCI_P2PDMA, @@ -66,27 +76,29 @@ enum memory_type { struct dev_pagemap_ops { /* - * Called once the page refcount reaches 1. (ZONE_DEVICE pages never - * reach 0 refcount unless there is a refcount bug. This allows the - * device driver to implement its own memory management.) + * Called once the page refcount reaches 0. The reference count will be + * reset to one by the core code after the method is called to prepare + * for handing out the page again. */ void (*page_free)(struct page *page); /* - * Transition the refcount in struct dev_pagemap to the dead state. - */ - void (*kill)(struct dev_pagemap *pgmap); - - /* - * Wait for refcount in struct dev_pagemap to be idle and reap it. - */ - void (*cleanup)(struct dev_pagemap *pgmap); - - /* * Used for private (un-addressable) device memory only. Must migrate * the page back to a CPU accessible page. */ vm_fault_t (*migrate_to_ram)(struct vm_fault *vmf); + + /* + * Handle the memory failure happens on a range of pfns. Notify the + * processes who are using these pfns, and try to recover the data on + * them if necessary. The mf_flags is finally passed to the recover + * function through the whole notify routine. + * + * When this is not implemented, or it returns -EOPNOTSUPP, the caller + * will fall back to a common handler called mf_generic_kill_procs(). + */ + int (*memory_failure)(struct dev_pagemap *pgmap, unsigned long pfn, + unsigned long nr_pages, int mf_flags); }; #define PGMAP_ALTMAP_VALID (1 << 0) @@ -95,10 +107,14 @@ struct dev_pagemap_ops { * struct dev_pagemap - metadata for ZONE_DEVICE mappings * @altmap: pre-allocated/reserved memory for vmemmap allocations * @ref: reference count that pins the devm_memremap_pages() mapping - * @internal_ref: internal reference if @ref is not provided by the caller - * @done: completion for @internal_ref + * @done: completion for @ref * @type: memory type: see MEMORY_* in memory_hotplug.h * @flags: PGMAP_* flags to specify defailed behavior + * @vmemmap_shift: structural definition of how the vmemmap page metadata + * is populated, specifically the metadata page order. + * A zero value (default) uses base pages as the vmemmap metadata + * representation. A bigger value will set up compound struct pages + * of the requested order value. * @ops: method table * @owner: an opaque pointer identifying the entity that manages this * instance. Used by various helpers to make sure that no @@ -109,11 +125,11 @@ struct dev_pagemap_ops { */ struct dev_pagemap { struct vmem_altmap altmap; - struct percpu_ref *ref; - struct percpu_ref internal_ref; + struct percpu_ref ref; struct completion done; enum memory_type type; unsigned int flags; + unsigned long vmemmap_shift; const struct dev_pagemap_ops *ops; void *owner; int nr_range; @@ -123,6 +139,11 @@ struct dev_pagemap { }; }; +static inline bool pgmap_has_memory_failure(struct dev_pagemap *pgmap) +{ + return pgmap->ops && pgmap->ops->memory_failure; +} + static inline struct vmem_altmap *pgmap_altmap(struct dev_pagemap *pgmap) { if (pgmap->flags & PGMAP_ALTMAP_VALID) @@ -130,7 +151,43 @@ static inline struct vmem_altmap *pgmap_altmap(struct dev_pagemap *pgmap) return NULL; } +static inline unsigned long pgmap_vmemmap_nr(struct dev_pagemap *pgmap) +{ + return 1 << pgmap->vmemmap_shift; +} + +static inline bool is_device_private_page(const struct page *page) +{ + return IS_ENABLED(CONFIG_DEVICE_PRIVATE) && + is_zone_device_page(page) && + page->pgmap->type == MEMORY_DEVICE_PRIVATE; +} + +static inline bool folio_is_device_private(const struct folio *folio) +{ + return is_device_private_page(&folio->page); +} + +static inline bool is_pci_p2pdma_page(const struct page *page) +{ + return IS_ENABLED(CONFIG_PCI_P2PDMA) && + is_zone_device_page(page) && + page->pgmap->type == MEMORY_DEVICE_PCI_P2PDMA; +} + +static inline bool is_device_coherent_page(const struct page *page) +{ + return is_zone_device_page(page) && + page->pgmap->type == MEMORY_DEVICE_COHERENT; +} + +static inline bool folio_is_device_coherent(const struct folio *folio) +{ + return is_device_coherent_page(&folio->page); +} + #ifdef CONFIG_ZONE_DEVICE +void zone_device_page_init(struct page *page); void *memremap_pages(struct dev_pagemap *pgmap, int nid); void memunmap_pages(struct dev_pagemap *pgmap); void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap); @@ -191,7 +248,7 @@ static inline unsigned long memremap_compat_align(void) static inline void put_dev_pagemap(struct dev_pagemap *pgmap) { if (pgmap) - percpu_ref_put(pgmap->ref); + percpu_ref_put(&pgmap->ref); } #endif /* _LINUX_MEMREMAP_H_ */ diff --git a/include/linux/mfd/bcm2835-pm.h b/include/linux/mfd/bcm2835-pm.h index ed37dc40e82a..f70a810c55f7 100644 --- a/include/linux/mfd/bcm2835-pm.h +++ b/include/linux/mfd/bcm2835-pm.h @@ -9,6 +9,7 @@ struct bcm2835_pm { struct device *dev; void __iomem *base; void __iomem *asb; + void __iomem *rpivid_asb; }; #endif /* BCM2835_MFD_PM_H */ diff --git a/include/linux/mfd/dbx500-prcmu.h b/include/linux/mfd/dbx500-prcmu.h index cbf9d7619493..e7a7e70fdb38 100644 --- a/include/linux/mfd/dbx500-prcmu.h +++ b/include/linux/mfd/dbx500-prcmu.h @@ -556,31 +556,11 @@ static inline void prcmu_clear(unsigned int reg, u32 bits) #define PRCMU_QOS_ARM_OPP 3 #define PRCMU_QOS_DEFAULT_VALUE -1 -#ifdef CONFIG_DBX500_PRCMU_QOS_POWER - -unsigned long prcmu_qos_get_cpufreq_opp_delay(void); -void prcmu_qos_set_cpufreq_opp_delay(unsigned long); -void prcmu_qos_force_opp(int, s32); -int prcmu_qos_requirement(int pm_qos_class); -int prcmu_qos_add_requirement(int pm_qos_class, char *name, s32 value); -int prcmu_qos_update_requirement(int pm_qos_class, char *name, s32 new_value); -void prcmu_qos_remove_requirement(int pm_qos_class, char *name); -int prcmu_qos_add_notifier(int prcmu_qos_class, - struct notifier_block *notifier); -int prcmu_qos_remove_notifier(int prcmu_qos_class, - struct notifier_block *notifier); - -#else - static inline unsigned long prcmu_qos_get_cpufreq_opp_delay(void) { return 0; } -static inline void prcmu_qos_set_cpufreq_opp_delay(unsigned long n) {} - -static inline void prcmu_qos_force_opp(int prcmu_qos_class, s32 i) {} - static inline int prcmu_qos_requirement(int prcmu_qos_class) { return 0; @@ -613,6 +593,4 @@ static inline int prcmu_qos_remove_notifier(int prcmu_qos_class, return 0; } -#endif - #endif /* __MACH_PRCMU_H */ diff --git a/include/linux/mfd/hi655x-pmic.h b/include/linux/mfd/hi655x-pmic.h index af5d97239c0d..6a012784dd1b 100644 --- a/include/linux/mfd/hi655x-pmic.h +++ b/include/linux/mfd/hi655x-pmic.h @@ -12,6 +12,8 @@ #ifndef __HI655X_PMIC_H #define __HI655X_PMIC_H +#include <linux/gpio/consumer.h> + /* Hi655x registers are mapped to memory bus in 4 bytes stride */ #define HI655X_STRIDE 4 #define HI655X_BUS_ADDR(x) ((x) << 2) @@ -53,7 +55,7 @@ struct hi655x_pmic { struct resource *res; struct device *dev; struct regmap *regmap; - int gpio; + struct gpio_desc *gpio; unsigned int ver; struct regmap_irq_chip_data *irq_data; }; diff --git a/include/linux/mfd/idt82p33_reg.h b/include/linux/mfd/idt82p33_reg.h index 129a6c078221..1db532feeb91 100644 --- a/include/linux/mfd/idt82p33_reg.h +++ b/include/linux/mfd/idt82p33_reg.h @@ -7,6 +7,8 @@ #ifndef HAVE_IDT82P33_REG #define HAVE_IDT82P33_REG +#define REG_ADDR(page, offset) (((page) << 0x7) | ((offset) & 0x7f)) + /* Register address */ #define DPLL1_TOD_CNFG 0x134 #define DPLL2_TOD_CNFG 0x1B4 @@ -41,6 +43,7 @@ #define REG_SOFT_RESET 0X381 #define OUT_MUX_CNFG(outn) REG_ADDR(0x6, (0xC * (outn))) +#define TOD_TRIGGER(wr_trig, rd_trig) ((wr_trig & 0xf) << 4 | (rd_trig & 0xf)) /* Register bit definitions */ #define SYNC_TOD BIT(1) diff --git a/include/linux/mfd/idt8a340_reg.h b/include/linux/mfd/idt8a340_reg.h index a18c1539a152..0c706085c205 100644 --- a/include/linux/mfd/idt8a340_reg.h +++ b/include/linux/mfd/idt8a340_reg.h @@ -407,7 +407,7 @@ #define TOD_READ_PRIMARY_0 0xcc40 #define TOD_READ_PRIMARY_0_V520 0xcc50 /* 8-bit subns, 32-bit ns, 48-bit seconds */ -#define TOD_READ_PRIMARY 0x0000 +#define TOD_READ_PRIMARY_BASE 0x0000 /* Counter increments after TOD write is completed */ #define TOD_READ_PRIMARY_COUNTER 0x000b /* Read trigger configuration */ @@ -424,6 +424,16 @@ #define TOD_READ_SECONDARY_0 0xcc90 #define TOD_READ_SECONDARY_0_V520 0xcca0 +/* 8-bit subns, 32-bit ns, 48-bit seconds */ +#define TOD_READ_SECONDARY_BASE 0x0000 +/* Counter increments after TOD write is completed */ +#define TOD_READ_SECONDARY_COUNTER 0x000b +/* Read trigger configuration */ +#define TOD_READ_SECONDARY_SEL_CFG_0 0x000c +/* Read trigger selection */ +#define TOD_READ_SECONDARY_CMD 0x000e +#define TOD_READ_SECONDARY_CMD_V520 0x000f + #define TOD_READ_SECONDARY_1 0xcca0 #define TOD_READ_SECONDARY_1_V520 0xccb0 #define TOD_READ_SECONDARY_2 0xccb0 diff --git a/include/linux/mfd/intel_soc_pmic.h b/include/linux/mfd/intel_soc_pmic.h index 6a88e34cb955..945bde1fe55c 100644 --- a/include/linux/mfd/intel_soc_pmic.h +++ b/include/linux/mfd/intel_soc_pmic.h @@ -13,6 +13,13 @@ #include <linux/regmap.h> +enum intel_cht_wc_models { + INTEL_CHT_WC_UNKNOWN, + INTEL_CHT_WC_GPD_WIN_POCKET, + INTEL_CHT_WC_XIAOMI_MIPAD2, + INTEL_CHT_WC_LENOVO_YOGABOOK1, +}; + /** * struct intel_soc_pmic - Intel SoC PMIC data * @irq: Master interrupt number of the parent PMIC device @@ -39,6 +46,7 @@ struct intel_soc_pmic { struct regmap_irq_chip_data *irq_chip_data_crit; struct device *dev; struct intel_scu_ipc_dev *scu; + enum intel_cht_wc_models cht_wc_model; }; int intel_soc_pmic_exec_mipi_pmic_seq_element(u16 i2c_address, u32 reg_address, diff --git a/include/linux/mfd/ipaq-micro.h b/include/linux/mfd/ipaq-micro.h index ee48a4321c57..d5caa4c86ecc 100644 --- a/include/linux/mfd/ipaq-micro.h +++ b/include/linux/mfd/ipaq-micro.h @@ -75,8 +75,8 @@ struct ipaq_micro_rxdev { * @id: 4-bit ID of the message * @tx_len: length of TX data * @tx_data: TX data to send - * @rx_len: length of receieved RX data - * @rx_data: RX data to recieve + * @rx_len: length of received RX data + * @rx_data: RX data to receive * @ack: a completion that will be completed when RX is complete * @node: list node if message gets queued */ diff --git a/include/linux/mfd/iqs62x.h b/include/linux/mfd/iqs62x.h index 5ced55eae11b..ffc86010af74 100644 --- a/include/linux/mfd/iqs62x.h +++ b/include/linux/mfd/iqs62x.h @@ -14,6 +14,11 @@ #define IQS624_PROD_NUM 0x43 #define IQS625_PROD_NUM 0x4E +#define IQS620_HW_NUM_V0 0x82 +#define IQS620_HW_NUM_V1 IQS620_HW_NUM_V0 +#define IQS620_HW_NUM_V2 IQS620_HW_NUM_V0 +#define IQS620_HW_NUM_V3 0x92 + #define IQS621_ALS_FLAGS 0x16 #define IQS622_ALS_FLAGS 0x14 @@ -129,6 +134,8 @@ struct iqs62x_core { struct completion fw_done; enum iqs62x_ui_sel ui_sel; unsigned long event_cache; + u8 sw_num; + u8 hw_num; }; extern const struct iqs62x_event_desc iqs62x_events[IQS62X_NUM_EVENTS]; diff --git a/include/linux/mfd/lp873x.h b/include/linux/mfd/lp873x.h index 5546688c7da7..fe8174cc8637 100644 --- a/include/linux/mfd/lp873x.h +++ b/include/linux/mfd/lp873x.h @@ -1,16 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * Functions to access LP873X power management chip. * * Copyright (C) 2016 Texas Instruments Incorporated - https://www.ti.com/ - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation version 2. - * - * This program is distributed "as is" WITHOUT ANY WARRANTY of any - * kind, whether express or implied; without even the implied warranty - * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. */ #ifndef __LINUX_MFD_LP873X_H diff --git a/include/linux/mfd/lpc_ich.h b/include/linux/mfd/lpc_ich.h index 39967a5eca6d..ea4a4b1b246a 100644 --- a/include/linux/mfd/lpc_ich.h +++ b/include/linux/mfd/lpc_ich.h @@ -8,7 +8,7 @@ #ifndef LPC_ICH_H #define LPC_ICH_H -#include <linux/platform_data/x86/intel-spi.h> +#include <linux/platform_data/x86/spi-intel.h> /* GPIO resources */ #define ICH_RES_GPIO 0 diff --git a/include/linux/mfd/max77686-private.h b/include/linux/mfd/max77686-private.h index b1482b3cf353..3acceeedbaba 100644 --- a/include/linux/mfd/max77686-private.h +++ b/include/linux/mfd/max77686-private.h @@ -152,7 +152,7 @@ enum max77686_rtc_reg { MAX77686_RTC_WEEKDAY = 0x0A, MAX77686_RTC_MONTH = 0x0B, MAX77686_RTC_YEAR = 0x0C, - MAX77686_RTC_DATE = 0x0D, + MAX77686_RTC_MONTHDAY = 0x0D, MAX77686_ALARM1_SEC = 0x0E, MAX77686_ALARM1_MIN = 0x0F, MAX77686_ALARM1_HOUR = 0x10, @@ -352,7 +352,7 @@ enum max77802_rtc_reg { MAX77802_RTC_WEEKDAY = 0xCA, MAX77802_RTC_MONTH = 0xCB, MAX77802_RTC_YEAR = 0xCC, - MAX77802_RTC_DATE = 0xCD, + MAX77802_RTC_MONTHDAY = 0xCD, MAX77802_RTC_AE1 = 0xCE, MAX77802_ALARM1_SEC = 0xCF, MAX77802_ALARM1_MIN = 0xD0, diff --git a/include/linux/mfd/max77714.h b/include/linux/mfd/max77714.h new file mode 100644 index 000000000000..7947e0d697a5 --- /dev/null +++ b/include/linux/mfd/max77714.h @@ -0,0 +1,60 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Maxim MAX77714 Register and data structures definition. + * + * Copyright (C) 2022 Luca Ceresoli + * Author: Luca Ceresoli <luca.ceresoli@bootlin.com> + */ + +#ifndef __LINUX_MFD_MAX77714_H_ +#define __LINUX_MFD_MAX77714_H_ + +#include <linux/bits.h> + +#define MAX77714_INT_TOP 0x00 +#define MAX77714_INT_TOPM 0x07 /* Datasheet says "read only", but it is RW */ + +#define MAX77714_INT_TOP_ONOFF BIT(1) +#define MAX77714_INT_TOP_RTC BIT(3) +#define MAX77714_INT_TOP_GPIO BIT(4) +#define MAX77714_INT_TOP_LDO BIT(5) +#define MAX77714_INT_TOP_SD BIT(6) +#define MAX77714_INT_TOP_GLBL BIT(7) + +#define MAX77714_32K_STATUS 0x30 +#define MAX77714_32K_STATUS_SIOSCOK BIT(5) +#define MAX77714_32K_STATUS_XOSCOK BIT(4) +#define MAX77714_32K_STATUS_32KSOURCE BIT(3) +#define MAX77714_32K_STATUS_32KLOAD_MSK 0x3 +#define MAX77714_32K_STATUS_32KLOAD_SHF 1 +#define MAX77714_32K_STATUS_CRYSTAL_CFG BIT(0) + +#define MAX77714_32K_CONFIG 0x31 +#define MAX77714_32K_CONFIG_XOSC_RETRY BIT(4) + +#define MAX77714_CNFG_GLBL2 0x91 +#define MAX77714_WDTEN BIT(2) +#define MAX77714_WDTSLPC BIT(3) +#define MAX77714_TWD_MASK 0x3 +#define MAX77714_TWD_2s 0x0 +#define MAX77714_TWD_16s 0x1 +#define MAX77714_TWD_64s 0x2 +#define MAX77714_TWD_128s 0x3 + +#define MAX77714_CNFG_GLBL3 0x92 +#define MAX77714_WDTC BIT(0) + +#define MAX77714_CNFG2_ONOFF 0x94 +#define MAX77714_WD_RST_WK BIT(5) + +/* Interrupts */ +enum { + MAX77714_IRQ_TOP_ONOFF, + MAX77714_IRQ_TOP_RTC, /* Real-time clock */ + MAX77714_IRQ_TOP_GPIO, /* GPIOs */ + MAX77714_IRQ_TOP_LDO, /* Low-dropout regulators */ + MAX77714_IRQ_TOP_SD, /* Step-down regulators */ + MAX77714_IRQ_TOP_GLBL, /* "Global resources": Low-Battery, overtemp... */ +}; + +#endif /* __LINUX_MFD_MAX77714_H_ */ diff --git a/include/linux/mfd/mt6331/core.h b/include/linux/mfd/mt6331/core.h new file mode 100644 index 000000000000..df8e6b1e4bc1 --- /dev/null +++ b/include/linux/mfd/mt6331/core.h @@ -0,0 +1,40 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2022 AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com> + */ + +#ifndef __MFD_MT6331_CORE_H__ +#define __MFD_MT6331_CORE_H__ + +enum mt6331_irq_status_numbers { + MT6331_IRQ_STATUS_PWRKEY = 0, + MT6331_IRQ_STATUS_HOMEKEY, + MT6331_IRQ_STATUS_CHRDET, + MT6331_IRQ_STATUS_THR_H, + MT6331_IRQ_STATUS_THR_L, + MT6331_IRQ_STATUS_BAT_H, + MT6331_IRQ_STATUS_BAT_L, + MT6331_IRQ_STATUS_RTC, + MT6331_IRQ_STATUS_AUDIO, + MT6331_IRQ_STATUS_MAD, + MT6331_IRQ_STATUS_ACCDET, + MT6331_IRQ_STATUS_ACCDET_EINT, + MT6331_IRQ_STATUS_ACCDET_NEGV = 12, + MT6331_IRQ_STATUS_VDVFS11_OC = 16, + MT6331_IRQ_STATUS_VDVFS12_OC, + MT6331_IRQ_STATUS_VDVFS13_OC, + MT6331_IRQ_STATUS_VDVFS14_OC, + MT6331_IRQ_STATUS_GPU_OC, + MT6331_IRQ_STATUS_VCORE1_OC, + MT6331_IRQ_STATUS_VCORE2_OC, + MT6331_IRQ_STATUS_VIO18_OC, + MT6331_IRQ_STATUS_LDO_OC, + MT6331_IRQ_STATUS_NR, +}; + +#define MT6331_IRQ_CON0_BASE MT6331_IRQ_STATUS_PWRKEY +#define MT6331_IRQ_CON0_BITS (MT6331_IRQ_STATUS_ACCDET_NEGV + 1) +#define MT6331_IRQ_CON1_BASE MT6331_IRQ_STATUS_VDVFS11_OC +#define MT6331_IRQ_CON1_BITS (MT6331_IRQ_STATUS_LDO_OC - MT6331_IRQ_STATUS_VDFS11_OC + 1) + +#endif /* __MFD_MT6331_CORE_H__ */ diff --git a/include/linux/mfd/mt6331/registers.h b/include/linux/mfd/mt6331/registers.h new file mode 100644 index 000000000000..e2be6bccd1a7 --- /dev/null +++ b/include/linux/mfd/mt6331/registers.h @@ -0,0 +1,584 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2022 AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com> + */ + +#ifndef __MFD_MT6331_REGISTERS_H__ +#define __MFD_MT6331_REGISTERS_H__ + +/* PMIC Registers */ +#define MT6331_STRUP_CON0 0x0 +#define MT6331_STRUP_CON2 0x2 +#define MT6331_STRUP_CON3 0x4 +#define MT6331_STRUP_CON4 0x6 +#define MT6331_STRUP_CON5 0x8 +#define MT6331_STRUP_CON6 0xA +#define MT6331_STRUP_CON7 0xC +#define MT6331_STRUP_CON8 0xE +#define MT6331_STRUP_CON9 0x10 +#define MT6331_STRUP_CON10 0x12 +#define MT6331_STRUP_CON11 0x14 +#define MT6331_STRUP_CON12 0x16 +#define MT6331_STRUP_CON13 0x18 +#define MT6331_STRUP_CON14 0x1A +#define MT6331_STRUP_CON15 0x1C +#define MT6331_STRUP_CON16 0x1E +#define MT6331_STRUP_CON17 0x20 +#define MT6331_STRUP_CON18 0x22 +#define MT6331_HWCID 0x100 +#define MT6331_SWCID 0x102 +#define MT6331_EXT_PMIC_STATUS 0x104 +#define MT6331_TOP_CON 0x106 +#define MT6331_TEST_OUT 0x108 +#define MT6331_TEST_CON0 0x10A +#define MT6331_TEST_CON1 0x10C +#define MT6331_TESTMODE_SW 0x10E +#define MT6331_EN_STATUS0 0x110 +#define MT6331_EN_STATUS1 0x112 +#define MT6331_EN_STATUS2 0x114 +#define MT6331_OCSTATUS0 0x116 +#define MT6331_OCSTATUS1 0x118 +#define MT6331_OCSTATUS2 0x11A +#define MT6331_PGSTATUS 0x11C +#define MT6331_TOPSTATUS 0x11E +#define MT6331_TDSEL_CON 0x120 +#define MT6331_RDSEL_CON 0x122 +#define MT6331_SMT_CON0 0x124 +#define MT6331_SMT_CON1 0x126 +#define MT6331_SMT_CON2 0x128 +#define MT6331_DRV_CON0 0x12A +#define MT6331_DRV_CON1 0x12C +#define MT6331_DRV_CON2 0x12E +#define MT6331_DRV_CON3 0x130 +#define MT6331_TOP_STATUS 0x132 +#define MT6331_TOP_STATUS_SET 0x134 +#define MT6331_TOP_STATUS_CLR 0x136 +#define MT6331_TOP_CKPDN_CON0 0x138 +#define MT6331_TOP_CKPDN_CON0_SET 0x13A +#define MT6331_TOP_CKPDN_CON0_CLR 0x13C +#define MT6331_TOP_CKPDN_CON1 0x13E +#define MT6331_TOP_CKPDN_CON1_SET 0x140 +#define MT6331_TOP_CKPDN_CON1_CLR 0x142 +#define MT6331_TOP_CKPDN_CON2 0x144 +#define MT6331_TOP_CKPDN_CON2_SET 0x146 +#define MT6331_TOP_CKPDN_CON2_CLR 0x148 +#define MT6331_TOP_CKSEL_CON 0x14A +#define MT6331_TOP_CKSEL_CON_SET 0x14C +#define MT6331_TOP_CKSEL_CON_CLR 0x14E +#define MT6331_TOP_CKHWEN_CON 0x150 +#define MT6331_TOP_CKHWEN_CON_SET 0x152 +#define MT6331_TOP_CKHWEN_CON_CLR 0x154 +#define MT6331_TOP_CKTST_CON0 0x156 +#define MT6331_TOP_CKTST_CON1 0x158 +#define MT6331_TOP_CLKSQ 0x15A +#define MT6331_TOP_CLKSQ_SET 0x15C +#define MT6331_TOP_CLKSQ_CLR 0x15E +#define MT6331_TOP_RST_CON 0x160 +#define MT6331_TOP_RST_CON_SET 0x162 +#define MT6331_TOP_RST_CON_CLR 0x164 +#define MT6331_TOP_RST_MISC 0x166 +#define MT6331_TOP_RST_MISC_SET 0x168 +#define MT6331_TOP_RST_MISC_CLR 0x16A +#define MT6331_INT_CON0 0x16C +#define MT6331_INT_CON0_SET 0x16E +#define MT6331_INT_CON0_CLR 0x170 +#define MT6331_INT_CON1 0x172 +#define MT6331_INT_CON1_SET 0x174 +#define MT6331_INT_CON1_CLR 0x176 +#define MT6331_INT_MISC_CON 0x178 +#define MT6331_INT_MISC_CON_SET 0x17A +#define MT6331_INT_MISC_CON_CLR 0x17C +#define MT6331_INT_STATUS_CON0 0x17E +#define MT6331_INT_STATUS_CON1 0x180 +#define MT6331_OC_GEAR_0 0x182 +#define MT6331_FQMTR_CON0 0x184 +#define MT6331_FQMTR_CON1 0x186 +#define MT6331_FQMTR_CON2 0x188 +#define MT6331_RG_SPI_CON 0x18A +#define MT6331_DEW_DIO_EN 0x18C +#define MT6331_DEW_READ_TEST 0x18E +#define MT6331_DEW_WRITE_TEST 0x190 +#define MT6331_DEW_CRC_SWRST 0x192 +#define MT6331_DEW_CRC_EN 0x194 +#define MT6331_DEW_CRC_VAL 0x196 +#define MT6331_DEW_DBG_MON_SEL 0x198 +#define MT6331_DEW_CIPHER_KEY_SEL 0x19A +#define MT6331_DEW_CIPHER_IV_SEL 0x19C +#define MT6331_DEW_CIPHER_EN 0x19E +#define MT6331_DEW_CIPHER_RDY 0x1A0 +#define MT6331_DEW_CIPHER_MODE 0x1A2 +#define MT6331_DEW_CIPHER_SWRST 0x1A4 +#define MT6331_DEW_RDDMY_NO 0x1A6 +#define MT6331_INT_TYPE_CON0 0x1A8 +#define MT6331_INT_TYPE_CON0_SET 0x1AA +#define MT6331_INT_TYPE_CON0_CLR 0x1AC +#define MT6331_INT_TYPE_CON1 0x1AE +#define MT6331_INT_TYPE_CON1_SET 0x1B0 +#define MT6331_INT_TYPE_CON1_CLR 0x1B2 +#define MT6331_INT_STA 0x1B4 +#define MT6331_BUCK_ALL_CON0 0x200 +#define MT6331_BUCK_ALL_CON1 0x202 +#define MT6331_BUCK_ALL_CON2 0x204 +#define MT6331_BUCK_ALL_CON3 0x206 +#define MT6331_BUCK_ALL_CON4 0x208 +#define MT6331_BUCK_ALL_CON5 0x20A +#define MT6331_BUCK_ALL_CON6 0x20C +#define MT6331_BUCK_ALL_CON7 0x20E +#define MT6331_BUCK_ALL_CON8 0x210 +#define MT6331_BUCK_ALL_CON9 0x212 +#define MT6331_BUCK_ALL_CON10 0x214 +#define MT6331_BUCK_ALL_CON11 0x216 +#define MT6331_BUCK_ALL_CON12 0x218 +#define MT6331_BUCK_ALL_CON13 0x21A +#define MT6331_BUCK_ALL_CON14 0x21C +#define MT6331_BUCK_ALL_CON15 0x21E +#define MT6331_BUCK_ALL_CON16 0x220 +#define MT6331_BUCK_ALL_CON17 0x222 +#define MT6331_BUCK_ALL_CON18 0x224 +#define MT6331_BUCK_ALL_CON19 0x226 +#define MT6331_BUCK_ALL_CON20 0x228 +#define MT6331_BUCK_ALL_CON21 0x22A +#define MT6331_BUCK_ALL_CON22 0x22C +#define MT6331_BUCK_ALL_CON23 0x22E +#define MT6331_BUCK_ALL_CON24 0x230 +#define MT6331_BUCK_ALL_CON25 0x232 +#define MT6331_BUCK_ALL_CON26 0x234 +#define MT6331_VDVFS11_CON0 0x236 +#define MT6331_VDVFS11_CON1 0x238 +#define MT6331_VDVFS11_CON2 0x23A +#define MT6331_VDVFS11_CON3 0x23C +#define MT6331_VDVFS11_CON4 0x23E +#define MT6331_VDVFS11_CON5 0x240 +#define MT6331_VDVFS11_CON6 0x242 +#define MT6331_VDVFS11_CON7 0x244 +#define MT6331_VDVFS11_CON8 0x246 +#define MT6331_VDVFS11_CON9 0x248 +#define MT6331_VDVFS11_CON10 0x24A +#define MT6331_VDVFS11_CON11 0x24C +#define MT6331_VDVFS11_CON12 0x24E +#define MT6331_VDVFS11_CON13 0x250 +#define MT6331_VDVFS11_CON14 0x252 +#define MT6331_VDVFS11_CON18 0x25A +#define MT6331_VDVFS11_CON19 0x25C +#define MT6331_VDVFS11_CON20 0x25E +#define MT6331_VDVFS11_CON21 0x260 +#define MT6331_VDVFS11_CON22 0x262 +#define MT6331_VDVFS11_CON23 0x264 +#define MT6331_VDVFS11_CON24 0x266 +#define MT6331_VDVFS11_CON25 0x268 +#define MT6331_VDVFS11_CON26 0x26A +#define MT6331_VDVFS11_CON27 0x26C +#define MT6331_VDVFS12_CON0 0x26E +#define MT6331_VDVFS12_CON1 0x270 +#define MT6331_VDVFS12_CON2 0x272 +#define MT6331_VDVFS12_CON3 0x274 +#define MT6331_VDVFS12_CON4 0x276 +#define MT6331_VDVFS12_CON5 0x278 +#define MT6331_VDVFS12_CON6 0x27A +#define MT6331_VDVFS12_CON7 0x27C +#define MT6331_VDVFS12_CON8 0x27E +#define MT6331_VDVFS12_CON9 0x280 +#define MT6331_VDVFS12_CON10 0x282 +#define MT6331_VDVFS12_CON11 0x284 +#define MT6331_VDVFS12_CON12 0x286 +#define MT6331_VDVFS12_CON13 0x288 +#define MT6331_VDVFS12_CON14 0x28A +#define MT6331_VDVFS12_CON18 0x292 +#define MT6331_VDVFS12_CON19 0x294 +#define MT6331_VDVFS12_CON20 0x296 +#define MT6331_VDVFS13_CON0 0x298 +#define MT6331_VDVFS13_CON1 0x29A +#define MT6331_VDVFS13_CON2 0x29C +#define MT6331_VDVFS13_CON3 0x29E +#define MT6331_VDVFS13_CON4 0x2A0 +#define MT6331_VDVFS13_CON5 0x2A2 +#define MT6331_VDVFS13_CON6 0x2A4 +#define MT6331_VDVFS13_CON7 0x2A6 +#define MT6331_VDVFS13_CON8 0x2A8 +#define MT6331_VDVFS13_CON9 0x2AA +#define MT6331_VDVFS13_CON10 0x2AC +#define MT6331_VDVFS13_CON11 0x2AE +#define MT6331_VDVFS13_CON12 0x2B0 +#define MT6331_VDVFS13_CON13 0x2B2 +#define MT6331_VDVFS13_CON14 0x2B4 +#define MT6331_VDVFS13_CON18 0x2BC +#define MT6331_VDVFS13_CON19 0x2BE +#define MT6331_VDVFS13_CON20 0x2C0 +#define MT6331_VDVFS14_CON0 0x2C2 +#define MT6331_VDVFS14_CON1 0x2C4 +#define MT6331_VDVFS14_CON2 0x2C6 +#define MT6331_VDVFS14_CON3 0x2C8 +#define MT6331_VDVFS14_CON4 0x2CA +#define MT6331_VDVFS14_CON5 0x2CC +#define MT6331_VDVFS14_CON6 0x2CE +#define MT6331_VDVFS14_CON7 0x2D0 +#define MT6331_VDVFS14_CON8 0x2D2 +#define MT6331_VDVFS14_CON9 0x2D4 +#define MT6331_VDVFS14_CON10 0x2D6 +#define MT6331_VDVFS14_CON11 0x2D8 +#define MT6331_VDVFS14_CON12 0x2DA +#define MT6331_VDVFS14_CON13 0x2DC +#define MT6331_VDVFS14_CON14 0x2DE +#define MT6331_VDVFS14_CON18 0x2E6 +#define MT6331_VDVFS14_CON19 0x2E8 +#define MT6331_VDVFS14_CON20 0x2EA +#define MT6331_VGPU_CON0 0x300 +#define MT6331_VGPU_CON1 0x302 +#define MT6331_VGPU_CON2 0x304 +#define MT6331_VGPU_CON3 0x306 +#define MT6331_VGPU_CON4 0x308 +#define MT6331_VGPU_CON5 0x30A +#define MT6331_VGPU_CON6 0x30C +#define MT6331_VGPU_CON7 0x30E +#define MT6331_VGPU_CON8 0x310 +#define MT6331_VGPU_CON9 0x312 +#define MT6331_VGPU_CON10 0x314 +#define MT6331_VGPU_CON11 0x316 +#define MT6331_VGPU_CON12 0x318 +#define MT6331_VGPU_CON13 0x31A +#define MT6331_VGPU_CON14 0x31C +#define MT6331_VGPU_CON15 0x31E +#define MT6331_VGPU_CON16 0x320 +#define MT6331_VGPU_CON17 0x322 +#define MT6331_VGPU_CON18 0x324 +#define MT6331_VGPU_CON19 0x326 +#define MT6331_VGPU_CON20 0x328 +#define MT6331_VCORE1_CON0 0x32A +#define MT6331_VCORE1_CON1 0x32C +#define MT6331_VCORE1_CON2 0x32E +#define MT6331_VCORE1_CON3 0x330 +#define MT6331_VCORE1_CON4 0x332 +#define MT6331_VCORE1_CON5 0x334 +#define MT6331_VCORE1_CON6 0x336 +#define MT6331_VCORE1_CON7 0x338 +#define MT6331_VCORE1_CON8 0x33A +#define MT6331_VCORE1_CON9 0x33C +#define MT6331_VCORE1_CON10 0x33E +#define MT6331_VCORE1_CON11 0x340 +#define MT6331_VCORE1_CON12 0x342 +#define MT6331_VCORE1_CON13 0x344 +#define MT6331_VCORE1_CON14 0x346 +#define MT6331_VCORE1_CON15 0x348 +#define MT6331_VCORE1_CON16 0x34A +#define MT6331_VCORE1_CON17 0x34C +#define MT6331_VCORE1_CON18 0x34E +#define MT6331_VCORE1_CON19 0x350 +#define MT6331_VCORE1_CON20 0x352 +#define MT6331_VCORE2_CON0 0x354 +#define MT6331_VCORE2_CON1 0x356 +#define MT6331_VCORE2_CON2 0x358 +#define MT6331_VCORE2_CON3 0x35A +#define MT6331_VCORE2_CON4 0x35C +#define MT6331_VCORE2_CON5 0x35E +#define MT6331_VCORE2_CON6 0x360 +#define MT6331_VCORE2_CON7 0x362 +#define MT6331_VCORE2_CON8 0x364 +#define MT6331_VCORE2_CON9 0x366 +#define MT6331_VCORE2_CON10 0x368 +#define MT6331_VCORE2_CON11 0x36A +#define MT6331_VCORE2_CON12 0x36C +#define MT6331_VCORE2_CON13 0x36E +#define MT6331_VCORE2_CON14 0x370 +#define MT6331_VCORE2_CON15 0x372 +#define MT6331_VCORE2_CON16 0x374 +#define MT6331_VCORE2_CON17 0x376 +#define MT6331_VCORE2_CON18 0x378 +#define MT6331_VCORE2_CON19 0x37A +#define MT6331_VCORE2_CON20 0x37C +#define MT6331_VCORE2_CON21 0x37E +#define MT6331_VIO18_CON0 0x380 +#define MT6331_VIO18_CON1 0x382 +#define MT6331_VIO18_CON2 0x384 +#define MT6331_VIO18_CON3 0x386 +#define MT6331_VIO18_CON4 0x388 +#define MT6331_VIO18_CON5 0x38A +#define MT6331_VIO18_CON6 0x38C +#define MT6331_VIO18_CON7 0x38E +#define MT6331_VIO18_CON8 0x390 +#define MT6331_VIO18_CON9 0x392 +#define MT6331_VIO18_CON10 0x394 +#define MT6331_VIO18_CON11 0x396 +#define MT6331_VIO18_CON12 0x398 +#define MT6331_VIO18_CON13 0x39A +#define MT6331_VIO18_CON14 0x39C +#define MT6331_VIO18_CON15 0x39E +#define MT6331_VIO18_CON16 0x3A0 +#define MT6331_VIO18_CON17 0x3A2 +#define MT6331_VIO18_CON18 0x3A4 +#define MT6331_VIO18_CON19 0x3A6 +#define MT6331_VIO18_CON20 0x3A8 +#define MT6331_BUCK_K_CON0 0x3AA +#define MT6331_BUCK_K_CON1 0x3AC +#define MT6331_BUCK_K_CON2 0x3AE +#define MT6331_BUCK_K_CON3 0x3B0 +#define MT6331_ZCD_CON0 0x400 +#define MT6331_ZCD_CON1 0x402 +#define MT6331_ZCD_CON2 0x404 +#define MT6331_ZCD_CON3 0x406 +#define MT6331_ZCD_CON4 0x408 +#define MT6331_ZCD_CON5 0x40A +#define MT6331_ISINK0_CON0 0x40C +#define MT6331_ISINK0_CON1 0x40E +#define MT6331_ISINK0_CON2 0x410 +#define MT6331_ISINK0_CON3 0x412 +#define MT6331_ISINK0_CON4 0x414 +#define MT6331_ISINK1_CON0 0x416 +#define MT6331_ISINK1_CON1 0x418 +#define MT6331_ISINK1_CON2 0x41A +#define MT6331_ISINK1_CON3 0x41C +#define MT6331_ISINK1_CON4 0x41E +#define MT6331_ISINK2_CON0 0x420 +#define MT6331_ISINK2_CON1 0x422 +#define MT6331_ISINK2_CON2 0x424 +#define MT6331_ISINK2_CON3 0x426 +#define MT6331_ISINK2_CON4 0x428 +#define MT6331_ISINK3_CON0 0x42A +#define MT6331_ISINK3_CON1 0x42C +#define MT6331_ISINK3_CON2 0x42E +#define MT6331_ISINK3_CON3 0x430 +#define MT6331_ISINK3_CON4 0x432 +#define MT6331_ISINK_ANA0 0x434 +#define MT6331_ISINK_ANA1 0x436 +#define MT6331_ISINK_PHASE_DLY 0x438 +#define MT6331_ISINK_EN_CTRL 0x43A +#define MT6331_ANALDO_CON0 0x500 +#define MT6331_ANALDO_CON1 0x502 +#define MT6331_ANALDO_CON2 0x504 +#define MT6331_ANALDO_CON3 0x506 +#define MT6331_ANALDO_CON4 0x508 +#define MT6331_ANALDO_CON5 0x50A +#define MT6331_ANALDO_CON6 0x50C +#define MT6331_ANALDO_CON7 0x50E +#define MT6331_ANALDO_CON8 0x510 +#define MT6331_ANALDO_CON9 0x512 +#define MT6331_ANALDO_CON10 0x514 +#define MT6331_ANALDO_CON11 0x516 +#define MT6331_ANALDO_CON12 0x518 +#define MT6331_ANALDO_CON13 0x51A +#define MT6331_SYSLDO_CON0 0x51C +#define MT6331_SYSLDO_CON1 0x51E +#define MT6331_SYSLDO_CON2 0x520 +#define MT6331_SYSLDO_CON3 0x522 +#define MT6331_SYSLDO_CON4 0x524 +#define MT6331_SYSLDO_CON5 0x526 +#define MT6331_SYSLDO_CON6 0x528 +#define MT6331_SYSLDO_CON7 0x52A +#define MT6331_SYSLDO_CON8 0x52C +#define MT6331_SYSLDO_CON9 0x52E +#define MT6331_SYSLDO_CON10 0x530 +#define MT6331_SYSLDO_CON11 0x532 +#define MT6331_SYSLDO_CON12 0x534 +#define MT6331_SYSLDO_CON13 0x536 +#define MT6331_SYSLDO_CON14 0x538 +#define MT6331_SYSLDO_CON15 0x53A +#define MT6331_SYSLDO_CON16 0x53C +#define MT6331_SYSLDO_CON17 0x53E +#define MT6331_SYSLDO_CON18 0x540 +#define MT6331_SYSLDO_CON19 0x542 +#define MT6331_SYSLDO_CON20 0x544 +#define MT6331_SYSLDO_CON21 0x546 +#define MT6331_DIGLDO_CON0 0x548 +#define MT6331_DIGLDO_CON1 0x54A +#define MT6331_DIGLDO_CON2 0x54C +#define MT6331_DIGLDO_CON3 0x54E +#define MT6331_DIGLDO_CON4 0x550 +#define MT6331_DIGLDO_CON5 0x552 +#define MT6331_DIGLDO_CON6 0x554 +#define MT6331_DIGLDO_CON7 0x556 +#define MT6331_DIGLDO_CON8 0x558 +#define MT6331_DIGLDO_CON9 0x55A +#define MT6331_DIGLDO_CON10 0x55C +#define MT6331_DIGLDO_CON11 0x55E +#define MT6331_DIGLDO_CON12 0x560 +#define MT6331_DIGLDO_CON13 0x562 +#define MT6331_DIGLDO_CON14 0x564 +#define MT6331_DIGLDO_CON15 0x566 +#define MT6331_DIGLDO_CON16 0x568 +#define MT6331_DIGLDO_CON17 0x56A +#define MT6331_DIGLDO_CON18 0x56C +#define MT6331_DIGLDO_CON19 0x56E +#define MT6331_DIGLDO_CON20 0x570 +#define MT6331_DIGLDO_CON21 0x572 +#define MT6331_DIGLDO_CON22 0x574 +#define MT6331_DIGLDO_CON23 0x576 +#define MT6331_DIGLDO_CON24 0x578 +#define MT6331_DIGLDO_CON25 0x57A +#define MT6331_DIGLDO_CON26 0x57C +#define MT6331_DIGLDO_CON27 0x57E +#define MT6331_DIGLDO_CON28 0x580 +#define MT6331_OTP_CON0 0x600 +#define MT6331_OTP_CON1 0x602 +#define MT6331_OTP_CON2 0x604 +#define MT6331_OTP_CON3 0x606 +#define MT6331_OTP_CON4 0x608 +#define MT6331_OTP_CON5 0x60A +#define MT6331_OTP_CON6 0x60C +#define MT6331_OTP_CON7 0x60E +#define MT6331_OTP_CON8 0x610 +#define MT6331_OTP_CON9 0x612 +#define MT6331_OTP_CON10 0x614 +#define MT6331_OTP_CON11 0x616 +#define MT6331_OTP_CON12 0x618 +#define MT6331_OTP_CON13 0x61A +#define MT6331_OTP_CON14 0x61C +#define MT6331_OTP_DOUT_0_15 0x61E +#define MT6331_OTP_DOUT_16_31 0x620 +#define MT6331_OTP_DOUT_32_47 0x622 +#define MT6331_OTP_DOUT_48_63 0x624 +#define MT6331_OTP_DOUT_64_79 0x626 +#define MT6331_OTP_DOUT_80_95 0x628 +#define MT6331_OTP_DOUT_96_111 0x62A +#define MT6331_OTP_DOUT_112_127 0x62C +#define MT6331_OTP_DOUT_128_143 0x62E +#define MT6331_OTP_DOUT_144_159 0x630 +#define MT6331_OTP_DOUT_160_175 0x632 +#define MT6331_OTP_DOUT_176_191 0x634 +#define MT6331_OTP_DOUT_192_207 0x636 +#define MT6331_OTP_DOUT_208_223 0x638 +#define MT6331_OTP_DOUT_224_239 0x63A +#define MT6331_OTP_DOUT_240_255 0x63C +#define MT6331_OTP_VAL_0_15 0x63E +#define MT6331_OTP_VAL_16_31 0x640 +#define MT6331_OTP_VAL_32_47 0x642 +#define MT6331_OTP_VAL_48_63 0x644 +#define MT6331_OTP_VAL_64_79 0x646 +#define MT6331_OTP_VAL_80_95 0x648 +#define MT6331_OTP_VAL_96_111 0x64A +#define MT6331_OTP_VAL_112_127 0x64C +#define MT6331_OTP_VAL_128_143 0x64E +#define MT6331_OTP_VAL_144_159 0x650 +#define MT6331_OTP_VAL_160_175 0x652 +#define MT6331_OTP_VAL_176_191 0x654 +#define MT6331_OTP_VAL_192_207 0x656 +#define MT6331_OTP_VAL_208_223 0x658 +#define MT6331_OTP_VAL_224_239 0x65A +#define MT6331_OTP_VAL_240_255 0x65C +#define MT6331_RTC_MIX_CON0 0x65E +#define MT6331_RTC_MIX_CON1 0x660 +#define MT6331_AUDDAC_CFG0 0x662 +#define MT6331_AUDBUF_CFG0 0x664 +#define MT6331_AUDBUF_CFG1 0x666 +#define MT6331_AUDBUF_CFG2 0x668 +#define MT6331_AUDBUF_CFG3 0x66A +#define MT6331_AUDBUF_CFG4 0x66C +#define MT6331_AUDBUF_CFG5 0x66E +#define MT6331_AUDBUF_CFG6 0x670 +#define MT6331_AUDBUF_CFG7 0x672 +#define MT6331_AUDBUF_CFG8 0x674 +#define MT6331_IBIASDIST_CFG0 0x676 +#define MT6331_AUDCLKGEN_CFG0 0x678 +#define MT6331_AUDLDO_CFG0 0x67A +#define MT6331_AUDDCDC_CFG0 0x67C +#define MT6331_AUDDCDC_CFG1 0x67E +#define MT6331_AUDNVREGGLB_CFG0 0x680 +#define MT6331_AUD_NCP0 0x682 +#define MT6331_AUD_ZCD_CFG0 0x684 +#define MT6331_AUDPREAMP_CFG0 0x686 +#define MT6331_AUDPREAMP_CFG1 0x688 +#define MT6331_AUDPREAMP_CFG2 0x68A +#define MT6331_AUDADC_CFG0 0x68C +#define MT6331_AUDADC_CFG1 0x68E +#define MT6331_AUDADC_CFG2 0x690 +#define MT6331_AUDADC_CFG3 0x692 +#define MT6331_AUDADC_CFG4 0x694 +#define MT6331_AUDADC_CFG5 0x696 +#define MT6331_AUDDIGMI_CFG0 0x698 +#define MT6331_AUDDIGMI_CFG1 0x69A +#define MT6331_AUDMICBIAS_CFG0 0x69C +#define MT6331_AUDMICBIAS_CFG1 0x69E +#define MT6331_AUDENCSPARE_CFG0 0x6A0 +#define MT6331_AUDPREAMPGAIN_CFG0 0x6A2 +#define MT6331_AUDMADPLL_CFG0 0x6A4 +#define MT6331_AUDMADPLL_CFG1 0x6A6 +#define MT6331_AUDMADPLL_CFG2 0x6A8 +#define MT6331_AUDLDO_NVREG_CFG0 0x6AA +#define MT6331_AUDLDO_NVREG_CFG1 0x6AC +#define MT6331_AUDLDO_NVREG_CFG2 0x6AE +#define MT6331_AUXADC_ADC0 0x700 +#define MT6331_AUXADC_ADC1 0x702 +#define MT6331_AUXADC_ADC2 0x704 +#define MT6331_AUXADC_ADC3 0x706 +#define MT6331_AUXADC_ADC4 0x708 +#define MT6331_AUXADC_ADC5 0x70A +#define MT6331_AUXADC_ADC6 0x70C +#define MT6331_AUXADC_ADC7 0x70E +#define MT6331_AUXADC_ADC8 0x710 +#define MT6331_AUXADC_ADC9 0x712 +#define MT6331_AUXADC_ADC10 0x714 +#define MT6331_AUXADC_ADC11 0x716 +#define MT6331_AUXADC_ADC12 0x718 +#define MT6331_AUXADC_ADC13 0x71A +#define MT6331_AUXADC_ADC14 0x71C +#define MT6331_AUXADC_ADC15 0x71E +#define MT6331_AUXADC_ADC16 0x720 +#define MT6331_AUXADC_ADC17 0x722 +#define MT6331_AUXADC_ADC18 0x724 +#define MT6331_AUXADC_ADC19 0x726 +#define MT6331_AUXADC_STA0 0x728 +#define MT6331_AUXADC_STA1 0x72A +#define MT6331_AUXADC_RQST0 0x72C +#define MT6331_AUXADC_RQST0_SET 0x72E +#define MT6331_AUXADC_RQST0_CLR 0x730 +#define MT6331_AUXADC_RQST1 0x732 +#define MT6331_AUXADC_RQST1_SET 0x734 +#define MT6331_AUXADC_RQST1_CLR 0x736 +#define MT6331_AUXADC_CON0 0x738 +#define MT6331_AUXADC_CON1 0x73A +#define MT6331_AUXADC_CON2 0x73C +#define MT6331_AUXADC_CON3 0x73E +#define MT6331_AUXADC_CON4 0x740 +#define MT6331_AUXADC_CON5 0x742 +#define MT6331_AUXADC_CON6 0x744 +#define MT6331_AUXADC_CON7 0x746 +#define MT6331_AUXADC_CON8 0x748 +#define MT6331_AUXADC_CON9 0x74A +#define MT6331_AUXADC_CON10 0x74C +#define MT6331_AUXADC_CON11 0x74E +#define MT6331_AUXADC_CON12 0x750 +#define MT6331_AUXADC_CON13 0x752 +#define MT6331_AUXADC_CON14 0x754 +#define MT6331_AUXADC_CON15 0x756 +#define MT6331_AUXADC_CON16 0x758 +#define MT6331_AUXADC_CON17 0x75A +#define MT6331_AUXADC_CON18 0x75C +#define MT6331_AUXADC_CON19 0x75E +#define MT6331_AUXADC_CON20 0x760 +#define MT6331_AUXADC_CON21 0x762 +#define MT6331_AUXADC_CON22 0x764 +#define MT6331_AUXADC_CON23 0x766 +#define MT6331_AUXADC_CON24 0x768 +#define MT6331_AUXADC_CON25 0x76A +#define MT6331_AUXADC_CON26 0x76C +#define MT6331_AUXADC_CON27 0x76E +#define MT6331_AUXADC_CON28 0x770 +#define MT6331_AUXADC_CON29 0x772 +#define MT6331_AUXADC_CON30 0x774 +#define MT6331_AUXADC_CON31 0x776 +#define MT6331_AUXADC_CON32 0x778 +#define MT6331_ACCDET_CON0 0x77A +#define MT6331_ACCDET_CON1 0x77C +#define MT6331_ACCDET_CON2 0x77E +#define MT6331_ACCDET_CON3 0x780 +#define MT6331_ACCDET_CON4 0x782 +#define MT6331_ACCDET_CON5 0x784 +#define MT6331_ACCDET_CON6 0x786 +#define MT6331_ACCDET_CON7 0x788 +#define MT6331_ACCDET_CON8 0x78A +#define MT6331_ACCDET_CON9 0x78C +#define MT6331_ACCDET_CON10 0x78E +#define MT6331_ACCDET_CON11 0x790 +#define MT6331_ACCDET_CON12 0x792 +#define MT6331_ACCDET_CON13 0x794 +#define MT6331_ACCDET_CON14 0x796 +#define MT6331_ACCDET_CON15 0x798 +#define MT6331_ACCDET_CON16 0x79A +#define MT6331_ACCDET_CON17 0x79C +#define MT6331_ACCDET_CON18 0x79E +#define MT6331_ACCDET_CON19 0x7A0 +#define MT6331_ACCDET_CON20 0x7A2 +#define MT6331_ACCDET_CON21 0x7A4 +#define MT6331_ACCDET_CON22 0x7A6 +#define MT6331_ACCDET_CON23 0x7A8 +#define MT6331_ACCDET_CON24 0x7AA + +#endif /* __MFD_MT6331_REGISTERS_H__ */ diff --git a/include/linux/mfd/mt6332/core.h b/include/linux/mfd/mt6332/core.h new file mode 100644 index 000000000000..cd6013eb82d9 --- /dev/null +++ b/include/linux/mfd/mt6332/core.h @@ -0,0 +1,65 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2022 AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com> + */ + +#ifndef __MFD_MT6332_CORE_H__ +#define __MFD_MT6332_CORE_H__ + +enum mt6332_irq_status_numbers { + MT6332_IRQ_STATUS_CHR_COMPLETE = 0, + MT6332_IRQ_STATUS_THERMAL_SD, + MT6332_IRQ_STATUS_THERMAL_REG_IN, + MT6332_IRQ_STATUS_THERMAL_REG_OUT, + MT6332_IRQ_STATUS_OTG_OC, + MT6332_IRQ_STATUS_CHR_OC, + MT6332_IRQ_STATUS_OTG_THERMAL, + MT6332_IRQ_STATUS_CHRIN_SHORT, + MT6332_IRQ_STATUS_DRVCDT_SHORT, + MT6332_IRQ_STATUS_PLUG_IN_FLASH, + MT6332_IRQ_STATUS_CHRWDT_FLAG, + MT6332_IRQ_STATUS_FLASH_EN_TIMEOUT, + MT6332_IRQ_STATUS_FLASH_VLED1_SHORT, + MT6332_IRQ_STATUS_FLASH_VLED1_OPEN = 13, + MT6332_IRQ_STATUS_OV = 16, + MT6332_IRQ_STATUS_BVALID_DET, + MT6332_IRQ_STATUS_VBATON_UNDET, + MT6332_IRQ_STATUS_CHR_PLUG_IN, + MT6332_IRQ_STATUS_CHR_PLUG_OUT, + MT6332_IRQ_STATUS_BC11_TIMEOUT, + MT6332_IRQ_STATUS_FLASH_VLED2_SHORT, + MT6332_IRQ_STATUS_FLASH_VLED2_OPEN = 23, + MT6332_IRQ_STATUS_THR_H = 32, + MT6332_IRQ_STATUS_THR_L, + MT6332_IRQ_STATUS_BAT_H, + MT6332_IRQ_STATUS_BAT_L, + MT6332_IRQ_STATUS_M3_H, + MT6332_IRQ_STATUS_M3_L, + MT6332_IRQ_STATUS_FG_BAT_H, + MT6332_IRQ_STATUS_FG_BAT_L, + MT6332_IRQ_STATUS_FG_CUR_H, + MT6332_IRQ_STATUS_FG_CUR_L, + MT6332_IRQ_STATUS_SPKL_D, + MT6332_IRQ_STATUS_SPKL_AB, + MT6332_IRQ_STATUS_BIF, + MT6332_IRQ_STATUS_VWLED_OC = 45, + MT6332_IRQ_STATUS_VDRAM_OC = 48, + MT6332_IRQ_STATUS_VDVFS2_OC, + MT6332_IRQ_STATUS_VRF1_OC, + MT6332_IRQ_STATUS_VRF2_OC, + MT6332_IRQ_STATUS_VPA_OC, + MT6332_IRQ_STATUS_VSBST_OC, + MT6332_IRQ_STATUS_LDO_OC, + MT6332_IRQ_STATUS_NR, +}; + +#define MT6332_IRQ_CON0_BASE MT6332_IRQ_STATUS_CHR_COMPLETE +#define MT6332_IRQ_CON0_BITS (MT6332_IRQ_STATUS_FLASH_VLED1_OPEN + 1) +#define MT6332_IRQ_CON1_BASE MT6332_IRQ_STATUS_OV +#define MT6332_IRQ_CON1_BITS (MT6332_IRQ_STATUS_FLASH_VLED2_OPEN - MT6332_IRQ_STATUS_OV + 1) +#define MT6332_IRQ_CON2_BASE MT6332_IRQ_STATUS_THR_H +#define MT6332_IRQ_CON2_BITS (MT6332_IRQ_STATUS_VWLED_OC - MT6332_IRQ_STATUS_THR_H + 1) +#define MT6332_IRQ_CON3_BASE MT6332_IRQ_STATUS_VDRAM_OC +#define MT6332_IRQ_CON3_BITS (MT6332_IRQ_STATUS_LDO_OC - MT6332_IRQ_STATUS_VDRAM_OC + 1) + +#endif /* __MFD_MT6332_CORE_H__ */ diff --git a/include/linux/mfd/mt6332/registers.h b/include/linux/mfd/mt6332/registers.h new file mode 100644 index 000000000000..65e0b86fceac --- /dev/null +++ b/include/linux/mfd/mt6332/registers.h @@ -0,0 +1,642 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2022 AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com> + */ + +#ifndef __MFD_MT6332_REGISTERS_H__ +#define __MFD_MT6332_REGISTERS_H__ + +/* PMIC Registers */ +#define MT6332_HWCID 0x8000 +#define MT6332_SWCID 0x8002 +#define MT6332_TOP_CON 0x8004 +#define MT6332_DDR_VREF_AP_CON 0x8006 +#define MT6332_DDR_VREF_DQ_CON 0x8008 +#define MT6332_DDR_VREF_CA_CON 0x800A +#define MT6332_TEST_OUT 0x800C +#define MT6332_TEST_CON0 0x800E +#define MT6332_TEST_CON1 0x8010 +#define MT6332_TESTMODE_SW 0x8012 +#define MT6332_TESTMODE_ANA 0x8014 +#define MT6332_TDSEL_CON 0x8016 +#define MT6332_RDSEL_CON 0x8018 +#define MT6332_SMT_CON0 0x801A +#define MT6332_SMT_CON1 0x801C +#define MT6332_DRV_CON0 0x801E +#define MT6332_DRV_CON1 0x8020 +#define MT6332_DRV_CON2 0x8022 +#define MT6332_EN_STATUS0 0x8024 +#define MT6332_OCSTATUS0 0x8026 +#define MT6332_TOP_STATUS 0x8028 +#define MT6332_TOP_STATUS_SET 0x802A +#define MT6332_TOP_STATUS_CLR 0x802C +#define MT6332_FLASH_CON0 0x802E +#define MT6332_FLASH_CON1 0x8030 +#define MT6332_FLASH_CON2 0x8032 +#define MT6332_CORE_CON0 0x8034 +#define MT6332_CORE_CON1 0x8036 +#define MT6332_CORE_CON2 0x8038 +#define MT6332_CORE_CON3 0x803A +#define MT6332_CORE_CON4 0x803C +#define MT6332_CORE_CON5 0x803E +#define MT6332_CORE_CON6 0x8040 +#define MT6332_CORE_CON7 0x8042 +#define MT6332_CORE_CON8 0x8044 +#define MT6332_CORE_CON9 0x8046 +#define MT6332_CORE_CON10 0x8048 +#define MT6332_CORE_CON11 0x804A +#define MT6332_CORE_CON12 0x804C +#define MT6332_CORE_CON13 0x804E +#define MT6332_CORE_CON14 0x8050 +#define MT6332_CORE_CON15 0x8052 +#define MT6332_STA_CON0 0x8054 +#define MT6332_STA_CON1 0x8056 +#define MT6332_STA_CON2 0x8058 +#define MT6332_STA_CON3 0x805A +#define MT6332_STA_CON4 0x805C +#define MT6332_STA_CON5 0x805E +#define MT6332_STA_CON6 0x8060 +#define MT6332_STA_CON7 0x8062 +#define MT6332_CHR_CON0 0x8064 +#define MT6332_CHR_CON1 0x8066 +#define MT6332_CHR_CON2 0x8068 +#define MT6332_CHR_CON3 0x806A +#define MT6332_CHR_CON4 0x806C +#define MT6332_CHR_CON5 0x806E +#define MT6332_CHR_CON6 0x8070 +#define MT6332_CHR_CON7 0x8072 +#define MT6332_CHR_CON8 0x8074 +#define MT6332_CHR_CON9 0x8076 +#define MT6332_CHR_CON10 0x8078 +#define MT6332_CHR_CON11 0x807A +#define MT6332_CHR_CON12 0x807C +#define MT6332_CHR_CON13 0x807E +#define MT6332_CHR_CON14 0x8080 +#define MT6332_CHR_CON15 0x8082 +#define MT6332_BOOST_CON0 0x8084 +#define MT6332_BOOST_CON1 0x8086 +#define MT6332_BOOST_CON2 0x8088 +#define MT6332_BOOST_CON3 0x808A +#define MT6332_BOOST_CON4 0x808C +#define MT6332_BOOST_CON5 0x808E +#define MT6332_BOOST_CON6 0x8090 +#define MT6332_BOOST_CON7 0x8092 +#define MT6332_TOP_CKPDN_CON0 0x8094 +#define MT6332_TOP_CKPDN_CON0_SET 0x8096 +#define MT6332_TOP_CKPDN_CON0_CLR 0x8098 +#define MT6332_TOP_CKPDN_CON1 0x809A +#define MT6332_TOP_CKPDN_CON1_SET 0x809C +#define MT6332_TOP_CKPDN_CON1_CLR 0x809E +#define MT6332_TOP_CKPDN_CON2 0x80A0 +#define MT6332_TOP_CKPDN_CON2_SET 0x80A2 +#define MT6332_TOP_CKPDN_CON2_CLR 0x80A4 +#define MT6332_TOP_CKSEL_CON0 0x80A6 +#define MT6332_TOP_CKSEL_CON0_SET 0x80A8 +#define MT6332_TOP_CKSEL_CON0_CLR 0x80AA +#define MT6332_TOP_CKSEL_CON1 0x80AC +#define MT6332_TOP_CKSEL_CON1_SET 0x80AE +#define MT6332_TOP_CKSEL_CON1_CLR 0x80B0 +#define MT6332_TOP_CKHWEN_CON 0x80B2 +#define MT6332_TOP_CKHWEN_CON_SET 0x80B4 +#define MT6332_TOP_CKHWEN_CON_CLR 0x80B6 +#define MT6332_TOP_CKTST_CON0 0x80B8 +#define MT6332_TOP_CKTST_CON1 0x80BA +#define MT6332_TOP_RST_CON 0x80BC +#define MT6332_TOP_RST_CON_SET 0x80BE +#define MT6332_TOP_RST_CON_CLR 0x80C0 +#define MT6332_TOP_RST_MISC 0x80C2 +#define MT6332_TOP_RST_MISC_SET 0x80C4 +#define MT6332_TOP_RST_MISC_CLR 0x80C6 +#define MT6332_INT_CON0 0x80C8 +#define MT6332_INT_CON0_SET 0x80CA +#define MT6332_INT_CON0_CLR 0x80CC +#define MT6332_INT_CON1 0x80CE +#define MT6332_INT_CON1_SET 0x80D0 +#define MT6332_INT_CON1_CLR 0x80D2 +#define MT6332_INT_CON2 0x80D4 +#define MT6332_INT_CON2_SET 0x80D6 +#define MT6332_INT_CON2_CLR 0x80D8 +#define MT6332_INT_CON3 0x80DA +#define MT6332_INT_CON3_SET 0x80DC +#define MT6332_INT_CON3_CLR 0x80DE +#define MT6332_CHRWDT_CON0 0x80E0 +#define MT6332_CHRWDT_STATUS0 0x80E2 +#define MT6332_INT_STATUS0 0x80E4 +#define MT6332_INT_STATUS1 0x80E6 +#define MT6332_INT_STATUS2 0x80E8 +#define MT6332_INT_STATUS3 0x80EA +#define MT6332_OC_GEAR_0 0x80EC +#define MT6332_OC_GEAR_1 0x80EE +#define MT6332_OC_GEAR_2 0x80F0 +#define MT6332_INT_MISC_CON 0x80F2 +#define MT6332_RG_SPI_CON 0x80F4 +#define MT6332_DEW_DIO_EN 0x80F6 +#define MT6332_DEW_READ_TEST 0x80F8 +#define MT6332_DEW_WRITE_TEST 0x80FA +#define MT6332_DEW_CRC_SWRST 0x80FC +#define MT6332_DEW_CRC_EN 0x80FE +#define MT6332_DEW_CRC_VAL 0x8100 +#define MT6332_DEW_DBG_MON_SEL 0x8102 +#define MT6332_DEW_CIPHER_KEY_SEL 0x8104 +#define MT6332_DEW_CIPHER_IV_SEL 0x8106 +#define MT6332_DEW_CIPHER_EN 0x8108 +#define MT6332_DEW_CIPHER_RDY 0x810A +#define MT6332_DEW_CIPHER_MODE 0x810C +#define MT6332_DEW_CIPHER_SWRST 0x810E +#define MT6332_DEW_RDDMY_NO 0x8110 +#define MT6332_INT_STA 0x8112 +#define MT6332_BIF_CON0 0x8114 +#define MT6332_BIF_CON1 0x8116 +#define MT6332_BIF_CON2 0x8118 +#define MT6332_BIF_CON3 0x811A +#define MT6332_BIF_CON4 0x811C +#define MT6332_BIF_CON5 0x811E +#define MT6332_BIF_CON6 0x8120 +#define MT6332_BIF_CON7 0x8122 +#define MT6332_BIF_CON8 0x8124 +#define MT6332_BIF_CON9 0x8126 +#define MT6332_BIF_CON10 0x8128 +#define MT6332_BIF_CON11 0x812A +#define MT6332_BIF_CON12 0x812C +#define MT6332_BIF_CON13 0x812E +#define MT6332_BIF_CON14 0x8130 +#define MT6332_BIF_CON15 0x8132 +#define MT6332_BIF_CON16 0x8134 +#define MT6332_BIF_CON17 0x8136 +#define MT6332_BIF_CON18 0x8138 +#define MT6332_BIF_CON19 0x813A +#define MT6332_BIF_CON20 0x813C +#define MT6332_BIF_CON21 0x813E +#define MT6332_BIF_CON22 0x8140 +#define MT6332_BIF_CON23 0x8142 +#define MT6332_BIF_CON24 0x8144 +#define MT6332_BIF_CON25 0x8146 +#define MT6332_BIF_CON26 0x8148 +#define MT6332_BIF_CON27 0x814A +#define MT6332_BIF_CON28 0x814C +#define MT6332_BIF_CON29 0x814E +#define MT6332_BIF_CON30 0x8150 +#define MT6332_BIF_CON31 0x8152 +#define MT6332_BIF_CON32 0x8154 +#define MT6332_BIF_CON33 0x8156 +#define MT6332_BIF_CON34 0x8158 +#define MT6332_BIF_CON35 0x815A +#define MT6332_BIF_CON36 0x815C +#define MT6332_BATON_CON0 0x815E +#define MT6332_BIF_CON37 0x8160 +#define MT6332_BIF_CON38 0x8162 +#define MT6332_CHR_CON16 0x8164 +#define MT6332_CHR_CON17 0x8166 +#define MT6332_CHR_CON18 0x8168 +#define MT6332_CHR_CON19 0x816A +#define MT6332_CHR_CON20 0x816C +#define MT6332_CHR_CON21 0x816E +#define MT6332_CHR_CON22 0x8170 +#define MT6332_CHR_CON23 0x8172 +#define MT6332_CHR_CON24 0x8174 +#define MT6332_CHR_CON25 0x8176 +#define MT6332_STA_CON8 0x8178 +#define MT6332_BUCK_ALL_CON0 0x8400 +#define MT6332_BUCK_ALL_CON1 0x8402 +#define MT6332_BUCK_ALL_CON2 0x8404 +#define MT6332_BUCK_ALL_CON3 0x8406 +#define MT6332_BUCK_ALL_CON4 0x8408 +#define MT6332_BUCK_ALL_CON5 0x840A +#define MT6332_BUCK_ALL_CON6 0x840C +#define MT6332_BUCK_ALL_CON7 0x840E +#define MT6332_BUCK_ALL_CON8 0x8410 +#define MT6332_BUCK_ALL_CON9 0x8412 +#define MT6332_BUCK_ALL_CON10 0x8414 +#define MT6332_BUCK_ALL_CON11 0x8416 +#define MT6332_BUCK_ALL_CON12 0x8418 +#define MT6332_BUCK_ALL_CON13 0x841A +#define MT6332_BUCK_ALL_CON14 0x841C +#define MT6332_BUCK_ALL_CON15 0x841E +#define MT6332_BUCK_ALL_CON16 0x8420 +#define MT6332_BUCK_ALL_CON17 0x8422 +#define MT6332_BUCK_ALL_CON18 0x8424 +#define MT6332_BUCK_ALL_CON19 0x8426 +#define MT6332_BUCK_ALL_CON20 0x8428 +#define MT6332_BUCK_ALL_CON21 0x842A +#define MT6332_BUCK_ALL_CON22 0x842C +#define MT6332_BUCK_ALL_CON23 0x842E +#define MT6332_BUCK_ALL_CON24 0x8430 +#define MT6332_BUCK_ALL_CON25 0x8432 +#define MT6332_BUCK_ALL_CON26 0x8434 +#define MT6332_BUCK_ALL_CON27 0x8436 +#define MT6332_VDRAM_CON0 0x8438 +#define MT6332_VDRAM_CON1 0x843A +#define MT6332_VDRAM_CON2 0x843C +#define MT6332_VDRAM_CON3 0x843E +#define MT6332_VDRAM_CON4 0x8440 +#define MT6332_VDRAM_CON5 0x8442 +#define MT6332_VDRAM_CON6 0x8444 +#define MT6332_VDRAM_CON7 0x8446 +#define MT6332_VDRAM_CON8 0x8448 +#define MT6332_VDRAM_CON9 0x844A +#define MT6332_VDRAM_CON10 0x844C +#define MT6332_VDRAM_CON11 0x844E +#define MT6332_VDRAM_CON12 0x8450 +#define MT6332_VDRAM_CON13 0x8452 +#define MT6332_VDRAM_CON14 0x8454 +#define MT6332_VDRAM_CON15 0x8456 +#define MT6332_VDRAM_CON16 0x8458 +#define MT6332_VDRAM_CON17 0x845A +#define MT6332_VDRAM_CON18 0x845C +#define MT6332_VDRAM_CON19 0x845E +#define MT6332_VDRAM_CON20 0x8460 +#define MT6332_VDRAM_CON21 0x8462 +#define MT6332_VDVFS2_CON0 0x8464 +#define MT6332_VDVFS2_CON1 0x8466 +#define MT6332_VDVFS2_CON2 0x8468 +#define MT6332_VDVFS2_CON3 0x846A +#define MT6332_VDVFS2_CON4 0x846C +#define MT6332_VDVFS2_CON5 0x846E +#define MT6332_VDVFS2_CON6 0x8470 +#define MT6332_VDVFS2_CON7 0x8472 +#define MT6332_VDVFS2_CON8 0x8474 +#define MT6332_VDVFS2_CON9 0x8476 +#define MT6332_VDVFS2_CON10 0x8478 +#define MT6332_VDVFS2_CON11 0x847A +#define MT6332_VDVFS2_CON12 0x847C +#define MT6332_VDVFS2_CON13 0x847E +#define MT6332_VDVFS2_CON14 0x8480 +#define MT6332_VDVFS2_CON15 0x8482 +#define MT6332_VDVFS2_CON16 0x8484 +#define MT6332_VDVFS2_CON17 0x8486 +#define MT6332_VDVFS2_CON18 0x8488 +#define MT6332_VDVFS2_CON19 0x848A +#define MT6332_VDVFS2_CON20 0x848C +#define MT6332_VDVFS2_CON21 0x848E +#define MT6332_VDVFS2_CON22 0x8490 +#define MT6332_VDVFS2_CON23 0x8492 +#define MT6332_VDVFS2_CON24 0x8494 +#define MT6332_VDVFS2_CON25 0x8496 +#define MT6332_VDVFS2_CON26 0x8498 +#define MT6332_VDVFS2_CON27 0x849A +#define MT6332_VRF1_CON0 0x849C +#define MT6332_VRF1_CON1 0x849E +#define MT6332_VRF1_CON2 0x84A0 +#define MT6332_VRF1_CON3 0x84A2 +#define MT6332_VRF1_CON4 0x84A4 +#define MT6332_VRF1_CON5 0x84A6 +#define MT6332_VRF1_CON6 0x84A8 +#define MT6332_VRF1_CON7 0x84AA +#define MT6332_VRF1_CON8 0x84AC +#define MT6332_VRF1_CON9 0x84AE +#define MT6332_VRF1_CON10 0x84B0 +#define MT6332_VRF1_CON11 0x84B2 +#define MT6332_VRF1_CON12 0x84B4 +#define MT6332_VRF1_CON13 0x84B6 +#define MT6332_VRF1_CON14 0x84B8 +#define MT6332_VRF1_CON15 0x84BA +#define MT6332_VRF1_CON16 0x84BC +#define MT6332_VRF1_CON17 0x84BE +#define MT6332_VRF1_CON18 0x84C0 +#define MT6332_VRF1_CON19 0x84C2 +#define MT6332_VRF1_CON20 0x84C4 +#define MT6332_VRF1_CON21 0x84C6 +#define MT6332_VRF2_CON0 0x84C8 +#define MT6332_VRF2_CON1 0x84CA +#define MT6332_VRF2_CON2 0x84CC +#define MT6332_VRF2_CON3 0x84CE +#define MT6332_VRF2_CON4 0x84D0 +#define MT6332_VRF2_CON5 0x84D2 +#define MT6332_VRF2_CON6 0x84D4 +#define MT6332_VRF2_CON7 0x84D6 +#define MT6332_VRF2_CON8 0x84D8 +#define MT6332_VRF2_CON9 0x84DA +#define MT6332_VRF2_CON10 0x84DC +#define MT6332_VRF2_CON11 0x84DE +#define MT6332_VRF2_CON12 0x84E0 +#define MT6332_VRF2_CON13 0x84E2 +#define MT6332_VRF2_CON14 0x84E4 +#define MT6332_VRF2_CON15 0x84E6 +#define MT6332_VRF2_CON16 0x84E8 +#define MT6332_VRF2_CON17 0x84EA +#define MT6332_VRF2_CON18 0x84EC +#define MT6332_VRF2_CON19 0x84EE +#define MT6332_VRF2_CON20 0x84F0 +#define MT6332_VRF2_CON21 0x84F2 +#define MT6332_VPA_CON0 0x84F4 +#define MT6332_VPA_CON1 0x84F6 +#define MT6332_VPA_CON2 0x84F8 +#define MT6332_VPA_CON3 0x84FC +#define MT6332_VPA_CON4 0x84FE +#define MT6332_VPA_CON5 0x8500 +#define MT6332_VPA_CON6 0x8502 +#define MT6332_VPA_CON7 0x8504 +#define MT6332_VPA_CON8 0x8506 +#define MT6332_VPA_CON9 0x8508 +#define MT6332_VPA_CON10 0x850A +#define MT6332_VPA_CON11 0x850C +#define MT6332_VPA_CON12 0x850E +#define MT6332_VPA_CON13 0x8510 +#define MT6332_VPA_CON14 0x8512 +#define MT6332_VPA_CON15 0x8514 +#define MT6332_VPA_CON16 0x8516 +#define MT6332_VPA_CON17 0x8518 +#define MT6332_VPA_CON18 0x851A +#define MT6332_VPA_CON19 0x851C +#define MT6332_VPA_CON20 0x851E +#define MT6332_VPA_CON21 0x8520 +#define MT6332_VPA_CON22 0x8522 +#define MT6332_VPA_CON23 0x8524 +#define MT6332_VPA_CON24 0x8526 +#define MT6332_VPA_CON25 0x8528 +#define MT6332_VSBST_CON0 0x852A +#define MT6332_VSBST_CON1 0x852C +#define MT6332_VSBST_CON2 0x852E +#define MT6332_VSBST_CON3 0x8530 +#define MT6332_VSBST_CON4 0x8532 +#define MT6332_VSBST_CON5 0x8534 +#define MT6332_VSBST_CON6 0x8536 +#define MT6332_VSBST_CON7 0x8538 +#define MT6332_VSBST_CON8 0x853A +#define MT6332_VSBST_CON9 0x853C +#define MT6332_VSBST_CON10 0x853E +#define MT6332_VSBST_CON11 0x8540 +#define MT6332_VSBST_CON12 0x8542 +#define MT6332_VSBST_CON13 0x8544 +#define MT6332_VSBST_CON14 0x8546 +#define MT6332_VSBST_CON15 0x8548 +#define MT6332_VSBST_CON16 0x854A +#define MT6332_VSBST_CON17 0x854C +#define MT6332_VSBST_CON18 0x854E +#define MT6332_VSBST_CON19 0x8550 +#define MT6332_VSBST_CON20 0x8552 +#define MT6332_VSBST_CON21 0x8554 +#define MT6332_BUCK_K_CON0 0x8556 +#define MT6332_BUCK_K_CON1 0x8558 +#define MT6332_BUCK_K_CON2 0x855A +#define MT6332_BUCK_K_CON3 0x855C +#define MT6332_BUCK_K_CON4 0x855E +#define MT6332_BUCK_K_CON5 0x8560 +#define MT6332_AUXADC_ADC0 0x8800 +#define MT6332_AUXADC_ADC1 0x8802 +#define MT6332_AUXADC_ADC2 0x8804 +#define MT6332_AUXADC_ADC3 0x8806 +#define MT6332_AUXADC_ADC4 0x8808 +#define MT6332_AUXADC_ADC5 0x880A +#define MT6332_AUXADC_ADC6 0x880C +#define MT6332_AUXADC_ADC7 0x880E +#define MT6332_AUXADC_ADC8 0x8810 +#define MT6332_AUXADC_ADC9 0x8812 +#define MT6332_AUXADC_ADC10 0x8814 +#define MT6332_AUXADC_ADC11 0x8816 +#define MT6332_AUXADC_ADC12 0x8818 +#define MT6332_AUXADC_ADC13 0x881A +#define MT6332_AUXADC_ADC14 0x881C +#define MT6332_AUXADC_ADC15 0x881E +#define MT6332_AUXADC_ADC16 0x8820 +#define MT6332_AUXADC_ADC17 0x8822 +#define MT6332_AUXADC_ADC18 0x8824 +#define MT6332_AUXADC_ADC19 0x8826 +#define MT6332_AUXADC_ADC20 0x8828 +#define MT6332_AUXADC_ADC21 0x882A +#define MT6332_AUXADC_ADC22 0x882C +#define MT6332_AUXADC_ADC23 0x882E +#define MT6332_AUXADC_ADC24 0x8830 +#define MT6332_AUXADC_ADC25 0x8832 +#define MT6332_AUXADC_ADC26 0x8834 +#define MT6332_AUXADC_ADC27 0x8836 +#define MT6332_AUXADC_ADC28 0x8838 +#define MT6332_AUXADC_ADC29 0x883A +#define MT6332_AUXADC_ADC30 0x883C +#define MT6332_AUXADC_ADC31 0x883E +#define MT6332_AUXADC_ADC32 0x8840 +#define MT6332_AUXADC_ADC33 0x8842 +#define MT6332_AUXADC_ADC34 0x8844 +#define MT6332_AUXADC_ADC35 0x8846 +#define MT6332_AUXADC_ADC36 0x8848 +#define MT6332_AUXADC_ADC37 0x884A +#define MT6332_AUXADC_ADC38 0x884C +#define MT6332_AUXADC_ADC39 0x884E +#define MT6332_AUXADC_ADC40 0x8850 +#define MT6332_AUXADC_ADC41 0x8852 +#define MT6332_AUXADC_ADC42 0x8854 +#define MT6332_AUXADC_ADC43 0x8856 +#define MT6332_AUXADC_STA0 0x8858 +#define MT6332_AUXADC_STA1 0x885A +#define MT6332_AUXADC_RQST0 0x885C +#define MT6332_AUXADC_RQST0_SET 0x885E +#define MT6332_AUXADC_RQST0_CLR 0x8860 +#define MT6332_AUXADC_RQST1 0x8862 +#define MT6332_AUXADC_RQST1_SET 0x8864 +#define MT6332_AUXADC_RQST1_CLR 0x8866 +#define MT6332_AUXADC_CON0 0x8868 +#define MT6332_AUXADC_CON1 0x886A +#define MT6332_AUXADC_CON2 0x886C +#define MT6332_AUXADC_CON3 0x886E +#define MT6332_AUXADC_CON4 0x8870 +#define MT6332_AUXADC_CON5 0x8872 +#define MT6332_AUXADC_CON6 0x8874 +#define MT6332_AUXADC_CON7 0x8876 +#define MT6332_AUXADC_CON8 0x8878 +#define MT6332_AUXADC_CON9 0x887A +#define MT6332_AUXADC_CON10 0x887C +#define MT6332_AUXADC_CON11 0x887E +#define MT6332_AUXADC_CON12 0x8880 +#define MT6332_AUXADC_CON13 0x8882 +#define MT6332_AUXADC_CON14 0x8884 +#define MT6332_AUXADC_CON15 0x8886 +#define MT6332_AUXADC_CON16 0x8888 +#define MT6332_AUXADC_CON17 0x888A +#define MT6332_AUXADC_CON18 0x888C +#define MT6332_AUXADC_CON19 0x888E +#define MT6332_AUXADC_CON20 0x8890 +#define MT6332_AUXADC_CON21 0x8892 +#define MT6332_AUXADC_CON22 0x8894 +#define MT6332_AUXADC_CON23 0x8896 +#define MT6332_AUXADC_CON24 0x8898 +#define MT6332_AUXADC_CON25 0x889A +#define MT6332_AUXADC_CON26 0x889C +#define MT6332_AUXADC_CON27 0x889E +#define MT6332_AUXADC_CON28 0x88A0 +#define MT6332_AUXADC_CON29 0x88A2 +#define MT6332_AUXADC_CON30 0x88A4 +#define MT6332_AUXADC_CON31 0x88A6 +#define MT6332_AUXADC_CON32 0x88A8 +#define MT6332_AUXADC_CON33 0x88AA +#define MT6332_AUXADC_CON34 0x88AC +#define MT6332_AUXADC_CON35 0x88AE +#define MT6332_AUXADC_CON36 0x88B0 +#define MT6332_AUXADC_CON37 0x88B2 +#define MT6332_AUXADC_CON38 0x88B4 +#define MT6332_AUXADC_CON39 0x88B6 +#define MT6332_AUXADC_CON40 0x88B8 +#define MT6332_AUXADC_CON41 0x88BA +#define MT6332_AUXADC_CON42 0x88BC +#define MT6332_AUXADC_CON43 0x88BE +#define MT6332_AUXADC_CON44 0x88C0 +#define MT6332_AUXADC_CON45 0x88C2 +#define MT6332_AUXADC_CON46 0x88C4 +#define MT6332_AUXADC_CON47 0x88C6 +#define MT6332_STRUP_CONA0 0x8C00 +#define MT6332_STRUP_CONA1 0x8C02 +#define MT6332_STRUP_CONA2 0x8C04 +#define MT6332_STRUP_CON0 0x8C06 +#define MT6332_STRUP_CON2 0x8C08 +#define MT6332_STRUP_CON3 0x8C0A +#define MT6332_STRUP_CON4 0x8C0C +#define MT6332_STRUP_CON5 0x8C0E +#define MT6332_STRUP_CON6 0x8C10 +#define MT6332_STRUP_CON7 0x8C12 +#define MT6332_STRUP_CON8 0x8C14 +#define MT6332_STRUP_CON9 0x8C16 +#define MT6332_STRUP_CON10 0x8C18 +#define MT6332_STRUP_CON11 0x8C1A +#define MT6332_STRUP_CON12 0x8C1C +#define MT6332_STRUP_CON13 0x8C1E +#define MT6332_STRUP_CON14 0x8C20 +#define MT6332_STRUP_CON15 0x8C22 +#define MT6332_STRUP_CON16 0x8C24 +#define MT6332_STRUP_CON17 0x8C26 +#define MT6332_FGADC_CON0 0x8C28 +#define MT6332_FGADC_CON1 0x8C2A +#define MT6332_FGADC_CON2 0x8C2C +#define MT6332_FGADC_CON3 0x8C2E +#define MT6332_FGADC_CON4 0x8C30 +#define MT6332_FGADC_CON5 0x8C32 +#define MT6332_FGADC_CON6 0x8C34 +#define MT6332_FGADC_CON7 0x8C36 +#define MT6332_FGADC_CON8 0x8C38 +#define MT6332_FGADC_CON9 0x8C3A +#define MT6332_FGADC_CON10 0x8C3C +#define MT6332_FGADC_CON11 0x8C3E +#define MT6332_FGADC_CON12 0x8C40 +#define MT6332_FGADC_CON13 0x8C42 +#define MT6332_FGADC_CON14 0x8C44 +#define MT6332_FGADC_CON15 0x8C46 +#define MT6332_FGADC_CON16 0x8C48 +#define MT6332_FGADC_CON17 0x8C4A +#define MT6332_FGADC_CON18 0x8C4C +#define MT6332_FGADC_CON19 0x8C4E +#define MT6332_FGADC_CON20 0x8C50 +#define MT6332_FGADC_CON21 0x8C52 +#define MT6332_FGADC_CON22 0x8C54 +#define MT6332_OTP_CON0 0x8C56 +#define MT6332_OTP_CON1 0x8C58 +#define MT6332_OTP_CON2 0x8C5A +#define MT6332_OTP_CON3 0x8C5C +#define MT6332_OTP_CON4 0x8C5E +#define MT6332_OTP_CON5 0x8C60 +#define MT6332_OTP_CON6 0x8C62 +#define MT6332_OTP_CON7 0x8C64 +#define MT6332_OTP_CON8 0x8C66 +#define MT6332_OTP_CON9 0x8C68 +#define MT6332_OTP_CON10 0x8C6A +#define MT6332_OTP_CON11 0x8C6C +#define MT6332_OTP_CON12 0x8C6E +#define MT6332_OTP_CON13 0x8C70 +#define MT6332_OTP_CON14 0x8C72 +#define MT6332_OTP_DOUT_0_15 0x8C74 +#define MT6332_OTP_DOUT_16_31 0x8C76 +#define MT6332_OTP_DOUT_32_47 0x8C78 +#define MT6332_OTP_DOUT_48_63 0x8C7A +#define MT6332_OTP_DOUT_64_79 0x8C7C +#define MT6332_OTP_DOUT_80_95 0x8C7E +#define MT6332_OTP_DOUT_96_111 0x8C80 +#define MT6332_OTP_DOUT_112_127 0x8C82 +#define MT6332_OTP_DOUT_128_143 0x8C84 +#define MT6332_OTP_DOUT_144_159 0x8C86 +#define MT6332_OTP_DOUT_160_175 0x8C88 +#define MT6332_OTP_DOUT_176_191 0x8C8A +#define MT6332_OTP_DOUT_192_207 0x8C8C +#define MT6332_OTP_DOUT_208_223 0x8C8E +#define MT6332_OTP_DOUT_224_239 0x8C90 +#define MT6332_OTP_DOUT_240_255 0x8C92 +#define MT6332_OTP_VAL_0_15 0x8C94 +#define MT6332_OTP_VAL_16_31 0x8C96 +#define MT6332_OTP_VAL_32_47 0x8C98 +#define MT6332_OTP_VAL_48_63 0x8C9A +#define MT6332_OTP_VAL_64_79 0x8C9C +#define MT6332_OTP_VAL_80_95 0x8C9E +#define MT6332_OTP_VAL_96_111 0x8CA0 +#define MT6332_OTP_VAL_112_127 0x8CA2 +#define MT6332_OTP_VAL_128_143 0x8CA4 +#define MT6332_OTP_VAL_144_159 0x8CA6 +#define MT6332_OTP_VAL_160_175 0x8CA8 +#define MT6332_OTP_VAL_176_191 0x8CAA +#define MT6332_OTP_VAL_192_207 0x8CAC +#define MT6332_OTP_VAL_208_223 0x8CAE +#define MT6332_OTP_VAL_224_239 0x8CB0 +#define MT6332_OTP_VAL_240_255 0x8CB2 +#define MT6332_LDO_CON0 0x8CB4 +#define MT6332_LDO_CON1 0x8CB6 +#define MT6332_LDO_CON2 0x8CB8 +#define MT6332_LDO_CON3 0x8CBA +#define MT6332_LDO_CON5 0x8CBC +#define MT6332_LDO_CON6 0x8CBE +#define MT6332_LDO_CON7 0x8CC0 +#define MT6332_LDO_CON8 0x8CC2 +#define MT6332_LDO_CON9 0x8CC4 +#define MT6332_LDO_CON10 0x8CC6 +#define MT6332_LDO_CON11 0x8CC8 +#define MT6332_LDO_CON12 0x8CCA +#define MT6332_LDO_CON13 0x8CCC +#define MT6332_FQMTR_CON0 0x8CCE +#define MT6332_FQMTR_CON1 0x8CD0 +#define MT6332_FQMTR_CON2 0x8CD2 +#define MT6332_IWLED_CON0 0x8CD4 +#define MT6332_IWLED_DEG 0x8CD6 +#define MT6332_IWLED_STATUS 0x8CD8 +#define MT6332_IWLED_EN_CTRL 0x8CDA +#define MT6332_IWLED_CON1 0x8CDC +#define MT6332_IWLED_CON2 0x8CDE +#define MT6332_IWLED_TRIM0 0x8CE0 +#define MT6332_IWLED_TRIM1 0x8CE2 +#define MT6332_IWLED_CON3 0x8CE4 +#define MT6332_IWLED_CON4 0x8CE6 +#define MT6332_IWLED_CON5 0x8CE8 +#define MT6332_IWLED_CON6 0x8CEA +#define MT6332_IWLED_CON7 0x8CEC +#define MT6332_IWLED_CON8 0x8CEE +#define MT6332_IWLED_CON9 0x8CF0 +#define MT6332_SPK_CON0 0x8CF2 +#define MT6332_SPK_CON1 0x8CF4 +#define MT6332_SPK_CON2 0x8CF6 +#define MT6332_SPK_CON3 0x8CF8 +#define MT6332_SPK_CON4 0x8CFA +#define MT6332_SPK_CON5 0x8CFC +#define MT6332_SPK_CON6 0x8CFE +#define MT6332_SPK_CON7 0x8D00 +#define MT6332_SPK_CON8 0x8D02 +#define MT6332_SPK_CON9 0x8D04 +#define MT6332_SPK_CON10 0x8D06 +#define MT6332_SPK_CON11 0x8D08 +#define MT6332_SPK_CON12 0x8D0A +#define MT6332_SPK_CON13 0x8D0C +#define MT6332_SPK_CON14 0x8D0E +#define MT6332_SPK_CON15 0x8D10 +#define MT6332_SPK_CON16 0x8D12 +#define MT6332_TESTI_CON0 0x8D14 +#define MT6332_TESTI_CON1 0x8D16 +#define MT6332_TESTI_CON2 0x8D18 +#define MT6332_TESTI_CON3 0x8D1A +#define MT6332_TESTI_CON4 0x8D1C +#define MT6332_TESTI_CON5 0x8D1E +#define MT6332_TESTI_CON6 0x8D20 +#define MT6332_TESTI_MUX_CON0 0x8D22 +#define MT6332_TESTI_MUX_CON1 0x8D24 +#define MT6332_TESTI_MUX_CON2 0x8D26 +#define MT6332_TESTI_MUX_CON3 0x8D28 +#define MT6332_TESTI_MUX_CON4 0x8D2A +#define MT6332_TESTI_MUX_CON5 0x8D2C +#define MT6332_TESTI_MUX_CON6 0x8D2E +#define MT6332_TESTO_CON0 0x8D30 +#define MT6332_TESTO_CON1 0x8D32 +#define MT6332_TEST_OMUX_CON0 0x8D34 +#define MT6332_TEST_OMUX_CON1 0x8D36 +#define MT6332_DEBUG_CON0 0x8D38 +#define MT6332_DEBUG_CON1 0x8D3A +#define MT6332_DEBUG_CON2 0x8D3C +#define MT6332_FGADC_CON23 0x8D3E +#define MT6332_FGADC_CON24 0x8D40 +#define MT6332_FGADC_CON25 0x8D42 +#define MT6332_TOP_RST_STATUS 0x8D44 +#define MT6332_TOP_RST_STATUS_SET 0x8D46 +#define MT6332_TOP_RST_STATUS_CLR 0x8D48 +#define MT6332_VDVFS2_CON28 0x8D4A + +#endif /* __MFD_MT6332_REGISTERS_H__ */ diff --git a/include/linux/mfd/mt6357/core.h b/include/linux/mfd/mt6357/core.h new file mode 100644 index 000000000000..2441611264fd --- /dev/null +++ b/include/linux/mfd/mt6357/core.h @@ -0,0 +1,119 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2022 BayLibre, SAS + * Author: Fabien Parent <fparent@baylibre.com> + */ + +#ifndef __MFD_MT6357_CORE_H__ +#define __MFD_MT6357_CORE_H__ + +enum mt6357_irq_top_status_shift { + MT6357_BUCK_TOP = 0, + MT6357_LDO_TOP, + MT6357_PSC_TOP, + MT6357_SCK_TOP, + MT6357_BM_TOP, + MT6357_HK_TOP, + MT6357_XPP_TOP, + MT6357_AUD_TOP, + MT6357_MISC_TOP, +}; + +enum mt6357_irq_numbers { + MT6357_IRQ_VPROC_OC = 0, + MT6357_IRQ_VCORE_OC, + MT6357_IRQ_VMODEM_OC, + MT6357_IRQ_VS1_OC, + MT6357_IRQ_VPA_OC, + MT6357_IRQ_VCORE_PREOC, + MT6357_IRQ_VFE28_OC = 16, + MT6357_IRQ_VXO22_OC, + MT6357_IRQ_VRF18_OC, + MT6357_IRQ_VRF12_OC, + MT6357_IRQ_VEFUSE_OC, + MT6357_IRQ_VCN33_OC, + MT6357_IRQ_VCN28_OC, + MT6357_IRQ_VCN18_OC, + MT6357_IRQ_VCAMA_OC, + MT6357_IRQ_VCAMD_OC, + MT6357_IRQ_VCAMIO_OC, + MT6357_IRQ_VLDO28_OC, + MT6357_IRQ_VUSB33_OC, + MT6357_IRQ_VAUX18_OC, + MT6357_IRQ_VAUD28_OC, + MT6357_IRQ_VIO28_OC, + MT6357_IRQ_VIO18_OC, + MT6357_IRQ_VSRAM_PROC_OC, + MT6357_IRQ_VSRAM_OTHERS_OC, + MT6357_IRQ_VIBR_OC, + MT6357_IRQ_VDRAM_OC, + MT6357_IRQ_VMC_OC, + MT6357_IRQ_VMCH_OC, + MT6357_IRQ_VEMC_OC, + MT6357_IRQ_VSIM1_OC, + MT6357_IRQ_VSIM2_OC, + MT6357_IRQ_PWRKEY = 48, + MT6357_IRQ_HOMEKEY, + MT6357_IRQ_PWRKEY_R, + MT6357_IRQ_HOMEKEY_R, + MT6357_IRQ_NI_LBAT_INT, + MT6357_IRQ_CHRDET, + MT6357_IRQ_CHRDET_EDGE, + MT6357_IRQ_VCDT_HV_DET, + MT6357_IRQ_WATCHDOG, + MT6357_IRQ_VBATON_UNDET, + MT6357_IRQ_BVALID_DET, + MT6357_IRQ_OV, + MT6357_IRQ_RTC = 64, + MT6357_IRQ_FG_BAT0_H = 80, + MT6357_IRQ_FG_BAT0_L, + MT6357_IRQ_FG_CUR_H, + MT6357_IRQ_FG_CUR_L, + MT6357_IRQ_FG_ZCV, + MT6357_IRQ_BATON_LV = 96, + MT6357_IRQ_BATON_HT, + MT6357_IRQ_BAT_H = 112, + MT6357_IRQ_BAT_L, + MT6357_IRQ_AUXADC_IMP, + MT6357_IRQ_NAG_C_DLTV, + MT6357_IRQ_AUDIO = 128, + MT6357_IRQ_ACCDET = 133, + MT6357_IRQ_ACCDET_EINT0, + MT6357_IRQ_ACCDET_EINT1, + MT6357_IRQ_SPI_CMD_ALERT = 144, + MT6357_IRQ_NR, +}; + +#define MT6357_IRQ_BUCK_BASE MT6357_IRQ_VPROC_OC +#define MT6357_IRQ_LDO_BASE MT6357_IRQ_VFE28_OC +#define MT6357_IRQ_PSC_BASE MT6357_IRQ_PWRKEY +#define MT6357_IRQ_SCK_BASE MT6357_IRQ_RTC +#define MT6357_IRQ_BM_BASE MT6357_IRQ_FG_BAT0_H +#define MT6357_IRQ_HK_BASE MT6357_IRQ_BAT_H +#define MT6357_IRQ_AUD_BASE MT6357_IRQ_AUDIO +#define MT6357_IRQ_MISC_BASE MT6357_IRQ_SPI_CMD_ALERT + +#define MT6357_IRQ_BUCK_BITS (MT6357_IRQ_VCORE_PREOC - MT6357_IRQ_BUCK_BASE + 1) +#define MT6357_IRQ_LDO_BITS (MT6357_IRQ_VSIM2_OC - MT6357_IRQ_LDO_BASE + 1) +#define MT6357_IRQ_PSC_BITS (MT6357_IRQ_VCDT_HV_DET - MT6357_IRQ_PSC_BASE + 1) +#define MT6357_IRQ_SCK_BITS (MT6357_IRQ_RTC - MT6357_IRQ_SCK_BASE + 1) +#define MT6357_IRQ_BM_BITS (MT6357_IRQ_BATON_HT - MT6357_IRQ_BM_BASE + 1) +#define MT6357_IRQ_HK_BITS (MT6357_IRQ_NAG_C_DLTV - MT6357_IRQ_HK_BASE + 1) +#define MT6357_IRQ_AUD_BITS (MT6357_IRQ_ACCDET_EINT1 - MT6357_IRQ_AUD_BASE + 1) +#define MT6357_IRQ_MISC_BITS \ + (MT6357_IRQ_SPI_CMD_ALERT - MT6357_IRQ_MISC_BASE + 1) + +#define MT6357_TOP_GEN(sp) \ +{ \ + .hwirq_base = MT6357_IRQ_##sp##_BASE, \ + .num_int_regs = \ + ((MT6357_IRQ_##sp##_BITS - 1) / \ + MTK_PMIC_REG_WIDTH) + 1, \ + .en_reg = MT6357_##sp##_TOP_INT_CON0, \ + .en_reg_shift = 0x6, \ + .sta_reg = MT6357_##sp##_TOP_INT_STATUS0, \ + .sta_reg_shift = 0x2, \ + .top_offset = MT6357_##sp##_TOP, \ +} + +#endif /* __MFD_MT6357_CORE_H__ */ diff --git a/include/linux/mfd/mt6357/registers.h b/include/linux/mfd/mt6357/registers.h new file mode 100644 index 000000000000..e24af83b618d --- /dev/null +++ b/include/linux/mfd/mt6357/registers.h @@ -0,0 +1,1574 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2022 MediaTek Inc. + */ + +#ifndef __MFD_MT6357_REGISTERS_H__ +#define __MFD_MT6357_REGISTERS_H__ + +/* PMIC Registers */ +#define MT6357_TOP0_ID 0x0 +#define MT6357_TOP0_REV0 0x2 +#define MT6357_TOP0_DSN_DBI 0x4 +#define MT6357_TOP0_DSN_DXI 0x6 +#define MT6357_HWCID 0x8 +#define MT6357_SWCID 0xa +#define MT6357_PONSTS 0xc +#define MT6357_POFFSTS 0xe +#define MT6357_PSTSCTL 0x10 +#define MT6357_PG_DEB_STS0 0x12 +#define MT6357_PG_SDN_STS0 0x14 +#define MT6357_OC_SDN_STS0 0x16 +#define MT6357_THERMALSTATUS 0x18 +#define MT6357_TOP_CON 0x1a +#define MT6357_TEST_OUT 0x1c +#define MT6357_TEST_CON0 0x1e +#define MT6357_TEST_CON1 0x20 +#define MT6357_TESTMODE_SW 0x22 +#define MT6357_TOPSTATUS 0x24 +#define MT6357_TDSEL_CON 0x26 +#define MT6357_RDSEL_CON 0x28 +#define MT6357_SMT_CON0 0x2a +#define MT6357_SMT_CON1 0x2c +#define MT6357_TOP_RSV0 0x2e +#define MT6357_TOP_RSV1 0x30 +#define MT6357_DRV_CON0 0x32 +#define MT6357_DRV_CON1 0x34 +#define MT6357_DRV_CON2 0x36 +#define MT6357_DRV_CON3 0x38 +#define MT6357_FILTER_CON0 0x3a +#define MT6357_FILTER_CON1 0x3c +#define MT6357_FILTER_CON2 0x3e +#define MT6357_FILTER_CON3 0x40 +#define MT6357_TOP_STATUS 0x42 +#define MT6357_TOP_STATUS_SET 0x44 +#define MT6357_TOP_STATUS_CLR 0x46 +#define MT6357_TOP_TRAP 0x48 +#define MT6357_TOP1_ID 0x80 +#define MT6357_TOP1_REV0 0x82 +#define MT6357_TOP1_DSN_DBI 0x84 +#define MT6357_TOP1_DSN_DXI 0x86 +#define MT6357_GPIO_DIR0 0x88 +#define MT6357_GPIO_DIR0_SET 0x8a +#define MT6357_GPIO_DIR0_CLR 0x8c +#define MT6357_GPIO_PULLEN0 0x8e +#define MT6357_GPIO_PULLEN0_SET 0x90 +#define MT6357_GPIO_PULLEN0_CLR 0x92 +#define MT6357_GPIO_PULLSEL0 0x94 +#define MT6357_GPIO_PULLSEL0_SET 0x96 +#define MT6357_GPIO_PULLSEL0_CLR 0x98 +#define MT6357_GPIO_DINV0 0x9a +#define MT6357_GPIO_DINV0_SET 0x9c +#define MT6357_GPIO_DINV0_CLR 0x9e +#define MT6357_GPIO_DOUT0 0xa0 +#define MT6357_GPIO_DOUT0_SET 0xa2 +#define MT6357_GPIO_DOUT0_CLR 0xa4 +#define MT6357_GPIO_PI0 0xa6 +#define MT6357_GPIO_POE0 0xa8 +#define MT6357_GPIO_MODE0 0xaa +#define MT6357_GPIO_MODE0_SET 0xac +#define MT6357_GPIO_MODE0_CLR 0xae +#define MT6357_GPIO_MODE1 0xb0 +#define MT6357_GPIO_MODE1_SET 0xb2 +#define MT6357_GPIO_MODE1_CLR 0xb4 +#define MT6357_GPIO_MODE2 0xb6 +#define MT6357_GPIO_MODE2_SET 0xb8 +#define MT6357_GPIO_MODE2_CLR 0xba +#define MT6357_GPIO_MODE3 0xbc +#define MT6357_GPIO_MODE3_SET 0xbe +#define MT6357_GPIO_MODE3_CLR 0xc0 +#define MT6357_GPIO_RSV 0xc2 +#define MT6357_TOP2_ID 0x100 +#define MT6357_TOP2_REV0 0x102 +#define MT6357_TOP2_DSN_DBI 0x104 +#define MT6357_TOP2_DSN_DXI 0x106 +#define MT6357_TOP_PAM0 0x108 +#define MT6357_TOP_PAM1 0x10a +#define MT6357_TOP_CKPDN_CON0 0x10c +#define MT6357_TOP_CKPDN_CON0_SET 0x10e +#define MT6357_TOP_CKPDN_CON0_CLR 0x110 +#define MT6357_TOP_CKPDN_CON1 0x112 +#define MT6357_TOP_CKPDN_CON1_SET 0x114 +#define MT6357_TOP_CKPDN_CON1_CLR 0x116 +#define MT6357_TOP_CKSEL_CON0 0x118 +#define MT6357_TOP_CKSEL_CON0_SET 0x11a +#define MT6357_TOP_CKSEL_CON0_CLR 0x11c +#define MT6357_TOP_CKSEL_CON1 0x11e +#define MT6357_TOP_CKSEL_CON1_SET 0x120 +#define MT6357_TOP_CKSEL_CON1_CLR 0x122 +#define MT6357_TOP_CKDIVSEL_CON0 0x124 +#define MT6357_TOP_CKDIVSEL_CON0_SET 0x126 +#define MT6357_TOP_CKDIVSEL_CON0_CLR 0x128 +#define MT6357_TOP_CKHWEN_CON0 0x12a +#define MT6357_TOP_CKHWEN_CON0_SET 0x12c +#define MT6357_TOP_CKHWEN_CON0_CLR 0x12e +#define MT6357_TOP_CKTST_CON0 0x130 +#define MT6357_TOP_CKTST_CON1 0x132 +#define MT6357_TOP_CLK_CON0 0x134 +#define MT6357_TOP_CLK_CON0_SET 0x136 +#define MT6357_TOP_CLK_CON0_CLR 0x138 +#define MT6357_TOP_DCM_CON0 0x13a +#define MT6357_TOP_HANDOVER_DEBUG0 0x13c +#define MT6357_TOP_RST_CON0 0x13e +#define MT6357_TOP_RST_CON0_SET 0x140 +#define MT6357_TOP_RST_CON0_CLR 0x142 +#define MT6357_TOP_RST_CON1 0x144 +#define MT6357_TOP_RST_CON1_SET 0x146 +#define MT6357_TOP_RST_CON1_CLR 0x148 +#define MT6357_TOP_RST_CON2 0x14a +#define MT6357_TOP_RST_MISC 0x14c +#define MT6357_TOP_RST_MISC_SET 0x14e +#define MT6357_TOP_RST_MISC_CLR 0x150 +#define MT6357_TOP_RST_STATUS 0x152 +#define MT6357_TOP_RST_STATUS_SET 0x154 +#define MT6357_TOP_RST_STATUS_CLR 0x156 +#define MT6357_TOP2_ELR_NUM 0x158 +#define MT6357_TOP2_ELR0 0x15a +#define MT6357_TOP2_ELR1 0x15c +#define MT6357_TOP3_ID 0x180 +#define MT6357_TOP3_REV0 0x182 +#define MT6357_TOP3_DSN_DBI 0x184 +#define MT6357_TOP3_DSN_DXI 0x186 +#define MT6357_MISC_TOP_INT_CON0 0x188 +#define MT6357_MISC_TOP_INT_CON0_SET 0x18a +#define MT6357_MISC_TOP_INT_CON0_CLR 0x18c +#define MT6357_MISC_TOP_INT_MASK_CON0 0x18e +#define MT6357_MISC_TOP_INT_MASK_CON0_SET 0x190 +#define MT6357_MISC_TOP_INT_MASK_CON0_CLR 0x192 +#define MT6357_MISC_TOP_INT_STATUS0 0x194 +#define MT6357_MISC_TOP_INT_RAW_STATUS0 0x196 +#define MT6357_TOP_INT_MASK_CON0 0x198 +#define MT6357_TOP_INT_MASK_CON0_SET 0x19a +#define MT6357_TOP_INT_MASK_CON0_CLR 0x19c +#define MT6357_TOP_INT_STATUS0 0x19e +#define MT6357_TOP_INT_RAW_STATUS0 0x1a0 +#define MT6357_TOP_INT_CON0 0x1a2 +#define MT6357_PLT0_ID 0x380 +#define MT6357_PLT0_REV0 0x382 +#define MT6357_PLT0_REV1 0x384 +#define MT6357_PLT0_DSN_DXI 0x386 +#define MT6357_FQMTR_CON0 0x388 +#define MT6357_FQMTR_CON1 0x38a +#define MT6357_FQMTR_CON2 0x38c +#define MT6357_TOP_CLK_TRIM 0x38e +#define MT6357_OTP_CON0 0x390 +#define MT6357_OTP_CON1 0x392 +#define MT6357_OTP_CON2 0x394 +#define MT6357_OTP_CON3 0x396 +#define MT6357_OTP_CON4 0x398 +#define MT6357_OTP_CON5 0x39a +#define MT6357_OTP_CON6 0x39c +#define MT6357_OTP_CON7 0x39e +#define MT6357_OTP_CON8 0x3a0 +#define MT6357_OTP_CON9 0x3a2 +#define MT6357_OTP_CON10 0x3a4 +#define MT6357_OTP_CON11 0x3a6 +#define MT6357_OTP_CON12 0x3a8 +#define MT6357_OTP_CON13 0x3aa +#define MT6357_OTP_CON14 0x3ac +#define MT6357_TOP_TMA_KEY 0x3ae +#define MT6357_TOP_MDB_CONF0 0x3b0 +#define MT6357_TOP_MDB_CONF1 0x3b2 +#define MT6357_TOP_MDB_CONF2 0x3b4 +#define MT6357_PLT0_ELR_NUM 0x3b6 +#define MT6357_PLT0_ELR0 0x3b8 +#define MT6357_PLT0_ELR1 0x3ba +#define MT6357_SPISLV_ID 0x400 +#define MT6357_SPISLV_REV0 0x402 +#define MT6357_SPISLV_REV1 0x404 +#define MT6357_SPISLV_DSN_DXI 0x406 +#define MT6357_RG_SPI_CON0 0x408 +#define MT6357_DEW_DIO_EN 0x40a +#define MT6357_DEW_READ_TEST 0x40c +#define MT6357_DEW_WRITE_TEST 0x40e +#define MT6357_DEW_CRC_SWRST 0x410 +#define MT6357_DEW_CRC_EN 0x412 +#define MT6357_DEW_CRC_VAL 0x414 +#define MT6357_DEW_DBG_MON_SEL 0x416 +#define MT6357_DEW_CIPHER_KEY_SEL 0x418 +#define MT6357_DEW_CIPHER_IV_SEL 0x41a +#define MT6357_DEW_CIPHER_EN 0x41c +#define MT6357_DEW_CIPHER_RDY 0x41e +#define MT6357_DEW_CIPHER_MODE 0x420 +#define MT6357_DEW_CIPHER_SWRST 0x422 +#define MT6357_DEW_RDDMY_NO 0x424 +#define MT6357_INT_TYPE_CON0 0x426 +#define MT6357_INT_TYPE_CON0_SET 0x428 +#define MT6357_INT_TYPE_CON0_CLR 0x42a +#define MT6357_INT_STA 0x42c +#define MT6357_RG_SPI_CON1 0x42e +#define MT6357_RG_SPI_CON2 0x430 +#define MT6357_RG_SPI_CON3 0x432 +#define MT6357_RG_SPI_CON4 0x434 +#define MT6357_RG_SPI_CON5 0x436 +#define MT6357_RG_SPI_CON6 0x438 +#define MT6357_RG_SPI_CON7 0x43a +#define MT6357_RG_SPI_CON8 0x43c +#define MT6357_RG_SPI_CON9 0x43e +#define MT6357_RG_SPI_CON10 0x440 +#define MT6357_RG_SPI_CON11 0x442 +#define MT6357_RG_SPI_CON12 0x444 +#define MT6357_RG_SPI_CON13 0x446 +#define MT6357_TOP_SPI_CON0 0x448 +#define MT6357_TOP_SPI_CON1 0x44a +#define MT6357_SCK_TOP_DSN_ID 0x500 +#define MT6357_SCK_TOP_DSN_REV0 0x502 +#define MT6357_SCK_TOP_DBI 0x504 +#define MT6357_SCK_TOP_DXI 0x506 +#define MT6357_SCK_TOP_TPM0 0x508 +#define MT6357_SCK_TOP_TPM1 0x50a +#define MT6357_SCK_TOP_CON0 0x50c +#define MT6357_SCK_TOP_CON1 0x50e +#define MT6357_SCK_TOP_TEST_OUT 0x510 +#define MT6357_SCK_TOP_TEST_CON0 0x512 +#define MT6357_SCK_TOP_CKPDN_CON0 0x514 +#define MT6357_SCK_TOP_CKPDN_CON0_SET 0x516 +#define MT6357_SCK_TOP_CKPDN_CON0_CLR 0x518 +#define MT6357_SCK_TOP_CKHWEN_CON0 0x51a +#define MT6357_SCK_TOP_CKHWEN_CON0_SET 0x51c +#define MT6357_SCK_TOP_CKHWEN_CON0_CLR 0x51e +#define MT6357_SCK_TOP_CKTST_CON 0x520 +#define MT6357_SCK_TOP_RST_CON0 0x522 +#define MT6357_SCK_TOP_RST_CON0_SET 0x524 +#define MT6357_SCK_TOP_RST_CON0_CLR 0x526 +#define MT6357_SCK_TOP_INT_CON0 0x528 +#define MT6357_SCK_TOP_INT_CON0_SET 0x52a +#define MT6357_SCK_TOP_INT_CON0_CLR 0x52c +#define MT6357_SCK_TOP_INT_MASK_CON0 0x52e +#define MT6357_SCK_TOP_INT_MASK_CON0_SET 0x530 +#define MT6357_SCK_TOP_INT_MASK_CON0_CLR 0x532 +#define MT6357_SCK_TOP_INT_STATUS0 0x534 +#define MT6357_SCK_TOP_INT_RAW_STATUS0 0x536 +#define MT6357_SCK_TOP_INT_MISC_CON 0x538 +#define MT6357_EOSC_CALI_CON0 0x53a +#define MT6357_EOSC_CALI_CON1 0x53c +#define MT6357_RTC_MIX_CON0 0x53e +#define MT6357_RTC_MIX_CON1 0x540 +#define MT6357_RTC_MIX_CON2 0x542 +#define MT6357_RTC_DSN_ID 0x580 +#define MT6357_RTC_DSN_REV0 0x582 +#define MT6357_RTC_DBI 0x584 +#define MT6357_RTC_DXI 0x586 +#define MT6357_RTC_BBPU 0x588 +#define MT6357_RTC_IRQ_STA 0x58a +#define MT6357_RTC_IRQ_EN 0x58c +#define MT6357_RTC_CII_EN 0x58e +#define MT6357_RTC_AL_MASK 0x590 +#define MT6357_RTC_TC_SEC 0x592 +#define MT6357_RTC_TC_MIN 0x594 +#define MT6357_RTC_TC_HOU 0x596 +#define MT6357_RTC_TC_DOM 0x598 +#define MT6357_RTC_TC_DOW 0x59a +#define MT6357_RTC_TC_MTH 0x59c +#define MT6357_RTC_TC_YEA 0x59e +#define MT6357_RTC_AL_SEC 0x5a0 +#define MT6357_RTC_AL_MIN 0x5a2 +#define MT6357_RTC_AL_HOU 0x5a4 +#define MT6357_RTC_AL_DOM 0x5a6 +#define MT6357_RTC_AL_DOW 0x5a8 +#define MT6357_RTC_AL_MTH 0x5aa +#define MT6357_RTC_AL_YEA 0x5ac +#define MT6357_RTC_OSC32CON 0x5ae +#define MT6357_RTC_POWERKEY1 0x5b0 +#define MT6357_RTC_POWERKEY2 0x5b2 +#define MT6357_RTC_PDN1 0x5b4 +#define MT6357_RTC_PDN2 0x5b6 +#define MT6357_RTC_SPAR0 0x5b8 +#define MT6357_RTC_SPAR1 0x5ba +#define MT6357_RTC_PROT 0x5bc +#define MT6357_RTC_DIFF 0x5be +#define MT6357_RTC_CALI 0x5c0 +#define MT6357_RTC_WRTGR 0x5c2 +#define MT6357_RTC_CON 0x5c4 +#define MT6357_RTC_SEC_CTRL 0x5c6 +#define MT6357_RTC_INT_CNT 0x5c8 +#define MT6357_RTC_SEC_DAT0 0x5ca +#define MT6357_RTC_SEC_DAT1 0x5cc +#define MT6357_RTC_SEC_DAT2 0x5ce +#define MT6357_RTC_SEC_DSN_ID 0x600 +#define MT6357_RTC_SEC_DSN_REV0 0x602 +#define MT6357_RTC_SEC_DBI 0x604 +#define MT6357_RTC_SEC_DXI 0x606 +#define MT6357_RTC_TC_SEC_SEC 0x608 +#define MT6357_RTC_TC_MIN_SEC 0x60a +#define MT6357_RTC_TC_HOU_SEC 0x60c +#define MT6357_RTC_TC_DOM_SEC 0x60e +#define MT6357_RTC_TC_DOW_SEC 0x610 +#define MT6357_RTC_TC_MTH_SEC 0x612 +#define MT6357_RTC_TC_YEA_SEC 0x614 +#define MT6357_RTC_SEC_CK_PDN 0x616 +#define MT6357_RTC_SEC_WRTGR 0x618 +#define MT6357_DCXO_DSN_ID 0x780 +#define MT6357_DCXO_DSN_REV0 0x782 +#define MT6357_DCXO_DSN_DBI 0x784 +#define MT6357_DCXO_DSN_DXI 0x786 +#define MT6357_DCXO_CW00 0x788 +#define MT6357_DCXO_CW00_SET 0x78a +#define MT6357_DCXO_CW00_CLR 0x78c +#define MT6357_DCXO_CW01 0x78e +#define MT6357_DCXO_CW02 0x790 +#define MT6357_DCXO_CW03 0x792 +#define MT6357_DCXO_CW04 0x794 +#define MT6357_DCXO_CW05 0x796 +#define MT6357_DCXO_CW06 0x798 +#define MT6357_DCXO_CW07 0x79a +#define MT6357_DCXO_CW08 0x79c +#define MT6357_DCXO_CW09 0x79e +#define MT6357_DCXO_CW10 0x7a0 +#define MT6357_DCXO_CW11 0x7a2 +#define MT6357_DCXO_CW11_SET 0x7a4 +#define MT6357_DCXO_CW11_CLR 0x7a6 +#define MT6357_DCXO_CW12 0x7a8 +#define MT6357_DCXO_CW13 0x7aa +#define MT6357_DCXO_CW14 0x7ac +#define MT6357_DCXO_CW15 0x7ae +#define MT6357_DCXO_CW16 0x7b0 +#define MT6357_DCXO_CW17 0x7b2 +#define MT6357_DCXO_CW18 0x7b4 +#define MT6357_DCXO_CW19 0x7b6 +#define MT6357_DCXO_CW20 0x7b8 +#define MT6357_DCXO_CW21 0x7ba +#define MT6357_DCXO_CW22 0x7bc +#define MT6357_DCXO_ELR_NUM 0x7be +#define MT6357_DCXO_ELR0 0x7c0 +#define MT6357_PSC_TOP_ID 0x900 +#define MT6357_PSC_TOP_REV0 0x902 +#define MT6357_PSC_TOP_DBI 0x904 +#define MT6357_PSC_TOP_DXI 0x906 +#define MT6357_PSC_TPM0 0x908 +#define MT6357_PSC_TPM1 0x90a +#define MT6357_PSC_TOP_RSTCTL_0 0x90c +#define MT6357_PSC_TOP_INT_CON0 0x90e +#define MT6357_PSC_TOP_INT_CON0_SET 0x910 +#define MT6357_PSC_TOP_INT_CON0_CLR 0x912 +#define MT6357_PSC_TOP_INT_MASK_CON0 0x914 +#define MT6357_PSC_TOP_INT_MASK_CON0_SET 0x916 +#define MT6357_PSC_TOP_INT_MASK_CON0_CLR 0x918 +#define MT6357_PSC_TOP_INT_STATUS0 0x91a +#define MT6357_PSC_TOP_INT_RAW_STATUS0 0x91c +#define MT6357_PSC_TOP_INT_MISC_CON 0x91e +#define MT6357_PSC_TOP_INT_MISC_CON_SET 0x920 +#define MT6357_PSC_TOP_INT_MISC_CON_CLR 0x922 +#define MT6357_PSC_TOP_MON_CTL 0x924 +#define MT6357_STRUP_ID 0x980 +#define MT6357_STRUP_REV0 0x982 +#define MT6357_STRUP_DBI 0x984 +#define MT6357_STRUP_DXI 0x986 +#define MT6357_STRUP_ANA_CON0 0x988 +#define MT6357_STRUP_ANA_CON1 0x98a +#define MT6357_STRUP_ANA_CON2 0x98c +#define MT6357_STRUP_ELR_NUM 0x98e +#define MT6357_STRUP_ELR_0 0x990 +#define MT6357_PSEQ_ID 0xa00 +#define MT6357_PSEQ_REV0 0xa02 +#define MT6357_PSEQ_DBI 0xa04 +#define MT6357_PSEQ_DXI 0xa06 +#define MT6357_PPCCTL0 0xa08 +#define MT6357_PPCCTL1 0xa0a +#define MT6357_PPCCTL2 0xa0c +#define MT6357_PPCCFG0 0xa0e +#define MT6357_PPCTST0 0xa10 +#define MT6357_PORFLAG 0xa12 +#define MT6357_STRUP_CON0 0xa14 +#define MT6357_STRUP_CON1 0xa16 +#define MT6357_STRUP_CON2 0xa18 +#define MT6357_STRUP_CON3 0xa1a +#define MT6357_STRUP_CON4 0xa1c +#define MT6357_STRUP_CON5 0xa1e +#define MT6357_STRUP_CON6 0xa20 +#define MT6357_STRUP_CON7 0xa22 +#define MT6357_CPSCFG0 0xa24 +#define MT6357_STRUP_CON9 0xa26 +#define MT6357_STRUP_CON10 0xa28 +#define MT6357_STRUP_CON11 0xa2a +#define MT6357_STRUP_CON12 0xa2c +#define MT6357_STRUP_CON13 0xa2e +#define MT6357_STRUP_CON14 0xa30 +#define MT6357_STRUP_CON15 0xa32 +#define MT6357_STRUP_CON16 0xa34 +#define MT6357_STRUP_CON19 0xa36 +#define MT6357_PSEQ_ELR_NUM 0xa38 +#define MT6357_PSEQ_ELR7 0xa3a +#define MT6357_PSEQ_ELR8 0xa3c +#define MT6357_PCHR_DIG_DSN_ID 0xa80 +#define MT6357_PCHR_DIG_DSN_REV0 0xa82 +#define MT6357_PCHR_DIG_DSN_DBI 0xa84 +#define MT6357_PCHR_DIG_DSN_DXI 0xa86 +#define MT6357_CHR_TOP_CON0 0xa88 +#define MT6357_CHR_TOP_CON1 0xa8a +#define MT6357_CHR_TOP_CON2 0xa8c +#define MT6357_CHR_TOP_CON3 0xa8e +#define MT6357_CHR_TOP_CON4 0xa90 +#define MT6357_CHR_TOP_CON5 0xa92 +#define MT6357_CHR_TOP_CON6 0xa94 +#define MT6357_PCHR_DIG_ELR_NUM 0xa96 +#define MT6357_PCHR_ELR0 0xa98 +#define MT6357_PCHR_ELR1 0xa9a +#define MT6357_PCHR_MACRO_DSN_ID 0xb80 +#define MT6357_PCHR_MACRO_DSN_REV0 0xb82 +#define MT6357_PCHR_MACRO_DSN_DBI 0xb84 +#define MT6357_PCHR_MACRO_DSN_DXI 0xb86 +#define MT6357_CHR_CON0 0xb88 +#define MT6357_CHR_CON1 0xb8a +#define MT6357_CHR_CON2 0xb8c +#define MT6357_CHR_CON3 0xb8e +#define MT6357_CHR_CON4 0xb90 +#define MT6357_CHR_CON5 0xb92 +#define MT6357_CHR_CON6 0xb94 +#define MT6357_CHR_CON7 0xb96 +#define MT6357_CHR_CON8 0xb98 +#define MT6357_CHR_CON9 0xb9a +#define MT6357_BM_TOP_DSN_ID 0xc00 +#define MT6357_BM_TOP_DSN_REV0 0xc02 +#define MT6357_BM_TOP_DBI 0xc04 +#define MT6357_BM_TOP_DXI 0xc06 +#define MT6357_BM_TPM0 0xc08 +#define MT6357_BM_TPM1 0xc0a +#define MT6357_BM_TOP_CKPDN_CON0 0xc0c +#define MT6357_BM_TOP_CKPDN_CON0_SET 0xc0e +#define MT6357_BM_TOP_CKPDN_CON0_CLR 0xc10 +#define MT6357_BM_TOP_CKSEL_CON0 0xc12 +#define MT6357_BM_TOP_CKSEL_CON0_SET 0xc14 +#define MT6357_BM_TOP_CKSEL_CON0_CLR 0xc16 +#define MT6357_BM_TOP_CKTST_CON0 0xc18 +#define MT6357_BM_TOP_RST_CON0 0xc1a +#define MT6357_BM_TOP_RST_CON0_SET 0xc1c +#define MT6357_BM_TOP_RST_CON0_CLR 0xc1e +#define MT6357_BM_TOP_INT_CON0 0xc20 +#define MT6357_BM_TOP_INT_CON0_SET 0xc22 +#define MT6357_BM_TOP_INT_CON0_CLR 0xc24 +#define MT6357_BM_TOP_INT_CON1 0xc26 +#define MT6357_BM_TOP_INT_CON1_SET 0xc28 +#define MT6357_BM_TOP_INT_CON1_CLR 0xc2a +#define MT6357_BM_TOP_INT_MASK_CON0 0xc2c +#define MT6357_BM_TOP_INT_MASK_CON0_SET 0xc2e +#define MT6357_BM_TOP_INT_MASK_CON0_CLR 0xc30 +#define MT6357_BM_TOP_INT_MASK_CON1 0xc32 +#define MT6357_BM_TOP_INT_MASK_CON1_SET 0xc34 +#define MT6357_BM_TOP_INT_MASK_CON1_CLR 0xc36 +#define MT6357_BM_TOP_INT_STATUS0 0xc38 +#define MT6357_BM_TOP_INT_STATUS1 0xc3a +#define MT6357_BM_TOP_INT_RAW_STATUS0 0xc3c +#define MT6357_BM_TOP_INT_RAW_STATUS1 0xc3e +#define MT6357_BM_TOP_INT_MISC_CON 0xc40 +#define MT6357_BM_TOP_DBG_CON 0xc42 +#define MT6357_BM_TOP_RSV0 0xc44 +#define MT6357_FGADC_ANA_DSN_ID 0xc80 +#define MT6357_FGADC_ANA_DSN_REV0 0xc82 +#define MT6357_FGADC_ANA_DSN_DBI 0xc84 +#define MT6357_FGADC_ANA_DSN_DXI 0xc86 +#define MT6357_FGADC_ANA_CON0 0xc88 +#define MT6357_FGADC_ANA_TEST_CON0 0xc8a +#define MT6357_FGADC_ANA_ELR_NUM 0xc8c +#define MT6357_FGADC_ANA_ELR0 0xc8e +#define MT6357_FGADC_ANA_ELR1 0xc90 +#define MT6357_FGADC0_DSN_ID 0xd00 +#define MT6357_FGADC0_DSN_REV0 0xd02 +#define MT6357_FGADC0_DSN_DBI 0xd04 +#define MT6357_FGADC0_DSN_DXI 0xd06 +#define MT6357_FGADC_CON0 0xd08 +#define MT6357_FGADC_CON1 0xd0a +#define MT6357_FGADC_CON2 0xd0c +#define MT6357_FGADC_CON3 0xd0e +#define MT6357_FGADC_CON4 0xd10 +#define MT6357_FGADC_CAR_CON0 0xd12 +#define MT6357_FGADC_CAR_CON1 0xd14 +#define MT6357_FGADC_CAR_CON2 0xd16 +#define MT6357_FGADC_CARTH_CON0 0xd18 +#define MT6357_FGADC_CARTH_CON1 0xd1a +#define MT6357_FGADC_CARTH_CON2 0xd1c +#define MT6357_FGADC_CARTH_CON3 0xd1e +#define MT6357_FGADC_NTER_CON0 0xd20 +#define MT6357_FGADC_NTER_CON1 0xd22 +#define MT6357_FGADC_NTER_CON2 0xd24 +#define MT6357_FGADC_SON_CON0 0xd26 +#define MT6357_FGADC_SON_CON1 0xd28 +#define MT6357_FGADC_SON_CON2 0xd2a +#define MT6357_FGADC_SON_CON3 0xd2c +#define MT6357_FGADC_ZCV_CON0 0xd2e +#define MT6357_FGADC_ZCV_CON1 0xd30 +#define MT6357_FGADC_ZCV_CON2 0xd32 +#define MT6357_FGADC_ZCV_CON3 0xd34 +#define MT6357_FGADC_ZCV_CON4 0xd36 +#define MT6357_FGADC_ZCVTH_CON0 0xd38 +#define MT6357_FGADC_ZCVTH_CON1 0xd3a +#define MT6357_FGADC_ZCVTH_CON2 0xd3c +#define MT6357_FGADC1_DSN_ID 0xd80 +#define MT6357_FGADC1_DSN_REV0 0xd82 +#define MT6357_FGADC1_DSN_DBI 0xd84 +#define MT6357_FGADC1_DSN_DXI 0xd86 +#define MT6357_FGADC_R_CON0 0xd88 +#define MT6357_FGADC_CUR_CON0 0xd8a +#define MT6357_FGADC_CUR_CON1 0xd8c +#define MT6357_FGADC_CUR_CON2 0xd8e +#define MT6357_FGADC_CUR_CON3 0xd90 +#define MT6357_FGADC_OFFSET_CON0 0xd92 +#define MT6357_FGADC_OFFSET_CON1 0xd94 +#define MT6357_FGADC_GAIN_CON0 0xd96 +#define MT6357_FGADC_TEST_CON0 0xd98 +#define MT6357_SYSTEM_INFO_CON0 0xd9a +#define MT6357_SYSTEM_INFO_CON1 0xd9c +#define MT6357_SYSTEM_INFO_CON2 0xd9e +#define MT6357_SYSTEM_INFO_CON3 0xda0 +#define MT6357_SYSTEM_INFO_CON4 0xda2 +#define MT6357_BATON_ANA_DSN_ID 0xe00 +#define MT6357_BATON_ANA_DSN_REV0 0xe02 +#define MT6357_BATON_ANA_DSN_DBI 0xe04 +#define MT6357_BATON_ANA_DSN_DXI 0xe06 +#define MT6357_BATON_ANA_CON0 0xe08 +#define MT6357_BATON_ANA_ELR_NUM 0xe0a +#define MT6357_BATON_ANA_ELR0 0xe0c +#define MT6357_HK_TOP_ID 0xf80 +#define MT6357_HK_TOP_REV0 0xf82 +#define MT6357_HK_TOP_DBI 0xf84 +#define MT6357_HK_TOP_DXI 0xf86 +#define MT6357_HK_TPM0 0xf88 +#define MT6357_HK_TPM1 0xf8a +#define MT6357_HK_TOP_CLK_CON0 0xf8c +#define MT6357_HK_TOP_CLK_CON1 0xf8e +#define MT6357_HK_TOP_RST_CON0 0xf90 +#define MT6357_HK_TOP_INT_CON0 0xf92 +#define MT6357_HK_TOP_INT_CON0_SET 0xf94 +#define MT6357_HK_TOP_INT_CON0_CLR 0xf96 +#define MT6357_HK_TOP_INT_MASK_CON0 0xf98 +#define MT6357_HK_TOP_INT_MASK_CON0_SET 0xf9a +#define MT6357_HK_TOP_INT_MASK_CON0_CLR 0xf9c +#define MT6357_HK_TOP_INT_STATUS0 0xf9e +#define MT6357_HK_TOP_INT_RAW_STATUS0 0xfa0 +#define MT6357_HK_TOP_MON_CON0 0xfa2 +#define MT6357_HK_TOP_MON_CON1 0xfa4 +#define MT6357_HK_TOP_MON_CON2 0xfa6 +#define MT6357_AUXADC_DSN_ID 0x1000 +#define MT6357_AUXADC_DSN_REV0 0x1002 +#define MT6357_AUXADC_DSN_DBI 0x1004 +#define MT6357_AUXADC_DSN_DXI 0x1006 +#define MT6357_AUXADC_ANA_CON0 0x1008 +#define MT6357_AUXADC_DIG_1_DSN_ID 0x1080 +#define MT6357_AUXADC_DIG_1_DSN_REV0 0x1082 +#define MT6357_AUXADC_DIG_1_DSN_DBI 0x1084 +#define MT6357_AUXADC_DIG_1_DSN_DXI 0x1086 +#define MT6357_AUXADC_ADC0 0x1088 +#define MT6357_AUXADC_ADC1 0x108a +#define MT6357_AUXADC_ADC2 0x108c +#define MT6357_AUXADC_ADC3 0x108e +#define MT6357_AUXADC_ADC4 0x1090 +#define MT6357_AUXADC_ADC5 0x1092 +#define MT6357_AUXADC_ADC6 0x1094 +#define MT6357_AUXADC_ADC7 0x1096 +#define MT6357_AUXADC_ADC8 0x1098 +#define MT6357_AUXADC_ADC9 0x109a +#define MT6357_AUXADC_ADC10 0x109c +#define MT6357_AUXADC_ADC11 0x109e +#define MT6357_AUXADC_ADC12 0x10a0 +#define MT6357_AUXADC_ADC14 0x10a2 +#define MT6357_AUXADC_ADC16 0x10a4 +#define MT6357_AUXADC_ADC17 0x10a6 +#define MT6357_AUXADC_ADC18 0x10a8 +#define MT6357_AUXADC_ADC19 0x10aa +#define MT6357_AUXADC_ADC20 0x10ac +#define MT6357_AUXADC_ADC21 0x10ae +#define MT6357_AUXADC_ADC22 0x10b0 +#define MT6357_AUXADC_ADC23 0x10b2 +#define MT6357_AUXADC_ADC24 0x10b4 +#define MT6357_AUXADC_ADC25 0x10b6 +#define MT6357_AUXADC_ADC26 0x10b8 +#define MT6357_AUXADC_ADC27 0x10ba +#define MT6357_AUXADC_ADC29 0x10bc +#define MT6357_AUXADC_ADC30 0x10be +#define MT6357_AUXADC_ADC31 0x10c0 +#define MT6357_AUXADC_ADC32 0x10c2 +#define MT6357_AUXADC_ADC33 0x10c4 +#define MT6357_AUXADC_ADC34 0x10c6 +#define MT6357_AUXADC_ADC35 0x10c8 +#define MT6357_AUXADC_ADC36 0x10ca +#define MT6357_AUXADC_ADC38 0x10cc +#define MT6357_AUXADC_ADC39 0x10ce +#define MT6357_AUXADC_ADC40 0x10d0 +#define MT6357_AUXADC_ADC41 0x10d2 +#define MT6357_AUXADC_ADC42 0x10d4 +#define MT6357_AUXADC_ADC43 0x10d6 +#define MT6357_AUXADC_ADC46 0x10d8 +#define MT6357_AUXADC_ADC47 0x10da +#define MT6357_AUXADC_DIG_1_ELR_NUM 0x10dc +#define MT6357_AUXADC_DIG_1_ELR0 0x10de +#define MT6357_AUXADC_DIG_1_ELR1 0x10e0 +#define MT6357_AUXADC_DIG_2_DSN_ID 0x1100 +#define MT6357_AUXADC_DIG_2_DSN_REV0 0x1102 +#define MT6357_AUXADC_DIG_2_DSN_DBI 0x1104 +#define MT6357_AUXADC_DIG_2_DSN_DXI 0x1106 +#define MT6357_AUXADC_STA0 0x1108 +#define MT6357_AUXADC_STA1 0x110a +#define MT6357_AUXADC_STA2 0x110c +#define MT6357_AUXADC_RQST0 0x110e +#define MT6357_AUXADC_RQST0_SET 0x1110 +#define MT6357_AUXADC_RQST0_CLR 0x1112 +#define MT6357_AUXADC_RQST2 0x1114 +#define MT6357_AUXADC_RQST2_SET 0x1116 +#define MT6357_AUXADC_RQST2_CLR 0x1118 +#define MT6357_AUXADC_RQST1 0x111a +#define MT6357_AUXADC_RQST1_SET 0x111c +#define MT6357_AUXADC_RQST1_CLR 0x111e +#define MT6357_AUXADC_CON0 0x1120 +#define MT6357_AUXADC_CON0_SET 0x1122 +#define MT6357_AUXADC_CON0_CLR 0x1124 +#define MT6357_AUXADC_CON1 0x1126 +#define MT6357_AUXADC_CON2 0x1128 +#define MT6357_AUXADC_CON3 0x112a +#define MT6357_AUXADC_CON4 0x112c +#define MT6357_AUXADC_CON5 0x112e +#define MT6357_AUXADC_CON6 0x1130 +#define MT6357_AUXADC_CON7 0x1132 +#define MT6357_AUXADC_CON8 0x1134 +#define MT6357_AUXADC_CON9 0x1136 +#define MT6357_AUXADC_CON10 0x1138 +#define MT6357_AUXADC_CON11 0x113a +#define MT6357_AUXADC_CON12 0x113c +#define MT6357_AUXADC_CON13 0x113e +#define MT6357_AUXADC_CON14 0x1140 +#define MT6357_AUXADC_CON15 0x1142 +#define MT6357_AUXADC_CON16 0x1144 +#define MT6357_AUXADC_CON17 0x1146 +#define MT6357_AUXADC_CON18 0x1148 +#define MT6357_AUXADC_CON19 0x114a +#define MT6357_AUXADC_CON20 0x114c +#define MT6357_AUXADC_DIG_3_DSN_ID 0x1180 +#define MT6357_AUXADC_DIG_3_DSN_REV0 0x1182 +#define MT6357_AUXADC_DIG_3_DSN_DBI 0x1184 +#define MT6357_AUXADC_DIG_3_DSN_DXI 0x1186 +#define MT6357_AUXADC_AUTORPT0 0x1188 +#define MT6357_AUXADC_LBAT0 0x118a +#define MT6357_AUXADC_LBAT1 0x118c +#define MT6357_AUXADC_LBAT2 0x118e +#define MT6357_AUXADC_LBAT3 0x1190 +#define MT6357_AUXADC_LBAT4 0x1192 +#define MT6357_AUXADC_LBAT5 0x1194 +#define MT6357_AUXADC_LBAT6 0x1196 +#define MT6357_AUXADC_ACCDET 0x1198 +#define MT6357_AUXADC_DBG0 0x119a +#define MT6357_AUXADC_IMP0 0x119c +#define MT6357_AUXADC_IMP1 0x119e +#define MT6357_AUXADC_DIG_3_ELR_NUM 0x11a0 +#define MT6357_AUXADC_DIG_3_ELR0 0x11a2 +#define MT6357_AUXADC_DIG_3_ELR1 0x11a4 +#define MT6357_AUXADC_DIG_3_ELR2 0x11a6 +#define MT6357_AUXADC_DIG_3_ELR3 0x11a8 +#define MT6357_AUXADC_DIG_3_ELR4 0x11aa +#define MT6357_AUXADC_DIG_3_ELR5 0x11ac +#define MT6357_AUXADC_DIG_3_ELR6 0x11ae +#define MT6357_AUXADC_DIG_3_ELR7 0x11b0 +#define MT6357_AUXADC_DIG_3_ELR8 0x11b2 +#define MT6357_AUXADC_DIG_3_ELR9 0x11b4 +#define MT6357_AUXADC_DIG_3_ELR10 0x11b6 +#define MT6357_AUXADC_DIG_3_ELR11 0x11b8 +#define MT6357_AUXADC_DIG_4_DSN_ID 0x1200 +#define MT6357_AUXADC_DIG_4_DSN_REV0 0x1202 +#define MT6357_AUXADC_DIG_4_DSN_DBI 0x1204 +#define MT6357_AUXADC_DIG_4_DSN_DXI 0x1206 +#define MT6357_AUXADC_MDRT_0 0x1208 +#define MT6357_AUXADC_MDRT_1 0x120a +#define MT6357_AUXADC_MDRT_2 0x120c +#define MT6357_AUXADC_MDRT_3 0x120e +#define MT6357_AUXADC_MDRT_4 0x1210 +#define MT6357_AUXADC_DCXO_MDRT_0 0x1212 +#define MT6357_AUXADC_DCXO_MDRT_1 0x1214 +#define MT6357_AUXADC_DCXO_MDRT_2 0x1216 +#define MT6357_AUXADC_NAG_0 0x1218 +#define MT6357_AUXADC_NAG_1 0x121a +#define MT6357_AUXADC_NAG_2 0x121c +#define MT6357_AUXADC_NAG_3 0x121e +#define MT6357_AUXADC_NAG_4 0x1220 +#define MT6357_AUXADC_NAG_5 0x1222 +#define MT6357_AUXADC_NAG_6 0x1224 +#define MT6357_AUXADC_NAG_7 0x1226 +#define MT6357_AUXADC_NAG_8 0x1228 +#define MT6357_AUXADC_RSV_1 0x122a +#define MT6357_AUXADC_ANA_0 0x122c +#define MT6357_AUXADC_IMP_CG0 0x122e +#define MT6357_AUXADC_LBAT_CG0 0x1230 +#define MT6357_AUXADC_NAG_CG0 0x1232 +#define MT6357_AUXADC_PRI_NEW 0x1234 +#define MT6357_AUXADC_CHR_TOP_CON2 0x1236 +#define MT6357_BUCK_TOP_DSN_ID 0x1400 +#define MT6357_BUCK_TOP_DSN_REV0 0x1402 +#define MT6357_BUCK_TOP_DBI 0x1404 +#define MT6357_BUCK_TOP_DXI 0x1406 +#define MT6357_BUCK_TOP_PAM0 0x1408 +#define MT6357_BUCK_TOP_PAM1 0x140a +#define MT6357_BUCK_TOP_CLK_CON0 0x140c +#define MT6357_BUCK_TOP_CLK_CON0_SET 0x140e +#define MT6357_BUCK_TOP_CLK_CON0_CLR 0x1410 +#define MT6357_BUCK_TOP_CLK_HWEN_CON0 0x1412 +#define MT6357_BUCK_TOP_CLK_HWEN_CON0_SET 0x1414 +#define MT6357_BUCK_TOP_CLK_HWEN_CON0_CLR 0x1416 +#define MT6357_BUCK_TOP_CLK_MISC_CON0 0x1418 +#define MT6357_BUCK_TOP_INT_CON0 0x141a +#define MT6357_BUCK_TOP_INT_CON0_SET 0x141c +#define MT6357_BUCK_TOP_INT_CON0_CLR 0x141e +#define MT6357_BUCK_TOP_INT_MASK_CON0 0x1420 +#define MT6357_BUCK_TOP_INT_MASK_CON0_SET 0x1422 +#define MT6357_BUCK_TOP_INT_MASK_CON0_CLR 0x1424 +#define MT6357_BUCK_TOP_INT_STATUS0 0x1426 +#define MT6357_BUCK_TOP_INT_RAW_STATUS0 0x1428 +#define MT6357_BUCK_TOP_STB_CON 0x142a +#define MT6357_BUCK_TOP_SLP_CON0 0x142c +#define MT6357_BUCK_TOP_SLP_CON1 0x142e +#define MT6357_BUCK_TOP_SLP_CON2 0x1430 +#define MT6357_BUCK_TOP_MINFREQ_CON 0x1432 +#define MT6357_BUCK_TOP_OC_CON0 0x1434 +#define MT6357_BUCK_TOP_K_CON0 0x1436 +#define MT6357_BUCK_TOP_K_CON1 0x1438 +#define MT6357_BUCK_TOP_K_CON2 0x143a +#define MT6357_BUCK_TOP_WDTDBG0 0x143c +#define MT6357_BUCK_TOP_WDTDBG1 0x143e +#define MT6357_BUCK_TOP_WDTDBG2 0x1440 +#define MT6357_BUCK_TOP_ELR_NUM 0x1442 +#define MT6357_BUCK_TOP_ELR0 0x1444 +#define MT6357_BUCK_TOP_ELR1 0x1446 +#define MT6357_BUCK_VPROC_DSN_ID 0x1480 +#define MT6357_BUCK_VPROC_DSN_REV0 0x1482 +#define MT6357_BUCK_VPROC_DSN_DBI 0x1484 +#define MT6357_BUCK_VPROC_DSN_DXI 0x1486 +#define MT6357_BUCK_VPROC_CON0 0x1488 +#define MT6357_BUCK_VPROC_CON1 0x148a +#define MT6357_BUCK_VPROC_CFG0 0x148c +#define MT6357_BUCK_VPROC_CFG1 0x148e +#define MT6357_BUCK_VPROC_OP_EN 0x1490 +#define MT6357_BUCK_VPROC_OP_EN_SET 0x1492 +#define MT6357_BUCK_VPROC_OP_EN_CLR 0x1494 +#define MT6357_BUCK_VPROC_OP_CFG 0x1496 +#define MT6357_BUCK_VPROC_OP_CFG_SET 0x1498 +#define MT6357_BUCK_VPROC_OP_CFG_CLR 0x149a +#define MT6357_BUCK_VPROC_SP_CON 0x149c +#define MT6357_BUCK_VPROC_SP_CFG 0x149e +#define MT6357_BUCK_VPROC_OC_CFG 0x14a0 +#define MT6357_BUCK_VPROC_DBG0 0x14a2 +#define MT6357_BUCK_VPROC_DBG1 0x14a4 +#define MT6357_BUCK_VPROC_DBG2 0x14a6 +#define MT6357_BUCK_VPROC_ELR_NUM 0x14a8 +#define MT6357_BUCK_VPROC_ELR0 0x14aa +#define MT6357_BUCK_VCORE_DSN_ID 0x1500 +#define MT6357_BUCK_VCORE_DSN_REV0 0x1502 +#define MT6357_BUCK_VCORE_DSN_DBI 0x1504 +#define MT6357_BUCK_VCORE_DSN_DXI 0x1506 +#define MT6357_BUCK_VCORE_CON0 0x1508 +#define MT6357_BUCK_VCORE_CON1 0x150a +#define MT6357_BUCK_VCORE_CFG0 0x150c +#define MT6357_BUCK_VCORE_CFG1 0x150e +#define MT6357_BUCK_VCORE_OP_EN 0x1510 +#define MT6357_BUCK_VCORE_OP_EN_SET 0x1512 +#define MT6357_BUCK_VCORE_OP_EN_CLR 0x1514 +#define MT6357_BUCK_VCORE_OP_CFG 0x1516 +#define MT6357_BUCK_VCORE_OP_CFG_SET 0x1518 +#define MT6357_BUCK_VCORE_OP_CFG_CLR 0x151a +#define MT6357_BUCK_VCORE_SP_CON 0x151c +#define MT6357_BUCK_VCORE_SP_CFG 0x151e +#define MT6357_BUCK_VCORE_OC_CFG 0x1520 +#define MT6357_BUCK_VCORE_DBG0 0x1522 +#define MT6357_BUCK_VCORE_DBG1 0x1524 +#define MT6357_BUCK_VCORE_DBG2 0x1526 +#define MT6357_BUCK_VCORE_ELR_NUM 0x1528 +#define MT6357_BUCK_VCORE_ELR0 0x152a +#define MT6357_BUCK_VMODEM_DSN_ID 0x1580 +#define MT6357_BUCK_VMODEM_DSN_REV0 0x1582 +#define MT6357_BUCK_VMODEM_DSN_DBI 0x1584 +#define MT6357_BUCK_VMODEM_DSN_DXI 0x1586 +#define MT6357_BUCK_VMODEM_CON0 0x1588 +#define MT6357_BUCK_VMODEM_CON1 0x158a +#define MT6357_BUCK_VMODEM_CFG0 0x158c +#define MT6357_BUCK_VMODEM_CFG1 0x158e +#define MT6357_BUCK_VMODEM_OP_EN 0x1590 +#define MT6357_BUCK_VMODEM_OP_EN_SET 0x1592 +#define MT6357_BUCK_VMODEM_OP_EN_CLR 0x1594 +#define MT6357_BUCK_VMODEM_OP_CFG 0x1596 +#define MT6357_BUCK_VMODEM_OP_CFG_SET 0x1598 +#define MT6357_BUCK_VMODEM_OP_CFG_CLR 0x159a +#define MT6357_BUCK_VMODEM_SP_CON 0x159c +#define MT6357_BUCK_VMODEM_SP_CFG 0x159e +#define MT6357_BUCK_VMODEM_OC_CFG 0x15a0 +#define MT6357_BUCK_VMODEM_DBG0 0x15a2 +#define MT6357_BUCK_VMODEM_DBG1 0x15a4 +#define MT6357_BUCK_VMODEM_DBG2 0x15a6 +#define MT6357_BUCK_VMODEM_ELR_NUM 0x15a8 +#define MT6357_BUCK_VMODEM_ELR0 0x15aa +#define MT6357_BUCK_VS1_DSN_ID 0x1600 +#define MT6357_BUCK_VS1_DSN_REV0 0x1602 +#define MT6357_BUCK_VS1_DSN_DBI 0x1604 +#define MT6357_BUCK_VS1_DSN_DXI 0x1606 +#define MT6357_BUCK_VS1_CON0 0x1608 +#define MT6357_BUCK_VS1_CON1 0x160a +#define MT6357_BUCK_VS1_CFG0 0x160c +#define MT6357_BUCK_VS1_CFG1 0x160e +#define MT6357_BUCK_VS1_OP_EN 0x1610 +#define MT6357_BUCK_VS1_OP_EN_SET 0x1612 +#define MT6357_BUCK_VS1_OP_EN_CLR 0x1614 +#define MT6357_BUCK_VS1_OP_CFG 0x1616 +#define MT6357_BUCK_VS1_OP_CFG_SET 0x1618 +#define MT6357_BUCK_VS1_OP_CFG_CLR 0x161a +#define MT6357_BUCK_VS1_SP_CON 0x161c +#define MT6357_BUCK_VS1_SP_CFG 0x161e +#define MT6357_BUCK_VS1_OC_CFG 0x1620 +#define MT6357_BUCK_VS1_DBG0 0x1622 +#define MT6357_BUCK_VS1_DBG1 0x1624 +#define MT6357_BUCK_VS1_DBG2 0x1626 +#define MT6357_BUCK_VS1_VOTER 0x1628 +#define MT6357_BUCK_VS1_VOTER_SET 0x162a +#define MT6357_BUCK_VS1_VOTER_CLR 0x162c +#define MT6357_BUCK_VS1_VOTER_CFG 0x162e +#define MT6357_BUCK_VS1_ELR_NUM 0x1630 +#define MT6357_BUCK_VS1_ELR0 0x1632 +#define MT6357_BUCK_VPA_DSN_ID 0x1680 +#define MT6357_BUCK_VPA_DSN_REV0 0x1682 +#define MT6357_BUCK_VPA_DSN_DBI 0x1684 +#define MT6357_BUCK_VPA_DSN_DXI 0x1686 +#define MT6357_BUCK_VPA_CON0 0x1688 +#define MT6357_BUCK_VPA_CON1 0x168a +#define MT6357_BUCK_VPA_CFG0 0x168c +#define MT6357_BUCK_VPA_CFG1 0x168e +#define MT6357_BUCK_VPA_OC_CFG 0x1690 +#define MT6357_BUCK_VPA_DBG0 0x1692 +#define MT6357_BUCK_VPA_DBG1 0x1694 +#define MT6357_BUCK_VPA_DBG2 0x1696 +#define MT6357_BUCK_VPA_DLC_CON0 0x1698 +#define MT6357_BUCK_VPA_DLC_CON1 0x169a +#define MT6357_BUCK_VPA_DLC_CON2 0x169c +#define MT6357_BUCK_VPA_MSFG_CON0 0x169e +#define MT6357_BUCK_VPA_MSFG_CON1 0x16a0 +#define MT6357_BUCK_VPA_MSFG_RRATE0 0x16a2 +#define MT6357_BUCK_VPA_MSFG_RRATE1 0x16a4 +#define MT6357_BUCK_VPA_MSFG_RRATE2 0x16a6 +#define MT6357_BUCK_VPA_MSFG_RTHD0 0x16a8 +#define MT6357_BUCK_VPA_MSFG_RTHD1 0x16aa +#define MT6357_BUCK_VPA_MSFG_RTHD2 0x16ac +#define MT6357_BUCK_VPA_MSFG_FRATE0 0x16ae +#define MT6357_BUCK_VPA_MSFG_FRATE1 0x16b0 +#define MT6357_BUCK_VPA_MSFG_FRATE2 0x16b2 +#define MT6357_BUCK_VPA_MSFG_FTHD0 0x16b4 +#define MT6357_BUCK_VPA_MSFG_FTHD1 0x16b6 +#define MT6357_BUCK_VPA_MSFG_FTHD2 0x16b8 +#define MT6357_BUCK_ANA_DSN_ID 0x1700 +#define MT6357_BUCK_ANA_DSN_REV0 0x1702 +#define MT6357_BUCK_ANA_DSN_DBI 0x1704 +#define MT6357_BUCK_ANA_DSN_FPI 0x1706 +#define MT6357_SMPS_ANA_CON0 0x1708 +#define MT6357_SMPS_ANA_CON1 0x170a +#define MT6357_SMPS_ANA_CON2 0x170c +#define MT6357_VCORE_VPROC_ANA_CON0 0x170e +#define MT6357_VCORE_VPROC_ANA_CON1 0x1710 +#define MT6357_VCORE_VPROC_ANA_CON2 0x1712 +#define MT6357_VCORE_VPROC_ANA_CON3 0x1714 +#define MT6357_VCORE_VPROC_ANA_CON4 0x1716 +#define MT6357_VCORE_VPROC_ANA_CON5 0x1718 +#define MT6357_VCORE_VPROC_ANA_CON6 0x171a +#define MT6357_VCORE_VPROC_ANA_CON7 0x171c +#define MT6357_VCORE_VPROC_ANA_CON8 0x171e +#define MT6357_VCORE_VPROC_ANA_CON9 0x1720 +#define MT6357_VCORE_VPROC_ANA_CON10 0x1722 +#define MT6357_VCORE_VPROC_ANA_CON11 0x1724 +#define MT6357_VMODEM_ANA_CON0 0x1726 +#define MT6357_VMODEM_ANA_CON1 0x1728 +#define MT6357_VMODEM_ANA_CON2 0x172a +#define MT6357_VMODEM_ANA_CON3 0x172c +#define MT6357_VMODEM_ANA_CON4 0x172e +#define MT6357_VMODEM_ANA_CON5 0x1730 +#define MT6357_VS1_ANA_CON0 0x1732 +#define MT6357_VS1_ANA_CON1 0x1734 +#define MT6357_VS1_ANA_CON2 0x1736 +#define MT6357_VS1_ANA_CON3 0x1738 +#define MT6357_VS1_ANA_CON4 0x173a +#define MT6357_VS1_ANA_CON5 0x173c +#define MT6357_VPA_ANA_CON0 0x173e +#define MT6357_VPA_ANA_CON1 0x1740 +#define MT6357_VPA_ANA_CON2 0x1742 +#define MT6357_VPA_ANA_CON3 0x1744 +#define MT6357_VPA_ANA_CON4 0x1746 +#define MT6357_VPA_ANA_CON5 0x1748 +#define MT6357_BUCK_ANA_ELR_NUM 0x174a +#define MT6357_SMPS_ELR_0 0x174c +#define MT6357_SMPS_ELR_1 0x174e +#define MT6357_SMPS_ELR_2 0x1750 +#define MT6357_SMPS_ELR_3 0x1752 +#define MT6357_SMPS_ELR_4 0x1754 +#define MT6357_SMPS_ELR_5 0x1756 +#define MT6357_VCORE_VPROC_ELR_0 0x1758 +#define MT6357_VCORE_VPROC_ELR_1 0x175a +#define MT6357_VCORE_VPROC_ELR_2 0x175c +#define MT6357_VCORE_VPROC_ELR_3 0x175e +#define MT6357_VCORE_VPROC_ELR_4 0x1760 +#define MT6357_VMODEM_ELR_0 0x1762 +#define MT6357_VMODEM_ELR_1 0x1764 +#define MT6357_VMODEM_ELR_2 0x1766 +#define MT6357_VS1_ELR_0 0x1768 +#define MT6357_VS1_ELR_1 0x176a +#define MT6357_VPA_ELR_0 0x176c +#define MT6357_LDO_TOP_ID 0x1880 +#define MT6357_LDO_TOP_REV0 0x1882 +#define MT6357_LDO_TOP_DBI 0x1884 +#define MT6357_LDO_TOP_DXI 0x1886 +#define MT6357_LDO_TPM0 0x1888 +#define MT6357_LDO_TPM1 0x188a +#define MT6357_LDO_TOP_CLK_DCM_CON0 0x188c +#define MT6357_LDO_TOP_CLK_VIO28_CON0 0x188e +#define MT6357_LDO_TOP_CLK_VIO18_CON0 0x1890 +#define MT6357_LDO_TOP_CLK_VAUD28_CON0 0x1892 +#define MT6357_LDO_TOP_CLK_VDRAM_CON0 0x1894 +#define MT6357_LDO_TOP_CLK_VSRAM_PROC_CON0 0x1896 +#define MT6357_LDO_TOP_CLK_VSRAM_OTHERS_CON0 0x1898 +#define MT6357_LDO_TOP_CLK_VAUX18_CON0 0x189a +#define MT6357_LDO_TOP_CLK_VUSB33_CON0 0x189c +#define MT6357_LDO_TOP_CLK_VEMC_CON0 0x189e +#define MT6357_LDO_TOP_CLK_VXO22_CON0 0x18a0 +#define MT6357_LDO_TOP_CLK_VSIM1_CON0 0x18a2 +#define MT6357_LDO_TOP_CLK_VSIM2_CON0 0x18a4 +#define MT6357_LDO_TOP_CLK_VCAMD_CON0 0x18a6 +#define MT6357_LDO_TOP_CLK_VCAMIO_CON0 0x18a8 +#define MT6357_LDO_TOP_CLK_VEFUSE_CON0 0x18aa +#define MT6357_LDO_TOP_CLK_VCN33_CON0 0x18ac +#define MT6357_LDO_TOP_CLK_VCN18_CON0 0x18ae +#define MT6357_LDO_TOP_CLK_VCN28_CON0 0x18b0 +#define MT6357_LDO_TOP_CLK_VIBR_CON0 0x18b2 +#define MT6357_LDO_TOP_CLK_VFE28_CON0 0x18b4 +#define MT6357_LDO_TOP_CLK_VMCH_CON0 0x18b6 +#define MT6357_LDO_TOP_CLK_VMC_CON0 0x18b8 +#define MT6357_LDO_TOP_CLK_VRF18_CON0 0x18ba +#define MT6357_LDO_TOP_CLK_VLDO28_CON0 0x18bc +#define MT6357_LDO_TOP_CLK_VRF12_CON0 0x18be +#define MT6357_LDO_TOP_CLK_VCAMA_CON0 0x18c0 +#define MT6357_LDO_TOP_CLK_TREF_CON0 0x18c2 +#define MT6357_LDO_TOP_INT_CON0 0x18c4 +#define MT6357_LDO_TOP_INT_CON0_SET 0x18c6 +#define MT6357_LDO_TOP_INT_CON0_CLR 0x18c8 +#define MT6357_LDO_TOP_INT_CON1 0x18ca +#define MT6357_LDO_TOP_INT_CON1_SET 0x18cc +#define MT6357_LDO_TOP_INT_CON1_CLR 0x18ce +#define MT6357_LDO_TOP_INT_MASK_CON0 0x18d0 +#define MT6357_LDO_TOP_INT_MASK_CON0_SET 0x18d2 +#define MT6357_LDO_TOP_INT_MASK_CON0_CLR 0x18d4 +#define MT6357_LDO_TOP_INT_MASK_CON1 0x18d6 +#define MT6357_LDO_TOP_INT_MASK_CON1_SET 0x18d8 +#define MT6357_LDO_TOP_INT_MASK_CON1_CLR 0x18da +#define MT6357_LDO_TOP_INT_STATUS0 0x18dc +#define MT6357_LDO_TOP_INT_STATUS1 0x18de +#define MT6357_LDO_TOP_INT_RAW_STATUS0 0x18e0 +#define MT6357_LDO_TOP_INT_RAW_STATUS1 0x18e2 +#define MT6357_LDO_TEST_CON0 0x18e4 +#define MT6357_LDO_TOP_WDT_CON0 0x18e6 +#define MT6357_LDO_TOP_RSV_CON0 0x18e8 +#define MT6357_LDO_TOP_RSV_CON1 0x18ea +#define MT6357_LDO_OCFB0 0x18ec +#define MT6357_LDO_LP_PROTECTION 0x18ee +#define MT6357_LDO_DUMMY_LOAD_GATED 0x18f0 +#define MT6357_LDO_GON0_DSN_ID 0x1900 +#define MT6357_LDO_GON0_DSN_REV0 0x1902 +#define MT6357_LDO_GON0_DSN_DBI 0x1904 +#define MT6357_LDO_GON0_DSN_DXI 0x1906 +#define MT6357_LDO_VXO22_CON0 0x1908 +#define MT6357_LDO_VXO22_OP_EN 0x190a +#define MT6357_LDO_VXO22_OP_EN_SET 0x190c +#define MT6357_LDO_VXO22_OP_EN_CLR 0x190e +#define MT6357_LDO_VXO22_OP_CFG 0x1910 +#define MT6357_LDO_VXO22_OP_CFG_SET 0x1912 +#define MT6357_LDO_VXO22_OP_CFG_CLR 0x1914 +#define MT6357_LDO_VXO22_CON1 0x1916 +#define MT6357_LDO_VXO22_CON2 0x1918 +#define MT6357_LDO_VXO22_CON3 0x191a +#define MT6357_LDO_VAUX18_CON0 0x191c +#define MT6357_LDO_VAUX18_OP_EN 0x191e +#define MT6357_LDO_VAUX18_OP_EN_SET 0x1920 +#define MT6357_LDO_VAUX18_OP_EN_CLR 0x1922 +#define MT6357_LDO_VAUX18_OP_CFG 0x1924 +#define MT6357_LDO_VAUX18_OP_CFG_SET 0x1926 +#define MT6357_LDO_VAUX18_OP_CFG_CLR 0x1928 +#define MT6357_LDO_VAUX18_CON1 0x192a +#define MT6357_LDO_VAUX18_CON2 0x192c +#define MT6357_LDO_VAUX18_CON3 0x192e +#define MT6357_LDO_VAUD28_CON0 0x1930 +#define MT6357_LDO_VAUD28_OP_EN 0x1932 +#define MT6357_LDO_VAUD28_OP_EN_SET 0x1934 +#define MT6357_LDO_VAUD28_OP_EN_CLR 0x1936 +#define MT6357_LDO_VAUD28_OP_CFG 0x1938 +#define MT6357_LDO_VAUD28_OP_CFG_SET 0x193a +#define MT6357_LDO_VAUD28_OP_CFG_CLR 0x193c +#define MT6357_LDO_VAUD28_CON1 0x193e +#define MT6357_LDO_VAUD28_CON2 0x1940 +#define MT6357_LDO_VAUD28_CON3 0x1942 +#define MT6357_LDO_VIO28_CON0 0x1944 +#define MT6357_LDO_VIO28_OP_EN 0x1946 +#define MT6357_LDO_VIO28_OP_EN_SET 0x1948 +#define MT6357_LDO_VIO28_OP_EN_CLR 0x194a +#define MT6357_LDO_VIO28_OP_CFG 0x194c +#define MT6357_LDO_VIO28_OP_CFG_SET 0x194e +#define MT6357_LDO_VIO28_OP_CFG_CLR 0x1950 +#define MT6357_LDO_VIO28_CON1 0x1952 +#define MT6357_LDO_VIO28_CON2 0x1954 +#define MT6357_LDO_VIO28_CON3 0x1956 +#define MT6357_LDO_VIO18_CON0 0x1958 +#define MT6357_LDO_VIO18_OP_EN 0x195a +#define MT6357_LDO_VIO18_OP_EN_SET 0x195c +#define MT6357_LDO_VIO18_OP_EN_CLR 0x195e +#define MT6357_LDO_VIO18_OP_CFG 0x1960 +#define MT6357_LDO_VIO18_OP_CFG_SET 0x1962 +#define MT6357_LDO_VIO18_OP_CFG_CLR 0x1964 +#define MT6357_LDO_VIO18_CON1 0x1966 +#define MT6357_LDO_VIO18_CON2 0x1968 +#define MT6357_LDO_VIO18_CON3 0x196a +#define MT6357_LDO_VDRAM_CON0 0x196c +#define MT6357_LDO_VDRAM_OP_EN 0x196e +#define MT6357_LDO_VDRAM_OP_EN_SET 0x1970 +#define MT6357_LDO_VDRAM_OP_EN_CLR 0x1972 +#define MT6357_LDO_VDRAM_OP_CFG 0x1974 +#define MT6357_LDO_VDRAM_OP_CFG_SET 0x1976 +#define MT6357_LDO_VDRAM_OP_CFG_CLR 0x1978 +#define MT6357_LDO_VDRAM_CON1 0x197a +#define MT6357_LDO_VDRAM_CON2 0x197c +#define MT6357_LDO_VDRAM_CON3 0x197e +#define MT6357_LDO_GON1_DSN_ID 0x1980 +#define MT6357_LDO_GON1_DSN_REV0 0x1982 +#define MT6357_LDO_GON1_DSN_DBI 0x1984 +#define MT6357_LDO_GON1_DSN_DXI 0x1986 +#define MT6357_LDO_VEMC_CON0 0x1988 +#define MT6357_LDO_VEMC_OP_EN 0x198a +#define MT6357_LDO_VEMC_OP_EN_SET 0x198c +#define MT6357_LDO_VEMC_OP_EN_CLR 0x198e +#define MT6357_LDO_VEMC_OP_CFG 0x1990 +#define MT6357_LDO_VEMC_OP_CFG_SET 0x1992 +#define MT6357_LDO_VEMC_OP_CFG_CLR 0x1994 +#define MT6357_LDO_VEMC_CON1 0x1996 +#define MT6357_LDO_VEMC_CON2 0x1998 +#define MT6357_LDO_VEMC_CON3 0x199a +#define MT6357_LDO_VUSB33_CON0_0 0x199c +#define MT6357_LDO_VUSB33_OP_EN 0x199e +#define MT6357_LDO_VUSB33_OP_EN_SET 0x19a0 +#define MT6357_LDO_VUSB33_OP_EN_CLR 0x19a2 +#define MT6357_LDO_VUSB33_OP_CFG 0x19a4 +#define MT6357_LDO_VUSB33_OP_CFG_SET 0x19a6 +#define MT6357_LDO_VUSB33_OP_CFG_CLR 0x19a8 +#define MT6357_LDO_VUSB33_CON0_1 0x19aa +#define MT6357_LDO_VUSB33_CON1 0x19ac +#define MT6357_LDO_VUSB33_CON2 0x19ae +#define MT6357_LDO_VUSB33_CON3 0x19b0 +#define MT6357_LDO_VSRAM_PROC_CON0 0x19b2 +#define MT6357_LDO_VSRAM_PROC_CON2 0x19b4 +#define MT6357_LDO_VSRAM_PROC_CFG0 0x19b6 +#define MT6357_LDO_VSRAM_PROC_CFG1 0x19b8 +#define MT6357_LDO_VSRAM_PROC_OP_EN 0x19ba +#define MT6357_LDO_VSRAM_PROC_OP_EN_SET 0x19bc +#define MT6357_LDO_VSRAM_PROC_OP_EN_CLR 0x19be +#define MT6357_LDO_VSRAM_PROC_OP_CFG 0x19c0 +#define MT6357_LDO_VSRAM_PROC_OP_CFG_SET 0x19c2 +#define MT6357_LDO_VSRAM_PROC_OP_CFG_CLR 0x19c4 +#define MT6357_LDO_VSRAM_PROC_CON3 0x19c6 +#define MT6357_LDO_VSRAM_PROC_CON4 0x19c8 +#define MT6357_LDO_VSRAM_PROC_CON5 0x19ca +#define MT6357_LDO_VSRAM_PROC_DBG0 0x19cc +#define MT6357_LDO_VSRAM_PROC_DBG1 0x19ce +#define MT6357_LDO_VSRAM_OTHERS_CON0 0x19d0 +#define MT6357_LDO_VSRAM_OTHERS_CON2 0x19d2 +#define MT6357_LDO_VSRAM_OTHERS_CFG0 0x19d4 +#define MT6357_LDO_VSRAM_OTHERS_CFG1 0x19d6 +#define MT6357_LDO_VSRAM_OTHERS_OP_EN 0x19d8 +#define MT6357_LDO_VSRAM_OTHERS_OP_EN_SET 0x19da +#define MT6357_LDO_VSRAM_OTHERS_OP_EN_CLR 0x19dc +#define MT6357_LDO_VSRAM_OTHERS_OP_CFG 0x19de +#define MT6357_LDO_VSRAM_OTHERS_OP_CFG_SET 0x19e0 +#define MT6357_LDO_VSRAM_OTHERS_OP_CFG_CLR 0x19e2 +#define MT6357_LDO_VSRAM_OTHERS_CON3 0x19e4 +#define MT6357_LDO_VSRAM_OTHERS_CON4 0x19e6 +#define MT6357_LDO_VSRAM_OTHERS_CON5 0x19e8 +#define MT6357_LDO_VSRAM_OTHERS_DBG0 0x19ea +#define MT6357_LDO_VSRAM_OTHERS_DBG1 0x19ec +#define MT6357_LDO_VSRAM_PROC_SP 0x19ee +#define MT6357_LDO_VSRAM_OTHERS_SP 0x19f0 +#define MT6357_LDO_VSRAM_PROC_R2R_PDN_DIS 0x19f2 +#define MT6357_LDO_VSRAM_OTHERS_R2R_PDN_DIS 0x19f4 +#define MT6357_LDO_VSRAM_WDT_DBG0 0x19f6 +#define MT6357_LDO_GON1_ELR_NUM 0x19f8 +#define MT6357_LDO_VSRAM_CON0 0x19fa +#define MT6357_LDO_VSRAM_CON1 0x19fc +#define MT6357_LDO_VSRAM_CON2 0x19fe +#define MT6357_LDO_GOFF0_DSN_ID 0x1a00 +#define MT6357_LDO_GOFF0_DSN_REV0 0x1a02 +#define MT6357_LDO_GOFF0_DSN_DBI 0x1a04 +#define MT6357_LDO_GOFF0_DSN_DXI 0x1a06 +#define MT6357_LDO_VFE28_CON0 0x1a08 +#define MT6357_LDO_VFE28_OP_EN 0x1a0a +#define MT6357_LDO_VFE28_OP_EN_SET 0x1a0c +#define MT6357_LDO_VFE28_OP_EN_CLR 0x1a0e +#define MT6357_LDO_VFE28_OP_CFG 0x1a10 +#define MT6357_LDO_VFE28_OP_CFG_SET 0x1a12 +#define MT6357_LDO_VFE28_OP_CFG_CLR 0x1a14 +#define MT6357_LDO_VFE28_CON1 0x1a16 +#define MT6357_LDO_VFE28_CON2 0x1a18 +#define MT6357_LDO_VFE28_CON3 0x1a1a +#define MT6357_LDO_VRF18_CON0 0x1a1c +#define MT6357_LDO_VRF18_OP_EN 0x1a1e +#define MT6357_LDO_VRF18_OP_EN_SET 0x1a20 +#define MT6357_LDO_VRF18_OP_EN_CLR 0x1a22 +#define MT6357_LDO_VRF18_OP_CFG 0x1a24 +#define MT6357_LDO_VRF18_OP_CFG_SET 0x1a26 +#define MT6357_LDO_VRF18_OP_CFG_CLR 0x1a28 +#define MT6357_LDO_VRF18_CON1 0x1a2a +#define MT6357_LDO_VRF18_CON2 0x1a2c +#define MT6357_LDO_VRF18_CON3 0x1a2e +#define MT6357_LDO_VRF12_CON0 0x1a30 +#define MT6357_LDO_VRF12_OP_EN 0x1a32 +#define MT6357_LDO_VRF12_OP_EN_SET 0x1a34 +#define MT6357_LDO_VRF12_OP_EN_CLR 0x1a36 +#define MT6357_LDO_VRF12_OP_CFG 0x1a38 +#define MT6357_LDO_VRF12_OP_CFG_SET 0x1a3a +#define MT6357_LDO_VRF12_OP_CFG_CLR 0x1a3c +#define MT6357_LDO_VRF12_CON1 0x1a3e +#define MT6357_LDO_VRF12_CON2 0x1a40 +#define MT6357_LDO_VRF12_CON3 0x1a42 +#define MT6357_LDO_VEFUSE_CON0 0x1a44 +#define MT6357_LDO_VEFUSE_OP_EN 0x1a46 +#define MT6357_LDO_VEFUSE_OP_EN_SET 0x1a48 +#define MT6357_LDO_VEFUSE_OP_EN_CLR 0x1a4a +#define MT6357_LDO_VEFUSE_OP_CFG 0x1a4c +#define MT6357_LDO_VEFUSE_OP_CFG_SET 0x1a4e +#define MT6357_LDO_VEFUSE_OP_CFG_CLR 0x1a50 +#define MT6357_LDO_VEFUSE_CON1 0x1a52 +#define MT6357_LDO_VEFUSE_CON2 0x1a54 +#define MT6357_LDO_VEFUSE_CON3 0x1a56 +#define MT6357_LDO_VCN18_CON0 0x1a58 +#define MT6357_LDO_VCN18_OP_EN 0x1a5a +#define MT6357_LDO_VCN18_OP_EN_SET 0x1a5c +#define MT6357_LDO_VCN18_OP_EN_CLR 0x1a5e +#define MT6357_LDO_VCN18_OP_CFG 0x1a60 +#define MT6357_LDO_VCN18_OP_CFG_SET 0x1a62 +#define MT6357_LDO_VCN18_OP_CFG_CLR 0x1a64 +#define MT6357_LDO_VCN18_CON1 0x1a66 +#define MT6357_LDO_VCN18_CON2 0x1a68 +#define MT6357_LDO_VCN18_CON3 0x1a6a +#define MT6357_LDO_VCAMA_CON0 0x1a6c +#define MT6357_LDO_VCAMA_OP_EN 0x1a6e +#define MT6357_LDO_VCAMA_OP_EN_SET 0x1a70 +#define MT6357_LDO_VCAMA_OP_EN_CLR 0x1a72 +#define MT6357_LDO_VCAMA_OP_CFG 0x1a74 +#define MT6357_LDO_VCAMA_OP_CFG_SET 0x1a76 +#define MT6357_LDO_VCAMA_OP_CFG_CLR 0x1a78 +#define MT6357_LDO_VCAMA_CON1 0x1a7a +#define MT6357_LDO_VCAMA_CON2 0x1a7c +#define MT6357_LDO_VCAMA_CON3 0x1a7e +#define MT6357_LDO_GOFF1_DSN_ID 0x1a80 +#define MT6357_LDO_GOFF1_DSN_REV0 0x1a82 +#define MT6357_LDO_GOFF1_DSN_DBI 0x1a84 +#define MT6357_LDO_GOFF1_DSN_DXI 0x1a86 +#define MT6357_LDO_VCAMD_CON0 0x1a88 +#define MT6357_LDO_VCAMD_OP_EN 0x1a8a +#define MT6357_LDO_VCAMD_OP_EN_SET 0x1a8c +#define MT6357_LDO_VCAMD_OP_EN_CLR 0x1a8e +#define MT6357_LDO_VCAMD_OP_CFG 0x1a90 +#define MT6357_LDO_VCAMD_OP_CFG_SET 0x1a92 +#define MT6357_LDO_VCAMD_OP_CFG_CLR 0x1a94 +#define MT6357_LDO_VCAMD_CON1 0x1a96 +#define MT6357_LDO_VCAMD_CON2 0x1a98 +#define MT6357_LDO_VCAMD_CON3 0x1a9a +#define MT6357_LDO_VCAMIO_CON0 0x1a9c +#define MT6357_LDO_VCAMIO_OP_EN 0x1a9e +#define MT6357_LDO_VCAMIO_OP_EN_SET 0x1aa0 +#define MT6357_LDO_VCAMIO_OP_EN_CLR 0x1aa2 +#define MT6357_LDO_VCAMIO_OP_CFG 0x1aa4 +#define MT6357_LDO_VCAMIO_OP_CFG_SET 0x1aa6 +#define MT6357_LDO_VCAMIO_OP_CFG_CLR 0x1aa8 +#define MT6357_LDO_VCAMIO_CON1 0x1aaa +#define MT6357_LDO_VCAMIO_CON2 0x1aac +#define MT6357_LDO_VCAMIO_CON3 0x1aae +#define MT6357_LDO_VMC_CON0 0x1ab0 +#define MT6357_LDO_VMC_OP_EN 0x1ab2 +#define MT6357_LDO_VMC_OP_EN_SET 0x1ab4 +#define MT6357_LDO_VMC_OP_EN_CLR 0x1ab6 +#define MT6357_LDO_VMC_OP_CFG 0x1ab8 +#define MT6357_LDO_VMC_OP_CFG_SET 0x1aba +#define MT6357_LDO_VMC_OP_CFG_CLR 0x1abc +#define MT6357_LDO_VMC_CON1 0x1abe +#define MT6357_LDO_VMC_CON2 0x1ac0 +#define MT6357_LDO_VMC_CON3 0x1ac2 +#define MT6357_LDO_VMCH_CON0 0x1ac4 +#define MT6357_LDO_VMCH_OP_EN 0x1ac6 +#define MT6357_LDO_VMCH_OP_EN_SET 0x1ac8 +#define MT6357_LDO_VMCH_OP_EN_CLR 0x1aca +#define MT6357_LDO_VMCH_OP_CFG 0x1acc +#define MT6357_LDO_VMCH_OP_CFG_SET 0x1ace +#define MT6357_LDO_VMCH_OP_CFG_CLR 0x1ad0 +#define MT6357_LDO_VMCH_CON1 0x1ad2 +#define MT6357_LDO_VMCH_CON2 0x1ad4 +#define MT6357_LDO_VMCH_CON3 0x1ad6 +#define MT6357_LDO_VSIM1_CON0 0x1ad8 +#define MT6357_LDO_VSIM1_OP_EN 0x1ada +#define MT6357_LDO_VSIM1_OP_EN_SET 0x1adc +#define MT6357_LDO_VSIM1_OP_EN_CLR 0x1ade +#define MT6357_LDO_VSIM1_OP_CFG 0x1ae0 +#define MT6357_LDO_VSIM1_OP_CFG_SET 0x1ae2 +#define MT6357_LDO_VSIM1_OP_CFG_CLR 0x1ae4 +#define MT6357_LDO_VSIM1_CON1 0x1ae6 +#define MT6357_LDO_VSIM1_CON2 0x1ae8 +#define MT6357_LDO_VSIM1_CON3 0x1aea +#define MT6357_LDO_VSIM2_CON0 0x1aec +#define MT6357_LDO_VSIM2_OP_EN 0x1aee +#define MT6357_LDO_VSIM2_OP_EN_SET 0x1af0 +#define MT6357_LDO_VSIM2_OP_EN_CLR 0x1af2 +#define MT6357_LDO_VSIM2_OP_CFG 0x1af4 +#define MT6357_LDO_VSIM2_OP_CFG_SET 0x1af6 +#define MT6357_LDO_VSIM2_OP_CFG_CLR 0x1af8 +#define MT6357_LDO_VSIM2_CON1 0x1afa +#define MT6357_LDO_VSIM2_CON2 0x1afc +#define MT6357_LDO_VSIM2_CON3 0x1afe +#define MT6357_LDO_GOFF2_DSN_ID 0x1b00 +#define MT6357_LDO_GOFF2_DSN_REV0 0x1b02 +#define MT6357_LDO_GOFF2_DSN_DBI 0x1b04 +#define MT6357_LDO_GOFF2_DSN_DXI 0x1b06 +#define MT6357_LDO_VIBR_CON0 0x1b08 +#define MT6357_LDO_VIBR_OP_EN 0x1b0a +#define MT6357_LDO_VIBR_OP_EN_SET 0x1b0c +#define MT6357_LDO_VIBR_OP_EN_CLR 0x1b0e +#define MT6357_LDO_VIBR_OP_CFG 0x1b10 +#define MT6357_LDO_VIBR_OP_CFG_SET 0x1b12 +#define MT6357_LDO_VIBR_OP_CFG_CLR 0x1b14 +#define MT6357_LDO_VIBR_CON1 0x1b16 +#define MT6357_LDO_VIBR_CON2 0x1b18 +#define MT6357_LDO_VIBR_CON3 0x1b1a +#define MT6357_LDO_VCN33_CON0_0 0x1b1c +#define MT6357_LDO_VCN33_OP_EN 0x1b1e +#define MT6357_LDO_VCN33_OP_EN_SET 0x1b20 +#define MT6357_LDO_VCN33_OP_EN_CLR 0x1b22 +#define MT6357_LDO_VCN33_OP_CFG 0x1b24 +#define MT6357_LDO_VCN33_OP_CFG_SET 0x1b26 +#define MT6357_LDO_VCN33_OP_CFG_CLR 0x1b28 +#define MT6357_LDO_VCN33_CON0_1 0x1b2a +#define MT6357_LDO_VCN33_CON1 0x1b2c +#define MT6357_LDO_VCN33_CON2 0x1b2e +#define MT6357_LDO_VCN33_CON3 0x1b30 +#define MT6357_LDO_VLDO28_CON0_0 0x1b32 +#define MT6357_LDO_VLDO28_OP_EN 0x1b34 +#define MT6357_LDO_VLDO28_OP_EN_SET 0x1b36 +#define MT6357_LDO_VLDO28_OP_EN_CLR 0x1b38 +#define MT6357_LDO_VLDO28_OP_CFG 0x1b3a +#define MT6357_LDO_VLDO28_OP_CFG_SET 0x1b3c +#define MT6357_LDO_VLDO28_OP_CFG_CLR 0x1b3e +#define MT6357_LDO_VLDO28_CON0_1 0x1b40 +#define MT6357_LDO_VLDO28_CON1 0x1b42 +#define MT6357_LDO_VLDO28_CON2 0x1b44 +#define MT6357_LDO_VLDO28_CON3 0x1b46 +#define MT6357_LDO_GOFF2_RSV_CON0 0x1b48 +#define MT6357_LDO_GOFF2_RSV_CON1 0x1b4a +#define MT6357_LDO_GOFF3_DSN_ID 0x1b80 +#define MT6357_LDO_GOFF3_DSN_REV0 0x1b82 +#define MT6357_LDO_GOFF3_DSN_DBI 0x1b84 +#define MT6357_LDO_GOFF3_DSN_DXI 0x1b86 +#define MT6357_LDO_VCN28_CON0 0x1b88 +#define MT6357_LDO_VCN28_OP_EN 0x1b8a +#define MT6357_LDO_VCN28_OP_EN_SET 0x1b8c +#define MT6357_LDO_VCN28_OP_EN_CLR 0x1b8e +#define MT6357_LDO_VCN28_OP_CFG 0x1b90 +#define MT6357_LDO_VCN28_OP_CFG_SET 0x1b92 +#define MT6357_LDO_VCN28_OP_CFG_CLR 0x1b94 +#define MT6357_LDO_VCN28_CON1 0x1b96 +#define MT6357_LDO_VCN28_CON2 0x1b98 +#define MT6357_LDO_VCN28_CON3 0x1b9a +#define MT6357_VRTC_CON0 0x1b9c +#define MT6357_LDO_TREF_CON0 0x1b9e +#define MT6357_LDO_TREF_OP_EN 0x1ba0 +#define MT6357_LDO_TREF_OP_EN_SET 0x1ba2 +#define MT6357_LDO_TREF_OP_EN_CLR 0x1ba4 +#define MT6357_LDO_TREF_OP_CFG 0x1ba6 +#define MT6357_LDO_TREF_OP_CFG_SET 0x1ba8 +#define MT6357_LDO_TREF_OP_CFG_CLR 0x1baa +#define MT6357_LDO_TREF_CON1 0x1bac +#define MT6357_LDO_GOFF3_RSV_CON0 0x1bae +#define MT6357_LDO_GOFF3_RSV_CON1 0x1bb0 +#define MT6357_LDO_ANA0_DSN_ID 0x1c00 +#define MT6357_LDO_ANA0_DSN_REV0 0x1c02 +#define MT6357_LDO_ANA0_DSN_DBI 0x1c04 +#define MT6357_LDO_ANA0_DSN_DXI 0x1c06 +#define MT6357_VFE28_ANA_CON0 0x1c08 +#define MT6357_VFE28_ANA_CON1 0x1c0a +#define MT6357_VCN28_ANA_CON0 0x1c0c +#define MT6357_VCN28_ANA_CON1 0x1c0e +#define MT6357_VAUD28_ANA_CON0 0x1c10 +#define MT6357_VAUD28_ANA_CON1 0x1c12 +#define MT6357_VAUX18_ANA_CON0 0x1c14 +#define MT6357_VAUX18_ANA_CON1 0x1c16 +#define MT6357_VXO22_ANA_CON0 0x1c18 +#define MT6357_VXO22_ANA_CON1 0x1c1a +#define MT6357_VCN33_ANA_CON0 0x1c1c +#define MT6357_VCN33_ANA_CON1 0x1c1e +#define MT6357_VEMC_ANA_CON0 0x1c20 +#define MT6357_VEMC_ANA_CON1 0x1c22 +#define MT6357_VLDO28_ANA_CON0 0x1c24 +#define MT6357_VLDO28_ANA_CON1 0x1c26 +#define MT6357_VIO28_ANA_CON0 0x1c28 +#define MT6357_VIO28_ANA_CON1 0x1c2a +#define MT6357_VIBR_ANA_CON0 0x1c2c +#define MT6357_VIBR_ANA_CON1 0x1c2e +#define MT6357_VSIM1_ANA_CON0 0x1c30 +#define MT6357_VSIM1_ANA_CON1 0x1c32 +#define MT6357_VSIM2_ANA_CON0 0x1c34 +#define MT6357_VSIM2_ANA_CON1 0x1c36 +#define MT6357_VMCH_ANA_CON0 0x1c38 +#define MT6357_VMCH_ANA_CON1 0x1c3a +#define MT6357_VMC_ANA_CON0 0x1c3c +#define MT6357_VMC_ANA_CON1 0x1c3e +#define MT6357_VCAMIO_ANA_CON0 0x1c40 +#define MT6357_VCAMIO_ANA_CON1 0x1c42 +#define MT6357_VCN18_ANA_CON0 0x1c44 +#define MT6357_VCN18_ANA_CON1 0x1c46 +#define MT6357_VRF18_ANA_CON0 0x1c48 +#define MT6357_VRF18_ANA_CON1 0x1c4a +#define MT6357_VIO18_ANA_CON0 0x1c4c +#define MT6357_VIO18_ANA_CON1 0x1c4e +#define MT6357_VDRAM_ANA_CON1 0x1c50 +#define MT6357_VRF12_ANA_CON0 0x1c52 +#define MT6357_VRF12_ANA_CON1 0x1c54 +#define MT6357_VSRAM_PROC_ANA_CON0 0x1c56 +#define MT6357_VSRAM_OTHERS_ANA_CON0 0x1c58 +#define MT6357_LDO_ANA0_ELR_NUM 0x1c5a +#define MT6357_VFE28_ELR_0 0x1c5c +#define MT6357_VCN28_ELR_0 0x1c5e +#define MT6357_VAUD28_ELR_0 0x1c60 +#define MT6357_VAUX18_ELR_0 0x1c62 +#define MT6357_VXO22_ELR_0 0x1c64 +#define MT6357_VCN33_ELR_0 0x1c66 +#define MT6357_VEMC_ELR_0 0x1c68 +#define MT6357_VLDO28_ELR_0 0x1c6a +#define MT6357_VIO28_ELR_0 0x1c6c +#define MT6357_VIBR_ELR_0 0x1c6e +#define MT6357_VSIM1_ELR_0 0x1c70 +#define MT6357_VSIM2_ELR_0 0x1c72 +#define MT6357_VMCH_ELR_0 0x1c74 +#define MT6357_VMC_ELR_0 0x1c76 +#define MT6357_VCAMIO_ELR_0 0x1c78 +#define MT6357_VCN18_ELR_0 0x1c7a +#define MT6357_VRF18_ELR_0 0x1c7c +#define MT6357_LDO_ANA1_DSN_ID 0x1c80 +#define MT6357_LDO_ANA1_DSN_REV0 0x1c82 +#define MT6357_LDO_ANA1_DSN_DBI 0x1c84 +#define MT6357_LDO_ANA1_DSN_DXI 0x1c86 +#define MT6357_VUSB33_ANA_CON0 0x1c88 +#define MT6357_VUSB33_ANA_CON1 0x1c8a +#define MT6357_VCAMA_ANA_CON0 0x1c8c +#define MT6357_VCAMA_ANA_CON1 0x1c8e +#define MT6357_VEFUSE_ANA_CON0 0x1c90 +#define MT6357_VEFUSE_ANA_CON1 0x1c92 +#define MT6357_VCAMD_ANA_CON0 0x1c94 +#define MT6357_VCAMD_ANA_CON1 0x1c96 +#define MT6357_LDO_ANA1_ELR_NUM 0x1c98 +#define MT6357_VUSB33_ELR_0 0x1c9a +#define MT6357_VCAMA_ELR_0 0x1c9c +#define MT6357_VEFUSE_ELR_0 0x1c9e +#define MT6357_VCAMD_ELR_0 0x1ca0 +#define MT6357_VIO18_ELR_0 0x1ca2 +#define MT6357_VDRAM_ELR_0 0x1ca4 +#define MT6357_VRF12_ELR_0 0x1ca6 +#define MT6357_VRTC_ELR_0 0x1ca8 +#define MT6357_VDRAM_ELR_1 0x1caa +#define MT6357_VDRAM_ELR_2 0x1cac +#define MT6357_XPP_TOP_ID 0x1e00 +#define MT6357_XPP_TOP_REV0 0x1e02 +#define MT6357_XPP_TOP_DBI 0x1e04 +#define MT6357_XPP_TOP_DXI 0x1e06 +#define MT6357_XPP_TPM0 0x1e08 +#define MT6357_XPP_TPM1 0x1e0a +#define MT6357_XPP_TOP_TEST_OUT 0x1e0c +#define MT6357_XPP_TOP_TEST_CON0 0x1e0e +#define MT6357_XPP_TOP_CKPDN_CON0 0x1e10 +#define MT6357_XPP_TOP_CKPDN_CON0_SET 0x1e12 +#define MT6357_XPP_TOP_CKPDN_CON0_CLR 0x1e14 +#define MT6357_XPP_TOP_CKSEL_CON0 0x1e16 +#define MT6357_XPP_TOP_CKSEL_CON0_SET 0x1e18 +#define MT6357_XPP_TOP_CKSEL_CON0_CLR 0x1e1a +#define MT6357_XPP_TOP_RST_CON0 0x1e1c +#define MT6357_XPP_TOP_RST_CON0_SET 0x1e1e +#define MT6357_XPP_TOP_RST_CON0_CLR 0x1e20 +#define MT6357_XPP_TOP_RST_BANK_CON0 0x1e22 +#define MT6357_XPP_TOP_RST_BANK_CON0_SET 0x1e24 +#define MT6357_XPP_TOP_RST_BANK_CON0_CLR 0x1e26 +#define MT6357_DRIVER_BL_DSN_ID 0x1e80 +#define MT6357_DRIVER_BL_DSN_REV0 0x1e82 +#define MT6357_DRIVER_BL_DSN_DBI 0x1e84 +#define MT6357_DRIVER_BL_DSN_DXI 0x1e86 +#define MT6357_ISINK1_CON0 0x1e88 +#define MT6357_ISINK1_CON1 0x1e8a +#define MT6357_ISINK1_CON2 0x1e8c +#define MT6357_ISINK1_CON3 0x1e8e +#define MT6357_ISINK_ANA1 0x1e90 +#define MT6357_ISINK_PHASE_DLY 0x1e92 +#define MT6357_ISINK_SFSTR 0x1e94 +#define MT6357_ISINK_EN_CTRL 0x1e96 +#define MT6357_ISINK_MODE_CTRL 0x1e98 +#define MT6357_DRIVER_ANA_CON0 0x1e9a +#define MT6357_ISINK_ANA_CON0 0x1e9c +#define MT6357_ISINK_ANA_CON1 0x1e9e +#define MT6357_DRIVER_BL_ELR_NUM 0x1ea0 +#define MT6357_DRIVER_BL_ELR_0 0x1ea2 +#define MT6357_DRIVER_CI_DSN_ID 0x1f00 +#define MT6357_DRIVER_CI_DSN_REV0 0x1f02 +#define MT6357_DRIVER_CI_DSN_DBI 0x1f04 +#define MT6357_DRIVER_CI_DSN_DXI 0x1f06 +#define MT6357_CHRIND_CON0 0x1f08 +#define MT6357_CHRIND_CON1 0x1f0a +#define MT6357_CHRIND_CON2 0x1f0c +#define MT6357_CHRIND_CON3 0x1f0e +#define MT6357_CHRIND_CON4 0x1f10 +#define MT6357_CHRIND_EN_CTRL 0x1f12 +#define MT6357_CHRIND_ANA_CON0 0x1f14 +#define MT6357_DRIVER_DL_DSN_ID 0x1f80 +#define MT6357_DRIVER_DL_DSN_REV0 0x1f82 +#define MT6357_DRIVER_DL_DSN_DBI 0x1f84 +#define MT6357_DRIVER_DL_DSN_DXI 0x1f86 +#define MT6357_ISINK2_CON0 0x1f88 +#define MT6357_ISINK3_CON0 0x1f8a +#define MT6357_ISINK_EN_CTRL_SMPL 0x1f8c +#define MT6357_AUD_TOP_ID 0x2080 +#define MT6357_AUD_TOP_REV0 0x2082 +#define MT6357_AUD_TOP_DBI 0x2084 +#define MT6357_AUD_TOP_DXI 0x2086 +#define MT6357_AUD_TOP_CKPDN_TPM0 0x2088 +#define MT6357_AUD_TOP_CKPDN_TPM1 0x208a +#define MT6357_AUD_TOP_CKPDN_CON0 0x208c +#define MT6357_AUD_TOP_CKPDN_CON0_SET 0x208e +#define MT6357_AUD_TOP_CKPDN_CON0_CLR 0x2090 +#define MT6357_AUD_TOP_CKSEL_CON0 0x2092 +#define MT6357_AUD_TOP_CKSEL_CON0_SET 0x2094 +#define MT6357_AUD_TOP_CKSEL_CON0_CLR 0x2096 +#define MT6357_AUD_TOP_CKTST_CON0 0x2098 +#define MT6357_AUD_TOP_RST_CON0 0x209a +#define MT6357_AUD_TOP_RST_CON0_SET 0x209c +#define MT6357_AUD_TOP_RST_CON0_CLR 0x209e +#define MT6357_AUD_TOP_RST_BANK_CON0 0x20a0 +#define MT6357_AUD_TOP_INT_CON0 0x20a2 +#define MT6357_AUD_TOP_INT_CON0_SET 0x20a4 +#define MT6357_AUD_TOP_INT_CON0_CLR 0x20a6 +#define MT6357_AUD_TOP_INT_MASK_CON0 0x20a8 +#define MT6357_AUD_TOP_INT_MASK_CON0_SET 0x20aa +#define MT6357_AUD_TOP_INT_MASK_CON0_CLR 0x20ac +#define MT6357_AUD_TOP_INT_STATUS0 0x20ae +#define MT6357_AUD_TOP_INT_RAW_STATUS0 0x20b0 +#define MT6357_AUD_TOP_INT_MISC_CON0 0x20b2 +#define MT6357_AUDNCP_CLKDIV_CON0 0x20b4 +#define MT6357_AUDNCP_CLKDIV_CON1 0x20b6 +#define MT6357_AUDNCP_CLKDIV_CON2 0x20b8 +#define MT6357_AUDNCP_CLKDIV_CON3 0x20ba +#define MT6357_AUDNCP_CLKDIV_CON4 0x20bc +#define MT6357_AUD_TOP_MON_CON0 0x20be +#define MT6357_AUDIO_DIG_DSN_ID 0x2100 +#define MT6357_AUDIO_DIG_DSN_REV0 0x2102 +#define MT6357_AUDIO_DIG_DSN_DBI 0x2104 +#define MT6357_AUDIO_DIG_DSN_DXI 0x2106 +#define MT6357_AFE_UL_DL_CON0 0x2108 +#define MT6357_AFE_DL_SRC2_CON0_L 0x210a +#define MT6357_AFE_UL_SRC_CON0_H 0x210c +#define MT6357_AFE_UL_SRC_CON0_L 0x210e +#define MT6357_AFE_TOP_CON0 0x2110 +#define MT6357_AUDIO_TOP_CON0 0x2112 +#define MT6357_AFE_MON_DEBUG0 0x2114 +#define MT6357_AFUNC_AUD_CON0 0x2116 +#define MT6357_AFUNC_AUD_CON1 0x2118 +#define MT6357_AFUNC_AUD_CON2 0x211a +#define MT6357_AFUNC_AUD_CON3 0x211c +#define MT6357_AFUNC_AUD_CON4 0x211e +#define MT6357_AFUNC_AUD_CON5 0x2120 +#define MT6357_AFUNC_AUD_CON6 0x2122 +#define MT6357_AFUNC_AUD_MON0 0x2124 +#define MT6357_AUDRC_TUNE_MON0 0x2126 +#define MT6357_AFE_ADDA_MTKAIF_FIFO_CFG0 0x2128 +#define MT6357_AFE_ADDA_MTKAIF_FIFO_LOG_MON1 0x212a +#define MT6357_AFE_ADDA_MTKAIF_MON0 0x212c +#define MT6357_AFE_ADDA_MTKAIF_MON1 0x212e +#define MT6357_AFE_ADDA_MTKAIF_MON2 0x2130 +#define MT6357_AFE_ADDA_MTKAIF_MON3 0x2132 +#define MT6357_AFE_ADDA_MTKAIF_CFG0 0x2134 +#define MT6357_AFE_ADDA_MTKAIF_RX_CFG0 0x2136 +#define MT6357_AFE_ADDA_MTKAIF_RX_CFG1 0x2138 +#define MT6357_AFE_ADDA_MTKAIF_RX_CFG2 0x213a +#define MT6357_AFE_ADDA_MTKAIF_RX_CFG3 0x213c +#define MT6357_AFE_ADDA_MTKAIF_TX_CFG1 0x213e +#define MT6357_AFE_SGEN_CFG0 0x2140 +#define MT6357_AFE_SGEN_CFG1 0x2142 +#define MT6357_AFE_ADC_ASYNC_FIFO_CFG 0x2144 +#define MT6357_AFE_DCCLK_CFG0 0x2146 +#define MT6357_AFE_DCCLK_CFG1 0x2148 +#define MT6357_AUDIO_DIG_CFG 0x214a +#define MT6357_AFE_AUD_PAD_TOP 0x214c +#define MT6357_AFE_AUD_PAD_TOP_MON 0x214e +#define MT6357_AFE_AUD_PAD_TOP_MON1 0x2150 +#define MT6357_AUDENC_DSN_ID 0x2180 +#define MT6357_AUDENC_DSN_REV0 0x2182 +#define MT6357_AUDENC_DSN_DBI 0x2184 +#define MT6357_AUDENC_DSN_FPI 0x2186 +#define MT6357_AUDENC_ANA_CON0 0x2188 +#define MT6357_AUDENC_ANA_CON1 0x218a +#define MT6357_AUDENC_ANA_CON2 0x218c +#define MT6357_AUDENC_ANA_CON3 0x218e +#define MT6357_AUDENC_ANA_CON4 0x2190 +#define MT6357_AUDENC_ANA_CON5 0x2192 +#define MT6357_AUDENC_ANA_CON6 0x2194 +#define MT6357_AUDENC_ANA_CON7 0x2196 +#define MT6357_AUDENC_ANA_CON8 0x2198 +#define MT6357_AUDENC_ANA_CON9 0x219a +#define MT6357_AUDENC_ANA_CON10 0x219c +#define MT6357_AUDENC_ANA_CON11 0x219e +#define MT6357_AUDDEC_DSN_ID 0x2200 +#define MT6357_AUDDEC_DSN_REV0 0x2202 +#define MT6357_AUDDEC_DSN_DBI 0x2204 +#define MT6357_AUDDEC_DSN_FPI 0x2206 +#define MT6357_AUDDEC_ANA_CON0 0x2208 +#define MT6357_AUDDEC_ANA_CON1 0x220a +#define MT6357_AUDDEC_ANA_CON2 0x220c +#define MT6357_AUDDEC_ANA_CON3 0x220e +#define MT6357_AUDDEC_ANA_CON4 0x2210 +#define MT6357_AUDDEC_ANA_CON5 0x2212 +#define MT6357_AUDDEC_ANA_CON6 0x2214 +#define MT6357_AUDDEC_ANA_CON7 0x2216 +#define MT6357_AUDDEC_ANA_CON8 0x2218 +#define MT6357_AUDDEC_ANA_CON9 0x221a +#define MT6357_AUDDEC_ANA_CON10 0x221c +#define MT6357_AUDDEC_ANA_CON11 0x221e +#define MT6357_AUDDEC_ANA_CON12 0x2220 +#define MT6357_AUDDEC_ANA_CON13 0x2222 +#define MT6357_AUDDEC_ELR_NUM 0x2224 +#define MT6357_AUDDEC_ELR_0 0x2226 +#define MT6357_AUDZCD_DSN_ID 0x2280 +#define MT6357_AUDZCD_DSN_REV0 0x2282 +#define MT6357_AUDZCD_DSN_DBI 0x2284 +#define MT6357_AUDZCD_DSN_FPI 0x2286 +#define MT6357_ZCD_CON0 0x2288 +#define MT6357_ZCD_CON1 0x228a +#define MT6357_ZCD_CON2 0x228c +#define MT6357_ZCD_CON3 0x228e +#define MT6357_ZCD_CON4 0x2290 +#define MT6357_ZCD_CON5 0x2292 +#define MT6357_ACCDET_DSN_DIG_ID 0x2300 +#define MT6357_ACCDET_DSN_DIG_REV0 0x2302 +#define MT6357_ACCDET_DSN_DBI 0x2304 +#define MT6357_ACCDET_DSN_FPI 0x2306 +#define MT6357_ACCDET_CON0 0x2308 +#define MT6357_ACCDET_CON1 0x230a +#define MT6357_ACCDET_CON2 0x230c +#define MT6357_ACCDET_CON3 0x230e +#define MT6357_ACCDET_CON4 0x2310 +#define MT6357_ACCDET_CON5 0x2312 +#define MT6357_ACCDET_CON6 0x2314 +#define MT6357_ACCDET_CON7 0x2316 +#define MT6357_ACCDET_CON8 0x2318 +#define MT6357_ACCDET_CON9 0x231a +#define MT6357_ACCDET_CON10 0x231c +#define MT6357_ACCDET_CON11 0x231e +#define MT6357_ACCDET_CON12 0x2320 +#define MT6357_ACCDET_CON13 0x2322 +#define MT6357_ACCDET_CON14 0x2324 +#define MT6357_ACCDET_CON15 0x2326 +#define MT6357_ACCDET_CON16 0x2328 +#define MT6357_ACCDET_CON17 0x232a +#define MT6357_ACCDET_CON18 0x232c +#define MT6357_ACCDET_CON19 0x232e +#define MT6357_ACCDET_CON20 0x2330 +#define MT6357_ACCDET_CON21 0x2332 +#define MT6357_ACCDET_CON22 0x2334 +#define MT6357_ACCDET_CON23 0x2336 +#define MT6357_ACCDET_CON24 0x2338 +#define MT6357_ACCDET_CON25 0x233a +#define MT6357_ACCDET_CON26 0x233c +#define MT6357_ACCDET_CON27 0x233e +#define MT6357_ACCDET_CON28 0x2340 + +#endif /* __MFD_MT6357_REGISTERS_H__ */ diff --git a/include/linux/mfd/mt6358/registers.h b/include/linux/mfd/mt6358/registers.h index 201139b12140..3d33517f178c 100644 --- a/include/linux/mfd/mt6358/registers.h +++ b/include/linux/mfd/mt6358/registers.h @@ -94,6 +94,10 @@ #define MT6358_BUCK_VCORE_CON0 0x1488 #define MT6358_BUCK_VCORE_DBG0 0x149e #define MT6358_BUCK_VCORE_DBG1 0x14a0 +#define MT6358_BUCK_VCORE_SSHUB_CON0 0x14a4 +#define MT6358_BUCK_VCORE_SSHUB_CON1 0x14a6 +#define MT6358_BUCK_VCORE_SSHUB_ELR0 MT6358_BUCK_VCORE_SSHUB_CON1 +#define MT6358_BUCK_VCORE_SSHUB_DBG1 MT6358_BUCK_VCORE_DBG1 #define MT6358_BUCK_VCORE_ELR0 0x14aa #define MT6358_BUCK_VGPU_CON0 0x1508 #define MT6358_BUCK_VGPU_DBG0 0x151e @@ -169,6 +173,9 @@ #define MT6358_LDO_VSRAM_OTHERS_CON0 0x1ba6 #define MT6358_LDO_VSRAM_OTHERS_DBG0 0x1bc0 #define MT6358_LDO_VSRAM_OTHERS_DBG1 0x1bc2 +#define MT6358_LDO_VSRAM_OTHERS_SSHUB_CON0 0x1bc4 +#define MT6358_LDO_VSRAM_OTHERS_SSHUB_CON1 0x1bc6 +#define MT6358_LDO_VSRAM_OTHERS_SSHUB_DBG1 MT6358_LDO_VSRAM_OTHERS_DBG1 #define MT6358_LDO_VSRAM_GPU_CON0 0x1bc8 #define MT6358_LDO_VSRAM_GPU_DBG0 0x1be2 #define MT6358_LDO_VSRAM_GPU_DBG1 0x1be4 diff --git a/include/linux/mfd/mt6359/registers.h b/include/linux/mfd/mt6359/registers.h index 2135c9695918..2a4394a27b1c 100644 --- a/include/linux/mfd/mt6359/registers.h +++ b/include/linux/mfd/mt6359/registers.h @@ -8,6 +8,8 @@ /* PMIC Registers */ #define MT6359_SWCID 0xa +#define MT6359_TOPSTATUS 0x2a +#define MT6359_TOP_RST_MISC 0x14c #define MT6359_MISC_TOP_INT_CON0 0x188 #define MT6359_MISC_TOP_INT_STATUS0 0x194 #define MT6359_TOP_INT_STATUS0 0x19e diff --git a/include/linux/mfd/mt6397/core.h b/include/linux/mfd/mt6397/core.h index 56f210eebc54..627487e26287 100644 --- a/include/linux/mfd/mt6397/core.h +++ b/include/linux/mfd/mt6397/core.h @@ -12,8 +12,12 @@ enum chip_id { MT6323_CHIP_ID = 0x23, + MT6331_CHIP_ID = 0x20, + MT6332_CHIP_ID = 0x20, + MT6357_CHIP_ID = 0x57, MT6358_CHIP_ID = 0x58, MT6359_CHIP_ID = 0x59, + MT6366_CHIP_ID = 0x66, MT6391_CHIP_ID = 0x91, MT6397_CHIP_ID = 0x97, }; diff --git a/include/linux/mfd/ocelot.h b/include/linux/mfd/ocelot.h new file mode 100644 index 000000000000..dd72073d2d4f --- /dev/null +++ b/include/linux/mfd/ocelot.h @@ -0,0 +1,62 @@ +/* SPDX-License-Identifier: GPL-2.0 OR MIT */ +/* Copyright 2022 Innovative Advantage Inc. */ + +#ifndef _LINUX_MFD_OCELOT_H +#define _LINUX_MFD_OCELOT_H + +#include <linux/err.h> +#include <linux/errno.h> +#include <linux/ioport.h> +#include <linux/platform_device.h> +#include <linux/regmap.h> +#include <linux/types.h> + +struct resource; + +static inline struct regmap * +ocelot_regmap_from_resource_optional(struct platform_device *pdev, + unsigned int index, + const struct regmap_config *config) +{ + struct device *dev = &pdev->dev; + struct resource *res; + void __iomem *regs; + + /* + * Don't use _get_and_ioremap_resource() here, since that will invoke + * prints of "invalid resource" which will simply add confusion. + */ + res = platform_get_resource(pdev, IORESOURCE_MEM, index); + if (res) { + regs = devm_ioremap_resource(dev, res); + if (IS_ERR(regs)) + return ERR_CAST(regs); + return devm_regmap_init_mmio(dev, regs, config); + } + + /* + * Fall back to using REG and getting the resource from the parent + * device, which is possible in an MFD configuration + */ + if (dev->parent) { + res = platform_get_resource(pdev, IORESOURCE_REG, index); + if (!res) + return NULL; + + return dev_get_regmap(dev->parent, res->name); + } + + return NULL; +} + +static inline struct regmap * +ocelot_regmap_from_resource(struct platform_device *pdev, unsigned int index, + const struct regmap_config *config) +{ + struct regmap *map; + + map = ocelot_regmap_from_resource_optional(pdev, index, config); + return map ?: ERR_PTR(-ENOENT); +} + +#endif diff --git a/include/linux/mfd/rk808.h b/include/linux/mfd/rk808.h index a96e6d43ca06..9af1f3105f80 100644 --- a/include/linux/mfd/rk808.h +++ b/include/linux/mfd/rk808.h @@ -373,6 +373,7 @@ enum rk805_reg { #define SWITCH2_EN BIT(6) #define SWITCH1_EN BIT(5) #define DEV_OFF_RST BIT(3) +#define DEV_RST BIT(2) #define DEV_OFF BIT(0) #define RTC_STOP BIT(0) @@ -518,6 +519,77 @@ enum rk809_reg_id { #define MIC_DIFF_DIS (0x0 << 7) #define MIC_DIFF_EN (0x1 << 7) +/* RK817 Battery Registers */ +#define RK817_GAS_GAUGE_ADC_CONFIG0 0x50 +#define RK817_GG_EN (0x1 << 7) +#define RK817_SYS_VOL_ADC_EN (0x1 << 6) +#define RK817_TS_ADC_EN (0x1 << 5) +#define RK817_USB_VOL_ADC_EN (0x1 << 4) +#define RK817_BAT_VOL_ADC_EN (0x1 << 3) +#define RK817_BAT_CUR_ADC_EN (0x1 << 2) + +#define RK817_GAS_GAUGE_ADC_CONFIG1 0x55 + +#define RK817_VOL_CUR_CALIB_UPD BIT(7) + +#define RK817_GAS_GAUGE_GG_CON 0x56 +#define RK817_GAS_GAUGE_GG_STS 0x57 + +#define RK817_BAT_CON (0x1 << 4) +#define RK817_RELAX_VOL_UPD (0x3 << 2) +#define RK817_RELAX_STS (0x1 << 1) + +#define RK817_GAS_GAUGE_RELAX_THRE_H 0x58 +#define RK817_GAS_GAUGE_RELAX_THRE_L 0x59 +#define RK817_GAS_GAUGE_OCV_THRE_VOL 0x62 +#define RK817_GAS_GAUGE_OCV_VOL_H 0x63 +#define RK817_GAS_GAUGE_OCV_VOL_L 0x64 +#define RK817_GAS_GAUGE_PWRON_VOL_H 0x6b +#define RK817_GAS_GAUGE_PWRON_VOL_L 0x6c +#define RK817_GAS_GAUGE_PWRON_CUR_H 0x6d +#define RK817_GAS_GAUGE_PWRON_CUR_L 0x6e +#define RK817_GAS_GAUGE_OFF_CNT 0x6f +#define RK817_GAS_GAUGE_Q_INIT_H3 0x70 +#define RK817_GAS_GAUGE_Q_INIT_H2 0x71 +#define RK817_GAS_GAUGE_Q_INIT_L1 0x72 +#define RK817_GAS_GAUGE_Q_INIT_L0 0x73 +#define RK817_GAS_GAUGE_Q_PRES_H3 0x74 +#define RK817_GAS_GAUGE_Q_PRES_H2 0x75 +#define RK817_GAS_GAUGE_Q_PRES_L1 0x76 +#define RK817_GAS_GAUGE_Q_PRES_L0 0x77 +#define RK817_GAS_GAUGE_BAT_VOL_H 0x78 +#define RK817_GAS_GAUGE_BAT_VOL_L 0x79 +#define RK817_GAS_GAUGE_BAT_CUR_H 0x7a +#define RK817_GAS_GAUGE_BAT_CUR_L 0x7b +#define RK817_GAS_GAUGE_USB_VOL_H 0x7e +#define RK817_GAS_GAUGE_USB_VOL_L 0x7f +#define RK817_GAS_GAUGE_SYS_VOL_H 0x80 +#define RK817_GAS_GAUGE_SYS_VOL_L 0x81 +#define RK817_GAS_GAUGE_Q_MAX_H3 0x82 +#define RK817_GAS_GAUGE_Q_MAX_H2 0x83 +#define RK817_GAS_GAUGE_Q_MAX_L1 0x84 +#define RK817_GAS_GAUGE_Q_MAX_L0 0x85 +#define RK817_GAS_GAUGE_SLEEP_CON_SAMP_CUR_H 0x8f +#define RK817_GAS_GAUGE_SLEEP_CON_SAMP_CUR_L 0x90 +#define RK817_GAS_GAUGE_CAL_OFFSET_H 0x91 +#define RK817_GAS_GAUGE_CAL_OFFSET_L 0x92 +#define RK817_GAS_GAUGE_VCALIB0_H 0x93 +#define RK817_GAS_GAUGE_VCALIB0_L 0x94 +#define RK817_GAS_GAUGE_VCALIB1_H 0x95 +#define RK817_GAS_GAUGE_VCALIB1_L 0x96 +#define RK817_GAS_GAUGE_IOFFSET_H 0x97 +#define RK817_GAS_GAUGE_IOFFSET_L 0x98 +#define RK817_GAS_GAUGE_BAT_R1 0x9a +#define RK817_GAS_GAUGE_BAT_R2 0x9b +#define RK817_GAS_GAUGE_BAT_R3 0x9c +#define RK817_GAS_GAUGE_DATA0 0x9d +#define RK817_GAS_GAUGE_DATA1 0x9e +#define RK817_GAS_GAUGE_DATA2 0x9f +#define RK817_GAS_GAUGE_DATA3 0xa0 +#define RK817_GAS_GAUGE_DATA4 0xa1 +#define RK817_GAS_GAUGE_DATA5 0xa2 +#define RK817_GAS_GAUGE_CUR_ADC_K0 0xb0 + #define RK817_POWER_EN_REG(i) (0xb1 + (i)) #define RK817_POWER_SLP_EN_REG(i) (0xb5 + (i)) @@ -543,10 +615,30 @@ enum rk809_reg_id { #define RK817_LDO_ON_VSEL_REG(idx) (0xcc + (idx) * 2) #define RK817_BOOST_OTG_CFG (0xde) +#define RK817_PMIC_CHRG_OUT 0xe4 +#define RK817_CHRG_VOL_SEL (0x07 << 4) +#define RK817_CHRG_CUR_SEL (0x07 << 0) + +#define RK817_PMIC_CHRG_IN 0xe5 +#define RK817_USB_VLIM_EN (0x01 << 7) +#define RK817_USB_VLIM_SEL (0x07 << 4) +#define RK817_USB_ILIM_EN (0x01 << 3) +#define RK817_USB_ILIM_SEL (0x07 << 0) +#define RK817_PMIC_CHRG_TERM 0xe6 +#define RK817_CHRG_TERM_ANA_DIG (0x01 << 2) +#define RK817_CHRG_TERM_ANA_SEL (0x03 << 0) +#define RK817_CHRG_EN (0x01 << 6) + +#define RK817_PMIC_CHRG_STS 0xeb +#define RK817_BAT_EXS BIT(7) +#define RK817_CHG_STS (0x07 << 4) + #define RK817_ID_MSB 0xed #define RK817_ID_LSB 0xee #define RK817_SYS_STS 0xf0 +#define RK817_PLUG_IN_STS (0x1 << 6) + #define RK817_SYS_CFG(i) (0xf1 + (i)) #define RK817_ON_SOURCE_REG 0xf5 diff --git a/include/linux/mfd/sy7636a.h b/include/linux/mfd/sy7636a.h new file mode 100644 index 000000000000..22f03b2f851e --- /dev/null +++ b/include/linux/mfd/sy7636a.h @@ -0,0 +1,34 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Functions to access SY3686A power management chip. + * + * Copyright (C) 2021 reMarkable AS - http://www.remarkable.com/ + */ + +#ifndef __MFD_SY7636A_H +#define __MFD_SY7636A_H + +#define SY7636A_REG_OPERATION_MODE_CRL 0x00 +/* It is set if a gpio is used to control the regulator */ +#define SY7636A_OPERATION_MODE_CRL_VCOMCTL BIT(6) +#define SY7636A_OPERATION_MODE_CRL_ONOFF BIT(7) +#define SY7636A_REG_VCOM_ADJUST_CTRL_L 0x01 +#define SY7636A_REG_VCOM_ADJUST_CTRL_H 0x02 +#define SY7636A_REG_VCOM_ADJUST_CTRL_MASK 0x01ff +#define SY7636A_REG_VLDO_VOLTAGE_ADJULST_CTRL 0x03 +#define SY7636A_REG_POWER_ON_DELAY_TIME 0x06 +#define SY7636A_REG_FAULT_FLAG 0x07 +#define SY7636A_FAULT_FLAG_PG BIT(0) +#define SY7636A_REG_TERMISTOR_READOUT 0x08 + +#define SY7636A_REG_MAX 0x08 + +#define VCOM_ADJUST_CTRL_MASK 0x1ff +// Used to shift the high byte +#define VCOM_ADJUST_CTRL_SHIFT 8 +// Used to scale from VCOM_ADJUST_CTRL to mv +#define VCOM_ADJUST_CTRL_SCAL 10000 + +#define FAULT_FLAG_SHIFT 1 + +#endif /* __LINUX_MFD_SY7636A_H */ diff --git a/include/linux/mfd/t7l66xb.h b/include/linux/mfd/t7l66xb.h index 69632c1b07bd..ae3e7a5c5219 100644 --- a/include/linux/mfd/t7l66xb.h +++ b/include/linux/mfd/t7l66xb.h @@ -12,7 +12,6 @@ struct t7l66xb_platform_data { int (*enable)(struct platform_device *dev); - int (*disable)(struct platform_device *dev); int (*suspend)(struct platform_device *dev); int (*resume)(struct platform_device *dev); diff --git a/include/linux/mfd/tc6387xb.h b/include/linux/mfd/tc6387xb.h index b4888209494a..aacf1dcc86b9 100644 --- a/include/linux/mfd/tc6387xb.h +++ b/include/linux/mfd/tc6387xb.h @@ -12,7 +12,6 @@ struct tc6387xb_platform_data { int (*enable)(struct platform_device *dev); - int (*disable)(struct platform_device *dev); int (*suspend)(struct platform_device *dev); int (*resume)(struct platform_device *dev); }; diff --git a/include/linux/mfd/tc6393xb.h b/include/linux/mfd/tc6393xb.h index fcc8e74f0e8d..d17807f2d0c9 100644 --- a/include/linux/mfd/tc6393xb.h +++ b/include/linux/mfd/tc6393xb.h @@ -22,14 +22,11 @@ struct tc6393xb_platform_data { u16 scr_gper; /* GP Enable */ int (*enable)(struct platform_device *dev); - int (*disable)(struct platform_device *dev); + void (*disable)(struct platform_device *dev); int (*suspend)(struct platform_device *dev); int (*resume)(struct platform_device *dev); int irq_base; /* base for subdevice irqs */ - int gpio_base; - int (*setup)(struct platform_device *dev); - void (*teardown)(struct platform_device *dev); struct tmio_nand_data *nand_data; struct tmio_fb_data *fb_data; diff --git a/include/linux/mfd/tps65086.h b/include/linux/mfd/tps65086.h index e0a417e53766..16f87cccc003 100644 --- a/include/linux/mfd/tps65086.h +++ b/include/linux/mfd/tps65086.h @@ -1,16 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2015 Texas Instruments Incorporated - https://www.ti.com/ * Andrew F. Davis <afd@ti.com> * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * This program is distributed "as is" WITHOUT ANY WARRANTY of any - * kind, whether expressed or implied; without even the implied warranty - * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License version 2 for more details. - * * Based on the TPS65912 driver */ diff --git a/include/linux/mfd/tps65217.h b/include/linux/mfd/tps65217.h index db7091824ed0..877d9c41c53d 100644 --- a/include/linux/mfd/tps65217.h +++ b/include/linux/mfd/tps65217.h @@ -1,18 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * linux/mfd/tps65217.h * * Functions to access TPS65217 power management chip. * * Copyright (C) 2011 Texas Instruments Incorporated - https://www.ti.com/ - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation version 2. - * - * This program is distributed "as is" WITHOUT ANY WARRANTY of any - * kind, whether express or implied; without even the implied warranty - * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. */ #ifndef __LINUX_MFD_TPS65217_H diff --git a/include/linux/mfd/tps65218.h b/include/linux/mfd/tps65218.h index f4ca367e3473..2946be2f15f3 100644 --- a/include/linux/mfd/tps65218.h +++ b/include/linux/mfd/tps65218.h @@ -1,18 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * linux/mfd/tps65218.h * - * Functions to access TPS65219 power management chip. + * Functions to access TPS65218 power management chip. * * Copyright (C) 2014 Texas Instruments Incorporated - https://www.ti.com/ - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * This program is distributed "as is" WITHOUT ANY WARRANTY of any - * kind, whether expressed or implied; without even the implied warranty - * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License version 2 for more details. */ #ifndef __LINUX_MFD_TPS65218_H diff --git a/include/linux/mfd/tps65912.h b/include/linux/mfd/tps65912.h index 8a61386cb8c1..860ec0a16c96 100644 --- a/include/linux/mfd/tps65912.h +++ b/include/linux/mfd/tps65912.h @@ -1,16 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2015 Texas Instruments Incorporated - https://www.ti.com/ * Andrew F. Davis <afd@ti.com> * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * This program is distributed "as is" WITHOUT ANY WARRANTY of any - * kind, whether expressed or implied; without even the implied warranty - * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License version 2 for more details. - * * Based on the TPS65218 driver and the previous TPS65912 driver by * Margarita Olaya Cabrera <magi@slimlogic.co.uk> */ diff --git a/include/linux/mfd/tps68470.h b/include/linux/mfd/tps68470.h index ffe81127d91c..7807fa329db0 100644 --- a/include/linux/mfd/tps68470.h +++ b/include/linux/mfd/tps68470.h @@ -75,6 +75,17 @@ #define TPS68470_CLKCFG1_MODE_A_MASK GENMASK(1, 0) #define TPS68470_CLKCFG1_MODE_B_MASK GENMASK(3, 2) +#define TPS68470_CLKCFG2_DRV_STR_2MA 0x05 +#define TPS68470_PLL_OUTPUT_ENABLE 0x02 +#define TPS68470_CLK_SRC_XTAL BIT(0) +#define TPS68470_PLLSWR_DEFAULT GENMASK(1, 0) +#define TPS68470_OSC_EXT_CAP_DEFAULT 0x05 + +#define TPS68470_OUTPUT_A_SHIFT 0x00 +#define TPS68470_OUTPUT_B_SHIFT 0x02 +#define TPS68470_CLK_SRC_SHIFT GENMASK(2, 0) +#define TPS68470_OSC_EXT_CAP_SHIFT BIT(2) + #define TPS68470_GPIO_CTL_REG_A(x) (TPS68470_REG_GPCTL0A + (x) * 2) #define TPS68470_GPIO_CTL_REG_B(x) (TPS68470_REG_GPCTL0B + (x) * 2) #define TPS68470_GPIO_MODE_MASK GENMASK(1, 0) diff --git a/include/linux/mfd/twl.h b/include/linux/mfd/twl.h index 8871cc5188a0..eaa233038254 100644 --- a/include/linux/mfd/twl.h +++ b/include/linux/mfd/twl.h @@ -594,8 +594,6 @@ struct twl4030_gpio_platform_data { int (*setup)(struct device *dev, unsigned gpio, unsigned ngpio); - int (*teardown)(struct device *dev, - unsigned gpio, unsigned ngpio); }; struct twl4030_madc_platform_data { @@ -694,61 +692,6 @@ struct twl4030_audio_data { unsigned int irq_base; }; -struct twl4030_platform_data { - struct twl4030_clock_init_data *clock; - struct twl4030_bci_platform_data *bci; - struct twl4030_gpio_platform_data *gpio; - struct twl4030_madc_platform_data *madc; - struct twl4030_keypad_data *keypad; - struct twl4030_usb_data *usb; - struct twl4030_power_data *power; - struct twl4030_audio_data *audio; - - /* Common LDO regulators for TWL4030/TWL6030 */ - struct regulator_init_data *vdac; - struct regulator_init_data *vaux1; - struct regulator_init_data *vaux2; - struct regulator_init_data *vaux3; - struct regulator_init_data *vdd1; - struct regulator_init_data *vdd2; - struct regulator_init_data *vdd3; - /* TWL4030 LDO regulators */ - struct regulator_init_data *vpll1; - struct regulator_init_data *vpll2; - struct regulator_init_data *vmmc1; - struct regulator_init_data *vmmc2; - struct regulator_init_data *vsim; - struct regulator_init_data *vaux4; - struct regulator_init_data *vio; - struct regulator_init_data *vintana1; - struct regulator_init_data *vintana2; - struct regulator_init_data *vintdig; - /* TWL6030 LDO regulators */ - struct regulator_init_data *vmmc; - struct regulator_init_data *vpp; - struct regulator_init_data *vusim; - struct regulator_init_data *vana; - struct regulator_init_data *vcxio; - struct regulator_init_data *vusb; - struct regulator_init_data *clk32kg; - struct regulator_init_data *v1v8; - struct regulator_init_data *v2v1; - /* TWL6032 LDO regulators */ - struct regulator_init_data *ldo1; - struct regulator_init_data *ldo2; - struct regulator_init_data *ldo3; - struct regulator_init_data *ldo4; - struct regulator_init_data *ldo5; - struct regulator_init_data *ldo6; - struct regulator_init_data *ldo7; - struct regulator_init_data *ldoln; - struct regulator_init_data *ldousb; - /* TWL6032 DCDC regulators */ - struct regulator_init_data *smps3; - struct regulator_init_data *smps4; - struct regulator_init_data *vio6025; -}; - struct twl_regulator_driver_data { int (*set_voltage)(void *data, int target_uV); int (*get_voltage)(void *data); diff --git a/include/linux/mhi.h b/include/linux/mhi.h index a5cc4cdf9cc8..a5441ad33c74 100644 --- a/include/linux/mhi.h +++ b/include/linux/mhi.h @@ -730,16 +730,27 @@ void mhi_device_put(struct mhi_device *mhi_dev); /** * mhi_prepare_for_transfer - Setup UL and DL channels for data transfer. - * Allocate and initialize the channel context and - * also issue the START channel command to both - * channels. Channels can be started only if both - * host and device execution environments match and - * channels are in a DISABLED state. * @mhi_dev: Device associated with the channels + * + * Allocate and initialize the channel context and also issue the START channel + * command to both channels. Channels can be started only if both host and + * device execution environments match and channels are in a DISABLED state. */ int mhi_prepare_for_transfer(struct mhi_device *mhi_dev); /** + * mhi_prepare_for_transfer_autoqueue - Setup UL and DL channels with auto queue + * buffers for DL traffic + * @mhi_dev: Device associated with the channels + * + * Allocate and initialize the channel context and also issue the START channel + * command to both channels. Channels can be started only if both host and + * device execution environments match and channels are in a DISABLED state. + * The MHI core will automatically allocate and queue buffers for the DL traffic. + */ +int mhi_prepare_for_transfer_autoqueue(struct mhi_device *mhi_dev); + +/** * mhi_unprepare_from_transfer - Reset UL and DL channels for data transfer. * Issue the RESET channel command and let the * device clean-up the context so no incoming diff --git a/include/linux/mhi_ep.h b/include/linux/mhi_ep.h new file mode 100644 index 000000000000..478aece17046 --- /dev/null +++ b/include/linux/mhi_ep.h @@ -0,0 +1,277 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2022, Linaro Ltd. + * + */ +#ifndef _MHI_EP_H_ +#define _MHI_EP_H_ + +#include <linux/dma-direction.h> +#include <linux/mhi.h> + +#define MHI_EP_DEFAULT_MTU 0x8000 + +/** + * struct mhi_ep_channel_config - Channel configuration structure for controller + * @name: The name of this channel + * @num: The number assigned to this channel + * @num_elements: The number of elements that can be queued to this channel + * @dir: Direction that data may flow on this channel + */ +struct mhi_ep_channel_config { + char *name; + u32 num; + u32 num_elements; + enum dma_data_direction dir; +}; + +/** + * struct mhi_ep_cntrl_config - MHI Endpoint controller configuration + * @mhi_version: MHI spec version supported by the controller + * @max_channels: Maximum number of channels supported + * @num_channels: Number of channels defined in @ch_cfg + * @ch_cfg: Array of defined channels + */ +struct mhi_ep_cntrl_config { + u32 mhi_version; + u32 max_channels; + u32 num_channels; + const struct mhi_ep_channel_config *ch_cfg; +}; + +/** + * struct mhi_ep_db_info - MHI Endpoint doorbell info + * @mask: Mask of the doorbell interrupt + * @status: Status of the doorbell interrupt + */ +struct mhi_ep_db_info { + u32 mask; + u32 status; +}; + +/** + * struct mhi_ep_cntrl - MHI Endpoint controller structure + * @cntrl_dev: Pointer to the struct device of physical bus acting as the MHI + * Endpoint controller + * @mhi_dev: MHI Endpoint device instance for the controller + * @mmio: MMIO region containing the MHI registers + * @mhi_chan: Points to the channel configuration table + * @mhi_event: Points to the event ring configurations table + * @mhi_cmd: Points to the command ring configurations table + * @sm: MHI Endpoint state machine + * @ch_ctx_cache: Cache of host channel context data structure + * @ev_ctx_cache: Cache of host event context data structure + * @cmd_ctx_cache: Cache of host command context data structure + * @ch_ctx_host_pa: Physical address of host channel context data structure + * @ev_ctx_host_pa: Physical address of host event context data structure + * @cmd_ctx_host_pa: Physical address of host command context data structure + * @ch_ctx_cache_phys: Physical address of the host channel context cache + * @ev_ctx_cache_phys: Physical address of the host event context cache + * @cmd_ctx_cache_phys: Physical address of the host command context cache + * @chdb: Array of channel doorbell interrupt info + * @event_lock: Lock for protecting event rings + * @list_lock: Lock for protecting state transition and channel doorbell lists + * @state_lock: Lock for protecting state transitions + * @st_transition_list: List of state transitions + * @ch_db_list: List of queued channel doorbells + * @wq: Dedicated workqueue for handling rings and state changes + * @state_work: State transition worker + * @reset_work: Worker for MHI Endpoint reset + * @cmd_ring_work: Worker for processing command rings + * @ch_ring_work: Worker for processing channel rings + * @raise_irq: CB function for raising IRQ to the host + * @alloc_map: CB function for allocating memory in endpoint for storing host context and mapping it + * @unmap_free: CB function to unmap and free the allocated memory in endpoint for storing host context + * @read_from_host: CB function for reading from host memory from endpoint + * @write_to_host: CB function for writing to host memory from endpoint + * @mhi_state: MHI Endpoint state + * @max_chan: Maximum channels supported by the endpoint controller + * @mru: MRU (Maximum Receive Unit) value of the endpoint controller + * @event_rings: Number of event rings supported by the endpoint controller + * @hw_event_rings: Number of hardware event rings supported by the endpoint controller + * @chdb_offset: Channel doorbell offset set by the host + * @erdb_offset: Event ring doorbell offset set by the host + * @index: MHI Endpoint controller index + * @irq: IRQ used by the endpoint controller + * @enabled: Check if the endpoint controller is enabled or not + */ +struct mhi_ep_cntrl { + struct device *cntrl_dev; + struct mhi_ep_device *mhi_dev; + void __iomem *mmio; + + struct mhi_ep_chan *mhi_chan; + struct mhi_ep_event *mhi_event; + struct mhi_ep_cmd *mhi_cmd; + struct mhi_ep_sm *sm; + + struct mhi_chan_ctxt *ch_ctx_cache; + struct mhi_event_ctxt *ev_ctx_cache; + struct mhi_cmd_ctxt *cmd_ctx_cache; + u64 ch_ctx_host_pa; + u64 ev_ctx_host_pa; + u64 cmd_ctx_host_pa; + phys_addr_t ch_ctx_cache_phys; + phys_addr_t ev_ctx_cache_phys; + phys_addr_t cmd_ctx_cache_phys; + + struct mhi_ep_db_info chdb[4]; + struct mutex event_lock; + spinlock_t list_lock; + spinlock_t state_lock; + + struct list_head st_transition_list; + struct list_head ch_db_list; + + struct workqueue_struct *wq; + struct work_struct state_work; + struct work_struct reset_work; + struct work_struct cmd_ring_work; + struct work_struct ch_ring_work; + + void (*raise_irq)(struct mhi_ep_cntrl *mhi_cntrl, u32 vector); + int (*alloc_map)(struct mhi_ep_cntrl *mhi_cntrl, u64 pci_addr, phys_addr_t *phys_ptr, + void __iomem **virt, size_t size); + void (*unmap_free)(struct mhi_ep_cntrl *mhi_cntrl, u64 pci_addr, phys_addr_t phys, + void __iomem *virt, size_t size); + int (*read_from_host)(struct mhi_ep_cntrl *mhi_cntrl, u64 from, void *to, size_t size); + int (*write_to_host)(struct mhi_ep_cntrl *mhi_cntrl, void *from, u64 to, size_t size); + + enum mhi_state mhi_state; + + u32 max_chan; + u32 mru; + u32 event_rings; + u32 hw_event_rings; + u32 chdb_offset; + u32 erdb_offset; + u32 index; + int irq; + bool enabled; +}; + +/** + * struct mhi_ep_device - Structure representing an MHI Endpoint device that binds + * to channels or is associated with controllers + * @dev: Driver model device node for the MHI Endpoint device + * @mhi_cntrl: Controller the device belongs to + * @id: Pointer to MHI Endpoint device ID struct + * @name: Name of the associated MHI Endpoint device + * @ul_chan: UL (from host to endpoint) channel for the device + * @dl_chan: DL (from endpoint to host) channel for the device + * @dev_type: MHI device type + */ +struct mhi_ep_device { + struct device dev; + struct mhi_ep_cntrl *mhi_cntrl; + const struct mhi_device_id *id; + const char *name; + struct mhi_ep_chan *ul_chan; + struct mhi_ep_chan *dl_chan; + enum mhi_device_type dev_type; +}; + +/** + * struct mhi_ep_driver - Structure representing a MHI Endpoint client driver + * @id_table: Pointer to MHI Endpoint device ID table + * @driver: Device driver model driver + * @probe: CB function for client driver probe function + * @remove: CB function for client driver remove function + * @ul_xfer_cb: CB function for UL (from host to endpoint) data transfer + * @dl_xfer_cb: CB function for DL (from endpoint to host) data transfer + */ +struct mhi_ep_driver { + const struct mhi_device_id *id_table; + struct device_driver driver; + int (*probe)(struct mhi_ep_device *mhi_ep, + const struct mhi_device_id *id); + void (*remove)(struct mhi_ep_device *mhi_ep); + void (*ul_xfer_cb)(struct mhi_ep_device *mhi_dev, + struct mhi_result *result); + void (*dl_xfer_cb)(struct mhi_ep_device *mhi_dev, + struct mhi_result *result); +}; + +#define to_mhi_ep_device(dev) container_of(dev, struct mhi_ep_device, dev) +#define to_mhi_ep_driver(drv) container_of(drv, struct mhi_ep_driver, driver) + +/* + * module_mhi_ep_driver() - Helper macro for drivers that don't do + * anything special other than using default mhi_ep_driver_register() and + * mhi_ep_driver_unregister(). This eliminates a lot of boilerplate. + * Each module may only use this macro once. + */ +#define module_mhi_ep_driver(mhi_drv) \ + module_driver(mhi_drv, mhi_ep_driver_register, \ + mhi_ep_driver_unregister) + +/* + * Macro to avoid include chaining to get THIS_MODULE + */ +#define mhi_ep_driver_register(mhi_drv) \ + __mhi_ep_driver_register(mhi_drv, THIS_MODULE) + +/** + * __mhi_ep_driver_register - Register a driver with MHI Endpoint bus + * @mhi_drv: Driver to be associated with the device + * @owner: The module owner + * + * Return: 0 if driver registrations succeeds, a negative error code otherwise. + */ +int __mhi_ep_driver_register(struct mhi_ep_driver *mhi_drv, struct module *owner); + +/** + * mhi_ep_driver_unregister - Unregister a driver from MHI Endpoint bus + * @mhi_drv: Driver associated with the device + */ +void mhi_ep_driver_unregister(struct mhi_ep_driver *mhi_drv); + +/** + * mhi_ep_register_controller - Register MHI Endpoint controller + * @mhi_cntrl: MHI Endpoint controller to register + * @config: Configuration to use for the controller + * + * Return: 0 if controller registrations succeeds, a negative error code otherwise. + */ +int mhi_ep_register_controller(struct mhi_ep_cntrl *mhi_cntrl, + const struct mhi_ep_cntrl_config *config); + +/** + * mhi_ep_unregister_controller - Unregister MHI Endpoint controller + * @mhi_cntrl: MHI Endpoint controller to unregister + */ +void mhi_ep_unregister_controller(struct mhi_ep_cntrl *mhi_cntrl); + +/** + * mhi_ep_power_up - Power up the MHI endpoint stack + * @mhi_cntrl: MHI Endpoint controller + * + * Return: 0 if power up succeeds, a negative error code otherwise. + */ +int mhi_ep_power_up(struct mhi_ep_cntrl *mhi_cntrl); + +/** + * mhi_ep_power_down - Power down the MHI endpoint stack + * @mhi_cntrl: MHI controller + */ +void mhi_ep_power_down(struct mhi_ep_cntrl *mhi_cntrl); + +/** + * mhi_ep_queue_is_empty - Determine whether the transfer queue is empty + * @mhi_dev: Device associated with the channels + * @dir: DMA direction for the channel + * + * Return: true if the queue is empty, false otherwise. + */ +bool mhi_ep_queue_is_empty(struct mhi_ep_device *mhi_dev, enum dma_data_direction dir); + +/** + * mhi_ep_queue_skb - Send SKBs to host over MHI Endpoint + * @mhi_dev: Device associated with the DL channel + * @skb: SKBs to be queued + * + * Return: 0 if the SKBs has been sent successfully, a negative error code otherwise. + */ +int mhi_ep_queue_skb(struct mhi_ep_device *mhi_dev, struct sk_buff *skb); + +#endif diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 4850cc5bf813..3ef77f52a4f0 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -19,33 +19,68 @@ struct migration_target_control; */ #define MIGRATEPAGE_SUCCESS 0 +/** + * struct movable_operations - Driver page migration + * @isolate_page: + * The VM calls this function to prepare the page to be moved. The page + * is locked and the driver should not unlock it. The driver should + * return ``true`` if the page is movable and ``false`` if it is not + * currently movable. After this function returns, the VM uses the + * page->lru field, so the driver must preserve any information which + * is usually stored here. + * + * @migrate_page: + * After isolation, the VM calls this function with the isolated + * @src page. The driver should copy the contents of the + * @src page to the @dst page and set up the fields of @dst page. + * Both pages are locked. + * If page migration is successful, the driver should call + * __ClearPageMovable(@src) and return MIGRATEPAGE_SUCCESS. + * If the driver cannot migrate the page at the moment, it can return + * -EAGAIN. The VM interprets this as a temporary migration failure and + * will retry it later. Any other error value is a permanent migration + * failure and migration will not be retried. + * The driver shouldn't touch the @src->lru field while in the + * migrate_page() function. It may write to @dst->lru. + * + * @putback_page: + * If migration fails on the isolated page, the VM informs the driver + * that the page is no longer a candidate for migration by calling + * this function. The driver should put the isolated page back into + * its own data structure. + */ +struct movable_operations { + bool (*isolate_page)(struct page *, isolate_mode_t); + int (*migrate_page)(struct page *dst, struct page *src, + enum migrate_mode); + void (*putback_page)(struct page *); +}; + /* Defined in mm/debug.c: */ extern const char *migrate_reason_names[MR_TYPES]; #ifdef CONFIG_MIGRATION extern void putback_movable_pages(struct list_head *l); -extern int migrate_page(struct address_space *mapping, - struct page *newpage, struct page *page, - enum migrate_mode mode); +int migrate_folio_extra(struct address_space *mapping, struct folio *dst, + struct folio *src, enum migrate_mode mode, int extra_count); +int migrate_folio(struct address_space *mapping, struct folio *dst, + struct folio *src, enum migrate_mode mode); extern int migrate_pages(struct list_head *l, new_page_t new, free_page_t free, unsigned long private, enum migrate_mode mode, int reason, unsigned int *ret_succeeded); extern struct page *alloc_migration_target(struct page *page, unsigned long private); extern int isolate_movable_page(struct page *page, isolate_mode_t mode); -extern void migrate_page_states(struct page *newpage, struct page *page); -extern void migrate_page_copy(struct page *newpage, struct page *page); -extern int migrate_huge_page_move_mapping(struct address_space *mapping, - struct page *newpage, struct page *page); -extern int migrate_page_move_mapping(struct address_space *mapping, - struct page *newpage, struct page *page, int extra_count); +int migrate_huge_page_move_mapping(struct address_space *mapping, + struct folio *dst, struct folio *src); +void migration_entry_wait_on_locked(swp_entry_t entry, pte_t *ptep, + spinlock_t *ptl); void folio_migrate_flags(struct folio *newfolio, struct folio *folio); void folio_migrate_copy(struct folio *newfolio, struct folio *folio); int folio_migrate_mapping(struct address_space *mapping, struct folio *newfolio, struct folio *folio, int extra_count); -extern bool numa_demotion_enabled; #else static inline void putback_movable_pages(struct list_head *l) {} @@ -59,30 +94,22 @@ static inline struct page *alloc_migration_target(struct page *page, static inline int isolate_movable_page(struct page *page, isolate_mode_t mode) { return -EBUSY; } -static inline void migrate_page_states(struct page *newpage, struct page *page) -{ -} - -static inline void migrate_page_copy(struct page *newpage, - struct page *page) {} - static inline int migrate_huge_page_move_mapping(struct address_space *mapping, - struct page *newpage, struct page *page) + struct folio *dst, struct folio *src) { return -ENOSYS; } -#define numa_demotion_enabled false #endif /* CONFIG_MIGRATION */ #ifdef CONFIG_COMPACTION -extern int PageMovable(struct page *page); -extern void __SetPageMovable(struct page *page, struct address_space *mapping); -extern void __ClearPageMovable(struct page *page); +bool PageMovable(struct page *page); +void __SetPageMovable(struct page *page, const struct movable_operations *ops); +void __ClearPageMovable(struct page *page); #else -static inline int PageMovable(struct page *page) { return 0; } +static inline bool PageMovable(struct page *page) { return false; } static inline void __SetPageMovable(struct page *page, - struct address_space *mapping) + const struct movable_operations *ops) { } static inline void __ClearPageMovable(struct page *page) @@ -90,6 +117,20 @@ static inline void __ClearPageMovable(struct page *page) } #endif +static inline bool folio_test_movable(struct folio *folio) +{ + return PageMovable(&folio->page); +} + +static inline +const struct movable_operations *page_movable_ops(struct page *page) +{ + VM_BUG_ON(!__PageMovable(page)); + + return (const struct movable_operations *) + ((unsigned long)page->mapping - PAGE_MAPPING_MOVABLE); +} + #ifdef CONFIG_NUMA_BALANCING extern int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma, int node); @@ -128,6 +169,7 @@ static inline unsigned long migrate_pfn(unsigned long pfn) enum migrate_vma_direction { MIGRATE_VMA_SELECT_SYSTEM = 1 << 0, MIGRATE_VMA_SELECT_DEVICE_PRIVATE = 1 << 1, + MIGRATE_VMA_SELECT_DEVICE_COHERENT = 1 << 2, }; struct migrate_vma { @@ -157,19 +199,23 @@ struct migrate_vma { */ void *pgmap_owner; unsigned long flags; + + /* + * Set to vmf->page if this is being called to migrate a page as part of + * a migrate_to_ram() callback. + */ + struct page *fault_page; }; int migrate_vma_setup(struct migrate_vma *args); void migrate_vma_pages(struct migrate_vma *migrate); void migrate_vma_finalize(struct migrate_vma *migrate); -int next_demotion_node(int node); - -#else /* CONFIG_MIGRATION disabled: */ - -static inline int next_demotion_node(int node) -{ - return NUMA_NO_NODE; -} +int migrate_device_range(unsigned long *src_pfns, unsigned long start, + unsigned long npages); +void migrate_device_pages(unsigned long *src_pfns, unsigned long *dst_pfns, + unsigned long npages); +void migrate_device_finalize(unsigned long *src_pfns, + unsigned long *dst_pfns, unsigned long npages); #endif /* CONFIG_MIGRATION */ diff --git a/include/linux/mii.h b/include/linux/mii.h index 12ea29e04293..d5a959ce4877 100644 --- a/include/linux/mii.h +++ b/include/linux/mii.h @@ -355,56 +355,6 @@ static inline u32 mii_adv_to_ethtool_adv_x(u32 adv) } /** - * mii_lpa_mod_linkmode_adv_sgmii - * @lp_advertising: pointer to destination link mode. - * @lpa: value of the MII_LPA register - * - * A small helper function that translates MII_LPA bits to - * linkmode advertisement settings for SGMII. - * Leaves other bits unchanged. - */ -static inline void -mii_lpa_mod_linkmode_lpa_sgmii(unsigned long *lp_advertising, u32 lpa) -{ - u32 speed_duplex = lpa & LPA_SGMII_DPX_SPD_MASK; - - linkmode_mod_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT, lp_advertising, - speed_duplex == LPA_SGMII_1000HALF); - - linkmode_mod_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT, lp_advertising, - speed_duplex == LPA_SGMII_1000FULL); - - linkmode_mod_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT, lp_advertising, - speed_duplex == LPA_SGMII_100HALF); - - linkmode_mod_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT, lp_advertising, - speed_duplex == LPA_SGMII_100FULL); - - linkmode_mod_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT, lp_advertising, - speed_duplex == LPA_SGMII_10HALF); - - linkmode_mod_bit(ETHTOOL_LINK_MODE_10baseT_Full_BIT, lp_advertising, - speed_duplex == LPA_SGMII_10FULL); -} - -/** - * mii_lpa_to_linkmode_adv_sgmii - * @advertising: pointer to destination link mode. - * @lpa: value of the MII_LPA register - * - * A small helper function that translates MII_ADVERTISE bits - * to linkmode advertisement settings when in SGMII mode. - * Clears the old value of advertising. - */ -static inline void mii_lpa_to_linkmode_lpa_sgmii(unsigned long *lp_advertising, - u32 lpa) -{ - linkmode_zero(lp_advertising); - - mii_lpa_mod_linkmode_lpa_sgmii(lp_advertising, lpa); -} - -/** * mii_adv_mod_linkmode_adv_t * @advertising:pointer to destination link mode. * @adv: value of the MII_ADVERTISE register @@ -595,4 +545,39 @@ static inline u8 mii_resolve_flowctrl_fdx(u16 lcladv, u16 rmtadv) return cap; } +/** + * mii_bmcr_encode_fixed - encode fixed speed/duplex settings to a BMCR value + * @speed: a SPEED_* value + * @duplex: a DUPLEX_* value + * + * Encode the speed and duplex to a BMCR value. 2500, 1000, 100 and 10 Mbps are + * supported. 2500Mbps is encoded to 1000Mbps. Other speeds are encoded as 10 + * Mbps. Unknown duplex values are encoded to half-duplex. + */ +static inline u16 mii_bmcr_encode_fixed(int speed, int duplex) +{ + u16 bmcr; + + switch (speed) { + case SPEED_2500: + case SPEED_1000: + bmcr = BMCR_SPEED1000; + break; + + case SPEED_100: + bmcr = BMCR_SPEED100; + break; + + case SPEED_10: + default: + bmcr = BMCR_SPEED10; + break; + } + + if (duplex == DUPLEX_FULL) + bmcr |= BMCR_FULLDPLX; + + return bmcr; +} + #endif /* __LINUX_MII_H__ */ diff --git a/include/linux/miscdevice.h b/include/linux/miscdevice.h index 0676f18093f9..c0fea6ca5076 100644 --- a/include/linux/miscdevice.h +++ b/include/linux/miscdevice.h @@ -44,7 +44,7 @@ #define AGPGART_MINOR 175 #define TOSH_MINOR_DEV 181 #define HWRNG_MINOR 183 -#define MICROCODE_MINOR 184 +/*#define MICROCODE_MINOR 184 unused */ #define KEYPAD_MINOR 185 #define IRNET_MINOR 187 #define D7S_MINOR 193 diff --git a/include/linux/mlx5/accel.h b/include/linux/mlx5/accel.h deleted file mode 100644 index dacf69516002..000000000000 --- a/include/linux/mlx5/accel.h +++ /dev/null @@ -1,156 +0,0 @@ -/* - * Copyright (c) 2018 Mellanox Technologies. All rights reserved. - * - * This software is available to you under a choice of one of two - * licenses. You may choose to be licensed under the terms of the GNU - * General Public License (GPL) Version 2, available from the file - * COPYING in the main directory of this source tree, or the - * OpenIB.org BSD license below: - * - * Redistribution and use in source and binary forms, with or - * without modification, are permitted provided that the following - * conditions are met: - * - * - Redistributions of source code must retain the above - * copyright notice, this list of conditions and the following - * disclaimer. - * - * - Redistributions in binary form must reproduce the above - * copyright notice, this list of conditions and the following - * disclaimer in the documentation and/or other materials - * provided with the distribution. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, - * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF - * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND - * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS - * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN - * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN - * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE - * SOFTWARE. - * - */ - -#ifndef __MLX5_ACCEL_H__ -#define __MLX5_ACCEL_H__ - -#include <linux/mlx5/driver.h> - -enum mlx5_accel_esp_aes_gcm_keymat_iv_algo { - MLX5_ACCEL_ESP_AES_GCM_IV_ALGO_SEQ, -}; - -enum mlx5_accel_esp_flags { - MLX5_ACCEL_ESP_FLAGS_TUNNEL = 0, /* Default */ - MLX5_ACCEL_ESP_FLAGS_TRANSPORT = 1UL << 0, - MLX5_ACCEL_ESP_FLAGS_ESN_TRIGGERED = 1UL << 1, - MLX5_ACCEL_ESP_FLAGS_ESN_STATE_OVERLAP = 1UL << 2, -}; - -enum mlx5_accel_esp_action { - MLX5_ACCEL_ESP_ACTION_DECRYPT, - MLX5_ACCEL_ESP_ACTION_ENCRYPT, -}; - -enum mlx5_accel_esp_keymats { - MLX5_ACCEL_ESP_KEYMAT_AES_NONE, - MLX5_ACCEL_ESP_KEYMAT_AES_GCM, -}; - -enum mlx5_accel_esp_replay { - MLX5_ACCEL_ESP_REPLAY_NONE, - MLX5_ACCEL_ESP_REPLAY_BMP, -}; - -struct aes_gcm_keymat { - u64 seq_iv; - enum mlx5_accel_esp_aes_gcm_keymat_iv_algo iv_algo; - - u32 salt; - u32 icv_len; - - u32 key_len; - u32 aes_key[256 / 32]; -}; - -struct mlx5_accel_esp_xfrm_attrs { - enum mlx5_accel_esp_action action; - u32 esn; - __be32 spi; - u32 seq; - u32 tfc_pad; - u32 flags; - u32 sa_handle; - enum mlx5_accel_esp_replay replay_type; - union { - struct { - u32 size; - - } bmp; - } replay; - enum mlx5_accel_esp_keymats keymat_type; - union { - struct aes_gcm_keymat aes_gcm; - } keymat; - - union { - __be32 a4; - __be32 a6[4]; - } saddr; - - union { - __be32 a4; - __be32 a6[4]; - } daddr; - - u8 is_ipv6; -}; - -struct mlx5_accel_esp_xfrm { - struct mlx5_core_dev *mdev; - struct mlx5_accel_esp_xfrm_attrs attrs; -}; - -enum { - MLX5_ACCEL_XFRM_FLAG_REQUIRE_METADATA = 1UL << 0, -}; - -enum mlx5_accel_ipsec_cap { - MLX5_ACCEL_IPSEC_CAP_DEVICE = 1 << 0, - MLX5_ACCEL_IPSEC_CAP_REQUIRED_METADATA = 1 << 1, - MLX5_ACCEL_IPSEC_CAP_ESP = 1 << 2, - MLX5_ACCEL_IPSEC_CAP_IPV6 = 1 << 3, - MLX5_ACCEL_IPSEC_CAP_LSO = 1 << 4, - MLX5_ACCEL_IPSEC_CAP_RX_NO_TRAILER = 1 << 5, - MLX5_ACCEL_IPSEC_CAP_ESN = 1 << 6, - MLX5_ACCEL_IPSEC_CAP_TX_IV_IS_ESN = 1 << 7, -}; - -#ifdef CONFIG_MLX5_ACCEL - -u32 mlx5_accel_ipsec_device_caps(struct mlx5_core_dev *mdev); - -struct mlx5_accel_esp_xfrm * -mlx5_accel_esp_create_xfrm(struct mlx5_core_dev *mdev, - const struct mlx5_accel_esp_xfrm_attrs *attrs, - u32 flags); -void mlx5_accel_esp_destroy_xfrm(struct mlx5_accel_esp_xfrm *xfrm); -int mlx5_accel_esp_modify_xfrm(struct mlx5_accel_esp_xfrm *xfrm, - const struct mlx5_accel_esp_xfrm_attrs *attrs); - -#else - -static inline u32 mlx5_accel_ipsec_device_caps(struct mlx5_core_dev *mdev) { return 0; } - -static inline struct mlx5_accel_esp_xfrm * -mlx5_accel_esp_create_xfrm(struct mlx5_core_dev *mdev, - const struct mlx5_accel_esp_xfrm_attrs *attrs, - u32 flags) { return ERR_PTR(-EOPNOTSUPP); } -static inline void -mlx5_accel_esp_destroy_xfrm(struct mlx5_accel_esp_xfrm *xfrm) {} -static inline int -mlx5_accel_esp_modify_xfrm(struct mlx5_accel_esp_xfrm *xfrm, - const struct mlx5_accel_esp_xfrm_attrs *attrs) { return -EOPNOTSUPP; } - -#endif /* CONFIG_MLX5_ACCEL */ -#endif /* __MLX5_ACCEL_H__ */ diff --git a/include/linux/mlx5/cq.h b/include/linux/mlx5/cq.h index 7bfb67363434..cb15308b5cb0 100644 --- a/include/linux/mlx5/cq.h +++ b/include/linux/mlx5/cq.h @@ -183,6 +183,8 @@ static inline void mlx5_cq_put(struct mlx5_core_cq *cq) complete(&cq->free); } +int mlx5_create_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq, + u32 *in, int inlen, u32 *out, int outlen); int mlx5_core_create_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq, u32 *in, int inlen, u32 *out, int outlen); int mlx5_core_destroy_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq); diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 604b85dd770a..1ff91cb79ded 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -325,6 +325,7 @@ enum mlx5_event { MLX5_EVENT_TYPE_WQ_INVAL_REQ_ERROR = 0x10, MLX5_EVENT_TYPE_WQ_ACCESS_ERROR = 0x11, MLX5_EVENT_TYPE_SRQ_CATAS_ERROR = 0x12, + MLX5_EVENT_TYPE_OBJECT_CHANGE = 0x27, MLX5_EVENT_TYPE_INTERNAL_ERROR = 0x08, MLX5_EVENT_TYPE_PORT_CHANGE = 0x09, @@ -387,21 +388,6 @@ enum { }; enum { - MLX5_DEV_CAP_FLAG_XRC = 1LL << 3, - MLX5_DEV_CAP_FLAG_BAD_PKEY_CNTR = 1LL << 8, - MLX5_DEV_CAP_FLAG_BAD_QKEY_CNTR = 1LL << 9, - MLX5_DEV_CAP_FLAG_APM = 1LL << 17, - MLX5_DEV_CAP_FLAG_ATOMIC = 1LL << 18, - MLX5_DEV_CAP_FLAG_BLOCK_MCAST = 1LL << 23, - MLX5_DEV_CAP_FLAG_ON_DMND_PG = 1LL << 24, - MLX5_DEV_CAP_FLAG_CQ_MODER = 1LL << 29, - MLX5_DEV_CAP_FLAG_RESIZE_CQ = 1LL << 30, - MLX5_DEV_CAP_FLAG_DCT = 1LL << 37, - MLX5_DEV_CAP_FLAG_SIG_HAND_OVER = 1LL << 40, - MLX5_DEV_CAP_FLAG_CMDIF_CSUM = 3LL << 46, -}; - -enum { MLX5_ROCE_VERSION_1 = 0, MLX5_ROCE_VERSION_2 = 2, }; @@ -455,6 +441,7 @@ enum { MLX5_OPCODE_UMR = 0x25, + MLX5_OPCODE_ACCESS_ASO = 0x2d, }; enum { @@ -496,10 +483,6 @@ enum { }; enum { - MLX5_CAP_OFF_CMDIF_CSUM = 46, -}; - -enum { /* * Max wqe size for rdma read is 512 bytes, so this * limits our max_sge_rd as the wqe needs to fit: @@ -717,6 +700,12 @@ struct mlx5_eqe_temp_warning { __be64 sensor_warning_lsb; } __packed; +struct mlx5_eqe_obj_change { + u8 rsvd0[2]; + __be16 obj_type; + __be32 obj_id; +} __packed; + #define SYNC_RST_STATE_MASK 0xf enum sync_rst_state_type { @@ -755,6 +744,7 @@ union ev_data { struct mlx5_eqe_xrq_err xrq_err; struct mlx5_eqe_sync_fw_update sync_fw_update; struct mlx5_eqe_vhca_state vhca_state; + struct mlx5_eqe_obj_change obj_change; } __packed; struct mlx5_eqe { @@ -840,7 +830,10 @@ struct mlx5_cqe64 { __be32 timestamp_l; __be32 sop_drop_qpn; __be16 wqe_counter; - u8 signature; + union { + u8 signature; + u8 validity_iteration_count; + }; u8 op_own; }; @@ -872,6 +865,11 @@ enum { MLX5_CQE_FORMAT_CSUM_STRIDX = 0x3, }; +enum { + MLX5_CQE_COMPRESS_LAYOUT_BASIC = 0, + MLX5_CQE_COMPRESS_LAYOUT_ENHANCED = 1, +}; + #define MLX5_MINI_CQE_ARRAY_SIZE 8 static inline u8 mlx5_get_cqe_format(struct mlx5_cqe64 *cqe) @@ -894,11 +892,6 @@ static inline u8 get_cqe_l4_hdr_type(struct mlx5_cqe64 *cqe) return (cqe->l4_l3_hdr_type >> 4) & 0x7; } -static inline u8 get_cqe_l3_hdr_type(struct mlx5_cqe64 *cqe) -{ - return (cqe->l4_l3_hdr_type >> 2) & 0x3; -} - static inline bool cqe_is_tunneled(struct mlx5_cqe64 *cqe) { return cqe->tls_outer_l3_tunneled & 0x1; @@ -1202,8 +1195,10 @@ enum mlx5_cap_type { MLX5_CAP_DEV_EVENT = 0x14, MLX5_CAP_IPSEC, MLX5_CAP_DEV_SHAMPO = 0x1d, + MLX5_CAP_MACSEC = 0x1f, MLX5_CAP_GENERAL_2 = 0x20, MLX5_CAP_PORT_SELECTION = 0x25, + MLX5_CAP_ADV_VIRTUALIZATION = 0x26, /* NUM OF CAP Types */ MLX5_CAP_NUM }; @@ -1369,6 +1364,14 @@ enum mlx5_qcam_feature_groups { MLX5_GET(port_selection_cap, \ mdev->caps.hca[MLX5_CAP_PORT_SELECTION]->max, cap) +#define MLX5_CAP_ADV_VIRTUALIZATION(mdev, cap) \ + MLX5_GET(adv_virtualization_cap, \ + mdev->caps.hca[MLX5_CAP_ADV_VIRTUALIZATION]->cur, cap) + +#define MLX5_CAP_ADV_VIRTUALIZATION_MAX(mdev, cap) \ + MLX5_GET(adv_virtualization_cap, \ + mdev->caps.hca[MLX5_CAP_ADV_VIRTUALIZATION]->max, cap) + #define MLX5_CAP_FLOWTABLE_PORT_SELECTION(mdev, cap) \ MLX5_CAP_PORT_SELECTION(mdev, flow_table_properties_port_selection.cap) @@ -1450,6 +1453,9 @@ enum mlx5_qcam_feature_groups { #define MLX5_CAP_DEV_SHAMPO(mdev, cap)\ MLX5_GET(shampo_cap, mdev->caps.hca_cur[MLX5_CAP_DEV_SHAMPO], cap) +#define MLX5_CAP_MACSEC(mdev, cap)\ + MLX5_GET(macsec_cap, (mdev)->caps.hca[MLX5_CAP_MACSEC]->cur, cap) + enum { MLX5_CMD_STAT_OK = 0x0, MLX5_CMD_STAT_INT_ERR = 0x1, diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 78655d8d13a7..af2ceb4160bc 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -84,7 +84,7 @@ enum mlx5_sqp_t { }; enum { - MLX5_MAX_PORTS = 2, + MLX5_MAX_PORTS = 4, }; enum { @@ -264,6 +264,16 @@ enum { struct mlx5_cmd_stats { u64 sum; u64 n; + /* number of times command failed */ + u64 failed; + /* number of times command failed on bad status returned by FW */ + u64 failed_mbox_status; + /* last command failed returned errno */ + u32 last_failed_errno; + /* last bad status returned by FW */ + u8 last_failed_mbox_status; + /* last command failed syndrome returned by FW */ + u32 last_failed_syndrome; struct dentry *root; /* protect command average calculations */ spinlock_t lock; @@ -437,6 +447,11 @@ struct mlx5_qp_table { struct radix_tree_root tree; }; +enum { + MLX5_PF_NOTIFY_DISABLE_VF, + MLX5_PF_NOTIFY_ENABLE_VF, +}; + struct mlx5_vf_context { int enabled; u64 port_guid; @@ -447,6 +462,7 @@ struct mlx5_vf_context { u8 port_guid_valid:1; u8 node_guid_valid:1; enum port_state_policy policy; + struct blocking_notifier_head notifier; }; struct mlx5_core_sriov { @@ -535,6 +551,10 @@ enum { * creation/deletion on drivers rescan. Unset during device attach. */ MLX5_PRIV_FLAGS_DETACH = 1 << 2, + /* Distinguish between mlx5e_probe/remove called by module init/cleanup + * and called by other flows which can already hold devlink lock + */ + MLX5_PRIV_FLAGS_MLX5E_LOCKED_FLOW = 1 << 3, }; struct mlx5_adev { @@ -543,6 +563,16 @@ struct mlx5_adev { int idx; }; +struct mlx5_debugfs_entries { + struct dentry *dbg_root; + struct dentry *qp_debugfs; + struct dentry *eq_debugfs; + struct dentry *cq_debugfs; + struct dentry *cmdif_debugfs; + struct dentry *pages_debugfs; + struct dentry *lag_debugfs; +}; + struct mlx5_ft_pool; struct mlx5_priv { /* IRQ table valid only for real pci devices PF or VF */ @@ -553,21 +583,19 @@ struct mlx5_priv { struct mlx5_nb pg_nb; struct workqueue_struct *pg_wq; struct xarray page_root_xa; - int fw_pages; + u32 fw_pages; atomic_t reg_pages; struct list_head free_list; - int vfs_pages; - int host_pf_pages; + u32 vfs_pages; + u32 host_pf_pages; + u32 fw_pages_alloc_failed; + u32 give_pages_dropped; + u32 reclaim_pages_discard; struct mlx5_core_health health; struct list_head traps; - /* start: qp staff */ - struct dentry *qp_debugfs; - struct dentry *eq_debugfs; - struct dentry *cq_debugfs; - struct dentry *cmdif_debugfs; - /* end: qp staff */ + struct mlx5_debugfs_entries dbg; /* start: alloc staff */ /* protect buffer allocation according to numa node */ @@ -577,12 +605,12 @@ struct mlx5_priv { struct mutex pgdir_mutex; struct list_head pgdir_list; /* end: alloc staff */ - struct dentry *dbg_root; struct list_head ctx_list; spinlock_t ctx_lock; struct mlx5_adev **adev; int adev_idx; + int sw_vhca_id; struct mlx5_events *events; struct mlx5_flow_steering *steering; @@ -618,6 +646,7 @@ enum mlx5_device_state { enum mlx5_interface_state { MLX5_INTERFACE_STATE_UP = BIT(0), + MLX5_BREAK_FW_WAIT = BIT(1), }; enum mlx5_pci_status { @@ -652,6 +681,7 @@ struct mlx5e_resources { enum mlx5_sw_icm_type { MLX5_SW_ICM_TYPE_STEERING, MLX5_SW_ICM_TYPE_HEADER_MODIFY, + MLX5_SW_ICM_TYPE_HEADER_MODIFY_PATTERN, }; #define MLX5_MAX_RESERVED_GIDS 8 @@ -668,6 +698,8 @@ struct mlx5_pps { struct work_struct out_work; u64 start[MAX_PIN_NUM]; u8 enabled; + u64 min_npps_period; + u64 min_out_pulse_duration_ns; }; struct mlx5_timer { @@ -703,10 +735,10 @@ enum { }; enum { - MR_CACHE_LAST_STD_ENTRY = 20, + MKEY_CACHE_LAST_STD_ENTRY = 20, MLX5_IMR_MTT_CACHE_ENTRY, MLX5_IMR_KSM_CACHE_ENTRY, - MAX_MR_CACHE_ENTRIES + MAX_MKEY_CACHE_ENTRIES }; struct mlx5_profile { @@ -715,7 +747,7 @@ struct mlx5_profile { struct { int size; int limit; - } mr_cache[MAX_MR_CACHE_ENTRIES]; + } mr_cache[MAX_MKEY_CACHE_ENTRIES]; }; struct mlx5_hca_cap { @@ -749,6 +781,7 @@ struct mlx5_core_dev { enum mlx5_device_state state; /* sync interface state */ struct mutex intf_state_mutex; + struct lock_class_key lock_key; unsigned long intf_state; struct mlx5_priv priv; struct mlx5_profile profile; @@ -764,9 +797,6 @@ struct mlx5_core_dev { #ifdef CONFIG_MLX5_FPGA struct mlx5_fpga_device *fpga; #endif -#ifdef CONFIG_MLX5_ACCEL - const struct mlx5_accel_ipsec_ops *ipsec_ops; -#endif struct mlx5_clock clock; struct mlx5_ib_clock_info *clock_info; struct mlx5_fw_tracer *tracer; @@ -827,11 +857,6 @@ struct mlx5_cmd_work_ent { refcount_t refcnt; }; -struct mlx5_pas { - u64 pa; - u8 log_sz; -}; - enum phy_port_state { MLX5_AAA_111 }; @@ -863,20 +888,10 @@ struct mlx5_hca_vport_context { bool grh_required; }; -static inline void *mlx5_buf_offset(struct mlx5_frag_buf *buf, int offset) -{ - return buf->frags->buf + offset; -} - #define STRUCT_FIELD(header, field) \ .struct_offset_bytes = offsetof(struct ib_unpacked_ ## header, field), \ .struct_size_bytes = sizeof((struct ib_unpacked_ ## header *)0)->field -static inline struct mlx5_core_dev *pci2mlx5_core_dev(struct pci_dev *pdev) -{ - return pci_get_drvdata(pdev); -} - extern struct dentry *mlx5_debugfs_root; static inline u16 fw_rev_maj(struct mlx5_core_dev *dev) @@ -955,7 +970,7 @@ void mlx5_cmd_allowed_opcode(struct mlx5_core_dev *dev, u16 opcode); struct mlx5_async_ctx { struct mlx5_core_dev *dev; atomic_t num_inflight; - struct wait_queue_head wait; + struct completion inflight_done; }; struct mlx5_async_work; @@ -965,6 +980,8 @@ typedef void (*mlx5_async_cbk_t)(int status, struct mlx5_async_work *context); struct mlx5_async_work { struct mlx5_async_ctx *ctx; mlx5_async_cbk_t user_callback; + u16 opcode; /* cmd opcode */ + void *out; /* pointer to the cmd output buffer */ }; void mlx5_cmd_init_async_ctx(struct mlx5_core_dev *dev, @@ -973,7 +990,9 @@ void mlx5_cmd_cleanup_async_ctx(struct mlx5_async_ctx *ctx); int mlx5_cmd_exec_cb(struct mlx5_async_ctx *ctx, void *in, int in_size, void *out, int out_size, mlx5_async_cbk_t callback, struct mlx5_async_work *work); - +void mlx5_cmd_out_err(struct mlx5_core_dev *dev, u16 opcode, u16 op_mod, void *out); +int mlx5_cmd_do(struct mlx5_core_dev *dev, void *in, int in_size, void *out, int out_size); +int mlx5_cmd_check(struct mlx5_core_dev *dev, int err, void *in, void *out); int mlx5_cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out, int out_size); @@ -991,20 +1010,16 @@ int mlx5_cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out, int mlx5_cmd_exec_polling(struct mlx5_core_dev *dev, void *in, int in_size, void *out, int out_size); -void mlx5_cmd_mbox_status(void *out, u8 *status, u32 *syndrome); bool mlx5_cmd_is_down(struct mlx5_core_dev *dev); int mlx5_core_get_caps(struct mlx5_core_dev *dev, enum mlx5_cap_type cap_type); -void mlx5_health_flush(struct mlx5_core_dev *dev); void mlx5_health_cleanup(struct mlx5_core_dev *dev); int mlx5_health_init(struct mlx5_core_dev *dev); void mlx5_start_health_poll(struct mlx5_core_dev *dev); void mlx5_stop_health_poll(struct mlx5_core_dev *dev, bool disable_health); +void mlx5_start_health_fw_log_up(struct mlx5_core_dev *dev); void mlx5_drain_health_wq(struct mlx5_core_dev *dev); void mlx5_trigger_health_work(struct mlx5_core_dev *dev); -int mlx5_buf_alloc(struct mlx5_core_dev *dev, - int size, struct mlx5_frag_buf *buf); -void mlx5_buf_free(struct mlx5_core_dev *dev, struct mlx5_frag_buf *buf); int mlx5_frag_buf_alloc_node(struct mlx5_core_dev *dev, int size, struct mlx5_frag_buf *buf, int node); void mlx5_frag_buf_free(struct mlx5_core_dev *dev, struct mlx5_frag_buf *buf); @@ -1023,6 +1038,8 @@ int mlx5_pagealloc_init(struct mlx5_core_dev *dev); void mlx5_pagealloc_cleanup(struct mlx5_core_dev *dev); void mlx5_pagealloc_start(struct mlx5_core_dev *dev); void mlx5_pagealloc_stop(struct mlx5_core_dev *dev); +void mlx5_pages_debugfs_init(struct mlx5_core_dev *dev); +void mlx5_pages_debugfs_cleanup(struct mlx5_core_dev *dev); void mlx5_core_req_pages_handler(struct mlx5_core_dev *dev, u16 func_id, s32 npages, bool ec_function); int mlx5_satisfy_startup_pages(struct mlx5_core_dev *dev, int boot); @@ -1030,22 +1047,30 @@ int mlx5_reclaim_startup_pages(struct mlx5_core_dev *dev); void mlx5_register_debugfs(void); void mlx5_unregister_debugfs(void); -void mlx5_fill_page_array(struct mlx5_frag_buf *buf, __be64 *pas); void mlx5_fill_page_frag_array_perm(struct mlx5_frag_buf *buf, __be64 *pas, u8 perm); void mlx5_fill_page_frag_array(struct mlx5_frag_buf *frag_buf, __be64 *pas); int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn); int mlx5_core_attach_mcg(struct mlx5_core_dev *dev, union ib_gid *mgid, u32 qpn); int mlx5_core_detach_mcg(struct mlx5_core_dev *dev, union ib_gid *mgid, u32 qpn); +struct dentry *mlx5_debugfs_get_dev_root(struct mlx5_core_dev *dev); void mlx5_qp_debugfs_init(struct mlx5_core_dev *dev); void mlx5_qp_debugfs_cleanup(struct mlx5_core_dev *dev); +int mlx5_access_reg(struct mlx5_core_dev *dev, void *data_in, int size_in, + void *data_out, int size_out, u16 reg_id, int arg, + int write, bool verbose); int mlx5_core_access_reg(struct mlx5_core_dev *dev, void *data_in, int size_in, void *data_out, int size_out, u16 reg_num, int arg, int write); -int mlx5_db_alloc(struct mlx5_core_dev *dev, struct mlx5_db *db); int mlx5_db_alloc_node(struct mlx5_core_dev *dev, struct mlx5_db *db, int node); + +static inline int mlx5_db_alloc(struct mlx5_core_dev *dev, struct mlx5_db *db) +{ + return mlx5_db_alloc_node(dev, db, dev->priv.numa_node); +} + void mlx5_db_free(struct mlx5_core_dev *dev, struct mlx5_db *db); const char *mlx5_command_str(int command); @@ -1057,8 +1082,6 @@ int mlx5_core_destroy_psv(struct mlx5_core_dev *dev, int psv_num); void mlx5_core_put_rsc(struct mlx5_core_rsc_common *common); int mlx5_query_odp_caps(struct mlx5_core_dev *dev, struct mlx5_odp_caps *odp_caps); -int mlx5_core_query_ib_ppcnt(struct mlx5_core_dev *dev, - u8 port_num, void *out, size_t sz); int mlx5_init_rl_table(struct mlx5_core_dev *dev); void mlx5_cleanup_rl_table(struct mlx5_core_dev *dev); @@ -1125,6 +1148,7 @@ int mlx5_cmd_destroy_vport_lag(struct mlx5_core_dev *dev); bool mlx5_lag_is_roce(struct mlx5_core_dev *dev); bool mlx5_lag_is_sriov(struct mlx5_core_dev *dev); bool mlx5_lag_is_active(struct mlx5_core_dev *dev); +bool mlx5_lag_mode_is_hash(struct mlx5_core_dev *dev); bool mlx5_lag_is_master(struct mlx5_core_dev *dev); bool mlx5_lag_is_shared_fdb(struct mlx5_core_dev *dev); struct net_device *mlx5_lag_get_roce_netdev(struct mlx5_core_dev *dev); @@ -1135,6 +1159,7 @@ int mlx5_lag_query_cong_counters(struct mlx5_core_dev *dev, int num_counters, size_t *offsets); struct mlx5_core_dev *mlx5_lag_get_peer_mdev(struct mlx5_core_dev *dev); +u8 mlx5_lag_get_num_ports(struct mlx5_core_dev *dev); struct mlx5_uars_page *mlx5_get_uars_page(struct mlx5_core_dev *mdev); void mlx5_put_uars_page(struct mlx5_core_dev *mdev, struct mlx5_uars_page *up); int mlx5_dm_sw_icm_alloc(struct mlx5_core_dev *dev, enum mlx5_sw_icm_type type, @@ -1143,6 +1168,15 @@ int mlx5_dm_sw_icm_alloc(struct mlx5_core_dev *dev, enum mlx5_sw_icm_type type, int mlx5_dm_sw_icm_dealloc(struct mlx5_core_dev *dev, enum mlx5_sw_icm_type type, u64 length, u16 uid, phys_addr_t addr, u32 obj_id); +struct mlx5_core_dev *mlx5_vf_get_core_dev(struct pci_dev *pdev); +void mlx5_vf_put_core_dev(struct mlx5_core_dev *mdev); + +int mlx5_sriov_blocking_notifier_register(struct mlx5_core_dev *mdev, + int vf_id, + struct notifier_block *nb); +void mlx5_sriov_blocking_notifier_unregister(struct mlx5_core_dev *mdev, + int vf_id, + struct notifier_block *nb); #ifdef CONFIG_MLX5_CORE_IPOIB struct net_device *mlx5_rdma_netdev_alloc(struct mlx5_core_dev *mdev, struct ib_device *ibdev, @@ -1242,16 +1276,21 @@ enum { MLX5_TRIGGERED_CMD_COMP = (u64)1 << 32, }; -static inline bool mlx5_is_roce_init_enabled(struct mlx5_core_dev *dev) +bool mlx5_is_roce_on(struct mlx5_core_dev *dev); + +static inline bool mlx5_get_roce_state(struct mlx5_core_dev *dev) { - struct devlink *devlink = priv_to_devlink(dev); - union devlink_param_value val; - int err; - - err = devlink_param_driverinit_value_get(devlink, - DEVLINK_PARAM_GENERIC_ID_ENABLE_ROCE, - &val); - return err ? MLX5_CAP_GEN(dev, roce) : val.vbool; + if (MLX5_CAP_GEN(dev, roce_rw_supported)) + return MLX5_CAP_GEN(dev, roce); + + /* If RoCE cap is read-only in FW, get RoCE state from devlink + * in order to support RoCE enable/disable feature + */ + return mlx5_is_roce_on(dev); } +enum { + MLX5_OCTWORD = 16, +}; + #endif /* MLX5_DRIVER_H */ diff --git a/include/linux/mlx5/eswitch.h b/include/linux/mlx5/eswitch.h index 8b18fe9771f9..e2701ed0200e 100644 --- a/include/linux/mlx5/eswitch.h +++ b/include/linux/mlx5/eswitch.h @@ -12,7 +12,6 @@ #define MLX5_ESWITCH_MANAGER(mdev) MLX5_CAP_GEN(mdev, eswitch_manager) enum { - MLX5_ESWITCH_NONE, MLX5_ESWITCH_LEGACY, MLX5_ESWITCH_OFFLOADS }; @@ -153,7 +152,7 @@ struct mlx5_core_dev *mlx5_eswitch_get_core_dev(struct mlx5_eswitch *esw); static inline u8 mlx5_eswitch_mode(const struct mlx5_core_dev *dev) { - return MLX5_ESWITCH_NONE; + return MLX5_ESWITCH_LEGACY; } static inline enum devlink_eswitch_encap_mode @@ -198,6 +197,11 @@ static inline struct mlx5_core_dev *mlx5_eswitch_get_core_dev(struct mlx5_eswitc #endif /* CONFIG_MLX5_ESWITCH */ +static inline bool is_mdev_legacy_mode(struct mlx5_core_dev *dev) +{ + return mlx5_eswitch_mode(dev) == MLX5_ESWITCH_LEGACY; +} + static inline bool is_mdev_switchdev_mode(struct mlx5_core_dev *dev) { return mlx5_eswitch_mode(dev) == MLX5_ESWITCH_OFFLOADS; diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index b1aad14689e3..c7a91981cd5a 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -40,6 +40,18 @@ #define MLX5_SET_CFG(p, f, v) MLX5_SET(create_flow_group_in, p, f, v) +enum mlx5_flow_destination_type { + MLX5_FLOW_DESTINATION_TYPE_NONE, + MLX5_FLOW_DESTINATION_TYPE_VPORT, + MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE, + MLX5_FLOW_DESTINATION_TYPE_TIR, + MLX5_FLOW_DESTINATION_TYPE_FLOW_SAMPLER, + MLX5_FLOW_DESTINATION_TYPE_UPLINK, + MLX5_FLOW_DESTINATION_TYPE_PORT, + MLX5_FLOW_DESTINATION_TYPE_COUNTER, + MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE_NUM, +}; + enum { MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO = 1 << 16, MLX5_FLOW_CONTEXT_ACTION_ENCRYPT = 1 << 17, @@ -67,6 +79,7 @@ static inline void build_leftovers_ft_param(int *priority, enum mlx5_flow_namespace_type { MLX5_FLOW_NAMESPACE_BYPASS, + MLX5_FLOW_NAMESPACE_KERNEL_RX_MACSEC, MLX5_FLOW_NAMESPACE_LAG, MLX5_FLOW_NAMESPACE_OFFLOADS, MLX5_FLOW_NAMESPACE_ETHTOOL, @@ -80,7 +93,8 @@ enum mlx5_flow_namespace_type { MLX5_FLOW_NAMESPACE_SNIFFER_RX, MLX5_FLOW_NAMESPACE_SNIFFER_TX, MLX5_FLOW_NAMESPACE_EGRESS, - MLX5_FLOW_NAMESPACE_EGRESS_KERNEL, + MLX5_FLOW_NAMESPACE_EGRESS_IPSEC, + MLX5_FLOW_NAMESPACE_EGRESS_MACSEC, MLX5_FLOW_NAMESPACE_RDMA_RX, MLX5_FLOW_NAMESPACE_RDMA_RX_KERNEL, MLX5_FLOW_NAMESPACE_RDMA_TX, @@ -166,6 +180,7 @@ struct mlx5_flow_table_attr { int max_fte; u32 level; u32 flags; + u16 uid; struct mlx5_flow_table *next_ft; struct { @@ -200,6 +215,19 @@ struct mlx5_flow_group * mlx5_create_flow_group(struct mlx5_flow_table *ft, u32 *in); void mlx5_destroy_flow_group(struct mlx5_flow_group *fg); +struct mlx5_exe_aso { + u32 object_id; + u8 type; + u8 return_reg_id; + union { + u32 ctrl_data; + struct { + u8 meter_idx; + u8 init_color; + } flow_meter; + }; +}; + struct mlx5_fs_vlan { u16 ethtype; u16 vid; @@ -217,13 +245,15 @@ struct mlx5_flow_act { u32 action; struct mlx5_modify_hdr *modify_hdr; struct mlx5_pkt_reformat *pkt_reformat; - union { - u32 ipsec_obj_id; - uintptr_t esp_id; - }; + struct mlx5_flow_act_crypto_params { + u8 type; + u32 obj_id; + } crypto; u32 flags; struct mlx5_fs_vlan vlan[MLX5_FS_VLAN_DEPTH]; struct ib_counters *counters; + struct mlx5_flow_group *fg; + struct mlx5_exe_aso exe_aso; }; #define MLX5_DECLARE_FLOW_ACT(name) \ @@ -288,4 +318,5 @@ struct mlx5_pkt_reformat *mlx5_packet_reformat_alloc(struct mlx5_core_dev *dev, void mlx5_packet_reformat_dealloc(struct mlx5_core_dev *dev, struct mlx5_pkt_reformat *reformat); +u32 mlx5_flow_table_id(struct mlx5_flow_table *ft); #endif diff --git a/include/linux/mlx5/fs_helpers.h b/include/linux/mlx5/fs_helpers.h index 9db21cd0e92c..bc5125bc0561 100644 --- a/include/linux/mlx5/fs_helpers.h +++ b/include/linux/mlx5/fs_helpers.h @@ -38,46 +38,6 @@ #define MLX5_FS_IPV4_VERSION 4 #define MLX5_FS_IPV6_VERSION 6 -static inline bool mlx5_fs_is_ipsec_flow(const u32 *match_c) -{ - void *misc_params_c = MLX5_ADDR_OF(fte_match_param, match_c, - misc_parameters); - - return MLX5_GET(fte_match_set_misc, misc_params_c, outer_esp_spi); -} - -static inline bool _mlx5_fs_is_outer_ipproto_flow(const u32 *match_c, - const u32 *match_v, u8 match) -{ - const void *headers_c = MLX5_ADDR_OF(fte_match_param, match_c, - outer_headers); - const void *headers_v = MLX5_ADDR_OF(fte_match_param, match_v, - outer_headers); - - return MLX5_GET(fte_match_set_lyr_2_4, headers_c, ip_protocol) == 0xff && - MLX5_GET(fte_match_set_lyr_2_4, headers_v, ip_protocol) == match; -} - -static inline bool mlx5_fs_is_outer_tcp_flow(const u32 *match_c, - const u32 *match_v) -{ - return _mlx5_fs_is_outer_ipproto_flow(match_c, match_v, IPPROTO_TCP); -} - -static inline bool mlx5_fs_is_outer_udp_flow(const u32 *match_c, - const u32 *match_v) -{ - return _mlx5_fs_is_outer_ipproto_flow(match_c, match_v, IPPROTO_UDP); -} - -static inline bool mlx5_fs_is_vxlan_flow(const u32 *match_c) -{ - void *misc_params_c = MLX5_ADDR_OF(fte_match_param, match_c, - misc_parameters); - - return MLX5_GET(fte_match_set_misc, misc_params_c, vxlan_vni); -} - static inline bool _mlx5_fs_is_outer_ipv_flow(struct mlx5_core_dev *mdev, const u32 *match_c, const u32 *match_v, int version) @@ -131,12 +91,4 @@ mlx5_fs_is_outer_ipv6_flow(struct mlx5_core_dev *mdev, const u32 *match_c, MLX5_FS_IPV6_VERSION); } -static inline bool mlx5_fs_is_outer_ipsec_flow(const u32 *match_c) -{ - void *misc_params_c = - MLX5_ADDR_OF(fte_match_param, match_c, misc_parameters); - - return MLX5_GET(fte_match_set_misc, misc_params_c, outer_esp_spi); -} - #endif diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 598ac3bcc901..5a4e914e2a6f 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -64,17 +64,11 @@ enum { }; enum { - MLX5_MODIFY_TIR_BITMASK_LRO = 0x0, - MLX5_MODIFY_TIR_BITMASK_INDIRECT_TABLE = 0x1, - MLX5_MODIFY_TIR_BITMASK_HASH = 0x2, - MLX5_MODIFY_TIR_BITMASK_TUNNELED_OFFLOAD_EN = 0x3 -}; - -enum { MLX5_SET_HCA_CAP_OP_MOD_GENERAL_DEVICE = 0x0, MLX5_SET_HCA_CAP_OP_MOD_ODP = 0x2, MLX5_SET_HCA_CAP_OP_MOD_ATOMIC = 0x3, MLX5_SET_HCA_CAP_OP_MOD_ROCE = 0x4, + MLX5_SET_HCA_CAP_OP_MODE_PORT_SELECTION = 0x25, }; enum { @@ -89,12 +83,15 @@ enum { MLX5_GENERAL_OBJ_TYPES_CAP_SW_ICM = (1ULL << MLX5_OBJ_TYPE_SW_ICM), MLX5_GENERAL_OBJ_TYPES_CAP_GENEVE_TLV_OPT = (1ULL << 11), MLX5_GENERAL_OBJ_TYPES_CAP_VIRTIO_NET_Q = (1ULL << 13), + MLX5_GENERAL_OBJ_TYPES_CAP_MACSEC_OFFLOAD = (1ULL << 39), }; enum { MLX5_OBJ_TYPE_GENEVE_TLV_OPT = 0x000b, MLX5_OBJ_TYPE_VIRTIO_NET_Q = 0x000d, + MLX5_OBJ_TYPE_VIRTIO_Q_COUNTERS = 0x001c, MLX5_OBJ_TYPE_MATCH_DEFINER = 0x0018, + MLX5_OBJ_TYPE_PAGE_TRACK = 0x46, MLX5_OBJ_TYPE_MKEY = 0xff01, MLX5_OBJ_TYPE_QP = 0xff02, MLX5_OBJ_TYPE_PSV = 0xff03, @@ -127,6 +124,11 @@ enum { MLX5_CMD_OP_QUERY_SF_PARTITION = 0x111, MLX5_CMD_OP_ALLOC_SF = 0x113, MLX5_CMD_OP_DEALLOC_SF = 0x114, + MLX5_CMD_OP_SUSPEND_VHCA = 0x115, + MLX5_CMD_OP_RESUME_VHCA = 0x116, + MLX5_CMD_OP_QUERY_VHCA_MIGRATION_STATE = 0x117, + MLX5_CMD_OP_SAVE_VHCA_STATE = 0x118, + MLX5_CMD_OP_LOAD_VHCA_STATE = 0x119, MLX5_CMD_OP_CREATE_MKEY = 0x200, MLX5_CMD_OP_QUERY_MKEY = 0x201, MLX5_CMD_OP_DESTROY_MKEY = 0x202, @@ -443,12 +445,19 @@ struct mlx5_ifc_flow_table_prop_layout_bits { u8 max_modify_header_actions[0x8]; u8 max_ft_level[0x8]; - u8 reserved_at_40[0x20]; + u8 reserved_at_40[0x6]; + u8 execute_aso[0x1]; + u8 reserved_at_47[0x19]; u8 reserved_at_60[0x2]; u8 reformat_insert[0x1]; u8 reformat_remove[0x1]; - u8 reserver_at_64[0x14]; + u8 macsec_encrypt[0x1]; + u8 macsec_decrypt[0x1]; + u8 reserved_at_66[0x2]; + u8 reformat_add_macsec[0x1]; + u8 reformat_remove_macsec[0x1]; + u8 reserved_at_6a[0xe]; u8 log_max_ft_num[0x8]; u8 reserved_at_80[0x10]; @@ -475,6 +484,22 @@ struct mlx5_ifc_odp_per_transport_service_cap_bits { u8 reserved_at_6[0x1a]; }; +struct mlx5_ifc_ipv4_layout_bits { + u8 reserved_at_0[0x60]; + + u8 ipv4[0x20]; +}; + +struct mlx5_ifc_ipv6_layout_bits { + u8 ipv6[16][0x8]; +}; + +union mlx5_ifc_ipv6_layout_ipv4_layout_auto_bits { + struct mlx5_ifc_ipv6_layout_bits ipv6_layout; + struct mlx5_ifc_ipv4_layout_bits ipv4_layout; + u8 reserved_at_0[0x80]; +}; + struct mlx5_ifc_fte_match_set_lyr_2_4_bits { u8 smac_47_16[0x20]; @@ -500,7 +525,10 @@ struct mlx5_ifc_fte_match_set_lyr_2_4_bits { u8 tcp_sport[0x10]; u8 tcp_dport[0x10]; - u8 reserved_at_c0[0x18]; + u8 reserved_at_c0[0x10]; + u8 ipv4_ihl[0x4]; + u8 reserved_at_c4[0x4]; + u8 ttl_hoplimit[0x8]; u8 udp_sport[0x10]; @@ -607,7 +635,11 @@ struct mlx5_ifc_fte_match_set_misc2_bits { u8 metadata_reg_a[0x20]; - u8 reserved_at_1a0[0x60]; + u8 reserved_at_1a0[0x8]; + + u8 macsec_syndrome[0x8]; + + u8 reserved_at_1b0[0x50]; }; struct mlx5_ifc_fte_match_set_misc3_bits { @@ -809,7 +841,9 @@ struct mlx5_ifc_flow_table_nic_cap_bits { struct mlx5_ifc_port_selection_cap_bits { u8 reserved_at_0[0x10]; u8 port_select_flow_table[0x1]; - u8 reserved_at_11[0xf]; + u8 reserved_at_11[0x1]; + u8 port_select_flow_table_bypass[0x1]; + u8 reserved_at_13[0xd]; u8 reserved_at_20[0x1e0]; @@ -938,7 +972,17 @@ struct mlx5_ifc_qos_cap_bits { u8 max_tsar_bw_share[0x20]; - u8 reserved_at_100[0x700]; + u8 reserved_at_100[0x20]; + + u8 reserved_at_120[0x3]; + u8 log_meter_aso_granularity[0x5]; + u8 reserved_at_128[0x3]; + u8 log_meter_aso_max_alloc[0x5]; + u8 reserved_at_130[0x3]; + u8 log_max_num_meter_aso[0x5]; + u8 reserved_at_138[0x8]; + + u8 reserved_at_140[0x6c0]; }; struct mlx5_ifc_debug_cap_bits { @@ -1084,11 +1128,14 @@ struct mlx5_ifc_device_mem_cap_bits { u8 log_sw_icm_alloc_granularity[0x6]; u8 log_steering_sw_icm_size[0x8]; - u8 reserved_at_120[0x20]; + u8 reserved_at_120[0x18]; + u8 log_header_modify_pattern_sw_icm_size[0x8]; u8 header_modify_sw_icm_start_address[0x40]; - u8 reserved_at_180[0x80]; + u8 reserved_at_180[0x40]; + + u8 header_modify_pattern_sw_icm_start_address[0x40]; u8 memic_operations[0x20]; @@ -1259,6 +1306,24 @@ struct mlx5_ifc_ipsec_cap_bits { u8 reserved_at_30[0x7d0]; }; +struct mlx5_ifc_macsec_cap_bits { + u8 macsec_epn[0x1]; + u8 reserved_at_1[0x2]; + u8 macsec_crypto_esp_aes_gcm_256_encrypt[0x1]; + u8 macsec_crypto_esp_aes_gcm_128_encrypt[0x1]; + u8 macsec_crypto_esp_aes_gcm_256_decrypt[0x1]; + u8 macsec_crypto_esp_aes_gcm_128_decrypt[0x1]; + u8 reserved_at_7[0x4]; + u8 log_max_macsec_offload[0x5]; + u8 reserved_at_10[0x10]; + + u8 min_log_macsec_full_replay_window[0x8]; + u8 max_log_macsec_full_replay_window[0x8]; + u8 reserved_at_30[0x10]; + + u8 reserved_at_40[0x7c0]; +}; + enum { MLX5_WQ_TYPE_LINKED_LIST = 0x0, MLX5_WQ_TYPE_CYCLIC = 0x1, @@ -1350,14 +1415,17 @@ enum mlx5_fc_bulk_alloc_bitmask { enum { MLX5_STEERING_FORMAT_CONNECTX_5 = 0, MLX5_STEERING_FORMAT_CONNECTX_6DX = 1, + MLX5_STEERING_FORMAT_CONNECTX_7 = 2, }; struct mlx5_ifc_cmd_hca_cap_bits { - u8 reserved_at_0[0x1f]; + u8 reserved_at_0[0x10]; + u8 shared_object_to_user_object_allowed[0x1]; + u8 reserved_at_13[0xe]; u8 vhca_resource_manager[0x1]; u8 hca_cap_2[0x1]; - u8 reserved_at_21[0x1]; + u8 create_lag_when_not_master_up[0x1]; u8 dtor[0x1]; u8 event_on_vhca_state_teardown_request[0x1]; u8 event_on_vhca_state_in_use[0x1]; @@ -1423,11 +1491,15 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_120[0xa]; u8 log_max_ra_req_dc[0x6]; - u8 reserved_at_130[0xa]; + u8 reserved_at_130[0x2]; + u8 eth_wqe_too_small[0x1]; + u8 reserved_at_133[0x6]; + u8 vnic_env_cq_overrun[0x1]; u8 log_max_ra_res_dc[0x6]; - u8 reserved_at_140[0x6]; + u8 reserved_at_140[0x5]; u8 release_all_pages[0x1]; + u8 must_not_use[0x1]; u8 reserved_at_147[0x2]; u8 roce_accl[0x1]; u8 log_max_ra_req_qp[0x6]; @@ -1617,7 +1689,11 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 nic_receive_steering_discard[0x1]; u8 receive_discard_vport_down[0x1]; u8 transmit_discard_vport_down[0x1]; - u8 reserved_at_343[0x5]; + u8 eq_overrun_count[0x1]; + u8 reserved_at_344[0x1]; + u8 invalid_command_count[0x1]; + u8 quota_exceeded_count[0x1]; + u8 reserved_at_347[0x1]; u8 log_max_flow_counter_bulk[0x8]; u8 max_flow_counter_15_0[0x10]; @@ -1681,7 +1757,9 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 steering_format_version[0x4]; u8 create_qp_start_hint[0x18]; - u8 reserved_at_460[0x3]; + u8 reserved_at_460[0x1]; + u8 ats[0x1]; + u8 reserved_at_462[0x1]; u8 log_max_uctx[0x5]; u8 reserved_at_468[0x2]; u8 ipsec_offload[0x1]; @@ -1707,7 +1785,9 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 max_geneve_tlv_options[0x8]; u8 reserved_at_568[0x3]; u8 max_geneve_tlv_option_data_len[0x5]; - u8 reserved_at_570[0x10]; + u8 reserved_at_570[0x9]; + u8 adv_virtualization[0x1]; + u8 reserved_at_57a[0x6]; u8 reserved_at_580[0xb]; u8 log_max_dci_stream_channels[0x5]; @@ -1715,7 +1795,9 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 log_max_dci_errored_streams[0x5]; u8 reserved_at_598[0x8]; - u8 reserved_at_5a0[0x13]; + u8 reserved_at_5a0[0x10]; + u8 enhanced_cqe_compression[0x1]; + u8 reserved_at_5b1[0x2]; u8 log_max_dek[0x5]; u8 reserved_at_5b8[0x4]; u8 mini_cqe_resp_stride_index[0x1]; @@ -1757,7 +1839,9 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_682[0x1]; u8 log_max_sf[0x5]; u8 apu[0x1]; - u8 reserved_at_689[0x7]; + u8 reserved_at_689[0x4]; + u8 migration[0x1]; + u8 reserved_at_68e[0x2]; u8 log_min_sf_size[0x8]; u8 max_num_sf_partitions[0x8]; @@ -1798,19 +1882,32 @@ struct mlx5_ifc_cmd_hca_cap_2_bits { u8 max_reformat_remove_size[0x8]; u8 max_reformat_remove_offset[0x8]; - u8 reserved_at_c0[0x740]; -}; + u8 reserved_at_c0[0xe0]; + + u8 reserved_at_1a0[0xb]; + u8 log_min_mkey_entity_size[0x5]; + u8 reserved_at_1b0[0x10]; + + u8 reserved_at_1c0[0x60]; + + u8 reserved_at_220[0x1]; + u8 sw_vhca_id_valid[0x1]; + u8 sw_vhca_id[0xe]; + u8 reserved_at_230[0x10]; + + u8 reserved_at_240[0xb]; + u8 ts_cqe_metadata_size2wqe_counter[0x5]; + u8 reserved_at_250[0x10]; -enum mlx5_flow_destination_type { - MLX5_FLOW_DESTINATION_TYPE_VPORT = 0x0, - MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE = 0x1, - MLX5_FLOW_DESTINATION_TYPE_TIR = 0x2, - MLX5_FLOW_DESTINATION_TYPE_FLOW_SAMPLER = 0x6, - MLX5_FLOW_DESTINATION_TYPE_UPLINK = 0x8, + u8 reserved_at_260[0x5a0]; +}; - MLX5_FLOW_DESTINATION_TYPE_PORT = 0x99, - MLX5_FLOW_DESTINATION_TYPE_COUNTER = 0x100, - MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE_NUM = 0x101, +enum mlx5_ifc_flow_destination_type { + MLX5_IFC_FLOW_DESTINATION_TYPE_VPORT = 0x0, + MLX5_IFC_FLOW_DESTINATION_TYPE_FLOW_TABLE = 0x1, + MLX5_IFC_FLOW_DESTINATION_TYPE_TIR = 0x2, + MLX5_IFC_FLOW_DESTINATION_TYPE_FLOW_SAMPLER = 0x6, + MLX5_IFC_FLOW_DESTINATION_TYPE_UPLINK = 0x8, }; enum mlx5_flow_table_miss_action { @@ -3258,6 +3355,7 @@ union mlx5_ifc_hca_cap_union_bits { struct mlx5_ifc_device_mem_cap_bits device_mem_cap; struct mlx5_ifc_virtio_emulation_cap_bits virtio_emulation_cap; struct mlx5_ifc_shampo_cap_bits shampo_cap; + struct mlx5_ifc_macsec_cap_bits macsec_cap; u8 reserved_at_0[0x8000]; }; @@ -3273,8 +3371,9 @@ enum { MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH = 0x100, MLX5_FLOW_CONTEXT_ACTION_VLAN_POP_2 = 0x400, MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH_2 = 0x800, - MLX5_FLOW_CONTEXT_ACTION_IPSEC_DECRYPT = 0x1000, - MLX5_FLOW_CONTEXT_ACTION_IPSEC_ENCRYPT = 0x2000, + MLX5_FLOW_CONTEXT_ACTION_CRYPTO_DECRYPT = 0x1000, + MLX5_FLOW_CONTEXT_ACTION_CRYPTO_ENCRYPT = 0x2000, + MLX5_FLOW_CONTEXT_ACTION_EXECUTE_ASO = 0x4000, }; enum { @@ -3283,6 +3382,11 @@ enum { MLX5_FLOW_CONTEXT_FLOW_SOURCE_LOCAL_VPORT = 0x2, }; +enum { + MLX5_FLOW_CONTEXT_ENCRYPT_DECRYPT_TYPE_IPSEC = 0x0, + MLX5_FLOW_CONTEXT_ENCRYPT_DECRYPT_TYPE_MACSEC = 0x1, +}; + struct mlx5_ifc_vlan_bits { u8 ethtype[0x10]; u8 prio[0x3]; @@ -3290,6 +3394,38 @@ struct mlx5_ifc_vlan_bits { u8 vid[0xc]; }; +enum { + MLX5_FLOW_METER_COLOR_RED = 0x0, + MLX5_FLOW_METER_COLOR_YELLOW = 0x1, + MLX5_FLOW_METER_COLOR_GREEN = 0x2, + MLX5_FLOW_METER_COLOR_UNDEFINED = 0x3, +}; + +enum { + MLX5_EXE_ASO_FLOW_METER = 0x2, +}; + +struct mlx5_ifc_exe_aso_ctrl_flow_meter_bits { + u8 return_reg_id[0x4]; + u8 aso_type[0x4]; + u8 reserved_at_8[0x14]; + u8 action[0x1]; + u8 init_color[0x2]; + u8 meter_id[0x1]; +}; + +union mlx5_ifc_exe_aso_ctrl { + struct mlx5_ifc_exe_aso_ctrl_flow_meter_bits exe_aso_ctrl_flow_meter; +}; + +struct mlx5_ifc_execute_aso_bits { + u8 valid[0x1]; + u8 reserved_at_1[0x7]; + u8 aso_object_id[0x18]; + + union mlx5_ifc_exe_aso_ctrl exe_aso_ctrl; +}; + struct mlx5_ifc_flow_context_bits { struct mlx5_ifc_vlan_bits push_vlan; @@ -3304,7 +3440,7 @@ struct mlx5_ifc_flow_context_bits { u8 extended_destination[0x1]; u8 reserved_at_81[0x1]; u8 flow_source[0x2]; - u8 reserved_at_84[0x4]; + u8 encrypt_decrypt_type[0x4]; u8 destination_list_size[0x18]; u8 reserved_at_a0[0x8]; @@ -3316,12 +3452,14 @@ struct mlx5_ifc_flow_context_bits { struct mlx5_ifc_vlan_bits push_vlan_2; - u8 ipsec_obj_id[0x20]; + u8 encrypt_decrypt_obj_id[0x20]; u8 reserved_at_140[0xc0]; struct mlx5_ifc_fte_match_param_bits match_value; - u8 reserved_at_1200[0x600]; + struct mlx5_ifc_execute_aso_bits execute_aso[4]; + + u8 reserved_at_1300[0x500]; union mlx5_ifc_dest_format_struct_flow_counter_list_auto_bits destination[]; }; @@ -3389,11 +3527,23 @@ struct mlx5_ifc_vnic_diagnostic_statistics_bits { u8 transmit_discard_vport_down[0x40]; - u8 reserved_at_140[0xa0]; + u8 async_eq_overrun[0x20]; + + u8 comp_eq_overrun[0x20]; + + u8 reserved_at_180[0x20]; + + u8 invalid_command[0x20]; + + u8 quota_exceeded_command[0x20]; u8 internal_rq_out_of_buffer[0x20]; - u8 reserved_at_200[0xe00]; + u8 cq_overrun[0x20]; + + u8 eth_wqe_too_small[0x20]; + + u8 reserved_at_220[0xdc0]; }; struct mlx5_ifc_traffic_counter_bits { @@ -3434,7 +3584,6 @@ enum { enum { MLX5_TIRC_PACKET_MERGE_MASK_IPV4_LRO = BIT(0), MLX5_TIRC_PACKET_MERGE_MASK_IPV6_LRO = BIT(1), - MLX5_TIRC_PACKET_MERGE_MASK_SHAMPO = BIT(2), }; enum { @@ -3714,6 +3863,11 @@ struct mlx5_ifc_rmpc_bits { struct mlx5_ifc_wq_bits wq; }; +enum { + VHCA_ID_TYPE_HW = 0, + VHCA_ID_TYPE_SW = 1, +}; + struct mlx5_ifc_nic_vport_context_bits { u8 reserved_at_0[0x5]; u8 min_wqe_inline_mode[0x3]; @@ -3730,8 +3884,8 @@ struct mlx5_ifc_nic_vport_context_bits { u8 event_on_mc_address_change[0x1]; u8 event_on_uc_address_change[0x1]; - u8 reserved_at_40[0xc]; - + u8 vhca_id_type[0x1]; + u8 reserved_at_41[0xb]; u8 affiliation_criteria[0x4]; u8 affiliated_vhca_id[0x10]; @@ -3787,7 +3941,9 @@ struct mlx5_ifc_mkc_bits { u8 lw[0x1]; u8 lr[0x1]; u8 access_mode_1_0[0x2]; - u8 reserved_at_18[0x8]; + u8 reserved_at_18[0x2]; + u8 ma_translation_mode[0x2]; + u8 reserved_at_1c[0x4]; u8 qpn[0x18]; u8 mkey_7_0[0x8]; @@ -4073,7 +4229,8 @@ struct mlx5_ifc_cqc_bits { u8 cqe_comp_en[0x1]; u8 mini_cqe_res_format[0x2]; u8 st[0x4]; - u8 reserved_at_18[0x8]; + u8 reserved_at_18[0x6]; + u8 cqe_compression_layout[0x2]; u8 reserved_at_20[0x20]; @@ -5176,12 +5333,11 @@ struct mlx5_ifc_query_qp_out_bits { u8 syndrome[0x20]; - u8 reserved_at_40[0x20]; - u8 ece[0x20]; + u8 reserved_at_40[0x40]; u8 opt_param_mask[0x20]; - u8 reserved_at_a0[0x20]; + u8 ece[0x20]; struct mlx5_ifc_qpc_bits qpc; @@ -5970,7 +6126,9 @@ struct mlx5_ifc_general_obj_in_cmd_hdr_bits { u8 obj_id[0x20]; - u8 reserved_at_60[0x20]; + u8 reserved_at_60[0x3]; + u8 log_obj_range[0x5]; + u8 reserved_at_68[0x18]; }; struct mlx5_ifc_general_obj_out_cmd_hdr_bits { @@ -6228,6 +6386,8 @@ enum mlx5_reformat_ctx_type { MLX5_REFORMAT_TYPE_L2_TO_L3_TUNNEL = 0x4, MLX5_REFORMAT_TYPE_INSERT_HDR = 0xf, MLX5_REFORMAT_TYPE_REMOVE_HDR = 0x10, + MLX5_REFORMAT_TYPE_ADD_MACSEC = 0x11, + MLX5_REFORMAT_TYPE_DEL_MACSEC = 0x12, }; struct mlx5_ifc_alloc_packet_reformat_context_in_bits { @@ -7189,7 +7349,12 @@ struct mlx5_ifc_init_hca_in_bits { u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_at_40[0x40]; + u8 reserved_at_40[0x20]; + + u8 reserved_at_60[0x2]; + u8 sw_vhca_id[0xe]; + u8 reserved_at_70[0x10]; + u8 sw_owner_id[4][0x20]; }; @@ -8437,7 +8602,7 @@ struct mlx5_ifc_create_flow_table_out_bits { struct mlx5_ifc_create_flow_table_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -9694,7 +9859,12 @@ struct mlx5_ifc_pcam_reg_bits { }; struct mlx5_ifc_mcam_enhanced_features_bits { - u8 reserved_at_0[0x6b]; + u8 reserved_at_0[0x5d]; + u8 mcia_32dwords[0x1]; + u8 out_pulse_duration_ns[0x1]; + u8 npps_period[0x1]; + u8 reserved_at_60[0xa]; + u8 reset_state[0x1]; u8 ptpcyc2realtime_modify[0x1]; u8 reserved_at_6c[0x2]; u8 pci_status_and_power[0x1]; @@ -9888,10 +10058,10 @@ struct mlx5_ifc_pcmr_reg_bits { }; struct mlx5_ifc_lane_2_module_mapping_bits { - u8 reserved_at_0[0x6]; - u8 rx_lane[0x2]; - u8 reserved_at_8[0x6]; - u8 tx_lane[0x2]; + u8 reserved_at_0[0x4]; + u8 rx_lane[0x4]; + u8 reserved_at_8[0x4]; + u8 tx_lane[0x4]; u8 reserved_at_10[0x8]; u8 module[0x8]; }; @@ -9900,8 +10070,8 @@ struct mlx5_ifc_bufferx_reg_bits { u8 reserved_at_0[0x6]; u8 lossy[0x1]; u8 epsb[0x1]; - u8 reserved_at_8[0xc]; - u8 size[0xc]; + u8 reserved_at_8[0x8]; + u8 size[0x10]; u8 xoff_threshold[0x10]; u8 xon_threshold[0x10]; @@ -10193,7 +10363,12 @@ struct mlx5_ifc_mtpps_reg_bits { u8 reserved_at_18[0x4]; u8 cap_max_num_of_pps_out_pins[0x4]; - u8 reserved_at_20[0x24]; + u8 reserved_at_20[0x13]; + u8 cap_log_min_npps_period[0x5]; + u8 reserved_at_38[0x3]; + u8 cap_log_min_out_pulse_duration_ns[0x5]; + + u8 reserved_at_40[0x4]; u8 cap_pin_3_mode[0x4]; u8 reserved_at_48[0x4]; u8 cap_pin_2_mode[0x4]; @@ -10212,7 +10387,9 @@ struct mlx5_ifc_mtpps_reg_bits { u8 cap_pin_4_mode[0x4]; u8 field_select[0x20]; - u8 reserved_at_a0[0x60]; + u8 reserved_at_a0[0x20]; + + u8 npps_period[0x40]; u8 enable[0x1]; u8 reserved_at_101[0xb]; @@ -10221,7 +10398,8 @@ struct mlx5_ifc_mtpps_reg_bits { u8 pin_mode[0x4]; u8 pin[0x8]; - u8 reserved_at_120[0x20]; + u8 reserved_at_120[0x2]; + u8 out_pulse_duration_ns[0x1e]; u8 time_stamp[0x40]; @@ -10376,6 +10554,14 @@ struct mlx5_ifc_mcda_reg_bits { }; enum { + MLX5_MFRL_REG_RESET_STATE_IDLE = 0, + MLX5_MFRL_REG_RESET_STATE_IN_NEGOTIATION = 1, + MLX5_MFRL_REG_RESET_STATE_RESET_IN_PROGRESS = 2, + MLX5_MFRL_REG_RESET_STATE_TIMEOUT = 3, + MLX5_MFRL_REG_RESET_STATE_NACK = 4, +}; + +enum { MLX5_MFRL_REG_RESET_TYPE_FULL_CHIP = BIT(0), MLX5_MFRL_REG_RESET_TYPE_NET_PORT_ALIVE = BIT(1), }; @@ -10393,7 +10579,8 @@ struct mlx5_ifc_mfrl_reg_bits { u8 pci_sync_for_fw_update_start[0x1]; u8 pci_sync_for_fw_update_resp[0x2]; u8 rst_type_sel[0x3]; - u8 reserved_at_28[0x8]; + u8 reserved_at_28[0x4]; + u8 reset_state[0x4]; u8 reset_type[0x8]; u8 reset_level[0x8]; }; @@ -10804,7 +10991,8 @@ struct mlx5_ifc_dcbx_param_bits { enum { MLX5_LAG_PORT_SELECT_MODE_QUEUE_AFFINITY = 0, - MLX5_LAG_PORT_SELECT_MODE_PORT_SELECT_FT, + MLX5_LAG_PORT_SELECT_MODE_PORT_SELECT_FT = 1, + MLX5_LAG_PORT_SELECT_MODE_PORT_SELECT_MPESW = 2, }; struct mlx5_ifc_lagc_bits { @@ -10814,7 +11002,9 @@ struct mlx5_ifc_lagc_bits { u8 reserved_at_18[0x5]; u8 lag_state[0x3]; - u8 reserved_at_20[0x14]; + u8 reserved_at_20[0xc]; + u8 active_port[0x4]; + u8 reserved_at_30[0x4]; u8 tx_remap_affinity_2[0x4]; u8 reserved_at_38[0x4]; u8 tx_remap_affinity_1[0x4]; @@ -11028,7 +11218,8 @@ struct mlx5_ifc_dealloc_memic_out_bits { struct mlx5_ifc_umem_bits { u8 reserved_at_0[0x80]; - u8 reserved_at_80[0x1b]; + u8 ats[0x1]; + u8 reserved_at_81[0x1a]; u8 log_page_size[0x5]; u8 page_offset[0x20]; @@ -11357,18 +11548,19 @@ enum { MLX5_HCA_CAP_GENERAL_OBJECT_TYPES_ENCRYPTION_KEY = BIT_ULL(0xc), MLX5_HCA_CAP_GENERAL_OBJECT_TYPES_IPSEC = BIT_ULL(0x13), MLX5_HCA_CAP_GENERAL_OBJECT_TYPES_SAMPLER = BIT_ULL(0x20), + MLX5_HCA_CAP_GENERAL_OBJECT_TYPES_FLOW_METER_ASO = BIT_ULL(0x24), }; enum { MLX5_GENERAL_OBJECT_TYPES_ENCRYPTION_KEY = 0xc, MLX5_GENERAL_OBJECT_TYPES_IPSEC = 0x13, MLX5_GENERAL_OBJECT_TYPES_SAMPLER = 0x20, + MLX5_GENERAL_OBJECT_TYPES_FLOW_METER_ASO = 0x24, + MLX5_GENERAL_OBJECT_TYPES_MACSEC = 0x27, }; enum { MLX5_IPSEC_OBJECT_ICV_LEN_16B, - MLX5_IPSEC_OBJECT_ICV_LEN_12B, - MLX5_IPSEC_OBJECT_ICV_LEN_8B, }; struct mlx5_ifc_ipsec_obj_bits { @@ -11415,6 +11607,96 @@ struct mlx5_ifc_modify_ipsec_obj_in_bits { struct mlx5_ifc_ipsec_obj_bits ipsec_object; }; +enum { + MLX5_MACSEC_ASO_REPLAY_PROTECTION = 0x1, +}; + +enum { + MLX5_MACSEC_ASO_REPLAY_WIN_32BIT = 0x0, + MLX5_MACSEC_ASO_REPLAY_WIN_64BIT = 0x1, + MLX5_MACSEC_ASO_REPLAY_WIN_128BIT = 0x2, + MLX5_MACSEC_ASO_REPLAY_WIN_256BIT = 0x3, +}; + +#define MLX5_MACSEC_ASO_INC_SN 0x2 +#define MLX5_MACSEC_ASO_REG_C_4_5 0x2 + +struct mlx5_ifc_macsec_aso_bits { + u8 valid[0x1]; + u8 reserved_at_1[0x1]; + u8 mode[0x2]; + u8 window_size[0x2]; + u8 soft_lifetime_arm[0x1]; + u8 hard_lifetime_arm[0x1]; + u8 remove_flow_enable[0x1]; + u8 epn_event_arm[0x1]; + u8 reserved_at_a[0x16]; + + u8 remove_flow_packet_count[0x20]; + + u8 remove_flow_soft_lifetime[0x20]; + + u8 reserved_at_60[0x80]; + + u8 mode_parameter[0x20]; + + u8 replay_protection_window[8][0x20]; +}; + +struct mlx5_ifc_macsec_offload_obj_bits { + u8 modify_field_select[0x40]; + + u8 confidentiality_en[0x1]; + u8 reserved_at_41[0x1]; + u8 epn_en[0x1]; + u8 epn_overlap[0x1]; + u8 reserved_at_44[0x2]; + u8 confidentiality_offset[0x2]; + u8 reserved_at_48[0x4]; + u8 aso_return_reg[0x4]; + u8 reserved_at_50[0x10]; + + u8 epn_msb[0x20]; + + u8 reserved_at_80[0x8]; + u8 dekn[0x18]; + + u8 reserved_at_a0[0x20]; + + u8 sci[0x40]; + + u8 reserved_at_100[0x8]; + u8 macsec_aso_access_pd[0x18]; + + u8 reserved_at_120[0x60]; + + u8 salt[3][0x20]; + + u8 reserved_at_1e0[0x20]; + + struct mlx5_ifc_macsec_aso_bits macsec_aso; +}; + +struct mlx5_ifc_create_macsec_obj_in_bits { + struct mlx5_ifc_general_obj_in_cmd_hdr_bits general_obj_in_cmd_hdr; + struct mlx5_ifc_macsec_offload_obj_bits macsec_object; +}; + +struct mlx5_ifc_modify_macsec_obj_in_bits { + struct mlx5_ifc_general_obj_in_cmd_hdr_bits general_obj_in_cmd_hdr; + struct mlx5_ifc_macsec_offload_obj_bits macsec_object; +}; + +enum { + MLX5_MODIFY_MACSEC_BITMASK_EPN_OVERLAP = BIT(0), + MLX5_MODIFY_MACSEC_BITMASK_EPN_MSB = BIT(1), +}; + +struct mlx5_ifc_query_macsec_obj_out_bits { + struct mlx5_ifc_general_obj_out_cmd_hdr_bits general_obj_out_cmd_hdr; + struct mlx5_ifc_macsec_offload_obj_bits macsec_object; +}; + struct mlx5_ifc_encryption_key_obj_bits { u8 modify_field_select[0x40]; @@ -11437,6 +11719,61 @@ struct mlx5_ifc_create_encryption_key_in_bits { struct mlx5_ifc_encryption_key_obj_bits encryption_key_object; }; +enum { + MLX5_FLOW_METER_MODE_BYTES_IP_LENGTH = 0x0, + MLX5_FLOW_METER_MODE_BYTES_CALC_WITH_L2 = 0x1, + MLX5_FLOW_METER_MODE_BYTES_CALC_WITH_L2_IPG = 0x2, + MLX5_FLOW_METER_MODE_NUM_PACKETS = 0x3, +}; + +struct mlx5_ifc_flow_meter_parameters_bits { + u8 valid[0x1]; + u8 bucket_overflow[0x1]; + u8 start_color[0x2]; + u8 both_buckets_on_green[0x1]; + u8 reserved_at_5[0x1]; + u8 meter_mode[0x2]; + u8 reserved_at_8[0x18]; + + u8 reserved_at_20[0x20]; + + u8 reserved_at_40[0x3]; + u8 cbs_exponent[0x5]; + u8 cbs_mantissa[0x8]; + u8 reserved_at_50[0x3]; + u8 cir_exponent[0x5]; + u8 cir_mantissa[0x8]; + + u8 reserved_at_60[0x20]; + + u8 reserved_at_80[0x3]; + u8 ebs_exponent[0x5]; + u8 ebs_mantissa[0x8]; + u8 reserved_at_90[0x3]; + u8 eir_exponent[0x5]; + u8 eir_mantissa[0x8]; + + u8 reserved_at_a0[0x60]; +}; + +struct mlx5_ifc_flow_meter_aso_obj_bits { + u8 modify_field_select[0x40]; + + u8 reserved_at_40[0x40]; + + u8 reserved_at_80[0x8]; + u8 meter_aso_access_pd[0x18]; + + u8 reserved_at_a0[0x160]; + + struct mlx5_ifc_flow_meter_parameters_bits flow_meter_parameters[2]; +}; + +struct mlx5_ifc_create_flow_meter_aso_obj_in_bits { + struct mlx5_ifc_general_obj_in_cmd_hdr_bits hdr; + struct mlx5_ifc_flow_meter_aso_obj_bits flow_meter_aso_obj; +}; + struct mlx5_ifc_sampler_obj_bits { u8 modify_field_select[0x40]; @@ -11477,6 +11814,7 @@ enum { enum { MLX5_GENERAL_OBJECT_TYPE_ENCRYPTION_KEY_TYPE_TLS = 0x1, MLX5_GENERAL_OBJECT_TYPE_ENCRYPTION_KEY_TYPE_IPSEC = 0x2, + MLX5_GENERAL_OBJECT_TYPE_ENCRYPTION_KEY_TYPE_MACSEC = 0x4, }; struct mlx5_ifc_tls_static_params_bits { @@ -11519,4 +11857,220 @@ enum { MLX5_MTT_PERM_RW = MLX5_MTT_PERM_READ | MLX5_MTT_PERM_WRITE, }; +enum { + MLX5_SUSPEND_VHCA_IN_OP_MOD_SUSPEND_INITIATOR = 0x0, + MLX5_SUSPEND_VHCA_IN_OP_MOD_SUSPEND_RESPONDER = 0x1, +}; + +struct mlx5_ifc_suspend_vhca_in_bits { + u8 opcode[0x10]; + u8 uid[0x10]; + + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + + u8 reserved_at_40[0x10]; + u8 vhca_id[0x10]; + + u8 reserved_at_60[0x20]; +}; + +struct mlx5_ifc_suspend_vhca_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_at_40[0x40]; +}; + +enum { + MLX5_RESUME_VHCA_IN_OP_MOD_RESUME_RESPONDER = 0x0, + MLX5_RESUME_VHCA_IN_OP_MOD_RESUME_INITIATOR = 0x1, +}; + +struct mlx5_ifc_resume_vhca_in_bits { + u8 opcode[0x10]; + u8 uid[0x10]; + + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + + u8 reserved_at_40[0x10]; + u8 vhca_id[0x10]; + + u8 reserved_at_60[0x20]; +}; + +struct mlx5_ifc_resume_vhca_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_at_40[0x40]; +}; + +struct mlx5_ifc_query_vhca_migration_state_in_bits { + u8 opcode[0x10]; + u8 uid[0x10]; + + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + + u8 reserved_at_40[0x10]; + u8 vhca_id[0x10]; + + u8 reserved_at_60[0x20]; +}; + +struct mlx5_ifc_query_vhca_migration_state_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_at_40[0x40]; + + u8 required_umem_size[0x20]; + + u8 reserved_at_a0[0x160]; +}; + +struct mlx5_ifc_save_vhca_state_in_bits { + u8 opcode[0x10]; + u8 uid[0x10]; + + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + + u8 reserved_at_40[0x10]; + u8 vhca_id[0x10]; + + u8 reserved_at_60[0x20]; + + u8 va[0x40]; + + u8 mkey[0x20]; + + u8 size[0x20]; +}; + +struct mlx5_ifc_save_vhca_state_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 actual_image_size[0x20]; + + u8 reserved_at_60[0x20]; +}; + +struct mlx5_ifc_load_vhca_state_in_bits { + u8 opcode[0x10]; + u8 uid[0x10]; + + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + + u8 reserved_at_40[0x10]; + u8 vhca_id[0x10]; + + u8 reserved_at_60[0x20]; + + u8 va[0x40]; + + u8 mkey[0x20]; + + u8 size[0x20]; +}; + +struct mlx5_ifc_load_vhca_state_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_at_40[0x40]; +}; + +struct mlx5_ifc_adv_virtualization_cap_bits { + u8 reserved_at_0[0x3]; + u8 pg_track_log_max_num[0x5]; + u8 pg_track_max_num_range[0x8]; + u8 pg_track_log_min_addr_space[0x8]; + u8 pg_track_log_max_addr_space[0x8]; + + u8 reserved_at_20[0x3]; + u8 pg_track_log_min_msg_size[0x5]; + u8 reserved_at_28[0x3]; + u8 pg_track_log_max_msg_size[0x5]; + u8 reserved_at_30[0x3]; + u8 pg_track_log_min_page_size[0x5]; + u8 reserved_at_38[0x3]; + u8 pg_track_log_max_page_size[0x5]; + + u8 reserved_at_40[0x7c0]; +}; + +struct mlx5_ifc_page_track_report_entry_bits { + u8 dirty_address_high[0x20]; + + u8 dirty_address_low[0x20]; +}; + +enum { + MLX5_PAGE_TRACK_STATE_TRACKING, + MLX5_PAGE_TRACK_STATE_REPORTING, + MLX5_PAGE_TRACK_STATE_ERROR, +}; + +struct mlx5_ifc_page_track_range_bits { + u8 start_address[0x40]; + + u8 length[0x40]; +}; + +struct mlx5_ifc_page_track_bits { + u8 modify_field_select[0x40]; + + u8 reserved_at_40[0x10]; + u8 vhca_id[0x10]; + + u8 reserved_at_60[0x20]; + + u8 state[0x4]; + u8 track_type[0x4]; + u8 log_addr_space_size[0x8]; + u8 reserved_at_90[0x3]; + u8 log_page_size[0x5]; + u8 reserved_at_98[0x3]; + u8 log_msg_size[0x5]; + + u8 reserved_at_a0[0x8]; + u8 reporting_qpn[0x18]; + + u8 reserved_at_c0[0x18]; + u8 num_ranges[0x8]; + + u8 reserved_at_e0[0x20]; + + u8 range_start_address[0x40]; + + u8 length[0x40]; + + struct mlx5_ifc_page_track_range_bits track_range[0]; +}; + +struct mlx5_ifc_create_page_track_obj_in_bits { + struct mlx5_ifc_general_obj_in_cmd_hdr_bits general_obj_in_cmd_hdr; + struct mlx5_ifc_page_track_bits obj_context; +}; + +struct mlx5_ifc_modify_page_track_obj_in_bits { + struct mlx5_ifc_general_obj_in_cmd_hdr_bits general_obj_in_cmd_hdr; + struct mlx5_ifc_page_track_bits obj_context; +}; + #endif /* MLX5_IFC_H */ diff --git a/include/linux/mlx5/mlx5_ifc_fpga.h b/include/linux/mlx5/mlx5_ifc_fpga.h index 07d77323f78a..0596472923ad 100644 --- a/include/linux/mlx5/mlx5_ifc_fpga.h +++ b/include/linux/mlx5/mlx5_ifc_fpga.h @@ -32,31 +32,6 @@ #ifndef MLX5_IFC_FPGA_H #define MLX5_IFC_FPGA_H -struct mlx5_ifc_ipv4_layout_bits { - u8 reserved_at_0[0x60]; - - u8 ipv4[0x20]; -}; - -struct mlx5_ifc_ipv6_layout_bits { - u8 ipv6[16][0x8]; -}; - -union mlx5_ifc_ipv6_layout_ipv4_layout_auto_bits { - struct mlx5_ifc_ipv6_layout_bits ipv6_layout; - struct mlx5_ifc_ipv4_layout_bits ipv4_layout; - u8 reserved_at_0[0x80]; -}; - -enum { - MLX5_FPGA_CAP_SANDBOX_VENDOR_ID_MLNX = 0x2c9, -}; - -enum { - MLX5_FPGA_CAP_SANDBOX_PRODUCT_ID_IPSEC = 0x2, - MLX5_FPGA_CAP_SANDBOX_PRODUCT_ID_TLS = 0x3, -}; - struct mlx5_ifc_fpga_shell_caps_bits { u8 max_num_qps[0x10]; u8 reserved_at_10[0x8]; @@ -387,89 +362,6 @@ struct mlx5_ifc_fpga_destroy_qp_out_bits { u8 reserved_at_40[0x40]; }; -struct mlx5_ifc_tls_extended_cap_bits { - u8 aes_gcm_128[0x1]; - u8 aes_gcm_256[0x1]; - u8 reserved_at_2[0x1e]; - u8 reserved_at_20[0x20]; - u8 context_capacity_total[0x20]; - u8 context_capacity_rx[0x20]; - u8 context_capacity_tx[0x20]; - u8 reserved_at_a0[0x10]; - u8 tls_counter_size[0x10]; - u8 tls_counters_addr_low[0x20]; - u8 tls_counters_addr_high[0x20]; - u8 rx[0x1]; - u8 tx[0x1]; - u8 tls_v12[0x1]; - u8 tls_v13[0x1]; - u8 lro[0x1]; - u8 ipv6[0x1]; - u8 reserved_at_106[0x1a]; -}; - -struct mlx5_ifc_ipsec_extended_cap_bits { - u8 encapsulation[0x20]; - - u8 reserved_0[0x12]; - u8 v2_command[0x1]; - u8 udp_encap[0x1]; - u8 rx_no_trailer[0x1]; - u8 ipv4_fragment[0x1]; - u8 ipv6[0x1]; - u8 esn[0x1]; - u8 lso[0x1]; - u8 transport_and_tunnel_mode[0x1]; - u8 tunnel_mode[0x1]; - u8 transport_mode[0x1]; - u8 ah_esp[0x1]; - u8 esp[0x1]; - u8 ah[0x1]; - u8 ipv4_options[0x1]; - - u8 auth_alg[0x20]; - - u8 enc_alg[0x20]; - - u8 sa_cap[0x20]; - - u8 reserved_1[0x10]; - u8 number_of_ipsec_counters[0x10]; - - u8 ipsec_counters_addr_low[0x20]; - u8 ipsec_counters_addr_high[0x20]; -}; - -struct mlx5_ifc_ipsec_counters_bits { - u8 dec_in_packets[0x40]; - - u8 dec_out_packets[0x40]; - - u8 dec_bypass_packets[0x40]; - - u8 enc_in_packets[0x40]; - - u8 enc_out_packets[0x40]; - - u8 enc_bypass_packets[0x40]; - - u8 drop_dec_packets[0x40]; - - u8 failed_auth_dec_packets[0x40]; - - u8 drop_enc_packets[0x40]; - - u8 success_add_sa[0x40]; - - u8 fail_add_sa[0x40]; - - u8 success_delete_sa[0x40]; - - u8 fail_delete_sa[0x40]; - - u8 dropped_cmd[0x40]; -}; - enum { MLX5_FPGA_QP_ERROR_EVENT_SYNDROME_RETRY_COUNTER_EXPIRED = 0x1, MLX5_FPGA_QP_ERROR_EVENT_SYNDROME_RNR_EXPIRED = 0x2, @@ -486,131 +378,4 @@ struct mlx5_ifc_fpga_qp_error_event_bits { u8 reserved_at_c0[0x8]; u8 fpga_qpn[0x18]; }; -enum mlx5_ifc_fpga_ipsec_response_syndrome { - MLX5_FPGA_IPSEC_RESPONSE_SUCCESS = 0, - MLX5_FPGA_IPSEC_RESPONSE_ILLEGAL_REQUEST = 1, - MLX5_FPGA_IPSEC_RESPONSE_SADB_ISSUE = 2, - MLX5_FPGA_IPSEC_RESPONSE_WRITE_RESPONSE_ISSUE = 3, -}; - -struct mlx5_ifc_fpga_ipsec_cmd_resp { - __be32 syndrome; - union { - __be32 sw_sa_handle; - __be32 flags; - }; - u8 reserved[24]; -} __packed; - -enum mlx5_ifc_fpga_ipsec_cmd_opcode { - MLX5_FPGA_IPSEC_CMD_OP_ADD_SA = 0, - MLX5_FPGA_IPSEC_CMD_OP_DEL_SA = 1, - MLX5_FPGA_IPSEC_CMD_OP_ADD_SA_V2 = 2, - MLX5_FPGA_IPSEC_CMD_OP_DEL_SA_V2 = 3, - MLX5_FPGA_IPSEC_CMD_OP_MOD_SA_V2 = 4, - MLX5_FPGA_IPSEC_CMD_OP_SET_CAP = 5, -}; - -enum mlx5_ifc_fpga_ipsec_cap { - MLX5_FPGA_IPSEC_CAP_NO_TRAILER = BIT(0), -}; - -struct mlx5_ifc_fpga_ipsec_cmd_cap { - __be32 cmd; - __be32 flags; - u8 reserved[24]; -} __packed; - -enum mlx5_ifc_fpga_ipsec_sa_flags { - MLX5_FPGA_IPSEC_SA_ESN_EN = BIT(0), - MLX5_FPGA_IPSEC_SA_ESN_OVERLAP = BIT(1), - MLX5_FPGA_IPSEC_SA_IPV6 = BIT(2), - MLX5_FPGA_IPSEC_SA_DIR_SX = BIT(3), - MLX5_FPGA_IPSEC_SA_SPI_EN = BIT(4), - MLX5_FPGA_IPSEC_SA_SA_VALID = BIT(5), - MLX5_FPGA_IPSEC_SA_IP_ESP = BIT(6), - MLX5_FPGA_IPSEC_SA_IP_AH = BIT(7), -}; - -enum mlx5_ifc_fpga_ipsec_sa_enc_mode { - MLX5_FPGA_IPSEC_SA_ENC_MODE_NONE = 0, - MLX5_FPGA_IPSEC_SA_ENC_MODE_AES_GCM_128_AUTH_128 = 1, - MLX5_FPGA_IPSEC_SA_ENC_MODE_AES_GCM_256_AUTH_128 = 3, -}; - -struct mlx5_ifc_fpga_ipsec_sa_v1 { - __be32 cmd; - u8 key_enc[32]; - u8 key_auth[32]; - __be32 sip[4]; - __be32 dip[4]; - union { - struct { - __be32 reserved; - u8 salt_iv[8]; - __be32 salt; - } __packed gcm; - struct { - u8 salt[16]; - } __packed cbc; - }; - __be32 spi; - __be32 sw_sa_handle; - __be16 tfclen; - u8 enc_mode; - u8 reserved1[2]; - u8 flags; - u8 reserved2[2]; -}; - -struct mlx5_ifc_fpga_ipsec_sa { - struct mlx5_ifc_fpga_ipsec_sa_v1 ipsec_sa_v1; - __be16 udp_sp; - __be16 udp_dp; - u8 reserved1[4]; - __be32 esn; - __be16 vid; /* only 12 bits, rest is reserved */ - __be16 reserved2; -} __packed; - -enum fpga_tls_cmds { - CMD_SETUP_STREAM = 0x1001, - CMD_TEARDOWN_STREAM = 0x1002, - CMD_RESYNC_RX = 0x1003, -}; - -#define MLX5_TLS_1_2 (0) - -#define MLX5_TLS_ALG_AES_GCM_128 (0) -#define MLX5_TLS_ALG_AES_GCM_256 (1) - -struct mlx5_ifc_tls_cmd_bits { - u8 command_type[0x20]; - u8 ipv6[0x1]; - u8 direction_sx[0x1]; - u8 tls_version[0x2]; - u8 reserved[0x1c]; - u8 swid[0x20]; - u8 src_port[0x10]; - u8 dst_port[0x10]; - union mlx5_ifc_ipv6_layout_ipv4_layout_auto_bits src_ipv4_src_ipv6; - union mlx5_ifc_ipv6_layout_ipv4_layout_auto_bits dst_ipv4_dst_ipv6; - u8 tls_rcd_sn[0x40]; - u8 tcp_sn[0x20]; - u8 tls_implicit_iv[0x20]; - u8 tls_xor_iv[0x40]; - u8 encryption_key[0x100]; - u8 alg[4]; - u8 reserved2[0x1c]; - u8 reserved3[0x4a0]; -}; - -struct mlx5_ifc_tls_resp_bits { - u8 syndrome[0x20]; - u8 stream_id[0x20]; - u8 reserved[0x40]; -}; - -#define MLX5_TLS_COMMAND_SIZE (0x100) - #endif /* MLX5_IFC_FPGA_H */ diff --git a/include/linux/mlx5/mlx5_ifc_vdpa.h b/include/linux/mlx5/mlx5_ifc_vdpa.h index 1a9c9d94cb59..9becdc3fa503 100644 --- a/include/linux/mlx5/mlx5_ifc_vdpa.h +++ b/include/linux/mlx5/mlx5_ifc_vdpa.h @@ -150,6 +150,14 @@ enum { MLX5_VIRTIO_NET_Q_OBJECT_STATE_ERR = 0x3, }; +/* This indicates that the object was not created or has already + * been desroyed. It is very safe to assume that this object will never + * have so many states + */ +enum { + MLX5_VIRTIO_NET_Q_OBJECT_NONE = 0xffffffff +}; + enum { MLX5_RQTC_LIST_Q_TYPE_RQ = 0x0, MLX5_RQTC_LIST_Q_TYPE_VIRTIO_NET_Q = 0x1, @@ -165,4 +173,43 @@ struct mlx5_ifc_modify_virtio_net_q_out_bits { struct mlx5_ifc_general_obj_out_cmd_hdr_bits general_obj_out_cmd_hdr; }; +struct mlx5_ifc_virtio_q_counters_bits { + u8 modify_field_select[0x40]; + u8 reserved_at_40[0x40]; + u8 received_desc[0x40]; + u8 completed_desc[0x40]; + u8 error_cqes[0x20]; + u8 bad_desc_errors[0x20]; + u8 exceed_max_chain[0x20]; + u8 invalid_buffer[0x20]; + u8 reserved_at_180[0x280]; +}; + +struct mlx5_ifc_create_virtio_q_counters_in_bits { + struct mlx5_ifc_general_obj_in_cmd_hdr_bits hdr; + struct mlx5_ifc_virtio_q_counters_bits virtio_q_counters; +}; + +struct mlx5_ifc_create_virtio_q_counters_out_bits { + struct mlx5_ifc_general_obj_in_cmd_hdr_bits hdr; + struct mlx5_ifc_virtio_q_counters_bits virtio_q_counters; +}; + +struct mlx5_ifc_destroy_virtio_q_counters_in_bits { + struct mlx5_ifc_general_obj_in_cmd_hdr_bits hdr; +}; + +struct mlx5_ifc_destroy_virtio_q_counters_out_bits { + struct mlx5_ifc_general_obj_out_cmd_hdr_bits hdr; +}; + +struct mlx5_ifc_query_virtio_q_counters_in_bits { + struct mlx5_ifc_general_obj_in_cmd_hdr_bits hdr; +}; + +struct mlx5_ifc_query_virtio_q_counters_out_bits { + struct mlx5_ifc_general_obj_in_cmd_hdr_bits hdr; + struct mlx5_ifc_virtio_q_counters_bits counters; +}; + #endif /* __MLX5_IFC_VDPA_H_ */ diff --git a/include/linux/mlx5/port.h b/include/linux/mlx5/port.h index 77ea4f9c5265..e96ee1e348cb 100644 --- a/include/linux/mlx5/port.h +++ b/include/linux/mlx5/port.h @@ -56,8 +56,6 @@ enum mlx5_an_status { MLX5_AN_LINK_DOWN = 4, }; -#define MLX5_EEPROM_MAX_BYTES 32 -#define MLX5_EEPROM_IDENTIFIER_BYTE_MASK 0x000000ff #define MLX5_I2C_ADDR_LOW 0x50 #define MLX5_I2C_ADDR_HIGH 0x51 #define MLX5_EEPROM_PAGE_LENGTH 256 @@ -143,7 +141,7 @@ enum mlx5_ptys_width { MLX5_PTYS_WIDTH_12X = 1 << 4, }; -#define MLX5E_PROT_MASK(link_mode) (1 << link_mode) +#define MLX5E_PROT_MASK(link_mode) (1U << link_mode) #define MLX5_GET_ETH_PROTO(reg, out, ext, field) \ (ext ? MLX5_GET(reg, out, ext_##field) : \ MLX5_GET(reg, out, field)) diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h index 61e48d459b23..4657d5c54abe 100644 --- a/include/linux/mlx5/qp.h +++ b/include/linux/mlx5/qp.h @@ -162,6 +162,8 @@ enum { MLX5_SEND_WQE_MAX_WQEBBS = 16, }; +#define MLX5_SEND_WQE_MAX_SIZE (MLX5_SEND_WQE_MAX_WQEBBS * MLX5_SEND_WQE_BB) + enum { MLX5_WQE_FMR_PERM_LOCAL_READ = 1 << 27, MLX5_WQE_FMR_PERM_LOCAL_WRITE = 1 << 28, @@ -202,6 +204,9 @@ struct mlx5_wqe_fmr_seg { struct mlx5_wqe_ctrl_seg { __be32 opmod_idx_opcode; __be32 qpn_ds; + + struct_group(trailer, + u8 signature; u8 rsvd[2]; u8 fm_ce_se; @@ -211,6 +216,8 @@ struct mlx5_wqe_ctrl_seg { __be32 umr_mkey; __be32 tis_tir_num; }; + + ); /* end of trailer group */ }; #define MLX5_WQE_CTRL_DS_MASK 0x3f @@ -247,6 +254,7 @@ enum { enum { MLX5_ETH_WQE_FT_META_IPSEC = BIT(0), + MLX5_ETH_WQE_FT_META_MACSEC = BIT(1), }; struct mlx5_wqe_eth_seg { @@ -470,6 +478,12 @@ struct mlx5_klm { __be64 va; }; +struct mlx5_ksm { + __be32 reserved; + __be32 key; + __be64 va; +}; + struct mlx5_stride_block_entry { __be16 stride; __be16 bcount; diff --git a/include/linux/mm.h b/include/linux/mm.h index de103949860f..8bbcccbc5565 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3,9 +3,6 @@ #define _LINUX_MM_H #include <linux/errno.h> - -#ifdef __KERNEL__ - #include <linux/mmdebug.h> #include <linux/gfp.h> #include <linux/bug.h> @@ -26,12 +23,12 @@ #include <linux/err.h> #include <linux/page-flags.h> #include <linux/page_ref.h> -#include <linux/memremap.h> #include <linux/overflow.h> #include <linux/sizes.h> #include <linux/sched.h> #include <linux/pgtable.h> #include <linux/kasan.h> +#include <linux/memremap.h> struct mempolicy; struct anon_vma; @@ -216,17 +213,26 @@ int overcommit_policy_handler(struct ctl_table *, int, void *, size_t *, #if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP) #define nth_page(page,n) pfn_to_page(page_to_pfn((page)) + (n)) +#define folio_page_idx(folio, p) (page_to_pfn(p) - folio_pfn(folio)) #else #define nth_page(page,n) ((page) + (n)) +#define folio_page_idx(folio, p) ((p) - &(folio)->page) #endif /* to align the pointer to the (next) page boundary */ #define PAGE_ALIGN(addr) ALIGN(addr, PAGE_SIZE) +/* to align the pointer to the (prev) page boundary */ +#define PAGE_ALIGN_DOWN(addr) ALIGN_DOWN(addr, PAGE_SIZE) + /* test whether an address (unsigned long or pointer) is aligned to PAGE_SIZE */ #define PAGE_ALIGNED(addr) IS_ALIGNED((unsigned long)(addr), PAGE_SIZE) #define lru_to_page(head) (list_entry((head)->prev, struct page, lru)) +static inline struct folio *lru_to_folio(struct list_head *head) +{ + return list_entry((head)->prev, struct folio, lru); +} void setup_initial_init_mm(void *start_code, void *end_code, void *end_data, void *brk); @@ -422,52 +428,6 @@ extern unsigned int kobjsize(const void *objp); * mapping from the currently active vm_flags protection bits (the * low four bits) to a page protection mask.. */ -extern pgprot_t protection_map[16]; - -/** - * enum fault_flag - Fault flag definitions. - * @FAULT_FLAG_WRITE: Fault was a write fault. - * @FAULT_FLAG_MKWRITE: Fault was mkwrite of existing PTE. - * @FAULT_FLAG_ALLOW_RETRY: Allow to retry the fault if blocked. - * @FAULT_FLAG_RETRY_NOWAIT: Don't drop mmap_lock and wait when retrying. - * @FAULT_FLAG_KILLABLE: The fault task is in SIGKILL killable region. - * @FAULT_FLAG_TRIED: The fault has been tried once. - * @FAULT_FLAG_USER: The fault originated in userspace. - * @FAULT_FLAG_REMOTE: The fault is not for current task/mm. - * @FAULT_FLAG_INSTRUCTION: The fault was during an instruction fetch. - * @FAULT_FLAG_INTERRUPTIBLE: The fault can be interrupted by non-fatal signals. - * - * About @FAULT_FLAG_ALLOW_RETRY and @FAULT_FLAG_TRIED: we can specify - * whether we would allow page faults to retry by specifying these two - * fault flags correctly. Currently there can be three legal combinations: - * - * (a) ALLOW_RETRY and !TRIED: this means the page fault allows retry, and - * this is the first try - * - * (b) ALLOW_RETRY and TRIED: this means the page fault allows retry, and - * we've already tried at least once - * - * (c) !ALLOW_RETRY and !TRIED: this means the page fault does not allow retry - * - * The unlisted combination (!ALLOW_RETRY && TRIED) is illegal and should never - * be used. Note that page faults can be allowed to retry for multiple times, - * in which case we'll have an initial fault with flags (a) then later on - * continuous faults with flags (b). We should always try to detect pending - * signals before a retry to make sure the continuous page faults can still be - * interrupted if necessary. - */ -enum fault_flag { - FAULT_FLAG_WRITE = 1 << 0, - FAULT_FLAG_MKWRITE = 1 << 1, - FAULT_FLAG_ALLOW_RETRY = 1 << 2, - FAULT_FLAG_RETRY_NOWAIT = 1 << 3, - FAULT_FLAG_KILLABLE = 1 << 4, - FAULT_FLAG_TRIED = 1 << 5, - FAULT_FLAG_USER = 1 << 6, - FAULT_FLAG_REMOTE = 1 << 7, - FAULT_FLAG_INSTRUCTION = 1 << 8, - FAULT_FLAG_INTERRUPTIBLE = 1 << 9, -}; /* * The default fault flags that should be used by most of the @@ -523,7 +483,8 @@ struct vm_fault { struct vm_area_struct *vma; /* Target VMA */ gfp_t gfp_mask; /* gfp mask to be used for allocations */ pgoff_t pgoff; /* Logical page offset based on vma */ - unsigned long address; /* Faulting virtual address */ + unsigned long address; /* Faulting virtual address - masked */ + unsigned long real_address; /* Faulting virtual address - unmasked */ }; enum fault_flag flags; /* FAULT_FLAG_xxx flags * XXX: should really be 'const' */ @@ -577,6 +538,10 @@ enum page_entry_size { */ struct vm_operations_struct { void (*open)(struct vm_area_struct * area); + /** + * @close: Called when the VMA is being removed from the MM. + * Context: User context. May sleep. Caller holds mmap_lock. + */ void (*close)(struct vm_area_struct * area); /* Called any time before splitting to check if it's allowed */ int (*may_split)(struct vm_area_struct *area, unsigned long addr); @@ -696,6 +661,38 @@ static inline bool vma_is_accessible(struct vm_area_struct *vma) return vma->vm_flags & VM_ACCESS_FLAGS; } +static inline +struct vm_area_struct *vma_find(struct vma_iterator *vmi, unsigned long max) +{ + return mas_find(&vmi->mas, max); +} + +static inline struct vm_area_struct *vma_next(struct vma_iterator *vmi) +{ + /* + * Uses vma_find() to get the first VMA when the iterator starts. + * Calling mas_next() could skip the first entry. + */ + return vma_find(vmi, ULONG_MAX); +} + +static inline struct vm_area_struct *vma_prev(struct vma_iterator *vmi) +{ + return mas_prev(&vmi->mas, 0); +} + +static inline unsigned long vma_iter_addr(struct vma_iterator *vmi) +{ + return vmi->mas.index; +} + +#define for_each_vma(__vmi, __vma) \ + while (((__vma) = vma_next(&(__vmi))) != NULL) + +/* The MM code likes to work with exclusive end addresses */ +#define for_each_vma_range(__vmi, __vma, __end) \ + while (((__vma) = vma_find(&(__vmi), (__end) - 1)) != NULL) + #ifdef CONFIG_SHMEM /* * The vma_is_shmem is not inline because it is used only by slow @@ -714,6 +711,29 @@ int vma_is_stack_for_current(struct vm_area_struct *vma); struct mmu_gather; struct inode; +static inline unsigned int compound_order(struct page *page) +{ + if (!PageHead(page)) + return 0; + return page[1].compound_order; +} + +/** + * folio_order - The allocation order of a folio. + * @folio: The folio. + * + * A folio is composed of 2^order pages. See get_order() for the definition + * of order. + * + * Return: The order of the folio. + */ +static inline unsigned int folio_order(struct folio *folio) +{ + if (!folio_test_large(folio)) + return 0; + return folio->_folio_order; +} + #include <linux/huge_mm.h> /* @@ -794,21 +814,26 @@ static inline int is_vmalloc_or_module_addr(const void *x) } #endif -static inline int head_compound_mapcount(struct page *head) +/* + * How many times the entire folio is mapped as a single unit (eg by a + * PMD or PUD entry). This is probably not what you want, except for + * debugging purposes; look at folio_mapcount() or page_mapcount() + * instead. + */ +static inline int folio_entire_mapcount(struct folio *folio) { - return atomic_read(compound_mapcount_ptr(head)) + 1; + VM_BUG_ON_FOLIO(!folio_test_large(folio), folio); + return atomic_read(folio_mapcount_ptr(folio)) + 1; } /* * Mapcount of compound page as a whole, does not include mapped sub-pages. * - * Must be called only for compound pages or any their tail sub-pages. + * Must be called only for compound pages. */ static inline int compound_mapcount(struct page *page) { - VM_BUG_ON_PAGE(!PageCompound(page), page); - page = compound_head(page); - return head_compound_mapcount(page); + return folio_entire_mapcount(page_folio(page)); } /* @@ -838,21 +863,18 @@ static inline int page_mapcount(struct page *page) return atomic_read(&page->_mapcount) + 1; } +int folio_mapcount(struct folio *folio); + #ifdef CONFIG_TRANSPARENT_HUGEPAGE -int total_mapcount(struct page *page); -int page_trans_huge_mapcount(struct page *page, int *total_mapcount); -#else static inline int total_mapcount(struct page *page) { - return page_mapcount(page); + return folio_mapcount(page_folio(page)); } -static inline int page_trans_huge_mapcount(struct page *page, - int *total_mapcount) + +#else +static inline int total_mapcount(struct page *page) { - int mapcount = page_mapcount(page); - if (total_mapcount) - *total_mapcount = mapcount; - return mapcount; + return page_mapcount(page); } #endif @@ -870,7 +892,7 @@ static inline struct folio *virt_to_folio(const void *x) return page_folio(page); } -void __put_page(struct page *page); +void __folio_put(struct folio *folio); void put_pages_list(struct list_head *pages); @@ -907,60 +929,19 @@ static inline void set_compound_page_dtor(struct page *page, page[1].compound_dtor = compound_dtor; } -static inline void destroy_compound_page(struct page *page) -{ - VM_BUG_ON_PAGE(page[1].compound_dtor >= NR_COMPOUND_DTORS, page); - compound_page_dtors[page[1].compound_dtor](page); -} - -static inline unsigned int compound_order(struct page *page) -{ - if (!PageHead(page)) - return 0; - return page[1].compound_order; -} - -/** - * folio_order - The allocation order of a folio. - * @folio: The folio. - * - * A folio is composed of 2^order pages. See get_order() for the definition - * of order. - * - * Return: The order of the folio. - */ -static inline unsigned int folio_order(struct folio *folio) -{ - return compound_order(&folio->page); -} - -static inline bool hpage_pincount_available(struct page *page) -{ - /* - * Can the page->hpage_pinned_refcount field be used? That field is in - * the 3rd page of the compound page, so the smallest (2-page) compound - * pages cannot support it. - */ - page = compound_head(page); - return PageCompound(page) && compound_order(page) > 1; -} +void destroy_large_folio(struct folio *folio); static inline int head_compound_pincount(struct page *head) { return atomic_read(compound_pincount_ptr(head)); } -static inline int compound_pincount(struct page *page) -{ - VM_BUG_ON_PAGE(!hpage_pincount_available(page), page); - page = compound_head(page); - return head_compound_pincount(page); -} - static inline void set_compound_order(struct page *page, unsigned int order) { page[1].compound_order = order; +#ifdef CONFIG_64BIT page[1].compound_nr = 1U << order; +#endif } /* Returns the number of pages in this potentially compound page. */ @@ -968,7 +949,11 @@ static inline unsigned long compound_nr(struct page *page) { if (!PageHead(page)) return 1; +#ifdef CONFIG_64BIT return page[1].compound_nr; +#else + return 1UL << compound_order(page); +#endif } /* Returns the number of bytes in this potentially compound page. */ @@ -983,6 +968,37 @@ static inline unsigned int page_shift(struct page *page) return PAGE_SHIFT + compound_order(page); } +/** + * thp_order - Order of a transparent huge page. + * @page: Head page of a transparent huge page. + */ +static inline unsigned int thp_order(struct page *page) +{ + VM_BUG_ON_PGFLAGS(PageTail(page), page); + return compound_order(page); +} + +/** + * thp_nr_pages - The number of regular pages in this huge page. + * @page: The head page of a huge page. + */ +static inline int thp_nr_pages(struct page *page) +{ + VM_BUG_ON_PGFLAGS(PageTail(page), page); + return compound_nr(page); +} + +/** + * thp_size - Size of a transparent huge page. + * @page: Head page of a transparent huge page. + * + * Return: Number of bytes in this page. + */ +static inline unsigned long thp_size(struct page *page) +{ + return PAGE_SIZE << thp_order(page); +} + void free_compound_page(struct page *page); #ifdef CONFIG_MMU @@ -1066,126 +1082,28 @@ vm_fault_t finish_mkwrite_fault(struct vm_fault *vmf); * back into memory. */ -/* - * The zone field is never updated after free_area_init_core() - * sets it, so none of the operations on it need to be atomic. - */ - -/* Page flags: | [SECTION] | [NODE] | ZONE | [LAST_CPUPID] | ... | FLAGS | */ -#define SECTIONS_PGOFF ((sizeof(unsigned long)*8) - SECTIONS_WIDTH) -#define NODES_PGOFF (SECTIONS_PGOFF - NODES_WIDTH) -#define ZONES_PGOFF (NODES_PGOFF - ZONES_WIDTH) -#define LAST_CPUPID_PGOFF (ZONES_PGOFF - LAST_CPUPID_WIDTH) -#define KASAN_TAG_PGOFF (LAST_CPUPID_PGOFF - KASAN_TAG_WIDTH) - -/* - * Define the bit shifts to access each section. For non-existent - * sections we define the shift as 0; that plus a 0 mask ensures - * the compiler will optimise away reference to them. - */ -#define SECTIONS_PGSHIFT (SECTIONS_PGOFF * (SECTIONS_WIDTH != 0)) -#define NODES_PGSHIFT (NODES_PGOFF * (NODES_WIDTH != 0)) -#define ZONES_PGSHIFT (ZONES_PGOFF * (ZONES_WIDTH != 0)) -#define LAST_CPUPID_PGSHIFT (LAST_CPUPID_PGOFF * (LAST_CPUPID_WIDTH != 0)) -#define KASAN_TAG_PGSHIFT (KASAN_TAG_PGOFF * (KASAN_TAG_WIDTH != 0)) - -/* NODE:ZONE or SECTION:ZONE is used to ID a zone for the buddy allocator */ -#ifdef NODE_NOT_IN_PAGE_FLAGS -#define ZONEID_SHIFT (SECTIONS_SHIFT + ZONES_SHIFT) -#define ZONEID_PGOFF ((SECTIONS_PGOFF < ZONES_PGOFF)? \ - SECTIONS_PGOFF : ZONES_PGOFF) -#else -#define ZONEID_SHIFT (NODES_SHIFT + ZONES_SHIFT) -#define ZONEID_PGOFF ((NODES_PGOFF < ZONES_PGOFF)? \ - NODES_PGOFF : ZONES_PGOFF) -#endif - -#define ZONEID_PGSHIFT (ZONEID_PGOFF * (ZONEID_SHIFT != 0)) - -#define ZONES_MASK ((1UL << ZONES_WIDTH) - 1) -#define NODES_MASK ((1UL << NODES_WIDTH) - 1) -#define SECTIONS_MASK ((1UL << SECTIONS_WIDTH) - 1) -#define LAST_CPUPID_MASK ((1UL << LAST_CPUPID_SHIFT) - 1) -#define KASAN_TAG_MASK ((1UL << KASAN_TAG_WIDTH) - 1) -#define ZONEID_MASK ((1UL << ZONEID_SHIFT) - 1) - -static inline enum zone_type page_zonenum(const struct page *page) -{ - ASSERT_EXCLUSIVE_BITS(page->flags, ZONES_MASK << ZONES_PGSHIFT); - return (page->flags >> ZONES_PGSHIFT) & ZONES_MASK; -} - -static inline enum zone_type folio_zonenum(const struct folio *folio) -{ - return page_zonenum(&folio->page); -} - -#ifdef CONFIG_ZONE_DEVICE -static inline bool is_zone_device_page(const struct page *page) -{ - return page_zonenum(page) == ZONE_DEVICE; -} -extern void memmap_init_zone_device(struct zone *, unsigned long, - unsigned long, struct dev_pagemap *); -#else -static inline bool is_zone_device_page(const struct page *page) -{ - return false; -} -#endif - -static inline bool is_zone_movable_page(const struct page *page) -{ - return page_zonenum(page) == ZONE_MOVABLE; -} - -#ifdef CONFIG_DEV_PAGEMAP_OPS -void free_devmap_managed_page(struct page *page); +#if defined(CONFIG_ZONE_DEVICE) && defined(CONFIG_FS_DAX) DECLARE_STATIC_KEY_FALSE(devmap_managed_key); -static inline bool page_is_devmap_managed(struct page *page) +bool __put_devmap_managed_page_refs(struct page *page, int refs); +static inline bool put_devmap_managed_page_refs(struct page *page, int refs) { if (!static_branch_unlikely(&devmap_managed_key)) return false; if (!is_zone_device_page(page)) return false; - switch (page->pgmap->type) { - case MEMORY_DEVICE_PRIVATE: - case MEMORY_DEVICE_FS_DAX: - return true; - default: - break; - } - return false; + return __put_devmap_managed_page_refs(page, refs); } - -void put_devmap_managed_page(struct page *page); - -#else /* CONFIG_DEV_PAGEMAP_OPS */ -static inline bool page_is_devmap_managed(struct page *page) +#else /* CONFIG_ZONE_DEVICE && CONFIG_FS_DAX */ +static inline bool put_devmap_managed_page_refs(struct page *page, int refs) { return false; } +#endif /* CONFIG_ZONE_DEVICE && CONFIG_FS_DAX */ -static inline void put_devmap_managed_page(struct page *page) -{ -} -#endif /* CONFIG_DEV_PAGEMAP_OPS */ - -static inline bool is_device_private_page(const struct page *page) +static inline bool put_devmap_managed_page(struct page *page) { - return IS_ENABLED(CONFIG_DEV_PAGEMAP_OPS) && - IS_ENABLED(CONFIG_DEVICE_PRIVATE) && - is_zone_device_page(page) && - page->pgmap->type == MEMORY_DEVICE_PRIVATE; -} - -static inline bool is_pci_p2pdma_page(const struct page *page) -{ - return IS_ENABLED(CONFIG_DEV_PAGEMAP_OPS) && - IS_ENABLED(CONFIG_PCI_P2PDMA) && - is_zone_device_page(page) && - page->pgmap->type == MEMORY_DEVICE_PCI_P2PDMA; + return put_devmap_managed_page_refs(page, 1); } /* 127: arbitrary random number, small enough to assemble well */ @@ -1212,9 +1130,6 @@ static inline void get_page(struct page *page) } bool __must_check try_grab_page(struct page *page, unsigned int flags); -struct page *try_grab_compound_head(struct page *page, int refs, - unsigned int flags); - static inline __must_check bool try_get_page(struct page *page) { @@ -1241,7 +1156,46 @@ static inline __must_check bool try_get_page(struct page *page) static inline void folio_put(struct folio *folio) { if (folio_put_testzero(folio)) - __put_page(&folio->page); + __folio_put(folio); +} + +/** + * folio_put_refs - Reduce the reference count on a folio. + * @folio: The folio. + * @refs: The amount to subtract from the folio's reference count. + * + * If the folio's reference count reaches zero, the memory will be + * released back to the page allocator and may be used by another + * allocation immediately. Do not access the memory or the struct folio + * after calling folio_put_refs() unless you can be sure that these weren't + * the last references. + * + * Context: May be called in process or interrupt context, but not in NMI + * context. May be called while holding a spinlock. + */ +static inline void folio_put_refs(struct folio *folio, int refs) +{ + if (folio_ref_sub_and_test(folio, refs)) + __folio_put(folio); +} + +void release_pages(struct page **pages, int nr); + +/** + * folios_put - Decrement the reference count on an array of folios. + * @folios: The folios. + * @nr: How many folios there are. + * + * Like folio_put(), but for an array of folios. This is more efficient + * than writing the loop yourself as it will optimise the locks which + * need to be taken if the folios are freed. + * + * Context: May be called in process or interrupt context, but not in NMI + * context. May be called while holding a spinlock. + */ +static inline void folios_put(struct folio **folios, unsigned int nr) +{ + release_pages((struct page **)folios, nr); } static inline void put_page(struct page *page) @@ -1249,16 +1203,11 @@ static inline void put_page(struct page *page) struct folio *folio = page_folio(page); /* - * For devmap managed pages we need to catch refcount transition from - * 2 to 1, when refcount reach one it means the page is free and we - * need to inform the device driver through callback. See - * include/linux/memremap.h and HMM for details. + * For some devmap managed pages we need to catch refcount transition + * from 2 to 1: */ - if (page_is_devmap_managed(&folio->page)) { - put_devmap_managed_page(&folio->page); + if (put_devmap_managed_page(&folio->page)) return; - } - folio_put(folio); } @@ -1288,10 +1237,9 @@ static inline void put_page(struct page *page) * applications that don't have huge page reference counts, this won't be an * issue. * - * Locking: the lockless algorithm described in page_cache_get_speculative() - * and page_cache_gup_pin_speculative() provides safe operation for - * get_user_pages and page_mkclean and other calls that race to set up page - * table entries. + * Locking: the lockless algorithm described in folio_try_get_rcu() + * provides safe operation for get_user_pages(), page_mkclean() and + * other calls that race to set up page table entries. */ #define GUP_PIN_COUNTING_BIAS (1U << 10) @@ -1302,70 +1250,11 @@ void unpin_user_page_range_dirty_lock(struct page *page, unsigned long npages, bool make_dirty); void unpin_user_pages(struct page **pages, unsigned long npages); -/** - * page_maybe_dma_pinned - Report if a page is pinned for DMA. - * @page: The page. - * - * This function checks if a page has been pinned via a call to - * a function in the pin_user_pages() family. - * - * For non-huge pages, the return value is partially fuzzy: false is not fuzzy, - * because it means "definitely not pinned for DMA", but true means "probably - * pinned for DMA, but possibly a false positive due to having at least - * GUP_PIN_COUNTING_BIAS worth of normal page references". - * - * False positives are OK, because: a) it's unlikely for a page to get that many - * refcounts, and b) all the callers of this routine are expected to be able to - * deal gracefully with a false positive. - * - * For huge pages, the result will be exactly correct. That's because we have - * more tracking data available: the 3rd struct page in the compound page is - * used to track the pincount (instead using of the GUP_PIN_COUNTING_BIAS - * scheme). - * - * For more information, please see Documentation/core-api/pin_user_pages.rst. - * - * Return: True, if it is likely that the page has been "dma-pinned". - * False, if the page is definitely not dma-pinned. - */ -static inline bool page_maybe_dma_pinned(struct page *page) -{ - if (hpage_pincount_available(page)) - return compound_pincount(page) > 0; - - /* - * page_ref_count() is signed. If that refcount overflows, then - * page_ref_count() returns a negative value, and callers will avoid - * further incrementing the refcount. - * - * Here, for that overflow case, use the signed bit to count a little - * bit higher via unsigned math, and thus still get an accurate result. - */ - return ((unsigned int)page_ref_count(compound_head(page))) >= - GUP_PIN_COUNTING_BIAS; -} - static inline bool is_cow_mapping(vm_flags_t flags) { return (flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE; } -/* - * This should most likely only be called during fork() to see whether we - * should break the cow immediately for a page on the src mm. - */ -static inline bool page_needs_cow_for_dma(struct vm_area_struct *vma, - struct page *page) -{ - if (!is_cow_mapping(vma->vm_flags)) - return false; - - if (!test_bit(MMF_HAS_PINNED, &vma->vm_mm->flags)) - return false; - - return page_maybe_dma_pinned(page); -} - #if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP) #define SECTION_IN_PAGE_FLAGS #endif @@ -1400,6 +1289,18 @@ static inline int folio_nid(const struct folio *folio) } #ifdef CONFIG_NUMA_BALANCING +/* page access time bits needs to hold at least 4 seconds */ +#define PAGE_ACCESS_TIME_MIN_BITS 12 +#if LAST_CPUPID_SHIFT < PAGE_ACCESS_TIME_MIN_BITS +#define PAGE_ACCESS_TIME_BUCKETS \ + (PAGE_ACCESS_TIME_MIN_BITS - LAST_CPUPID_SHIFT) +#else +#define PAGE_ACCESS_TIME_BUCKETS 0 +#endif + +#define PAGE_ACCESS_TIME_MASK \ + (LAST_CPUPID_MASK << PAGE_ACCESS_TIME_BUCKETS) + static inline int cpu_pid_to_cpupid(int cpu, int pid) { return ((cpu & LAST__CPU_MASK) << LAST__PID_SHIFT) | (pid & LAST__PID_MASK); @@ -1463,12 +1364,25 @@ static inline void page_cpupid_reset_last(struct page *page) page->flags |= LAST_CPUPID_MASK << LAST_CPUPID_PGSHIFT; } #endif /* LAST_CPUPID_NOT_IN_PAGE_FLAGS */ + +static inline int xchg_page_access_time(struct page *page, int time) +{ + int last_time; + + last_time = page_cpupid_xchg_last(page, time >> PAGE_ACCESS_TIME_BUCKETS); + return last_time << PAGE_ACCESS_TIME_BUCKETS; +} #else /* !CONFIG_NUMA_BALANCING */ static inline int page_cpupid_xchg_last(struct page *page, int cpupid) { return page_to_nid(page); /* XXX */ } +static inline int xchg_page_access_time(struct page *page, int time) +{ + return 0; +} + static inline int page_cpupid_last(struct page *page) { return page_to_nid(page); /* XXX */ @@ -1531,11 +1445,18 @@ static inline u8 page_kasan_tag(const struct page *page) static inline void page_kasan_tag_set(struct page *page, u8 tag) { - if (kasan_enabled()) { - tag ^= 0xff; - page->flags &= ~(KASAN_TAG_MASK << KASAN_TAG_PGSHIFT); - page->flags |= (tag & KASAN_TAG_MASK) << KASAN_TAG_PGSHIFT; - } + unsigned long old_flags, flags; + + if (!kasan_enabled()) + return; + + tag ^= 0xff; + old_flags = READ_ONCE(page->flags); + do { + flags = old_flags; + flags &= ~(KASAN_TAG_MASK << KASAN_TAG_PGSHIFT); + flags |= (tag & KASAN_TAG_MASK) << KASAN_TAG_PGSHIFT; + } while (unlikely(!try_cmpxchg(&page->flags, &old_flags, flags))); } static inline void page_kasan_tag_reset(struct page *page) @@ -1603,20 +1524,113 @@ static inline unsigned long folio_pfn(struct folio *folio) return page_to_pfn(&folio->page); } +static inline struct folio *pfn_folio(unsigned long pfn) +{ + return page_folio(pfn_to_page(pfn)); +} + +static inline atomic_t *folio_pincount_ptr(struct folio *folio) +{ + return &folio_page(folio, 1)->compound_pincount; +} + +/** + * folio_maybe_dma_pinned - Report if a folio may be pinned for DMA. + * @folio: The folio. + * + * This function checks if a folio has been pinned via a call to + * a function in the pin_user_pages() family. + * + * For small folios, the return value is partially fuzzy: false is not fuzzy, + * because it means "definitely not pinned for DMA", but true means "probably + * pinned for DMA, but possibly a false positive due to having at least + * GUP_PIN_COUNTING_BIAS worth of normal folio references". + * + * False positives are OK, because: a) it's unlikely for a folio to + * get that many refcounts, and b) all the callers of this routine are + * expected to be able to deal gracefully with a false positive. + * + * For large folios, the result will be exactly correct. That's because + * we have more tracking data available: the compound_pincount is used + * instead of the GUP_PIN_COUNTING_BIAS scheme. + * + * For more information, please see Documentation/core-api/pin_user_pages.rst. + * + * Return: True, if it is likely that the page has been "dma-pinned". + * False, if the page is definitely not dma-pinned. + */ +static inline bool folio_maybe_dma_pinned(struct folio *folio) +{ + if (folio_test_large(folio)) + return atomic_read(folio_pincount_ptr(folio)) > 0; + + /* + * folio_ref_count() is signed. If that refcount overflows, then + * folio_ref_count() returns a negative value, and callers will avoid + * further incrementing the refcount. + * + * Here, for that overflow case, use the sign bit to count a little + * bit higher via unsigned math, and thus still get an accurate result. + */ + return ((unsigned int)folio_ref_count(folio)) >= + GUP_PIN_COUNTING_BIAS; +} + +static inline bool page_maybe_dma_pinned(struct page *page) +{ + return folio_maybe_dma_pinned(page_folio(page)); +} + +/* + * This should most likely only be called during fork() to see whether we + * should break the cow immediately for an anon page on the src mm. + * + * The caller has to hold the PT lock and the vma->vm_mm->->write_protect_seq. + */ +static inline bool page_needs_cow_for_dma(struct vm_area_struct *vma, + struct page *page) +{ + VM_BUG_ON(!(raw_read_seqcount(&vma->vm_mm->write_protect_seq) & 1)); + + if (!test_bit(MMF_HAS_PINNED, &vma->vm_mm->flags)) + return false; + + return page_maybe_dma_pinned(page); +} + /* MIGRATE_CMA and ZONE_MOVABLE do not allow pin pages */ #ifdef CONFIG_MIGRATION -static inline bool is_pinnable_page(struct page *page) +static inline bool is_longterm_pinnable_page(struct page *page) { - return !(is_zone_movable_page(page) || is_migrate_cma_page(page)) || - is_zero_pfn(page_to_pfn(page)); +#ifdef CONFIG_CMA + int mt = get_pageblock_migratetype(page); + + if (mt == MIGRATE_CMA || mt == MIGRATE_ISOLATE) + return false; +#endif + /* The zero page may always be pinned */ + if (is_zero_pfn(page_to_pfn(page))) + return true; + + /* Coherent device memory must always allow eviction. */ + if (is_device_coherent_page(page)) + return false; + + /* Otherwise, non-movable zone pages can be pinned. */ + return !is_zone_movable_page(page); } #else -static inline bool is_pinnable_page(struct page *page) +static inline bool is_longterm_pinnable_page(struct page *page) { return true; } #endif +static inline bool folio_is_longterm_pinnable(struct folio *folio) +{ + return is_longterm_pinnable_page(&folio->page); +} + static inline void set_page_zone(struct page *page, enum zone_type zone) { page->flags &= ~(ZONES_MASK << ZONES_PGSHIFT); @@ -1647,7 +1661,13 @@ static inline void set_page_links(struct page *page, enum zone_type zone, */ static inline long folio_nr_pages(struct folio *folio) { - return compound_nr(&folio->page); + if (!folio_test_large(folio)) + return 1; +#ifdef CONFIG_64BIT + return folio->_folio_nr_pages; +#else + return 1L << folio->_folio_order; +#endif } /** @@ -1766,7 +1786,6 @@ static inline void *folio_address(const struct folio *folio) } extern void *page_rmapping(struct page *page); -extern struct anon_vma *page_anon_vma(struct page *page); extern pgoff_t __page_file_index(struct page *page); /* @@ -1827,7 +1846,11 @@ extern void pagefault_out_of_memory(void); */ #define SHOW_MEM_FILTER_NODES (0x0001u) /* disallowed nodes */ -extern void show_free_areas(unsigned int flags, nodemask_t *nodemask); +extern void __show_free_areas(unsigned int flags, nodemask_t *nodemask, int max_zone_idx); +static void __maybe_unused show_free_areas(unsigned int flags, nodemask_t *nodemask) +{ + __show_free_areas(flags, nodemask, MAX_NR_ZONES - 1); +} #ifdef CONFIG_MMU extern bool can_do_mlock(void); @@ -1837,28 +1860,6 @@ static inline bool can_do_mlock(void) { return false; } extern int user_shm_lock(size_t, struct ucounts *); extern void user_shm_unlock(size_t, struct ucounts *); -/* - * Parameter block passed down to zap_pte_range in exceptional cases. - */ -struct zap_details { - struct address_space *zap_mapping; /* Check page->mapping if set */ - struct page *single_page; /* Locked page to be unmapped */ -}; - -/* - * We set details->zap_mappings when we want to unmap shared but keep private - * pages. Return true if skip zapping this page, false otherwise. - */ -static inline bool -zap_skip_check_mapping(struct zap_details *details, struct page *page) -{ - if (!details || !page) - return false; - - return details->zap_mapping && - (details->zap_mapping != page_rmapping(page)); -} - struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, pte_t pte); struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr, @@ -1868,8 +1869,9 @@ void zap_vma_ptes(struct vm_area_struct *vma, unsigned long address, unsigned long size); void zap_page_range(struct vm_area_struct *vma, unsigned long address, unsigned long size); -void unmap_vmas(struct mmu_gather *tlb, struct vm_area_struct *start_vma, - unsigned long start, unsigned long end); +void unmap_vmas(struct mmu_gather *tlb, struct maple_tree *mt, + struct vm_area_struct *start_vma, unsigned long start, + unsigned long end); struct mmu_notifier_range; @@ -1877,9 +1879,6 @@ void free_pgd_range(struct mmu_gather *tlb, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling); int copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma); -int follow_invalidate_pte(struct mm_struct *mm, unsigned long address, - struct mmu_notifier_range *range, pte_t **ptepp, - pmd_t **pmdpp, spinlock_t **ptlp); int follow_pte(struct mm_struct *mm, unsigned long address, pte_t **ptepp, spinlock_t **ptlp); int follow_pfn(struct vm_area_struct *vma, unsigned long address, @@ -1893,9 +1892,7 @@ extern void truncate_pagecache(struct inode *inode, loff_t new); extern void truncate_setsize(struct inode *inode, loff_t newsize); void pagecache_isize_extended(struct inode *inode, loff_t from, loff_t to); void truncate_pagecache_range(struct inode *inode, loff_t offset, loff_t end); -int truncate_inode_page(struct address_space *mapping, struct page *page); int generic_error_remove_page(struct address_space *mapping, struct page *page); -int invalidate_inode_page(struct page *page); #ifdef CONFIG_MMU extern vm_fault_t handle_mm_fault(struct vm_area_struct *vma, @@ -1904,7 +1901,6 @@ extern vm_fault_t handle_mm_fault(struct vm_area_struct *vma, extern int fixup_user_fault(struct mm_struct *mm, unsigned long address, unsigned int fault_flags, bool *unlocked); -void unmap_mapping_page(struct page *page); void unmap_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t nr, bool even_cows); void unmap_mapping_range(struct address_space *mapping, @@ -1925,7 +1921,6 @@ static inline int fixup_user_fault(struct mm_struct *mm, unsigned long address, BUG(); return -EFAULT; } -static inline void unmap_mapping_page(struct page *page) { } static inline void unmap_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t nr, bool even_cows) { } static inline void unmap_mapping_range(struct address_space *mapping, @@ -1959,10 +1954,6 @@ long get_user_pages(unsigned long start, unsigned long nr_pages, long pin_user_pages(unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, struct vm_area_struct **vmas); -long get_user_pages_locked(unsigned long start, unsigned long nr_pages, - unsigned int gup_flags, struct page **pages, int *locked); -long pin_user_pages_locked(unsigned long start, unsigned long nr_pages, - unsigned int gup_flags, struct page **pages, int *locked); long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages, struct page **pages, unsigned int gup_flags); long pin_user_pages_unlocked(unsigned long start, unsigned long nr_pages, @@ -1982,10 +1973,6 @@ int get_kernel_pages(const struct kvec *iov, int nr_pages, int write, struct page **pages); struct page *get_dump_page(unsigned long addr); -extern int try_to_release_page(struct page * page, gfp_t gfp_mask); -extern void do_invalidatepage(struct page *page, unsigned int offset, - unsigned int length); - bool folio_mark_dirty(struct folio *folio); bool set_page_dirty(struct page *page); int set_page_dirty_lock(struct page *page); @@ -2003,8 +1990,12 @@ extern unsigned long move_page_tables(struct vm_area_struct *vma, * for now all the callers are only use one of the flags at the same * time. */ -/* Whether we should allow dirty bit accounting */ -#define MM_CP_DIRTY_ACCT (1UL << 0) +/* + * Whether we should manually check if we can map individual PTEs writable, + * because something (e.g., COW, uffd-wp) blocks that from happening for all + * PTEs automatically in a writable mapping. + */ +#define MM_CP_TRY_CHANGE_WRITABLE (1UL << 0) /* Whether this protection change is for NUMA hints */ #define MM_CP_PROT_NUMA (1UL << 1) /* Whether this change is for write protecting */ @@ -2013,10 +2004,11 @@ extern unsigned long move_page_tables(struct vm_area_struct *vma, #define MM_CP_UFFD_WP_ALL (MM_CP_UFFD_WP | \ MM_CP_UFFD_WP_RESOLVE) -extern unsigned long change_protection(struct vm_area_struct *vma, unsigned long start, +extern unsigned long change_protection(struct mmu_gather *tlb, + struct vm_area_struct *vma, unsigned long start, unsigned long end, pgprot_t newprot, unsigned long cp_flags); -extern int mprotect_fixup(struct vm_area_struct *vma, +extern int mprotect_fixup(struct mmu_gather *tlb, struct vm_area_struct *vma, struct vm_area_struct **pprev, unsigned long start, unsigned long end, unsigned long newflags); @@ -2497,7 +2489,6 @@ static inline spinlock_t *pud_lock(struct mm_struct *mm, pud_t *pud) } extern void __init pagecache_init(void); -extern void __init free_area_init_memoryless_node(int nid); extern void free_initmem(void); /* @@ -2579,7 +2570,6 @@ extern unsigned long absent_pages_in_range(unsigned long start_pfn, unsigned long end_pfn); extern void get_pfn_range_for_nid(unsigned int nid, unsigned long *start_pfn, unsigned long *end_pfn); -extern unsigned long find_min_pfn_with_active_regions(void); #ifndef CONFIG_NUMA static inline int early_pfn_to_nid(unsigned long pfn) @@ -2600,7 +2590,12 @@ extern void calculate_min_free_kbytes(void); extern int __meminit init_per_zone_wmark_min(void); extern void mem_init(void); extern void __init mmap_init(void); -extern void show_mem(unsigned int flags, nodemask_t *nodemask); + +extern void __show_mem(unsigned int flags, nodemask_t *nodemask, int max_zone_idx); +static inline void show_mem(unsigned int flags, nodemask_t *nodemask) +{ + __show_mem(flags, nodemask, MAX_NR_ZONES - 1); +} extern long si_mem_available(void); extern void si_meminfo(struct sysinfo * val); extern void si_meminfo_node(struct sysinfo *val, int nid); @@ -2670,21 +2665,22 @@ static inline int vma_adjust(struct vm_area_struct *vma, unsigned long start, extern struct vm_area_struct *vma_merge(struct mm_struct *, struct vm_area_struct *prev, unsigned long addr, unsigned long end, unsigned long vm_flags, struct anon_vma *, struct file *, pgoff_t, - struct mempolicy *, struct vm_userfaultfd_ctx); + struct mempolicy *, struct vm_userfaultfd_ctx, struct anon_vma_name *); extern struct anon_vma *find_mergeable_anon_vma(struct vm_area_struct *); extern int __split_vma(struct mm_struct *, struct vm_area_struct *, unsigned long addr, int new_below); extern int split_vma(struct mm_struct *, struct vm_area_struct *, unsigned long addr, int new_below); extern int insert_vm_struct(struct mm_struct *, struct vm_area_struct *); -extern void __vma_link_rb(struct mm_struct *, struct vm_area_struct *, - struct rb_node **, struct rb_node *); extern void unlink_file_vma(struct vm_area_struct *); extern struct vm_area_struct *copy_vma(struct vm_area_struct **, unsigned long addr, unsigned long len, pgoff_t pgoff, bool *need_rmap_locks); extern void exit_mmap(struct mm_struct *); +void vma_mas_store(struct vm_area_struct *vma, struct ma_state *mas); +void vma_mas_remove(struct vm_area_struct *vma, struct ma_state *mas); + static inline int check_data_rlimit(unsigned long rlim, unsigned long new, unsigned long start, @@ -2722,6 +2718,7 @@ extern int install_special_mapping(struct mm_struct *mm, unsigned long flags, struct page **pages); unsigned long randomize_stack_top(unsigned long stack_top); +unsigned long randomize_page(unsigned long start, unsigned long range); extern unsigned long get_unmapped_area(struct file *, unsigned long, unsigned long, unsigned long, unsigned long); @@ -2731,8 +2728,9 @@ extern unsigned long mmap_region(struct file *file, unsigned long addr, extern unsigned long do_mmap(struct file *file, unsigned long addr, unsigned long len, unsigned long prot, unsigned long flags, unsigned long pgoff, unsigned long *populate, struct list_head *uf); -extern int __do_munmap(struct mm_struct *, unsigned long, size_t, - struct list_head *uf, bool downgrade); +extern int do_mas_munmap(struct ma_state *mas, struct mm_struct *mm, + unsigned long start, size_t len, struct list_head *uf, + bool downgrade); extern int do_munmap(struct mm_struct *, unsigned long, size_t, struct list_head *uf); extern int do_madvise(struct mm_struct *mm, unsigned long start, size_t len_in, int behavior); @@ -2799,26 +2797,12 @@ extern struct vm_area_struct * find_vma(struct mm_struct * mm, unsigned long add extern struct vm_area_struct * find_vma_prev(struct mm_struct * mm, unsigned long addr, struct vm_area_struct **pprev); -/** - * find_vma_intersection() - Look up the first VMA which intersects the interval - * @mm: The process address space. - * @start_addr: The inclusive start user address. - * @end_addr: The exclusive end user address. - * - * Returns: The first VMA within the provided range, %NULL otherwise. Assumes - * start_addr < end_addr. +/* + * Look up the first VMA which intersects the interval [start_addr, end_addr) + * NULL if none. Assume start_addr < end_addr. */ -static inline struct vm_area_struct *find_vma_intersection(struct mm_struct *mm, - unsigned long start_addr, - unsigned long end_addr) -{ - struct vm_area_struct *vma = find_vma(mm, start_addr); - - if (vma && end_addr <= vma->vm_start) - vma = NULL; - return vma; -} + unsigned long start_addr, unsigned long end_addr); /** * vma_lookup() - Find a VMA at a specific address @@ -2830,12 +2814,7 @@ struct vm_area_struct *find_vma_intersection(struct mm_struct *mm, static inline struct vm_area_struct *vma_lookup(struct mm_struct *mm, unsigned long addr) { - struct vm_area_struct *vma = find_vma(mm, addr); - - if (vma && addr < vma->vm_start) - vma = NULL; - - return vma; + return mtree_load(&mm->mm_mt, addr); } static inline unsigned long vm_start_gap(struct vm_area_struct *vma) @@ -2871,7 +2850,7 @@ static inline unsigned long vma_pages(struct vm_area_struct *vma) static inline struct vm_area_struct *find_exact_vma(struct mm_struct *mm, unsigned long vm_start, unsigned long vm_end) { - struct vm_area_struct *vma = find_vma(mm, vm_start); + struct vm_area_struct *vma = vma_lookup(mm, vm_start); if (vma && (vma->vm_start != vm_start || vma->vm_end != vm_end)) vma = NULL; @@ -2969,15 +2948,11 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address, #define FOLL_FORCE 0x10 /* get_user_pages read/write w/o permission */ #define FOLL_NOWAIT 0x20 /* if a disk transfer is needed, start the IO * and return without waiting upon it */ -#define FOLL_POPULATE 0x40 /* fault in pages (with FOLL_MLOCK) */ #define FOLL_NOFAULT 0x80 /* do not fault in pages */ #define FOLL_HWPOISON 0x100 /* check page is hwpoisoned */ -#define FOLL_NUMA 0x200 /* force NUMA hinting page fault */ #define FOLL_MIGRATION 0x400 /* wait for page to replace migration entry */ #define FOLL_TRIED 0x800 /* a retry, previous pass started an IO */ -#define FOLL_MLOCK 0x1000 /* lock present pages */ #define FOLL_REMOTE 0x2000 /* we are working on non-current tsk/mm */ -#define FOLL_COW 0x4000 /* internal GUP flag */ #define FOLL_ANON 0x8000 /* don't do file mappings */ #define FOLL_LONGTERM 0x10000 /* mapping lifetime is indefinite: see below */ #define FOLL_SPLIT_PMD 0x20000 /* split huge pmd before returning */ @@ -3051,6 +3026,65 @@ static inline int vm_fault_to_errno(vm_fault_t vm_fault, int foll_flags) return 0; } +/* + * Indicates for which pages that are write-protected in the page table, + * whether GUP has to trigger unsharing via FAULT_FLAG_UNSHARE such that the + * GUP pin will remain consistent with the pages mapped into the page tables + * of the MM. + * + * Temporary unmapping of PageAnonExclusive() pages or clearing of + * PageAnonExclusive() has to protect against concurrent GUP: + * * Ordinary GUP: Using the PT lock + * * GUP-fast and fork(): mm->write_protect_seq + * * GUP-fast and KSM or temporary unmapping (swap, migration): see + * page_try_share_anon_rmap() + * + * Must be called with the (sub)page that's actually referenced via the + * page table entry, which might not necessarily be the head page for a + * PTE-mapped THP. + */ +static inline bool gup_must_unshare(unsigned int flags, struct page *page) +{ + /* + * FOLL_WRITE is implicitly handled correctly as the page table entry + * has to be writable -- and if it references (part of) an anonymous + * folio, that part is required to be marked exclusive. + */ + if ((flags & (FOLL_WRITE | FOLL_PIN)) != FOLL_PIN) + return false; + /* + * Note: PageAnon(page) is stable until the page is actually getting + * freed. + */ + if (!PageAnon(page)) + return false; + + /* Paired with a memory barrier in page_try_share_anon_rmap(). */ + if (IS_ENABLED(CONFIG_HAVE_FAST_GUP)) + smp_rmb(); + + /* + * Note that PageKsm() pages cannot be exclusive, and consequently, + * cannot get pinned. + */ + return !PageAnonExclusive(page); +} + +/* + * Indicates whether GUP can follow a PROT_NONE mapped page, or whether + * a (NUMA hinting) fault is required. + */ +static inline bool gup_can_follow_protnone(unsigned int flags) +{ + /* + * FOLL_FORCE has to be able to make progress even if the VMA is + * inaccessible. Further, FOLL_FORCE access usually does not represent + * application behaviour and we should avoid triggering NUMA hinting + * faults. + */ + return flags & FOLL_FORCE; +} + typedef int (*pte_fn_t)(pte_t *pte, unsigned long addr, void *data); extern int apply_to_page_range(struct mm_struct *mm, unsigned long address, unsigned long size, pte_fn_t fn, void *data); @@ -3058,7 +3092,7 @@ extern int apply_to_existing_page_range(struct mm_struct *mm, unsigned long address, unsigned long size, pte_fn_t fn, void *data); -extern void init_mem_debugging_and_hardening(void); +extern void __init init_mem_debugging_and_hardening(void); #ifdef CONFIG_PAGE_POISONING extern void __kernel_poison_pages(struct page *page, int numpages); extern void __kernel_unpoison_pages(struct page *page, int numpages); @@ -3179,7 +3213,6 @@ int drop_caches_sysctl_handler(struct ctl_table *, int, void *, size_t *, #endif void drop_slab(void); -void drop_slab_node(int nid); #ifndef CONFIG_MMU #define randomize_va_space 0 @@ -3196,20 +3229,16 @@ static inline void print_vma_addr(char *prefix, unsigned long rip) } #endif -int vmemmap_remap_free(unsigned long start, unsigned long end, - unsigned long reuse); -int vmemmap_remap_alloc(unsigned long start, unsigned long end, - unsigned long reuse, gfp_t gfp_mask); - void *sparse_buffer_alloc(unsigned long size); struct page * __populate_section_memmap(unsigned long pfn, - unsigned long nr_pages, int nid, struct vmem_altmap *altmap); + unsigned long nr_pages, int nid, struct vmem_altmap *altmap, + struct dev_pagemap *pgmap); pgd_t *vmemmap_pgd_populate(unsigned long addr, int node); p4d_t *vmemmap_p4d_populate(pgd_t *pgd, unsigned long addr, int node); pud_t *vmemmap_pud_populate(p4d_t *p4d, unsigned long addr, int node); pmd_t *vmemmap_pmd_populate(pud_t *pud, unsigned long addr, int node); pte_t *vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node, - struct vmem_altmap *altmap); + struct vmem_altmap *altmap, struct page *reuse); void *vmemmap_alloc_block(unsigned long size, int node); struct vmem_altmap; void *vmemmap_alloc_block_buf(unsigned long size, int node, @@ -3232,7 +3261,12 @@ enum mf_flags { MF_ACTION_REQUIRED = 1 << 1, MF_MUST_KILL = 1 << 2, MF_SOFT_OFFLINE = 1 << 3, + MF_UNPOISON = 1 << 4, + MF_SW_SIMULATED = 1 << 5, + MF_NO_RETRY = 1 << 6, }; +int mf_dax_kill_procs(struct address_space *mapping, pgoff_t index, + unsigned long count, int mf_flags); extern int memory_failure(unsigned long pfn, int flags); extern void memory_failure_queue(unsigned long pfn, int flags); extern void memory_failure_queue_kick(int cpu); @@ -3242,6 +3276,14 @@ extern int sysctl_memory_failure_recovery; extern void shake_page(struct page *p); extern atomic_long_t num_poisoned_pages __read_mostly; extern int soft_offline_page(unsigned long pfn, int flags); +#ifdef CONFIG_MEMORY_FAILURE +extern int __get_huge_page_for_hwpoison(unsigned long pfn, int flags); +#else +static inline int __get_huge_page_for_hwpoison(unsigned long pfn, int flags) +{ + return 0; +} +#endif #ifndef arch_memory_failure static inline int arch_memory_failure(unsigned long pfn, int flags) @@ -3272,10 +3314,8 @@ enum mf_action_page_type { MF_MSG_KERNEL_HIGH_ORDER, MF_MSG_SLAB, MF_MSG_DIFFERENT_COMPOUND, - MF_MSG_POISONED_HUGE, MF_MSG_HUGE, MF_MSG_FREE_HUGE, - MF_MSG_NON_PMD_HUGE, MF_MSG_UNMAP_FAILED, MF_MSG_DIRTY_SWAPCACHE, MF_MSG_CLEAN_SWAPCACHE, @@ -3287,7 +3327,6 @@ enum mf_action_page_type { MF_MSG_CLEAN_LRU, MF_MSG_TRUNCATED_LRU, MF_MSG_BUDDY, - MF_MSG_BUDDY_2ND, MF_MSG_DAX, MF_MSG_UNSPLIT_THP, MF_MSG_UNKNOWN, @@ -3416,5 +3455,24 @@ static inline int seal_check_future_write(int seals, struct vm_area_struct *vma) return 0; } -#endif /* __KERNEL__ */ +#ifdef CONFIG_ANON_VMA_NAME +int madvise_set_anon_name(struct mm_struct *mm, unsigned long start, + unsigned long len_in, + struct anon_vma_name *anon_name); +#else +static inline int +madvise_set_anon_name(struct mm_struct *mm, unsigned long start, + unsigned long len_in, struct anon_vma_name *anon_name) { + return 0; +} +#endif + +/* + * Whether to drop the pte markers, for example, the uffd-wp information for + * file-backed memory. This should only be specified when we will completely + * drop the page in the mm, either by truncation or unmapping of the vma. By + * default, the flag is not set. + */ +#define ZAP_FLAG_DROP_MARKER ((__force zap_flags_t) BIT(0)) + #endif /* _LINUX_MM_H */ diff --git a/include/linux/mm_api.h b/include/linux/mm_api.h new file mode 100644 index 000000000000..a5ace2b198b8 --- /dev/null +++ b/include/linux/mm_api.h @@ -0,0 +1 @@ +#include <linux/mm.h> diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index e2ec68b0515c..e8ed225d8f7c 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -2,8 +2,12 @@ #ifndef LINUX_MM_INLINE_H #define LINUX_MM_INLINE_H +#include <linux/atomic.h> #include <linux/huge_mm.h> #include <linux/swap.h> +#include <linux/string.h> +#include <linux/userfaultfd_k.h> +#include <linux/swapops.h> /** * folio_is_file_lru - Should the folio be on a file LRU or anon LRU? @@ -30,15 +34,25 @@ static inline int page_is_file_lru(struct page *page) return folio_is_file_lru(page_folio(page)); } -static __always_inline void update_lru_size(struct lruvec *lruvec, +static __always_inline void __update_lru_size(struct lruvec *lruvec, enum lru_list lru, enum zone_type zid, long nr_pages) { struct pglist_data *pgdat = lruvec_pgdat(lruvec); + lockdep_assert_held(&lruvec->lru_lock); + WARN_ON_ONCE(nr_pages != (int)nr_pages); + __mod_lruvec_state(lruvec, NR_LRU_BASE + lru, nr_pages); __mod_zone_page_state(&pgdat->node_zones[zid], NR_ZONE_LRU_BASE + lru, nr_pages); +} + +static __always_inline void update_lru_size(struct lruvec *lruvec, + enum lru_list lru, enum zone_type zid, + long nr_pages) +{ + __update_lru_size(lruvec, lru, zid, nr_pages); #ifdef CONFIG_MEMCG mem_cgroup_update_lru_size(lruvec, lru, zid, nr_pages); #endif @@ -62,11 +76,6 @@ static __always_inline void __folio_clear_lru_flags(struct folio *folio) __folio_clear_unevictable(folio); } -static __always_inline void __clear_page_lru_flags(struct page *page) -{ - __folio_clear_lru_flags(page_folio(page)); -} - /** * folio_lru_list - Which LRU list should a folio be on? * @folio: The folio to test. @@ -90,14 +99,228 @@ static __always_inline enum lru_list folio_lru_list(struct folio *folio) return lru; } +#ifdef CONFIG_LRU_GEN + +#ifdef CONFIG_LRU_GEN_ENABLED +static inline bool lru_gen_enabled(void) +{ + DECLARE_STATIC_KEY_TRUE(lru_gen_caps[NR_LRU_GEN_CAPS]); + + return static_branch_likely(&lru_gen_caps[LRU_GEN_CORE]); +} +#else +static inline bool lru_gen_enabled(void) +{ + DECLARE_STATIC_KEY_FALSE(lru_gen_caps[NR_LRU_GEN_CAPS]); + + return static_branch_unlikely(&lru_gen_caps[LRU_GEN_CORE]); +} +#endif + +static inline bool lru_gen_in_fault(void) +{ + return current->in_lru_fault; +} + +static inline int lru_gen_from_seq(unsigned long seq) +{ + return seq % MAX_NR_GENS; +} + +static inline int lru_hist_from_seq(unsigned long seq) +{ + return seq % NR_HIST_GENS; +} + +static inline int lru_tier_from_refs(int refs) +{ + VM_WARN_ON_ONCE(refs > BIT(LRU_REFS_WIDTH)); + + /* see the comment in folio_lru_refs() */ + return order_base_2(refs + 1); +} + +static inline int folio_lru_refs(struct folio *folio) +{ + unsigned long flags = READ_ONCE(folio->flags); + bool workingset = flags & BIT(PG_workingset); + + /* + * Return the number of accesses beyond PG_referenced, i.e., N-1 if the + * total number of accesses is N>1, since N=0,1 both map to the first + * tier. lru_tier_from_refs() will account for this off-by-one. Also see + * the comment on MAX_NR_TIERS. + */ + return ((flags & LRU_REFS_MASK) >> LRU_REFS_PGOFF) + workingset; +} + +static inline int folio_lru_gen(struct folio *folio) +{ + unsigned long flags = READ_ONCE(folio->flags); + + return ((flags & LRU_GEN_MASK) >> LRU_GEN_PGOFF) - 1; +} + +static inline bool lru_gen_is_active(struct lruvec *lruvec, int gen) +{ + unsigned long max_seq = lruvec->lrugen.max_seq; + + VM_WARN_ON_ONCE(gen >= MAX_NR_GENS); + + /* see the comment on MIN_NR_GENS */ + return gen == lru_gen_from_seq(max_seq) || gen == lru_gen_from_seq(max_seq - 1); +} + +static inline void lru_gen_update_size(struct lruvec *lruvec, struct folio *folio, + int old_gen, int new_gen) +{ + int type = folio_is_file_lru(folio); + int zone = folio_zonenum(folio); + int delta = folio_nr_pages(folio); + enum lru_list lru = type * LRU_INACTIVE_FILE; + struct lru_gen_struct *lrugen = &lruvec->lrugen; + + VM_WARN_ON_ONCE(old_gen != -1 && old_gen >= MAX_NR_GENS); + VM_WARN_ON_ONCE(new_gen != -1 && new_gen >= MAX_NR_GENS); + VM_WARN_ON_ONCE(old_gen == -1 && new_gen == -1); + + if (old_gen >= 0) + WRITE_ONCE(lrugen->nr_pages[old_gen][type][zone], + lrugen->nr_pages[old_gen][type][zone] - delta); + if (new_gen >= 0) + WRITE_ONCE(lrugen->nr_pages[new_gen][type][zone], + lrugen->nr_pages[new_gen][type][zone] + delta); + + /* addition */ + if (old_gen < 0) { + if (lru_gen_is_active(lruvec, new_gen)) + lru += LRU_ACTIVE; + __update_lru_size(lruvec, lru, zone, delta); + return; + } + + /* deletion */ + if (new_gen < 0) { + if (lru_gen_is_active(lruvec, old_gen)) + lru += LRU_ACTIVE; + __update_lru_size(lruvec, lru, zone, -delta); + return; + } + + /* promotion */ + if (!lru_gen_is_active(lruvec, old_gen) && lru_gen_is_active(lruvec, new_gen)) { + __update_lru_size(lruvec, lru, zone, -delta); + __update_lru_size(lruvec, lru + LRU_ACTIVE, zone, delta); + } + + /* demotion requires isolation, e.g., lru_deactivate_fn() */ + VM_WARN_ON_ONCE(lru_gen_is_active(lruvec, old_gen) && !lru_gen_is_active(lruvec, new_gen)); +} + +static inline bool lru_gen_add_folio(struct lruvec *lruvec, struct folio *folio, bool reclaiming) +{ + unsigned long seq; + unsigned long flags; + int gen = folio_lru_gen(folio); + int type = folio_is_file_lru(folio); + int zone = folio_zonenum(folio); + struct lru_gen_struct *lrugen = &lruvec->lrugen; + + VM_WARN_ON_ONCE_FOLIO(gen != -1, folio); + + if (folio_test_unevictable(folio) || !lrugen->enabled) + return false; + /* + * There are three common cases for this page: + * 1. If it's hot, e.g., freshly faulted in or previously hot and + * migrated, add it to the youngest generation. + * 2. If it's cold but can't be evicted immediately, i.e., an anon page + * not in swapcache or a dirty page pending writeback, add it to the + * second oldest generation. + * 3. Everything else (clean, cold) is added to the oldest generation. + */ + if (folio_test_active(folio)) + seq = lrugen->max_seq; + else if ((type == LRU_GEN_ANON && !folio_test_swapcache(folio)) || + (folio_test_reclaim(folio) && + (folio_test_dirty(folio) || folio_test_writeback(folio)))) + seq = lrugen->min_seq[type] + 1; + else + seq = lrugen->min_seq[type]; + + gen = lru_gen_from_seq(seq); + flags = (gen + 1UL) << LRU_GEN_PGOFF; + /* see the comment on MIN_NR_GENS about PG_active */ + set_mask_bits(&folio->flags, LRU_GEN_MASK | BIT(PG_active), flags); + + lru_gen_update_size(lruvec, folio, -1, gen); + /* for folio_rotate_reclaimable() */ + if (reclaiming) + list_add_tail(&folio->lru, &lrugen->lists[gen][type][zone]); + else + list_add(&folio->lru, &lrugen->lists[gen][type][zone]); + + return true; +} + +static inline bool lru_gen_del_folio(struct lruvec *lruvec, struct folio *folio, bool reclaiming) +{ + unsigned long flags; + int gen = folio_lru_gen(folio); + + if (gen < 0) + return false; + + VM_WARN_ON_ONCE_FOLIO(folio_test_active(folio), folio); + VM_WARN_ON_ONCE_FOLIO(folio_test_unevictable(folio), folio); + + /* for folio_migrate_flags() */ + flags = !reclaiming && lru_gen_is_active(lruvec, gen) ? BIT(PG_active) : 0; + flags = set_mask_bits(&folio->flags, LRU_GEN_MASK, flags); + gen = ((flags & LRU_GEN_MASK) >> LRU_GEN_PGOFF) - 1; + + lru_gen_update_size(lruvec, folio, gen, -1); + list_del(&folio->lru); + + return true; +} + +#else /* !CONFIG_LRU_GEN */ + +static inline bool lru_gen_enabled(void) +{ + return false; +} + +static inline bool lru_gen_in_fault(void) +{ + return false; +} + +static inline bool lru_gen_add_folio(struct lruvec *lruvec, struct folio *folio, bool reclaiming) +{ + return false; +} + +static inline bool lru_gen_del_folio(struct lruvec *lruvec, struct folio *folio, bool reclaiming) +{ + return false; +} + +#endif /* CONFIG_LRU_GEN */ + static __always_inline void lruvec_add_folio(struct lruvec *lruvec, struct folio *folio) { enum lru_list lru = folio_lru_list(folio); + if (lru_gen_add_folio(lruvec, folio, false)) + return; + update_lru_size(lruvec, lru, folio_zonenum(folio), folio_nr_pages(folio)); - list_add(&folio->lru, &lruvec->lists[lru]); + if (lru != LRU_UNEVICTABLE) + list_add(&folio->lru, &lruvec->lists[lru]); } static __always_inline void add_page_to_lru_list(struct page *page, @@ -111,22 +334,26 @@ void lruvec_add_folio_tail(struct lruvec *lruvec, struct folio *folio) { enum lru_list lru = folio_lru_list(folio); + if (lru_gen_add_folio(lruvec, folio, true)) + return; + update_lru_size(lruvec, lru, folio_zonenum(folio), folio_nr_pages(folio)); + /* This is not expected to be used on LRU_UNEVICTABLE */ list_add_tail(&folio->lru, &lruvec->lists[lru]); } -static __always_inline void add_page_to_lru_list_tail(struct page *page, - struct lruvec *lruvec) -{ - lruvec_add_folio_tail(lruvec, page_folio(page)); -} - static __always_inline void lruvec_del_folio(struct lruvec *lruvec, struct folio *folio) { - list_del(&folio->lru); - update_lru_size(lruvec, folio_lru_list(folio), folio_zonenum(folio), + enum lru_list lru = folio_lru_list(folio); + + if (lru_gen_del_folio(lruvec, folio, false)) + return; + + if (lru != LRU_UNEVICTABLE) + list_del(&folio->lru); + update_lru_size(lruvec, lru, folio_zonenum(folio), -folio_nr_pages(folio)); } @@ -135,4 +362,220 @@ static __always_inline void del_page_from_lru_list(struct page *page, { lruvec_del_folio(lruvec, page_folio(page)); } + +#ifdef CONFIG_ANON_VMA_NAME +/* + * mmap_lock should be read-locked when calling anon_vma_name(). Caller should + * either keep holding the lock while using the returned pointer or it should + * raise anon_vma_name refcount before releasing the lock. + */ +extern struct anon_vma_name *anon_vma_name(struct vm_area_struct *vma); +extern struct anon_vma_name *anon_vma_name_alloc(const char *name); +extern void anon_vma_name_free(struct kref *kref); + +/* mmap_lock should be read-locked */ +static inline void anon_vma_name_get(struct anon_vma_name *anon_name) +{ + if (anon_name) + kref_get(&anon_name->kref); +} + +static inline void anon_vma_name_put(struct anon_vma_name *anon_name) +{ + if (anon_name) + kref_put(&anon_name->kref, anon_vma_name_free); +} + +static inline +struct anon_vma_name *anon_vma_name_reuse(struct anon_vma_name *anon_name) +{ + /* Prevent anon_name refcount saturation early on */ + if (kref_read(&anon_name->kref) < REFCOUNT_MAX) { + anon_vma_name_get(anon_name); + return anon_name; + + } + return anon_vma_name_alloc(anon_name->name); +} + +static inline void dup_anon_vma_name(struct vm_area_struct *orig_vma, + struct vm_area_struct *new_vma) +{ + struct anon_vma_name *anon_name = anon_vma_name(orig_vma); + + if (anon_name) + new_vma->anon_name = anon_vma_name_reuse(anon_name); +} + +static inline void free_anon_vma_name(struct vm_area_struct *vma) +{ + /* + * Not using anon_vma_name because it generates a warning if mmap_lock + * is not held, which might be the case here. + */ + if (!vma->vm_file) + anon_vma_name_put(vma->anon_name); +} + +static inline bool anon_vma_name_eq(struct anon_vma_name *anon_name1, + struct anon_vma_name *anon_name2) +{ + if (anon_name1 == anon_name2) + return true; + + return anon_name1 && anon_name2 && + !strcmp(anon_name1->name, anon_name2->name); +} + +#else /* CONFIG_ANON_VMA_NAME */ +static inline struct anon_vma_name *anon_vma_name(struct vm_area_struct *vma) +{ + return NULL; +} + +static inline struct anon_vma_name *anon_vma_name_alloc(const char *name) +{ + return NULL; +} + +static inline void anon_vma_name_get(struct anon_vma_name *anon_name) {} +static inline void anon_vma_name_put(struct anon_vma_name *anon_name) {} +static inline void dup_anon_vma_name(struct vm_area_struct *orig_vma, + struct vm_area_struct *new_vma) {} +static inline void free_anon_vma_name(struct vm_area_struct *vma) {} + +static inline bool anon_vma_name_eq(struct anon_vma_name *anon_name1, + struct anon_vma_name *anon_name2) +{ + return true; +} + +#endif /* CONFIG_ANON_VMA_NAME */ + +static inline void init_tlb_flush_pending(struct mm_struct *mm) +{ + atomic_set(&mm->tlb_flush_pending, 0); +} + +static inline void inc_tlb_flush_pending(struct mm_struct *mm) +{ + atomic_inc(&mm->tlb_flush_pending); + /* + * The only time this value is relevant is when there are indeed pages + * to flush. And we'll only flush pages after changing them, which + * requires the PTL. + * + * So the ordering here is: + * + * atomic_inc(&mm->tlb_flush_pending); + * spin_lock(&ptl); + * ... + * set_pte_at(); + * spin_unlock(&ptl); + * + * spin_lock(&ptl) + * mm_tlb_flush_pending(); + * .... + * spin_unlock(&ptl); + * + * flush_tlb_range(); + * atomic_dec(&mm->tlb_flush_pending); + * + * Where the increment if constrained by the PTL unlock, it thus + * ensures that the increment is visible if the PTE modification is + * visible. After all, if there is no PTE modification, nobody cares + * about TLB flushes either. + * + * This very much relies on users (mm_tlb_flush_pending() and + * mm_tlb_flush_nested()) only caring about _specific_ PTEs (and + * therefore specific PTLs), because with SPLIT_PTE_PTLOCKS and RCpc + * locks (PPC) the unlock of one doesn't order against the lock of + * another PTL. + * + * The decrement is ordered by the flush_tlb_range(), such that + * mm_tlb_flush_pending() will not return false unless all flushes have + * completed. + */ +} + +static inline void dec_tlb_flush_pending(struct mm_struct *mm) +{ + /* + * See inc_tlb_flush_pending(). + * + * This cannot be smp_mb__before_atomic() because smp_mb() simply does + * not order against TLB invalidate completion, which is what we need. + * + * Therefore we must rely on tlb_flush_*() to guarantee order. + */ + atomic_dec(&mm->tlb_flush_pending); +} + +static inline bool mm_tlb_flush_pending(struct mm_struct *mm) +{ + /* + * Must be called after having acquired the PTL; orders against that + * PTLs release and therefore ensures that if we observe the modified + * PTE we must also observe the increment from inc_tlb_flush_pending(). + * + * That is, it only guarantees to return true if there is a flush + * pending for _this_ PTL. + */ + return atomic_read(&mm->tlb_flush_pending); +} + +static inline bool mm_tlb_flush_nested(struct mm_struct *mm) +{ + /* + * Similar to mm_tlb_flush_pending(), we must have acquired the PTL + * for which there is a TLB flush pending in order to guarantee + * we've seen both that PTE modification and the increment. + * + * (no requirement on actually still holding the PTL, that is irrelevant) + */ + return atomic_read(&mm->tlb_flush_pending) > 1; +} + +/* + * If this pte is wr-protected by uffd-wp in any form, arm the special pte to + * replace a none pte. NOTE! This should only be called when *pte is already + * cleared so we will never accidentally replace something valuable. Meanwhile + * none pte also means we are not demoting the pte so tlb flushed is not needed. + * E.g., when pte cleared the caller should have taken care of the tlb flush. + * + * Must be called with pgtable lock held so that no thread will see the none + * pte, and if they see it, they'll fault and serialize at the pgtable lock. + * + * This function is a no-op if PTE_MARKER_UFFD_WP is not enabled. + */ +static inline void +pte_install_uffd_wp_if_needed(struct vm_area_struct *vma, unsigned long addr, + pte_t *pte, pte_t pteval) +{ +#ifdef CONFIG_PTE_MARKER_UFFD_WP + bool arm_uffd_pte = false; + + /* The current status of the pte should be "cleared" before calling */ + WARN_ON_ONCE(!pte_none(*pte)); + + if (vma_is_anonymous(vma) || !userfaultfd_wp(vma)) + return; + + /* A uffd-wp wr-protected normal pte */ + if (unlikely(pte_present(pteval) && pte_uffd_wp(pteval))) + arm_uffd_pte = true; + + /* + * A uffd-wp wr-protected swap pte. Note: this should even cover an + * existing pte marker with uffd-wp bit set. + */ + if (unlikely(pte_swp_uffd_wp_any(pteval))) + arm_uffd_pte = true; + + if (unlikely(arm_uffd_pte)) + set_pte_at(vma->vm_mm, addr, pte, + make_pte_marker(PTE_MARKER_UFFD_WP)); +#endif +} + #endif diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 1ae3537c7920..500e536796ca 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -5,9 +5,11 @@ #include <linux/mm_types_task.h> #include <linux/auxvec.h> +#include <linux/kref.h> #include <linux/list.h> #include <linux/spinlock.h> #include <linux/rbtree.h> +#include <linux/maple_tree.h> #include <linux/rwsem.h> #include <linux/completion.h> #include <linux/cpumask.h> @@ -84,7 +86,21 @@ struct page { * lruvec->lru_lock. Sometimes used as a generic list * by the page owner. */ - struct list_head lru; + union { + struct list_head lru; + + /* Or, for the Unevictable "LRU list" slot */ + struct { + /* Always even, to negate PageTail */ + void *__filler; + /* Count page's or folio's mlocks */ + unsigned int mlock_count; + }; + + /* Or, free page */ + struct list_head buddy_list; + struct list_head pcp_list; + }; /* See page-flags.h for PAGE_MAPPING_FLAGS */ struct address_space *mapping; pgoff_t index; /* Our offset within mapping. */ @@ -118,31 +134,6 @@ struct page { atomic_long_t pp_frag_count; }; }; - struct { /* slab, slob and slub */ - union { - struct list_head slab_list; - struct { /* Partial pages */ - struct page *next; -#ifdef CONFIG_64BIT - int pages; /* Nr of pages left */ -#else - short int pages; -#endif - }; - }; - struct kmem_cache *slab_cache; /* not slob */ - /* Double-word boundary */ - void *freelist; /* first free object */ - union { - void *s_mem; /* slab: first object */ - unsigned long counters; /* SLUB */ - struct { /* SLUB */ - unsigned inuse:16; - unsigned objects:15; - unsigned frozen:1; - }; - }; - }; struct { /* Tail pages of compound page */ unsigned long compound_head; /* Bit zero is set */ @@ -150,11 +141,14 @@ struct page { unsigned char compound_dtor; unsigned char compound_order; atomic_t compound_mapcount; + atomic_t compound_pincount; +#ifdef CONFIG_64BIT unsigned int compound_nr; /* 1 << compound_order */ +#endif }; struct { /* Second tail page of compound page */ unsigned long _compound_pad_1; /* compound_head */ - atomic_t hpage_pinned_refcount; + unsigned long _compound_pad_2; /* For both global and memcg */ struct list_head deferred_list; }; @@ -206,9 +200,6 @@ struct page { * which are currently stored here. */ unsigned int page_type; - - unsigned int active; /* SLAB */ - int units; /* SLOB */ }; /* Usage count. *DO NOT USE DIRECTLY*. See page_ref.h */ @@ -233,6 +224,18 @@ struct page { not kmapped, ie. highmem) */ #endif /* WANT_PAGE_VIRTUAL */ +#ifdef CONFIG_KMSAN + /* + * KMSAN metadata for this page: + * - shadow page: every bit indicates whether the corresponding + * bit of the original page is initialized (0) or not (1); + * - origin page: every 4 bytes contain an id of the stack trace + * where the uninitialized value was created. + */ + struct page *kmsan_shadow; + struct page *kmsan_origin; +#endif + #ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS int _last_cpupid; #endif @@ -242,6 +245,7 @@ struct page { * struct folio - Represents a contiguous set of bytes. * @flags: Identical to the page flags. * @lru: Least Recently Used list; tracks how recently this folio was used. + * @mlock_count: Number of times this folio has been pinned by mlock(). * @mapping: The file this page belongs to, or refers to the anon_vma for * anonymous memory. * @index: Offset within the file, in units of pages. For anonymous memory, @@ -253,6 +257,13 @@ struct page { * @_refcount: Do not access this member directly. Use folio_ref_count() * to find how many references there are to this folio. * @memcg_data: Memory Control Group data. + * @_flags_1: For large folios, additional page flags. + * @__head: Points to the folio. Do not use. + * @_folio_dtor: Which destructor to use for this folio. + * @_folio_order: Do not use directly, call folio_order(). + * @_total_mapcount: Do not use directly, call folio_entire_mapcount(). + * @_pincount: Do not use directly, call folio_maybe_dma_pinned(). + * @_folio_nr_pages: Do not use directly, call folio_nr_pages(). * * A folio is a physically, virtually and logically contiguous set * of bytes. It is a power-of-two in size, and it is aligned to that @@ -268,7 +279,17 @@ struct folio { struct { /* public: */ unsigned long flags; - struct list_head lru; + union { + struct list_head lru; + /* private: avoid cluttering the output */ + struct { + void *__filler; + /* public: */ + unsigned int mlock_count; + /* private: */ + }; + /* public: */ + }; struct address_space *mapping; pgoff_t index; void *private; @@ -281,13 +302,22 @@ struct folio { }; struct page page; }; + unsigned long _flags_1; + unsigned long __head; + unsigned char _folio_dtor; + unsigned char _folio_order; + atomic_t _total_mapcount; + atomic_t _pincount; +#ifdef CONFIG_64BIT + unsigned int _folio_nr_pages; +#endif }; -static_assert(sizeof(struct page) == sizeof(struct folio)); #define FOLIO_MATCH(pg, fl) \ static_assert(offsetof(struct page, pg) == offsetof(struct folio, fl)) FOLIO_MATCH(flags, flags); FOLIO_MATCH(lru, lru); +FOLIO_MATCH(mapping, mapping); FOLIO_MATCH(compound_head, lru); FOLIO_MATCH(index, index); FOLIO_MATCH(private, private); @@ -297,6 +327,19 @@ FOLIO_MATCH(_refcount, _refcount); FOLIO_MATCH(memcg_data, memcg_data); #endif #undef FOLIO_MATCH +#define FOLIO_MATCH(pg, fl) \ + static_assert(offsetof(struct folio, fl) == \ + offsetof(struct page, pg) + sizeof(struct page)) +FOLIO_MATCH(flags, _flags_1); +FOLIO_MATCH(compound_head, __head); +FOLIO_MATCH(compound_dtor, _folio_dtor); +FOLIO_MATCH(compound_order, _folio_order); +FOLIO_MATCH(compound_mapcount, _total_mapcount); +FOLIO_MATCH(compound_pincount, _pincount); +#ifdef CONFIG_64BIT +FOLIO_MATCH(compound_nr, _folio_nr_pages); +#endif +#undef FOLIO_MATCH static inline atomic_t *folio_mapcount_ptr(struct folio *folio) { @@ -311,7 +354,7 @@ static inline atomic_t *compound_mapcount_ptr(struct page *page) static inline atomic_t *compound_pincount_ptr(struct page *page) { - return &page[2].hpage_pinned_refcount; + return &page[1].compound_pincount; } /* @@ -386,6 +429,12 @@ struct vm_userfaultfd_ctx { struct vm_userfaultfd_ctx {}; #endif /* CONFIG_USERFAULTFD */ +struct anon_vma_name { + struct kref kref; + /* The name needs to be at the end because it is dynamically sized. */ + char name[]; +}; + /* * This struct describes a virtual memory area. There is one of these * per VM-area/task. A VM area is any part of the process virtual memory @@ -399,21 +448,6 @@ struct vm_area_struct { unsigned long vm_end; /* The first byte after our end address within vm_mm. */ - /* linked list of VM areas per task, sorted by address */ - struct vm_area_struct *vm_next, *vm_prev; - - struct rb_node vm_rb; - - /* - * Largest free memory gap in bytes to the left of this VMA. - * Either between this VMA and vma->vm_prev, or between one of the - * VMAs below us in the VMA rbtree and its ->vm_prev. This helps - * get_unmapped_area find a free area of the right size. - */ - unsigned long rb_subtree_gap; - - /* Second cache line starts here. */ - struct mm_struct *vm_mm; /* The address space we belong to. */ /* @@ -426,11 +460,22 @@ struct vm_area_struct { /* * For areas with an address space and backing store, * linkage into the address_space->i_mmap interval tree. + * + * For private anonymous mappings, a pointer to a null terminated string + * containing the name given to the vma, or NULL if unnamed. */ - struct { - struct rb_node rb; - unsigned long rb_subtree_last; - } shared; + + union { + struct { + struct rb_node rb; + unsigned long rb_subtree_last; + } shared; + /* + * Serialized by mmap_sem. Never use directly because it is + * valid only when vm_file is NULL. Use anon_vma_name instead. + */ + struct anon_vma_name *anon_name; + }; /* * A file's MAP_PRIVATE vma can be in both i_mmap tree and anon_vma @@ -466,9 +511,7 @@ struct vm_area_struct { struct kioctx_table; struct mm_struct { struct { - struct vm_area_struct *mmap; /* list of VMAs */ - struct rb_root mm_rb; - u64 vmacache_seqnum; /* per-thread vmacache */ + struct maple_tree mm_mt; #ifdef CONFIG_MMU unsigned long (*get_unmapped_area) (struct file *filp, unsigned long addr, unsigned long len, @@ -482,7 +525,6 @@ struct mm_struct { unsigned long mmap_compat_legacy_base; #endif unsigned long task_size; /* size of task vm space */ - unsigned long highest_vm_end; /* highest vma end address */ pgd_t * pgd; #ifdef CONFIG_MEMBARRIER @@ -612,27 +654,27 @@ struct mm_struct { #endif #ifdef CONFIG_NUMA_BALANCING /* - * numa_next_scan is the next time that the PTEs will be marked - * pte_numa. NUMA hinting faults will gather statistics and - * migrate pages to new nodes if necessary. + * numa_next_scan is the next time that PTEs will be remapped + * PROT_NONE to trigger NUMA hinting faults; such faults gather + * statistics and migrate pages to new nodes if necessary. */ unsigned long numa_next_scan; - /* Restart point for scanning and setting pte_numa */ + /* Restart point for scanning and remapping PTEs. */ unsigned long numa_scan_offset; - /* numa_scan_seq prevents two threads setting pte_numa */ + /* numa_scan_seq prevents two threads remapping PTEs. */ int numa_scan_seq; #endif /* * An operation with batched TLB flushing is going on. Anything * that can move process memory needs to flush the TLB when - * moving a PROT_NONE or PROT_NUMA mapped page. + * moving a PROT_NONE mapped page. */ atomic_t tlb_flush_pending; #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH /* See flush_tlb_batched_pending() */ - bool tlb_flush_batched; + atomic_t tlb_flush_batched; #endif struct uprobes_state uprobes_state; #ifdef CONFIG_PREEMPT_RT @@ -643,9 +685,37 @@ struct mm_struct { #endif struct work_struct async_put_work; -#ifdef CONFIG_IOMMU_SUPPORT +#ifdef CONFIG_IOMMU_SVA u32 pasid; #endif +#ifdef CONFIG_KSM + /* + * Represent how many pages of this process are involved in KSM + * merging. + */ + unsigned long ksm_merging_pages; + /* + * Represent how many pages are checked for ksm merging + * including merged and not merged. + */ + unsigned long ksm_rmap_items; +#endif +#ifdef CONFIG_LRU_GEN + struct { + /* this mm_struct is on lru_gen_mm_list */ + struct list_head list; + /* + * Set when switching to this mm_struct, as a hint of + * whether it has been used since the last time per-node + * page table walkers cleared the corresponding bits. + */ + unsigned long bitmap; +#ifdef CONFIG_MEMCG + /* points to the memcg of "owner" above */ + struct mem_cgroup *memcg; +#endif + } lru_gen; +#endif /* CONFIG_LRU_GEN */ } __randomize_layout; /* @@ -655,6 +725,7 @@ struct mm_struct { unsigned long cpu_bitmap[]; }; +#define MM_MT_FLAGS (MT_FLAGS_ALLOC_RANGE | MT_FLAGS_LOCK_EXTERN) extern struct mm_struct init_mm; /* Pointer magic because the dynamic array size confuses some compilers. */ @@ -672,94 +743,91 @@ static inline cpumask_t *mm_cpumask(struct mm_struct *mm) return (struct cpumask *)&mm->cpu_bitmap; } -struct mmu_gather; -extern void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm); -extern void tlb_gather_mmu_fullmm(struct mmu_gather *tlb, struct mm_struct *mm); -extern void tlb_finish_mmu(struct mmu_gather *tlb); +#ifdef CONFIG_LRU_GEN + +struct lru_gen_mm_list { + /* mm_struct list for page table walkers */ + struct list_head fifo; + /* protects the list above */ + spinlock_t lock; +}; + +void lru_gen_add_mm(struct mm_struct *mm); +void lru_gen_del_mm(struct mm_struct *mm); +#ifdef CONFIG_MEMCG +void lru_gen_migrate_mm(struct mm_struct *mm); +#endif -static inline void init_tlb_flush_pending(struct mm_struct *mm) +static inline void lru_gen_init_mm(struct mm_struct *mm) { - atomic_set(&mm->tlb_flush_pending, 0); + INIT_LIST_HEAD(&mm->lru_gen.list); + mm->lru_gen.bitmap = 0; +#ifdef CONFIG_MEMCG + mm->lru_gen.memcg = NULL; +#endif } -static inline void inc_tlb_flush_pending(struct mm_struct *mm) +static inline void lru_gen_use_mm(struct mm_struct *mm) { - atomic_inc(&mm->tlb_flush_pending); /* - * The only time this value is relevant is when there are indeed pages - * to flush. And we'll only flush pages after changing them, which - * requires the PTL. - * - * So the ordering here is: - * - * atomic_inc(&mm->tlb_flush_pending); - * spin_lock(&ptl); - * ... - * set_pte_at(); - * spin_unlock(&ptl); - * - * spin_lock(&ptl) - * mm_tlb_flush_pending(); - * .... - * spin_unlock(&ptl); - * - * flush_tlb_range(); - * atomic_dec(&mm->tlb_flush_pending); - * - * Where the increment if constrained by the PTL unlock, it thus - * ensures that the increment is visible if the PTE modification is - * visible. After all, if there is no PTE modification, nobody cares - * about TLB flushes either. - * - * This very much relies on users (mm_tlb_flush_pending() and - * mm_tlb_flush_nested()) only caring about _specific_ PTEs (and - * therefore specific PTLs), because with SPLIT_PTE_PTLOCKS and RCpc - * locks (PPC) the unlock of one doesn't order against the lock of - * another PTL. - * - * The decrement is ordered by the flush_tlb_range(), such that - * mm_tlb_flush_pending() will not return false unless all flushes have - * completed. + * When the bitmap is set, page reclaim knows this mm_struct has been + * used since the last time it cleared the bitmap. So it might be worth + * walking the page tables of this mm_struct to clear the accessed bit. */ + WRITE_ONCE(mm->lru_gen.bitmap, -1); } -static inline void dec_tlb_flush_pending(struct mm_struct *mm) +#else /* !CONFIG_LRU_GEN */ + +static inline void lru_gen_add_mm(struct mm_struct *mm) { - /* - * See inc_tlb_flush_pending(). - * - * This cannot be smp_mb__before_atomic() because smp_mb() simply does - * not order against TLB invalidate completion, which is what we need. - * - * Therefore we must rely on tlb_flush_*() to guarantee order. - */ - atomic_dec(&mm->tlb_flush_pending); } -static inline bool mm_tlb_flush_pending(struct mm_struct *mm) +static inline void lru_gen_del_mm(struct mm_struct *mm) { - /* - * Must be called after having acquired the PTL; orders against that - * PTLs release and therefore ensures that if we observe the modified - * PTE we must also observe the increment from inc_tlb_flush_pending(). - * - * That is, it only guarantees to return true if there is a flush - * pending for _this_ PTL. - */ - return atomic_read(&mm->tlb_flush_pending); } -static inline bool mm_tlb_flush_nested(struct mm_struct *mm) +#ifdef CONFIG_MEMCG +static inline void lru_gen_migrate_mm(struct mm_struct *mm) { - /* - * Similar to mm_tlb_flush_pending(), we must have acquired the PTL - * for which there is a TLB flush pending in order to guarantee - * we've seen both that PTE modification and the increment. - * - * (no requirement on actually still holding the PTL, that is irrelevant) - */ - return atomic_read(&mm->tlb_flush_pending) > 1; } +#endif + +static inline void lru_gen_init_mm(struct mm_struct *mm) +{ +} + +static inline void lru_gen_use_mm(struct mm_struct *mm) +{ +} + +#endif /* CONFIG_LRU_GEN */ + +struct vma_iterator { + struct ma_state mas; +}; + +#define VMA_ITERATOR(name, __mm, __addr) \ + struct vma_iterator name = { \ + .mas = { \ + .tree = &(__mm)->mm_mt, \ + .index = __addr, \ + .node = MAS_START, \ + }, \ + } + +static inline void vma_iter_init(struct vma_iterator *vmi, + struct mm_struct *mm, unsigned long addr) +{ + vmi->mas.tree = &mm->mm_mt; + vmi->mas.index = addr; + vmi->mas.node = MAS_START; +} + +struct mmu_gather; +extern void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm); +extern void tlb_gather_mmu_fullmm(struct mmu_gather *tlb, struct mm_struct *mm); +extern void tlb_finish_mmu(struct mmu_gather *tlb); struct vm_fault; @@ -792,6 +860,7 @@ typedef __bitwise unsigned int vm_fault_t; * @VM_FAULT_NEEDDSYNC: ->fault did not modify page tables and needs * fsync() to complete (for synchronous page faults * in DAX) + * @VM_FAULT_COMPLETED: ->fault completed, meanwhile mmap lock released * @VM_FAULT_HINDEX_MASK: mask HINDEX value * */ @@ -809,6 +878,7 @@ enum vm_fault_reason { VM_FAULT_FALLBACK = (__force vm_fault_t)0x000800, VM_FAULT_DONE_COW = (__force vm_fault_t)0x001000, VM_FAULT_NEEDDSYNC = (__force vm_fault_t)0x002000, + VM_FAULT_COMPLETED = (__force vm_fault_t)0x004000, VM_FAULT_HINDEX_MASK = (__force vm_fault_t)0x0f0000, }; @@ -875,4 +945,62 @@ typedef struct { unsigned long val; } swp_entry_t; +/** + * enum fault_flag - Fault flag definitions. + * @FAULT_FLAG_WRITE: Fault was a write fault. + * @FAULT_FLAG_MKWRITE: Fault was mkwrite of existing PTE. + * @FAULT_FLAG_ALLOW_RETRY: Allow to retry the fault if blocked. + * @FAULT_FLAG_RETRY_NOWAIT: Don't drop mmap_lock and wait when retrying. + * @FAULT_FLAG_KILLABLE: The fault task is in SIGKILL killable region. + * @FAULT_FLAG_TRIED: The fault has been tried once. + * @FAULT_FLAG_USER: The fault originated in userspace. + * @FAULT_FLAG_REMOTE: The fault is not for current task/mm. + * @FAULT_FLAG_INSTRUCTION: The fault was during an instruction fetch. + * @FAULT_FLAG_INTERRUPTIBLE: The fault can be interrupted by non-fatal signals. + * @FAULT_FLAG_UNSHARE: The fault is an unsharing request to unshare (and mark + * exclusive) a possibly shared anonymous page that is + * mapped R/O. + * @FAULT_FLAG_ORIG_PTE_VALID: whether the fault has vmf->orig_pte cached. + * We should only access orig_pte if this flag set. + * + * About @FAULT_FLAG_ALLOW_RETRY and @FAULT_FLAG_TRIED: we can specify + * whether we would allow page faults to retry by specifying these two + * fault flags correctly. Currently there can be three legal combinations: + * + * (a) ALLOW_RETRY and !TRIED: this means the page fault allows retry, and + * this is the first try + * + * (b) ALLOW_RETRY and TRIED: this means the page fault allows retry, and + * we've already tried at least once + * + * (c) !ALLOW_RETRY and !TRIED: this means the page fault does not allow retry + * + * The unlisted combination (!ALLOW_RETRY && TRIED) is illegal and should never + * be used. Note that page faults can be allowed to retry for multiple times, + * in which case we'll have an initial fault with flags (a) then later on + * continuous faults with flags (b). We should always try to detect pending + * signals before a retry to make sure the continuous page faults can still be + * interrupted if necessary. + * + * The combination FAULT_FLAG_WRITE|FAULT_FLAG_UNSHARE is illegal. + * FAULT_FLAG_UNSHARE is ignored and treated like an ordinary read fault when + * no existing R/O-mapped anonymous page is encountered. + */ +enum fault_flag { + FAULT_FLAG_WRITE = 1 << 0, + FAULT_FLAG_MKWRITE = 1 << 1, + FAULT_FLAG_ALLOW_RETRY = 1 << 2, + FAULT_FLAG_RETRY_NOWAIT = 1 << 3, + FAULT_FLAG_KILLABLE = 1 << 4, + FAULT_FLAG_TRIED = 1 << 5, + FAULT_FLAG_USER = 1 << 6, + FAULT_FLAG_REMOTE = 1 << 7, + FAULT_FLAG_INSTRUCTION = 1 << 8, + FAULT_FLAG_INTERRUPTIBLE = 1 << 9, + FAULT_FLAG_UNSHARE = 1 << 10, + FAULT_FLAG_ORIG_PTE_VALID = 1 << 11, +}; + +typedef unsigned int __bitwise zap_flags_t; + #endif /* _LINUX_MM_TYPES_H */ diff --git a/include/linux/mm_types_task.h b/include/linux/mm_types_task.h index c1bc6731125c..0bb4b6da9993 100644 --- a/include/linux/mm_types_task.h +++ b/include/linux/mm_types_task.h @@ -25,18 +25,6 @@ #define ALLOC_SPLIT_PTLOCKS (SPINLOCK_SIZE > BITS_PER_LONG/8) /* - * The per task VMA cache array: - */ -#define VMACACHE_BITS 2 -#define VMACACHE_SIZE (1U << VMACACHE_BITS) -#define VMACACHE_MASK (VMACACHE_SIZE - 1) - -struct vmacache { - u64 seqnum; - struct vm_area_struct *vmas[VMACACHE_SIZE]; -}; - -/* * When updating this, please also update struct resident_page_types[] in * kernel/fork.c */ diff --git a/include/linux/mman.h b/include/linux/mman.h index b66e91b8176c..58b3abd457a3 100644 --- a/include/linux/mman.h +++ b/include/linux/mman.h @@ -93,10 +93,6 @@ static inline void vm_unacct_memory(long pages) #define arch_calc_vm_flag_bits(flags) 0 #endif -#ifndef arch_vm_get_page_prot -#define arch_vm_get_page_prot(vm_flags) __pgprot(0) -#endif - #ifndef arch_validate_prot /* * This is called from mprotect(). PROT_GROWSDOWN and PROT_GROWSUP have diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h index 37f975875102..c726ea781255 100644 --- a/include/linux/mmc/card.h +++ b/include/linux/mmc/card.h @@ -219,7 +219,8 @@ struct sdio_cccr { wide_bus:1, high_power:1, high_speed:1, - disable_cd:1; + disable_cd:1, + enable_async_irq:1; }; struct sdio_cis { @@ -292,6 +293,7 @@ struct mmc_card { #define MMC_QUIRK_BROKEN_IRQ_POLLING (1<<11) /* Polling SDIO_CCCR_INTx could create a fake interrupt */ #define MMC_QUIRK_TRIM_BROKEN (1<<12) /* Skip trim */ #define MMC_QUIRK_BROKEN_HPI (1<<13) /* Disable broken HPI support */ +#define MMC_QUIRK_BROKEN_SD_DISCARD (1<<14) /* Disable broken SD discard support */ bool reenable_cmdq; /* Re-enable Command Queue */ @@ -343,10 +345,16 @@ static inline bool mmc_large_sector(struct mmc_card *card) return card->ext_csd.data_sector_size == 4096; } +static inline int mmc_card_enable_async_irq(struct mmc_card *card) +{ + return card->cccr.enable_async_irq; +} + bool mmc_card_is_blockaddr(struct mmc_card *card); #define mmc_card_mmc(c) ((c)->type == MMC_TYPE_MMC) #define mmc_card_sd(c) ((c)->type == MMC_TYPE_SD) #define mmc_card_sdio(c) ((c)->type == MMC_TYPE_SDIO) +#define mmc_card_sd_combo(c) ((c)->type == MMC_TYPE_SD_COMBO) #endif /* LINUX_MMC_CARD_H */ diff --git a/include/linux/mmc/core.h b/include/linux/mmc/core.h index 71101d1ec825..6efec0b9820c 100644 --- a/include/linux/mmc/core.h +++ b/include/linux/mmc/core.h @@ -175,8 +175,8 @@ void mmc_wait_for_req(struct mmc_host *host, struct mmc_request *mrq); int mmc_wait_for_cmd(struct mmc_host *host, struct mmc_command *cmd, int retries); -int mmc_hw_reset(struct mmc_host *host); -int mmc_sw_reset(struct mmc_host *host); +int mmc_hw_reset(struct mmc_card *card); +int mmc_sw_reset(struct mmc_card *card); void mmc_set_data_timeout(struct mmc_data *data, const struct mmc_card *card); #endif /* LINUX_MMC_CORE_H */ diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 7afb57cab00b..8fdd3cf971a3 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -93,6 +93,25 @@ struct mmc_clk_phase_map { struct mmc_host; +enum mmc_err_stat { + MMC_ERR_CMD_TIMEOUT, + MMC_ERR_CMD_CRC, + MMC_ERR_DAT_TIMEOUT, + MMC_ERR_DAT_CRC, + MMC_ERR_AUTO_CMD, + MMC_ERR_ADMA, + MMC_ERR_TUNING, + MMC_ERR_CMDQ_RED, + MMC_ERR_CMDQ_GCE, + MMC_ERR_CMDQ_ICCE, + MMC_ERR_REQ_TIMEOUT, + MMC_ERR_CMDQ_REQ_TIMEOUT, + MMC_ERR_ICE_CFG, + MMC_ERR_CTRL_TIMEOUT, + MMC_ERR_UNEXPECTED_IRQ, + MMC_ERR_MAX, +}; + struct mmc_host_ops { /* * It is optional for the host to implement pre_req and post_req in @@ -181,7 +200,7 @@ struct mmc_host_ops { unsigned int max_dtr, int host_drv, int card_drv, int *drv_type); /* Reset the eMMC card via RST_n */ - void (*hw_reset)(struct mmc_host *host); + void (*card_hw_reset)(struct mmc_host *host); void (*card_event)(struct mmc_host *host); /* @@ -457,7 +476,7 @@ struct mmc_host { unsigned int sdio_irqs; struct task_struct *sdio_irq_thread; - struct delayed_work sdio_irq_work; + struct work_struct sdio_irq_work; bool sdio_irq_pending; atomic_t sdio_irq_thread_abort; @@ -501,6 +520,7 @@ struct mmc_host { /* Host Software Queue support */ bool hsq_enabled; + u32 err_stats[MMC_ERR_MAX]; unsigned long private[] ____cacheline_aligned; }; @@ -635,6 +655,12 @@ static inline enum dma_data_direction mmc_get_dma_dir(struct mmc_data *data) return data->flags & MMC_DATA_WRITE ? DMA_TO_DEVICE : DMA_FROM_DEVICE; } +static inline void mmc_debugfs_err_stats_inc(struct mmc_host *host, + enum mmc_err_stat stat) +{ + host->err_stats[stat] += 1; +} + int mmc_send_tuning(struct mmc_host *host, u32 opcode, int *cmd_error); int mmc_send_abort_tuning(struct mmc_host *host, u32 opcode); int mmc_get_ext_csd(struct mmc_card *card, u8 **new_ext_csd); diff --git a/include/linux/mmc/mmc.h b/include/linux/mmc/mmc.h index d9a65c6a8816..9c50bc40f8ff 100644 --- a/include/linux/mmc/mmc.h +++ b/include/linux/mmc/mmc.h @@ -99,6 +99,12 @@ static inline bool mmc_op_multi(u32 opcode) opcode == MMC_READ_MULTIPLE_BLOCK; } +static inline bool mmc_op_tuning(u32 opcode) +{ + return opcode == MMC_SEND_TUNING_BLOCK || + opcode == MMC_SEND_TUNING_BLOCK_HS200; +} + /* * MMC_SWITCH argument format: * diff --git a/include/linux/mmc/sdio.h b/include/linux/mmc/sdio.h index 2a05d1ac4f0e..1ef400f28642 100644 --- a/include/linux/mmc/sdio.h +++ b/include/linux/mmc/sdio.h @@ -159,6 +159,11 @@ #define SDIO_DTSx_SET_TYPE_A (1 << SDIO_DRIVE_DTSx_SHIFT) #define SDIO_DTSx_SET_TYPE_C (2 << SDIO_DRIVE_DTSx_SHIFT) #define SDIO_DTSx_SET_TYPE_D (3 << SDIO_DRIVE_DTSx_SHIFT) + +#define SDIO_CCCR_INTERRUPT_EXT 0x16 +#define SDIO_INTERRUPT_EXT_SAI (1 << 0) +#define SDIO_INTERRUPT_EXT_EAI (1 << 1) + /* * Function Basic Registers (FBR) */ diff --git a/include/linux/mmc/sdio_ids.h b/include/linux/mmc/sdio_ids.h index 53f0efa0bccf..74f9d9a6d330 100644 --- a/include/linux/mmc/sdio_ids.h +++ b/include/linux/mmc/sdio_ids.h @@ -74,6 +74,7 @@ #define SDIO_DEVICE_ID_BROADCOM_43362 0xa962 #define SDIO_DEVICE_ID_BROADCOM_43364 0xa9a4 #define SDIO_DEVICE_ID_BROADCOM_43430 0xa9a6 +#define SDIO_DEVICE_ID_BROADCOM_CYPRESS_43439 0xa9af #define SDIO_DEVICE_ID_BROADCOM_43455 0xa9bf #define SDIO_DEVICE_ID_BROADCOM_CYPRESS_43752 0xaae8 diff --git a/include/linux/mmdebug.h b/include/linux/mmdebug.h index d7285f8148a3..b8728d11c949 100644 --- a/include/linux/mmdebug.h +++ b/include/linux/mmdebug.h @@ -54,6 +54,15 @@ void dump_mm(const struct mm_struct *mm); } \ unlikely(__ret_warn_once); \ }) +#define VM_WARN_ON_FOLIO(cond, folio) ({ \ + int __ret_warn = !!(cond); \ + \ + if (unlikely(__ret_warn)) { \ + dump_page(&folio->page, "VM_WARN_ON_FOLIO(" __stringify(cond)")");\ + WARN_ON(1); \ + } \ + unlikely(__ret_warn); \ +}) #define VM_WARN_ON_ONCE_FOLIO(cond, folio) ({ \ static bool __section(".data.once") __warned; \ int __ret_warn_once = !!(cond); \ @@ -79,11 +88,18 @@ void dump_mm(const struct mm_struct *mm); #define VM_WARN_ON(cond) BUILD_BUG_ON_INVALID(cond) #define VM_WARN_ON_ONCE(cond) BUILD_BUG_ON_INVALID(cond) #define VM_WARN_ON_ONCE_PAGE(cond, page) BUILD_BUG_ON_INVALID(cond) +#define VM_WARN_ON_FOLIO(cond, folio) BUILD_BUG_ON_INVALID(cond) #define VM_WARN_ON_ONCE_FOLIO(cond, folio) BUILD_BUG_ON_INVALID(cond) #define VM_WARN_ONCE(cond, format...) BUILD_BUG_ON_INVALID(cond) #define VM_WARN(cond, format...) BUILD_BUG_ON_INVALID(cond) #endif +#ifdef CONFIG_DEBUG_VM_IRQSOFF +#define VM_WARN_ON_IRQS_ENABLED() WARN_ON_ONCE(!irqs_disabled()) +#else +#define VM_WARN_ON_IRQS_ENABLED() do { } while (0) +#endif + #ifdef CONFIG_DEBUG_VIRTUAL #define VIRTUAL_BUG_ON(cond) BUG_ON(cond) #else diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h index 45fc2c81e370..d6c06e140277 100644 --- a/include/linux/mmu_notifier.h +++ b/include/linux/mmu_notifier.h @@ -198,7 +198,7 @@ struct mmu_notifier_ops { * invalidate_range_start()/end() notifiers, as * invalidate_range() already catches the points in time when an * external TLB range needs to be flushed. For more in depth - * discussion on this see Documentation/vm/mmu_notifier.rst + * discussion on this see Documentation/mm/mmu_notifier.rst * * Note that this function might be called with just a sub-range * of what was passed to invalidate_range_start()/end(), if diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 936dc0b6c226..5f74891556f3 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -24,10 +24,10 @@ #include <asm/page.h> /* Free memory management - zoned buddy allocator. */ -#ifndef CONFIG_FORCE_MAX_ZONEORDER +#ifndef CONFIG_ARCH_FORCE_MAX_ORDER #define MAX_ORDER 11 #else -#define MAX_ORDER CONFIG_FORCE_MAX_ZONEORDER +#define MAX_ORDER CONFIG_ARCH_FORCE_MAX_ORDER #endif #define MAX_ORDER_NR_PAGES (1 << (MAX_ORDER - 1)) @@ -54,10 +54,7 @@ enum migratetype { * * The way to use it is to change migratetype of a range of * pageblocks to MIGRATE_CMA which can be done by - * __free_pageblock_cma() function. What is important though - * is that a range of pageblocks must be aligned to - * MAX_ORDER_NR_PAGES should biggest page be bigger than - * a single pageblock. + * __free_pageblock_cma() function. */ MIGRATE_CMA, #endif @@ -83,6 +80,17 @@ static inline bool is_migrate_movable(int mt) return is_migrate_cma(mt) || mt == MIGRATE_MOVABLE; } +/* + * Check whether a migratetype can be merged with another migratetype. + * + * It is only mergeable when it can fall back to other migratetypes for + * allocation. See fallbacks[MIGRATE_TYPES][3] in page_alloc.c. + */ +static inline bool migratetype_is_mergeable(int mt) +{ + return mt < MIGRATE_PCPTYPES; +} + #define for_each_migratetype_order(order, type) \ for (order = 0; order < MAX_ORDER; order++) \ for (type = 0; type < MIGRATE_TYPES; type++) @@ -113,20 +121,6 @@ static inline bool free_area_empty(struct free_area *area, int migratetype) struct pglist_data; -/* - * Add a wild amount of padding here to ensure data fall into separate - * cachelines. There are very few zone structures in the machine, so space - * consumption is not a concern here. - */ -#if defined(CONFIG_SMP) -struct zone_padding { - char x[0]; -} ____cacheline_internodealigned_in_smp; -#define ZONE_PADDING(name) struct zone_padding name; -#else -#define ZONE_PADDING(name) -#endif - #ifdef CONFIG_NUMA enum numa_stat_item { NUMA_HIT, /* allocated in intended node */ @@ -208,9 +202,14 @@ enum node_stat_item { NR_KERNEL_SCS_KB, /* measured in KiB */ #endif NR_PAGETABLE, /* used for pagetables */ + NR_SECONDARY_PAGETABLE, /* secondary pagetables, e.g. KVM pagetables */ #ifdef CONFIG_SWAP NR_SWAPCACHE, #endif +#ifdef CONFIG_NUMA_BALANCING + PGPROMOTE_SUCCESS, /* promote successfully */ + PGPROMOTE_CANDIDATE, /* candidate pages to promote */ +#endif NR_VM_NODE_STAT_ITEMS }; @@ -295,6 +294,8 @@ static inline bool is_active_lru(enum lru_list lru) return (lru == LRU_ACTIVE_ANON || lru == LRU_ACTIVE_FILE); } +#define WORKINGSET_ANON 0 +#define WORKINGSET_FILE 1 #define ANON_AND_FILE 2 enum lruvec_flags { @@ -303,6 +304,207 @@ enum lruvec_flags { */ }; +#endif /* !__GENERATING_BOUNDS_H */ + +/* + * Evictable pages are divided into multiple generations. The youngest and the + * oldest generation numbers, max_seq and min_seq, are monotonically increasing. + * They form a sliding window of a variable size [MIN_NR_GENS, MAX_NR_GENS]. An + * offset within MAX_NR_GENS, i.e., gen, indexes the LRU list of the + * corresponding generation. The gen counter in folio->flags stores gen+1 while + * a page is on one of lrugen->lists[]. Otherwise it stores 0. + * + * A page is added to the youngest generation on faulting. The aging needs to + * check the accessed bit at least twice before handing this page over to the + * eviction. The first check takes care of the accessed bit set on the initial + * fault; the second check makes sure this page hasn't been used since then. + * This process, AKA second chance, requires a minimum of two generations, + * hence MIN_NR_GENS. And to maintain ABI compatibility with the active/inactive + * LRU, e.g., /proc/vmstat, these two generations are considered active; the + * rest of generations, if they exist, are considered inactive. See + * lru_gen_is_active(). + * + * PG_active is always cleared while a page is on one of lrugen->lists[] so that + * the aging needs not to worry about it. And it's set again when a page + * considered active is isolated for non-reclaiming purposes, e.g., migration. + * See lru_gen_add_folio() and lru_gen_del_folio(). + * + * MAX_NR_GENS is set to 4 so that the multi-gen LRU can support twice the + * number of categories of the active/inactive LRU when keeping track of + * accesses through page tables. This requires order_base_2(MAX_NR_GENS+1) bits + * in folio->flags. + */ +#define MIN_NR_GENS 2U +#define MAX_NR_GENS 4U + +/* + * Each generation is divided into multiple tiers. A page accessed N times + * through file descriptors is in tier order_base_2(N). A page in the first tier + * (N=0,1) is marked by PG_referenced unless it was faulted in through page + * tables or read ahead. A page in any other tier (N>1) is marked by + * PG_referenced and PG_workingset. This implies a minimum of two tiers is + * supported without using additional bits in folio->flags. + * + * In contrast to moving across generations which requires the LRU lock, moving + * across tiers only involves atomic operations on folio->flags and therefore + * has a negligible cost in the buffered access path. In the eviction path, + * comparisons of refaulted/(evicted+protected) from the first tier and the + * rest infer whether pages accessed multiple times through file descriptors + * are statistically hot and thus worth protecting. + * + * MAX_NR_TIERS is set to 4 so that the multi-gen LRU can support twice the + * number of categories of the active/inactive LRU when keeping track of + * accesses through file descriptors. This uses MAX_NR_TIERS-2 spare bits in + * folio->flags. + */ +#define MAX_NR_TIERS 4U + +#ifndef __GENERATING_BOUNDS_H + +struct lruvec; +struct page_vma_mapped_walk; + +#define LRU_GEN_MASK ((BIT(LRU_GEN_WIDTH) - 1) << LRU_GEN_PGOFF) +#define LRU_REFS_MASK ((BIT(LRU_REFS_WIDTH) - 1) << LRU_REFS_PGOFF) + +#ifdef CONFIG_LRU_GEN + +enum { + LRU_GEN_ANON, + LRU_GEN_FILE, +}; + +enum { + LRU_GEN_CORE, + LRU_GEN_MM_WALK, + LRU_GEN_NONLEAF_YOUNG, + NR_LRU_GEN_CAPS +}; + +#define MIN_LRU_BATCH BITS_PER_LONG +#define MAX_LRU_BATCH (MIN_LRU_BATCH * 64) + +/* whether to keep historical stats from evicted generations */ +#ifdef CONFIG_LRU_GEN_STATS +#define NR_HIST_GENS MAX_NR_GENS +#else +#define NR_HIST_GENS 1U +#endif + +/* + * The youngest generation number is stored in max_seq for both anon and file + * types as they are aged on an equal footing. The oldest generation numbers are + * stored in min_seq[] separately for anon and file types as clean file pages + * can be evicted regardless of swap constraints. + * + * Normally anon and file min_seq are in sync. But if swapping is constrained, + * e.g., out of swap space, file min_seq is allowed to advance and leave anon + * min_seq behind. + * + * The number of pages in each generation is eventually consistent and therefore + * can be transiently negative when reset_batch_size() is pending. + */ +struct lru_gen_struct { + /* the aging increments the youngest generation number */ + unsigned long max_seq; + /* the eviction increments the oldest generation numbers */ + unsigned long min_seq[ANON_AND_FILE]; + /* the birth time of each generation in jiffies */ + unsigned long timestamps[MAX_NR_GENS]; + /* the multi-gen LRU lists, lazily sorted on eviction */ + struct list_head lists[MAX_NR_GENS][ANON_AND_FILE][MAX_NR_ZONES]; + /* the multi-gen LRU sizes, eventually consistent */ + long nr_pages[MAX_NR_GENS][ANON_AND_FILE][MAX_NR_ZONES]; + /* the exponential moving average of refaulted */ + unsigned long avg_refaulted[ANON_AND_FILE][MAX_NR_TIERS]; + /* the exponential moving average of evicted+protected */ + unsigned long avg_total[ANON_AND_FILE][MAX_NR_TIERS]; + /* the first tier doesn't need protection, hence the minus one */ + unsigned long protected[NR_HIST_GENS][ANON_AND_FILE][MAX_NR_TIERS - 1]; + /* can be modified without holding the LRU lock */ + atomic_long_t evicted[NR_HIST_GENS][ANON_AND_FILE][MAX_NR_TIERS]; + atomic_long_t refaulted[NR_HIST_GENS][ANON_AND_FILE][MAX_NR_TIERS]; + /* whether the multi-gen LRU is enabled */ + bool enabled; +}; + +enum { + MM_LEAF_TOTAL, /* total leaf entries */ + MM_LEAF_OLD, /* old leaf entries */ + MM_LEAF_YOUNG, /* young leaf entries */ + MM_NONLEAF_TOTAL, /* total non-leaf entries */ + MM_NONLEAF_FOUND, /* non-leaf entries found in Bloom filters */ + MM_NONLEAF_ADDED, /* non-leaf entries added to Bloom filters */ + NR_MM_STATS +}; + +/* double-buffering Bloom filters */ +#define NR_BLOOM_FILTERS 2 + +struct lru_gen_mm_state { + /* set to max_seq after each iteration */ + unsigned long seq; + /* where the current iteration continues (inclusive) */ + struct list_head *head; + /* where the last iteration ended (exclusive) */ + struct list_head *tail; + /* to wait for the last page table walker to finish */ + struct wait_queue_head wait; + /* Bloom filters flip after each iteration */ + unsigned long *filters[NR_BLOOM_FILTERS]; + /* the mm stats for debugging */ + unsigned long stats[NR_HIST_GENS][NR_MM_STATS]; + /* the number of concurrent page table walkers */ + int nr_walkers; +}; + +struct lru_gen_mm_walk { + /* the lruvec under reclaim */ + struct lruvec *lruvec; + /* unstable max_seq from lru_gen_struct */ + unsigned long max_seq; + /* the next address within an mm to scan */ + unsigned long next_addr; + /* to batch promoted pages */ + int nr_pages[MAX_NR_GENS][ANON_AND_FILE][MAX_NR_ZONES]; + /* to batch the mm stats */ + int mm_stats[NR_MM_STATS]; + /* total batched items */ + int batched; + bool can_swap; + bool force_scan; +}; + +void lru_gen_init_lruvec(struct lruvec *lruvec); +void lru_gen_look_around(struct page_vma_mapped_walk *pvmw); + +#ifdef CONFIG_MEMCG +void lru_gen_init_memcg(struct mem_cgroup *memcg); +void lru_gen_exit_memcg(struct mem_cgroup *memcg); +#endif + +#else /* !CONFIG_LRU_GEN */ + +static inline void lru_gen_init_lruvec(struct lruvec *lruvec) +{ +} + +static inline void lru_gen_look_around(struct page_vma_mapped_walk *pvmw) +{ +} + +#ifdef CONFIG_MEMCG +static inline void lru_gen_init_memcg(struct mem_cgroup *memcg) +{ +} + +static inline void lru_gen_exit_memcg(struct mem_cgroup *memcg) +{ +} +#endif + +#endif /* CONFIG_LRU_GEN */ + struct lruvec { struct list_head lists[NR_LRU_LISTS]; /* per lruvec lru_lock for memcg */ @@ -320,6 +522,12 @@ struct lruvec { unsigned long refaults[ANON_AND_FILE]; /* Various lruvec state flags (enum lruvec_flags) */ unsigned long flags; +#ifdef CONFIG_LRU_GEN + /* evictable pages divided into generations */ + struct lru_gen_struct lrugen; + /* to concurrently iterate lru_gen_mm_list */ + struct lru_gen_mm_state mm_state; +#endif #ifdef CONFIG_MEMCG struct pglist_data *pgdat; #endif @@ -339,26 +547,23 @@ enum zone_watermarks { WMARK_MIN, WMARK_LOW, WMARK_HIGH, + WMARK_PROMO, NR_WMARK }; /* - * One per migratetype for each PAGE_ALLOC_COSTLY_ORDER plus one additional - * for pageblock size for THP if configured. + * One per migratetype for each PAGE_ALLOC_COSTLY_ORDER. One additional list + * for THP which will usually be GFP_MOVABLE. Even if it is another type, + * it should not contribute to serious fragmentation causing THP allocation + * failures. */ #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define NR_PCP_THP 1 #else #define NR_PCP_THP 0 #endif -#define NR_PCP_LISTS (MIGRATE_PCPTYPES * (PAGE_ALLOC_COSTLY_ORDER + 1 + NR_PCP_THP)) - -/* - * Shift to encode migratetype and order in the same integer, with order - * in the least significant bits. - */ -#define NR_PCP_ORDER_WIDTH 8 -#define NR_PCP_ORDER_MASK ((1<<NR_PCP_ORDER_WIDTH) - 1) +#define NR_LOWORDER_PCP_LISTS (MIGRATE_PCPTYPES * (PAGE_ALLOC_COSTLY_ORDER + 1)) +#define NR_PCP_LISTS (NR_LOWORDER_PCP_LISTS + NR_PCP_THP) #define min_wmark_pages(z) (z->_watermark[WMARK_MIN] + z->watermark_boost) #define low_wmark_pages(z) (z->_watermark[WMARK_LOW] + z->watermark_boost) @@ -367,6 +572,7 @@ enum zone_watermarks { /* Fields and list protected by pagesets local_lock in page_alloc.c */ struct per_cpu_pages { + spinlock_t lock; /* Protects lists field */ int count; /* number of pages in the list */ int high; /* high watermark, emptying needed */ int batch; /* chunk size for buddy add/remove */ @@ -377,7 +583,7 @@ struct per_cpu_pages { /* Lists of pages, one per migrate type stored on the pcp-lists */ struct list_head lists[NR_PCP_LISTS]; -}; +} ____cacheline_aligned_in_smp; struct per_cpu_zonestat { #ifdef CONFIG_SMP @@ -579,8 +785,8 @@ struct zone { * give them a chance of being in the same cacheline. * * Write access to present_pages at runtime should be protected by - * mem_hotplug_begin/end(). Any reader who can't tolerant drift of - * present_pages should get_online_mems() to get a stable value. + * mem_hotplug_begin/done(). Any reader who can't tolerant drift of + * present_pages should use get_online_mems() to get a stable value. */ atomic_long_t managed_pages; unsigned long spanned_pages; @@ -611,7 +817,7 @@ struct zone { int initialized; /* Write-intensive fields used from the page allocator */ - ZONE_PADDING(_pad1_) + CACHELINE_PADDING(_pad1_); /* free areas of different sizes */ struct free_area free_area[MAX_ORDER]; @@ -623,7 +829,7 @@ struct zone { spinlock_t lock; /* Write-intensive fields used by compaction and vmstats. */ - ZONE_PADDING(_pad2_) + CACHELINE_PADDING(_pad2_); /* * When free pages are below this point, additional steps are taken @@ -660,7 +866,7 @@ struct zone { bool contiguous; - ZONE_PADDING(_pad3_) + CACHELINE_PADDING(_pad3_); /* Zone statistics */ atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS]; atomic_long_t vm_numa_event[NR_VM_NUMA_EVENT_ITEMS]; @@ -718,6 +924,88 @@ static inline bool zone_is_empty(struct zone *zone) return zone->spanned_pages == 0; } +#ifndef BUILD_VDSO32_64 +/* + * The zone field is never updated after free_area_init_core() + * sets it, so none of the operations on it need to be atomic. + */ + +/* Page flags: | [SECTION] | [NODE] | ZONE | [LAST_CPUPID] | ... | FLAGS | */ +#define SECTIONS_PGOFF ((sizeof(unsigned long)*8) - SECTIONS_WIDTH) +#define NODES_PGOFF (SECTIONS_PGOFF - NODES_WIDTH) +#define ZONES_PGOFF (NODES_PGOFF - ZONES_WIDTH) +#define LAST_CPUPID_PGOFF (ZONES_PGOFF - LAST_CPUPID_WIDTH) +#define KASAN_TAG_PGOFF (LAST_CPUPID_PGOFF - KASAN_TAG_WIDTH) +#define LRU_GEN_PGOFF (KASAN_TAG_PGOFF - LRU_GEN_WIDTH) +#define LRU_REFS_PGOFF (LRU_GEN_PGOFF - LRU_REFS_WIDTH) + +/* + * Define the bit shifts to access each section. For non-existent + * sections we define the shift as 0; that plus a 0 mask ensures + * the compiler will optimise away reference to them. + */ +#define SECTIONS_PGSHIFT (SECTIONS_PGOFF * (SECTIONS_WIDTH != 0)) +#define NODES_PGSHIFT (NODES_PGOFF * (NODES_WIDTH != 0)) +#define ZONES_PGSHIFT (ZONES_PGOFF * (ZONES_WIDTH != 0)) +#define LAST_CPUPID_PGSHIFT (LAST_CPUPID_PGOFF * (LAST_CPUPID_WIDTH != 0)) +#define KASAN_TAG_PGSHIFT (KASAN_TAG_PGOFF * (KASAN_TAG_WIDTH != 0)) + +/* NODE:ZONE or SECTION:ZONE is used to ID a zone for the buddy allocator */ +#ifdef NODE_NOT_IN_PAGE_FLAGS +#define ZONEID_SHIFT (SECTIONS_SHIFT + ZONES_SHIFT) +#define ZONEID_PGOFF ((SECTIONS_PGOFF < ZONES_PGOFF) ? \ + SECTIONS_PGOFF : ZONES_PGOFF) +#else +#define ZONEID_SHIFT (NODES_SHIFT + ZONES_SHIFT) +#define ZONEID_PGOFF ((NODES_PGOFF < ZONES_PGOFF) ? \ + NODES_PGOFF : ZONES_PGOFF) +#endif + +#define ZONEID_PGSHIFT (ZONEID_PGOFF * (ZONEID_SHIFT != 0)) + +#define ZONES_MASK ((1UL << ZONES_WIDTH) - 1) +#define NODES_MASK ((1UL << NODES_WIDTH) - 1) +#define SECTIONS_MASK ((1UL << SECTIONS_WIDTH) - 1) +#define LAST_CPUPID_MASK ((1UL << LAST_CPUPID_SHIFT) - 1) +#define KASAN_TAG_MASK ((1UL << KASAN_TAG_WIDTH) - 1) +#define ZONEID_MASK ((1UL << ZONEID_SHIFT) - 1) + +static inline enum zone_type page_zonenum(const struct page *page) +{ + ASSERT_EXCLUSIVE_BITS(page->flags, ZONES_MASK << ZONES_PGSHIFT); + return (page->flags >> ZONES_PGSHIFT) & ZONES_MASK; +} + +static inline enum zone_type folio_zonenum(const struct folio *folio) +{ + return page_zonenum(&folio->page); +} + +#ifdef CONFIG_ZONE_DEVICE +static inline bool is_zone_device_page(const struct page *page) +{ + return page_zonenum(page) == ZONE_DEVICE; +} +extern void memmap_init_zone_device(struct zone *, unsigned long, + unsigned long, struct dev_pagemap *); +#else +static inline bool is_zone_device_page(const struct page *page) +{ + return false; +} +#endif + +static inline bool folio_is_zone_device(const struct folio *folio) +{ + return is_zone_device_page(&folio->page); +} + +static inline bool is_zone_movable_page(const struct page *page) +{ + return page_zonenum(page) == ZONE_MOVABLE; +} +#endif + /* * Return true if [start_pfn, start_pfn + nr_pages) range has a non-empty * intersection with the given zone @@ -857,8 +1145,10 @@ typedef struct pglist_data { atomic_t nr_writeback_throttled;/* nr of writeback-throttled tasks */ unsigned long nr_reclaim_start; /* nr pages written while throttled * when throttling started. */ - struct task_struct *kswapd; /* Protected by - mem_hotplug_begin/end() */ +#ifdef CONFIG_MEMORY_HOTPLUG + struct mutex kswapd_lock; +#endif + struct task_struct *kswapd; /* Protected by kswapd_lock */ int kswapd_order; enum zone_type kswapd_highest_zoneidx; @@ -886,7 +1176,7 @@ typedef struct pglist_data { #endif /* CONFIG_NUMA */ /* Write-intensive fields used by page reclaim */ - ZONE_PADDING(_pad1_) + CACHELINE_PADDING(_pad1_); #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT /* @@ -900,6 +1190,21 @@ typedef struct pglist_data { struct deferred_split deferred_split_queue; #endif +#ifdef CONFIG_NUMA_BALANCING + /* start time in ms of current promote rate limit period */ + unsigned int nbp_rl_start; + /* number of promote candidate pages at start time of current rate limit period */ + unsigned long nbp_rl_nr_cand; + /* promote threshold in ms */ + unsigned int nbp_threshold; + /* start time in ms of current promote threshold adjustment period */ + unsigned int nbp_th_start; + /* + * number of promote candidate pages at stat time of current promote + * threshold adjustment period + */ + unsigned long nbp_th_nr_cand; +#endif /* Fields commonly accessed by the page reclaim scanner */ /* @@ -911,21 +1216,23 @@ typedef struct pglist_data { unsigned long flags; - ZONE_PADDING(_pad2_) +#ifdef CONFIG_LRU_GEN + /* kswap mm walk data */ + struct lru_gen_mm_walk mm_walk; +#endif + + CACHELINE_PADDING(_pad2_); /* Per-node vmstats */ struct per_cpu_nodestat __percpu *per_cpu_nodestats; atomic_long_t vm_stat[NR_VM_NODE_STAT_ITEMS]; +#ifdef CONFIG_NUMA + struct memory_tier __rcu *memtier; +#endif } pg_data_t; #define node_present_pages(nid) (NODE_DATA(nid)->node_present_pages) #define node_spanned_pages(nid) (NODE_DATA(nid)->node_spanned_pages) -#ifdef CONFIG_FLATMEM -#define pgdat_page_nr(pgdat, pagenr) ((pgdat)->node_mem_map + (pagenr)) -#else -#define pgdat_page_nr(pgdat, pagenr) pfn_to_page((pgdat)->node_start_pfn + (pagenr)) -#endif -#define nid_page_nr(nid, pagenr) pgdat_page_nr(NODE_DATA(nid),(pagenr)) #define node_start_pfn(nid) (NODE_DATA(nid)->node_start_pfn) #define node_end_pfn(nid) pgdat_end_pfn(NODE_DATA(nid)) @@ -935,11 +1242,6 @@ static inline unsigned long pgdat_end_pfn(pg_data_t *pgdat) return pgdat->node_start_pfn + pgdat->node_spanned_pages; } -static inline bool pgdat_is_empty(pg_data_t *pgdat) -{ - return !pgdat->node_start_pfn && !pgdat->node_spanned_pages; -} - #include <linux/memory_hotplug.h> void build_all_zonelists(pg_data_t *pgdat); @@ -1056,12 +1358,17 @@ static inline int is_highmem_idx(enum zone_type idx) */ static inline int is_highmem(struct zone *zone) { -#ifdef CONFIG_HIGHMEM return is_highmem_idx(zone_idx(zone)); +} + +#ifdef CONFIG_ZONE_DMA +bool has_managed_dma(void); #else - return 0; -#endif +static inline bool has_managed_dma(void) +{ + return false; } +#endif /* These two functions are used to setup the per zone pages min values */ struct ctl_table; @@ -1092,7 +1399,6 @@ static inline struct pglist_data *NODE_DATA(int nid) { return &contig_page_data; } -#define NODE_MEM_MAP(nid) mem_map #else /* CONFIG_NUMA */ @@ -1380,13 +1686,16 @@ static inline unsigned long *section_to_usemap(struct mem_section *ms) static inline struct mem_section *__nr_to_section(unsigned long nr) { + unsigned long root = SECTION_NR_TO_ROOT(nr); + + if (unlikely(root >= NR_SECTION_ROOTS)) + return NULL; + #ifdef CONFIG_SPARSEMEM_EXTREME - if (!mem_section) + if (!mem_section || !mem_section[root]) return NULL; #endif - if (!mem_section[SECTION_NR_TO_ROOT(nr)]) - return NULL; - return &mem_section[SECTION_NR_TO_ROOT(nr)][nr & SECTION_ROOT_MASK]; + return &mem_section[root][nr & SECTION_ROOT_MASK]; } extern size_t mem_section_usage_size(void); @@ -1401,16 +1710,32 @@ extern size_t mem_section_usage_size(void); * (equal SECTION_SIZE_BITS - PAGE_SHIFT), and the * worst combination is powerpc with 256k pages, * which results in PFN_SECTION_SHIFT equal 6. - * To sum it up, at least 6 bits are available. + * To sum it up, at least 6 bits are available on all architectures. + * However, we can exceed 6 bits on some other architectures except + * powerpc (e.g. 15 bits are available on x86_64, 13 bits are available + * with the worst case of 64K pages on arm64) if we make sure the + * exceeded bit is not applicable to powerpc. */ -#define SECTION_MARKED_PRESENT (1UL<<0) -#define SECTION_HAS_MEM_MAP (1UL<<1) -#define SECTION_IS_ONLINE (1UL<<2) -#define SECTION_IS_EARLY (1UL<<3) -#define SECTION_TAINT_ZONE_DEVICE (1UL<<4) -#define SECTION_MAP_LAST_BIT (1UL<<5) -#define SECTION_MAP_MASK (~(SECTION_MAP_LAST_BIT-1)) -#define SECTION_NID_SHIFT 6 +enum { + SECTION_MARKED_PRESENT_BIT, + SECTION_HAS_MEM_MAP_BIT, + SECTION_IS_ONLINE_BIT, + SECTION_IS_EARLY_BIT, +#ifdef CONFIG_ZONE_DEVICE + SECTION_TAINT_ZONE_DEVICE_BIT, +#endif + SECTION_MAP_LAST_BIT, +}; + +#define SECTION_MARKED_PRESENT BIT(SECTION_MARKED_PRESENT_BIT) +#define SECTION_HAS_MEM_MAP BIT(SECTION_HAS_MEM_MAP_BIT) +#define SECTION_IS_ONLINE BIT(SECTION_IS_ONLINE_BIT) +#define SECTION_IS_EARLY BIT(SECTION_IS_EARLY_BIT) +#ifdef CONFIG_ZONE_DEVICE +#define SECTION_TAINT_ZONE_DEVICE BIT(SECTION_TAINT_ZONE_DEVICE_BIT) +#endif +#define SECTION_MAP_MASK (~(BIT(SECTION_MAP_LAST_BIT) - 1)) +#define SECTION_NID_SHIFT SECTION_MAP_LAST_BIT static inline struct page *__section_mem_map_addr(struct mem_section *section) { @@ -1449,12 +1774,19 @@ static inline int online_section(struct mem_section *section) return (section && (section->section_mem_map & SECTION_IS_ONLINE)); } +#ifdef CONFIG_ZONE_DEVICE static inline int online_device_section(struct mem_section *section) { unsigned long flags = SECTION_IS_ONLINE | SECTION_TAINT_ZONE_DEVICE; return section && ((section->section_mem_map & flags) == flags); } +#else +static inline int online_device_section(struct mem_section *section) +{ + return 0; +} +#endif static inline int online_section_nr(unsigned long nr) { diff --git a/include/linux/mnt_idmapping.h b/include/linux/mnt_idmapping.h index ee5a217de2a8..f6e5369d2928 100644 --- a/include/linux/mnt_idmapping.h +++ b/include/linux/mnt_idmapping.h @@ -13,6 +13,129 @@ struct user_namespace; */ extern struct user_namespace init_user_ns; +typedef struct { + uid_t val; +} vfsuid_t; + +typedef struct { + gid_t val; +} vfsgid_t; + +static_assert(sizeof(vfsuid_t) == sizeof(kuid_t)); +static_assert(sizeof(vfsgid_t) == sizeof(kgid_t)); +static_assert(offsetof(vfsuid_t, val) == offsetof(kuid_t, val)); +static_assert(offsetof(vfsgid_t, val) == offsetof(kgid_t, val)); + +#ifdef CONFIG_MULTIUSER +static inline uid_t __vfsuid_val(vfsuid_t uid) +{ + return uid.val; +} + +static inline gid_t __vfsgid_val(vfsgid_t gid) +{ + return gid.val; +} +#else +static inline uid_t __vfsuid_val(vfsuid_t uid) +{ + return 0; +} + +static inline gid_t __vfsgid_val(vfsgid_t gid) +{ + return 0; +} +#endif + +static inline bool vfsuid_valid(vfsuid_t uid) +{ + return __vfsuid_val(uid) != (uid_t)-1; +} + +static inline bool vfsgid_valid(vfsgid_t gid) +{ + return __vfsgid_val(gid) != (gid_t)-1; +} + +static inline bool vfsuid_eq(vfsuid_t left, vfsuid_t right) +{ + return vfsuid_valid(left) && __vfsuid_val(left) == __vfsuid_val(right); +} + +static inline bool vfsgid_eq(vfsgid_t left, vfsgid_t right) +{ + return vfsgid_valid(left) && __vfsgid_val(left) == __vfsgid_val(right); +} + +/** + * vfsuid_eq_kuid - check whether kuid and vfsuid have the same value + * @vfsuid: the vfsuid to compare + * @kuid: the kuid to compare + * + * Check whether @vfsuid and @kuid have the same values. + * + * Return: true if @vfsuid and @kuid have the same value, false if not. + * Comparison between two invalid uids returns false. + */ +static inline bool vfsuid_eq_kuid(vfsuid_t vfsuid, kuid_t kuid) +{ + return vfsuid_valid(vfsuid) && __vfsuid_val(vfsuid) == __kuid_val(kuid); +} + +/** + * vfsgid_eq_kgid - check whether kgid and vfsgid have the same value + * @vfsgid: the vfsgid to compare + * @kgid: the kgid to compare + * + * Check whether @vfsgid and @kgid have the same values. + * + * Return: true if @vfsgid and @kgid have the same value, false if not. + * Comparison between two invalid gids returns false. + */ +static inline bool vfsgid_eq_kgid(vfsgid_t vfsgid, kgid_t kgid) +{ + return vfsgid_valid(vfsgid) && __vfsgid_val(vfsgid) == __kgid_val(kgid); +} + +/* + * vfs{g,u}ids are created from k{g,u}ids. + * We don't allow them to be created from regular {u,g}id. + */ +#define VFSUIDT_INIT(val) (vfsuid_t){ __kuid_val(val) } +#define VFSGIDT_INIT(val) (vfsgid_t){ __kgid_val(val) } + +#define INVALID_VFSUID VFSUIDT_INIT(INVALID_UID) +#define INVALID_VFSGID VFSGIDT_INIT(INVALID_GID) + +/* + * Allow a vfs{g,u}id to be used as a k{g,u}id where we want to compare + * whether the mapped value is identical to value of a k{g,u}id. + */ +#define AS_KUIDT(val) (kuid_t){ __vfsuid_val(val) } +#define AS_KGIDT(val) (kgid_t){ __vfsgid_val(val) } + +#ifdef CONFIG_MULTIUSER +/** + * vfsgid_in_group_p() - check whether a vfsuid matches the caller's groups + * @vfsgid: the mnt gid to match + * + * This function can be used to determine whether @vfsuid matches any of the + * caller's groups. + * + * Return: 1 if vfsuid matches caller's groups, 0 if not. + */ +static inline int vfsgid_in_group_p(vfsgid_t vfsgid) +{ + return in_group_p(AS_KGIDT(vfsgid)); +} +#else +static inline int vfsgid_in_group_p(vfsgid_t vfsgid) +{ + return 1; +} +#endif + /** * initial_idmapping - check whether this is the initial mapping * @ns: idmapping to check @@ -48,7 +171,7 @@ static inline bool no_idmapping(const struct user_namespace *mnt_userns, } /** - * mapped_kuid_fs - map a filesystem kuid into a mnt_userns + * make_vfsuid - map a filesystem kuid into a mnt_userns * @mnt_userns: the mount's idmapping * @fs_userns: the filesystem's idmapping * @kuid : kuid to be mapped @@ -67,25 +190,33 @@ static inline bool no_idmapping(const struct user_namespace *mnt_userns, * If @kuid has no mapping in either @mnt_userns or @fs_userns INVALID_UID is * returned. */ -static inline kuid_t mapped_kuid_fs(struct user_namespace *mnt_userns, - struct user_namespace *fs_userns, - kuid_t kuid) + +static inline vfsuid_t make_vfsuid(struct user_namespace *mnt_userns, + struct user_namespace *fs_userns, + kuid_t kuid) { uid_t uid; if (no_idmapping(mnt_userns, fs_userns)) - return kuid; + return VFSUIDT_INIT(kuid); if (initial_idmapping(fs_userns)) uid = __kuid_val(kuid); else uid = from_kuid(fs_userns, kuid); if (uid == (uid_t)-1) - return INVALID_UID; - return make_kuid(mnt_userns, uid); + return INVALID_VFSUID; + return VFSUIDT_INIT(make_kuid(mnt_userns, uid)); +} + +static inline kuid_t mapped_kuid_fs(struct user_namespace *mnt_userns, + struct user_namespace *fs_userns, + kuid_t kuid) +{ + return AS_KUIDT(make_vfsuid(mnt_userns, fs_userns, kuid)); } /** - * mapped_kgid_fs - map a filesystem kgid into a mnt_userns + * make_vfsgid - map a filesystem kgid into a mnt_userns * @mnt_userns: the mount's idmapping * @fs_userns: the filesystem's idmapping * @kgid : kgid to be mapped @@ -104,21 +235,56 @@ static inline kuid_t mapped_kuid_fs(struct user_namespace *mnt_userns, * If @kgid has no mapping in either @mnt_userns or @fs_userns INVALID_GID is * returned. */ -static inline kgid_t mapped_kgid_fs(struct user_namespace *mnt_userns, - struct user_namespace *fs_userns, - kgid_t kgid) + +static inline vfsgid_t make_vfsgid(struct user_namespace *mnt_userns, + struct user_namespace *fs_userns, + kgid_t kgid) { gid_t gid; if (no_idmapping(mnt_userns, fs_userns)) - return kgid; + return VFSGIDT_INIT(kgid); if (initial_idmapping(fs_userns)) gid = __kgid_val(kgid); else gid = from_kgid(fs_userns, kgid); if (gid == (gid_t)-1) - return INVALID_GID; - return make_kgid(mnt_userns, gid); + return INVALID_VFSGID; + return VFSGIDT_INIT(make_kgid(mnt_userns, gid)); +} + +static inline kgid_t mapped_kgid_fs(struct user_namespace *mnt_userns, + struct user_namespace *fs_userns, + kgid_t kgid) +{ + return AS_KGIDT(make_vfsgid(mnt_userns, fs_userns, kgid)); +} + +/** + * from_vfsuid - map a vfsuid into the filesystem idmapping + * @mnt_userns: the mount's idmapping + * @fs_userns: the filesystem's idmapping + * @vfsuid : vfsuid to be mapped + * + * Map @vfsuid into the filesystem idmapping. This function has to be used in + * order to e.g. write @vfsuid to inode->i_uid. + * + * Return: @vfsuid mapped into the filesystem idmapping + */ +static inline kuid_t from_vfsuid(struct user_namespace *mnt_userns, + struct user_namespace *fs_userns, + vfsuid_t vfsuid) +{ + uid_t uid; + + if (no_idmapping(mnt_userns, fs_userns)) + return AS_KUIDT(vfsuid); + uid = from_kuid(mnt_userns, AS_KUIDT(vfsuid)); + if (uid == (uid_t)-1) + return INVALID_UID; + if (initial_idmapping(fs_userns)) + return KUIDT_INIT(uid); + return make_kuid(fs_userns, uid); } /** @@ -145,16 +311,66 @@ static inline kuid_t mapped_kuid_user(struct user_namespace *mnt_userns, struct user_namespace *fs_userns, kuid_t kuid) { - uid_t uid; + return from_vfsuid(mnt_userns, fs_userns, VFSUIDT_INIT(kuid)); +} + +/** + * vfsuid_has_fsmapping - check whether a vfsuid maps into the filesystem + * @mnt_userns: the mount's idmapping + * @fs_userns: the filesystem's idmapping + * @vfsuid: vfsuid to be mapped + * + * Check whether @vfsuid has a mapping in the filesystem idmapping. Use this + * function to check whether the filesystem idmapping has a mapping for + * @vfsuid. + * + * Return: true if @vfsuid has a mapping in the filesystem, false if not. + */ +static inline bool vfsuid_has_fsmapping(struct user_namespace *mnt_userns, + struct user_namespace *fs_userns, + vfsuid_t vfsuid) +{ + return uid_valid(from_vfsuid(mnt_userns, fs_userns, vfsuid)); +} + +/** + * vfsuid_into_kuid - convert vfsuid into kuid + * @vfsuid: the vfsuid to convert + * + * This can be used when a vfsuid is committed as a kuid. + * + * Return: a kuid with the value of @vfsuid + */ +static inline kuid_t vfsuid_into_kuid(vfsuid_t vfsuid) +{ + return AS_KUIDT(vfsuid); +} + +/** + * from_vfsgid - map a vfsgid into the filesystem idmapping + * @mnt_userns: the mount's idmapping + * @fs_userns: the filesystem's idmapping + * @vfsgid : vfsgid to be mapped + * + * Map @vfsgid into the filesystem idmapping. This function has to be used in + * order to e.g. write @vfsgid to inode->i_gid. + * + * Return: @vfsgid mapped into the filesystem idmapping + */ +static inline kgid_t from_vfsgid(struct user_namespace *mnt_userns, + struct user_namespace *fs_userns, + vfsgid_t vfsgid) +{ + gid_t gid; if (no_idmapping(mnt_userns, fs_userns)) - return kuid; - uid = from_kuid(mnt_userns, kuid); - if (uid == (uid_t)-1) - return INVALID_UID; + return AS_KGIDT(vfsgid); + gid = from_kgid(mnt_userns, AS_KGIDT(vfsgid)); + if (gid == (gid_t)-1) + return INVALID_GID; if (initial_idmapping(fs_userns)) - return KUIDT_INIT(uid); - return make_kuid(fs_userns, uid); + return KGIDT_INIT(gid); + return make_kgid(fs_userns, gid); } /** @@ -181,16 +397,39 @@ static inline kgid_t mapped_kgid_user(struct user_namespace *mnt_userns, struct user_namespace *fs_userns, kgid_t kgid) { - gid_t gid; + return from_vfsgid(mnt_userns, fs_userns, VFSGIDT_INIT(kgid)); +} - if (no_idmapping(mnt_userns, fs_userns)) - return kgid; - gid = from_kgid(mnt_userns, kgid); - if (gid == (gid_t)-1) - return INVALID_GID; - if (initial_idmapping(fs_userns)) - return KGIDT_INIT(gid); - return make_kgid(fs_userns, gid); +/** + * vfsgid_has_fsmapping - check whether a vfsgid maps into the filesystem + * @mnt_userns: the mount's idmapping + * @fs_userns: the filesystem's idmapping + * @vfsgid: vfsgid to be mapped + * + * Check whether @vfsgid has a mapping in the filesystem idmapping. Use this + * function to check whether the filesystem idmapping has a mapping for + * @vfsgid. + * + * Return: true if @vfsgid has a mapping in the filesystem, false if not. + */ +static inline bool vfsgid_has_fsmapping(struct user_namespace *mnt_userns, + struct user_namespace *fs_userns, + vfsgid_t vfsgid) +{ + return gid_valid(from_vfsgid(mnt_userns, fs_userns, vfsgid)); +} + +/** + * vfsgid_into_kgid - convert vfsgid into kgid + * @vfsgid: the vfsgid to convert + * + * This can be used when a vfsgid is committed as a kgid. + * + * Return: a kgid with the value of @vfsgid + */ +static inline kgid_t vfsgid_into_kgid(vfsgid_t vfsgid) +{ + return AS_KGIDT(vfsgid); } /** @@ -209,7 +448,8 @@ static inline kgid_t mapped_kgid_user(struct user_namespace *mnt_userns, static inline kuid_t mapped_fsuid(struct user_namespace *mnt_userns, struct user_namespace *fs_userns) { - return mapped_kuid_user(mnt_userns, fs_userns, current_fsuid()); + return from_vfsuid(mnt_userns, fs_userns, + VFSUIDT_INIT(current_fsuid())); } /** @@ -228,7 +468,8 @@ static inline kuid_t mapped_fsuid(struct user_namespace *mnt_userns, static inline kgid_t mapped_fsgid(struct user_namespace *mnt_userns, struct user_namespace *fs_userns) { - return mapped_kgid_user(mnt_userns, fs_userns, current_fsgid()); + return from_vfsgid(mnt_userns, fs_userns, + VFSGIDT_INIT(current_fsgid())); } #endif /* _LINUX_MNT_IDMAPPING_H */ diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index 4bb71979a8fd..549590e9c644 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -211,7 +211,7 @@ struct css_device_id { kernel_ulong_t driver_data; }; -#define ACPI_ID_LEN 9 +#define ACPI_ID_LEN 16 struct acpi_device_id { __u8 id[ACPI_ID_LEN]; @@ -835,6 +835,8 @@ struct wmi_device_id { #define MHI_DEVICE_MODALIAS_FMT "mhi:%s" #define MHI_NAME_SIZE 32 +#define MHI_EP_DEVICE_MODALIAS_FMT "mhi_ep:%s" + /** * struct mhi_device_id - MHI device identification * @chan: MHI channel name diff --git a/include/linux/module.h b/include/linux/module.h index c9f1200b2312..ec61fb53979a 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -27,7 +27,6 @@ #include <linux/tracepoint-defs.h> #include <linux/srcu.h> #include <linux/static_call_types.h> -#include <linux/cfi.h> #include <linux/percpu.h> #include <asm/module.h> @@ -132,7 +131,7 @@ extern void cleanup_module(void); { return initfn; } \ int init_module(void) __copy(initfn) \ __attribute__((alias(#initfn))); \ - __CFI_ADDRESSABLE(init_module, __initdata); + ___ADDRESSABLE(init_module, __initdata); /* This is only required if you want to be unloadable. */ #define module_exit(exitfn) \ @@ -140,7 +139,7 @@ extern void cleanup_module(void); { return exitfn; } \ void cleanup_module(void) __copy(exitfn) \ __attribute__((alias(#exitfn))); \ - __CFI_ADDRESSABLE(cleanup_module, __exitdata); + ___ADDRESSABLE(cleanup_module, __exitdata); #endif @@ -290,7 +289,7 @@ extern typeof(name) __mod_##type##__##name##_device_table \ * files require multiple MODULE_FIRMWARE() specifiers */ #define MODULE_FIRMWARE(_firmware) MODULE_INFO(firmware, _firmware) -#define MODULE_IMPORT_NS(ns) MODULE_INFO(import_ns, #ns) +#define MODULE_IMPORT_NS(ns) MODULE_INFO(import_ns, __stringify(ns)) struct notifier_block; @@ -387,8 +386,9 @@ struct module { const s32 *crcs; unsigned int num_syms; -#ifdef CONFIG_CFI_CLANG - cfi_check_fn cfi_check; +#ifdef CONFIG_ARCH_USES_CFI_TRAPS + s32 *kcfi_traps; + s32 *kcfi_traps_end; #endif /* Kernel parameters. */ @@ -421,6 +421,9 @@ struct module { /* Core layout: rbtree is accessed frequently, so keep together. */ struct module_layout core_layout __module_layout_align; struct module_layout init_layout; +#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC + struct module_layout data_layout; +#endif /* Arch-specific module values */ struct mod_arch_specific arch; @@ -502,6 +505,11 @@ struct module { int num_static_call_sites; struct static_call_site *static_call_sites; #endif +#if IS_ENABLED(CONFIG_KUNIT) + int num_kunit_suites; + struct kunit_suite **kunit_suites; +#endif + #ifdef CONFIG_LIVEPATCH bool klp; /* Is this a livepatch module? */ @@ -568,6 +576,11 @@ bool is_module_text_address(unsigned long addr); static inline bool within_module_core(unsigned long addr, const struct module *mod) { +#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC + if ((unsigned long)mod->data_layout.base <= addr && + addr < (unsigned long)mod->data_layout.base + mod->data_layout.size) + return true; +#endif return (unsigned long)mod->core_layout.base <= addr && addr < (unsigned long)mod->core_layout.base + mod->core_layout.size; } @@ -595,9 +608,9 @@ int module_get_kallsym(unsigned int symnum, unsigned long *value, char *type, /* Look for this name: can be of form module:name. */ unsigned long module_kallsyms_lookup_name(const char *name); -extern void __noreturn __module_put_and_exit(struct module *mod, +extern void __noreturn __module_put_and_kthread_exit(struct module *mod, long code); -#define module_put_and_exit(code) __module_put_and_exit(THIS_MODULE, code) +#define module_put_and_kthread_exit(code) __module_put_and_kthread_exit(THIS_MODULE, code) #ifdef CONFIG_MODULE_UNLOAD int module_refcount(struct module *mod); @@ -662,19 +675,15 @@ static inline bool module_requested_async_probing(struct module *module) return module && module->async_probe_requested; } -#ifdef CONFIG_LIVEPATCH static inline bool is_livepatch_module(struct module *mod) { +#ifdef CONFIG_LIVEPATCH return mod->klp; -} -#else /* !CONFIG_LIVEPATCH */ -static inline bool is_livepatch_module(struct module *mod) -{ +#else return false; +#endif } -#endif /* CONFIG_LIVEPATCH */ -bool is_module_sig_enforced(void); void set_module_sig_enforced(void); #else /* !CONFIG_MODULES... */ @@ -790,7 +799,7 @@ static inline int unregister_module_notifier(struct notifier_block *nb) return 0; } -#define module_put_and_exit(code) do_exit(code) +#define module_put_and_kthread_exit(code) kthread_exit(code) static inline void print_modules(void) { @@ -801,10 +810,6 @@ static inline bool module_requested_async_probing(struct module *module) return false; } -static inline bool is_module_sig_enforced(void) -{ - return false; -} static inline void set_module_sig_enforced(void) { @@ -856,11 +861,18 @@ static inline bool retpoline_module_ok(bool has_retpoline) #endif #ifdef CONFIG_MODULE_SIG +bool is_module_sig_enforced(void); + static inline bool module_sig_ok(struct module *module) { return module->sig_ok; } #else /* !CONFIG_MODULE_SIG */ +static inline bool is_module_sig_enforced(void) +{ + return false; +} + static inline bool module_sig_ok(struct module *module) { return true; diff --git a/include/linux/mount.h b/include/linux/mount.h index 5d92a7e1a742..55a4abaf6715 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -11,17 +11,15 @@ #define _LINUX_MOUNT_H #include <linux/types.h> -#include <linux/list.h> -#include <linux/nodemask.h> -#include <linux/spinlock.h> -#include <linux/seqlock.h> -#include <linux/atomic.h> +#include <asm/barrier.h> struct super_block; -struct vfsmount; struct dentry; -struct mnt_namespace; +struct user_namespace; +struct file_system_type; struct fs_context; +struct file; +struct path; #define MNT_NOSUID 0x01 #define MNT_NODEV 0x02 @@ -81,9 +79,6 @@ static inline struct user_namespace *mnt_user_ns(const struct vfsmount *mnt) return smp_load_acquire(&mnt->mnt_userns); } -struct file; /* forward dec */ -struct path; - extern int mnt_want_write(struct vfsmount *mnt); extern int mnt_want_write_file(struct file *file); extern void mnt_drop_write(struct vfsmount *mnt); @@ -94,12 +89,10 @@ extern struct vfsmount *mnt_clone_internal(const struct path *path); extern bool __mnt_is_readonly(struct vfsmount *mnt); extern bool mnt_may_suid(struct vfsmount *mnt); -struct path; extern struct vfsmount *clone_private_mount(const struct path *path); extern int __mnt_want_write(struct vfsmount *); extern void __mnt_drop_write(struct vfsmount *); -struct file_system_type; extern struct vfsmount *fc_mount(struct fs_context *fc); extern struct vfsmount *vfs_create_mount(struct fs_context *fc); extern struct vfsmount *vfs_kern_mount(struct file_system_type *type, @@ -113,11 +106,20 @@ extern void mnt_set_expiry(struct vfsmount *mnt, struct list_head *expiry_list); extern void mark_mounts_for_expiry(struct list_head *mounts); extern dev_t name_to_dev_t(const char *name); - -extern unsigned int sysctl_mount_max; - extern bool path_is_mountpoint(const struct path *path); +extern bool our_mnt(struct vfsmount *mnt); + +extern struct vfsmount *kern_mount(struct file_system_type *); +extern void kern_unmount(struct vfsmount *mnt); +extern int may_umount_tree(struct vfsmount *); +extern int may_umount(struct vfsmount *); +extern long do_mount(const char *, const char __user *, + const char *, unsigned long, void *); +extern struct vfsmount *collect_mounts(const struct path *); +extern void drop_collected_mounts(struct vfsmount *); +extern int iterate_mounts(int (*)(struct vfsmount *, void *), void *, + struct vfsmount *); extern void kern_unmount_array(struct vfsmount *mnt[], unsigned int num); #endif /* _LINUX_MOUNT_H */ diff --git a/include/linux/mpage.h b/include/linux/mpage.h index f4f5e90a6844..1bdc39daac0a 100644 --- a/include/linux/mpage.h +++ b/include/linux/mpage.h @@ -16,10 +16,8 @@ struct writeback_control; struct readahead_control; void mpage_readahead(struct readahead_control *, get_block_t get_block); -int mpage_readpage(struct page *page, get_block_t get_block); +int mpage_read_folio(struct folio *folio, get_block_t get_block); int mpage_writepages(struct address_space *mapping, struct writeback_control *wbc, get_block_t get_block); -int mpage_writepage(struct page *page, get_block_t *get_block, - struct writeback_control *wbc); #endif diff --git a/include/linux/mroute.h b/include/linux/mroute.h index 6cbbfe94348c..80b8400ab8b2 100644 --- a/include/linux/mroute.h +++ b/include/linux/mroute.h @@ -17,7 +17,7 @@ static inline int ip_mroute_opt(int opt) } int ip_mroute_setsockopt(struct sock *, int, sockptr_t, unsigned int); -int ip_mroute_getsockopt(struct sock *, int, char __user *, int __user *); +int ip_mroute_getsockopt(struct sock *, int, sockptr_t, sockptr_t); int ipmr_ioctl(struct sock *sk, int cmd, void __user *arg); int ipmr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg); int ip_mr_init(void); @@ -29,8 +29,8 @@ static inline int ip_mroute_setsockopt(struct sock *sock, int optname, return -ENOPROTOOPT; } -static inline int ip_mroute_getsockopt(struct sock *sock, int optname, - char __user *optval, int __user *optlen) +static inline int ip_mroute_getsockopt(struct sock *sk, int optname, + sockptr_t optval, sockptr_t optlen) { return -ENOPROTOOPT; } diff --git a/include/linux/mroute6.h b/include/linux/mroute6.h index bc351a85ce9b..8f2b307fb124 100644 --- a/include/linux/mroute6.h +++ b/include/linux/mroute6.h @@ -27,7 +27,7 @@ struct sock; #ifdef CONFIG_IPV6_MROUTE extern int ip6_mroute_setsockopt(struct sock *, int, sockptr_t, unsigned int); -extern int ip6_mroute_getsockopt(struct sock *, int, char __user *, int __user *); +extern int ip6_mroute_getsockopt(struct sock *, int, sockptr_t, sockptr_t); extern int ip6_mr_input(struct sk_buff *skb); extern int ip6mr_ioctl(struct sock *sk, int cmd, void __user *arg); extern int ip6mr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg); @@ -42,7 +42,7 @@ static inline int ip6_mroute_setsockopt(struct sock *sock, int optname, static inline int ip6_mroute_getsockopt(struct sock *sock, - int optname, char __user *optval, int __user *optlen) + int optname, sockptr_t optval, sockptr_t optlen) { return -ENOPROTOOPT; } diff --git a/include/linux/mroute_base.h b/include/linux/mroute_base.h index e05ee9f001ff..9dd4bf157255 100644 --- a/include/linux/mroute_base.h +++ b/include/linux/mroute_base.h @@ -26,7 +26,7 @@ * @remote: Remote address for tunnels */ struct vif_device { - struct net_device *dev; + struct net_device __rcu *dev; netdevice_tracker dev_tracker; unsigned long bytes_in, bytes_out; unsigned long pkt_in, pkt_out; @@ -52,6 +52,7 @@ static inline int mr_call_vif_notifier(struct notifier_block *nb, unsigned short family, enum fib_event_type event_type, struct vif_device *vif, + struct net_device *vif_dev, unsigned short vif_index, u32 tb_id, struct netlink_ext_ack *extack) { @@ -60,7 +61,7 @@ static inline int mr_call_vif_notifier(struct notifier_block *nb, .family = family, .extack = extack, }, - .dev = vif->dev, + .dev = vif_dev, .vif_index = vif_index, .vif_flags = vif->flags, .tb_id = tb_id, @@ -73,6 +74,7 @@ static inline int mr_call_vif_notifiers(struct net *net, unsigned short family, enum fib_event_type event_type, struct vif_device *vif, + struct net_device *vif_dev, unsigned short vif_index, u32 tb_id, unsigned int *ipmr_seq) { @@ -80,7 +82,7 @@ static inline int mr_call_vif_notifiers(struct net *net, .info = { .family = family, }, - .dev = vif->dev, + .dev = vif_dev, .vif_index = vif_index, .vif_flags = vif->flags, .tb_id = tb_id, @@ -98,7 +100,8 @@ static inline int mr_call_vif_notifiers(struct net *net, #define MAXVIFS 32 #endif -#define VIF_EXISTS(_mrt, _idx) (!!((_mrt)->vif_table[_idx].dev)) +/* Note: This helper is deprecated. */ +#define VIF_EXISTS(_mrt, _idx) (!!rcu_access_pointer((_mrt)->vif_table[_idx].dev)) /* mfc_flags: * MFC_STATIC - the entry was added statically (not by a routing daemon) @@ -305,7 +308,7 @@ int mr_dump(struct net *net, struct notifier_block *nb, unsigned short family, struct netlink_ext_ack *extack), struct mr_table *(*mr_iter)(struct net *net, struct mr_table *mrt), - rwlock_t *mrt_lock, struct netlink_ext_ack *extack); + struct netlink_ext_ack *extack); #else static inline void vif_device_init(struct vif_device *v, struct net_device *dev, @@ -360,7 +363,7 @@ static inline int mr_dump(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack), struct mr_table *(*mr_iter)(struct net *net, struct mr_table *mrt), - rwlock_t *mrt_lock, struct netlink_ext_ack *extack) + struct netlink_ext_ack *extack) { return -EINVAL; } diff --git a/include/linux/msi.h b/include/linux/msi.h index e616f94c7c58..fc918a658d48 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -2,7 +2,23 @@ #ifndef LINUX_MSI_H #define LINUX_MSI_H -#include <linux/kobject.h> +/* + * This header file contains MSI data structures and functions which are + * only relevant for: + * - Interrupt core code + * - PCI/MSI core code + * - MSI interrupt domain implementations + * - IOMMU, low level VFIO, NTB and other justified exceptions + * dealing with low level MSI details. + * + * Regular device drivers have no business with any of these functions and + * especially storing MSI descriptor pointers in random code is considered + * abuse. The only function which is relevant for drivers is msi_get_virq(). + */ + +#include <linux/cpumask.h> +#include <linux/xarray.h> +#include <linux/mutex.h> #include <linux/list.h> #include <asm/msi.h> @@ -56,6 +72,8 @@ struct irq_data; struct msi_desc; struct pci_dev; struct platform_msi_priv_data; +struct device_attribute; + void __get_cached_msi_msg(struct msi_desc *entry, struct msi_msg *msg); #ifdef CONFIG_GENERIC_MSI_IRQ void get_cached_msi_msg(unsigned int irq, struct msi_msg *msg); @@ -69,62 +87,59 @@ typedef void (*irq_write_msi_msg_t)(struct msi_desc *desc, struct msi_msg *msg); /** - * platform_msi_desc - Platform device specific msi descriptor data - * @msi_priv_data: Pointer to platform private data - * @msi_index: The index of the MSI descriptor for multi MSI - */ -struct platform_msi_desc { - struct platform_msi_priv_data *msi_priv_data; - u16 msi_index; -}; - -/** - * fsl_mc_msi_desc - FSL-MC device specific msi descriptor data - * @msi_index: The index of the MSI descriptor + * pci_msi_desc - PCI/MSI specific MSI descriptor data + * + * @msi_mask: [PCI MSI] MSI cached mask bits + * @msix_ctrl: [PCI MSI-X] MSI-X cached per vector control bits + * @is_msix: [PCI MSI/X] True if MSI-X + * @multiple: [PCI MSI/X] log2 num of messages allocated + * @multi_cap: [PCI MSI/X] log2 num of messages supported + * @can_mask: [PCI MSI/X] Masking supported? + * @is_64: [PCI MSI/X] Address size: 0=32bit 1=64bit + * @default_irq:[PCI MSI/X] The default pre-assigned non-MSI irq + * @mask_pos: [PCI MSI] Mask register position + * @mask_base: [PCI MSI-X] Mask register base address */ -struct fsl_mc_msi_desc { - u16 msi_index; +struct pci_msi_desc { + union { + u32 msi_mask; + u32 msix_ctrl; + }; + struct { + u8 is_msix : 1; + u8 multiple : 3; + u8 multi_cap : 3; + u8 can_mask : 1; + u8 is_64 : 1; + u8 is_virtual : 1; + unsigned default_irq; + } msi_attrib; + union { + u8 mask_pos; + void __iomem *mask_base; + }; }; -/** - * ti_sci_inta_msi_desc - TISCI based INTA specific msi descriptor data - * @dev_index: TISCI device index - */ -struct ti_sci_inta_msi_desc { - u16 dev_index; -}; +#define MSI_MAX_INDEX ((unsigned int)USHRT_MAX) /** * struct msi_desc - Descriptor structure for MSI based interrupts - * @list: List head for management * @irq: The base interrupt number * @nvec_used: The number of vectors used * @dev: Pointer to the device which uses this descriptor * @msg: The last set MSI message cached for reuse * @affinity: Optional pointer to a cpu affinity mask for this descriptor + * @sysfs_attr: Pointer to sysfs device attribute * * @write_msi_msg: Callback that may be called when the MSI message * address or data changes * @write_msi_msg_data: Data parameter for the callback. * - * @msi_mask: [PCI MSI] MSI cached mask bits - * @msix_ctrl: [PCI MSI-X] MSI-X cached per vector control bits - * @is_msix: [PCI MSI/X] True if MSI-X - * @multiple: [PCI MSI/X] log2 num of messages allocated - * @multi_cap: [PCI MSI/X] log2 num of messages supported - * @maskbit: [PCI MSI/X] Mask-Pending bit supported? - * @is_64: [PCI MSI/X] Address size: 0=32bit 1=64bit - * @entry_nr: [PCI MSI/X] Entry which is described by this descriptor - * @default_irq:[PCI MSI/X] The default pre-assigned non-MSI irq - * @mask_pos: [PCI MSI] Mask register position - * @mask_base: [PCI MSI-X] Mask register base address - * @platform: [platform] Platform device specific msi descriptor data - * @fsl_mc: [fsl-mc] FSL MC device specific msi descriptor data - * @inta: [INTA] TISCI based INTA specific msi descriptor data + * @msi_index: Index of the msi descriptor + * @pci: PCI specific msi descriptor data */ struct msi_desc { /* Shared device/bus type independent data */ - struct list_head list; unsigned int irq; unsigned int nvec_used; struct device *dev; @@ -133,61 +148,71 @@ struct msi_desc { #ifdef CONFIG_IRQ_MSI_IOMMU const void *iommu_cookie; #endif +#ifdef CONFIG_SYSFS + struct device_attribute *sysfs_attrs; +#endif void (*write_msi_msg)(struct msi_desc *entry, void *data); void *write_msi_msg_data; - union { - /* PCI MSI/X specific data */ - struct { - union { - u32 msi_mask; - u32 msix_ctrl; - }; - struct { - u8 is_msix : 1; - u8 multiple : 3; - u8 multi_cap : 3; - u8 can_mask : 1; - u8 is_64 : 1; - u8 is_virtual : 1; - u16 entry_nr; - unsigned default_irq; - } msi_attrib; - union { - u8 mask_pos; - void __iomem *mask_base; - }; - }; - - /* - * Non PCI variants add their data structure here. New - * entries need to use a named structure. We want - * proper name spaces for this. The PCI part is - * anonymous for now as it would require an immediate - * tree wide cleanup. - */ - struct platform_msi_desc platform; - struct fsl_mc_msi_desc fsl_mc; - struct ti_sci_inta_msi_desc inta; - }; + u16 msi_index; + struct pci_msi_desc pci; +}; + +/* + * Filter values for the MSI descriptor iterators and accessor functions. + */ +enum msi_desc_filter { + /* All descriptors */ + MSI_DESC_ALL, + /* Descriptors which have no interrupt associated */ + MSI_DESC_NOTASSOCIATED, + /* Descriptors which have an interrupt associated */ + MSI_DESC_ASSOCIATED, }; -/* Helpers to hide struct msi_desc implementation details */ +/** + * msi_device_data - MSI per device data + * @properties: MSI properties which are interesting to drivers + * @platform_data: Platform-MSI specific data + * @mutex: Mutex protecting the MSI descriptor store + * @__store: Xarray for storing MSI descriptor pointers + * @__iter_idx: Index to search the next entry for iterators + */ +struct msi_device_data { + unsigned long properties; + struct platform_msi_priv_data *platform_data; + struct mutex mutex; + struct xarray __store; + unsigned long __iter_idx; +}; + +int msi_setup_device_data(struct device *dev); + +unsigned int msi_get_virq(struct device *dev, unsigned int index); +void msi_lock_descs(struct device *dev); +void msi_unlock_descs(struct device *dev); + +struct msi_desc *msi_first_desc(struct device *dev, enum msi_desc_filter filter); +struct msi_desc *msi_next_desc(struct device *dev, enum msi_desc_filter filter); + +/** + * msi_for_each_desc - Iterate the MSI descriptors + * + * @desc: struct msi_desc pointer used as iterator + * @dev: struct device pointer - device to iterate + * @filter: Filter for descriptor selection + * + * Notes: + * - The loop must be protected with a msi_lock_descs()/msi_unlock_descs() + * pair. + * - It is safe to remove a retrieved MSI descriptor in the loop. + */ +#define msi_for_each_desc(desc, dev, filter) \ + for ((desc) = msi_first_desc((dev), (filter)); (desc); \ + (desc) = msi_next_desc((dev), (filter))) + #define msi_desc_to_dev(desc) ((desc)->dev) -#define dev_to_msi_list(dev) (&(dev)->msi_list) -#define first_msi_entry(dev) \ - list_first_entry(dev_to_msi_list((dev)), struct msi_desc, list) -#define for_each_msi_entry(desc, dev) \ - list_for_each_entry((desc), dev_to_msi_list((dev)), list) -#define for_each_msi_entry_safe(desc, tmp, dev) \ - list_for_each_entry_safe((desc), (tmp), dev_to_msi_list((dev)), list) -#define for_each_msi_vector(desc, __irq, dev) \ - for_each_msi_entry((desc), (dev)) \ - if ((desc)->irq) \ - for (__irq = (desc)->irq; \ - __irq < ((desc)->irq + (desc)->nvec_used); \ - __irq++) #ifdef CONFIG_IRQ_MSI_IOMMU static inline const void *msi_desc_get_iommu_cookie(struct msi_desc *desc) @@ -213,36 +238,33 @@ static inline void msi_desc_set_iommu_cookie(struct msi_desc *desc, #endif #ifdef CONFIG_PCI_MSI -#define first_pci_msi_entry(pdev) first_msi_entry(&(pdev)->dev) -#define for_each_pci_msi_entry(desc, pdev) \ - for_each_msi_entry((desc), &(pdev)->dev) - struct pci_dev *msi_desc_to_pci_dev(struct msi_desc *desc); -void *msi_desc_to_pci_sysdata(struct msi_desc *desc); void pci_write_msi_msg(unsigned int irq, struct msi_msg *msg); #else /* CONFIG_PCI_MSI */ -static inline void *msi_desc_to_pci_sysdata(struct msi_desc *desc) -{ - return NULL; -} static inline void pci_write_msi_msg(unsigned int irq, struct msi_msg *msg) { } #endif /* CONFIG_PCI_MSI */ -struct msi_desc *alloc_msi_entry(struct device *dev, int nvec, - const struct irq_affinity_desc *affinity); -void free_msi_entry(struct msi_desc *entry); +int msi_add_msi_desc(struct device *dev, struct msi_desc *init_desc); +void msi_free_msi_descs_range(struct device *dev, enum msi_desc_filter filter, + unsigned int first_index, unsigned int last_index); + +/** + * msi_free_msi_descs - Free MSI descriptors of a device + * @dev: Device to free the descriptors + */ +static inline void msi_free_msi_descs(struct device *dev) +{ + msi_free_msi_descs_range(dev, MSI_DESC_ALL, 0, MSI_MAX_INDEX); +} + void __pci_read_msi_msg(struct msi_desc *entry, struct msi_msg *msg); void __pci_write_msi_msg(struct msi_desc *entry, struct msi_msg *msg); void pci_msi_mask_irq(struct irq_data *data); void pci_msi_unmask_irq(struct irq_data *data); -const struct attribute_group **msi_populate_sysfs(struct device *dev); -void msi_destroy_sysfs(struct device *dev, - const struct attribute_group **msi_irq_groups); - /* * The arch hooks to setup up msi irqs. Default functions are implemented * as weak symbols so that they /can/ be overriden by architecture specific @@ -256,25 +278,20 @@ int arch_setup_msi_irq(struct pci_dev *dev, struct msi_desc *desc); void arch_teardown_msi_irq(unsigned int irq); int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type); void arch_teardown_msi_irqs(struct pci_dev *dev); -#else -static inline int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) -{ - WARN_ON_ONCE(1); - return -ENODEV; -} - -static inline void arch_teardown_msi_irqs(struct pci_dev *dev) -{ - WARN_ON_ONCE(1); -} -#endif +#ifdef CONFIG_SYSFS +int msi_device_populate_sysfs(struct device *dev); +void msi_device_destroy_sysfs(struct device *dev); +#else /* CONFIG_SYSFS */ +static inline int msi_device_populate_sysfs(struct device *dev) { return 0; } +static inline void msi_device_destroy_sysfs(struct device *dev) { } +#endif /* !CONFIG_SYSFS */ +#endif /* CONFIG_PCI_MSI_ARCH_FALLBACKS */ /* - * The restore hooks are still available as they are useful even - * for fully irq domain based setups. Courtesy to XEN/X86. + * The restore hook is still available even for fully irq domain based + * setups. Courtesy to XEN/X86. */ -void arch_restore_msi_irqs(struct pci_dev *dev); -void default_restore_msi_irqs(struct pci_dev *dev); +bool arch_restore_msi_irqs(struct pci_dev *dev); #ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN @@ -294,20 +311,17 @@ struct msi_domain_info; * @msi_free: Domain specific function to free a MSI interrupts * @msi_check: Callback for verification of the domain/info/dev data * @msi_prepare: Prepare the allocation of the interrupts in the domain - * @msi_finish: Optional callback to finalize the allocation * @set_desc: Set the msi descriptor for an interrupt - * @handle_error: Optional error handler if the allocation fails * @domain_alloc_irqs: Optional function to override the default allocation * function. * @domain_free_irqs: Optional function to override the default free * function. * - * @get_hwirq, @msi_init and @msi_free are callbacks used by - * msi_create_irq_domain() and related interfaces + * @get_hwirq, @msi_init and @msi_free are callbacks used by the underlying + * irqdomain. * - * @msi_check, @msi_prepare, @msi_finish, @set_desc and @handle_error - * are callbacks used by msi_domain_alloc_irqs() and related - * interfaces which are based on msi_desc. + * @msi_check, @msi_prepare and @set_desc are callbacks used by + * msi_domain_alloc/free_irqs(). * * @domain_alloc_irqs, @domain_free_irqs can be used to override the * default allocation/free functions (__msi_domain_alloc/free_irqs). This @@ -341,11 +355,8 @@ struct msi_domain_ops { int (*msi_prepare)(struct irq_domain *domain, struct device *dev, int nvec, msi_alloc_info_t *arg); - void (*msi_finish)(msi_alloc_info_t *arg, int retval); void (*set_desc)(msi_alloc_info_t *arg, struct msi_desc *desc); - int (*handle_error)(struct irq_domain *domain, - struct msi_desc *desc, int error); int (*domain_alloc_irqs)(struct irq_domain *domain, struct device *dev, int nvec); void (*domain_free_irqs)(struct irq_domain *domain, @@ -399,6 +410,14 @@ enum { MSI_FLAG_MUST_REACTIVATE = (1 << 5), /* Is level-triggered capable, using two messages */ MSI_FLAG_LEVEL_CAPABLE = (1 << 6), + /* Populate sysfs on alloc() and destroy it on free() */ + MSI_FLAG_DEV_SYSFS = (1 << 7), + /* MSI-X entries must be contiguous */ + MSI_FLAG_MSIX_CONTIGUOUS = (1 << 8), + /* Allocate simple MSI descriptors */ + MSI_FLAG_ALLOC_SIMPLE_MSI_DESCS = (1 << 9), + /* Free MSI descriptors */ + MSI_FLAG_FREE_MSI_DESCS = (1 << 10), }; int msi_domain_set_affinity(struct irq_data *data, const struct cpumask *mask, @@ -409,9 +428,12 @@ struct irq_domain *msi_create_irq_domain(struct fwnode_handle *fwnode, struct irq_domain *parent); int __msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev, int nvec); +int msi_domain_alloc_irqs_descs_locked(struct irq_domain *domain, struct device *dev, + int nvec); int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev, int nvec); void __msi_domain_free_irqs(struct irq_domain *domain, struct device *dev); +void msi_domain_free_irqs_descs_locked(struct irq_domain *domain, struct device *dev); void msi_domain_free_irqs(struct irq_domain *domain, struct device *dev); struct msi_domain_info *msi_get_domain_info(struct irq_domain *domain); @@ -440,20 +462,17 @@ __platform_msi_create_device_domain(struct device *dev, #define platform_msi_create_device_tree_domain(dev, nvec, write, ops, data) \ __platform_msi_create_device_domain(dev, nvec, true, write, ops, data) -int platform_msi_domain_alloc(struct irq_domain *domain, unsigned int virq, - unsigned int nr_irqs); -void platform_msi_domain_free(struct irq_domain *domain, unsigned int virq, - unsigned int nvec); +int platform_msi_device_domain_alloc(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs); +void platform_msi_device_domain_free(struct irq_domain *domain, unsigned int virq, + unsigned int nvec); void *platform_msi_get_host_data(struct irq_domain *domain); #endif /* CONFIG_GENERIC_MSI_IRQ_DOMAIN */ #ifdef CONFIG_PCI_MSI_IRQ_DOMAIN -void pci_msi_domain_write_msg(struct irq_data *irq_data, struct msi_msg *msg); struct irq_domain *pci_msi_create_irq_domain(struct fwnode_handle *fwnode, struct msi_domain_info *info, struct irq_domain *parent); -int pci_msi_domain_check_cap(struct irq_domain *domain, - struct msi_domain_info *info, struct device *dev); u32 pci_msi_domain_get_msi_rid(struct irq_domain *domain, struct pci_dev *pdev); struct irq_domain *pci_msi_get_device_domain(struct pci_dev *pdev); bool pci_dev_has_special_msi_domain(struct pci_dev *pdev); diff --git a/include/linux/mtd/cfi.h b/include/linux/mtd/cfi.h index fd1ecb821106..d88bb56c18e2 100644 --- a/include/linux/mtd/cfi.h +++ b/include/linux/mtd/cfi.h @@ -286,6 +286,7 @@ struct cfi_private { map_word sector_erase_cmd; unsigned long chipshift; /* Because they're of the same type */ const char *im_name; /* inter_module name for cmdset_setup */ + unsigned long quirks; struct flchip chips[]; /* per-chip data structure for each chip */ }; diff --git a/include/linux/mtd/hyperbus.h b/include/linux/mtd/hyperbus.h index 0ce612428aea..bb6b7121a542 100644 --- a/include/linux/mtd/hyperbus.h +++ b/include/linux/mtd/hyperbus.h @@ -89,9 +89,7 @@ int hyperbus_register_device(struct hyperbus_device *hbdev); /** * hyperbus_unregister_device - deregister HyperBus slave memory device * @hbdev: hyperbus_device to be unregistered - * - * Return: 0 for success, others for failure. */ -int hyperbus_unregister_device(struct hyperbus_device *hbdev); +void hyperbus_unregister_device(struct hyperbus_device *hbdev); #endif /* __LINUX_MTD_HYPERBUS_H__ */ diff --git a/include/linux/mtd/mtd.h b/include/linux/mtd/mtd.h index 1ffa933121f6..7c58c44662b8 100644 --- a/include/linux/mtd/mtd.h +++ b/include/linux/mtd/mtd.h @@ -40,6 +40,12 @@ struct mtd_erase_region_info { unsigned long *lockmap; /* If keeping bitmap of locks */ }; +struct mtd_req_stats { + unsigned int uncorrectable_errors; + unsigned int corrected_bitflips; + unsigned int max_bitflips; +}; + /** * struct mtd_oob_ops - oob operation operands * @mode: operation mode @@ -70,6 +76,7 @@ struct mtd_oob_ops { uint32_t ooboffs; uint8_t *datbuf; uint8_t *oobbuf; + struct mtd_req_stats *stats; }; /** @@ -188,9 +195,6 @@ struct module; /* only needed for owner field in mtd_info */ */ struct mtd_debug_info { struct dentry *dfs_dir; - - const char *partname; - const char *partid; }; /** @@ -392,10 +396,8 @@ struct mtd_info { /* List of partitions attached to this MTD device */ struct list_head partitions; - union { - struct mtd_part part; - struct mtd_master master; - }; + struct mtd_part part; + struct mtd_master master; }; static inline struct mtd_info *mtd_get_master(struct mtd_info *mtd) @@ -682,6 +684,7 @@ extern int mtd_device_unregister(struct mtd_info *master); extern struct mtd_info *get_mtd_device(struct mtd_info *mtd, int num); extern int __get_mtd_device(struct mtd_info *mtd); extern void __put_mtd_device(struct mtd_info *mtd); +extern struct mtd_info *of_get_mtd_device_by_node(struct device_node *np); extern struct mtd_info *get_mtd_device_nm(const char *name); extern void put_mtd_device(struct mtd_info *mtd); @@ -711,7 +714,11 @@ static inline int mtd_is_bitflip_or_eccerr(int err) { unsigned mtd_mmap_capabilities(struct mtd_info *mtd); -extern char *mtd_expert_analysis_warning; -extern bool mtd_expert_analysis_mode; +#ifdef CONFIG_DEBUG_FS +bool mtd_check_expert_analysis_mode(void); +#else +static inline bool mtd_check_expert_analysis_mode(void) { return false; } +#endif + #endif /* __MTD_MTD_H__ */ diff --git a/include/linux/mtd/nand-ecc-mtk.h b/include/linux/mtd/nand-ecc-mtk.h new file mode 100644 index 000000000000..0e48c36e6ca0 --- /dev/null +++ b/include/linux/mtd/nand-ecc-mtk.h @@ -0,0 +1,47 @@ +/* SPDX-License-Identifier: GPL-2.0 OR MIT */ +/* + * MTK SDG1 ECC controller + * + * Copyright (c) 2016 Mediatek + * Authors: Xiaolei Li <xiaolei.li@mediatek.com> + * Jorge Ramirez-Ortiz <jorge.ramirez-ortiz@linaro.org> + */ + +#ifndef __DRIVERS_MTD_NAND_MTK_ECC_H__ +#define __DRIVERS_MTD_NAND_MTK_ECC_H__ + +#include <linux/types.h> + +enum mtk_ecc_mode {ECC_DMA_MODE = 0, ECC_NFI_MODE = 1}; +enum mtk_ecc_operation {ECC_ENCODE, ECC_DECODE}; + +struct device_node; +struct mtk_ecc; + +struct mtk_ecc_stats { + u32 corrected; + u32 bitflips; + u32 failed; +}; + +struct mtk_ecc_config { + enum mtk_ecc_operation op; + enum mtk_ecc_mode mode; + dma_addr_t addr; + u32 strength; + u32 sectors; + u32 len; +}; + +int mtk_ecc_encode(struct mtk_ecc *, struct mtk_ecc_config *, u8 *, u32); +void mtk_ecc_get_stats(struct mtk_ecc *, struct mtk_ecc_stats *, int); +int mtk_ecc_wait_done(struct mtk_ecc *, enum mtk_ecc_operation); +int mtk_ecc_enable(struct mtk_ecc *, struct mtk_ecc_config *); +void mtk_ecc_disable(struct mtk_ecc *); +void mtk_ecc_adjust_strength(struct mtk_ecc *ecc, u32 *p); +unsigned int mtk_ecc_get_parity_bits(struct mtk_ecc *ecc); + +struct mtk_ecc *of_mtk_ecc_get(struct device_node *); +void mtk_ecc_release(struct mtk_ecc *); + +#endif diff --git a/include/linux/mtd/nand-ecc-mxic.h b/include/linux/mtd/nand-ecc-mxic.h new file mode 100644 index 000000000000..b125926e458c --- /dev/null +++ b/include/linux/mtd/nand-ecc-mxic.h @@ -0,0 +1,49 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright © 2019 Macronix + * Author: Miquèl Raynal <miquel.raynal@bootlin.com> + * + * Header for the Macronix external ECC engine. + */ + +#ifndef __MTD_NAND_ECC_MXIC_H__ +#define __MTD_NAND_ECC_MXIC_H__ + +#include <linux/platform_device.h> +#include <linux/device.h> + +struct mxic_ecc_engine; + +#if IS_ENABLED(CONFIG_MTD_NAND_ECC_MXIC) && IS_REACHABLE(CONFIG_MTD_NAND_CORE) + +struct nand_ecc_engine_ops *mxic_ecc_get_pipelined_ops(void); +struct nand_ecc_engine *mxic_ecc_get_pipelined_engine(struct platform_device *spi_pdev); +void mxic_ecc_put_pipelined_engine(struct nand_ecc_engine *eng); +int mxic_ecc_process_data_pipelined(struct nand_ecc_engine *eng, + unsigned int direction, dma_addr_t dirmap); + +#else /* !CONFIG_MTD_NAND_ECC_MXIC */ + +static inline struct nand_ecc_engine_ops *mxic_ecc_get_pipelined_ops(void) +{ + return NULL; +} + +static inline struct nand_ecc_engine * +mxic_ecc_get_pipelined_engine(struct platform_device *spi_pdev) +{ + return ERR_PTR(-EOPNOTSUPP); +} + +static inline void mxic_ecc_put_pipelined_engine(struct nand_ecc_engine *eng) {} + +static inline int mxic_ecc_process_data_pipelined(struct nand_ecc_engine *eng, + unsigned int direction, + dma_addr_t dirmap) +{ + return -EOPNOTSUPP; +} + +#endif /* CONFIG_MTD_NAND_ECC_MXIC */ + +#endif /* __MTD_NAND_ECC_MXIC_H__ */ diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index 32fc7edf65b3..c3693bb87b4c 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -264,11 +264,35 @@ struct nand_ecc_engine_ops { }; /** + * enum nand_ecc_engine_integration - How the NAND ECC engine is integrated + * @NAND_ECC_ENGINE_INTEGRATION_INVALID: Invalid value + * @NAND_ECC_ENGINE_INTEGRATION_PIPELINED: Pipelined engine, performs on-the-fly + * correction, does not need to copy + * data around + * @NAND_ECC_ENGINE_INTEGRATION_EXTERNAL: External engine, needs to bring the + * data into its own area before use + */ +enum nand_ecc_engine_integration { + NAND_ECC_ENGINE_INTEGRATION_INVALID, + NAND_ECC_ENGINE_INTEGRATION_PIPELINED, + NAND_ECC_ENGINE_INTEGRATION_EXTERNAL, +}; + +/** * struct nand_ecc_engine - ECC engine abstraction for NAND devices + * @dev: Host device + * @node: Private field for registration time * @ops: ECC engine operations + * @integration: How the engine is integrated with the host + * (only relevant on %NAND_ECC_ENGINE_TYPE_ON_HOST engines) + * @priv: Private data */ struct nand_ecc_engine { + struct device *dev; + struct list_head node; struct nand_ecc_engine_ops *ops; + enum nand_ecc_engine_integration integration; + void *priv; }; void of_get_nand_ecc_user_config(struct nand_device *nand); @@ -279,8 +303,28 @@ int nand_ecc_prepare_io_req(struct nand_device *nand, int nand_ecc_finish_io_req(struct nand_device *nand, struct nand_page_io_req *req); bool nand_ecc_is_strong_enough(struct nand_device *nand); + +#if IS_REACHABLE(CONFIG_MTD_NAND_CORE) +int nand_ecc_register_on_host_hw_engine(struct nand_ecc_engine *engine); +int nand_ecc_unregister_on_host_hw_engine(struct nand_ecc_engine *engine); +#else +static inline int +nand_ecc_register_on_host_hw_engine(struct nand_ecc_engine *engine) +{ + return -ENOTSUPP; +} +static inline int +nand_ecc_unregister_on_host_hw_engine(struct nand_ecc_engine *engine) +{ + return -ENOTSUPP; +} +#endif + struct nand_ecc_engine *nand_ecc_get_sw_engine(struct nand_device *nand); struct nand_ecc_engine *nand_ecc_get_on_die_hw_engine(struct nand_device *nand); +struct nand_ecc_engine *nand_ecc_get_on_host_hw_engine(struct nand_device *nand); +void nand_ecc_put_on_host_hw_engine(struct nand_device *nand); +struct device *nand_ecc_get_engine_dev(struct device *host); #if IS_ENABLED(CONFIG_MTD_NAND_ECC_SW_HAMMING) struct nand_ecc_engine *nand_ecc_sw_hamming_get_engine(void); @@ -962,6 +1006,11 @@ int nanddev_markbad(struct nand_device *nand, const struct nand_pos *pos); int nanddev_ecc_engine_init(struct nand_device *nand); void nanddev_ecc_engine_cleanup(struct nand_device *nand); +static inline void *nand_to_ecc_ctx(struct nand_device *nand) +{ + return nand->ecc.ctx.priv; +} + /* BBT related functions */ enum nand_bbt_block_status { NAND_BBT_BLOCK_STATUS_UNKNOWN, diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 5b88cd51fadb..dcf90144d70b 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1240,6 +1240,7 @@ struct nand_secure_region { * @lock: Lock protecting the suspended field. Also used to serialize accesses * to the NAND device * @suspended: Set to 1 when the device is suspended, 0 when it's not + * @resume_wq: wait queue to sleep if rawnand is in suspended state. * @cur_cs: Currently selected target. -1 means no target selected, otherwise we * should always have cur_cs >= 0 && cur_cs < nanddev_ntargets(). * NAND Controller drivers should not modify this value, but they're @@ -1294,6 +1295,7 @@ struct nand_chip { /* Internals */ struct mutex lock; unsigned int suspended : 1; + wait_queue_head_t resume_wq; int cur_cs; int read_retries; struct nand_secure_region *secure_regions; diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h index fc90fce26e33..42218a1164f6 100644 --- a/include/linux/mtd/spi-nor.h +++ b/include/linux/mtd/spi-nor.h @@ -47,10 +47,6 @@ #define SPINOR_OP_RDID 0x9f /* Read JEDEC ID */ #define SPINOR_OP_RDSFDP 0x5a /* Read SFDP */ #define SPINOR_OP_RDCR 0x35 /* Read configuration register */ -#define SPINOR_OP_RDFSR 0x70 /* Read flag status register */ -#define SPINOR_OP_CLFSR 0x50 /* Clear flag status register */ -#define SPINOR_OP_RDEAR 0xc8 /* Read Extended Address Register */ -#define SPINOR_OP_WREAR 0xc5 /* Write Extended Address Register */ #define SPINOR_OP_SRSTEN 0x66 /* Software Reset Enable */ #define SPINOR_OP_SRST 0x99 /* Software Reset */ #define SPINOR_OP_GBULK 0x98 /* Global Block Unlock */ @@ -86,22 +82,12 @@ #define SPINOR_OP_BP 0x02 /* Byte program */ #define SPINOR_OP_AAI_WP 0xad /* Auto address increment word program */ -/* Used for S3AN flashes only */ -#define SPINOR_OP_XSE 0x50 /* Sector erase */ -#define SPINOR_OP_XPP 0x82 /* Page program */ -#define SPINOR_OP_XRDSR 0xd7 /* Read status register */ - -#define XSR_PAGESIZE BIT(0) /* Page size in Po2 or Linear */ -#define XSR_RDY BIT(7) /* Ready */ - - /* Used for Macronix and Winbond flashes. */ #define SPINOR_OP_EN4B 0xb7 /* Enter 4-byte mode */ #define SPINOR_OP_EX4B 0xe9 /* Exit 4-byte mode */ /* Used for Spansion flashes only. */ #define SPINOR_OP_BRWR 0x17 /* Bank register write */ -#define SPINOR_OP_CLSR 0x30 /* Clear status register 1 */ /* Used for Micron flashes only. */ #define SPINOR_OP_RD_EVCR 0x65 /* Read EVCR register */ @@ -135,12 +121,6 @@ /* Enhanced Volatile Configuration Register bits */ #define EVCR_QUAD_EN_MICRON BIT(7) /* Micron Quad I/O */ -/* Flag Status Register bits */ -#define FSR_READY BIT(7) /* Device status, 0 = Busy, 1 = Ready */ -#define FSR_E_ERR BIT(5) /* Erase operation status */ -#define FSR_P_ERR BIT(4) /* Program operation status */ -#define FSR_PT_ERR BIT(1) /* Protection error bit */ - /* Status Register 2 bits. */ #define SR2_QUAD_EN_BIT1 BIT(1) #define SR2_LB1 BIT(3) /* Security Register Lock Bit 1 */ @@ -371,7 +351,7 @@ struct spi_nor_flash_parameter; * @bouncebuf_size: size of the bounce buffer * @info: SPI NOR part JEDEC MFR ID and other info * @manufacturer: SPI NOR manufacturer - * @addr_width: number of address bytes + * @addr_nbytes: number of address bytes * @erase_opcode: the opcode for erasing a sector * @read_opcode: the read opcode * @read_dummy: the dummy needed by the read operation @@ -383,6 +363,7 @@ struct spi_nor_flash_parameter; * @write_proto: the SPI protocol for write operations * @reg_proto: the SPI protocol for read_reg/write_reg/erase operations * @sfdp: the SFDP data of the flash + * @debugfs_root: pointer to the debugfs directory * @controller_ops: SPI NOR controller driver specific operations. * @params: [FLASH-SPECIFIC] SPI NOR flash parameters and settings. * The structure includes legacy flash parameters and @@ -400,7 +381,7 @@ struct spi_nor { size_t bouncebuf_size; const struct flash_info *info; const struct spi_nor_manufacturer *manufacturer; - u8 addr_width; + u8 addr_nbytes; u8 erase_opcode; u8 read_opcode; u8 read_dummy; @@ -412,6 +393,7 @@ struct spi_nor { u32 flags; enum spi_nor_cmd_ext cmd_ext_type; struct sfdp *sfdp; + struct dentry *debugfs_root; const struct spi_nor_controller_ops *controller_ops; diff --git a/include/linux/mtd/spinand.h b/include/linux/mtd/spinand.h index 6988956b8492..6d3392a7edc6 100644 --- a/include/linux/mtd/spinand.h +++ b/include/linux/mtd/spinand.h @@ -260,12 +260,14 @@ struct spinand_manufacturer { }; /* SPI NAND manufacturers */ +extern const struct spinand_manufacturer ato_spinand_manufacturer; extern const struct spinand_manufacturer gigadevice_spinand_manufacturer; extern const struct spinand_manufacturer macronix_spinand_manufacturer; extern const struct spinand_manufacturer micron_spinand_manufacturer; extern const struct spinand_manufacturer paragon_spinand_manufacturer; extern const struct spinand_manufacturer toshiba_spinand_manufacturer; extern const struct spinand_manufacturer winbond_spinand_manufacturer; +extern const struct spinand_manufacturer xtx_spinand_manufacturer; /** * struct spinand_op_variants - SPI NAND operation variants @@ -389,6 +391,8 @@ struct spinand_info { struct spinand_dirmap { struct spi_mem_dirmap_desc *wdesc; struct spi_mem_dirmap_desc *rdesc; + struct spi_mem_dirmap_desc *wdesc_ecc; + struct spi_mem_dirmap_desc *rdesc_ecc; }; /** diff --git a/include/linux/mutex_api.h b/include/linux/mutex_api.h new file mode 100644 index 000000000000..85ab9491e13e --- /dev/null +++ b/include/linux/mutex_api.h @@ -0,0 +1 @@ +#include <linux/mutex.h> diff --git a/include/linux/mux/consumer.h b/include/linux/mux/consumer.h index 7a09b040ac39..2e25c838f831 100644 --- a/include/linux/mux/consumer.h +++ b/include/linux/mux/consumer.h @@ -14,14 +14,19 @@ struct device; struct mux_control; +struct mux_state; unsigned int mux_control_states(struct mux_control *mux); int __must_check mux_control_select_delay(struct mux_control *mux, unsigned int state, unsigned int delay_us); +int __must_check mux_state_select_delay(struct mux_state *mstate, + unsigned int delay_us); int __must_check mux_control_try_select_delay(struct mux_control *mux, unsigned int state, unsigned int delay_us); +int __must_check mux_state_try_select_delay(struct mux_state *mstate, + unsigned int delay_us); static inline int __must_check mux_control_select(struct mux_control *mux, unsigned int state) @@ -29,18 +34,31 @@ static inline int __must_check mux_control_select(struct mux_control *mux, return mux_control_select_delay(mux, state, 0); } +static inline int __must_check mux_state_select(struct mux_state *mstate) +{ + return mux_state_select_delay(mstate, 0); +} + static inline int __must_check mux_control_try_select(struct mux_control *mux, unsigned int state) { return mux_control_try_select_delay(mux, state, 0); } +static inline int __must_check mux_state_try_select(struct mux_state *mstate) +{ + return mux_state_try_select_delay(mstate, 0); +} + int mux_control_deselect(struct mux_control *mux); +int mux_state_deselect(struct mux_state *mstate); struct mux_control *mux_control_get(struct device *dev, const char *mux_name); void mux_control_put(struct mux_control *mux); struct mux_control *devm_mux_control_get(struct device *dev, const char *mux_name); +struct mux_state *devm_mux_state_get(struct device *dev, + const char *mux_name); #endif /* _LINUX_MUX_CONSUMER_H */ diff --git a/include/linux/namei.h b/include/linux/namei.h index e89329bb3134..00fee52df842 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -69,6 +69,12 @@ extern struct dentry *lookup_one_len(const char *, struct dentry *, int); extern struct dentry *lookup_one_len_unlocked(const char *, struct dentry *, int); extern struct dentry *lookup_positive_unlocked(const char *, struct dentry *, int); struct dentry *lookup_one(struct user_namespace *, const char *, struct dentry *, int); +struct dentry *lookup_one_unlocked(struct user_namespace *mnt_userns, + const char *name, struct dentry *base, + int len); +struct dentry *lookup_one_positive_unlocked(struct user_namespace *mnt_userns, + const char *name, + struct dentry *base, int len); extern int follow_down_one(struct path *); extern int follow_down(struct path *); @@ -77,7 +83,7 @@ extern int follow_up(struct path *); extern struct dentry *lock_rename(struct dentry *, struct dentry *); extern void unlock_rename(struct dentry *, struct dentry *); -extern int __must_check nd_jump_link(struct path *path); +extern int __must_check nd_jump_link(const struct path *path); static inline void nd_terminate_link(void *name, size_t len, size_t maxlen) { diff --git a/include/linux/nd.h b/include/linux/nd.h index 8a8c63edb1b2..b9771ba1ef87 100644 --- a/include/linux/nd.h +++ b/include/linux/nd.h @@ -8,6 +8,7 @@ #include <linux/ndctl.h> #include <linux/device.h> #include <linux/badblocks.h> +#include <linux/perf_event.h> enum nvdimm_event { NVDIMM_REVALIDATE_POISON, @@ -23,6 +24,57 @@ enum nvdimm_claim_class { NVDIMM_CCLASS_UNKNOWN, }; +#define NVDIMM_EVENT_VAR(_id) event_attr_##_id +#define NVDIMM_EVENT_PTR(_id) (&event_attr_##_id.attr.attr) + +#define NVDIMM_EVENT_ATTR(_name, _id) \ + PMU_EVENT_ATTR(_name, NVDIMM_EVENT_VAR(_id), _id, \ + nvdimm_events_sysfs_show) + +/* Event attribute array index */ +#define NVDIMM_PMU_FORMAT_ATTR 0 +#define NVDIMM_PMU_EVENT_ATTR 1 +#define NVDIMM_PMU_CPUMASK_ATTR 2 +#define NVDIMM_PMU_NULL_ATTR 3 + +/** + * struct nvdimm_pmu - data structure for nvdimm perf driver + * @pmu: pmu data structure for nvdimm performance stats. + * @dev: nvdimm device pointer. + * @cpu: designated cpu for counter access. + * @node: node for cpu hotplug notifier link. + * @cpuhp_state: state for cpu hotplug notification. + * @arch_cpumask: cpumask to get designated cpu for counter access. + */ +struct nvdimm_pmu { + struct pmu pmu; + struct device *dev; + int cpu; + struct hlist_node node; + enum cpuhp_state cpuhp_state; + /* cpumask provided by arch/platform specific code */ + struct cpumask arch_cpumask; +}; + +struct platform_device; + +#ifdef CONFIG_PERF_EVENTS +extern ssize_t nvdimm_events_sysfs_show(struct device *dev, + struct device_attribute *attr, + char *page); + +int register_nvdimm_pmu(struct nvdimm_pmu *nvdimm, struct platform_device *pdev); +void unregister_nvdimm_pmu(struct nvdimm_pmu *nd_pmu); + +#else +static inline int register_nvdimm_pmu(struct nvdimm_pmu *nvdimm, struct platform_device *pdev) +{ + return -ENXIO; +} + +static inline void unregister_nvdimm_pmu(struct nvdimm_pmu *nd_pmu) { } +#endif + struct nd_device_driver { struct device_driver drv; unsigned long type; @@ -92,27 +144,6 @@ struct nd_namespace_pmem { int id; }; -/** - * struct nd_namespace_blk - namespace for dimm-bounded persistent memory - * @alt_name: namespace name supplied in the dimm label - * @uuid: namespace name supplied in the dimm label - * @id: ida allocated id - * @lbasize: blk namespaces have a native sector size when btt not present - * @size: sum of all the resource ranges allocated to this namespace - * @num_resources: number of dpa extents to claim - * @res: discontiguous dpa extents for given dimm - */ -struct nd_namespace_blk { - struct nd_namespace_common common; - char *alt_name; - uuid_t *uuid; - int id; - unsigned long lbasize; - resource_size_t size; - int num_resources; - struct resource **res; -}; - static inline struct nd_namespace_io *to_nd_namespace_io(const struct device *dev) { return container_of(dev, struct nd_namespace_io, common.dev); @@ -125,11 +156,6 @@ static inline struct nd_namespace_pmem *to_nd_namespace_pmem(const struct device return container_of(nsio, struct nd_namespace_pmem, nsio); } -static inline struct nd_namespace_blk *to_nd_namespace_blk(const struct device *dev) -{ - return container_of(dev, struct nd_namespace_blk, common.dev); -} - /** * nvdimm_read_bytes() - synchronously read bytes from an nvdimm namespace * @ndns: device to read diff --git a/include/linux/net.h b/include/linux/net.h index ba736b457a06..18d942bbdf6e 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -41,6 +41,7 @@ struct net; #define SOCK_NOSPACE 2 #define SOCK_PASSCRED 3 #define SOCK_PASSSEC 4 +#define SOCK_SUPPORT_ZC 5 #ifndef ARCH_HAS_SOCKET_TYPES /** @@ -125,6 +126,25 @@ struct socket { struct socket_wq wq; }; +/* + * "descriptor" for what we're up to with a read. + * This allows us to use the same read code yet + * have multiple different users of the data that + * we read from a file. + * + * The simplest case just copies the data to user + * mode. + */ +typedef struct { + size_t written; + size_t count; + union { + char __user *buf; + void *data; + } arg; + int error; +} read_descriptor_t; + struct vm_area_struct; struct page; struct sockaddr; @@ -133,6 +153,8 @@ struct module; struct sk_buff; typedef int (*sk_read_actor_t)(read_descriptor_t *, struct sk_buff *, unsigned int, size_t); +typedef int (*skb_read_actor_t)(struct sock *, struct sk_buff *); + struct proto_ops { int family; @@ -195,6 +217,8 @@ struct proto_ops { */ int (*read_sock)(struct sock *sk, read_descriptor_t *desc, sk_read_actor_t recv_actor); + /* This is different from read_sock(), it reads an entire skb at a time. */ + int (*read_skb)(struct sock *sk, skb_read_actor_t recv_actor); int (*sendpage_locked)(struct sock *sk, struct page *page, int offset, size_t size, int flags); int (*sendmsg_locked)(struct sock *sk, struct msghdr *msg, @@ -284,8 +308,6 @@ do { \ #define net_get_random_once(buf, nbytes) \ get_random_once((buf), (nbytes)) -#define net_get_random_once_wait(buf, nbytes) \ - get_random_once_wait((buf), (nbytes)) /* * E.g. XFS meta- & log-data is in slab pages, or bcache meta diff --git a/include/linux/net/intel/i40e_client.h b/include/linux/net/intel/i40e_client.h index 6b3267b49755..ed42bd5f639f 100644 --- a/include/linux/net/intel/i40e_client.h +++ b/include/linux/net/intel/i40e_client.h @@ -26,11 +26,6 @@ struct i40e_client_version { u8 rsvd; }; -enum i40e_client_state { - __I40E_CLIENT_NULL, - __I40E_CLIENT_REGISTERED -}; - enum i40e_client_instance_state { __I40E_CLIENT_INSTANCE_NONE, __I40E_CLIENT_INSTANCE_OPENED, @@ -190,11 +185,6 @@ struct i40e_client { const struct i40e_client_ops *ops; /* client ops provided by the client */ }; -static inline bool i40e_client_is_registered(struct i40e_client *client) -{ - return test_bit(__I40E_CLIENT_REGISTERED, &client->state); -} - void i40e_client_device_register(struct i40e_info *ldev, struct i40e_client *client); void i40e_client_device_unregister(struct i40e_info *ldev); diff --git a/include/linux/net/intel/iidc.h b/include/linux/net/intel/iidc.h index 1289593411d3..1c1332e4df26 100644 --- a/include/linux/net/intel/iidc.h +++ b/include/linux/net/intel/iidc.h @@ -32,6 +32,8 @@ enum iidc_rdma_protocol { }; #define IIDC_MAX_USER_PRIORITY 8 +#define IIDC_MAX_DSCP_MAPPING 64 +#define IIDC_DSCP_PFC_MODE 0x1 /* Struct to hold per RDMA Qset info */ struct iidc_rdma_qset_params { @@ -60,6 +62,8 @@ struct iidc_qos_params { u8 vport_relative_bw; u8 vport_priority_type; u8 num_tc; + u8 pfc_mode; + u8 dscp_map[IIDC_MAX_DSCP_MAPPING]; }; struct iidc_event { diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index 2c6b9e416225..7c2d77d75a88 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -169,7 +169,7 @@ enum { #define NETIF_F_HW_HSR_FWD __NETIF_F(HW_HSR_FWD) #define NETIF_F_HW_HSR_DUP __NETIF_F(HW_HSR_DUP) -/* Finds the next feature with the highest number of the range of start till 0. +/* Finds the next feature with the highest number of the range of start-1 till 0. */ static inline int find_next_netdev_feature(u64 feature, unsigned long start) { @@ -188,7 +188,7 @@ static inline int find_next_netdev_feature(u64 feature, unsigned long start) for ((bit) = find_next_netdev_feature((mask_addr), \ NETDEV_FEATURE_COUNT); \ (bit) >= 0; \ - (bit) = find_next_netdev_feature((mask_addr), (bit) - 1)) + (bit) = find_next_netdev_feature((mask_addr), (bit))) /* Features valid for ethtool to change */ /* = all defined minus driver/device-class-related */ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 3213c7227b59..eddf8ee270e7 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -28,6 +28,7 @@ #include <linux/prefetch.h> #include <asm/cache.h> #include <asm/byteorder.h> +#include <asm/local.h> #include <linux/percpu.h> #include <linux/rculist.h> @@ -49,6 +50,7 @@ #include <linux/hashtable.h> #include <linux/rbtree.h> #include <net/net_trackers.h> +#include <net/net_debug.h> struct netpoll_info; struct device; @@ -58,7 +60,8 @@ struct dsa_port; struct ip_tunnel_parm; struct macsec_context; struct macsec_ops; - +struct netdev_name_node; +struct sd_flow_limit; struct sfp_bus; /* 802.11 specific */ struct wireless_dev; @@ -194,6 +197,15 @@ struct net_device_stats { unsigned long tx_compressed; }; +/* per-cpu stats, allocated on demand. + * Try to fit them in a single cache line, for dev_get_stats() sake. + */ +struct net_device_core_stats { + unsigned long rx_dropped; + unsigned long tx_dropped; + unsigned long rx_nohandler; + unsigned long rx_otherhost_dropped; +} __aligned(4 * sizeof(unsigned long)); #include <linux/cache.h> #include <linux/skbuff.h> @@ -241,11 +253,17 @@ struct netdev_hw_addr_list { #define netdev_uc_empty(dev) netdev_hw_addr_list_empty(&(dev)->uc) #define netdev_for_each_uc_addr(ha, dev) \ netdev_hw_addr_list_for_each(ha, &(dev)->uc) +#define netdev_for_each_synced_uc_addr(_ha, _dev) \ + netdev_for_each_uc_addr((_ha), (_dev)) \ + if ((_ha)->sync_cnt) #define netdev_mc_count(dev) netdev_hw_addr_list_count(&(dev)->mc) #define netdev_mc_empty(dev) netdev_hw_addr_list_empty(&(dev)->mc) #define netdev_for_each_mc_addr(ha, dev) \ netdev_hw_addr_list_for_each(ha, &(dev)->mc) +#define netdev_for_each_synced_mc_addr(_ha, _dev) \ + netdev_for_each_mc_addr((_ha), (_dev)) \ + if ((_ha)->sync_cnt) struct hh_cache { unsigned int hh_len; @@ -534,8 +552,8 @@ static inline bool napi_if_scheduled_mark_missed(struct napi_struct *n) { unsigned long val, new; + val = READ_ONCE(n->state); do { - val = READ_ONCE(n->state); if (val & NAPIF_STATE_DISABLE) return true; @@ -543,7 +561,7 @@ static inline bool napi_if_scheduled_mark_missed(struct napi_struct *n) return false; new = val | NAPIF_STATE_MISSED; - } while (cmpxchg(&n->state, val, new) != val); + } while (!try_cmpxchg(&n->state, &val, new)); return true; } @@ -628,9 +646,23 @@ extern int sysctl_devconf_inherit_init_net; */ static inline bool net_has_fallback_tunnels(const struct net *net) { - return !IS_ENABLED(CONFIG_SYSCTL) || - !sysctl_fb_tunnels_only_for_init_net || - (net == &init_net && sysctl_fb_tunnels_only_for_init_net == 1); +#if IS_ENABLED(CONFIG_SYSCTL) + int fb_tunnels_only_for_init_net = READ_ONCE(sysctl_fb_tunnels_only_for_init_net); + + return !fb_tunnels_only_for_init_net || + (net_eq(net, &init_net) && fb_tunnels_only_for_init_net == 1); +#else + return true; +#endif +} + +static inline int net_inherit_devconf(void) +{ +#if IS_ENABLED(CONFIG_SYSCTL) + return READ_ONCE(sysctl_devconf_inherit_init_net); +#else + return 0; +#endif } static inline int netdev_queue_numa_node_read(const struct netdev_queue *q) @@ -853,6 +885,7 @@ enum net_device_path_type { DEV_PATH_BRIDGE, DEV_PATH_PPPOE, DEV_PATH_DSA, + DEV_PATH_MTK_WDMA, }; struct net_device_path { @@ -878,6 +911,12 @@ struct net_device_path { int port; u16 proto; } dsa; + struct { + u8 wdma_idx; + u8 queue; + u16 wcid; + u8 bss; + } mtk_wdma; }; }; @@ -891,7 +930,7 @@ struct net_device_path_stack { struct net_device_path_ctx { const struct net_device *dev; - const u8 *daddr; + u8 daddr[ETH_ALEN]; int num_vlans; struct { @@ -901,6 +940,7 @@ struct net_device_path_ctx { }; enum tc_setup_type { + TC_QUERY_CAPS, TC_SETUP_QDISC_MQPRIO, TC_SETUP_CLSU32, TC_SETUP_CLSFLOWER, @@ -1004,16 +1044,6 @@ struct dev_ifalias { struct devlink; struct tlsdev_ops; -struct netdev_name_node { - struct hlist_node hlist; - struct list_head list; - struct net_device *dev; - const char *name; -}; - -int netdev_name_node_alt_create(struct net_device *dev, const char *name); -int netdev_name_node_alt_destroy(struct net_device *dev, const char *name); - struct netdev_net_notifier { struct list_head list; struct notifier_block *nb; @@ -1252,6 +1282,10 @@ struct netdev_net_notifier { * struct net_device *dev, * const unsigned char *addr, u16 vid) * Deletes the FDB entry from dev coresponding to addr. + * int (*ndo_fdb_del_bulk)(struct ndmsg *ndm, struct nlattr *tb[], + * struct net_device *dev, + * u16 vid, + * struct netlink_ext_ack *extack); * int (*ndo_fdb_dump)(struct sk_buff *skb, struct netlink_callback *cb, * struct net_device *dev, struct net_device *filter_dev, * int *idx) @@ -1344,6 +1378,12 @@ struct netdev_net_notifier { * The caller must be under RCU read context. * int (*ndo_fill_forward_path)(struct net_device_path_ctx *ctx, struct net_device_path *path); * Get the forwarding path to reach the real device from the HW destination address + * ktime_t (*ndo_get_tstamp)(struct net_device *dev, + * const struct skb_shared_hwtstamps *hwtstamps, + * bool cycles); + * Get hardware timestamp based on normal/adjustable time or free running + * cycle counter. This function is required if physical clock supports a + * free running cycle counter. */ struct net_device_ops { int (*ndo_init)(struct net_device *dev); @@ -1501,7 +1541,12 @@ struct net_device_ops { struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, - u16 vid); + u16 vid, struct netlink_ext_ack *extack); + int (*ndo_fdb_del_bulk)(struct ndmsg *ndm, + struct nlattr *tb[], + struct net_device *dev, + u16 vid, + struct netlink_ext_ack *extack); int (*ndo_fdb_dump)(struct sk_buff *skb, struct netlink_callback *cb, struct net_device *dev, @@ -1561,6 +1606,9 @@ struct net_device_ops { struct net_device * (*ndo_get_peer_dev)(struct net_device *dev); int (*ndo_fill_forward_path)(struct net_device_path_ctx *ctx, struct net_device_path *path); + ktime_t (*ndo_get_tstamp)(struct net_device *dev, + const struct skb_shared_hwtstamps *hwtstamps, + bool cycles); }; /** @@ -1644,7 +1692,7 @@ enum netdev_priv_flags { IFF_FAILOVER_SLAVE = 1<<28, IFF_L3MDEV_RX_HANDLER = 1<<29, IFF_LIVE_RENAME_OK = 1<<30, - IFF_TX_SKB_NO_LINEAR = 1<<31, + IFF_TX_SKB_NO_LINEAR = BIT_ULL(31), IFF_CHANGE_PROTO_DOWN = BIT_ULL(32), }; @@ -1735,12 +1783,8 @@ enum netdev_ml_priv_type { * @stats: Statistics struct, which was left as a legacy, use * rtnl_link_stats64 instead * - * @rx_dropped: Dropped packets by core network, - * do not use this in drivers - * @tx_dropped: Dropped packets by core network, + * @core_stats: core networking counters, * do not use this in drivers - * @rx_nohandler: nohandler dropped packets by core network on - * inactive devices, do not use this in drivers * @carrier_up_count: Number of times the carrier has been up * @carrier_down_count: Number of times the carrier has been down * @@ -1814,7 +1858,6 @@ enum netdev_ml_priv_type { * @tipc_ptr: TIPC specific data * @atalk_ptr: AppleTalk link * @ip_ptr: IPv4 specific data - * @dn_ptr: DECnet specific data * @ip6_ptr: IPv6 specific data * @ax25_ptr: AX.25 specific data * @ieee80211_ptr: IEEE 802.11 specific data, assign before registering @@ -1894,6 +1937,8 @@ enum netdev_ml_priv_type { * @garp_port: GARP * @mrp_port: MRP * + * @dm_private: Drop monitor private + * * @dev: Class/net/name entry * @sysfs_groups: Space for optional device, statistics and wireless * sysfs groups @@ -1902,8 +1947,10 @@ enum netdev_ml_priv_type { * @rtnl_link_ops: Rtnl_link_ops * * @gso_max_size: Maximum size of generic segmentation offload + * @tso_max_size: Device (as in HW) limit on the max TSO request size * @gso_max_segs: Maximum number of segments that can be passed to the * NIC for GSO + * @tso_max_segs: Device (as in HW) limit on the max TSO segment count * * @dcbnl_ops: Data Center Bridging netlink ops * @num_tc: Number of traffic classes in the net device @@ -1948,6 +1995,9 @@ enum netdev_ml_priv_type { * @dev_addr_shadow: Copy of @dev_addr to catch direct writes. * @linkwatch_dev_tracker: refcount tracker used by linkwatch. * @watchdog_dev_tracker: refcount tracker used by watchdog. + * @dev_registered_tracker: tracker for reference held while + * registered + * @offload_xstats_l3: L3 HW stats for this netdevice. * * FIXME: cleanup struct net_device such that network protocol info * moves out. @@ -2020,9 +2070,7 @@ struct net_device { struct net_device_stats stats; /* not used by modern drivers */ - atomic_long_t rx_dropped; - atomic_long_t tx_dropped; - atomic_long_t rx_nohandler; + struct net_device_core_stats __percpu *core_stats; /* Stats to monitor link on/off, flapping */ atomic_t carrier_up_count; @@ -2091,6 +2139,8 @@ struct net_device { /* Protocol-specific pointers */ + struct in_device __rcu *ip_ptr; + struct inet6_dev __rcu *ip6_ptr; #if IS_ENABLED(CONFIG_VLAN_8021Q) struct vlan_info __rcu *vlan_info; #endif @@ -2103,16 +2153,15 @@ struct net_device { #if IS_ENABLED(CONFIG_ATALK) void *atalk_ptr; #endif - struct in_device __rcu *ip_ptr; -#if IS_ENABLED(CONFIG_DECNET) - struct dn_dev __rcu *dn_ptr; -#endif - struct inet6_dev __rcu *ip6_ptr; #if IS_ENABLED(CONFIG_AX25) void *ax25_ptr; #endif +#if IS_ENABLED(CONFIG_CFG80211) struct wireless_dev *ieee80211_ptr; +#endif +#if IS_ENABLED(CONFIG_IEEE802154) || IS_ENABLED(CONFIG_6LOWPAN) struct wpan_dev *ieee802154_ptr; +#endif #if IS_ENABLED(CONFIG_MPLS_ROUTING) struct mpls_dev __rcu *mpls_ptr; #endif @@ -2133,7 +2182,11 @@ struct net_device { struct bpf_prog __rcu *xdp_prog; unsigned long gro_flush_timeout; int napi_defer_hard_irqs; -#define GRO_MAX_SIZE 65536 +#define GRO_LEGACY_MAX_SIZE 65536u +/* TCP minimal MSS is 8 (TCP_MIN_GSO_SIZE), + * and shinfo->gso_segs is a 16bit field. + */ +#define GRO_MAX_SIZE (8 * 65535u) unsigned int gro_max_size; rx_handler_func_t __rcu *rx_handler; void __rcu *rx_handler_data; @@ -2158,7 +2211,7 @@ struct net_device { struct netdev_queue *_tx ____cacheline_aligned_in_smp; unsigned int num_tx_queues; unsigned int real_num_tx_queues; - struct Qdisc *qdisc; + struct Qdisc __rcu *qdisc; unsigned int tx_queue_len; spinlock_t tx_global_lock; @@ -2234,7 +2287,9 @@ struct net_device { #if IS_ENABLED(CONFIG_MRP) struct mrp_port __rcu *mrp_port; #endif - +#if IS_ENABLED(CONFIG_NET_DROP_MONITOR) + struct dm_hw_stat_delta __rcu *dm_private; +#endif struct device dev; const struct attribute_group *sysfs_groups[4]; const struct attribute_group *sysfs_rx_queue_group; @@ -2242,10 +2297,20 @@ struct net_device { const struct rtnl_link_ops *rtnl_link_ops; /* for setting kernel sock attribute on TCP connection setup */ -#define GSO_MAX_SIZE 65536 +#define GSO_MAX_SEGS 65535u +#define GSO_LEGACY_MAX_SIZE 65536u +/* TCP minimal MSS is 8 (TCP_MIN_GSO_SIZE), + * and shinfo->gso_segs is a 16bit field. + */ +#define GSO_MAX_SIZE (8 * GSO_MAX_SEGS) + unsigned int gso_max_size; -#define GSO_MAX_SEGS 65535 +#define TSO_LEGACY_MAX_SIZE 65536 +#define TSO_MAX_SIZE UINT_MAX + unsigned int tso_max_size; u16 gso_max_segs; +#define TSO_MAX_SEGS U16_MAX + u16 tso_max_segs; #ifdef CONFIG_DCB const struct dcbnl_rtnl_ops *dcbnl_ops; @@ -2282,6 +2347,8 @@ struct net_device { u8 dev_addr_shadow[MAX_ADDR_LEN]; netdevice_tracker linkwatch_dev_tracker; netdevice_tracker watchdog_dev_tracker; + netdevice_tracker dev_registered_tracker; + struct rtnl_hw_stats64 *offload_xstats_l3; }; #define to_net_dev(d) container_of(d, struct net_device, dev) @@ -2479,37 +2546,50 @@ static inline void *netdev_priv(const struct net_device *dev) */ #define NAPI_POLL_WEIGHT 64 +void netif_napi_add_weight(struct net_device *dev, struct napi_struct *napi, + int (*poll)(struct napi_struct *, int), int weight); + /** - * netif_napi_add - initialize a NAPI context - * @dev: network device - * @napi: NAPI context - * @poll: polling function - * @weight: default weight + * netif_napi_add() - initialize a NAPI context + * @dev: network device + * @napi: NAPI context + * @poll: polling function * * netif_napi_add() must be used to initialize a NAPI context prior to calling * *any* of the other NAPI-related functions. */ -void netif_napi_add(struct net_device *dev, struct napi_struct *napi, - int (*poll)(struct napi_struct *, int), int weight); +static inline void +netif_napi_add(struct net_device *dev, struct napi_struct *napi, + int (*poll)(struct napi_struct *, int)) +{ + netif_napi_add_weight(dev, napi, poll, NAPI_POLL_WEIGHT); +} + +static inline void +netif_napi_add_tx_weight(struct net_device *dev, + struct napi_struct *napi, + int (*poll)(struct napi_struct *, int), + int weight) +{ + set_bit(NAPI_STATE_NO_BUSY_POLL, &napi->state); + netif_napi_add_weight(dev, napi, poll, weight); +} /** - * netif_tx_napi_add - initialize a NAPI context - * @dev: network device - * @napi: NAPI context - * @poll: polling function - * @weight: default weight + * netif_napi_add_tx() - initialize a NAPI context to be used for Tx only + * @dev: network device + * @napi: NAPI context + * @poll: polling function * * This variant of netif_napi_add() should be used from drivers using NAPI * to exclusively poll a TX queue. * This will avoid we add it into napi_hash[], thus polluting this hash table. */ -static inline void netif_tx_napi_add(struct net_device *dev, +static inline void netif_napi_add_tx(struct net_device *dev, struct napi_struct *napi, - int (*poll)(struct napi_struct *, int), - int weight) + int (*poll)(struct napi_struct *, int)) { - set_bit(NAPI_STATE_NO_BUSY_POLL, &napi->state); - netif_napi_add(dev, napi, poll, weight); + netif_napi_add_tx_weight(dev, napi, poll, NAPI_POLL_WEIGHT); } /** @@ -2548,6 +2628,7 @@ struct packet_type { struct net_device *); bool (*id_match)(struct packet_type *ptype, struct sock *sk); + struct net *af_packet_net; void *af_packet_priv; struct list_head list; }; @@ -2569,10 +2650,10 @@ struct packet_offload { /* often modified stats are per-CPU, other are shared (netdev->stats) */ struct pcpu_sw_netstats { - u64 rx_packets; - u64 rx_bytes; - u64 tx_packets; - u64 tx_bytes; + u64_stats_t rx_packets; + u64_stats_t rx_bytes; + u64_stats_t tx_packets; + u64_stats_t tx_bytes; struct u64_stats_sync syncp; } __aligned(4 * sizeof(u64)); @@ -2589,8 +2670,8 @@ static inline void dev_sw_netstats_rx_add(struct net_device *dev, unsigned int l struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats); u64_stats_update_begin(&tstats->syncp); - tstats->rx_bytes += len; - tstats->rx_packets++; + u64_stats_add(&tstats->rx_bytes, len); + u64_stats_inc(&tstats->rx_packets); u64_stats_update_end(&tstats->syncp); } @@ -2601,8 +2682,8 @@ static inline void dev_sw_netstats_tx_add(struct net_device *dev, struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats); u64_stats_update_begin(&tstats->syncp); - tstats->tx_bytes += len; - tstats->tx_packets += packets; + u64_stats_add(&tstats->tx_bytes, len); + u64_stats_add(&tstats->tx_packets, packets); u64_stats_update_end(&tstats->syncp); } @@ -2721,6 +2802,10 @@ enum netdev_cmd { NETDEV_CVLAN_FILTER_DROP_INFO, NETDEV_SVLAN_FILTER_PUSH_INFO, NETDEV_SVLAN_FILTER_DROP_INFO, + NETDEV_OFFLOAD_XSTATS_ENABLE, + NETDEV_OFFLOAD_XSTATS_DISABLE, + NETDEV_OFFLOAD_XSTATS_REPORT_USED, + NETDEV_OFFLOAD_XSTATS_REPORT_DELTA, }; const char *netdev_cmd_to_name(enum netdev_cmd cmd); @@ -2771,6 +2856,42 @@ struct netdev_notifier_pre_changeaddr_info { const unsigned char *dev_addr; }; +enum netdev_offload_xstats_type { + NETDEV_OFFLOAD_XSTATS_TYPE_L3 = 1, +}; + +struct netdev_notifier_offload_xstats_info { + struct netdev_notifier_info info; /* must be first */ + enum netdev_offload_xstats_type type; + + union { + /* NETDEV_OFFLOAD_XSTATS_REPORT_DELTA */ + struct netdev_notifier_offload_xstats_rd *report_delta; + /* NETDEV_OFFLOAD_XSTATS_REPORT_USED */ + struct netdev_notifier_offload_xstats_ru *report_used; + }; +}; + +int netdev_offload_xstats_enable(struct net_device *dev, + enum netdev_offload_xstats_type type, + struct netlink_ext_ack *extack); +int netdev_offload_xstats_disable(struct net_device *dev, + enum netdev_offload_xstats_type type); +bool netdev_offload_xstats_enabled(const struct net_device *dev, + enum netdev_offload_xstats_type type); +int netdev_offload_xstats_get(struct net_device *dev, + enum netdev_offload_xstats_type type, + struct rtnl_hw_stats64 *stats, bool *used, + struct netlink_ext_ack *extack); +void +netdev_offload_xstats_report_delta(struct netdev_notifier_offload_xstats_rd *rd, + const struct rtnl_hw_stats64 *stats); +void +netdev_offload_xstats_report_used(struct netdev_notifier_offload_xstats_ru *ru); +void netdev_offload_xstats_push_delta(struct net_device *dev, + enum netdev_offload_xstats_type type, + const struct rtnl_hw_stats64 *stats); + static inline void netdev_notifier_info_init(struct netdev_notifier_info *info, struct net_device *dev) { @@ -2879,10 +3000,20 @@ u16 dev_pick_tx_zero(struct net_device *dev, struct sk_buff *skb, u16 dev_pick_tx_cpu_id(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev); -int dev_queue_xmit(struct sk_buff *skb); -int dev_queue_xmit_accel(struct sk_buff *skb, struct net_device *sb_dev); +int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev); int __dev_direct_xmit(struct sk_buff *skb, u16 queue_id); +static inline int dev_queue_xmit(struct sk_buff *skb) +{ + return __dev_queue_xmit(skb, NULL); +} + +static inline int dev_queue_xmit_accel(struct sk_buff *skb, + struct net_device *sb_dev) +{ + return __dev_queue_xmit(skb, sb_dev); +} + static inline int dev_direct_xmit(struct sk_buff *skb, u16 queue_id) { int ret; @@ -2915,7 +3046,6 @@ struct net_device *dev_get_by_index(struct net *net, int ifindex); struct net_device *__dev_get_by_index(struct net *net, int ifindex); struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex); struct net_device *dev_get_by_napi_id(unsigned int napi_id); -int netdev_get_name(struct net *net, char *name, int ifindex); int dev_restart(struct net_device *dev); @@ -2974,19 +3104,6 @@ static inline bool dev_has_header(const struct net_device *dev) return dev->header_ops && dev->header_ops->create; } -#ifdef CONFIG_NET_FLOW_LIMIT -#define FLOW_LIMIT_HISTORY (1 << 7) /* must be ^2 and !overflow buckets */ -struct sd_flow_limit { - u64 count; - unsigned int num_buckets; - unsigned int history_head; - u16 history[FLOW_LIMIT_HISTORY]; - u8 buckets[]; -}; - -extern int netdev_flow_limit_table_len; -#endif /* CONFIG_NET_FLOW_LIMIT */ - /* * Incoming packets are placed on per-CPU queues */ @@ -3014,6 +3131,9 @@ struct softnet_data { struct { u16 recursion; u8 more; +#ifdef CONFIG_NET_EGRESS + u8 skip_txqueue; +#endif } xmit; #ifdef CONFIG_RPS /* input_queue_head should be written by cpu owning this struct, @@ -3031,6 +3151,12 @@ struct softnet_data { struct sk_buff_head input_pkt_queue; struct napi_struct backlog; + /* Another possibly contended cache line */ + spinlock_t defer_lock ____cacheline_aligned_in_smp; + int defer_count; + int defer_ipi_scheduled; + struct sk_buff *defer_list; + call_single_data_t defer_csd; }; static inline void input_queue_head_incr(struct softnet_data *sd) @@ -3231,6 +3357,16 @@ static inline void netdev_txq_bql_complete_prefetchw(struct netdev_queue *dev_qu #endif } +/** + * netdev_tx_sent_queue - report the number of bytes queued to a given tx queue + * @dev_queue: network device queue + * @bytes: number of bytes queued to the device queue + * + * Report the number of bytes queued for sending/completion to the network + * device hardware queue. @bytes should be a good approximation and should + * exactly match netdev_completed_queue() @bytes. + * This is typically called once per packet, from ndo_start_xmit(). + */ static inline void netdev_tx_sent_queue(struct netdev_queue *dev_queue, unsigned int bytes) { @@ -3276,13 +3412,14 @@ static inline bool __netdev_tx_sent_queue(struct netdev_queue *dev_queue, } /** - * netdev_sent_queue - report the number of bytes queued to hardware - * @dev: network device - * @bytes: number of bytes queued to the hardware device queue + * netdev_sent_queue - report the number of bytes queued to hardware + * @dev: network device + * @bytes: number of bytes queued to the hardware device queue * - * Report the number of bytes queued for sending/completion to the network - * device hardware queue. @bytes should be a good approximation and should - * exactly match netdev_completed_queue() @bytes + * Report the number of bytes queued for sending/completion to the network + * device hardware queue#0. @bytes should be a good approximation and should + * exactly match netdev_completed_queue() @bytes. + * This is typically called once per packet, from ndo_start_xmit(). */ static inline void netdev_sent_queue(struct net_device *dev, unsigned int bytes) { @@ -3297,6 +3434,15 @@ static inline bool __netdev_sent_queue(struct net_device *dev, xmit_more); } +/** + * netdev_tx_completed_queue - report number of packets/bytes at TX completion. + * @dev_queue: network device queue + * @pkts: number of packets (currently ignored) + * @bytes: number of bytes dequeued from the device queue + * + * Must be called at most once per TX completion round (and not per + * individual packet), so that BQL can adjust its limits appropriately. + */ static inline void netdev_tx_completed_queue(struct netdev_queue *dev_queue, unsigned int pkts, unsigned int bytes) { @@ -3613,7 +3759,6 @@ static inline unsigned int get_netdev_rx_queue_index( } #endif -#define DEFAULT_MAX_NUM_RSS_QUEUES (8) int netif_get_num_default_rss_queues(void); enum skb_free_reason { @@ -3668,8 +3813,8 @@ u32 bpf_prog_run_generic_xdp(struct sk_buff *skb, struct xdp_buff *xdp, void generic_xdp_tx(struct sk_buff *skb, struct bpf_prog *xdp_prog); int do_xdp_generic(struct bpf_prog *xdp_prog, struct sk_buff *skb); int netif_rx(struct sk_buff *skb); -int netif_rx_ni(struct sk_buff *skb); -int netif_rx_any_context(struct sk_buff *skb); +int __netif_rx(struct sk_buff *skb); + int netif_receive_skb(struct sk_buff *skb); int netif_receive_skb_core(struct sk_buff *skb); void netif_receive_skb_list_internal(struct list_head *head); @@ -3677,6 +3822,7 @@ void netif_receive_skb_list(struct list_head *head); gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb); void napi_gro_flush(struct napi_struct *napi, bool flush_old); struct sk_buff *napi_get_frags(struct napi_struct *napi); +void napi_get_frags_check(struct napi_struct *napi); gro_result_t napi_gro_frags(struct napi_struct *napi); struct packet_offload *gro_find_receive_by_type(__be16 type); struct packet_offload *gro_find_complete_by_type(__be16 type); @@ -3711,7 +3857,6 @@ int dev_change_flags(struct net_device *dev, unsigned int flags, struct netlink_ext_ack *extack); void __dev_notify_flags(struct net_device *, unsigned int old_flags, unsigned int gchanges); -int dev_change_name(struct net_device *, const char *); int dev_set_alias(struct net_device *, const char *, size_t); int dev_get_alias(const struct net_device *, char *, size_t); int __dev_change_net_namespace(struct net_device *dev, struct net *net, @@ -3723,13 +3868,7 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, return __dev_change_net_namespace(dev, net, pat, 0); } int __dev_set_mtu(struct net_device *, int); -int dev_validate_mtu(struct net_device *dev, int mtu, - struct netlink_ext_ack *extack); -int dev_set_mtu_ext(struct net_device *dev, int mtu, - struct netlink_ext_ack *extack); int dev_set_mtu(struct net_device *, int); -int dev_change_tx_queue_len(struct net_device *, unsigned long); -void dev_set_group(struct net_device *, int); int dev_pre_changeaddr_notify(struct net_device *dev, const char *addr, struct netlink_ext_ack *extack); int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa, @@ -3737,24 +3876,13 @@ int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa, int dev_set_mac_address_user(struct net_device *dev, struct sockaddr *sa, struct netlink_ext_ack *extack); int dev_get_mac_address(struct sockaddr *sa, struct net *net, char *dev_name); -int dev_change_carrier(struct net_device *, bool new_carrier); -int dev_get_phys_port_id(struct net_device *dev, - struct netdev_phys_item_id *ppid); -int dev_get_phys_port_name(struct net_device *dev, - char *name, size_t len); int dev_get_port_parent_id(struct net_device *dev, struct netdev_phys_item_id *ppid, bool recurse); bool netdev_port_same_parent_id(struct net_device *a, struct net_device *b); -int dev_change_proto_down(struct net_device *dev, bool proto_down); -void dev_change_proto_down_reason(struct net_device *dev, unsigned long mask, - u32 value); struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *dev, bool *again); struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, struct netdev_queue *txq, int *ret); -typedef int (*bpf_op_t)(struct net_device *dev, struct netdev_bpf *bpf); -int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack, - int fd, int expected_fd, u32 flags); int bpf_xdp_link_attach(const union bpf_attr *attr, struct bpf_prog *prog); u8 dev_xdp_prog_count(struct net_device *dev); u32 dev_xdp_prog_id(struct net_device *dev, enum bpf_xdp_mode mode); @@ -3791,13 +3919,40 @@ static __always_inline bool __is_skb_forwardable(const struct net_device *dev, return false; } +struct net_device_core_stats __percpu *netdev_core_stats_alloc(struct net_device *dev); + +static inline struct net_device_core_stats __percpu *dev_core_stats(struct net_device *dev) +{ + /* This READ_ONCE() pairs with the write in netdev_core_stats_alloc() */ + struct net_device_core_stats __percpu *p = READ_ONCE(dev->core_stats); + + if (likely(p)) + return p; + + return netdev_core_stats_alloc(dev); +} + +#define DEV_CORE_STATS_INC(FIELD) \ +static inline void dev_core_stats_##FIELD##_inc(struct net_device *dev) \ +{ \ + struct net_device_core_stats __percpu *p; \ + \ + p = dev_core_stats(dev); \ + if (p) \ + this_cpu_inc(p->FIELD); \ +} +DEV_CORE_STATS_INC(rx_dropped) +DEV_CORE_STATS_INC(tx_dropped) +DEV_CORE_STATS_INC(rx_nohandler) +DEV_CORE_STATS_INC(rx_otherhost_dropped) + static __always_inline int ____dev_forward_skb(struct net_device *dev, struct sk_buff *skb, const bool check_mtu) { if (skb_orphan_frags(skb, GFP_ATOMIC) || unlikely(!__is_skb_forwardable(dev, skb, check_mtu))) { - atomic_long_inc(&dev->rx_dropped); + dev_core_stats_rx_dropped_inc(dev); kfree_skb(skb); return NET_RX_DROP; } @@ -3810,20 +3965,7 @@ static __always_inline int ____dev_forward_skb(struct net_device *dev, bool dev_nit_active(struct net_device *dev); void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev); -extern int netdev_budget; -extern unsigned int netdev_budget_usecs; - -/* Called by rtnetlink.c:rtnl_unlock() */ -void netdev_run_todo(void); - -/** - * dev_put - release reference to device - * @dev: network device - * - * Release reference to device to allow it to be freed. - * Try using dev_put_track() instead. - */ -static inline void dev_put(struct net_device *dev) +static inline void __dev_put(struct net_device *dev) { if (dev) { #ifdef CONFIG_PCPU_DEV_REFCNT @@ -3834,14 +3976,7 @@ static inline void dev_put(struct net_device *dev) } } -/** - * dev_hold - get reference to device - * @dev: network device - * - * Hold reference to device to keep it from being freed. - * Try using dev_hold_track() instead. - */ -static inline void dev_hold(struct net_device *dev) +static inline void __dev_hold(struct net_device *dev) { if (dev) { #ifdef CONFIG_PCPU_DEV_REFCNT @@ -3852,11 +3987,24 @@ static inline void dev_hold(struct net_device *dev) } } +static inline void __netdev_tracker_alloc(struct net_device *dev, + netdevice_tracker *tracker, + gfp_t gfp) +{ +#ifdef CONFIG_NET_DEV_REFCNT_TRACKER + ref_tracker_alloc(&dev->refcnt_tracker, tracker, gfp); +#endif +} + +/* netdev_tracker_alloc() can upgrade a prior untracked reference + * taken by dev_get_by_name()/dev_get_by_index() to a tracked one. + */ static inline void netdev_tracker_alloc(struct net_device *dev, netdevice_tracker *tracker, gfp_t gfp) { #ifdef CONFIG_NET_DEV_REFCNT_TRACKER - ref_tracker_alloc(&dev->refcnt_tracker, tracker, gfp); + refcount_dec(&dev->refcnt_tracker.no_tracker); + __netdev_tracker_alloc(dev, tracker, gfp); #endif } @@ -3868,37 +4016,61 @@ static inline void netdev_tracker_free(struct net_device *dev, #endif } -static inline void dev_hold_track(struct net_device *dev, - netdevice_tracker *tracker, gfp_t gfp) +static inline void netdev_hold(struct net_device *dev, + netdevice_tracker *tracker, gfp_t gfp) { if (dev) { - dev_hold(dev); - netdev_tracker_alloc(dev, tracker, gfp); + __dev_hold(dev); + __netdev_tracker_alloc(dev, tracker, gfp); } } -static inline void dev_put_track(struct net_device *dev, - netdevice_tracker *tracker) +static inline void netdev_put(struct net_device *dev, + netdevice_tracker *tracker) { if (dev) { netdev_tracker_free(dev, tracker); - dev_put(dev); + __dev_put(dev); } } -static inline void dev_replace_track(struct net_device *odev, - struct net_device *ndev, - netdevice_tracker *tracker, - gfp_t gfp) +/** + * dev_hold - get reference to device + * @dev: network device + * + * Hold reference to device to keep it from being freed. + * Try using netdev_hold() instead. + */ +static inline void dev_hold(struct net_device *dev) +{ + netdev_hold(dev, NULL, GFP_ATOMIC); +} + +/** + * dev_put - release reference to device + * @dev: network device + * + * Release reference to device to allow it to be freed. + * Try using netdev_put() instead. + */ +static inline void dev_put(struct net_device *dev) +{ + netdev_put(dev, NULL); +} + +static inline void netdev_ref_replace(struct net_device *odev, + struct net_device *ndev, + netdevice_tracker *tracker, + gfp_t gfp) { if (odev) netdev_tracker_free(odev, tracker); - dev_hold(ndev); - dev_put(odev); + __dev_hold(ndev); + __dev_put(odev); if (ndev) - netdev_tracker_alloc(ndev, tracker, gfp); + __netdev_tracker_alloc(ndev, tracker, gfp); } /* Carrier loss detection, dial on demand. The functions netif_carrier_on @@ -3909,10 +4081,7 @@ static inline void dev_replace_track(struct net_device *odev, * called netif_lowerlayer_*() because they represent the state of any * kind of lower layer not just hardware media. */ - -void linkwatch_init_dev(struct net_device *dev); void linkwatch_fire_event(struct net_device *dev); -void linkwatch_forget_dev(struct net_device *dev); /** * netif_carrier_ok - test if carrier present @@ -4358,9 +4527,6 @@ int dev_addr_add(struct net_device *dev, const unsigned char *addr, unsigned char addr_type); int dev_addr_del(struct net_device *dev, const unsigned char *addr, unsigned char addr_type); -void dev_addr_flush(struct net_device *dev); -int dev_addr_init(struct net_device *dev); -void dev_addr_check(struct net_device *dev); /* Functions used for unicast addresses handling */ int dev_uc_add(struct net_device *dev, const unsigned char *addr); @@ -4450,7 +4616,6 @@ static inline void __dev_mc_unsync(struct net_device *dev, /* Functions used for secondary unicast and multicast support */ void dev_set_rx_mode(struct net_device *dev); -void __dev_set_rx_mode(struct net_device *dev); int dev_set_promiscuity(struct net_device *dev, int inc); int dev_set_allmulti(struct net_device *dev, int inc); void netdev_state_change(struct net_device *dev); @@ -4468,11 +4633,6 @@ void dev_fetch_sw_netstats(struct rtnl_link_stats64 *s, void dev_get_tstats64(struct net_device *dev, struct rtnl_link_stats64 *s); extern int netdev_max_backlog; -extern int netdev_tstamp_prequeue; -extern int netdev_unregister_timeout_secs; -extern int weight_p; -extern int dev_weight_rx_bias; -extern int dev_weight_tx_bias; extern int dev_rx_weight; extern int dev_tx_weight; extern int gro_normal_batch; @@ -4497,16 +4657,6 @@ bool netdev_has_upper_dev(struct net_device *dev, struct net_device *upper_dev); struct net_device *netdev_upper_get_next_dev_rcu(struct net_device *dev, struct list_head **iter); -#ifdef CONFIG_LOCKDEP -static LIST_HEAD(net_unlink_list); - -static inline void net_unlink_todo(struct net_device *dev) -{ - if (list_empty(&dev->unlink_list)) - list_add_tail(&dev->unlink_list, &net_unlink_list); -} -#endif - /* iterate through upper list, must be called under RCU read lock */ #define netdev_for_each_upper_dev_rcu(dev, updev, iter) \ for (iter = &(dev)->adj_list.upper, \ @@ -4601,6 +4751,8 @@ int skb_csum_hwoffload_help(struct sk_buff *skb, struct sk_buff *__skb_gso_segment(struct sk_buff *skb, netdev_features_t features, bool tx_path); +struct sk_buff *skb_eth_gso_segment(struct sk_buff *skb, + netdev_features_t features, __be16 type); struct sk_buff *skb_mac_gso_segment(struct sk_buff *skb, netdev_features_t features); @@ -4668,11 +4820,17 @@ static inline void netdev_rx_csum_fault(struct net_device *dev, void net_enable_timestamp(void); void net_disable_timestamp(void); -#ifdef CONFIG_PROC_FS -int __init dev_proc_init(void); -#else -#define dev_proc_init() 0 -#endif +static inline ktime_t netdev_get_tstamp(struct net_device *dev, + const struct skb_shared_hwtstamps *hwtstamps, + bool cycles) +{ + const struct net_device_ops *ops = dev->netdev_ops; + + if (ops->ndo_get_tstamp) + return ops->ndo_get_tstamp(dev, hwtstamps, cycles); + + return hwtstamps->hwtstamp; +} static inline netdev_tx_t __netdev_start_xmit(const struct net_device_ops *ops, struct sk_buff *skb, struct net_device *dev, @@ -4709,8 +4867,6 @@ extern const struct kobj_ns_type_operations net_ns_type_operations; const char *netdev_drivername(const struct net_device *dev); -void linkwatch_run_queue(void); - static inline netdev_features_t netdev_intersect_features(netdev_features_t f1, netdev_features_t f2) { @@ -4796,26 +4952,10 @@ static inline bool netif_needs_gso(struct sk_buff *skb, (skb->ip_summed != CHECKSUM_UNNECESSARY))); } -static inline void netif_set_gso_max_size(struct net_device *dev, - unsigned int size) -{ - /* dev->gso_max_size is read locklessly from sk_setup_caps() */ - WRITE_ONCE(dev->gso_max_size, size); -} - -static inline void netif_set_gso_max_segs(struct net_device *dev, - unsigned int segs) -{ - /* dev->gso_max_segs is read locklessly from sk_setup_caps() */ - WRITE_ONCE(dev->gso_max_segs, segs); -} - -static inline void netif_set_gro_max_size(struct net_device *dev, - unsigned int size) -{ - /* This pairs with the READ_ONCE() in skb_gro_receive() */ - WRITE_ONCE(dev->gro_max_size, size); -} +void netif_set_tso_max_size(struct net_device *dev, unsigned int size); +void netif_set_tso_max_segs(struct net_device *dev, unsigned int segs); +void netif_inherit_tso_max(struct net_device *to, + const struct net_device *from); static inline void skb_gso_error_unwind(struct sk_buff *skb, __be16 protocol, int pulled_hlen, u16 mac_offset, @@ -4981,81 +5121,9 @@ static inline const char *netdev_reg_state(const struct net_device *dev) return " (unknown)"; } -__printf(3, 4) __cold -void netdev_printk(const char *level, const struct net_device *dev, - const char *format, ...); -__printf(2, 3) __cold -void netdev_emerg(const struct net_device *dev, const char *format, ...); -__printf(2, 3) __cold -void netdev_alert(const struct net_device *dev, const char *format, ...); -__printf(2, 3) __cold -void netdev_crit(const struct net_device *dev, const char *format, ...); -__printf(2, 3) __cold -void netdev_err(const struct net_device *dev, const char *format, ...); -__printf(2, 3) __cold -void netdev_warn(const struct net_device *dev, const char *format, ...); -__printf(2, 3) __cold -void netdev_notice(const struct net_device *dev, const char *format, ...); -__printf(2, 3) __cold -void netdev_info(const struct net_device *dev, const char *format, ...); - -#define netdev_level_once(level, dev, fmt, ...) \ -do { \ - static bool __section(".data.once") __print_once; \ - \ - if (!__print_once) { \ - __print_once = true; \ - netdev_printk(level, dev, fmt, ##__VA_ARGS__); \ - } \ -} while (0) - -#define netdev_emerg_once(dev, fmt, ...) \ - netdev_level_once(KERN_EMERG, dev, fmt, ##__VA_ARGS__) -#define netdev_alert_once(dev, fmt, ...) \ - netdev_level_once(KERN_ALERT, dev, fmt, ##__VA_ARGS__) -#define netdev_crit_once(dev, fmt, ...) \ - netdev_level_once(KERN_CRIT, dev, fmt, ##__VA_ARGS__) -#define netdev_err_once(dev, fmt, ...) \ - netdev_level_once(KERN_ERR, dev, fmt, ##__VA_ARGS__) -#define netdev_warn_once(dev, fmt, ...) \ - netdev_level_once(KERN_WARNING, dev, fmt, ##__VA_ARGS__) -#define netdev_notice_once(dev, fmt, ...) \ - netdev_level_once(KERN_NOTICE, dev, fmt, ##__VA_ARGS__) -#define netdev_info_once(dev, fmt, ...) \ - netdev_level_once(KERN_INFO, dev, fmt, ##__VA_ARGS__) - #define MODULE_ALIAS_NETDEV(device) \ MODULE_ALIAS("netdev-" device) -#if defined(CONFIG_DYNAMIC_DEBUG) || \ - (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE)) -#define netdev_dbg(__dev, format, args...) \ -do { \ - dynamic_netdev_dbg(__dev, format, ##args); \ -} while (0) -#elif defined(DEBUG) -#define netdev_dbg(__dev, format, args...) \ - netdev_printk(KERN_DEBUG, __dev, format, ##args) -#else -#define netdev_dbg(__dev, format, args...) \ -({ \ - if (0) \ - netdev_printk(KERN_DEBUG, __dev, format, ##args); \ -}) -#endif - -#if defined(VERBOSE_DEBUG) -#define netdev_vdbg netdev_dbg -#else - -#define netdev_vdbg(dev, format, args...) \ -({ \ - if (0) \ - netdev_printk(KERN_DEBUG, dev, format, ##args); \ - 0; \ -}) -#endif - /* * netdev_WARN() acts like dev_printk(), but with the key difference * of using a WARN/WARN_ON to get the message out, including the @@ -5069,74 +5137,6 @@ do { \ WARN_ONCE(1, "netdevice: %s%s: " format, netdev_name(dev), \ netdev_reg_state(dev), ##args) -/* netif printk helpers, similar to netdev_printk */ - -#define netif_printk(priv, type, level, dev, fmt, args...) \ -do { \ - if (netif_msg_##type(priv)) \ - netdev_printk(level, (dev), fmt, ##args); \ -} while (0) - -#define netif_level(level, priv, type, dev, fmt, args...) \ -do { \ - if (netif_msg_##type(priv)) \ - netdev_##level(dev, fmt, ##args); \ -} while (0) - -#define netif_emerg(priv, type, dev, fmt, args...) \ - netif_level(emerg, priv, type, dev, fmt, ##args) -#define netif_alert(priv, type, dev, fmt, args...) \ - netif_level(alert, priv, type, dev, fmt, ##args) -#define netif_crit(priv, type, dev, fmt, args...) \ - netif_level(crit, priv, type, dev, fmt, ##args) -#define netif_err(priv, type, dev, fmt, args...) \ - netif_level(err, priv, type, dev, fmt, ##args) -#define netif_warn(priv, type, dev, fmt, args...) \ - netif_level(warn, priv, type, dev, fmt, ##args) -#define netif_notice(priv, type, dev, fmt, args...) \ - netif_level(notice, priv, type, dev, fmt, ##args) -#define netif_info(priv, type, dev, fmt, args...) \ - netif_level(info, priv, type, dev, fmt, ##args) - -#if defined(CONFIG_DYNAMIC_DEBUG) || \ - (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE)) -#define netif_dbg(priv, type, netdev, format, args...) \ -do { \ - if (netif_msg_##type(priv)) \ - dynamic_netdev_dbg(netdev, format, ##args); \ -} while (0) -#elif defined(DEBUG) -#define netif_dbg(priv, type, dev, format, args...) \ - netif_printk(priv, type, KERN_DEBUG, dev, format, ##args) -#else -#define netif_dbg(priv, type, dev, format, args...) \ -({ \ - if (0) \ - netif_printk(priv, type, KERN_DEBUG, dev, format, ##args); \ - 0; \ -}) -#endif - -/* if @cond then downgrade to debug, else print at @level */ -#define netif_cond_dbg(priv, type, netdev, cond, level, fmt, args...) \ - do { \ - if (cond) \ - netif_dbg(priv, type, netdev, fmt, ##args); \ - else \ - netif_ ## level(priv, type, netdev, fmt, ##args); \ - } while (0) - -#if defined(VERBOSE_DEBUG) -#define netif_vdbg netif_dbg -#else -#define netif_vdbg(priv, type, dev, format, args...) \ -({ \ - if (0) \ - netif_printk(priv, type, KERN_DEBUG, dev, format, ##args); \ - 0; \ -}) -#endif - /* * The list of packet types we will receive (as opposed to discard) * and the routines to invoke. diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 15e71bfff726..d8817d381c14 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -243,11 +243,6 @@ static inline int nf_hook(u_int8_t pf, unsigned int hook, struct net *net, hook_head = rcu_dereference(net->nf.hooks_bridge[hook]); #endif break; -#if IS_ENABLED(CONFIG_DECNET) - case NFPROTO_DECNET: - hook_head = rcu_dereference(net->nf.hooks_decnet[hook]); - break; -#endif default: WARN_ON_ONCE(1); break; @@ -379,6 +374,7 @@ struct nf_nat_hook { unsigned int (*manip_pkt)(struct sk_buff *skb, struct nf_conn *ct, enum nf_nat_manip_type mtype, enum ip_conntrack_dir dir); + void (*remove_nat_bysrc)(struct nf_conn *ct); }; extern const struct nf_nat_hook __rcu *nf_nat_hook; diff --git a/include/linux/netfilter/nf_conntrack_h323.h b/include/linux/netfilter/nf_conntrack_h323.h index 4561ec0fcea4..9e937f64a1ad 100644 --- a/include/linux/netfilter/nf_conntrack_h323.h +++ b/include/linux/netfilter/nf_conntrack_h323.h @@ -38,60 +38,63 @@ void nf_conntrack_h245_expect(struct nf_conn *new, struct nf_conntrack_expect *this); void nf_conntrack_q931_expect(struct nf_conn *new, struct nf_conntrack_expect *this); -extern int (*set_h245_addr_hook) (struct sk_buff *skb, unsigned int protoff, - unsigned char **data, int dataoff, - H245_TransportAddress *taddr, - union nf_inet_addr *addr, - __be16 port); -extern int (*set_h225_addr_hook) (struct sk_buff *skb, unsigned int protoff, - unsigned char **data, int dataoff, - TransportAddress *taddr, - union nf_inet_addr *addr, - __be16 port); -extern int (*set_sig_addr_hook) (struct sk_buff *skb, - struct nf_conn *ct, - enum ip_conntrack_info ctinfo, - unsigned int protoff, unsigned char **data, - TransportAddress *taddr, int count); -extern int (*set_ras_addr_hook) (struct sk_buff *skb, - struct nf_conn *ct, - enum ip_conntrack_info ctinfo, - unsigned int protoff, unsigned char **data, - TransportAddress *taddr, int count); -extern int (*nat_rtp_rtcp_hook) (struct sk_buff *skb, - struct nf_conn *ct, - enum ip_conntrack_info ctinfo, - unsigned int protoff, unsigned char **data, - int dataoff, - H245_TransportAddress *taddr, - __be16 port, __be16 rtp_port, - struct nf_conntrack_expect *rtp_exp, - struct nf_conntrack_expect *rtcp_exp); -extern int (*nat_t120_hook) (struct sk_buff *skb, struct nf_conn *ct, - enum ip_conntrack_info ctinfo, - unsigned int protoff, + +struct nfct_h323_nat_hooks { + int (*set_h245_addr)(struct sk_buff *skb, unsigned int protoff, unsigned char **data, int dataoff, - H245_TransportAddress *taddr, __be16 port, - struct nf_conntrack_expect *exp); -extern int (*nat_h245_hook) (struct sk_buff *skb, struct nf_conn *ct, - enum ip_conntrack_info ctinfo, - unsigned int protoff, + H245_TransportAddress *taddr, + union nf_inet_addr *addr, __be16 port); + int (*set_h225_addr)(struct sk_buff *skb, unsigned int protoff, unsigned char **data, int dataoff, - TransportAddress *taddr, __be16 port, - struct nf_conntrack_expect *exp); -extern int (*nat_callforwarding_hook) (struct sk_buff *skb, - struct nf_conn *ct, - enum ip_conntrack_info ctinfo, - unsigned int protoff, - unsigned char **data, int dataoff, - TransportAddress *taddr, - __be16 port, - struct nf_conntrack_expect *exp); -extern int (*nat_q931_hook) (struct sk_buff *skb, struct nf_conn *ct, - enum ip_conntrack_info ctinfo, - unsigned int protoff, - unsigned char **data, TransportAddress *taddr, - int idx, __be16 port, - struct nf_conntrack_expect *exp); + TransportAddress *taddr, + union nf_inet_addr *addr, __be16 port); + int (*set_sig_addr)(struct sk_buff *skb, + struct nf_conn *ct, + enum ip_conntrack_info ctinfo, + unsigned int protoff, unsigned char **data, + TransportAddress *taddr, int count); + int (*set_ras_addr)(struct sk_buff *skb, + struct nf_conn *ct, + enum ip_conntrack_info ctinfo, + unsigned int protoff, unsigned char **data, + TransportAddress *taddr, int count); + int (*nat_rtp_rtcp)(struct sk_buff *skb, + struct nf_conn *ct, + enum ip_conntrack_info ctinfo, + unsigned int protoff, + unsigned char **data, int dataoff, + H245_TransportAddress *taddr, + __be16 port, __be16 rtp_port, + struct nf_conntrack_expect *rtp_exp, + struct nf_conntrack_expect *rtcp_exp); + int (*nat_t120)(struct sk_buff *skb, + struct nf_conn *ct, + enum ip_conntrack_info ctinfo, + unsigned int protoff, + unsigned char **data, int dataoff, + H245_TransportAddress *taddr, __be16 port, + struct nf_conntrack_expect *exp); + int (*nat_h245)(struct sk_buff *skb, + struct nf_conn *ct, + enum ip_conntrack_info ctinfo, + unsigned int protoff, + unsigned char **data, int dataoff, + TransportAddress *taddr, __be16 port, + struct nf_conntrack_expect *exp); + int (*nat_callforwarding)(struct sk_buff *skb, + struct nf_conn *ct, + enum ip_conntrack_info ctinfo, + unsigned int protoff, + unsigned char **data, int dataoff, + TransportAddress *taddr, __be16 port, + struct nf_conntrack_expect *exp); + int (*nat_q931)(struct sk_buff *skb, + struct nf_conn *ct, + enum ip_conntrack_info ctinfo, + unsigned int protoff, + unsigned char **data, TransportAddress *taddr, int idx, + __be16 port, struct nf_conntrack_expect *exp); +}; +extern const struct nfct_h323_nat_hooks __rcu *nfct_h323_nat_hook; #endif diff --git a/include/linux/netfilter/nf_conntrack_pptp.h b/include/linux/netfilter/nf_conntrack_pptp.h index a28aa289afdc..c3bdb4370938 100644 --- a/include/linux/netfilter/nf_conntrack_pptp.h +++ b/include/linux/netfilter/nf_conntrack_pptp.h @@ -300,26 +300,22 @@ union pptp_ctrl_union { struct PptpSetLinkInfo setlink; }; -extern int -(*nf_nat_pptp_hook_outbound)(struct sk_buff *skb, - struct nf_conn *ct, enum ip_conntrack_info ctinfo, - unsigned int protoff, - struct PptpControlHeader *ctlh, - union pptp_ctrl_union *pptpReq); - -extern int -(*nf_nat_pptp_hook_inbound)(struct sk_buff *skb, - struct nf_conn *ct, enum ip_conntrack_info ctinfo, - unsigned int protoff, - struct PptpControlHeader *ctlh, - union pptp_ctrl_union *pptpReq); - -extern void -(*nf_nat_pptp_hook_exp_gre)(struct nf_conntrack_expect *exp_orig, - struct nf_conntrack_expect *exp_reply); - -extern void -(*nf_nat_pptp_hook_expectfn)(struct nf_conn *ct, - struct nf_conntrack_expect *exp); +struct nf_nat_pptp_hook { + int (*outbound)(struct sk_buff *skb, + struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff, + struct PptpControlHeader *ctlh, + union pptp_ctrl_union *pptpReq); + int (*inbound)(struct sk_buff *skb, + struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff, + struct PptpControlHeader *ctlh, + union pptp_ctrl_union *pptpReq); + void (*exp_gre)(struct nf_conntrack_expect *exp_orig, + struct nf_conntrack_expect *exp_reply); + void (*expectfn)(struct nf_conn *ct, + struct nf_conntrack_expect *exp); +}; +extern const struct nf_nat_pptp_hook __rcu *nf_nat_pptp_hook; #endif /* _NF_CONNTRACK_PPTP_H */ diff --git a/include/linux/netfilter/nf_conntrack_sip.h b/include/linux/netfilter/nf_conntrack_sip.h index c620521c42bc..dbc614dfe0d5 100644 --- a/include/linux/netfilter/nf_conntrack_sip.h +++ b/include/linux/netfilter/nf_conntrack_sip.h @@ -164,7 +164,7 @@ struct nf_nat_sip_hooks { unsigned int medialen, union nf_inet_addr *rtp_addr); }; -extern const struct nf_nat_sip_hooks *nf_nat_sip_hooks; +extern const struct nf_nat_sip_hooks __rcu *nf_nat_sip_hooks; int ct_sip_parse_request(const struct nf_conn *ct, const char *dptr, unsigned int datalen, unsigned int *matchoff, diff --git a/include/linux/netfilter_bridge/ebtables.h b/include/linux/netfilter_bridge/ebtables.h index a13296d6c7ce..fd533552a062 100644 --- a/include/linux/netfilter_bridge/ebtables.h +++ b/include/linux/netfilter_bridge/ebtables.h @@ -94,10 +94,6 @@ struct ebt_table { struct ebt_replace_kernel *table; unsigned int valid_hooks; rwlock_t lock; - /* e.g. could be the table explicitly only allows certain - * matches, targets, ... 0 == let it in */ - int (*check)(const struct ebt_table_info *info, - unsigned int valid_hooks); /* the data used by the kernel */ struct ebt_table_info *private; struct nf_hook_ops *ops; diff --git a/include/linux/netfilter_defs.h b/include/linux/netfilter_defs.h index 8dddfb151f00..a5f7bef1b3a4 100644 --- a/include/linux/netfilter_defs.h +++ b/include/linux/netfilter_defs.h @@ -7,14 +7,6 @@ /* in/out/forward only */ #define NF_ARP_NUMHOOKS 3 -/* max hook is NF_DN_ROUTE (6), also see uapi/linux/netfilter_decnet.h */ -#define NF_DN_NUMHOOKS 7 - -#if IS_ENABLED(CONFIG_DECNET) -/* Largest hook number + 1, see uapi/linux/netfilter_decnet.h */ -#define NF_MAX_HOOKS NF_DN_NUMHOOKS -#else #define NF_MAX_HOOKS NF_INET_NUMHOOKS -#endif #endif diff --git a/include/linux/netfilter_netdev.h b/include/linux/netfilter_netdev.h index b4dd96e4dc8d..8676316547cc 100644 --- a/include/linux/netfilter_netdev.h +++ b/include/linux/netfilter_netdev.h @@ -99,9 +99,13 @@ static inline struct sk_buff *nf_hook_egress(struct sk_buff *skb, int *rc, return skb; nf_hook_state_init(&state, NF_NETDEV_EGRESS, - NFPROTO_NETDEV, dev, NULL, NULL, + NFPROTO_NETDEV, NULL, dev, NULL, dev_net(dev), NULL); + + /* nf assumes rcu_read_lock, not just read_lock_bh */ + rcu_read_lock(); ret = nf_hook_slow(skb, &state, e, 0); + rcu_read_unlock(); if (ret == 1) { return skb; diff --git a/include/linux/netfs.h b/include/linux/netfs.h index ca0683b9e3d1..f2402ddeafbf 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -18,6 +18,8 @@ #include <linux/fs.h> #include <linux/pagemap.h> +enum netfs_sreq_ref_trace; + /* * Overload PG_private_2 to give us PG_fscache - this is used to indicate that * a page is currently backed by a local disk cache @@ -106,7 +108,7 @@ static inline int wait_on_page_fscache_killable(struct page *page) return folio_wait_private_2_killable(page_folio(page)); } -enum netfs_read_source { +enum netfs_io_source { NETFS_FILL_WITH_ZEROES, NETFS_DOWNLOAD_FROM_SERVER, NETFS_READ_FROM_CACHE, @@ -117,6 +119,18 @@ typedef void (*netfs_io_terminated_t)(void *priv, ssize_t transferred_or_error, bool was_async); /* + * Per-inode context. This wraps the VFS inode. + */ +struct netfs_inode { + struct inode inode; /* The VFS inode */ + const struct netfs_request_ops *ops; +#if IS_ENABLED(CONFIG_FSCACHE) + struct fscache_cookie *cache; +#endif + loff_t remote_i_size; /* Size of the remote file */ +}; + +/* * Resources required to do operations on a cache. */ struct netfs_cache_resources { @@ -124,75 +138,93 @@ struct netfs_cache_resources { void *cache_priv; void *cache_priv2; unsigned int debug_id; /* Cookie debug ID */ + unsigned int inval_counter; /* object->inval_counter at begin_op */ }; /* * Descriptor for a single component subrequest. */ -struct netfs_read_subrequest { - struct netfs_read_request *rreq; /* Supervising read request */ +struct netfs_io_subrequest { + struct netfs_io_request *rreq; /* Supervising I/O request */ struct list_head rreq_link; /* Link in rreq->subrequests */ loff_t start; /* Where to start the I/O */ size_t len; /* Size of the I/O */ size_t transferred; /* Amount of data transferred */ - refcount_t usage; + refcount_t ref; short error; /* 0 or error that occurred */ unsigned short debug_index; /* Index in list (for debugging output) */ - enum netfs_read_source source; /* Where to read from */ + enum netfs_io_source source; /* Where to read from/write to */ unsigned long flags; -#define NETFS_SREQ_WRITE_TO_CACHE 0 /* Set if should write to cache */ +#define NETFS_SREQ_COPY_TO_CACHE 0 /* Set if should copy the data to the cache */ #define NETFS_SREQ_CLEAR_TAIL 1 /* Set if the rest of the read should be cleared */ -#define NETFS_SREQ_SHORT_READ 2 /* Set if there was a short read from the cache */ +#define NETFS_SREQ_SHORT_IO 2 /* Set if the I/O was short */ #define NETFS_SREQ_SEEK_DATA_READ 3 /* Set if ->read() should SEEK_DATA first */ #define NETFS_SREQ_NO_PROGRESS 4 /* Set if we didn't manage to read any data */ +#define NETFS_SREQ_ONDEMAND 5 /* Set if it's from on-demand read mode */ }; +enum netfs_io_origin { + NETFS_READAHEAD, /* This read was triggered by readahead */ + NETFS_READPAGE, /* This read is a synchronous read */ + NETFS_READ_FOR_WRITE, /* This read is to prepare a write */ +} __mode(byte); + /* - * Descriptor for a read helper request. This is used to make multiple I/O - * requests on a variety of sources and then stitch the result together. + * Descriptor for an I/O helper request. This is used to make multiple I/O + * operations to a variety of data stores and then stitch the result together. */ -struct netfs_read_request { +struct netfs_io_request { struct work_struct work; struct inode *inode; /* The file being accessed */ struct address_space *mapping; /* The mapping being accessed */ struct netfs_cache_resources cache_resources; - struct list_head subrequests; /* Requests to fetch I/O from disk or net */ + struct list_head subrequests; /* Contributory I/O operations */ void *netfs_priv; /* Private data for the netfs */ unsigned int debug_id; - atomic_t nr_rd_ops; /* Number of read ops in progress */ - atomic_t nr_wr_ops; /* Number of write ops in progress */ + atomic_t nr_outstanding; /* Number of ops in progress */ + atomic_t nr_copy_ops; /* Number of copy-to-cache ops in progress */ size_t submitted; /* Amount submitted for I/O so far */ size_t len; /* Length of the request */ short error; /* 0 or error that occurred */ + enum netfs_io_origin origin; /* Origin of the request */ loff_t i_size; /* Size of the file */ loff_t start; /* Start position */ pgoff_t no_unlock_folio; /* Don't unlock this folio after read */ - refcount_t usage; + refcount_t ref; unsigned long flags; #define NETFS_RREQ_INCOMPLETE_IO 0 /* Some ioreqs terminated short or with error */ -#define NETFS_RREQ_WRITE_TO_CACHE 1 /* Need to write to the cache */ +#define NETFS_RREQ_COPY_TO_CACHE 1 /* Need to write to the cache */ #define NETFS_RREQ_NO_UNLOCK_FOLIO 2 /* Don't unlock no_unlock_folio on completion */ #define NETFS_RREQ_DONT_UNLOCK_FOLIOS 3 /* Don't unlock the folios on completion */ #define NETFS_RREQ_FAILED 4 /* The request failed */ #define NETFS_RREQ_IN_PROGRESS 5 /* Unlocked when the request completes */ - const struct netfs_read_request_ops *netfs_ops; + const struct netfs_request_ops *netfs_ops; }; /* * Operations the network filesystem can/must provide to the helpers. */ -struct netfs_read_request_ops { - bool (*is_cache_enabled)(struct inode *inode); - void (*init_rreq)(struct netfs_read_request *rreq, struct file *file); - int (*begin_cache_operation)(struct netfs_read_request *rreq); - void (*expand_readahead)(struct netfs_read_request *rreq); - bool (*clamp_length)(struct netfs_read_subrequest *subreq); - void (*issue_op)(struct netfs_read_subrequest *subreq); - bool (*is_still_valid)(struct netfs_read_request *rreq); +struct netfs_request_ops { + int (*init_request)(struct netfs_io_request *rreq, struct file *file); + void (*free_request)(struct netfs_io_request *rreq); + int (*begin_cache_operation)(struct netfs_io_request *rreq); + + void (*expand_readahead)(struct netfs_io_request *rreq); + bool (*clamp_length)(struct netfs_io_subrequest *subreq); + void (*issue_read)(struct netfs_io_subrequest *subreq); + bool (*is_still_valid)(struct netfs_io_request *rreq); int (*check_write_begin)(struct file *file, loff_t pos, unsigned len, - struct folio *folio, void **_fsdata); - void (*done)(struct netfs_read_request *rreq); - void (*cleanup)(struct address_space *mapping, void *netfs_priv); + struct folio **foliop, void **_fsdata); + void (*done)(struct netfs_io_request *rreq); +}; + +/* + * How to handle reading from a hole. + */ +enum netfs_read_from_hole { + NETFS_READ_HOLE_IGNORE, + NETFS_READ_HOLE_CLEAR, + NETFS_READ_HOLE_FAIL, }; /* @@ -207,7 +239,7 @@ struct netfs_cache_ops { int (*read)(struct netfs_cache_resources *cres, loff_t start_pos, struct iov_iter *iter, - bool seek_data, + enum netfs_read_from_hole read_hole, netfs_io_terminated_t term_func, void *term_func_priv); @@ -225,31 +257,93 @@ struct netfs_cache_ops { /* Prepare a read operation, shortening it to a cached/uncached * boundary as appropriate. */ - enum netfs_read_source (*prepare_read)(struct netfs_read_subrequest *subreq, - loff_t i_size); + enum netfs_io_source (*prepare_read)(struct netfs_io_subrequest *subreq, + loff_t i_size); /* Prepare a write operation, working out what part of the write we can * actually do. */ int (*prepare_write)(struct netfs_cache_resources *cres, - loff_t *_start, size_t *_len, loff_t i_size); + loff_t *_start, size_t *_len, loff_t i_size, + bool no_space_allocated_yet); + + /* Query the occupancy of the cache in a region, returning where the + * next chunk of data starts and how long it is. + */ + int (*query_occupancy)(struct netfs_cache_resources *cres, + loff_t start, size_t len, size_t granularity, + loff_t *_data_start, size_t *_data_len); }; struct readahead_control; -extern void netfs_readahead(struct readahead_control *, - const struct netfs_read_request_ops *, - void *); -extern int netfs_readpage(struct file *, - struct folio *, - const struct netfs_read_request_ops *, - void *); -extern int netfs_write_begin(struct file *, struct address_space *, - loff_t, unsigned int, unsigned int, struct folio **, - void **, - const struct netfs_read_request_ops *, - void *); - -extern void netfs_subreq_terminated(struct netfs_read_subrequest *, ssize_t, bool); -extern void netfs_stats_show(struct seq_file *); +void netfs_readahead(struct readahead_control *); +int netfs_read_folio(struct file *, struct folio *); +int netfs_write_begin(struct netfs_inode *, struct file *, + struct address_space *, loff_t pos, unsigned int len, + struct folio **, void **fsdata); + +void netfs_subreq_terminated(struct netfs_io_subrequest *, ssize_t, bool); +void netfs_get_subrequest(struct netfs_io_subrequest *subreq, + enum netfs_sreq_ref_trace what); +void netfs_put_subrequest(struct netfs_io_subrequest *subreq, + bool was_async, enum netfs_sreq_ref_trace what); +void netfs_stats_show(struct seq_file *); + +/** + * netfs_inode - Get the netfs inode context from the inode + * @inode: The inode to query + * + * Get the netfs lib inode context from the network filesystem's inode. The + * context struct is expected to directly follow on from the VFS inode struct. + */ +static inline struct netfs_inode *netfs_inode(struct inode *inode) +{ + return container_of(inode, struct netfs_inode, inode); +} + +/** + * netfs_inode_init - Initialise a netfslib inode context + * @ctx: The netfs inode to initialise + * @ops: The netfs's operations list + * + * Initialise the netfs library context struct. This is expected to follow on + * directly from the VFS inode struct. + */ +static inline void netfs_inode_init(struct netfs_inode *ctx, + const struct netfs_request_ops *ops) +{ + ctx->ops = ops; + ctx->remote_i_size = i_size_read(&ctx->inode); +#if IS_ENABLED(CONFIG_FSCACHE) + ctx->cache = NULL; +#endif +} + +/** + * netfs_resize_file - Note that a file got resized + * @ctx: The netfs inode being resized + * @new_i_size: The new file size + * + * Inform the netfs lib that a file got resized so that it can adjust its state. + */ +static inline void netfs_resize_file(struct netfs_inode *ctx, loff_t new_i_size) +{ + ctx->remote_i_size = new_i_size; +} + +/** + * netfs_i_cookie - Get the cache cookie from the inode + * @ctx: The netfs inode to query + * + * Get the caching cookie (if enabled) from the network filesystem's inode. + */ +static inline struct fscache_cookie *netfs_i_cookie(struct netfs_inode *ctx) +{ +#if IS_ENABLED(CONFIG_FSCACHE) + return ctx->cache; +#else + return NULL; +#endif +} #endif /* _LINUX_NETFS_H */ diff --git a/include/linux/netlink.h b/include/linux/netlink.h index 1ec631838af9..d51e041d2242 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -71,6 +71,8 @@ netlink_kernel_create(struct net *net, int unit, struct netlink_kernel_cfg *cfg) * %NL_SET_ERR_MSG * @bad_attr: attribute with error * @policy: policy for a bad attribute + * @miss_type: attribute type which was missing + * @miss_nest: nest missing an attribute (%NULL if missing top level attr) * @cookie: cookie data to return to userspace (for success) * @cookie_len: actual cookie data length */ @@ -78,6 +80,8 @@ struct netlink_ext_ack { const char *_msg; const struct nlattr *bad_attr; const struct nla_policy *policy; + const struct nlattr *miss_nest; + u16 miss_type; u8 cookie[NETLINK_MAX_COOKIE_LEN]; u8 cookie_len; }; @@ -126,6 +130,26 @@ struct netlink_ext_ack { #define NL_SET_ERR_MSG_ATTR(extack, attr, msg) \ NL_SET_ERR_MSG_ATTR_POL(extack, attr, NULL, msg) +#define NL_SET_ERR_ATTR_MISS(extack, nest, type) do { \ + struct netlink_ext_ack *__extack = (extack); \ + \ + if (__extack) { \ + __extack->miss_nest = (nest); \ + __extack->miss_type = (type); \ + } \ +} while (0) + +#define NL_REQ_ATTR_CHECK(extack, nest, tb, type) ({ \ + struct nlattr **__tb = (tb); \ + u32 __attr = (type); \ + int __retval; \ + \ + __retval = !__tb[__attr]; \ + if (__retval) \ + NL_SET_ERR_ATTR_MISS((extack), (nest), __attr); \ + __retval; \ +}) + static inline void nl_set_extack_cookie_u64(struct netlink_ext_ack *extack, u64 cookie) { @@ -135,15 +159,6 @@ static inline void nl_set_extack_cookie_u64(struct netlink_ext_ack *extack, extack->cookie_len = sizeof(cookie); } -static inline void nl_set_extack_cookie_u32(struct netlink_ext_ack *extack, - u32 cookie) -{ - if (!extack) - return; - memcpy(extack->cookie, &cookie, sizeof(cookie)); - extack->cookie_len = sizeof(cookie); -} - void netlink_kernel_release(struct sock *sk); int __netlink_change_ngroups(struct sock *sk, unsigned int groups); int netlink_change_ngroups(struct sock *sk, unsigned int groups); diff --git a/include/linux/nfs.h b/include/linux/nfs.h index 0dc7ad38a0da..b06375e88e58 100644 --- a/include/linux/nfs.h +++ b/include/linux/nfs.h @@ -36,14 +36,6 @@ static inline void nfs_copy_fh(struct nfs_fh *target, const struct nfs_fh *sourc memcpy(target->data, source->data, source->size); } - -/* - * This is really a general kernel constant, but since nothing like - * this is defined in the kernel headers, I have to do it here. - */ -#define NFS_OFFSET_MAX ((__s64)((~(__u64)0) >> 1)) - - enum nfs3_stable_how { NFS_UNSTABLE = 0, NFS_DATA_SYNC = 1, diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index 5662d8be04eb..8d04b6a5964c 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -451,6 +451,8 @@ enum lock_type4 { #define FATTR4_WORD1_TIME_MODIFY (1UL << 21) #define FATTR4_WORD1_TIME_MODIFY_SET (1UL << 22) #define FATTR4_WORD1_MOUNTED_ON_FILEID (1UL << 23) +#define FATTR4_WORD1_DACL (1UL << 26) +#define FATTR4_WORD1_SACL (1UL << 27) #define FATTR4_WORD1_FS_LAYOUT_TYPES (1UL << 30) #define FATTR4_WORD2_LAYOUT_TYPES (1UL << 0) #define FATTR4_WORD2_LAYOUT_BLKSIZE (1UL << 1) diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 05f249f20f55..7931fa472561 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -46,11 +46,6 @@ #define NFS_MAX_TRANSPORTS 16 /* - * These are the default flags for swap requests - */ -#define NFS_RPC_SWAPFLAGS (RPC_TASK_SWAPPER|RPC_TASK_ROOTCREDS) - -/* * Size of the NFS directory verifier */ #define NFS_DIR_VERIFIER_SIZE 2 @@ -61,7 +56,9 @@ struct nfs_access_entry { struct rb_node rb_node; struct list_head lru; - const struct cred * cred; + kuid_t fsuid; + kgid_t fsgid; + struct group_info *group_info; __u32 mask; struct rcu_head rcu_head; }; @@ -86,7 +83,6 @@ struct nfs_open_context { fmode_t mode; unsigned long flags; -#define NFS_CONTEXT_RESEND_WRITES (1) #define NFS_CONTEXT_BAD (2) #define NFS_CONTEXT_UNLOCK (3) #define NFS_CONTEXT_FILE_OPEN (4) @@ -99,12 +95,17 @@ struct nfs_open_context { struct nfs_open_dir_context { struct list_head list; + atomic_t cache_hits; + atomic_t cache_misses; unsigned long attr_gencount; __be32 verf[NFS_DIR_VERIFIER_SIZE]; __u64 dir_cookie; - __u64 dup_cookie; + __u64 last_cookie; pgoff_t page_index; - signed char duped; + unsigned int dtsize; + bool force_clear; + bool eof; + struct rcu_head rcu_head; }; /* @@ -180,6 +181,7 @@ struct nfs_inode { /* Regular file */ struct { atomic_long_t nrequests; + atomic_long_t redirtied_pages; struct nfs_mds_commit_info commit_info; struct mutex commit_mutex; }; @@ -244,7 +246,6 @@ struct nfs4_copy_state { #define NFS_INO_INVALID_ATIME BIT(2) /* cached atime is invalid */ #define NFS_INO_INVALID_ACCESS BIT(3) /* cached access cred invalid */ #define NFS_INO_INVALID_ACL BIT(4) /* cached acls are invalid */ -#define NFS_INO_REVAL_PAGECACHE BIT(5) /* must revalidate pagecache */ #define NFS_INO_REVAL_FORCED BIT(6) /* force revalidation ignoring a delegation */ #define NFS_INO_INVALID_LABEL BIT(7) /* cached label is invalid */ #define NFS_INO_INVALID_CHANGE BIT(8) /* cached change is invalid */ @@ -270,13 +271,11 @@ struct nfs4_copy_state { /* * Bit offsets in flags field */ -#define NFS_INO_ADVISE_RDPLUS (0) /* advise readdirplus */ #define NFS_INO_STALE (1) /* possible stale inode */ #define NFS_INO_ACL_LRU_SET (2) /* Inode is on the LRU list */ #define NFS_INO_INVALIDATING (3) /* inode is being invalidated */ +#define NFS_INO_PRESERVE_UNLINKED (4) /* preserve file if removed while open */ #define NFS_INO_FSCACHE (5) /* inode can be cached by FS-Cache */ -#define NFS_INO_FSCACHE_LOCK (6) /* FS-Cache cookie management lock */ -#define NFS_INO_FORCE_READDIR (7) /* force readdirplus */ #define NFS_INO_LAYOUTCOMMIT (9) /* layoutcommit required */ #define NFS_INO_LAYOUTCOMMITTING (10) /* layoutcommit inflight */ #define NFS_INO_LAYOUTSTATS (11) /* layoutstats inflight */ @@ -353,17 +352,15 @@ static inline void nfs_mark_for_revalidate(struct inode *inode) struct nfs_inode *nfsi = NFS_I(inode); spin_lock(&inode->i_lock); - nfsi->cache_validity |= NFS_INO_REVAL_PAGECACHE - | NFS_INO_INVALID_ACCESS - | NFS_INO_INVALID_ACL - | NFS_INO_INVALID_CHANGE - | NFS_INO_INVALID_CTIME; + nfsi->cache_validity |= NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL | + NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_CTIME | + NFS_INO_INVALID_SIZE; if (S_ISDIR(inode->i_mode)) nfsi->cache_validity |= NFS_INO_INVALID_DATA; spin_unlock(&inode->i_lock); } -static inline int nfs_server_capable(struct inode *inode, int cap) +static inline int nfs_server_capable(const struct inode *inode, int cap) { return NFS_SERVER(inode)->caps & cap; } @@ -396,7 +393,7 @@ extern int nfs_post_op_update_inode_force_wcc(struct inode *inode, struct nfs_fa extern int nfs_post_op_update_inode_force_wcc_locked(struct inode *inode, struct nfs_fattr *fattr); extern int nfs_getattr(struct user_namespace *, const struct path *, struct kstat *, u32, unsigned int); -extern void nfs_access_add_cache(struct inode *, struct nfs_access_entry *); +extern void nfs_access_add_cache(struct inode *, struct nfs_access_entry *, const struct cred *); extern void nfs_access_set_mask(struct nfs_access_entry *, u32); extern int nfs_permission(struct user_namespace *, struct inode *, int); extern int nfs_open(struct inode *, struct file *); @@ -510,11 +507,11 @@ static inline const struct cred *nfs_file_cred(struct file *file) /* * linux/fs/nfs/direct.c */ -extern ssize_t nfs_direct_IO(struct kiocb *, struct iov_iter *); -extern ssize_t nfs_file_direct_read(struct kiocb *iocb, - struct iov_iter *iter); -extern ssize_t nfs_file_direct_write(struct kiocb *iocb, - struct iov_iter *iter); +int nfs_swap_rw(struct kiocb *iocb, struct iov_iter *iter); +ssize_t nfs_file_direct_read(struct kiocb *iocb, + struct iov_iter *iter, bool swap); +ssize_t nfs_file_direct_write(struct kiocb *iocb, + struct iov_iter *iter, bool swap); /* * linux/fs/nfs/dir.c @@ -533,8 +530,8 @@ extern int nfs_instantiate(struct dentry *dentry, struct nfs_fh *fh, struct nfs_fattr *fattr); extern int nfs_may_open(struct inode *inode, const struct cred *cred, int openflags); extern void nfs_access_zap_cache(struct inode *inode); -extern int nfs_access_get_cached(struct inode *inode, const struct cred *cred, struct nfs_access_entry *res, - bool may_block); +extern int nfs_access_get_cached(struct inode *inode, const struct cred *cred, + u32 *mask, bool may_block); /* * linux/fs/nfs/symlink.c @@ -581,26 +578,24 @@ extern int nfs_updatepage(struct file *, struct page *, unsigned int, unsigned extern int nfs_sync_inode(struct inode *inode); extern int nfs_wb_all(struct inode *inode); extern int nfs_wb_page(struct inode *inode, struct page *page); -extern int nfs_wb_page_cancel(struct inode *inode, struct page* page); +int nfs_wb_folio_cancel(struct inode *inode, struct folio *folio); extern int nfs_commit_inode(struct inode *, int); -extern struct nfs_commit_data *nfs_commitdata_alloc(bool never_fail); +extern struct nfs_commit_data *nfs_commitdata_alloc(void); extern void nfs_commit_free(struct nfs_commit_data *data); bool nfs_commit_end(struct nfs_mds_commit_info *cinfo); -static inline int -nfs_have_writebacks(struct inode *inode) +static inline bool nfs_have_writebacks(const struct inode *inode) { if (S_ISREG(inode->i_mode)) return atomic_long_read(&NFS_I(inode)->nrequests) != 0; - return 0; + return false; } /* * linux/fs/nfs/read.c */ -extern int nfs_readpage(struct file *, struct page *); -extern int nfs_readpages(struct file *, struct address_space *, - struct list_head *, unsigned); +int nfs_read_folio(struct file *, struct folio *); +void nfs_readahead(struct readahead_control *); /* * inline functions @@ -622,6 +617,15 @@ nfs_fileid_to_ino_t(u64 fileid) #define NFS_JUKEBOX_RETRY_TIME (5 * HZ) +/* We need to block new opens while a file is being unlinked. + * If it is opened *before* we decide to unlink, we will silly-rename + * instead. If it is opened *after*, then we need to create or will fail. + * If we allow the two to race, we could end up with a file that is open + * but deleted on the server resulting in ESTALE. + * So use ->d_fsdata to record when the unlink is happening + * and block dentry revalidation while it is set. + */ +#define NFS_FSDATA_BLOCKED ((void*)1) # undef ifdebug # ifdef NFS_DEBUG diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 2a9acbfe00f0..ea2f7e6b1b0b 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -120,11 +120,6 @@ struct nfs_client { * This is used to generate the mv0 callback address. */ char cl_ipaddr[48]; - -#ifdef CONFIG_NFS_FSCACHE - struct fscache_cookie *fscache; /* client index cache cookie */ -#endif - struct net *cl_net; struct list_head pending_cb_stateids; }; @@ -143,6 +138,7 @@ struct nfs_server { struct nlm_host *nlm_host; /* NLM client handle */ struct nfs_iostats __percpu *io_stats; /* I/O statistics */ atomic_long_t writeback; /* number of writeback pages */ + unsigned int write_congested;/* flag set when writeback gets too high */ unsigned int flags; /* various flags */ /* The following are for internal use only. Also see uapi/linux/nfs_mount.h */ @@ -156,6 +152,7 @@ struct nfs_server { #define NFS_MOUNT_SOFTREVAL 0x800000 #define NFS_MOUNT_WRITE_EAGER 0x01000000 #define NFS_MOUNT_WRITE_WAIT 0x02000000 +#define NFS_MOUNT_TRUNK_DISCOVERY 0x04000000 unsigned int fattr_valid; /* Valid attributes */ unsigned int caps; /* server capabilities */ @@ -194,8 +191,8 @@ struct nfs_server { struct nfs_auth_info auth_info; /* parsed auth flavors */ #ifdef CONFIG_NFS_FSCACHE - struct nfs_fscache_key *fscache_key; /* unique key for superblock */ - struct fscache_cookie *fscache; /* superblock cookie */ + struct fscache_volume *fscache; /* superblock cookie */ + char *fscache_uniq; /* Uniquifier (or NULL) */ #endif u32 pnfs_blksize; /* layout_blksize attr */ @@ -271,6 +268,8 @@ struct nfs_server { #define NFS_CAP_ACLS (1U << 3) #define NFS_CAP_ATOMIC_OPEN (1U << 4) #define NFS_CAP_LGOPEN (1U << 5) +#define NFS_CAP_CASE_INSENSITIVE (1U << 6) +#define NFS_CAP_CASE_PRESERVING (1U << 7) #define NFS_CAP_POSIX_LOCK (1U << 14) #define NFS_CAP_UIDGID_NOMAP (1U << 15) #define NFS_CAP_STATEID_NFSV41 (1U << 16) @@ -287,5 +286,6 @@ struct nfs_server { #define NFS_CAP_COPY_NOTIFY (1U << 27) #define NFS_CAP_XATTR (1U << 28) #define NFS_CAP_READ_PLUS (1U << 29) - +#define NFS_CAP_FS_LOCATIONS (1U << 30) +#define NFS_CAP_MOVEABLE (1U << 31) #endif diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index f0373a6cb5fb..ba7e2e4b0926 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -202,8 +202,7 @@ nfs_list_entry(struct list_head *head) return list_entry(head, struct nfs_page, wb_list); } -static inline -loff_t req_offset(struct nfs_page *req) +static inline loff_t req_offset(const struct nfs_page *req) { return (((loff_t)req->wb_index) << PAGE_SHIFT) + req->wb_offset; } diff --git a/include/linux/nfs_ssc.h b/include/linux/nfs_ssc.h index 222ae8883e85..75843c00f326 100644 --- a/include/linux/nfs_ssc.h +++ b/include/linux/nfs_ssc.h @@ -64,7 +64,7 @@ struct nfsd4_ssc_umount_item { refcount_t nsui_refcnt; unsigned long nsui_expire; struct vfsmount *nsui_vfsmount; - char nsui_ipaddr[RPC_MAX_ADDRBUFLEN]; + char nsui_ipaddr[RPC_MAX_ADDRBUFLEN + 1]; }; #endif diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 967a0098f0a9..e86cf6642d21 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -745,8 +745,7 @@ struct nfs_auth_info { */ struct nfs_entry { __u64 ino; - __u64 cookie, - prev_cookie; + __u64 cookie; const char * name; unsigned int len; int eof; @@ -801,9 +800,17 @@ struct nfs_setattrargs { const struct nfs4_label *label; }; +enum nfs4_acl_type { + NFS4ACL_NONE = 0, + NFS4ACL_ACL, + NFS4ACL_DACL, + NFS4ACL_SACL, +}; + struct nfs_setaclargs { struct nfs4_sequence_args seq_args; struct nfs_fh * fh; + enum nfs4_acl_type acl_type; size_t acl_len; struct page ** acl_pages; }; @@ -815,6 +822,7 @@ struct nfs_setaclres { struct nfs_getaclargs { struct nfs4_sequence_args seq_args; struct nfs_fh * fh; + enum nfs4_acl_type acl_type; size_t acl_len; struct page ** acl_pages; }; @@ -823,6 +831,7 @@ struct nfs_getaclargs { #define NFS4_ACL_TRUNC 0x0001 /* ACL was truncated */ struct nfs_getaclres { struct nfs4_sequence_res seq_res; + enum nfs4_acl_type acl_type; size_t acl_len; size_t acl_data_offset; int acl_flags; @@ -1194,6 +1203,8 @@ struct nfs4_server_caps_res { u32 has_links; u32 has_symlinks; u32 fh_expire_type; + u32 case_insensitive; + u32 case_preserving; }; #define NFS4_PATHNAME_MAXCOMPONENTS 512 @@ -1211,7 +1222,7 @@ struct nfs4_fs_location { #define NFS4_FS_LOCATIONS_MAXENTRIES 10 struct nfs4_fs_locations { - struct nfs_fattr fattr; + struct nfs_fattr *fattr; const struct nfs_server *server; struct nfs4_pathname fs_path; int nlocations; @@ -1589,6 +1600,7 @@ enum { NFS_IOHDR_STAT, NFS_IOHDR_RESEND_PNFS, NFS_IOHDR_RESEND_MDS, + NFS_IOHDR_UNSTABLE_WRITES, }; struct nfs_io_completion; @@ -1693,6 +1705,7 @@ struct nfs_unlinkdata { struct nfs_renamedata { struct nfs_renameargs args; struct nfs_renameres res; + struct rpc_task task; const struct cred *cred; struct inode *old_dir; struct dentry *old_dentry; @@ -1737,7 +1750,7 @@ struct nfs_rpc_ops { struct nfs_fh *, struct nfs_fattr *); int (*lookupp) (struct inode *, struct nfs_fh *, struct nfs_fattr *); - int (*access) (struct inode *, struct nfs_access_entry *); + int (*access) (struct inode *, struct nfs_access_entry *, const struct cred *); int (*readlink)(struct inode *, struct page *, unsigned int, unsigned int); int (*create) (struct inode *, struct dentry *, @@ -1795,6 +1808,9 @@ struct nfs_rpc_ops { struct nfs_server *(*create_server)(struct fs_context *); struct nfs_server *(*clone_server)(struct nfs_server *, struct nfs_fh *, struct nfs_fattr *, rpc_authflavor_t); + int (*discover_trunking)(struct nfs_server *, struct nfs_fh *); + void (*enable_swap)(struct inode *inode); + void (*disable_swap)(struct inode *inode); }; /* diff --git a/include/linux/nl802154.h b/include/linux/nl802154.h index b22782225f27..cbe5fd1dd2e7 100644 --- a/include/linux/nl802154.h +++ b/include/linux/nl802154.h @@ -8,6 +8,8 @@ #ifndef NL802154_H #define NL802154_H +#include <net/netlink.h> + #define IEEE802154_NL_NAME "802.15.4 MAC" #define IEEE802154_MCAST_COORD_NAME "coordinator" #define IEEE802154_MCAST_BEACON_NAME "beacon" diff --git a/include/linux/nmi.h b/include/linux/nmi.h index 750c7f395ca9..f700ff2df074 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -122,6 +122,8 @@ int watchdog_nmi_probe(void); int watchdog_nmi_enable(unsigned int cpu); void watchdog_nmi_disable(unsigned int cpu); +void lockup_detector_reconfigure(void); + /** * touch_nmi_watchdog - restart NMI watchdog timeout. * diff --git a/include/linux/node.h b/include/linux/node.h index bb21fd631b16..427a5975cf40 100644 --- a/include/linux/node.h +++ b/include/linux/node.h @@ -2,15 +2,15 @@ /* * include/linux/node.h - generic node definition * - * This is mainly for topological representation. We define the - * basic 'struct node' here, which can be embedded in per-arch + * This is mainly for topological representation. We define the + * basic 'struct node' here, which can be embedded in per-arch * definitions of processors. * * Basic handling of the devices is done in drivers/base/node.c - * and system devices are handled in drivers/base/sys.c. + * and system devices are handled in drivers/base/sys.c. * * Nodes are exported via driverfs in the class/node/devices/ - * directory. + * directory. */ #ifndef _LINUX_NODE_H_ #define _LINUX_NODE_H_ @@ -18,7 +18,6 @@ #include <linux/device.h> #include <linux/cpumask.h> #include <linux/list.h> -#include <linux/workqueue.h> /** * struct node_hmem_attrs - heterogeneous memory performance attributes @@ -84,10 +83,6 @@ static inline void node_set_perf_attrs(unsigned int nid, struct node { struct device dev; struct list_head access_list; - -#if defined(CONFIG_MEMORY_HOTPLUG) && defined(CONFIG_HUGETLBFS) - struct work_struct node_work; -#endif #ifdef CONFIG_HMEM_REPORTING struct list_head cache_attrs; struct device *cache_dev; @@ -96,22 +91,22 @@ struct node { struct memory_block; extern struct node *node_devices[]; -typedef void (*node_registration_func_t)(struct node *); #if defined(CONFIG_MEMORY_HOTPLUG) && defined(CONFIG_NUMA) -void link_mem_sections(int nid, unsigned long start_pfn, - unsigned long end_pfn, - enum meminit_context context); +void register_memory_blocks_under_node(int nid, unsigned long start_pfn, + unsigned long end_pfn, + enum meminit_context context); #else -static inline void link_mem_sections(int nid, unsigned long start_pfn, - unsigned long end_pfn, - enum meminit_context context) +static inline void register_memory_blocks_under_node(int nid, unsigned long start_pfn, + unsigned long end_pfn, + enum meminit_context context) { } #endif extern void unregister_node(struct node *node); #ifdef CONFIG_NUMA +extern void node_dev_init(void); /* Core of the node registration - only memory hotplug should use this */ extern int __register_one_node(int nid); @@ -128,8 +123,8 @@ static inline int register_one_node(int nid) error = __register_one_node(nid); if (error) return error; - /* link memory sections under this node */ - link_mem_sections(nid, start_pfn, end_pfn, MEMINIT_EARLY); + register_memory_blocks_under_node(nid, start_pfn, end_pfn, + MEMINIT_EARLY); } return error; @@ -143,12 +138,10 @@ extern void unregister_memory_block_under_nodes(struct memory_block *mem_blk); extern int register_memory_node_under_compute_node(unsigned int mem_nid, unsigned int cpu_nid, unsigned access); - -#ifdef CONFIG_HUGETLBFS -extern void register_hugetlbfs_with_node(node_registration_func_t doregister, - node_registration_func_t unregister); -#endif #else +static inline void node_dev_init(void) +{ +} static inline int __register_one_node(int nid) { return 0; @@ -172,11 +165,6 @@ static inline int unregister_cpu_under_node(unsigned int cpu, unsigned int nid) static inline void unregister_memory_block_under_nodes(struct memory_block *mem_blk) { } - -static inline void register_hugetlbfs_with_node(node_registration_func_t reg, - node_registration_func_t unreg) -{ -} #endif #define to_node(device) container_of(device, struct node, dev) diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h index 567c3ddba2c4..efef68c9352a 100644 --- a/include/linux/nodemask.h +++ b/include/linux/nodemask.h @@ -42,11 +42,11 @@ * void nodes_shift_right(dst, src, n) Shift right * void nodes_shift_left(dst, src, n) Shift left * - * int first_node(mask) Number lowest set bit, or MAX_NUMNODES - * int next_node(node, mask) Next node past 'node', or MAX_NUMNODES - * int next_node_in(node, mask) Next node past 'node', or wrap to first, + * unsigned int first_node(mask) Number lowest set bit, or MAX_NUMNODES + * unsigend int next_node(node, mask) Next node past 'node', or MAX_NUMNODES + * unsigned int next_node_in(node, mask) Next node past 'node', or wrap to first, * or MAX_NUMNODES - * int first_unset_node(mask) First node not set in mask, or + * unsigned int first_unset_node(mask) First node not set in mask, or * MAX_NUMNODES * * nodemask_t nodemask_of_node(node) Return nodemask with bit 'node' set @@ -94,6 +94,7 @@ #include <linux/bitmap.h> #include <linux/minmax.h> #include <linux/numa.h> +#include <linux/random.h> typedef struct { DECLARE_BITMAP(bits, MAX_NUMNODES); } nodemask_t; extern nodemask_t _unused_nodemask_arg_; @@ -153,7 +154,7 @@ static inline void __nodes_clear(nodemask_t *dstp, unsigned int nbits) #define node_test_and_set(node, nodemask) \ __node_test_and_set((node), &(nodemask)) -static inline int __node_test_and_set(int node, nodemask_t *addr) +static inline bool __node_test_and_set(int node, nodemask_t *addr) { return test_and_set_bit(node, addr->bits); } @@ -200,7 +201,7 @@ static inline void __nodes_complement(nodemask_t *dstp, #define nodes_equal(src1, src2) \ __nodes_equal(&(src1), &(src2), MAX_NUMNODES) -static inline int __nodes_equal(const nodemask_t *src1p, +static inline bool __nodes_equal(const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { return bitmap_equal(src1p->bits, src2p->bits, nbits); @@ -208,7 +209,7 @@ static inline int __nodes_equal(const nodemask_t *src1p, #define nodes_intersects(src1, src2) \ __nodes_intersects(&(src1), &(src2), MAX_NUMNODES) -static inline int __nodes_intersects(const nodemask_t *src1p, +static inline bool __nodes_intersects(const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { return bitmap_intersects(src1p->bits, src2p->bits, nbits); @@ -216,20 +217,20 @@ static inline int __nodes_intersects(const nodemask_t *src1p, #define nodes_subset(src1, src2) \ __nodes_subset(&(src1), &(src2), MAX_NUMNODES) -static inline int __nodes_subset(const nodemask_t *src1p, +static inline bool __nodes_subset(const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { return bitmap_subset(src1p->bits, src2p->bits, nbits); } #define nodes_empty(src) __nodes_empty(&(src), MAX_NUMNODES) -static inline int __nodes_empty(const nodemask_t *srcp, unsigned int nbits) +static inline bool __nodes_empty(const nodemask_t *srcp, unsigned int nbits) { return bitmap_empty(srcp->bits, nbits); } #define nodes_full(nodemask) __nodes_full(&(nodemask), MAX_NUMNODES) -static inline int __nodes_full(const nodemask_t *srcp, unsigned int nbits) +static inline bool __nodes_full(const nodemask_t *srcp, unsigned int nbits) { return bitmap_full(srcp->bits, nbits); } @@ -260,15 +261,15 @@ static inline void __nodes_shift_left(nodemask_t *dstp, > MAX_NUMNODES, then the silly min_ts could be dropped. */ #define first_node(src) __first_node(&(src)) -static inline int __first_node(const nodemask_t *srcp) +static inline unsigned int __first_node(const nodemask_t *srcp) { - return min_t(int, MAX_NUMNODES, find_first_bit(srcp->bits, MAX_NUMNODES)); + return min_t(unsigned int, MAX_NUMNODES, find_first_bit(srcp->bits, MAX_NUMNODES)); } #define next_node(n, src) __next_node((n), &(src)) -static inline int __next_node(int n, const nodemask_t *srcp) +static inline unsigned int __next_node(int n, const nodemask_t *srcp) { - return min_t(int,MAX_NUMNODES,find_next_bit(srcp->bits, MAX_NUMNODES, n+1)); + return min_t(unsigned int, MAX_NUMNODES, find_next_bit(srcp->bits, MAX_NUMNODES, n+1)); } /* @@ -276,7 +277,14 @@ static inline int __next_node(int n, const nodemask_t *srcp) * the first node in src if needed. Returns MAX_NUMNODES if src is empty. */ #define next_node_in(n, src) __next_node_in((n), &(src)) -int __next_node_in(int node, const nodemask_t *srcp); +static inline unsigned int __next_node_in(int node, const nodemask_t *srcp) +{ + unsigned int ret = __next_node(node, srcp); + + if (ret == MAX_NUMNODES) + ret = __first_node(srcp); + return ret; +} static inline void init_nodemask_of_node(nodemask_t *mask, int node) { @@ -296,9 +304,9 @@ static inline void init_nodemask_of_node(nodemask_t *mask, int node) }) #define first_unset_node(mask) __first_unset_node(&(mask)) -static inline int __first_unset_node(const nodemask_t *maskp) +static inline unsigned int __first_unset_node(const nodemask_t *maskp) { - return min_t(int,MAX_NUMNODES, + return min_t(unsigned int, MAX_NUMNODES, find_first_zero_bit(maskp->bits, MAX_NUMNODES)); } @@ -375,14 +383,13 @@ static inline void __nodes_fold(nodemask_t *dstp, const nodemask_t *origp, } #if MAX_NUMNODES > 1 -#define for_each_node_mask(node, mask) \ - for ((node) = first_node(mask); \ - (node) < MAX_NUMNODES; \ - (node) = next_node((node), (mask))) +#define for_each_node_mask(node, mask) \ + for ((node) = first_node(mask); \ + (node >= 0) && (node) < MAX_NUMNODES; \ + (node) = next_node((node), (mask))) #else /* MAX_NUMNODES == 1 */ -#define for_each_node_mask(node, mask) \ - if (!nodes_empty(mask)) \ - for ((node) = 0; (node) < 1; (node)++) +#define for_each_node_mask(node, mask) \ + for ((node) = 0; (node) < 1 && !nodes_empty(mask); (node)++) #endif /* MAX_NUMNODES */ /* @@ -436,11 +443,11 @@ static inline int num_node_state(enum node_states state) #define first_online_node first_node(node_states[N_ONLINE]) #define first_memory_node first_node(node_states[N_MEMORY]) -static inline int next_online_node(int nid) +static inline unsigned int next_online_node(int nid) { return next_node(nid, node_states[N_ONLINE]); } -static inline int next_memory_node(int nid) +static inline unsigned int next_memory_node(int nid) { return next_node(nid, node_states[N_MEMORY]); } @@ -486,6 +493,7 @@ static inline int num_node_state(enum node_states state) #define first_online_node 0 #define first_memory_node 0 #define next_online_node(nid) (MAX_NUMNODES) +#define next_memory_node(nid) (MAX_NUMNODES) #define nr_node_ids 1U #define nr_online_nodes 1U @@ -494,14 +502,28 @@ static inline int num_node_state(enum node_states state) #endif +static inline int node_random(const nodemask_t *maskp) +{ #if defined(CONFIG_NUMA) && (MAX_NUMNODES > 1) -extern int node_random(const nodemask_t *maskp); + int w, bit; + + w = nodes_weight(*maskp); + switch (w) { + case 0: + bit = NUMA_NO_NODE; + break; + case 1: + bit = first_node(*maskp); + break; + default: + bit = find_nth_bit(maskp->bits, MAX_NUMNODES, prandom_u32_max(w)); + break; + } + return bit; #else -static inline int node_random(const nodemask_t *mask) -{ return 0; -} #endif +} #define node_online_map node_states[N_ONLINE] #define node_possible_map node_states[N_POSSIBLE] diff --git a/include/linux/notifier.h b/include/linux/notifier.h index 87069b8459af..aef88c2d1173 100644 --- a/include/linux/notifier.h +++ b/include/linux/notifier.h @@ -150,6 +150,11 @@ extern int raw_notifier_chain_register(struct raw_notifier_head *nh, extern int srcu_notifier_chain_register(struct srcu_notifier_head *nh, struct notifier_block *nb); +extern int atomic_notifier_chain_register_unique_prio( + struct atomic_notifier_head *nh, struct notifier_block *nb); +extern int blocking_notifier_chain_register_unique_prio( + struct blocking_notifier_head *nh, struct notifier_block *nb); + extern int atomic_notifier_chain_unregister(struct atomic_notifier_head *nh, struct notifier_block *nb); extern int blocking_notifier_chain_unregister(struct blocking_notifier_head *nh, @@ -173,6 +178,8 @@ extern int blocking_notifier_call_chain_robust(struct blocking_notifier_head *nh extern int raw_notifier_call_chain_robust(struct raw_notifier_head *nh, unsigned long val_up, unsigned long val_down, void *v); +extern bool atomic_notifier_call_chain_is_empty(struct atomic_notifier_head *nh); + #define NOTIFY_DONE 0x0000 /* Don't care */ #define NOTIFY_OK 0x0001 /* Suits me */ #define NOTIFY_STOP_MASK 0x8000 /* Don't call further */ diff --git a/include/linux/nvme-auth.h b/include/linux/nvme-auth.h new file mode 100644 index 000000000000..dcb8030062dd --- /dev/null +++ b/include/linux/nvme-auth.h @@ -0,0 +1,41 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2021 Hannes Reinecke, SUSE Software Solutions + */ + +#ifndef _NVME_AUTH_H +#define _NVME_AUTH_H + +#include <crypto/kpp.h> + +struct nvme_dhchap_key { + u8 *key; + size_t len; + u8 hash; +}; + +u32 nvme_auth_get_seqnum(void); +const char *nvme_auth_dhgroup_name(u8 dhgroup_id); +const char *nvme_auth_dhgroup_kpp(u8 dhgroup_id); +u8 nvme_auth_dhgroup_id(const char *dhgroup_name); + +const char *nvme_auth_hmac_name(u8 hmac_id); +const char *nvme_auth_digest_name(u8 hmac_id); +size_t nvme_auth_hmac_hash_len(u8 hmac_id); +u8 nvme_auth_hmac_id(const char *hmac_name); + +struct nvme_dhchap_key *nvme_auth_extract_key(unsigned char *secret, + u8 key_hash); +void nvme_auth_free_key(struct nvme_dhchap_key *key); +u8 *nvme_auth_transform_key(struct nvme_dhchap_key *key, char *nqn); +int nvme_auth_generate_key(u8 *secret, struct nvme_dhchap_key **ret_key); +int nvme_auth_augmented_challenge(u8 hmac_id, u8 *skey, size_t skey_len, + u8 *challenge, u8 *aug, size_t hlen); +int nvme_auth_gen_privkey(struct crypto_kpp *dh_tfm, u8 dh_gid); +int nvme_auth_gen_pubkey(struct crypto_kpp *dh_tfm, + u8 *host_key, size_t host_key_len); +int nvme_auth_gen_shared_secret(struct crypto_kpp *dh_tfm, + u8 *ctrl_key, size_t ctrl_key_len, + u8 *sess_key, size_t sess_key_len); + +#endif /* _NVME_AUTH_H */ diff --git a/include/linux/nvme-fc-driver.h b/include/linux/nvme-fc-driver.h index cb909edb76c4..fa092b9be2fd 100644 --- a/include/linux/nvme-fc-driver.h +++ b/include/linux/nvme-fc-driver.h @@ -564,6 +564,15 @@ int nvme_fc_rcv_ls_req(struct nvme_fc_remote_port *remoteport, void *lsreqbuf, u32 lsreqbuf_len); +/* + * Routine called to get the appid field associated with request by the lldd + * + * If the return value is NULL : the user/libvirt has not set the appid to VM + * If the return value is non-zero: Returns the appid associated with VM + * + * @req: IO request from nvme fc to driver + */ +char *nvme_fc_io_getuuid(struct nvmefc_fcp_req *req); /* * *************** LLDD FC-NVME Target/Subsystem API *************** @@ -721,7 +730,7 @@ enum { * * Fields with static values for the port. Initialized by the * port_info struct supplied to the registration call. - * @port_num: NVME-FC transport subsytem port number + * @port_num: NVME-FC transport subsystem port number * @node_name: FC WWNN for the port * @port_name: FC WWPN for the port * @private: pointer to memory allocated alongside the local port @@ -1048,5 +1057,10 @@ int nvmet_fc_rcv_fcp_req(struct nvmet_fc_target_port *tgtport, void nvmet_fc_rcv_fcp_abort(struct nvmet_fc_target_port *tgtport, struct nvmefc_tgt_fcp_req *fcpreq); +/* + * add a define, visible to the compiler, that indicates support + * for feature. Allows for conditional compilation in LLDDs. + */ +#define NVME_FC_FEAT_UUID 0x0001 #endif /* _NVME_FC_DRIVER_H */ diff --git a/include/linux/nvme-tcp.h b/include/linux/nvme-tcp.h index 959e0bd9a913..75470159a194 100644 --- a/include/linux/nvme-tcp.h +++ b/include/linux/nvme-tcp.h @@ -12,6 +12,7 @@ #define NVME_TCP_DISC_PORT 8009 #define NVME_TCP_ADMIN_CCSZ SZ_8K #define NVME_TCP_DIGEST_LENGTH 4 +#define NVME_TCP_MIN_MAXH2CDATA 4096 enum nvme_tcp_pfv { NVME_TCP_PFV_1_0 = 0x0, diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 855dd9b3e84b..050d7d0cd81b 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -19,6 +19,7 @@ #define NVMF_TRSVCID_SIZE 32 #define NVMF_TRADDR_SIZE 256 #define NVMF_TSAS_SIZE 256 +#define NVMF_AUTH_HASH_LEN 64 #define NVME_DISC_SUBSYS_NAME "nqn.2014-08.org.nvmexpress.discovery" @@ -43,6 +44,12 @@ enum nvme_ctrl_type { NVME_CTRL_ADMIN = 3, /* Administrative controller */ }; +enum nvme_dctype { + NVME_DCTYPE_NOT_REPORTED = 0, + NVME_DCTYPE_DDC = 1, /* Direct Discovery Controller */ + NVME_DCTYPE_CDC = 2, /* Central Discovery Controller */ +}; + /* Address Family codes for Discovery Log Page entry ADRFAM field */ enum { NVMF_ADDR_FAMILY_PCI = 0, /* PCIe */ @@ -131,6 +138,7 @@ enum { NVME_REG_CMBMSC = 0x0050, /* Controller Memory Buffer Memory * Space Control */ + NVME_REG_CRTO = 0x0068, /* Controller Ready Timeouts */ NVME_REG_PMRCAP = 0x0e00, /* Persistent Memory Capabilities */ NVME_REG_PMRCTL = 0x0e04, /* Persistent Memory Region Control */ NVME_REG_PMRSTS = 0x0e08, /* Persistent Memory Region Status */ @@ -155,6 +163,9 @@ enum { #define NVME_CMB_BIR(cmbloc) ((cmbloc) & 0x7) #define NVME_CMB_OFST(cmbloc) (((cmbloc) >> 12) & 0xfffff) +#define NVME_CRTO_CRIMT(crto) ((crto) >> 16) +#define NVME_CRTO_CRWMT(crto) ((crto) & 0xffff) + enum { NVME_CMBSZ_SQS = 1 << 0, NVME_CMBSZ_CQS = 1 << 1, @@ -198,8 +209,10 @@ enum { NVME_CC_SHN_MASK = 3 << NVME_CC_SHN_SHIFT, NVME_CC_IOSQES = NVME_NVM_IOSQES << NVME_CC_IOSQES_SHIFT, NVME_CC_IOCQES = NVME_NVM_IOCQES << NVME_CC_IOCQES_SHIFT, - NVME_CAP_CSS_NVM = 1 << 0, - NVME_CAP_CSS_CSI = 1 << 6, + NVME_CC_CRIME = 1 << 24, +}; + +enum { NVME_CSTS_RDY = 1 << 0, NVME_CSTS_CFS = 1 << 1, NVME_CSTS_NSSRO = 1 << 4, @@ -208,10 +221,23 @@ enum { NVME_CSTS_SHST_OCCUR = 1 << 2, NVME_CSTS_SHST_CMPLT = 2 << 2, NVME_CSTS_SHST_MASK = 3 << 2, +}; + +enum { NVME_CMBMSC_CRE = 1 << 0, NVME_CMBMSC_CMSE = 1 << 1, }; +enum { + NVME_CAP_CSS_NVM = 1 << 0, + NVME_CAP_CSS_CSI = 1 << 6, +}; + +enum { + NVME_CAP_CRMS_CRWMS = 1ULL << 59, + NVME_CAP_CRMS_CRIMS = 1ULL << 60, +}; + struct nvme_id_power_state { __le16 max_power; /* centiwatts */ __u8 rsvd2; @@ -238,6 +264,7 @@ enum { enum nvme_ctrl_attr { NVME_CTRL_ATTR_HID_128_BIT = (1 << 0), NVME_CTRL_ATTR_TBKAS = (1 << 6), + NVME_CTRL_ATTR_ELBAS = (1 << 15), }; struct nvme_id_ctrl { @@ -320,7 +347,9 @@ struct nvme_id_ctrl { __le16 icdoff; __u8 ctrattr; __u8 msdbd; - __u8 rsvd1804[244]; + __u8 rsvd1804[2]; + __u8 dctype; + __u8 rsvd1807[241]; struct nvme_id_power_state psd[32]; __u8 vs[1024]; }; @@ -337,6 +366,7 @@ enum { NVME_CTRL_ONCS_TIMESTAMP = 1 << 6, NVME_CTRL_VWC_PRESENT = 1 << 0, NVME_CTRL_OACS_SEC_SUPP = 1 << 0, + NVME_CTRL_OACS_NS_MNGT_SUPP = 1 << 3, NVME_CTRL_OACS_DIRECTIVES = 1 << 5, NVME_CTRL_OACS_DBBUF_SUPP = 1 << 8, NVME_CTRL_LPA_CMD_EFFECTS_LOG = 1 << 1, @@ -391,11 +421,25 @@ struct nvme_id_ns { __le16 endgid; __u8 nguid[16]; __u8 eui64[8]; - struct nvme_lbaf lbaf[16]; - __u8 rsvd192[192]; + struct nvme_lbaf lbaf[64]; __u8 vs[3712]; }; +/* I/O Command Set Independent Identify Namespace Data Structure */ +struct nvme_id_ns_cs_indep { + __u8 nsfeat; + __u8 nmic; + __u8 rescap; + __u8 fpi; + __le32 anagrpid; + __u8 nsattr; + __u8 rsvd9; + __le16 nvmsetid; + __le16 endgid; + __u8 nstat; + __u8 rsvd15[4081]; +}; + struct nvme_zns_lbafe { __le64 zsze; __u8 zdes; @@ -410,8 +454,7 @@ struct nvme_id_ns_zns { __le32 rrl; __le32 frl; __u8 rsvd20[2796]; - struct nvme_zns_lbafe lbafe[16]; - __u8 rsvd3072[768]; + struct nvme_zns_lbafe lbafe[64]; __u8 vs[256]; }; @@ -420,6 +463,30 @@ struct nvme_id_ctrl_zns { __u8 rsvd1[4095]; }; +struct nvme_id_ns_nvm { + __le64 lbstm; + __u8 pic; + __u8 rsvd9[3]; + __le32 elbaf[64]; + __u8 rsvd268[3828]; +}; + +enum { + NVME_ID_NS_NVM_STS_MASK = 0x3f, + NVME_ID_NS_NVM_GUARD_SHIFT = 7, + NVME_ID_NS_NVM_GUARD_MASK = 0x3, +}; + +static inline __u8 nvme_elbaf_sts(__u32 elbaf) +{ + return elbaf & NVME_ID_NS_NVM_STS_MASK; +} + +static inline __u8 nvme_elbaf_guard_type(__u32 elbaf) +{ + return (elbaf >> NVME_ID_NS_NVM_GUARD_SHIFT) & NVME_ID_NS_NVM_GUARD_MASK; +} + struct nvme_id_ctrl_nvm { __u8 vsl; __u8 wzsl; @@ -437,6 +504,7 @@ enum { NVME_ID_CNS_NS_DESC_LIST = 0x03, NVME_ID_CNS_CS_NS = 0x05, NVME_ID_CNS_CS_CTRL = 0x06, + NVME_ID_CNS_NS_CS_INDEP = 0x08, NVME_ID_CNS_NS_PRESENT_LIST = 0x10, NVME_ID_CNS_NS_PRESENT = 0x11, NVME_ID_CNS_CTRL_NS_LIST = 0x12, @@ -470,6 +538,8 @@ enum { NVME_NS_FEAT_IO_OPT = 1 << 4, NVME_NS_ATTR_RO = 1 << 0, NVME_NS_FLBAS_LBA_MASK = 0xf, + NVME_NS_FLBAS_LBA_UMASK = 0x60, + NVME_NS_FLBAS_LBA_SHIFT = 1, NVME_NS_FLBAS_META_EXT = 0x10, NVME_NS_NMIC_SHARED = 1 << 0, NVME_LBAF_RP_BEST = 0, @@ -488,6 +558,22 @@ enum { NVME_NS_DPS_PI_TYPE3 = 3, }; +enum { + NVME_NSTAT_NRDY = 1 << 0, +}; + +enum { + NVME_NVM_NS_16B_GUARD = 0, + NVME_NVM_NS_32B_GUARD = 1, + NVME_NVM_NS_64B_GUARD = 2, +}; + +static inline __u8 nvme_lbaf_index(__u8 flbas) +{ + return (flbas & NVME_NS_FLBAS_LBA_MASK) | + ((flbas & NVME_NS_FLBAS_LBA_UMASK) >> NVME_NS_FLBAS_LBA_SHIFT); +} + /* Identify Namespace Metadata Capabilities (MC): */ enum { NVME_MC_EXTENDED_LBA = (1 << 0), @@ -627,6 +713,10 @@ enum { }; enum { + NVME_AER_ERROR_PERSIST_INT_ERR = 0x03, +}; + +enum { NVME_AER_NOTICE_NS_CHANGED = 0x00, NVME_AER_NOTICE_FW_ACT_STARTING = 0x01, NVME_AER_NOTICE_ANA = 0x03, @@ -821,12 +911,14 @@ struct nvme_common_command { __le32 cdw2[2]; __le64 metadata; union nvme_data_ptr dptr; + struct_group(cdws, __le32 cdw10; __le32 cdw11; __le32 cdw12; __le32 cdw13; __le32 cdw14; __le32 cdw15; + ); }; struct nvme_rw_command { @@ -834,7 +926,8 @@ struct nvme_rw_command { __u8 flags; __u16 command_id; __le32 nsid; - __u64 rsvd2; + __le32 cdw2; + __le32 cdw3; __le64 metadata; union nvme_data_ptr dptr; __le64 slba; @@ -988,11 +1081,14 @@ enum { struct nvme_feat_host_behavior { __u8 acre; - __u8 resv1[511]; + __u8 etdas; + __u8 lbafee; + __u8 resv1[509]; }; enum { NVME_ENABLE_ACRE = 1, + NVME_ENABLE_LBAFEE = 1, }; /* Admin commands */ @@ -1278,6 +1374,8 @@ enum nvmf_capsule_command { nvme_fabrics_type_property_set = 0x00, nvme_fabrics_type_connect = 0x01, nvme_fabrics_type_property_get = 0x04, + nvme_fabrics_type_auth_send = 0x05, + nvme_fabrics_type_auth_receive = 0x06, }; #define nvme_fabrics_type_name(type) { type, #type } @@ -1285,7 +1383,9 @@ enum nvmf_capsule_command { __print_symbolic(type, \ nvme_fabrics_type_name(nvme_fabrics_type_property_set), \ nvme_fabrics_type_name(nvme_fabrics_type_connect), \ - nvme_fabrics_type_name(nvme_fabrics_type_property_get)) + nvme_fabrics_type_name(nvme_fabrics_type_property_get), \ + nvme_fabrics_type_name(nvme_fabrics_type_auth_send), \ + nvme_fabrics_type_name(nvme_fabrics_type_auth_receive)) /* * If not fabrics command, fctype will be ignored. @@ -1381,6 +1481,11 @@ struct nvmf_connect_command { __u8 resv4[12]; }; +enum { + NVME_CONNECT_AUTHREQ_ASCR = (1U << 18), + NVME_CONNECT_AUTHREQ_ATR = (1U << 17), +}; + struct nvmf_connect_data { uuid_t hostid; __le16 cntlid; @@ -1415,6 +1520,200 @@ struct nvmf_property_get_command { __u8 resv4[16]; }; +struct nvmf_auth_common_command { + __u8 opcode; + __u8 resv1; + __u16 command_id; + __u8 fctype; + __u8 resv2[19]; + union nvme_data_ptr dptr; + __u8 resv3; + __u8 spsp0; + __u8 spsp1; + __u8 secp; + __le32 al_tl; + __u8 resv4[16]; +}; + +struct nvmf_auth_send_command { + __u8 opcode; + __u8 resv1; + __u16 command_id; + __u8 fctype; + __u8 resv2[19]; + union nvme_data_ptr dptr; + __u8 resv3; + __u8 spsp0; + __u8 spsp1; + __u8 secp; + __le32 tl; + __u8 resv4[16]; +}; + +struct nvmf_auth_receive_command { + __u8 opcode; + __u8 resv1; + __u16 command_id; + __u8 fctype; + __u8 resv2[19]; + union nvme_data_ptr dptr; + __u8 resv3; + __u8 spsp0; + __u8 spsp1; + __u8 secp; + __le32 al; + __u8 resv4[16]; +}; + +/* Value for secp */ +enum { + NVME_AUTH_DHCHAP_PROTOCOL_IDENTIFIER = 0xe9, +}; + +/* Defined value for auth_type */ +enum { + NVME_AUTH_COMMON_MESSAGES = 0x00, + NVME_AUTH_DHCHAP_MESSAGES = 0x01, +}; + +/* Defined messages for auth_id */ +enum { + NVME_AUTH_DHCHAP_MESSAGE_NEGOTIATE = 0x00, + NVME_AUTH_DHCHAP_MESSAGE_CHALLENGE = 0x01, + NVME_AUTH_DHCHAP_MESSAGE_REPLY = 0x02, + NVME_AUTH_DHCHAP_MESSAGE_SUCCESS1 = 0x03, + NVME_AUTH_DHCHAP_MESSAGE_SUCCESS2 = 0x04, + NVME_AUTH_DHCHAP_MESSAGE_FAILURE2 = 0xf0, + NVME_AUTH_DHCHAP_MESSAGE_FAILURE1 = 0xf1, +}; + +struct nvmf_auth_dhchap_protocol_descriptor { + __u8 authid; + __u8 rsvd; + __u8 halen; + __u8 dhlen; + __u8 idlist[60]; +}; + +enum { + NVME_AUTH_DHCHAP_AUTH_ID = 0x01, +}; + +/* Defined hash functions for DH-HMAC-CHAP authentication */ +enum { + NVME_AUTH_HASH_SHA256 = 0x01, + NVME_AUTH_HASH_SHA384 = 0x02, + NVME_AUTH_HASH_SHA512 = 0x03, + NVME_AUTH_HASH_INVALID = 0xff, +}; + +/* Defined Diffie-Hellman group identifiers for DH-HMAC-CHAP authentication */ +enum { + NVME_AUTH_DHGROUP_NULL = 0x00, + NVME_AUTH_DHGROUP_2048 = 0x01, + NVME_AUTH_DHGROUP_3072 = 0x02, + NVME_AUTH_DHGROUP_4096 = 0x03, + NVME_AUTH_DHGROUP_6144 = 0x04, + NVME_AUTH_DHGROUP_8192 = 0x05, + NVME_AUTH_DHGROUP_INVALID = 0xff, +}; + +union nvmf_auth_protocol { + struct nvmf_auth_dhchap_protocol_descriptor dhchap; +}; + +struct nvmf_auth_dhchap_negotiate_data { + __u8 auth_type; + __u8 auth_id; + __le16 rsvd; + __le16 t_id; + __u8 sc_c; + __u8 napd; + union nvmf_auth_protocol auth_protocol[]; +}; + +struct nvmf_auth_dhchap_challenge_data { + __u8 auth_type; + __u8 auth_id; + __u16 rsvd1; + __le16 t_id; + __u8 hl; + __u8 rsvd2; + __u8 hashid; + __u8 dhgid; + __le16 dhvlen; + __le32 seqnum; + /* 'hl' bytes of challenge value */ + __u8 cval[]; + /* followed by 'dhvlen' bytes of DH value */ +}; + +struct nvmf_auth_dhchap_reply_data { + __u8 auth_type; + __u8 auth_id; + __le16 rsvd1; + __le16 t_id; + __u8 hl; + __u8 rsvd2; + __u8 cvalid; + __u8 rsvd3; + __le16 dhvlen; + __le32 seqnum; + /* 'hl' bytes of response data */ + __u8 rval[]; + /* followed by 'hl' bytes of Challenge value */ + /* followed by 'dhvlen' bytes of DH value */ +}; + +enum { + NVME_AUTH_DHCHAP_RESPONSE_VALID = (1 << 0), +}; + +struct nvmf_auth_dhchap_success1_data { + __u8 auth_type; + __u8 auth_id; + __le16 rsvd1; + __le16 t_id; + __u8 hl; + __u8 rsvd2; + __u8 rvalid; + __u8 rsvd3[7]; + /* 'hl' bytes of response value if 'rvalid' is set */ + __u8 rval[]; +}; + +struct nvmf_auth_dhchap_success2_data { + __u8 auth_type; + __u8 auth_id; + __le16 rsvd1; + __le16 t_id; + __u8 rsvd2[10]; +}; + +struct nvmf_auth_dhchap_failure_data { + __u8 auth_type; + __u8 auth_id; + __le16 rsvd1; + __le16 t_id; + __u8 rescode; + __u8 rescode_exp; +}; + +enum { + NVME_AUTH_DHCHAP_FAILURE_REASON_FAILED = 0x01, +}; + +enum { + NVME_AUTH_DHCHAP_FAILURE_FAILED = 0x01, + NVME_AUTH_DHCHAP_FAILURE_NOT_USABLE = 0x02, + NVME_AUTH_DHCHAP_FAILURE_CONCAT_MISMATCH = 0x03, + NVME_AUTH_DHCHAP_FAILURE_HASH_UNUSABLE = 0x04, + NVME_AUTH_DHCHAP_FAILURE_DHGROUP_UNUSABLE = 0x05, + NVME_AUTH_DHCHAP_FAILURE_INCORRECT_PAYLOAD = 0x06, + NVME_AUTH_DHCHAP_FAILURE_INCORRECT_MESSAGE = 0x07, +}; + + struct nvme_dbbuf { __u8 opcode; __u8 flags; @@ -1458,6 +1757,9 @@ struct nvme_command { struct nvmf_connect_command connect; struct nvmf_property_set_command prop_set; struct nvmf_property_get_command prop_get; + struct nvmf_auth_common_command auth_common; + struct nvmf_auth_send_command auth_send; + struct nvmf_auth_receive_command auth_receive; struct nvme_dbbuf dbbuf; struct nvme_directive_cmd directive; }; @@ -1533,6 +1835,7 @@ enum { NVME_SC_NS_WRITE_PROTECTED = 0x20, NVME_SC_CMD_INTERRUPTED = 0x21, NVME_SC_TRANSIENT_TR_ERR = 0x22, + NVME_SC_ADMIN_COMMAND_MEDIA_NOT_READY = 0x24, NVME_SC_INVALID_IO_CMD_SET = 0x2C, NVME_SC_LBA_RANGE = 0x80, @@ -1629,13 +1932,16 @@ enum { /* * Path-related Errors: */ + NVME_SC_INTERNAL_PATH_ERROR = 0x300, NVME_SC_ANA_PERSISTENT_LOSS = 0x301, NVME_SC_ANA_INACCESSIBLE = 0x302, NVME_SC_ANA_TRANSITION = 0x303, + NVME_SC_CTRL_PATH_ERROR = 0x360, NVME_SC_HOST_PATH_ERROR = 0x370, NVME_SC_HOST_ABORTED_CMD = 0x371, NVME_SC_CRD = 0x1800, + NVME_SC_MORE = 0x2000, NVME_SC_DNR = 0x4000, }; diff --git a/include/linux/nvmem-consumer.h b/include/linux/nvmem-consumer.h index c0c0cefc3b92..980f9c9ac0bc 100644 --- a/include/linux/nvmem-consumer.h +++ b/include/linux/nvmem-consumer.h @@ -25,6 +25,7 @@ struct nvmem_cell_info { unsigned int bytes; unsigned int bit_offset; unsigned int nbits; + struct device_node *np; }; /** diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h index 98efb7b5660d..50caa117cb62 100644 --- a/include/linux/nvmem-provider.h +++ b/include/linux/nvmem-provider.h @@ -70,7 +70,8 @@ struct nvmem_keepout { * @word_size: Minimum read/write access granularity. * @stride: Minimum read/write access stride. * @priv: User context passed to read/write callbacks. - * @wp-gpio: Write protect pin + * @wp-gpio: Write protect pin + * @ignore_wp: Write Protect pin is managed by the provider. * * Note: A default "nvmem<id>" name will be assigned to the device if * no name is specified in its configuration. In such case "<id>" is @@ -92,6 +93,7 @@ struct nvmem_config { enum nvmem_type type; bool read_only; bool root_only; + bool ignore_wp; struct device_node *of_node; bool no_of_node; nvmem_reg_read_t reg_read; @@ -133,8 +135,6 @@ void nvmem_unregister(struct nvmem_device *nvmem); struct nvmem_device *devm_nvmem_register(struct device *dev, const struct nvmem_config *cfg); -int devm_nvmem_unregister(struct device *dev, struct nvmem_device *nvmem); - void nvmem_add_cell_table(struct nvmem_cell_table *table); void nvmem_del_cell_table(struct nvmem_cell_table *table); @@ -153,12 +153,6 @@ devm_nvmem_register(struct device *dev, const struct nvmem_config *c) return nvmem_register(c); } -static inline int -devm_nvmem_unregister(struct device *dev, struct nvmem_device *nvmem) -{ - return -EOPNOTSUPP; -} - static inline void nvmem_add_cell_table(struct nvmem_cell_table *table) {} static inline void nvmem_del_cell_table(struct nvmem_cell_table *table) {} diff --git a/include/linux/objtool.h b/include/linux/objtool.h index aca52db2f3f3..62c54ffbeeaa 100644 --- a/include/linux/objtool.h +++ b/include/linux/objtool.h @@ -32,13 +32,20 @@ struct unwind_hint { * * UNWIND_HINT_FUNC: Generate the unwind metadata of a callable function. * Useful for code which doesn't have an ELF function annotation. + * + * UNWIND_HINT_ENTRY: machine entry without stack, SYSCALL/SYSENTER etc. */ #define UNWIND_HINT_TYPE_CALL 0 #define UNWIND_HINT_TYPE_REGS 1 #define UNWIND_HINT_TYPE_REGS_PARTIAL 2 #define UNWIND_HINT_TYPE_FUNC 3 +#define UNWIND_HINT_TYPE_ENTRY 4 +#define UNWIND_HINT_TYPE_SAVE 5 +#define UNWIND_HINT_TYPE_RESTORE 6 + +#ifdef CONFIG_OBJTOOL -#ifdef CONFIG_STACK_VALIDATION +#include <asm/asm.h> #ifndef __ASSEMBLY__ @@ -60,7 +67,7 @@ struct unwind_hint { * It should only be used in special cases where you're 100% sure it won't * affect the reliability of frame pointers and kernel stack traces. * - * For more information, see tools/objtool/Documentation/stack-validation.txt. + * For more information, see tools/objtool/Documentation/objtool.txt. */ #define STACK_FRAME_NON_STANDARD(func) \ static void __used __section(".discard.func_stack_frame_non_standard") \ @@ -77,6 +84,18 @@ struct unwind_hint { #define STACK_FRAME_NON_STANDARD_FP(func) #endif +#define ANNOTATE_NOENDBR \ + "986: \n\t" \ + ".pushsection .discard.noendbr\n\t" \ + _ASM_PTR " 986b\n\t" \ + ".popsection\n\t" + +#define ASM_REACHABLE \ + "998:\n\t" \ + ".pushsection .discard.reachable\n\t" \ + ".long 998b - .\n\t" \ + ".popsection\n\t" + #else /* __ASSEMBLY__ */ /* @@ -110,7 +129,7 @@ struct unwind_hint { * the debuginfo as necessary. It will also warn if it sees any * inconsistencies. */ -.macro UNWIND_HINT sp_reg:req sp_offset=0 type:req end=0 +.macro UNWIND_HINT type:req sp_reg=0 sp_offset=0 end=0 .Lunwind_hint_ip_\@: .pushsection .discard.unwind_hints /* struct unwind_hint */ @@ -125,13 +144,33 @@ struct unwind_hint { .macro STACK_FRAME_NON_STANDARD func:req .pushsection .discard.func_stack_frame_non_standard, "aw" - .long \func - . + _ASM_PTR \func + .popsection +.endm + +.macro STACK_FRAME_NON_STANDARD_FP func:req +#ifdef CONFIG_FRAME_POINTER + STACK_FRAME_NON_STANDARD \func +#endif +.endm + +.macro ANNOTATE_NOENDBR +.Lhere_\@: + .pushsection .discard.noendbr + .quad .Lhere_\@ + .popsection +.endm + +.macro REACHABLE +.Lhere_\@: + .pushsection .discard.reachable + .long .Lhere_\@ - . .popsection .endm #endif /* __ASSEMBLY__ */ -#else /* !CONFIG_STACK_VALIDATION */ +#else /* !CONFIG_OBJTOOL */ #ifndef __ASSEMBLY__ @@ -139,14 +178,20 @@ struct unwind_hint { "\n\t" #define STACK_FRAME_NON_STANDARD(func) #define STACK_FRAME_NON_STANDARD_FP(func) +#define ANNOTATE_NOENDBR +#define ASM_REACHABLE #else #define ANNOTATE_INTRA_FUNCTION_CALL -.macro UNWIND_HINT sp_reg:req sp_offset=0 type:req end=0 +.macro UNWIND_HINT type:req sp_reg=0 sp_offset=0 end=0 .endm .macro STACK_FRAME_NON_STANDARD func:req .endm +.macro ANNOTATE_NOENDBR +.endm +.macro REACHABLE +.endm #endif -#endif /* CONFIG_STACK_VALIDATION */ +#endif /* CONFIG_OBJTOOL */ #endif /* _LINUX_OBJTOOL_H */ diff --git a/include/linux/of.h b/include/linux/of.h index ff143a027abc..6b79ef9a6541 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -207,7 +207,7 @@ static inline void of_node_clear_flag(struct device_node *n, unsigned long flag) } #if defined(CONFIG_OF_DYNAMIC) || defined(CONFIG_SPARC) -static inline int of_property_check_flag(struct property *p, unsigned long flag) +static inline int of_property_check_flag(const struct property *p, unsigned long flag) { return test_bit(flag, &p->_flags); } @@ -342,7 +342,7 @@ extern int of_property_read_string_helper(const struct device_node *np, const char **out_strs, size_t sz, int index); extern int of_device_is_compatible(const struct device_node *device, const char *); -extern int of_device_compatible_match(struct device_node *device, +extern int of_device_compatible_match(const struct device_node *device, const char *const *compat); extern bool of_device_is_available(const struct device_node *device); extern bool of_device_is_big_endian(const struct device_node *device); @@ -364,18 +364,12 @@ extern const struct of_device_id *of_match_node( const struct of_device_id *matches, const struct device_node *node); extern int of_modalias_node(struct device_node *node, char *modalias, int len); extern void of_print_phandle_args(const char *msg, const struct of_phandle_args *args); -extern struct device_node *of_parse_phandle(const struct device_node *np, - const char *phandle_name, - int index); -extern int of_parse_phandle_with_args(const struct device_node *np, - const char *list_name, const char *cells_name, int index, - struct of_phandle_args *out_args); +extern int __of_parse_phandle_with_args(const struct device_node *np, + const char *list_name, const char *cells_name, int cell_count, + int index, struct of_phandle_args *out_args); extern int of_parse_phandle_with_args_map(const struct device_node *np, const char *list_name, const char *stem_name, int index, struct of_phandle_args *out_args); -extern int of_parse_phandle_with_fixed_args(const struct device_node *np, - const char *list_name, int cells_count, int index, - struct of_phandle_args *out_args); extern int of_count_phandle_with_args(const struct device_node *np, const char *list_name, const char *cells_name); @@ -394,9 +388,6 @@ extern int of_phandle_iterator_args(struct of_phandle_iterator *it, extern void of_alias_scan(void * (*dt_alloc)(u64 size, u64 align)); extern int of_alias_get_id(struct device_node *np, const char *stem); extern int of_alias_get_highest_id(const char *stem); -extern int of_alias_get_alias_list(const struct of_device_id *matches, - const char *stem, unsigned long *bitmap, - unsigned int nbits); extern int of_machine_is_compatible(const char *compat); @@ -416,130 +407,6 @@ extern int of_detach_node(struct device_node *); #define of_match_ptr(_ptr) (_ptr) -/** - * of_property_read_u8_array - Find and read an array of u8 from a property. - * - * @np: device node from which the property value is to be read. - * @propname: name of the property to be searched. - * @out_values: pointer to return value, modified only if return value is 0. - * @sz: number of array elements to read - * - * Search for a property in a device node and read 8-bit value(s) from - * it. - * - * dts entry of array should be like: - * ``property = /bits/ 8 <0x50 0x60 0x70>;`` - * - * Return: 0 on success, -EINVAL if the property does not exist, - * -ENODATA if property does not have a value, and -EOVERFLOW if the - * property data isn't large enough. - * - * The out_values is modified only if a valid u8 value can be decoded. - */ -static inline int of_property_read_u8_array(const struct device_node *np, - const char *propname, - u8 *out_values, size_t sz) -{ - int ret = of_property_read_variable_u8_array(np, propname, out_values, - sz, 0); - if (ret >= 0) - return 0; - else - return ret; -} - -/** - * of_property_read_u16_array - Find and read an array of u16 from a property. - * - * @np: device node from which the property value is to be read. - * @propname: name of the property to be searched. - * @out_values: pointer to return value, modified only if return value is 0. - * @sz: number of array elements to read - * - * Search for a property in a device node and read 16-bit value(s) from - * it. - * - * dts entry of array should be like: - * ``property = /bits/ 16 <0x5000 0x6000 0x7000>;`` - * - * Return: 0 on success, -EINVAL if the property does not exist, - * -ENODATA if property does not have a value, and -EOVERFLOW if the - * property data isn't large enough. - * - * The out_values is modified only if a valid u16 value can be decoded. - */ -static inline int of_property_read_u16_array(const struct device_node *np, - const char *propname, - u16 *out_values, size_t sz) -{ - int ret = of_property_read_variable_u16_array(np, propname, out_values, - sz, 0); - if (ret >= 0) - return 0; - else - return ret; -} - -/** - * of_property_read_u32_array - Find and read an array of 32 bit integers - * from a property. - * - * @np: device node from which the property value is to be read. - * @propname: name of the property to be searched. - * @out_values: pointer to return value, modified only if return value is 0. - * @sz: number of array elements to read - * - * Search for a property in a device node and read 32-bit value(s) from - * it. - * - * Return: 0 on success, -EINVAL if the property does not exist, - * -ENODATA if property does not have a value, and -EOVERFLOW if the - * property data isn't large enough. - * - * The out_values is modified only if a valid u32 value can be decoded. - */ -static inline int of_property_read_u32_array(const struct device_node *np, - const char *propname, - u32 *out_values, size_t sz) -{ - int ret = of_property_read_variable_u32_array(np, propname, out_values, - sz, 0); - if (ret >= 0) - return 0; - else - return ret; -} - -/** - * of_property_read_u64_array - Find and read an array of 64 bit integers - * from a property. - * - * @np: device node from which the property value is to be read. - * @propname: name of the property to be searched. - * @out_values: pointer to return value, modified only if return value is 0. - * @sz: number of array elements to read - * - * Search for a property in a device node and read 64-bit value(s) from - * it. - * - * Return: 0 on success, -EINVAL if the property does not exist, - * -ENODATA if property does not have a value, and -EOVERFLOW if the - * property data isn't large enough. - * - * The out_values is modified only if a valid u64 value can be decoded. - */ -static inline int of_property_read_u64_array(const struct device_node *np, - const char *propname, - u64 *out_values, size_t sz) -{ - int ret = of_property_read_variable_u64_array(np, propname, out_values, - sz, 0); - if (ret >= 0) - return 0; - else - return ret; -} - /* * struct property *prop; * const __be32 *p; @@ -574,8 +441,6 @@ void *of_kexec_alloc_and_setup_fdt(const struct kimage *image, unsigned long initrd_load_addr, unsigned long initrd_len, const char *cmdline, size_t extra_fdt_size); -int ima_get_kexec_buffer(void **addr, size_t *size); -int ima_free_kexec_buffer(void); #else /* CONFIG_OF */ static inline void of_core_init(void) @@ -697,7 +562,7 @@ static inline int of_device_is_compatible(const struct device_node *device, return 0; } -static inline int of_device_compatible_match(struct device_node *device, +static inline int of_device_compatible_match(const struct device_node *device, const char *const *compat) { return 0; @@ -734,32 +599,6 @@ static inline int of_property_count_elems_of_size(const struct device_node *np, return -ENOSYS; } -static inline int of_property_read_u8_array(const struct device_node *np, - const char *propname, u8 *out_values, size_t sz) -{ - return -ENOSYS; -} - -static inline int of_property_read_u16_array(const struct device_node *np, - const char *propname, u16 *out_values, size_t sz) -{ - return -ENOSYS; -} - -static inline int of_property_read_u32_array(const struct device_node *np, - const char *propname, - u32 *out_values, size_t sz) -{ - return -ENOSYS; -} - -static inline int of_property_read_u64_array(const struct device_node *np, - const char *propname, - u64 *out_values, size_t sz) -{ - return -ENOSYS; -} - static inline int of_property_read_u32_index(const struct device_node *np, const char *propname, u32 index, u32 *out_value) { @@ -865,18 +704,12 @@ static inline int of_property_read_string_helper(const struct device_node *np, return -ENOSYS; } -static inline struct device_node *of_parse_phandle(const struct device_node *np, - const char *phandle_name, - int index) -{ - return NULL; -} - -static inline int of_parse_phandle_with_args(const struct device_node *np, - const char *list_name, - const char *cells_name, - int index, - struct of_phandle_args *out_args) +static inline int __of_parse_phandle_with_args(const struct device_node *np, + const char *list_name, + const char *cells_name, + int cell_count, + int index, + struct of_phandle_args *out_args) { return -ENOSYS; } @@ -890,13 +723,6 @@ static inline int of_parse_phandle_with_args_map(const struct device_node *np, return -ENOSYS; } -static inline int of_parse_phandle_with_fixed_args(const struct device_node *np, - const char *list_name, int cells_count, int index, - struct of_phandle_args *out_args) -{ - return -ENOSYS; -} - static inline int of_count_phandle_with_args(const struct device_node *np, const char *list_name, const char *cells_name) @@ -935,13 +761,6 @@ static inline int of_alias_get_highest_id(const char *stem) return -ENOSYS; } -static inline int of_alias_get_alias_list(const struct of_device_id *matches, - const char *stem, unsigned long *bitmap, - unsigned int nbits) -{ - return -ENOSYS; -} - static inline int of_machine_is_compatible(const char *compat) { return 0; @@ -993,7 +812,8 @@ static inline void of_node_clear_flag(struct device_node *n, unsigned long flag) { } -static inline int of_property_check_flag(struct property *p, unsigned long flag) +static inline int of_property_check_flag(const struct property *p, + unsigned long flag) { return 0; } @@ -1078,6 +898,117 @@ static inline bool of_node_is_type(const struct device_node *np, const char *typ } /** + * of_parse_phandle - Resolve a phandle property to a device_node pointer + * @np: Pointer to device node holding phandle property + * @phandle_name: Name of property holding a phandle value + * @index: For properties holding a table of phandles, this is the index into + * the table + * + * Return: The device_node pointer with refcount incremented. Use + * of_node_put() on it when done. + */ +static inline struct device_node *of_parse_phandle(const struct device_node *np, + const char *phandle_name, + int index) +{ + struct of_phandle_args args; + + if (__of_parse_phandle_with_args(np, phandle_name, NULL, 0, + index, &args)) + return NULL; + + return args.np; +} + +/** + * of_parse_phandle_with_args() - Find a node pointed by phandle in a list + * @np: pointer to a device tree node containing a list + * @list_name: property name that contains a list + * @cells_name: property name that specifies phandles' arguments count + * @index: index of a phandle to parse out + * @out_args: optional pointer to output arguments structure (will be filled) + * + * This function is useful to parse lists of phandles and their arguments. + * Returns 0 on success and fills out_args, on error returns appropriate + * errno value. + * + * Caller is responsible to call of_node_put() on the returned out_args->np + * pointer. + * + * Example:: + * + * phandle1: node1 { + * #list-cells = <2>; + * }; + * + * phandle2: node2 { + * #list-cells = <1>; + * }; + * + * node3 { + * list = <&phandle1 1 2 &phandle2 3>; + * }; + * + * To get a device_node of the ``node2`` node you may call this: + * of_parse_phandle_with_args(node3, "list", "#list-cells", 1, &args); + */ +static inline int of_parse_phandle_with_args(const struct device_node *np, + const char *list_name, + const char *cells_name, + int index, + struct of_phandle_args *out_args) +{ + int cell_count = -1; + + /* If cells_name is NULL we assume a cell count of 0 */ + if (!cells_name) + cell_count = 0; + + return __of_parse_phandle_with_args(np, list_name, cells_name, + cell_count, index, out_args); +} + +/** + * of_parse_phandle_with_fixed_args() - Find a node pointed by phandle in a list + * @np: pointer to a device tree node containing a list + * @list_name: property name that contains a list + * @cell_count: number of argument cells following the phandle + * @index: index of a phandle to parse out + * @out_args: optional pointer to output arguments structure (will be filled) + * + * This function is useful to parse lists of phandles and their arguments. + * Returns 0 on success and fills out_args, on error returns appropriate + * errno value. + * + * Caller is responsible to call of_node_put() on the returned out_args->np + * pointer. + * + * Example:: + * + * phandle1: node1 { + * }; + * + * phandle2: node2 { + * }; + * + * node3 { + * list = <&phandle1 0 2 &phandle2 2 3>; + * }; + * + * To get a device_node of the ``node2`` node you may call this: + * of_parse_phandle_with_fixed_args(node3, "list", 2, 1, &args); + */ +static inline int of_parse_phandle_with_fixed_args(const struct device_node *np, + const char *list_name, + int cell_count, + int index, + struct of_phandle_args *out_args) +{ + return __of_parse_phandle_with_args(np, list_name, NULL, cell_count, + index, out_args); +} + +/** * of_property_count_u8_elems - Count the number of u8 elements in a property * * @np: device node from which the property value is to be read. @@ -1236,6 +1167,130 @@ static inline bool of_property_read_bool(const struct device_node *np, return prop ? true : false; } +/** + * of_property_read_u8_array - Find and read an array of u8 from a property. + * + * @np: device node from which the property value is to be read. + * @propname: name of the property to be searched. + * @out_values: pointer to return value, modified only if return value is 0. + * @sz: number of array elements to read + * + * Search for a property in a device node and read 8-bit value(s) from + * it. + * + * dts entry of array should be like: + * ``property = /bits/ 8 <0x50 0x60 0x70>;`` + * + * Return: 0 on success, -EINVAL if the property does not exist, + * -ENODATA if property does not have a value, and -EOVERFLOW if the + * property data isn't large enough. + * + * The out_values is modified only if a valid u8 value can be decoded. + */ +static inline int of_property_read_u8_array(const struct device_node *np, + const char *propname, + u8 *out_values, size_t sz) +{ + int ret = of_property_read_variable_u8_array(np, propname, out_values, + sz, 0); + if (ret >= 0) + return 0; + else + return ret; +} + +/** + * of_property_read_u16_array - Find and read an array of u16 from a property. + * + * @np: device node from which the property value is to be read. + * @propname: name of the property to be searched. + * @out_values: pointer to return value, modified only if return value is 0. + * @sz: number of array elements to read + * + * Search for a property in a device node and read 16-bit value(s) from + * it. + * + * dts entry of array should be like: + * ``property = /bits/ 16 <0x5000 0x6000 0x7000>;`` + * + * Return: 0 on success, -EINVAL if the property does not exist, + * -ENODATA if property does not have a value, and -EOVERFLOW if the + * property data isn't large enough. + * + * The out_values is modified only if a valid u16 value can be decoded. + */ +static inline int of_property_read_u16_array(const struct device_node *np, + const char *propname, + u16 *out_values, size_t sz) +{ + int ret = of_property_read_variable_u16_array(np, propname, out_values, + sz, 0); + if (ret >= 0) + return 0; + else + return ret; +} + +/** + * of_property_read_u32_array - Find and read an array of 32 bit integers + * from a property. + * + * @np: device node from which the property value is to be read. + * @propname: name of the property to be searched. + * @out_values: pointer to return value, modified only if return value is 0. + * @sz: number of array elements to read + * + * Search for a property in a device node and read 32-bit value(s) from + * it. + * + * Return: 0 on success, -EINVAL if the property does not exist, + * -ENODATA if property does not have a value, and -EOVERFLOW if the + * property data isn't large enough. + * + * The out_values is modified only if a valid u32 value can be decoded. + */ +static inline int of_property_read_u32_array(const struct device_node *np, + const char *propname, + u32 *out_values, size_t sz) +{ + int ret = of_property_read_variable_u32_array(np, propname, out_values, + sz, 0); + if (ret >= 0) + return 0; + else + return ret; +} + +/** + * of_property_read_u64_array - Find and read an array of 64 bit integers + * from a property. + * + * @np: device node from which the property value is to be read. + * @propname: name of the property to be searched. + * @out_values: pointer to return value, modified only if return value is 0. + * @sz: number of array elements to read + * + * Search for a property in a device node and read 64-bit value(s) from + * it. + * + * Return: 0 on success, -EINVAL if the property does not exist, + * -ENODATA if property does not have a value, and -EOVERFLOW if the + * property data isn't large enough. + * + * The out_values is modified only if a valid u64 value can be decoded. + */ +static inline int of_property_read_u64_array(const struct device_node *np, + const char *propname, + u64 *out_values, size_t sz) +{ + int ret = of_property_read_variable_u64_array(np, propname, out_values, + sz, 0); + if (ret >= 0) + return 0; + else + return ret; +} + static inline int of_property_read_u8(const struct device_node *np, const char *propname, u8 *out_value) @@ -1487,12 +1542,26 @@ static inline bool of_device_is_system_power_controller(const struct device_node */ enum of_overlay_notify_action { - OF_OVERLAY_PRE_APPLY = 0, + OF_OVERLAY_INIT = 0, /* kzalloc() of ovcs sets this value */ + OF_OVERLAY_PRE_APPLY, OF_OVERLAY_POST_APPLY, OF_OVERLAY_PRE_REMOVE, OF_OVERLAY_POST_REMOVE, }; +static inline char *of_overlay_action_name(enum of_overlay_notify_action action) +{ + static char *of_overlay_action_name[] = { + "init", + "pre-apply", + "post-apply", + "pre-remove", + "post-remove", + }; + + return of_overlay_action_name[action]; +} + struct of_overlay_notify_data { struct device_node *overlay; struct device_node *target; diff --git a/include/linux/of_device.h b/include/linux/of_device.h index 1d7992a02e36..1a803e4335d3 100644 --- a/include/linux/of_device.h +++ b/include/linux/of_device.h @@ -101,8 +101,9 @@ static inline struct device_node *of_cpu_device_node_get(int cpu) } static inline int of_dma_configure_id(struct device *dev, - struct device_node *np, - bool force_dma) + struct device_node *np, + bool force_dma, + const u32 *id) { return 0; } diff --git a/include/linux/of_fdt.h b/include/linux/of_fdt.h index cf48983d3c86..d69ad5bb1eb1 100644 --- a/include/linux/of_fdt.h +++ b/include/linux/of_fdt.h @@ -58,10 +58,9 @@ extern int of_flat_dt_is_compatible(unsigned long node, const char *name); extern unsigned long of_get_flat_dt_root(void); extern uint32_t of_get_flat_dt_phandle(unsigned long node); -extern int early_init_dt_scan_chosen(unsigned long node, const char *uname, - int depth, void *data); -extern int early_init_dt_scan_memory(unsigned long node, const char *uname, - int depth, void *data); +extern int early_init_dt_scan_chosen(char *cmdline); +extern int early_init_dt_scan_memory(void); +extern void early_init_dt_check_for_usable_mem_range(void); extern int early_init_dt_scan_chosen_stdout(void); extern void early_init_fdt_scan_reserved_mem(void); extern void early_init_fdt_reserve_self(void); @@ -69,8 +68,7 @@ extern void early_init_dt_add_memory_arch(u64 base, u64 size); extern u64 dt_mem_next_cell(int s, const __be32 **cellp); /* Early flat tree scan hooks */ -extern int early_init_dt_scan_root(unsigned long node, const char *uname, - int depth, void *data); +extern int early_init_dt_scan_root(void); extern bool early_init_dt_scan(void *params); extern bool early_init_dt_verify(void *params); @@ -86,6 +84,7 @@ extern void unflatten_and_copy_device_tree(void); extern void early_init_devtree(void *); extern void early_get_first_memblock_info(void *, phys_addr_t *); #else /* CONFIG_OF_EARLY_FLATTREE */ +static inline void early_init_dt_check_for_usable_mem_range(void) {} static inline int early_init_dt_scan_chosen_stdout(void) { return -ENODEV; } static inline void early_init_fdt_scan_reserved_mem(void) {} static inline void early_init_fdt_reserve_self(void) {} diff --git a/include/linux/of_gpio.h b/include/linux/of_gpio.h index 8bf2ea859653..a5166eb93437 100644 --- a/include/linux/of_gpio.h +++ b/include/linux/of_gpio.h @@ -29,6 +29,7 @@ enum of_gpio_flags { OF_GPIO_TRANSITORY = 0x8, OF_GPIO_PULL_UP = 0x10, OF_GPIO_PULL_DOWN = 0x20, + OF_GPIO_PULL_DISABLE = 0x40, }; #ifdef CONFIG_OF_GPIO diff --git a/include/linux/of_irq.h b/include/linux/of_irq.h index aaf219bd0354..d6d3eae2f145 100644 --- a/include/linux/of_irq.h +++ b/include/linux/of_irq.h @@ -20,12 +20,12 @@ typedef int (*of_irq_init_cb_t)(struct device_node *, struct device_node *); #if defined(CONFIG_PPC32) && defined(CONFIG_PPC_PMAC) extern unsigned int of_irq_workarounds; extern struct device_node *of_irq_dflt_pic; -extern int of_irq_parse_oldworld(struct device_node *device, int index, - struct of_phandle_args *out_irq); +int of_irq_parse_oldworld(const struct device_node *device, int index, + struct of_phandle_args *out_irq); #else /* CONFIG_PPC32 && CONFIG_PPC_PMAC */ #define of_irq_workarounds (0) #define of_irq_dflt_pic (NULL) -static inline int of_irq_parse_oldworld(struct device_node *device, int index, +static inline int of_irq_parse_oldworld(const struct device_node *device, int index, struct of_phandle_args *out_irq) { return -EINVAL; @@ -37,9 +37,8 @@ extern unsigned int irq_create_of_mapping(struct of_phandle_args *irq_data); extern int of_irq_to_resource(struct device_node *dev, int index, struct resource *r); -extern void of_irq_init(const struct of_device_id *matches); - #ifdef CONFIG_OF_IRQ +extern void of_irq_init(const struct of_device_id *matches); extern int of_irq_parse_one(struct device_node *device, int index, struct of_phandle_args *out_irq); extern int of_irq_count(struct device_node *dev); @@ -57,6 +56,9 @@ extern struct irq_domain *of_msi_map_get_device_domain(struct device *dev, extern void of_msi_configure(struct device *dev, struct device_node *np); u32 of_msi_map_id(struct device *dev, struct device_node *msi_np, u32 id_in); #else +static inline void of_irq_init(const struct of_device_id *matches) +{ +} static inline int of_irq_parse_one(struct device_node *device, int index, struct of_phandle_args *out_irq) { diff --git a/include/linux/of_platform.h b/include/linux/of_platform.h index 84a966623e78..d15b6cd5e1c3 100644 --- a/include/linux/of_platform.h +++ b/include/linux/of_platform.h @@ -61,16 +61,18 @@ static inline struct platform_device *of_find_device_by_node(struct device_node } #endif +extern int of_platform_bus_probe(struct device_node *root, + const struct of_device_id *matches, + struct device *parent); + +#ifdef CONFIG_OF_ADDRESS /* Platform devices and busses creation */ extern struct platform_device *of_platform_device_create(struct device_node *np, const char *bus_id, struct device *parent); extern int of_platform_device_destroy(struct device *dev, void *data); -extern int of_platform_bus_probe(struct device_node *root, - const struct of_device_id *matches, - struct device *parent); -#ifdef CONFIG_OF_ADDRESS + extern int of_platform_populate(struct device_node *root, const struct of_device_id *matches, const struct of_dev_auxdata *lookup, @@ -84,6 +86,18 @@ extern int devm_of_platform_populate(struct device *dev); extern void devm_of_platform_depopulate(struct device *dev); #else +/* Platform devices and busses creation */ +static inline struct platform_device *of_platform_device_create(struct device_node *np, + const char *bus_id, + struct device *parent) +{ + return NULL; +} +static inline int of_platform_device_destroy(struct device *dev, void *data) +{ + return -ENODEV; +} + static inline int of_platform_populate(struct device_node *root, const struct of_device_id *matches, const struct of_dev_auxdata *lookup, diff --git a/include/linux/omap-dma.h b/include/linux/omap-dma.h index 5c5c93ad6b50..6f6c31e3fb93 100644 --- a/include/linux/omap-dma.h +++ b/include/linux/omap-dma.h @@ -292,15 +292,22 @@ struct omap_system_dma_plat_info { #define dma_omap15xx() __dma_omap15xx(d) #define dma_omap16xx() __dma_omap16xx(d) -#if defined(CONFIG_ARCH_OMAP) extern struct omap_system_dma_plat_info *omap_get_plat_info(void); +#if defined(CONFIG_ARCH_OMAP1) extern void omap_set_dma_priority(int lch, int dst_port, int priority); +#else +static inline void omap_set_dma_priority(int lch, int dst_port, int priority) +{ +} +#endif + extern int omap_request_dma(int dev_id, const char *dev_name, void (*callback)(int lch, u16 ch_status, void *data), void *data, int *dma_ch); -extern void omap_disable_dma_irq(int ch, u16 irq_bits); extern void omap_free_dma(int ch); +#if IS_ENABLED(CONFIG_USB_OMAP) +extern void omap_disable_dma_irq(int ch, u16 irq_bits); extern void omap_start_dma(int lch); extern void omap_stop_dma(int lch); extern void omap_set_dma_transfer_params(int lch, int data_type, @@ -326,10 +333,12 @@ extern void omap_set_dma_dest_burst_mode(int lch, extern dma_addr_t omap_get_dma_src_pos(int lch); extern dma_addr_t omap_get_dma_dst_pos(int lch); extern int omap_get_dma_active_status(int lch); +#endif + extern int omap_dma_running(void); -#if defined(CONFIG_ARCH_OMAP1) && IS_ENABLED(CONFIG_FB_OMAP) -#include <mach/lcd_dma.h> +#if IS_ENABLED(CONFIG_FB_OMAP) +extern int omap_lcd_dma_running(void); #else static inline int omap_lcd_dma_running(void) { @@ -337,22 +346,4 @@ static inline int omap_lcd_dma_running(void) } #endif -#else /* CONFIG_ARCH_OMAP */ - -static inline struct omap_system_dma_plat_info *omap_get_plat_info(void) -{ - return NULL; -} - -static inline int omap_request_dma(int dev_id, const char *dev_name, - void (*callback)(int lch, u16 ch_status, void *data), - void *data, int *dma_ch) -{ - return -ENODEV; -} - -static inline void omap_free_dma(int ch) { } - -#endif /* CONFIG_ARCH_OMAP */ - #endif /* __LINUX_OMAP_DMA_H */ diff --git a/include/linux/once.h b/include/linux/once.h index f54523052bbc..bc714d414448 100644 --- a/include/linux/once.h +++ b/include/linux/once.h @@ -5,10 +5,18 @@ #include <linux/types.h> #include <linux/jump_label.h> +/* Helpers used from arbitrary contexts. + * Hard irqs are blocked, be cautious. + */ bool __do_once_start(bool *done, unsigned long *flags); void __do_once_done(bool *done, struct static_key_true *once_key, unsigned long *flags, struct module *mod); +/* Variant for process contexts only. */ +bool __do_once_sleepable_start(bool *done); +void __do_once_sleepable_done(bool *done, struct static_key_true *once_key, + struct module *mod); + /* Call a function exactly once. The idea of DO_ONCE() is to perform * a function call such as initialization of random seeds, etc, only * once, where DO_ONCE() can live in the fast-path. After @func has @@ -52,9 +60,27 @@ void __do_once_done(bool *done, struct static_key_true *once_key, ___ret; \ }) +/* Variant of DO_ONCE() for process/sleepable contexts. */ +#define DO_ONCE_SLEEPABLE(func, ...) \ + ({ \ + bool ___ret = false; \ + static bool __section(".data.once") ___done = false; \ + static DEFINE_STATIC_KEY_TRUE(___once_key); \ + if (static_branch_unlikely(&___once_key)) { \ + ___ret = __do_once_sleepable_start(&___done); \ + if (unlikely(___ret)) { \ + func(__VA_ARGS__); \ + __do_once_sleepable_done(&___done, &___once_key,\ + THIS_MODULE); \ + } \ + } \ + ___ret; \ + }) + #define get_random_once(buf, nbytes) \ DO_ONCE(get_random_bytes, (buf), (nbytes)) -#define get_random_once_wait(buf, nbytes) \ - DO_ONCE(get_random_bytes_wait, (buf), (nbytes)) \ + +#define get_random_sleepable_once(buf, nbytes) \ + DO_ONCE_SLEEPABLE(get_random_bytes, (buf), (nbytes)) #endif /* _LINUX_ONCE_H */ diff --git a/include/linux/once_lite.h b/include/linux/once_lite.h index 861e606b820f..b7bce4983638 100644 --- a/include/linux/once_lite.h +++ b/include/linux/once_lite.h @@ -9,15 +9,27 @@ */ #define DO_ONCE_LITE(func, ...) \ DO_ONCE_LITE_IF(true, func, ##__VA_ARGS__) -#define DO_ONCE_LITE_IF(condition, func, ...) \ + +#define __ONCE_LITE_IF(condition) \ ({ \ static bool __section(".data.once") __already_done; \ - bool __ret_do_once = !!(condition); \ + bool __ret_cond = !!(condition); \ + bool __ret_once = false; \ \ - if (unlikely(__ret_do_once && !__already_done)) { \ + if (unlikely(__ret_cond && !__already_done)) { \ __already_done = true; \ - func(__VA_ARGS__); \ + __ret_once = true; \ } \ + unlikely(__ret_once); \ + }) + +#define DO_ONCE_LITE_IF(condition, func, ...) \ + ({ \ + bool __ret_do_once = !!(condition); \ + \ + if (__ONCE_LITE_IF(__ret_do_once)) \ + func(__VA_ARGS__); \ + \ unlikely(__ret_do_once); \ }) diff --git a/include/linux/oom.h b/include/linux/oom.h index 2db9a1432511..7d0c9c48a0c5 100644 --- a/include/linux/oom.h +++ b/include/linux/oom.h @@ -78,15 +78,6 @@ static inline bool tsk_is_oom_victim(struct task_struct * tsk) } /* - * Use this helper if tsk->mm != mm and the victim mm needs a special - * handling. This is guaranteed to stay true after once set. - */ -static inline bool mm_is_oom_victim(struct mm_struct *mm) -{ - return test_bit(MMF_OOM_VICTIM, &mm->flags); -} - -/* * Checks whether a page fault on the given mm is still reliable. * This is no longer true if the oom reaper started to reap the * address space which is reflected by MMF_UNSTABLE flag set in @@ -106,8 +97,6 @@ static inline vm_fault_t check_stable_address_space(struct mm_struct *mm) return 0; } -bool __oom_reap_task_mm(struct mm_struct *mm); - long oom_badness(struct task_struct *p, unsigned long totalpages); @@ -123,8 +112,4 @@ extern void oom_killer_enable(void); extern struct task_struct *find_lock_task_mm(struct task_struct *p); -/* sysctls */ -extern int sysctl_oom_dump_tasks; -extern int sysctl_oom_kill_allocating_task; -extern int sysctl_panic_on_oom; #endif /* _INCLUDE_LINUX_OOM_H */ diff --git a/include/linux/overflow.h b/include/linux/overflow.h index 4669632bd72b..1d3be1a2204c 100644 --- a/include/linux/overflow.h +++ b/include/linux/overflow.h @@ -4,6 +4,7 @@ #include <linux/compiler.h> #include <linux/limits.h> +#include <linux/const.h> /* * We need to compute the minimum and maximum values representable in a given @@ -29,7 +30,6 @@ * https://mail-index.netbsd.org/tech-misc/2007/02/05/0000.html - * credit to Christian Biere. */ -#define is_signed_type(type) (((type)(-1)) < (type)1) #define __type_half_max(type) ((type)1 << (8*sizeof(type) - 1 - is_signed_type(type))) #define type_max(T) ((T)((__type_half_max(T) - 1) + __type_half_max(T))) #define type_min(T) ((T)((T)-type_max(T)-(T)1)) @@ -51,58 +51,69 @@ static inline bool __must_check __must_check_overflow(bool overflow) return unlikely(overflow); } -/* - * For simplicity and code hygiene, the fallback code below insists on - * a, b and *d having the same type (similar to the min() and max() - * macros), whereas gcc's type-generic overflow checkers accept - * different types. Hence we don't just make check_add_overflow an - * alias for __builtin_add_overflow, but add type checks similar to - * below. +/** + * check_add_overflow() - Calculate addition with overflow checking + * @a: first addend + * @b: second addend + * @d: pointer to store sum + * + * Returns 0 on success. + * + * *@d holds the results of the attempted addition, but is not considered + * "safe for use" on a non-zero return value, which indicates that the + * sum has overflowed or been truncated. */ -#define check_add_overflow(a, b, d) __must_check_overflow(({ \ - typeof(a) __a = (a); \ - typeof(b) __b = (b); \ - typeof(d) __d = (d); \ - (void) (&__a == &__b); \ - (void) (&__a == __d); \ - __builtin_add_overflow(__a, __b, __d); \ -})) +#define check_add_overflow(a, b, d) \ + __must_check_overflow(__builtin_add_overflow(a, b, d)) -#define check_sub_overflow(a, b, d) __must_check_overflow(({ \ - typeof(a) __a = (a); \ - typeof(b) __b = (b); \ - typeof(d) __d = (d); \ - (void) (&__a == &__b); \ - (void) (&__a == __d); \ - __builtin_sub_overflow(__a, __b, __d); \ -})) - -#define check_mul_overflow(a, b, d) __must_check_overflow(({ \ - typeof(a) __a = (a); \ - typeof(b) __b = (b); \ - typeof(d) __d = (d); \ - (void) (&__a == &__b); \ - (void) (&__a == __d); \ - __builtin_mul_overflow(__a, __b, __d); \ -})) +/** + * check_sub_overflow() - Calculate subtraction with overflow checking + * @a: minuend; value to subtract from + * @b: subtrahend; value to subtract from @a + * @d: pointer to store difference + * + * Returns 0 on success. + * + * *@d holds the results of the attempted subtraction, but is not considered + * "safe for use" on a non-zero return value, which indicates that the + * difference has underflowed or been truncated. + */ +#define check_sub_overflow(a, b, d) \ + __must_check_overflow(__builtin_sub_overflow(a, b, d)) -/** check_shl_overflow() - Calculate a left-shifted value and check overflow +/** + * check_mul_overflow() - Calculate multiplication with overflow checking + * @a: first factor + * @b: second factor + * @d: pointer to store product * + * Returns 0 on success. + * + * *@d holds the results of the attempted multiplication, but is not + * considered "safe for use" on a non-zero return value, which indicates + * that the product has overflowed or been truncated. + */ +#define check_mul_overflow(a, b, d) \ + __must_check_overflow(__builtin_mul_overflow(a, b, d)) + +/** + * check_shl_overflow() - Calculate a left-shifted value and check overflow * @a: Value to be shifted * @s: How many bits left to shift * @d: Pointer to where to store the result * * Computes *@d = (@a << @s) * - * Returns true if '*d' cannot hold the result or when 'a << s' doesn't + * Returns true if '*@d' cannot hold the result or when '@a << @s' doesn't * make sense. Example conditions: - * - 'a << s' causes bits to be lost when stored in *d. - * - 's' is garbage (e.g. negative) or so large that the result of - * 'a << s' is guaranteed to be 0. - * - 'a' is negative. - * - 'a << s' sets the sign bit, if any, in '*d'. * - * '*d' will hold the results of the attempted shift, but is not + * - '@a << @s' causes bits to be lost when stored in *@d. + * - '@s' is garbage (e.g. negative) or so large that the result of + * '@a << @s' is guaranteed to be 0. + * - '@a' is negative. + * - '@a << @s' sets the sign bit, if any, in '*@d'. + * + * '*@d' will hold the results of the attempted shift, but is not * considered "safe for use" if true is returned. */ #define check_shl_overflow(a, s, d) __must_check_overflow(({ \ @@ -118,86 +129,93 @@ static inline bool __must_check __must_check_overflow(bool overflow) })) /** - * array_size() - Calculate size of 2-dimensional array. + * size_mul() - Calculate size_t multiplication with saturation at SIZE_MAX + * @factor1: first factor + * @factor2: second factor * - * @a: dimension one - * @b: dimension two - * - * Calculates size of 2-dimensional array: @a * @b. - * - * Returns: number of bytes needed to represent the array or SIZE_MAX on - * overflow. + * Returns: calculate @factor1 * @factor2, both promoted to size_t, + * with any overflow causing the return value to be SIZE_MAX. The + * lvalue must be size_t to avoid implicit type conversion. */ -static inline __must_check size_t array_size(size_t a, size_t b) +static inline size_t __must_check size_mul(size_t factor1, size_t factor2) { size_t bytes; - if (check_mul_overflow(a, b, &bytes)) + if (check_mul_overflow(factor1, factor2, &bytes)) return SIZE_MAX; return bytes; } /** - * array3_size() - Calculate size of 3-dimensional array. + * size_add() - Calculate size_t addition with saturation at SIZE_MAX + * @addend1: first addend + * @addend2: second addend * - * @a: dimension one - * @b: dimension two - * @c: dimension three - * - * Calculates size of 3-dimensional array: @a * @b * @c. - * - * Returns: number of bytes needed to represent the array or SIZE_MAX on - * overflow. + * Returns: calculate @addend1 + @addend2, both promoted to size_t, + * with any overflow causing the return value to be SIZE_MAX. The + * lvalue must be size_t to avoid implicit type conversion. */ -static inline __must_check size_t array3_size(size_t a, size_t b, size_t c) +static inline size_t __must_check size_add(size_t addend1, size_t addend2) { size_t bytes; - if (check_mul_overflow(a, b, &bytes)) - return SIZE_MAX; - if (check_mul_overflow(bytes, c, &bytes)) + if (check_add_overflow(addend1, addend2, &bytes)) return SIZE_MAX; return bytes; } -/* - * Compute a*b+c, returning SIZE_MAX on overflow. Internal helper for - * struct_size() below. +/** + * size_sub() - Calculate size_t subtraction with saturation at SIZE_MAX + * @minuend: value to subtract from + * @subtrahend: value to subtract from @minuend + * + * Returns: calculate @minuend - @subtrahend, both promoted to size_t, + * with any overflow causing the return value to be SIZE_MAX. For + * composition with the size_add() and size_mul() helpers, neither + * argument may be SIZE_MAX (or the result with be forced to SIZE_MAX). + * The lvalue must be size_t to avoid implicit type conversion. */ -static inline __must_check size_t __ab_c_size(size_t a, size_t b, size_t c) +static inline size_t __must_check size_sub(size_t minuend, size_t subtrahend) { size_t bytes; - if (check_mul_overflow(a, b, &bytes)) - return SIZE_MAX; - if (check_add_overflow(bytes, c, &bytes)) + if (minuend == SIZE_MAX || subtrahend == SIZE_MAX || + check_sub_overflow(minuend, subtrahend, &bytes)) return SIZE_MAX; return bytes; } /** - * struct_size() - Calculate size of structure with trailing array. - * @p: Pointer to the structure. - * @member: Name of the array member. - * @count: Number of elements in the array. + * array_size() - Calculate size of 2-dimensional array. + * @a: dimension one + * @b: dimension two * - * Calculates size of memory needed for structure @p followed by an - * array of @count number of @member elements. + * Calculates size of 2-dimensional array: @a * @b. * - * Return: number of bytes needed or SIZE_MAX on overflow. + * Returns: number of bytes needed to represent the array or SIZE_MAX on + * overflow. */ -#define struct_size(p, member, count) \ - __ab_c_size(count, \ - sizeof(*(p)->member) + __must_be_array((p)->member),\ - sizeof(*(p))) +#define array_size(a, b) size_mul(a, b) + +/** + * array3_size() - Calculate size of 3-dimensional array. + * @a: dimension one + * @b: dimension two + * @c: dimension three + * + * Calculates size of 3-dimensional array: @a * @b * @c. + * + * Returns: number of bytes needed to represent the array or SIZE_MAX on + * overflow. + */ +#define array3_size(a, b, c) size_mul(size_mul(a, b), c) /** * flex_array_size() - Calculate size of a flexible array member * within an enclosing structure. - * * @p: Pointer to the structure. * @member: Name of the flexible array member. * @count: Number of elements in the array. @@ -208,7 +226,24 @@ static inline __must_check size_t __ab_c_size(size_t a, size_t b, size_t c) * Return: number of bytes needed or SIZE_MAX on overflow. */ #define flex_array_size(p, member, count) \ - array_size(count, \ - sizeof(*(p)->member) + __must_be_array((p)->member)) + __builtin_choose_expr(__is_constexpr(count), \ + (count) * sizeof(*(p)->member) + __must_be_array((p)->member), \ + size_mul(count, sizeof(*(p)->member) + __must_be_array((p)->member))) + +/** + * struct_size() - Calculate size of structure with trailing flexible array. + * @p: Pointer to the structure. + * @member: Name of the array member. + * @count: Number of elements in the array. + * + * Calculates size of memory needed for structure @p followed by an + * array of @count number of @member elements. + * + * Return: number of bytes needed or SIZE_MAX on overflow. + */ +#define struct_size(p, member, count) \ + __builtin_choose_expr(__is_constexpr(count), \ + sizeof(*(p)) + flex_array_size(p, member, count), \ + size_add(sizeof(*(p)), flex_array_size(p, member, count))) #endif /* __LINUX_OVERFLOW_H */ diff --git a/include/linux/page-flags-layout.h b/include/linux/page-flags-layout.h index ef1e3e736e14..7d79818dc065 100644 --- a/include/linux/page-flags-layout.h +++ b/include/linux/page-flags-layout.h @@ -55,7 +55,8 @@ #define SECTIONS_WIDTH 0 #endif -#if ZONES_WIDTH + SECTIONS_WIDTH + NODES_SHIFT <= BITS_PER_LONG - NR_PAGEFLAGS +#if ZONES_WIDTH + LRU_GEN_WIDTH + SECTIONS_WIDTH + NODES_SHIFT \ + <= BITS_PER_LONG - NR_PAGEFLAGS #define NODES_WIDTH NODES_SHIFT #elif defined(CONFIG_SPARSEMEM_VMEMMAP) #error "Vmemmap: No space for nodes field in page flags" @@ -89,8 +90,8 @@ #define LAST_CPUPID_SHIFT 0 #endif -#if ZONES_WIDTH + SECTIONS_WIDTH + NODES_WIDTH + KASAN_TAG_WIDTH + LAST_CPUPID_SHIFT \ - <= BITS_PER_LONG - NR_PAGEFLAGS +#if ZONES_WIDTH + LRU_GEN_WIDTH + SECTIONS_WIDTH + NODES_WIDTH + \ + KASAN_TAG_WIDTH + LAST_CPUPID_SHIFT <= BITS_PER_LONG - NR_PAGEFLAGS #define LAST_CPUPID_WIDTH LAST_CPUPID_SHIFT #else #define LAST_CPUPID_WIDTH 0 @@ -100,10 +101,15 @@ #define LAST_CPUPID_NOT_IN_PAGE_FLAGS #endif -#if ZONES_WIDTH + SECTIONS_WIDTH + NODES_WIDTH + KASAN_TAG_WIDTH + LAST_CPUPID_WIDTH \ - > BITS_PER_LONG - NR_PAGEFLAGS +#if ZONES_WIDTH + LRU_GEN_WIDTH + SECTIONS_WIDTH + NODES_WIDTH + \ + KASAN_TAG_WIDTH + LAST_CPUPID_WIDTH > BITS_PER_LONG - NR_PAGEFLAGS #error "Not enough bits in page flags" #endif +/* see the comment on MAX_NR_TIERS */ +#define LRU_REFS_WIDTH min(__LRU_REFS_WIDTH, BITS_PER_LONG - NR_PAGEFLAGS - \ + ZONES_WIDTH - LRU_GEN_WIDTH - SECTIONS_WIDTH - \ + NODES_WIDTH - KASAN_TAG_WIDTH - LAST_CPUPID_WIDTH) + #endif #endif /* _LINUX_PAGE_FLAGS_LAYOUT */ diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index b5f14d581113..0b0ae5084e60 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -68,9 +68,6 @@ * might lose their PG_swapbacked flag when they simply can be dropped (e.g. as * a result of MADV_FREE). * - * PG_uptodate tells whether the page's contents is valid. When a read - * completes, the page becomes uptodate, unless a disk I/O error happened. - * * PG_referenced, PG_reclaim are used for page reclaim for anonymous and * file-backed pagecache (see mm/vmscan.c). * @@ -145,6 +142,15 @@ enum pageflags { PG_readahead = PG_reclaim, + /* + * Depending on the way an anonymous folio can be mapped into a page + * table (e.g., single PMD/PUD/CONT of the head page vs. PTE-mapped + * THP), PG_anon_exclusive may be set only for the head page or for + * tail pages of an anonymous folio. For now, we only expect it to be + * set on tail pages for PTE-mapped THP. + */ + PG_anon_exclusive = PG_mappedtodisk, + /* Filesystems */ PG_checked = PG_owner_priv_1, @@ -179,7 +185,7 @@ enum pageflags { * Indicates that at least one subpage is hwpoisoned in the * THP. */ - PG_has_hwpoisoned = PG_mappedtodisk, + PG_has_hwpoisoned = PG_error, #endif /* non-lru isolated movable page */ @@ -187,19 +193,68 @@ enum pageflags { /* Only valid for buddy pages. Used to track pages that are reported */ PG_reported = PG_uptodate, + +#ifdef CONFIG_MEMORY_HOTPLUG + /* For self-hosted memmap pages */ + PG_vmemmap_self_hosted = PG_owner_priv_1, +#endif }; #define PAGEFLAGS_MASK ((1UL << NR_PAGEFLAGS) - 1) #ifndef __GENERATING_BOUNDS_H +#ifdef CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP +DECLARE_STATIC_KEY_FALSE(hugetlb_optimize_vmemmap_key); + +/* + * Return the real head page struct iff the @page is a fake head page, otherwise + * return the @page itself. See Documentation/mm/vmemmap_dedup.rst. + */ +static __always_inline const struct page *page_fixed_fake_head(const struct page *page) +{ + if (!static_branch_unlikely(&hugetlb_optimize_vmemmap_key)) + return page; + + /* + * Only addresses aligned with PAGE_SIZE of struct page may be fake head + * struct page. The alignment check aims to avoid access the fields ( + * e.g. compound_head) of the @page[1]. It can avoid touch a (possibly) + * cold cacheline in some cases. + */ + if (IS_ALIGNED((unsigned long)page, PAGE_SIZE) && + test_bit(PG_head, &page->flags)) { + /* + * We can safely access the field of the @page[1] with PG_head + * because the @page is a compound page composed with at least + * two contiguous pages. + */ + unsigned long head = READ_ONCE(page[1].compound_head); + + if (likely(head & 1)) + return (const struct page *)(head - 1); + } + return page; +} +#else +static inline const struct page *page_fixed_fake_head(const struct page *page) +{ + return page; +} +#endif + +static __always_inline int page_is_fake_head(struct page *page) +{ + return page_fixed_fake_head(page) != page; +} + static inline unsigned long _compound_head(const struct page *page) { unsigned long head = READ_ONCE(page->compound_head); if (unlikely(head & 1)) return head - 1; - return (unsigned long)page; + return (unsigned long)page_fixed_fake_head(page); } #define compound_head(page) ((typeof(page))_compound_head(page)) @@ -234,12 +289,13 @@ static inline unsigned long _compound_head(const struct page *page) static __always_inline int PageTail(struct page *page) { - return READ_ONCE(page->compound_head) & 1; + return READ_ONCE(page->compound_head) & 1 || page_is_fake_head(page); } static __always_inline int PageCompound(struct page *page) { - return test_bit(PG_head, &page->flags) || PageTail(page); + return test_bit(PG_head, &page->flags) || + READ_ONCE(page->compound_head) & 1; } #define PAGE_POISON_PATTERN -1l @@ -383,7 +439,7 @@ static __always_inline int TestClearPage##uname(struct page *page) \ TESTCLEARFLAG(uname, lname, policy) #define TESTPAGEFLAG_FALSE(uname, lname) \ -static inline bool folio_test_##lname(const struct folio *folio) { return 0; } \ +static inline bool folio_test_##lname(const struct folio *folio) { return false; } \ static inline int Page##uname(const struct page *page) { return 0; } #define SETPAGEFLAG_NOOP(uname, lname) \ @@ -415,7 +471,7 @@ static inline int TestClearPage##uname(struct page *page) { return 0; } TESTSETFLAG_FALSE(uname, lname) TESTCLEARFLAG_FALSE(uname, lname) __PAGEFLAG(Locked, locked, PF_NO_TAIL) -PAGEFLAG(Waiters, waiters, PF_ONLY_HEAD) __CLEARPAGEFLAG(Waiters, waiters, PF_ONLY_HEAD) +PAGEFLAG(Waiters, waiters, PF_ONLY_HEAD) PAGEFLAG(Error, error, PF_NO_TAIL) TESTCLEARFLAG(Error, error, PF_NO_TAIL) PAGEFLAG(Referenced, referenced, PF_HEAD) TESTCLEARFLAG(Referenced, referenced, PF_HEAD) @@ -450,7 +506,7 @@ PAGEFLAG(SwapBacked, swapbacked, PF_NO_TAIL) /* * Private page markings that may be used by the filesystem that owns the page * for its own purposes. - * - PG_private and PG_private_2 cause releasepage() and co to be invoked + * - PG_private and PG_private_2 cause release_folio() and co to be invoked */ PAGEFLAG(Private, private, PF_ANY) PAGEFLAG(Private2, private_2, PF_ANY) TESTSCFLAG(Private2, private_2, PF_ANY) @@ -522,7 +578,11 @@ PAGEFLAG_FALSE(Uncached, uncached) PAGEFLAG(HWPoison, hwpoison, PF_ANY) TESTSCFLAG(HWPoison, hwpoison, PF_ANY) #define __PG_HWPOISON (1UL << PG_hwpoison) +#define MAGIC_HWPOISON 0x48575053U /* HWPS */ +extern void SetPageHWPoisonTakenOff(struct page *page); +extern void ClearPageHWPoisonTakenOff(struct page *page); extern bool take_page_off_buddy(struct page *page); +extern bool put_page_back_buddy(struct page *page); #else PAGEFLAG_FALSE(HWPoison, hwpoison) #define __PG_HWPOISON 0 @@ -549,6 +609,12 @@ PAGEFLAG_FALSE(SkipKASanPoison, skip_kasan_poison) */ __PAGEFLAG(Reported, reported, PF_NO_COMPOUND) +#ifdef CONFIG_MEMORY_HOTPLUG +PAGEFLAG(VmemmapSelfHosted, vmemmap_self_hosted, PF_ANY) +#else +PAGEFLAG_FALSE(VmemmapSelfHosted, vmemmap_self_hosted) +#endif + /* * On an anonymous page mapped into a user virtual memory area, * page->mapping points to its anon_vma, not to a struct address_space; @@ -560,7 +626,7 @@ __PAGEFLAG(Reported, reported, PF_NO_COMPOUND) * structure which KSM associates with that merged page. See ksm.h. * * PAGE_MAPPING_KSM without PAGE_MAPPING_ANON is used for non-lru movable - * page and then page->mapping points a struct address_space. + * page and then page->mapping points to a struct movable_operations. * * Please note that, confusingly, "page_mapping" refers to the inode * address_space which maps the page from disk; whereas "page_mapped" @@ -571,6 +637,17 @@ __PAGEFLAG(Reported, reported, PF_NO_COMPOUND) #define PAGE_MAPPING_KSM (PAGE_MAPPING_ANON | PAGE_MAPPING_MOVABLE) #define PAGE_MAPPING_FLAGS (PAGE_MAPPING_ANON | PAGE_MAPPING_MOVABLE) +/* + * Different with flags above, this flag is used only for fsdax mode. It + * indicates that this page->mapping is now under reflink case. + */ +#define PAGE_MAPPING_DAX_COW 0x1 + +static __always_inline bool folio_mapping_flags(struct folio *folio) +{ + return ((unsigned long)folio->mapping & PAGE_MAPPING_FLAGS) != 0; +} + static __always_inline int PageMappingFlags(struct page *page) { return ((unsigned long)page->mapping & PAGE_MAPPING_FLAGS) != 0; @@ -586,6 +663,12 @@ static __always_inline bool PageAnon(struct page *page) return folio_test_anon(page_folio(page)); } +static __always_inline bool __folio_test_movable(const struct folio *folio) +{ + return ((unsigned long)folio->mapping & PAGE_MAPPING_FLAGS) == + PAGE_MAPPING_MOVABLE; +} + static __always_inline int __PageMovable(struct page *page) { return ((unsigned long)page->mapping & PAGE_MAPPING_FLAGS) == @@ -615,6 +698,16 @@ TESTPAGEFLAG_FALSE(Ksm, ksm) u64 stable_page_flags(struct page *page); +/** + * folio_test_uptodate - Is this folio up to date? + * @folio: The folio. + * + * The uptodate flag is set on a folio when every byte in the folio is + * at least as new as the corresponding bytes on storage. Anonymous + * and CoW folios are always uptodate. If the folio is not uptodate, + * some of the bytes in it may be; see the is_partially_uptodate() + * address_space operation. + */ static inline bool folio_test_uptodate(struct folio *folio) { bool ret = test_bit(PG_uptodate, folio_flags(folio, 0)); @@ -684,7 +777,20 @@ static inline bool test_set_page_writeback(struct page *page) return set_page_writeback(page); } -__PAGEFLAG(Head, head, PF_ANY) CLEARPAGEFLAG(Head, head, PF_ANY) +static __always_inline bool folio_test_head(struct folio *folio) +{ + return test_bit(PG_head, folio_flags(folio, FOLIO_PF_ANY)); +} + +static __always_inline int PageHead(struct page *page) +{ + PF_POISONED_CHECK(page); + return test_bit(PG_head, &page->flags) && !page_is_fake_head(page); +} + +__SETPAGEFLAG(Head, head, PF_ANY) +__CLEARPAGEFLAG(Head, head, PF_ANY) +CLEARPAGEFLAG(Head, head, PF_ANY) /** * folio_test_large() - Does this folio contain more than one page? @@ -907,43 +1013,34 @@ PAGE_TYPE_OPS(Guard, guard) extern bool is_free_buddy_page(struct page *page); -__PAGEFLAG(Isolated, isolated, PF_ANY); +PAGEFLAG(Isolated, isolated, PF_ANY); -/* - * If network-based swap is enabled, sl*b must keep track of whether pages - * were allocated from pfmemalloc reserves. - */ -static inline int PageSlabPfmemalloc(struct page *page) -{ - VM_BUG_ON_PAGE(!PageSlab(page), page); - return PageActive(page); -} - -/* - * A version of PageSlabPfmemalloc() for opportunistic checks where the page - * might have been freed under us and not be a PageSlab anymore. - */ -static inline int __PageSlabPfmemalloc(struct page *page) +static __always_inline int PageAnonExclusive(struct page *page) { - return PageActive(page); + VM_BUG_ON_PGFLAGS(!PageAnon(page), page); + VM_BUG_ON_PGFLAGS(PageHuge(page) && !PageHead(page), page); + return test_bit(PG_anon_exclusive, &PF_ANY(page, 1)->flags); } -static inline void SetPageSlabPfmemalloc(struct page *page) +static __always_inline void SetPageAnonExclusive(struct page *page) { - VM_BUG_ON_PAGE(!PageSlab(page), page); - SetPageActive(page); + VM_BUG_ON_PGFLAGS(!PageAnon(page) || PageKsm(page), page); + VM_BUG_ON_PGFLAGS(PageHuge(page) && !PageHead(page), page); + set_bit(PG_anon_exclusive, &PF_ANY(page, 1)->flags); } -static inline void __ClearPageSlabPfmemalloc(struct page *page) +static __always_inline void ClearPageAnonExclusive(struct page *page) { - VM_BUG_ON_PAGE(!PageSlab(page), page); - __ClearPageActive(page); + VM_BUG_ON_PGFLAGS(!PageAnon(page) || PageKsm(page), page); + VM_BUG_ON_PGFLAGS(PageHuge(page) && !PageHead(page), page); + clear_bit(PG_anon_exclusive, &PF_ANY(page, 1)->flags); } -static inline void ClearPageSlabPfmemalloc(struct page *page) +static __always_inline void __ClearPageAnonExclusive(struct page *page) { - VM_BUG_ON_PAGE(!PageSlab(page), page); - ClearPageActive(page); + VM_BUG_ON_PGFLAGS(!PageAnon(page), page); + VM_BUG_ON_PGFLAGS(PageHuge(page) && !PageHead(page), page); + __clear_bit(PG_anon_exclusive, &PF_ANY(page, 1)->flags); } #ifdef CONFIG_MMU @@ -961,7 +1058,7 @@ static inline void ClearPageSlabPfmemalloc(struct page *page) 1UL << PG_private | 1UL << PG_private_2 | \ 1UL << PG_writeback | 1UL << PG_reserved | \ 1UL << PG_slab | 1UL << PG_active | \ - 1UL << PG_unevictable | __PG_MLOCKED) + 1UL << PG_unevictable | __PG_MLOCKED | LRU_GEN_MASK) /* * Flags checked when a page is prepped for return by the page allocator. @@ -972,7 +1069,7 @@ static inline void ClearPageSlabPfmemalloc(struct page *page) * alloc-free cycle to prevent from reusing the page. */ #define PAGE_FLAGS_CHECK_AT_PREP \ - (PAGEFLAGS_MASK & ~__PG_HWPOISON) + ((PAGEFLAGS_MASK & ~__PG_HWPOISON) | LRU_GEN_MASK | LRU_REFS_MASK) #define PAGE_FLAGS_PRIVATE \ (1UL << PG_private | 1UL << PG_private_2) diff --git a/include/linux/page-isolation.h b/include/linux/page-isolation.h index 572458016331..5456b7be38ae 100644 --- a/include/linux/page-isolation.h +++ b/include/linux/page-isolation.h @@ -33,8 +33,6 @@ static inline bool is_migrate_isolate(int migratetype) #define MEMORY_OFFLINE 0x1 #define REPORT_FAILURE 0x2 -struct page *has_unmovable_pages(struct zone *zone, struct page *page, - int migratetype, int flags); void set_pageblock_migratetype(struct page *page, int migratetype); int move_freepages_block(struct zone *zone, struct page *page, int migratetype, int *num_movable); @@ -44,7 +42,7 @@ int move_freepages_block(struct zone *zone, struct page *page, */ int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, - unsigned migratetype, int flags); + int migratetype, int flags, gfp_t gfp_flags); /* * Changes MIGRATE_ISOLATE to MIGRATE_MOVABLE. @@ -52,7 +50,7 @@ start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, */ void undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, - unsigned migratetype); + int migratetype); /* * Test all pages in [start_pfn, end_pfn) are isolated or not. diff --git a/include/linux/page_counter.h b/include/linux/page_counter.h index 679591301994..c141ea9a95ef 100644 --- a/include/linux/page_counter.h +++ b/include/linux/page_counter.h @@ -3,15 +3,17 @@ #define _LINUX_PAGE_COUNTER_H #include <linux/atomic.h> +#include <linux/cache.h> #include <linux/kernel.h> #include <asm/page.h> struct page_counter { + /* + * Make sure 'usage' does not share cacheline with any other field. The + * memcg->memory.usage is a hot member of struct mem_cgroup. + */ atomic_long_t usage; - unsigned long min; - unsigned long low; - unsigned long high; - unsigned long max; + CACHELINE_PADDING(_pad1_); /* effective memory.min and memory.min usage tracking */ unsigned long emin; @@ -23,18 +25,18 @@ struct page_counter { atomic_long_t low_usage; atomic_long_t children_low_usage; - /* legacy */ unsigned long watermark; unsigned long failcnt; - /* - * 'parent' is placed here to be far from 'usage' to reduce - * cache false sharing, as 'usage' is written mostly while - * parent is frequently read for cgroup's hierarchical - * counting nature. - */ + /* Keep all the read most fields in a separete cacheline. */ + CACHELINE_PADDING(_pad2_); + + unsigned long min; + unsigned long low; + unsigned long high; + unsigned long max; struct page_counter *parent; -}; +} ____cacheline_internodealigned_in_smp; #if BITS_PER_LONG == 32 #define PAGE_COUNTER_MAX LONG_MAX diff --git a/include/linux/page_ext.h b/include/linux/page_ext.h index fabb2e1e087f..22be4582faae 100644 --- a/include/linux/page_ext.h +++ b/include/linux/page_ext.h @@ -36,9 +36,15 @@ struct page_ext { unsigned long flags; }; +extern bool early_page_ext; extern unsigned long page_ext_size; extern void pgdat_page_ext_init(struct pglist_data *pgdat); +static inline bool early_page_ext_enabled(void) +{ + return early_page_ext; +} + #ifdef CONFIG_SPARSEMEM static inline void page_ext_init_flatmem(void) { @@ -55,7 +61,8 @@ static inline void page_ext_init(void) } #endif -struct page_ext *lookup_page_ext(const struct page *page); +extern struct page_ext *page_ext_get(struct page *page); +extern void page_ext_put(struct page_ext *page_ext); static inline struct page_ext *page_ext_next(struct page_ext *curr) { @@ -67,13 +74,13 @@ static inline struct page_ext *page_ext_next(struct page_ext *curr) #else /* !CONFIG_PAGE_EXTENSION */ struct page_ext; -static inline void pgdat_page_ext_init(struct pglist_data *pgdat) +static inline bool early_page_ext_enabled(void) { + return false; } -static inline struct page_ext *lookup_page_ext(const struct page *page) +static inline void pgdat_page_ext_init(struct pglist_data *pgdat) { - return NULL; } static inline void page_ext_init(void) @@ -87,5 +94,14 @@ static inline void page_ext_init_flatmem_late(void) static inline void page_ext_init_flatmem(void) { } + +static inline struct page_ext *page_ext_get(struct page *page) +{ + return NULL; +} + +static inline void page_ext_put(struct page_ext *page_ext) +{ +} #endif /* CONFIG_PAGE_EXTENSION */ #endif /* __LINUX_PAGE_EXT_H */ diff --git a/include/linux/page_idle.h b/include/linux/page_idle.h index 83abf95e9fa7..5cb7bd2078ec 100644 --- a/include/linux/page_idle.h +++ b/include/linux/page_idle.h @@ -13,66 +13,79 @@ * If there is not enough space to store Idle and Young bits in page flags, use * page ext flags instead. */ -extern struct page_ext_operations page_idle_ops; - static inline bool folio_test_young(struct folio *folio) { - struct page_ext *page_ext = lookup_page_ext(&folio->page); + struct page_ext *page_ext = page_ext_get(&folio->page); + bool page_young; if (unlikely(!page_ext)) return false; - return test_bit(PAGE_EXT_YOUNG, &page_ext->flags); + page_young = test_bit(PAGE_EXT_YOUNG, &page_ext->flags); + page_ext_put(page_ext); + + return page_young; } static inline void folio_set_young(struct folio *folio) { - struct page_ext *page_ext = lookup_page_ext(&folio->page); + struct page_ext *page_ext = page_ext_get(&folio->page); if (unlikely(!page_ext)) return; set_bit(PAGE_EXT_YOUNG, &page_ext->flags); + page_ext_put(page_ext); } static inline bool folio_test_clear_young(struct folio *folio) { - struct page_ext *page_ext = lookup_page_ext(&folio->page); + struct page_ext *page_ext = page_ext_get(&folio->page); + bool page_young; if (unlikely(!page_ext)) return false; - return test_and_clear_bit(PAGE_EXT_YOUNG, &page_ext->flags); + page_young = test_and_clear_bit(PAGE_EXT_YOUNG, &page_ext->flags); + page_ext_put(page_ext); + + return page_young; } static inline bool folio_test_idle(struct folio *folio) { - struct page_ext *page_ext = lookup_page_ext(&folio->page); + struct page_ext *page_ext = page_ext_get(&folio->page); + bool page_idle; if (unlikely(!page_ext)) return false; - return test_bit(PAGE_EXT_IDLE, &page_ext->flags); + page_idle = test_bit(PAGE_EXT_IDLE, &page_ext->flags); + page_ext_put(page_ext); + + return page_idle; } static inline void folio_set_idle(struct folio *folio) { - struct page_ext *page_ext = lookup_page_ext(&folio->page); + struct page_ext *page_ext = page_ext_get(&folio->page); if (unlikely(!page_ext)) return; set_bit(PAGE_EXT_IDLE, &page_ext->flags); + page_ext_put(page_ext); } static inline void folio_clear_idle(struct folio *folio) { - struct page_ext *page_ext = lookup_page_ext(&folio->page); + struct page_ext *page_ext = page_ext_get(&folio->page); if (unlikely(!page_ext)) return; clear_bit(PAGE_EXT_IDLE, &page_ext->flags); + page_ext_put(page_ext); } #endif /* !CONFIG_64BIT */ diff --git a/include/linux/page_table_check.h b/include/linux/page_table_check.h new file mode 100644 index 000000000000..01e16c7696ec --- /dev/null +++ b/include/linux/page_table_check.h @@ -0,0 +1,166 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* + * Copyright (c) 2021, Google LLC. + * Pasha Tatashin <pasha.tatashin@soleen.com> + */ +#ifndef __LINUX_PAGE_TABLE_CHECK_H +#define __LINUX_PAGE_TABLE_CHECK_H + +#ifdef CONFIG_PAGE_TABLE_CHECK +#include <linux/jump_label.h> + +extern struct static_key_true page_table_check_disabled; +extern struct page_ext_operations page_table_check_ops; + +void __page_table_check_zero(struct page *page, unsigned int order); +void __page_table_check_pte_clear(struct mm_struct *mm, unsigned long addr, + pte_t pte); +void __page_table_check_pmd_clear(struct mm_struct *mm, unsigned long addr, + pmd_t pmd); +void __page_table_check_pud_clear(struct mm_struct *mm, unsigned long addr, + pud_t pud); +void __page_table_check_pte_set(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t pte); +void __page_table_check_pmd_set(struct mm_struct *mm, unsigned long addr, + pmd_t *pmdp, pmd_t pmd); +void __page_table_check_pud_set(struct mm_struct *mm, unsigned long addr, + pud_t *pudp, pud_t pud); +void __page_table_check_pte_clear_range(struct mm_struct *mm, + unsigned long addr, + pmd_t pmd); + +static inline void page_table_check_alloc(struct page *page, unsigned int order) +{ + if (static_branch_likely(&page_table_check_disabled)) + return; + + __page_table_check_zero(page, order); +} + +static inline void page_table_check_free(struct page *page, unsigned int order) +{ + if (static_branch_likely(&page_table_check_disabled)) + return; + + __page_table_check_zero(page, order); +} + +static inline void page_table_check_pte_clear(struct mm_struct *mm, + unsigned long addr, pte_t pte) +{ + if (static_branch_likely(&page_table_check_disabled)) + return; + + __page_table_check_pte_clear(mm, addr, pte); +} + +static inline void page_table_check_pmd_clear(struct mm_struct *mm, + unsigned long addr, pmd_t pmd) +{ + if (static_branch_likely(&page_table_check_disabled)) + return; + + __page_table_check_pmd_clear(mm, addr, pmd); +} + +static inline void page_table_check_pud_clear(struct mm_struct *mm, + unsigned long addr, pud_t pud) +{ + if (static_branch_likely(&page_table_check_disabled)) + return; + + __page_table_check_pud_clear(mm, addr, pud); +} + +static inline void page_table_check_pte_set(struct mm_struct *mm, + unsigned long addr, pte_t *ptep, + pte_t pte) +{ + if (static_branch_likely(&page_table_check_disabled)) + return; + + __page_table_check_pte_set(mm, addr, ptep, pte); +} + +static inline void page_table_check_pmd_set(struct mm_struct *mm, + unsigned long addr, pmd_t *pmdp, + pmd_t pmd) +{ + if (static_branch_likely(&page_table_check_disabled)) + return; + + __page_table_check_pmd_set(mm, addr, pmdp, pmd); +} + +static inline void page_table_check_pud_set(struct mm_struct *mm, + unsigned long addr, pud_t *pudp, + pud_t pud) +{ + if (static_branch_likely(&page_table_check_disabled)) + return; + + __page_table_check_pud_set(mm, addr, pudp, pud); +} + +static inline void page_table_check_pte_clear_range(struct mm_struct *mm, + unsigned long addr, + pmd_t pmd) +{ + if (static_branch_likely(&page_table_check_disabled)) + return; + + __page_table_check_pte_clear_range(mm, addr, pmd); +} + +#else + +static inline void page_table_check_alloc(struct page *page, unsigned int order) +{ +} + +static inline void page_table_check_free(struct page *page, unsigned int order) +{ +} + +static inline void page_table_check_pte_clear(struct mm_struct *mm, + unsigned long addr, pte_t pte) +{ +} + +static inline void page_table_check_pmd_clear(struct mm_struct *mm, + unsigned long addr, pmd_t pmd) +{ +} + +static inline void page_table_check_pud_clear(struct mm_struct *mm, + unsigned long addr, pud_t pud) +{ +} + +static inline void page_table_check_pte_set(struct mm_struct *mm, + unsigned long addr, pte_t *ptep, + pte_t pte) +{ +} + +static inline void page_table_check_pmd_set(struct mm_struct *mm, + unsigned long addr, pmd_t *pmdp, + pmd_t pmd) +{ +} + +static inline void page_table_check_pud_set(struct mm_struct *mm, + unsigned long addr, pud_t *pudp, + pud_t pud) +{ +} + +static inline void page_table_check_pte_clear_range(struct mm_struct *mm, + unsigned long addr, + pmd_t pmd) +{ +} + +#endif /* CONFIG_PAGE_TABLE_CHECK */ +#endif /* __LINUX_PAGE_TABLE_CHECK_H */ diff --git a/include/linux/pageblock-flags.h b/include/linux/pageblock-flags.h index 973fd731a520..5f1ae07d724b 100644 --- a/include/linux/pageblock-flags.h +++ b/include/linux/pageblock-flags.h @@ -37,8 +37,11 @@ extern unsigned int pageblock_order; #else /* CONFIG_HUGETLB_PAGE_SIZE_VARIABLE */ -/* Huge pages are a constant size */ -#define pageblock_order HUGETLB_PAGE_ORDER +/* + * Huge pages are a constant size, but don't exceed the maximum allocation + * granularity. + */ +#define pageblock_order min_t(unsigned int, HUGETLB_PAGE_ORDER, MAX_ORDER - 1) #endif /* CONFIG_HUGETLB_PAGE_SIZE_VARIABLE */ @@ -50,6 +53,10 @@ extern unsigned int pageblock_order; #endif /* CONFIG_HUGETLB_PAGE */ #define pageblock_nr_pages (1UL << pageblock_order) +#define pageblock_align(pfn) ALIGN((pfn), pageblock_nr_pages) +#define pageblock_aligned(pfn) IS_ALIGNED((pfn), pageblock_nr_pages) +#define pageblock_start_pfn(pfn) ALIGN_DOWN((pfn), pageblock_nr_pages) +#define pageblock_end_pfn(pfn) ALIGN((pfn) + 1, pageblock_nr_pages) /* Forward declaration */ struct page; diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index d150a9082b31..bbccb4044222 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -16,7 +16,121 @@ #include <linux/hardirq.h> /* for in_interrupt() */ #include <linux/hugetlb_inline.h> -struct pagevec; +struct folio_batch; + +unsigned long invalidate_mapping_pages(struct address_space *mapping, + pgoff_t start, pgoff_t end); + +static inline void invalidate_remote_inode(struct inode *inode) +{ + if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || + S_ISLNK(inode->i_mode)) + invalidate_mapping_pages(inode->i_mapping, 0, -1); +} +int invalidate_inode_pages2(struct address_space *mapping); +int invalidate_inode_pages2_range(struct address_space *mapping, + pgoff_t start, pgoff_t end); +int write_inode_now(struct inode *, int sync); +int filemap_fdatawrite(struct address_space *); +int filemap_flush(struct address_space *); +int filemap_fdatawait_keep_errors(struct address_space *mapping); +int filemap_fdatawait_range(struct address_space *, loff_t lstart, loff_t lend); +int filemap_fdatawait_range_keep_errors(struct address_space *mapping, + loff_t start_byte, loff_t end_byte); + +static inline int filemap_fdatawait(struct address_space *mapping) +{ + return filemap_fdatawait_range(mapping, 0, LLONG_MAX); +} + +bool filemap_range_has_page(struct address_space *, loff_t lstart, loff_t lend); +int filemap_write_and_wait_range(struct address_space *mapping, + loff_t lstart, loff_t lend); +int __filemap_fdatawrite_range(struct address_space *mapping, + loff_t start, loff_t end, int sync_mode); +int filemap_fdatawrite_range(struct address_space *mapping, + loff_t start, loff_t end); +int filemap_check_errors(struct address_space *mapping); +void __filemap_set_wb_err(struct address_space *mapping, int err); +int filemap_fdatawrite_wbc(struct address_space *mapping, + struct writeback_control *wbc); + +static inline int filemap_write_and_wait(struct address_space *mapping) +{ + return filemap_write_and_wait_range(mapping, 0, LLONG_MAX); +} + +/** + * filemap_set_wb_err - set a writeback error on an address_space + * @mapping: mapping in which to set writeback error + * @err: error to be set in mapping + * + * When writeback fails in some way, we must record that error so that + * userspace can be informed when fsync and the like are called. We endeavor + * to report errors on any file that was open at the time of the error. Some + * internal callers also need to know when writeback errors have occurred. + * + * When a writeback error occurs, most filesystems will want to call + * filemap_set_wb_err to record the error in the mapping so that it will be + * automatically reported whenever fsync is called on the file. + */ +static inline void filemap_set_wb_err(struct address_space *mapping, int err) +{ + /* Fastpath for common case of no error */ + if (unlikely(err)) + __filemap_set_wb_err(mapping, err); +} + +/** + * filemap_check_wb_err - has an error occurred since the mark was sampled? + * @mapping: mapping to check for writeback errors + * @since: previously-sampled errseq_t + * + * Grab the errseq_t value from the mapping, and see if it has changed "since" + * the given value was sampled. + * + * If it has then report the latest error set, otherwise return 0. + */ +static inline int filemap_check_wb_err(struct address_space *mapping, + errseq_t since) +{ + return errseq_check(&mapping->wb_err, since); +} + +/** + * filemap_sample_wb_err - sample the current errseq_t to test for later errors + * @mapping: mapping to be sampled + * + * Writeback errors are always reported relative to a particular sample point + * in the past. This function provides those sample points. + */ +static inline errseq_t filemap_sample_wb_err(struct address_space *mapping) +{ + return errseq_sample(&mapping->wb_err); +} + +/** + * file_sample_sb_err - sample the current errseq_t to test for later errors + * @file: file pointer to be sampled + * + * Grab the most current superblock-level errseq_t value for the given + * struct file. + */ +static inline errseq_t file_sample_sb_err(struct file *file) +{ + return errseq_sample(&file->f_path.dentry->d_sb->s_wb_err); +} + +/* + * Flush file data before changing attributes. Caller must hold any locks + * required to prevent further writes to this file until we're done setting + * flags. + */ +static inline int inode_drain_writes(struct inode *inode) +{ + inode_dio_wait(inode); + return filemap_write_and_wait(inode->i_mapping); +} static inline bool mapping_empty(struct address_space *mapping) { @@ -192,9 +306,14 @@ static inline void mapping_set_large_folios(struct address_space *mapping) __set_bit(AS_LARGE_FOLIO_SUPPORT, &mapping->flags); } +/* + * Large folio support currently depends on THP. These dependencies are + * being worked on but are not yet fixed. + */ static inline bool mapping_large_folio_support(struct address_space *mapping) { - return test_bit(AS_LARGE_FOLIO_SUPPORT, &mapping->flags); + return IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && + test_bit(AS_LARGE_FOLIO_SUPPORT, &mapping->flags); } static inline int filemap_nr_thps(struct address_space *mapping) @@ -212,7 +331,7 @@ static inline void filemap_nr_thps_inc(struct address_space *mapping) if (!mapping_large_folio_support(mapping)) atomic_inc(&mapping->nr_thps); #else - WARN_ON_ONCE(1); + WARN_ON_ONCE(mapping_large_folio_support(mapping) == 0); #endif } @@ -222,12 +341,10 @@ static inline void filemap_nr_thps_dec(struct address_space *mapping) if (!mapping_large_folio_support(mapping)) atomic_dec(&mapping->nr_thps); #else - WARN_ON_ONCE(1); + WARN_ON_ONCE(mapping_large_folio_support(mapping) == 0); #endif } -void release_pages(struct page **pages, int nr); - struct address_space *page_mapping(struct page *); struct address_space *folio_mapping(struct folio *); struct address_space *swapcache_mapping(struct folio *); @@ -283,16 +400,6 @@ static inline struct inode *folio_inode(struct folio *folio) return folio->mapping->host; } -static inline bool page_cache_add_speculative(struct page *page, int count) -{ - return folio_ref_try_add_rcu((struct folio *)page, count); -} - -static inline bool page_cache_get_speculative(struct page *page) -{ - return page_cache_add_speculative(page, 1); -} - /** * folio_attach_private - Attach private data to a folio. * @folio: Folio to attach data to. @@ -383,7 +490,7 @@ static inline gfp_t readahead_gfp_mask(struct address_space *x) return mapping_gfp_mask(x) | __GFP_NORETRY | __GFP_NOWARN; } -typedef int filler_t(void *, struct page *); +typedef int filler_t(struct file *, struct folio *); pgoff_t page_cache_next_miss(struct address_space *mapping, pgoff_t index, unsigned long max_scan); @@ -423,6 +530,24 @@ static inline struct folio *filemap_get_folio(struct address_space *mapping, } /** + * filemap_lock_folio - Find and lock a folio. + * @mapping: The address_space to search. + * @index: The page index. + * + * Looks up the page cache entry at @mapping & @index. If a folio is + * present, it is returned locked with an increased refcount. + * + * Context: May sleep. + * Return: A folio or %NULL if there is no folio in the cache for this + * index. Will not return a shadow, swap or DAX entry. + */ +static inline struct folio *filemap_lock_folio(struct address_space *mapping, + pgoff_t index) +{ + return __filemap_get_folio(mapping, index, FGP_LOCK, 0); +} + +/** * find_get_page - find and get a page reference * @mapping: the address_space to search * @offset: the page index @@ -511,15 +636,6 @@ static inline struct page *grab_cache_page_nowait(struct address_space *mapping, mapping_gfp_mask(mapping)); } -/* Does this page contain this index? */ -static inline bool thp_contains(struct page *head, pgoff_t index) -{ - /* HugeTLBfs indexes the page cache in units of hpage_size */ - if (PageHuge(head)) - return head->index == index; - return page_index(head) == (index & ~(thp_nr_pages(head) - 1UL)); -} - #define swapcache_index(folio) __page_file_index(&(folio)->page) /** @@ -600,20 +716,10 @@ static inline struct page *find_subpage(struct page *head, pgoff_t index) return head + (index & (thp_nr_pages(head) - 1)); } -unsigned find_get_entries(struct address_space *mapping, pgoff_t start, - pgoff_t end, struct pagevec *pvec, pgoff_t *indices); -unsigned find_get_pages_range(struct address_space *mapping, pgoff_t *start, - pgoff_t end, unsigned int nr_pages, - struct page **pages); -static inline unsigned find_get_pages(struct address_space *mapping, - pgoff_t *start, unsigned int nr_pages, - struct page **pages) -{ - return find_get_pages_range(mapping, start, (pgoff_t)-1, nr_pages, - pages); -} -unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t start, - unsigned int nr_pages, struct page **pages); +unsigned filemap_get_folios(struct address_space *mapping, pgoff_t *start, + pgoff_t end, struct folio_batch *fbatch); +unsigned filemap_get_folios_contig(struct address_space *mapping, + pgoff_t *start, pgoff_t end, struct folio_batch *fbatch); unsigned find_get_pages_range_tag(struct address_space *mapping, pgoff_t *index, pgoff_t end, xa_mark_t tag, unsigned int nr_pages, struct page **pages); @@ -626,7 +732,7 @@ static inline unsigned find_get_pages_tag(struct address_space *mapping, } struct page *grab_cache_page_write_begin(struct address_space *mapping, - pgoff_t index, unsigned flags); + pgoff_t index); /* * Returns locked page at given index in given cache, creating it if needed. @@ -637,17 +743,23 @@ static inline struct page *grab_cache_page(struct address_space *mapping, return find_or_create_page(mapping, index, mapping_gfp_mask(mapping)); } -extern struct page * read_cache_page(struct address_space *mapping, - pgoff_t index, filler_t *filler, void *data); +struct folio *read_cache_folio(struct address_space *, pgoff_t index, + filler_t *filler, struct file *file); +struct page *read_cache_page(struct address_space *, pgoff_t index, + filler_t *filler, struct file *file); extern struct page * read_cache_page_gfp(struct address_space *mapping, pgoff_t index, gfp_t gfp_mask); -extern int read_cache_pages(struct address_space *mapping, - struct list_head *pages, filler_t *filler, void *data); static inline struct page *read_mapping_page(struct address_space *mapping, - pgoff_t index, void *data) + pgoff_t index, struct file *file) +{ + return read_cache_page(mapping, index, NULL, file); +} + +static inline struct folio *read_mapping_folio(struct address_space *mapping, + pgoff_t index, struct file *file) { - return read_cache_page(mapping, index, NULL, data); + return read_cache_folio(mapping, index, NULL, file); } /* @@ -716,6 +828,17 @@ static inline loff_t folio_file_pos(struct folio *folio) return page_file_offset(&folio->page); } +/* + * Get the offset in PAGE_SIZE (even for hugetlb folios). + * (TODO: hugetlb folios should have ->index in PAGE_SIZE) + */ +static inline pgoff_t folio_pgoff(struct folio *folio) +{ + if (unlikely(folio_test_hugetlb(folio))) + return hugetlb_basepage_index(&folio->page); + return folio->index; +} + extern pgoff_t linear_hugepage_index(struct vm_area_struct *vma, unsigned long address); @@ -762,6 +885,18 @@ bool __folio_lock_or_retry(struct folio *folio, struct mm_struct *mm, void unlock_page(struct page *page); void folio_unlock(struct folio *folio); +/** + * folio_trylock() - Attempt to lock a folio. + * @folio: The folio to attempt to lock. + * + * Sometimes it is undesirable to wait for a folio to be unlocked (eg + * when the locks are being taken in the wrong order, or if making + * progress through a batch of folios is more important than processing + * them in order). Usually folio_lock() is the correct function to call. + * + * Context: Any context. + * Return: Whether the lock was successfully acquired. + */ static inline bool folio_trylock(struct folio *folio) { return likely(!test_and_set_bit_lock(PG_locked, folio_flags(folio, 0))); @@ -775,6 +910,28 @@ static inline int trylock_page(struct page *page) return folio_trylock(page_folio(page)); } +/** + * folio_lock() - Lock this folio. + * @folio: The folio to lock. + * + * The folio lock protects against many things, probably more than it + * should. It is primarily held while a folio is being brought uptodate, + * either from its backing file or from swap. It is also held while a + * folio is being truncated from its address_space, so holding the lock + * is sufficient to keep folio->mapping stable. + * + * The folio lock is also held while write() is modifying the page to + * provide POSIX atomicity guarantees (as long as the write does not + * cross a page boundary). Other modifications to the data in the folio + * do not hold the folio lock and can race with writes, eg DMA and stores + * to mapped pages. + * + * Context: May sleep. If you need to acquire the locks of two or + * more folios, they must be in order of ascending index, if they are + * in the same address_space. If they are in different address_spaces, + * acquire the lock of the folio which belongs to the address_space which + * has the lowest address in memory first. + */ static inline void folio_lock(struct folio *folio) { might_sleep(); @@ -782,8 +939,16 @@ static inline void folio_lock(struct folio *folio) __folio_lock(folio); } -/* - * lock_page may only be called if we have the page's inode pinned. +/** + * lock_page() - Lock the folio containing this page. + * @page: The page to lock. + * + * See folio_lock() for a description of what the lock protects. + * This is a legacy function and new code should probably use folio_lock() + * instead. + * + * Context: May sleep. Pages in the same folio share a lock, so do not + * attempt to lock two pages which share a folio. */ static inline void lock_page(struct page *page) { @@ -795,6 +960,16 @@ static inline void lock_page(struct page *page) __folio_lock(folio); } +/** + * folio_lock_killable() - Lock this folio, interruptible by a fatal signal. + * @folio: The folio to lock. + * + * Attempts to lock the folio, like folio_lock(), except that the sleep + * to acquire the lock is interruptible by a fatal signal. + * + * Context: May sleep; see folio_lock(). + * Return: 0 if the lock was acquired; -EINTR if a fatal signal was received. + */ static inline int folio_lock_killable(struct folio *folio) { might_sleep(); @@ -814,19 +989,16 @@ static inline int lock_page_killable(struct page *page) } /* - * lock_page_or_retry - Lock the page, unless this would block and the + * folio_lock_or_retry - Lock the folio, unless this would block and the * caller indicated that it can handle a retry. * * Return value and mmap_lock implications depend on flags; see * __folio_lock_or_retry(). */ -static inline bool lock_page_or_retry(struct page *page, struct mm_struct *mm, - unsigned int flags) +static inline bool folio_lock_or_retry(struct folio *folio, + struct mm_struct *mm, unsigned int flags) { - struct folio *folio; might_sleep(); - - folio = page_folio(page); return folio_trylock(folio) || __folio_lock_or_retry(folio, mm, flags); } @@ -841,8 +1013,8 @@ int folio_wait_bit_killable(struct folio *folio, int bit_nr); * Wait for a folio to be unlocked. * * This must be called with the caller "holding" the folio, - * ie with increased "page->count" so that the folio won't - * go away during the wait.. + * ie with increased folio reference count so that the folio won't + * go away during the wait. */ static inline void folio_wait_locked(struct folio *folio) { @@ -867,7 +1039,6 @@ static inline int wait_on_page_locked_killable(struct page *page) return folio_wait_locked_killable(page_folio(page)); } -int put_and_wait_on_page_locked(struct page *page, int state); void wait_on_page_writeback(struct page *page); void folio_wait_writeback(struct folio *folio); int folio_wait_writeback_killable(struct folio *folio); @@ -881,13 +1052,7 @@ static inline void __set_page_dirty(struct page *page, { __folio_mark_dirty(page_folio(page), mapping, warn); } -void folio_account_cleaned(struct folio *folio, struct address_space *mapping, - struct bdi_writeback *wb); -static inline void account_page_cleaned(struct page *page, - struct address_space *mapping, struct bdi_writeback *wb) -{ - return folio_account_cleaned(page_folio(page), mapping, wb); -} +void folio_account_cleaned(struct folio *folio, struct bdi_writeback *wb); void __folio_cancel_dirty(struct folio *folio); static inline void folio_cancel_dirty(struct folio *folio) { @@ -895,12 +1060,9 @@ static inline void folio_cancel_dirty(struct folio *folio) if (folio_test_dirty(folio)) __folio_cancel_dirty(folio); } -static inline void cancel_dirty_page(struct page *page) -{ - folio_cancel_dirty(page_folio(page)); -} bool folio_clear_dirty_for_io(struct folio *folio); bool clear_page_dirty_for_io(struct page *page); +void folio_invalidate(struct folio *folio, size_t offset, size_t length); int __must_check folio_write_one(struct folio *folio); static inline int __must_check write_one_page(struct page *page) { @@ -908,8 +1070,14 @@ static inline int __must_check write_one_page(struct page *page) } int __set_page_dirty_nobuffers(struct page *page); -int __set_page_dirty_no_writeback(struct page *page); +bool noop_dirty_folio(struct address_space *mapping, struct folio *folio); +#ifdef CONFIG_MIGRATION +int filemap_migrate_folio(struct address_space *mapping, struct folio *dst, + struct folio *src, enum migrate_mode mode); +#else +#define filemap_migrate_folio NULL +#endif void page_endio(struct page *page, bool is_write, int err); void folio_end_private_2(struct folio *folio); @@ -925,43 +1093,58 @@ void folio_add_wait_queue(struct folio *folio, wait_queue_entry_t *waiter); * Fault in userspace address range. */ size_t fault_in_writeable(char __user *uaddr, size_t size); +size_t fault_in_subpage_writeable(char __user *uaddr, size_t size); size_t fault_in_safe_writeable(const char __user *uaddr, size_t size); size_t fault_in_readable(const char __user *uaddr, size_t size); -int add_to_page_cache_locked(struct page *page, struct address_space *mapping, - pgoff_t index, gfp_t gfp); int add_to_page_cache_lru(struct page *page, struct address_space *mapping, pgoff_t index, gfp_t gfp); int filemap_add_folio(struct address_space *mapping, struct folio *folio, pgoff_t index, gfp_t gfp); -extern void delete_from_page_cache(struct page *page); -extern void __delete_from_page_cache(struct page *page, void *shadow); +void filemap_remove_folio(struct folio *folio); +void delete_from_page_cache(struct page *page); +void __filemap_remove_folio(struct folio *folio, void *shadow); void replace_page_cache_page(struct page *old, struct page *new); void delete_from_page_cache_batch(struct address_space *mapping, - struct pagevec *pvec); + struct folio_batch *fbatch); +int try_to_release_page(struct page *page, gfp_t gfp); +bool filemap_release_folio(struct folio *folio, gfp_t gfp); loff_t mapping_seek_hole_data(struct address_space *, loff_t start, loff_t end, int whence); -/* - * Like add_to_page_cache_locked, but used to add newly allocated pages: - * the page is new, so we can just run __SetPageLocked() against it. - */ -static inline int add_to_page_cache(struct page *page, - struct address_space *mapping, pgoff_t offset, gfp_t gfp_mask) -{ - int error; - - __SetPageLocked(page); - error = add_to_page_cache_locked(page, mapping, offset, gfp_mask); - if (unlikely(error)) - __ClearPageLocked(page); - return error; -} - /* Must be non-static for BPF error injection */ int __filemap_add_folio(struct address_space *mapping, struct folio *folio, pgoff_t index, gfp_t gfp, void **shadowp); +bool filemap_range_has_writeback(struct address_space *mapping, + loff_t start_byte, loff_t end_byte); + +/** + * filemap_range_needs_writeback - check if range potentially needs writeback + * @mapping: address space within which to check + * @start_byte: offset in bytes where the range starts + * @end_byte: offset in bytes where the range ends (inclusive) + * + * Find at least one page in the range supplied, usually used to check if + * direct writing in this range will trigger a writeback. Used by O_DIRECT + * read/write with IOCB_NOWAIT, to see if the caller needs to do + * filemap_write_and_wait_range() before proceeding. + * + * Return: %true if the caller should do filemap_write_and_wait_range() before + * doing O_DIRECT to a page in this range, %false otherwise. + */ +static inline bool filemap_range_needs_writeback(struct address_space *mapping, + loff_t start_byte, + loff_t end_byte) +{ + if (!mapping->nrpages) + return false; + if (!mapping_tagged(mapping, PAGECACHE_TAG_DIRTY) && + !mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK)) + return false; + return filemap_range_has_writeback(mapping, start_byte, end_byte); +} + /** * struct readahead_control - Describes a readahead request. * @@ -986,6 +1169,8 @@ struct readahead_control { pgoff_t _index; unsigned int _nr_pages; unsigned int _batch_count; + bool _workingset; + unsigned long _pflags; }; #define DEFINE_READAHEAD(ractl, f, r, m, i) \ @@ -1001,7 +1186,7 @@ struct readahead_control { void page_cache_ra_unbounded(struct readahead_control *, unsigned long nr_to_read, unsigned long lookahead_count); void page_cache_sync_ra(struct readahead_control *, unsigned long req_count); -void page_cache_async_ra(struct readahead_control *, struct page *, +void page_cache_async_ra(struct readahead_control *, struct folio *, unsigned long req_count); void readahead_expand(struct readahead_control *ractl, loff_t new_start, size_t new_len); @@ -1033,7 +1218,7 @@ void page_cache_sync_readahead(struct address_space *mapping, * @mapping: address_space which holds the pagecache and I/O vectors * @ra: file_ra_state which holds the readahead state * @file: Used by the filesystem for authentication. - * @page: The page at @index which triggered the readahead call. + * @folio: The folio at @index which triggered the readahead call. * @index: Index of first page to be read. * @req_count: Total number of pages being read by the caller. * @@ -1045,10 +1230,10 @@ void page_cache_sync_readahead(struct address_space *mapping, static inline void page_cache_async_readahead(struct address_space *mapping, struct file_ra_state *ra, struct file *file, - struct page *page, pgoff_t index, unsigned long req_count) + struct folio *folio, pgoff_t index, unsigned long req_count) { DEFINE_READAHEAD(ractl, file, ra, mapping, index); - page_cache_async_ra(&ractl, page, req_count); + page_cache_async_ra(&ractl, folio, req_count); } static inline struct folio *__readahead_folio(struct readahead_control *ractl) @@ -1125,16 +1310,6 @@ static inline unsigned int __readahead_batch(struct readahead_control *rac, VM_BUG_ON_PAGE(PageTail(page), page); array[i++] = page; rac->_batch_count += thp_nr_pages(page); - - /* - * The page cache isn't using multi-index entries yet, - * so the xas cursor needs to be manually moved to the - * next index. This can be removed once the page cache - * is converted. - */ - if (PageHead(page)) - xas_set(&xas, rac->_index + rac->_batch_count); - if (i == array_sz) break; } diff --git a/include/linux/pagevec.h b/include/linux/pagevec.h index 7f3f19065a9f..215eb6c3bdc9 100644 --- a/include/linux/pagevec.h +++ b/include/linux/pagevec.h @@ -15,8 +15,10 @@ #define PAGEVEC_SIZE 15 struct page; +struct folio; struct address_space; +/* Layout must match folio_batch */ struct pagevec { unsigned char nr; bool percpu_pvec_drained; @@ -24,18 +26,6 @@ struct pagevec { }; void __pagevec_release(struct pagevec *pvec); -void __pagevec_lru_add(struct pagevec *pvec); -void pagevec_remove_exceptionals(struct pagevec *pvec); -unsigned pagevec_lookup_range(struct pagevec *pvec, - struct address_space *mapping, - pgoff_t *start, pgoff_t end); -static inline unsigned pagevec_lookup(struct pagevec *pvec, - struct address_space *mapping, - pgoff_t *start) -{ - return pagevec_lookup_range(pvec, mapping, start, (pgoff_t)-1); -} - unsigned pagevec_lookup_range_tag(struct pagevec *pvec, struct address_space *mapping, pgoff_t *index, pgoff_t end, xa_mark_t tag); @@ -81,4 +71,69 @@ static inline void pagevec_release(struct pagevec *pvec) __pagevec_release(pvec); } +/** + * struct folio_batch - A collection of folios. + * + * The folio_batch is used to amortise the cost of retrieving and + * operating on a set of folios. The order of folios in the batch may be + * significant (eg delete_from_page_cache_batch()). Some users of the + * folio_batch store "exceptional" entries in it which can be removed + * by calling folio_batch_remove_exceptionals(). + */ +struct folio_batch { + unsigned char nr; + bool percpu_pvec_drained; + struct folio *folios[PAGEVEC_SIZE]; +}; + +/* Layout must match pagevec */ +static_assert(sizeof(struct pagevec) == sizeof(struct folio_batch)); +static_assert(offsetof(struct pagevec, pages) == + offsetof(struct folio_batch, folios)); + +/** + * folio_batch_init() - Initialise a batch of folios + * @fbatch: The folio batch. + * + * A freshly initialised folio_batch contains zero folios. + */ +static inline void folio_batch_init(struct folio_batch *fbatch) +{ + fbatch->nr = 0; + fbatch->percpu_pvec_drained = false; +} + +static inline unsigned int folio_batch_count(struct folio_batch *fbatch) +{ + return fbatch->nr; +} + +static inline unsigned int fbatch_space(struct folio_batch *fbatch) +{ + return PAGEVEC_SIZE - fbatch->nr; +} + +/** + * folio_batch_add() - Add a folio to a batch. + * @fbatch: The folio batch. + * @folio: The folio to add. + * + * The folio is added to the end of the batch. + * The batch must have previously been initialised using folio_batch_init(). + * + * Return: The number of slots still available. + */ +static inline unsigned folio_batch_add(struct folio_batch *fbatch, + struct folio *folio) +{ + fbatch->folios[fbatch->nr++] = folio; + return fbatch_space(fbatch); +} + +static inline void folio_batch_release(struct folio_batch *fbatch) +{ + pagevec_release((struct pagevec *)fbatch); +} + +void folio_batch_remove_exceptionals(struct folio_batch *fbatch); #endif /* _LINUX_PAGEVEC_H */ diff --git a/include/linux/pagewalk.h b/include/linux/pagewalk.h index ac7b38ad5903..f3fafb731ffd 100644 --- a/include/linux/pagewalk.h +++ b/include/linux/pagewalk.h @@ -15,12 +15,12 @@ struct mm_walk; * this handler is required to be able to handle * pmd_trans_huge() pmds. They may simply choose to * split_huge_page() instead of handling it explicitly. - * @pte_entry: if set, called for each non-empty PTE (lowest-level) - * entry + * @pte_entry: if set, called for each PTE (lowest-level) entry, + * including empty ones * @pte_hole: if set, called for each hole at all levels, - * depth is -1 if not known, 0:PGD, 1:P4D, 2:PUD, 3:PMD - * 4:PTE. Any folded depths (where PTRS_PER_P?D is equal - * to 1) are skipped. + * depth is -1 if not known, 0:PGD, 1:P4D, 2:PUD, 3:PMD. + * Any folded depths (where PTRS_PER_P?D is equal to 1) + * are skipped. * @hugetlb_entry: if set, called for each hugetlb entry * @test_walk: caller specific callback function to determine whether * we walk over the current vma or not. Returning 0 means diff --git a/include/linux/panic.h b/include/linux/panic.h index f5844908a089..c7759b3f2045 100644 --- a/include/linux/panic.h +++ b/include/linux/panic.h @@ -15,12 +15,6 @@ extern void oops_enter(void); extern void oops_exit(void); extern bool oops_may_print(void); -#ifdef CONFIG_SMP -extern unsigned int sysctl_oops_all_cpu_backtrace; -#else -#define sysctl_oops_all_cpu_backtrace 0 -#endif /* CONFIG_SMP */ - extern int panic_timeout; extern unsigned long panic_print; extern int panic_on_oops; @@ -74,7 +68,8 @@ static inline void set_arch_panic_timeout(int timeout, int arch_default_timeout) #define TAINT_LIVEPATCH 15 #define TAINT_AUX 16 #define TAINT_RANDSTRUCT 17 -#define TAINT_FLAGS_COUNT 18 +#define TAINT_TEST 18 +#define TAINT_FLAGS_COUNT 19 #define TAINT_FLAGS_MAX ((1UL << TAINT_FLAGS_COUNT) - 1) struct taint_flag { diff --git a/include/linux/part_stat.h b/include/linux/part_stat.h index 6f7949b2fd8d..abeba356bc3f 100644 --- a/include/linux/part_stat.h +++ b/include/linux/part_stat.h @@ -2,7 +2,7 @@ #ifndef _LINUX_PART_STAT_H #define _LINUX_PART_STAT_H -#include <linux/genhd.h> +#include <linux/blkdev.h> #include <asm/local.h> struct disk_stats { diff --git a/include/linux/pci-dma-compat.h b/include/linux/pci-dma-compat.h deleted file mode 100644 index 249d4d7fbf18..000000000000 --- a/include/linux/pci-dma-compat.h +++ /dev/null @@ -1,129 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* include this file if the platform implements the dma_ DMA Mapping API - * and wants to provide the pci_ DMA Mapping API in terms of it */ - -#ifndef _ASM_GENERIC_PCI_DMA_COMPAT_H -#define _ASM_GENERIC_PCI_DMA_COMPAT_H - -#include <linux/dma-mapping.h> - -/* This defines the direction arg to the DMA mapping routines. */ -#define PCI_DMA_BIDIRECTIONAL DMA_BIDIRECTIONAL -#define PCI_DMA_TODEVICE DMA_TO_DEVICE -#define PCI_DMA_FROMDEVICE DMA_FROM_DEVICE -#define PCI_DMA_NONE DMA_NONE - -static inline void * -pci_alloc_consistent(struct pci_dev *hwdev, size_t size, - dma_addr_t *dma_handle) -{ - return dma_alloc_coherent(&hwdev->dev, size, dma_handle, GFP_ATOMIC); -} - -static inline void * -pci_zalloc_consistent(struct pci_dev *hwdev, size_t size, - dma_addr_t *dma_handle) -{ - return dma_alloc_coherent(&hwdev->dev, size, dma_handle, GFP_ATOMIC); -} - -static inline void -pci_free_consistent(struct pci_dev *hwdev, size_t size, - void *vaddr, dma_addr_t dma_handle) -{ - dma_free_coherent(&hwdev->dev, size, vaddr, dma_handle); -} - -static inline dma_addr_t -pci_map_single(struct pci_dev *hwdev, void *ptr, size_t size, int direction) -{ - return dma_map_single(&hwdev->dev, ptr, size, (enum dma_data_direction)direction); -} - -static inline void -pci_unmap_single(struct pci_dev *hwdev, dma_addr_t dma_addr, - size_t size, int direction) -{ - dma_unmap_single(&hwdev->dev, dma_addr, size, (enum dma_data_direction)direction); -} - -static inline dma_addr_t -pci_map_page(struct pci_dev *hwdev, struct page *page, - unsigned long offset, size_t size, int direction) -{ - return dma_map_page(&hwdev->dev, page, offset, size, (enum dma_data_direction)direction); -} - -static inline void -pci_unmap_page(struct pci_dev *hwdev, dma_addr_t dma_address, - size_t size, int direction) -{ - dma_unmap_page(&hwdev->dev, dma_address, size, (enum dma_data_direction)direction); -} - -static inline int -pci_map_sg(struct pci_dev *hwdev, struct scatterlist *sg, - int nents, int direction) -{ - return dma_map_sg(&hwdev->dev, sg, nents, (enum dma_data_direction)direction); -} - -static inline void -pci_unmap_sg(struct pci_dev *hwdev, struct scatterlist *sg, - int nents, int direction) -{ - dma_unmap_sg(&hwdev->dev, sg, nents, (enum dma_data_direction)direction); -} - -static inline void -pci_dma_sync_single_for_cpu(struct pci_dev *hwdev, dma_addr_t dma_handle, - size_t size, int direction) -{ - dma_sync_single_for_cpu(&hwdev->dev, dma_handle, size, (enum dma_data_direction)direction); -} - -static inline void -pci_dma_sync_single_for_device(struct pci_dev *hwdev, dma_addr_t dma_handle, - size_t size, int direction) -{ - dma_sync_single_for_device(&hwdev->dev, dma_handle, size, (enum dma_data_direction)direction); -} - -static inline void -pci_dma_sync_sg_for_cpu(struct pci_dev *hwdev, struct scatterlist *sg, - int nelems, int direction) -{ - dma_sync_sg_for_cpu(&hwdev->dev, sg, nelems, (enum dma_data_direction)direction); -} - -static inline void -pci_dma_sync_sg_for_device(struct pci_dev *hwdev, struct scatterlist *sg, - int nelems, int direction) -{ - dma_sync_sg_for_device(&hwdev->dev, sg, nelems, (enum dma_data_direction)direction); -} - -static inline int -pci_dma_mapping_error(struct pci_dev *pdev, dma_addr_t dma_addr) -{ - return dma_mapping_error(&pdev->dev, dma_addr); -} - -#ifdef CONFIG_PCI -static inline int pci_set_dma_mask(struct pci_dev *dev, u64 mask) -{ - return dma_set_mask(&dev->dev, mask); -} - -static inline int pci_set_consistent_dma_mask(struct pci_dev *dev, u64 mask) -{ - return dma_set_coherent_mask(&dev->dev, mask); -} -#else -static inline int pci_set_dma_mask(struct pci_dev *dev, u64 mask) -{ return -EIO; } -static inline int pci_set_consistent_dma_mask(struct pci_dev *dev, u64 mask) -{ return -EIO; } -#endif - -#endif diff --git a/include/linux/pci-doe.h b/include/linux/pci-doe.h new file mode 100644 index 000000000000..ed9b4df792b8 --- /dev/null +++ b/include/linux/pci-doe.h @@ -0,0 +1,77 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Data Object Exchange + * PCIe r6.0, sec 6.30 DOE + * + * Copyright (C) 2021 Huawei + * Jonathan Cameron <Jonathan.Cameron@huawei.com> + * + * Copyright (C) 2022 Intel Corporation + * Ira Weiny <ira.weiny@intel.com> + */ + +#ifndef LINUX_PCI_DOE_H +#define LINUX_PCI_DOE_H + +struct pci_doe_protocol { + u16 vid; + u8 type; +}; + +struct pci_doe_mb; + +/** + * struct pci_doe_task - represents a single query/response + * + * @prot: DOE Protocol + * @request_pl: The request payload + * @request_pl_sz: Size of the request payload (bytes) + * @response_pl: The response payload + * @response_pl_sz: Size of the response payload (bytes) + * @rv: Return value. Length of received response or error (bytes) + * @complete: Called when task is complete + * @private: Private data for the consumer + * @work: Used internally by the mailbox + * @doe_mb: Used internally by the mailbox + * + * The payload sizes and rv are specified in bytes with the following + * restrictions concerning the protocol. + * + * 1) The request_pl_sz must be a multiple of double words (4 bytes) + * 2) The response_pl_sz must be >= a single double word (4 bytes) + * 3) rv is returned as bytes but it will be a multiple of double words + * + * NOTE there is no need for the caller to initialize work or doe_mb. + */ +struct pci_doe_task { + struct pci_doe_protocol prot; + u32 *request_pl; + size_t request_pl_sz; + u32 *response_pl; + size_t response_pl_sz; + int rv; + void (*complete)(struct pci_doe_task *task); + void *private; + + /* No need for the user to initialize these fields */ + struct work_struct work; + struct pci_doe_mb *doe_mb; +}; + +/** + * pci_doe_for_each_off - Iterate each DOE capability + * @pdev: struct pci_dev to iterate + * @off: u16 of config space offset of each mailbox capability found + */ +#define pci_doe_for_each_off(pdev, off) \ + for (off = pci_find_next_ext_capability(pdev, off, \ + PCI_EXT_CAP_ID_DOE); \ + off > 0; \ + off = pci_find_next_ext_capability(pdev, off, \ + PCI_EXT_CAP_ID_DOE)) + +struct pci_doe_mb *pcim_doe_create_mb(struct pci_dev *pdev, u16 cap_offset); +bool pci_doe_supports_prot(struct pci_doe_mb *doe_mb, u16 vid, u8 type); +int pci_doe_submit_task(struct pci_doe_mb *doe_mb, struct pci_doe_task *task); + +#endif diff --git a/include/linux/pci-ecam.h b/include/linux/pci-ecam.h index adea5a4771cf..6b1301e2498e 100644 --- a/include/linux/pci-ecam.h +++ b/include/linux/pci-ecam.h @@ -87,6 +87,7 @@ extern const struct pci_ecam_ops xgene_v1_pcie_ecam_ops; /* APM X-Gene PCIe v1 * extern const struct pci_ecam_ops xgene_v2_pcie_ecam_ops; /* APM X-Gene PCIe v2.x */ extern const struct pci_ecam_ops al_pcie_ops; /* Amazon Annapurna Labs PCIe */ extern const struct pci_ecam_ops tegra194_pcie_ops; /* Tegra194 PCIe */ +extern const struct pci_ecam_ops loongson_pci_ecam_ops; /* Loongson PCIe */ #endif #if IS_ENABLED(CONFIG_PCI_HOST_COMMON) diff --git a/include/linux/pci-p2pdma.h b/include/linux/pci-p2pdma.h index 8318a97c9c61..2c07aa6b7665 100644 --- a/include/linux/pci-p2pdma.h +++ b/include/linux/pci-p2pdma.h @@ -30,10 +30,6 @@ struct scatterlist *pci_p2pmem_alloc_sgl(struct pci_dev *pdev, unsigned int *nents, u32 length); void pci_p2pmem_free_sgl(struct pci_dev *pdev, struct scatterlist *sgl); void pci_p2pmem_publish(struct pci_dev *pdev, bool publish); -int pci_p2pdma_map_sg_attrs(struct device *dev, struct scatterlist *sg, - int nents, enum dma_data_direction dir, unsigned long attrs); -void pci_p2pdma_unmap_sg_attrs(struct device *dev, struct scatterlist *sg, - int nents, enum dma_data_direction dir, unsigned long attrs); int pci_p2pdma_enable_store(const char *page, struct pci_dev **p2p_dev, bool *use_p2pdma); ssize_t pci_p2pdma_enable_show(char *page, struct pci_dev *p2p_dev, @@ -83,17 +79,6 @@ static inline void pci_p2pmem_free_sgl(struct pci_dev *pdev, static inline void pci_p2pmem_publish(struct pci_dev *pdev, bool publish) { } -static inline int pci_p2pdma_map_sg_attrs(struct device *dev, - struct scatterlist *sg, int nents, enum dma_data_direction dir, - unsigned long attrs) -{ - return 0; -} -static inline void pci_p2pdma_unmap_sg_attrs(struct device *dev, - struct scatterlist *sg, int nents, enum dma_data_direction dir, - unsigned long attrs) -{ -} static inline int pci_p2pdma_enable_store(const char *page, struct pci_dev **p2p_dev, bool *use_p2pdma) { @@ -119,16 +104,4 @@ static inline struct pci_dev *pci_p2pmem_find(struct device *client) return pci_p2pmem_find_many(&client, 1); } -static inline int pci_p2pdma_map_sg(struct device *dev, struct scatterlist *sg, - int nents, enum dma_data_direction dir) -{ - return pci_p2pdma_map_sg_attrs(dev, sg, nents, dir, 0); -} - -static inline void pci_p2pdma_unmap_sg(struct device *dev, - struct scatterlist *sg, int nents, enum dma_data_direction dir) -{ - pci_p2pdma_unmap_sg_attrs(dev, sg, nents, dir, 0); -} - #endif /* _LINUX_PCI_P2P_H */ diff --git a/include/linux/pci.h b/include/linux/pci.h index 18a75c8e615c..2bda4a4e47e8 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -155,6 +155,15 @@ enum pci_interrupt_pin { #define PCI_NUM_INTX 4 /* + * Reading from a device that doesn't respond typically returns ~0. A + * successful read from a device may also return ~0, so you need additional + * information to reliably identify errors. + */ +#define PCI_ERROR_RESPONSE (~0ULL) +#define PCI_SET_ERROR_RESPONSE(val) (*(val) = ((typeof(*(val))) PCI_ERROR_RESPONSE)) +#define PCI_POSSIBLE_ERROR(val) ((val) == ((typeof(val)) PCI_ERROR_RESPONSE)) + +/* * pci_power_t values must match the bits in the Capabilities PME_Support * and Control/Status PowerState fields in the Power Management capability. */ @@ -370,10 +379,6 @@ struct pci_dev { unsigned int mmio_always_on:1; /* Disallow turning off io/mem decoding during BAR sizing */ unsigned int wakeup_prepared:1; - unsigned int runtime_d3cold:1; /* Whether go through runtime - D3cold, not set for devices - powered on/off by the - corresponding bridge */ unsigned int skip_bus_pm:1; /* Internal: Skip bus-level PM */ unsigned int ignore_hotplug:1; /* Ignore hotplug events */ unsigned int hotplug_user_indicators:1; /* SlotCtl indicators @@ -425,7 +430,8 @@ struct pci_dev { unsigned int ats_enabled:1; /* Address Translation Svc */ unsigned int pasid_enabled:1; /* Process Address Space ID */ unsigned int pri_enabled:1; /* Page Request Interface */ - unsigned int is_managed:1; + unsigned int is_managed:1; /* Managed via devres */ + unsigned int is_msi_managed:1; /* MSI release via devres installed */ unsigned int needs_freset:1; /* Requires fundamental reset */ unsigned int state_saved:1; unsigned int is_physfn:1; @@ -455,6 +461,7 @@ struct pci_dev { unsigned int link_active_reporting:1;/* Device capable of reporting link active */ unsigned int no_vf_scan:1; /* Don't scan for VFs after IOV enablement */ unsigned int no_command_memory:1; /* No PCI_COMMAND_MEMORY */ + unsigned int rom_bar_overlap:1; /* ROM BAR disable broken */ pci_dev_flags_t dev_flags; atomic_t enable_cnt; /* pci_enable_device has been called */ @@ -468,12 +475,14 @@ struct pci_dev { unsigned int broken_cmd_compl:1; /* No compl for some cmds */ #endif #ifdef CONFIG_PCIE_PTM + u16 ptm_cap; /* PTM Capability */ unsigned int ptm_root:1; unsigned int ptm_enabled:1; u8 ptm_granularity; #endif #ifdef CONFIG_PCI_MSI - const struct attribute_group **msi_irq_groups; + void __iomem *msix_base; + raw_spinlock_t msi_lock; #endif struct pci_vpd vpd; #ifdef CONFIG_PCIE_DPC @@ -504,7 +513,11 @@ struct pci_dev { u16 acs_cap; /* ACS Capability offset */ phys_addr_t rom; /* Physical address if not from BAR */ size_t romlen; /* Length if not from BAR */ - char *driver_override; /* Driver name to force a match */ + /* + * Driver name to force a match. Do not set directly, because core + * frees it. Use driver_set_override() to set or clear it. + */ + const char *driver_override; unsigned long priv_flags; /* Private flags for the PCI driver */ @@ -656,6 +669,7 @@ struct pci_bus { struct bin_attribute *legacy_io; /* Legacy I/O for this bus */ struct bin_attribute *legacy_mem; /* Legacy mem */ unsigned int is_added:1; + unsigned int unsafe_warn:1; /* warned about RW1C config write */ }; #define to_pci_bus(n) container_of(n, struct pci_bus, dev) @@ -882,6 +896,13 @@ struct module; * created once it is bound to the driver. * @driver: Driver model structure. * @dynids: List of dynamically added device IDs. + * @driver_managed_dma: Device driver doesn't use kernel DMA API for DMA. + * For most device drivers, no need to care about this flag + * as long as all DMAs are handled through the kernel DMA API. + * For some special ones, for example VFIO drivers, they know + * how to manage the DMA themselves and set this flag so that + * the IOMMU layer will allow them to setup and manage their + * own I/O address space. */ struct pci_driver { struct list_head node; @@ -900,6 +921,7 @@ struct pci_driver { const struct attribute_group **dev_groups; struct device_driver driver; struct pci_dynids dynids; + bool driver_managed_dma; }; static inline struct pci_driver *to_pci_driver(struct device_driver *drv) @@ -1656,10 +1678,12 @@ bool pci_ats_disabled(void); #ifdef CONFIG_PCIE_PTM int pci_enable_ptm(struct pci_dev *dev, u8 *granularity); +void pci_disable_ptm(struct pci_dev *dev); bool pcie_ptm_enabled(struct pci_dev *dev); #else static inline int pci_enable_ptm(struct pci_dev *dev, u8 *granularity) { return -EINVAL; } +static inline void pci_disable_ptm(struct pci_dev *dev) { } static inline bool pcie_ptm_enabled(struct pci_dev *dev) { return false; } #endif @@ -1775,7 +1799,10 @@ static inline struct pci_dev *pci_get_class(unsigned int class, struct pci_dev *from) { return NULL; } -#define pci_dev_present(ids) (0) + +static inline int pci_dev_present(const struct pci_device_id *ids) +{ return 0; } + #define no_pci_devices() (1) #define pci_dev_put(dev) do { } while (0) @@ -1885,24 +1912,14 @@ pci_alloc_irq_vectors(struct pci_dev *dev, unsigned int min_vecs, #include <asm/pci.h> -/* These two functions provide almost identical functionality. Depending - * on the architecture, one will be implemented as a wrapper around the - * other (in drivers/pci/mmap.c). - * +/* * pci_mmap_resource_range() maps a specific BAR, and vm->vm_pgoff * is expected to be an offset within that region. * - * pci_mmap_page_range() is the legacy architecture-specific interface, - * which accepts a "user visible" resource address converted by - * pci_resource_to_user(), as used in the legacy mmap() interface in - * /proc/bus/pci/. */ int pci_mmap_resource_range(struct pci_dev *dev, int bar, struct vm_area_struct *vma, enum pci_mmap_state mmap_state, int write_combine); -int pci_mmap_page_range(struct pci_dev *pdev, int bar, - struct vm_area_struct *vma, - enum pci_mmap_state mmap_state, int write_combine); #ifndef arch_can_pci_mmap_wc #define arch_can_pci_mmap_wc() 0 @@ -2005,8 +2022,8 @@ enum pci_fixup_pass { #ifdef CONFIG_LTO_CLANG #define __DECLARE_PCI_FIXUP_SECTION(sec, name, vendor, device, class, \ class_shift, hook, stub) \ - void __cficanonical stub(struct pci_dev *dev); \ - void __cficanonical stub(struct pci_dev *dev) \ + void stub(struct pci_dev *dev); \ + void stub(struct pci_dev *dev) \ { \ hook(dev); \ } \ @@ -2151,7 +2168,8 @@ void __iomem *pci_ioremap_wc_bar(struct pci_dev *pdev, int bar); #ifdef CONFIG_PCI_IOV int pci_iov_virtfn_bus(struct pci_dev *dev, int id); int pci_iov_virtfn_devfn(struct pci_dev *dev, int id); - +int pci_iov_vf_id(struct pci_dev *dev); +void *pci_iov_get_pf_drvdata(struct pci_dev *dev, struct pci_driver *pf_driver); int pci_enable_sriov(struct pci_dev *dev, int nr_virtfn); void pci_disable_sriov(struct pci_dev *dev); @@ -2179,6 +2197,18 @@ static inline int pci_iov_virtfn_devfn(struct pci_dev *dev, int id) { return -ENOSYS; } + +static inline int pci_iov_vf_id(struct pci_dev *dev) +{ + return -ENOSYS; +} + +static inline void *pci_iov_get_pf_drvdata(struct pci_dev *dev, + struct pci_driver *pf_driver) +{ + return ERR_PTR(-EINVAL); +} + static inline int pci_enable_sriov(struct pci_dev *dev, int nr_virtfn) { return -ENODEV; } @@ -2444,8 +2474,7 @@ static inline bool pci_is_thunderbolt_attached(struct pci_dev *pdev) void pci_uevent_ers(struct pci_dev *pdev, enum pci_ers_result err_type); #endif -/* Provide the legacy pci_dma_* API */ -#include <linux/pci-dma-compat.h> +#include <linux/dma-mapping.h> #define pci_printk(level, pdev, fmt, arg...) \ dev_printk(level, &(pdev)->dev, fmt, ##arg) diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index b5248f27910e..b362d90eb9b0 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -60,6 +60,8 @@ #define PCI_CLASS_BRIDGE_EISA 0x0602 #define PCI_CLASS_BRIDGE_MC 0x0603 #define PCI_CLASS_BRIDGE_PCI 0x0604 +#define PCI_CLASS_BRIDGE_PCI_NORMAL 0x060400 +#define PCI_CLASS_BRIDGE_PCI_SUBTRACTIVE 0x060401 #define PCI_CLASS_BRIDGE_PCMCIA 0x0605 #define PCI_CLASS_BRIDGE_NUBUS 0x0606 #define PCI_CLASS_BRIDGE_CARDBUS 0x0607 @@ -73,6 +75,9 @@ #define PCI_CLASS_COMMUNICATION_MODEM 0x0703 #define PCI_CLASS_COMMUNICATION_OTHER 0x0780 +/* Interface for SERIAL/MODEM */ +#define PCI_SERIAL_16550_COMPATIBLE 0x02 + #define PCI_BASE_CLASS_SYSTEM 0x08 #define PCI_CLASS_SYSTEM_PIC 0x0800 #define PCI_CLASS_SYSTEM_PIC_IOAPIC 0x080010 @@ -149,6 +154,7 @@ #define PCI_CLASS_OTHERS 0xff /* Vendors and devices. Sort key: vendor first, device next. */ +#define PCI_VENDOR_ID_PCI_SIG 0x0001 #define PCI_VENDOR_ID_LOONGSON 0x0014 @@ -554,10 +560,13 @@ #define PCI_DEVICE_ID_AMD_17H_M30H_DF_F3 0x1493 #define PCI_DEVICE_ID_AMD_17H_M60H_DF_F3 0x144b #define PCI_DEVICE_ID_AMD_17H_M70H_DF_F3 0x1443 +#define PCI_DEVICE_ID_AMD_17H_MA0H_DF_F3 0x1727 #define PCI_DEVICE_ID_AMD_19H_DF_F3 0x1653 #define PCI_DEVICE_ID_AMD_19H_M10H_DF_F3 0x14b0 #define PCI_DEVICE_ID_AMD_19H_M40H_DF_F3 0x167c #define PCI_DEVICE_ID_AMD_19H_M50H_DF_F3 0x166d +#define PCI_DEVICE_ID_AMD_19H_M60H_DF_F3 0x14e3 +#define PCI_DEVICE_ID_AMD_19H_M70H_DF_F3 0x14f3 #define PCI_DEVICE_ID_AMD_CNB17H_F3 0x1703 #define PCI_DEVICE_ID_AMD_LANCE 0x2000 #define PCI_DEVICE_ID_AMD_LANCE_HOME 0x2001 @@ -1965,24 +1974,6 @@ #define PCI_DEVICE_ID_APPLICOM_PCI2000PFB 0x0003 #define PCI_VENDOR_ID_MOXA 0x1393 -#define PCI_DEVICE_ID_MOXA_RC7000 0x0001 -#define PCI_DEVICE_ID_MOXA_CP102 0x1020 -#define PCI_DEVICE_ID_MOXA_CP102UL 0x1021 -#define PCI_DEVICE_ID_MOXA_CP102U 0x1022 -#define PCI_DEVICE_ID_MOXA_C104 0x1040 -#define PCI_DEVICE_ID_MOXA_CP104U 0x1041 -#define PCI_DEVICE_ID_MOXA_CP104JU 0x1042 -#define PCI_DEVICE_ID_MOXA_CP104EL 0x1043 -#define PCI_DEVICE_ID_MOXA_CT114 0x1140 -#define PCI_DEVICE_ID_MOXA_CP114 0x1141 -#define PCI_DEVICE_ID_MOXA_CP118U 0x1180 -#define PCI_DEVICE_ID_MOXA_CP118EL 0x1181 -#define PCI_DEVICE_ID_MOXA_CP132 0x1320 -#define PCI_DEVICE_ID_MOXA_CP132U 0x1321 -#define PCI_DEVICE_ID_MOXA_CP134U 0x1340 -#define PCI_DEVICE_ID_MOXA_C168 0x1680 -#define PCI_DEVICE_ID_MOXA_CP168U 0x1681 -#define PCI_DEVICE_ID_MOXA_CP168EL 0x1682 #define PCI_DEVICE_ID_MOXA_CP204J 0x2040 #define PCI_DEVICE_ID_MOXA_C218 0x2180 #define PCI_DEVICE_ID_MOXA_C320 0x3200 @@ -2091,6 +2082,9 @@ #define PCI_DEVICE_ID_ICE_1712 0x1712 #define PCI_DEVICE_ID_VT1724 0x1724 +#define PCI_VENDOR_ID_MICROSOFT 0x1414 +#define PCI_DEVICE_ID_HYPERV_VIDEO 0x5353 + #define PCI_VENDOR_ID_OXSEMI 0x1415 #define PCI_DEVICE_ID_OXSEMI_12PCI840 0x8403 #define PCI_DEVICE_ID_OXSEMI_PCIe840 0xC000 @@ -2547,11 +2541,16 @@ #define PCI_DEVICE_ID_KORENIX_JETCARDF3 0x17ff #define PCI_VENDOR_ID_HUAWEI 0x19e5 +#define PCI_DEVICE_ID_HUAWEI_ZIP_VF 0xa251 +#define PCI_DEVICE_ID_HUAWEI_SEC_VF 0xa256 +#define PCI_DEVICE_ID_HUAWEI_HPRE_VF 0xa259 #define PCI_VENDOR_ID_NETRONOME 0x19ee +#define PCI_DEVICE_ID_NETRONOME_NFP3800 0x3800 #define PCI_DEVICE_ID_NETRONOME_NFP4000 0x4000 #define PCI_DEVICE_ID_NETRONOME_NFP5000 0x5000 #define PCI_DEVICE_ID_NETRONOME_NFP6000 0x6000 +#define PCI_DEVICE_ID_NETRONOME_NFP3800_VF 0x3803 #define PCI_DEVICE_ID_NETRONOME_NFP6000_VF 0x6003 #define PCI_VENDOR_ID_QMI 0x1a32 @@ -2579,6 +2578,8 @@ #define PCI_VENDOR_ID_HYGON 0x1d94 +#define PCI_VENDOR_ID_FUNGIBLE 0x1dad + #define PCI_VENDOR_ID_HXT 0x1dbf #define PCI_VENDOR_ID_TEKRAM 0x1de1 @@ -2636,8 +2637,8 @@ #define PCI_DEVICE_ID_INTEL_PXHD_0 0x0320 #define PCI_DEVICE_ID_INTEL_PXHD_1 0x0321 #define PCI_DEVICE_ID_INTEL_PXH_0 0x0329 -#define PCI_DEVICE_ID_INTEL_PXH_1 0x032A -#define PCI_DEVICE_ID_INTEL_PXHV 0x032C +#define PCI_DEVICE_ID_INTEL_PXH_1 0x032a +#define PCI_DEVICE_ID_INTEL_PXHV 0x032c #define PCI_DEVICE_ID_INTEL_80332_0 0x0330 #define PCI_DEVICE_ID_INTEL_80332_1 0x0332 #define PCI_DEVICE_ID_INTEL_80333_0 0x0370 @@ -2655,14 +2656,14 @@ #define PCI_DEVICE_ID_INTEL_MFD_SDIO2 0x0822 #define PCI_DEVICE_ID_INTEL_MFD_EMMC0 0x0823 #define PCI_DEVICE_ID_INTEL_MFD_EMMC1 0x0824 -#define PCI_DEVICE_ID_INTEL_MRST_SD2 0x084F -#define PCI_DEVICE_ID_INTEL_QUARK_X1000_ILB 0x095E +#define PCI_DEVICE_ID_INTEL_MRST_SD2 0x084f +#define PCI_DEVICE_ID_INTEL_QUARK_X1000_ILB 0x095e #define PCI_DEVICE_ID_INTEL_I960 0x0960 #define PCI_DEVICE_ID_INTEL_I960RM 0x0962 #define PCI_DEVICE_ID_INTEL_CENTERTON_ILB 0x0c60 #define PCI_DEVICE_ID_INTEL_8257X_SOL 0x1062 #define PCI_DEVICE_ID_INTEL_82573E_SOL 0x1085 -#define PCI_DEVICE_ID_INTEL_82573L_SOL 0x108F +#define PCI_DEVICE_ID_INTEL_82573L_SOL 0x108f #define PCI_DEVICE_ID_INTEL_82815_MC 0x1130 #define PCI_DEVICE_ID_INTEL_82815_CGC 0x1132 #define PCI_DEVICE_ID_INTEL_82092AA_0 0x1221 @@ -2756,12 +2757,6 @@ #define PCI_DEVICE_ID_INTEL_82801EB_11 0x24db #define PCI_DEVICE_ID_INTEL_82801EB_12 0x24dc #define PCI_DEVICE_ID_INTEL_82801EB_13 0x24dd -#define PCI_DEVICE_ID_INTEL_ESB_1 0x25a1 -#define PCI_DEVICE_ID_INTEL_ESB_2 0x25a2 -#define PCI_DEVICE_ID_INTEL_ESB_4 0x25a4 -#define PCI_DEVICE_ID_INTEL_ESB_5 0x25a6 -#define PCI_DEVICE_ID_INTEL_ESB_9 0x25ab -#define PCI_DEVICE_ID_INTEL_ESB_10 0x25ac #define PCI_DEVICE_ID_INTEL_82820_HB 0x2500 #define PCI_DEVICE_ID_INTEL_82820_UP_HB 0x2501 #define PCI_DEVICE_ID_INTEL_82850_HB 0x2530 @@ -2776,14 +2771,15 @@ #define PCI_DEVICE_ID_INTEL_82915G_IG 0x2582 #define PCI_DEVICE_ID_INTEL_82915GM_HB 0x2590 #define PCI_DEVICE_ID_INTEL_82915GM_IG 0x2592 -#define PCI_DEVICE_ID_INTEL_5000_ERR 0x25F0 -#define PCI_DEVICE_ID_INTEL_5000_FBD0 0x25F5 -#define PCI_DEVICE_ID_INTEL_5000_FBD1 0x25F6 -#define PCI_DEVICE_ID_INTEL_82945G_HB 0x2770 -#define PCI_DEVICE_ID_INTEL_82945G_IG 0x2772 -#define PCI_DEVICE_ID_INTEL_3000_HB 0x2778 -#define PCI_DEVICE_ID_INTEL_82945GM_HB 0x27A0 -#define PCI_DEVICE_ID_INTEL_82945GM_IG 0x27A2 +#define PCI_DEVICE_ID_INTEL_ESB_1 0x25a1 +#define PCI_DEVICE_ID_INTEL_ESB_2 0x25a2 +#define PCI_DEVICE_ID_INTEL_ESB_4 0x25a4 +#define PCI_DEVICE_ID_INTEL_ESB_5 0x25a6 +#define PCI_DEVICE_ID_INTEL_ESB_9 0x25ab +#define PCI_DEVICE_ID_INTEL_ESB_10 0x25ac +#define PCI_DEVICE_ID_INTEL_5000_ERR 0x25f0 +#define PCI_DEVICE_ID_INTEL_5000_FBD0 0x25f5 +#define PCI_DEVICE_ID_INTEL_5000_FBD1 0x25f6 #define PCI_DEVICE_ID_INTEL_ICH6_0 0x2640 #define PCI_DEVICE_ID_INTEL_ICH6_1 0x2641 #define PCI_DEVICE_ID_INTEL_ICH6_2 0x2642 @@ -2795,6 +2791,11 @@ #define PCI_DEVICE_ID_INTEL_ESB2_14 0x2698 #define PCI_DEVICE_ID_INTEL_ESB2_17 0x269b #define PCI_DEVICE_ID_INTEL_ESB2_18 0x269e +#define PCI_DEVICE_ID_INTEL_82945G_HB 0x2770 +#define PCI_DEVICE_ID_INTEL_82945G_IG 0x2772 +#define PCI_DEVICE_ID_INTEL_3000_HB 0x2778 +#define PCI_DEVICE_ID_INTEL_82945GM_HB 0x27a0 +#define PCI_DEVICE_ID_INTEL_82945GM_IG 0x27a2 #define PCI_DEVICE_ID_INTEL_ICH7_0 0x27b8 #define PCI_DEVICE_ID_INTEL_ICH7_1 0x27b9 #define PCI_DEVICE_ID_INTEL_ICH7_30 0x27b0 @@ -2847,7 +2848,7 @@ #define PCI_DEVICE_ID_INTEL_LYNNFIELD_QPI_PHY0 0x2c91 #define PCI_DEVICE_ID_INTEL_LYNNFIELD_MCR 0x2c98 #define PCI_DEVICE_ID_INTEL_LYNNFIELD_MC_TAD 0x2c99 -#define PCI_DEVICE_ID_INTEL_LYNNFIELD_MC_TEST 0x2c9C +#define PCI_DEVICE_ID_INTEL_LYNNFIELD_MC_TEST 0x2c9c #define PCI_DEVICE_ID_INTEL_LYNNFIELD_MC_CH0_CTRL 0x2ca0 #define PCI_DEVICE_ID_INTEL_LYNNFIELD_MC_CH0_ADDR 0x2ca1 #define PCI_DEVICE_ID_INTEL_LYNNFIELD_MC_CH0_RANK 0x2ca2 @@ -2959,16 +2960,16 @@ #define PCI_DEVICE_ID_INTEL_SBRIDGE_BR 0x3cf5 /* 13.6 */ #define PCI_DEVICE_ID_INTEL_SBRIDGE_SAD1 0x3cf6 /* 12.7 */ #define PCI_DEVICE_ID_INTEL_IOAT_SNB 0x402f -#define PCI_DEVICE_ID_INTEL_5100_16 0x65f0 -#define PCI_DEVICE_ID_INTEL_5100_19 0x65f3 -#define PCI_DEVICE_ID_INTEL_5100_21 0x65f5 -#define PCI_DEVICE_ID_INTEL_5100_22 0x65f6 #define PCI_DEVICE_ID_INTEL_5400_ERR 0x4030 #define PCI_DEVICE_ID_INTEL_5400_FBD0 0x4035 #define PCI_DEVICE_ID_INTEL_5400_FBD1 0x4036 -#define PCI_DEVICE_ID_INTEL_IOAT_SCNB 0x65ff #define PCI_DEVICE_ID_INTEL_EP80579_0 0x5031 #define PCI_DEVICE_ID_INTEL_EP80579_1 0x5032 +#define PCI_DEVICE_ID_INTEL_5100_16 0x65f0 +#define PCI_DEVICE_ID_INTEL_5100_19 0x65f3 +#define PCI_DEVICE_ID_INTEL_5100_21 0x65f5 +#define PCI_DEVICE_ID_INTEL_5100_22 0x65f6 +#define PCI_DEVICE_ID_INTEL_IOAT_SCNB 0x65ff #define PCI_DEVICE_ID_INTEL_82371SB_0 0x7000 #define PCI_DEVICE_ID_INTEL_82371SB_1 0x7010 #define PCI_DEVICE_ID_INTEL_82371SB_2 0x7020 diff --git a/include/linux/pcs-altera-tse.h b/include/linux/pcs-altera-tse.h new file mode 100644 index 000000000000..92ab9f08e835 --- /dev/null +++ b/include/linux/pcs-altera-tse.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2022 Bootlin + * + * Maxime Chevallier <maxime.chevallier@bootlin.com> + */ + +#ifndef __LINUX_PCS_ALTERA_TSE_H +#define __LINUX_PCS_ALTERA_TSE_H + +struct phylink_pcs; +struct net_device; + +struct phylink_pcs *alt_tse_pcs_create(struct net_device *ndev, + void __iomem *pcs_base, int reg_width); + +#endif /* __LINUX_PCS_ALTERA_TSE_H */ diff --git a/include/linux/pcs-rzn1-miic.h b/include/linux/pcs-rzn1-miic.h new file mode 100644 index 000000000000..56d12b21365d --- /dev/null +++ b/include/linux/pcs-rzn1-miic.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2022 Schneider Electric + * + * Clément Léger <clement.leger@bootlin.com> + */ + +#ifndef __LINUX_PCS_MIIC_H +#define __LINUX_PCS_MIIC_H + +struct phylink; +struct device_node; + +struct phylink_pcs *miic_create(struct device *dev, struct device_node *np); + +void miic_destroy(struct phylink_pcs *pcs); + +#endif /* __LINUX_PCS_MIIC_H */ diff --git a/include/linux/pcs/pcs-xpcs.h b/include/linux/pcs/pcs-xpcs.h index add077a81b21..d2da1e0b4a92 100644 --- a/include/linux/pcs/pcs-xpcs.h +++ b/include/linux/pcs/pcs-xpcs.h @@ -17,6 +17,7 @@ #define DW_AN_C73 1 #define DW_AN_C37_SGMII 2 #define DW_2500BASEX 3 +#define DW_AN_C37_1000BASEX 4 struct xpcs_id; @@ -30,9 +31,8 @@ int xpcs_get_an_mode(struct dw_xpcs *xpcs, phy_interface_t interface); void xpcs_link_up(struct phylink_pcs *pcs, unsigned int mode, phy_interface_t interface, int speed, int duplex); int xpcs_do_config(struct dw_xpcs *xpcs, phy_interface_t interface, - unsigned int mode); -void xpcs_validate(struct dw_xpcs *xpcs, unsigned long *supported, - struct phylink_link_state *state); + unsigned int mode, const unsigned long *advertising); +void xpcs_get_interfaces(struct dw_xpcs *xpcs, unsigned long *interfaces); int xpcs_config_eee(struct dw_xpcs *xpcs, int mult_fact_100ns, int enable); struct dw_xpcs *xpcs_create(struct mdio_device *mdiodev, diff --git a/include/linux/pe.h b/include/linux/pe.h index daf09ffffe38..1d3836ef9d92 100644 --- a/include/linux/pe.h +++ b/include/linux/pe.h @@ -65,6 +65,8 @@ #define IMAGE_FILE_MACHINE_SH5 0x01a8 #define IMAGE_FILE_MACHINE_THUMB 0x01c2 #define IMAGE_FILE_MACHINE_WCEMIPSV2 0x0169 +#define IMAGE_FILE_MACHINE_LOONGARCH32 0x6232 +#define IMAGE_FILE_MACHINE_LOONGARCH64 0x6264 /* flags */ #define IMAGE_FILE_RELOCS_STRIPPED 0x0001 diff --git a/include/linux/peci-cpu.h b/include/linux/peci-cpu.h new file mode 100644 index 000000000000..ff8ae9c26c80 --- /dev/null +++ b/include/linux/peci-cpu.h @@ -0,0 +1,40 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright (c) 2021 Intel Corporation */ + +#ifndef __LINUX_PECI_CPU_H +#define __LINUX_PECI_CPU_H + +#include <linux/types.h> + +#include "../../arch/x86/include/asm/intel-family.h" + +#define PECI_PCS_PKG_ID 0 /* Package Identifier Read */ +#define PECI_PKG_ID_CPU_ID 0x0000 /* CPUID Info */ +#define PECI_PKG_ID_PLATFORM_ID 0x0001 /* Platform ID */ +#define PECI_PKG_ID_DEVICE_ID 0x0002 /* Uncore Device ID */ +#define PECI_PKG_ID_MAX_THREAD_ID 0x0003 /* Max Thread ID */ +#define PECI_PKG_ID_MICROCODE_REV 0x0004 /* CPU Microcode Update Revision */ +#define PECI_PKG_ID_MCA_ERROR_LOG 0x0005 /* Machine Check Status */ +#define PECI_PCS_MODULE_TEMP 9 /* Per Core DTS Temperature Read */ +#define PECI_PCS_THERMAL_MARGIN 10 /* DTS thermal margin */ +#define PECI_PCS_DDR_DIMM_TEMP 14 /* DDR DIMM Temperature */ +#define PECI_PCS_TEMP_TARGET 16 /* Temperature Target Read */ +#define PECI_PCS_TDP_UNITS 30 /* Units for power/energy registers */ + +struct peci_device; + +int peci_temp_read(struct peci_device *device, s16 *temp_raw); + +int peci_pcs_read(struct peci_device *device, u8 index, + u16 param, u32 *data); + +int peci_pci_local_read(struct peci_device *device, u8 bus, u8 dev, + u8 func, u16 reg, u32 *data); + +int peci_ep_pci_local_read(struct peci_device *device, u8 seg, + u8 bus, u8 dev, u8 func, u16 reg, u32 *data); + +int peci_mmio_read(struct peci_device *device, u8 bar, u8 seg, + u8 bus, u8 dev, u8 func, u64 address, u32 *data); + +#endif /* __LINUX_PECI_CPU_H */ diff --git a/include/linux/peci.h b/include/linux/peci.h new file mode 100644 index 000000000000..06e6ef935297 --- /dev/null +++ b/include/linux/peci.h @@ -0,0 +1,112 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright (c) 2018-2021 Intel Corporation */ + +#ifndef __LINUX_PECI_H +#define __LINUX_PECI_H + +#include <linux/device.h> +#include <linux/kernel.h> +#include <linux/mutex.h> +#include <linux/types.h> + +/* + * Currently we don't support any PECI command over 32 bytes. + */ +#define PECI_REQUEST_MAX_BUF_SIZE 32 + +struct peci_controller; +struct peci_request; + +/** + * struct peci_controller_ops - PECI controller specific methods + * @xfer: PECI transfer function + * + * PECI controllers may have different hardware interfaces - the drivers + * implementing PECI controllers can use this structure to abstract away those + * differences by exposing a common interface for PECI core. + */ +struct peci_controller_ops { + int (*xfer)(struct peci_controller *controller, u8 addr, struct peci_request *req); +}; + +/** + * struct peci_controller - PECI controller + * @dev: device object to register PECI controller to the device model + * @ops: pointer to device specific controller operations + * @bus_lock: lock used to protect multiple callers + * @id: PECI controller ID + * + * PECI controllers usually connect to their drivers using non-PECI bus, + * such as the platform bus. + * Each PECI controller can communicate with one or more PECI devices. + */ +struct peci_controller { + struct device dev; + struct peci_controller_ops *ops; + struct mutex bus_lock; /* held for the duration of xfer */ + u8 id; +}; + +struct peci_controller *devm_peci_controller_add(struct device *parent, + struct peci_controller_ops *ops); + +static inline struct peci_controller *to_peci_controller(void *d) +{ + return container_of(d, struct peci_controller, dev); +} + +/** + * struct peci_device - PECI device + * @dev: device object to register PECI device to the device model + * @controller: manages the bus segment hosting this PECI device + * @info: PECI device characteristics + * @info.family: device family + * @info.model: device model + * @info.peci_revision: PECI revision supported by the PECI device + * @info.socket_id: the socket ID represented by the PECI device + * @addr: address used on the PECI bus connected to the parent controller + * @deleted: indicates that PECI device was already deleted + * + * A peci_device identifies a single device (i.e. CPU) connected to a PECI bus. + * The behaviour exposed to the rest of the system is defined by the PECI driver + * managing the device. + */ +struct peci_device { + struct device dev; + struct { + u16 family; + u8 model; + u8 peci_revision; + u8 socket_id; + } info; + u8 addr; + bool deleted; +}; + +static inline struct peci_device *to_peci_device(struct device *d) +{ + return container_of(d, struct peci_device, dev); +} + +/** + * struct peci_request - PECI request + * @device: PECI device to which the request is sent + * @tx: TX buffer specific data + * @tx.buf: TX buffer + * @tx.len: transfer data length in bytes + * @rx: RX buffer specific data + * @rx.buf: RX buffer + * @rx.len: received data length in bytes + * + * A peci_request represents a request issued by PECI originator (TX) and + * a response received from PECI responder (RX). + */ +struct peci_request { + struct peci_device *device; + struct { + u8 buf[PECI_REQUEST_MAX_BUF_SIZE]; + u8 len; + } rx, tx; +}; + +#endif /* __LINUX_PECI_H */ diff --git a/include/linux/percpu-rwsem.h b/include/linux/percpu-rwsem.h index 5fda40f97fe9..36b942b67b7d 100644 --- a/include/linux/percpu-rwsem.h +++ b/include/linux/percpu-rwsem.h @@ -121,9 +121,15 @@ static inline void percpu_up_read(struct percpu_rw_semaphore *sem) preempt_enable(); } +extern bool percpu_is_read_locked(struct percpu_rw_semaphore *); extern void percpu_down_write(struct percpu_rw_semaphore *); extern void percpu_up_write(struct percpu_rw_semaphore *); +static inline bool percpu_is_write_locked(struct percpu_rw_semaphore *sem) +{ + return atomic_read(&sem->block); +} + extern int __percpu_init_rwsem(struct percpu_rw_semaphore *, const char *, struct lock_class_key *); diff --git a/include/linux/percpu.h b/include/linux/percpu.h index ae4004e7957e..f1ec5ad1351c 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -94,10 +94,7 @@ extern const char * const pcpu_fc_names[PCPU_FC_NR]; extern enum pcpu_fc pcpu_chosen_fc; -typedef void * (*pcpu_fc_alloc_fn_t)(unsigned int cpu, size_t size, - size_t align); -typedef void (*pcpu_fc_free_fn_t)(void *ptr, size_t size); -typedef void (*pcpu_fc_populate_pte_fn_t)(unsigned long addr); +typedef int (pcpu_fc_cpu_to_node_fn_t)(int cpu); typedef int (pcpu_fc_cpu_distance_fn_t)(unsigned int from, unsigned int to); extern struct pcpu_alloc_info * __init pcpu_alloc_alloc_info(int nr_groups, @@ -111,15 +108,13 @@ extern void __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai, extern int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size, size_t atom_size, pcpu_fc_cpu_distance_fn_t cpu_distance_fn, - pcpu_fc_alloc_fn_t alloc_fn, - pcpu_fc_free_fn_t free_fn); + pcpu_fc_cpu_to_node_fn_t cpu_to_nd_fn); #endif #ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK +void __init pcpu_populate_pte(unsigned long addr); extern int __init pcpu_page_first_chunk(size_t reserved_size, - pcpu_fc_alloc_fn_t alloc_fn, - pcpu_fc_free_fn_t free_fn, - pcpu_fc_populate_pte_fn_t populate_pte_fn); + pcpu_fc_cpu_to_node_fn_t cpu_to_nd_fn); #endif extern void __percpu *__alloc_reserved_percpu(size_t size, size_t align) __alloc_size(1); diff --git a/include/linux/percpu_counter.h b/include/linux/percpu_counter.h index 01861eebed79..8ed5fba6d156 100644 --- a/include/linux/percpu_counter.h +++ b/include/linux/percpu_counter.h @@ -15,6 +15,9 @@ #include <linux/types.h> #include <linux/gfp.h> +/* percpu_counter batch for local add or sub */ +#define PERCPU_COUNTER_LOCAL_BATCH INT_MAX + #ifdef CONFIG_SMP struct percpu_counter { @@ -56,6 +59,22 @@ static inline void percpu_counter_add(struct percpu_counter *fbc, s64 amount) percpu_counter_add_batch(fbc, amount, percpu_counter_batch); } +/* + * With percpu_counter_add_local() and percpu_counter_sub_local(), counts + * are accumulated in local per cpu counter and not in fbc->count until + * local count overflows PERCPU_COUNTER_LOCAL_BATCH. This makes counter + * write efficient. + * But percpu_counter_sum(), instead of percpu_counter_read(), needs to be + * used to add up the counts from each CPU to account for all the local + * counts. So percpu_counter_add_local() and percpu_counter_sub_local() + * should be used when a counter is updated frequently and read rarely. + */ +static inline void +percpu_counter_add_local(struct percpu_counter *fbc, s64 amount) +{ + percpu_counter_add_batch(fbc, amount, PERCPU_COUNTER_LOCAL_BATCH); +} + static inline s64 percpu_counter_sum_positive(struct percpu_counter *fbc) { s64 ret = __percpu_counter_sum(fbc); @@ -138,6 +157,13 @@ percpu_counter_add(struct percpu_counter *fbc, s64 amount) preempt_enable(); } +/* non-SMP percpu_counter_add_local is the same with percpu_counter_add */ +static inline void +percpu_counter_add_local(struct percpu_counter *fbc, s64 amount) +{ + percpu_counter_add(fbc, amount); +} + static inline void percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount, s32 batch) { @@ -193,4 +219,10 @@ static inline void percpu_counter_sub(struct percpu_counter *fbc, s64 amount) percpu_counter_add(fbc, -amount); } +static inline void +percpu_counter_sub_local(struct percpu_counter *fbc, s64 amount) +{ + percpu_counter_add_local(fbc, -amount); +} + #endif /* _LINUX_PERCPU_COUNTER_H */ diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h index 2512e2f9cd4e..0356cb6a215d 100644 --- a/include/linux/perf/arm_pmu.h +++ b/include/linux/perf/arm_pmu.h @@ -24,8 +24,11 @@ /* * ARM PMU hw_event flags */ -/* Event uses a 64bit counter */ -#define ARMPMU_EVT_64BIT 1 +#define ARMPMU_EVT_64BIT 0x00001 /* Event uses a 64bit counter */ +#define ARMPMU_EVT_47BIT 0x00002 /* Event uses a 47bit counter */ + +static_assert((PERF_EVENT_FLAG_ARCH & ARMPMU_EVT_64BIT) == ARMPMU_EVT_64BIT); +static_assert((PERF_EVENT_FLAG_ARCH & ARMPMU_EVT_47BIT) == ARMPMU_EVT_47BIT); #define HW_OP_UNSUPPORTED 0xFFFF #define C(_x) PERF_COUNT_HW_CACHE_##_x diff --git a/include/linux/perf/riscv_pmu.h b/include/linux/perf/riscv_pmu.h new file mode 100644 index 000000000000..e17e86ad6f3a --- /dev/null +++ b/include/linux/perf/riscv_pmu.h @@ -0,0 +1,79 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2018 SiFive + * Copyright (C) 2018 Andes Technology Corporation + * Copyright (C) 2021 Western Digital Corporation or its affiliates. + * + */ + +#ifndef _ASM_RISCV_PERF_EVENT_H +#define _ASM_RISCV_PERF_EVENT_H + +#include <linux/perf_event.h> +#include <linux/ptrace.h> +#include <linux/interrupt.h> + +#ifdef CONFIG_RISCV_PMU + +/* + * The RISCV_MAX_COUNTERS parameter should be specified. + */ + +#define RISCV_MAX_COUNTERS 64 +#define RISCV_OP_UNSUPP (-EOPNOTSUPP) +#define RISCV_PMU_PDEV_NAME "riscv-pmu" +#define RISCV_PMU_LEGACY_PDEV_NAME "riscv-pmu-legacy" + +#define RISCV_PMU_STOP_FLAG_RESET 1 + +struct cpu_hw_events { + /* currently enabled events */ + int n_events; + /* Counter overflow interrupt */ + int irq; + /* currently enabled events */ + struct perf_event *events[RISCV_MAX_COUNTERS]; + /* currently enabled hardware counters */ + DECLARE_BITMAP(used_hw_ctrs, RISCV_MAX_COUNTERS); + /* currently enabled firmware counters */ + DECLARE_BITMAP(used_fw_ctrs, RISCV_MAX_COUNTERS); +}; + +struct riscv_pmu { + struct pmu pmu; + char *name; + + irqreturn_t (*handle_irq)(int irq_num, void *dev); + + unsigned long cmask; + u64 (*ctr_read)(struct perf_event *event); + int (*ctr_get_idx)(struct perf_event *event); + int (*ctr_get_width)(int idx); + void (*ctr_clear_idx)(struct perf_event *event); + void (*ctr_start)(struct perf_event *event, u64 init_val); + void (*ctr_stop)(struct perf_event *event, unsigned long flag); + int (*event_map)(struct perf_event *event, u64 *config); + + struct cpu_hw_events __percpu *hw_events; + struct hlist_node node; + struct notifier_block riscv_pm_nb; +}; + +#define to_riscv_pmu(p) (container_of(p, struct riscv_pmu, pmu)) + +void riscv_pmu_start(struct perf_event *event, int flags); +void riscv_pmu_stop(struct perf_event *event, int flags); +unsigned long riscv_pmu_ctr_read_csr(unsigned long csr); +int riscv_pmu_event_set_period(struct perf_event *event); +uint64_t riscv_pmu_ctr_get_width_mask(struct perf_event *event); +u64 riscv_pmu_event_update(struct perf_event *event); +#ifdef CONFIG_RISCV_PMU_LEGACY +void riscv_pmu_legacy_skip_init(void); +#else +static inline void riscv_pmu_legacy_skip_init(void) {}; +#endif +struct riscv_pmu *riscv_pmu_alloc(void); + +#endif /* CONFIG_RISCV_PMU */ + +#endif /* _ASM_RISCV_PERF_EVENT_H */ diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 474eaecd63ba..0031f7b4d9ab 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -26,14 +26,17 @@ # include <asm/local64.h> #endif +#define PERF_GUEST_ACTIVE 0x01 +#define PERF_GUEST_USER 0x02 + struct perf_guest_info_callbacks { - int (*is_in_guest)(void); - int (*is_user_mode)(void); - unsigned long (*get_guest_ip)(void); - void (*handle_intel_pt_intr)(void); + unsigned int (*state)(void); + unsigned long (*get_ip)(void); + unsigned int (*handle_intel_pt_intr)(void); }; #ifdef CONFIG_HAVE_HW_BREAKPOINT +#include <linux/rhashtable-types.h> #include <asm/hw_breakpoint.h> #endif @@ -58,6 +61,7 @@ struct perf_guest_info_callbacks { #include <linux/refcount.h> #include <linux/security.h> #include <linux/static_call.h> +#include <linux/lockdep.h> #include <asm/local.h> struct perf_callchain_entry { @@ -135,9 +139,11 @@ struct hw_perf_event_extra { * PERF_EVENT_FLAG_ARCH bits are reserved for architecture-specific * usage. */ -#define PERF_EVENT_FLAG_ARCH 0x0000ffff +#define PERF_EVENT_FLAG_ARCH 0x000fffff #define PERF_EVENT_FLAG_USER_READ_CNT 0x80000000 +static_assert((PERF_EVENT_FLAG_USER_READ_CNT & PERF_EVENT_FLAG_ARCH) == 0); + /** * struct hw_perf_event - performance event hardware details: */ @@ -176,7 +182,7 @@ struct hw_perf_event { * creation and event initalization. */ struct arch_hw_breakpoint info; - struct list_head bp_list; + struct rhlist_head bp_list; }; #endif struct { /* amd_iommu */ @@ -629,7 +635,23 @@ struct pmu_event_list { struct list_head list; }; +/* + * event->sibling_list is modified whole holding both ctx->lock and ctx->mutex + * as such iteration must hold either lock. However, since ctx->lock is an IRQ + * safe lock, and is only held by the CPU doing the modification, having IRQs + * disabled is sufficient since it will hold-off the IPIs. + */ +#ifdef CONFIG_PROVE_LOCKING +#define lockdep_assert_event_ctx(event) \ + WARN_ON_ONCE(__lockdep_enabled && \ + (this_cpu_read(hardirqs_enabled) && \ + lockdep_is_held(&(event)->ctx->mutex) != LOCK_STATE_HELD)) +#else +#define lockdep_assert_event_ctx(event) +#endif + #define for_each_sibling_event(sibling, event) \ + lockdep_assert_event_ctx(event); \ if ((event)->group_leader == (event)) \ list_for_each_entry((sibling), &(event)->sibling_list, sibling_list) @@ -691,18 +713,6 @@ struct perf_event { u64 total_time_running; u64 tstamp; - /* - * timestamp shadows the actual context timing but it can - * be safely used in NMI interrupt context. It reflects the - * context time as it was when the event was last scheduled in, - * or when ctx_sched_in failed to schedule the event because we - * run out of PMC. - * - * ctx_time already accounts for ctx->timestamp. Therefore to - * compute ctx_time for a sample, simply add perf_clock(). - */ - u64 shadow_ctx_time; - struct perf_event_attr attr; u16 header_size; u16 id_header_size; @@ -746,11 +756,14 @@ struct perf_event { struct fasync_struct *fasync; /* delayed work for NMIs and such */ - int pending_wakeup; - int pending_kill; - int pending_disable; + unsigned int pending_wakeup; + unsigned int pending_kill; + unsigned int pending_disable; + unsigned int pending_sigtrap; unsigned long pending_addr; /* SIGTRAP */ - struct irq_work pending; + struct irq_work pending_irq; + struct callback_head pending_task; + unsigned int pending_work; atomic_t event_limit; @@ -769,6 +782,8 @@ struct perf_event { struct pid_namespace *ns; u64 id; + atomic64_t lost_samples; + u64 (*clock)(void); perf_overflow_handler_t overflow_handler; void *overflow_handler_context; @@ -850,6 +865,7 @@ struct perf_event_context { */ u64 time; u64 timestamp; + u64 timeoffset; /* * These fields let us detect when two contexts have both @@ -864,6 +880,14 @@ struct perf_event_context { #endif void *task_ctx_data; /* pmu specific data */ struct rcu_head rcu_head; + + /* + * Sum (event->pending_sigtrap + event->pending_work) + * + * The SIGTRAP is targeted at ctx->task, as such it won't do changing + * that until the signal is delivered. + */ + local_t nr_pending; }; /* @@ -873,7 +897,7 @@ struct perf_event_context { #define PERF_NR_CONTEXTS 4 /** - * struct perf_event_cpu_context - per cpu event context structure + * struct perf_cpu_context - per cpu event context structure */ struct perf_cpu_context { struct perf_event_context ctx; @@ -932,6 +956,8 @@ struct bpf_perf_event_data_kern { struct perf_cgroup_info { u64 time; u64 timestamp; + u64 timeoffset; + int active; }; struct perf_cgroup { @@ -1012,18 +1038,20 @@ struct perf_sample_data { * Fields set by perf_sample_data_init(), group so as to * minimize the cachelines touched. */ - u64 addr; - struct perf_raw_record *raw; - struct perf_branch_stack *br_stack; + u64 sample_flags; u64 period; - union perf_sample_weight weight; - u64 txn; - union perf_mem_data_src data_src; /* * The other fields, optionally {set,used} by * perf_{prepare,output}_sample(). */ + struct perf_branch_stack *br_stack; + union perf_sample_weight weight; + union perf_mem_data_src data_src; + u64 txn; + u64 addr; + struct perf_raw_record *raw; + u64 type; u64 ip; struct { @@ -1061,13 +1089,30 @@ static inline void perf_sample_data_init(struct perf_sample_data *data, u64 addr, u64 period) { /* remaining struct members initialized in perf_prepare_sample() */ - data->addr = addr; - data->raw = NULL; - data->br_stack = NULL; + data->sample_flags = PERF_SAMPLE_PERIOD; data->period = period; - data->weight.full = 0; - data->data_src.val = PERF_MEM_NA; - data->txn = 0; + + if (addr) { + data->addr = addr; + data->sample_flags |= PERF_SAMPLE_ADDR; + } +} + +/* + * Clear all bitfields in the perf_branch_entry. + * The to and from fields are not cleared because they are + * systematically modified by caller. + */ +static inline void perf_clear_branch_entry_bitfields(struct perf_branch_entry *br) +{ + br->mispred = 0; + br->predicted = 0; + br->in_tx = 0; + br->abort = 0; + br->cycles = 0; + br->type = 0; + br->spec = PERF_BR_SPEC_NA; + br->reserved = 0; } extern void perf_output_sample(struct perf_output_handle *handle, @@ -1251,9 +1296,32 @@ extern void perf_event_bpf_event(struct bpf_prog *prog, enum perf_bpf_event_type type, u16 flags); -extern struct perf_guest_info_callbacks *perf_guest_cbs; -extern int perf_register_guest_info_callbacks(struct perf_guest_info_callbacks *callbacks); -extern int perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks *callbacks); +#ifdef CONFIG_GUEST_PERF_EVENTS +extern struct perf_guest_info_callbacks __rcu *perf_guest_cbs; + +DECLARE_STATIC_CALL(__perf_guest_state, *perf_guest_cbs->state); +DECLARE_STATIC_CALL(__perf_guest_get_ip, *perf_guest_cbs->get_ip); +DECLARE_STATIC_CALL(__perf_guest_handle_intel_pt_intr, *perf_guest_cbs->handle_intel_pt_intr); + +static inline unsigned int perf_guest_state(void) +{ + return static_call(__perf_guest_state)(); +} +static inline unsigned long perf_guest_get_ip(void) +{ + return static_call(__perf_guest_get_ip)(); +} +static inline unsigned int perf_guest_handle_intel_pt_intr(void) +{ + return static_call(__perf_guest_handle_intel_pt_intr)(); +} +extern void perf_register_guest_info_callbacks(struct perf_guest_info_callbacks *cbs); +extern void perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks *cbs); +#else +static inline unsigned int perf_guest_state(void) { return 0; } +static inline unsigned long perf_guest_get_ip(void) { return 0; } +static inline unsigned int perf_guest_handle_intel_pt_intr(void) { return 0; } +#endif /* CONFIG_GUEST_PERF_EVENTS */ extern void perf_event_exec(void); extern void perf_event_comm(struct task_struct *tsk, bool exec); @@ -1497,11 +1565,6 @@ perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr) { } static inline void perf_bp_event(struct perf_event *event, void *data) { } -static inline int perf_register_guest_info_callbacks -(struct perf_guest_info_callbacks *callbacks) { return 0; } -static inline int perf_unregister_guest_info_callbacks -(struct perf_guest_info_callbacks *callbacks) { return 0; } - static inline void perf_event_mmap(struct vm_area_struct *vma) { } typedef int (perf_ksymbol_get_name_f)(char *name, int name_len, void *data); @@ -1649,4 +1712,36 @@ typedef int (perf_snapshot_branch_stack_t)(struct perf_branch_entry *entries, unsigned int cnt); DECLARE_STATIC_CALL(perf_snapshot_branch_stack, perf_snapshot_branch_stack_t); +#ifndef PERF_NEEDS_LOPWR_CB +static inline void perf_lopwr_cb(bool mode) +{ +} +#endif + +#ifdef CONFIG_PERF_EVENTS +static inline bool branch_sample_no_flags(const struct perf_event *event) +{ + return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_NO_FLAGS; +} + +static inline bool branch_sample_no_cycles(const struct perf_event *event) +{ + return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_NO_CYCLES; +} + +static inline bool branch_sample_type(const struct perf_event *event) +{ + return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_TYPE_SAVE; +} + +static inline bool branch_sample_hw_index(const struct perf_event *event) +{ + return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_HW_INDEX; +} + +static inline bool branch_sample_priv(const struct perf_event *event) +{ + return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_PRIV_SAVE; +} +#endif /* CONFIG_PERF_EVENTS */ #endif /* _LINUX_PERF_EVENT_H */ diff --git a/include/linux/perf_event_api.h b/include/linux/perf_event_api.h new file mode 100644 index 000000000000..c2fd6048b790 --- /dev/null +++ b/include/linux/perf_event_api.h @@ -0,0 +1 @@ +#include <linux/perf_event.h> diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index e24d2c992b11..a108b60a6962 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -12,6 +12,7 @@ #include <linux/bug.h> #include <linux/errno.h> #include <asm-generic/pgtable_uffd.h> +#include <linux/page_table_check.h> #if 5 - defined(__PAGETABLE_P4D_FOLDED) - defined(__PAGETABLE_PUD_FOLDED) - \ defined(__PAGETABLE_PMD_FOLDED) != CONFIG_PGTABLE_LEVELS @@ -62,6 +63,7 @@ static inline unsigned long pte_index(unsigned long address) { return (address >> PAGE_SHIFT) & (PTRS_PER_PTE - 1); } +#define pte_index pte_index #ifndef pmd_index static inline unsigned long pmd_index(unsigned long address) @@ -211,7 +213,7 @@ static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, #endif #ifndef __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG -#ifdef CONFIG_TRANSPARENT_HUGEPAGE +#if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG) static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) @@ -232,7 +234,7 @@ static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma, BUILD_BUG(); return 0; } -#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ +#endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG */ #endif #ifndef __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH @@ -258,6 +260,19 @@ static inline int pmdp_clear_flush_young(struct vm_area_struct *vma, #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #endif +#ifndef arch_has_hw_pte_young +/* + * Return whether the accessed bit is supported on the local CPU. + * + * This stub assumes accessing through an old PTE triggers a page fault. + * Architectures that automatically set the access bit should overwrite it. + */ +static inline bool arch_has_hw_pte_young(void) +{ + return false; +} +#endif + #ifndef __HAVE_ARCH_PTEP_GET_AND_CLEAR static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long address, @@ -265,10 +280,17 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm, { pte_t pte = *ptep; pte_clear(mm, address, ptep); + page_table_check_pte_clear(mm, address, pte); return pte; } #endif +static inline void ptep_clear(struct mm_struct *mm, unsigned long addr, + pte_t *ptep) +{ + ptep_get_and_clear(mm, addr, ptep); +} + #ifndef __HAVE_ARCH_PTEP_GET static inline pte_t ptep_get(pte_t *ptep) { @@ -338,7 +360,10 @@ static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, pmd_t *pmdp) { pmd_t pmd = *pmdp; + pmd_clear(pmdp); + page_table_check_pmd_clear(mm, address, pmd); + return pmd; } #endif /* __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR */ @@ -350,6 +375,8 @@ static inline pud_t pudp_huge_get_and_clear(struct mm_struct *mm, pud_t pud = *pudp; pud_clear(pudp); + page_table_check_pud_clear(mm, address, pud); + return pud; } #endif /* __HAVE_ARCH_PUDP_HUGE_GET_AND_CLEAR */ @@ -561,6 +588,26 @@ extern pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp); #endif +#ifndef __HAVE_ARCH_PMDP_INVALIDATE_AD + +/* + * pmdp_invalidate_ad() invalidates the PMD while changing a transparent + * hugepage mapping in the page tables. This function is similar to + * pmdp_invalidate(), but should only be used if the access and dirty bits would + * not be cleared by the software in the new PMD value. The function ensures + * that hardware changes of the access and dirty bits updates would not be lost. + * + * Doing so can allow in certain architectures to avoid a TLB flush in most + * cases. Yet, another TLB flush might be necessary later if the PMD update + * itself requires such flush (e.g., if protection was set to be stricter). Yet, + * even when a TLB flush is needed because of the update, the caller may be able + * to batch these TLB flushing operations, so fewer TLB flush operations are + * needed. + */ +extern pmd_t pmdp_invalidate_ad(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp); +#endif + #ifndef __HAVE_ARCH_PTE_SAME static inline int pte_same(pte_t pte_a, pte_t pte_b) { @@ -729,7 +776,7 @@ static inline void arch_swap_invalidate_area(int type) #endif #ifndef __HAVE_ARCH_SWAP_RESTORE -static inline void arch_swap_restore(swp_entry_t entry, struct page *page) +static inline void arch_swap_restore(swp_entry_t entry, struct folio *folio) { } #endif @@ -994,6 +1041,35 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot) #define arch_start_context_switch(prev) do {} while (0) #endif +/* + * When replacing an anonymous page by a real (!non) swap entry, we clear + * PG_anon_exclusive from the page and instead remember whether the flag was + * set in the swp pte. During fork(), we have to mark the entry as !exclusive + * (possibly shared). On swapin, we use that information to restore + * PG_anon_exclusive, which is very helpful in cases where we might have + * additional (e.g., FOLL_GET) references on a page and wouldn't be able to + * detect exclusivity. + * + * These functions don't apply to non-swap entries (e.g., migration, hwpoison, + * ...). + */ +#ifndef __HAVE_ARCH_PTE_SWP_EXCLUSIVE +static inline pte_t pte_swp_mkexclusive(pte_t pte) +{ + return pte; +} + +static inline int pte_swp_exclusive(pte_t pte) +{ + return false; +} + +static inline pte_t pte_swp_clear_exclusive(pte_t pte) +{ + return pte; +} +#endif + #ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY #ifndef CONFIG_ARCH_ENABLE_THP_MIGRATION static inline pmd_t pmd_swp_mksoft_dirty(pmd_t pmd) @@ -1213,8 +1289,7 @@ static inline int pgd_devmap(pgd_t pgd) #endif #if !defined(CONFIG_TRANSPARENT_HUGEPAGE) || \ - (defined(CONFIG_TRANSPARENT_HUGEPAGE) && \ - !defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD)) + !defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) static inline int pud_trans_huge(pud_t pud) { return 0; @@ -1385,16 +1460,13 @@ static inline int pmd_protnone(pmd_t pmd) #ifndef __PAGETABLE_P4D_FOLDED int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot); -int p4d_clear_huge(p4d_t *p4d); +void p4d_clear_huge(p4d_t *p4d); #else static inline int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot) { return 0; } -static inline int p4d_clear_huge(p4d_t *p4d) -{ - return 0; -} +static inline void p4d_clear_huge(p4d_t *p4d) { } #endif /* !__PAGETABLE_P4D_FOLDED */ int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot); @@ -1417,10 +1489,7 @@ static inline int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot) { return 0; } -static inline int p4d_clear_huge(p4d_t *p4d) -{ - return 0; -} +static inline void p4d_clear_huge(p4d_t *p4d) { } static inline int pud_clear_huge(pud_t *pud) { return 0; @@ -1541,11 +1610,7 @@ typedef unsigned int pgtbl_mod_mask; #endif #ifndef has_transparent_hugepage -#ifdef CONFIG_TRANSPARENT_HUGEPAGE -#define has_transparent_hugepage() 1 -#else -#define has_transparent_hugepage() 0 -#endif +#define has_transparent_hugepage() IS_BUILTIN(CONFIG_TRANSPARENT_HUGEPAGE) #endif /* @@ -1632,4 +1697,32 @@ typedef unsigned int pgtbl_mod_mask; #define MAX_PTRS_PER_P4D PTRS_PER_P4D #endif +/* description of effects of mapping type and prot in current implementation. + * this is due to the limited x86 page protection hardware. The expected + * behavior is in parens: + * + * map_type prot + * PROT_NONE PROT_READ PROT_WRITE PROT_EXEC + * MAP_SHARED r: (no) no r: (yes) yes r: (no) yes r: (no) yes + * w: (no) no w: (no) no w: (yes) yes w: (no) no + * x: (no) no x: (no) yes x: (no) yes x: (yes) yes + * + * MAP_PRIVATE r: (no) no r: (yes) yes r: (no) yes r: (no) yes + * w: (no) no w: (no) no w: (copy) copy w: (no) no + * x: (no) no x: (no) yes x: (no) yes x: (yes) yes + * + * On arm64, PROT_EXEC has the following behaviour for both MAP_SHARED and + * MAP_PRIVATE (with Enhanced PAN supported): + * r: (no) no + * w: (no) no + * x: (yes) yes + */ +#define DECLARE_VM_GET_PAGE_PROT \ +pgprot_t vm_get_page_prot(unsigned long vm_flags) \ +{ \ + return protection_map[vm_flags & \ + (VM_READ | VM_WRITE | VM_EXEC | VM_SHARED)]; \ +} \ +EXPORT_SYMBOL(vm_get_page_prot); + #endif /* _LINUX_PGTABLE_H */ diff --git a/include/linux/pgtable_api.h b/include/linux/pgtable_api.h new file mode 100644 index 000000000000..ff367a4ba8c4 --- /dev/null +++ b/include/linux/pgtable_api.h @@ -0,0 +1 @@ +#include <linux/pgtable.h> diff --git a/include/linux/phy.h b/include/linux/phy.h index 6de8d7a90d78..ddf66198f751 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -65,7 +65,7 @@ extern const int phy_basic_ports_array[3]; extern const int phy_fibre_port_array[1]; extern const int phy_all_ports_features_array[7]; extern const int phy_10_100_features_array[4]; -extern const int phy_basic_t1_features_array[2]; +extern const int phy_basic_t1_features_array[3]; extern const int phy_gbit_features_array[2]; extern const int phy_10gbit_features_array[1]; @@ -87,8 +87,8 @@ extern const int phy_10gbit_features_array[1]; * * @PHY_INTERFACE_MODE_NA: Not Applicable - don't touch * @PHY_INTERFACE_MODE_INTERNAL: No interface, MAC and PHY combined - * @PHY_INTERFACE_MODE_MII: Median-independent interface - * @PHY_INTERFACE_MODE_GMII: Gigabit median-independent interface + * @PHY_INTERFACE_MODE_MII: Media-independent interface + * @PHY_INTERFACE_MODE_GMII: Gigabit media-independent interface * @PHY_INTERFACE_MODE_SGMII: Serial gigabit media-independent interface * @PHY_INTERFACE_MODE_TBI: Ten Bit Interface * @PHY_INTERFACE_MODE_REVMII: Reverse Media Independent Interface @@ -115,6 +115,8 @@ extern const int phy_10gbit_features_array[1]; * @PHY_INTERFACE_MODE_25GBASER: 25G BaseR * @PHY_INTERFACE_MODE_USXGMII: Universal Serial 10GE MII * @PHY_INTERFACE_MODE_10GKR: 10GBASE-KR - with Clause 73 AN + * @PHY_INTERFACE_MODE_QUSGMII: Quad Universal SGMII + * @PHY_INTERFACE_MODE_1000BASEKX: 1000Base-KX - with Clause 73 AN * @PHY_INTERFACE_MODE_MAX: Book keeping * * Describes the interface between the MAC and PHY. @@ -152,6 +154,8 @@ typedef enum { PHY_INTERFACE_MODE_USXGMII, /* 10GBASE-KR - with Clause 73 AN */ PHY_INTERFACE_MODE_10GKR, + PHY_INTERFACE_MODE_QUSGMII, + PHY_INTERFACE_MODE_1000BASEKX, PHY_INTERFACE_MODE_MAX, } phy_interface_t; @@ -249,6 +253,8 @@ static inline const char *phy_modes(phy_interface_t interface) return "trgmii"; case PHY_INTERFACE_MODE_1000BASEX: return "1000base-x"; + case PHY_INTERFACE_MODE_1000BASEKX: + return "1000base-kx"; case PHY_INTERFACE_MODE_2500BASEX: return "2500base-x"; case PHY_INTERFACE_MODE_5GBASER: @@ -267,12 +273,13 @@ static inline const char *phy_modes(phy_interface_t interface) return "10gbase-kr"; case PHY_INTERFACE_MODE_100BASEX: return "100base-x"; + case PHY_INTERFACE_MODE_QUSGMII: + return "qusgmii"; default: return "unknown"; } } - #define PHY_INIT_TIMEOUT 100000 #define PHY_FORCE_TIMEOUT 10 @@ -564,13 +571,20 @@ struct macsec_ops; * @advertising: Currently advertised linkmodes * @adv_old: Saved advertised while power saving for WoL * @lp_advertising: Current link partner advertised linkmodes + * @host_interfaces: PHY interface modes supported by host * @eee_broken_modes: Energy efficient ethernet modes which should be prohibited * @autoneg: Flag autoneg being used + * @rate_matching: Current rate matching mode * @link: Current link state * @autoneg_complete: Flag auto negotiation of the link has completed * @mdix: Current crossover * @mdix_ctrl: User setting of crossover + * @pma_extable: Cached value of PMA/PMD Extended Abilities Register * @interrupts: Flag interrupts have been enabled + * @irq_suspended: Flag indicating PHY is suspended and therefore interrupt + * handling shall be postponed until PHY has resumed + * @irq_rerun: Flag indicating interrupts occurred while PHY was suspended, + * requiring a rerun of the interrupt handler after resume * @interface: enum phy_interface_t value * @skb: Netlink message for cable diagnostics * @nest: Netlink nest used for cable diagnostics @@ -583,6 +597,7 @@ struct macsec_ops; * @master_slave_get: Current master/slave advertisement * @master_slave_state: Current master/slave configuration * @mii_ts: Pointer to time stamper callbacks + * @psec: Pointer to Power Sourcing Equipment control struct * @lock: Mutex for serialization access to PHY * @state_queue: Work queue for state machine * @shared: Pointer to private data shared by phys in one package @@ -625,6 +640,10 @@ struct phy_device { /* Interrupts are enabled */ unsigned interrupts:1; + unsigned irq_suspended:1; + unsigned irq_rerun:1; + + int rate_matching; enum phy_state state; @@ -653,6 +672,9 @@ struct phy_device { /* used with phy_speed_down */ __ETHTOOL_DECLARE_LINK_MODE_MASK(adv_old); + /* Host supported PHY interface types. Should be ignored if empty. */ + DECLARE_PHY_INTERFACE_MASK(host_interfaces); + /* Energy efficient ethernet modes which should be prohibited */ u32 eee_broken_modes; @@ -694,10 +716,13 @@ struct phy_device { struct phylink *phylink; struct net_device *attached_dev; struct mii_timestamper *mii_ts; + struct pse_control *psec; u8 mdix; u8 mdix_ctrl; + int pma_extable; + void (*phy_link_change)(struct phy_device *phydev, bool up); void (*adjust_link)(struct net_device *dev); @@ -788,6 +813,21 @@ struct phy_driver { */ int (*get_features)(struct phy_device *phydev); + /** + * @get_rate_matching: Get the supported type of rate matching for a + * particular phy interface. This is used by phy consumers to determine + * whether to advertise lower-speed modes for that interface. It is + * assumed that if a rate matching mode is supported on an interface, + * then that interface's rate can be adapted to all slower link speeds + * supported by the phy. If iface is %PHY_INTERFACE_MODE_NA, and the phy + * supports any kind of rate matching for any interface, then it must + * return that rate matching mode (preferring %RATE_MATCH_PAUSE to + * %RATE_MATCH_CRS). If the interface is not supported, this should + * return %RATE_MATCH_NONE. + */ + int (*get_rate_matching)(struct phy_device *phydev, + phy_interface_t iface); + /* PHY Power Management */ /** @suspend: Suspend the hardware, saving state if needed */ int (*suspend)(struct phy_device *phydev); @@ -954,6 +994,9 @@ struct phy_fixup { const char *phy_speed_to_str(int speed); const char *phy_duplex_to_str(unsigned int duplex); +const char *phy_rate_matching_to_str(int rate_matching); + +int phy_interface_num_ports(phy_interface_t interface); /* A structure for mapping a particular speed and duplex * combination to a particular SUPPORTED and ADVERTISED value @@ -1536,6 +1579,9 @@ static inline void phy_device_reset(struct phy_device *phydev, int value) #define phydev_err(_phydev, format, args...) \ dev_err(&_phydev->mdio.dev, format, ##args) +#define phydev_err_probe(_phydev, err, format, args...) \ + dev_err_probe(&_phydev->mdio.dev, err, format, ##args) + #define phydev_info(_phydev, format, args...) \ dev_info(&_phydev->mdio.dev, format, ##args) @@ -1578,6 +1624,7 @@ int genphy_update_link(struct phy_device *phydev); int genphy_read_lpa(struct phy_device *phydev); int genphy_read_status_fixed(struct phy_device *phydev); int genphy_read_status(struct phy_device *phydev); +int genphy_read_master_slave(struct phy_device *phydev); int genphy_suspend(struct phy_device *phydev); int genphy_resume(struct phy_device *phydev); int genphy_loopback(struct phy_device *phydev, bool enable); @@ -1610,11 +1657,14 @@ int genphy_c45_read_link(struct phy_device *phydev); int genphy_c45_read_lpa(struct phy_device *phydev); int genphy_c45_read_pma(struct phy_device *phydev); int genphy_c45_pma_setup_forced(struct phy_device *phydev); +int genphy_c45_pma_baset1_setup_master_slave(struct phy_device *phydev); int genphy_c45_an_config_aneg(struct phy_device *phydev); int genphy_c45_an_disable_aneg(struct phy_device *phydev); int genphy_c45_read_mdix(struct phy_device *phydev); int genphy_c45_pma_read_abilities(struct phy_device *phydev); +int genphy_c45_pma_baset1_read_master_slave(struct phy_device *phydev); int genphy_c45_read_status(struct phy_device *phydev); +int genphy_c45_baset1_read_status(struct phy_device *phydev); int genphy_c45_config_aneg(struct phy_device *phydev); int genphy_c45_loopback(struct phy_device *phydev, bool enable); int genphy_c45_pma_resume(struct phy_device *phydev); @@ -1661,7 +1711,9 @@ int phy_disable_interrupts(struct phy_device *phydev); void phy_request_interrupt(struct phy_device *phydev); void phy_free_interrupt(struct phy_device *phydev); void phy_print_status(struct phy_device *phydev); -int phy_set_max_speed(struct phy_device *phydev, u32 max_speed); +int phy_get_rate_matching(struct phy_device *phydev, + phy_interface_t iface); +void phy_set_max_speed(struct phy_device *phydev, u32 max_speed); void phy_remove_link_mode(struct phy_device *phydev, u32 link_mode); void phy_advertise_supported(struct phy_device *phydev); void phy_support_sym_pause(struct phy_device *phydev); diff --git a/include/linux/phy/pcie.h b/include/linux/phy/pcie.h new file mode 100644 index 000000000000..e7ac81764576 --- /dev/null +++ b/include/linux/phy/pcie.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2022 Rockchip Electronics Co., Ltd. + */ +#ifndef __PHY_PCIE_H +#define __PHY_PCIE_H + +#define PHY_MODE_PCIE_RC 20 +#define PHY_MODE_PCIE_EP 21 +#define PHY_MODE_PCIE_BIFURCATION 22 + +#endif diff --git a/include/linux/phy/phy-lvds.h b/include/linux/phy/phy-lvds.h new file mode 100644 index 000000000000..09931d080a6d --- /dev/null +++ b/include/linux/phy/phy-lvds.h @@ -0,0 +1,32 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright 2020,2022 NXP + */ + +#ifndef __PHY_LVDS_H_ +#define __PHY_LVDS_H_ + +/** + * struct phy_configure_opts_lvds - LVDS configuration set + * @bits_per_lane_and_dclk_cycle: Number of bits per lane per differential + * clock cycle. + * @differential_clk_rate: Clock rate, in Hertz, of the LVDS + * differential clock. + * @lanes: Number of active, consecutive, + * data lanes, starting from lane 0, + * used for the transmissions. + * @is_slave: Boolean, true if the phy is a slave + * which works together with a master + * phy to support dual link transmission, + * otherwise a regular phy or a master phy. + * + * This structure is used to represent the configuration state of a LVDS phy. + */ +struct phy_configure_opts_lvds { + unsigned int bits_per_lane_and_dclk_cycle; + unsigned long differential_clk_rate; + unsigned int lanes; + bool is_slave; +}; + +#endif /* __PHY_LVDS_H_ */ diff --git a/include/linux/phy/phy.h b/include/linux/phy/phy.h index f3286f4cd306..b1413757fcc3 100644 --- a/include/linux/phy/phy.h +++ b/include/linux/phy/phy.h @@ -17,6 +17,7 @@ #include <linux/regulator/consumer.h> #include <linux/phy/phy-dp.h> +#include <linux/phy/phy-lvds.h> #include <linux/phy/phy-mipi-dphy.h> struct phy; @@ -57,10 +58,13 @@ enum phy_media { * the MIPI_DPHY phy mode. * @dp: Configuration set applicable for phys supporting * the DisplayPort protocol. + * @lvds: Configuration set applicable for phys supporting + * the LVDS phy mode. */ union phy_configure_opts { struct phy_configure_opts_mipi_dphy mipi_dphy; struct phy_configure_opts_dp dp; + struct phy_configure_opts_lvds lvds; }; /** diff --git a/include/linux/phy/tegra/xusb.h b/include/linux/phy/tegra/xusb.h index 3a35e74cdc61..70998e6dd6fd 100644 --- a/include/linux/phy/tegra/xusb.h +++ b/include/linux/phy/tegra/xusb.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* - * Copyright (c) 2016-2020, NVIDIA CORPORATION. All rights reserved. + * Copyright (c) 2016-2022, NVIDIA CORPORATION. All rights reserved. */ #ifndef PHY_TEGRA_XUSB_H @@ -21,6 +21,8 @@ int tegra_xusb_padctl_usb3_set_lfps_detect(struct tegra_xusb_padctl *padctl, unsigned int port, bool enable); int tegra_xusb_padctl_set_vbus_override(struct tegra_xusb_padctl *padctl, bool val); +void tegra_phy_xusb_utmi_pad_power_on(struct phy *phy); +void tegra_phy_xusb_utmi_pad_power_down(struct phy *phy); int tegra_phy_xusb_utmi_port_reset(struct phy *phy); int tegra_xusb_padctl_get_usb3_companion(struct tegra_xusb_padctl *padctl, unsigned int port); diff --git a/include/linux/phy_fixed.h b/include/linux/phy_fixed.h index 52bc8e487ef7..1acafd86ab13 100644 --- a/include/linux/phy_fixed.h +++ b/include/linux/phy_fixed.h @@ -2,6 +2,8 @@ #ifndef __PHY_FIXED_H #define __PHY_FIXED_H +#include <linux/types.h> + struct fixed_phy_status { int link; int speed; @@ -12,6 +14,7 @@ struct fixed_phy_status { struct device_node; struct gpio_desc; +struct net_device; #if IS_ENABLED(CONFIG_FIXED_PHY) extern int fixed_phy_change_carrier(struct net_device *dev, bool new_carrier); diff --git a/include/linux/phylink.h b/include/linux/phylink.h index 713a0c928b7c..3f01ac8017e0 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -21,6 +21,35 @@ enum { MLO_AN_FIXED, /* Fixed-link mode */ MLO_AN_INBAND, /* In-band protocol */ + /* MAC_SYM_PAUSE and MAC_ASYM_PAUSE are used when configuring our + * autonegotiation advertisement. They correspond to the PAUSE and + * ASM_DIR bits defined by 802.3, respectively. + * + * The following table lists the values of tx_pause and rx_pause which + * might be requested in mac_link_up. The exact values depend on either + * the results of autonegotation (if MLO_PAUSE_AN is set) or user + * configuration (if MLO_PAUSE_AN is not set). + * + * MAC_SYM_PAUSE MAC_ASYM_PAUSE MLO_PAUSE_AN tx_pause/rx_pause + * ============= ============== ============ ================== + * 0 0 0 0/0 + * 0 0 1 0/0 + * 0 1 0 0/0, 0/1, 1/0, 1/1 + * 0 1 1 0/0, 1/0 + * 1 0 0 0/0, 1/1 + * 1 0 1 0/0, 1/1 + * 1 1 0 0/0, 0/1, 1/0, 1/1 + * 1 1 1 0/0, 0/1, 1/1 + * + * If you set MAC_ASYM_PAUSE, the user may request any combination of + * tx_pause and rx_pause. You do not have to support these + * combinations. + * + * However, you should support combinations of tx_pause and rx_pause + * which might be the result of autonegotation. For example, don't set + * MAC_SYM_PAUSE unless your device can support tx_pause and rx_pause + * at the same time. + */ MAC_SYM_PAUSE = BIT(0), MAC_ASYM_PAUSE = BIT(1), MAC_10HD = BIT(2), @@ -59,6 +88,10 @@ static inline bool phylink_autoneg_inband(unsigned int mode) * @speed: link speed, one of the SPEED_* constants. * @duplex: link duplex mode, one of DUPLEX_* constants. * @pause: link pause state, described by MLO_PAUSE_* constants. + * @rate_matching: rate matching being performed, one of the RATE_MATCH_* + * constants. If rate matching is taking place, then the speed/duplex of + * the medium link mode (@speed and @duplex) and the speed/duplex of the phy + * interface mode (@interface) are different. * @link: true if the link is up. * @an_enabled: true if autonegotiation is enabled/desired. * @an_complete: true if autonegotiation has completed. @@ -70,6 +103,7 @@ struct phylink_link_state { int speed; int duplex; int pause; + int rate_matching; unsigned int link:1; unsigned int an_enabled:1; unsigned int an_complete:1; @@ -86,9 +120,9 @@ enum phylink_op_type { * @type: operation type of PHYLINK instance * @legacy_pre_march2020: driver has not been updated for March 2020 updates * (See commit 7cceb599d15d ("net: phylink: avoid mac_config calls") - * @pcs_poll: MAC PCS cannot provide link change interrupt * @poll_fixed_state: if true, starts link_poll, * if MAC link is at %MLO_AN_FIXED mode. + * @mac_managed_pm: if true, indicate the MAC driver is responsible for PHY PM. * @ovr_an_inband: if true, override PCS to MLO_AN_INBAND * @get_fixed_state: callback to execute to determine the fixed link state, * if MAC link is at %MLO_AN_FIXED mode. @@ -100,8 +134,8 @@ struct phylink_config { struct device *dev; enum phylink_op_type type; bool legacy_pre_march2020; - bool pcs_poll; bool poll_fixed_state; + bool mac_managed_pm; bool ovr_an_inband; void (*get_fixed_state)(struct phylink_config *config, struct phylink_link_state *state); @@ -162,11 +196,6 @@ struct phylink_mac_ops { * clearing unsupported speeds and duplex settings. The port modes * should not be cleared; phylink_set_port_modes() will help with this. * - * If the @state->interface mode is %PHY_INTERFACE_MODE_1000BASEX - * or %PHY_INTERFACE_MODE_2500BASEX, select the appropriate mode - * based on @state->advertising and/or @state->speed and update - * @state->interface accordingly. See phylink_helper_basex_speed(). - * * When @config->supported_interfaces has been set, phylink will iterate * over the supported interfaces to determine the full capability of the * MAC. The validation function must not print errors if @state->interface @@ -525,8 +554,10 @@ void pcs_link_up(struct phylink_pcs *pcs, unsigned int mode, phy_interface_t interface, int speed, int duplex); #endif -void phylink_get_linkmodes(unsigned long *linkmodes, phy_interface_t interface, - unsigned long mac_capabilities); +void phylink_caps_to_linkmodes(unsigned long *linkmodes, unsigned long caps); +unsigned long phylink_get_capabilities(phy_interface_t interface, + unsigned long mac_capabilities, + int rate_matching); void phylink_generic_validate(struct phylink_config *config, unsigned long *supported, struct phylink_link_state *state); @@ -534,7 +565,6 @@ void phylink_generic_validate(struct phylink_config *config, struct phylink *phylink_create(struct phylink_config *, struct fwnode_handle *, phy_interface_t iface, const struct phylink_mac_ops *mac_ops); -void phylink_set_pcs(struct phylink *, struct phylink_pcs *pcs); void phylink_destroy(struct phylink *); int phylink_connect_phy(struct phylink *, struct phy_device *); @@ -582,8 +612,6 @@ int phylink_speed_up(struct phylink *pl); #define phylink_test(bm, mode) __phylink_do_bit(test_bit, bm, mode) void phylink_set_port_modes(unsigned long *bits); -void phylink_set_10g_modes(unsigned long *mask); -void phylink_helper_basex_speed(struct phylink_link_state *state); void phylink_mii_c22_pcs_decode_state(struct phylink_link_state *state, u16 bmsr, u16 lpa); diff --git a/include/linux/pid_namespace.h b/include/linux/pid_namespace.h index 7c7e627503d2..07481bb87d4e 100644 --- a/include/linux/pid_namespace.h +++ b/include/linux/pid_namespace.h @@ -86,4 +86,9 @@ extern struct pid_namespace *task_active_pid_ns(struct task_struct *tsk); void pidhash_init(void); void pid_idr_init(void); +static inline bool task_is_in_init_pid_ns(struct task_struct *tsk) +{ + return task_active_pid_ns(tsk) == &init_pid_ns; +} + #endif /* _LINUX_PID_NS_H */ diff --git a/include/linux/pinctrl/pinconf-generic.h b/include/linux/pinctrl/pinconf-generic.h index eee0e3948537..2422211d6a5a 100644 --- a/include/linux/pinctrl/pinconf-generic.h +++ b/include/linux/pinctrl/pinconf-generic.h @@ -91,6 +91,8 @@ struct pinctrl_map; * configuration (eg. the currently selected mux function) drive values on * the line. Use argument 1 to enable output mode, argument 0 to disable * it. + * @PIN_CONFIG_OUTPUT_IMPEDANCE_OHMS: this will configure the output impedance + * of the pin with the value passed as argument. The argument is in ohms. * @PIN_CONFIG_PERSIST_STATE: retain pin state across sleep or controller reset * @PIN_CONFIG_POWER_SOURCE: if the pin can select between different power * supplies, the argument to this parameter (on a custom format) tells @@ -129,6 +131,7 @@ enum pin_config_param { PIN_CONFIG_MODE_PWM, PIN_CONFIG_OUTPUT, PIN_CONFIG_OUTPUT_ENABLE, + PIN_CONFIG_OUTPUT_IMPEDANCE_OHMS, PIN_CONFIG_PERSIST_STATE, PIN_CONFIG_POWER_SOURCE, PIN_CONFIG_SKEW_DELAY, diff --git a/include/linux/pinctrl/pinctrl.h b/include/linux/pinctrl/pinctrl.h index 70b45d28e7a9..487117ccb1bc 100644 --- a/include/linux/pinctrl/pinctrl.h +++ b/include/linux/pinctrl/pinctrl.h @@ -27,6 +27,26 @@ struct gpio_chip; struct device_node; /** + * struct pingroup - provides information on pingroup + * @name: a name for pingroup + * @pins: an array of pins in the pingroup + * @npins: number of pins in the pingroup + */ +struct pingroup { + const char *name; + const unsigned int *pins; + size_t npins; +}; + +/* Convenience macro to define a single named or anonymous pingroup */ +#define PINCTRL_PINGROUP(_name, _pins, _npins) \ +(struct pingroup){ \ + .name = _name, \ + .pins = _pins, \ + .npins = _npins, \ +} + +/** * struct pinctrl_pin_desc - boards/machines provide information on their * pins, pads or other muxable units in this struct * @number: unique pin number from the global pin number space diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h index fc5642431b92..6cb65df3e3ba 100644 --- a/include/linux/pipe_fs_i.h +++ b/include/linux/pipe_fs_i.h @@ -71,7 +71,7 @@ struct pipe_inode_info { unsigned int files; unsigned int r_counter; unsigned int w_counter; - unsigned int poll_usage; + bool poll_usage; struct page *tmp_page; struct fasync_struct *fasync_readers; struct fasync_struct *fasync_writers; @@ -157,26 +157,6 @@ static inline bool pipe_full(unsigned int head, unsigned int tail, } /** - * pipe_space_for_user - Return number of slots available to userspace - * @head: The pipe ring head pointer - * @tail: The pipe ring tail pointer - * @pipe: The pipe info structure - */ -static inline unsigned int pipe_space_for_user(unsigned int head, unsigned int tail, - struct pipe_inode_info *pipe) -{ - unsigned int p_occupancy, p_space; - - p_occupancy = pipe_occupancy(head, tail); - if (p_occupancy >= pipe->max_usage) - return 0; - p_space = pipe->ring_size - p_occupancy; - if (p_space > pipe->max_usage) - p_space = pipe->max_usage; - return p_space; -} - -/** * pipe_buf_get - get a reference to a pipe_buffer * @pipe: the pipe that the buffer belongs to * @buf: the buffer to get a reference to @@ -229,6 +209,15 @@ static inline bool pipe_buf_try_steal(struct pipe_inode_info *pipe, return buf->ops->try_steal(pipe, buf); } +static inline void pipe_discard_from(struct pipe_inode_info *pipe, + unsigned int old_head) +{ + unsigned int mask = pipe->ring_size - 1; + + while (pipe->head > old_head) + pipe_buf_release(pipe, &pipe->bufs[--pipe->head & mask]); +} + /* Differs from PIPE_BUF in that PIPE_SIZE is the length of the actual memory allocation, whereas PIPE_BUF makes atomicity guarantees. */ #define PIPE_SIZE PAGE_SIZE @@ -238,10 +227,6 @@ void pipe_lock(struct pipe_inode_info *); void pipe_unlock(struct pipe_inode_info *); void pipe_double_lock(struct pipe_inode_info *, struct pipe_inode_info *); -extern unsigned int pipe_max_size; -extern unsigned long pipe_user_pages_hard; -extern unsigned long pipe_user_pages_soft; - /* Wait for a pipe to be readable/writable while dropping the pipe lock */ void pipe_wait_readable(struct pipe_inode_info *); void pipe_wait_writable(struct pipe_inode_info *); diff --git a/include/linux/pktcdvd.h b/include/linux/pktcdvd.h index 174601554b06..f9c5ac80d59b 100644 --- a/include/linux/pktcdvd.h +++ b/include/linux/pktcdvd.h @@ -152,14 +152,6 @@ struct packet_stacked_data }; #define PSD_POOL_SIZE 64 -struct pktcdvd_kobj -{ - struct kobject kobj; - struct pktcdvd_device *pd; -}; -#define to_pktcdvdkobj(_k) \ - ((struct pktcdvd_kobj*)container_of(_k,struct pktcdvd_kobj,kobj)) - struct pktcdvd_device { struct block_device *bdev; /* dev attached */ @@ -183,6 +175,8 @@ struct pktcdvd_device spinlock_t lock; /* Serialize access to bio_queue */ struct rb_root bio_queue; /* Work queue of bios we need to handle */ int bio_queue_size; /* Number of nodes in bio_queue */ + bool congested; /* Someone is waiting for bio_queue_size + * to drop. */ sector_t current_sector; /* Keep track of where the elevator is */ atomic_t scan_queue; /* Set to non-zero when pkt_handle_queue */ /* needs to be run. */ @@ -195,8 +189,6 @@ struct pktcdvd_device int write_congestion_on; struct device *dev; /* sysfs pktcdvd[0-7] dev */ - struct pktcdvd_kobj *kobj_stat; /* sysfs pktcdvd[0-7]/stat/ */ - struct pktcdvd_kobj *kobj_wqueue; /* sysfs pktcdvd[0-7]/write_queue/ */ struct dentry *dfs_d_root; /* debugfs: devname directory */ struct dentry *dfs_f_info; /* debugfs: info file */ diff --git a/include/linux/platform_data/ad5755.h b/include/linux/platform_data/ad5755.h deleted file mode 100644 index e371e08f04bc..000000000000 --- a/include/linux/platform_data/ad5755.h +++ /dev/null @@ -1,102 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright 2012 Analog Devices Inc. - */ -#ifndef __LINUX_PLATFORM_DATA_AD5755_H__ -#define __LINUX_PLATFORM_DATA_AD5755_H__ - -enum ad5755_mode { - AD5755_MODE_VOLTAGE_0V_5V = 0, - AD5755_MODE_VOLTAGE_0V_10V = 1, - AD5755_MODE_VOLTAGE_PLUSMINUS_5V = 2, - AD5755_MODE_VOLTAGE_PLUSMINUS_10V = 3, - AD5755_MODE_CURRENT_4mA_20mA = 4, - AD5755_MODE_CURRENT_0mA_20mA = 5, - AD5755_MODE_CURRENT_0mA_24mA = 6, -}; - -enum ad5755_dc_dc_phase { - AD5755_DC_DC_PHASE_ALL_SAME_EDGE = 0, - AD5755_DC_DC_PHASE_A_B_SAME_EDGE_C_D_OPP_EDGE = 1, - AD5755_DC_DC_PHASE_A_C_SAME_EDGE_B_D_OPP_EDGE = 2, - AD5755_DC_DC_PHASE_90_DEGREE = 3, -}; - -enum ad5755_dc_dc_freq { - AD5755_DC_DC_FREQ_250kHZ = 0, - AD5755_DC_DC_FREQ_410kHZ = 1, - AD5755_DC_DC_FREQ_650kHZ = 2, -}; - -enum ad5755_dc_dc_maxv { - AD5755_DC_DC_MAXV_23V = 0, - AD5755_DC_DC_MAXV_24V5 = 1, - AD5755_DC_DC_MAXV_27V = 2, - AD5755_DC_DC_MAXV_29V5 = 3, -}; - -enum ad5755_slew_rate { - AD5755_SLEW_RATE_64k = 0, - AD5755_SLEW_RATE_32k = 1, - AD5755_SLEW_RATE_16k = 2, - AD5755_SLEW_RATE_8k = 3, - AD5755_SLEW_RATE_4k = 4, - AD5755_SLEW_RATE_2k = 5, - AD5755_SLEW_RATE_1k = 6, - AD5755_SLEW_RATE_500 = 7, - AD5755_SLEW_RATE_250 = 8, - AD5755_SLEW_RATE_125 = 9, - AD5755_SLEW_RATE_64 = 10, - AD5755_SLEW_RATE_32 = 11, - AD5755_SLEW_RATE_16 = 12, - AD5755_SLEW_RATE_8 = 13, - AD5755_SLEW_RATE_4 = 14, - AD5755_SLEW_RATE_0_5 = 15, -}; - -enum ad5755_slew_step_size { - AD5755_SLEW_STEP_SIZE_1 = 0, - AD5755_SLEW_STEP_SIZE_2 = 1, - AD5755_SLEW_STEP_SIZE_4 = 2, - AD5755_SLEW_STEP_SIZE_8 = 3, - AD5755_SLEW_STEP_SIZE_16 = 4, - AD5755_SLEW_STEP_SIZE_32 = 5, - AD5755_SLEW_STEP_SIZE_64 = 6, - AD5755_SLEW_STEP_SIZE_128 = 7, - AD5755_SLEW_STEP_SIZE_256 = 8, -}; - -/** - * struct ad5755_platform_data - AD5755 DAC driver platform data - * @ext_dc_dc_compenstation_resistor: Whether an external DC-DC converter - * compensation register is used. - * @dc_dc_phase: DC-DC converter phase. - * @dc_dc_freq: DC-DC converter frequency. - * @dc_dc_maxv: DC-DC maximum allowed boost voltage. - * @dac.mode: The mode to be used for the DAC output. - * @dac.ext_current_sense_resistor: Whether an external current sense resistor - * is used. - * @dac.enable_voltage_overrange: Whether to enable 20% voltage output overrange. - * @dac.slew.enable: Whether to enable digital slew. - * @dac.slew.rate: Slew rate of the digital slew. - * @dac.slew.step_size: Slew step size of the digital slew. - **/ -struct ad5755_platform_data { - bool ext_dc_dc_compenstation_resistor; - enum ad5755_dc_dc_phase dc_dc_phase; - enum ad5755_dc_dc_freq dc_dc_freq; - enum ad5755_dc_dc_maxv dc_dc_maxv; - - struct { - enum ad5755_mode mode; - bool ext_current_sense_resistor; - bool enable_voltage_overrange; - struct { - bool enable; - enum ad5755_slew_rate rate; - enum ad5755_slew_step_size step_size; - } slew; - } dac[4]; -}; - -#endif diff --git a/include/linux/platform_data/adp5588.h b/include/linux/platform_data/adp5588.h deleted file mode 100644 index 6d3f7d911a92..000000000000 --- a/include/linux/platform_data/adp5588.h +++ /dev/null @@ -1,171 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * Analog Devices ADP5588 I/O Expander and QWERTY Keypad Controller - * - * Copyright 2009-2010 Analog Devices Inc. - */ - -#ifndef _ADP5588_H -#define _ADP5588_H - -#define DEV_ID 0x00 /* Device ID */ -#define CFG 0x01 /* Configuration Register1 */ -#define INT_STAT 0x02 /* Interrupt Status Register */ -#define KEY_LCK_EC_STAT 0x03 /* Key Lock and Event Counter Register */ -#define Key_EVENTA 0x04 /* Key Event Register A */ -#define Key_EVENTB 0x05 /* Key Event Register B */ -#define Key_EVENTC 0x06 /* Key Event Register C */ -#define Key_EVENTD 0x07 /* Key Event Register D */ -#define Key_EVENTE 0x08 /* Key Event Register E */ -#define Key_EVENTF 0x09 /* Key Event Register F */ -#define Key_EVENTG 0x0A /* Key Event Register G */ -#define Key_EVENTH 0x0B /* Key Event Register H */ -#define Key_EVENTI 0x0C /* Key Event Register I */ -#define Key_EVENTJ 0x0D /* Key Event Register J */ -#define KP_LCK_TMR 0x0E /* Keypad Lock1 to Lock2 Timer */ -#define UNLOCK1 0x0F /* Unlock Key1 */ -#define UNLOCK2 0x10 /* Unlock Key2 */ -#define GPIO_INT_STAT1 0x11 /* GPIO Interrupt Status */ -#define GPIO_INT_STAT2 0x12 /* GPIO Interrupt Status */ -#define GPIO_INT_STAT3 0x13 /* GPIO Interrupt Status */ -#define GPIO_DAT_STAT1 0x14 /* GPIO Data Status, Read twice to clear */ -#define GPIO_DAT_STAT2 0x15 /* GPIO Data Status, Read twice to clear */ -#define GPIO_DAT_STAT3 0x16 /* GPIO Data Status, Read twice to clear */ -#define GPIO_DAT_OUT1 0x17 /* GPIO DATA OUT */ -#define GPIO_DAT_OUT2 0x18 /* GPIO DATA OUT */ -#define GPIO_DAT_OUT3 0x19 /* GPIO DATA OUT */ -#define GPIO_INT_EN1 0x1A /* GPIO Interrupt Enable */ -#define GPIO_INT_EN2 0x1B /* GPIO Interrupt Enable */ -#define GPIO_INT_EN3 0x1C /* GPIO Interrupt Enable */ -#define KP_GPIO1 0x1D /* Keypad or GPIO Selection */ -#define KP_GPIO2 0x1E /* Keypad or GPIO Selection */ -#define KP_GPIO3 0x1F /* Keypad or GPIO Selection */ -#define GPI_EM1 0x20 /* GPI Event Mode 1 */ -#define GPI_EM2 0x21 /* GPI Event Mode 2 */ -#define GPI_EM3 0x22 /* GPI Event Mode 3 */ -#define GPIO_DIR1 0x23 /* GPIO Data Direction */ -#define GPIO_DIR2 0x24 /* GPIO Data Direction */ -#define GPIO_DIR3 0x25 /* GPIO Data Direction */ -#define GPIO_INT_LVL1 0x26 /* GPIO Edge/Level Detect */ -#define GPIO_INT_LVL2 0x27 /* GPIO Edge/Level Detect */ -#define GPIO_INT_LVL3 0x28 /* GPIO Edge/Level Detect */ -#define Debounce_DIS1 0x29 /* Debounce Disable */ -#define Debounce_DIS2 0x2A /* Debounce Disable */ -#define Debounce_DIS3 0x2B /* Debounce Disable */ -#define GPIO_PULL1 0x2C /* GPIO Pull Disable */ -#define GPIO_PULL2 0x2D /* GPIO Pull Disable */ -#define GPIO_PULL3 0x2E /* GPIO Pull Disable */ -#define CMP_CFG_STAT 0x30 /* Comparator Configuration and Status Register */ -#define CMP_CONFG_SENS1 0x31 /* Sensor1 Comparator Configuration Register */ -#define CMP_CONFG_SENS2 0x32 /* L2 Light Sensor Reference Level, Output Falling for Sensor 1 */ -#define CMP1_LVL2_TRIP 0x33 /* L2 Light Sensor Hysteresis (Active when Output Rising) for Sensor 1 */ -#define CMP1_LVL2_HYS 0x34 /* L3 Light Sensor Reference Level, Output Falling For Sensor 1 */ -#define CMP1_LVL3_TRIP 0x35 /* L3 Light Sensor Hysteresis (Active when Output Rising) For Sensor 1 */ -#define CMP1_LVL3_HYS 0x36 /* Sensor 2 Comparator Configuration Register */ -#define CMP2_LVL2_TRIP 0x37 /* L2 Light Sensor Reference Level, Output Falling for Sensor 2 */ -#define CMP2_LVL2_HYS 0x38 /* L2 Light Sensor Hysteresis (Active when Output Rising) for Sensor 2 */ -#define CMP2_LVL3_TRIP 0x39 /* L3 Light Sensor Reference Level, Output Falling For Sensor 2 */ -#define CMP2_LVL3_HYS 0x3A /* L3 Light Sensor Hysteresis (Active when Output Rising) For Sensor 2 */ -#define CMP1_ADC_DAT_R1 0x3B /* Comparator 1 ADC data Register1 */ -#define CMP1_ADC_DAT_R2 0x3C /* Comparator 1 ADC data Register2 */ -#define CMP2_ADC_DAT_R1 0x3D /* Comparator 2 ADC data Register1 */ -#define CMP2_ADC_DAT_R2 0x3E /* Comparator 2 ADC data Register2 */ - -#define ADP5588_DEVICE_ID_MASK 0xF - - /* Configuration Register1 */ -#define ADP5588_AUTO_INC (1 << 7) -#define ADP5588_GPIEM_CFG (1 << 6) -#define ADP5588_OVR_FLOW_M (1 << 5) -#define ADP5588_INT_CFG (1 << 4) -#define ADP5588_OVR_FLOW_IEN (1 << 3) -#define ADP5588_K_LCK_IM (1 << 2) -#define ADP5588_GPI_IEN (1 << 1) -#define ADP5588_KE_IEN (1 << 0) - -/* Interrupt Status Register */ -#define ADP5588_CMP2_INT (1 << 5) -#define ADP5588_CMP1_INT (1 << 4) -#define ADP5588_OVR_FLOW_INT (1 << 3) -#define ADP5588_K_LCK_INT (1 << 2) -#define ADP5588_GPI_INT (1 << 1) -#define ADP5588_KE_INT (1 << 0) - -/* Key Lock and Event Counter Register */ -#define ADP5588_K_LCK_EN (1 << 6) -#define ADP5588_LCK21 0x30 -#define ADP5588_KEC 0xF - -#define ADP5588_MAXGPIO 18 -#define ADP5588_BANK(offs) ((offs) >> 3) -#define ADP5588_BIT(offs) (1u << ((offs) & 0x7)) - -/* Put one of these structures in i2c_board_info platform_data */ - -#define ADP5588_KEYMAPSIZE 80 - -#define GPI_PIN_ROW0 97 -#define GPI_PIN_ROW1 98 -#define GPI_PIN_ROW2 99 -#define GPI_PIN_ROW3 100 -#define GPI_PIN_ROW4 101 -#define GPI_PIN_ROW5 102 -#define GPI_PIN_ROW6 103 -#define GPI_PIN_ROW7 104 -#define GPI_PIN_COL0 105 -#define GPI_PIN_COL1 106 -#define GPI_PIN_COL2 107 -#define GPI_PIN_COL3 108 -#define GPI_PIN_COL4 109 -#define GPI_PIN_COL5 110 -#define GPI_PIN_COL6 111 -#define GPI_PIN_COL7 112 -#define GPI_PIN_COL8 113 -#define GPI_PIN_COL9 114 - -#define GPI_PIN_ROW_BASE GPI_PIN_ROW0 -#define GPI_PIN_ROW_END GPI_PIN_ROW7 -#define GPI_PIN_COL_BASE GPI_PIN_COL0 -#define GPI_PIN_COL_END GPI_PIN_COL9 - -#define GPI_PIN_BASE GPI_PIN_ROW_BASE -#define GPI_PIN_END GPI_PIN_COL_END - -#define ADP5588_GPIMAPSIZE_MAX (GPI_PIN_END - GPI_PIN_BASE + 1) - -struct adp5588_gpi_map { - unsigned short pin; - unsigned short sw_evt; -}; - -struct adp5588_kpad_platform_data { - int rows; /* Number of rows */ - int cols; /* Number of columns */ - const unsigned short *keymap; /* Pointer to keymap */ - unsigned short keymapsize; /* Keymap size */ - unsigned repeat:1; /* Enable key repeat */ - unsigned en_keylock:1; /* Enable Key Lock feature */ - unsigned short unlock_key1; /* Unlock Key 1 */ - unsigned short unlock_key2; /* Unlock Key 2 */ - const struct adp5588_gpi_map *gpimap; - unsigned short gpimapsize; - const struct adp5588_gpio_platform_data *gpio_data; -}; - -struct i2c_client; /* forward declaration */ - -struct adp5588_gpio_platform_data { - int gpio_start; /* GPIO Chip base # */ - const char *const *names; - unsigned irq_base; /* interrupt base # */ - unsigned pullup_dis_mask; /* Pull-Up Disable Mask */ - int (*setup)(struct i2c_client *client, - unsigned gpio, unsigned ngpio, - void *context); - int (*teardown)(struct i2c_client *client, - unsigned gpio, unsigned ngpio, - void *context); - void *context; -}; - -#endif diff --git a/include/linux/platform_data/asoc-poodle.h b/include/linux/platform_data/asoc-poodle.h new file mode 100644 index 000000000000..2052fad55c5c --- /dev/null +++ b/include/linux/platform_data/asoc-poodle.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LINUX_PLATFORM_DATA_POODLE_AUDIO +#define __LINUX_PLATFORM_DATA_POODLE_AUDIO + +/* locomo is not a proper gpio driver, and uses its own api */ +struct poodle_audio_platform_data { + struct device *locomo_dev; + + int gpio_amp_on; + int gpio_mute_l; + int gpio_mute_r; + int gpio_232vcc_on; + int gpio_jk_b; +}; + +#endif diff --git a/include/linux/platform_data/asoc-pxa.h b/include/linux/platform_data/asoc-pxa.h new file mode 100644 index 000000000000..327454cd8246 --- /dev/null +++ b/include/linux/platform_data/asoc-pxa.h @@ -0,0 +1,31 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __SOC_PXA_AUDIO_H__ +#define __SOC_PXA_AUDIO_H__ + +#include <sound/core.h> +#include <sound/pcm.h> +#include <sound/ac97_codec.h> + +/* + * @reset_gpio: AC97 reset gpio (normally gpio113 or gpio95) + * a -1 value means no gpio will be used for reset + * @codec_pdata: AC97 codec platform_data + + * reset_gpio should only be specified for pxa27x CPUs where a silicon + * bug prevents correct operation of the reset line. If not specified, + * the default behaviour on these CPUs is to consider gpio 113 as the + * AC97 reset line, which is the default on most boards. + */ +typedef struct { + int (*startup)(struct snd_pcm_substream *, void *); + void (*shutdown)(struct snd_pcm_substream *, void *); + void (*suspend)(void *); + void (*resume)(void *); + void *priv; + int reset_gpio; + void *codec_pdata[AC97_BUS_MAX_DEVICES]; +} pxa2xx_audio_ops_t; + +extern void pxa_set_ac97_info(pxa2xx_audio_ops_t *ops); + +#endif diff --git a/include/linux/platform_data/bcm7038_wdt.h b/include/linux/platform_data/bcm7038_wdt.h new file mode 100644 index 000000000000..e18cfd9ec8f9 --- /dev/null +++ b/include/linux/platform_data/bcm7038_wdt.h @@ -0,0 +1,8 @@ +#ifndef __BCM7038_WDT_PDATA_H +#define __BCM7038_WDT_PDATA_H + +struct bcm7038_wdt_platform_data { + const char *clk_name; +}; + +#endif /* __BCM7038_WDT_PDATA_H */ diff --git a/include/linux/platform_data/brcmfmac.h b/include/linux/platform_data/brcmfmac.h index 2b5676ff35be..f922a192fe58 100644 --- a/include/linux/platform_data/brcmfmac.h +++ b/include/linux/platform_data/brcmfmac.h @@ -178,7 +178,7 @@ struct brcmfmac_platform_data { void (*power_off)(void); char *fw_alternative_path; int device_count; - struct brcmfmac_pd_device devices[0]; + struct brcmfmac_pd_device devices[]; }; diff --git a/include/linux/platform_data/brcmnand.h b/include/linux/platform_data/brcmnand.h new file mode 100644 index 000000000000..8b8777985dce --- /dev/null +++ b/include/linux/platform_data/brcmnand.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef BRCMNAND_PLAT_DATA_H +#define BRCMNAND_PLAT_DATA_H + +struct brcmnand_platform_data { + int chip_select; + const char * const *part_probe_types; + unsigned int ecc_stepsize; + unsigned int ecc_strength; +}; + +#endif /* BRCMNAND_PLAT_DATA_H */ diff --git a/include/linux/platform_data/clk-fch.h b/include/linux/platform_data/clk-fch.h index b9f682459f08..11a2a23fd9b2 100644 --- a/include/linux/platform_data/clk-fch.h +++ b/include/linux/platform_data/clk-fch.h @@ -12,7 +12,7 @@ struct fch_clk_data { void __iomem *base; - u32 is_rv; + char *name; }; #endif /* __CLK_FCH_H */ diff --git a/include/linux/platform_data/cros_ec_commands.h b/include/linux/platform_data/cros_ec_commands.h index 271bd87bff0a..5744a2d746aa 100644 --- a/include/linux/platform_data/cros_ec_commands.h +++ b/include/linux/platform_data/cros_ec_commands.h @@ -13,8 +13,8 @@ #ifndef __CROS_EC_COMMANDS_H #define __CROS_EC_COMMANDS_H - - +#include <linux/bits.h> +#include <linux/types.h> #define BUILD_ASSERT(_cond) @@ -51,10 +51,14 @@ /* * The actual block is 0x800-0x8ff, but some BIOSes think it's 0x880-0x8ff * and they tell the kernel that so we have to think of it as two parts. + * + * Other BIOSes report only the I/O port region spanned by the Microchip + * MEC series EC; an attempt to address a larger region may fail. */ -#define EC_HOST_CMD_REGION0 0x800 -#define EC_HOST_CMD_REGION1 0x880 -#define EC_HOST_CMD_REGION_SIZE 0x80 +#define EC_HOST_CMD_REGION0 0x800 +#define EC_HOST_CMD_REGION1 0x880 +#define EC_HOST_CMD_REGION_SIZE 0x80 +#define EC_HOST_CMD_MEC_REGION_SIZE 0x8 /* EC command register bit functions */ #define EC_LPC_CMDR_DATA BIT(0) /* Data ready for host to read */ @@ -783,7 +787,7 @@ struct ec_host_response { * * Packets always start with a request or response header. They are followed * by data_len bytes of data. If the data_crc_present flag is set, the data - * bytes are followed by a CRC-8 of that data, using using x^8 + x^2 + x + 1 + * bytes are followed by a CRC-8 of that data, using x^8 + x^2 + x + 1 * polynomial. * * Host algorithm when sending a request q: @@ -1296,6 +1300,8 @@ enum ec_feature_code { * mux. */ EC_FEATURE_TYPEC_MUX_REQUIRE_AP_ACK = 43, + /* The MCU is a System Companion Processor (SCP) 2nd Core. */ + EC_FEATURE_SCP_C1 = 45, }; #define EC_FEATURE_MASK_0(event_code) BIT(event_code % 32) @@ -3386,6 +3392,9 @@ enum ec_mkbp_event { /* Send an incoming CEC message to the AP */ EC_MKBP_EVENT_CEC_MESSAGE = 9, + /* Peripheral device charger event */ + EC_MKBP_EVENT_PCHG = 12, + /* Number of MKBP events */ EC_MKBP_EVENT_COUNT, }; @@ -5527,6 +5536,67 @@ enum pchg_state { [PCHG_STATE_CONNECTED] = "CONNECTED", \ } +/* + * Update firmware of peripheral chip + */ +#define EC_CMD_PCHG_UPDATE 0x0136 + +/* Port number is encoded in bit[28:31]. */ +#define EC_MKBP_PCHG_PORT_SHIFT 28 +/* Utility macro for converting MKBP event to port number. */ +#define EC_MKBP_PCHG_EVENT_TO_PORT(e) (((e) >> EC_MKBP_PCHG_PORT_SHIFT) & 0xf) +/* Utility macro for extracting event bits. */ +#define EC_MKBP_PCHG_EVENT_MASK(e) ((e) \ + & GENMASK(EC_MKBP_PCHG_PORT_SHIFT-1, 0)) + +#define EC_MKBP_PCHG_UPDATE_OPENED BIT(0) +#define EC_MKBP_PCHG_WRITE_COMPLETE BIT(1) +#define EC_MKBP_PCHG_UPDATE_CLOSED BIT(2) +#define EC_MKBP_PCHG_UPDATE_ERROR BIT(3) +#define EC_MKBP_PCHG_DEVICE_EVENT BIT(4) + +enum ec_pchg_update_cmd { + /* Reset chip to normal mode. */ + EC_PCHG_UPDATE_CMD_RESET_TO_NORMAL = 0, + /* Reset and put a chip in update (a.k.a. download) mode. */ + EC_PCHG_UPDATE_CMD_OPEN, + /* Write a block of data containing FW image. */ + EC_PCHG_UPDATE_CMD_WRITE, + /* Close update session. */ + EC_PCHG_UPDATE_CMD_CLOSE, + /* End of commands */ + EC_PCHG_UPDATE_CMD_COUNT, +}; + +struct ec_params_pchg_update { + /* PCHG port number */ + uint8_t port; + /* enum ec_pchg_update_cmd */ + uint8_t cmd; + /* Padding */ + uint8_t reserved0; + uint8_t reserved1; + /* Version of new firmware */ + uint32_t version; + /* CRC32 of new firmware */ + uint32_t crc32; + /* Address in chip memory where <data> is written to */ + uint32_t addr; + /* Size of <data> */ + uint32_t size; + /* Partial data of new firmware */ + uint8_t data[]; +} __ec_align4; + +BUILD_ASSERT(EC_PCHG_UPDATE_CMD_COUNT + < BIT(sizeof(((struct ec_params_pchg_update *)0)->cmd)*8)); + +struct ec_response_pchg_update { + /* Block size */ + uint32_t block_size; +} __ec_align4; + + /*****************************************************************************/ /* Voltage regulator controls */ @@ -5644,7 +5714,7 @@ struct ec_response_typec_discovery { uint8_t svid_count; /* Number of SVIDs partner sent */ uint16_t reserved; uint32_t discovery_vdo[6]; /* Max VDOs allowed after VDM header is 6 */ - struct svid_mode_info svids[0]; + struct svid_mode_info svids[]; } __ec_align1; /* USB Type-C commands for AP-controlled device policy. */ @@ -5654,8 +5724,21 @@ enum typec_control_command { TYPEC_CONTROL_COMMAND_EXIT_MODES, TYPEC_CONTROL_COMMAND_CLEAR_EVENTS, TYPEC_CONTROL_COMMAND_ENTER_MODE, + TYPEC_CONTROL_COMMAND_TBT_UFP_REPLY, + TYPEC_CONTROL_COMMAND_USB_MUX_SET, +}; + +/* Replies the AP may specify to the TBT EnterMode command as a UFP */ +enum typec_tbt_ufp_reply { + TYPEC_TBT_UFP_REPLY_NAK, + TYPEC_TBT_UFP_REPLY_ACK, }; +struct typec_usb_mux_set { + uint8_t mux_index; /* Index of the mux to set in the chain */ + uint8_t mux_flags; /* USB_PD_MUX_*-encoded USB mux state to set */ +} __ec_align1; + struct ec_params_typec_control { uint8_t port; uint8_t command; /* enum typec_control_command */ @@ -5669,6 +5752,8 @@ struct ec_params_typec_control { union { uint32_t clear_events_mask; uint8_t mode_to_enter; /* enum typec_mode */ + uint8_t tbt_ufp_reply; /* enum typec_tbt_ufp_reply */ + struct typec_usb_mux_set mux_params; uint8_t placeholder[128]; }; } __ec_align1; @@ -5747,6 +5832,9 @@ enum tcpc_cc_polarity { #define PD_STATUS_EVENT_SOP_DISC_DONE BIT(0) #define PD_STATUS_EVENT_SOP_PRIME_DISC_DONE BIT(1) #define PD_STATUS_EVENT_HARD_RESET BIT(2) +#define PD_STATUS_EVENT_DISCONNECTED BIT(3) +#define PD_STATUS_EVENT_MUX_0_SET_DONE BIT(4) +#define PD_STATUS_EVENT_MUX_1_SET_DONE BIT(5) struct ec_params_typec_status { uint8_t port; diff --git a/include/linux/platform_data/cros_ec_proto.h b/include/linux/platform_data/cros_ec_proto.h index df3c78c92ca2..e43107e0bee1 100644 --- a/include/linux/platform_data/cros_ec_proto.h +++ b/include/linux/platform_data/cros_ec_proto.h @@ -19,8 +19,12 @@ #define CROS_EC_DEV_ISH_NAME "cros_ish" #define CROS_EC_DEV_PD_NAME "cros_pd" #define CROS_EC_DEV_SCP_NAME "cros_scp" +#define CROS_EC_DEV_SCP_C1_NAME "cros_scp_c1" #define CROS_EC_DEV_TP_NAME "cros_tp" +#define CROS_EC_DEV_EC_INDEX 0 +#define CROS_EC_DEV_PD_INDEX 1 + /* * The EC is unresponsive for a time after a reboot command. Add a * simple delay to make sure that the bus stays locked. @@ -76,8 +80,6 @@ struct cros_ec_command { * struct cros_ec_device - Information about a ChromeOS EC device. * @phys_name: Name of physical comms layer (e.g. 'i2c-4'). * @dev: Device pointer for physical comms device - * @was_wake_device: True if this device was set to wake the system from - * sleep at the last suspend. * @cros_class: The class structure for this device. * @cmd_readmem: Direct read of the EC memory-mapped region, if supported. * @offset: Is within EC_LPC_ADDR_MEMMAP region. @@ -137,7 +139,6 @@ struct cros_ec_device { /* These are used by other drivers that want to talk to the EC */ const char *phys_name; struct device *dev; - bool was_wake_device; struct class *cros_class; int (*cmd_readmem)(struct cros_ec_device *ec, unsigned int offset, unsigned int bytes, void *dest); @@ -168,6 +169,7 @@ struct cros_ec_device { int event_size; u32 host_event_wake_mask; u32 last_resume_result; + u16 suspend_timeout_ms; ktime_t last_event_time; struct notifier_block notifier_ready; @@ -216,6 +218,9 @@ int cros_ec_prepare_tx(struct cros_ec_device *ec_dev, int cros_ec_check_result(struct cros_ec_device *ec_dev, struct cros_ec_command *msg); +int cros_ec_cmd_xfer(struct cros_ec_device *ec_dev, + struct cros_ec_command *msg); + int cros_ec_cmd_xfer_status(struct cros_ec_device *ec_dev, struct cros_ec_command *msg); @@ -231,8 +236,8 @@ bool cros_ec_check_features(struct cros_ec_dev *ec, int feature); int cros_ec_get_sensor_count(struct cros_ec_dev *ec); -int cros_ec_command(struct cros_ec_device *ec_dev, unsigned int version, int command, void *outdata, - int outsize, void *indata, int insize); +int cros_ec_cmd(struct cros_ec_device *ec_dev, unsigned int version, int command, void *outdata, + size_t outsize, void *indata, size_t insize); /** * cros_ec_get_time_ns() - Return time in ns. diff --git a/include/linux/platform_data/davinci_asp.h b/include/linux/platform_data/davinci_asp.h index 76b13ef67562..c8645b2ed3c0 100644 --- a/include/linux/platform_data/davinci_asp.h +++ b/include/linux/platform_data/davinci_asp.h @@ -1,16 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * TI DaVinci Audio Serial Port support * * Copyright (C) 2012 Texas Instruments Incorporated - https://www.ti.com/ - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation version 2. - * - * This program is distributed "as is" WITHOUT ANY WARRANTY of any - * kind, whether express or implied; without even the implied warranty - * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. */ #ifndef __DAVINCI_ASP_H diff --git a/include/linux/platform_data/dma-hsu.h b/include/linux/platform_data/dma-hsu.h index c65b412b2b33..611bae193c1c 100644 --- a/include/linux/platform_data/dma-hsu.h +++ b/include/linux/platform_data/dma-hsu.h @@ -8,7 +8,7 @@ #ifndef _PLATFORM_DATA_DMA_HSU_H #define _PLATFORM_DATA_DMA_HSU_H -#include <linux/device.h> +struct device; struct hsu_dma_slave { struct device *dma_dev; diff --git a/include/linux/platform_data/emc2305.h b/include/linux/platform_data/emc2305.h new file mode 100644 index 000000000000..54d672dd6f7d --- /dev/null +++ b/include/linux/platform_data/emc2305.h @@ -0,0 +1,22 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __LINUX_PLATFORM_DATA_EMC2305__ +#define __LINUX_PLATFORM_DATA_EMC2305__ + +#define EMC2305_PWM_MAX 5 + +/** + * struct emc2305_platform_data - EMC2305 driver platform data + * @max_state: maximum cooling state of the cooling device; + * @pwm_num: number of active channels; + * @pwm_separate: separate PWM settings for every channel; + * @pwm_min: array of minimum PWM per channel; + */ +struct emc2305_platform_data { + u8 max_state; + u8 pwm_num; + bool pwm_separate; + u8 pwm_min[EMC2305_PWM_MAX]; +}; + +#endif diff --git a/include/linux/platform_data/eth_ixp4xx.h b/include/linux/platform_data/eth_ixp4xx.h deleted file mode 100644 index 114b0940729f..000000000000 --- a/include/linux/platform_data/eth_ixp4xx.h +++ /dev/null @@ -1,21 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __PLATFORM_DATA_ETH_IXP4XX -#define __PLATFORM_DATA_ETH_IXP4XX - -#include <linux/types.h> - -#define IXP4XX_ETH_NPEA 0x00 -#define IXP4XX_ETH_NPEB 0x10 -#define IXP4XX_ETH_NPEC 0x20 - -/* Information about built-in Ethernet MAC interfaces */ -struct eth_plat_info { - u8 phy; /* MII PHY ID, 0 - 31 */ - u8 rxq; /* configurable, currently 0 - 31 only */ - u8 txreadyq; - u8 hwaddr[6]; - u8 npe; /* NPE instance used by this interface */ - bool has_mdio; /* If this instance has an MDIO bus */ -}; - -#endif diff --git a/include/linux/platform_data/gpio-davinci.h b/include/linux/platform_data/gpio-davinci.h index e182a46e609f..b82e44662efe 100644 --- a/include/linux/platform_data/gpio-davinci.h +++ b/include/linux/platform_data/gpio-davinci.h @@ -1,16 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * DaVinci GPIO Platform Related Defines * * Copyright (C) 2013 Texas Instruments Incorporated - https://www.ti.com/ - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation version 2. - * - * This program is distributed "as is" WITHOUT ANY WARRANTY of any - * kind, whether express or implied; without even the implied warranty - * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. */ #ifndef __DAVINCI_GPIO_PLATFORM_H diff --git a/include/linux/platform_data/max732x.h b/include/linux/platform_data/max732x.h index f231c635faec..423999207cd5 100644 --- a/include/linux/platform_data/max732x.h +++ b/include/linux/platform_data/max732x.h @@ -7,17 +7,5 @@ struct max732x_platform_data { /* number of the first GPIO */ unsigned gpio_base; - - /* interrupt base */ - int irq_base; - - void *context; /* param to setup/teardown */ - - int (*setup)(struct i2c_client *client, - unsigned gpio, unsigned ngpio, - void *context); - int (*teardown)(struct i2c_client *client, - unsigned gpio, unsigned ngpio, - void *context); }; #endif /* __LINUX_I2C_MAX732X_H */ diff --git a/include/linux/platform_data/mlxreg.h b/include/linux/platform_data/mlxreg.h index 40185f9d7c14..a6bd74e29b6b 100644 --- a/include/linux/platform_data/mlxreg.h +++ b/include/linux/platform_data/mlxreg.h @@ -216,6 +216,8 @@ struct mlxreg_core_platform_data { * @mask_low: low aggregation interrupt common mask; * @deferred_nr: I2C adapter number must be exist prior probing execution; * @shift_nr: I2C adapter numbers must be incremented by this value; + * @handle: handle to be passed by callback; + * @completion_notify: callback to notify when platform driver probing is done; */ struct mlxreg_core_hotplug_platform_data { struct mlxreg_core_item *items; @@ -228,6 +230,8 @@ struct mlxreg_core_hotplug_platform_data { u32 mask_low; int deferred_nr; int shift_nr; + void *handle; + int (*completion_notify)(void *handle, int id); }; #endif /* __LINUX_PLATFORM_DATA_MLXREG_H */ diff --git a/include/linux/platform_data/pca953x.h b/include/linux/platform_data/pca953x.h index 4eb53e023997..96c1a14ab365 100644 --- a/include/linux/platform_data/pca953x.h +++ b/include/linux/platform_data/pca953x.h @@ -22,7 +22,7 @@ struct pca953x_platform_data { int (*setup)(struct i2c_client *client, unsigned gpio, unsigned ngpio, void *context); - int (*teardown)(struct i2c_client *client, + void (*teardown)(struct i2c_client *client, unsigned gpio, unsigned ngpio, void *context); const char *const *names; diff --git a/include/linux/platform_data/pcf857x.h b/include/linux/platform_data/pcf857x.h index 11d4ed78c7f4..01d0a3ea3aef 100644 --- a/include/linux/platform_data/pcf857x.h +++ b/include/linux/platform_data/pcf857x.h @@ -36,7 +36,7 @@ struct pcf857x_platform_data { int (*setup)(struct i2c_client *client, int gpio, unsigned ngpio, void *context); - int (*teardown)(struct i2c_client *client, + void (*teardown)(struct i2c_client *client, int gpio, unsigned ngpio, void *context); void *context; diff --git a/include/linux/platform_data/pcmcia-pxa2xx_viper.h b/include/linux/platform_data/pcmcia-pxa2xx_viper.h deleted file mode 100644 index a23b58aff9e1..000000000000 --- a/include/linux/platform_data/pcmcia-pxa2xx_viper.h +++ /dev/null @@ -1,12 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __ARCOM_PCMCIA_H -#define __ARCOM_PCMCIA_H - -struct arcom_pcmcia_pdata { - int cd_gpio; - int rdy_gpio; - int pwr_gpio; - void (*reset)(int state); -}; - -#endif diff --git a/include/linux/mmc/sh_mmcif.h b/include/linux/platform_data/sh_mmcif.h index e25533b95d9f..6eb914f958f9 100644 --- a/include/linux/mmc/sh_mmcif.h +++ b/include/linux/platform_data/sh_mmcif.h @@ -1,7 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* - * include/linux/mmc/sh_mmcif.h - * * platform data for eMMC driver * * Copyright (C) 2010 Renesas Solutions Corp. diff --git a/include/linux/platform_data/spi-s3c64xx.h b/include/linux/platform_data/spi-s3c64xx.h index 773daf7915a3..5df1ace6d2c9 100644 --- a/include/linux/platform_data/spi-s3c64xx.h +++ b/include/linux/platform_data/spi-s3c64xx.h @@ -16,7 +16,6 @@ struct platform_device; * struct s3c64xx_spi_csinfo - ChipSelect description * @fb_delay: Slave specific feedback delay. * Refer to FB_CLK_SEL register definition in SPI chapter. - * @line: Custom 'identity' of the CS line. * * This is per SPI-Slave Chipselect information. * Allocate and initialize one in machine init code and make the @@ -24,7 +23,6 @@ struct platform_device; */ struct s3c64xx_spi_csinfo { u8 fb_delay; - unsigned line; }; /** @@ -43,26 +41,16 @@ struct s3c64xx_spi_info { /** * s3c64xx_spi_set_platdata - SPI Controller configure callback by the board * initialization code. - * @cfg_gpio: Pointer to gpio setup function. * @src_clk_nr: Clock the SPI controller is to use to generate SPI clocks. * @num_cs: Number of elements in the 'cs' array. * * Call this from machine init code for each SPI Controller that * has some chips attached to it. */ -extern void s3c64xx_spi0_set_platdata(int (*cfg_gpio)(void), int src_clk_nr, - int num_cs); -extern void s3c64xx_spi1_set_platdata(int (*cfg_gpio)(void), int src_clk_nr, - int num_cs); -extern void s3c64xx_spi2_set_platdata(int (*cfg_gpio)(void), int src_clk_nr, - int num_cs); +extern void s3c64xx_spi0_set_platdata(int src_clk_nr, int num_cs); /* defined by architecture to configure gpio */ extern int s3c64xx_spi0_cfg_gpio(void); -extern int s3c64xx_spi1_cfg_gpio(void); -extern int s3c64xx_spi2_cfg_gpio(void); extern struct s3c64xx_spi_info s3c64xx_spi0_pdata; -extern struct s3c64xx_spi_info s3c64xx_spi1_pdata; -extern struct s3c64xx_spi_info s3c64xx_spi2_pdata; #endif /*__SPI_S3C64XX_H */ diff --git a/include/linux/platform_data/ssm2518.h b/include/linux/platform_data/ssm2518.h deleted file mode 100644 index 3f9e632d6f63..000000000000 --- a/include/linux/platform_data/ssm2518.h +++ /dev/null @@ -1,21 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * SSM2518 amplifier audio driver - * - * Copyright 2013 Analog Devices Inc. - * Author: Lars-Peter Clausen <lars@metafoo.de> - */ - -#ifndef __LINUX_PLATFORM_DATA_SSM2518_H__ -#define __LINUX_PLATFORM_DATA_SSM2518_H__ - -/** - * struct ssm2518_platform_data - Platform data for the ssm2518 driver - * @enable_gpio: GPIO connected to the nSD pin. Set to -1 if the nSD pin is - * hardwired. - */ -struct ssm2518_platform_data { - int enable_gpio; -}; - -#endif diff --git a/include/linux/platform_data/timer-ixp4xx.h b/include/linux/platform_data/timer-ixp4xx.h deleted file mode 100644 index ee92ae7edaed..000000000000 --- a/include/linux/platform_data/timer-ixp4xx.h +++ /dev/null @@ -1,11 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __TIMER_IXP4XX_H -#define __TIMER_IXP4XX_H - -#include <linux/ioport.h> - -void __init ixp4xx_timer_setup(resource_size_t timerbase, - int timer_irq, - unsigned int timer_freq); - -#endif diff --git a/include/linux/platform_data/tps68470.h b/include/linux/platform_data/tps68470.h index 126d082c3f2e..e605a2cab07f 100644 --- a/include/linux/platform_data/tps68470.h +++ b/include/linux/platform_data/tps68470.h @@ -27,9 +27,14 @@ struct tps68470_regulator_platform_data { const struct regulator_init_data *reg_init_data[TPS68470_NUM_REGULATORS]; }; -struct tps68470_clk_platform_data { +struct tps68470_clk_consumer { const char *consumer_dev_name; const char *consumer_con_id; }; +struct tps68470_clk_platform_data { + unsigned int n_consumers; + struct tps68470_clk_consumer consumers[]; +}; + #endif diff --git a/include/linux/platform_data/uio_dmem_genirq.h b/include/linux/platform_data/uio_dmem_genirq.h index 973c1bb32168..c8f6de685306 100644 --- a/include/linux/platform_data/uio_dmem_genirq.h +++ b/include/linux/platform_data/uio_dmem_genirq.h @@ -1,16 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * include/linux/platform_data/uio_dmem_genirq.h * * Copyright (C) 2012 Damian Hobson-Garcia - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation version 2. - * - * This program is distributed "as is" WITHOUT ANY WARRANTY of any - * kind, whether express or implied; without even the implied warranty - * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. */ #ifndef _UIO_DMEM_GENIRQ_H diff --git a/include/linux/platform_data/uio_pruss.h b/include/linux/platform_data/uio_pruss.h index 31f2e22661bc..f76fa393b802 100644 --- a/include/linux/platform_data/uio_pruss.h +++ b/include/linux/platform_data/uio_pruss.h @@ -1,18 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * include/linux/platform_data/uio_pruss.h * * Platform data for uio_pruss driver * * Copyright (C) 2010-11 Texas Instruments Incorporated - https://www.ti.com/ - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation version 2. - * - * This program is distributed "as is" WITHOUT ANY WARRANTY of any - * kind, whether express or implied; without even the implied warranty - * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. */ #ifndef _UIO_PRUSS_H_ diff --git a/include/linux/platform_data/usb-omap.h b/include/linux/platform_data/usb-omap.h index 5e70d667031c..580978e468f8 100644 --- a/include/linux/platform_data/usb-omap.h +++ b/include/linux/platform_data/usb-omap.h @@ -1,22 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * usb-omap.h - Platform data for the various OMAP USB IPs * * Copyright (C) 2012 Texas Instruments Incorporated - https://www.ti.com - * - * This software is distributed under the terms of the GNU General Public - * License ("GPL") version 2, as published by the Free Software Foundation. - * - * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" - * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE - * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE - * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE - * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR - * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF - * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS - * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN - * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) - * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE - * POSSIBILITY OF SUCH DAMAGE. */ #define OMAP3_HS_USB_PORTS 3 diff --git a/include/linux/platform_data/usb-omap1.h b/include/linux/platform_data/usb-omap1.h index 878e572a78bf..e7b8dc92a269 100644 --- a/include/linux/platform_data/usb-omap1.h +++ b/include/linux/platform_data/usb-omap1.h @@ -50,6 +50,8 @@ struct omap_usb_config { int (*ocpi_enable)(void); void (*lb_reset)(void); + + int (*transceiver_power)(int on); }; #endif /* __LINUX_USB_OMAP1_H */ diff --git a/include/linux/platform_data/usb-s3c2410_udc.h b/include/linux/platform_data/usb-s3c2410_udc.h index 07394819d03b..c0fbe1fe3426 100644 --- a/include/linux/platform_data/usb-s3c2410_udc.h +++ b/include/linux/platform_data/usb-s3c2410_udc.h @@ -22,12 +22,6 @@ enum s3c2410_udc_cmd_e { struct s3c2410_udc_mach_info { void (*udc_command)(enum s3c2410_udc_cmd_e); void (*vbus_draw)(unsigned int ma); - - unsigned int pullup_pin; - unsigned int pullup_pin_inverted; - - unsigned int vbus_pin; - unsigned char vbus_pin_inverted; }; extern void __init s3c24xx_udc_set_platdata(struct s3c2410_udc_mach_info *); diff --git a/include/linux/platform_data/video-imxfb.h b/include/linux/platform_data/video-imxfb.h deleted file mode 100644 index 02812651af7d..000000000000 --- a/include/linux/platform_data/video-imxfb.h +++ /dev/null @@ -1,70 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * This structure describes the machine which we are running on. - */ -#ifndef __MACH_IMXFB_H__ -#define __MACH_IMXFB_H__ - -#include <linux/fb.h> - -#define PCR_TFT (1 << 31) -#define PCR_COLOR (1 << 30) -#define PCR_PBSIZ_1 (0 << 28) -#define PCR_PBSIZ_2 (1 << 28) -#define PCR_PBSIZ_4 (2 << 28) -#define PCR_PBSIZ_8 (3 << 28) -#define PCR_BPIX_1 (0 << 25) -#define PCR_BPIX_2 (1 << 25) -#define PCR_BPIX_4 (2 << 25) -#define PCR_BPIX_8 (3 << 25) -#define PCR_BPIX_12 (4 << 25) -#define PCR_BPIX_16 (5 << 25) -#define PCR_BPIX_18 (6 << 25) -#define PCR_PIXPOL (1 << 24) -#define PCR_FLMPOL (1 << 23) -#define PCR_LPPOL (1 << 22) -#define PCR_CLKPOL (1 << 21) -#define PCR_OEPOL (1 << 20) -#define PCR_SCLKIDLE (1 << 19) -#define PCR_END_SEL (1 << 18) -#define PCR_END_BYTE_SWAP (1 << 17) -#define PCR_REV_VS (1 << 16) -#define PCR_ACD_SEL (1 << 15) -#define PCR_ACD(x) (((x) & 0x7f) << 8) -#define PCR_SCLK_SEL (1 << 7) -#define PCR_SHARP (1 << 6) -#define PCR_PCD(x) ((x) & 0x3f) - -#define PWMR_CLS(x) (((x) & 0x1ff) << 16) -#define PWMR_LDMSK (1 << 15) -#define PWMR_SCR1 (1 << 10) -#define PWMR_SCR0 (1 << 9) -#define PWMR_CC_EN (1 << 8) -#define PWMR_PW(x) ((x) & 0xff) - -#define LSCR1_PS_RISE_DELAY(x) (((x) & 0x7f) << 26) -#define LSCR1_CLS_RISE_DELAY(x) (((x) & 0x3f) << 16) -#define LSCR1_REV_TOGGLE_DELAY(x) (((x) & 0xf) << 8) -#define LSCR1_GRAY2(x) (((x) & 0xf) << 4) -#define LSCR1_GRAY1(x) (((x) & 0xf)) - -struct imx_fb_videomode { - struct fb_videomode mode; - u32 pcr; - bool aus_mode; - unsigned char bpp; -}; - -struct imx_fb_platform_data { - struct imx_fb_videomode *mode; - int num_modes; - - u_int pwmr; - u_int lscr1; - u_int dmacr; - - int (*init)(struct platform_device *); - void (*exit)(struct platform_device *); -}; - -#endif /* ifndef __MACH_IMXFB_H__ */ diff --git a/include/linux/platform_data/video-pxafb.h b/include/linux/platform_data/video-pxafb.h index b3d574778326..6333bac166a5 100644 --- a/include/linux/platform_data/video-pxafb.h +++ b/include/linux/platform_data/video-pxafb.h @@ -8,7 +8,6 @@ */ #include <linux/fb.h> -#include <mach/regs-lcd.h> /* * Supported LCD connections @@ -153,6 +152,27 @@ struct pxafb_mach_info { void pxa_set_fb_info(struct device *, struct pxafb_mach_info *); unsigned long pxafb_get_hsync_time(struct device *dev); +/* smartpanel related */ +#define SMART_CMD_A0 (0x1 << 8) +#define SMART_CMD_READ_STATUS_REG (0x0 << 9) +#define SMART_CMD_READ_FRAME_BUFFER ((0x0 << 9) | SMART_CMD_A0) +#define SMART_CMD_WRITE_COMMAND (0x1 << 9) +#define SMART_CMD_WRITE_DATA ((0x1 << 9) | SMART_CMD_A0) +#define SMART_CMD_WRITE_FRAME ((0x2 << 9) | SMART_CMD_A0) +#define SMART_CMD_WAIT_FOR_VSYNC (0x3 << 9) +#define SMART_CMD_NOOP (0x4 << 9) +#define SMART_CMD_INTERRUPT (0x5 << 9) + +#define SMART_CMD(x) (SMART_CMD_WRITE_COMMAND | ((x) & 0xff)) +#define SMART_DAT(x) (SMART_CMD_WRITE_DATA | ((x) & 0xff)) + +/* SMART_DELAY() is introduced for software controlled delay primitive which + * can be inserted between command sequences, unused command 0x6 is used here + * and delay ranges from 0ms ~ 255ms + */ +#define SMART_CMD_DELAY (0x6 << 9) +#define SMART_DELAY(ms) (SMART_CMD_DELAY | ((ms) & 0xff)) + #ifdef CONFIG_FB_PXA_SMARTPANEL extern int pxafb_smart_queue(struct fb_info *info, uint16_t *cmds, int); extern int pxafb_smart_flush(struct fb_info *info); diff --git a/include/linux/platform_data/wan_ixp4xx_hss.h b/include/linux/platform_data/wan_ixp4xx_hss.h deleted file mode 100644 index d525a0feb9e1..000000000000 --- a/include/linux/platform_data/wan_ixp4xx_hss.h +++ /dev/null @@ -1,17 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __PLATFORM_DATA_WAN_IXP4XX_HSS_H -#define __PLATFORM_DATA_WAN_IXP4XX_HSS_H - -#include <linux/types.h> - -/* Information about built-in HSS (synchronous serial) interfaces */ -struct hss_plat_info { - int (*set_clock)(int port, unsigned int clock_type); - int (*open)(int port, void *pdev, - void (*set_carrier_cb)(void *pdev, int carrier)); - void (*close)(int port, void *pdev); - u8 txreadyq; - u32 timer_freq; -}; - -#endif diff --git a/include/linux/platform_data/x86/asus-wmi.h b/include/linux/platform_data/x86/asus-wmi.h index a571b47ff362..28234dc9fa6a 100644 --- a/include/linux/platform_data/x86/asus-wmi.h +++ b/include/linux/platform_data/x86/asus-wmi.h @@ -49,6 +49,7 @@ #define ASUS_WMI_DEVID_LED4 0x00020014 #define ASUS_WMI_DEVID_LED5 0x00020015 #define ASUS_WMI_DEVID_LED6 0x00020016 +#define ASUS_WMI_DEVID_MICMUTE_LED 0x00040017 /* Backlight and Brightness */ #define ASUS_WMI_DEVID_ALS_ENABLE 0x00050001 /* Ambient Light Sensor */ @@ -64,6 +65,7 @@ #define ASUS_WMI_DEVID_PANEL_OD 0x00050019 #define ASUS_WMI_DEVID_CAMERA 0x00060013 #define ASUS_WMI_DEVID_LID_FLIP 0x00060062 +#define ASUS_WMI_DEVID_LID_FLIP_ROG 0x00060077 /* Storage */ #define ASUS_WMI_DEVID_CARDREADER 0x00080013 @@ -77,6 +79,7 @@ #define ASUS_WMI_DEVID_THERMAL_CTRL 0x00110011 #define ASUS_WMI_DEVID_FAN_CTRL 0x00110012 /* deprecated */ #define ASUS_WMI_DEVID_CPU_FAN_CTRL 0x00110013 +#define ASUS_WMI_DEVID_GPU_FAN_CTRL 0x00110014 #define ASUS_WMI_DEVID_CPU_FAN_CURVE 0x00110024 #define ASUS_WMI_DEVID_GPU_FAN_CURVE 0x00110025 @@ -98,6 +101,15 @@ /* dgpu on/off */ #define ASUS_WMI_DEVID_DGPU 0x00090020 +/* gpu mux switch, 0 = dGPU, 1 = Optimus */ +#define ASUS_WMI_DEVID_GPU_MUX 0x00090016 + +/* TUF laptop RGB modes/colours */ +#define ASUS_WMI_DEVID_TUF_RGB_MODE 0x00100056 + +/* TUF laptop RGB power/state */ +#define ASUS_WMI_DEVID_TUF_RGB_STATE 0x00100057 + /* DSTS masks */ #define ASUS_WMI_DSTS_STATUS_BIT 0x00000001 #define ASUS_WMI_DSTS_UNKNOWN_BIT 0x00000002 diff --git a/include/linux/platform_data/x86/nvidia-wmi-ec-backlight.h b/include/linux/platform_data/x86/nvidia-wmi-ec-backlight.h new file mode 100644 index 000000000000..23d60130272c --- /dev/null +++ b/include/linux/platform_data/x86/nvidia-wmi-ec-backlight.h @@ -0,0 +1,76 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2020, NVIDIA CORPORATION. All rights reserved. + */ + +#ifndef __PLATFORM_DATA_X86_NVIDIA_WMI_EC_BACKLIGHT_H +#define __PLATFORM_DATA_X86_NVIDIA_WMI_EC_BACKLIGHT_H + +#define WMI_BRIGHTNESS_GUID "603E9613-EF25-4338-A3D0-C46177516DB7" + +/** + * enum wmi_brightness_method - WMI method IDs + * @WMI_BRIGHTNESS_METHOD_LEVEL: Get/Set EC brightness level status + * @WMI_BRIGHTNESS_METHOD_SOURCE: Get/Set EC Brightness Source + */ +enum wmi_brightness_method { + WMI_BRIGHTNESS_METHOD_LEVEL = 1, + WMI_BRIGHTNESS_METHOD_SOURCE = 2, + WMI_BRIGHTNESS_METHOD_MAX +}; + +/** + * enum wmi_brightness_mode - Operation mode for WMI-wrapped method + * @WMI_BRIGHTNESS_MODE_GET: Get the current brightness level/source. + * @WMI_BRIGHTNESS_MODE_SET: Set the brightness level. + * @WMI_BRIGHTNESS_MODE_GET_MAX_LEVEL: Get the maximum brightness level. This + * is only valid when the WMI method is + * %WMI_BRIGHTNESS_METHOD_LEVEL. + */ +enum wmi_brightness_mode { + WMI_BRIGHTNESS_MODE_GET = 0, + WMI_BRIGHTNESS_MODE_SET = 1, + WMI_BRIGHTNESS_MODE_GET_MAX_LEVEL = 2, + WMI_BRIGHTNESS_MODE_MAX +}; + +/** + * enum wmi_brightness_source - Backlight brightness control source selection + * @WMI_BRIGHTNESS_SOURCE_GPU: Backlight brightness is controlled by the GPU. + * @WMI_BRIGHTNESS_SOURCE_EC: Backlight brightness is controlled by the + * system's Embedded Controller (EC). + * @WMI_BRIGHTNESS_SOURCE_AUX: Backlight brightness is controlled over the + * DisplayPort AUX channel. + */ +enum wmi_brightness_source { + WMI_BRIGHTNESS_SOURCE_GPU = 1, + WMI_BRIGHTNESS_SOURCE_EC = 2, + WMI_BRIGHTNESS_SOURCE_AUX = 3, + WMI_BRIGHTNESS_SOURCE_MAX +}; + +/** + * struct wmi_brightness_args - arguments for the WMI-wrapped ACPI method + * @mode: Pass in an &enum wmi_brightness_mode value to select between + * getting or setting a value. + * @val: In parameter for value to set when using %WMI_BRIGHTNESS_MODE_SET + * mode. Not used in conjunction with %WMI_BRIGHTNESS_MODE_GET or + * %WMI_BRIGHTNESS_MODE_GET_MAX_LEVEL mode. + * @ret: Out parameter returning retrieved value when operating in + * %WMI_BRIGHTNESS_MODE_GET or %WMI_BRIGHTNESS_MODE_GET_MAX_LEVEL + * mode. Not used in %WMI_BRIGHTNESS_MODE_SET mode. + * @ignored: Padding; not used. The ACPI method expects a 24 byte params struct. + * + * This is the parameters structure for the WmiBrightnessNotify ACPI method as + * wrapped by WMI. The value passed in to @val or returned by @ret will be a + * brightness value when the WMI method ID is %WMI_BRIGHTNESS_METHOD_LEVEL, or + * an &enum wmi_brightness_source value with %WMI_BRIGHTNESS_METHOD_SOURCE. + */ +struct wmi_brightness_args { + u32 mode; + u32 val; + u32 ret; + u32 ignored[3]; +}; + +#endif diff --git a/include/linux/platform_data/x86/p2sb.h b/include/linux/platform_data/x86/p2sb.h new file mode 100644 index 000000000000..a1d5fddc8f13 --- /dev/null +++ b/include/linux/platform_data/x86/p2sb.h @@ -0,0 +1,28 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Primary to Sideband (P2SB) bridge access support + */ + +#ifndef _PLATFORM_DATA_X86_P2SB_H +#define _PLATFORM_DATA_X86_P2SB_H + +#include <linux/errno.h> +#include <linux/kconfig.h> + +struct pci_bus; +struct resource; + +#if IS_BUILTIN(CONFIG_P2SB) + +int p2sb_bar(struct pci_bus *bus, unsigned int devfn, struct resource *mem); + +#else /* CONFIG_P2SB */ + +static inline int p2sb_bar(struct pci_bus *bus, unsigned int devfn, struct resource *mem) +{ + return -ENODEV; +} + +#endif /* CONFIG_P2SB is not set */ + +#endif /* _PLATFORM_DATA_X86_P2SB_H */ diff --git a/include/linux/platform_data/x86/pmc_atom.h b/include/linux/platform_data/x86/pmc_atom.h index 022bcea9edec..b8a701c77fd0 100644 --- a/include/linux/platform_data/x86/pmc_atom.h +++ b/include/linux/platform_data/x86/pmc_atom.h @@ -1,12 +1,14 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* - * Intel Atom SOC Power Management Controller Header File - * Copyright (c) 2014, Intel Corporation. + * Intel Atom SoC Power Management Controller Header File + * Copyright (c) 2014-2015,2022 Intel Corporation. */ #ifndef PMC_ATOM_H #define PMC_ATOM_H +#include <linux/bits.h> + /* ValleyView Power Control Unit PCI Device ID */ #define PCI_DEVICE_ID_VLV_PMC 0x0F1C /* CherryTrail Power Control Unit PCI Device ID */ @@ -47,7 +49,7 @@ #define PMC_S0I2_TMR 0x88 #define PMC_S0I3_TMR 0x8C #define PMC_S0_TMR 0x90 -/* Sleep state counter is in units of of 32us */ +/* Sleep state counter is in units of 32us */ #define PMC_TMR_SHIFT 5 /* Power status of power islands */ @@ -139,11 +141,10 @@ #define ACPI_MMIO_REG_LEN 0x100 #define PM1_CNT 0x4 -#define SLEEP_TYPE_MASK 0xFFFFECFF +#define SLEEP_TYPE_MASK GENMASK(12, 10) #define SLEEP_TYPE_S5 0x1C00 -#define SLEEP_ENABLE 0x2000 +#define SLEEP_ENABLE BIT(13) extern int pmc_atom_read(int offset, u32 *value); -extern int pmc_atom_write(int offset, u32 value); #endif /* PMC_ATOM_H */ diff --git a/include/linux/platform_data/x86/simatic-ipc-base.h b/include/linux/platform_data/x86/simatic-ipc-base.h index 62d2bc774067..57d6a10dfc9e 100644 --- a/include/linux/platform_data/x86/simatic-ipc-base.h +++ b/include/linux/platform_data/x86/simatic-ipc-base.h @@ -19,11 +19,10 @@ #define SIMATIC_IPC_DEVICE_427E 2 #define SIMATIC_IPC_DEVICE_127E 3 #define SIMATIC_IPC_DEVICE_227E 4 +#define SIMATIC_IPC_DEVICE_227G 5 struct simatic_ipc_platform { u8 devmode; }; -u32 simatic_ipc_get_membase0(unsigned int p2sb); - #endif /* __PLATFORM_DATA_X86_SIMATIC_IPC_BASE_H */ diff --git a/include/linux/platform_data/x86/simatic-ipc.h b/include/linux/platform_data/x86/simatic-ipc.h index f3b76b39776b..632320ec8f08 100644 --- a/include/linux/platform_data/x86/simatic-ipc.h +++ b/include/linux/platform_data/x86/simatic-ipc.h @@ -31,6 +31,8 @@ enum simatic_ipc_station_ids { SIMATIC_IPC_IPC427E = 0x00000A01, SIMATIC_IPC_IPC477E = 0x00000A02, SIMATIC_IPC_IPC127E = 0x00000D01, + SIMATIC_IPC_IPC227G = 0x00000F01, + SIMATIC_IPC_IPC427G = 0x00001001, }; static inline u32 simatic_ipc_get_station_id(u8 *data, int max_len) diff --git a/include/linux/platform_data/x86/intel-spi.h b/include/linux/platform_data/x86/spi-intel.h index 7f53a5c6f35e..a512ec37abbb 100644 --- a/include/linux/platform_data/x86/intel-spi.h +++ b/include/linux/platform_data/x86/spi-intel.h @@ -6,8 +6,8 @@ * Author: Mika Westerberg <mika.westerberg@linux.intel.com> */ -#ifndef INTEL_SPI_PDATA_H -#define INTEL_SPI_PDATA_H +#ifndef SPI_INTEL_PDATA_H +#define SPI_INTEL_PDATA_H enum intel_spi_type { INTEL_SPI_BYT = 1, @@ -19,11 +19,13 @@ enum intel_spi_type { /** * struct intel_spi_boardinfo - Board specific data for Intel SPI driver * @type: Type which this controller is compatible with - * @writeable: The chip is writeable + * @set_writeable: Try to make the chip writeable (optional) + * @data: Data to be passed to @set_writeable can be %NULL */ struct intel_spi_boardinfo { enum intel_spi_type type; - bool writeable; + bool (*set_writeable)(void __iomem *base, void *data); + void *data; }; -#endif /* INTEL_SPI_PDATA_H */ +#endif /* SPI_INTEL_PDATA_H */ diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h index 7c96f169d274..b0d5a253156e 100644 --- a/include/linux/platform_device.h +++ b/include/linux/platform_device.h @@ -31,7 +31,11 @@ struct platform_device { struct resource *resource; const struct platform_device_id *id_entry; - char *driver_override; /* Driver name to force a match */ + /* + * Driver name to force a match. Do not set directly, because core + * frees it. Use driver_set_override() to set or clear it. + */ + const char *driver_override; /* MFD cell pointer */ struct mfd_cell *mfd_cell; @@ -210,6 +214,14 @@ struct platform_driver { struct device_driver driver; const struct platform_device_id *id_table; bool prevent_deferred_probe; + /* + * For most device drivers, no need to care about this flag as long as + * all DMAs are handled through the kernel DMA API. For some special + * ones, for example VFIO drivers, they know how to manage the DMA + * themselves and set this flag so that the IOMMU layer will allow them + * to setup and manage their own I/O address space. + */ + bool driver_managed_dma; }; #define to_platform_driver(drv) (container_of((drv), struct platform_driver, \ @@ -328,8 +340,6 @@ extern int platform_pm_restore(struct device *dev); #define platform_pm_restore NULL #endif -extern int platform_dma_configure(struct device *dev); - #ifdef CONFIG_PM_SLEEP #define USE_PLATFORM_PM_SLEEP_OPS \ .suspend = platform_pm_suspend, \ diff --git a/include/linux/pm.h b/include/linux/pm.h index e1e9402180b9..93cd34f00822 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -8,6 +8,7 @@ #ifndef _LINUX_PM_H #define _LINUX_PM_H +#include <linux/export.h> #include <linux/list.h> #include <linux/workqueue.h> #include <linux/spinlock.h> @@ -20,7 +21,6 @@ * Callbacks for platform drivers to implement. */ extern void (*pm_power_off)(void); -extern void (*pm_power_off_prepare)(void); struct device; /* we have a circular dep with device.h */ #ifdef CONFIG_VT_CONSOLE_SLEEP @@ -35,6 +35,15 @@ static inline void pm_vt_switch_unregister(struct device *dev) } #endif /* CONFIG_VT_CONSOLE_SLEEP */ +#ifdef CONFIG_CXL_SUSPEND +bool cxl_mem_active(void); +#else +static inline bool cxl_mem_active(void) +{ + return false; +} +#endif + /* * Device power management */ @@ -357,13 +366,60 @@ struct dev_pm_ops { #define SET_RUNTIME_PM_OPS(suspend_fn, resume_fn, idle_fn) #endif +#define _DEFINE_DEV_PM_OPS(name, \ + suspend_fn, resume_fn, \ + runtime_suspend_fn, runtime_resume_fn, idle_fn) \ +const struct dev_pm_ops name = { \ + SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) \ + RUNTIME_PM_OPS(runtime_suspend_fn, runtime_resume_fn, idle_fn) \ +} + +#ifdef CONFIG_PM +#define _EXPORT_DEV_PM_OPS(name, sec, ns) \ + const struct dev_pm_ops name; \ + __EXPORT_SYMBOL(name, sec, ns); \ + const struct dev_pm_ops name +#else +#define _EXPORT_DEV_PM_OPS(name, sec, ns) \ + static __maybe_unused const struct dev_pm_ops __static_##name +#endif + +#define EXPORT_DEV_PM_OPS(name) _EXPORT_DEV_PM_OPS(name, "", "") +#define EXPORT_GPL_DEV_PM_OPS(name) _EXPORT_DEV_PM_OPS(name, "_gpl", "") +#define EXPORT_NS_DEV_PM_OPS(name, ns) _EXPORT_DEV_PM_OPS(name, "", #ns) +#define EXPORT_NS_GPL_DEV_PM_OPS(name, ns) _EXPORT_DEV_PM_OPS(name, "_gpl", #ns) + /* * Use this if you want to use the same suspend and resume callbacks for suspend * to RAM and hibernation. + * + * If the underlying dev_pm_ops struct symbol has to be exported, use + * EXPORT_SIMPLE_DEV_PM_OPS() or EXPORT_GPL_SIMPLE_DEV_PM_OPS() instead. */ #define DEFINE_SIMPLE_DEV_PM_OPS(name, suspend_fn, resume_fn) \ -static const struct dev_pm_ops name = { \ - SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) \ + _DEFINE_DEV_PM_OPS(name, suspend_fn, resume_fn, NULL, NULL, NULL) + +#define EXPORT_SIMPLE_DEV_PM_OPS(name, suspend_fn, resume_fn) \ + EXPORT_DEV_PM_OPS(name) = { \ + SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) \ + } +#define EXPORT_GPL_SIMPLE_DEV_PM_OPS(name, suspend_fn, resume_fn) \ + EXPORT_GPL_DEV_PM_OPS(name) = { \ + SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) \ + } +#define EXPORT_NS_SIMPLE_DEV_PM_OPS(name, suspend_fn, resume_fn, ns) \ + EXPORT_NS_DEV_PM_OPS(name, ns) = { \ + SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) \ + } +#define EXPORT_NS_GPL_SIMPLE_DEV_PM_OPS(name, suspend_fn, resume_fn, ns) \ + EXPORT_NS_GPL_DEV_PM_OPS(name, ns) = { \ + SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) \ + } + +/* Deprecated. Use DEFINE_SIMPLE_DEV_PM_OPS() instead. */ +#define SIMPLE_DEV_PM_OPS(name, suspend_fn, resume_fn) \ +const struct dev_pm_ops __maybe_unused name = { \ + SET_SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) \ } /* @@ -378,20 +434,10 @@ static const struct dev_pm_ops name = { \ * suspend and "early" resume callback pointers, .suspend_late() and * .resume_early(), to the same routines as .runtime_suspend() and * .runtime_resume(), respectively (and analogously for hibernation). + * + * Deprecated. You most likely don't want this macro. Use + * DEFINE_RUNTIME_DEV_PM_OPS() instead. */ -#define DEFINE_UNIVERSAL_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn) \ -static const struct dev_pm_ops name = { \ - SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) \ - RUNTIME_PM_OPS(suspend_fn, resume_fn, idle_fn) \ -} - -/* Deprecated. Use DEFINE_SIMPLE_DEV_PM_OPS() instead. */ -#define SIMPLE_DEV_PM_OPS(name, suspend_fn, resume_fn) \ -const struct dev_pm_ops __maybe_unused name = { \ - SET_SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) \ -} - -/* Deprecated. Use DEFINE_UNIVERSAL_DEV_PM_OPS() instead. */ #define UNIVERSAL_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn) \ const struct dev_pm_ops __maybe_unused name = { \ SET_SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) \ @@ -745,11 +791,11 @@ extern int dpm_suspend_late(pm_message_t state); extern int dpm_suspend(pm_message_t state); extern int dpm_prepare(pm_message_t state); -extern void __suspend_report_result(const char *function, void *fn, int ret); +extern void __suspend_report_result(const char *function, struct device *dev, void *fn, int ret); -#define suspend_report_result(fn, ret) \ +#define suspend_report_result(dev, fn, ret) \ do { \ - __suspend_report_result(__func__, fn, ret); \ + __suspend_report_result(__func__, dev, fn, ret); \ } while (0) extern int device_pm_wait_for_dev(struct device *sub, struct device *dev); @@ -789,7 +835,7 @@ static inline int dpm_suspend_start(pm_message_t state) return 0; } -#define suspend_report_result(fn, ret) do {} while (0) +#define suspend_report_result(dev, fn, ret) do {} while (0) static inline int device_pm_wait_for_dev(struct device *a, struct device *b) { diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index 67017c9390c8..ebc351698090 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -91,6 +91,14 @@ struct gpd_dev_ops { int (*stop)(struct device *dev); }; +struct genpd_governor_data { + s64 max_off_time_ns; + bool max_off_time_changed; + ktime_t next_wakeup; + bool cached_power_down_ok; + bool cached_power_down_state_idx; +}; + struct genpd_power_state { s64 power_off_latency_ns; s64 power_on_latency_ns; @@ -98,7 +106,7 @@ struct genpd_power_state { u64 usage; u64 rejected; struct fwnode_handle *fwnode; - ktime_t idle_time; + u64 idle_time; void *data; }; @@ -114,6 +122,7 @@ struct generic_pm_domain { struct list_head child_links; /* Links with PM domain as a child */ struct list_head dev_list; /* List of devices */ struct dev_power_governor *gov; + struct genpd_governor_data *gd; /* Data used by a genpd governor. */ struct work_struct power_off_work; struct fwnode_handle *provider; /* Identity of the domain provider */ bool has_provider; @@ -134,11 +143,6 @@ struct generic_pm_domain { int (*set_performance_state)(struct generic_pm_domain *genpd, unsigned int state); struct gpd_dev_ops dev_ops; - s64 max_off_time_ns; /* Maximum allowed "suspended" time. */ - ktime_t next_wakeup; /* Maintained by the domain governor */ - bool max_off_time_changed; - bool cached_power_down_ok; - bool cached_power_down_state_idx; int (*attach_dev)(struct generic_pm_domain *domain, struct device *dev); void (*detach_dev)(struct generic_pm_domain *domain, @@ -149,8 +153,8 @@ struct generic_pm_domain { unsigned int state_count); unsigned int state_count; /* number of states */ unsigned int state_idx; /* state that genpd will go to when off */ - ktime_t on_time; - ktime_t accounting_time; + u64 on_time; + u64 accounting_time; const struct genpd_lock_ops *lock_ops; union { struct mutex mlock; @@ -182,6 +186,7 @@ struct gpd_timing_data { s64 suspend_latency_ns; s64 resume_latency_ns; s64 effective_constraint_ns; + ktime_t next_wakeup; bool constraint_changed; bool cached_suspend_ok; }; @@ -193,14 +198,13 @@ struct pm_domain_data { struct generic_pm_domain_data { struct pm_domain_data base; - struct gpd_timing_data td; + struct gpd_timing_data *td; struct notifier_block nb; struct notifier_block *power_nb; int cpu; unsigned int performance_state; unsigned int default_pstate; unsigned int rpm_pstate; - ktime_t next_wakeup; void *data; }; diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h index 879c138c7b8e..dc1fb5890792 100644 --- a/include/linux/pm_opp.h +++ b/include/linux/pm_opp.h @@ -32,14 +32,17 @@ enum dev_pm_opp_event { * @u_volt_min: Minimum voltage in microvolts corresponding to this OPP * @u_volt_max: Maximum voltage in microvolts corresponding to this OPP * @u_amp: Maximum current drawn by the device in microamperes + * @u_watt: Power used by the device in microwatts * - * This structure stores the voltage/current values for a single power supply. + * This structure stores the voltage/current/power values for a single power + * supply. */ struct dev_pm_opp_supply { unsigned long u_volt; unsigned long u_volt_min; unsigned long u_volt_max; unsigned long u_amp; + unsigned long u_watt; }; /** @@ -54,37 +57,39 @@ struct dev_pm_opp_icc_bw { u32 peak; }; -/** - * struct dev_pm_opp_info - OPP freq/voltage/current values - * @rate: Target clk rate in hz - * @supplies: Array of voltage/current values for all power supplies - * - * This structure stores the freq/voltage/current values for a single OPP. - */ -struct dev_pm_opp_info { - unsigned long rate; - struct dev_pm_opp_supply *supplies; -}; +typedef int (*config_regulators_t)(struct device *dev, + struct dev_pm_opp *old_opp, struct dev_pm_opp *new_opp, + struct regulator **regulators, unsigned int count); + +typedef int (*config_clks_t)(struct device *dev, struct opp_table *opp_table, + struct dev_pm_opp *opp, void *data, bool scaling_down); /** - * struct dev_pm_set_opp_data - Set OPP data - * @old_opp: Old OPP info - * @new_opp: New OPP info - * @regulators: Array of regulator pointers - * @regulator_count: Number of regulators - * @clk: Pointer to clk - * @dev: Pointer to the struct device + * struct dev_pm_opp_config - Device OPP configuration values + * @clk_names: Clk names, NULL terminated array. + * @config_clks: Custom set clk helper. + * @prop_name: Name to postfix to properties. + * @config_regulators: Custom set regulator helper. + * @supported_hw: Array of hierarchy of versions to match. + * @supported_hw_count: Number of elements in the array. + * @regulator_names: Array of pointers to the names of the regulator, NULL terminated. + * @genpd_names: Null terminated array of pointers containing names of genpd to + * attach. + * @virt_devs: Pointer to return the array of virtual devices. * - * This structure contains all information required for setting an OPP. + * This structure contains platform specific OPP configurations for the device. */ -struct dev_pm_set_opp_data { - struct dev_pm_opp_info old_opp; - struct dev_pm_opp_info new_opp; - - struct regulator **regulators; - unsigned int regulator_count; - struct clk *clk; - struct device *dev; +struct dev_pm_opp_config { + /* NULL terminated */ + const char * const *clk_names; + config_clks_t config_clks; + const char *prop_name; + config_regulators_t config_regulators; + const unsigned int *supported_hw; + unsigned int supported_hw_count; + const char * const *regulator_names; + const char * const *genpd_names; + struct device ***virt_devs; }; #if defined(CONFIG_PM_OPP) @@ -94,6 +99,10 @@ void dev_pm_opp_put_opp_table(struct opp_table *opp_table); unsigned long dev_pm_opp_get_voltage(struct dev_pm_opp *opp); +int dev_pm_opp_get_supplies(struct dev_pm_opp *opp, struct dev_pm_opp_supply *supplies); + +unsigned long dev_pm_opp_get_power(struct dev_pm_opp *opp); + unsigned long dev_pm_opp_get_freq(struct dev_pm_opp *opp); unsigned int dev_pm_opp_get_level(struct dev_pm_opp *opp); @@ -112,18 +121,23 @@ unsigned long dev_pm_opp_get_suspend_opp_freq(struct device *dev); struct dev_pm_opp *dev_pm_opp_find_freq_exact(struct device *dev, unsigned long freq, bool available); +struct dev_pm_opp *dev_pm_opp_find_freq_floor(struct device *dev, + unsigned long *freq); + struct dev_pm_opp *dev_pm_opp_find_level_exact(struct device *dev, unsigned int level); struct dev_pm_opp *dev_pm_opp_find_level_ceil(struct device *dev, unsigned int *level); -struct dev_pm_opp *dev_pm_opp_find_freq_floor(struct device *dev, - unsigned long *freq); -struct dev_pm_opp *dev_pm_opp_find_freq_ceil_by_volt(struct device *dev, - unsigned long u_volt); - struct dev_pm_opp *dev_pm_opp_find_freq_ceil(struct device *dev, unsigned long *freq); + +struct dev_pm_opp *dev_pm_opp_find_bw_ceil(struct device *dev, + unsigned int *bw, int index); + +struct dev_pm_opp *dev_pm_opp_find_bw_floor(struct device *dev, + unsigned int *bw, int index); + void dev_pm_opp_put(struct dev_pm_opp *opp); int dev_pm_opp_add(struct device *dev, unsigned long freq, @@ -142,23 +156,13 @@ int dev_pm_opp_disable(struct device *dev, unsigned long freq); int dev_pm_opp_register_notifier(struct device *dev, struct notifier_block *nb); int dev_pm_opp_unregister_notifier(struct device *dev, struct notifier_block *nb); -struct opp_table *dev_pm_opp_set_supported_hw(struct device *dev, const u32 *versions, unsigned int count); -void dev_pm_opp_put_supported_hw(struct opp_table *opp_table); -int devm_pm_opp_set_supported_hw(struct device *dev, const u32 *versions, unsigned int count); -struct opp_table *dev_pm_opp_set_prop_name(struct device *dev, const char *name); -void dev_pm_opp_put_prop_name(struct opp_table *opp_table); -struct opp_table *dev_pm_opp_set_regulators(struct device *dev, const char * const names[], unsigned int count); -void dev_pm_opp_put_regulators(struct opp_table *opp_table); -int devm_pm_opp_set_regulators(struct device *dev, const char * const names[], unsigned int count); -struct opp_table *dev_pm_opp_set_clkname(struct device *dev, const char *name); -void dev_pm_opp_put_clkname(struct opp_table *opp_table); -int devm_pm_opp_set_clkname(struct device *dev, const char *name); -struct opp_table *dev_pm_opp_register_set_opp_helper(struct device *dev, int (*set_opp)(struct dev_pm_set_opp_data *data)); -void dev_pm_opp_unregister_set_opp_helper(struct opp_table *opp_table); -int devm_pm_opp_register_set_opp_helper(struct device *dev, int (*set_opp)(struct dev_pm_set_opp_data *data)); -struct opp_table *dev_pm_opp_attach_genpd(struct device *dev, const char * const *names, struct device ***virt_devs); -void dev_pm_opp_detach_genpd(struct opp_table *opp_table); -int devm_pm_opp_attach_genpd(struct device *dev, const char * const *names, struct device ***virt_devs); +int dev_pm_opp_set_config(struct device *dev, struct dev_pm_opp_config *config); +int devm_pm_opp_set_config(struct device *dev, struct dev_pm_opp_config *config); +void dev_pm_opp_clear_config(int token); +int dev_pm_opp_config_clks_simple(struct device *dev, + struct opp_table *opp_table, struct dev_pm_opp *opp, void *data, + bool scaling_down); + struct dev_pm_opp *dev_pm_opp_xlate_required_opp(struct opp_table *src_table, struct opp_table *dst_table, struct dev_pm_opp *src_opp); int dev_pm_opp_xlate_performance_state(struct opp_table *src_table, struct opp_table *dst_table, unsigned int pstate); int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq); @@ -186,6 +190,16 @@ static inline unsigned long dev_pm_opp_get_voltage(struct dev_pm_opp *opp) return 0; } +static inline int dev_pm_opp_get_supplies(struct dev_pm_opp *opp, struct dev_pm_opp_supply *supplies) +{ + return -EOPNOTSUPP; +} + +static inline unsigned long dev_pm_opp_get_power(struct dev_pm_opp *opp) +{ + return 0; +} + static inline unsigned long dev_pm_opp_get_freq(struct dev_pm_opp *opp) { return 0; @@ -233,12 +247,6 @@ static inline unsigned long dev_pm_opp_get_suspend_opp_freq(struct device *dev) return 0; } -static inline struct dev_pm_opp *dev_pm_opp_find_freq_exact(struct device *dev, - unsigned long freq, bool available) -{ - return ERR_PTR(-EOPNOTSUPP); -} - static inline struct dev_pm_opp *dev_pm_opp_find_level_exact(struct device *dev, unsigned int level) { @@ -251,14 +259,14 @@ static inline struct dev_pm_opp *dev_pm_opp_find_level_ceil(struct device *dev, return ERR_PTR(-EOPNOTSUPP); } -static inline struct dev_pm_opp *dev_pm_opp_find_freq_floor(struct device *dev, - unsigned long *freq) +static inline struct dev_pm_opp *dev_pm_opp_find_freq_exact(struct device *dev, + unsigned long freq, bool available) { return ERR_PTR(-EOPNOTSUPP); } -static inline struct dev_pm_opp *dev_pm_opp_find_freq_ceil_by_volt(struct device *dev, - unsigned long u_volt) +static inline struct dev_pm_opp *dev_pm_opp_find_freq_floor(struct device *dev, + unsigned long *freq) { return ERR_PTR(-EOPNOTSUPP); } @@ -269,6 +277,18 @@ static inline struct dev_pm_opp *dev_pm_opp_find_freq_ceil(struct device *dev, return ERR_PTR(-EOPNOTSUPP); } +static inline struct dev_pm_opp *dev_pm_opp_find_bw_ceil(struct device *dev, + unsigned int *bw, int index) +{ + return ERR_PTR(-EOPNOTSUPP); +} + +static inline struct dev_pm_opp *dev_pm_opp_find_bw_floor(struct device *dev, + unsigned int *bw, int index) +{ + return ERR_PTR(-EOPNOTSUPP); +} + static inline void dev_pm_opp_put(struct dev_pm_opp *opp) {} static inline int dev_pm_opp_add(struct device *dev, unsigned long freq, @@ -313,79 +333,21 @@ static inline int dev_pm_opp_unregister_notifier(struct device *dev, struct noti return -EOPNOTSUPP; } -static inline struct opp_table *dev_pm_opp_set_supported_hw(struct device *dev, - const u32 *versions, - unsigned int count) -{ - return ERR_PTR(-EOPNOTSUPP); -} - -static inline void dev_pm_opp_put_supported_hw(struct opp_table *opp_table) {} - -static inline int devm_pm_opp_set_supported_hw(struct device *dev, - const u32 *versions, - unsigned int count) -{ - return -EOPNOTSUPP; -} - -static inline struct opp_table *dev_pm_opp_register_set_opp_helper(struct device *dev, - int (*set_opp)(struct dev_pm_set_opp_data *data)) -{ - return ERR_PTR(-EOPNOTSUPP); -} - -static inline void dev_pm_opp_unregister_set_opp_helper(struct opp_table *opp_table) {} - -static inline int devm_pm_opp_register_set_opp_helper(struct device *dev, - int (*set_opp)(struct dev_pm_set_opp_data *data)) +static inline int dev_pm_opp_set_config(struct device *dev, struct dev_pm_opp_config *config) { return -EOPNOTSUPP; } -static inline struct opp_table *dev_pm_opp_set_prop_name(struct device *dev, const char *name) -{ - return ERR_PTR(-EOPNOTSUPP); -} - -static inline void dev_pm_opp_put_prop_name(struct opp_table *opp_table) {} - -static inline struct opp_table *dev_pm_opp_set_regulators(struct device *dev, const char * const names[], unsigned int count) -{ - return ERR_PTR(-EOPNOTSUPP); -} - -static inline void dev_pm_opp_put_regulators(struct opp_table *opp_table) {} - -static inline int devm_pm_opp_set_regulators(struct device *dev, - const char * const names[], - unsigned int count) -{ - return -EOPNOTSUPP; -} - -static inline struct opp_table *dev_pm_opp_set_clkname(struct device *dev, const char *name) -{ - return ERR_PTR(-EOPNOTSUPP); -} - -static inline void dev_pm_opp_put_clkname(struct opp_table *opp_table) {} - -static inline int devm_pm_opp_set_clkname(struct device *dev, const char *name) +static inline int devm_pm_opp_set_config(struct device *dev, struct dev_pm_opp_config *config) { return -EOPNOTSUPP; } -static inline struct opp_table *dev_pm_opp_attach_genpd(struct device *dev, const char * const *names, struct device ***virt_devs) -{ - return ERR_PTR(-EOPNOTSUPP); -} - -static inline void dev_pm_opp_detach_genpd(struct opp_table *opp_table) {} +static inline void dev_pm_opp_clear_config(int token) {} -static inline int devm_pm_opp_attach_genpd(struct device *dev, - const char * const *names, - struct device ***virt_devs) +static inline int dev_pm_opp_config_clks_simple(struct device *dev, + struct opp_table *opp_table, struct dev_pm_opp *opp, void *data, + bool scaling_down) { return -EOPNOTSUPP; } @@ -440,8 +402,6 @@ static inline int dev_pm_opp_sync_regulators(struct device *dev) int dev_pm_opp_of_add_table(struct device *dev); int dev_pm_opp_of_add_table_indexed(struct device *dev, int index); int devm_pm_opp_of_add_table_indexed(struct device *dev, int index); -int dev_pm_opp_of_add_table_noclk(struct device *dev, int index); -int devm_pm_opp_of_add_table_noclk(struct device *dev, int index); void dev_pm_opp_of_remove_table(struct device *dev); int devm_pm_opp_of_add_table(struct device *dev); int dev_pm_opp_of_cpumask_add_table(const struct cpumask *cpumask); @@ -472,16 +432,6 @@ static inline int devm_pm_opp_of_add_table_indexed(struct device *dev, int index return -EOPNOTSUPP; } -static inline int dev_pm_opp_of_add_table_noclk(struct device *dev, int index) -{ - return -EOPNOTSUPP; -} - -static inline int devm_pm_opp_of_add_table_noclk(struct device *dev, int index) -{ - return -EOPNOTSUPP; -} - static inline void dev_pm_opp_of_remove_table(struct device *dev) { } @@ -536,4 +486,149 @@ static inline int dev_pm_opp_of_find_icc_paths(struct device *dev, struct opp_ta } #endif +/* OPP Configuration helpers */ + +/* Regulators helpers */ +static inline int dev_pm_opp_set_regulators(struct device *dev, + const char * const names[]) +{ + struct dev_pm_opp_config config = { + .regulator_names = names, + }; + + return dev_pm_opp_set_config(dev, &config); +} + +static inline void dev_pm_opp_put_regulators(int token) +{ + dev_pm_opp_clear_config(token); +} + +static inline int devm_pm_opp_set_regulators(struct device *dev, + const char * const names[]) +{ + struct dev_pm_opp_config config = { + .regulator_names = names, + }; + + return devm_pm_opp_set_config(dev, &config); +} + +/* Supported-hw helpers */ +static inline int dev_pm_opp_set_supported_hw(struct device *dev, + const u32 *versions, + unsigned int count) +{ + struct dev_pm_opp_config config = { + .supported_hw = versions, + .supported_hw_count = count, + }; + + return dev_pm_opp_set_config(dev, &config); +} + +static inline void dev_pm_opp_put_supported_hw(int token) +{ + dev_pm_opp_clear_config(token); +} + +static inline int devm_pm_opp_set_supported_hw(struct device *dev, + const u32 *versions, + unsigned int count) +{ + struct dev_pm_opp_config config = { + .supported_hw = versions, + .supported_hw_count = count, + }; + + return devm_pm_opp_set_config(dev, &config); +} + +/* clkname helpers */ +static inline int dev_pm_opp_set_clkname(struct device *dev, const char *name) +{ + const char *names[] = { name, NULL }; + struct dev_pm_opp_config config = { + .clk_names = names, + }; + + return dev_pm_opp_set_config(dev, &config); +} + +static inline void dev_pm_opp_put_clkname(int token) +{ + dev_pm_opp_clear_config(token); +} + +static inline int devm_pm_opp_set_clkname(struct device *dev, const char *name) +{ + const char *names[] = { name, NULL }; + struct dev_pm_opp_config config = { + .clk_names = names, + }; + + return devm_pm_opp_set_config(dev, &config); +} + +/* config-regulators helpers */ +static inline int dev_pm_opp_set_config_regulators(struct device *dev, + config_regulators_t helper) +{ + struct dev_pm_opp_config config = { + .config_regulators = helper, + }; + + return dev_pm_opp_set_config(dev, &config); +} + +static inline void dev_pm_opp_put_config_regulators(int token) +{ + dev_pm_opp_clear_config(token); +} + +/* genpd helpers */ +static inline int dev_pm_opp_attach_genpd(struct device *dev, + const char * const *names, + struct device ***virt_devs) +{ + struct dev_pm_opp_config config = { + .genpd_names = names, + .virt_devs = virt_devs, + }; + + return dev_pm_opp_set_config(dev, &config); +} + +static inline void dev_pm_opp_detach_genpd(int token) +{ + dev_pm_opp_clear_config(token); +} + +static inline int devm_pm_opp_attach_genpd(struct device *dev, + const char * const *names, + struct device ***virt_devs) +{ + struct dev_pm_opp_config config = { + .genpd_names = names, + .virt_devs = virt_devs, + }; + + return devm_pm_opp_set_config(dev, &config); +} + +/* prop-name helpers */ +static inline int dev_pm_opp_set_prop_name(struct device *dev, const char *name) +{ + struct dev_pm_opp_config config = { + .prop_name = name, + }; + + return dev_pm_opp_set_config(dev, &config); +} + +static inline void dev_pm_opp_put_prop_name(int token) +{ + dev_pm_opp_clear_config(token); +} + #endif /* __LINUX_OPP_H__ */ diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h index 016de5776b6d..9a8151a2bdea 100644 --- a/include/linux/pm_runtime.h +++ b/include/linux/pm_runtime.h @@ -22,6 +22,40 @@ usage_count */ #define RPM_AUTO 0x08 /* Use autosuspend_delay */ +/* + * Use this for defining a set of PM operations to be used in all situations + * (system suspend, hibernation or runtime PM). + * + * Note that the behaviour differs from the deprecated UNIVERSAL_DEV_PM_OPS() + * macro, which uses the provided callbacks for both runtime PM and system + * sleep, while DEFINE_RUNTIME_DEV_PM_OPS() uses pm_runtime_force_suspend() + * and pm_runtime_force_resume() for its system sleep callbacks. + * + * If the underlying dev_pm_ops struct symbol has to be exported, use + * EXPORT_RUNTIME_DEV_PM_OPS() or EXPORT_GPL_RUNTIME_DEV_PM_OPS() instead. + */ +#define DEFINE_RUNTIME_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn) \ + _DEFINE_DEV_PM_OPS(name, pm_runtime_force_suspend, \ + pm_runtime_force_resume, suspend_fn, \ + resume_fn, idle_fn) + +#define EXPORT_RUNTIME_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn) \ + EXPORT_DEV_PM_OPS(name) = { \ + RUNTIME_PM_OPS(suspend_fn, resume_fn, idle_fn) \ + } +#define EXPORT_GPL_RUNTIME_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn) \ + EXPORT_GPL_DEV_PM_OPS(name) = { \ + RUNTIME_PM_OPS(suspend_fn, resume_fn, idle_fn) \ + } +#define EXPORT_NS_RUNTIME_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn, ns) \ + EXPORT_NS_DEV_PM_OPS(name, ns) = { \ + RUNTIME_PM_OPS(suspend_fn, resume_fn, idle_fn) \ + } +#define EXPORT_NS_GPL_RUNTIME_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn, ns) \ + EXPORT_NS_GPL_DEV_PM_OPS(name, ns) = { \ + RUNTIME_PM_OPS(suspend_fn, resume_fn, idle_fn) \ + } + #ifdef CONFIG_PM extern struct workqueue_struct *pm_wq; @@ -58,7 +92,7 @@ extern void pm_runtime_get_suppliers(struct device *dev); extern void pm_runtime_put_suppliers(struct device *dev); extern void pm_runtime_new_link(struct device *dev); extern void pm_runtime_drop_link(struct device_link *link); -extern void pm_runtime_release_supplier(struct device_link *link, bool check_idle); +extern void pm_runtime_release_supplier(struct device_link *link); extern int devm_pm_runtime_enable(struct device *dev); @@ -284,8 +318,7 @@ static inline void pm_runtime_get_suppliers(struct device *dev) {} static inline void pm_runtime_put_suppliers(struct device *dev) {} static inline void pm_runtime_new_link(struct device *dev) {} static inline void pm_runtime_drop_link(struct device_link *link) {} -static inline void pm_runtime_release_supplier(struct device_link *link, - bool check_idle) {} +static inline void pm_runtime_release_supplier(struct device_link *link) {} #endif /* !CONFIG_PM */ @@ -543,6 +576,10 @@ static inline void pm_runtime_disable(struct device *dev) * Allow the runtime PM autosuspend mechanism to be used for @dev whenever * requested (or "autosuspend" will be handled as direct runtime-suspend for * it). + * + * NOTE: It's important to undo this with pm_runtime_dont_use_autosuspend() + * at driver exit time unless your driver initially enabled pm_runtime + * with devm_pm_runtime_enable() (which handles it for you). */ static inline void pm_runtime_use_autosuspend(struct device *dev) { diff --git a/include/linux/pm_wakeirq.h b/include/linux/pm_wakeirq.h index e63a63aa47a3..dd42d16945d0 100644 --- a/include/linux/pm_wakeirq.h +++ b/include/linux/pm_wakeirq.h @@ -1,15 +1,5 @@ -/* - * pm_wakeirq.h - Device wakeirq helper functions - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * This program is distributed "as is" WITHOUT ANY WARRANTY of any - * kind, whether express or implied; without even the implied warranty - * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - */ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* pm_wakeirq.h - Device wakeirq helper functions */ #ifndef _LINUX_PM_WAKEIRQ_H #define _LINUX_PM_WAKEIRQ_H diff --git a/include/linux/pm_wakeup.h b/include/linux/pm_wakeup.h index 196a157456aa..77f4849e3418 100644 --- a/include/linux/pm_wakeup.h +++ b/include/linux/pm_wakeup.h @@ -109,7 +109,6 @@ extern struct wakeup_source *wakeup_sources_walk_next(struct wakeup_source *ws); extern int device_wakeup_enable(struct device *dev); extern int device_wakeup_disable(struct device *dev); extern void device_set_wakeup_capable(struct device *dev, bool capable); -extern int device_init_wakeup(struct device *dev, bool val); extern int device_set_wakeup_enable(struct device *dev, bool enable); extern void __pm_stay_awake(struct wakeup_source *ws); extern void pm_stay_awake(struct device *dev); @@ -167,13 +166,6 @@ static inline int device_set_wakeup_enable(struct device *dev, bool enable) return 0; } -static inline int device_init_wakeup(struct device *dev, bool val) -{ - device_set_wakeup_capable(dev, val); - device_set_wakeup_enable(dev, val); - return 0; -} - static inline bool device_may_wakeup(struct device *dev) { return dev->power.can_wakeup && dev->power.should_wakeup; @@ -217,4 +209,27 @@ static inline void pm_wakeup_hard_event(struct device *dev) return pm_wakeup_dev_event(dev, 0, true); } +/** + * device_init_wakeup - Device wakeup initialization. + * @dev: Device to handle. + * @enable: Whether or not to enable @dev as a wakeup device. + * + * By default, most devices should leave wakeup disabled. The exceptions are + * devices that everyone expects to be wakeup sources: keyboards, power buttons, + * possibly network interfaces, etc. Also, devices that don't generate their + * own wakeup requests but merely forward requests from one bus to another + * (like PCI bridges) should have wakeup enabled by default. + */ +static inline int device_init_wakeup(struct device *dev, bool enable) +{ + if (enable) { + device_set_wakeup_capable(dev, true); + return device_wakeup_enable(dev); + } else { + device_wakeup_disable(dev); + device_set_wakeup_capable(dev, false); + return 0; + } +} + #endif /* _LINUX_PM_WAKEUP_H */ diff --git a/include/linux/pmu.h b/include/linux/pmu.h index 52453a24a24f..c677442d007c 100644 --- a/include/linux/pmu.h +++ b/include/linux/pmu.h @@ -13,7 +13,7 @@ #include <uapi/linux/pmu.h> -extern int find_via_pmu(void); +extern int __init find_via_pmu(void); extern int pmu_request(struct adb_request *req, void (*done)(struct adb_request *), int nbytes, ...); diff --git a/include/linux/poison.h b/include/linux/poison.h index d62ef5a6b4e9..2d3249eb0e62 100644 --- a/include/linux/poison.h +++ b/include/linux/poison.h @@ -81,4 +81,7 @@ /********** net/core/page_pool.c **********/ #define PP_SIGNATURE (0x40 + POISON_POINTER_DELTA) +/********** kernel/bpf/ **********/ +#define BPF_PTR_POISON ((void *)(0xeB9FUL + POISON_POINTER_DELTA)) + #endif diff --git a/include/linux/poll.h b/include/linux/poll.h index 1cdc32b1f1b0..a9e0e1c2d1f2 100644 --- a/include/linux/poll.h +++ b/include/linux/poll.h @@ -8,12 +8,10 @@ #include <linux/wait.h> #include <linux/string.h> #include <linux/fs.h> -#include <linux/sysctl.h> #include <linux/uaccess.h> #include <uapi/linux/poll.h> #include <uapi/linux/eventpoll.h> -extern struct ctl_table epoll_table[]; /* for sysctl */ /* ~832 bytes of stack space used max in sys_select/sys_poll before allocating additional memory. */ #ifdef __clang__ diff --git a/include/linux/polynomial.h b/include/linux/polynomial.h new file mode 100644 index 000000000000..9e074a0bb6fa --- /dev/null +++ b/include/linux/polynomial.h @@ -0,0 +1,35 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2020 BAIKAL ELECTRONICS, JSC + */ + +#ifndef _POLYNOMIAL_H +#define _POLYNOMIAL_H + +/* + * struct polynomial_term - one term descriptor of a polynomial + * @deg: degree of the term. + * @coef: multiplication factor of the term. + * @divider: distributed divider per each degree. + * @divider_leftover: divider leftover, which couldn't be redistributed. + */ +struct polynomial_term { + unsigned int deg; + long coef; + long divider; + long divider_leftover; +}; + +/* + * struct polynomial - a polynomial descriptor + * @total_divider: total data divider. + * @terms: polynomial terms, last term must have degree of 0 + */ +struct polynomial { + long total_divider; + struct polynomial_term terms[]; +}; + +long polynomial_calc(const struct polynomial *poly, long data); + +#endif diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h index 5bbcd280bfd2..2c6e99ca48af 100644 --- a/include/linux/posix-timers.h +++ b/include/linux/posix-timers.h @@ -6,7 +6,6 @@ #include <linux/list.h> #include <linux/alarmtimer.h> #include <linux/timerqueue.h> -#include <linux/task_work.h> struct kernel_siginfo; struct task_struct; @@ -253,7 +252,7 @@ void posix_cpu_timers_exit_group(struct task_struct *task); void set_process_cpu_timer(struct task_struct *task, unsigned int clock_idx, u64 *newval, u64 *oldval); -void update_rlimit_cpu(struct task_struct *task, unsigned long rlim_new); +int update_rlimit_cpu(struct task_struct *task, unsigned long rlim_new); void posixtimer_rearm(struct kernel_siginfo *info); #endif diff --git a/include/linux/posix_acl.h b/include/linux/posix_acl.h index b65c877d92b8..7d1e604c1325 100644 --- a/include/linux/posix_acl.h +++ b/include/linux/posix_acl.h @@ -73,6 +73,7 @@ extern int set_posix_acl(struct user_namespace *, struct inode *, int, struct posix_acl *); struct posix_acl *get_cached_acl_rcu(struct inode *inode, int type); +struct posix_acl *posix_acl_clone(const struct posix_acl *acl, gfp_t flags); #ifdef CONFIG_FS_POSIX_ACL int posix_acl_chmod(struct user_namespace *, struct inode *, umode_t); diff --git a/include/linux/posix_acl_xattr.h b/include/linux/posix_acl_xattr.h index 060e8d203181..8163dd48c430 100644 --- a/include/linux/posix_acl_xattr.h +++ b/include/linux/posix_acl_xattr.h @@ -33,17 +33,22 @@ posix_acl_xattr_count(size_t size) } #ifdef CONFIG_FS_POSIX_ACL -void posix_acl_fix_xattr_from_user(struct user_namespace *mnt_userns, - void *value, size_t size); -void posix_acl_fix_xattr_to_user(struct user_namespace *mnt_userns, - void *value, size_t size); +void posix_acl_fix_xattr_from_user(void *value, size_t size); +void posix_acl_fix_xattr_to_user(void *value, size_t size); +void posix_acl_getxattr_idmapped_mnt(struct user_namespace *mnt_userns, + const struct inode *inode, + void *value, size_t size); #else -static inline void posix_acl_fix_xattr_from_user(struct user_namespace *mnt_userns, - void *value, size_t size) +static inline void posix_acl_fix_xattr_from_user(void *value, size_t size) { } -static inline void posix_acl_fix_xattr_to_user(struct user_namespace *mnt_userns, - void *value, size_t size) +static inline void posix_acl_fix_xattr_to_user(void *value, size_t size) +{ +} +static inline void +posix_acl_getxattr_idmapped_mnt(struct user_namespace *mnt_userns, + const struct inode *inode, void *value, + size_t size) { } #endif @@ -52,6 +57,9 @@ struct posix_acl *posix_acl_from_xattr(struct user_namespace *user_ns, const void *value, size_t size); int posix_acl_to_xattr(struct user_namespace *user_ns, const struct posix_acl *acl, void *buffer, size_t size); +struct posix_acl *vfs_set_acl_prepare(struct user_namespace *mnt_userns, + struct user_namespace *fs_userns, + const void *value, size_t size); extern const struct xattr_handler posix_acl_access_xattr_handler; extern const struct xattr_handler posix_acl_default_xattr_handler; diff --git a/include/linux/power/bq25890_charger.h b/include/linux/power/bq25890_charger.h new file mode 100644 index 000000000000..c706ddb77a08 --- /dev/null +++ b/include/linux/power/bq25890_charger.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Platform data for the TI bq25890 battery charger driver. + */ + +#ifndef _BQ25890_CHARGER_H_ +#define _BQ25890_CHARGER_H_ + +struct regulator_init_data; + +struct bq25890_platform_data { + const struct regulator_init_data *regulator_init_data; +}; + +#endif diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h index e218041cc000..aa2c4a7c4826 100644 --- a/include/linux/power_supply.h +++ b/include/linux/power_supply.h @@ -49,6 +49,7 @@ enum { POWER_SUPPLY_CHARGE_TYPE_ADAPTIVE, /* dynamically adjusted speed */ POWER_SUPPLY_CHARGE_TYPE_CUSTOM, /* use CHARGE_CONTROL_* props */ POWER_SUPPLY_CHARGE_TYPE_LONGLIFE, /* slow speed, longer life */ + POWER_SUPPLY_CHARGE_TYPE_BYPASS, /* bypassing the charger */ }; enum { @@ -348,6 +349,93 @@ struct power_supply_resistance_temp_table { int resistance; /* internal resistance percent */ }; +struct power_supply_vbat_ri_table { + int vbat_uv; /* Battery voltage in microvolt */ + int ri_uohm; /* Internal resistance in microohm */ +}; + +/** + * struct power_supply_maintenance_charge_table - setting for maintenace charging + * @charge_current_max_ua: maintenance charging current that is used to keep + * the charge of the battery full as current is consumed after full charging. + * The corresponding charge_voltage_max_uv is used as a safeguard: when we + * reach this voltage the maintenance charging current is turned off. It is + * turned back on if we fall below this voltage. + * @charge_voltage_max_uv: maintenance charging voltage that is usually a bit + * lower than the constant_charge_voltage_max_uv. We can apply this settings + * charge_current_max_ua until we get back up to this voltage. + * @safety_timer_minutes: maintenance charging safety timer, with an expiry + * time in minutes. We will only use maintenance charging in this setting + * for a certain amount of time, then we will first move to the next + * maintenance charge current and voltage pair in respective array and wait + * for the next safety timer timeout, or, if we reached the last maintencance + * charging setting, disable charging until we reach + * charge_restart_voltage_uv and restart ordinary CC/CV charging from there. + * These timers should be chosen to align with the typical discharge curve + * for the battery. + * + * Ordinary CC/CV charging will stop charging when the charge current goes + * below charge_term_current_ua, and then restart it (if the device is still + * plugged into the charger) at charge_restart_voltage_uv. This happens in most + * consumer products because the power usage while connected to a charger is + * not zero, and devices are not manufactured to draw power directly from the + * charger: instead they will at all times dissipate the battery a little, like + * the power used in standby mode. This will over time give a charge graph + * such as this: + * + * Energy + * ^ ... ... ... ... ... ... ... + * | . . . . . . . . . . . . . + * | .. . .. . .. . .. . .. . .. . .. + * |. .. .. .. .. .. .. + * +-------------------------------------------------------------------> t + * + * Practically this means that the Li-ions are wandering back and forth in the + * battery and this causes degeneration of the battery anode and cathode. + * To prolong the life of the battery, maintenance charging is applied after + * reaching charge_term_current_ua to hold up the charge in the battery while + * consuming power, thus lowering the wear on the battery: + * + * Energy + * ^ ....................................... + * | . ...................... + * | .. + * |. + * +-------------------------------------------------------------------> t + * + * Maintenance charging uses the voltages from this table: a table of settings + * is traversed using a slightly lower current and voltage than what is used for + * CC/CV charging. The maintenance charging will for safety reasons not go on + * indefinately: we lower the current and voltage with successive maintenance + * settings, then disable charging completely after we reach the last one, + * and after that we do not restart charging until we reach + * charge_restart_voltage_uv (see struct power_supply_battery_info) and restart + * ordinary CC/CV charging from there. + * + * As an example, a Samsung EB425161LA Lithium-Ion battery is CC/CV charged + * at 900mA to 4340mV, then maintenance charged at 600mA and 4150mV for up to + * 60 hours, then maintenance charged at 600mA and 4100mV for up to 200 hours. + * After this the charge cycle is restarted waiting for + * charge_restart_voltage_uv. + * + * For most mobile electronics this type of maintenance charging is enough for + * the user to disconnect the device and make use of it before both maintenance + * charging cycles are complete, if the current and voltage has been chosen + * appropriately. These need to be determined from battery discharge curves + * and expected standby current. + * + * If the voltage anyway drops to charge_restart_voltage_uv during maintenance + * charging, ordinary CC/CV charging is restarted. This can happen if the + * device is e.g. actively used during charging, so more current is drawn than + * the expected stand-by current. Also overvoltage protection will be applied + * as usual. + */ +struct power_supply_maintenance_charge_table { + int charge_current_max_ua; + int charge_voltage_max_uv; + int charge_safety_timer_minutes; +}; + #define POWER_SUPPLY_OCV_TEMP_MAX 20 /** @@ -393,10 +481,34 @@ struct power_supply_resistance_temp_table { * @constant_charge_voltage_max_uv: voltage in microvolts signifying the end of * the CC (constant current) charging phase and the beginning of the CV * (constant voltage) charging phase. + * @maintenance_charge: an array of maintenance charging settings to be used + * after the main CC/CV charging phase is complete. + * @maintenance_charge_size: the number of maintenance charging settings in + * maintenance_charge. + * @alert_low_temp_charge_current_ua: The charging current to use if the battery + * enters low alert temperature, i.e. if the internal temperature is between + * temp_alert_min and temp_min. No matter the charging phase, this + * and alert_high_temp_charge_voltage_uv will be applied. + * @alert_low_temp_charge_voltage_uv: Same as alert_low_temp_charge_current_ua, + * but for the charging voltage. + * @alert_high_temp_charge_current_ua: The charging current to use if the + * battery enters high alert temperature, i.e. if the internal temperature is + * between temp_alert_max and temp_max. No matter the charging phase, this + * and alert_high_temp_charge_voltage_uv will be applied, usually lowering + * the charging current as an evasive manouver. + * @alert_high_temp_charge_voltage_uv: Same as + * alert_high_temp_charge_current_ua, but for the charging voltage. * @factory_internal_resistance_uohm: the internal resistance of the battery * at fabrication time, expressed in microohms. This resistance will vary * depending on the lifetime and charge of the battery, so this is just a - * nominal ballpark figure. + * nominal ballpark figure. This internal resistance is given for the state + * when the battery is discharging. + * @factory_internal_resistance_charging_uohm: the internal resistance of the + * battery at fabrication time while charging, expressed in microohms. + * The charging process will affect the internal resistance of the battery + * so this value provides a better resistance under these circumstances. + * This resistance will vary depending on the lifetime and charge of the + * battery, so this is just a nominal ballpark figure. * @ocv_temp: array indicating the open circuit voltage (OCV) capacity * temperature indices. This is an array of temperatures in degrees Celsius * indicating which capacity table to use for a certain temperature, since @@ -434,13 +546,38 @@ struct power_supply_resistance_temp_table { * by temperature: highest temperature with lowest resistance first, lowest * temperature with highest resistance last. * @resist_table_size: the number of items in the resist_table. + * @vbat2ri_discharging: this is a table that correlates Battery voltage (VBAT) + * to internal resistance (Ri). The resistance is given in microohm for the + * corresponding voltage in microvolts. The internal resistance is used to + * determine the open circuit voltage so that we can determine the capacity + * of the battery. These voltages to resistance tables apply when the battery + * is discharging. The table must be ordered descending by voltage: highest + * voltage first. + * @vbat2ri_discharging_size: the number of items in the vbat2ri_discharging + * table. + * @vbat2ri_charging: same function as vbat2ri_discharging but for the state + * when the battery is charging. Being under charge changes the battery's + * internal resistance characteristics so a separate table is needed.* + * The table must be ordered descending by voltage: highest voltage first. + * @vbat2ri_charging_size: the number of items in the vbat2ri_charging + * table. + * @bti_resistance_ohm: The Battery Type Indicator (BIT) nominal resistance + * in ohms for this battery, if an identification resistor is mounted + * between a third battery terminal and ground. This scheme is used by a lot + * of mobile device batteries. + * @bti_resistance_tolerance: The tolerance in percent of the BTI resistance, + * for example 10 for +/- 10%, if the bti_resistance is set to 7000 and the + * tolerance is 10% we will detect a proper battery if the BTI resistance + * is between 6300 and 7700 Ohm. * * This is the recommended struct to manage static battery parameters, * populated by power_supply_get_battery_info(). Most platform drivers should * use these for consistency. * * Its field names must correspond to elements in enum power_supply_property. - * The default field value is -EINVAL. + * The default field value is -EINVAL or NULL for pointers. + * + * CC/CV CHARGING: * * The charging parameters here assume a CC/CV charging scheme. This method * is most common with Lithium Ion batteries (other methods are possible) and @@ -525,6 +662,66 @@ struct power_supply_resistance_temp_table { * Overcharging Lithium Ion cells can be DANGEROUS and lead to fire or * explosions. * + * DETERMINING BATTERY CAPACITY: + * + * Several members of the struct deal with trying to determine the remaining + * capacity in the battery, usually as a percentage of charge. In practice + * many chargers uses a so-called fuel gauge or coloumb counter that measure + * how much charge goes into the battery and how much goes out (+/- leak + * consumption). This does not help if we do not know how much capacity the + * battery has to begin with, such as when it is first used or was taken out + * and charged in a separate charger. Therefore many capacity algorithms use + * the open circuit voltage with a look-up table to determine the rough + * capacity of the battery. The open circuit voltage can be conceptualized + * with an ideal voltage source (V) in series with an internal resistance (Ri) + * like this: + * + * +-------> IBAT >----------------+ + * | ^ | + * [ ] Ri | | + * | | VBAT | + * o <---------- | | + * +| ^ | [ ] Rload + * .---. | | | + * | V | | OCV | | + * '---' | | | + * | | | | + * GND +-------------------------------+ + * + * If we disconnect the load (here simplified as a fixed resistance Rload) + * and measure VBAT with a infinite impedance voltage meter we will get + * VBAT = OCV and this assumption is sometimes made even under load, assuming + * Rload is insignificant. However this will be of dubious quality because the + * load is rarely that small and Ri is strongly nonlinear depending on + * temperature and how much capacity is left in the battery due to the + * chemistry involved. + * + * In many practical applications we cannot just disconnect the battery from + * the load, so instead we often try to measure the instantaneous IBAT (the + * current out from the battery), estimate the Ri and thus calculate the + * voltage drop over Ri and compensate like this: + * + * OCV = VBAT - (IBAT * Ri) + * + * The tables vbat2ri_discharging and vbat2ri_charging are used to determine + * (by interpolation) the Ri from the VBAT under load. These curves are highly + * nonlinear and may need many datapoints but can be found in datasheets for + * some batteries. This gives the compensated open circuit voltage (OCV) for + * the battery even under load. Using this method will also compensate for + * temperature changes in the environment: this will also make the internal + * resistance change, and it will affect the VBAT under load, so correlating + * VBAT to Ri takes both remaining capacity and temperature into consideration. + * + * Alternatively a manufacturer can specify how the capacity of the battery + * is dependent on the battery temperature which is the main factor affecting + * Ri. As we know all checmical reactions are faster when it is warm and slower + * when it is cold. You can put in 1500mAh and only get 800mAh out before the + * voltage drops too low for example. This effect is also highly nonlinear and + * the purpose of the table resist_table: this will take a temperature and + * tell us how big percentage of Ri the specified temperature correlates to. + * Usually we have 100% of the factory_internal_resistance_uohm at 25 degrees + * Celsius. + * * The power supply class itself doesn't use this struct as of now. */ @@ -542,7 +739,14 @@ struct power_supply_battery_info { int overvoltage_limit_uv; int constant_charge_current_max_ua; int constant_charge_voltage_max_uv; + struct power_supply_maintenance_charge_table *maintenance_charge; + int maintenance_charge_size; + int alert_low_temp_charge_current_ua; + int alert_low_temp_charge_voltage_uv; + int alert_high_temp_charge_current_ua; + int alert_high_temp_charge_voltage_uv; int factory_internal_resistance_uohm; + int factory_internal_resistance_charging_uohm; int ocv_temp[POWER_SUPPLY_OCV_TEMP_MAX]; int temp_ambient_alert_min; int temp_ambient_alert_max; @@ -554,6 +758,12 @@ struct power_supply_battery_info { int ocv_table_size[POWER_SUPPLY_OCV_TEMP_MAX]; struct power_supply_resistance_temp_table *resist_table; int resist_table_size; + struct power_supply_vbat_ri_table *vbat2ri_discharging; + int vbat2ri_discharging_size; + struct power_supply_vbat_ri_table *vbat2ri_charging; + int vbat2ri_charging_size; + int bti_resistance_ohm; + int bti_resistance_tolerance; }; extern struct atomic_notifier_head power_supply_notifier; @@ -595,12 +805,43 @@ extern int power_supply_batinfo_ocv2cap(struct power_supply_battery_info *info, extern int power_supply_temp2resist_simple(struct power_supply_resistance_temp_table *table, int table_len, int temp); +extern int power_supply_vbat2ri(struct power_supply_battery_info *info, + int vbat_uv, bool charging); +extern struct power_supply_maintenance_charge_table * +power_supply_get_maintenance_charging_setting(struct power_supply_battery_info *info, int index); +extern bool power_supply_battery_bti_in_range(struct power_supply_battery_info *info, + int resistance); extern void power_supply_changed(struct power_supply *psy); extern int power_supply_am_i_supplied(struct power_supply *psy); -extern int power_supply_set_input_current_limit_from_supplier( - struct power_supply *psy); +int power_supply_get_property_from_supplier(struct power_supply *psy, + enum power_supply_property psp, + union power_supply_propval *val); extern int power_supply_set_battery_charged(struct power_supply *psy); +static inline bool +power_supply_supports_maintenance_charging(struct power_supply_battery_info *info) +{ + struct power_supply_maintenance_charge_table *mt; + + mt = power_supply_get_maintenance_charging_setting(info, 0); + + return (mt != NULL); +} + +static inline bool +power_supply_supports_vbat2ri(struct power_supply_battery_info *info) +{ + return ((info->vbat2ri_discharging != NULL) && + info->vbat2ri_discharging_size > 0); +} + +static inline bool +power_supply_supports_temp2ri(struct power_supply_battery_info *info) +{ + return ((info->resist_table != NULL) && + info->resist_table_size > 0); +} + #ifdef CONFIG_POWER_SUPPLY extern int power_supply_is_system_supplied(void); #else diff --git a/include/linux/ppp-comp.h b/include/linux/ppp-comp.h index 9d3ffc8f5ea6..fb847e47f148 100644 --- a/include/linux/ppp-comp.h +++ b/include/linux/ppp-comp.h @@ -9,7 +9,7 @@ #include <uapi/linux/ppp-comp.h> - +struct compstat; struct module; /* diff --git a/include/linux/ppp_channel.h b/include/linux/ppp_channel.h index 91f9a928344e..45e6e427ceb8 100644 --- a/include/linux/ppp_channel.h +++ b/include/linux/ppp_channel.h @@ -20,6 +20,8 @@ #include <linux/poll.h> #include <net/net_namespace.h> +struct net_device_path; +struct net_device_path_ctx; struct ppp_channel; struct ppp_channel_ops { diff --git a/include/linux/ppp_defs.h b/include/linux/ppp_defs.h index 9d2b388fae1a..b7e57fdbd413 100644 --- a/include/linux/ppp_defs.h +++ b/include/linux/ppp_defs.h @@ -11,4 +11,18 @@ #include <uapi/linux/ppp_defs.h> #define PPP_FCS(fcs, c) crc_ccitt_byte(fcs, c) + +/** + * ppp_proto_is_valid - checks if PPP protocol is valid + * @proto: PPP protocol + * + * Assumes proto is not compressed. + * Protocol is valid if the value is odd and the least significant bit of the + * most significant octet is 0 (see RFC 1661, section 2). + */ +static inline bool ppp_proto_is_valid(u16 proto) +{ + return !!((proto & 0x0101) == 0x0001); +} + #endif /* _PPP_DEFS_H_ */ diff --git a/include/linux/prandom.h b/include/linux/prandom.h index 056d31317e49..e0a0759dd09c 100644 --- a/include/linux/prandom.h +++ b/include/linux/prandom.h @@ -10,63 +10,7 @@ #include <linux/types.h> #include <linux/percpu.h> - -u32 prandom_u32(void); -void prandom_bytes(void *buf, size_t nbytes); -void prandom_seed(u32 seed); -void prandom_reseed_late(void); - -DECLARE_PER_CPU(unsigned long, net_rand_noise); - -#define PRANDOM_ADD_NOISE(a, b, c, d) \ - prandom_u32_add_noise((unsigned long)(a), (unsigned long)(b), \ - (unsigned long)(c), (unsigned long)(d)) - -#if BITS_PER_LONG == 64 -/* - * The core SipHash round function. Each line can be executed in - * parallel given enough CPU resources. - */ -#define PRND_SIPROUND(v0, v1, v2, v3) ( \ - v0 += v1, v1 = rol64(v1, 13), v2 += v3, v3 = rol64(v3, 16), \ - v1 ^= v0, v0 = rol64(v0, 32), v3 ^= v2, \ - v0 += v3, v3 = rol64(v3, 21), v2 += v1, v1 = rol64(v1, 17), \ - v3 ^= v0, v1 ^= v2, v2 = rol64(v2, 32) \ -) - -#define PRND_K0 (0x736f6d6570736575 ^ 0x6c7967656e657261) -#define PRND_K1 (0x646f72616e646f6d ^ 0x7465646279746573) - -#elif BITS_PER_LONG == 32 -/* - * On 32-bit machines, we use HSipHash, a reduced-width version of SipHash. - * This is weaker, but 32-bit machines are not used for high-traffic - * applications, so there is less output for an attacker to analyze. - */ -#define PRND_SIPROUND(v0, v1, v2, v3) ( \ - v0 += v1, v1 = rol32(v1, 5), v2 += v3, v3 = rol32(v3, 8), \ - v1 ^= v0, v0 = rol32(v0, 16), v3 ^= v2, \ - v0 += v3, v3 = rol32(v3, 7), v2 += v1, v1 = rol32(v1, 13), \ - v3 ^= v0, v1 ^= v2, v2 = rol32(v2, 16) \ -) -#define PRND_K0 0x6c796765 -#define PRND_K1 0x74656462 - -#else -#error Unsupported BITS_PER_LONG -#endif - -static inline void prandom_u32_add_noise(unsigned long a, unsigned long b, - unsigned long c, unsigned long d) -{ - /* - * This is not used cryptographically; it's just - * a convenient 4-word hash function. (3 xor, 2 add, 2 rol) - */ - a ^= raw_cpu_read(net_rand_noise); - PRND_SIPROUND(a, b, c, d); - raw_cpu_write(net_rand_noise, d); -} +#include <linux/random.h> struct rnd_state { __u32 s1, s2, s3, s4; @@ -83,17 +27,20 @@ void prandom_seed_full_state(struct rnd_state __percpu *pcpu_state); * prandom_u32_max - returns a pseudo-random number in interval [0, ep_ro) * @ep_ro: right open interval endpoint * - * Returns a pseudo-random number that is in interval [0, ep_ro). Note - * that the result depends on PRNG being well distributed in [0, ~0U] - * u32 space. Here we use maximally equidistributed combined Tausworthe - * generator, that is, prandom_u32(). This is useful when requesting a - * random index of an array containing ep_ro elements, for example. + * Returns a pseudo-random number that is in interval [0, ep_ro). This is + * useful when requesting a random index of an array containing ep_ro elements, + * for example. The result is somewhat biased when ep_ro is not a power of 2, + * so do not use this for cryptographic purposes. * * Returns: pseudo-random number in interval [0, ep_ro) */ static inline u32 prandom_u32_max(u32 ep_ro) { - return (u32)(((u64) prandom_u32() * ep_ro) >> 32); + if (__builtin_constant_p(ep_ro <= 1U << 8) && ep_ro <= 1U << 8) + return (get_random_u8() * ep_ro) >> 8; + if (__builtin_constant_p(ep_ro <= 1U << 16) && ep_ro <= 1U << 16) + return (get_random_u16() * ep_ro) >> 16; + return ((u64)get_random_u32() * ep_ro) >> 32; } /* @@ -117,7 +64,6 @@ static inline void prandom_seed_state(struct rnd_state *state, u64 seed) state->s2 = __seed(i, 8U); state->s3 = __seed(i, 16U); state->s4 = __seed(i, 128U); - PRANDOM_ADD_NOISE(state, i, 0, 0); } /* Pseudo random number generator from numerical recipes. */ diff --git a/include/linux/preempt.h b/include/linux/preempt.h index b4381f255a5c..0df425bf9bd7 100644 --- a/include/linux/preempt.h +++ b/include/linux/preempt.h @@ -421,4 +421,46 @@ static inline void migrate_enable(void) { } #endif /* CONFIG_SMP */ +/** + * preempt_disable_nested - Disable preemption inside a normally preempt disabled section + * + * Use for code which requires preemption protection inside a critical + * section which has preemption disabled implicitly on non-PREEMPT_RT + * enabled kernels, by e.g.: + * - holding a spinlock/rwlock + * - soft interrupt context + * - regular interrupt handlers + * + * On PREEMPT_RT enabled kernels spinlock/rwlock held sections, soft + * interrupt context and regular interrupt handlers are preemptible and + * only prevent migration. preempt_disable_nested() ensures that preemption + * is disabled for cases which require CPU local serialization even on + * PREEMPT_RT. For non-PREEMPT_RT kernels this is a NOP. + * + * The use cases are code sequences which are not serialized by a + * particular lock instance, e.g.: + * - seqcount write side critical sections where the seqcount is not + * associated to a particular lock and therefore the automatic + * protection mechanism does not work. This prevents a live lock + * against a preempting high priority reader. + * - RMW per CPU variable updates like vmstat. + */ +/* Macro to avoid header recursion hell vs. lockdep */ +#define preempt_disable_nested() \ +do { \ + if (IS_ENABLED(CONFIG_PREEMPT_RT)) \ + preempt_disable(); \ + else \ + lockdep_assert_preemption_disabled(); \ +} while (0) + +/** + * preempt_enable_nested - Undo the effect of preempt_disable_nested() + */ +static __always_inline void preempt_enable_nested(void) +{ + if (IS_ENABLED(CONFIG_PREEMPT_RT)) + preempt_enable(); +} + #endif /* __LINUX_PREEMPT_H */ diff --git a/include/linux/printk.h b/include/linux/printk.h index 9497f6b98339..8c81806c2e99 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -6,7 +6,6 @@ #include <linux/init.h> #include <linux/kern_levels.h> #include <linux/linkage.h> -#include <linux/cache.h> #include <linux/ratelimit_types.h> #include <linux/once_lite.h> @@ -183,10 +182,6 @@ extern bool printk_timed_ratelimit(unsigned long *caller_jiffies, extern int printk_delay_msec; extern int dmesg_restrict; -extern int -devkmsg_sysctl_set_loglvl(struct ctl_table *table, int write, void *buf, - size_t *lenp, loff_t *ppos); - extern void wake_up_klogd(void); char *log_buf_addr_get(void); @@ -281,45 +276,57 @@ static inline void printk_trigger_flush(void) #endif #ifdef CONFIG_SMP -extern int __printk_cpu_trylock(void); -extern void __printk_wait_on_cpu_lock(void); -extern void __printk_cpu_unlock(void); +extern int __printk_cpu_sync_try_get(void); +extern void __printk_cpu_sync_wait(void); +extern void __printk_cpu_sync_put(void); + +#else + +#define __printk_cpu_sync_try_get() true +#define __printk_cpu_sync_wait() +#define __printk_cpu_sync_put() +#endif /* CONFIG_SMP */ /** - * printk_cpu_lock_irqsave() - Acquire the printk cpu-reentrant spinning - * lock and disable interrupts. + * printk_cpu_sync_get_irqsave() - Disable interrupts and acquire the printk + * cpu-reentrant spinning lock. * @flags: Stack-allocated storage for saving local interrupt state, - * to be passed to printk_cpu_unlock_irqrestore(). + * to be passed to printk_cpu_sync_put_irqrestore(). * * If the lock is owned by another CPU, spin until it becomes available. * Interrupts are restored while spinning. + * + * CAUTION: This function must be used carefully. It does not behave like a + * typical lock. Here are important things to watch out for... + * + * * This function is reentrant on the same CPU. Therefore the calling + * code must not assume exclusive access to data if code accessing the + * data can run reentrant or within NMI context on the same CPU. + * + * * If there exists usage of this function from NMI context, it becomes + * unsafe to perform any type of locking or spinning to wait for other + * CPUs after calling this function from any context. This includes + * using spinlocks or any other busy-waiting synchronization methods. */ -#define printk_cpu_lock_irqsave(flags) \ - for (;;) { \ - local_irq_save(flags); \ - if (__printk_cpu_trylock()) \ - break; \ - local_irq_restore(flags); \ - __printk_wait_on_cpu_lock(); \ +#define printk_cpu_sync_get_irqsave(flags) \ + for (;;) { \ + local_irq_save(flags); \ + if (__printk_cpu_sync_try_get()) \ + break; \ + local_irq_restore(flags); \ + __printk_cpu_sync_wait(); \ } /** - * printk_cpu_unlock_irqrestore() - Release the printk cpu-reentrant spinning - * lock and restore interrupts. - * @flags: Caller's saved interrupt state, from printk_cpu_lock_irqsave(). + * printk_cpu_sync_put_irqrestore() - Release the printk cpu-reentrant spinning + * lock and restore interrupts. + * @flags: Caller's saved interrupt state, from printk_cpu_sync_get_irqsave(). */ -#define printk_cpu_unlock_irqrestore(flags) \ +#define printk_cpu_sync_put_irqrestore(flags) \ do { \ - __printk_cpu_unlock(); \ + __printk_cpu_sync_put(); \ local_irq_restore(flags); \ - } while (0) \ - -#else - -#define printk_cpu_lock_irqsave(flags) ((void)flags) -#define printk_cpu_unlock_irqrestore(flags) ((void)flags) - -#endif /* CONFIG_SMP */ + } while (0) extern int kptr_restrict; diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index 069c7fd95396..81d6e4ec2294 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -110,7 +110,16 @@ extern struct proc_dir_entry *proc_create_data(const char *, umode_t, struct proc_dir_entry *proc_create(const char *name, umode_t mode, struct proc_dir_entry *parent, const struct proc_ops *proc_ops); extern void proc_set_size(struct proc_dir_entry *, loff_t); extern void proc_set_user(struct proc_dir_entry *, kuid_t, kgid_t); -extern void *PDE_DATA(const struct inode *); + +/* + * Obtain the private data passed by user through proc_create_data() or + * related. + */ +static inline void *pde_data(const struct inode *inode) +{ + return inode->i_private; +} + extern void *proc_get_parent_data(const struct inode *); extern void proc_remove(struct proc_dir_entry *); extern void remove_proc_entry(const char *, struct proc_dir_entry *); @@ -178,12 +187,20 @@ static inline struct proc_dir_entry *proc_mkdir_mode(const char *name, #define proc_create_seq(name, mode, parent, ops) ({NULL;}) #define proc_create_single(name, mode, parent, show) ({NULL;}) #define proc_create_single_data(name, mode, parent, show, data) ({NULL;}) -#define proc_create(name, mode, parent, proc_ops) ({NULL;}) -#define proc_create_data(name, mode, parent, proc_ops, data) ({NULL;}) + +static inline struct proc_dir_entry * +proc_create(const char *name, umode_t mode, struct proc_dir_entry *parent, + const struct proc_ops *proc_ops) +{ return NULL; } + +static inline struct proc_dir_entry * +proc_create_data(const char *name, umode_t mode, struct proc_dir_entry *parent, + const struct proc_ops *proc_ops, void *data) +{ return NULL; } static inline void proc_set_size(struct proc_dir_entry *de, loff_t size) {} static inline void proc_set_user(struct proc_dir_entry *de, kuid_t uid, kgid_t gid) {} -static inline void *PDE_DATA(const struct inode *inode) {BUG(); return NULL;} +static inline void *pde_data(const struct inode *inode) {BUG(); return NULL;} static inline void *proc_get_parent_data(const struct inode *inode) { BUG(); return NULL; } static inline void proc_remove(struct proc_dir_entry *de) {} diff --git a/include/linux/profile.h b/include/linux/profile.h index fd18ca96f557..11db1ec516e2 100644 --- a/include/linux/profile.h +++ b/include/linux/profile.h @@ -31,11 +31,6 @@ static inline int create_proc_profile(void) } #endif -enum profile_type { - PROFILE_TASK_EXIT, - PROFILE_MUNMAP -}; - #ifdef CONFIG_PROFILING extern int prof_on __read_mostly; @@ -66,23 +61,6 @@ static inline void profile_hit(int type, void *ip) struct task_struct; struct mm_struct; -/* task is in do_exit() */ -void profile_task_exit(struct task_struct * task); - -/* task is dead, free task struct ? Returns 1 if - * the task was taken, 0 if the task should be freed. - */ -int profile_handoff_task(struct task_struct * task); - -/* sys_munmap */ -void profile_munmap(unsigned long addr); - -int task_handoff_register(struct notifier_block * n); -int task_handoff_unregister(struct notifier_block * n); - -int profile_event_register(enum profile_type, struct notifier_block * n); -int profile_event_unregister(enum profile_type, struct notifier_block * n); - #else #define prof_on 0 @@ -107,29 +85,6 @@ static inline void profile_hit(int type, void *ip) return; } -static inline int task_handoff_register(struct notifier_block * n) -{ - return -ENOSYS; -} - -static inline int task_handoff_unregister(struct notifier_block * n) -{ - return -ENOSYS; -} - -static inline int profile_event_register(enum profile_type t, struct notifier_block * n) -{ - return -ENOSYS; -} - -static inline int profile_event_unregister(enum profile_type t, struct notifier_block * n) -{ - return -ENOSYS; -} - -#define profile_task_exit(a) do { } while (0) -#define profile_handoff_task(a) (0) -#define profile_munmap(a) do { } while (0) #endif /* CONFIG_PROFILING */ diff --git a/include/linux/property.h b/include/linux/property.h index 8355f99ebd47..117cc200c656 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -32,7 +32,7 @@ enum dev_dma_attr { DEV_DMA_COHERENT, }; -struct fwnode_handle *dev_fwnode(struct device *dev); +struct fwnode_handle *dev_fwnode(const struct device *dev); bool device_property_present(struct device *dev, const char *propname); int device_property_read_u8_array(struct device *dev, const char *propname, @@ -83,15 +83,19 @@ struct fwnode_handle *fwnode_find_reference(const struct fwnode_handle *fwnode, const char *fwnode_get_name(const struct fwnode_handle *fwnode); const char *fwnode_get_name_prefix(const struct fwnode_handle *fwnode); + struct fwnode_handle *fwnode_get_parent(const struct fwnode_handle *fwnode); -struct fwnode_handle *fwnode_get_next_parent( - struct fwnode_handle *fwnode); +struct fwnode_handle *fwnode_get_next_parent(struct fwnode_handle *fwnode); + +#define fwnode_for_each_parent_node(fwnode, parent) \ + for (parent = fwnode_get_parent(fwnode); parent; \ + parent = fwnode_get_next_parent(parent)) + struct device *fwnode_get_next_parent_dev(struct fwnode_handle *fwnode); unsigned int fwnode_count_parents(const struct fwnode_handle *fwn); struct fwnode_handle *fwnode_get_nth_parent(struct fwnode_handle *fwn, unsigned int depth); -bool fwnode_is_ancestor_of(struct fwnode_handle *test_ancestor, - struct fwnode_handle *test_child); +bool fwnode_is_ancestor_of(struct fwnode_handle *ancestor, struct fwnode_handle *child); struct fwnode_handle *fwnode_get_next_child_node( const struct fwnode_handle *fwnode, struct fwnode_handle *child); struct fwnode_handle *fwnode_get_next_available_child_node( @@ -121,6 +125,7 @@ struct fwnode_handle *fwnode_handle_get(struct fwnode_handle *fwnode); void fwnode_handle_put(struct fwnode_handle *fwnode); int fwnode_irq_get(const struct fwnode_handle *fwnode, unsigned int index); +int fwnode_irq_get_byname(const struct fwnode_handle *fwnode, const char *name); unsigned int device_get_child_node_count(struct device *dev); @@ -382,11 +387,13 @@ bool device_dma_supported(struct device *dev); enum dev_dma_attr device_get_dma_attr(struct device *dev); -const void *device_get_match_data(struct device *dev); +const void *device_get_match_data(const struct device *dev); int device_get_phy_mode(struct device *dev); - int fwnode_get_phy_mode(struct fwnode_handle *fwnode); + +void __iomem *fwnode_iomap(struct fwnode_handle *fwnode, int index); + struct fwnode_handle *fwnode_graph_get_next_endpoint( const struct fwnode_handle *fwnode, struct fwnode_handle *prev); struct fwnode_handle * @@ -444,6 +451,11 @@ static inline void *device_connection_find_match(struct device *dev, return fwnode_connection_find_match(dev_fwnode(dev), con_id, data, match); } +int fwnode_connection_find_matches(struct fwnode_handle *fwnode, + const char *con_id, void *data, + devcon_match_fn_t match, + void **matches, unsigned int matches_len); + /* -------------------------------------------------------------------------- */ /* Software fwnode support - when HW description is incomplete or missing */ diff --git a/include/linux/pse-pd/pse.h b/include/linux/pse-pd/pse.h new file mode 100644 index 000000000000..fb724c65c77b --- /dev/null +++ b/include/linux/pse-pd/pse.h @@ -0,0 +1,129 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* +// Copyright (c) 2022 Pengutronix, Oleksij Rempel <kernel@pengutronix.de> + */ +#ifndef _LINUX_PSE_CONTROLLER_H +#define _LINUX_PSE_CONTROLLER_H + +#include <linux/ethtool.h> +#include <linux/list.h> +#include <uapi/linux/ethtool.h> + +struct phy_device; +struct pse_controller_dev; + +/** + * struct pse_control_config - PSE control/channel configuration. + * + * @admin_cotrol: set PoDL PSE admin control as described in + * IEEE 802.3-2018 30.15.1.2.1 acPoDLPSEAdminControl + */ +struct pse_control_config { + enum ethtool_podl_pse_admin_state admin_cotrol; +}; + +/** + * struct pse_control_status - PSE control/channel status. + * + * @podl_admin_state: operational state of the PoDL PSE + * functions. IEEE 802.3-2018 30.15.1.1.2 aPoDLPSEAdminState + * @podl_pw_status: power detection status of the PoDL PSE. + * IEEE 802.3-2018 30.15.1.1.3 aPoDLPSEPowerDetectionStatus: + */ +struct pse_control_status { + enum ethtool_podl_pse_admin_state podl_admin_state; + enum ethtool_podl_pse_pw_d_status podl_pw_status; +}; + +/** + * struct pse_controller_ops - PSE controller driver callbacks + * + * @ethtool_get_status: get PSE control status for ethtool interface + * @ethtool_set_config: set PSE control configuration over ethtool interface + */ +struct pse_controller_ops { + int (*ethtool_get_status)(struct pse_controller_dev *pcdev, + unsigned long id, struct netlink_ext_ack *extack, + struct pse_control_status *status); + int (*ethtool_set_config)(struct pse_controller_dev *pcdev, + unsigned long id, struct netlink_ext_ack *extack, + const struct pse_control_config *config); +}; + +struct module; +struct device_node; +struct of_phandle_args; +struct pse_control; + +/** + * struct pse_controller_dev - PSE controller entity that might + * provide multiple PSE controls + * @ops: a pointer to device specific struct pse_controller_ops + * @owner: kernel module of the PSE controller driver + * @list: internal list of PSE controller devices + * @pse_control_head: head of internal list of requested PSE controls + * @dev: corresponding driver model device struct + * @of_pse_n_cells: number of cells in PSE line specifiers + * @of_xlate: translation function to translate from specifier as found in the + * device tree to id as given to the PSE control ops + * @nr_lines: number of PSE controls in this controller device + * @lock: Mutex for serialization access to the PSE controller + */ +struct pse_controller_dev { + const struct pse_controller_ops *ops; + struct module *owner; + struct list_head list; + struct list_head pse_control_head; + struct device *dev; + int of_pse_n_cells; + int (*of_xlate)(struct pse_controller_dev *pcdev, + const struct of_phandle_args *pse_spec); + unsigned int nr_lines; + struct mutex lock; +}; + +#if IS_ENABLED(CONFIG_PSE_CONTROLLER) +int pse_controller_register(struct pse_controller_dev *pcdev); +void pse_controller_unregister(struct pse_controller_dev *pcdev); +struct device; +int devm_pse_controller_register(struct device *dev, + struct pse_controller_dev *pcdev); + +struct pse_control *of_pse_control_get(struct device_node *node); +void pse_control_put(struct pse_control *psec); + +int pse_ethtool_get_status(struct pse_control *psec, + struct netlink_ext_ack *extack, + struct pse_control_status *status); +int pse_ethtool_set_config(struct pse_control *psec, + struct netlink_ext_ack *extack, + const struct pse_control_config *config); + +#else + +static inline struct pse_control *of_pse_control_get(struct device_node *node) +{ + return ERR_PTR(-ENOENT); +} + +static inline void pse_control_put(struct pse_control *psec) +{ +} + +static inline int pse_ethtool_get_status(struct pse_control *psec, + struct netlink_ext_ack *extack, + struct pse_control_status *status) +{ + return -ENOTSUPP; +} + +static inline int pse_ethtool_set_config(struct pse_control *psec, + struct netlink_ext_ack *extack, + const struct pse_control_config *config) +{ + return -ENOTSUPP; +} + +#endif + +#endif diff --git a/include/linux/psi.h b/include/linux/psi.h index a70ca833c6d7..b029a847def1 100644 --- a/include/linux/psi.h +++ b/include/linux/psi.h @@ -6,6 +6,8 @@ #include <linux/psi_types.h> #include <linux/sched.h> #include <linux/poll.h> +#include <linux/cgroup-defs.h> +#include <linux/cgroup.h> struct seq_file; struct css_set; @@ -17,26 +19,27 @@ extern struct psi_group psi_system; void psi_init(void); -void psi_task_change(struct task_struct *task, int clear, int set); -void psi_task_switch(struct task_struct *prev, struct task_struct *next, - bool sleep); - void psi_memstall_enter(unsigned long *flags); void psi_memstall_leave(unsigned long *flags); int psi_show(struct seq_file *s, struct psi_group *group, enum psi_res res); +struct psi_trigger *psi_trigger_create(struct psi_group *group, + char *buf, enum psi_res res); +void psi_trigger_destroy(struct psi_trigger *t); + +__poll_t psi_trigger_poll(void **trigger_ptr, struct file *file, + poll_table *wait); #ifdef CONFIG_CGROUPS +static inline struct psi_group *cgroup_psi(struct cgroup *cgrp) +{ + return cgroup_ino(cgrp) == 1 ? &psi_system : cgrp->psi; +} + int psi_cgroup_alloc(struct cgroup *cgrp); void psi_cgroup_free(struct cgroup *cgrp); void cgroup_move_task(struct task_struct *p, struct css_set *to); - -struct psi_trigger *psi_trigger_create(struct psi_group *group, - char *buf, size_t nbytes, enum psi_res res); -void psi_trigger_replace(void **trigger_ptr, struct psi_trigger *t); - -__poll_t psi_trigger_poll(void **trigger_ptr, struct file *file, - poll_table *wait); +void psi_cgroup_restart(struct psi_group *group); #endif #else /* CONFIG_PSI */ @@ -58,6 +61,7 @@ static inline void cgroup_move_task(struct task_struct *p, struct css_set *to) { rcu_assign_pointer(p->cgroups, to); } +static inline void psi_cgroup_restart(struct psi_group *group) {} #endif #endif /* CONFIG_PSI */ diff --git a/include/linux/psi_types.h b/include/linux/psi_types.h index 516c0fe836fd..6e4372735068 100644 --- a/include/linux/psi_types.h +++ b/include/linux/psi_types.h @@ -16,13 +16,6 @@ enum psi_task_count { NR_MEMSTALL, NR_RUNNING, /* - * This can't have values other than 0 or 1 and could be - * implemented as a bit flag. But for now we still have room - * in the first cacheline of psi_group_cpu, and this way we - * don't have to special case any state tracking for it. - */ - NR_ONCPU, - /* * For IO and CPU stalls the presence of running/oncpu tasks * in the domain means a partial rather than a full stall. * For memory it's not so simple because of page reclaimers: @@ -32,22 +25,27 @@ enum psi_task_count { * threads and memstall ones. */ NR_MEMSTALL_RUNNING, - NR_PSI_TASK_COUNTS = 5, + NR_PSI_TASK_COUNTS = 4, }; /* Task state bitmasks */ #define TSK_IOWAIT (1 << NR_IOWAIT) #define TSK_MEMSTALL (1 << NR_MEMSTALL) #define TSK_RUNNING (1 << NR_RUNNING) -#define TSK_ONCPU (1 << NR_ONCPU) #define TSK_MEMSTALL_RUNNING (1 << NR_MEMSTALL_RUNNING) +/* Only one task can be scheduled, no corresponding task count */ +#define TSK_ONCPU (1 << NR_PSI_TASK_COUNTS) + /* Resources that workloads could be stalled on */ enum psi_res { PSI_IO, PSI_MEM, PSI_CPU, - NR_PSI_RESOURCES = 3, +#ifdef CONFIG_IRQ_TIME_ACCOUNTING + PSI_IRQ, +#endif + NR_PSI_RESOURCES, }; /* @@ -63,11 +61,17 @@ enum psi_states { PSI_MEM_FULL, PSI_CPU_SOME, PSI_CPU_FULL, +#ifdef CONFIG_IRQ_TIME_ACCOUNTING + PSI_IRQ_FULL, +#endif /* Only per-CPU, to weigh the CPU in the global average: */ PSI_NONIDLE, - NR_PSI_STATES = 7, + NR_PSI_STATES, }; +/* Use one bit in the state mask to track TSK_ONCPU */ +#define PSI_ONCPU (1 << NR_PSI_STATES) + enum psi_aggregators { PSI_AVGS = 0, PSI_POLL, @@ -142,11 +146,14 @@ struct psi_trigger { */ u64 last_event_time; - /* Refcounting to prevent premature destruction */ - struct kref refcount; + /* Deferred event(s) from previous ratelimit window */ + bool pending_event; }; struct psi_group { + struct psi_group *parent; + bool enabled; + /* Protects data used by the aggregator */ struct mutex avgs_lock; @@ -188,6 +195,8 @@ struct psi_group { #else /* CONFIG_PSI */ +#define NR_PSI_RESOURCES 0 + struct psi_group { }; #endif /* CONFIG_PSI */ diff --git a/include/linux/pstore.h b/include/linux/pstore.h index eb93a54cff31..638507a3c8ff 100644 --- a/include/linux/pstore.h +++ b/include/linux/pstore.h @@ -14,7 +14,7 @@ #include <linux/errno.h> #include <linux/kmsg_dump.h> #include <linux/mutex.h> -#include <linux/semaphore.h> +#include <linux/spinlock.h> #include <linux/time.h> #include <linux/types.h> @@ -57,6 +57,9 @@ struct pstore_info; * @size: size of @buf * @ecc_notice_size: * ECC information for @buf + * @priv: pointer for backend specific use, will be + * kfree()d by the pstore core if non-NULL + * when the record is freed. * * Valid for PSTORE_TYPE_DMESG @type: * @@ -74,6 +77,7 @@ struct pstore_record { char *buf; ssize_t size; ssize_t ecc_notice_size; + void *priv; int count; enum kmsg_dump_reason reason; @@ -87,7 +91,7 @@ struct pstore_record { * @owner: module which is responsible for this backend driver * @name: name of the backend driver * - * @buf_lock: semaphore to serialize access to @buf + * @buf_lock: spinlock to serialize access to @buf * @buf: preallocated crash dump buffer * @bufsize: size of @buf available for crash dump bytes (must match * smallest number of bytes available for writing to a @@ -178,7 +182,7 @@ struct pstore_info { struct module *owner; const char *name; - struct semaphore buf_lock; + spinlock_t buf_lock; char *buf; size_t bufsize; diff --git a/include/linux/ptp_classify.h b/include/linux/ptp_classify.h index 9afd34a2d36c..2b6ea36ad162 100644 --- a/include/linux/ptp_classify.h +++ b/include/linux/ptp_classify.h @@ -43,6 +43,9 @@ #define OFF_PTP_SOURCE_UUID 22 /* PTPv1 only */ #define OFF_PTP_SEQUENCE_ID 30 +/* PTP header flag fields */ +#define PTP_FLAG_TWOSTEP BIT(1) + /* Below defines should actually be removed at some point in time. */ #define IP6_HLEN 40 #define UDP_HLEN 8 @@ -126,6 +129,17 @@ static inline u8 ptp_get_msgtype(const struct ptp_header *hdr, return msgtype; } +/** + * ptp_msg_is_sync - Evaluates whether the given skb is a PTP Sync message + * @skb: packet buffer + * @type: type of the packet (see ptp_classify_raw()) + * + * This function evaluates whether the given skb is a PTP Sync message. + * + * Return: true if sync message, false otherwise + */ +bool ptp_msg_is_sync(struct sk_buff *skb, unsigned int type); + void __init ptp_classifier_init(void); #else static inline void ptp_classifier_init(void) @@ -148,5 +162,9 @@ static inline u8 ptp_get_msgtype(const struct ptp_header *hdr, */ return PTP_MSGTYPE_SYNC; } +static inline bool ptp_msg_is_sync(struct sk_buff *skb, unsigned int type) +{ + return false; +} #endif #endif /* _PTP_CLASSIFY_H_ */ diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h index 554454cb8693..92b44161408e 100644 --- a/include/linux/ptp_clock_kernel.h +++ b/include/linux/ptp_clock_kernel.h @@ -108,6 +108,32 @@ struct ptp_system_timestamp { * @settime64: Set the current time on the hardware clock. * parameter ts: Time value to set. * + * @getcycles64: Reads the current free running cycle counter from the hardware + * clock. + * If @getcycles64 and @getcyclesx64 are not supported, then + * @gettime64 or @gettimex64 will be used as default + * implementation. + * parameter ts: Holds the result. + * + * @getcyclesx64: Reads the current free running cycle counter from the + * hardware clock and optionally also the system clock. + * If @getcycles64 and @getcyclesx64 are not supported, then + * @gettimex64 will be used as default implementation if + * available. + * parameter ts: Holds the PHC timestamp. + * parameter sts: If not NULL, it holds a pair of timestamps + * from the system clock. The first reading is made right before + * reading the lowest bits of the PHC timestamp and the second + * reading immediately follows that. + * + * @getcrosscycles: Reads the current free running cycle counter from the + * hardware clock and system clock simultaneously. + * If @getcycles64 and @getcyclesx64 are not supported, then + * @getcrosststamp will be used as default implementation if + * available. + * parameter cts: Contains timestamp (device,system) pair, + * where system time is realtime and monotonic. + * * @enable: Request driver to enable or disable an ancillary feature. * parameter request: Desired resource to enable or disable. * parameter on: Caller passes one to enable or zero to disable. @@ -155,6 +181,11 @@ struct ptp_clock_info { int (*getcrosststamp)(struct ptp_clock_info *ptp, struct system_device_crosststamp *cts); int (*settime64)(struct ptp_clock_info *p, const struct timespec64 *ts); + int (*getcycles64)(struct ptp_clock_info *ptp, struct timespec64 *ts); + int (*getcyclesx64)(struct ptp_clock_info *ptp, struct timespec64 *ts, + struct ptp_system_timestamp *sts); + int (*getcrosscycles)(struct ptp_clock_info *ptp, + struct system_device_crosststamp *cts); int (*enable)(struct ptp_clock_info *ptp, struct ptp_clock_request *request, int on); int (*verify)(struct ptp_clock_info *ptp, unsigned int pin, @@ -321,6 +352,10 @@ static inline int ptp_clock_index(struct ptp_clock *ptp) static inline int ptp_find_pin(struct ptp_clock *ptp, enum ptp_pin_function func, unsigned int chan) { return -1; } +static inline int ptp_find_pin_unlocked(struct ptp_clock *ptp, + enum ptp_pin_function func, + unsigned int chan) +{ return -1; } static inline int ptp_schedule_worker(struct ptp_clock *ptp, unsigned long delay) { return -EOPNOTSUPP; } @@ -349,17 +384,16 @@ int ptp_get_vclocks_index(int pclock_index, int **vclock_index); /** * ptp_convert_timestamp() - convert timestamp to a ptp vclock time * - * @hwtstamps: skb_shared_hwtstamps structure pointer + * @hwtstamp: timestamp * @vclock_index: phc index of ptp vclock. * * Returns converted timestamp, or 0 on error. */ -ktime_t ptp_convert_timestamp(const struct skb_shared_hwtstamps *hwtstamps, - int vclock_index); +ktime_t ptp_convert_timestamp(const ktime_t *hwtstamp, int vclock_index); #else static inline int ptp_get_vclocks_index(int pclock_index, int **vclock_index) { return 0; } -static inline ktime_t ptp_convert_timestamp(const struct skb_shared_hwtstamps *hwtstamps, +static inline ktime_t ptp_convert_timestamp(const ktime_t *hwtstamp, int vclock_index) { return 0; } diff --git a/include/linux/ptp_kvm.h b/include/linux/ptp_kvm.h index f960a719f0d5..c2e28deef33a 100644 --- a/include/linux/ptp_kvm.h +++ b/include/linux/ptp_kvm.h @@ -8,6 +8,8 @@ #ifndef _PTP_KVM_H_ #define _PTP_KVM_H_ +#include <linux/types.h> + struct timespec64; struct clocksource; diff --git a/include/linux/ptp_pch.h b/include/linux/ptp_pch.h index 51818198c292..7ba643b62c15 100644 --- a/include/linux/ptp_pch.h +++ b/include/linux/ptp_pch.h @@ -10,6 +10,10 @@ #ifndef _PTP_PCH_H_ #define _PTP_PCH_H_ +#include <linux/types.h> + +struct pci_dev; + void pch_ch_control_write(struct pci_dev *pdev, u32 val); u32 pch_ch_event_read(struct pci_dev *pdev); void pch_ch_event_write(struct pci_dev *pdev, u32 val); diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index 8aee2945ff08..c952c5ba8fab 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -30,7 +30,6 @@ extern int ptrace_access_vm(struct task_struct *tsk, unsigned long addr, #define PT_SEIZED 0x00010000 /* SEIZE used, enable new behavior */ #define PT_PTRACED 0x00000001 -#define PT_DTRACE 0x00000002 /* delayed trace (used on m68k, i386) */ #define PT_OPT_FLAG_SHIFT 3 /* PT_TRACE_* event enable flags */ @@ -47,12 +46,6 @@ extern int ptrace_access_vm(struct task_struct *tsk, unsigned long addr, #define PT_EXITKILL (PTRACE_O_EXITKILL << PT_OPT_FLAG_SHIFT) #define PT_SUSPEND_SECCOMP (PTRACE_O_SUSPEND_SECCOMP << PT_OPT_FLAG_SHIFT) -/* single stepping state bits (used on ARM and PA-RISC) */ -#define PT_SINGLESTEP_BIT 31 -#define PT_SINGLESTEP (1<<PT_SINGLESTEP_BIT) -#define PT_BLOCKSTEP_BIT 30 -#define PT_BLOCKSTEP (1<<PT_BLOCKSTEP_BIT) - extern long arch_ptrace(struct task_struct *child, long request, unsigned long addr, unsigned long data); extern int ptrace_readdata(struct task_struct *tsk, unsigned long src, char __user *dst, int len); @@ -60,7 +53,7 @@ extern int ptrace_writedata(struct task_struct *tsk, char __user *src, unsigned extern void ptrace_disable(struct task_struct *); extern int ptrace_request(struct task_struct *child, long request, unsigned long addr, unsigned long data); -extern void ptrace_notify(int exit_code); +extern int ptrace_notify(int exit_code, unsigned long message); extern void __ptrace_link(struct task_struct *child, struct task_struct *new_parent, const struct cred *ptracer_cred); @@ -155,8 +148,7 @@ static inline bool ptrace_event_enabled(struct task_struct *task, int event) static inline void ptrace_event(int event, unsigned long message) { if (unlikely(ptrace_event_enabled(current, event))) { - current->ptrace_message = message; - ptrace_notify((event << 8) | SIGTRAP); + ptrace_notify((event << 8) | SIGTRAP, message); } else if (event == PTRACE_EVENT_EXEC) { /* legacy EXEC report via SIGTRAP */ if ((current->ptrace & (PT_PTRACED|PT_SEIZED)) == PT_PTRACED) @@ -413,4 +405,80 @@ static inline void user_single_step_report(struct pt_regs *regs) extern int task_current_syscall(struct task_struct *target, struct syscall_info *info); extern void sigaction_compat_abi(struct k_sigaction *act, struct k_sigaction *oact); + +/* + * ptrace report for syscall entry and exit looks identical. + */ +static inline int ptrace_report_syscall(unsigned long message) +{ + int ptrace = current->ptrace; + int signr; + + if (!(ptrace & PT_PTRACED)) + return 0; + + signr = ptrace_notify(SIGTRAP | ((ptrace & PT_TRACESYSGOOD) ? 0x80 : 0), + message); + + /* + * this isn't the same as continuing with a signal, but it will do + * for normal use. strace only continues with a signal if the + * stopping signal is not SIGTRAP. -brl + */ + if (signr) + send_sig(signr, current, 1); + + return fatal_signal_pending(current); +} + +/** + * ptrace_report_syscall_entry - task is about to attempt a system call + * @regs: user register state of current task + * + * This will be called if %SYSCALL_WORK_SYSCALL_TRACE or + * %SYSCALL_WORK_SYSCALL_EMU have been set, when the current task has just + * entered the kernel for a system call. Full user register state is + * available here. Changing the values in @regs can affect the system + * call number and arguments to be tried. It is safe to block here, + * preventing the system call from beginning. + * + * Returns zero normally, or nonzero if the calling arch code should abort + * the system call. That must prevent normal entry so no system call is + * made. If @task ever returns to user mode after this, its register state + * is unspecified, but should be something harmless like an %ENOSYS error + * return. It should preserve enough information so that syscall_rollback() + * can work (see asm-generic/syscall.h). + * + * Called without locks, just after entering kernel mode. + */ +static inline __must_check int ptrace_report_syscall_entry( + struct pt_regs *regs) +{ + return ptrace_report_syscall(PTRACE_EVENTMSG_SYSCALL_ENTRY); +} + +/** + * ptrace_report_syscall_exit - task has just finished a system call + * @regs: user register state of current task + * @step: nonzero if simulating single-step or block-step + * + * This will be called if %SYSCALL_WORK_SYSCALL_TRACE has been set, when + * the current task has just finished an attempted system call. Full + * user register state is available here. It is safe to block here, + * preventing signals from being processed. + * + * If @step is nonzero, this report is also in lieu of the normal + * trap that would follow the system call instruction because + * user_enable_block_step() or user_enable_single_step() was used. + * In this case, %SYSCALL_WORK_SYSCALL_TRACE might not be set. + * + * Called without locks, just before checking for pending signals. + */ +static inline void ptrace_report_syscall_exit(struct pt_regs *regs, int step) +{ + if (step) + user_single_step_report(regs); + else + ptrace_report_syscall(PTRACE_EVENTMSG_SYSCALL_EXIT); +} #endif diff --git a/include/linux/ptrace_api.h b/include/linux/ptrace_api.h new file mode 100644 index 000000000000..26e7d275ad8d --- /dev/null +++ b/include/linux/ptrace_api.h @@ -0,0 +1 @@ +#include <linux/ptrace.h> diff --git a/include/linux/pwm.h b/include/linux/pwm.h index 9771a0761a40..d70c6e5a839d 100644 --- a/include/linux/pwm.h +++ b/include/linux/pwm.h @@ -6,9 +6,6 @@ #include <linux/mutex.h> #include <linux/of.h> -struct pwm_capture; -struct seq_file; - struct pwm_chip; /** @@ -252,6 +249,16 @@ pwm_set_relative_duty_cycle(struct pwm_state *state, unsigned int duty_cycle, } /** + * struct pwm_capture - PWM capture data + * @period: period of the PWM signal (in nanoseconds) + * @duty_cycle: duty cycle of the PWM signal (in nanoseconds) + */ +struct pwm_capture { + unsigned int period; + unsigned int duty_cycle; +}; + +/** * struct pwm_ops - PWM controller operations * @request: optional hook for requesting a PWM * @free: optional hook for freeing a PWM @@ -261,10 +268,6 @@ pwm_set_relative_duty_cycle(struct pwm_state *state, unsigned int duty_cycle, * called once per PWM device when the PWM chip is * registered. * @owner: helps prevent removal of modules exporting active PWMs - * @config: configure duty cycles and period length for this PWM - * @set_polarity: configure the polarity of this PWM - * @enable: enable PWM output toggling - * @disable: disable PWM output toggling */ struct pwm_ops { int (*request)(struct pwm_chip *chip, struct pwm_device *pwm); @@ -276,14 +279,6 @@ struct pwm_ops { void (*get_state)(struct pwm_chip *chip, struct pwm_device *pwm, struct pwm_state *state); struct module *owner; - - /* Only used by legacy drivers */ - int (*config)(struct pwm_chip *chip, struct pwm_device *pwm, - int duty_ns, int period_ns); - int (*set_polarity)(struct pwm_chip *chip, struct pwm_device *pwm, - enum pwm_polarity polarity); - int (*enable)(struct pwm_chip *chip, struct pwm_device *pwm); - void (*disable)(struct pwm_chip *chip, struct pwm_device *pwm); }; /** @@ -312,16 +307,6 @@ struct pwm_chip { struct pwm_device *pwms; }; -/** - * struct pwm_capture - PWM capture data - * @period: period of the PWM signal (in nanoseconds) - * @duty_cycle: duty cycle of the PWM signal (in nanoseconds) - */ -struct pwm_capture { - unsigned int period; - unsigned int duty_cycle; -}; - #if IS_ENABLED(CONFIG_PWM) /* PWM user APIs */ struct pwm_device *pwm_request(int pwm_id, const char *label); @@ -418,13 +403,9 @@ struct pwm_device *of_pwm_single_xlate(struct pwm_chip *pc, const struct of_phandle_args *args); struct pwm_device *pwm_get(struct device *dev, const char *con_id); -struct pwm_device *of_pwm_get(struct device *dev, struct device_node *np, - const char *con_id); void pwm_put(struct pwm_device *pwm); struct pwm_device *devm_pwm_get(struct device *dev, const char *con_id); -struct pwm_device *devm_of_pwm_get(struct device *dev, struct device_node *np, - const char *con_id); struct pwm_device *devm_fwnode_pwm_get(struct device *dev, struct fwnode_handle *fwnode, const char *con_id); @@ -512,14 +493,6 @@ static inline struct pwm_device *pwm_get(struct device *dev, return ERR_PTR(-ENODEV); } -static inline struct pwm_device *of_pwm_get(struct device *dev, - struct device_node *np, - const char *con_id) -{ - might_sleep(); - return ERR_PTR(-ENODEV); -} - static inline void pwm_put(struct pwm_device *pwm) { might_sleep(); @@ -532,14 +505,6 @@ static inline struct pwm_device *devm_pwm_get(struct device *dev, return ERR_PTR(-ENODEV); } -static inline struct pwm_device *devm_of_pwm_get(struct device *dev, - struct device_node *np, - const char *con_id) -{ - might_sleep(); - return ERR_PTR(-ENODEV); -} - static inline struct pwm_device * devm_fwnode_pwm_get(struct device *dev, struct fwnode_handle *fwnode, const char *con_id) diff --git a/include/linux/qcom_scm.h b/include/linux/qcom_scm.h index 81cad9e1e412..f8335644a01a 100644 --- a/include/linux/qcom_scm.h +++ b/include/linux/qcom_scm.h @@ -63,13 +63,21 @@ enum qcom_scm_ice_cipher { extern bool qcom_scm_is_available(void); -extern int qcom_scm_set_cold_boot_addr(void *entry, const cpumask_t *cpus); -extern int qcom_scm_set_warm_boot_addr(void *entry, const cpumask_t *cpus); +extern int qcom_scm_set_cold_boot_addr(void *entry); +extern int qcom_scm_set_warm_boot_addr(void *entry); extern void qcom_scm_cpu_power_down(u32 flags); extern int qcom_scm_set_remote_state(u32 state, u32 id); +struct qcom_scm_pas_metadata { + void *ptr; + dma_addr_t phys; + ssize_t size; +}; + extern int qcom_scm_pas_init_image(u32 peripheral, const void *metadata, - size_t size); + size_t size, + struct qcom_scm_pas_metadata *ctx); +void qcom_scm_pas_metadata_release(struct qcom_scm_pas_metadata *ctx); extern int qcom_scm_pas_mem_setup(u32 peripheral, phys_addr_t addr, phys_addr_t size); extern int qcom_scm_pas_auth_and_reset(u32 peripheral); @@ -83,6 +91,7 @@ extern bool qcom_scm_restore_sec_cfg_available(void); extern int qcom_scm_restore_sec_cfg(u32 device_id, u32 spare); extern int qcom_scm_iommu_secure_ptbl_size(u32 spare, size_t *size); extern int qcom_scm_iommu_secure_ptbl_init(u64 addr, u32 size, u32 spare); +extern int qcom_scm_iommu_set_cp_pool_size(u32 spare, u32 size); extern int qcom_scm_mem_protect_video_var(u32 cp_start, u32 cp_size, u32 cp_nonpixel_start, u32 cp_nonpixel_size); @@ -107,6 +116,7 @@ extern bool qcom_scm_hdcp_available(void); extern int qcom_scm_hdcp_req(struct qcom_scm_hdcp_req *req, u32 req_cnt, u32 *resp); +extern int qcom_scm_iommu_set_pt_format(u32 sec_id, u32 ctx_num, u32 pt_fmt); extern int qcom_scm_qsmmu500_wait_safe_toggle(bool en); extern int qcom_scm_lmh_dcvsh(u32 payload_fn, u32 payload_reg, u32 payload_val, diff --git a/include/linux/qed/qed_fcoe_if.h b/include/linux/qed/qed_fcoe_if.h index 16752eca5cbd..90e3045b2dcb 100644 --- a/include/linux/qed/qed_fcoe_if.h +++ b/include/linux/qed/qed_fcoe_if.h @@ -76,7 +76,7 @@ void qed_fcoe_set_pf_params(struct qed_dev *cdev, * @fill_dev_info: fills FCoE specific information * @param cdev * @param info - * @return 0 on sucesss, otherwise error value. + * @return 0 on success, otherwise error value. * @register_ops: register FCoE operations * @param cdev * @param ops - specified using qed_iscsi_cb_ops @@ -96,7 +96,7 @@ void qed_fcoe_set_pf_params(struct qed_dev *cdev, * connection. * @param p_doorbell - qed will fill the address of the * doorbell. - * return 0 on sucesss, otherwise error value. + * return 0 on success, otherwise error value. * @release_conn: release a previously acquired fcoe connection * @param cdev * @param handle - the connection handle. diff --git a/include/linux/qed/qed_iscsi_if.h b/include/linux/qed/qed_iscsi_if.h index 494cdc3cd840..fbf7973ae9ba 100644 --- a/include/linux/qed/qed_iscsi_if.h +++ b/include/linux/qed/qed_iscsi_if.h @@ -133,7 +133,7 @@ struct qed_iscsi_cb_ops { * @fill_dev_info: fills iSCSI specific information * @param cdev * @param info - * @return 0 on sucesss, otherwise error value. + * @return 0 on success, otherwise error value. * @register_ops: register iscsi operations * @param cdev * @param ops - specified using qed_iscsi_cb_ops @@ -152,7 +152,7 @@ struct qed_iscsi_cb_ops { * connection. * @param p_doorbell - qed will fill the address of the * doorbell. - * @return 0 on sucesss, otherwise error value. + * @return 0 on success, otherwise error value. * @release_conn: release a previously acquired iscsi connection * @param cdev * @param handle - the connection handle. diff --git a/include/linux/qed/qed_nvmetcp_if.h b/include/linux/qed/qed_nvmetcp_if.h index 1d51df347560..bbfbfba51f37 100644 --- a/include/linux/qed/qed_nvmetcp_if.h +++ b/include/linux/qed/qed_nvmetcp_if.h @@ -132,7 +132,7 @@ struct nvmetcp_task_params { * connection. * @param p_doorbell - qed will fill the address of the * doorbell. - * @return 0 on sucesss, otherwise error value. + * @return 0 on success, otherwise error value. * @release_conn: release a previously acquired nvmetcp connection * @param cdev * @param handle - the connection handle. diff --git a/include/linux/qed/qed_nvmetcp_ip_services_if.h b/include/linux/qed/qed_nvmetcp_ip_services_if.h deleted file mode 100644 index 3604aee53796..000000000000 --- a/include/linux/qed/qed_nvmetcp_ip_services_if.h +++ /dev/null @@ -1,29 +0,0 @@ -/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ -/* - * Copyright 2021 Marvell. All rights reserved. - */ - -#ifndef _QED_IP_SERVICES_IF_H -#define _QED_IP_SERVICES_IF_H - -#include <linux/types.h> -#include <net/route.h> -#include <net/ip6_route.h> -#include <linux/inetdevice.h> - -int qed_route_ipv4(struct sockaddr_storage *local_addr, - struct sockaddr_storage *remote_addr, - struct sockaddr *hardware_address, - struct net_device **ndev); -int qed_route_ipv6(struct sockaddr_storage *local_addr, - struct sockaddr_storage *remote_addr, - struct sockaddr *hardware_address, - struct net_device **ndev); -void qed_vlan_get_ndev(struct net_device **ndev, u16 *vlan_id); -struct pci_dev *qed_validate_ndev(struct net_device *ndev); -void qed_return_tcp_port(struct socket *sock); -int qed_fetch_tcp_port(struct sockaddr_storage local_ip_addr, - struct socket **sock, u16 *port); -__be16 qed_get_in_port(struct sockaddr_storage *sa); - -#endif /* _QED_IP_SERVICES_IF_H */ diff --git a/include/linux/quota.h b/include/linux/quota.h index 18ebd39c9487..fd692b4a41d5 100644 --- a/include/linux/quota.h +++ b/include/linux/quota.h @@ -91,7 +91,7 @@ extern bool qid_valid(struct kqid qid); * * When there is no mapping defined for the user-namespace, type, * qid tuple an invalid kqid is returned. Callers are expected to - * test for and handle handle invalid kqids being returned. + * test for and handle invalid kqids being returned. * Invalid kqids may be tested for using qid_valid(). */ static inline struct kqid make_kqid(struct user_namespace *from, diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h index a0f6668924d3..0d8625d71733 100644 --- a/include/linux/quotaops.h +++ b/include/linux/quotaops.h @@ -20,11 +20,12 @@ static inline struct quota_info *sb_dqopt(struct super_block *sb) } /* i_mutex must being held */ -static inline bool is_quota_modification(struct inode *inode, struct iattr *ia) +static inline bool is_quota_modification(struct user_namespace *mnt_userns, + struct inode *inode, struct iattr *ia) { - return (ia->ia_valid & ATTR_SIZE) || - (ia->ia_valid & ATTR_UID && !uid_eq(ia->ia_uid, inode->i_uid)) || - (ia->ia_valid & ATTR_GID && !gid_eq(ia->ia_gid, inode->i_gid)); + return ((ia->ia_valid & ATTR_SIZE) || + i_uid_needs_update(mnt_userns, ia, inode) || + i_gid_needs_update(mnt_userns, ia, inode)); } #if defined(CONFIG_QUOTA) @@ -115,7 +116,8 @@ int dquot_set_dqblk(struct super_block *sb, struct kqid id, struct qc_dqblk *di); int __dquot_transfer(struct inode *inode, struct dquot **transfer_to); -int dquot_transfer(struct inode *inode, struct iattr *iattr); +int dquot_transfer(struct user_namespace *mnt_userns, struct inode *inode, + struct iattr *iattr); static inline struct mem_dqinfo *sb_dqinfo(struct super_block *sb, int type) { @@ -234,7 +236,8 @@ static inline void dquot_free_inode(struct inode *inode) { } -static inline int dquot_transfer(struct inode *inode, struct iattr *iattr) +static inline int dquot_transfer(struct user_namespace *mnt_userns, + struct inode *inode, struct iattr *iattr) { return 0; } diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index f7c1d21c2f39..eae67015ce51 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -9,7 +9,7 @@ #define _LINUX_RADIX_TREE_H #include <linux/bitops.h> -#include <linux/gfp.h> +#include <linux/gfp_types.h> #include <linux/list.h> #include <linux/lockdep.h> #include <linux/math.h> diff --git a/include/linux/raid/pq.h b/include/linux/raid/pq.h index 154e954b711d..d6e5a1feb947 100644 --- a/include/linux/raid/pq.h +++ b/include/linux/raid/pq.h @@ -81,7 +81,7 @@ struct raid6_calls { void (*xor_syndrome)(int, int, int, size_t, void **); int (*valid)(void); /* Returns 1 if this routine set is usable */ const char *name; /* Name of this routine set */ - int prefer; /* Has special performance attribute */ + int priority; /* Relative priority ranking if non-zero */ }; /* Selected algorithm */ diff --git a/include/linux/raid/xor.h b/include/linux/raid/xor.h index 2a9fee8ddae3..51b811b62322 100644 --- a/include/linux/raid/xor.h +++ b/include/linux/raid/xor.h @@ -11,13 +11,20 @@ struct xor_block_template { struct xor_block_template *next; const char *name; int speed; - void (*do_2)(unsigned long, unsigned long *, unsigned long *); - void (*do_3)(unsigned long, unsigned long *, unsigned long *, - unsigned long *); - void (*do_4)(unsigned long, unsigned long *, unsigned long *, - unsigned long *, unsigned long *); - void (*do_5)(unsigned long, unsigned long *, unsigned long *, - unsigned long *, unsigned long *, unsigned long *); + void (*do_2)(unsigned long, unsigned long * __restrict, + const unsigned long * __restrict); + void (*do_3)(unsigned long, unsigned long * __restrict, + const unsigned long * __restrict, + const unsigned long * __restrict); + void (*do_4)(unsigned long, unsigned long * __restrict, + const unsigned long * __restrict, + const unsigned long * __restrict, + const unsigned long * __restrict); + void (*do_5)(unsigned long, unsigned long * __restrict, + const unsigned long * __restrict, + const unsigned long * __restrict, + const unsigned long * __restrict, + const unsigned long * __restrict); }; #endif diff --git a/include/linux/random.h b/include/linux/random.h index c45b2693e51f..147a5e0d0b8e 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -1,9 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* - * include/linux/random.h - * - * Include file for the random number generator. - */ + #ifndef _LINUX_RANDOM_H #define _LINUX_RANDOM_H @@ -14,47 +10,38 @@ #include <uapi/linux/random.h> -struct random_ready_callback { - struct list_head list; - void (*func)(struct random_ready_callback *rdy); - struct module *owner; -}; +struct notifier_block; -extern void add_device_randomness(const void *, unsigned int); -extern void add_bootloader_randomness(const void *, unsigned int); +void add_device_randomness(const void *buf, size_t len); +void __init add_bootloader_randomness(const void *buf, size_t len); +void add_input_randomness(unsigned int type, unsigned int code, + unsigned int value) __latent_entropy; +void add_interrupt_randomness(int irq) __latent_entropy; +void add_hwgenerator_randomness(const void *buf, size_t len, size_t entropy); #if defined(LATENT_ENTROPY_PLUGIN) && !defined(__CHECKER__) static inline void add_latent_entropy(void) { - add_device_randomness((const void *)&latent_entropy, - sizeof(latent_entropy)); + add_device_randomness((const void *)&latent_entropy, sizeof(latent_entropy)); } #else -static inline void add_latent_entropy(void) {} +static inline void add_latent_entropy(void) { } #endif -extern void add_input_randomness(unsigned int type, unsigned int code, - unsigned int value) __latent_entropy; -extern void add_interrupt_randomness(int irq) __latent_entropy; - -extern void get_random_bytes(void *buf, int nbytes); -extern int wait_for_random_bytes(void); -extern int __init rand_initialize(void); -extern bool rng_is_initialized(void); -extern int add_random_ready_callback(struct random_ready_callback *rdy); -extern void del_random_ready_callback(struct random_ready_callback *rdy); -extern int __must_check get_random_bytes_arch(void *buf, int nbytes); - -#ifndef MODULE -extern const struct file_operations random_fops, urandom_fops; +#if IS_ENABLED(CONFIG_VMGENID) +void add_vmfork_randomness(const void *unique_vm_id, size_t len); +int register_random_vmfork_notifier(struct notifier_block *nb); +int unregister_random_vmfork_notifier(struct notifier_block *nb); +#else +static inline int register_random_vmfork_notifier(struct notifier_block *nb) { return 0; } +static inline int unregister_random_vmfork_notifier(struct notifier_block *nb) { return 0; } #endif +void get_random_bytes(void *buf, size_t len); +u8 get_random_u8(void); +u16 get_random_u16(void); u32 get_random_u32(void); u64 get_random_u64(void); -static inline unsigned int get_random_int(void) -{ - return get_random_u32(); -} static inline unsigned long get_random_long(void) { #if BITS_PER_LONG == 64 @@ -80,36 +67,38 @@ static inline unsigned long get_random_long(void) static inline unsigned long get_random_canary(void) { - unsigned long val = get_random_long(); - - return val & CANARY_MASK; + return get_random_long() & CANARY_MASK; } +void __init random_init_early(const char *command_line); +void __init random_init(void); +bool rng_is_initialized(void); +int wait_for_random_bytes(void); + /* Calls wait_for_random_bytes() and then calls get_random_bytes(buf, nbytes). * Returns the result of the call to wait_for_random_bytes. */ -static inline int get_random_bytes_wait(void *buf, int nbytes) +static inline int get_random_bytes_wait(void *buf, size_t nbytes) { int ret = wait_for_random_bytes(); get_random_bytes(buf, nbytes); return ret; } -#define declare_get_random_var_wait(var) \ - static inline int get_random_ ## var ## _wait(var *out) { \ +#define declare_get_random_var_wait(name, ret_type) \ + static inline int get_random_ ## name ## _wait(ret_type *out) { \ int ret = wait_for_random_bytes(); \ if (unlikely(ret)) \ return ret; \ - *out = get_random_ ## var(); \ + *out = get_random_ ## name(); \ return 0; \ } -declare_get_random_var_wait(u32) -declare_get_random_var_wait(u64) -declare_get_random_var_wait(int) -declare_get_random_var_wait(long) +declare_get_random_var_wait(u8, u8) +declare_get_random_var_wait(u16, u16) +declare_get_random_var_wait(u32, u32) +declare_get_random_var_wait(u64, u32) +declare_get_random_var_wait(long, unsigned long) #undef declare_get_random_var -unsigned long randomize_page(unsigned long start, unsigned long range); - /* * This is designed to be standalone for just prandom * users, but for now we include it from <linux/random.h> @@ -117,45 +106,35 @@ unsigned long randomize_page(unsigned long start, unsigned long range); */ #include <linux/prandom.h> -#ifdef CONFIG_ARCH_RANDOM -# include <asm/archrandom.h> -#else -static inline bool __must_check arch_get_random_long(unsigned long *v) -{ - return false; -} -static inline bool __must_check arch_get_random_int(unsigned int *v) -{ - return false; -} -static inline bool __must_check arch_get_random_seed_long(unsigned long *v) -{ - return false; -} -static inline bool __must_check arch_get_random_seed_int(unsigned int *v) -{ - return false; -} -#endif +#include <asm/archrandom.h> /* * Called from the boot CPU during startup; not valid to call once * secondary CPUs are up and preemption is possible. */ -#ifndef arch_get_random_seed_long_early -static inline bool __init arch_get_random_seed_long_early(unsigned long *v) +#ifndef arch_get_random_seed_longs_early +static inline size_t __init arch_get_random_seed_longs_early(unsigned long *v, size_t max_longs) { WARN_ON(system_state != SYSTEM_BOOTING); - return arch_get_random_seed_long(v); + return arch_get_random_seed_longs(v, max_longs); } #endif -#ifndef arch_get_random_long_early -static inline bool __init arch_get_random_long_early(unsigned long *v) +#ifndef arch_get_random_longs_early +static inline bool __init arch_get_random_longs_early(unsigned long *v, size_t max_longs) { WARN_ON(system_state != SYSTEM_BOOTING); - return arch_get_random_long(v); + return arch_get_random_longs(v, max_longs); } #endif +#ifdef CONFIG_SMP +int random_prepare_cpu(unsigned int cpu); +int random_online_cpu(unsigned int cpu); +#endif + +#ifndef MODULE +extern const struct file_operations random_fops, urandom_fops; +#endif + #endif /* _LINUX_RANDOM_H */ diff --git a/include/linux/randomize_kstack.h b/include/linux/randomize_kstack.h index bebc911161b6..5d868505a94e 100644 --- a/include/linux/randomize_kstack.h +++ b/include/linux/randomize_kstack.h @@ -2,6 +2,7 @@ #ifndef _LINUX_RANDOMIZE_KSTACK_H #define _LINUX_RANDOMIZE_KSTACK_H +#ifdef CONFIG_RANDOMIZE_KSTACK_OFFSET #include <linux/kernel.h> #include <linux/jump_label.h> #include <linux/percpu-defs.h> @@ -16,8 +17,20 @@ DECLARE_PER_CPU(u32, kstack_offset); * alignment. Also, since this use is being explicitly masked to a max of * 10 bits, stack-clash style attacks are unlikely. For more details see * "VLAs" in Documentation/process/deprecated.rst + * + * The normal __builtin_alloca() is initialized with INIT_STACK_ALL (currently + * only with Clang and not GCC). Initializing the unused area on each syscall + * entry is expensive, and generating an implicit call to memset() may also be + * problematic (such as in noinstr functions). Therefore, if the compiler + * supports it (which it should if it initializes allocas), always use the + * "uninitialized" variant of the builtin. */ -void *__builtin_alloca(size_t size); +#if __has_builtin(__builtin_alloca_uninitialized) +#define __kstack_alloca __builtin_alloca_uninitialized +#else +#define __kstack_alloca __builtin_alloca +#endif + /* * Use, at most, 10 bits of entropy. We explicitly cap this to keep the * "VLA" from being unbounded (see above). 10 bits leaves enough room for @@ -27,21 +40,42 @@ void *__builtin_alloca(size_t size); */ #define KSTACK_OFFSET_MAX(x) ((x) & 0x3FF) -/* - * These macros must be used during syscall entry when interrupts and +/** + * add_random_kstack_offset - Increase stack utilization by previously + * chosen random offset + * + * This should be used in the syscall entry path when interrupts and * preempt are disabled, and after user registers have been stored to - * the stack. + * the stack. For testing the resulting entropy, please see: + * tools/testing/selftests/lkdtm/stack-entropy.sh */ #define add_random_kstack_offset() do { \ if (static_branch_maybe(CONFIG_RANDOMIZE_KSTACK_OFFSET_DEFAULT, \ &randomize_kstack_offset)) { \ u32 offset = raw_cpu_read(kstack_offset); \ - u8 *ptr = __builtin_alloca(KSTACK_OFFSET_MAX(offset)); \ + u8 *ptr = __kstack_alloca(KSTACK_OFFSET_MAX(offset)); \ /* Keep allocation even after "ptr" loses scope. */ \ asm volatile("" :: "r"(ptr) : "memory"); \ } \ } while (0) +/** + * choose_random_kstack_offset - Choose the random offset for the next + * add_random_kstack_offset() + * + * This should only be used during syscall exit when interrupts and + * preempt are disabled. This position in the syscall flow is done to + * frustrate attacks from userspace attempting to learn the next offset: + * - Maximize the timing uncertainty visible from userspace: if the + * offset is chosen at syscall entry, userspace has much more control + * over the timing between choosing offsets. "How long will we be in + * kernel mode?" tends to be more difficult to predict than "how long + * will we be in user mode?" + * - Reduce the lifetime of the new offset sitting in memory during + * kernel mode execution. Exposure of "thread-local" memory content + * (e.g. current, percpu, etc) tends to be easier than arbitrary + * location memory exposure. + */ #define choose_random_kstack_offset(rand) do { \ if (static_branch_maybe(CONFIG_RANDOMIZE_KSTACK_OFFSET_DEFAULT, \ &randomize_kstack_offset)) { \ @@ -50,5 +84,9 @@ void *__builtin_alloca(size_t size); raw_cpu_write(kstack_offset, offset); \ } \ } while (0) +#else /* CONFIG_RANDOMIZE_KSTACK_OFFSET */ +#define add_random_kstack_offset() do { } while (0) +#define choose_random_kstack_offset(rand) do { } while (0) +#endif /* CONFIG_RANDOMIZE_KSTACK_OFFSET */ #endif diff --git a/include/linux/ratelimit_types.h b/include/linux/ratelimit_types.h index b676aa419eef..002266693e50 100644 --- a/include/linux/ratelimit_types.h +++ b/include/linux/ratelimit_types.h @@ -4,7 +4,7 @@ #include <linux/bits.h> #include <linux/param.h> -#include <linux/spinlock_types.h> +#include <linux/spinlock_types_raw.h> #define DEFAULT_RATELIMIT_INTERVAL (5 * HZ) #define DEFAULT_RATELIMIT_BURST 10 @@ -23,12 +23,16 @@ struct ratelimit_state { unsigned long flags; }; -#define RATELIMIT_STATE_INIT(name, interval_init, burst_init) { \ - .lock = __RAW_SPIN_LOCK_UNLOCKED(name.lock), \ - .interval = interval_init, \ - .burst = burst_init, \ +#define RATELIMIT_STATE_INIT_FLAGS(name, interval_init, burst_init, flags_init) { \ + .lock = __RAW_SPIN_LOCK_UNLOCKED(name.lock), \ + .interval = interval_init, \ + .burst = burst_init, \ + .flags = flags_init, \ } +#define RATELIMIT_STATE_INIT(name, interval_init, burst_init) \ + RATELIMIT_STATE_INIT_FLAGS(name, interval_init, burst_init, 0) + #define RATELIMIT_STATE_INIT_DISABLED \ RATELIMIT_STATE_INIT(ratelimit_state, 0, DEFAULT_RATELIMIT_BURST) diff --git a/include/linux/rbtree.h b/include/linux/rbtree.h index 235047d7a1b5..f7edca369eda 100644 --- a/include/linux/rbtree.h +++ b/include/linux/rbtree.h @@ -17,9 +17,9 @@ #ifndef _LINUX_RBTREE_H #define _LINUX_RBTREE_H +#include <linux/container_of.h> #include <linux/rbtree_types.h> -#include <linux/kernel.h> #include <linux/stddef.h> #include <linux/rcupdate.h> diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 88b42eb46406..08605ce7379d 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -29,6 +29,7 @@ #include <linux/lockdep.h> #include <asm/processor.h> #include <linux/cpumask.h> +#include <linux/context_tracking_irq.h> #define ULONG_CMP_GE(a, b) (ULONG_MAX / 2 >= (a) - (b)) #define ULONG_CMP_LT(a, b) (ULONG_MAX / 2 < (a) - (b)) @@ -42,6 +43,31 @@ void rcu_barrier_tasks(void); void rcu_barrier_tasks_rude(void); void synchronize_rcu(void); +struct rcu_gp_oldstate; +unsigned long get_completed_synchronize_rcu(void); +void get_completed_synchronize_rcu_full(struct rcu_gp_oldstate *rgosp); + +// Maximum number of unsigned long values corresponding to +// not-yet-completed RCU grace periods. +#define NUM_ACTIVE_RCU_POLL_OLDSTATE 2 + +/** + * same_state_synchronize_rcu - Are two old-state values identical? + * @oldstate1: First old-state value. + * @oldstate2: Second old-state value. + * + * The two old-state values must have been obtained from either + * get_state_synchronize_rcu(), start_poll_synchronize_rcu(), or + * get_completed_synchronize_rcu(). Returns @true if the two values are + * identical and @false otherwise. This allows structures whose lifetimes + * are tracked by old-state values to push these values to a list header, + * allowing those structures to be slightly smaller. + */ +static inline bool same_state_synchronize_rcu(unsigned long oldstate1, unsigned long oldstate2) +{ + return oldstate1 == oldstate2; +} + #ifdef CONFIG_PREEMPT_RCU void __rcu_read_lock(void); @@ -84,7 +110,7 @@ static inline int rcu_preempt_depth(void) /* Internal to kernel */ void rcu_init(void); -extern int rcu_scheduler_active __read_mostly; +extern int rcu_scheduler_active; void rcu_sched_clock_irq(int user); void rcu_report_dead(unsigned int cpu); void rcutree_migrate_callbacks(int cpu); @@ -103,13 +129,11 @@ static inline void rcu_sysrq_start(void) { } static inline void rcu_sysrq_end(void) { } #endif /* #else #ifdef CONFIG_RCU_STALL_COMMON */ -#ifdef CONFIG_NO_HZ_FULL -void rcu_user_enter(void); -void rcu_user_exit(void); +#if defined(CONFIG_NO_HZ_FULL) && (!defined(CONFIG_GENERIC_ENTRY) || !defined(CONFIG_KVM_XFER_TO_GUEST_WORK)) +void rcu_irq_work_resched(void); #else -static inline void rcu_user_enter(void) { } -static inline void rcu_user_exit(void) { } -#endif /* CONFIG_NO_HZ_FULL */ +static inline void rcu_irq_work_resched(void) { } +#endif #ifdef CONFIG_RCU_NOCB_CPU void rcu_init_nohz(void); @@ -128,7 +152,7 @@ static inline void rcu_nocb_flush_deferred_wakeup(void) { } * @a: Code that RCU needs to pay attention to. * * RCU read-side critical sections are forbidden in the inner idle loop, - * that is, between the rcu_idle_enter() and the rcu_idle_exit() -- RCU + * that is, between the ct_idle_enter() and the ct_idle_exit() -- RCU * will happily ignore any such read-side critical sections. However, * things like powertop need tracepoints in the inner idle loop. * @@ -143,9 +167,9 @@ static inline void rcu_nocb_flush_deferred_wakeup(void) { } */ #define RCU_NONIDLE(a) \ do { \ - rcu_irq_enter_irqson(); \ + ct_irq_enter_irqson(); \ do { a; } while (0); \ - rcu_irq_exit_irqson(); \ + ct_irq_exit_irqson(); \ } while (0) /* @@ -169,13 +193,24 @@ void synchronize_rcu_tasks(void); # endif # ifdef CONFIG_TASKS_TRACE_RCU -# define rcu_tasks_trace_qs(t) \ - do { \ - if (!likely(READ_ONCE((t)->trc_reader_checked)) && \ - !unlikely(READ_ONCE((t)->trc_reader_nesting))) { \ - smp_store_release(&(t)->trc_reader_checked, true); \ - smp_mb(); /* Readers partitioned by store. */ \ - } \ +// Bits for ->trc_reader_special.b.need_qs field. +#define TRC_NEED_QS 0x1 // Task needs a quiescent state. +#define TRC_NEED_QS_CHECKED 0x2 // Task has been checked for needing quiescent state. + +u8 rcu_trc_cmpxchg_need_qs(struct task_struct *t, u8 old, u8 new); +void rcu_tasks_trace_qs_blkd(struct task_struct *t); + +# define rcu_tasks_trace_qs(t) \ + do { \ + int ___rttq_nesting = READ_ONCE((t)->trc_reader_nesting); \ + \ + if (likely(!READ_ONCE((t)->trc_reader_special.b.need_qs)) && \ + likely(!___rttq_nesting)) { \ + rcu_trc_cmpxchg_need_qs((t), 0, TRC_NEED_QS_CHECKED); \ + } else if (___rttq_nesting && ___rttq_nesting != INT_MIN && \ + !READ_ONCE((t)->trc_reader_special.b.blocked)) { \ + rcu_tasks_trace_qs_blkd(t); \ + } \ } while (0) # else # define rcu_tasks_trace_qs(t) do { } while (0) @@ -184,7 +219,7 @@ void synchronize_rcu_tasks(void); #define rcu_tasks_qs(t, preempt) \ do { \ rcu_tasks_classic_qs((t), (preempt)); \ - rcu_tasks_trace_qs((t)); \ + rcu_tasks_trace_qs(t); \ } while (0) # ifdef CONFIG_TASKS_RUDE_RCU @@ -196,6 +231,7 @@ void synchronize_rcu_tasks_rude(void); void exit_tasks_rcu_start(void); void exit_tasks_rcu_finish(void); #else /* #ifdef CONFIG_TASKS_RCU_GENERIC */ +#define rcu_tasks_classic_qs(t, preempt) do { } while (0) #define rcu_tasks_qs(t, preempt) do { } while (0) #define rcu_note_voluntary_context_switch(t) do { } while (0) #define call_rcu_tasks call_rcu @@ -484,13 +520,21 @@ do { \ * against NULL. Although rcu_access_pointer() may also be used in cases * where update-side locks prevent the value of the pointer from changing, * you should instead use rcu_dereference_protected() for this use case. + * Within an RCU read-side critical section, there is little reason to + * use rcu_access_pointer(). + * + * It is usually best to test the rcu_access_pointer() return value + * directly in order to avoid accidental dereferences being introduced + * by later inattentive changes. In other words, assigning the + * rcu_access_pointer() return value to a local variable results in an + * accident waiting to happen. * * It is also permissible to use rcu_access_pointer() when read-side - * access to the pointer was removed at least one grace period ago, as - * is the case in the context of the RCU callback that is freeing up - * the data, or after a synchronize_rcu() returns. This can be useful - * when tearing down multi-linked structures after a grace period - * has elapsed. + * access to the pointer was removed at least one grace period ago, as is + * the case in the context of the RCU callback that is freeing up the data, + * or after a synchronize_rcu() returns. This can be useful when tearing + * down multi-linked structures after a grace period has elapsed. However, + * rcu_dereference_protected() is normally preferred for this use case. */ #define rcu_access_pointer(p) __rcu_access_pointer((p), __UNIQUE_ID(rcu), __rcu) @@ -924,7 +968,7 @@ static inline notrace void rcu_read_unlock_sched_notrace(void) * * kvfree_rcu(ptr); * - * where @ptr is a pointer to kvfree(). + * where @ptr is the pointer to be freed by kvfree(). * * Please note, head-less way of freeing is permitted to * use from a context that has to follow might_sleep() diff --git a/include/linux/rcupdate_trace.h b/include/linux/rcupdate_trace.h index 6f9c35817398..9bc8cbb33340 100644 --- a/include/linux/rcupdate_trace.h +++ b/include/linux/rcupdate_trace.h @@ -75,7 +75,7 @@ static inline void rcu_read_unlock_trace(void) nesting = READ_ONCE(t->trc_reader_nesting) - 1; barrier(); // Critical section before disabling. // Disable IPI-based setting of .need_qs. - WRITE_ONCE(t->trc_reader_nesting, INT_MIN); + WRITE_ONCE(t->trc_reader_nesting, INT_MIN + nesting); if (likely(!READ_ONCE(t->trc_reader_special.s)) || nesting) { WRITE_ONCE(t->trc_reader_nesting, nesting); return; // We assume shallow reader nesting. diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index 858f4d429946..768196a5f39d 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -14,15 +14,75 @@ #include <asm/param.h> /* for HZ */ +struct rcu_gp_oldstate { + unsigned long rgos_norm; +}; + +// Maximum number of rcu_gp_oldstate values corresponding to +// not-yet-completed RCU grace periods. +#define NUM_ACTIVE_RCU_POLL_FULL_OLDSTATE 2 + +/* + * Are the two oldstate values the same? See the Tree RCU version for + * docbook header. + */ +static inline bool same_state_synchronize_rcu_full(struct rcu_gp_oldstate *rgosp1, + struct rcu_gp_oldstate *rgosp2) +{ + return rgosp1->rgos_norm == rgosp2->rgos_norm; +} + unsigned long get_state_synchronize_rcu(void); + +static inline void get_state_synchronize_rcu_full(struct rcu_gp_oldstate *rgosp) +{ + rgosp->rgos_norm = get_state_synchronize_rcu(); +} + unsigned long start_poll_synchronize_rcu(void); + +static inline void start_poll_synchronize_rcu_full(struct rcu_gp_oldstate *rgosp) +{ + rgosp->rgos_norm = start_poll_synchronize_rcu(); +} + bool poll_state_synchronize_rcu(unsigned long oldstate); +static inline bool poll_state_synchronize_rcu_full(struct rcu_gp_oldstate *rgosp) +{ + return poll_state_synchronize_rcu(rgosp->rgos_norm); +} + static inline void cond_synchronize_rcu(unsigned long oldstate) { might_sleep(); } +static inline void cond_synchronize_rcu_full(struct rcu_gp_oldstate *rgosp) +{ + cond_synchronize_rcu(rgosp->rgos_norm); +} + +static inline unsigned long start_poll_synchronize_rcu_expedited(void) +{ + return start_poll_synchronize_rcu(); +} + +static inline void start_poll_synchronize_rcu_expedited_full(struct rcu_gp_oldstate *rgosp) +{ + rgosp->rgos_norm = start_poll_synchronize_rcu_expedited(); +} + +static inline void cond_synchronize_rcu_expedited(unsigned long oldstate) +{ + cond_synchronize_rcu(oldstate); +} + +static inline void cond_synchronize_rcu_expedited_full(struct rcu_gp_oldstate *rgosp) +{ + cond_synchronize_rcu_expedited(rgosp->rgos_norm); +} + extern void rcu_barrier(void); static inline void synchronize_rcu_expedited(void) @@ -38,7 +98,7 @@ static inline void synchronize_rcu_expedited(void) */ extern void kvfree(const void *addr); -static inline void kvfree_call_rcu(struct rcu_head *head, rcu_callback_t func) +static inline void __kvfree_call_rcu(struct rcu_head *head, rcu_callback_t func) { if (head) { call_rcu(head, func); @@ -51,6 +111,15 @@ static inline void kvfree_call_rcu(struct rcu_head *head, rcu_callback_t func) kvfree((void *) func); } +#ifdef CONFIG_KASAN_GENERIC +void kvfree_call_rcu(struct rcu_head *head, rcu_callback_t func); +#else +static inline void kvfree_call_rcu(struct rcu_head *head, rcu_callback_t func) +{ + __kvfree_call_rcu(head, func); +} +#endif + void rcu_qs(void); static inline void rcu_softirq_qs(void) @@ -64,9 +133,8 @@ static inline void rcu_softirq_qs(void) rcu_tasks_qs(current, (preempt)); \ } while (0) -static inline int rcu_needs_cpu(u64 basemono, u64 *nextevt) +static inline int rcu_needs_cpu(void) { - *nextevt = KTIME_MAX; return 0; } @@ -77,12 +145,6 @@ static inline int rcu_needs_cpu(u64 basemono, u64 *nextevt) static inline void rcu_virt_note_context_switch(int cpu) { } static inline void rcu_cpu_stall_reset(void) { } static inline int rcu_jiffies_till_stall_check(void) { return 21 * HZ; } -static inline void rcu_idle_enter(void) { } -static inline void rcu_idle_exit(void) { } -static inline void rcu_irq_enter(void) { } -static inline void rcu_irq_exit_irqson(void) { } -static inline void rcu_irq_enter_irqson(void) { } -static inline void rcu_irq_exit(void) { } static inline void rcu_irq_exit_check_preempt(void) { } #define rcu_is_idle_cpu(cpu) \ (is_idle_task(current) && !in_nmi() && !in_hardirq() && !in_serving_softirq()) diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index 53209d669400..5efb51486e8a 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -19,7 +19,7 @@ void rcu_softirq_qs(void); void rcu_note_context_switch(bool preempt); -int rcu_needs_cpu(u64 basem, u64 *nextevt); +int rcu_needs_cpu(void); void rcu_cpu_stall_reset(void); /* @@ -40,17 +40,53 @@ bool rcu_eqs_special_set(int cpu); void rcu_momentary_dyntick_idle(void); void kfree_rcu_scheduler_running(void); bool rcu_gp_might_be_stalled(void); + +struct rcu_gp_oldstate { + unsigned long rgos_norm; + unsigned long rgos_exp; +}; + +// Maximum number of rcu_gp_oldstate values corresponding to +// not-yet-completed RCU grace periods. +#define NUM_ACTIVE_RCU_POLL_FULL_OLDSTATE 4 + +/** + * same_state_synchronize_rcu_full - Are two old-state values identical? + * @rgosp1: First old-state value. + * @rgosp2: Second old-state value. + * + * The two old-state values must have been obtained from either + * get_state_synchronize_rcu_full(), start_poll_synchronize_rcu_full(), + * or get_completed_synchronize_rcu_full(). Returns @true if the two + * values are identical and @false otherwise. This allows structures + * whose lifetimes are tracked by old-state values to push these values + * to a list header, allowing those structures to be slightly smaller. + * + * Note that equality is judged on a bitwise basis, so that an + * @rcu_gp_oldstate structure with an already-completed state in one field + * will compare not-equal to a structure with an already-completed state + * in the other field. After all, the @rcu_gp_oldstate structure is opaque + * so how did such a situation come to pass in the first place? + */ +static inline bool same_state_synchronize_rcu_full(struct rcu_gp_oldstate *rgosp1, + struct rcu_gp_oldstate *rgosp2) +{ + return rgosp1->rgos_norm == rgosp2->rgos_norm && rgosp1->rgos_exp == rgosp2->rgos_exp; +} + +unsigned long start_poll_synchronize_rcu_expedited(void); +void start_poll_synchronize_rcu_expedited_full(struct rcu_gp_oldstate *rgosp); +void cond_synchronize_rcu_expedited(unsigned long oldstate); +void cond_synchronize_rcu_expedited_full(struct rcu_gp_oldstate *rgosp); unsigned long get_state_synchronize_rcu(void); +void get_state_synchronize_rcu_full(struct rcu_gp_oldstate *rgosp); unsigned long start_poll_synchronize_rcu(void); +void start_poll_synchronize_rcu_full(struct rcu_gp_oldstate *rgosp); bool poll_state_synchronize_rcu(unsigned long oldstate); +bool poll_state_synchronize_rcu_full(struct rcu_gp_oldstate *rgosp); void cond_synchronize_rcu(unsigned long oldstate); +void cond_synchronize_rcu_full(struct rcu_gp_oldstate *rgosp); -void rcu_idle_enter(void); -void rcu_idle_exit(void); -void rcu_irq_enter(void); -void rcu_irq_exit(void); -void rcu_irq_enter_irqson(void); -void rcu_irq_exit_irqson(void); bool rcu_is_idle_cpu(int cpu); #ifdef CONFIG_PROVE_RCU @@ -59,10 +95,13 @@ void rcu_irq_exit_check_preempt(void); static inline void rcu_irq_exit_check_preempt(void) { } #endif +struct task_struct; +void rcu_preempt_deferred_qs(struct task_struct *t); + void exit_rcu(void); void rcu_scheduler_starting(void); -extern int rcu_scheduler_active __read_mostly; +extern int rcu_scheduler_active; void rcu_end_inkernel_boot(void); bool rcu_inkernel_boot_has_ended(void); bool rcu_is_watching(void); diff --git a/include/linux/rcuwait.h b/include/linux/rcuwait.h index 61c56cca95c4..8052d34da782 100644 --- a/include/linux/rcuwait.h +++ b/include/linux/rcuwait.h @@ -47,11 +47,7 @@ static inline void prepare_to_rcuwait(struct rcuwait *w) rcu_assign_pointer(w->task, current); } -static inline void finish_rcuwait(struct rcuwait *w) -{ - rcu_assign_pointer(w->task, NULL); - __set_current_state(TASK_RUNNING); -} +extern void finish_rcuwait(struct rcuwait *w); #define rcuwait_wait_event(w, condition, state) \ ({ \ diff --git a/include/linux/rcuwait_api.h b/include/linux/rcuwait_api.h new file mode 100644 index 000000000000..f962e28544dd --- /dev/null +++ b/include/linux/rcuwait_api.h @@ -0,0 +1 @@ +#include <linux/rcuwait.h> diff --git a/include/linux/reboot.h b/include/linux/reboot.h index af907a3d68d1..2b6bb593be5b 100644 --- a/include/linux/reboot.h +++ b/include/linux/reboot.h @@ -7,6 +7,7 @@ #include <uapi/linux/reboot.h> struct device; +struct sys_off_handler; #define SYS_DOWN 0x0001 /* Notify of system down */ #define SYS_RESTART SYS_DOWN @@ -62,6 +63,103 @@ extern void machine_shutdown(void); struct pt_regs; extern void machine_crash_shutdown(struct pt_regs *); +void do_kernel_power_off(void); + +/* + * sys-off handler API. + */ + +/* + * Standard sys-off priority levels. Users are expected to set priorities + * relative to the standard levels. + * + * SYS_OFF_PRIO_PLATFORM: Use this for platform-level handlers. + * + * SYS_OFF_PRIO_LOW: Use this for handler of last resort. + * + * SYS_OFF_PRIO_DEFAULT: Use this for normal handlers. + * + * SYS_OFF_PRIO_HIGH: Use this for higher priority handlers. + * + * SYS_OFF_PRIO_FIRMWARE: Use this if handler uses firmware call. + */ +#define SYS_OFF_PRIO_PLATFORM -256 +#define SYS_OFF_PRIO_LOW -128 +#define SYS_OFF_PRIO_DEFAULT 0 +#define SYS_OFF_PRIO_HIGH 192 +#define SYS_OFF_PRIO_FIRMWARE 224 + +enum sys_off_mode { + /** + * @SYS_OFF_MODE_POWER_OFF_PREPARE: + * + * Handlers prepare system to be powered off. Handlers are + * allowed to sleep. + */ + SYS_OFF_MODE_POWER_OFF_PREPARE, + + /** + * @SYS_OFF_MODE_POWER_OFF: + * + * Handlers power-off system. Handlers are disallowed to sleep. + */ + SYS_OFF_MODE_POWER_OFF, + + /** + * @SYS_OFF_MODE_RESTART_PREPARE: + * + * Handlers prepare system to be restarted. Handlers are + * allowed to sleep. + */ + SYS_OFF_MODE_RESTART_PREPARE, + + /** + * @SYS_OFF_MODE_RESTART: + * + * Handlers restart system. Handlers are disallowed to sleep. + */ + SYS_OFF_MODE_RESTART, +}; + +/** + * struct sys_off_data - sys-off callback argument + * + * @mode: Mode ID. Currently used only by the sys-off restart mode, + * see enum reboot_mode for the available modes. + * @cb_data: User's callback data. + * @cmd: Command string. Currently used only by the sys-off restart mode, + * NULL otherwise. + */ +struct sys_off_data { + int mode; + void *cb_data; + const char *cmd; +}; + +struct sys_off_handler * +register_sys_off_handler(enum sys_off_mode mode, + int priority, + int (*callback)(struct sys_off_data *data), + void *cb_data); +void unregister_sys_off_handler(struct sys_off_handler *handler); + +int devm_register_sys_off_handler(struct device *dev, + enum sys_off_mode mode, + int priority, + int (*callback)(struct sys_off_data *data), + void *cb_data); + +int devm_register_power_off_handler(struct device *dev, + int (*callback)(struct sys_off_data *data), + void *cb_data); + +int devm_register_restart_handler(struct device *dev, + int (*callback)(struct sys_off_data *data), + void *cb_data); + +int register_platform_power_off(void (*power_off)(void)); +void unregister_platform_power_off(void (*power_off)(void)); + /* * Architecture independent implemenations of sys_reboot commands. */ @@ -70,13 +168,10 @@ extern void kernel_restart_prepare(char *cmd); extern void kernel_restart(char *cmd); extern void kernel_halt(void); extern void kernel_power_off(void); +extern bool kernel_can_power_off(void); -extern int C_A_D; /* for sysctl */ void ctrl_alt_del(void); -#define POWEROFF_CMD_PATH_LEN 256 -extern char poweroff_cmd[POWEROFF_CMD_PATH_LEN]; - extern void orderly_poweroff(bool force); extern void orderly_reboot(void); void hw_protection_shutdown(const char *reason, int ms_until_forced); diff --git a/include/linux/ref_tracker.h b/include/linux/ref_tracker.h index c11c9db5825c..9ca353ab712b 100644 --- a/include/linux/ref_tracker.h +++ b/include/linux/ref_tracker.h @@ -4,6 +4,7 @@ #include <linux/refcount.h> #include <linux/types.h> #include <linux/spinlock.h> +#include <linux/stackdepot.h> struct ref_tracker; @@ -12,6 +13,8 @@ struct ref_tracker_dir { spinlock_t lock; unsigned int quarantine_avail; refcount_t untracked; + refcount_t no_tracker; + bool dead; struct list_head list; /* List of active trackers */ struct list_head quarantine; /* List of dead trackers */ #endif @@ -25,7 +28,10 @@ static inline void ref_tracker_dir_init(struct ref_tracker_dir *dir, INIT_LIST_HEAD(&dir->quarantine); spin_lock_init(&dir->lock); dir->quarantine_avail = quarantine_count; + dir->dead = false; refcount_set(&dir->untracked, 1); + refcount_set(&dir->no_tracker, 1); + stack_depot_init(); } void ref_tracker_dir_exit(struct ref_tracker_dir *dir); diff --git a/include/linux/refcount.h b/include/linux/refcount.h index b8a6e387f8f9..a62fcca97486 100644 --- a/include/linux/refcount.h +++ b/include/linux/refcount.h @@ -361,9 +361,9 @@ static inline void refcount_dec(refcount_t *r) extern __must_check bool refcount_dec_if_one(refcount_t *r); extern __must_check bool refcount_dec_not_one(refcount_t *r); -extern __must_check bool refcount_dec_and_mutex_lock(refcount_t *r, struct mutex *lock); -extern __must_check bool refcount_dec_and_lock(refcount_t *r, spinlock_t *lock); +extern __must_check bool refcount_dec_and_mutex_lock(refcount_t *r, struct mutex *lock) __cond_acquires(lock); +extern __must_check bool refcount_dec_and_lock(refcount_t *r, spinlock_t *lock) __cond_acquires(lock); extern __must_check bool refcount_dec_and_lock_irqsave(refcount_t *r, spinlock_t *lock, - unsigned long *flags); + unsigned long *flags) __cond_acquires(lock); #endif /* _LINUX_REFCOUNT_H */ diff --git a/include/linux/refcount_api.h b/include/linux/refcount_api.h new file mode 100644 index 000000000000..5f032589f568 --- /dev/null +++ b/include/linux/refcount_api.h @@ -0,0 +1 @@ +#include <linux/refcount.h> diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 22652e5fbc38..ca3434dca3a0 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -237,6 +237,10 @@ typedef void (*regmap_unlock)(void *); * @reg_stride: The register address stride. Valid register addresses are a * multiple of this value. If set to 0, a value of 1 will be * used. + * @reg_downshift: The number of bits to downshift the register before + * performing any operations. + * @reg_base: Value to be added to every register address before performing any + * operation. * @pad_bits: Number of bits of padding between register and value. * @val_bits: Number of bits in a register value, mandatory. * @@ -295,12 +299,20 @@ typedef void (*regmap_unlock)(void *); * if the function require special handling with lock and reg * handling and the operation cannot be represented as a simple * update_bits operation on a bus such as SPI, I2C, etc. + * @read: Optional callback that if filled will be used to perform all the + * bulk reads from the registers. Data is returned in the buffer used + * to transmit data. + * @write: Same as above for writing. + * @max_raw_read: Max raw read size that can be used on the device. + * @max_raw_write: Max raw write size that can be used on the device. * @fast_io: Register IO is fast. Use a spinlock instead of a mutex * to perform locking. This field is ignored if custom lock/unlock * functions are used (see fields lock/unlock of struct regmap_config). * This field is a duplicate of a similar file in * 'struct regmap_bus' and serves exact same purpose. * Use it only for "no-bus" cases. + * @io_port: Support IO port accessors. Makes sense only when MMIO vs. IO port + * access can be distinguished. * @max_register: Optional, specifies the maximum valid register address. * @wr_table: Optional, points to a struct regmap_access_table specifying * valid ranges for write access. @@ -360,6 +372,8 @@ struct regmap_config { int reg_bits; int reg_stride; + int reg_downshift; + unsigned int reg_base; int pad_bits; int val_bits; @@ -379,8 +393,15 @@ struct regmap_config { int (*reg_write)(void *context, unsigned int reg, unsigned int val); int (*reg_update_bits)(void *context, unsigned int reg, unsigned int mask, unsigned int val); + /* Bulk read/write */ + int (*read)(void *context, const void *reg_buf, size_t reg_size, + void *val_buf, size_t val_size); + int (*write)(void *context, const void *data, size_t count); + size_t max_raw_read; + size_t max_raw_write; bool fast_io; + bool io_port; unsigned int max_register; const struct regmap_access_table *wr_table; @@ -471,8 +492,12 @@ typedef int (*regmap_hw_read)(void *context, void *val_buf, size_t val_size); typedef int (*regmap_hw_reg_read)(void *context, unsigned int reg, unsigned int *val); +typedef int (*regmap_hw_reg_noinc_read)(void *context, unsigned int reg, + void *val, size_t val_count); typedef int (*regmap_hw_reg_write)(void *context, unsigned int reg, unsigned int val); +typedef int (*regmap_hw_reg_noinc_write)(void *context, unsigned int reg, + const void *val, size_t val_count); typedef int (*regmap_hw_reg_update_bits)(void *context, unsigned int reg, unsigned int mask, unsigned int val); typedef struct regmap_async *(*regmap_hw_async_alloc)(void); @@ -493,6 +518,8 @@ typedef void (*regmap_hw_free_context)(void *context); * must serialise with respect to non-async I/O. * @reg_write: Write a single register value to the given register address. This * write operation has to complete when returning from the function. + * @reg_write_noinc: Write multiple register value to the same register. This + * write operation has to complete when returning from the function. * @reg_update_bits: Update bits operation to be used against volatile * registers, intended for devices supporting some mechanism * for setting clearing bits without having to @@ -520,9 +547,11 @@ struct regmap_bus { regmap_hw_gather_write gather_write; regmap_hw_async_write async_write; regmap_hw_reg_write reg_write; + regmap_hw_reg_noinc_write reg_noinc_write; regmap_hw_reg_update_bits reg_update_bits; regmap_hw_read read; regmap_hw_reg_read reg_read; + regmap_hw_reg_noinc_read reg_noinc_read; regmap_hw_free_context free_context; regmap_hw_async_alloc async_alloc; u8 read_flag_mask; @@ -1318,6 +1347,22 @@ static inline int regmap_field_update_bits(struct regmap_field *field, NULL, false, false); } +static inline int regmap_field_set_bits(struct regmap_field *field, + unsigned int bits) +{ + return regmap_field_update_bits_base(field, bits, bits, NULL, false, + false); +} + +static inline int regmap_field_clear_bits(struct regmap_field *field, + unsigned int bits) +{ + return regmap_field_update_bits_base(field, bits, 0, NULL, false, + false); +} + +int regmap_field_test_bits(struct regmap_field *field, unsigned int bits); + static inline int regmap_field_force_update_bits(struct regmap_field *field, unsigned int mask, unsigned int val) @@ -1406,6 +1451,8 @@ struct regmap_irq_sub_irq_map { unsigned int *offset; }; +struct regmap_irq_chip_data; + /** * struct regmap_irq_chip - Description of a generic regmap irq_chip. * @@ -1433,32 +1480,50 @@ struct regmap_irq_sub_irq_map { * main_status set. * * @status_base: Base status register address. - * @mask_base: Base mask register address. - * @mask_writeonly: Base mask register is write only. - * @unmask_base: Base unmask register address. for chips who have - * separate mask and unmask registers + * @mask_base: Base mask register address. Mask bits are set to 1 when an + * interrupt is masked, 0 when unmasked. + * @unmask_base: Base unmask register address. Unmask bits are set to 1 when + * an interrupt is unmasked and 0 when masked. * @ack_base: Base ack address. If zero then the chip is clear on read. * Using zero value is possible with @use_ack bit. * @wake_base: Base address for wake enables. If zero unsupported. - * @type_base: Base address for irq type. If zero unsupported. - * @virt_reg_base: Base addresses for extra config regs. + * @type_base: Base address for irq type. If zero unsupported. Deprecated, + * use @config_base instead. + * @virt_reg_base: Base addresses for extra config regs. Deprecated, use + * @config_base instead. + * @config_base: Base address for IRQ type config regs. If null unsupported. * @irq_reg_stride: Stride to use for chips where registers are not contiguous. * @init_ack_masked: Ack all masked interrupts once during initalization. * @mask_invert: Inverted mask register: cleared bits are masked out. + * Deprecated; prefer describing an inverted mask register as + * an unmask register. + * @mask_unmask_non_inverted: Controls mask bit inversion for chips that set + * both @mask_base and @unmask_base. If false, mask and unmask bits are + * inverted (which is deprecated behavior); if true, bits will not be + * inverted and the registers keep their normal behavior. Note that if + * you use only one of @mask_base or @unmask_base, this flag has no + * effect and is unnecessary. Any new drivers that set both @mask_base + * and @unmask_base should set this to true to avoid relying on the + * deprecated behavior. * @use_ack: Use @ack register even if it is zero. * @ack_invert: Inverted ack register: cleared bits for ack. * @clear_ack: Use this to set 1 and 0 or vice-versa to clear interrupts. * @wake_invert: Inverted wake register: cleared bits are wake enabled. - * @type_invert: Invert the type flags. - * @type_in_mask: Use the mask registers for controlling irq type. For - * interrupts defining type_rising/falling_mask use mask_base - * for edge configuration and never update bits in type_base. + * @type_invert: Invert the type flags. Deprecated, use config registers + * instead. + * @type_in_mask: Use the mask registers for controlling irq type. Use this if + * the hardware provides separate bits for rising/falling edge + * or low/high level interrupts and they should be combined into + * a single logical interrupt. Use &struct regmap_irq_type data + * to define the mask bit for each irq type. * @clear_on_unmask: For chips with interrupts cleared on read: read the status * registers before unmasking interrupts to clear any bits * set when they were masked. * @not_fixed_stride: Used when chip peripherals are not laid out with fixed - * stride. Must be used with sub_reg_offsets containing the - * offsets to each peripheral. + * stride. Must be used with sub_reg_offsets containing the + * offsets to each peripheral. Deprecated; the same thing + * can be accomplished with a @get_irq_reg callback, without + * the need for a @sub_reg_offsets table. * @status_invert: Inverted status register: cleared bits are active interrupts. * @runtime_pm: Hold a runtime PM lock on the device when accessing it. * @@ -1466,17 +1531,28 @@ struct regmap_irq_sub_irq_map { * @irqs: Descriptors for individual IRQs. Interrupt numbers are * assigned based on the index in the array of the interrupt. * @num_irqs: Number of descriptors. - * @num_type_reg: Number of type registers. + * @num_type_reg: Number of type registers. Deprecated, use config registers + * instead. * @num_virt_regs: Number of non-standard irq configuration registers. - * If zero unsupported. - * @type_reg_stride: Stride to use for chips where type registers are not - * contiguous. + * If zero unsupported. Deprecated, use config registers + * instead. + * @num_config_bases: Number of config base registers. + * @num_config_regs: Number of config registers for each config base register. * @handle_pre_irq: Driver specific callback to handle interrupt from device * before regmap_irq_handler process the interrupts. * @handle_post_irq: Driver specific callback to handle interrupt from device * after handling the interrupts in regmap_irq_handler(). * @set_type_virt: Driver specific callback to extend regmap_irq_set_type() - * and configure virt regs. + * and configure virt regs. Deprecated, use @set_type_config + * callback and config registers instead. + * @set_type_config: Callback used for configuring irq types. + * @get_irq_reg: Callback for mapping (base register, index) pairs to register + * addresses. The base register will be one of @status_base, + * @mask_base, etc., @main_status, or any of @config_base. + * The index will be in the range [0, num_main_regs[ for the + * main status base, [0, num_type_settings[ for any config + * register base, and [0, num_regs[ for any other base. + * If unspecified then regmap_irq_get_irq_reg_linear() is used. * @irq_drv_data: Driver specific IRQ data which is passed as parameter when * driver specific pre/post interrupt handler is called. * @@ -1499,20 +1575,21 @@ struct regmap_irq_chip { unsigned int wake_base; unsigned int type_base; unsigned int *virt_reg_base; + const unsigned int *config_base; unsigned int irq_reg_stride; - bool mask_writeonly:1; - bool init_ack_masked:1; - bool mask_invert:1; - bool use_ack:1; - bool ack_invert:1; - bool clear_ack:1; - bool wake_invert:1; - bool runtime_pm:1; - bool type_invert:1; - bool type_in_mask:1; - bool clear_on_unmask:1; - bool not_fixed_stride:1; - bool status_invert:1; + unsigned int init_ack_masked:1; + unsigned int mask_invert:1; + unsigned int mask_unmask_non_inverted:1; + unsigned int use_ack:1; + unsigned int ack_invert:1; + unsigned int clear_ack:1; + unsigned int wake_invert:1; + unsigned int runtime_pm:1; + unsigned int type_invert:1; + unsigned int type_in_mask:1; + unsigned int clear_on_unmask:1; + unsigned int not_fixed_stride:1; + unsigned int status_invert:1; int num_regs; @@ -1521,16 +1598,24 @@ struct regmap_irq_chip { int num_type_reg; int num_virt_regs; - unsigned int type_reg_stride; + int num_config_bases; + int num_config_regs; int (*handle_pre_irq)(void *irq_drv_data); int (*handle_post_irq)(void *irq_drv_data); int (*set_type_virt)(unsigned int **buf, unsigned int type, unsigned long hwirq, int reg); + int (*set_type_config)(unsigned int **buf, unsigned int type, + const struct regmap_irq *irq_data, int idx); + unsigned int (*get_irq_reg)(struct regmap_irq_chip_data *data, + unsigned int base, int index); void *irq_drv_data; }; -struct regmap_irq_chip_data; +unsigned int regmap_irq_get_irq_reg_linear(struct regmap_irq_chip_data *data, + unsigned int base, int index); +int regmap_irq_set_type_config_simple(unsigned int **buf, unsigned int type, + const struct regmap_irq *irq_data, int idx); int regmap_add_irq_chip(struct regmap *map, int irq, int irq_flags, int irq_base, const struct regmap_irq_chip *chip, @@ -1751,6 +1836,27 @@ regmap_field_force_update_bits(struct regmap_field *field, return -EINVAL; } +static inline int regmap_field_set_bits(struct regmap_field *field, + unsigned int bits) +{ + WARN_ONCE(1, "regmap API is disabled"); + return -EINVAL; +} + +static inline int regmap_field_clear_bits(struct regmap_field *field, + unsigned int bits) +{ + WARN_ONCE(1, "regmap API is disabled"); + return -EINVAL; +} + +static inline int regmap_field_test_bits(struct regmap_field *field, + unsigned int bits) +{ + WARN_ONCE(1, "regmap API is disabled"); + return -EINVAL; +} + static inline int regmap_fields_write(struct regmap_field *field, unsigned int id, unsigned int val) { diff --git a/include/linux/regulator/consumer.h b/include/linux/regulator/consumer.h index bbf6590a6dec..ee3b4a014611 100644 --- a/include/linux/regulator/consumer.h +++ b/include/linux/regulator/consumer.h @@ -171,10 +171,13 @@ struct regulator; /** * struct regulator_bulk_data - Data used for bulk regulator operations. * - * @supply: The name of the supply. Initialised by the user before - * using the bulk regulator APIs. - * @consumer: The regulator consumer for the supply. This will be managed - * by the bulk API. + * @supply: The name of the supply. Initialised by the user before + * using the bulk regulator APIs. + * @init_load_uA: After getting the regulator, regulator_set_load() will be + * called with this load. Initialised by the user before + * using the bulk regulator APIs. + * @consumer: The regulator consumer for the supply. This will be managed + * by the bulk API. * * The regulator APIs provide a series of regulator_bulk_() API calls as * a convenience to consumers which require multiple supplies. This @@ -182,6 +185,7 @@ struct regulator; */ struct regulator_bulk_data { const char *supply; + int init_load_uA; struct regulator *consumer; /* private: Internal use */ @@ -203,6 +207,8 @@ struct regulator *__must_check regulator_get_optional(struct device *dev, const char *id); struct regulator *__must_check devm_regulator_get_optional(struct device *dev, const char *id); +int devm_regulator_get_enable(struct device *dev, const char *id); +int devm_regulator_get_enable_optional(struct device *dev, const char *id); void regulator_put(struct regulator *regulator); void devm_regulator_put(struct regulator *regulator); @@ -240,8 +246,15 @@ int __must_check regulator_bulk_get(struct device *dev, int num_consumers, struct regulator_bulk_data *consumers); int __must_check devm_regulator_bulk_get(struct device *dev, int num_consumers, struct regulator_bulk_data *consumers); +void devm_regulator_bulk_put(struct regulator_bulk_data *consumers); +int __must_check devm_regulator_bulk_get_const( + struct device *dev, int num_consumers, + const struct regulator_bulk_data *in_consumers, + struct regulator_bulk_data **out_consumers); int __must_check regulator_bulk_enable(int num_consumers, struct regulator_bulk_data *consumers); +int devm_regulator_bulk_get_enable(struct device *dev, int num_consumers, + const char * const *id); int regulator_bulk_disable(int num_consumers, struct regulator_bulk_data *consumers); int regulator_bulk_force_disable(int num_consumers, @@ -346,6 +359,17 @@ devm_regulator_get_exclusive(struct device *dev, const char *id) return ERR_PTR(-ENODEV); } +static inline int devm_regulator_get_enable(struct device *dev, const char *id) +{ + return -ENODEV; +} + +static inline int devm_regulator_get_enable_optional(struct device *dev, + const char *id) +{ + return -ENODEV; +} + static inline struct regulator *__must_check regulator_get_optional(struct device *dev, const char *id) { @@ -367,6 +391,10 @@ static inline void devm_regulator_put(struct regulator *regulator) { } +static inline void devm_regulator_bulk_put(struct regulator_bulk_data *consumers) +{ +} + static inline int regulator_register_supply_alias(struct device *dev, const char *id, struct device *alias_dev, @@ -457,6 +485,13 @@ static inline int regulator_bulk_enable(int num_consumers, return 0; } +static inline int devm_regulator_bulk_get_enable(struct device *dev, + int num_consumers, + const char * const *id) +{ + return 0; +} + static inline int regulator_bulk_disable(int num_consumers, struct regulator_bulk_data *consumers) { diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index 0228caaa6741..f9a7461e72b8 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -348,6 +348,7 @@ enum regulator_type { * @ramp_delay_table: Table for mapping the regulator ramp-rate values. Values * should be given in units of V/S (uV/uS). See the * regulator_set_ramp_delay_regmap(). + * @n_ramp_values: number of elements at @ramp_delay_table. * * @enable_time: Time taken for initial enable of regulator (in uS). * @off_on_delay: guard time (in uS), before re-enabling a regulator diff --git a/include/linux/regulator/gpio-regulator.h b/include/linux/regulator/gpio-regulator.h index fdeb312cdabd..c223e50ff9f7 100644 --- a/include/linux/regulator/gpio-regulator.h +++ b/include/linux/regulator/gpio-regulator.h @@ -42,6 +42,7 @@ struct gpio_regulator_state { /** * struct gpio_regulator_config - config structure * @supply_name: Name of the regulator supply + * @input_supply: Name of the input regulator supply * @enabled_at_boot: Whether regulator has been enabled at * boot or not. 1 = Yes, 0 = No * This is used to keep the regulator at @@ -62,6 +63,7 @@ struct gpio_regulator_state { */ struct gpio_regulator_config { const char *supply_name; + const char *input_supply; unsigned enabled_at_boot:1; unsigned startup_delay; diff --git a/include/linux/regulator/mt6331-regulator.h b/include/linux/regulator/mt6331-regulator.h new file mode 100644 index 000000000000..2801a9879c14 --- /dev/null +++ b/include/linux/regulator/mt6331-regulator.h @@ -0,0 +1,46 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2022 Collabora Ltd. + * Author: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com> + */ + +#ifndef __LINUX_REGULATOR_MT6331_H +#define __LINUX_REGULATOR_MT6331_H + +enum { + /* BUCK */ + MT6331_ID_VDVFS11 = 0, + MT6331_ID_VDVFS12, + MT6331_ID_VDVFS13, + MT6331_ID_VDVFS14, + MT6331_ID_VCORE2, + MT6331_ID_VIO18, + /* LDO */ + MT6331_ID_VTCXO1, + MT6331_ID_VTCXO2, + MT6331_ID_AVDD32_AUD, + MT6331_ID_VAUXA32, + MT6331_ID_VCAMA, + MT6331_ID_VIO28, + MT6331_ID_VCAM_AF, + MT6331_ID_VMC, + MT6331_ID_VMCH, + MT6331_ID_VEMC33, + MT6331_ID_VGP1, + MT6331_ID_VSIM1, + MT6331_ID_VSIM2, + MT6331_ID_VMIPI, + MT6331_ID_VIBR, + MT6331_ID_VGP4, + MT6331_ID_VCAMD, + MT6331_ID_VUSB10, + MT6331_ID_VCAM_IO, + MT6331_ID_VSRAM_DVFS1, + MT6331_ID_VGP2, + MT6331_ID_VGP3, + MT6331_ID_VRTC, + MT6331_ID_VDIG18, + MT6331_ID_VREG_MAX +}; + +#endif /* __LINUX_REGULATOR_MT6331_H */ diff --git a/include/linux/regulator/mt6332-regulator.h b/include/linux/regulator/mt6332-regulator.h new file mode 100644 index 000000000000..af5e3ed31029 --- /dev/null +++ b/include/linux/regulator/mt6332-regulator.h @@ -0,0 +1,27 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2022 Collabora Ltd. + * Author: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com> + */ + +#ifndef __LINUX_REGULATOR_MT6332_H +#define __LINUX_REGULATOR_MT6332_H + +enum { + /* BUCK */ + MT6332_ID_VDRAM = 0, + MT6332_ID_VDVFS2, + MT6332_ID_VPA, + MT6332_ID_VRF1, + MT6332_ID_VRF2, + MT6332_ID_VSBST, + /* LDO */ + MT6332_ID_VAUXB32, + MT6332_ID_VBIF28, + MT6332_ID_VDIG18, + MT6332_ID_VSRAM_DVFS2, + MT6332_ID_VUSB33, + MT6332_ID_VREG_MAX +}; + +#endif /* __LINUX_REGULATOR_MT6332_H */ diff --git a/include/linux/regulator/mt6358-regulator.h b/include/linux/regulator/mt6358-regulator.h index 1cc304946d09..bdcf83cd719e 100644 --- a/include/linux/regulator/mt6358-regulator.h +++ b/include/linux/regulator/mt6358-regulator.h @@ -48,9 +48,54 @@ enum { MT6358_ID_VLDO28, MT6358_ID_VAUD28, MT6358_ID_VSIM2, + MT6358_ID_VCORE_SSHUB, + MT6358_ID_VSRAM_OTHERS_SSHUB, MT6358_ID_RG_MAX, }; +enum { + MT6366_ID_VDRAM1 = 0, + MT6366_ID_VCORE, + MT6366_ID_VPA, + MT6366_ID_VPROC11, + MT6366_ID_VPROC12, + MT6366_ID_VGPU, + MT6366_ID_VS2, + MT6366_ID_VMODEM, + MT6366_ID_VS1, + MT6366_ID_VDRAM2, + MT6366_ID_VSIM1, + MT6366_ID_VIBR, + MT6366_ID_VRF12, + MT6366_ID_VIO18, + MT6366_ID_VUSB, + MT6366_ID_VCN18, + MT6366_ID_VFE28, + MT6366_ID_VSRAM_PROC11, + MT6366_ID_VCN28, + MT6366_ID_VSRAM_OTHERS, + MT6366_ID_VSRAM_GPU, + MT6366_ID_VXO22, + MT6366_ID_VEFUSE, + MT6366_ID_VAUX18, + MT6366_ID_VMCH, + MT6366_ID_VBIF28, + MT6366_ID_VSRAM_PROC12, + MT6366_ID_VEMC, + MT6366_ID_VIO28, + MT6366_ID_VA12, + MT6366_ID_VRF18, + MT6366_ID_VCN33_BT, + MT6366_ID_VCN33_WIFI, + MT6366_ID_VMC, + MT6366_ID_VAUD28, + MT6366_ID_VSIM2, + MT6366_ID_VCORE_SSHUB, + MT6366_ID_VSRAM_OTHERS_SSHUB, + MT6366_ID_RG_MAX, +}; + #define MT6358_MAX_REGULATOR MT6358_ID_RG_MAX +#define MT6366_MAX_REGULATOR MT6366_ID_RG_MAX #endif /* __LINUX_REGULATOR_MT6358_H */ diff --git a/include/linux/regulator/pca9450.h b/include/linux/regulator/pca9450.h index 71902f41c919..3c01c2bf84f5 100644 --- a/include/linux/regulator/pca9450.h +++ b/include/linux/regulator/pca9450.h @@ -226,4 +226,11 @@ enum { #define WDOG_B_CFG_COLD_LDO12 0x80 #define WDOG_B_CFG_COLD 0xC0 +/* PCA9450_REG_CONFIG2 bits */ +#define I2C_LT_MASK 0x03 +#define I2C_LT_FORCE_DISABLE 0x00 +#define I2C_LT_ON_STANDBY_RUN 0x01 +#define I2C_LT_ON_RUN 0x02 +#define I2C_LT_FORCE_ENABLE 0x03 + #endif /* __LINUX_REG_PCA9450_H__ */ diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index e0600e1e5c17..fe8978eb69f1 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -490,6 +490,20 @@ struct rproc_dump_segment { }; /** + * enum rproc_features - features supported + * + * @RPROC_FEAT_ATTACH_ON_RECOVERY: The remote processor does not need help + * from Linux to recover, such as firmware + * loading. Linux just needs to attach after + * recovery. + */ + +enum rproc_features { + RPROC_FEAT_ATTACH_ON_RECOVERY, + RPROC_MAX_FEATURES, +}; + +/** * struct rproc - represents a physical remote processor device * @node: list node of this rproc object * @domain: iommu domain @@ -523,12 +537,14 @@ struct rproc_dump_segment { * @table_sz: size of @cached_table * @has_iommu: flag to indicate if remote processor is behind an MMU * @auto_boot: flag to indicate if remote processor should be auto-started + * @sysfs_read_only: flag to make remoteproc sysfs files read only * @dump_segments: list of segments in the firmware * @nb_vdev: number of vdev currently handled by rproc * @elf_class: firmware ELF class * @elf_machine: firmware ELF machine * @cdev: character device of the rproc * @cdev_put_on_release: flag to indicate if remoteproc should be shutdown on @char_dev release + * @features: indicate remoteproc features */ struct rproc { struct list_head node; @@ -562,12 +578,14 @@ struct rproc { size_t table_sz; bool has_iommu; bool auto_boot; + bool sysfs_read_only; struct list_head dump_segments; int nb_vdev; u8 elf_class; u16 elf_machine; struct cdev cdev; bool cdev_put_on_release; + DECLARE_BITMAP(features, RPROC_MAX_FEATURES); }; /** @@ -595,7 +613,7 @@ struct rproc_subdev { /** * struct rproc_vring - remoteproc vring state * @va: virtual address - * @len: length, in bytes + * @num: vring size * @da: device address * @align: vring alignment * @notifyid: rproc-specific unique vring index @@ -604,7 +622,7 @@ struct rproc_subdev { */ struct rproc_vring { void *va; - int len; + int num; u32 da; u32 align; int notifyid; @@ -614,9 +632,8 @@ struct rproc_vring { /** * struct rproc_vdev - remoteproc state for a supported virtio device - * @refcount: reference counter for the vdev and vring allocations * @subdev: handle for registering the vdev as a rproc subdevice - * @dev: device struct used for reference count semantics + * @pdev: remoteproc virtio platform device * @id: virtio device id (as in virtio_ids.h) * @node: list node * @rproc: the rproc handle @@ -625,10 +642,9 @@ struct rproc_vring { * @index: vdev position versus other vdev declared in resource table */ struct rproc_vdev { - struct kref refcount; struct rproc_subdev subdev; - struct device dev; + struct platform_device *pdev; unsigned int id; struct list_head node; @@ -669,10 +685,11 @@ rproc_of_resm_mem_entry_init(struct device *dev, u32 of_resm_idx, size_t len, u32 da, const char *name, ...); int rproc_boot(struct rproc *rproc); -void rproc_shutdown(struct rproc *rproc); +int rproc_shutdown(struct rproc *rproc); int rproc_detach(struct rproc *rproc); int rproc_set_firmware(struct rproc *rproc, const char *fw_name); void rproc_report_crash(struct rproc *rproc, enum rproc_crash_type type); +void *rproc_da_to_va(struct rproc *rproc, u64 da, size_t len, bool *is_iomem); void rproc_coredump_using_sections(struct rproc *rproc); int rproc_coredump_add_segment(struct rproc *rproc, dma_addr_t da, size_t size); int rproc_coredump_add_custom_segment(struct rproc *rproc, diff --git a/include/linux/remoteproc/mtk_scp.h b/include/linux/remoteproc/mtk_scp.h index b47416f7aeb8..7c2b7cc9fe6c 100644 --- a/include/linux/remoteproc/mtk_scp.h +++ b/include/linux/remoteproc/mtk_scp.h @@ -41,6 +41,8 @@ enum scp_ipi_id { SCP_IPI_ISP_FRAME, SCP_IPI_FD_CMD, SCP_IPI_CROS_HOST_CMD, + SCP_IPI_VDEC_LAT, + SCP_IPI_VDEC_CORE, SCP_IPI_NS_SERVICE = 0xFF, SCP_IPI_MAX = 0x100, }; diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h index 21deb5212bbd..0cf5b20c6ddf 100644 --- a/include/linux/resctrl.h +++ b/include/linux/resctrl.h @@ -15,6 +15,9 @@ int proc_resctrl_show(struct seq_file *m, #endif +/* max value for struct rdt_domain's mbps_val */ +#define MBA_MAX_MBPS U32_MAX + /** * enum resctrl_conf_type - The type of configuration. * @CDP_NONE: No prioritisation, both code and data are controlled or monitored. @@ -29,6 +32,16 @@ enum resctrl_conf_type { #define CDP_NUM_TYPES (CDP_DATA + 1) +/* + * Event IDs, the values match those used to program IA32_QM_EVTSEL before + * reading IA32_QM_CTR on RDT systems. + */ +enum resctrl_event_id { + QOS_L3_OCCUP_EVENT_ID = 0x01, + QOS_L3_MBM_TOTAL_EVENT_ID = 0x02, + QOS_L3_MBM_LOCAL_EVENT_ID = 0x03, +}; + /** * struct resctrl_staged_config - parsed configuration to be applied * @new_ctrl: new ctrl value to be loaded @@ -53,6 +66,9 @@ struct resctrl_staged_config { * @cqm_work_cpu: worker CPU for CQM h/w counters * @plr: pseudo-locked region (if any) associated with domain * @staged_config: parsed configuration to be applied + * @mbps_val: When mba_sc is enabled, this holds the array of user + * specified control values for mba_sc in MBps, indexed + * by closid */ struct rdt_domain { struct list_head list; @@ -67,6 +83,7 @@ struct rdt_domain { int cqm_work_cpu; struct pseudo_lock_region *plr; struct resctrl_staged_config staged_config[CDP_NUM_TYPES]; + u32 *mbps_val; }; /** @@ -130,8 +147,6 @@ struct resctrl_schema; /** * struct rdt_resource - attributes of a resctrl resource * @rid: The index of the resource - * @alloc_enabled: Is allocation enabled on this machine - * @mon_enabled: Is monitoring enabled for this feature * @alloc_capable: Is allocation available on this machine * @mon_capable: Is monitor feature available on this machine * @num_rmid: Number of RMIDs available @@ -150,8 +165,6 @@ struct resctrl_schema; */ struct rdt_resource { int rid; - bool alloc_enabled; - bool mon_enabled; bool alloc_capable; bool mon_capable; int num_rmid; @@ -194,7 +207,50 @@ struct resctrl_schema { /* The number of closid supported by this resource regardless of CDP */ u32 resctrl_arch_get_num_closid(struct rdt_resource *r); int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid); + +/* + * Update the ctrl_val and apply this config right now. + * Must be called on one of the domain's CPUs. + */ +int resctrl_arch_update_one(struct rdt_resource *r, struct rdt_domain *d, + u32 closid, enum resctrl_conf_type t, u32 cfg_val); + u32 resctrl_arch_get_config(struct rdt_resource *r, struct rdt_domain *d, u32 closid, enum resctrl_conf_type type); +int resctrl_online_domain(struct rdt_resource *r, struct rdt_domain *d); +void resctrl_offline_domain(struct rdt_resource *r, struct rdt_domain *d); + +/** + * resctrl_arch_rmid_read() - Read the eventid counter corresponding to rmid + * for this resource and domain. + * @r: resource that the counter should be read from. + * @d: domain that the counter should be read from. + * @rmid: rmid of the counter to read. + * @eventid: eventid to read, e.g. L3 occupancy. + * @val: result of the counter read in bytes. + * + * Call from process context on a CPU that belongs to domain @d. + * + * Return: + * 0 on success, or -EIO, -EINVAL etc on error. + */ +int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d, + u32 rmid, enum resctrl_event_id eventid, u64 *val); + +/** + * resctrl_arch_reset_rmid() - Reset any private state associated with rmid + * and eventid. + * @r: The domain's resource. + * @d: The rmid's domain. + * @rmid: The rmid whose counter values should be reset. + * @eventid: The eventid whose counter values should be reset. + * + * This can be called from any CPU. + */ +void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_domain *d, + u32 rmid, enum resctrl_event_id eventid); + +extern unsigned int resctrl_rmid_realloc_threshold; +extern unsigned int resctrl_rmid_realloc_limit; #endif /* _RESCTRL_H */ diff --git a/include/linux/reset.h b/include/linux/reset.h index db0e6115a2f6..514ddf003efc 100644 --- a/include/linux/reset.h +++ b/include/linux/reset.h @@ -455,6 +455,26 @@ static inline struct reset_control *of_reset_control_get_exclusive( } /** + * of_reset_control_get_optional_exclusive - Lookup and obtain an optional exclusive + * reference to a reset controller. + * @node: device to be reset by the controller + * @id: reset line name + * + * Optional variant of of_reset_control_get_exclusive(). If the requested reset + * is not specified in the device tree, this function returns NULL instead of + * an error. + * + * Returns a struct reset_control or IS_ERR() condition containing errno. + * + * Use of id names is optional. + */ +static inline struct reset_control *of_reset_control_get_optional_exclusive( + struct device_node *node, const char *id) +{ + return __of_reset_control_get(node, id, 0, false, true, true); +} + +/** * of_reset_control_get_shared - Lookup and obtain a shared reference * to a reset controller. * @node: device to be reset by the controller @@ -711,7 +731,7 @@ static inline int __must_check devm_reset_control_bulk_get_optional_exclusive(struct device *dev, int num_rstcs, struct reset_control_bulk_data *rstcs) { - return __devm_reset_control_bulk_get(dev, num_rstcs, rstcs, true, false, true); + return __devm_reset_control_bulk_get(dev, num_rstcs, rstcs, false, true, true); } /** diff --git a/include/linux/reset/bcm63xx_pmb.h b/include/linux/reset/bcm63xx_pmb.h index bb4af7b5eb36..c77b6999518a 100644 --- a/include/linux/reset/bcm63xx_pmb.h +++ b/include/linux/reset/bcm63xx_pmb.h @@ -1,17 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * Broadcom BCM63xx Processor Monitor Bus shared routines (SMP and reset) * * Copyright (C) 2015, Broadcom Corporation * Author: Florian Fainelli <f.fainelli@gmail.com> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation version 2. - * - * This program is distributed "as is" WITHOUT ANY WARRANTY of any - * kind, whether express or implied; without even the implied warranty - * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. */ #ifndef __BCM63XX_PMB_H #define __BCM63XX_PMB_H diff --git a/include/linux/resource.h b/include/linux/resource.h index bdf491cbcab7..4fdbc0c3f315 100644 --- a/include/linux/resource.h +++ b/include/linux/resource.h @@ -8,7 +8,5 @@ struct task_struct; void getrusage(struct task_struct *p, int who, struct rusage *ru); -int do_prlimit(struct task_struct *tsk, unsigned int resource, - struct rlimit *new_rlim, struct rlimit *old_rlim); #endif diff --git a/include/linux/resume_user_mode.h b/include/linux/resume_user_mode.h new file mode 100644 index 000000000000..285189454449 --- /dev/null +++ b/include/linux/resume_user_mode.h @@ -0,0 +1,64 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef LINUX_RESUME_USER_MODE_H +#define LINUX_RESUME_USER_MODE_H + +#include <linux/sched.h> +#include <linux/task_work.h> +#include <linux/memcontrol.h> +#include <linux/blk-cgroup.h> + +/** + * set_notify_resume - cause resume_user_mode_work() to be called + * @task: task that will call resume_user_mode_work() + * + * Calling this arranges that @task will call resume_user_mode_work() + * before returning to user mode. If it's already running in user mode, + * it will enter the kernel and call resume_user_mode_work() soon. + * If it's blocked, it will not be woken. + */ +static inline void set_notify_resume(struct task_struct *task) +{ + if (!test_and_set_tsk_thread_flag(task, TIF_NOTIFY_RESUME)) + kick_process(task); +} + + +/** + * resume_user_mode_work - Perform work before returning to user mode + * @regs: user-mode registers of @current task + * + * This is called when %TIF_NOTIFY_RESUME has been set. Now we are + * about to return to user mode, and the user state in @regs can be + * inspected or adjusted. The caller in arch code has cleared + * %TIF_NOTIFY_RESUME before the call. If the flag gets set again + * asynchronously, this will be called again before we return to + * user mode. + * + * Called without locks. + */ +static inline void resume_user_mode_work(struct pt_regs *regs) +{ + clear_thread_flag(TIF_NOTIFY_RESUME); + /* + * This barrier pairs with task_work_add()->set_notify_resume() after + * hlist_add_head(task->task_works); + */ + smp_mb__after_atomic(); + if (unlikely(task_work_pending(current))) + task_work_run(); + +#ifdef CONFIG_KEYS_REQUEST_CACHE + if (unlikely(current->cached_requested_key)) { + key_put(current->cached_requested_key); + current->cached_requested_key = NULL; + } +#endif + + mem_cgroup_handle_over_high(); + blkcg_maybe_throttle_current(); + + rseq_handle_notify_resume(NULL, regs); +} + +#endif /* LINUX_RESUME_USER_MODE_H */ diff --git a/include/linux/rethook.h b/include/linux/rethook.h new file mode 100644 index 000000000000..c8ac1e5afcd1 --- /dev/null +++ b/include/linux/rethook.h @@ -0,0 +1,100 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Return hooking with list-based shadow stack. + */ +#ifndef _LINUX_RETHOOK_H +#define _LINUX_RETHOOK_H + +#include <linux/compiler.h> +#include <linux/freelist.h> +#include <linux/kallsyms.h> +#include <linux/llist.h> +#include <linux/rcupdate.h> +#include <linux/refcount.h> + +struct rethook_node; + +typedef void (*rethook_handler_t) (struct rethook_node *, void *, struct pt_regs *); + +/** + * struct rethook - The rethook management data structure. + * @data: The user-defined data storage. + * @handler: The user-defined return hook handler. + * @pool: The pool of struct rethook_node. + * @ref: The reference counter. + * @rcu: The rcu_head for deferred freeing. + * + * Don't embed to another data structure, because this is a self-destructive + * data structure when all rethook_node are freed. + */ +struct rethook { + void *data; + rethook_handler_t handler; + struct freelist_head pool; + refcount_t ref; + struct rcu_head rcu; +}; + +/** + * struct rethook_node - The rethook shadow-stack entry node. + * @freelist: The freelist, linked to struct rethook::pool. + * @rcu: The rcu_head for deferred freeing. + * @llist: The llist, linked to a struct task_struct::rethooks. + * @rethook: The pointer to the struct rethook. + * @ret_addr: The storage for the real return address. + * @frame: The storage for the frame pointer. + * + * You can embed this to your extended data structure to store any data + * on each entry of the shadow stack. + */ +struct rethook_node { + union { + struct freelist_node freelist; + struct rcu_head rcu; + }; + struct llist_node llist; + struct rethook *rethook; + unsigned long ret_addr; + unsigned long frame; +}; + +struct rethook *rethook_alloc(void *data, rethook_handler_t handler); +void rethook_free(struct rethook *rh); +void rethook_add_node(struct rethook *rh, struct rethook_node *node); +struct rethook_node *rethook_try_get(struct rethook *rh); +void rethook_recycle(struct rethook_node *node); +void rethook_hook(struct rethook_node *node, struct pt_regs *regs, bool mcount); +unsigned long rethook_find_ret_addr(struct task_struct *tsk, unsigned long frame, + struct llist_node **cur); + +/* Arch dependent code must implement arch_* and trampoline code */ +void arch_rethook_prepare(struct rethook_node *node, struct pt_regs *regs, bool mcount); +void arch_rethook_trampoline(void); + +/** + * is_rethook_trampoline() - Check whether the address is rethook trampoline + * @addr: The address to be checked + * + * Return true if the @addr is the rethook trampoline address. + */ +static inline bool is_rethook_trampoline(unsigned long addr) +{ + return addr == (unsigned long)dereference_symbol_descriptor(arch_rethook_trampoline); +} + +/* If the architecture needs to fixup the return address, implement it. */ +void arch_rethook_fixup_return(struct pt_regs *regs, + unsigned long correct_ret_addr); + +/* Generic trampoline handler, arch code must prepare asm stub */ +unsigned long rethook_trampoline_handler(struct pt_regs *regs, + unsigned long frame); + +#ifdef CONFIG_RETHOOK +void rethook_flush_task(struct task_struct *tk); +#else +#define rethook_flush_task(tsk) do { } while (0) +#endif + +#endif + diff --git a/include/linux/rfkill.h b/include/linux/rfkill.h index c35f3962dc4f..373003ace639 100644 --- a/include/linux/rfkill.h +++ b/include/linux/rfkill.h @@ -308,6 +308,11 @@ static inline bool rfkill_blocked(struct rfkill *rfkill) return false; } +static inline bool rfkill_soft_blocked(struct rfkill *rfkill) +{ + return false; +} + static inline enum rfkill_type rfkill_find_type(const char *name) { return RFKILL_TYPE_ALL; diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h index dac53fd3afea..2504df9a0453 100644 --- a/include/linux/ring_buffer.h +++ b/include/linux/ring_buffer.h @@ -101,7 +101,7 @@ __ring_buffer_alloc(unsigned long size, unsigned flags, struct lock_class_key *k int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full); __poll_t ring_buffer_poll_wait(struct trace_buffer *buffer, int cpu, struct file *filp, poll_table *poll_table); - +void ring_buffer_wake_waiters(struct trace_buffer *buffer, int cpu); #define RING_BUFFER_ALL_CPUS -1 diff --git a/include/linux/rio_ids.h b/include/linux/rio_ids.h index 4846f72759b2..c7e2f21dd5c1 100644 --- a/include/linux/rio_ids.h +++ b/include/linux/rio_ids.h @@ -9,18 +9,6 @@ #ifndef LINUX_RIO_IDS_H #define LINUX_RIO_IDS_H -#define RIO_VID_FREESCALE 0x0002 -#define RIO_DID_MPC8560 0x0003 - -#define RIO_VID_TUNDRA 0x000d -#define RIO_DID_TSI500 0x0500 -#define RIO_DID_TSI568 0x0568 -#define RIO_DID_TSI572 0x0572 -#define RIO_DID_TSI574 0x0574 -#define RIO_DID_TSI576 0x0578 /* Same ID as Tsi578 */ -#define RIO_DID_TSI577 0x0577 -#define RIO_DID_TSI578 0x0578 - #define RIO_VID_IDT 0x0038 #define RIO_DID_IDT70K200 0x0310 #define RIO_DID_IDTCPS8 0x035c @@ -33,7 +21,6 @@ #define RIO_DID_IDTCPS1616 0x0379 #define RIO_DID_IDTVPS1616 0x0377 #define RIO_DID_IDTSPS1616 0x0378 -#define RIO_DID_TSI721 0x80ab #define RIO_DID_IDTRXS1632 0x80e5 #define RIO_DID_IDTRXS2448 0x80e6 diff --git a/include/linux/rmap.h b/include/linux/rmap.h index e704b1a4c06c..bd3504d11b15 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -11,6 +11,8 @@ #include <linux/rwsem.h> #include <linux/memcontrol.h> #include <linux/highmem.h> +#include <linux/pagemap.h> +#include <linux/memremap.h> /* * The anon_vma heads a list of private "related" vmas, to scan if @@ -39,12 +41,15 @@ struct anon_vma { atomic_t refcount; /* - * Count of child anon_vmas and VMAs which points to this anon_vma. + * Count of child anon_vmas. Equals to the count of all anon_vmas that + * have ->parent pointing to this one, including itself. * * This counter is used for making decision about reusing anon_vma * instead of forking new one. See comments in function anon_vma_clone. */ - unsigned degree; + unsigned long num_children; + /* Count of VMAs whose ->anon_vma pointer points to this object. */ + unsigned long num_active_vmas; struct anon_vma *parent; /* Parent of this anon_vma */ @@ -126,6 +131,11 @@ static inline void anon_vma_lock_read(struct anon_vma *anon_vma) down_read(&anon_vma->root->rwsem); } +static inline int anon_vma_trylock_read(struct anon_vma *anon_vma) +{ + return down_read_trylock(&anon_vma->root->rwsem); +} + static inline void anon_vma_unlock_read(struct anon_vma *anon_vma) { up_read(&anon_vma->root->rwsem); @@ -156,43 +166,199 @@ static inline void anon_vma_merge(struct vm_area_struct *vma, unlink_anon_vmas(next); } -struct anon_vma *page_get_anon_vma(struct page *page); +struct anon_vma *folio_get_anon_vma(struct folio *folio); + +/* RMAP flags, currently only relevant for some anon rmap operations. */ +typedef int __bitwise rmap_t; + +/* + * No special request: if the page is a subpage of a compound page, it is + * mapped via a PTE. The mapped (sub)page is possibly shared between processes. + */ +#define RMAP_NONE ((__force rmap_t)0) + +/* The (sub)page is exclusive to a single process. */ +#define RMAP_EXCLUSIVE ((__force rmap_t)BIT(0)) -/* bitflags for do_page_add_anon_rmap() */ -#define RMAP_EXCLUSIVE 0x01 -#define RMAP_COMPOUND 0x02 +/* + * The compound page is not mapped via PTEs, but instead via a single PMD and + * should be accounted accordingly. + */ +#define RMAP_COMPOUND ((__force rmap_t)BIT(1)) /* * rmap interfaces called when adding or removing pte of page */ void page_move_anon_rmap(struct page *, struct vm_area_struct *); void page_add_anon_rmap(struct page *, struct vm_area_struct *, - unsigned long, bool); -void do_page_add_anon_rmap(struct page *, struct vm_area_struct *, - unsigned long, int); + unsigned long address, rmap_t flags); void page_add_new_anon_rmap(struct page *, struct vm_area_struct *, - unsigned long, bool); -void page_add_file_rmap(struct page *, bool); -void page_remove_rmap(struct page *, bool); + unsigned long address); +void page_add_file_rmap(struct page *, struct vm_area_struct *, + bool compound); +void page_remove_rmap(struct page *, struct vm_area_struct *, + bool compound); void hugepage_add_anon_rmap(struct page *, struct vm_area_struct *, - unsigned long); + unsigned long address, rmap_t flags); void hugepage_add_new_anon_rmap(struct page *, struct vm_area_struct *, - unsigned long); + unsigned long address); -static inline void page_dup_rmap(struct page *page, bool compound) +static inline void __page_dup_rmap(struct page *page, bool compound) { atomic_inc(compound ? compound_mapcount_ptr(page) : &page->_mapcount); } +static inline void page_dup_file_rmap(struct page *page, bool compound) +{ + __page_dup_rmap(page, compound); +} + +/** + * page_try_dup_anon_rmap - try duplicating a mapping of an already mapped + * anonymous page + * @page: the page to duplicate the mapping for + * @compound: the page is mapped as compound or as a small page + * @vma: the source vma + * + * The caller needs to hold the PT lock and the vma->vma_mm->write_protect_seq. + * + * Duplicating the mapping can only fail if the page may be pinned; device + * private pages cannot get pinned and consequently this function cannot fail. + * + * If duplicating the mapping succeeds, the page has to be mapped R/O into + * the parent and the child. It must *not* get mapped writable after this call. + * + * Returns 0 if duplicating the mapping succeeded. Returns -EBUSY otherwise. + */ +static inline int page_try_dup_anon_rmap(struct page *page, bool compound, + struct vm_area_struct *vma) +{ + VM_BUG_ON_PAGE(!PageAnon(page), page); + + /* + * No need to check+clear for already shared pages, including KSM + * pages. + */ + if (!PageAnonExclusive(page)) + goto dup; + + /* + * If this page may have been pinned by the parent process, + * don't allow to duplicate the mapping but instead require to e.g., + * copy the page immediately for the child so that we'll always + * guarantee the pinned page won't be randomly replaced in the + * future on write faults. + */ + if (likely(!is_device_private_page(page) && + unlikely(page_needs_cow_for_dma(vma, page)))) + return -EBUSY; + + ClearPageAnonExclusive(page); + /* + * It's okay to share the anon page between both processes, mapping + * the page R/O into both processes. + */ +dup: + __page_dup_rmap(page, compound); + return 0; +} + +/** + * page_try_share_anon_rmap - try marking an exclusive anonymous page possibly + * shared to prepare for KSM or temporary unmapping + * @page: the exclusive anonymous page to try marking possibly shared + * + * The caller needs to hold the PT lock and has to have the page table entry + * cleared/invalidated. + * + * This is similar to page_try_dup_anon_rmap(), however, not used during fork() + * to duplicate a mapping, but instead to prepare for KSM or temporarily + * unmapping a page (swap, migration) via page_remove_rmap(). + * + * Marking the page shared can only fail if the page may be pinned; device + * private pages cannot get pinned and consequently this function cannot fail. + * + * Returns 0 if marking the page possibly shared succeeded. Returns -EBUSY + * otherwise. + */ +static inline int page_try_share_anon_rmap(struct page *page) +{ + VM_BUG_ON_PAGE(!PageAnon(page) || !PageAnonExclusive(page), page); + + /* device private pages cannot get pinned via GUP. */ + if (unlikely(is_device_private_page(page))) { + ClearPageAnonExclusive(page); + return 0; + } + + /* + * We have to make sure that when we clear PageAnonExclusive, that + * the page is not pinned and that concurrent GUP-fast won't succeed in + * concurrently pinning the page. + * + * Conceptually, PageAnonExclusive clearing consists of: + * (A1) Clear PTE + * (A2) Check if the page is pinned; back off if so. + * (A3) Clear PageAnonExclusive + * (A4) Restore PTE (optional, but certainly not writable) + * + * When clearing PageAnonExclusive, we cannot possibly map the page + * writable again, because anon pages that may be shared must never + * be writable. So in any case, if the PTE was writable it cannot + * be writable anymore afterwards and there would be a PTE change. Only + * if the PTE wasn't writable, there might not be a PTE change. + * + * Conceptually, GUP-fast pinning of an anon page consists of: + * (B1) Read the PTE + * (B2) FOLL_WRITE: check if the PTE is not writable; back off if so. + * (B3) Pin the mapped page + * (B4) Check if the PTE changed by re-reading it; back off if so. + * (B5) If the original PTE is not writable, check if + * PageAnonExclusive is not set; back off if so. + * + * If the PTE was writable, we only have to make sure that GUP-fast + * observes a PTE change and properly backs off. + * + * If the PTE was not writable, we have to make sure that GUP-fast either + * detects a (temporary) PTE change or that PageAnonExclusive is cleared + * and properly backs off. + * + * Consequently, when clearing PageAnonExclusive(), we have to make + * sure that (A1), (A2)/(A3) and (A4) happen in the right memory + * order. In GUP-fast pinning code, we have to make sure that (B3),(B4) + * and (B5) happen in the right memory order. + * + * We assume that there might not be a memory barrier after + * clearing/invalidating the PTE (A1) and before restoring the PTE (A4), + * so we use explicit ones here. + */ + + /* Paired with the memory barrier in try_grab_folio(). */ + if (IS_ENABLED(CONFIG_HAVE_FAST_GUP)) + smp_mb(); + + if (unlikely(page_maybe_dma_pinned(page))) + return -EBUSY; + ClearPageAnonExclusive(page); + + /* + * This is conceptually a smp_wmb() paired with the smp_rmb() in + * gup_must_unshare(). + */ + if (IS_ENABLED(CONFIG_HAVE_FAST_GUP)) + smp_mb__after_atomic(); + return 0; +} + /* * Called from mm/vmscan.c to handle paging out */ -int page_referenced(struct page *, int is_locked, +int folio_referenced(struct folio *, int is_locked, struct mem_cgroup *memcg, unsigned long *vm_flags); -void try_to_migrate(struct page *page, enum ttu_flags flags); -void try_to_unmap(struct page *, enum ttu_flags flags); +void try_to_migrate(struct folio *folio, enum ttu_flags flags); +void try_to_unmap(struct folio *, enum ttu_flags flags); int make_device_exclusive_range(struct mm_struct *mm, unsigned long start, unsigned long end, struct page **pages, @@ -200,11 +366,13 @@ int make_device_exclusive_range(struct mm_struct *mm, unsigned long start, /* Avoid racy checks */ #define PVMW_SYNC (1 << 0) -/* Look for migarion entries rather than present PTEs */ +/* Look for migration entries rather than present PTEs */ #define PVMW_MIGRATION (1 << 1) struct page_vma_mapped_walk { - struct page *page; + unsigned long pfn; + unsigned long nr_pages; + pgoff_t pgoff; struct vm_area_struct *vma; unsigned long address; pmd_t *pmd; @@ -213,10 +381,30 @@ struct page_vma_mapped_walk { unsigned int flags; }; +#define DEFINE_PAGE_VMA_WALK(name, _page, _vma, _address, _flags) \ + struct page_vma_mapped_walk name = { \ + .pfn = page_to_pfn(_page), \ + .nr_pages = compound_nr(_page), \ + .pgoff = page_to_pgoff(_page), \ + .vma = _vma, \ + .address = _address, \ + .flags = _flags, \ + } + +#define DEFINE_FOLIO_VMA_WALK(name, _folio, _vma, _address, _flags) \ + struct page_vma_mapped_walk name = { \ + .pfn = folio_pfn(_folio), \ + .nr_pages = folio_nr_pages(_folio), \ + .pgoff = folio_pgoff(_folio), \ + .vma = _vma, \ + .address = _address, \ + .flags = _flags, \ + } + static inline void page_vma_mapped_walk_done(struct page_vma_mapped_walk *pvmw) { /* HugeTLB pte is set to the relevant page table entry without pte_mapped. */ - if (pvmw->pte && !PageHuge(pvmw->page)) + if (pvmw->pte && !is_vm_hugetlb_page(pvmw->vma)) pte_unmap(pvmw->pte); if (pvmw->ptl) spin_unlock(pvmw->ptl); @@ -237,25 +425,19 @@ unsigned long page_address_in_vma(struct page *, struct vm_area_struct *); */ int folio_mkclean(struct folio *); -/* - * called in munlock()/munmap() path to check for other vmas holding - * the page mlocked. - */ -void page_mlock(struct page *page); +int pfn_mkclean_range(unsigned long pfn, unsigned long nr_pages, pgoff_t pgoff, + struct vm_area_struct *vma); -void remove_migration_ptes(struct page *old, struct page *new, bool locked); +void remove_migration_ptes(struct folio *src, struct folio *dst, bool locked); -/* - * Called by memory-failure.c to kill processes. - */ -struct anon_vma *page_lock_anon_vma_read(struct page *page); -void page_unlock_anon_vma_read(struct anon_vma *anon_vma); int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma); /* * rmap_walk_control: To control rmap traversing for specific needs * * arg: passed to rmap_one() and invalid_vma() + * try_lock: bail out if the rmap lock is contended + * contended: indicate the rmap traversal bailed out due to lock contention * rmap_one: executed on each vma where page is mapped * done: for checking traversing termination condition * anon_lock: for getting anon_lock by optimized way rather than default @@ -263,19 +445,24 @@ int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma); */ struct rmap_walk_control { void *arg; + bool try_lock; + bool contended; /* * Return false if page table scanning in rmap_walk should be stopped. * Otherwise, return true. */ - bool (*rmap_one)(struct page *page, struct vm_area_struct *vma, + bool (*rmap_one)(struct folio *folio, struct vm_area_struct *vma, unsigned long addr, void *arg); - int (*done)(struct page *page); - struct anon_vma *(*anon_lock)(struct page *page); + int (*done)(struct folio *folio); + struct anon_vma *(*anon_lock)(struct folio *folio, + struct rmap_walk_control *rwc); bool (*invalid_vma)(struct vm_area_struct *vma, void *arg); }; -void rmap_walk(struct page *page, struct rmap_walk_control *rwc); -void rmap_walk_locked(struct page *page, struct rmap_walk_control *rwc); +void rmap_walk(struct folio *folio, struct rmap_walk_control *rwc); +void rmap_walk_locked(struct folio *folio, struct rmap_walk_control *rwc); +struct anon_vma *folio_lock_anon_vma_read(struct folio *folio, + struct rmap_walk_control *rwc); #else /* !CONFIG_MMU */ @@ -283,7 +470,7 @@ void rmap_walk_locked(struct page *page, struct rmap_walk_control *rwc); #define anon_vma_prepare(vma) (0) #define anon_vma_link(vma) do {} while (0) -static inline int page_referenced(struct page *page, int is_locked, +static inline int folio_referenced(struct folio *folio, int is_locked, struct mem_cgroup *memcg, unsigned long *vm_flags) { @@ -291,7 +478,7 @@ static inline int page_referenced(struct page *page, int is_locked, return 0; } -static inline void try_to_unmap(struct page *page, enum ttu_flags flags) +static inline void try_to_unmap(struct folio *folio, enum ttu_flags flags) { } diff --git a/include/linux/rpmsg.h b/include/linux/rpmsg.h index 02fa9116cd60..523c98b96cb4 100644 --- a/include/linux/rpmsg.h +++ b/include/linux/rpmsg.h @@ -41,7 +41,9 @@ struct rpmsg_channel_info { * rpmsg_device - device that belong to the rpmsg bus * @dev: the device struct * @id: device id (used to match between rpmsg drivers and devices) - * @driver_override: driver name to force a match + * @driver_override: driver name to force a match; do not set directly, + * because core frees it; use driver_set_override() to + * set or clear it. * @src: local address * @dst: destination address * @ept: the rpmsg endpoint of this channel @@ -51,7 +53,7 @@ struct rpmsg_channel_info { struct rpmsg_device { struct device dev; struct rpmsg_device_id id; - char *driver_override; + const char *driver_override; u32 src; u32 dst; struct rpmsg_endpoint *ept; @@ -163,6 +165,8 @@ static inline __rpmsg64 cpu_to_rpmsg64(struct rpmsg_device *rpdev, u64 val) #if IS_ENABLED(CONFIG_RPMSG) +int rpmsg_register_device_override(struct rpmsg_device *rpdev, + const char *driver_override); int rpmsg_register_device(struct rpmsg_device *rpdev); int rpmsg_unregister_device(struct device *parent, struct rpmsg_channel_info *chinfo); @@ -190,6 +194,12 @@ ssize_t rpmsg_get_mtu(struct rpmsg_endpoint *ept); #else +static inline int rpmsg_register_device_override(struct rpmsg_device *rpdev, + const char *driver_override) +{ + return -ENXIO; +} + static inline int rpmsg_register_device(struct rpmsg_device *rpdev) { return -ENXIO; diff --git a/include/linux/rtc.h b/include/linux/rtc.h index 47fd1c2d3a57..1fd9c6a21ebe 100644 --- a/include/linux/rtc.h +++ b/include/linux/rtc.h @@ -110,8 +110,6 @@ struct rtc_device { struct hrtimer pie_timer; /* sub second exp, so needs hrtimer */ int pie_enabled; struct work_struct irqwork; - /* Some hardware can't support UIE mode */ - int uie_unsupported; /* * This offset specifies the update timing of the RTC. diff --git a/include/linux/rtc/ds1685.h b/include/linux/rtc/ds1685.h index 67ee9d20cc5a..5a41c3bbcbe3 100644 --- a/include/linux/rtc/ds1685.h +++ b/include/linux/rtc/ds1685.h @@ -46,7 +46,6 @@ struct ds1685_priv { u32 regstep; int irq_num; bool bcd_mode; - bool no_irq; u8 (*read)(struct ds1685_priv *, int); void (*write)(struct ds1685_priv *, int, u8); void (*prepare_poweroff)(void); diff --git a/include/linux/rtmutex.h b/include/linux/rtmutex.h index 9deedfeec2b1..7d049883a08a 100644 --- a/include/linux/rtmutex.h +++ b/include/linux/rtmutex.h @@ -99,13 +99,22 @@ extern void __rt_mutex_init(struct rt_mutex *lock, const char *name, struct lock #ifdef CONFIG_DEBUG_LOCK_ALLOC extern void rt_mutex_lock_nested(struct rt_mutex *lock, unsigned int subclass); +extern void _rt_mutex_lock_nest_lock(struct rt_mutex *lock, struct lockdep_map *nest_lock); #define rt_mutex_lock(lock) rt_mutex_lock_nested(lock, 0) +#define rt_mutex_lock_nest_lock(lock, nest_lock) \ + do { \ + typecheck(struct lockdep_map *, &(nest_lock)->dep_map); \ + _rt_mutex_lock_nest_lock(lock, &(nest_lock)->dep_map); \ + } while (0) + #else extern void rt_mutex_lock(struct rt_mutex *lock); #define rt_mutex_lock_nested(lock, subclass) rt_mutex_lock(lock) +#define rt_mutex_lock_nest_lock(lock, nest_lock) rt_mutex_lock(lock) #endif extern int rt_mutex_lock_interruptible(struct rt_mutex *lock); +extern int rt_mutex_lock_killable(struct rt_mutex *lock); extern int rt_mutex_trylock(struct rt_mutex *lock); extern void rt_mutex_unlock(struct rt_mutex *lock); diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index bb9cb84114c1..ae2c6a3cec5d 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -100,6 +100,7 @@ void net_dec_ingress_queue(void); #ifdef CONFIG_NET_EGRESS void net_inc_egress_queue(void); void net_dec_egress_queue(void); +void netdev_xmit_skip_txqueue(bool skip); #endif void rtnetlink_init(void); @@ -134,4 +135,7 @@ extern int ndo_dflt_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, int (*vlan_fill)(struct sk_buff *skb, struct net_device *dev, u32 filter_mask)); + +extern void rtnl_offload_xstats_notify(struct net_device *dev); + #endif /* __LINUX_RTNETLINK_H */ diff --git a/include/linux/rtsx_pci.h b/include/linux/rtsx_pci.h index 4ab7bfc675f1..534038d962e4 100644 --- a/include/linux/rtsx_pci.h +++ b/include/linux/rtsx_pci.h @@ -1067,6 +1067,9 @@ #define PCR_SETTING_REG1 0x724 #define PCR_SETTING_REG2 0x814 #define PCR_SETTING_REG3 0x747 +#define PCR_SETTING_REG4 0x818 +#define PCR_SETTING_REG5 0x81C + #define rtsx_pci_init_cmd(pcr) ((pcr)->ci = 0) @@ -1095,7 +1098,7 @@ struct pcr_ops { unsigned int (*cd_deglitch)(struct rtsx_pcr *pcr); int (*conv_clk_and_div_n)(int clk, int dir); void (*fetch_vendor_settings)(struct rtsx_pcr *pcr); - void (*force_power_down)(struct rtsx_pcr *pcr, u8 pm_state); + void (*force_power_down)(struct rtsx_pcr *pcr, u8 pm_state, bool runtime); void (*stop_cmd)(struct rtsx_pcr *pcr); void (*set_aspm)(struct rtsx_pcr *pcr, bool enable); @@ -1201,8 +1204,6 @@ struct rtsx_pcr { unsigned int card_exist; struct delayed_work carddet_work; - struct delayed_work idle_work; - struct delayed_work rtd3_work; spinlock_t lock; struct mutex pcr_mutex; @@ -1212,7 +1213,6 @@ struct rtsx_pcr { unsigned int cur_clock; bool remove_pci; bool msi_en; - bool is_runtime_suspended; #define EXTRA_CAPS_SD_SDR50 (1 << 0) #define EXTRA_CAPS_SD_SDR104 (1 << 1) diff --git a/include/linux/rtsx_usb.h b/include/linux/rtsx_usb.h index 159729cffd8e..3247ed8e9ff0 100644 --- a/include/linux/rtsx_usb.h +++ b/include/linux/rtsx_usb.h @@ -54,8 +54,6 @@ struct rtsx_ucr { struct usb_device *pusb_dev; struct usb_interface *pusb_intf; struct usb_sg_request current_sg; - unsigned char *iobuf; - dma_addr_t iobuf_dma; struct timer_list sg_timer; struct mutex dev_mutex; diff --git a/include/linux/rv.h b/include/linux/rv.h new file mode 100644 index 000000000000..8883b41d88ec --- /dev/null +++ b/include/linux/rv.h @@ -0,0 +1,70 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Runtime Verification. + * + * For futher information, see: kernel/trace/rv/rv.c. + */ +#ifndef _LINUX_RV_H +#define _LINUX_RV_H + +#define MAX_DA_NAME_LEN 24 + +#ifdef CONFIG_RV +/* + * Deterministic automaton per-object variables. + */ +struct da_monitor { + bool monitoring; + unsigned int curr_state; +}; + +/* + * Per-task RV monitors count. Nowadays fixed in RV_PER_TASK_MONITORS. + * If we find justification for more monitors, we can think about + * adding more or developing a dynamic method. So far, none of + * these are justified. + */ +#define RV_PER_TASK_MONITORS 1 +#define RV_PER_TASK_MONITOR_INIT (RV_PER_TASK_MONITORS) + +/* + * Futher monitor types are expected, so make this a union. + */ +union rv_task_monitor { + struct da_monitor da_mon; +}; + +#ifdef CONFIG_RV_REACTORS +struct rv_reactor { + const char *name; + const char *description; + void (*react)(char *msg); +}; +#endif + +struct rv_monitor { + const char *name; + const char *description; + bool enabled; + int (*enable)(void); + void (*disable)(void); + void (*reset)(void); +#ifdef CONFIG_RV_REACTORS + void (*react)(char *msg); +#endif +}; + +bool rv_monitoring_on(void); +int rv_unregister_monitor(struct rv_monitor *monitor); +int rv_register_monitor(struct rv_monitor *monitor); +int rv_get_task_monitor_slot(void); +void rv_put_task_monitor_slot(int slot); + +#ifdef CONFIG_RV_REACTORS +bool rv_reacting_on(void); +int rv_unregister_reactor(struct rv_reactor *reactor); +int rv_register_reactor(struct rv_reactor *reactor); +#endif /* CONFIG_RV_REACTORS */ + +#endif /* CONFIG_RV */ +#endif /* _LINUX_RV_H */ diff --git a/include/linux/rwlock.h b/include/linux/rwlock.h index 2c0ad417ce3c..c0ef596f340b 100644 --- a/include/linux/rwlock.h +++ b/include/linux/rwlock.h @@ -1,7 +1,7 @@ #ifndef __LINUX_RWLOCK_H #define __LINUX_RWLOCK_H -#ifndef __LINUX_SPINLOCK_H +#ifndef __LINUX_INSIDE_SPINLOCK_H # error "please don't include this file directly" #endif @@ -55,6 +55,12 @@ do { \ #define write_lock(lock) _raw_write_lock(lock) #define read_lock(lock) _raw_read_lock(lock) +#ifdef CONFIG_DEBUG_LOCK_ALLOC +#define write_lock_nested(lock, subclass) _raw_write_lock_nested(lock, subclass) +#else +#define write_lock_nested(lock, subclass) _raw_write_lock(lock) +#endif + #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) #define read_lock_irqsave(lock, flags) \ diff --git a/include/linux/rwlock_api_smp.h b/include/linux/rwlock_api_smp.h index f1db6f17c4fb..dceb0a59b692 100644 --- a/include/linux/rwlock_api_smp.h +++ b/include/linux/rwlock_api_smp.h @@ -17,6 +17,7 @@ void __lockfunc _raw_read_lock(rwlock_t *lock) __acquires(lock); void __lockfunc _raw_write_lock(rwlock_t *lock) __acquires(lock); +void __lockfunc _raw_write_lock_nested(rwlock_t *lock, int subclass) __acquires(lock); void __lockfunc _raw_read_lock_bh(rwlock_t *lock) __acquires(lock); void __lockfunc _raw_write_lock_bh(rwlock_t *lock) __acquires(lock); void __lockfunc _raw_read_lock_irq(rwlock_t *lock) __acquires(lock); @@ -209,6 +210,13 @@ static inline void __raw_write_lock(rwlock_t *lock) LOCK_CONTENDED(lock, do_raw_write_trylock, do_raw_write_lock); } +static inline void __raw_write_lock_nested(rwlock_t *lock, int subclass) +{ + preempt_disable(); + rwlock_acquire(&lock->dep_map, subclass, 0, _RET_IP_); + LOCK_CONTENDED(lock, do_raw_write_trylock, do_raw_write_lock); +} + #endif /* !CONFIG_GENERIC_LOCKBREAK || CONFIG_DEBUG_LOCK_ALLOC */ static inline void __raw_write_unlock(rwlock_t *lock) diff --git a/include/linux/rwlock_rt.h b/include/linux/rwlock_rt.h index 49c1f3842ed5..8544ff05e594 100644 --- a/include/linux/rwlock_rt.h +++ b/include/linux/rwlock_rt.h @@ -28,6 +28,7 @@ extern void rt_read_lock(rwlock_t *rwlock); extern int rt_read_trylock(rwlock_t *rwlock); extern void rt_read_unlock(rwlock_t *rwlock); extern void rt_write_lock(rwlock_t *rwlock); +extern void rt_write_lock_nested(rwlock_t *rwlock, int subclass); extern int rt_write_trylock(rwlock_t *rwlock); extern void rt_write_unlock(rwlock_t *rwlock); @@ -83,6 +84,15 @@ static __always_inline void write_lock(rwlock_t *rwlock) rt_write_lock(rwlock); } +#ifdef CONFIG_DEBUG_LOCK_ALLOC +static __always_inline void write_lock_nested(rwlock_t *rwlock, int subclass) +{ + rt_write_lock_nested(rwlock, subclass); +} +#else +#define write_lock_nested(lock, subclass) rt_write_lock(((void)(subclass), (lock))) +#endif + static __always_inline void write_lock_bh(rwlock_t *rwlock) { local_bh_disable(); diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h index f9348769e558..efa5c324369a 100644 --- a/include/linux/rwsem.h +++ b/include/linux/rwsem.h @@ -230,7 +230,7 @@ extern void _down_write_nest_lock(struct rw_semaphore *sem, struct lockdep_map * do { \ typecheck(struct lockdep_map *, &(nest_lock)->dep_map); \ _down_write_nest_lock(sem, &(nest_lock)->dep_map); \ -} while (0); +} while (0) /* * Take/release a lock when not the owner will release it. diff --git a/include/linux/sbitmap.h b/include/linux/sbitmap.h index fc0357a6e19b..4d2d5205ab58 100644 --- a/include/linux/sbitmap.h +++ b/include/linux/sbitmap.h @@ -28,14 +28,9 @@ struct seq_file; */ struct sbitmap_word { /** - * @depth: Number of bits being used in @word/@cleared - */ - unsigned long depth; - - /** * @word: word holding free bits */ - unsigned long word ____cacheline_aligned_in_smp; + unsigned long word; /** * @cleared: word holding cleared bits @@ -140,7 +135,7 @@ struct sbitmap_queue { /** * @min_shallow_depth: The minimum shallow depth which may be passed to - * sbitmap_queue_get_shallow() or __sbitmap_queue_get_shallow(). + * sbitmap_queue_get_shallow() */ unsigned int min_shallow_depth; }; @@ -164,6 +159,14 @@ struct sbitmap_queue { int sbitmap_init_node(struct sbitmap *sb, unsigned int depth, int shift, gfp_t flags, int node, bool round_robin, bool alloc_hint); +/* sbitmap internal helper */ +static inline unsigned int __map_depth(const struct sbitmap *sb, int index) +{ + if (index == sb->map_nr - 1) + return sb->depth - (index << sb->shift); + return 1U << sb->shift; +} + /** * sbitmap_free() - Free memory used by a &struct sbitmap. * @sb: Bitmap to free. @@ -171,7 +174,7 @@ int sbitmap_init_node(struct sbitmap *sb, unsigned int depth, int shift, static inline void sbitmap_free(struct sbitmap *sb) { free_percpu(sb->alloc_hint); - kfree(sb->map); + kvfree(sb->map); sb->map = NULL; } @@ -251,7 +254,7 @@ static inline void __sbitmap_for_each_set(struct sbitmap *sb, while (scanned < sb->depth) { unsigned long word; unsigned int depth = min_t(unsigned int, - sb->map[index].depth - nr, + __map_depth(sb, index) - nr, sb->depth - scanned); scanned += depth; @@ -416,6 +419,17 @@ static inline void sbitmap_queue_free(struct sbitmap_queue *sbq) } /** + * sbitmap_queue_recalculate_wake_batch() - Recalculate wake batch + * @sbq: Bitmap queue to recalculate wake batch. + * @users: Number of shares. + * + * Like sbitmap_queue_update_wake_batch(), this will calculate wake batch + * by depth. This interface is for HCTX shared tags or queue shared tags. + */ +void sbitmap_queue_recalculate_wake_batch(struct sbitmap_queue *sbq, + unsigned int users); + +/** * sbitmap_queue_resize() - Resize a &struct sbitmap_queue. * @sbq: Bitmap queue to resize. * @depth: New number of bits to resize to. @@ -449,7 +463,7 @@ unsigned long __sbitmap_queue_get_batch(struct sbitmap_queue *sbq, int nr_tags, unsigned int *offset); /** - * __sbitmap_queue_get_shallow() - Try to allocate a free bit from a &struct + * sbitmap_queue_get_shallow() - Try to allocate a free bit from a &struct * sbitmap_queue, limiting the depth used from each word, with preemption * already disabled. * @sbq: Bitmap queue to allocate from. @@ -461,8 +475,8 @@ unsigned long __sbitmap_queue_get_batch(struct sbitmap_queue *sbq, int nr_tags, * * Return: Non-negative allocated bit number if successful, -1 otherwise. */ -int __sbitmap_queue_get_shallow(struct sbitmap_queue *sbq, - unsigned int shallow_depth); +int sbitmap_queue_get_shallow(struct sbitmap_queue *sbq, + unsigned int shallow_depth); /** * sbitmap_queue_get() - Try to allocate a free bit from a &struct @@ -485,32 +499,6 @@ static inline int sbitmap_queue_get(struct sbitmap_queue *sbq, } /** - * sbitmap_queue_get_shallow() - Try to allocate a free bit from a &struct - * sbitmap_queue, limiting the depth used from each word. - * @sbq: Bitmap queue to allocate from. - * @cpu: Output parameter; will contain the CPU we ran on (e.g., to be passed to - * sbitmap_queue_clear()). - * @shallow_depth: The maximum number of bits to allocate from a single word. - * See sbitmap_get_shallow(). - * - * If you call this, make sure to call sbitmap_queue_min_shallow_depth() after - * initializing @sbq. - * - * Return: Non-negative allocated bit number if successful, -1 otherwise. - */ -static inline int sbitmap_queue_get_shallow(struct sbitmap_queue *sbq, - unsigned int *cpu, - unsigned int shallow_depth) -{ - int nr; - - *cpu = get_cpu(); - nr = __sbitmap_queue_get_shallow(sbq, shallow_depth); - put_cpu(); - return nr; -} - -/** * sbitmap_queue_min_shallow_depth() - Inform a &struct sbitmap_queue of the * minimum shallow depth that will be used. * @sbq: Bitmap queue in question. @@ -587,8 +575,9 @@ void sbitmap_queue_wake_all(struct sbitmap_queue *sbq); * sbitmap_queue_wake_up() - Wake up some of waiters in one waitqueue * on a &struct sbitmap_queue. * @sbq: Bitmap queue to wake up. + * @nr: Number of bits cleared. */ -void sbitmap_queue_wake_up(struct sbitmap_queue *sbq); +void sbitmap_queue_wake_up(struct sbitmap_queue *sbq, int nr); /** * sbitmap_queue_show() - Dump &struct sbitmap_queue information to a &struct diff --git a/include/linux/scatterlist.h b/include/linux/scatterlist.h index 266754a55327..375a5e90d86a 100644 --- a/include/linux/scatterlist.h +++ b/include/linux/scatterlist.h @@ -16,6 +16,9 @@ struct scatterlist { #ifdef CONFIG_NEED_SG_DMA_LENGTH unsigned int dma_length; #endif +#ifdef CONFIG_PCI_P2PDMA + unsigned int dma_flags; +#endif }; /* @@ -69,10 +72,27 @@ struct sg_append_table { * a valid sg entry, or whether it points to the start of a new scatterlist. * Those low bits are there for everyone! (thanks mason :-) */ -#define sg_is_chain(sg) ((sg)->page_link & SG_CHAIN) -#define sg_is_last(sg) ((sg)->page_link & SG_END) -#define sg_chain_ptr(sg) \ - ((struct scatterlist *) ((sg)->page_link & ~(SG_CHAIN | SG_END))) +#define SG_PAGE_LINK_MASK (SG_CHAIN | SG_END) + +static inline unsigned int __sg_flags(struct scatterlist *sg) +{ + return sg->page_link & SG_PAGE_LINK_MASK; +} + +static inline struct scatterlist *sg_chain_ptr(struct scatterlist *sg) +{ + return (struct scatterlist *)(sg->page_link & ~SG_PAGE_LINK_MASK); +} + +static inline bool sg_is_chain(struct scatterlist *sg) +{ + return __sg_flags(sg) & SG_CHAIN; +} + +static inline bool sg_is_last(struct scatterlist *sg) +{ + return __sg_flags(sg) & SG_END; +} /** * sg_assign_page - Assign a given page to an SG entry @@ -92,7 +112,7 @@ static inline void sg_assign_page(struct scatterlist *sg, struct page *page) * In order for the low bit stealing approach to work, pages * must be aligned at a 32-bit boundary as a minimum. */ - BUG_ON((unsigned long) page & (SG_CHAIN | SG_END)); + BUG_ON((unsigned long)page & SG_PAGE_LINK_MASK); #ifdef CONFIG_DEBUG_SG BUG_ON(sg_is_chain(sg)); #endif @@ -126,7 +146,7 @@ static inline struct page *sg_page(struct scatterlist *sg) #ifdef CONFIG_DEBUG_SG BUG_ON(sg_is_chain(sg)); #endif - return (struct page *)((sg)->page_link & ~(SG_CHAIN | SG_END)); + return (struct page *)((sg)->page_link & ~SG_PAGE_LINK_MASK); } /** @@ -228,6 +248,72 @@ static inline void sg_unmark_end(struct scatterlist *sg) sg->page_link &= ~SG_END; } +/* + * CONFGI_PCI_P2PDMA depends on CONFIG_64BIT which means there is 4 bytes + * in struct scatterlist (assuming also CONFIG_NEED_SG_DMA_LENGTH is set). + * Use this padding for DMA flags bits to indicate when a specific + * dma address is a bus address. + */ +#ifdef CONFIG_PCI_P2PDMA + +#define SG_DMA_BUS_ADDRESS (1 << 0) + +/** + * sg_dma_is_bus address - Return whether a given segment was marked + * as a bus address + * @sg: SG entry + * + * Description: + * Returns true if sg_dma_mark_bus_address() has been called on + * this segment. + **/ +static inline bool sg_is_dma_bus_address(struct scatterlist *sg) +{ + return sg->dma_flags & SG_DMA_BUS_ADDRESS; +} + +/** + * sg_dma_mark_bus address - Mark the scatterlist entry as a bus address + * @sg: SG entry + * + * Description: + * Marks the passed in sg entry to indicate that the dma_address is + * a bus address and doesn't need to be unmapped. This should only be + * used by dma_map_sg() implementations to mark bus addresses + * so they can be properly cleaned up in dma_unmap_sg(). + **/ +static inline void sg_dma_mark_bus_address(struct scatterlist *sg) +{ + sg->dma_flags |= SG_DMA_BUS_ADDRESS; +} + +/** + * sg_unmark_bus_address - Unmark the scatterlist entry as a bus address + * @sg: SG entry + * + * Description: + * Clears the bus address mark. + **/ +static inline void sg_dma_unmark_bus_address(struct scatterlist *sg) +{ + sg->dma_flags &= ~SG_DMA_BUS_ADDRESS; +} + +#else + +static inline bool sg_is_dma_bus_address(struct scatterlist *sg) +{ + return false; +} +static inline void sg_dma_mark_bus_address(struct scatterlist *sg) +{ +} +static inline void sg_dma_unmark_bus_address(struct scatterlist *sg) +{ +} + +#endif + /** * sg_phys - Return physical address of an sg entry * @sg: SG entry diff --git a/include/linux/sched.h b/include/linux/sched.h index 4d0a12618e3c..ffb6eb55cd13 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -14,6 +14,7 @@ #include <linux/pid.h> #include <linux/sem.h> #include <linux/shm.h> +#include <linux/kmsan_types.h> #include <linux/mutex.h> #include <linux/plist.h> #include <linux/hrtimer.h> @@ -34,6 +35,7 @@ #include <linux/rseq.h> #include <linux/seqlock.h> #include <linux/kcsan.h> +#include <linux/rv.h> #include <asm/kmap_size.h> /* task_struct member predeclarations (sorted alphabetically): */ @@ -80,30 +82,39 @@ struct task_group; */ /* Used in tsk->state: */ -#define TASK_RUNNING 0x0000 -#define TASK_INTERRUPTIBLE 0x0001 -#define TASK_UNINTERRUPTIBLE 0x0002 -#define __TASK_STOPPED 0x0004 -#define __TASK_TRACED 0x0008 +#define TASK_RUNNING 0x00000000 +#define TASK_INTERRUPTIBLE 0x00000001 +#define TASK_UNINTERRUPTIBLE 0x00000002 +#define __TASK_STOPPED 0x00000004 +#define __TASK_TRACED 0x00000008 /* Used in tsk->exit_state: */ -#define EXIT_DEAD 0x0010 -#define EXIT_ZOMBIE 0x0020 +#define EXIT_DEAD 0x00000010 +#define EXIT_ZOMBIE 0x00000020 #define EXIT_TRACE (EXIT_ZOMBIE | EXIT_DEAD) /* Used in tsk->state again: */ -#define TASK_PARKED 0x0040 -#define TASK_DEAD 0x0080 -#define TASK_WAKEKILL 0x0100 -#define TASK_WAKING 0x0200 -#define TASK_NOLOAD 0x0400 -#define TASK_NEW 0x0800 -/* RT specific auxilliary flag to mark RT lock waiters */ -#define TASK_RTLOCK_WAIT 0x1000 -#define TASK_STATE_MAX 0x2000 +#define TASK_PARKED 0x00000040 +#define TASK_DEAD 0x00000080 +#define TASK_WAKEKILL 0x00000100 +#define TASK_WAKING 0x00000200 +#define TASK_NOLOAD 0x00000400 +#define TASK_NEW 0x00000800 +#define TASK_RTLOCK_WAIT 0x00001000 +#define TASK_FREEZABLE 0x00002000 +#define __TASK_FREEZABLE_UNSAFE (0x00004000 * IS_ENABLED(CONFIG_LOCKDEP)) +#define TASK_FROZEN 0x00008000 +#define TASK_STATE_MAX 0x00010000 + +#define TASK_ANY (TASK_STATE_MAX-1) + +/* + * DO NOT ADD ANY NEW USERS ! + */ +#define TASK_FREEZABLE_UNSAFE (TASK_FREEZABLE | __TASK_FREEZABLE_UNSAFE) /* Convenience macros for the sake of set_current_state: */ #define TASK_KILLABLE (TASK_WAKEKILL | TASK_UNINTERRUPTIBLE) #define TASK_STOPPED (TASK_WAKEKILL | __TASK_STOPPED) -#define TASK_TRACED (TASK_WAKEKILL | __TASK_TRACED) +#define TASK_TRACED __TASK_TRACED #define TASK_IDLE (TASK_UNINTERRUPTIBLE | TASK_NOLOAD) @@ -118,11 +129,9 @@ struct task_group; #define task_is_running(task) (READ_ONCE((task)->__state) == TASK_RUNNING) -#define task_is_traced(task) ((READ_ONCE(task->__state) & __TASK_TRACED) != 0) - -#define task_is_stopped(task) ((READ_ONCE(task->__state) & __TASK_STOPPED) != 0) - -#define task_is_stopped_or_traced(task) ((READ_ONCE(task->__state) & (__TASK_STOPPED | __TASK_TRACED)) != 0) +#define task_is_traced(task) ((READ_ONCE(task->jobctl) & JOBCTL_TRACED) != 0) +#define task_is_stopped(task) ((READ_ONCE(task->jobctl) & JOBCTL_STOPPED) != 0) +#define task_is_stopped_or_traced(task) ((READ_ONCE(task->jobctl) & (JOBCTL_STOPPED | JOBCTL_TRACED)) != 0) /* * Special states are those that do not use the normal wait-loop pattern. See @@ -274,8 +283,13 @@ struct task_group; #define get_current_state() READ_ONCE(current->__state) -/* Task command name length: */ -#define TASK_COMM_LEN 16 +/* + * Define the task command name length as enum, then it can be visible to + * BPF programs. + */ +enum { + TASK_COMM_LEN = 16, +}; extern void scheduler_tick(void); @@ -614,10 +628,6 @@ struct sched_dl_entity { * task has to wait for a replenishment to be performed at the * next firing of dl_timer. * - * @dl_boosted tells if we are boosted due to DI. If so we are - * outside bandwidth enforcement mechanism (but only until we - * exit the critical section); - * * @dl_yielded tells if task gave up the CPU before consuming * all its available runtime during the last job. * @@ -844,8 +854,9 @@ struct task_struct { int trc_reader_nesting; int trc_ipi_to_cpu; union rcu_special trc_reader_special; - bool trc_reader_checked; struct list_head trc_holdout_list; + struct list_head trc_blkd_node; + int trc_blkd_cpu; #endif /* #ifdef CONFIG_TASKS_TRACE_RCU */ struct sched_info sched_info; @@ -859,9 +870,6 @@ struct task_struct { struct mm_struct *mm; struct mm_struct *active_mm; - /* Per-thread vma caching: */ - struct vmacache vmacache; - #ifdef SPLIT_RSS_COUNTING struct task_rss_stat rss_stat; #endif @@ -913,6 +921,10 @@ struct task_struct { #ifdef CONFIG_MEMCG unsigned in_user_fault:1; #endif +#ifdef CONFIG_LRU_GEN + /* whether the LRU algorithm may apply to this access */ + unsigned in_lru_fault:1; +#endif #ifdef CONFIG_COMPAT_BRK unsigned brk_randomized:1; #endif @@ -935,7 +947,17 @@ struct task_struct { #endif #ifdef CONFIG_EVENTFD /* Recursion prevention for eventfd_signal() */ - unsigned in_eventfd_signal:1; + unsigned in_eventfd:1; +#endif +#ifdef CONFIG_IOMMU_SVA + unsigned pasid_activated:1; +#endif +#ifdef CONFIG_CPU_SUP_INTEL + unsigned reported_split_lock:1; +#endif +#ifdef CONFIG_TASK_DELAY_ACCT + /* delay due to memory thrashing */ + unsigned in_thrashing:1; #endif unsigned long atomic_flags; /* Flags requiring atomic access. */ @@ -991,8 +1013,8 @@ struct task_struct { /* CLONE_CHILD_CLEARTID: */ int __user *clear_child_tid; - /* PF_IO_WORKER */ - void *pf_io_worker; + /* PF_KTHREAD | PF_IO_WORKER */ + void *worker_private; u64 utime; u64 stime; @@ -1348,6 +1370,10 @@ struct task_struct { #endif #endif +#ifdef CONFIG_KMSAN + struct kmsan_ctx kmsan_ctx; +#endif + #if IS_ENABLED(CONFIG_KUNIT) struct kunit *kunit_test; #endif @@ -1374,9 +1400,6 @@ struct task_struct { #endif #ifdef CONFIG_TRACING - /* State flags for use by tracers: */ - unsigned long trace; - /* Bitmask and counter of trace recursion: */ unsigned long trace_recursion; #endif /* CONFIG_TRACING */ @@ -1439,6 +1462,7 @@ struct task_struct { int pagefault_disabled; #ifdef CONFIG_MMU struct task_struct *oom_reaper_list; + struct timer_list oom_reaper_timer; #endif #ifdef CONFIG_VMAP_STACK struct vm_struct *stack_vm_area; @@ -1480,6 +1504,9 @@ struct task_struct { #ifdef CONFIG_KRETPROBES struct llist_head kretprobe_instances; #endif +#ifdef CONFIG_RETHOOK + struct llist_head rethooks; +#endif #ifdef CONFIG_ARCH_HAS_PARANOID_L1D_FLUSH /* @@ -1491,6 +1518,16 @@ struct task_struct { struct callback_head l1d_flush_kill; #endif +#ifdef CONFIG_RV + /* + * Per-task RV monitor. Nowadays fixed in RV_PER_TASK_MONITORS. + * If we find justification for more monitors, we can think + * about adding more or developing a dynamic method. So far, + * none of these are justified. + */ + union rv_task_monitor rv[RV_PER_TASK_MONITORS]; +#endif + /* * New fields for task_struct should be added above here, so that * they are included in the randomized portion of task_struct. @@ -1619,19 +1656,32 @@ static inline pid_t task_pgrp_nr(struct task_struct *tsk) #define TASK_REPORT_IDLE (TASK_REPORT + 1) #define TASK_REPORT_MAX (TASK_REPORT_IDLE << 1) -static inline unsigned int task_state_index(struct task_struct *tsk) +static inline unsigned int __task_state_index(unsigned int tsk_state, + unsigned int tsk_exit_state) { - unsigned int tsk_state = READ_ONCE(tsk->__state); - unsigned int state = (tsk_state | tsk->exit_state) & TASK_REPORT; + unsigned int state = (tsk_state | tsk_exit_state) & TASK_REPORT; BUILD_BUG_ON_NOT_POWER_OF_2(TASK_REPORT_MAX); if (tsk_state == TASK_IDLE) state = TASK_REPORT_IDLE; + /* + * We're lying here, but rather than expose a completely new task state + * to userspace, we can make this appear as if the task has gone through + * a regular rt_mutex_lock() call. + */ + if (tsk_state == TASK_RTLOCK_WAIT) + state = TASK_UNINTERRUPTIBLE; + return fls(state); } +static inline unsigned int task_state_index(struct task_struct *tsk) +{ + return __task_state_index(READ_ONCE(tsk->__state), tsk->exit_state); +} + static inline char task_index_to_char(unsigned int state) { static const char state_char[] = "RSDTtXZPI"; @@ -1679,9 +1729,9 @@ extern struct pid *cad_pid; #define PF_MEMALLOC 0x00000800 /* Allocating memory */ #define PF_NPROC_EXCEEDED 0x00001000 /* set_user() noticed that RLIMIT_NPROC was exceeded */ #define PF_USED_MATH 0x00002000 /* If unset the fpu must be initialized before use */ -#define PF_USED_ASYNC 0x00004000 /* Used async_schedule*(), used by module init */ +#define PF__HOLE__00004000 0x00004000 #define PF_NOFREEZE 0x00008000 /* This thread should not be frozen */ -#define PF_FROZEN 0x00010000 /* Frozen for system suspend */ +#define PF__HOLE__00010000 0x00010000 #define PF_KSWAPD 0x00020000 /* I am kswapd */ #define PF_MEMALLOC_NOFS 0x00040000 /* All allocation requests will inherit GFP_NOFS */ #define PF_MEMALLOC_NOIO 0x00080000 /* All allocation requests will inherit GFP_NOIO */ @@ -1689,11 +1739,14 @@ extern struct pid *cad_pid; * I am cleaning dirty pages from some other bdi. */ #define PF_KTHREAD 0x00200000 /* I am a kernel thread */ #define PF_RANDOMIZE 0x00400000 /* Randomize virtual address space */ -#define PF_SWAPWRITE 0x00800000 /* Allowed to write to swap */ +#define PF__HOLE__00800000 0x00800000 +#define PF__HOLE__01000000 0x01000000 +#define PF__HOLE__02000000 0x02000000 #define PF_NO_SETAFFINITY 0x04000000 /* Userland is not allowed to meddle with cpus_mask */ #define PF_MCE_EARLY 0x08000000 /* Early kill for mce process policy */ #define PF_MEMALLOC_PIN 0x10000000 /* Allocation context constrained to zones which allow long term pinning. */ -#define PF_FREEZER_SKIP 0x40000000 /* Freezer should not count it as freezable */ +#define PF__HOLE__20000000 0x20000000 +#define PF__HOLE__40000000 0x40000000 #define PF_SUSPEND_TASK 0x80000000 /* This thread called freeze_processes() and should not be frozen */ /* @@ -1793,7 +1846,7 @@ current_restore_flags(unsigned long orig_flags, unsigned long flags) } extern int cpuset_cpumask_can_shrink(const struct cpumask *cur, const struct cpumask *trial); -extern int task_can_attach(struct task_struct *p, const struct cpumask *cs_cpus_allowed); +extern int task_can_attach(struct task_struct *p, const struct cpumask *cs_effective_cpus); #ifdef CONFIG_SMP extern void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask); extern int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask); @@ -2015,7 +2068,7 @@ static inline int test_tsk_need_resched(struct task_struct *tsk) #if !defined(CONFIG_PREEMPTION) || defined(CONFIG_PREEMPT_DYNAMIC) extern int __cond_resched(void); -#ifdef CONFIG_PREEMPT_DYNAMIC +#if defined(CONFIG_PREEMPT_DYNAMIC) && defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL) DECLARE_STATIC_CALL(cond_resched, __cond_resched); @@ -2024,6 +2077,14 @@ static __always_inline int _cond_resched(void) return static_call_mod(cond_resched)(); } +#elif defined(CONFIG_PREEMPT_DYNAMIC) && defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY) +extern int dynamic_cond_resched(void); + +static __always_inline int _cond_resched(void) +{ + return dynamic_cond_resched(); +} + #else static inline int _cond_resched(void) @@ -2091,6 +2152,47 @@ static inline void cond_resched_rcu(void) #endif } +#ifdef CONFIG_PREEMPT_DYNAMIC + +extern bool preempt_model_none(void); +extern bool preempt_model_voluntary(void); +extern bool preempt_model_full(void); + +#else + +static inline bool preempt_model_none(void) +{ + return IS_ENABLED(CONFIG_PREEMPT_NONE); +} +static inline bool preempt_model_voluntary(void) +{ + return IS_ENABLED(CONFIG_PREEMPT_VOLUNTARY); +} +static inline bool preempt_model_full(void) +{ + return IS_ENABLED(CONFIG_PREEMPT); +} + +#endif + +static inline bool preempt_model_rt(void) +{ + return IS_ENABLED(CONFIG_PREEMPT_RT); +} + +/* + * Does the preemption model allow non-cooperative preemption? + * + * For !CONFIG_PREEMPT_DYNAMIC kernels this is an exact match with + * CONFIG_PREEMPTION; for CONFIG_PREEMPT_DYNAMIC this doesn't work as the + * kernel is *built* with CONFIG_PREEMPTION=y but may run with e.g. the + * PREEMPT_NONE model. + */ +static inline bool preempt_model_preemptible(void) +{ + return preempt_model_full() || preempt_model_rt(); +} + /* * Does a critical section need to be broken due to another * task waiting?: (technically does not depend on CONFIG_PREEMPTION, @@ -2154,6 +2256,7 @@ static inline void set_task_cpu(struct task_struct *p, unsigned int cpu) extern bool sched_task_on_rq(struct task_struct *p); extern unsigned long get_wchan(struct task_struct *p); +extern struct task_struct *cpu_curr_snapshot(int cpu); /* * In order to reduce various lock holder preemption latencies provide an @@ -2178,8 +2281,17 @@ extern long sched_getaffinity(pid_t pid, struct cpumask *mask); #endif #ifdef CONFIG_SMP +static inline bool owner_on_cpu(struct task_struct *owner) +{ + /* + * As lock holder preemption issue, we both skip spinning if + * task is not on cpu or its cpu is preempted + */ + return READ_ONCE(owner->on_cpu) && !vcpu_is_preempted(task_cpu(owner)); +} + /* Returns effective CPU energy utilization, as seen by the scheduler */ -unsigned long sched_cpu_util(int cpu, unsigned long max); +unsigned long sched_cpu_util(int cpu); #endif /* CONFIG_SMP */ #ifdef CONFIG_RSEQ @@ -2302,20 +2414,6 @@ static inline void rseq_syscall(struct pt_regs *regs) #endif -const struct sched_avg *sched_trace_cfs_rq_avg(struct cfs_rq *cfs_rq); -char *sched_trace_cfs_rq_path(struct cfs_rq *cfs_rq, char *str, int len); -int sched_trace_cfs_rq_cpu(struct cfs_rq *cfs_rq); - -const struct sched_avg *sched_trace_rq_avg_rt(struct rq *rq); -const struct sched_avg *sched_trace_rq_avg_dl(struct rq *rq); -const struct sched_avg *sched_trace_rq_avg_irq(struct rq *rq); - -int sched_trace_rq_cpu(struct rq *rq); -int sched_trace_rq_cpu_capacity(struct rq *rq); -int sched_trace_rq_nr_running(struct rq *rq); - -const struct cpumask *sched_trace_rd_span(struct root_domain *rd); - #ifdef CONFIG_SCHED_CORE extern void sched_core_free(struct task_struct *tsk); extern void sched_core_fork(struct task_struct *p); @@ -2326,4 +2424,6 @@ static inline void sched_core_free(struct task_struct *tsk) { } static inline void sched_core_fork(struct task_struct *p) { } #endif +extern void sched_set_stop_task(int cpu, struct task_struct *stop); + #endif diff --git a/include/linux/sched/affinity.h b/include/linux/sched/affinity.h new file mode 100644 index 000000000000..227f5be81bcd --- /dev/null +++ b/include/linux/sched/affinity.h @@ -0,0 +1 @@ +#include <linux/sched.h> diff --git a/include/linux/sched/cond_resched.h b/include/linux/sched/cond_resched.h new file mode 100644 index 000000000000..227f5be81bcd --- /dev/null +++ b/include/linux/sched/cond_resched.h @@ -0,0 +1 @@ +#include <linux/sched.h> diff --git a/include/linux/sched/coredump.h b/include/linux/sched/coredump.h index 4d9e3a656875..8270ad7ae14c 100644 --- a/include/linux/sched/coredump.h +++ b/include/linux/sched/coredump.h @@ -57,7 +57,8 @@ static inline int get_dumpable(struct mm_struct *mm) #endif /* leave room for more dump flags */ #define MMF_VM_MERGEABLE 16 /* KSM may merge identical pages */ -#define MMF_VM_HUGEPAGE 17 /* set when VM_HUGEPAGE is set on vma */ +#define MMF_VM_HUGEPAGE 17 /* set when mm is available for + khugepaged */ /* * This one-shot flag is dropped due to necessity of changing exe once again * on NFS restore @@ -70,9 +71,8 @@ static inline int get_dumpable(struct mm_struct *mm) #define MMF_UNSTABLE 22 /* mm is unstable for copy_from_user */ #define MMF_HUGE_ZERO_PAGE 23 /* mm has ever used the global huge zero page */ #define MMF_DISABLE_THP 24 /* disable THP for all VMAs */ -#define MMF_OOM_VICTIM 25 /* mm is the oom victim */ -#define MMF_OOM_REAP_QUEUED 26 /* mm was queued for oom_reaper */ -#define MMF_MULTIPROCESS 27 /* mm is shared between processes */ +#define MMF_OOM_REAP_QUEUED 25 /* mm was queued for oom_reaper */ +#define MMF_MULTIPROCESS 26 /* mm is shared between processes */ /* * MMF_HAS_PINNED: Whether this mm has pinned any pages. This can be either * replaced in the future by mm.pinned_vm when it becomes stable, or grow into @@ -80,7 +80,7 @@ static inline int get_dumpable(struct mm_struct *mm) * pinned pages were unpinned later on, we'll still keep this bit set for the * lifecycle of this mm, just for simplicity. */ -#define MMF_HAS_PINNED 28 /* FOLL_PIN has run, never cleared */ +#define MMF_HAS_PINNED 27 /* FOLL_PIN has run, never cleared */ #define MMF_DISABLE_THP_MASK (1 << MMF_DISABLE_THP) #define MMF_INIT_MASK (MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK |\ diff --git a/include/linux/sched/deadline.h b/include/linux/sched/deadline.h index 1aff00b65f3c..7c83d4d5a971 100644 --- a/include/linux/sched/deadline.h +++ b/include/linux/sched/deadline.h @@ -6,6 +6,8 @@ * NORMAL/BATCH tasks. */ +#include <linux/sched.h> + #define MAX_DL_PRIO 0 static inline int dl_prio(int prio) diff --git a/include/linux/sched/isolation.h b/include/linux/sched/isolation.h index cc9f393e2a70..8c15abd67aed 100644 --- a/include/linux/sched/isolation.h +++ b/include/linux/sched/isolation.h @@ -5,54 +5,55 @@ #include <linux/init.h> #include <linux/tick.h> -enum hk_flags { - HK_FLAG_TIMER = 1, - HK_FLAG_RCU = (1 << 1), - HK_FLAG_MISC = (1 << 2), - HK_FLAG_SCHED = (1 << 3), - HK_FLAG_TICK = (1 << 4), - HK_FLAG_DOMAIN = (1 << 5), - HK_FLAG_WQ = (1 << 6), - HK_FLAG_MANAGED_IRQ = (1 << 7), - HK_FLAG_KTHREAD = (1 << 8), +enum hk_type { + HK_TYPE_TIMER, + HK_TYPE_RCU, + HK_TYPE_MISC, + HK_TYPE_SCHED, + HK_TYPE_TICK, + HK_TYPE_DOMAIN, + HK_TYPE_WQ, + HK_TYPE_MANAGED_IRQ, + HK_TYPE_KTHREAD, + HK_TYPE_MAX }; #ifdef CONFIG_CPU_ISOLATION DECLARE_STATIC_KEY_FALSE(housekeeping_overridden); -extern int housekeeping_any_cpu(enum hk_flags flags); -extern const struct cpumask *housekeeping_cpumask(enum hk_flags flags); -extern bool housekeeping_enabled(enum hk_flags flags); -extern void housekeeping_affine(struct task_struct *t, enum hk_flags flags); -extern bool housekeeping_test_cpu(int cpu, enum hk_flags flags); +extern int housekeeping_any_cpu(enum hk_type type); +extern const struct cpumask *housekeeping_cpumask(enum hk_type type); +extern bool housekeeping_enabled(enum hk_type type); +extern void housekeeping_affine(struct task_struct *t, enum hk_type type); +extern bool housekeeping_test_cpu(int cpu, enum hk_type type); extern void __init housekeeping_init(void); #else -static inline int housekeeping_any_cpu(enum hk_flags flags) +static inline int housekeeping_any_cpu(enum hk_type type) { return smp_processor_id(); } -static inline const struct cpumask *housekeeping_cpumask(enum hk_flags flags) +static inline const struct cpumask *housekeeping_cpumask(enum hk_type type) { return cpu_possible_mask; } -static inline bool housekeeping_enabled(enum hk_flags flags) +static inline bool housekeeping_enabled(enum hk_type type) { return false; } static inline void housekeeping_affine(struct task_struct *t, - enum hk_flags flags) { } + enum hk_type type) { } static inline void housekeeping_init(void) { } #endif /* CONFIG_CPU_ISOLATION */ -static inline bool housekeeping_cpu(int cpu, enum hk_flags flags) +static inline bool housekeeping_cpu(int cpu, enum hk_type type) { #ifdef CONFIG_CPU_ISOLATION if (static_branch_unlikely(&housekeeping_overridden)) - return housekeeping_test_cpu(cpu, flags); + return housekeeping_test_cpu(cpu, type); #endif return true; } diff --git a/include/linux/sched/jobctl.h b/include/linux/sched/jobctl.h index fa067de9f1a9..68876d0a7ef9 100644 --- a/include/linux/sched/jobctl.h +++ b/include/linux/sched/jobctl.h @@ -19,6 +19,10 @@ struct task_struct; #define JOBCTL_TRAPPING_BIT 21 /* switching to TRACED */ #define JOBCTL_LISTENING_BIT 22 /* ptracer is listening for events */ #define JOBCTL_TRAP_FREEZE_BIT 23 /* trap for cgroup freezer */ +#define JOBCTL_PTRACE_FROZEN_BIT 24 /* frozen for ptrace */ + +#define JOBCTL_STOPPED_BIT 26 /* do_signal_stop() */ +#define JOBCTL_TRACED_BIT 27 /* ptrace_stop() */ #define JOBCTL_STOP_DEQUEUED (1UL << JOBCTL_STOP_DEQUEUED_BIT) #define JOBCTL_STOP_PENDING (1UL << JOBCTL_STOP_PENDING_BIT) @@ -28,6 +32,10 @@ struct task_struct; #define JOBCTL_TRAPPING (1UL << JOBCTL_TRAPPING_BIT) #define JOBCTL_LISTENING (1UL << JOBCTL_LISTENING_BIT) #define JOBCTL_TRAP_FREEZE (1UL << JOBCTL_TRAP_FREEZE_BIT) +#define JOBCTL_PTRACE_FROZEN (1UL << JOBCTL_PTRACE_FROZEN_BIT) + +#define JOBCTL_STOPPED (1UL << JOBCTL_STOPPED_BIT) +#define JOBCTL_TRACED (1UL << JOBCTL_TRACED_BIT) #define JOBCTL_TRAP_MASK (JOBCTL_TRAP_STOP | JOBCTL_TRAP_NOTIFY) #define JOBCTL_PENDING_MASK (JOBCTL_STOP_PENDING | JOBCTL_TRAP_MASK) diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index aca874d33fe6..2a243616f222 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -8,6 +8,7 @@ #include <linux/mm_types.h> #include <linux/gfp.h> #include <linux/sync_core.h> +#include <linux/ioasid.h> /* * Routines for handling mm_structs @@ -28,7 +29,7 @@ extern struct mm_struct *mm_alloc(void); * * Use mmdrop() to release the reference acquired by mmgrab(). * - * See also <Documentation/vm/active_mm.rst> for an in-depth explanation + * See also <Documentation/mm/active_mm.rst> for an in-depth explanation * of &mm_struct.mm_count vs &mm_struct.mm_users. */ static inline void mmgrab(struct mm_struct *mm) @@ -91,7 +92,7 @@ static inline void mmdrop_sched(struct mm_struct *mm) * * Use mmput() to release the reference acquired by mmget(). * - * See also <Documentation/vm/active_mm.rst> for an in-depth explanation + * See also <Documentation/mm/active_mm.rst> for an in-depth explanation * of &mm_struct.mm_count vs &mm_struct.mm_users. */ static inline void mmget(struct mm_struct *mm) @@ -135,6 +136,14 @@ static inline void mm_update_next_owner(struct mm_struct *mm) #endif /* CONFIG_MEMCG */ #ifdef CONFIG_MMU +#ifndef arch_get_mmap_end +#define arch_get_mmap_end(addr, len, flags) (TASK_SIZE) +#endif + +#ifndef arch_get_mmap_base +#define arch_get_mmap_base(addr, base) (base) +#endif + extern void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack); extern unsigned long @@ -144,6 +153,15 @@ extern unsigned long arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); + +unsigned long +generic_get_unmapped_area(struct file *filp, unsigned long addr, + unsigned long len, unsigned long pgoff, + unsigned long flags); +unsigned long +generic_get_unmapped_area_topdown(struct file *filp, unsigned long addr, + unsigned long len, unsigned long pgoff, + unsigned long flags); #else static inline void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack) {} @@ -214,6 +232,32 @@ static inline void fs_reclaim_acquire(gfp_t gfp_mask) { } static inline void fs_reclaim_release(gfp_t gfp_mask) { } #endif +/* Any memory-allocation retry loop should use + * memalloc_retry_wait(), and pass the flags for the most + * constrained allocation attempt that might have failed. + * This provides useful documentation of where loops are, + * and a central place to fine tune the waiting as the MM + * implementation changes. + */ +static inline void memalloc_retry_wait(gfp_t gfp_flags) +{ + /* We use io_schedule_timeout because waiting for memory + * typically included waiting for dirty pages to be + * written out, which requires IO. + */ + __set_current_state(TASK_UNINTERRUPTIBLE); + gfp_flags = current_gfp_context(gfp_flags); + if (gfpflags_allow_blocking(gfp_flags) && + !(gfp_flags & __GFP_NORETRY)) + /* Probably waited already, no need for much more */ + io_schedule_timeout(1); + else + /* Probably didn't wait, and has now released a lock, + * so now is a good time to wait + */ + io_schedule_timeout(HZ/50); +} + /** * might_alloc - Mark possible allocation sites * @gfp_mask: gfp_t flags that would be used to allocate @@ -407,4 +451,29 @@ static inline void membarrier_update_current_mm(struct mm_struct *next_mm) } #endif +#ifdef CONFIG_IOMMU_SVA +static inline void mm_pasid_init(struct mm_struct *mm) +{ + mm->pasid = INVALID_IOASID; +} + +/* Associate a PASID with an mm_struct: */ +static inline void mm_pasid_set(struct mm_struct *mm, u32 pasid) +{ + mm->pasid = pasid; +} + +static inline void mm_pasid_drop(struct mm_struct *mm) +{ + if (pasid_valid(mm->pasid)) { + ioasid_free(mm->pasid); + mm->pasid = INVALID_IOASID; + } +} +#else +static inline void mm_pasid_init(struct mm_struct *mm) {} +static inline void mm_pasid_set(struct mm_struct *mm, u32 pasid) {} +static inline void mm_pasid_drop(struct mm_struct *mm) {} +#endif + #endif /* _LINUX_SCHED_MM_H */ diff --git a/include/linux/sched/posix-timers.h b/include/linux/sched/posix-timers.h new file mode 100644 index 000000000000..523a381d6c88 --- /dev/null +++ b/include/linux/sched/posix-timers.h @@ -0,0 +1 @@ +#include <linux/posix-timers.h> diff --git a/include/linux/sched/rseq_api.h b/include/linux/sched/rseq_api.h new file mode 100644 index 000000000000..cf2af72693e1 --- /dev/null +++ b/include/linux/sched/rseq_api.h @@ -0,0 +1 @@ +#include <linux/rseq.h> diff --git a/include/linux/sched/rt.h b/include/linux/sched/rt.h index e5af028c08b4..994c25640e15 100644 --- a/include/linux/sched/rt.h +++ b/include/linux/sched/rt.h @@ -39,20 +39,12 @@ static inline struct task_struct *rt_mutex_get_top_task(struct task_struct *p) } extern void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task); extern void rt_mutex_adjust_pi(struct task_struct *p); -static inline bool tsk_is_pi_blocked(struct task_struct *tsk) -{ - return tsk->pi_blocked_on != NULL; -} #else static inline struct task_struct *rt_mutex_get_top_task(struct task_struct *task) { return NULL; } # define rt_mutex_adjust_pi(p) do { } while (0) -static inline bool tsk_is_pi_blocked(struct task_struct *tsk) -{ - return false; -} #endif extern void normalize_rt_tasks(void); diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index 33a50642cf41..20099268fa25 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -94,6 +94,7 @@ struct signal_struct { refcount_t sigcnt; atomic_t live; int nr_threads; + int quick_threads; struct list_head thread_head; wait_queue_head_t wait_chldexit; /* for wait4() */ @@ -109,13 +110,9 @@ struct signal_struct { /* thread group exit support */ int group_exit_code; - /* overloaded: - * - notify group_exit_task when ->count is equal to notify_count - * - everyone except group_exit_task is stopped during signal delivery - * of fatal signals, group_exit_task processes the signal. - */ + /* notify group_exec_task when notify_count is less or equal to 0 */ int notify_count; - struct task_struct *group_exit_task; + struct task_struct *group_exec_task; /* thread group stop support, overloads group_exit_code too */ int group_stop_count; @@ -256,7 +253,6 @@ struct signal_struct { #define SIGNAL_STOP_STOPPED 0x00000001 /* job control stop in effect */ #define SIGNAL_STOP_CONTINUED 0x00000002 /* SIGCONT since WCONTINUED reap */ #define SIGNAL_GROUP_EXIT 0x00000004 /* group exit in progress */ -#define SIGNAL_GROUP_COREDUMP 0x00000008 /* coredump in progress */ /* * Pending notifications to parent. */ @@ -272,31 +268,25 @@ struct signal_struct { static inline void signal_set_stop_flags(struct signal_struct *sig, unsigned int flags) { - WARN_ON(sig->flags & (SIGNAL_GROUP_EXIT|SIGNAL_GROUP_COREDUMP)); + WARN_ON(sig->flags & SIGNAL_GROUP_EXIT); sig->flags = (sig->flags & ~SIGNAL_STOP_MASK) | flags; } -/* If true, all threads except ->group_exit_task have pending SIGKILL */ -static inline int signal_group_exit(const struct signal_struct *sig) -{ - return (sig->flags & SIGNAL_GROUP_EXIT) || - (sig->group_exit_task != NULL); -} - extern void flush_signals(struct task_struct *); extern void ignore_signals(struct task_struct *); extern void flush_signal_handlers(struct task_struct *, int force_default); -extern int dequeue_signal(struct task_struct *task, - sigset_t *mask, kernel_siginfo_t *info); +extern int dequeue_signal(struct task_struct *task, sigset_t *mask, + kernel_siginfo_t *info, enum pid_type *type); static inline int kernel_dequeue_signal(void) { struct task_struct *task = current; kernel_siginfo_t __info; + enum pid_type __type; int ret; spin_lock_irq(&task->sighand->siglock); - ret = dequeue_signal(task, &task->blocked, &__info); + ret = dequeue_signal(task, &task->blocked, &__info, &__type); spin_unlock_irq(&task->sighand->siglock); return ret; @@ -305,8 +295,10 @@ static inline int kernel_dequeue_signal(void) static inline void kernel_signal_stop(void) { spin_lock_irq(¤t->sighand->siglock); - if (current->jobctl & JOBCTL_STOP_DEQUEUED) + if (current->jobctl & JOBCTL_STOP_DEQUEUED) { + current->jobctl |= JOBCTL_STOPPED; set_special_state(TASK_STOPPED); + } spin_unlock_irq(¤t->sighand->siglock); schedule(); @@ -331,7 +323,7 @@ int send_sig_mceerr(int code, void __user *, short, struct task_struct *); int force_sig_bnderr(void __user *addr, void __user *lower, void __user *upper); int force_sig_pkuerr(void __user *addr, u32 pkey); -int force_sig_perf(void __user *addr, u32 type, u64 sig_data); +int send_sig_perf(void __user *addr, u32 type, u64 sig_data); int force_sig_ptrace_errno_trap(int errno, void __user *addr); int force_sig_fault_trapno(int sig, int code, void __user *addr, int trapno); @@ -360,6 +352,32 @@ extern void sigqueue_free(struct sigqueue *); extern int send_sigqueue(struct sigqueue *, struct pid *, enum pid_type); extern int do_sigaction(int, struct k_sigaction *, struct k_sigaction *); +static inline void clear_notify_signal(void) +{ + clear_thread_flag(TIF_NOTIFY_SIGNAL); + smp_mb__after_atomic(); +} + +/* + * Returns 'true' if kick_process() is needed to force a transition from + * user -> kernel to guarantee expedient run of TWA_SIGNAL based task_work. + */ +static inline bool __set_notify_signal(struct task_struct *task) +{ + return !test_and_set_tsk_thread_flag(task, TIF_NOTIFY_SIGNAL) && + !wake_up_state(task, TASK_INTERRUPTIBLE); +} + +/* + * Called to break out of interruptible wait loops, and enter the + * exit_to_user_mode_loop(). + */ +static inline void set_notify_signal(struct task_struct *task) +{ + if (__set_notify_signal(task)) + kick_process(task); +} + static inline int restart_syscall(void) { set_tsk_thread_flag(current, TIF_SIGPENDING); @@ -429,13 +447,23 @@ extern void calculate_sigpending(void); extern void signal_wake_up_state(struct task_struct *t, unsigned int state); -static inline void signal_wake_up(struct task_struct *t, bool resume) +static inline void signal_wake_up(struct task_struct *t, bool fatal) { - signal_wake_up_state(t, resume ? TASK_WAKEKILL : 0); + unsigned int state = 0; + if (fatal && !(t->jobctl & JOBCTL_PTRACE_FROZEN)) { + t->jobctl &= ~(JOBCTL_STOPPED | JOBCTL_TRACED); + state = TASK_WAKEKILL | __TASK_TRACED; + } + signal_wake_up_state(t, state); } static inline void ptrace_signal_wake_up(struct task_struct *t, bool resume) { - signal_wake_up_state(t, resume ? __TASK_TRACED : 0); + unsigned int state = 0; + if (resume) { + t->jobctl &= ~JOBCTL_TRACED; + state = __TASK_TRACED; + } + signal_wake_up_state(t, state); } void task_join_group_stop(struct task_struct *task); diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index 304f431178fd..303ee7dd0c7e 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -7,27 +7,13 @@ struct ctl_table; #ifdef CONFIG_DETECT_HUNG_TASK - -#ifdef CONFIG_SMP -extern unsigned int sysctl_hung_task_all_cpu_backtrace; -#else -#define sysctl_hung_task_all_cpu_backtrace 0 -#endif /* CONFIG_SMP */ - -extern int sysctl_hung_task_check_count; -extern unsigned int sysctl_hung_task_panic; +/* used for hung_task and block/ */ extern unsigned long sysctl_hung_task_timeout_secs; -extern unsigned long sysctl_hung_task_check_interval_secs; -extern int sysctl_hung_task_warnings; -int proc_dohung_task_timeout_secs(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos); #else /* Avoid need for ifdefs elsewhere in the code */ enum { sysctl_hung_task_timeout_secs = 0 }; #endif -extern unsigned int sysctl_sched_child_runs_first; - enum sched_tunable_scaling { SCHED_TUNABLESCALING_NONE, SCHED_TUNABLESCALING_LOG, @@ -35,50 +21,18 @@ enum sched_tunable_scaling { SCHED_TUNABLESCALING_END, }; -/* - * control realtime throttling: - * - * /proc/sys/kernel/sched_rt_period_us - * /proc/sys/kernel/sched_rt_runtime_us - */ -extern unsigned int sysctl_sched_rt_period; -extern int sysctl_sched_rt_runtime; - -extern unsigned int sysctl_sched_dl_period_max; -extern unsigned int sysctl_sched_dl_period_min; - -#ifdef CONFIG_UCLAMP_TASK -extern unsigned int sysctl_sched_uclamp_util_min; -extern unsigned int sysctl_sched_uclamp_util_max; -extern unsigned int sysctl_sched_uclamp_util_min_rt_default; -#endif - -#ifdef CONFIG_CFS_BANDWIDTH -extern unsigned int sysctl_sched_cfs_bandwidth_slice; -#endif +#define NUMA_BALANCING_DISABLED 0x0 +#define NUMA_BALANCING_NORMAL 0x1 +#define NUMA_BALANCING_MEMORY_TIERING 0x2 -#ifdef CONFIG_SCHED_AUTOGROUP -extern unsigned int sysctl_sched_autogroup_enabled; +#ifdef CONFIG_NUMA_BALANCING +extern int sysctl_numa_balancing_mode; +extern unsigned int sysctl_numa_balancing_promote_rate_limit; +#else +#define sysctl_numa_balancing_mode 0 #endif -extern int sysctl_sched_rr_timeslice; -extern int sched_rr_timeslice; - -int sched_rr_handler(struct ctl_table *table, int write, void *buffer, - size_t *lenp, loff_t *ppos); -int sched_rt_handler(struct ctl_table *table, int write, void *buffer, - size_t *lenp, loff_t *ppos); -int sysctl_sched_uclamp_handler(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos); int sysctl_numa_balancing(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); -int sysctl_schedstats(struct ctl_table *table, int write, void *buffer, - size_t *lenp, loff_t *ppos); - -#if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) -extern unsigned int sysctl_sched_energy_aware; -int sched_energy_aware_handler(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos); -#endif #endif /* _LINUX_SCHED_SYSCTL_H */ diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index 058d7f371e25..d6c48163c6de 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -32,6 +32,10 @@ struct kernel_clone_args { size_t set_tid_size; int cgroup; int io_thread; + int kthread; + int idle; + int (*fn)(void *); + void *fn_arg; struct cgroup *cgrp; struct css_set *cset; }; @@ -54,11 +58,12 @@ extern asmlinkage void schedule_tail(struct task_struct *prev); extern void init_idle(struct task_struct *idle, int cpu); extern int sched_fork(unsigned long clone_flags, struct task_struct *p); -extern void sched_post_fork(struct task_struct *p, - struct kernel_clone_args *kargs); +extern void sched_cgroup_fork(struct task_struct *p, struct kernel_clone_args *kargs); +extern void sched_post_fork(struct task_struct *p); extern void sched_dead(struct task_struct *p); void __noreturn do_task_dead(void); +void __noreturn make_task_dead(int signr); extern void proc_caches_init(void); @@ -66,8 +71,7 @@ extern void fork_init(void); extern void release_task(struct task_struct * p); -extern int copy_thread(unsigned long, unsigned long, unsigned long, - struct task_struct *, unsigned long); +extern int copy_thread(struct task_struct *, const struct kernel_clone_args *); extern void flush_thread(void); @@ -78,16 +82,17 @@ static inline void exit_thread(struct task_struct *tsk) { } #endif -extern void do_group_exit(int); +extern __noreturn void do_group_exit(int); extern void exit_files(struct task_struct *); -extern void exit_itimers(struct signal_struct *); +extern void exit_itimers(struct task_struct *); extern pid_t kernel_clone(struct kernel_clone_args *kargs); struct task_struct *create_io_thread(int (*fn)(void *), void *arg, int node); struct task_struct *fork_idle(int); struct mm_struct *copy_init_mm(void); extern pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags); +extern pid_t user_mode_thread(int (*fn)(void *), void *arg, unsigned long flags); extern long kernel_wait4(pid_t, int __user *, int, struct rusage *); int kernel_wait(pid_t pid, int *stat); @@ -122,6 +127,9 @@ static inline void put_task_struct_many(struct task_struct *t, int nr) void put_task_struct_rcu_user(struct task_struct *task); +/* Free all architecture-specific resources held by a thread. */ +void release_thread(struct task_struct *dead_task); + #ifdef CONFIG_ARCH_WANTS_DYNAMIC_TASK_STRUCT extern int arch_task_struct_size __read_mostly; #else diff --git a/include/linux/sched/task_flags.h b/include/linux/sched/task_flags.h new file mode 100644 index 000000000000..227f5be81bcd --- /dev/null +++ b/include/linux/sched/task_flags.h @@ -0,0 +1 @@ +#include <linux/sched.h> diff --git a/include/linux/sched/task_stack.h b/include/linux/sched/task_stack.h index d10150587d81..5e799a47431e 100644 --- a/include/linux/sched/task_stack.h +++ b/include/linux/sched/task_stack.h @@ -16,7 +16,7 @@ * try_get_task_stack() instead. task_stack_page will return a pointer * that could get freed out from under you. */ -static inline void *task_stack_page(const struct task_struct *task) +static __always_inline void *task_stack_page(const struct task_struct *task) { return task->stack; } @@ -79,6 +79,8 @@ static inline void *try_get_task_stack(struct task_struct *tsk) static inline void put_task_stack(struct task_struct *tsk) {} #endif +void exit_task_stack_account(struct task_struct *tsk); + #define task_stack_end_corrupted(task) \ (*(end_of_stack(task)) != STACK_END_MAGIC) diff --git a/include/linux/sched/thread_info_api.h b/include/linux/sched/thread_info_api.h new file mode 100644 index 000000000000..2c60fbc16c08 --- /dev/null +++ b/include/linux/sched/thread_info_api.h @@ -0,0 +1 @@ +#include <linux/thread_info.h> diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h index 8054641c0a7b..816df6cc444e 100644 --- a/include/linux/sched/topology.h +++ b/include/linux/sched/topology.h @@ -81,6 +81,7 @@ struct sched_domain_shared { atomic_t ref; atomic_t nr_busy_cpus; int has_idle_cores; + int nr_idle_scan; }; struct sched_domain { @@ -93,6 +94,7 @@ struct sched_domain { unsigned int busy_factor; /* less balancing by factor if busy */ unsigned int imbalance_pct; /* No balance until over watermark */ unsigned int cache_nice_tries; /* Leave cache hot tasks for # tries */ + unsigned int imb_numa_nr; /* Nr running tasks that allows a NUMA imbalance */ int nohz_idle; /* NOHZ IDLE status */ int flags; /* See SD_* */ diff --git a/include/linux/sched/user.h b/include/linux/sched/user.h index 00ed419dd464..f054d0360a75 100644 --- a/include/linux/sched/user.h +++ b/include/linux/sched/user.h @@ -24,7 +24,8 @@ struct user_struct { kuid_t uid; #if defined(CONFIG_PERF_EVENTS) || defined(CONFIG_BPF_SYSCALL) || \ - defined(CONFIG_NET) || defined(CONFIG_IO_URING) + defined(CONFIG_NET) || defined(CONFIG_IO_URING) || \ + defined(CONFIG_VFIO_PCI_ZDEV_KVM) atomic_long_t locked_vm; #endif #ifdef CONFIG_WATCH_QUEUE diff --git a/include/linux/sched_clock.h b/include/linux/sched_clock.h index 835ee87ed792..cb41c5edb4d4 100644 --- a/include/linux/sched_clock.h +++ b/include/linux/sched_clock.h @@ -5,6 +5,8 @@ #ifndef LINUX_SCHED_CLOCK #define LINUX_SCHED_CLOCK +#include <linux/types.h> + #ifdef CONFIG_GENERIC_SCHED_CLOCK /** * struct clock_read_data - data required to read from sched_clock() diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h index 80e781c51ddc..4f765bc788ff 100644 --- a/include/linux/scmi_protocol.h +++ b/include/linux/scmi_protocol.h @@ -13,8 +13,9 @@ #include <linux/notifier.h> #include <linux/types.h> -#define SCMI_MAX_STR_SIZE 16 -#define SCMI_MAX_NUM_RATES 16 +#define SCMI_MAX_STR_SIZE 64 +#define SCMI_SHORT_NAME_MAX_SIZE 16 +#define SCMI_MAX_NUM_RATES 16 /** * struct scmi_revision_info - version information structure @@ -36,13 +37,16 @@ struct scmi_revision_info { u8 num_protocols; u8 num_agents; u32 impl_ver; - char vendor_id[SCMI_MAX_STR_SIZE]; - char sub_vendor_id[SCMI_MAX_STR_SIZE]; + char vendor_id[SCMI_SHORT_NAME_MAX_SIZE]; + char sub_vendor_id[SCMI_SHORT_NAME_MAX_SIZE]; }; struct scmi_clock_info { char name[SCMI_MAX_STR_SIZE]; + unsigned int enable_latency; bool rate_discrete; + bool rate_changed_notifications; + bool rate_change_requested_notifications; union { struct { int num_rates; @@ -56,6 +60,12 @@ struct scmi_clock_info { }; }; +enum scmi_power_scale { + SCMI_POWER_BOGOWATTS, + SCMI_POWER_MILLIWATTS, + SCMI_POWER_MICROWATTS +}; + struct scmi_handle; struct scmi_device; struct scmi_protocol_handle; @@ -74,7 +84,7 @@ struct scmi_protocol_handle; struct scmi_clk_proto_ops { int (*count_get)(const struct scmi_protocol_handle *ph); - const struct scmi_clock_info *(*info_get) + const struct scmi_clock_info __must_check *(*info_get) (const struct scmi_protocol_handle *ph, u32 clk_id); int (*rate_get)(const struct scmi_protocol_handle *ph, u32 clk_id, u64 *rate); @@ -82,6 +92,9 @@ struct scmi_clk_proto_ops { u64 rate); int (*enable)(const struct scmi_protocol_handle *ph, u32 clk_id); int (*disable)(const struct scmi_protocol_handle *ph, u32 clk_id); + int (*enable_atomic)(const struct scmi_protocol_handle *ph, u32 clk_id); + int (*disable_atomic)(const struct scmi_protocol_handle *ph, + u32 clk_id); }; /** @@ -128,7 +141,7 @@ struct scmi_perf_proto_ops { unsigned long *rate, unsigned long *power); bool (*fast_switch_possible)(const struct scmi_protocol_handle *ph, struct device *dev); - bool (*power_scale_mw_get)(const struct scmi_protocol_handle *ph); + enum scmi_power_scale (*power_scale_get)(const struct scmi_protocol_handle *ph); }; /** @@ -142,7 +155,8 @@ struct scmi_perf_proto_ops { */ struct scmi_power_proto_ops { int (*num_domains_get)(const struct scmi_protocol_handle *ph); - char *(*name_get)(const struct scmi_protocol_handle *ph, u32 domain); + const char *(*name_get)(const struct scmi_protocol_handle *ph, + u32 domain); #define SCMI_POWER_STATE_TYPE_SHIFT 30 #define SCMI_POWER_STATE_ID_MASK (BIT(28) - 1) #define SCMI_POWER_STATE_PARAM(type, id) \ @@ -452,7 +466,7 @@ enum scmi_sensor_class { */ struct scmi_sensor_proto_ops { int (*count_get)(const struct scmi_protocol_handle *ph); - const struct scmi_sensor_info *(*info_get) + const struct scmi_sensor_info __must_check *(*info_get) (const struct scmi_protocol_handle *ph, u32 sensor_id); int (*trip_point_config)(const struct scmi_protocol_handle *ph, u32 sensor_id, u8 trip_id, u64 trip_value); @@ -480,13 +494,19 @@ struct scmi_sensor_proto_ops { */ struct scmi_reset_proto_ops { int (*num_domains_get)(const struct scmi_protocol_handle *ph); - char *(*name_get)(const struct scmi_protocol_handle *ph, u32 domain); + const char *(*name_get)(const struct scmi_protocol_handle *ph, + u32 domain); int (*latency_get)(const struct scmi_protocol_handle *ph, u32 domain); int (*reset)(const struct scmi_protocol_handle *ph, u32 domain); int (*assert)(const struct scmi_protocol_handle *ph, u32 domain); int (*deassert)(const struct scmi_protocol_handle *ph, u32 domain); }; +enum scmi_voltage_level_mode { + SCMI_VOLTAGE_LEVEL_SET_AUTO, + SCMI_VOLTAGE_LEVEL_SET_SYNC, +}; + /** * struct scmi_voltage_info - describe one available SCMI Voltage Domain * @@ -499,7 +519,8 @@ struct scmi_reset_proto_ops { * supported voltage level * @negative_volts_allowed: True if any of the entries of @levels_uv represent * a negative voltage. - * @attributes: represents Voltage Domain advertised attributes + * @async_level_set: True when the voltage domain supports asynchronous level + * set commands. * @name: name assigned to the Voltage Domain by platform * @num_levels: number of total entries in @levels_uv. * @levels_uv: array of entries describing the available voltage levels for @@ -509,7 +530,7 @@ struct scmi_voltage_info { unsigned int id; bool segmented; bool negative_volts_allowed; - unsigned int attributes; + bool async_level_set; char name[SCMI_MAX_STR_SIZE]; unsigned int num_levels; #define SCMI_VOLTAGE_SEGMENT_LOW 0 @@ -540,12 +561,122 @@ struct scmi_voltage_proto_ops { int (*config_get)(const struct scmi_protocol_handle *ph, u32 domain_id, u32 *config); int (*level_set)(const struct scmi_protocol_handle *ph, u32 domain_id, - u32 flags, s32 volt_uV); + enum scmi_voltage_level_mode mode, s32 volt_uV); int (*level_get)(const struct scmi_protocol_handle *ph, u32 domain_id, s32 *volt_uV); }; /** + * struct scmi_powercap_info - Describe one available Powercap domain + * + * @id: Domain ID as advertised by the platform. + * @notify_powercap_cap_change: CAP change notification support. + * @notify_powercap_measurement_change: MEASUREMENTS change notifications + * support. + * @async_powercap_cap_set: Asynchronous CAP set support. + * @powercap_cap_config: CAP configuration support. + * @powercap_monitoring: Monitoring (measurements) support. + * @powercap_pai_config: PAI configuration support. + * @powercap_scale_mw: Domain reports power data in milliwatt units. + * @powercap_scale_uw: Domain reports power data in microwatt units. + * Note that, when both @powercap_scale_mw and + * @powercap_scale_uw are set to false, the domain + * reports power data on an abstract linear scale. + * @name: name assigned to the Powercap Domain by platform. + * @min_pai: Minimum configurable PAI. + * @max_pai: Maximum configurable PAI. + * @pai_step: Step size between two consecutive PAI values. + * @min_power_cap: Minimum configurable CAP. + * @max_power_cap: Maximum configurable CAP. + * @power_cap_step: Step size between two consecutive CAP values. + * @sustainable_power: Maximum sustainable power consumption for this domain + * under normal conditions. + * @accuracy: The accuracy with which the power is measured and reported in + * integral multiples of 0.001 percent. + * @parent_id: Identifier of the containing parent power capping domain, or the + * value 0xFFFFFFFF if this powercap domain is a root domain not + * contained in any other domain. + */ +struct scmi_powercap_info { + unsigned int id; + bool notify_powercap_cap_change; + bool notify_powercap_measurement_change; + bool async_powercap_cap_set; + bool powercap_cap_config; + bool powercap_monitoring; + bool powercap_pai_config; + bool powercap_scale_mw; + bool powercap_scale_uw; + bool fastchannels; + char name[SCMI_MAX_STR_SIZE]; + unsigned int min_pai; + unsigned int max_pai; + unsigned int pai_step; + unsigned int min_power_cap; + unsigned int max_power_cap; + unsigned int power_cap_step; + unsigned int sustainable_power; + unsigned int accuracy; +#define SCMI_POWERCAP_ROOT_ZONE_ID 0xFFFFFFFFUL + unsigned int parent_id; + struct scmi_fc_info *fc_info; +}; + +/** + * struct scmi_powercap_proto_ops - represents the various operations provided + * by SCMI Powercap Protocol + * + * @num_domains_get: get the count of powercap domains provided by SCMI. + * @info_get: get the information for the specified domain. + * @cap_get: get the current CAP value for the specified domain. + * @cap_set: set the CAP value for the specified domain to the provided value; + * if the domain supports setting the CAP with an asynchronous command + * this request will finally trigger an asynchronous transfer, but, if + * @ignore_dresp here is set to true, this call will anyway return + * immediately without waiting for the related delayed response. + * @pai_get: get the current PAI value for the specified domain. + * @pai_set: set the PAI value for the specified domain to the provided value. + * @measurements_get: retrieve the current average power measurements for the + * specified domain and the related PAI upon which is + * calculated. + * @measurements_threshold_set: set the desired low and high power thresholds + * to be used when registering for notification + * of type POWERCAP_MEASUREMENTS_NOTIFY with this + * powercap domain. + * Note that this must be called at least once + * before registering any callback with the usual + * @scmi_notify_ops; moreover, in case this method + * is called with measurement notifications already + * enabled it will also trigger, transparently, a + * proper update of the power thresholds configured + * in the SCMI backend server. + * @measurements_threshold_get: get the currently configured low and high power + * thresholds used when registering callbacks for + * notification POWERCAP_MEASUREMENTS_NOTIFY. + */ +struct scmi_powercap_proto_ops { + int (*num_domains_get)(const struct scmi_protocol_handle *ph); + const struct scmi_powercap_info __must_check *(*info_get) + (const struct scmi_protocol_handle *ph, u32 domain_id); + int (*cap_get)(const struct scmi_protocol_handle *ph, u32 domain_id, + u32 *power_cap); + int (*cap_set)(const struct scmi_protocol_handle *ph, u32 domain_id, + u32 power_cap, bool ignore_dresp); + int (*pai_get)(const struct scmi_protocol_handle *ph, u32 domain_id, + u32 *pai); + int (*pai_set)(const struct scmi_protocol_handle *ph, u32 domain_id, + u32 pai); + int (*measurements_get)(const struct scmi_protocol_handle *ph, + u32 domain_id, u32 *average_power, u32 *pai); + int (*measurements_threshold_set)(const struct scmi_protocol_handle *ph, + u32 domain_id, u32 power_thresh_low, + u32 power_thresh_high); + int (*measurements_threshold_get)(const struct scmi_protocol_handle *ph, + u32 domain_id, u32 *power_thresh_low, + u32 *power_thresh_high); +}; + +/** * struct scmi_notify_ops - represents notifications' operations provided by * SCMI core * @devm_event_notifier_register: Managed registration of a notifier_block for @@ -609,19 +740,35 @@ struct scmi_notify_ops { * * @dev: pointer to the SCMI device * @version: pointer to the structure containing SCMI version information + * @devm_protocol_acquire: devres managed method to get hold of a protocol, + * causing its initialization and related resource + * accounting * @devm_protocol_get: devres managed method to acquire a protocol and get specific * operations and a dedicated protocol handler * @devm_protocol_put: devres managed method to release a protocol + * @is_transport_atomic: method to check if the underlying transport for this + * instance handle is configured to support atomic + * transactions for commands. + * Some users of the SCMI stack in the upper layers could + * be interested to know if they can assume SCMI + * command transactions associated to this handle will + * never sleep and act accordingly. + * An optional atomic threshold value could be returned + * where configured. * @notify_ops: pointer to set of notifications related operations */ struct scmi_handle { struct device *dev; struct scmi_revision_info *version; + int __must_check (*devm_protocol_acquire)(struct scmi_device *sdev, + u8 proto); const void __must_check * (*devm_protocol_get)(struct scmi_device *sdev, u8 proto, struct scmi_protocol_handle **ph); void (*devm_protocol_put)(struct scmi_device *sdev, u8 proto); + bool (*is_transport_atomic)(const struct scmi_handle *handle, + unsigned int *atomic_threshold); const struct scmi_notify_ops *notify_ops; }; @@ -635,6 +782,7 @@ enum scmi_std_protocol { SCMI_PROTOCOL_SENSOR = 0x15, SCMI_PROTOCOL_RESET = 0x16, SCMI_PROTOCOL_VOLTAGE = 0x17, + SCMI_PROTOCOL_POWERCAP = 0x18, }; enum scmi_system_events { @@ -727,6 +875,8 @@ void scmi_protocol_unregister(const struct scmi_protocol *proto); /* SCMI Notification API - Custom Event Reports */ enum scmi_notification_events { SCMI_EVENT_POWER_STATE_CHANGED = 0x0, + SCMI_EVENT_CLOCK_RATE_CHANGED = 0x0, + SCMI_EVENT_CLOCK_RATE_CHANGE_REQUESTED = 0x1, SCMI_EVENT_PERFORMANCE_LIMITS_CHANGED = 0x0, SCMI_EVENT_PERFORMANCE_LEVEL_CHANGED = 0x1, SCMI_EVENT_SENSOR_TRIP_POINT_EVENT = 0x0, @@ -734,6 +884,8 @@ enum scmi_notification_events { SCMI_EVENT_RESET_ISSUED = 0x0, SCMI_EVENT_BASE_ERROR_EVENT = 0x0, SCMI_EVENT_SYSTEM_POWER_STATE_NOTIFIER = 0x0, + SCMI_EVENT_POWERCAP_CAP_CHANGED = 0x0, + SCMI_EVENT_POWERCAP_MEASUREMENTS_CHANGED = 0x1, }; struct scmi_power_state_changed_report { @@ -743,11 +895,20 @@ struct scmi_power_state_changed_report { unsigned int power_state; }; +struct scmi_clock_rate_notif_report { + ktime_t timestamp; + unsigned int agent_id; + unsigned int clock_id; + unsigned long long rate; +}; + struct scmi_system_power_state_notifier_report { ktime_t timestamp; unsigned int agent_id; +#define SCMI_SYSPOWER_IS_REQUEST_GRACEFUL(flags) ((flags) & BIT(0)) unsigned int flags; unsigned int system_state; + unsigned int timeout; }; struct scmi_perf_limits_report { @@ -795,4 +956,18 @@ struct scmi_base_error_report { unsigned long long reports[]; }; +struct scmi_powercap_cap_changed_report { + ktime_t timestamp; + unsigned int agent_id; + unsigned int domain_id; + unsigned int power_cap; + unsigned int pai; +}; + +struct scmi_powercap_meas_changed_report { + ktime_t timestamp; + unsigned int agent_id; + unsigned int domain_id; + unsigned int power; +}; #endif /* _LINUX_SCMI_PROTOCOL_H */ diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h index 0c564e5d40ff..d31d76be4982 100644 --- a/include/linux/seccomp.h +++ b/include/linux/seccomp.h @@ -8,7 +8,8 @@ SECCOMP_FILTER_FLAG_LOG | \ SECCOMP_FILTER_FLAG_SPEC_ALLOW | \ SECCOMP_FILTER_FLAG_NEW_LISTENER | \ - SECCOMP_FILTER_FLAG_TSYNC_ESRCH) + SECCOMP_FILTER_FLAG_TSYNC_ESRCH | \ + SECCOMP_FILTER_FLAG_WAIT_KILLABLE_RECV) /* sizeof() the first published struct seccomp_notif_addfd */ #define SECCOMP_NOTIFY_ADDFD_SIZE_VER0 24 diff --git a/include/linux/security.h b/include/linux/security.h index 6d72772182c8..ca1b7109c0db 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -114,6 +114,7 @@ enum lockdown_reason { LOCKDOWN_IOPORT, LOCKDOWN_MSR, LOCKDOWN_ACPI_TABLES, + LOCKDOWN_DEVICE_TREE, LOCKDOWN_PCMCIA_CIS, LOCKDOWN_TIOCSSERIAL, LOCKDOWN_MODULE_PARAMETERS, @@ -121,10 +122,13 @@ enum lockdown_reason { LOCKDOWN_DEBUGFS, LOCKDOWN_XMON_WR, LOCKDOWN_BPF_WRITE_USER, + LOCKDOWN_DBG_WRITE_KERNEL, + LOCKDOWN_RTAS_ERROR_INJECTION, LOCKDOWN_INTEGRITY_MAX, LOCKDOWN_KCORE, LOCKDOWN_KPROBES, LOCKDOWN_BPF_READ_KERNEL, + LOCKDOWN_DBG_READ_KERNEL, LOCKDOWN_PERF, LOCKDOWN_TRACEFS, LOCKDOWN_XMON_RW, @@ -351,7 +355,8 @@ int security_inode_readlink(struct dentry *dentry); int security_inode_follow_link(struct dentry *dentry, struct inode *inode, bool rcu); int security_inode_permission(struct inode *inode, int mask); -int security_inode_setattr(struct dentry *dentry, struct iattr *attr); +int security_inode_setattr(struct user_namespace *mnt_userns, + struct dentry *dentry, struct iattr *attr); int security_inode_getattr(const struct path *path); int security_inode_setxattr(struct user_namespace *mnt_userns, struct dentry *dentry, const char *name, @@ -413,6 +418,7 @@ int security_task_fix_setuid(struct cred *new, const struct cred *old, int flags); int security_task_fix_setgid(struct cred *new, const struct cred *old, int flags); +int security_task_fix_setgroups(struct cred *new, const struct cred *old); int security_task_setpgid(struct task_struct *p, pid_t pgid); int security_task_getpgid(struct task_struct *p); int security_task_getsid(struct task_struct *p); @@ -433,6 +439,7 @@ int security_task_kill(struct task_struct *p, struct kernel_siginfo *info, int security_task_prctl(int option, unsigned long arg2, unsigned long arg3, unsigned long arg4, unsigned long arg5); void security_task_to_inode(struct task_struct *p, struct inode *inode); +int security_create_user_ns(const struct cred *cred); int security_ipc_permission(struct kern_ipc_perm *ipcp, short flag); void security_ipc_getsecid(struct kern_ipc_perm *ipcp, u32 *secid); int security_msg_msg_alloc(struct msg_msg *msg); @@ -457,7 +464,7 @@ int security_sem_semctl(struct kern_ipc_perm *sma, int cmd); int security_sem_semop(struct kern_ipc_perm *sma, struct sembuf *sops, unsigned nsops, int alter); void security_d_instantiate(struct dentry *dentry, struct inode *inode); -int security_getprocattr(struct task_struct *p, const char *lsm, char *name, +int security_getprocattr(struct task_struct *p, const char *lsm, const char *name, char **value); int security_setprocattr(const char *lsm, const char *name, void *value, size_t size); @@ -846,8 +853,9 @@ static inline int security_inode_permission(struct inode *inode, int mask) return 0; } -static inline int security_inode_setattr(struct dentry *dentry, - struct iattr *attr) +static inline int security_inode_setattr(struct user_namespace *mnt_userns, + struct dentry *dentry, + struct iattr *attr) { return 0; } @@ -1096,6 +1104,12 @@ static inline int security_task_fix_setgid(struct cred *new, return 0; } +static inline int security_task_fix_setgroups(struct cred *new, + const struct cred *old) +{ + return 0; +} + static inline int security_task_setpgid(struct task_struct *p, pid_t pgid) { return 0; @@ -1183,6 +1197,11 @@ static inline int security_task_prctl(int option, unsigned long arg2, static inline void security_task_to_inode(struct task_struct *p, struct inode *inode) { } +static inline int security_create_user_ns(const struct cred *cred) +{ + return 0; +} + static inline int security_ipc_permission(struct kern_ipc_perm *ipcp, short flag) { @@ -1290,7 +1309,7 @@ static inline void security_d_instantiate(struct dentry *dentry, { } static inline int security_getprocattr(struct task_struct *p, const char *lsm, - char *name, char **value) + const char *name, char **value) { return -EINVAL; } @@ -1422,6 +1441,8 @@ int security_sctp_bind_connect(struct sock *sk, int optname, struct sockaddr *address, int addrlen); void security_sctp_sk_clone(struct sctp_association *asoc, struct sock *sk, struct sock *newsk); +int security_sctp_assoc_established(struct sctp_association *asoc, + struct sk_buff *skb); #else /* CONFIG_SECURITY_NETWORK */ static inline int security_unix_stream_connect(struct sock *sock, @@ -1641,6 +1662,12 @@ static inline void security_sctp_sk_clone(struct sctp_association *asoc, struct sock *newsk) { } + +static inline int security_sctp_assoc_established(struct sctp_association *asoc, + struct sk_buff *skb) +{ + return 0; +} #endif /* CONFIG_SECURITY_NETWORK */ #ifdef CONFIG_SECURITY_INFINIBAND @@ -2041,6 +2068,7 @@ static inline int security_perf_event_write(struct perf_event *event) #ifdef CONFIG_SECURITY extern int security_uring_override_creds(const struct cred *new); extern int security_uring_sqpoll(void); +extern int security_uring_cmd(struct io_uring_cmd *ioucmd); #else static inline int security_uring_override_creds(const struct cred *new) { @@ -2050,6 +2078,10 @@ static inline int security_uring_sqpoll(void) { return 0; } +static inline int security_uring_cmd(struct io_uring_cmd *ioucmd) +{ + return 0; +} #endif /* CONFIG_SECURITY */ #endif /* CONFIG_IO_URING */ diff --git a/include/linux/sed-opal.h b/include/linux/sed-opal.h index 1ac0d712a9c3..6f837bb6c715 100644 --- a/include/linux/sed-opal.h +++ b/include/linux/sed-opal.h @@ -43,6 +43,7 @@ static inline bool is_sed_ioctl(unsigned int cmd) case IOC_OPAL_MBR_DONE: case IOC_OPAL_WRITE_SHADOW_MBR: case IOC_OPAL_GENERIC_TABLE_RW: + case IOC_OPAL_GET_STATUS: return true; } return false; diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h index 72dbb44a4573..bd023dd38ae6 100644 --- a/include/linux/seq_file.h +++ b/include/linux/seq_file.h @@ -162,6 +162,7 @@ int seq_dentry(struct seq_file *, struct dentry *, const char *); int seq_path_root(struct seq_file *m, const struct path *path, const struct path *root, const char *esc); +void *single_start(struct seq_file *, loff_t *); int single_open(struct file *, int (*)(struct seq_file *, void *), void *); int single_open_size(struct file *, int (*)(struct seq_file *, void *), void *, size_t); int single_release(struct inode *, struct file *); @@ -209,7 +210,7 @@ static const struct file_operations __name ## _fops = { \ #define DEFINE_PROC_SHOW_ATTRIBUTE(__name) \ static int __name ## _open(struct inode *inode, struct file *file) \ { \ - return single_open(file, __name ## _show, PDE_DATA(inode)); \ + return single_open(file, __name ## _show, pde_data(inode)); \ } \ \ static const struct proc_ops __name ## _proc_ops = { \ @@ -276,6 +277,10 @@ extern struct list_head *seq_list_start_head(struct list_head *head, extern struct list_head *seq_list_next(void *v, struct list_head *head, loff_t *ppos); +extern struct list_head *seq_list_start_rcu(struct list_head *head, loff_t pos); +extern struct list_head *seq_list_start_head_rcu(struct list_head *head, loff_t pos); +extern struct list_head *seq_list_next_rcu(void *v, struct list_head *head, loff_t *ppos); + /* * Helpers for iteration over hlist_head-s in seq_files */ diff --git a/include/linux/seq_file_net.h b/include/linux/seq_file_net.h index b97912fdbae7..79638395bc32 100644 --- a/include/linux/seq_file_net.h +++ b/include/linux/seq_file_net.h @@ -3,6 +3,7 @@ #define __SEQ_FILE_NET_H__ #include <linux/seq_file.h> +#include <net/net_trackers.h> struct net; extern struct net init_net; diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h index 37ded6b8fee6..3926e9027947 100644 --- a/include/linux/seqlock.h +++ b/include/linux/seqlock.h @@ -17,7 +17,6 @@ #include <linux/kcsan-checks.h> #include <linux/lockdep.h> #include <linux/mutex.h> -#include <linux/ww_mutex.h> #include <linux/preempt.h> #include <linux/spinlock.h> @@ -164,7 +163,7 @@ static inline void seqcount_lockdep_reader_access(const seqcount_t *s) * static initializer or init function. This enables lockdep to validate * that the write side critical section is properly serialized. * - * LOCKNAME: raw_spinlock, spinlock, rwlock, mutex, or ww_mutex. + * LOCKNAME: raw_spinlock, spinlock, rwlock or mutex */ /* @@ -184,7 +183,6 @@ static inline void seqcount_lockdep_reader_access(const seqcount_t *s) #define seqcount_spinlock_init(s, lock) seqcount_LOCKNAME_init(s, lock, spinlock) #define seqcount_rwlock_init(s, lock) seqcount_LOCKNAME_init(s, lock, rwlock) #define seqcount_mutex_init(s, lock) seqcount_LOCKNAME_init(s, lock, mutex) -#define seqcount_ww_mutex_init(s, lock) seqcount_LOCKNAME_init(s, lock, ww_mutex) /* * SEQCOUNT_LOCKNAME() - Instantiate seqcount_LOCKNAME_t and helpers @@ -277,7 +275,6 @@ SEQCOUNT_LOCKNAME(raw_spinlock, raw_spinlock_t, false, s->lock, raw_s SEQCOUNT_LOCKNAME(spinlock, spinlock_t, __SEQ_RT, s->lock, spin, spin_lock(s->lock)) SEQCOUNT_LOCKNAME(rwlock, rwlock_t, __SEQ_RT, s->lock, read, read_lock(s->lock)) SEQCOUNT_LOCKNAME(mutex, struct mutex, true, s->lock, mutex, mutex_lock(s->lock)) -SEQCOUNT_LOCKNAME(ww_mutex, struct ww_mutex, true, &s->lock->base, ww_mutex, ww_mutex_lock(s->lock, NULL)) /* * SEQCNT_LOCKNAME_ZERO - static initializer for seqcount_LOCKNAME_t @@ -304,8 +301,7 @@ SEQCOUNT_LOCKNAME(ww_mutex, struct ww_mutex, true, &s->lock->base, ww_mu __seqprop_case((s), raw_spinlock, prop), \ __seqprop_case((s), spinlock, prop), \ __seqprop_case((s), rwlock, prop), \ - __seqprop_case((s), mutex, prop), \ - __seqprop_case((s), ww_mutex, prop)) + __seqprop_case((s), mutex, prop)) #define seqprop_ptr(s) __seqprop(s, ptr) #define seqprop_sequence(s) __seqprop(s, sequence) diff --git a/include/linux/seqlock_api.h b/include/linux/seqlock_api.h new file mode 100644 index 000000000000..be91e7d3b826 --- /dev/null +++ b/include/linux/seqlock_api.h @@ -0,0 +1 @@ +#include <linux/seqlock.h> diff --git a/include/linux/serdev.h b/include/linux/serdev.h index 3368c261ab62..66f624fc618c 100644 --- a/include/linux/serdev.h +++ b/include/linux/serdev.h @@ -7,6 +7,7 @@ #include <linux/types.h> #include <linux/device.h> +#include <linux/uaccess.h> #include <linux/termios.h> #include <linux/delay.h> diff --git a/include/linux/serial.h b/include/linux/serial.h index 0916107c77f9..3d6fe3ef92cf 100644 --- a/include/linux/serial.h +++ b/include/linux/serial.h @@ -9,9 +9,19 @@ #ifndef _LINUX_SERIAL_H #define _LINUX_SERIAL_H -#include <asm/page.h> #include <uapi/linux/serial.h> +#include <uapi/linux/serial_reg.h> +/* Helper for dealing with UART_LCR_WLEN* defines */ +#define UART_LCR_WLEN(x) ((x) - 5) + +/* FIFO and shifting register empty */ +#define UART_LSR_BOTH_EMPTY (UART_LSR_TEMT | UART_LSR_THRE) + +static inline bool uart_lsr_tx_empty(u16 lsr) +{ + return (lsr & UART_LSR_BOTH_EMPTY) == UART_LSR_BOTH_EMPTY; +} /* * Counters of the input lines (CTS, DSR, RI, CD) interrupts @@ -23,11 +33,6 @@ struct async_icount { __u32 buf_overrun; }; -/* - * The size of the serial xmit buffer is 1 page, or 4096 bytes - */ -#define SERIAL_XMIT_SIZE PAGE_SIZE - #include <linux/compiler.h> #endif /* _LINUX_SERIAL_H */ diff --git a/include/linux/serial_8250.h b/include/linux/serial_8250.h index 5db211f43b29..19376bee9667 100644 --- a/include/linux/serial_8250.h +++ b/include/linux/serial_8250.h @@ -32,7 +32,7 @@ struct plat_serial8250_port { void (*serial_out)(struct uart_port *, int, int); void (*set_termios)(struct uart_port *, struct ktermios *new, - struct ktermios *old); + const struct ktermios *old); void (*set_ldisc)(struct uart_port *, struct ktermios *); unsigned int (*get_mctrl)(struct uart_port *); @@ -74,6 +74,7 @@ struct uart_8250_port; struct uart_8250_ops { int (*setup_irq)(struct uart_8250_port *); void (*release_irq)(struct uart_8250_port *); + void (*setup_timer)(struct uart_8250_port *); }; struct uart_8250_em485 { @@ -104,8 +105,6 @@ struct uart_8250_port { unsigned char ier; unsigned char lcr; unsigned char mcr; - unsigned char mcr_mask; /* mask of user bits */ - unsigned char mcr_force; /* mask of forced bits */ unsigned char cur_iotype; /* Running I/O type */ unsigned int rpm_tx_active; unsigned char canary; /* non-zero during system sleep @@ -121,7 +120,8 @@ struct uart_8250_port { * be immediately processed. */ #define LSR_SAVE_FLAGS UART_LSR_BRK_ERROR_BITS - unsigned char lsr_saved_flags; + u16 lsr_saved_flags; + u16 lsr_save_mask; #define MSR_SAVE_FLAGS UART_MSR_ANY_DELTA unsigned char msr_saved_flags; @@ -158,7 +158,7 @@ extern int early_serial8250_setup(struct earlycon_device *device, extern void serial8250_update_uartclk(struct uart_port *port, unsigned int uartclk); extern void serial8250_do_set_termios(struct uart_port *port, - struct ktermios *termios, struct ktermios *old); + struct ktermios *termios, const struct ktermios *old); extern void serial8250_do_set_ldisc(struct uart_port *port, struct ktermios *termios); extern unsigned int serial8250_do_get_mctrl(struct uart_port *port); @@ -172,8 +172,8 @@ extern void serial8250_do_set_divisor(struct uart_port *port, unsigned int baud, unsigned int quot_frac); extern int fsl8250_handle_irq(struct uart_port *port); int serial8250_handle_irq(struct uart_port *port, unsigned int iir); -unsigned char serial8250_rx_chars(struct uart_8250_port *up, unsigned char lsr); -void serial8250_read_char(struct uart_8250_port *up, unsigned char lsr); +u16 serial8250_rx_chars(struct uart_8250_port *up, u16 lsr); +void serial8250_read_char(struct uart_8250_port *up, u16 lsr); void serial8250_tx_chars(struct uart_8250_port *up); unsigned int serial8250_modem_status(struct uart_8250_port *up); void serial8250_init_port(struct uart_8250_port *up); diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index c58cc142d23f..d657f2a42a7b 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -31,9 +31,344 @@ struct serial_struct; struct device; struct gpio_desc; -/* +/** + * struct uart_ops -- interface between serial_core and the driver + * * This structure describes all the operations that can be done on the - * physical hardware. See Documentation/driver-api/serial/driver.rst for details. + * physical hardware. + * + * @tx_empty: ``unsigned int ()(struct uart_port *port)`` + * + * This function tests whether the transmitter fifo and shifter for the + * @port is empty. If it is empty, this function should return + * %TIOCSER_TEMT, otherwise return 0. If the port does not support this + * operation, then it should return %TIOCSER_TEMT. + * + * Locking: none. + * Interrupts: caller dependent. + * This call must not sleep + * + * @set_mctrl: ``void ()(struct uart_port *port, unsigned int mctrl)`` + * + * This function sets the modem control lines for @port to the state + * described by @mctrl. The relevant bits of @mctrl are: + * + * - %TIOCM_RTS RTS signal. + * - %TIOCM_DTR DTR signal. + * - %TIOCM_OUT1 OUT1 signal. + * - %TIOCM_OUT2 OUT2 signal. + * - %TIOCM_LOOP Set the port into loopback mode. + * + * If the appropriate bit is set, the signal should be driven + * active. If the bit is clear, the signal should be driven + * inactive. + * + * Locking: @port->lock taken. + * Interrupts: locally disabled. + * This call must not sleep + * + * @get_mctrl: ``unsigned int ()(struct uart_port *port)`` + * + * Returns the current state of modem control inputs of @port. The state + * of the outputs should not be returned, since the core keeps track of + * their state. The state information should include: + * + * - %TIOCM_CAR state of DCD signal + * - %TIOCM_CTS state of CTS signal + * - %TIOCM_DSR state of DSR signal + * - %TIOCM_RI state of RI signal + * + * The bit is set if the signal is currently driven active. If + * the port does not support CTS, DCD or DSR, the driver should + * indicate that the signal is permanently active. If RI is + * not available, the signal should not be indicated as active. + * + * Locking: @port->lock taken. + * Interrupts: locally disabled. + * This call must not sleep + * + * @stop_tx: ``void ()(struct uart_port *port)`` + * + * Stop transmitting characters. This might be due to the CTS line + * becoming inactive or the tty layer indicating we want to stop + * transmission due to an %XOFF character. + * + * The driver should stop transmitting characters as soon as possible. + * + * Locking: @port->lock taken. + * Interrupts: locally disabled. + * This call must not sleep + * + * @start_tx: ``void ()(struct uart_port *port)`` + * + * Start transmitting characters. + * + * Locking: @port->lock taken. + * Interrupts: locally disabled. + * This call must not sleep + * + * @throttle: ``void ()(struct uart_port *port)`` + * + * Notify the serial driver that input buffers for the line discipline are + * close to full, and it should somehow signal that no more characters + * should be sent to the serial port. + * This will be called only if hardware assisted flow control is enabled. + * + * Locking: serialized with @unthrottle() and termios modification by the + * tty layer. + * + * @unthrottle: ``void ()(struct uart_port *port)`` + * + * Notify the serial driver that characters can now be sent to the serial + * port without fear of overrunning the input buffers of the line + * disciplines. + * + * This will be called only if hardware assisted flow control is enabled. + * + * Locking: serialized with @throttle() and termios modification by the + * tty layer. + * + * @send_xchar: ``void ()(struct uart_port *port, char ch)`` + * + * Transmit a high priority character, even if the port is stopped. This + * is used to implement XON/XOFF flow control and tcflow(). If the serial + * driver does not implement this function, the tty core will append the + * character to the circular buffer and then call start_tx() / stop_tx() + * to flush the data out. + * + * Do not transmit if @ch == '\0' (%__DISABLED_CHAR). + * + * Locking: none. + * Interrupts: caller dependent. + * + * @start_rx: ``void ()(struct uart_port *port)`` + * + * Start receiving characters. + * + * Locking: @port->lock taken. + * Interrupts: locally disabled. + * This call must not sleep + * + * @stop_rx: ``void ()(struct uart_port *port)`` + * + * Stop receiving characters; the @port is in the process of being closed. + * + * Locking: @port->lock taken. + * Interrupts: locally disabled. + * This call must not sleep + * + * @enable_ms: ``void ()(struct uart_port *port)`` + * + * Enable the modem status interrupts. + * + * This method may be called multiple times. Modem status interrupts + * should be disabled when the @shutdown() method is called. + * + * Locking: @port->lock taken. + * Interrupts: locally disabled. + * This call must not sleep + * + * @break_ctl: ``void ()(struct uart_port *port, int ctl)`` + * + * Control the transmission of a break signal. If @ctl is nonzero, the + * break signal should be transmitted. The signal should be terminated + * when another call is made with a zero @ctl. + * + * Locking: caller holds tty_port->mutex + * + * @startup: ``int ()(struct uart_port *port)`` + * + * Grab any interrupt resources and initialise any low level driver state. + * Enable the port for reception. It should not activate RTS nor DTR; + * this will be done via a separate call to @set_mctrl(). + * + * This method will only be called when the port is initially opened. + * + * Locking: port_sem taken. + * Interrupts: globally disabled. + * + * @shutdown: ``void ()(struct uart_port *port)`` + * + * Disable the @port, disable any break condition that may be in effect, + * and free any interrupt resources. It should not disable RTS nor DTR; + * this will have already been done via a separate call to @set_mctrl(). + * + * Drivers must not access @port->state once this call has completed. + * + * This method will only be called when there are no more users of this + * @port. + * + * Locking: port_sem taken. + * Interrupts: caller dependent. + * + * @flush_buffer: ``void ()(struct uart_port *port)`` + * + * Flush any write buffers, reset any DMA state and stop any ongoing DMA + * transfers. + * + * This will be called whenever the @port->state->xmit circular buffer is + * cleared. + * + * Locking: @port->lock taken. + * Interrupts: locally disabled. + * This call must not sleep + * + * @set_termios: ``void ()(struct uart_port *port, struct ktermios *new, + * struct ktermios *old)`` + * + * Change the @port parameters, including word length, parity, stop bits. + * Update @port->read_status_mask and @port->ignore_status_mask to + * indicate the types of events we are interested in receiving. Relevant + * ktermios::c_cflag bits are: + * + * - %CSIZE - word size + * - %CSTOPB - 2 stop bits + * - %PARENB - parity enable + * - %PARODD - odd parity (when %PARENB is in force) + * - %ADDRB - address bit (changed through uart_port::rs485_config()). + * - %CREAD - enable reception of characters (if not set, still receive + * characters from the port, but throw them away). + * - %CRTSCTS - if set, enable CTS status change reporting. + * - %CLOCAL - if not set, enable modem status change reporting. + * + * Relevant ktermios::c_iflag bits are: + * + * - %INPCK - enable frame and parity error events to be passed to the TTY + * layer. + * - %BRKINT / %PARMRK - both of these enable break events to be passed to + * the TTY layer. + * - %IGNPAR - ignore parity and framing errors. + * - %IGNBRK - ignore break errors. If %IGNPAR is also set, ignore overrun + * errors as well. + * + * The interaction of the ktermios::c_iflag bits is as follows (parity + * error given as an example): + * + * ============ ======= ======= ========================================= + * Parity error INPCK IGNPAR + * ============ ======= ======= ========================================= + * n/a 0 n/a character received, marked as %TTY_NORMAL + * None 1 n/a character received, marked as %TTY_NORMAL + * Yes 1 0 character received, marked as %TTY_PARITY + * Yes 1 1 character discarded + * ============ ======= ======= ========================================= + * + * Other flags may be used (eg, xon/xoff characters) if your hardware + * supports hardware "soft" flow control. + * + * Locking: caller holds tty_port->mutex + * Interrupts: caller dependent. + * This call must not sleep + * + * @set_ldisc: ``void ()(struct uart_port *port, struct ktermios *termios)`` + * + * Notifier for discipline change. See + * Documentation/driver-api/tty/tty_ldisc.rst. + * + * Locking: caller holds tty_port->mutex + * + * @pm: ``void ()(struct uart_port *port, unsigned int state, + * unsigned int oldstate)`` + * + * Perform any power management related activities on the specified @port. + * @state indicates the new state (defined by enum uart_pm_state), + * @oldstate indicates the previous state. + * + * This function should not be used to grab any resources. + * + * This will be called when the @port is initially opened and finally + * closed, except when the @port is also the system console. This will + * occur even if %CONFIG_PM is not set. + * + * Locking: none. + * Interrupts: caller dependent. + * + * @type: ``const char *()(struct uart_port *port)`` + * + * Return a pointer to a string constant describing the specified @port, + * or return %NULL, in which case the string 'unknown' is substituted. + * + * Locking: none. + * Interrupts: caller dependent. + * + * @release_port: ``void ()(struct uart_port *port)`` + * + * Release any memory and IO region resources currently in use by the + * @port. + * + * Locking: none. + * Interrupts: caller dependent. + * + * @request_port: ``int ()(struct uart_port *port)`` + * + * Request any memory and IO region resources required by the port. If any + * fail, no resources should be registered when this function returns, and + * it should return -%EBUSY on failure. + * + * Locking: none. + * Interrupts: caller dependent. + * + * @config_port: ``void ()(struct uart_port *port, int type)`` + * + * Perform any autoconfiguration steps required for the @port. @type + * contains a bit mask of the required configuration. %UART_CONFIG_TYPE + * indicates that the port requires detection and identification. + * @port->type should be set to the type found, or %PORT_UNKNOWN if no + * port was detected. + * + * %UART_CONFIG_IRQ indicates autoconfiguration of the interrupt signal, + * which should be probed using standard kernel autoprobing techniques. + * This is not necessary on platforms where ports have interrupts + * internally hard wired (eg, system on a chip implementations). + * + * Locking: none. + * Interrupts: caller dependent. + * + * @verify_port: ``int ()(struct uart_port *port, + * struct serial_struct *serinfo)`` + * + * Verify the new serial port information contained within @serinfo is + * suitable for this port type. + * + * Locking: none. + * Interrupts: caller dependent. + * + * @ioctl: ``int ()(struct uart_port *port, unsigned int cmd, + * unsigned long arg)`` + * + * Perform any port specific IOCTLs. IOCTL commands must be defined using + * the standard numbering system found in <asm/ioctl.h>. + * + * Locking: none. + * Interrupts: caller dependent. + * + * @poll_init: ``int ()(struct uart_port *port)`` + * + * Called by kgdb to perform the minimal hardware initialization needed to + * support @poll_put_char() and @poll_get_char(). Unlike @startup(), this + * should not request interrupts. + * + * Locking: %tty_mutex and tty_port->mutex taken. + * Interrupts: n/a. + * + * @poll_put_char: ``void ()(struct uart_port *port, unsigned char ch)`` + * + * Called by kgdb to write a single character @ch directly to the serial + * @port. It can and should block until there is space in the TX FIFO. + * + * Locking: none. + * Interrupts: caller dependent. + * This call must not sleep + * + * @poll_get_char: ``int ()(struct uart_port *port)`` + * + * Called by kgdb to read a single character directly from the serial + * port. If data is available, it should be returned; otherwise the + * function should return %NO_POLL_CHAR immediately. + * + * Locking: none. + * Interrupts: caller dependent. + * This call must not sleep */ struct uart_ops { unsigned int (*tx_empty)(struct uart_port *); @@ -45,32 +380,19 @@ struct uart_ops { void (*unthrottle)(struct uart_port *); void (*send_xchar)(struct uart_port *, char ch); void (*stop_rx)(struct uart_port *); + void (*start_rx)(struct uart_port *); void (*enable_ms)(struct uart_port *); void (*break_ctl)(struct uart_port *, int ctl); int (*startup)(struct uart_port *); void (*shutdown)(struct uart_port *); void (*flush_buffer)(struct uart_port *); void (*set_termios)(struct uart_port *, struct ktermios *new, - struct ktermios *old); + const struct ktermios *old); void (*set_ldisc)(struct uart_port *, struct ktermios *); void (*pm)(struct uart_port *, unsigned int state, unsigned int oldstate); - - /* - * Return a string describing the type of the port - */ const char *(*type)(struct uart_port *); - - /* - * Release IO and memory resources used by the port. - * This includes iounmap if necessary. - */ void (*release_port)(struct uart_port *); - - /* - * Request IO and memory resources used by the port. - * This includes iomapping the port if necessary. - */ int (*request_port)(struct uart_port *); void (*config_port)(struct uart_port *, int); int (*verify_port)(struct uart_port *, struct serial_struct *); @@ -100,7 +422,7 @@ struct uart_icount { __u32 buf_overrun; }; -typedef unsigned int __bitwise upf_t; +typedef u64 __bitwise upf_t; typedef unsigned int __bitwise upstat_t; struct uart_port { @@ -111,7 +433,7 @@ struct uart_port { void (*serial_out)(struct uart_port *, int, int); void (*set_termios)(struct uart_port *, struct ktermios *new, - struct ktermios *old); + const struct ktermios *old); void (*set_ldisc)(struct uart_port *, struct ktermios *); unsigned int (*get_mctrl)(struct uart_port *); @@ -132,6 +454,7 @@ struct uart_port { unsigned int old); void (*handle_break)(struct uart_port *); int (*rs485_config)(struct uart_port *, + struct ktermios *termios, struct serial_rs485 *rs485); int (*iso7816_config)(struct uart_port *, struct serial_iso7816 *iso7816); @@ -171,7 +494,7 @@ struct uart_port { * assigned from the serial_struct flags in uart_set_info() * [for bit definitions in the UPF_CHANGE_MASK] * - * Bits [0..UPF_LAST_USER] are userspace defined/visible/changeable + * Bits [0..ASYNCB_LAST_USER] are userspace defined/visible/changeable * The remaining bits are serial-core specific and not modifiable by * userspace. */ @@ -190,23 +513,24 @@ struct uart_port { #define UPF_BUGGY_UART ((__force upf_t) ASYNC_BUGGY_UART /* 14 */ ) #define UPF_MAGIC_MULTIPLIER ((__force upf_t) ASYNC_MAGIC_MULTIPLIER /* 16 */ ) -#define UPF_NO_THRE_TEST ((__force upf_t) (1 << 19)) +#define UPF_NO_THRE_TEST ((__force upf_t) BIT_ULL(19)) /* Port has hardware-assisted h/w flow control */ -#define UPF_AUTO_CTS ((__force upf_t) (1 << 20)) -#define UPF_AUTO_RTS ((__force upf_t) (1 << 21)) +#define UPF_AUTO_CTS ((__force upf_t) BIT_ULL(20)) +#define UPF_AUTO_RTS ((__force upf_t) BIT_ULL(21)) #define UPF_HARD_FLOW ((__force upf_t) (UPF_AUTO_CTS | UPF_AUTO_RTS)) /* Port has hardware-assisted s/w flow control */ -#define UPF_SOFT_FLOW ((__force upf_t) (1 << 22)) -#define UPF_CONS_FLOW ((__force upf_t) (1 << 23)) -#define UPF_SHARE_IRQ ((__force upf_t) (1 << 24)) -#define UPF_EXAR_EFR ((__force upf_t) (1 << 25)) -#define UPF_BUG_THRE ((__force upf_t) (1 << 26)) +#define UPF_SOFT_FLOW ((__force upf_t) BIT_ULL(22)) +#define UPF_CONS_FLOW ((__force upf_t) BIT_ULL(23)) +#define UPF_SHARE_IRQ ((__force upf_t) BIT_ULL(24)) +#define UPF_EXAR_EFR ((__force upf_t) BIT_ULL(25)) +#define UPF_BUG_THRE ((__force upf_t) BIT_ULL(26)) /* The exact UART type is known and should not be probed. */ -#define UPF_FIXED_TYPE ((__force upf_t) (1 << 27)) -#define UPF_BOOT_AUTOCONF ((__force upf_t) (1 << 28)) -#define UPF_FIXED_PORT ((__force upf_t) (1 << 29)) -#define UPF_DEAD ((__force upf_t) (1 << 30)) -#define UPF_IOREMAP ((__force upf_t) (1 << 31)) +#define UPF_FIXED_TYPE ((__force upf_t) BIT_ULL(27)) +#define UPF_BOOT_AUTOCONF ((__force upf_t) BIT_ULL(28)) +#define UPF_FIXED_PORT ((__force upf_t) BIT_ULL(29)) +#define UPF_DEAD ((__force upf_t) BIT_ULL(30)) +#define UPF_IOREMAP ((__force upf_t) BIT_ULL(31)) +#define UPF_FULL_PROBE ((__force upf_t) BIT_ULL(32)) #define __UPF_CHANGE_MASK 0x17fff #define UPF_CHANGE_MASK ((__force upf_t) __UPF_CHANGE_MASK) @@ -231,7 +555,7 @@ struct uart_port { int hw_stopped; /* sw-assisted CTS flow state */ unsigned int mctrl; /* current modem ctrl settings */ - unsigned int timeout; /* character-based timeout */ + unsigned int frame_time; /* frame timing in ns */ unsigned int type; /* port type */ const struct uart_ops *ops; unsigned int custom_divisor; @@ -253,6 +577,7 @@ struct uart_port { struct attribute_group *attr_group; /* port specific attributes */ const struct attribute_group **tty_groups; /* all attributes (serial core use only) */ struct serial_rs485 rs485; + struct serial_rs485 rs485_supported; /* Supported mask for serial_rs485 */ struct gpio_desc *rs485_term_gpio; /* enable RS485 bus termination */ struct serial_iso7816 iso7816; void *private_data; /* generic platform data pointer */ @@ -300,6 +625,23 @@ struct uart_state { /* number of characters left in xmit buffer before we ask for more */ #define WAKEUP_CHARS 256 +/** + * uart_xmit_advance - Advance xmit buffer and account Tx'ed chars + * @up: uart_port structure describing the port + * @chars: number of characters sent + * + * This function advances the tail of circular xmit buffer by the number of + * @chars transmitted and handles accounting of transmitted bytes (into + * @up's icount.tx). + */ +static inline void uart_xmit_advance(struct uart_port *up, unsigned int chars) +{ + struct circ_buf *xmit = &up->state->xmit; + + xmit->tail = (xmit->tail + chars) & (UART_XMIT_SIZE - 1); + up->icount.tx += chars; +} + struct module; struct tty_driver; @@ -328,14 +670,27 @@ void uart_write_wakeup(struct uart_port *port); void uart_update_timeout(struct uart_port *port, unsigned int cflag, unsigned int baud); unsigned int uart_get_baud_rate(struct uart_port *port, struct ktermios *termios, - struct ktermios *old, unsigned int min, + const struct ktermios *old, unsigned int min, unsigned int max); unsigned int uart_get_divisor(struct uart_port *port, unsigned int baud); +/* + * Calculates FIFO drain time. + */ +static inline unsigned long uart_fifo_timeout(struct uart_port *port) +{ + u64 fifo_timeout = (u64)READ_ONCE(port->frame_time) * port->fifosize; + + /* Add .02 seconds of slop */ + fifo_timeout += 20 * NSEC_PER_MSEC; + + return max(nsecs_to_jiffies(fifo_timeout), 1UL); +} + /* Base timer interval for polling */ static inline int uart_poll_timeout(struct uart_port *port) { - int timeout = port->timeout; + int timeout = uart_fifo_timeout(port); return timeout > 6 ? (timeout / 2 - 2) : 1; } @@ -388,6 +743,11 @@ static const bool earlycon_acpi_spcr_enable EARLYCON_USED_OR_UNUSED; static inline int setup_earlycon(char *buf) { return 0; } #endif +static inline bool uart_console_enabled(struct uart_port *port) +{ + return uart_console(port) && (port->cons->flags & CON_ENABLED); +} + struct uart_port *uart_get_console(struct uart_port *ports, int nr, struct console *c); int uart_parse_earlycon(char *p, unsigned char *iotype, resource_size_t *addr, @@ -399,7 +759,7 @@ int uart_set_options(struct uart_port *port, struct console *co, int baud, struct tty_driver *uart_console_device(struct console *co, int *index); void uart_console_write(struct uart_port *port, const char *s, unsigned int count, - void (*putchar)(struct uart_port *, int)); + void (*putchar)(struct uart_port *, unsigned char)); /* * Port/driver registration/removal @@ -458,6 +818,8 @@ extern void uart_handle_cts_change(struct uart_port *uport, extern void uart_insert_char(struct uart_port *port, unsigned int status, unsigned int overrun, unsigned int ch, unsigned int flag); +void uart_xchar_out(struct uart_port *uport, int offset); + #ifdef CONFIG_MAGIC_SYSRQ_SERIAL #define SYSRQ_TIMEOUT (HZ * 5) diff --git a/include/linux/serial_s3c.h b/include/linux/serial_s3c.h index cf0de4a86640..1672cf0810ef 100644 --- a/include/linux/serial_s3c.h +++ b/include/linux/serial_s3c.h @@ -27,15 +27,6 @@ #define S3C2410_UERSTAT (0x14) #define S3C2410_UFSTAT (0x18) #define S3C2410_UMSTAT (0x1C) -#define USI_CON (0xC4) -#define USI_OPTION (0xC8) - -#define USI_CON_RESET (1<<0) -#define USI_CON_RESET_MASK (1<<0) - -#define USI_OPTION_HWACG_CLKREQ_ON (1<<1) -#define USI_OPTION_HWACG_CLKSTOP_ON (1<<2) -#define USI_OPTION_HWACG_MASK (3<<1) #define S3C2410_LCON_CFGMASK ((0xF<<3)|(0x3)) @@ -92,7 +83,7 @@ #define S3C2410_UCON_RXIRQMODE (1<<0) #define S3C2410_UCON_RXFIFO_TOI (1<<7) #define S3C2443_UCON_RXERR_IRQEN (1<<6) -#define S3C2443_UCON_LOOPBACK (1<<5) +#define S3C2410_UCON_LOOPBACK (1<<5) #define S3C2410_UCON_DEFAULT (S3C2410_UCON_TXILEVEL | \ S3C2410_UCON_RXILEVEL | \ @@ -265,6 +256,9 @@ #define APPLE_S5L_UCON_DEFAULT (S3C2410_UCON_TXIRQMODE | \ S3C2410_UCON_RXIRQMODE | \ S3C2410_UCON_RXFIFO_TOI) +#define APPLE_S5L_UCON_MASK (APPLE_S5L_UCON_RXTO_ENA_MSK | \ + APPLE_S5L_UCON_RXTHRESH_ENA_MSK | \ + APPLE_S5L_UCON_TXTHRESH_ENA_MSK) #define APPLE_S5L_UTRSTAT_RXTHRESH (1<<4) #define APPLE_S5L_UTRSTAT_TXTHRESH (1<<5) diff --git a/include/linux/set_memory.h b/include/linux/set_memory.h index f36be5166c19..369769ce7399 100644 --- a/include/linux/set_memory.h +++ b/include/linux/set_memory.h @@ -42,14 +42,14 @@ static inline bool can_set_direct_map(void) #endif #endif /* CONFIG_ARCH_HAS_SET_DIRECT_MAP */ -#ifndef set_mce_nospec -static inline int set_mce_nospec(unsigned long pfn, bool unmap) +#ifdef CONFIG_X86_64 +int set_mce_nospec(unsigned long pfn); +int clear_mce_nospec(unsigned long pfn); +#else +static inline int set_mce_nospec(unsigned long pfn) { return 0; } -#endif - -#ifndef clear_mce_nospec static inline int clear_mce_nospec(unsigned long pfn) { return 0; diff --git a/include/linux/sfp.h b/include/linux/sfp.h index 302094b855fb..d1f343853b6c 100644 --- a/include/linux/sfp.h +++ b/include/linux/sfp.h @@ -535,7 +535,7 @@ int sfp_parse_port(struct sfp_bus *bus, const struct sfp_eeprom_id *id, unsigned long *support); bool sfp_may_have_phy(struct sfp_bus *bus, const struct sfp_eeprom_id *id); void sfp_parse_support(struct sfp_bus *bus, const struct sfp_eeprom_id *id, - unsigned long *support); + unsigned long *support, unsigned long *interfaces); phy_interface_t sfp_select_interface(struct sfp_bus *bus, unsigned long *link_modes); @@ -568,7 +568,8 @@ static inline bool sfp_may_have_phy(struct sfp_bus *bus, static inline void sfp_parse_support(struct sfp_bus *bus, const struct sfp_eeprom_id *id, - unsigned long *support) + unsigned long *support, + unsigned long *interfaces) { } diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index 166158b6e917..d500ea967dc7 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -24,9 +24,16 @@ struct shmem_inode_info { struct shared_policy policy; /* NUMA memory alloc policy */ struct simple_xattrs xattrs; /* list of xattrs */ atomic_t stop_eviction; /* hold when working on inode */ + struct timespec64 i_crtime; /* file creation time */ + unsigned int fsflags; /* flags for FS_IOC_[SG]ETFLAGS */ struct inode vfs_inode; }; +#define SHMEM_FL_USER_VISIBLE FS_FL_USER_VISIBLE +#define SHMEM_FL_USER_MODIFIABLE \ + (FS_IMMUTABLE_FL | FS_APPEND_FL | FS_NODUMP_FL | FS_NOATIME_FL) +#define SHMEM_FL_INHERITED (FS_NODUMP_FL | FS_NOATIME_FL) + struct shmem_sb_info { unsigned long max_blocks; /* How many blocks are allowed */ struct percpu_counter used_blocks; /* How many are allocated */ @@ -55,7 +62,7 @@ static inline struct shmem_inode_info *SHMEM_I(struct inode *inode) * Functions in mm/shmem.c called directly from elsewhere: */ extern const struct fs_parameter_spec shmem_fs_parameters[]; -extern int shmem_init(void); +extern void shmem_init(void); extern int shmem_init_fs_context(struct fs_context *fc); extern struct file *shmem_file_setup(const char *name, loff_t size, unsigned long flags); @@ -83,20 +90,21 @@ extern void shmem_unlock_mapping(struct address_space *mapping); extern struct page *shmem_read_mapping_page_gfp(struct address_space *mapping, pgoff_t index, gfp_t gfp_mask); extern void shmem_truncate_range(struct inode *inode, loff_t start, loff_t end); -extern int shmem_unuse(unsigned int type, bool frontswap, - unsigned long *fs_pages_to_unuse); +int shmem_unuse(unsigned int type); -extern bool shmem_is_huge(struct vm_area_struct *vma, - struct inode *inode, pgoff_t index); -static inline bool shmem_huge_enabled(struct vm_area_struct *vma) +extern bool shmem_is_huge(struct vm_area_struct *vma, struct inode *inode, + pgoff_t index, bool shmem_huge_force); +static inline bool shmem_huge_enabled(struct vm_area_struct *vma, + bool shmem_huge_force) { - return shmem_is_huge(vma, file_inode(vma->vm_file), vma->vm_pgoff); + return shmem_is_huge(vma, file_inode(vma->vm_file), vma->vm_pgoff, + shmem_huge_force); } extern unsigned long shmem_swap_usage(struct vm_area_struct *vma); extern unsigned long shmem_partial_swap_usage(struct address_space *mapping, pgoff_t start, pgoff_t end); -/* Flag allocation requirements to shmem_getpage */ +/* Flag allocation requirements to shmem_get_folio */ enum sgp_type { SGP_READ, /* don't exceed i_size, don't allocate page */ SGP_NOALLOC, /* similar, but fail on hole or use fallocated page */ @@ -105,8 +113,8 @@ enum sgp_type { SGP_FALLOC, /* like SGP_WRITE, but make existing page Uptodate */ }; -extern int shmem_getpage(struct inode *inode, pgoff_t index, - struct page **pagep, enum sgp_type sgp); +int shmem_get_folio(struct inode *inode, pgoff_t index, struct folio **foliop, + enum sgp_type sgp); static inline struct page *shmem_read_mapping_page( struct address_space *mapping, pgoff_t index) @@ -145,11 +153,11 @@ extern int shmem_mfill_atomic_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd, struct vm_area_struct *dst_vma, unsigned long dst_addr, unsigned long src_addr, - bool zeropage, + bool zeropage, bool wp_copy, struct page **pagep); #else /* !CONFIG_SHMEM */ #define shmem_mfill_atomic_pte(dst_mm, dst_pmd, dst_vma, dst_addr, \ - src_addr, zeropage, pagep) ({ BUG(); 0; }) + src_addr, zeropage, wp_copy, pagep) ({ BUG(); 0; }) #endif /* CONFIG_SHMEM */ #endif /* CONFIG_USERFAULTFD */ diff --git a/include/linux/shrinker.h b/include/linux/shrinker.h index 76fbf92b04d9..08e6054e061f 100644 --- a/include/linux/shrinker.h +++ b/include/linux/shrinker.h @@ -73,6 +73,11 @@ struct shrinker { /* ID in shrinker_idr */ int id; #endif +#ifdef CONFIG_SHRINKER_DEBUG + int debugfs_id; + const char *name; + struct dentry *debugfs_entry; +#endif /* objs pending delete, per node */ atomic_long_t *nr_deferred; }; @@ -88,10 +93,32 @@ struct shrinker { */ #define SHRINKER_NONSLAB (1 << 3) -extern int prealloc_shrinker(struct shrinker *shrinker); +extern int __printf(2, 3) prealloc_shrinker(struct shrinker *shrinker, + const char *fmt, ...); extern void register_shrinker_prepared(struct shrinker *shrinker); -extern int register_shrinker(struct shrinker *shrinker); +extern int __printf(2, 3) register_shrinker(struct shrinker *shrinker, + const char *fmt, ...); extern void unregister_shrinker(struct shrinker *shrinker); extern void free_prealloced_shrinker(struct shrinker *shrinker); extern void synchronize_shrinkers(void); -#endif + +#ifdef CONFIG_SHRINKER_DEBUG +extern int shrinker_debugfs_add(struct shrinker *shrinker); +extern void shrinker_debugfs_remove(struct shrinker *shrinker); +extern int __printf(2, 3) shrinker_debugfs_rename(struct shrinker *shrinker, + const char *fmt, ...); +#else /* CONFIG_SHRINKER_DEBUG */ +static inline int shrinker_debugfs_add(struct shrinker *shrinker) +{ + return 0; +} +static inline void shrinker_debugfs_remove(struct shrinker *shrinker) +{ +} +static inline __printf(2, 3) +int shrinker_debugfs_rename(struct shrinker *shrinker, const char *fmt, ...) +{ + return 0; +} +#endif /* CONFIG_SHRINKER_DEBUG */ +#endif /* _LINUX_SHRINKER_H */ diff --git a/include/linux/signal.h b/include/linux/signal.h index a6db6f2ae113..3b98e7a28538 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -282,7 +282,8 @@ extern int do_send_sig_info(int sig, struct kernel_siginfo *info, struct task_struct *p, enum pid_type type); extern int group_send_sig_info(int sig, struct kernel_siginfo *info, struct task_struct *p, enum pid_type type); -extern int __group_send_sig_info(int, struct kernel_siginfo *, struct task_struct *); +extern int send_signal_locked(int sig, struct kernel_siginfo *info, + struct task_struct *p, enum pid_type type); extern int sigprocmask(int, sigset_t *, sigset_t *); extern void set_current_blocked(sigset_t *); extern void __set_current_blocked(const sigset_t *); diff --git a/include/linux/siphash.h b/include/linux/siphash.h index cce8a9acc76c..9153e77382e1 100644 --- a/include/linux/siphash.h +++ b/include/linux/siphash.h @@ -1,6 +1,5 @@ -/* Copyright (C) 2016 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. - * - * This file is provided under a dual BSD/GPLv2 license. +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ +/* Copyright (C) 2016-2022 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. * * SipHash: a fast short-input PRF * https://131002.net/siphash/ @@ -138,4 +137,32 @@ static inline u32 hsiphash(const void *data, size_t len, return ___hsiphash_aligned(data, len, key); } +/* + * These macros expose the raw SipHash and HalfSipHash permutations. + * Do not use them directly! If you think you have a use for them, + * be sure to CC the maintainer of this file explaining why. + */ + +#define SIPHASH_PERMUTATION(a, b, c, d) ( \ + (a) += (b), (b) = rol64((b), 13), (b) ^= (a), (a) = rol64((a), 32), \ + (c) += (d), (d) = rol64((d), 16), (d) ^= (c), \ + (a) += (d), (d) = rol64((d), 21), (d) ^= (a), \ + (c) += (b), (b) = rol64((b), 17), (b) ^= (c), (c) = rol64((c), 32)) + +#define SIPHASH_CONST_0 0x736f6d6570736575ULL +#define SIPHASH_CONST_1 0x646f72616e646f6dULL +#define SIPHASH_CONST_2 0x6c7967656e657261ULL +#define SIPHASH_CONST_3 0x7465646279746573ULL + +#define HSIPHASH_PERMUTATION(a, b, c, d) ( \ + (a) += (b), (b) = rol32((b), 5), (b) ^= (a), (a) = rol32((a), 16), \ + (c) += (d), (d) = rol32((d), 8), (d) ^= (c), \ + (a) += (d), (d) = rol32((d), 7), (d) ^= (a), \ + (c) += (b), (b) = rol32((b), 13), (b) ^= (c), (c) = rol32((c), 16)) + +#define HSIPHASH_CONST_0 0U +#define HSIPHASH_CONST_1 0U +#define HSIPHASH_CONST_2 0x6c796765U +#define HSIPHASH_CONST_3 0x74656462U + #endif /* _LINUX_SIPHASH_H */ diff --git a/include/linux/sizes.h b/include/linux/sizes.h index 1ac79bcee2bb..84aa448d8bb3 100644 --- a/include/linux/sizes.h +++ b/include/linux/sizes.h @@ -47,6 +47,8 @@ #define SZ_8G _AC(0x200000000, ULL) #define SZ_16G _AC(0x400000000, ULL) #define SZ_32G _AC(0x800000000, ULL) + +#define SZ_1T _AC(0x10000000000, ULL) #define SZ_64T _AC(0x400000000000, ULL) #endif /* __LINUX_SIZES_H__ */ diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index bf11e1fbd69b..7be5bb4c94b6 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -42,99 +42,115 @@ #if IS_ENABLED(CONFIG_NF_CONNTRACK) #include <linux/netfilter/nf_conntrack_common.h> #endif +#include <net/net_debug.h> +#include <net/dropreason.h> -/* The interface for checksum offload between the stack and networking drivers +/** + * DOC: skb checksums + * + * The interface for checksum offload between the stack and networking drivers * is as follows... * - * A. IP checksum related features + * IP checksum related features + * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~ * * Drivers advertise checksum offload capabilities in the features of a device. * From the stack's point of view these are capabilities offered by the driver. * A driver typically only advertises features that it is capable of offloading * to its device. * - * The checksum related features are: - * - * NETIF_F_HW_CSUM - The driver (or its device) is able to compute one - * IP (one's complement) checksum for any combination - * of protocols or protocol layering. The checksum is - * computed and set in a packet per the CHECKSUM_PARTIAL - * interface (see below). - * - * NETIF_F_IP_CSUM - Driver (device) is only able to checksum plain - * TCP or UDP packets over IPv4. These are specifically - * unencapsulated packets of the form IPv4|TCP or - * IPv4|UDP where the Protocol field in the IPv4 header - * is TCP or UDP. The IPv4 header may contain IP options. - * This feature cannot be set in features for a device - * with NETIF_F_HW_CSUM also set. This feature is being - * DEPRECATED (see below). - * - * NETIF_F_IPV6_CSUM - Driver (device) is only able to checksum plain - * TCP or UDP packets over IPv6. These are specifically - * unencapsulated packets of the form IPv6|TCP or - * IPv6|UDP where the Next Header field in the IPv6 - * header is either TCP or UDP. IPv6 extension headers - * are not supported with this feature. This feature - * cannot be set in features for a device with - * NETIF_F_HW_CSUM also set. This feature is being - * DEPRECATED (see below). - * - * NETIF_F_RXCSUM - Driver (device) performs receive checksum offload. - * This flag is only used to disable the RX checksum - * feature for a device. The stack will accept receive - * checksum indication in packets received on a device - * regardless of whether NETIF_F_RXCSUM is set. - * - * B. Checksumming of received packets by device. Indication of checksum - * verification is set in skb->ip_summed. Possible values are: - * - * CHECKSUM_NONE: + * .. flat-table:: Checksum related device features + * :widths: 1 10 + * + * * - %NETIF_F_HW_CSUM + * - The driver (or its device) is able to compute one + * IP (one's complement) checksum for any combination + * of protocols or protocol layering. The checksum is + * computed and set in a packet per the CHECKSUM_PARTIAL + * interface (see below). + * + * * - %NETIF_F_IP_CSUM + * - Driver (device) is only able to checksum plain + * TCP or UDP packets over IPv4. These are specifically + * unencapsulated packets of the form IPv4|TCP or + * IPv4|UDP where the Protocol field in the IPv4 header + * is TCP or UDP. The IPv4 header may contain IP options. + * This feature cannot be set in features for a device + * with NETIF_F_HW_CSUM also set. This feature is being + * DEPRECATED (see below). + * + * * - %NETIF_F_IPV6_CSUM + * - Driver (device) is only able to checksum plain + * TCP or UDP packets over IPv6. These are specifically + * unencapsulated packets of the form IPv6|TCP or + * IPv6|UDP where the Next Header field in the IPv6 + * header is either TCP or UDP. IPv6 extension headers + * are not supported with this feature. This feature + * cannot be set in features for a device with + * NETIF_F_HW_CSUM also set. This feature is being + * DEPRECATED (see below). + * + * * - %NETIF_F_RXCSUM + * - Driver (device) performs receive checksum offload. + * This flag is only used to disable the RX checksum + * feature for a device. The stack will accept receive + * checksum indication in packets received on a device + * regardless of whether NETIF_F_RXCSUM is set. + * + * Checksumming of received packets by device + * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + * + * Indication of checksum verification is set in &sk_buff.ip_summed. + * Possible values are: + * + * - %CHECKSUM_NONE * * Device did not checksum this packet e.g. due to lack of capabilities. * The packet contains full (though not verified) checksum in packet but * not in skb->csum. Thus, skb->csum is undefined in this case. * - * CHECKSUM_UNNECESSARY: + * - %CHECKSUM_UNNECESSARY * * The hardware you're dealing with doesn't calculate the full checksum - * (as in CHECKSUM_COMPLETE), but it does parse headers and verify checksums - * for specific protocols. For such packets it will set CHECKSUM_UNNECESSARY - * if their checksums are okay. skb->csum is still undefined in this case + * (as in %CHECKSUM_COMPLETE), but it does parse headers and verify checksums + * for specific protocols. For such packets it will set %CHECKSUM_UNNECESSARY + * if their checksums are okay. &sk_buff.csum is still undefined in this case * though. A driver or device must never modify the checksum field in the * packet even if checksum is verified. * - * CHECKSUM_UNNECESSARY is applicable to following protocols: - * TCP: IPv6 and IPv4. - * UDP: IPv4 and IPv6. A device may apply CHECKSUM_UNNECESSARY to a + * %CHECKSUM_UNNECESSARY is applicable to following protocols: + * + * - TCP: IPv6 and IPv4. + * - UDP: IPv4 and IPv6. A device may apply CHECKSUM_UNNECESSARY to a * zero UDP checksum for either IPv4 or IPv6, the networking stack * may perform further validation in this case. - * GRE: only if the checksum is present in the header. - * SCTP: indicates the CRC in SCTP header has been validated. - * FCOE: indicates the CRC in FC frame has been validated. + * - GRE: only if the checksum is present in the header. + * - SCTP: indicates the CRC in SCTP header has been validated. + * - FCOE: indicates the CRC in FC frame has been validated. * - * skb->csum_level indicates the number of consecutive checksums found in - * the packet minus one that have been verified as CHECKSUM_UNNECESSARY. + * &sk_buff.csum_level indicates the number of consecutive checksums found in + * the packet minus one that have been verified as %CHECKSUM_UNNECESSARY. * For instance if a device receives an IPv6->UDP->GRE->IPv4->TCP packet * and a device is able to verify the checksums for UDP (possibly zero), - * GRE (checksum flag is set) and TCP, skb->csum_level would be set to + * GRE (checksum flag is set) and TCP, &sk_buff.csum_level would be set to * two. If the device were only able to verify the UDP checksum and not * GRE, either because it doesn't support GRE checksum or because GRE * checksum is bad, skb->csum_level would be set to zero (TCP checksum is * not considered in this case). * - * CHECKSUM_COMPLETE: + * - %CHECKSUM_COMPLETE * * This is the most generic way. The device supplied checksum of the _whole_ - * packet as seen by netif_rx() and fills in skb->csum. This means the + * packet as seen by netif_rx() and fills in &sk_buff.csum. This means the * hardware doesn't need to parse L3/L4 headers to implement this. * * Notes: + * * - Even if device supports only some protocols, but is able to produce * skb->csum, it MUST use CHECKSUM_COMPLETE, not CHECKSUM_UNNECESSARY. * - CHECKSUM_COMPLETE is not applicable to SCTP and FCoE protocols. * - * CHECKSUM_PARTIAL: + * - %CHECKSUM_PARTIAL * * A checksum is set up to be offloaded to a device as described in the * output description for CHECKSUM_PARTIAL. This may occur on a packet @@ -146,14 +162,18 @@ * packet that are after the checksum being offloaded are not considered to * be verified. * - * C. Checksumming on transmit for non-GSO. The stack requests checksum offload - * in the skb->ip_summed for a packet. Values are: + * Checksumming on transmit for non-GSO + * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ * - * CHECKSUM_PARTIAL: + * The stack requests checksum offload in the &sk_buff.ip_summed for a packet. + * Values are: + * + * - %CHECKSUM_PARTIAL * * The driver is required to checksum the packet as seen by hard_start_xmit() - * from skb->csum_start up to the end, and to record/write the checksum at - * offset skb->csum_start + skb->csum_offset. A driver may verify that the + * from &sk_buff.csum_start up to the end, and to record/write the checksum at + * offset &sk_buff.csum_start + &sk_buff.csum_offset. + * A driver may verify that the * csum_start and csum_offset values are valid values given the length and * offset of the packet, but it should not attempt to validate that the * checksum refers to a legitimate transport layer checksum -- it is the @@ -165,55 +185,66 @@ * checksum calculation to the device, or call skb_checksum_help (in the case * that the device does not support offload for a particular checksum). * - * NETIF_F_IP_CSUM and NETIF_F_IPV6_CSUM are being deprecated in favor of - * NETIF_F_HW_CSUM. New devices should use NETIF_F_HW_CSUM to indicate + * %NETIF_F_IP_CSUM and %NETIF_F_IPV6_CSUM are being deprecated in favor of + * %NETIF_F_HW_CSUM. New devices should use %NETIF_F_HW_CSUM to indicate * checksum offload capability. - * skb_csum_hwoffload_help() can be called to resolve CHECKSUM_PARTIAL based + * skb_csum_hwoffload_help() can be called to resolve %CHECKSUM_PARTIAL based * on network device checksumming capabilities: if a packet does not match - * them, skb_checksum_help or skb_crc32c_help (depending on the value of - * csum_not_inet, see item D.) is called to resolve the checksum. + * them, skb_checksum_help() or skb_crc32c_help() (depending on the value of + * &sk_buff.csum_not_inet, see :ref:`crc`) + * is called to resolve the checksum. * - * CHECKSUM_NONE: + * - %CHECKSUM_NONE * * The skb was already checksummed by the protocol, or a checksum is not * required. * - * CHECKSUM_UNNECESSARY: + * - %CHECKSUM_UNNECESSARY * * This has the same meaning as CHECKSUM_NONE for checksum offload on * output. * - * CHECKSUM_COMPLETE: + * - %CHECKSUM_COMPLETE + * * Not used in checksum output. If a driver observes a packet with this value - * set in skbuff, it should treat the packet as if CHECKSUM_NONE were set. - * - * D. Non-IP checksum (CRC) offloads - * - * NETIF_F_SCTP_CRC - This feature indicates that a device is capable of - * offloading the SCTP CRC in a packet. To perform this offload the stack - * will set csum_start and csum_offset accordingly, set ip_summed to - * CHECKSUM_PARTIAL and set csum_not_inet to 1, to provide an indication in - * the skbuff that the CHECKSUM_PARTIAL refers to CRC32c. - * A driver that supports both IP checksum offload and SCTP CRC32c offload - * must verify which offload is configured for a packet by testing the - * value of skb->csum_not_inet; skb_crc32c_csum_help is provided to resolve - * CHECKSUM_PARTIAL on skbs where csum_not_inet is set to 1. - * - * NETIF_F_FCOE_CRC - This feature indicates that a device is capable of - * offloading the FCOE CRC in a packet. To perform this offload the stack - * will set ip_summed to CHECKSUM_PARTIAL and set csum_start and csum_offset - * accordingly. Note that there is no indication in the skbuff that the - * CHECKSUM_PARTIAL refers to an FCOE checksum, so a driver that supports - * both IP checksum offload and FCOE CRC offload must verify which offload - * is configured for a packet, presumably by inspecting packet headers. - * - * E. Checksumming on output with GSO. - * - * In the case of a GSO packet (skb_is_gso(skb) is true), checksum offload + * set in skbuff, it should treat the packet as if %CHECKSUM_NONE were set. + * + * .. _crc: + * + * Non-IP checksum (CRC) offloads + * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + * + * .. flat-table:: + * :widths: 1 10 + * + * * - %NETIF_F_SCTP_CRC + * - This feature indicates that a device is capable of + * offloading the SCTP CRC in a packet. To perform this offload the stack + * will set csum_start and csum_offset accordingly, set ip_summed to + * %CHECKSUM_PARTIAL and set csum_not_inet to 1, to provide an indication + * in the skbuff that the %CHECKSUM_PARTIAL refers to CRC32c. + * A driver that supports both IP checksum offload and SCTP CRC32c offload + * must verify which offload is configured for a packet by testing the + * value of &sk_buff.csum_not_inet; skb_crc32c_csum_help() is provided to + * resolve %CHECKSUM_PARTIAL on skbs where csum_not_inet is set to 1. + * + * * - %NETIF_F_FCOE_CRC + * - This feature indicates that a device is capable of offloading the FCOE + * CRC in a packet. To perform this offload the stack will set ip_summed + * to %CHECKSUM_PARTIAL and set csum_start and csum_offset + * accordingly. Note that there is no indication in the skbuff that the + * %CHECKSUM_PARTIAL refers to an FCOE checksum, so a driver that supports + * both IP checksum offload and FCOE CRC offload must verify which offload + * is configured for a packet, presumably by inspecting packet headers. + * + * Checksumming on output with GSO + * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + * + * In the case of a GSO packet (skb_is_gso() is true), checksum offload * is implied by the SKB_GSO_* flags in gso_type. Most obviously, if the - * gso_type is SKB_GSO_TCPV4 or SKB_GSO_TCPV6, TCP checksum offload as + * gso_type is %SKB_GSO_TCPV4 or %SKB_GSO_TCPV6, TCP checksum offload as * part of the GSO operation is implied. If a checksum is being offloaded - * with GSO then ip_summed is CHECKSUM_PARTIAL, and both csum_start and + * with GSO then ip_summed is %CHECKSUM_PARTIAL, and both csum_start and * csum_offset are set to refer to the outermost checksum being offloaded * (two offloaded checksums are possible with UDP encapsulation). */ @@ -307,22 +338,6 @@ struct sk_buff_head { struct sk_buff; -/* The reason of skb drop, which is used in kfree_skb_reason(). - * en...maybe they should be splited by group? - * - * Each item here should also be in 'TRACE_SKB_DROP_REASON', which is - * used to translate the reason to string. - */ -enum skb_drop_reason { - SKB_DROP_REASON_NOT_SPECIFIED, - SKB_DROP_REASON_NO_SOCKET, - SKB_DROP_REASON_PKT_TOO_SMALL, - SKB_DROP_REASON_TCP_CSUM, - SKB_DROP_REASON_TCP_FILTER, - SKB_DROP_REASON_UDP_CSUM, - SKB_DROP_REASON_MAX, -}; - /* To allow 64K frame to be packed as single skb without frag_list we * require 64K/PAGE_SIZE pages plus 1 additional page to allow for * buffers which do not start on a page boundary. @@ -427,8 +442,10 @@ static inline bool skb_frag_must_loop(struct page *p) /** * struct skb_shared_hwtstamps - hardware time stamps - * @hwtstamp: hardware time stamp transformed into duration - * since arbitrary point in time + * @hwtstamp: hardware time stamp transformed into duration + * since arbitrary point in time + * @netdev_data: address/cookie of network device driver used as + * reference to actual hardware time stamp * * Software time stamps generated by ktime_get_real() are stored in * skb->tstamp. @@ -440,7 +457,10 @@ static inline bool skb_frag_must_loop(struct page *p) * &skb_shared_info. Use skb_hwtstamps() to get a pointer. */ struct skb_shared_hwtstamps { - ktime_t hwtstamp; + union { + ktime_t hwtstamp; + void *netdev_data; + }; }; /* Definitions for tx_flags in struct skb_shared_info */ @@ -454,16 +474,24 @@ enum { /* device driver is going to provide hardware time stamp */ SKBTX_IN_PROGRESS = 1 << 2, + /* generate hardware time stamp based on cycles if supported */ + SKBTX_HW_TSTAMP_USE_CYCLES = 1 << 3, + /* generate wifi status information (where possible) */ SKBTX_WIFI_STATUS = 1 << 4, + /* determine hardware time stamp based on time or cycles */ + SKBTX_HW_TSTAMP_NETDEV = 1 << 5, + /* generate software time stamp when entering packet scheduling */ SKBTX_SCHED_TSTAMP = 1 << 6, }; #define SKBTX_ANY_SW_TSTAMP (SKBTX_SW_TSTAMP | \ SKBTX_SCHED_TSTAMP) -#define SKBTX_ANY_TSTAMP (SKBTX_HW_TSTAMP | SKBTX_ANY_SW_TSTAMP) +#define SKBTX_ANY_TSTAMP (SKBTX_HW_TSTAMP | \ + SKBTX_HW_TSTAMP_USE_CYCLES | \ + SKBTX_ANY_SW_TSTAMP) /* Definitions for flags in struct skb_shared_info */ enum { @@ -481,10 +509,18 @@ enum { * charged to the kernel memory. */ SKBFL_PURE_ZEROCOPY = BIT(2), + + SKBFL_DONT_ORPHAN = BIT(3), + + /* page references are managed by the ubuf_info, so it's safe to + * use frags only up until ubuf_info is released + */ + SKBFL_MANAGED_FRAG_REFS = BIT(4), }; #define SKBFL_ZEROCOPY_FRAG (SKBFL_ZEROCOPY_ENABLE | SKBFL_SHARED_FRAG) -#define SKBFL_ALL_ZEROCOPY (SKBFL_ZEROCOPY_FRAG | SKBFL_PURE_ZEROCOPY) +#define SKBFL_ALL_ZEROCOPY (SKBFL_ZEROCOPY_FRAG | SKBFL_PURE_ZEROCOPY | \ + SKBFL_DONT_ORPHAN | SKBFL_MANAGED_FRAG_REFS) /* * The callback notifies userspace to release buffers when skb DMA is done in @@ -497,6 +533,13 @@ enum { struct ubuf_info { void (*callback)(struct sk_buff *, struct ubuf_info *, bool zerocopy_success); + refcount_t refcnt; + u8 flags; +}; + +struct ubuf_info_msgzc { + struct ubuf_info ubuf; + union { struct { unsigned long desc; @@ -509,8 +552,6 @@ struct ubuf_info { u32 bytelen; }; }; - refcount_t refcnt; - u8 flags; struct mmpin { struct user_struct *user; @@ -519,24 +560,12 @@ struct ubuf_info { }; #define skb_uarg(SKB) ((struct ubuf_info *)(skb_shinfo(SKB)->destructor_arg)) +#define uarg_to_msgzc(ubuf_ptr) container_of((ubuf_ptr), struct ubuf_info_msgzc, \ + ubuf) int mm_account_pinned_pages(struct mmpin *mmp, size_t size); void mm_unaccount_pinned_pages(struct mmpin *mmp); -struct ubuf_info *msg_zerocopy_alloc(struct sock *sk, size_t size); -struct ubuf_info *msg_zerocopy_realloc(struct sock *sk, size_t size, - struct ubuf_info *uarg); - -void msg_zerocopy_put_abort(struct ubuf_info *uarg, bool have_uref); - -void msg_zerocopy_callback(struct sk_buff *skb, struct ubuf_info *uarg, - bool success); - -int skb_zerocopy_iter_dgram(struct sk_buff *skb, struct msghdr *msg, int len); -int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb, - struct msghdr *msg, int len, - struct ubuf_info *uarg); - /* This data is invariant across clones and lives at * the end of the header data, ie. at skb->end. */ @@ -557,6 +586,7 @@ struct skb_shared_info { * Warning : all fields before dataref are cleared in __alloc_skb() */ atomic_t dataref; + unsigned int xdp_frags_size; /* Intermediate layers must ensure that destructor_arg * remains valid until skb destructor */ @@ -566,16 +596,32 @@ struct skb_shared_info { skb_frag_t frags[MAX_SKB_FRAGS]; }; -/* We divide dataref into two halves. The higher 16 bits hold references - * to the payload part of skb->data. The lower 16 bits hold references to - * the entire skb->data. A clone of a headerless skb holds the length of - * the header in skb->hdr_len. - * - * All users must obey the rule that the skb->data reference count must be - * greater than or equal to the payload reference count. - * - * Holding a reference to the payload part means that the user does not - * care about modifications to the header part of skb->data. +/** + * DOC: dataref and headerless skbs + * + * Transport layers send out clones of payload skbs they hold for + * retransmissions. To allow lower layers of the stack to prepend their headers + * we split &skb_shared_info.dataref into two halves. + * The lower 16 bits count the overall number of references. + * The higher 16 bits indicate how many of the references are payload-only. + * skb_header_cloned() checks if skb is allowed to add / write the headers. + * + * The creator of the skb (e.g. TCP) marks its skb as &sk_buff.nohdr + * (via __skb_header_release()). Any clone created from marked skb will get + * &sk_buff.hdr_len populated with the available headroom. + * If there's the only clone in existence it's able to modify the headroom + * at will. The sequence of calls inside the transport layer is:: + * + * <alloc skb> + * skb_reserve() + * __skb_header_release() + * skb_clone() + * // send the clone down the stack + * + * This is not a very generic construct and it depends on the transport layers + * doing the right thing. In practice there's usually only one payload-only skb. + * Having multiple payload-only skbs with different lengths of hdr_len is not + * possible. The payload-only skbs should never leave their owner. */ #define SKB_DATAREF_SHIFT 16 #define SKB_DATAREF_MASK ((1 << SKB_DATAREF_SHIFT) - 1) @@ -640,6 +686,46 @@ typedef unsigned char *sk_buff_data_t; #endif /** + * DOC: Basic sk_buff geometry + * + * struct sk_buff itself is a metadata structure and does not hold any packet + * data. All the data is held in associated buffers. + * + * &sk_buff.head points to the main "head" buffer. The head buffer is divided + * into two parts: + * + * - data buffer, containing headers and sometimes payload; + * this is the part of the skb operated on by the common helpers + * such as skb_put() or skb_pull(); + * - shared info (struct skb_shared_info) which holds an array of pointers + * to read-only data in the (page, offset, length) format. + * + * Optionally &skb_shared_info.frag_list may point to another skb. + * + * Basic diagram may look like this:: + * + * --------------- + * | sk_buff | + * --------------- + * ,--------------------------- + head + * / ,----------------- + data + * / / ,----------- + tail + * | | | , + end + * | | | | + * v v v v + * ----------------------------------------------- + * | headroom | data | tailroom | skb_shared_info | + * ----------------------------------------------- + * + [page frag] + * + [page frag] + * + [page frag] + * + [page frag] --------- + * + frag_list --> | sk_buff | + * --------- + * + */ + +/** * struct sk_buff - socket buffer * @next: Next buffer in list * @prev: Previous buffer in list @@ -717,11 +803,17 @@ typedef unsigned char *sk_buff_data_t; * @csum_level: indicates the number of consecutive checksums found in * the packet minus one that have been verified as * CHECKSUM_UNNECESSARY (max 3) + * @scm_io_uring: SKB holds io_uring registered files * @dst_pending_confirm: need to confirm neighbour * @decrypted: Decrypted SKB * @slow_gro: state present at GRO time, slower prepare step required + * @mono_delivery_time: When set, skb->tstamp has the + * delivery_time in mono clock base (i.e. EDT). Otherwise, the + * skb->tstamp has the (rcv) timestamp at ingress and + * delivery_time at egress. * @napi_id: id of the NAPI struct this skb came from * @sender_cpu: (aka @napi_id) source CPU in XPS + * @alloc_cpu: CPU which did the skb allocation. * @secmark: security marking * @mark: Generic packet mark * @reserved_tailroom: (aka @mark) number of bytes of free space available @@ -862,8 +954,12 @@ struct sk_buff { __u8 vlan_present:1; /* See PKT_VLAN_PRESENT_BIT */ __u8 csum_complete_sw:1; __u8 csum_level:2; - __u8 csum_not_inet:1; __u8 dst_pending_confirm:1; + __u8 mono_delivery_time:1; /* See SKB_MONO_DELIVERY_TIME_MASK */ +#ifdef CONFIG_NET_CLS_ACT + __u8 tc_skip_classify:1; + __u8 tc_at_ingress:1; /* See TC_AT_INGRESS_MASK */ +#endif #ifdef CONFIG_IPV6_NDISC_NODETYPE __u8 ndisc_nodetype:2; #endif @@ -875,10 +971,6 @@ struct sk_buff { __u8 offload_fwd_mark:1; __u8 offload_l3_fwd_mark:1; #endif -#ifdef CONFIG_NET_CLS_ACT - __u8 tc_skip_classify:1; - __u8 tc_at_ingress:1; -#endif __u8 redirected:1; #ifdef CONFIG_NET_REDIRECT __u8 from_ingress:1; @@ -890,6 +982,8 @@ struct sk_buff { __u8 decrypted:1; #endif __u8 slow_gro:1; + __u8 csum_not_inet:1; + __u8 scm_io_uring:1; #ifdef CONFIG_NET_SCHED __u16 tc_index; /* traffic control index */ @@ -913,6 +1007,7 @@ struct sk_buff { unsigned int sender_cpu; }; #endif + u16 alloc_cpu; #ifdef CONFIG_NETWORK_SECMARK __u32 secmark; #endif @@ -964,11 +1059,17 @@ struct sk_buff { #endif #define PKT_TYPE_OFFSET offsetof(struct sk_buff, __pkt_type_offset) -/* if you move pkt_vlan_present around you also must adapt these constants */ +/* if you move pkt_vlan_present, tc_at_ingress, or mono_delivery_time + * around, you also must adapt these constants. + */ #ifdef __BIG_ENDIAN_BITFIELD #define PKT_VLAN_PRESENT_BIT 7 +#define TC_AT_INGRESS_MASK (1 << 0) +#define SKB_MONO_DELIVERY_TIME_MASK (1 << 2) #else #define PKT_VLAN_PRESENT_BIT 0 +#define TC_AT_INGRESS_MASK (1 << 7) +#define SKB_MONO_DELIVERY_TIME_MASK (1 << 5) #endif #define PKT_VLAN_PRESENT_OFFSET offsetof(struct sk_buff, __pkt_vlan_present_offset) @@ -1103,7 +1204,8 @@ static inline bool skb_unref(struct sk_buff *skb) return true; } -void kfree_skb_reason(struct sk_buff *skb, enum skb_drop_reason reason); +void __fix_address +kfree_skb_reason(struct sk_buff *skb, enum skb_drop_reason reason); /** * kfree_skb - free an sk_buff with 'NOT_SPECIFIED' reason @@ -1115,10 +1217,16 @@ static inline void kfree_skb(struct sk_buff *skb) } void skb_release_head_state(struct sk_buff *skb); -void kfree_skb_list(struct sk_buff *segs); +void kfree_skb_list_reason(struct sk_buff *segs, + enum skb_drop_reason reason); void skb_dump(const char *level, const struct sk_buff *skb, bool full_pkt); void skb_tx_error(struct sk_buff *skb); +static inline void kfree_skb_list(struct sk_buff *segs) +{ + kfree_skb_list_reason(segs, SKB_DROP_REASON_NOT_SPECIFIED); +} + #ifdef CONFIG_TRACEPOINTS void consume_skb(struct sk_buff *skb); #else @@ -1142,6 +1250,7 @@ struct sk_buff *__build_skb(void *data, unsigned int frag_size); struct sk_buff *build_skb(void *data, unsigned int frag_size); struct sk_buff *build_skb_around(struct sk_buff *skb, void *data, unsigned int frag_size); +void skb_attempt_defer_free(struct sk_buff *skb); struct sk_buff *napi_build_skb(void *data, unsigned int frag_size); @@ -1361,8 +1470,8 @@ void skb_flow_dissector_init(struct flow_dissector *flow_dissector, unsigned int key_count); struct bpf_flow_dissector; -bool bpf_flow_dissect(struct bpf_prog *prog, struct bpf_flow_dissector *ctx, - __be16 proto, int nhoff, int hlen, unsigned int flags); +u32 bpf_flow_dissect(struct bpf_prog *prog, struct bpf_flow_dissector *ctx, + __be16 proto, int nhoff, int hlen, unsigned int flags); bool __skb_flow_dissect(const struct net *net, const struct sk_buff *skb, @@ -1475,6 +1584,11 @@ static inline unsigned int skb_end_offset(const struct sk_buff *skb) { return skb->end; } + +static inline void skb_set_end_offset(struct sk_buff *skb, unsigned int offset) +{ + skb->end = offset; +} #else static inline unsigned char *skb_end_pointer(const struct sk_buff *skb) { @@ -1485,8 +1599,35 @@ static inline unsigned int skb_end_offset(const struct sk_buff *skb) { return skb->end - skb->head; } + +static inline void skb_set_end_offset(struct sk_buff *skb, unsigned int offset) +{ + skb->end = skb->head + offset; +} #endif +struct ubuf_info *msg_zerocopy_realloc(struct sock *sk, size_t size, + struct ubuf_info *uarg); + +void msg_zerocopy_put_abort(struct ubuf_info *uarg, bool have_uref); + +void msg_zerocopy_callback(struct sk_buff *skb, struct ubuf_info *uarg, + bool success); + +int __zerocopy_sg_from_iter(struct msghdr *msg, struct sock *sk, + struct sk_buff *skb, struct iov_iter *from, + size_t length); + +static inline int skb_zerocopy_iter_dgram(struct sk_buff *skb, + struct msghdr *msg, int len) +{ + return __zerocopy_sg_from_iter(msg, skb->sk, skb, &msg->msg_iter, len); +} + +int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb, + struct msghdr *msg, int len, + struct ubuf_info *uarg); + /* Internal */ #define skb_shinfo(SKB) ((struct skb_shared_info *)(skb_end_pointer(SKB))) @@ -1507,6 +1648,11 @@ static inline bool skb_zcopy_pure(const struct sk_buff *skb) return skb_shinfo(skb)->flags & SKBFL_PURE_ZEROCOPY; } +static inline bool skb_zcopy_managed(const struct sk_buff *skb) +{ + return skb_shinfo(skb)->flags & SKBFL_MANAGED_FRAG_REFS; +} + static inline bool skb_pure_zcopy_same(const struct sk_buff *skb1, const struct sk_buff *skb2) { @@ -1581,6 +1727,14 @@ static inline void skb_zcopy_clear(struct sk_buff *skb, bool zerocopy_success) } } +void __skb_zcopy_downgrade_managed(struct sk_buff *skb); + +static inline void skb_zcopy_downgrade_managed(struct sk_buff *skb) +{ + if (unlikely(skb_zcopy_managed(skb))) + __skb_zcopy_downgrade_managed(skb); +} + static inline void skb_mark_not_on_list(struct sk_buff *skb) { skb->next = NULL; @@ -1724,19 +1878,19 @@ static inline int skb_unclone(struct sk_buff *skb, gfp_t pri) return 0; } -/* This variant of skb_unclone() makes sure skb->truesize is not changed */ +/* This variant of skb_unclone() makes sure skb->truesize + * and skb_end_offset() are not changed, whenever a new skb->head is needed. + * + * Indeed there is no guarantee that ksize(kmalloc(X)) == ksize(kmalloc(X)) + * when various debugging features are in place. + */ +int __skb_unclone_keeptruesize(struct sk_buff *skb, gfp_t pri); static inline int skb_unclone_keeptruesize(struct sk_buff *skb, gfp_t pri) { might_sleep_if(gfpflags_allow_blocking(pri)); - if (skb_cloned(skb)) { - unsigned int save = skb->truesize; - int res; - - res = pskb_expand_head(skb, 0, 0, pri); - skb->truesize = save; - return res; - } + if (skb_cloned(skb)) + return __skb_unclone_keeptruesize(skb, pri); return 0; } @@ -1770,8 +1924,10 @@ static inline int skb_header_unclone(struct sk_buff *skb, gfp_t pri) } /** - * __skb_header_release - release reference to header - * @skb: buffer to operate on + * __skb_header_release() - allow clones to use the headroom + * @skb: buffer to operate on + * + * See "DOC: dataref and headerless skbs". */ static inline void __skb_header_release(struct sk_buff *skb) { @@ -2227,6 +2383,34 @@ static inline unsigned int skb_pagelen(const struct sk_buff *skb) return skb_headlen(skb) + __skb_pagelen(skb); } +static inline void __skb_fill_page_desc_noacc(struct skb_shared_info *shinfo, + int i, struct page *page, + int off, int size) +{ + skb_frag_t *frag = &shinfo->frags[i]; + + /* + * Propagate page pfmemalloc to the skb if we can. The problem is + * that not all callers have unique ownership of the page but rely + * on page_is_pfmemalloc doing the right thing(tm). + */ + frag->bv_page = page; + frag->bv_offset = off; + skb_frag_size_set(frag, size); +} + +/** + * skb_len_add - adds a number to len fields of skb + * @skb: buffer to add len to + * @delta: number of bytes to add + */ +static inline void skb_len_add(struct sk_buff *skb, int delta) +{ + skb->len += delta; + skb->data_len += delta; + skb->truesize += delta; +} + /** * __skb_fill_page_desc - initialise a paged fragment in an skb * @skb: buffer containing fragment to be initialised @@ -2243,17 +2427,7 @@ static inline unsigned int skb_pagelen(const struct sk_buff *skb) static inline void __skb_fill_page_desc(struct sk_buff *skb, int i, struct page *page, int off, int size) { - skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; - - /* - * Propagate page pfmemalloc to the skb if we can. The problem is - * that not all callers have unique ownership of the page but rely - * on page_is_pfmemalloc doing the right thing(tm). - */ - frag->bv_page = page; - frag->bv_offset = off; - skb_frag_size_set(frag, size); - + __skb_fill_page_desc_noacc(skb_shinfo(skb), i, page, off, size); page = compound_head(page); if (page_is_pfmemalloc(page)) skb->pfmemalloc = true; @@ -2280,6 +2454,27 @@ static inline void skb_fill_page_desc(struct sk_buff *skb, int i, skb_shinfo(skb)->nr_frags = i + 1; } +/** + * skb_fill_page_desc_noacc - initialise a paged fragment in an skb + * @skb: buffer containing fragment to be initialised + * @i: paged fragment index to initialise + * @page: the page to use for this fragment + * @off: the offset to the data with @page + * @size: the length of the data + * + * Variant of skb_fill_page_desc() which does not deal with + * pfmemalloc, if page is not owned by us. + */ +static inline void skb_fill_page_desc_noacc(struct sk_buff *skb, int i, + struct page *page, int off, + int size) +{ + struct skb_shared_info *shinfo = skb_shinfo(skb); + + __skb_fill_page_desc_noacc(shinfo, i, page, off, size); + shinfo->nr_frags = i + 1; +} + void skb_add_rx_frag(struct sk_buff *skb, int i, struct page *page, int off, int size, unsigned int truesize); @@ -2323,6 +2518,14 @@ static inline void skb_set_tail_pointer(struct sk_buff *skb, const int offset) #endif /* NET_SKBUFF_DATA_USES_OFFSET */ +static inline void skb_assert_len(struct sk_buff *skb) +{ +#ifdef CONFIG_DEBUG_NET + if (WARN_ONCE(!skb->len, "%s\n", __func__)) + DO_ONCE_LITE(skb_dump, KERN_ERR, skb, false); +#endif /* CONFIG_DEBUG_NET */ +} + /* * Add data to an sk_buff */ @@ -2395,7 +2598,14 @@ void *skb_pull(struct sk_buff *skb, unsigned int len); static inline void *__skb_pull(struct sk_buff *skb, unsigned int len) { skb->len -= len; - BUG_ON(skb->len < skb->data_len); + if (unlikely(skb->len < skb->data_len)) { +#if defined(CONFIG_DEBUG_NET) + skb->len += len; + pr_err("__skb_pull(len=%u)\n", len); + skb_dump(KERN_ERR, skb, false); +#endif + BUG(); + } return skb->data += len; } @@ -2408,20 +2618,6 @@ void *skb_pull_data(struct sk_buff *skb, size_t len); void *__pskb_pull_tail(struct sk_buff *skb, int delta); -static inline void *__pskb_pull(struct sk_buff *skb, unsigned int len) -{ - if (len > skb_headlen(skb) && - !__pskb_pull_tail(skb, len - skb_headlen(skb))) - return NULL; - skb->len -= len; - return skb->data += len; -} - -static inline void *pskb_pull(struct sk_buff *skb, unsigned int len) -{ - return unlikely(len > skb->len) ? NULL : __pskb_pull(skb, len); -} - static inline bool pskb_may_pull(struct sk_buff *skb, unsigned int len) { if (likely(len <= skb_headlen(skb))) @@ -2431,6 +2627,15 @@ static inline bool pskb_may_pull(struct sk_buff *skb, unsigned int len) return __pskb_pull_tail(skb, len - skb_headlen(skb)) != NULL; } +static inline void *pskb_pull(struct sk_buff *skb, unsigned int len) +{ + if (!pskb_may_pull(skb, len)) + return NULL; + + skb->len -= len; + return skb->data += len; +} + void skb_condense(struct sk_buff *skb); /** @@ -2600,6 +2805,7 @@ static inline bool skb_transport_header_was_set(const struct sk_buff *skb) static inline unsigned char *skb_transport_header(const struct sk_buff *skb) { + DEBUG_NET_WARN_ON_ONCE(!skb_transport_header_was_set(skb)); return skb->head + skb->transport_header; } @@ -2631,8 +2837,14 @@ static inline void skb_set_network_header(struct sk_buff *skb, const int offset) skb->network_header += offset; } +static inline int skb_mac_header_was_set(const struct sk_buff *skb) +{ + return skb->mac_header != (typeof(skb->mac_header))~0U; +} + static inline unsigned char *skb_mac_header(const struct sk_buff *skb) { + DEBUG_NET_WARN_ON_ONCE(!skb_mac_header_was_set(skb)); return skb->head + skb->mac_header; } @@ -2643,14 +2855,10 @@ static inline int skb_mac_offset(const struct sk_buff *skb) static inline u32 skb_mac_header_len(const struct sk_buff *skb) { + DEBUG_NET_WARN_ON_ONCE(!skb_mac_header_was_set(skb)); return skb->network_header - skb->mac_header; } -static inline int skb_mac_header_was_set(const struct sk_buff *skb) -{ - return skb->mac_header != (typeof(skb->mac_header))~0U; -} - static inline void skb_unset_mac_header(struct sk_buff *skb) { skb->mac_header = (typeof(skb->mac_header))~0U; @@ -2873,8 +3081,7 @@ static inline int skb_orphan_frags(struct sk_buff *skb, gfp_t gfp_mask) { if (likely(!skb_zcopy(skb))) return 0; - if (!skb_zcopy_is_nouarg(skb) && - skb_uarg(skb)->callback == msg_zerocopy_callback) + if (skb_shinfo(skb)->flags & SKBFL_DONT_ORPHAN) return 0; return skb_copy_ubufs(skb, gfp_mask); } @@ -3187,7 +3394,10 @@ static inline void __skb_frag_unref(skb_frag_t *frag, bool recycle) */ static inline void skb_frag_unref(struct sk_buff *skb, int f) { - __skb_frag_unref(&skb_shinfo(skb)->frags[f], skb->pp_recycle); + struct skb_shared_info *shinfo = skb_shinfo(skb); + + if (!skb_zcopy_managed(skb)) + __skb_frag_unref(&shinfo->frags[f], skb->pp_recycle); } /** @@ -3684,8 +3894,7 @@ struct sk_buff *__skb_try_recv_datagram(struct sock *sk, struct sk_buff *__skb_recv_datagram(struct sock *sk, struct sk_buff_head *sk_queue, unsigned int flags, int *off, int *err); -struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned flags, int noblock, - int *err); +struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned int flags, int *err); __poll_t datagram_poll(struct file *file, struct socket *sock, struct poll_table_struct *wait); int skb_copy_datagram_iter(const struct sk_buff *from, int offset, @@ -3734,7 +3943,7 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features); struct sk_buff *skb_segment_list(struct sk_buff *skb, netdev_features_t features, unsigned int offset); struct sk_buff *skb_vlan_untag(struct sk_buff *skb); -int skb_ensure_writable(struct sk_buff *skb, int write_len); +int skb_ensure_writable(struct sk_buff *skb, unsigned int write_len); int __skb_vlan_pop(struct sk_buff *skb, u16 *vlan_tci); int skb_vlan_pop(struct sk_buff *skb); int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci); @@ -3891,6 +4100,7 @@ static inline void skb_get_new_timestampns(const struct sk_buff *skb, static inline void __net_timestamp(struct sk_buff *skb) { skb->tstamp = ktime_get_real(); + skb->mono_delivery_time = 0; } static inline ktime_t net_timedelta(ktime_t t) @@ -3898,8 +4108,53 @@ static inline ktime_t net_timedelta(ktime_t t) return ktime_sub(ktime_get_real(), t); } -static inline ktime_t net_invalid_timestamp(void) +static inline void skb_set_delivery_time(struct sk_buff *skb, ktime_t kt, + bool mono) { + skb->tstamp = kt; + skb->mono_delivery_time = kt && mono; +} + +DECLARE_STATIC_KEY_FALSE(netstamp_needed_key); + +/* It is used in the ingress path to clear the delivery_time. + * If needed, set the skb->tstamp to the (rcv) timestamp. + */ +static inline void skb_clear_delivery_time(struct sk_buff *skb) +{ + if (skb->mono_delivery_time) { + skb->mono_delivery_time = 0; + if (static_branch_unlikely(&netstamp_needed_key)) + skb->tstamp = ktime_get_real(); + else + skb->tstamp = 0; + } +} + +static inline void skb_clear_tstamp(struct sk_buff *skb) +{ + if (skb->mono_delivery_time) + return; + + skb->tstamp = 0; +} + +static inline ktime_t skb_tstamp(const struct sk_buff *skb) +{ + if (skb->mono_delivery_time) + return 0; + + return skb->tstamp; +} + +static inline ktime_t skb_tstamp_cond(const struct sk_buff *skb, bool cond) +{ + if (!skb->mono_delivery_time && skb->tstamp) + return skb->tstamp; + + if (static_branch_unlikely(&netstamp_needed_key) || cond) + return ktime_get_real(); + return 0; } @@ -4697,9 +4952,7 @@ static inline void skb_forward_csum(struct sk_buff *skb) */ static inline void skb_checksum_none_assert(const struct sk_buff *skb) { -#ifdef DEBUG - BUG_ON(skb->ip_summed != CHECKSUM_NONE); -#endif + DEBUG_NET_WARN_ON_ONCE(skb->ip_summed != CHECKSUM_NONE); } bool skb_partial_csum_set(struct sk_buff *skb, u16 start, u16 off); @@ -4759,7 +5012,7 @@ static inline void skb_set_redirected(struct sk_buff *skb, bool from_ingress) #ifdef CONFIG_NET_REDIRECT skb->from_ingress = from_ingress; if (skb->from_ingress) - skb->tstamp = 0; + skb_clear_tstamp(skb); #endif } diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 18a717fe62eb..70d6cb94e580 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -29,7 +29,7 @@ struct sk_msg_sg { u32 end; u32 size; u32 copybreak; - unsigned long copy; + DECLARE_BITMAP(copy, MAX_MSG_FRAGS + 2); /* The extra two elements: * 1) used for chaining the front and sections when the list becomes * partitioned (e.g. end < start). The crypto APIs require the @@ -38,7 +38,6 @@ struct sk_msg_sg { */ struct scatterlist data[MAX_MSG_FRAGS + 2]; }; -static_assert(BITS_PER_LONG >= NR_MSG_FRAG_IDS); /* UAPI in filter.c depends on struct sk_msg_sg being first element. */ struct sk_msg { @@ -96,6 +95,7 @@ struct sk_psock { spinlock_t link_lock; refcount_t refcnt; void (*saved_unhash)(struct sock *sk); + void (*saved_destroy)(struct sock *sk); void (*saved_close)(struct sock *sk, long timeout); void (*saved_write_space)(struct sock *sk); void (*saved_data_ready)(struct sock *sk); @@ -171,11 +171,6 @@ static inline u32 sk_msg_iter_dist(u32 start, u32 end) #define sk_msg_iter_next(msg, which) \ sk_msg_iter_var_next(msg->sg.which) -static inline void sk_msg_clear_meta(struct sk_msg *msg) -{ - memset(&msg->sg, 0, offsetofend(struct sk_msg_sg, copy)); -} - static inline void sk_msg_init(struct sk_msg *msg) { BUILD_BUG_ON(ARRAY_SIZE(msg->sg.data) - 1 != NR_MSG_FRAG_IDS); @@ -234,7 +229,7 @@ static inline void sk_msg_compute_data_pointers(struct sk_msg *msg) { struct scatterlist *sge = sk_msg_elem(msg, msg->sg.start); - if (test_bit(msg->sg.start, &msg->sg.copy)) { + if (test_bit(msg->sg.start, msg->sg.copy)) { msg->data = NULL; msg->data_end = NULL; } else { @@ -253,7 +248,7 @@ static inline void sk_msg_page_add(struct sk_msg *msg, struct page *page, sg_set_page(sge, page, len, offset); sg_unmark_end(sge); - __set_bit(msg->sg.end, &msg->sg.copy); + __set_bit(msg->sg.end, msg->sg.copy); msg->sg.size += len; sk_msg_iter_next(msg, end); } @@ -262,9 +257,9 @@ static inline void sk_msg_sg_copy(struct sk_msg *msg, u32 i, bool copy_state) { do { if (copy_state) - __set_bit(i, &msg->sg.copy); + __set_bit(i, msg->sg.copy); else - __clear_bit(i, &msg->sg.copy); + __clear_bit(i, msg->sg.copy); sk_msg_iter_var_next(i); if (i == msg->sg.end) break; @@ -283,7 +278,8 @@ static inline void sk_msg_sg_copy_clear(struct sk_msg *msg, u32 start) static inline struct sk_psock *sk_psock(const struct sock *sk) { - return rcu_dereference_sk_user_data(sk); + return __rcu_dereference_sk_user_data_with_flags(sk, + SK_USER_DATA_PSOCK); } static inline void sk_psock_set_state(struct sk_psock *psock, @@ -310,21 +306,16 @@ static inline void sock_drop(struct sock *sk, struct sk_buff *skb) kfree_skb(skb); } -static inline void drop_sk_msg(struct sk_psock *psock, struct sk_msg *msg) -{ - if (msg->skb) - sock_drop(psock->sk, msg->skb); - kfree(msg); -} - static inline void sk_psock_queue_msg(struct sk_psock *psock, struct sk_msg *msg) { spin_lock_bh(&psock->ingress_lock); if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) list_add_tail(&msg->list, &psock->ingress_msg); - else - drop_sk_msg(psock, msg); + else { + sk_msg_free(psock->sk, msg); + kfree(msg); + } spin_unlock_bh(&psock->ingress_lock); } @@ -385,7 +376,7 @@ static inline void sk_psock_report_error(struct sk_psock *psock, int err) } struct sk_psock *sk_psock_init(struct sock *sk, int node); -void sk_psock_stop(struct sk_psock *psock, bool wait); +void sk_psock_stop(struct sk_psock *psock); #if IS_ENABLED(CONFIG_BPF_STREAM_PARSER) int sk_psock_init_strp(struct sock *sk, struct sk_psock *psock); diff --git a/include/linux/slab.h b/include/linux/slab.h index 367366f1d1ff..45efc6c553b8 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -29,6 +29,8 @@ #define SLAB_RED_ZONE ((slab_flags_t __force)0x00000400U) /* DEBUG: Poison objects */ #define SLAB_POISON ((slab_flags_t __force)0x00000800U) +/* Indicate a kmalloc slab */ +#define SLAB_KMALLOC ((slab_flags_t __force)0x00001000U) /* Align objs on cache lines */ #define SLAB_HWCACHE_ALIGN ((slab_flags_t __force)0x00002000U) /* Use GFP_DMA memory */ @@ -106,20 +108,30 @@ # define SLAB_ACCOUNT 0 #endif -#ifdef CONFIG_KASAN +#ifdef CONFIG_KASAN_GENERIC #define SLAB_KASAN ((slab_flags_t __force)0x08000000U) #else #define SLAB_KASAN 0 #endif +/* + * Ignore user specified debugging flags. + * Intended for caches created for self-tests so they have only flags + * specified in the code and other flags are ignored. + */ +#define SLAB_NO_USER_FLAGS ((slab_flags_t __force)0x10000000U) + +#ifdef CONFIG_KFENCE +#define SLAB_SKIP_KFENCE ((slab_flags_t __force)0x20000000U) +#else +#define SLAB_SKIP_KFENCE 0 +#endif + /* The following flags affect the page allocator grouping pages by mobility */ /* Objects are reclaimable */ #define SLAB_RECLAIM_ACCOUNT ((slab_flags_t __force)0x00020000U) #define SLAB_TEMPORARY SLAB_RECLAIM_ACCOUNT /* Objects are short-lived */ -/* Slab deactivation flag */ -#define SLAB_DEACTIVATED ((slab_flags_t __force)0x10000000U) - /* * ZERO_SIZE_PTR will be returned for zero sized kmalloc requests. * @@ -135,6 +147,7 @@ #include <linux/kasan.h> +struct list_lru; struct mem_cgroup; /* * struct kmem_cache related prototypes @@ -179,11 +192,25 @@ int kmem_cache_shrink(struct kmem_cache *s); /* * Common kmalloc functions provided by all allocators */ -void * __must_check krealloc(const void *objp, size_t new_size, gfp_t flags) __alloc_size(2); +void * __must_check krealloc(const void *objp, size_t new_size, gfp_t flags) __realloc_size(2); void kfree(const void *objp); void kfree_sensitive(const void *objp); size_t __ksize(const void *objp); + +/** + * ksize - Report actual allocation size of associated object + * + * @objp: Pointer returned from a prior kmalloc()-family allocation. + * + * This should not be used for writing beyond the originally requested + * allocation size. Either use krealloc() or round up the allocation size + * with kmalloc_size_roundup() prior to allocation. If this is used to + * access beyond the originally requested allocation size, UBSAN_BOUNDS + * and/or FORTIFY_SOURCE may trip, since they only know about the + * originally allocated size via the __alloc_size attribute. + */ size_t ksize(const void *objp); + #ifdef CONFIG_PRINTK bool kmem_valid_obj(void *object); void kmem_dump_obj(void *object); @@ -192,7 +219,7 @@ void kmem_dump_obj(void *object); /* * Some archs want to perform DMA into kmalloc caches and need a guaranteed * alignment larger than the alignment of a 64-bit integer. - * Setting ARCH_KMALLOC_MINALIGN in arch headers allows that. + * Setting ARCH_DMA_MINALIGN in arch headers allows that. */ #if defined(ARCH_DMA_MINALIGN) && ARCH_DMA_MINALIGN > 8 #define ARCH_KMALLOC_MINALIGN ARCH_DMA_MINALIGN @@ -212,9 +239,21 @@ void kmem_dump_obj(void *object); #endif /* - * kmalloc and friends return ARCH_KMALLOC_MINALIGN aligned - * pointers. kmem_cache_alloc and friends return ARCH_SLAB_MINALIGN - * aligned pointers. + * Arches can define this function if they want to decide the minimum slab + * alignment at runtime. The value returned by the function must be a power + * of two and >= ARCH_SLAB_MINALIGN. + */ +#ifndef arch_slab_minalign +static inline unsigned int arch_slab_minalign(void) +{ + return ARCH_SLAB_MINALIGN; +} +#endif + +/* + * kmem_cache_alloc and friends return pointers aligned to ARCH_SLAB_MINALIGN. + * kmalloc and friends return pointers aligned to both ARCH_KMALLOC_MINALIGN + * and ARCH_SLAB_MINALIGN, but here we only assume the former alignment. */ #define __assume_kmalloc_alignment __assume_aligned(ARCH_KMALLOC_MINALIGN) #define __assume_slab_alignment __assume_aligned(ARCH_SLAB_MINALIGN) @@ -226,27 +265,17 @@ void kmem_dump_obj(void *object); #ifdef CONFIG_SLAB /* - * The largest kmalloc size supported by the SLAB allocators is - * 32 megabyte (2^25) or the maximum allocatable page order if that is - * less than 32 MB. - * - * WARNING: Its not easy to increase this value since the allocators have - * to do various tricks to work around compiler limitations in order to - * ensure proper constant folding. + * SLAB and SLUB directly allocates requests fitting in to an order-1 page + * (PAGE_SIZE*2). Larger requests are passed to the page allocator. */ -#define KMALLOC_SHIFT_HIGH ((MAX_ORDER + PAGE_SHIFT - 1) <= 25 ? \ - (MAX_ORDER + PAGE_SHIFT - 1) : 25) -#define KMALLOC_SHIFT_MAX KMALLOC_SHIFT_HIGH +#define KMALLOC_SHIFT_HIGH (PAGE_SHIFT + 1) +#define KMALLOC_SHIFT_MAX (MAX_ORDER + PAGE_SHIFT - 1) #ifndef KMALLOC_SHIFT_LOW #define KMALLOC_SHIFT_LOW 5 #endif #endif #ifdef CONFIG_SLUB -/* - * SLUB directly allocates requests fitting in to an order-1 page - * (PAGE_SIZE*2). Larger requests are passed to the page allocator. - */ #define KMALLOC_SHIFT_HIGH (PAGE_SHIFT + 1) #define KMALLOC_SHIFT_MAX (MAX_ORDER + PAGE_SHIFT - 1) #ifndef KMALLOC_SHIFT_LOW @@ -398,13 +427,8 @@ static __always_inline unsigned int __kmalloc_index(size_t size, if (size <= 512 * 1024) return 19; if (size <= 1024 * 1024) return 20; if (size <= 2 * 1024 * 1024) return 21; - if (size <= 4 * 1024 * 1024) return 22; - if (size <= 8 * 1024 * 1024) return 23; - if (size <= 16 * 1024 * 1024) return 24; - if (size <= 32 * 1024 * 1024) return 25; - if ((IS_ENABLED(CONFIG_CC_IS_GCC) || CONFIG_CLANG_VERSION >= 110000) - && !IS_ENABLED(CONFIG_PROFILE_ALL_BRANCHES) && size_is_constant) + if (!IS_ENABLED(CONFIG_PROFILE_ALL_BRANCHES) && size_is_constant) BUILD_BUG_ON_MSG(1, "unexpected size in kmalloc_index()"); else BUG(); @@ -412,11 +436,14 @@ static __always_inline unsigned int __kmalloc_index(size_t size, /* Will never be reached. Needed because the compiler may complain */ return -1; } +static_assert(PAGE_SHIFT <= 20); #define kmalloc_index(s) __kmalloc_index(s, true) #endif /* !CONFIG_SLOB */ void *__kmalloc(size_t size, gfp_t flags) __assume_kmalloc_alignment __alloc_size(1); void *kmem_cache_alloc(struct kmem_cache *s, gfp_t flags) __assume_slab_alignment __malloc; +void *kmem_cache_alloc_lru(struct kmem_cache *s, struct list_lru *lru, + gfp_t gfpflags) __assume_slab_alignment __malloc; void kmem_cache_free(struct kmem_cache *s, void *objp); /* @@ -438,78 +465,22 @@ static __always_inline void kfree_bulk(size_t size, void **p) kmem_cache_free_bulk(NULL, size, p); } -#ifdef CONFIG_NUMA void *__kmalloc_node(size_t size, gfp_t flags, int node) __assume_kmalloc_alignment __alloc_size(1); void *kmem_cache_alloc_node(struct kmem_cache *s, gfp_t flags, int node) __assume_slab_alignment __malloc; -#else -static __always_inline __alloc_size(1) void *__kmalloc_node(size_t size, gfp_t flags, int node) -{ - return __kmalloc(size, flags); -} - -static __always_inline void *kmem_cache_alloc_node(struct kmem_cache *s, gfp_t flags, int node) -{ - return kmem_cache_alloc(s, flags); -} -#endif -#ifdef CONFIG_TRACING -extern void *kmem_cache_alloc_trace(struct kmem_cache *s, gfp_t flags, size_t size) - __assume_slab_alignment __alloc_size(3); +void *kmalloc_trace(struct kmem_cache *s, gfp_t flags, size_t size) + __assume_kmalloc_alignment __alloc_size(3); -#ifdef CONFIG_NUMA -extern void *kmem_cache_alloc_node_trace(struct kmem_cache *s, gfp_t gfpflags, - int node, size_t size) __assume_slab_alignment - __alloc_size(4); -#else -static __always_inline __alloc_size(4) void *kmem_cache_alloc_node_trace(struct kmem_cache *s, - gfp_t gfpflags, int node, size_t size) -{ - return kmem_cache_alloc_trace(s, gfpflags, size); -} -#endif /* CONFIG_NUMA */ - -#else /* CONFIG_TRACING */ -static __always_inline __alloc_size(3) void *kmem_cache_alloc_trace(struct kmem_cache *s, - gfp_t flags, size_t size) -{ - void *ret = kmem_cache_alloc(s, flags); - - ret = kasan_kmalloc(s, ret, size, flags); - return ret; -} - -static __always_inline void *kmem_cache_alloc_node_trace(struct kmem_cache *s, gfp_t gfpflags, - int node, size_t size) -{ - void *ret = kmem_cache_alloc_node(s, gfpflags, node); - - ret = kasan_kmalloc(s, ret, size, gfpflags); - return ret; -} -#endif /* CONFIG_TRACING */ +void *kmalloc_node_trace(struct kmem_cache *s, gfp_t gfpflags, + int node, size_t size) __assume_kmalloc_alignment + __alloc_size(4); +void *kmalloc_large(size_t size, gfp_t flags) __assume_page_alignment + __alloc_size(1); -extern void *kmalloc_order(size_t size, gfp_t flags, unsigned int order) __assume_page_alignment - __alloc_size(1); - -#ifdef CONFIG_TRACING -extern void *kmalloc_order_trace(size_t size, gfp_t flags, unsigned int order) - __assume_page_alignment __alloc_size(1); -#else -static __always_inline __alloc_size(1) void *kmalloc_order_trace(size_t size, gfp_t flags, - unsigned int order) -{ - return kmalloc_order(size, flags, order); -} -#endif - -static __always_inline __alloc_size(1) void *kmalloc_large(size_t size, gfp_t flags) -{ - unsigned int order = get_order(size); - return kmalloc_order_trace(size, flags, order); -} +void *kmalloc_large_node(size_t size, gfp_t flags, int node) __assume_page_alignment + __alloc_size(1); /** * kmalloc - allocate memory @@ -579,7 +550,7 @@ static __always_inline __alloc_size(1) void *kmalloc(size_t size, gfp_t flags) if (!index) return ZERO_SIZE_PTR; - return kmem_cache_alloc_trace( + return kmalloc_trace( kmalloc_caches[kmalloc_type(flags)][index], flags, size); #endif @@ -587,23 +558,35 @@ static __always_inline __alloc_size(1) void *kmalloc(size_t size, gfp_t flags) return __kmalloc(size, flags); } +#ifndef CONFIG_SLOB static __always_inline __alloc_size(1) void *kmalloc_node(size_t size, gfp_t flags, int node) { -#ifndef CONFIG_SLOB - if (__builtin_constant_p(size) && - size <= KMALLOC_MAX_CACHE_SIZE) { - unsigned int i = kmalloc_index(size); + if (__builtin_constant_p(size)) { + unsigned int index; + + if (size > KMALLOC_MAX_CACHE_SIZE) + return kmalloc_large_node(size, flags, node); - if (!i) + index = kmalloc_index(size); + + if (!index) return ZERO_SIZE_PTR; - return kmem_cache_alloc_node_trace( - kmalloc_caches[kmalloc_type(flags)][i], - flags, node, size); + return kmalloc_node_trace( + kmalloc_caches[kmalloc_type(flags)][index], + flags, node, size); } -#endif return __kmalloc_node(size, flags, node); } +#else +static __always_inline __alloc_size(1) void *kmalloc_node(size_t size, gfp_t flags, int node) +{ + if (__builtin_constant_p(size) && size > KMALLOC_MAX_CACHE_SIZE) + return kmalloc_large_node(size, flags, node); + + return __kmalloc_node(size, flags, node); +} +#endif /** * kmalloc_array - allocate memory for an array. @@ -629,10 +612,10 @@ static inline __alloc_size(1, 2) void *kmalloc_array(size_t n, size_t size, gfp_ * @new_size: new size of a single member of the array * @flags: the type of memory to allocate (see kmalloc) */ -static inline __alloc_size(2, 3) void * __must_check krealloc_array(void *p, - size_t new_n, - size_t new_size, - gfp_t flags) +static inline __realloc_size(2, 3) void * __must_check krealloc_array(void *p, + size_t new_n, + size_t new_size, + gfp_t flags) { size_t bytes; @@ -653,6 +636,12 @@ static inline __alloc_size(1, 2) void *kcalloc(size_t n, size_t size, gfp_t flag return kmalloc_array(n, size, flags | __GFP_ZERO); } +void *__kmalloc_node_track_caller(size_t size, gfp_t flags, int node, + unsigned long caller) __alloc_size(1); +#define kmalloc_node_track_caller(size, flags, node) \ + __kmalloc_node_track_caller(size, flags, node, \ + _RET_IP_) + /* * kmalloc_track_caller is a special version of kmalloc that records the * calling function of the routine calling it for slab leak tracking instead @@ -661,10 +650,9 @@ static inline __alloc_size(1, 2) void *kcalloc(size_t n, size_t size, gfp_t flag * allocator where we care about the real place the memory allocation * request comes from. */ -extern void *__kmalloc_track_caller(size_t size, gfp_t flags, unsigned long caller) - __alloc_size(1); #define kmalloc_track_caller(size, flags) \ - __kmalloc_track_caller(size, flags, _RET_IP_) + __kmalloc_node_track_caller(size, flags, \ + NUMA_NO_NODE, _RET_IP_) static inline __alloc_size(1, 2) void *kmalloc_array_node(size_t n, size_t size, gfp_t flags, int node) @@ -683,21 +671,6 @@ static inline __alloc_size(1, 2) void *kcalloc_node(size_t n, size_t size, gfp_t return kmalloc_array_node(n, size, flags | __GFP_ZERO, node); } - -#ifdef CONFIG_NUMA -extern void *__kmalloc_node_track_caller(size_t size, gfp_t flags, int node, - unsigned long caller) __alloc_size(1); -#define kmalloc_node_track_caller(size, flags, node) \ - __kmalloc_node_track_caller(size, flags, node, \ - _RET_IP_) - -#else /* CONFIG_NUMA */ - -#define kmalloc_node_track_caller(size, flags, node) \ - kmalloc_track_caller(size, flags) - -#endif /* CONFIG_NUMA */ - /* * Shortcuts */ @@ -757,11 +730,28 @@ static inline __alloc_size(1, 2) void *kvcalloc(size_t n, size_t size, gfp_t fla } extern void *kvrealloc(const void *p, size_t oldsize, size_t newsize, gfp_t flags) - __alloc_size(3); + __realloc_size(3); extern void kvfree(const void *addr); extern void kvfree_sensitive(const void *addr, size_t len); unsigned int kmem_cache_size(struct kmem_cache *s); + +/** + * kmalloc_size_roundup - Report allocation bucket size for the given size + * + * @size: Number of bytes to round up from. + * + * This returns the number of bytes that would be available in a kmalloc() + * allocation of @size bytes. For example, a 126 byte request would be + * rounded up to the next sized kmalloc bucket, 128 bytes. (This is strictly + * for the general-purpose kmalloc()-based allocations, and is not for the + * pre-sized kmem_cache_alloc()-based allocations.) + * + * Use this to kmalloc() the full bucket size ahead of time instead of using + * ksize() to query the size after an allocation. + */ +size_t kmalloc_size_roundup(size_t size); + void __init kmem_cache_init_late(void); #if defined(CONFIG_SMP) && defined(CONFIG_SLAB) diff --git a/include/linux/slab_def.h b/include/linux/slab_def.h index e24c9aff6fed..f0ffad6a3365 100644 --- a/include/linux/slab_def.h +++ b/include/linux/slab_def.h @@ -33,7 +33,6 @@ struct kmem_cache { size_t colour; /* cache colouring range */ unsigned int colour_off; /* colour offset */ - struct kmem_cache *freelist_cache; unsigned int freelist_size; /* constructor func */ diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index 33c5c0e3bd8d..f9c68a9dac04 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -105,7 +105,6 @@ struct kmem_cache { struct kmem_cache_order_objects oo; /* Allocation and freeing of slabs */ - struct kmem_cache_order_objects max; struct kmem_cache_order_objects min; gfp_t allocflags; /* gfp flags to use on each alloc */ int refcount; /* Refcount for slab cache destroy */ diff --git a/include/linux/soc/apple/rtkit.h b/include/linux/soc/apple/rtkit.h new file mode 100644 index 000000000000..c9cabb679cd1 --- /dev/null +++ b/include/linux/soc/apple/rtkit.h @@ -0,0 +1,167 @@ +/* SPDX-License-Identifier: GPL-2.0-only OR MIT */ +/* + * Apple RTKit IPC Library + * Copyright (C) The Asahi Linux Contributors + * + * Apple's SoCs come with various co-processors running their RTKit operating + * system. This protocol library is used by client drivers to use the + * features provided by them. + */ +#ifndef _LINUX_APPLE_RTKIT_H_ +#define _LINUX_APPLE_RTKIT_H_ + +#include <linux/device.h> +#include <linux/types.h> +#include <linux/mailbox_client.h> + +/* + * Struct to represent implementation-specific RTKit operations. + * + * @buffer: Shared memory buffer allocated inside normal RAM. + * @iomem: Shared memory buffer controlled by the co-processors. + * @size: Size of the shared memory buffer. + * @iova: Device VA of shared memory buffer. + * @is_mapped: Shared memory buffer is managed by the co-processor. + */ + +struct apple_rtkit_shmem { + void *buffer; + void __iomem *iomem; + size_t size; + dma_addr_t iova; + bool is_mapped; +}; + +/* + * Struct to represent implementation-specific RTKit operations. + * + * @crashed: Called when the co-processor has crashed. Runs in process + * context. + * @recv_message: Function called when a message from RTKit is received + * on a non-system endpoint. Called from a worker thread. + * @recv_message_early: + * Like recv_message, but called from atomic context. It + * should return true if it handled the message. If it + * returns false, the message will be passed on to the + * worker thread. + * @shmem_setup: Setup shared memory buffer. If bfr.is_iomem is true the + * buffer is managed by the co-processor and needs to be mapped. + * Otherwise the buffer is managed by Linux and needs to be + * allocated. If not specified dma_alloc_coherent is used. + * Called in process context. + * @shmem_destroy: Undo the shared memory buffer setup in shmem_setup. If not + * specified dma_free_coherent is used. Called in process + * context. + */ +struct apple_rtkit_ops { + void (*crashed)(void *cookie); + void (*recv_message)(void *cookie, u8 endpoint, u64 message); + bool (*recv_message_early)(void *cookie, u8 endpoint, u64 message); + int (*shmem_setup)(void *cookie, struct apple_rtkit_shmem *bfr); + void (*shmem_destroy)(void *cookie, struct apple_rtkit_shmem *bfr); +}; + +struct apple_rtkit; + +/* + * Initializes the internal state required to handle RTKit. This + * should usually be called within _probe. + * + * @dev: Pointer to the device node this coprocessor is assocated with + * @cookie: opaque cookie passed to all functions defined in rtkit_ops + * @mbox_name: mailbox name used to communicate with the co-processor + * @mbox_idx: mailbox index to be used if mbox_name is NULL + * @ops: pointer to rtkit_ops to be used for this co-processor + */ +struct apple_rtkit *devm_apple_rtkit_init(struct device *dev, void *cookie, + const char *mbox_name, int mbox_idx, + const struct apple_rtkit_ops *ops); + +/* + * Reinitialize internal structures. Must only be called with the co-processor + * is held in reset. + */ +int apple_rtkit_reinit(struct apple_rtkit *rtk); + +/* + * Handle RTKit's boot process. Should be called after the CPU of the + * co-processor has been started. + */ +int apple_rtkit_boot(struct apple_rtkit *rtk); + +/* + * Quiesce the co-processor. + */ +int apple_rtkit_quiesce(struct apple_rtkit *rtk); + +/* + * Wake the co-processor up from hibernation mode. + */ +int apple_rtkit_wake(struct apple_rtkit *rtk); + +/* + * Shutdown the co-processor + */ +int apple_rtkit_shutdown(struct apple_rtkit *rtk); + +/* + * Checks if RTKit is running and ready to handle messages. + */ +bool apple_rtkit_is_running(struct apple_rtkit *rtk); + +/* + * Checks if RTKit has crashed. + */ +bool apple_rtkit_is_crashed(struct apple_rtkit *rtk); + +/* + * Starts an endpoint. Must be called after boot but before any messages can be + * sent or received from that endpoint. + */ +int apple_rtkit_start_ep(struct apple_rtkit *rtk, u8 endpoint); + +/* + * Send a message to the given endpoint. + * + * @rtk: RTKit reference + * @ep: target endpoint + * @message: message to be sent + * @completeion: will be completed once the message has been submitted + * to the hardware FIFO. Can be NULL. + * @atomic: if set to true this function can be called from atomic + * context. + */ +int apple_rtkit_send_message(struct apple_rtkit *rtk, u8 ep, u64 message, + struct completion *completion, bool atomic); + +/* + * Send a message to the given endpoint and wait until it has been submitted + * to the hardware FIFO. + * Will return zero on success and a negative error code on failure + * (e.g. -ETIME when the message couldn't be written within the given + * timeout) + * + * @rtk: RTKit reference + * @ep: target endpoint + * @message: message to be sent + * @timeout: timeout in milliseconds to allow the message transmission + * to be completed + * @atomic: if set to true this function can be called from atomic + * context. + */ +int apple_rtkit_send_message_wait(struct apple_rtkit *rtk, u8 ep, u64 message, + unsigned long timeout, bool atomic); + +/* + * Process incoming messages in atomic context. + * This only guarantees that messages arrive as far as the recv_message_early + * callback; drivers expecting to handle incoming messages synchronously + * by calling this function must do it that way. + * Will return 1 if some data was processed, 0 if none was, or a + * negative error code on failure. + * + * @rtk: RTKit reference + */ +int apple_rtkit_poll(struct apple_rtkit *rtk); + +#endif /* _LINUX_APPLE_RTKIT_H_ */ diff --git a/include/linux/soc/apple/sart.h b/include/linux/soc/apple/sart.h new file mode 100644 index 000000000000..2249bf6cde09 --- /dev/null +++ b/include/linux/soc/apple/sart.h @@ -0,0 +1,53 @@ +/* SPDX-License-Identifier: GPL-2.0-only OR MIT */ +/* + * Apple SART device driver + * Copyright (C) The Asahi Linux Contributors + * + * Apple SART is a simple address filter for DMA transactions. + * Regions of physical memory must be added to the SART's allow + * list before any DMA can target these. Unlike a proper + * IOMMU no remapping can be done. + */ + +#ifndef _LINUX_SOC_APPLE_SART_H_ +#define _LINUX_SOC_APPLE_SART_H_ + +#include <linux/device.h> +#include <linux/err.h> +#include <linux/types.h> + +struct apple_sart; + +/* + * Get a reference to the SART attached to dev. + * + * Looks for the phandle reference in apple,sart and returns a pointer + * to the corresponding apple_sart struct to be used with + * apple_sart_add_allowed_region and apple_sart_remove_allowed_region. + */ +struct apple_sart *devm_apple_sart_get(struct device *dev); + +/* + * Adds the region [paddr, paddr+size] to the DMA allow list. + * + * @sart: SART reference + * @paddr: Start address of the region to be used for DMA + * @size: Size of the region to be used for DMA. + */ +int apple_sart_add_allowed_region(struct apple_sart *sart, phys_addr_t paddr, + size_t size); + +/* + * Removes the region [paddr, paddr+size] from the DMA allow list. + * + * Note that exact same paddr and size used for apple_sart_add_allowed_region + * have to be passed. + * + * @sart: SART reference + * @paddr: Start address of the region no longer used for DMA + * @size: Size of the region no longer used for DMA. + */ +int apple_sart_remove_allowed_region(struct apple_sart *sart, phys_addr_t paddr, + size_t size); + +#endif /* _LINUX_SOC_APPLE_SART_H_ */ diff --git a/include/linux/soc/ixp4xx/cpu.h b/include/linux/soc/ixp4xx/cpu.h index 88bd8de0e803..f526ac33afea 100644 --- a/include/linux/soc/ixp4xx/cpu.h +++ b/include/linux/soc/ixp4xx/cpu.h @@ -9,6 +9,7 @@ #define __SOC_IXP4XX_CPU_H__ #include <linux/io.h> +#include <linux/regmap.h> #ifdef CONFIG_ARM #include <asm/cputype.h> #endif @@ -23,6 +24,9 @@ #define IXP46X_PROCESSOR_ID_VALUE 0x69054200 /* including IXP455 */ #define IXP46X_PROCESSOR_ID_MASK 0xfffffff0 +/* Feature register in the expansion bus controller */ +#define IXP4XX_EXP_CNFG2 0x2c + /* "fuse" bits of IXP_EXP_CFG2 */ /* All IXP4xx CPUs */ #define IXP4XX_FEATURE_RCOMP (1 << 0) @@ -86,21 +90,31 @@ IXP43X_PROCESSOR_ID_VALUE) #define cpu_is_ixp46x() ((read_cpuid_id() & IXP46X_PROCESSOR_ID_MASK) == \ IXP46X_PROCESSOR_ID_VALUE) +static inline u32 cpu_ixp4xx_features(struct regmap *rmap) +{ + u32 val; -u32 ixp4xx_read_feature_bits(void); -void ixp4xx_write_feature_bits(u32 value); + regmap_read(rmap, IXP4XX_EXP_CNFG2, &val); + /* For some reason this register is inverted */ + val = ~val; + if (cpu_is_ixp42x_rev_a0()) + return IXP42X_FEATURE_MASK & ~(IXP4XX_FEATURE_RCOMP | + IXP4XX_FEATURE_AES); + if (cpu_is_ixp42x()) + return val & IXP42X_FEATURE_MASK; + if (cpu_is_ixp43x()) + return val & IXP43X_FEATURE_MASK; + return val & IXP46X_FEATURE_MASK; +} #else #define cpu_is_ixp42x_rev_a0() 0 #define cpu_is_ixp42x() 0 #define cpu_is_ixp43x() 0 #define cpu_is_ixp46x() 0 -static inline u32 ixp4xx_read_feature_bits(void) +static inline u32 cpu_ixp4xx_features(struct regmap *rmap) { return 0; } -static inline void ixp4xx_write_feature_bits(u32 value) -{ -} #endif #endif /* _ASM_ARCH_CPU_H */ diff --git a/include/linux/soc/ixp4xx/npe.h b/include/linux/soc/ixp4xx/npe.h index 2a91f465d456..9efeac777da1 100644 --- a/include/linux/soc/ixp4xx/npe.h +++ b/include/linux/soc/ixp4xx/npe.h @@ -3,6 +3,7 @@ #define __IXP4XX_NPE_H #include <linux/kernel.h> +#include <linux/regmap.h> extern const char *npe_names[]; @@ -17,6 +18,7 @@ struct npe_regs { struct npe { struct npe_regs __iomem *regs; + struct regmap *rmap; int id; int valid; }; diff --git a/include/linux/soc/mediatek/infracfg.h b/include/linux/soc/mediatek/infracfg.h index 4615a228da51..50804ac748bd 100644 --- a/include/linux/soc/mediatek/infracfg.h +++ b/include/linux/soc/mediatek/infracfg.h @@ -2,6 +2,88 @@ #ifndef __SOC_MEDIATEK_INFRACFG_H #define __SOC_MEDIATEK_INFRACFG_H +#define MT8195_TOP_AXI_PROT_EN_STA1 0x228 +#define MT8195_TOP_AXI_PROT_EN_1_STA1 0x258 +#define MT8195_TOP_AXI_PROT_EN_SET 0x2a0 +#define MT8195_TOP_AXI_PROT_EN_CLR 0x2a4 +#define MT8195_TOP_AXI_PROT_EN_1_SET 0x2a8 +#define MT8195_TOP_AXI_PROT_EN_1_CLR 0x2ac +#define MT8195_TOP_AXI_PROT_EN_MM_SET 0x2d4 +#define MT8195_TOP_AXI_PROT_EN_MM_CLR 0x2d8 +#define MT8195_TOP_AXI_PROT_EN_MM_STA1 0x2ec +#define MT8195_TOP_AXI_PROT_EN_2_SET 0x714 +#define MT8195_TOP_AXI_PROT_EN_2_CLR 0x718 +#define MT8195_TOP_AXI_PROT_EN_2_STA1 0x724 +#define MT8195_TOP_AXI_PROT_EN_VDNR_SET 0xb84 +#define MT8195_TOP_AXI_PROT_EN_VDNR_CLR 0xb88 +#define MT8195_TOP_AXI_PROT_EN_VDNR_STA1 0xb90 +#define MT8195_TOP_AXI_PROT_EN_VDNR_1_SET 0xba4 +#define MT8195_TOP_AXI_PROT_EN_VDNR_1_CLR 0xba8 +#define MT8195_TOP_AXI_PROT_EN_VDNR_1_STA1 0xbb0 +#define MT8195_TOP_AXI_PROT_EN_VDNR_2_SET 0xbb8 +#define MT8195_TOP_AXI_PROT_EN_VDNR_2_CLR 0xbbc +#define MT8195_TOP_AXI_PROT_EN_VDNR_2_STA1 0xbc4 +#define MT8195_TOP_AXI_PROT_EN_SUB_INFRA_VDNR_SET 0xbcc +#define MT8195_TOP_AXI_PROT_EN_SUB_INFRA_VDNR_CLR 0xbd0 +#define MT8195_TOP_AXI_PROT_EN_SUB_INFRA_VDNR_STA1 0xbd8 +#define MT8195_TOP_AXI_PROT_EN_MM_2_SET 0xdcc +#define MT8195_TOP_AXI_PROT_EN_MM_2_CLR 0xdd0 +#define MT8195_TOP_AXI_PROT_EN_MM_2_STA1 0xdd8 + +#define MT8195_TOP_AXI_PROT_EN_VDOSYS0 BIT(6) +#define MT8195_TOP_AXI_PROT_EN_VPPSYS0 BIT(10) +#define MT8195_TOP_AXI_PROT_EN_MFG1 BIT(11) +#define MT8195_TOP_AXI_PROT_EN_MFG1_2ND GENMASK(22, 21) +#define MT8195_TOP_AXI_PROT_EN_VPPSYS0_2ND BIT(23) +#define MT8195_TOP_AXI_PROT_EN_1_MFG1 GENMASK(20, 19) +#define MT8195_TOP_AXI_PROT_EN_1_CAM BIT(22) +#define MT8195_TOP_AXI_PROT_EN_2_CAM BIT(0) +#define MT8195_TOP_AXI_PROT_EN_2_MFG1_2ND GENMASK(6, 5) +#define MT8195_TOP_AXI_PROT_EN_2_MFG1 BIT(7) +#define MT8195_TOP_AXI_PROT_EN_2_AUDIO (BIT(9) | BIT(11)) +#define MT8195_TOP_AXI_PROT_EN_2_ADSP (BIT(12) | GENMASK(16, 14)) +#define MT8195_TOP_AXI_PROT_EN_MM_CAM (BIT(0) | BIT(2) | BIT(4)) +#define MT8195_TOP_AXI_PROT_EN_MM_IPE BIT(1) +#define MT8195_TOP_AXI_PROT_EN_MM_IMG BIT(3) +#define MT8195_TOP_AXI_PROT_EN_MM_VDOSYS0 GENMASK(21, 17) +#define MT8195_TOP_AXI_PROT_EN_MM_VPPSYS1 GENMASK(8, 5) +#define MT8195_TOP_AXI_PROT_EN_MM_VENC (BIT(9) | BIT(11)) +#define MT8195_TOP_AXI_PROT_EN_MM_VENC_CORE1 (BIT(10) | BIT(12)) +#define MT8195_TOP_AXI_PROT_EN_MM_VDEC0 BIT(13) +#define MT8195_TOP_AXI_PROT_EN_MM_VDEC1 BIT(14) +#define MT8195_TOP_AXI_PROT_EN_MM_VDOSYS1_2ND BIT(22) +#define MT8195_TOP_AXI_PROT_EN_MM_VPPSYS1_2ND BIT(23) +#define MT8195_TOP_AXI_PROT_EN_MM_CAM_2ND BIT(24) +#define MT8195_TOP_AXI_PROT_EN_MM_IMG_2ND BIT(25) +#define MT8195_TOP_AXI_PROT_EN_MM_VENC_2ND BIT(26) +#define MT8195_TOP_AXI_PROT_EN_MM_WPESYS BIT(27) +#define MT8195_TOP_AXI_PROT_EN_MM_VDEC0_2ND BIT(28) +#define MT8195_TOP_AXI_PROT_EN_MM_VDEC1_2ND BIT(29) +#define MT8195_TOP_AXI_PROT_EN_MM_VDOSYS1 GENMASK(31, 30) +#define MT8195_TOP_AXI_PROT_EN_MM_2_VPPSYS0_2ND (GENMASK(1, 0) | BIT(4) | BIT(11)) +#define MT8195_TOP_AXI_PROT_EN_MM_2_VENC BIT(2) +#define MT8195_TOP_AXI_PROT_EN_MM_2_VENC_CORE1 (BIT(3) | BIT(15)) +#define MT8195_TOP_AXI_PROT_EN_MM_2_CAM (BIT(5) | BIT(17)) +#define MT8195_TOP_AXI_PROT_EN_MM_2_VPPSYS1 (GENMASK(7, 6) | BIT(18)) +#define MT8195_TOP_AXI_PROT_EN_MM_2_VPPSYS0 GENMASK(9, 8) +#define MT8195_TOP_AXI_PROT_EN_MM_2_VDOSYS1 BIT(10) +#define MT8195_TOP_AXI_PROT_EN_MM_2_VDEC2_2ND BIT(12) +#define MT8195_TOP_AXI_PROT_EN_MM_2_VDEC0_2ND BIT(13) +#define MT8195_TOP_AXI_PROT_EN_MM_2_WPESYS_2ND BIT(14) +#define MT8195_TOP_AXI_PROT_EN_MM_2_IPE BIT(16) +#define MT8195_TOP_AXI_PROT_EN_MM_2_VDEC2 BIT(21) +#define MT8195_TOP_AXI_PROT_EN_MM_2_VDEC0 BIT(22) +#define MT8195_TOP_AXI_PROT_EN_MM_2_WPESYS GENMASK(24, 23) +#define MT8195_TOP_AXI_PROT_EN_VDNR_1_EPD_TX BIT(1) +#define MT8195_TOP_AXI_PROT_EN_VDNR_1_DP_TX BIT(2) +#define MT8195_TOP_AXI_PROT_EN_VDNR_PCIE_MAC_P0 (BIT(11) | BIT(28)) +#define MT8195_TOP_AXI_PROT_EN_VDNR_PCIE_MAC_P1 (BIT(12) | BIT(29)) +#define MT8195_TOP_AXI_PROT_EN_VDNR_1_PCIE_MAC_P0 BIT(13) +#define MT8195_TOP_AXI_PROT_EN_VDNR_1_PCIE_MAC_P1 BIT(14) +#define MT8195_TOP_AXI_PROT_EN_SUB_INFRA_VDNR_MFG1 (BIT(17) | BIT(19)) +#define MT8195_TOP_AXI_PROT_EN_SUB_INFRA_VDNR_VPPSYS0 BIT(20) +#define MT8195_TOP_AXI_PROT_EN_SUB_INFRA_VDNR_VDOSYS0 BIT(21) + #define MT8192_TOP_AXI_PROT_EN_STA1 0x228 #define MT8192_TOP_AXI_PROT_EN_1_STA1 0x258 #define MT8192_TOP_AXI_PROT_EN_SET 0x2a0 @@ -58,6 +140,54 @@ #define MT8192_TOP_AXI_PROT_EN_MM_2_MDP_2ND BIT(13) #define MT8192_TOP_AXI_PROT_EN_VDNR_CAM BIT(21) +#define MT8186_TOP_AXI_PROT_EN_SET (0x2A0) +#define MT8186_TOP_AXI_PROT_EN_CLR (0x2A4) +#define MT8186_TOP_AXI_PROT_EN_STA (0x228) +#define MT8186_TOP_AXI_PROT_EN_1_SET (0x2A8) +#define MT8186_TOP_AXI_PROT_EN_1_CLR (0x2AC) +#define MT8186_TOP_AXI_PROT_EN_1_STA (0x258) +#define MT8186_TOP_AXI_PROT_EN_2_SET (0x2B0) +#define MT8186_TOP_AXI_PROT_EN_2_CLR (0x2B4) +#define MT8186_TOP_AXI_PROT_EN_2_STA (0x26C) +#define MT8186_TOP_AXI_PROT_EN_3_SET (0x2B8) +#define MT8186_TOP_AXI_PROT_EN_3_CLR (0x2BC) +#define MT8186_TOP_AXI_PROT_EN_3_STA (0x2C8) + +/* MFG1 */ +#define MT8186_TOP_AXI_PROT_EN_1_MFG1_STEP1 (GENMASK(28, 27)) +#define MT8186_TOP_AXI_PROT_EN_MFG1_STEP2 (GENMASK(22, 21)) +#define MT8186_TOP_AXI_PROT_EN_MFG1_STEP3 (BIT(25)) +#define MT8186_TOP_AXI_PROT_EN_1_MFG1_STEP4 (BIT(29)) +/* DIS */ +#define MT8186_TOP_AXI_PROT_EN_1_DIS_STEP1 (GENMASK(12, 11)) +#define MT8186_TOP_AXI_PROT_EN_DIS_STEP2 (GENMASK(2, 1) | GENMASK(11, 10)) +/* IMG */ +#define MT8186_TOP_AXI_PROT_EN_1_IMG_STEP1 (BIT(23)) +#define MT8186_TOP_AXI_PROT_EN_1_IMG_STEP2 (BIT(15)) +/* IPE */ +#define MT8186_TOP_AXI_PROT_EN_1_IPE_STEP1 (BIT(24)) +#define MT8186_TOP_AXI_PROT_EN_1_IPE_STEP2 (BIT(16)) +/* CAM */ +#define MT8186_TOP_AXI_PROT_EN_1_CAM_STEP1 (GENMASK(22, 21)) +#define MT8186_TOP_AXI_PROT_EN_1_CAM_STEP2 (GENMASK(14, 13)) +/* VENC */ +#define MT8186_TOP_AXI_PROT_EN_1_VENC_STEP1 (BIT(31)) +#define MT8186_TOP_AXI_PROT_EN_1_VENC_STEP2 (BIT(19)) +/* VDEC */ +#define MT8186_TOP_AXI_PROT_EN_1_VDEC_STEP1 (BIT(30)) +#define MT8186_TOP_AXI_PROT_EN_1_VDEC_STEP2 (BIT(17)) +/* WPE */ +#define MT8186_TOP_AXI_PROT_EN_2_WPE_STEP1 (BIT(17)) +#define MT8186_TOP_AXI_PROT_EN_2_WPE_STEP2 (BIT(16)) +/* CONN_ON */ +#define MT8186_TOP_AXI_PROT_EN_1_CONN_ON_STEP1 (BIT(18)) +#define MT8186_TOP_AXI_PROT_EN_CONN_ON_STEP2 (BIT(14)) +#define MT8186_TOP_AXI_PROT_EN_CONN_ON_STEP3 (BIT(13)) +#define MT8186_TOP_AXI_PROT_EN_CONN_ON_STEP4 (BIT(16)) +/* ADSP_TOP */ +#define MT8186_TOP_AXI_PROT_EN_3_ADSP_TOP_STEP1 (GENMASK(12, 11)) +#define MT8186_TOP_AXI_PROT_EN_3_ADSP_TOP_STEP2 (GENMASK(1, 0)) + #define MT8183_TOP_AXI_PROT_EN_STA1 0x228 #define MT8183_TOP_AXI_PROT_EN_STA1_1 0x258 #define MT8183_TOP_AXI_PROT_EN_SET 0x2a0 @@ -147,6 +277,9 @@ #define INFRA_TOPAXI_PROTECTEN_SET 0x0260 #define INFRA_TOPAXI_PROTECTEN_CLR 0x0264 +#define MT8192_INFRA_CTRL 0x290 +#define MT8192_INFRA_CTRL_DISABLE_MFG2ACP BIT(9) + #define REG_INFRA_MISC 0xf00 #define F_DDR_4GB_SUPPORT_EN BIT(13) diff --git a/include/linux/soc/mediatek/mtk-cmdq.h b/include/linux/soc/mediatek/mtk-cmdq.h index ac6b5f3cba95..2b498f4f3946 100644 --- a/include/linux/soc/mediatek/mtk-cmdq.h +++ b/include/linux/soc/mediatek/mtk-cmdq.h @@ -268,8 +268,6 @@ int cmdq_pkt_finalize(struct cmdq_pkt *pkt); * cmdq_pkt_flush_async() - trigger CMDQ to asynchronously execute the CMDQ * packet and call back at the end of done packet * @pkt: the CMDQ packet - * @cb: called at the end of done packet - * @data: this data will pass back to cb * * Return: 0 for success; else the error code is returned * @@ -277,7 +275,6 @@ int cmdq_pkt_finalize(struct cmdq_pkt *pkt); * at the end of done packet. Note that this is an ASYNC function. When the * function returned, it may or may not be finished. */ -int cmdq_pkt_flush_async(struct cmdq_pkt *pkt, cmdq_async_flush_cb cb, - void *data); +int cmdq_pkt_flush_async(struct cmdq_pkt *pkt); #endif /* __MTK_CMDQ_H__ */ diff --git a/include/linux/soc/mediatek/mtk-mmsys.h b/include/linux/soc/mediatek/mtk-mmsys.h index 4bba275e235a..d2b02bb43768 100644 --- a/include/linux/soc/mediatek/mtk-mmsys.h +++ b/include/linux/soc/mediatek/mtk-mmsys.h @@ -17,13 +17,25 @@ enum mtk_ddp_comp_id { DDP_COMPONENT_COLOR0, DDP_COMPONENT_COLOR1, DDP_COMPONENT_DITHER, + DDP_COMPONENT_DITHER0 = DDP_COMPONENT_DITHER, + DDP_COMPONENT_DITHER1, + DDP_COMPONENT_DP_INTF0, + DDP_COMPONENT_DP_INTF1, DDP_COMPONENT_DPI0, DDP_COMPONENT_DPI1, + DDP_COMPONENT_DSC0, + DDP_COMPONENT_DSC1, DDP_COMPONENT_DSI0, DDP_COMPONENT_DSI1, DDP_COMPONENT_DSI2, DDP_COMPONENT_DSI3, DDP_COMPONENT_GAMMA, + DDP_COMPONENT_MERGE0, + DDP_COMPONENT_MERGE1, + DDP_COMPONENT_MERGE2, + DDP_COMPONENT_MERGE3, + DDP_COMPONENT_MERGE4, + DDP_COMPONENT_MERGE5, DDP_COMPONENT_OD0, DDP_COMPONENT_OD1, DDP_COMPONENT_OVL0, @@ -53,4 +65,6 @@ void mtk_mmsys_ddp_disconnect(struct device *dev, enum mtk_ddp_comp_id cur, enum mtk_ddp_comp_id next); +void mtk_mmsys_ddp_dpi_fmt_config(struct device *dev, u32 val); + #endif /* __MTK_MMSYS_H */ diff --git a/include/linux/soc/mediatek/mtk-mutex.h b/include/linux/soc/mediatek/mtk-mutex.h index 6fe4ffbde290..b335c2837cd8 100644 --- a/include/linux/soc/mediatek/mtk-mutex.h +++ b/include/linux/soc/mediatek/mtk-mutex.h @@ -10,11 +10,35 @@ struct regmap; struct device; struct mtk_mutex; +enum mtk_mutex_mod_index { + /* MDP table index */ + MUTEX_MOD_IDX_MDP_RDMA0, + MUTEX_MOD_IDX_MDP_RSZ0, + MUTEX_MOD_IDX_MDP_RSZ1, + MUTEX_MOD_IDX_MDP_TDSHP0, + MUTEX_MOD_IDX_MDP_WROT0, + MUTEX_MOD_IDX_MDP_WDMA, + MUTEX_MOD_IDX_MDP_AAL0, + MUTEX_MOD_IDX_MDP_CCORR0, + MUTEX_MOD_IDX_MDP_HDR0, + MUTEX_MOD_IDX_MDP_COLOR0, + + MUTEX_MOD_IDX_MAX /* ALWAYS keep at the end */ +}; + +enum mtk_mutex_sof_index { + MUTEX_SOF_IDX_SINGLE_MODE, + + MUTEX_SOF_IDX_MAX /* ALWAYS keep at the end */ +}; + struct mtk_mutex *mtk_mutex_get(struct device *dev); int mtk_mutex_prepare(struct mtk_mutex *mutex); void mtk_mutex_add_comp(struct mtk_mutex *mutex, enum mtk_ddp_comp_id id); void mtk_mutex_enable(struct mtk_mutex *mutex); +int mtk_mutex_enable_by_cmdq(struct mtk_mutex *mutex, + void *pkt); void mtk_mutex_disable(struct mtk_mutex *mutex); void mtk_mutex_remove_comp(struct mtk_mutex *mutex, enum mtk_ddp_comp_id id); @@ -22,5 +46,10 @@ void mtk_mutex_unprepare(struct mtk_mutex *mutex); void mtk_mutex_put(struct mtk_mutex *mutex); void mtk_mutex_acquire(struct mtk_mutex *mutex); void mtk_mutex_release(struct mtk_mutex *mutex); +int mtk_mutex_write_mod(struct mtk_mutex *mutex, + enum mtk_mutex_mod_index idx, + bool clear); +int mtk_mutex_write_sof(struct mtk_mutex *mutex, + enum mtk_mutex_sof_index idx); #endif /* MTK_MUTEX_H */ diff --git a/include/linux/soc/mediatek/mtk_sip_svc.h b/include/linux/soc/mediatek/mtk_sip_svc.h index 082398e0cfb1..0761128b4354 100644 --- a/include/linux/soc/mediatek/mtk_sip_svc.h +++ b/include/linux/soc/mediatek/mtk_sip_svc.h @@ -22,4 +22,7 @@ ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, MTK_SIP_SMC_CONVENTION, \ ARM_SMCCC_OWNER_SIP, fn_id) +/* IOMMU related SMC call */ +#define MTK_SIP_KERNEL_IOMMU_CONTROL MTK_SIP_SMC_CMD(0x514) + #endif diff --git a/include/linux/soc/mediatek/mtk_wed.h b/include/linux/soc/mediatek/mtk_wed.h new file mode 100644 index 000000000000..4450c8b7a1cb --- /dev/null +++ b/include/linux/soc/mediatek/mtk_wed.h @@ -0,0 +1,148 @@ +#ifndef __MTK_WED_H +#define __MTK_WED_H + +#include <linux/kernel.h> +#include <linux/rcupdate.h> +#include <linux/regmap.h> +#include <linux/pci.h> + +#define MTK_WED_TX_QUEUES 2 + +struct mtk_wed_hw; +struct mtk_wdma_desc; + +enum mtk_wed_bus_tye { + MTK_WED_BUS_PCIE, + MTK_WED_BUS_AXI, +}; + +struct mtk_wed_ring { + struct mtk_wdma_desc *desc; + dma_addr_t desc_phys; + u32 desc_size; + int size; + + u32 reg_base; + void __iomem *wpdma; +}; + +struct mtk_wed_device { +#ifdef CONFIG_NET_MEDIATEK_SOC_WED + const struct mtk_wed_ops *ops; + struct device *dev; + struct mtk_wed_hw *hw; + bool init_done, running; + int wdma_idx; + int irq; + + struct mtk_wed_ring tx_ring[MTK_WED_TX_QUEUES]; + struct mtk_wed_ring txfree_ring; + struct mtk_wed_ring tx_wdma[MTK_WED_TX_QUEUES]; + + struct { + int size; + void **pages; + struct mtk_wdma_desc *desc; + dma_addr_t desc_phys; + } buf_ring; + + /* filled by driver: */ + struct { + union { + struct platform_device *platform_dev; + struct pci_dev *pci_dev; + }; + enum mtk_wed_bus_tye bus_type; + + u32 wpdma_phys; + u32 wpdma_int; + u32 wpdma_mask; + u32 wpdma_tx; + u32 wpdma_txfree; + + u16 token_start; + unsigned int nbuf; + + u8 tx_tbit[MTK_WED_TX_QUEUES]; + u8 txfree_tbit; + + u32 (*init_buf)(void *ptr, dma_addr_t phys, int token_id); + int (*offload_enable)(struct mtk_wed_device *wed); + void (*offload_disable)(struct mtk_wed_device *wed); + } wlan; +#endif +}; + +struct mtk_wed_ops { + int (*attach)(struct mtk_wed_device *dev); + int (*tx_ring_setup)(struct mtk_wed_device *dev, int ring, + void __iomem *regs); + int (*txfree_ring_setup)(struct mtk_wed_device *dev, + void __iomem *regs); + void (*detach)(struct mtk_wed_device *dev); + + void (*stop)(struct mtk_wed_device *dev); + void (*start)(struct mtk_wed_device *dev, u32 irq_mask); + void (*reset_dma)(struct mtk_wed_device *dev); + + u32 (*reg_read)(struct mtk_wed_device *dev, u32 reg); + void (*reg_write)(struct mtk_wed_device *dev, u32 reg, u32 val); + + u32 (*irq_get)(struct mtk_wed_device *dev, u32 mask); + void (*irq_set_mask)(struct mtk_wed_device *dev, u32 mask); +}; + +extern const struct mtk_wed_ops __rcu *mtk_soc_wed_ops; + +static inline int +mtk_wed_device_attach(struct mtk_wed_device *dev) +{ + int ret = -ENODEV; + +#ifdef CONFIG_NET_MEDIATEK_SOC_WED + rcu_read_lock(); + dev->ops = rcu_dereference(mtk_soc_wed_ops); + if (dev->ops) + ret = dev->ops->attach(dev); + else + rcu_read_unlock(); + + if (ret) + dev->ops = NULL; +#endif + + return ret; +} + +#ifdef CONFIG_NET_MEDIATEK_SOC_WED +#define mtk_wed_device_active(_dev) !!(_dev)->ops +#define mtk_wed_device_detach(_dev) (_dev)->ops->detach(_dev) +#define mtk_wed_device_start(_dev, _mask) (_dev)->ops->start(_dev, _mask) +#define mtk_wed_device_tx_ring_setup(_dev, _ring, _regs) \ + (_dev)->ops->tx_ring_setup(_dev, _ring, _regs) +#define mtk_wed_device_txfree_ring_setup(_dev, _regs) \ + (_dev)->ops->txfree_ring_setup(_dev, _regs) +#define mtk_wed_device_reg_read(_dev, _reg) \ + (_dev)->ops->reg_read(_dev, _reg) +#define mtk_wed_device_reg_write(_dev, _reg, _val) \ + (_dev)->ops->reg_write(_dev, _reg, _val) +#define mtk_wed_device_irq_get(_dev, _mask) \ + (_dev)->ops->irq_get(_dev, _mask) +#define mtk_wed_device_irq_set_mask(_dev, _mask) \ + (_dev)->ops->irq_set_mask(_dev, _mask) +#else +static inline bool mtk_wed_device_active(struct mtk_wed_device *dev) +{ + return false; +} +#define mtk_wed_device_detach(_dev) do {} while (0) +#define mtk_wed_device_start(_dev, _mask) do {} while (0) +#define mtk_wed_device_tx_ring_setup(_dev, _ring, _regs) -ENODEV +#define mtk_wed_device_txfree_ring_setup(_dev, _ring, _regs) -ENODEV +#define mtk_wed_device_reg_read(_dev, _reg) 0 +#define mtk_wed_device_reg_write(_dev, _reg, _val) do {} while (0) +#define mtk_wed_device_irq_get(_dev, _mask) 0 +#define mtk_wed_device_irq_set_mask(_dev, _mask) do {} while (0) +#endif + +#endif diff --git a/include/linux/soc/pxa/cpu.h b/include/linux/soc/pxa/cpu.h new file mode 100644 index 000000000000..5782450ee45c --- /dev/null +++ b/include/linux/soc/pxa/cpu.h @@ -0,0 +1,252 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Author: Nicolas Pitre + * Created: Jun 15, 2001 + * Copyright: MontaVista Software Inc. + */ + +#ifndef __SOC_PXA_CPU_H +#define __SOC_PXA_CPU_H + +#ifdef CONFIG_ARM +#include <asm/cputype.h> +#endif + +/* + * CPU Stepping CPU_ID JTAG_ID + * + * PXA210 B0 0x69052922 0x2926C013 + * PXA210 B1 0x69052923 0x3926C013 + * PXA210 B2 0x69052924 0x4926C013 + * PXA210 C0 0x69052D25 0x5926C013 + * + * PXA250 A0 0x69052100 0x09264013 + * PXA250 A1 0x69052101 0x19264013 + * PXA250 B0 0x69052902 0x29264013 + * PXA250 B1 0x69052903 0x39264013 + * PXA250 B2 0x69052904 0x49264013 + * PXA250 C0 0x69052D05 0x59264013 + * + * PXA255 A0 0x69052D06 0x69264013 + * + * PXA26x A0 0x69052903 0x39264013 + * PXA26x B0 0x69052D05 0x59264013 + * + * PXA27x A0 0x69054110 0x09265013 + * PXA27x A1 0x69054111 0x19265013 + * PXA27x B0 0x69054112 0x29265013 + * PXA27x B1 0x69054113 0x39265013 + * PXA27x C0 0x69054114 0x49265013 + * PXA27x C5 0x69054117 0x79265013 + * + * PXA30x A0 0x69056880 0x0E648013 + * PXA30x A1 0x69056881 0x1E648013 + * PXA31x A0 0x69056890 0x0E649013 + * PXA31x A1 0x69056891 0x1E649013 + * PXA31x A2 0x69056892 0x2E649013 + * PXA32x B1 0x69056825 0x5E642013 + * PXA32x B2 0x69056826 0x6E642013 + * + * PXA930 B0 0x69056835 0x5E643013 + * PXA930 B1 0x69056837 0x7E643013 + * PXA930 B2 0x69056838 0x8E643013 + * + * PXA935 A0 0x56056931 0x1E653013 + * PXA935 B0 0x56056936 0x6E653013 + * PXA935 B1 0x56056938 0x8E653013 + */ +#ifdef CONFIG_PXA25x +#define __cpu_is_pxa210(id) \ + ({ \ + unsigned int _id = (id) & 0xf3f0; \ + _id == 0x2120; \ + }) + +#define __cpu_is_pxa250(id) \ + ({ \ + unsigned int _id = (id) & 0xf3ff; \ + _id <= 0x2105; \ + }) + +#define __cpu_is_pxa255(id) \ + ({ \ + unsigned int _id = (id) & 0xffff; \ + _id == 0x2d06; \ + }) + +#define __cpu_is_pxa25x(id) \ + ({ \ + unsigned int _id = (id) & 0xf300; \ + _id == 0x2100; \ + }) +#else +#define __cpu_is_pxa210(id) (0) +#define __cpu_is_pxa250(id) (0) +#define __cpu_is_pxa255(id) (0) +#define __cpu_is_pxa25x(id) (0) +#endif + +#ifdef CONFIG_PXA27x +#define __cpu_is_pxa27x(id) \ + ({ \ + unsigned int _id = (id) >> 4 & 0xfff; \ + _id == 0x411; \ + }) +#else +#define __cpu_is_pxa27x(id) (0) +#endif + +#ifdef CONFIG_CPU_PXA300 +#define __cpu_is_pxa300(id) \ + ({ \ + unsigned int _id = (id) >> 4 & 0xfff; \ + _id == 0x688; \ + }) +#else +#define __cpu_is_pxa300(id) (0) +#endif + +#ifdef CONFIG_CPU_PXA310 +#define __cpu_is_pxa310(id) \ + ({ \ + unsigned int _id = (id) >> 4 & 0xfff; \ + _id == 0x689; \ + }) +#else +#define __cpu_is_pxa310(id) (0) +#endif + +#ifdef CONFIG_CPU_PXA320 +#define __cpu_is_pxa320(id) \ + ({ \ + unsigned int _id = (id) >> 4 & 0xfff; \ + _id == 0x603 || _id == 0x682; \ + }) +#else +#define __cpu_is_pxa320(id) (0) +#endif + +#ifdef CONFIG_CPU_PXA930 +#define __cpu_is_pxa930(id) \ + ({ \ + unsigned int _id = (id) >> 4 & 0xfff; \ + _id == 0x683; \ + }) +#else +#define __cpu_is_pxa930(id) (0) +#endif + +#ifdef CONFIG_CPU_PXA935 +#define __cpu_is_pxa935(id) \ + ({ \ + unsigned int _id = (id) >> 4 & 0xfff; \ + _id == 0x693; \ + }) +#else +#define __cpu_is_pxa935(id) (0) +#endif + +#define cpu_is_pxa210() \ + ({ \ + __cpu_is_pxa210(read_cpuid_id()); \ + }) + +#define cpu_is_pxa250() \ + ({ \ + __cpu_is_pxa250(read_cpuid_id()); \ + }) + +#define cpu_is_pxa255() \ + ({ \ + __cpu_is_pxa255(read_cpuid_id()); \ + }) + +#define cpu_is_pxa25x() \ + ({ \ + __cpu_is_pxa25x(read_cpuid_id()); \ + }) + +#define cpu_is_pxa27x() \ + ({ \ + __cpu_is_pxa27x(read_cpuid_id()); \ + }) + +#define cpu_is_pxa300() \ + ({ \ + __cpu_is_pxa300(read_cpuid_id()); \ + }) + +#define cpu_is_pxa310() \ + ({ \ + __cpu_is_pxa310(read_cpuid_id()); \ + }) + +#define cpu_is_pxa320() \ + ({ \ + __cpu_is_pxa320(read_cpuid_id()); \ + }) + +#define cpu_is_pxa930() \ + ({ \ + __cpu_is_pxa930(read_cpuid_id()); \ + }) + +#define cpu_is_pxa935() \ + ({ \ + __cpu_is_pxa935(read_cpuid_id()); \ + }) + + + +/* + * CPUID Core Generation Bit + * <= 0x2 for pxa21x/pxa25x/pxa26x/pxa27x + */ +#if defined(CONFIG_PXA25x) || defined(CONFIG_PXA27x) +#define __cpu_is_pxa2xx(id) \ + ({ \ + unsigned int _id = (id) >> 13 & 0x7; \ + _id <= 0x2; \ + }) +#else +#define __cpu_is_pxa2xx(id) (0) +#endif + +#ifdef CONFIG_PXA3xx +#define __cpu_is_pxa3xx(id) \ + ({ \ + __cpu_is_pxa300(id) \ + || __cpu_is_pxa310(id) \ + || __cpu_is_pxa320(id) \ + || __cpu_is_pxa93x(id); \ + }) +#else +#define __cpu_is_pxa3xx(id) (0) +#endif + +#if defined(CONFIG_CPU_PXA930) || defined(CONFIG_CPU_PXA935) +#define __cpu_is_pxa93x(id) \ + ({ \ + __cpu_is_pxa930(id) \ + || __cpu_is_pxa935(id); \ + }) +#else +#define __cpu_is_pxa93x(id) (0) +#endif + +#define cpu_is_pxa2xx() \ + ({ \ + __cpu_is_pxa2xx(read_cpuid_id()); \ + }) + +#define cpu_is_pxa3xx() \ + ({ \ + __cpu_is_pxa3xx(read_cpuid_id()); \ + }) + +#define cpu_is_pxa93x() \ + ({ \ + __cpu_is_pxa93x(read_cpuid_id()); \ + }) + +#endif diff --git a/include/linux/soc/pxa/mfp.h b/include/linux/soc/pxa/mfp.h new file mode 100644 index 000000000000..39779cbed0c0 --- /dev/null +++ b/include/linux/soc/pxa/mfp.h @@ -0,0 +1,470 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Common Multi-Function Pin Definitions + * + * Copyright (C) 2007 Marvell International Ltd. + * + * 2007-8-21: eric miao <eric.miao@marvell.com> + * initial version + */ + +#ifndef __ASM_PLAT_MFP_H +#define __ASM_PLAT_MFP_H + +#define mfp_to_gpio(m) ((m) % 256) + +/* list of all the configurable MFP pins */ +enum { + MFP_PIN_INVALID = -1, + + MFP_PIN_GPIO0 = 0, + MFP_PIN_GPIO1, + MFP_PIN_GPIO2, + MFP_PIN_GPIO3, + MFP_PIN_GPIO4, + MFP_PIN_GPIO5, + MFP_PIN_GPIO6, + MFP_PIN_GPIO7, + MFP_PIN_GPIO8, + MFP_PIN_GPIO9, + MFP_PIN_GPIO10, + MFP_PIN_GPIO11, + MFP_PIN_GPIO12, + MFP_PIN_GPIO13, + MFP_PIN_GPIO14, + MFP_PIN_GPIO15, + MFP_PIN_GPIO16, + MFP_PIN_GPIO17, + MFP_PIN_GPIO18, + MFP_PIN_GPIO19, + MFP_PIN_GPIO20, + MFP_PIN_GPIO21, + MFP_PIN_GPIO22, + MFP_PIN_GPIO23, + MFP_PIN_GPIO24, + MFP_PIN_GPIO25, + MFP_PIN_GPIO26, + MFP_PIN_GPIO27, + MFP_PIN_GPIO28, + MFP_PIN_GPIO29, + MFP_PIN_GPIO30, + MFP_PIN_GPIO31, + MFP_PIN_GPIO32, + MFP_PIN_GPIO33, + MFP_PIN_GPIO34, + MFP_PIN_GPIO35, + MFP_PIN_GPIO36, + MFP_PIN_GPIO37, + MFP_PIN_GPIO38, + MFP_PIN_GPIO39, + MFP_PIN_GPIO40, + MFP_PIN_GPIO41, + MFP_PIN_GPIO42, + MFP_PIN_GPIO43, + MFP_PIN_GPIO44, + MFP_PIN_GPIO45, + MFP_PIN_GPIO46, + MFP_PIN_GPIO47, + MFP_PIN_GPIO48, + MFP_PIN_GPIO49, + MFP_PIN_GPIO50, + MFP_PIN_GPIO51, + MFP_PIN_GPIO52, + MFP_PIN_GPIO53, + MFP_PIN_GPIO54, + MFP_PIN_GPIO55, + MFP_PIN_GPIO56, + MFP_PIN_GPIO57, + MFP_PIN_GPIO58, + MFP_PIN_GPIO59, + MFP_PIN_GPIO60, + MFP_PIN_GPIO61, + MFP_PIN_GPIO62, + MFP_PIN_GPIO63, + MFP_PIN_GPIO64, + MFP_PIN_GPIO65, + MFP_PIN_GPIO66, + MFP_PIN_GPIO67, + MFP_PIN_GPIO68, + MFP_PIN_GPIO69, + MFP_PIN_GPIO70, + MFP_PIN_GPIO71, + MFP_PIN_GPIO72, + MFP_PIN_GPIO73, + MFP_PIN_GPIO74, + MFP_PIN_GPIO75, + MFP_PIN_GPIO76, + MFP_PIN_GPIO77, + MFP_PIN_GPIO78, + MFP_PIN_GPIO79, + MFP_PIN_GPIO80, + MFP_PIN_GPIO81, + MFP_PIN_GPIO82, + MFP_PIN_GPIO83, + MFP_PIN_GPIO84, + MFP_PIN_GPIO85, + MFP_PIN_GPIO86, + MFP_PIN_GPIO87, + MFP_PIN_GPIO88, + MFP_PIN_GPIO89, + MFP_PIN_GPIO90, + MFP_PIN_GPIO91, + MFP_PIN_GPIO92, + MFP_PIN_GPIO93, + MFP_PIN_GPIO94, + MFP_PIN_GPIO95, + MFP_PIN_GPIO96, + MFP_PIN_GPIO97, + MFP_PIN_GPIO98, + MFP_PIN_GPIO99, + MFP_PIN_GPIO100, + MFP_PIN_GPIO101, + MFP_PIN_GPIO102, + MFP_PIN_GPIO103, + MFP_PIN_GPIO104, + MFP_PIN_GPIO105, + MFP_PIN_GPIO106, + MFP_PIN_GPIO107, + MFP_PIN_GPIO108, + MFP_PIN_GPIO109, + MFP_PIN_GPIO110, + MFP_PIN_GPIO111, + MFP_PIN_GPIO112, + MFP_PIN_GPIO113, + MFP_PIN_GPIO114, + MFP_PIN_GPIO115, + MFP_PIN_GPIO116, + MFP_PIN_GPIO117, + MFP_PIN_GPIO118, + MFP_PIN_GPIO119, + MFP_PIN_GPIO120, + MFP_PIN_GPIO121, + MFP_PIN_GPIO122, + MFP_PIN_GPIO123, + MFP_PIN_GPIO124, + MFP_PIN_GPIO125, + MFP_PIN_GPIO126, + MFP_PIN_GPIO127, + + MFP_PIN_GPIO128, + MFP_PIN_GPIO129, + MFP_PIN_GPIO130, + MFP_PIN_GPIO131, + MFP_PIN_GPIO132, + MFP_PIN_GPIO133, + MFP_PIN_GPIO134, + MFP_PIN_GPIO135, + MFP_PIN_GPIO136, + MFP_PIN_GPIO137, + MFP_PIN_GPIO138, + MFP_PIN_GPIO139, + MFP_PIN_GPIO140, + MFP_PIN_GPIO141, + MFP_PIN_GPIO142, + MFP_PIN_GPIO143, + MFP_PIN_GPIO144, + MFP_PIN_GPIO145, + MFP_PIN_GPIO146, + MFP_PIN_GPIO147, + MFP_PIN_GPIO148, + MFP_PIN_GPIO149, + MFP_PIN_GPIO150, + MFP_PIN_GPIO151, + MFP_PIN_GPIO152, + MFP_PIN_GPIO153, + MFP_PIN_GPIO154, + MFP_PIN_GPIO155, + MFP_PIN_GPIO156, + MFP_PIN_GPIO157, + MFP_PIN_GPIO158, + MFP_PIN_GPIO159, + MFP_PIN_GPIO160, + MFP_PIN_GPIO161, + MFP_PIN_GPIO162, + MFP_PIN_GPIO163, + MFP_PIN_GPIO164, + MFP_PIN_GPIO165, + MFP_PIN_GPIO166, + MFP_PIN_GPIO167, + MFP_PIN_GPIO168, + MFP_PIN_GPIO169, + MFP_PIN_GPIO170, + MFP_PIN_GPIO171, + MFP_PIN_GPIO172, + MFP_PIN_GPIO173, + MFP_PIN_GPIO174, + MFP_PIN_GPIO175, + MFP_PIN_GPIO176, + MFP_PIN_GPIO177, + MFP_PIN_GPIO178, + MFP_PIN_GPIO179, + MFP_PIN_GPIO180, + MFP_PIN_GPIO181, + MFP_PIN_GPIO182, + MFP_PIN_GPIO183, + MFP_PIN_GPIO184, + MFP_PIN_GPIO185, + MFP_PIN_GPIO186, + MFP_PIN_GPIO187, + MFP_PIN_GPIO188, + MFP_PIN_GPIO189, + MFP_PIN_GPIO190, + MFP_PIN_GPIO191, + + MFP_PIN_GPIO255 = 255, + + MFP_PIN_GPIO0_2, + MFP_PIN_GPIO1_2, + MFP_PIN_GPIO2_2, + MFP_PIN_GPIO3_2, + MFP_PIN_GPIO4_2, + MFP_PIN_GPIO5_2, + MFP_PIN_GPIO6_2, + MFP_PIN_GPIO7_2, + MFP_PIN_GPIO8_2, + MFP_PIN_GPIO9_2, + MFP_PIN_GPIO10_2, + MFP_PIN_GPIO11_2, + MFP_PIN_GPIO12_2, + MFP_PIN_GPIO13_2, + MFP_PIN_GPIO14_2, + MFP_PIN_GPIO15_2, + MFP_PIN_GPIO16_2, + MFP_PIN_GPIO17_2, + + MFP_PIN_ULPI_STP, + MFP_PIN_ULPI_NXT, + MFP_PIN_ULPI_DIR, + + MFP_PIN_nXCVREN, + MFP_PIN_DF_CLE_nOE, + MFP_PIN_DF_nADV1_ALE, + MFP_PIN_DF_SCLK_E, + MFP_PIN_DF_SCLK_S, + MFP_PIN_nBE0, + MFP_PIN_nBE1, + MFP_PIN_DF_nADV2_ALE, + MFP_PIN_DF_INT_RnB, + MFP_PIN_DF_nCS0, + MFP_PIN_DF_nCS1, + MFP_PIN_nLUA, + MFP_PIN_nLLA, + MFP_PIN_DF_nWE, + MFP_PIN_DF_ALE_nWE, + MFP_PIN_DF_nRE_nOE, + MFP_PIN_DF_ADDR0, + MFP_PIN_DF_ADDR1, + MFP_PIN_DF_ADDR2, + MFP_PIN_DF_ADDR3, + MFP_PIN_DF_IO0, + MFP_PIN_DF_IO1, + MFP_PIN_DF_IO2, + MFP_PIN_DF_IO3, + MFP_PIN_DF_IO4, + MFP_PIN_DF_IO5, + MFP_PIN_DF_IO6, + MFP_PIN_DF_IO7, + MFP_PIN_DF_IO8, + MFP_PIN_DF_IO9, + MFP_PIN_DF_IO10, + MFP_PIN_DF_IO11, + MFP_PIN_DF_IO12, + MFP_PIN_DF_IO13, + MFP_PIN_DF_IO14, + MFP_PIN_DF_IO15, + MFP_PIN_DF_nCS0_SM_nCS2, + MFP_PIN_DF_nCS1_SM_nCS3, + MFP_PIN_SM_nCS0, + MFP_PIN_SM_nCS1, + MFP_PIN_DF_WEn, + MFP_PIN_DF_REn, + MFP_PIN_DF_CLE_SM_OEn, + MFP_PIN_DF_ALE_SM_WEn, + MFP_PIN_DF_RDY0, + MFP_PIN_DF_RDY1, + + MFP_PIN_SM_SCLK, + MFP_PIN_SM_BE0, + MFP_PIN_SM_BE1, + MFP_PIN_SM_ADV, + MFP_PIN_SM_ADVMUX, + MFP_PIN_SM_RDY, + + MFP_PIN_MMC1_DAT7, + MFP_PIN_MMC1_DAT6, + MFP_PIN_MMC1_DAT5, + MFP_PIN_MMC1_DAT4, + MFP_PIN_MMC1_DAT3, + MFP_PIN_MMC1_DAT2, + MFP_PIN_MMC1_DAT1, + MFP_PIN_MMC1_DAT0, + MFP_PIN_MMC1_CMD, + MFP_PIN_MMC1_CLK, + MFP_PIN_MMC1_CD, + MFP_PIN_MMC1_WP, + + /* additional pins on PXA930 */ + MFP_PIN_GSIM_UIO, + MFP_PIN_GSIM_UCLK, + MFP_PIN_GSIM_UDET, + MFP_PIN_GSIM_nURST, + MFP_PIN_PMIC_INT, + MFP_PIN_RDY, + + /* additional pins on MMP2 */ + MFP_PIN_TWSI1_SCL, + MFP_PIN_TWSI1_SDA, + MFP_PIN_TWSI4_SCL, + MFP_PIN_TWSI4_SDA, + MFP_PIN_CLK_REQ, + + MFP_PIN_MAX, +}; + +/* + * a possible MFP configuration is represented by a 32-bit integer + * + * bit 0.. 9 - MFP Pin Number (1024 Pins Maximum) + * bit 10..12 - Alternate Function Selection + * bit 13..15 - Drive Strength + * bit 16..18 - Low Power Mode State + * bit 19..20 - Low Power Mode Edge Detection + * bit 21..22 - Run Mode Pull State + * + * to facilitate the definition, the following macros are provided + * + * MFP_CFG_DEFAULT - default MFP configuration value, with + * alternate function = 0, + * drive strength = fast 3mA (MFP_DS03X) + * low power mode = default + * edge detection = none + * + * MFP_CFG - default MFPR value with alternate function + * MFP_CFG_DRV - default MFPR value with alternate function and + * pin drive strength + * MFP_CFG_LPM - default MFPR value with alternate function and + * low power mode + * MFP_CFG_X - default MFPR value with alternate function, + * pin drive strength and low power mode + */ + +typedef unsigned long mfp_cfg_t; + +#define MFP_PIN(x) ((x) & 0x3ff) + +#define MFP_AF0 (0x0 << 10) +#define MFP_AF1 (0x1 << 10) +#define MFP_AF2 (0x2 << 10) +#define MFP_AF3 (0x3 << 10) +#define MFP_AF4 (0x4 << 10) +#define MFP_AF5 (0x5 << 10) +#define MFP_AF6 (0x6 << 10) +#define MFP_AF7 (0x7 << 10) +#define MFP_AF_MASK (0x7 << 10) +#define MFP_AF(x) (((x) >> 10) & 0x7) + +#define MFP_DS01X (0x0 << 13) +#define MFP_DS02X (0x1 << 13) +#define MFP_DS03X (0x2 << 13) +#define MFP_DS04X (0x3 << 13) +#define MFP_DS06X (0x4 << 13) +#define MFP_DS08X (0x5 << 13) +#define MFP_DS10X (0x6 << 13) +#define MFP_DS13X (0x7 << 13) +#define MFP_DS_MASK (0x7 << 13) +#define MFP_DS(x) (((x) >> 13) & 0x7) + +#define MFP_LPM_DEFAULT (0x0 << 16) +#define MFP_LPM_DRIVE_LOW (0x1 << 16) +#define MFP_LPM_DRIVE_HIGH (0x2 << 16) +#define MFP_LPM_PULL_LOW (0x3 << 16) +#define MFP_LPM_PULL_HIGH (0x4 << 16) +#define MFP_LPM_FLOAT (0x5 << 16) +#define MFP_LPM_INPUT (0x6 << 16) +#define MFP_LPM_STATE_MASK (0x7 << 16) +#define MFP_LPM_STATE(x) (((x) >> 16) & 0x7) + +#define MFP_LPM_EDGE_NONE (0x0 << 19) +#define MFP_LPM_EDGE_RISE (0x1 << 19) +#define MFP_LPM_EDGE_FALL (0x2 << 19) +#define MFP_LPM_EDGE_BOTH (0x3 << 19) +#define MFP_LPM_EDGE_MASK (0x3 << 19) +#define MFP_LPM_EDGE(x) (((x) >> 19) & 0x3) + +#define MFP_PULL_NONE (0x0 << 21) +#define MFP_PULL_LOW (0x1 << 21) +#define MFP_PULL_HIGH (0x2 << 21) +#define MFP_PULL_BOTH (0x3 << 21) +#define MFP_PULL_FLOAT (0x4 << 21) +#define MFP_PULL_MASK (0x7 << 21) +#define MFP_PULL(x) (((x) >> 21) & 0x7) + +#define MFP_CFG_DEFAULT (MFP_AF0 | MFP_DS03X | MFP_LPM_DEFAULT |\ + MFP_LPM_EDGE_NONE | MFP_PULL_NONE) + +#define MFP_CFG(pin, af) \ + ((MFP_CFG_DEFAULT & ~MFP_AF_MASK) |\ + (MFP_PIN(MFP_PIN_##pin) | MFP_##af)) + +#define MFP_CFG_DRV(pin, af, drv) \ + ((MFP_CFG_DEFAULT & ~(MFP_AF_MASK | MFP_DS_MASK)) |\ + (MFP_PIN(MFP_PIN_##pin) | MFP_##af | MFP_##drv)) + +#define MFP_CFG_LPM(pin, af, lpm) \ + ((MFP_CFG_DEFAULT & ~(MFP_AF_MASK | MFP_LPM_STATE_MASK)) |\ + (MFP_PIN(MFP_PIN_##pin) | MFP_##af | MFP_LPM_##lpm)) + +#define MFP_CFG_X(pin, af, drv, lpm) \ + ((MFP_CFG_DEFAULT & ~(MFP_AF_MASK | MFP_DS_MASK | MFP_LPM_STATE_MASK)) |\ + (MFP_PIN(MFP_PIN_##pin) | MFP_##af | MFP_##drv | MFP_LPM_##lpm)) + +#if defined(CONFIG_PXA3xx) || defined(CONFIG_ARCH_MMP) +/* + * each MFP pin will have a MFPR register, since the offset of the + * register varies between processors, the processor specific code + * should initialize the pin offsets by mfp_init() + * + * mfp_init_base() - accepts a virtual base for all MFPR registers and + * initialize the MFP table to a default state + * + * mfp_init_addr() - accepts a table of "mfp_addr_map" structure, which + * represents a range of MFP pins from "start" to "end", with the offset + * beginning at "offset", to define a single pin, let "end" = -1. + * + * use + * + * MFP_ADDR_X() to define a range of pins + * MFP_ADDR() to define a single pin + * MFP_ADDR_END to signal the end of pin offset definitions + */ +struct mfp_addr_map { + unsigned int start; + unsigned int end; + unsigned long offset; +}; + +#define MFP_ADDR_X(start, end, offset) \ + { MFP_PIN_##start, MFP_PIN_##end, offset } + +#define MFP_ADDR(pin, offset) \ + { MFP_PIN_##pin, -1, offset } + +#define MFP_ADDR_END { MFP_PIN_INVALID, 0 } + +void mfp_init_base(void __iomem *mfpr_base); +void mfp_init_addr(struct mfp_addr_map *map); + +/* + * mfp_{read, write}() - for direct read/write access to the MFPR register + * mfp_config() - for configuring a group of MFPR registers + * mfp_config_lpm() - configuring all low power MFPR registers for suspend + * mfp_config_run() - configuring all run time MFPR registers after resume + */ +unsigned long mfp_read(int mfp); +void mfp_write(int mfp, unsigned long mfpr_val); +void mfp_config(unsigned long *mfp_cfgs, int num); +void mfp_config_run(void); +void mfp_config_lpm(void); +#endif /* CONFIG_PXA3xx || CONFIG_ARCH_MMP */ + +#endif /* __ASM_PLAT_MFP_H */ diff --git a/include/linux/soc/pxa/smemc.h b/include/linux/soc/pxa/smemc.h new file mode 100644 index 000000000000..f1ffea236c15 --- /dev/null +++ b/include/linux/soc/pxa/smemc.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef __PXA_REGS_H +#define __PXA_REGS_H + +#include <linux/types.h> + +void pxa_smemc_set_pcmcia_timing(int sock, u32 mcmem, u32 mcatt, u32 mcio); +void pxa_smemc_set_pcmcia_socket(int nr); +int pxa2xx_smemc_get_sdram_rows(void); +unsigned int pxa3xx_smemc_get_memclkdiv(void); +void __iomem *pxa_smemc_get_mdrefr(void); + +#endif diff --git a/include/linux/soc/qcom/llcc-qcom.h b/include/linux/soc/qcom/llcc-qcom.h index 9e8fd92c96b7..bc2fb8343a94 100644 --- a/include/linux/soc/qcom/llcc-qcom.h +++ b/include/linux/soc/qcom/llcc-qcom.h @@ -29,13 +29,20 @@ #define LLCC_AUDHW 22 #define LLCC_NPU 23 #define LLCC_WLHW 24 +#define LLCC_PIMEM 25 +#define LLCC_DRE 26 #define LLCC_CVP 28 #define LLCC_MODPE 29 #define LLCC_APTCM 30 #define LLCC_WRCACHE 31 #define LLCC_CVPFW 32 #define LLCC_CPUSS1 33 +#define LLCC_CAMEXP0 34 +#define LLCC_CPUMTE 35 #define LLCC_CPUHWT 36 +#define LLCC_MDMCLAD2 37 +#define LLCC_CAMEXP1 38 +#define LLCC_AENPU 45 /** * struct llcc_slice_desc - Cache slice descriptor @@ -71,11 +78,40 @@ struct llcc_edac_reg_data { u8 ways_shift; }; +struct llcc_edac_reg_offset { + /* LLCC TRP registers */ + u32 trp_ecc_error_status0; + u32 trp_ecc_error_status1; + u32 trp_ecc_sb_err_syn0; + u32 trp_ecc_db_err_syn0; + u32 trp_ecc_error_cntr_clear; + u32 trp_interrupt_0_status; + u32 trp_interrupt_0_clear; + u32 trp_interrupt_0_enable; + + /* LLCC Common registers */ + u32 cmn_status0; + u32 cmn_interrupt_0_enable; + u32 cmn_interrupt_2_enable; + + /* LLCC DRP registers */ + u32 drp_ecc_error_cfg; + u32 drp_ecc_error_cntr_clear; + u32 drp_interrupt_status; + u32 drp_interrupt_clear; + u32 drp_interrupt_enable; + u32 drp_ecc_error_status0; + u32 drp_ecc_error_status1; + u32 drp_ecc_sb_err_syn0; + u32 drp_ecc_db_err_syn0; +}; + /** * struct llcc_drv_data - Data associated with the llcc driver * @regmap: regmap associated with the llcc device * @bcast_regmap: regmap associated with llcc broadcast offset * @cfg: pointer to the data structure for slice configuration + * @edac_reg_offset: Offset of the LLCC EDAC registers * @lock: mutex associated with each slice * @cfg_size: size of the config data table * @max_slices: max slices as read from device tree @@ -83,12 +119,13 @@ struct llcc_edac_reg_data { * @bitmap: Bit map to track the active slice ids * @offsets: Pointer to the bank offsets array * @ecc_irq: interrupt for llcc cache error detection and reporting - * @major_version: Indicates the LLCC major version + * @version: Indicates the LLCC version */ struct llcc_drv_data { struct regmap *regmap; struct regmap *bcast_regmap; const struct llcc_slice_config *cfg; + const struct llcc_edac_reg_offset *edac_reg_offset; struct mutex lock; u32 cfg_size; u32 max_slices; @@ -96,7 +133,7 @@ struct llcc_drv_data { unsigned long *bitmap; u32 *offsets; int ecc_irq; - u32 major_version; + u32 version; }; #if IS_ENABLED(CONFIG_QCOM_LLCC) diff --git a/include/linux/soc/qcom/mdt_loader.h b/include/linux/soc/qcom/mdt_loader.h index afd47217996b..9e8e60421192 100644 --- a/include/linux/soc/qcom/mdt_loader.h +++ b/include/linux/soc/qcom/mdt_loader.h @@ -10,10 +10,14 @@ struct device; struct firmware; +struct qcom_scm_pas_metadata; #if IS_ENABLED(CONFIG_QCOM_MDT_LOADER) ssize_t qcom_mdt_get_size(const struct firmware *fw); +int qcom_mdt_pas_init(struct device *dev, const struct firmware *fw, + const char *fw_name, int pas_id, phys_addr_t mem_phys, + struct qcom_scm_pas_metadata *pas_metadata_ctx); int qcom_mdt_load(struct device *dev, const struct firmware *fw, const char *fw_name, int pas_id, void *mem_region, phys_addr_t mem_phys, size_t mem_size, @@ -23,7 +27,8 @@ int qcom_mdt_load_no_init(struct device *dev, const struct firmware *fw, const char *fw_name, int pas_id, void *mem_region, phys_addr_t mem_phys, size_t mem_size, phys_addr_t *reloc_base); -void *qcom_mdt_read_metadata(const struct firmware *fw, size_t *data_len); +void *qcom_mdt_read_metadata(const struct firmware *fw, size_t *data_len, + const char *fw_name, struct device *dev); #else /* !IS_ENABLED(CONFIG_QCOM_MDT_LOADER) */ @@ -32,6 +37,13 @@ static inline ssize_t qcom_mdt_get_size(const struct firmware *fw) return -ENODEV; } +static inline int qcom_mdt_pas_init(struct device *dev, const struct firmware *fw, + const char *fw_name, int pas_id, phys_addr_t mem_phys, + struct qcom_scm_pas_metadata *pas_metadata_ctx) +{ + return -ENODEV; +} + static inline int qcom_mdt_load(struct device *dev, const struct firmware *fw, const char *fw_name, int pas_id, void *mem_region, phys_addr_t mem_phys, @@ -51,7 +63,8 @@ static inline int qcom_mdt_load_no_init(struct device *dev, } static inline void *qcom_mdt_read_metadata(const struct firmware *fw, - size_t *data_len) + size_t *data_len, const char *fw_name, + struct device *dev) { return ERR_PTR(-ENODEV); } diff --git a/include/linux/soc/qcom/qmi.h b/include/linux/soc/qcom/qmi.h index b1f80e756d2a..469e02d2aa0d 100644 --- a/include/linux/soc/qcom/qmi.h +++ b/include/linux/soc/qcom/qmi.h @@ -75,7 +75,7 @@ struct qmi_elem_info { enum qmi_array_type array_type; u8 tlv_type; u32 offset; - struct qmi_elem_info *ei_array; + const struct qmi_elem_info *ei_array; }; #define QMI_RESULT_SUCCESS_V01 0 @@ -102,7 +102,7 @@ struct qmi_response_type_v01 { u16 error; }; -extern struct qmi_elem_info qmi_response_type_v01_ei[]; +extern const struct qmi_elem_info qmi_response_type_v01_ei[]; /** * struct qmi_service - context to track lookup-results @@ -173,7 +173,7 @@ struct qmi_txn { struct completion completion; int result; - struct qmi_elem_info *ei; + const struct qmi_elem_info *ei; void *dest; }; @@ -189,7 +189,7 @@ struct qmi_msg_handler { unsigned int type; unsigned int msg_id; - struct qmi_elem_info *ei; + const struct qmi_elem_info *ei; size_t decoded_size; void (*fn)(struct qmi_handle *qmi, struct sockaddr_qrtr *sq, @@ -249,23 +249,23 @@ void qmi_handle_release(struct qmi_handle *qmi); ssize_t qmi_send_request(struct qmi_handle *qmi, struct sockaddr_qrtr *sq, struct qmi_txn *txn, int msg_id, size_t len, - struct qmi_elem_info *ei, const void *c_struct); + const struct qmi_elem_info *ei, const void *c_struct); ssize_t qmi_send_response(struct qmi_handle *qmi, struct sockaddr_qrtr *sq, struct qmi_txn *txn, int msg_id, size_t len, - struct qmi_elem_info *ei, const void *c_struct); + const struct qmi_elem_info *ei, const void *c_struct); ssize_t qmi_send_indication(struct qmi_handle *qmi, struct sockaddr_qrtr *sq, - int msg_id, size_t len, struct qmi_elem_info *ei, + int msg_id, size_t len, const struct qmi_elem_info *ei, const void *c_struct); void *qmi_encode_message(int type, unsigned int msg_id, size_t *len, - unsigned int txn_id, struct qmi_elem_info *ei, + unsigned int txn_id, const struct qmi_elem_info *ei, const void *c_struct); int qmi_decode_message(const void *buf, size_t len, - struct qmi_elem_info *ei, void *c_struct); + const struct qmi_elem_info *ei, void *c_struct); int qmi_txn_init(struct qmi_handle *qmi, struct qmi_txn *txn, - struct qmi_elem_info *ei, void *c_struct); + const struct qmi_elem_info *ei, void *c_struct); int qmi_txn_wait(struct qmi_txn *txn, unsigned long timeout); void qmi_txn_cancel(struct qmi_txn *txn); diff --git a/include/linux/soc/qcom/smd-rpm.h b/include/linux/soc/qcom/smd-rpm.h index 860dd8cdf9f3..3ab8c07f71c0 100644 --- a/include/linux/soc/qcom/smd-rpm.h +++ b/include/linux/soc/qcom/smd-rpm.h @@ -40,6 +40,8 @@ struct qcom_smd_rpm; #define QCOM_SMD_RPM_AGGR_CLK 0x72676761 #define QCOM_SMD_RPM_HWKM_CLK 0x6d6b7768 #define QCOM_SMD_RPM_PKA_CLK 0x616b70 +#define QCOM_SMD_RPM_MCFG_CLK 0x6766636d +#define QCOM_SMD_RPM_MMXI_CLK 0x69786d6d int qcom_rpm_smd_write(struct qcom_smd_rpm *rpm, int state, diff --git a/include/linux/soc/renesas/r9a06g032-sysctrl.h b/include/linux/soc/renesas/r9a06g032-sysctrl.h new file mode 100644 index 000000000000..066dfb15cbdd --- /dev/null +++ b/include/linux/soc/renesas/r9a06g032-sysctrl.h @@ -0,0 +1,11 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LINUX_SOC_RENESAS_R9A06G032_SYSCTRL_H__ +#define __LINUX_SOC_RENESAS_R9A06G032_SYSCTRL_H__ + +#ifdef CONFIG_CLK_R9A06G032 +int r9a06g032_sysctrl_set_dmamux(u32 mask, u32 val); +#else +static inline int r9a06g032_sysctrl_set_dmamux(u32 mask, u32 val) { return -ENODEV; } +#endif + +#endif /* __LINUX_SOC_RENESAS_R9A06G032_SYSCTRL_H__ */ diff --git a/include/linux/soc/sunxi/sunxi_sram.h b/include/linux/soc/sunxi/sunxi_sram.h index c5f663bba9c2..60e274d1b821 100644 --- a/include/linux/soc/sunxi/sunxi_sram.h +++ b/include/linux/soc/sunxi/sunxi_sram.h @@ -14,6 +14,6 @@ #define _SUNXI_SRAM_H_ int sunxi_sram_claim(struct device *dev); -int sunxi_sram_release(struct device *dev); +void sunxi_sram_release(struct device *dev); #endif /* _SUNXI_SRAM_H_ */ diff --git a/include/linux/soc/ti/knav_dma.h b/include/linux/soc/ti/knav_dma.h index 7127ec301537..18d806a8e52c 100644 --- a/include/linux/soc/ti/knav_dma.h +++ b/include/linux/soc/ti/knav_dma.h @@ -1,17 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2014 Texas Instruments Incorporated * Authors: Sandeep Nair <sandeep_n@ti.com * Cyril Chemparathy <cyril@ti.com Santosh Shilimkar <santosh.shilimkar@ti.com> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation version 2. - * - * This program is distributed "as is" WITHOUT ANY WARRANTY of any - * kind, whether express or implied; without even the implied warranty - * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. */ #ifndef __SOC_TI_KEYSTONE_NAVIGATOR_DMA_H__ diff --git a/include/linux/soc/ti/knav_qmss.h b/include/linux/soc/ti/knav_qmss.h index c75ef99c99ca..175f466ebcc3 100644 --- a/include/linux/soc/ti/knav_qmss.h +++ b/include/linux/soc/ti/knav_qmss.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * Keystone Navigator Queue Management Sub-System header * @@ -5,15 +6,6 @@ * Author: Sandeep Nair <sandeep_n@ti.com> * Cyril Chemparathy <cyril@ti.com> * Santosh Shilimkar <santosh.shilimkar@ti.com> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation version 2. - * - * This program is distributed "as is" WITHOUT ANY WARRANTY of any - * kind, whether express or implied; without even the implied warranty - * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. */ #ifndef __SOC_TI_KNAV_QMSS_H__ diff --git a/include/linux/soc/ti/omap1-io.h b/include/linux/soc/ti/omap1-io.h new file mode 100644 index 000000000000..f7f12728d4a6 --- /dev/null +++ b/include/linux/soc/ti/omap1-io.h @@ -0,0 +1,143 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef __ASM_ARCH_OMAP_IO_H +#define __ASM_ARCH_OMAP_IO_H + +#ifndef __ASSEMBLER__ +#include <linux/types.h> + +#ifdef CONFIG_ARCH_OMAP1_ANY +/* + * NOTE: Please use ioremap + __raw_read/write where possible instead of these + */ +extern u8 omap_readb(u32 pa); +extern u16 omap_readw(u32 pa); +extern u32 omap_readl(u32 pa); +extern void omap_writeb(u8 v, u32 pa); +extern void omap_writew(u16 v, u32 pa); +extern void omap_writel(u32 v, u32 pa); +#else +static inline u8 omap_readb(u32 pa) { return 0; } +static inline u16 omap_readw(u32 pa) { return 0; } +static inline u32 omap_readl(u32 pa) { return 0; } +static inline void omap_writeb(u8 v, u32 pa) { } +static inline void omap_writew(u16 v, u32 pa) { } +static inline void omap_writel(u32 v, u32 pa) { } +#endif +#endif + +/* + * ---------------------------------------------------------------------------- + * System control registers + * ---------------------------------------------------------------------------- + */ +#define MOD_CONF_CTRL_0 0xfffe1080 +#define MOD_CONF_CTRL_1 0xfffe1110 + +/* + * --------------------------------------------------------------------------- + * UPLD + * --------------------------------------------------------------------------- + */ +#define ULPD_REG_BASE (0xfffe0800) +#define ULPD_IT_STATUS (ULPD_REG_BASE + 0x14) +#define ULPD_SETUP_ANALOG_CELL_3 (ULPD_REG_BASE + 0x24) +#define ULPD_CLOCK_CTRL (ULPD_REG_BASE + 0x30) +# define DIS_USB_PVCI_CLK (1 << 5) /* no USB/FAC synch */ +# define USB_MCLK_EN (1 << 4) /* enable W4_USB_CLKO */ +#define ULPD_SOFT_REQ (ULPD_REG_BASE + 0x34) +# define SOFT_UDC_REQ (1 << 4) +# define SOFT_USB_CLK_REQ (1 << 3) +# define SOFT_DPLL_REQ (1 << 0) +#define ULPD_DPLL_CTRL (ULPD_REG_BASE + 0x3c) +#define ULPD_STATUS_REQ (ULPD_REG_BASE + 0x40) +#define ULPD_APLL_CTRL (ULPD_REG_BASE + 0x4c) +#define ULPD_POWER_CTRL (ULPD_REG_BASE + 0x50) +#define ULPD_SOFT_DISABLE_REQ_REG (ULPD_REG_BASE + 0x68) +# define DIS_MMC2_DPLL_REQ (1 << 11) +# define DIS_MMC1_DPLL_REQ (1 << 10) +# define DIS_UART3_DPLL_REQ (1 << 9) +# define DIS_UART2_DPLL_REQ (1 << 8) +# define DIS_UART1_DPLL_REQ (1 << 7) +# define DIS_USB_HOST_DPLL_REQ (1 << 6) +#define ULPD_SDW_CLK_DIV_CTRL_SEL (ULPD_REG_BASE + 0x74) +#define ULPD_CAM_CLK_CTRL (ULPD_REG_BASE + 0x7c) + +/* + * ---------------------------------------------------------------------------- + * Clocks + * ---------------------------------------------------------------------------- + */ +#define CLKGEN_REG_BASE (0xfffece00) +#define ARM_CKCTL (CLKGEN_REG_BASE + 0x0) +#define ARM_IDLECT1 (CLKGEN_REG_BASE + 0x4) +#define ARM_IDLECT2 (CLKGEN_REG_BASE + 0x8) +#define ARM_EWUPCT (CLKGEN_REG_BASE + 0xC) +#define ARM_RSTCT1 (CLKGEN_REG_BASE + 0x10) +#define ARM_RSTCT2 (CLKGEN_REG_BASE + 0x14) +#define ARM_SYSST (CLKGEN_REG_BASE + 0x18) +#define ARM_IDLECT3 (CLKGEN_REG_BASE + 0x24) + +#define CK_RATEF 1 +#define CK_IDLEF 2 +#define CK_ENABLEF 4 +#define CK_SELECTF 8 +#define SETARM_IDLE_SHIFT + +/* DPLL control registers */ +#define DPLL_CTL (0xfffecf00) + +/* DSP clock control. Must use __raw_readw() and __raw_writew() with these */ +#define DSP_CONFIG_REG_BASE IOMEM(0xe1008000) +#define DSP_CKCTL (DSP_CONFIG_REG_BASE + 0x0) +#define DSP_IDLECT1 (DSP_CONFIG_REG_BASE + 0x4) +#define DSP_IDLECT2 (DSP_CONFIG_REG_BASE + 0x8) +#define DSP_RSTCT2 (DSP_CONFIG_REG_BASE + 0x14) + +/* + * ---------------------------------------------------------------------------- + * Pulse-Width Light + * ---------------------------------------------------------------------------- + */ +#define OMAP_PWL_BASE 0xfffb5800 +#define OMAP_PWL_ENABLE (OMAP_PWL_BASE + 0x00) +#define OMAP_PWL_CLK_ENABLE (OMAP_PWL_BASE + 0x04) + +/* + * ---------------------------------------------------------------------------- + * Pin multiplexing registers + * ---------------------------------------------------------------------------- + */ +#define FUNC_MUX_CTRL_0 0xfffe1000 +#define FUNC_MUX_CTRL_1 0xfffe1004 +#define FUNC_MUX_CTRL_2 0xfffe1008 +#define COMP_MODE_CTRL_0 0xfffe100c +#define FUNC_MUX_CTRL_3 0xfffe1010 +#define FUNC_MUX_CTRL_4 0xfffe1014 +#define FUNC_MUX_CTRL_5 0xfffe1018 +#define FUNC_MUX_CTRL_6 0xfffe101C +#define FUNC_MUX_CTRL_7 0xfffe1020 +#define FUNC_MUX_CTRL_8 0xfffe1024 +#define FUNC_MUX_CTRL_9 0xfffe1028 +#define FUNC_MUX_CTRL_A 0xfffe102C +#define FUNC_MUX_CTRL_B 0xfffe1030 +#define FUNC_MUX_CTRL_C 0xfffe1034 +#define FUNC_MUX_CTRL_D 0xfffe1038 +#define PULL_DWN_CTRL_0 0xfffe1040 +#define PULL_DWN_CTRL_1 0xfffe1044 +#define PULL_DWN_CTRL_2 0xfffe1048 +#define PULL_DWN_CTRL_3 0xfffe104c +#define PULL_DWN_CTRL_4 0xfffe10ac + +/* OMAP-1610 specific multiplexing registers */ +#define FUNC_MUX_CTRL_E 0xfffe1090 +#define FUNC_MUX_CTRL_F 0xfffe1094 +#define FUNC_MUX_CTRL_10 0xfffe1098 +#define FUNC_MUX_CTRL_11 0xfffe109c +#define FUNC_MUX_CTRL_12 0xfffe10a0 +#define PU_PD_SEL_0 0xfffe10b4 +#define PU_PD_SEL_1 0xfffe10b8 +#define PU_PD_SEL_2 0xfffe10bc +#define PU_PD_SEL_3 0xfffe10c0 +#define PU_PD_SEL_4 0xfffe10c4 + +#endif diff --git a/include/linux/soc/ti/omap1-mux.h b/include/linux/soc/ti/omap1-mux.h new file mode 100644 index 000000000000..59c239b5569c --- /dev/null +++ b/include/linux/soc/ti/omap1-mux.h @@ -0,0 +1,311 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef __SOC_TI_OMAP1_MUX_H +#define __SOC_TI_OMAP1_MUX_H +/* + * This should not really be a global header, it reflects the + * traditional way that omap1 does pin muxing without the + * pinctrl subsystem. + */ + +enum omap7xx_index { + /* OMAP 730 keyboard */ + E2_7XX_KBR0, + J7_7XX_KBR1, + E1_7XX_KBR2, + F3_7XX_KBR3, + D2_7XX_KBR4, + C2_7XX_KBC0, + D3_7XX_KBC1, + E4_7XX_KBC2, + F4_7XX_KBC3, + E3_7XX_KBC4, + + /* USB */ + AA17_7XX_USB_DM, + W16_7XX_USB_PU_EN, + W17_7XX_USB_VBUSI, + W18_7XX_USB_DMCK_OUT, + W19_7XX_USB_DCRST, + + /* MMC */ + MMC_7XX_CMD, + MMC_7XX_CLK, + MMC_7XX_DAT0, + + /* I2C */ + I2C_7XX_SCL, + I2C_7XX_SDA, + + /* SPI */ + SPI_7XX_1, + SPI_7XX_2, + SPI_7XX_3, + SPI_7XX_4, + SPI_7XX_5, + SPI_7XX_6, + + /* UART */ + UART_7XX_1, + UART_7XX_2, +}; + +enum omap1xxx_index { + /* UART1 (BT_UART_GATING)*/ + UART1_TX = 0, + UART1_RTS, + + /* UART2 (COM_UART_GATING)*/ + UART2_TX, + UART2_RX, + UART2_CTS, + UART2_RTS, + + /* UART3 (GIGA_UART_GATING) */ + UART3_TX, + UART3_RX, + UART3_CTS, + UART3_RTS, + UART3_CLKREQ, + UART3_BCLK, /* 12MHz clock out */ + Y15_1610_UART3_RTS, + + /* PWT & PWL */ + PWT, + PWL, + + /* USB master generic */ + R18_USB_VBUS, + R18_1510_USB_GPIO0, + W4_USB_PUEN, + W4_USB_CLKO, + W4_USB_HIGHZ, + W4_GPIO58, + + /* USB1 master */ + USB1_SUSP, + USB1_SEO, + W13_1610_USB1_SE0, + USB1_TXEN, + USB1_TXD, + USB1_VP, + USB1_VM, + USB1_RCV, + USB1_SPEED, + R13_1610_USB1_SPEED, + R13_1710_USB1_SE0, + + /* USB2 master */ + USB2_SUSP, + USB2_VP, + USB2_TXEN, + USB2_VM, + USB2_RCV, + USB2_SEO, + USB2_TXD, + + /* OMAP-1510 GPIO */ + R18_1510_GPIO0, + R19_1510_GPIO1, + M14_1510_GPIO2, + + /* OMAP1610 GPIO */ + P18_1610_GPIO3, + Y15_1610_GPIO17, + + /* OMAP-1710 GPIO */ + R18_1710_GPIO0, + V2_1710_GPIO10, + N21_1710_GPIO14, + W15_1710_GPIO40, + + /* MPUIO */ + MPUIO2, + N15_1610_MPUIO2, + MPUIO4, + MPUIO5, + T20_1610_MPUIO5, + W11_1610_MPUIO6, + V10_1610_MPUIO7, + W11_1610_MPUIO9, + V10_1610_MPUIO10, + W10_1610_MPUIO11, + E20_1610_MPUIO13, + U20_1610_MPUIO14, + E19_1610_MPUIO15, + + /* MCBSP2 */ + MCBSP2_CLKR, + MCBSP2_CLKX, + MCBSP2_DR, + MCBSP2_DX, + MCBSP2_FSR, + MCBSP2_FSX, + + /* MCBSP3 */ + MCBSP3_CLKX, + + /* Misc ballouts */ + BALLOUT_V8_ARMIO3, + N20_HDQ, + + /* OMAP-1610 MMC2 */ + W8_1610_MMC2_DAT0, + V8_1610_MMC2_DAT1, + W15_1610_MMC2_DAT2, + R10_1610_MMC2_DAT3, + Y10_1610_MMC2_CLK, + Y8_1610_MMC2_CMD, + V9_1610_MMC2_CMDDIR, + V5_1610_MMC2_DATDIR0, + W19_1610_MMC2_DATDIR1, + R18_1610_MMC2_CLKIN, + + /* OMAP-1610 External Trace Interface */ + M19_1610_ETM_PSTAT0, + L15_1610_ETM_PSTAT1, + L18_1610_ETM_PSTAT2, + L19_1610_ETM_D0, + J19_1610_ETM_D6, + J18_1610_ETM_D7, + + /* OMAP16XX GPIO */ + P20_1610_GPIO4, + V9_1610_GPIO7, + W8_1610_GPIO9, + N20_1610_GPIO11, + N19_1610_GPIO13, + P10_1610_GPIO22, + V5_1610_GPIO24, + AA20_1610_GPIO_41, + W19_1610_GPIO48, + M7_1610_GPIO62, + V14_16XX_GPIO37, + R9_16XX_GPIO18, + L14_16XX_GPIO49, + + /* OMAP-1610 uWire */ + V19_1610_UWIRE_SCLK, + U18_1610_UWIRE_SDI, + W21_1610_UWIRE_SDO, + N14_1610_UWIRE_CS0, + P15_1610_UWIRE_CS3, + N15_1610_UWIRE_CS1, + + /* OMAP-1610 SPI */ + U19_1610_SPIF_SCK, + U18_1610_SPIF_DIN, + P20_1610_SPIF_DIN, + W21_1610_SPIF_DOUT, + R18_1610_SPIF_DOUT, + N14_1610_SPIF_CS0, + N15_1610_SPIF_CS1, + T19_1610_SPIF_CS2, + P15_1610_SPIF_CS3, + + /* OMAP-1610 Flash */ + L3_1610_FLASH_CS2B_OE, + M8_1610_FLASH_CS2B_WE, + + /* First MMC */ + MMC_CMD, + MMC_DAT1, + MMC_DAT2, + MMC_DAT0, + MMC_CLK, + MMC_DAT3, + + /* OMAP-1710 MMC CMDDIR and DATDIR0 */ + M15_1710_MMC_CLKI, + P19_1710_MMC_CMDDIR, + P20_1710_MMC_DATDIR0, + + /* OMAP-1610 USB0 alternate pin configuration */ + W9_USB0_TXEN, + AA9_USB0_VP, + Y5_USB0_RCV, + R9_USB0_VM, + V6_USB0_TXD, + W5_USB0_SE0, + V9_USB0_SPEED, + V9_USB0_SUSP, + + /* USB2 */ + W9_USB2_TXEN, + AA9_USB2_VP, + Y5_USB2_RCV, + R9_USB2_VM, + V6_USB2_TXD, + W5_USB2_SE0, + + /* 16XX UART */ + R13_1610_UART1_TX, + V14_16XX_UART1_RX, + R14_1610_UART1_CTS, + AA15_1610_UART1_RTS, + R9_16XX_UART2_RX, + L14_16XX_UART3_RX, + + /* I2C OMAP-1610 */ + I2C_SCL, + I2C_SDA, + + /* Keypad */ + F18_1610_KBC0, + D20_1610_KBC1, + D19_1610_KBC2, + E18_1610_KBC3, + C21_1610_KBC4, + G18_1610_KBR0, + F19_1610_KBR1, + H14_1610_KBR2, + E20_1610_KBR3, + E19_1610_KBR4, + N19_1610_KBR5, + + /* Power management */ + T20_1610_LOW_PWR, + + /* MCLK Settings */ + V5_1710_MCLK_ON, + V5_1710_MCLK_OFF, + R10_1610_MCLK_ON, + R10_1610_MCLK_OFF, + + /* CompactFlash controller */ + P11_1610_CF_CD2, + R11_1610_CF_IOIS16, + V10_1610_CF_IREQ, + W10_1610_CF_RESET, + W11_1610_CF_CD1, + + /* parallel camera */ + J15_1610_CAM_LCLK, + J18_1610_CAM_D7, + J19_1610_CAM_D6, + J14_1610_CAM_D5, + K18_1610_CAM_D4, + K19_1610_CAM_D3, + K15_1610_CAM_D2, + K14_1610_CAM_D1, + L19_1610_CAM_D0, + L18_1610_CAM_VS, + L15_1610_CAM_HS, + M19_1610_CAM_RSTZ, + Y15_1610_CAM_OUTCLK, + + /* serial camera */ + H19_1610_CAM_EXCLK, + Y12_1610_CCP_CLKP, + W13_1610_CCP_CLKM, + W14_1610_CCP_DATAP, + Y14_1610_CCP_DATAM, + +}; + +#ifdef CONFIG_OMAP_MUX +extern int omap_cfg_reg(unsigned long reg_cfg); +#else +static inline int omap_cfg_reg(unsigned long reg_cfg) { return 0; } +#endif + +#endif diff --git a/include/linux/soc/ti/omap1-soc.h b/include/linux/soc/ti/omap1-soc.h new file mode 100644 index 000000000000..81008d400bb6 --- /dev/null +++ b/include/linux/soc/ti/omap1-soc.h @@ -0,0 +1,198 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * OMAP cpu type detection + * + * Copyright (C) 2004, 2008 Nokia Corporation + * + * Copyright (C) 2009-11 Texas Instruments. + * + * Written by Tony Lindgren <tony.lindgren@nokia.com> + * + * Added OMAP4/5 specific defines - Santosh Shilimkar<santosh.shilimkar@ti.com> + */ + +#ifndef __ASM_ARCH_OMAP_CPU_H +#define __ASM_ARCH_OMAP_CPU_H + +/* + * Test if multicore OMAP support is needed + */ +#undef MULTI_OMAP1 +#undef OMAP_NAME + +#ifdef CONFIG_ARCH_OMAP730 +# ifdef OMAP_NAME +# undef MULTI_OMAP1 +# define MULTI_OMAP1 +# else +# define OMAP_NAME omap730 +# endif +#endif +#ifdef CONFIG_ARCH_OMAP850 +# ifdef OMAP_NAME +# undef MULTI_OMAP1 +# define MULTI_OMAP1 +# else +# define OMAP_NAME omap850 +# endif +#endif +#ifdef CONFIG_ARCH_OMAP15XX +# ifdef OMAP_NAME +# undef MULTI_OMAP1 +# define MULTI_OMAP1 +# else +# define OMAP_NAME omap1510 +# endif +#endif +#ifdef CONFIG_ARCH_OMAP16XX +# ifdef OMAP_NAME +# undef MULTI_OMAP1 +# define MULTI_OMAP1 +# else +# define OMAP_NAME omap16xx +# endif +#endif + +/* + * omap_rev bits: + * CPU id bits (0730, 1510, 1710, 2422...) [31:16] + * CPU revision (See _REV_ defined in cpu.h) [15:08] + * CPU class bits (15xx, 16xx, 24xx, 34xx...) [07:00] + */ +unsigned int omap_rev(void); + +/* + * Get the CPU revision for OMAP devices + */ +#define GET_OMAP_REVISION() ((omap_rev() >> 8) & 0xff) + +/* + * Macros to group OMAP into cpu classes. + * These can be used in most places. + * cpu_is_omap7xx(): True for OMAP730, OMAP850 + * cpu_is_omap15xx(): True for OMAP1510, OMAP5910 and OMAP310 + * cpu_is_omap16xx(): True for OMAP1610, OMAP5912 and OMAP1710 + */ +#define GET_OMAP_CLASS (omap_rev() & 0xff) + +#define IS_OMAP_CLASS(class, id) \ +static inline int is_omap ##class (void) \ +{ \ + return (GET_OMAP_CLASS == (id)) ? 1 : 0; \ +} + +#define GET_OMAP_SUBCLASS ((omap_rev() >> 20) & 0x0fff) + +#define IS_OMAP_SUBCLASS(subclass, id) \ +static inline int is_omap ##subclass (void) \ +{ \ + return (GET_OMAP_SUBCLASS == (id)) ? 1 : 0; \ +} + +IS_OMAP_CLASS(7xx, 0x07) +IS_OMAP_CLASS(15xx, 0x15) +IS_OMAP_CLASS(16xx, 0x16) + +#define cpu_is_omap7xx() 0 +#define cpu_is_omap15xx() 0 +#define cpu_is_omap16xx() 0 + +#if defined(MULTI_OMAP1) +# if defined(CONFIG_ARCH_OMAP730) +# undef cpu_is_omap7xx +# define cpu_is_omap7xx() is_omap7xx() +# endif +# if defined(CONFIG_ARCH_OMAP850) +# undef cpu_is_omap7xx +# define cpu_is_omap7xx() is_omap7xx() +# endif +# if defined(CONFIG_ARCH_OMAP15XX) +# undef cpu_is_omap15xx +# define cpu_is_omap15xx() is_omap15xx() +# endif +# if defined(CONFIG_ARCH_OMAP16XX) +# undef cpu_is_omap16xx +# define cpu_is_omap16xx() is_omap16xx() +# endif +#else +# if defined(CONFIG_ARCH_OMAP730) +# undef cpu_is_omap7xx +# define cpu_is_omap7xx() 1 +# endif +# if defined(CONFIG_ARCH_OMAP850) +# undef cpu_is_omap7xx +# define cpu_is_omap7xx() 1 +# endif +# if defined(CONFIG_ARCH_OMAP15XX) +# undef cpu_is_omap15xx +# define cpu_is_omap15xx() 1 +# endif +# if defined(CONFIG_ARCH_OMAP16XX) +# undef cpu_is_omap16xx +# define cpu_is_omap16xx() 1 +# endif +#endif + +/* + * Macros to detect individual cpu types. + * These are only rarely needed. + * cpu_is_omap310(): True for OMAP310 + * cpu_is_omap1510(): True for OMAP1510 + * cpu_is_omap1610(): True for OMAP1610 + * cpu_is_omap1611(): True for OMAP1611 + * cpu_is_omap5912(): True for OMAP5912 + * cpu_is_omap1621(): True for OMAP1621 + * cpu_is_omap1710(): True for OMAP1710 + */ +#define GET_OMAP_TYPE ((omap_rev() >> 16) & 0xffff) + +#define IS_OMAP_TYPE(type, id) \ +static inline int is_omap ##type (void) \ +{ \ + return (GET_OMAP_TYPE == (id)) ? 1 : 0; \ +} + +IS_OMAP_TYPE(310, 0x0310) +IS_OMAP_TYPE(1510, 0x1510) +IS_OMAP_TYPE(1610, 0x1610) +IS_OMAP_TYPE(1611, 0x1611) +IS_OMAP_TYPE(5912, 0x1611) +IS_OMAP_TYPE(1621, 0x1621) +IS_OMAP_TYPE(1710, 0x1710) + +#define cpu_is_omap310() 0 +#define cpu_is_omap1510() 0 +#define cpu_is_omap1610() 0 +#define cpu_is_omap5912() 0 +#define cpu_is_omap1611() 0 +#define cpu_is_omap1621() 0 +#define cpu_is_omap1710() 0 + +#define cpu_class_is_omap1() 1 + +/* + * Whether we have MULTI_OMAP1 or not, we still need to distinguish + * between 310 vs. 1510 and 1611B/5912 vs. 1710. + */ + +#if defined(CONFIG_ARCH_OMAP15XX) +# undef cpu_is_omap310 +# undef cpu_is_omap1510 +# define cpu_is_omap310() is_omap310() +# define cpu_is_omap1510() is_omap1510() +#endif + +#if defined(CONFIG_ARCH_OMAP16XX) +# undef cpu_is_omap1610 +# undef cpu_is_omap1611 +# undef cpu_is_omap5912 +# undef cpu_is_omap1621 +# undef cpu_is_omap1710 +# define cpu_is_omap1610() is_omap1610() +# define cpu_is_omap1611() is_omap1611() +# define cpu_is_omap5912() is_omap5912() +# define cpu_is_omap1621() is_omap1621() +# define cpu_is_omap1710() is_omap1710() +#endif + +#endif diff --git a/include/linux/soc/ti/omap1-usb.h b/include/linux/soc/ti/omap1-usb.h new file mode 100644 index 000000000000..67488698601a --- /dev/null +++ b/include/linux/soc/ti/omap1-usb.h @@ -0,0 +1,116 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __SOC_TI_OMAP1_USB +#define __SOC_TI_OMAP1_USB +/* + * Constants in this file are used all over the place, in platform + * code, as well as the udc, phy and ohci drivers. + * This is not a great design, but unlikely to get fixed after + * such a long time. Don't do this elsewhere. + */ + +#define OMAP1_OTG_BASE 0xfffb0400 +#define OMAP1_UDC_BASE 0xfffb4000 + +#define OMAP2_UDC_BASE 0x4805e200 +#define OMAP2_OTG_BASE 0x4805e300 +#define OTG_BASE OMAP1_OTG_BASE +#define UDC_BASE OMAP1_UDC_BASE + +/* + * OTG and transceiver registers, for OMAPs starting with ARM926 + */ +#define OTG_REV (OTG_BASE + 0x00) +#define OTG_SYSCON_1 (OTG_BASE + 0x04) +# define USB2_TRX_MODE(w) (((w)>>24)&0x07) +# define USB1_TRX_MODE(w) (((w)>>20)&0x07) +# define USB0_TRX_MODE(w) (((w)>>16)&0x07) +# define OTG_IDLE_EN (1 << 15) +# define HST_IDLE_EN (1 << 14) +# define DEV_IDLE_EN (1 << 13) +# define OTG_RESET_DONE (1 << 2) +# define OTG_SOFT_RESET (1 << 1) +#define OTG_SYSCON_2 (OTG_BASE + 0x08) +# define OTG_EN (1 << 31) +# define USBX_SYNCHRO (1 << 30) +# define OTG_MST16 (1 << 29) +# define SRP_GPDATA (1 << 28) +# define SRP_GPDVBUS (1 << 27) +# define SRP_GPUVBUS(w) (((w)>>24)&0x07) +# define A_WAIT_VRISE(w) (((w)>>20)&0x07) +# define B_ASE_BRST(w) (((w)>>16)&0x07) +# define SRP_DPW (1 << 14) +# define SRP_DATA (1 << 13) +# define SRP_VBUS (1 << 12) +# define OTG_PADEN (1 << 10) +# define HMC_PADEN (1 << 9) +# define UHOST_EN (1 << 8) +# define HMC_TLLSPEED (1 << 7) +# define HMC_TLLATTACH (1 << 6) +# define OTG_HMC(w) (((w)>>0)&0x3f) +#define OTG_CTRL (OTG_BASE + 0x0c) +# define OTG_USB2_EN (1 << 29) +# define OTG_USB2_DP (1 << 28) +# define OTG_USB2_DM (1 << 27) +# define OTG_USB1_EN (1 << 26) +# define OTG_USB1_DP (1 << 25) +# define OTG_USB1_DM (1 << 24) +# define OTG_USB0_EN (1 << 23) +# define OTG_USB0_DP (1 << 22) +# define OTG_USB0_DM (1 << 21) +# define OTG_ASESSVLD (1 << 20) +# define OTG_BSESSEND (1 << 19) +# define OTG_BSESSVLD (1 << 18) +# define OTG_VBUSVLD (1 << 17) +# define OTG_ID (1 << 16) +# define OTG_DRIVER_SEL (1 << 15) +# define OTG_A_SETB_HNPEN (1 << 12) +# define OTG_A_BUSREQ (1 << 11) +# define OTG_B_HNPEN (1 << 9) +# define OTG_B_BUSREQ (1 << 8) +# define OTG_BUSDROP (1 << 7) +# define OTG_PULLDOWN (1 << 5) +# define OTG_PULLUP (1 << 4) +# define OTG_DRV_VBUS (1 << 3) +# define OTG_PD_VBUS (1 << 2) +# define OTG_PU_VBUS (1 << 1) +# define OTG_PU_ID (1 << 0) +#define OTG_IRQ_EN (OTG_BASE + 0x10) /* 16-bit */ +# define DRIVER_SWITCH (1 << 15) +# define A_VBUS_ERR (1 << 13) +# define A_REQ_TMROUT (1 << 12) +# define A_SRP_DETECT (1 << 11) +# define B_HNP_FAIL (1 << 10) +# define B_SRP_TMROUT (1 << 9) +# define B_SRP_DONE (1 << 8) +# define B_SRP_STARTED (1 << 7) +# define OPRT_CHG (1 << 0) +#define OTG_IRQ_SRC (OTG_BASE + 0x14) /* 16-bit */ + // same bits as in IRQ_EN +#define OTG_OUTCTRL (OTG_BASE + 0x18) /* 16-bit */ +# define OTGVPD (1 << 14) +# define OTGVPU (1 << 13) +# define OTGPUID (1 << 12) +# define USB2VDR (1 << 10) +# define USB2PDEN (1 << 9) +# define USB2PUEN (1 << 8) +# define USB1VDR (1 << 6) +# define USB1PDEN (1 << 5) +# define USB1PUEN (1 << 4) +# define USB0VDR (1 << 2) +# define USB0PDEN (1 << 1) +# define USB0PUEN (1 << 0) +#define OTG_TEST (OTG_BASE + 0x20) /* 16-bit */ +#define OTG_VENDOR_CODE (OTG_BASE + 0xfc) /* 16-bit */ + +/*-------------------------------------------------------------------------*/ + +/* OMAP1 */ +#define USB_TRANSCEIVER_CTRL (0xfffe1000 + 0x0064) +# define CONF_USB2_UNI_R (1 << 8) +# define CONF_USB1_UNI_R (1 << 7) +# define CONF_USB_PORT0_R(x) (((x)>>4)&0x7) +# define CONF_USB0_ISOLATE_R (1 << 3) +# define CONF_USB_PWRDN_DM_R (1 << 2) +# define CONF_USB_PWRDN_DP_R (1 << 1) + +#endif diff --git a/include/linux/soc/ti/ti-msgmgr.h b/include/linux/soc/ti/ti-msgmgr.h index 1f6e76d423cf..543da257a5f2 100644 --- a/include/linux/soc/ti/ti-msgmgr.h +++ b/include/linux/soc/ti/ti-msgmgr.h @@ -1,26 +1,22 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * Texas Instruments' Message Manager * - * Copyright (C) 2015-2016 Texas Instruments Incorporated - https://www.ti.com/ + * Copyright (C) 2015-2022 Texas Instruments Incorporated - https://www.ti.com/ * Nishanth Menon - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * This program is distributed "as is" WITHOUT ANY WARRANTY of any - * kind, whether express or implied; without even the implied warranty - * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. */ #ifndef TI_MSGMGR_H #define TI_MSGMGR_H +struct mbox_chan; + /** * struct ti_msgmgr_message - Message Manager structure * @len: Length of data in the Buffer * @buf: Buffer pointer + * @chan_rx: Expected channel for response, must be provided to use polled rx + * @timeout_rx_ms: Timeout value to use if polling for response * * This is the structure for data used in mbox_send_message * the length of data buffer used depends on the SoC integration @@ -30,6 +26,8 @@ struct ti_msgmgr_message { size_t len; u8 *buf; + struct mbox_chan *chan_rx; + int timeout_rx_ms; }; #endif /* TI_MSGMGR_H */ diff --git a/include/linux/soc/ti/ti_sci_inta_msi.h b/include/linux/soc/ti/ti_sci_inta_msi.h index e3aa8b14612e..4dba2f2aff6f 100644 --- a/include/linux/soc/ti/ti_sci_inta_msi.h +++ b/include/linux/soc/ti/ti_sci_inta_msi.h @@ -18,6 +18,4 @@ struct irq_domain struct irq_domain *parent); int ti_sci_inta_msi_domain_alloc_irqs(struct device *dev, struct ti_sci_resource *res); -unsigned int ti_sci_inta_msi_get_virq(struct device *dev, u32 index); -void ti_sci_inta_msi_domain_free_irqs(struct device *dev); #endif /* __INCLUDE_LINUX_IRQCHIP_TI_SCI_INTA_H */ diff --git a/include/linux/soc/ti/ti_sci_protocol.h b/include/linux/soc/ti/ti_sci_protocol.h index 0aad7009b50e..bd0d11af76c5 100644 --- a/include/linux/soc/ti/ti_sci_protocol.h +++ b/include/linux/soc/ti/ti_sci_protocol.h @@ -645,7 +645,7 @@ devm_ti_sci_get_of_resource(const struct ti_sci_handle *handle, static inline struct ti_sci_resource * devm_ti_sci_get_resource(const struct ti_sci_handle *handle, struct device *dev, - u32 dev_id, u32 sub_type); + u32 dev_id, u32 sub_type) { return ERR_PTR(-EINVAL); } diff --git a/include/linux/socket.h b/include/linux/socket.h index 8ef26d89ef49..de3701a2a212 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -14,6 +14,8 @@ struct file; struct pid; struct cred; struct socket; +struct sock; +struct sk_buff; #define __sockaddr_check_size(size) \ BUILD_BUG_ON(((size) > sizeof(struct __kernel_sockaddr_storage))) @@ -50,6 +52,9 @@ struct linger { struct msghdr { void *msg_name; /* ptr to socket address structure */ int msg_namelen; /* size of socket address structure */ + + int msg_inq; /* output, data left in socket */ + struct iov_iter msg_iter; /* data */ /* @@ -62,9 +67,13 @@ struct msghdr { void __user *msg_control_user; }; bool msg_control_is_user : 1; - __kernel_size_t msg_controllen; /* ancillary data buffer length */ + bool msg_get_inq : 1;/* return INQ after receive */ unsigned int msg_flags; /* flags on received message */ + __kernel_size_t msg_controllen; /* ancillary data buffer length */ struct kiocb *msg_iocb; /* ptr to iocb for async requests */ + struct ubuf_info *msg_ubuf; + int (*sg_from_iter)(struct sock *sk, struct sk_buff *skb, + struct iov_iter *from, size_t length); }; struct user_msghdr { @@ -366,6 +375,7 @@ struct ucred { #define SOL_XDP 283 #define SOL_MPTCP 284 #define SOL_MCTP 285 +#define SOL_SMC 286 /* IPX options */ #define IPX_TYPE 1 @@ -411,10 +421,9 @@ extern int recvmsg_copy_msghdr(struct msghdr *msg, struct user_msghdr __user *umsg, unsigned flags, struct sockaddr __user **uaddr, struct iovec **iov); -extern int __copy_msghdr_from_user(struct msghdr *kmsg, - struct user_msghdr __user *umsg, - struct sockaddr __user **save_addr, - struct iovec __user **uiov, size_t *nsegs); +extern int __copy_msghdr(struct msghdr *kmsg, + struct user_msghdr *umsg, + struct sockaddr __user **save_addr); /* helpers which do the actual work for syscalls */ extern int __sys_recvfrom(int fd, void __user *ubuf, size_t size, @@ -423,16 +432,13 @@ extern int __sys_recvfrom(int fd, void __user *ubuf, size_t size, extern int __sys_sendto(int fd, void __user *buff, size_t len, unsigned int flags, struct sockaddr __user *addr, int addr_len); -extern int __sys_accept4_file(struct file *file, unsigned file_flags, - struct sockaddr __user *upeer_sockaddr, - int __user *upeer_addrlen, int flags, - unsigned long nofile); extern struct file *do_accept(struct file *file, unsigned file_flags, struct sockaddr __user *upeer_sockaddr, int __user *upeer_addrlen, int flags); extern int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr, int __user *upeer_addrlen, int flags); extern int __sys_socket(int family, int type, int protocol); +extern struct file *__sys_socket_file(int family, int type, int protocol); extern int __sys_bind(int fd, struct sockaddr __user *umyaddr, int addrlen); extern int __sys_connect_file(struct file *file, struct sockaddr_storage *addr, int addrlen, int file_flags); diff --git a/include/linux/sockptr.h b/include/linux/sockptr.h index ea193414298b..bae5e2369b4f 100644 --- a/include/linux/sockptr.h +++ b/include/linux/sockptr.h @@ -64,6 +64,11 @@ static inline int copy_to_sockptr_offset(sockptr_t dst, size_t offset, return 0; } +static inline int copy_to_sockptr(sockptr_t dst, const void *src, size_t size) +{ + return copy_to_sockptr_offset(dst, 0, src, size); +} + static inline void *memdup_sockptr(sockptr_t src, size_t len) { void *p = kmalloc_track_caller(len, GFP_USER | __GFP_NOWARN); @@ -102,4 +107,12 @@ static inline long strncpy_from_sockptr(char *dst, sockptr_t src, size_t count) return strncpy_from_user(dst, src.user, count); } +static inline int check_zeroed_sockptr(sockptr_t src, size_t offset, + size_t size) +{ + if (!sockptr_is_kernel(src)) + return check_zeroed_user(src.user + offset, size); + return memchr_inv(src.kernel + offset, 0, size) == NULL; +} + #endif /* _LINUX_SOCKPTR_H */ diff --git a/include/linux/softirq.h b/include/linux/softirq.h new file mode 100644 index 000000000000..c73d7dcb4cb5 --- /dev/null +++ b/include/linux/softirq.h @@ -0,0 +1 @@ +#include <linux/interrupt.h> diff --git a/include/linux/sort.h b/include/linux/sort.h index b5898725fe9d..e163287ac6c1 100644 --- a/include/linux/sort.h +++ b/include/linux/sort.h @@ -6,7 +6,7 @@ void sort_r(void *base, size_t num, size_t size, cmp_r_func_t cmp_func, - swap_func_t swap_func, + swap_r_func_t swap_func, const void *priv); void sort(void *base, size_t num, size_t size, diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h index 76ce3f3ac0f2..9e4537f409c2 100644 --- a/include/linux/soundwire/sdw.h +++ b/include/linux/soundwire/sdw.h @@ -637,7 +637,6 @@ struct sdw_slave_ops { * @dev: Linux device * @status: Status reported by the Slave * @bus: Bus handle - * @ops: Slave callback ops * @prop: Slave properties * @debugfs: Slave debugfs * @node: node for bus list @@ -646,9 +645,6 @@ struct sdw_slave_ops { * @dev_num: Current Device Number, values can be 0 or dev_num_sticky * @dev_num_sticky: one-time static Device Number assigned by Bus * @probed: boolean tracking driver state - * @probe_complete: completion utility to control potential races - * on startup between driver probe/initialization and SoundWire - * Slave state changes/implementation-defined interrupts * @enumeration_complete: completion utility to control potential races * on startup between device enumeration and read/write access to the * Slave device @@ -663,13 +659,13 @@ struct sdw_slave_ops { * for a Slave happens for the first time after enumeration * @is_mockup_device: status flag used to squelch errors in the command/control * protocol for SoundWire mockup devices + * @sdw_dev_lock: mutex used to protect callbacks/remove races */ struct sdw_slave { struct sdw_slave_id id; struct device dev; enum sdw_slave_status status; struct sdw_bus *bus; - const struct sdw_slave_ops *ops; struct sdw_slave_prop prop; #ifdef CONFIG_DEBUG_FS struct dentry *debugfs; @@ -680,12 +676,12 @@ struct sdw_slave { u16 dev_num; u16 dev_num_sticky; bool probed; - struct completion probe_complete; struct completion enumeration_complete; struct completion initialization_complete; u32 unattach_request; bool first_interrupt_done; bool is_mockup_device; + struct mutex sdw_dev_lock; /* protect callbacks/remove races */ }; #define dev_to_sdw_dev(_dev) container_of(_dev, struct sdw_slave, dev) @@ -843,6 +839,8 @@ struct sdw_defer { * @set_bus_conf: Set the bus configuration * @pre_bank_switch: Callback for pre bank switch * @post_bank_switch: Callback for post bank switch + * @read_ping_status: Read status from PING frames, reported with two bits per Device. + * Bits 31:24 are reserved. */ struct sdw_master_ops { int (*read_prop)(struct sdw_bus *bus); @@ -859,6 +857,7 @@ struct sdw_master_ops { struct sdw_bus_params *params); int (*pre_bank_switch)(struct sdw_bus *bus); int (*post_bank_switch)(struct sdw_bus *bus); + u32 (*read_ping_status)(struct sdw_bus *bus); }; @@ -893,6 +892,9 @@ struct sdw_master_ops { * meaningful if multi_link is set. If set to 1, hardware-based * synchronization will be used even if a stream only uses a single * SoundWire segment. + * @dev_num_ida_min: if set, defines the minimum values for the IDA + * used to allocate system-unique device numbers. This value needs to be + * identical across all SoundWire bus in the system. */ struct sdw_bus { struct device *dev; @@ -917,12 +919,15 @@ struct sdw_bus { u32 bank_switch_timeout; bool multi_link; int hw_sync_min_links; + int dev_num_ida_min; }; int sdw_bus_master_add(struct sdw_bus *bus, struct device *parent, struct fwnode_handle *fwnode); void sdw_bus_master_delete(struct sdw_bus *bus); +void sdw_show_ping_status(struct sdw_bus *bus, bool sync_delay); + /** * sdw_port_config: Master or Slave Port configuration * diff --git a/include/linux/soundwire/sdw_intel.h b/include/linux/soundwire/sdw_intel.h index 8a463b8fc12a..2e9fd91572d4 100644 --- a/include/linux/soundwire/sdw_intel.h +++ b/include/linux/soundwire/sdw_intel.h @@ -9,36 +9,27 @@ #define SDW_SHIM_BASE 0x2C000 #define SDW_ALH_BASE 0x2C800 +#define SDW_SHIM_BASE_ACE 0x38000 +#define SDW_ALH_BASE_ACE 0x24000 #define SDW_LINK_BASE 0x30000 #define SDW_LINK_SIZE 0x10000 /* Intel SHIM Registers Definition */ +/* LCAP */ #define SDW_SHIM_LCAP 0x0 -#define SDW_SHIM_LCTL 0x4 -#define SDW_SHIM_IPPTR 0x8 -#define SDW_SHIM_SYNC 0xC - -#define SDW_SHIM_CTLSCAP(x) (0x010 + 0x60 * (x)) -#define SDW_SHIM_CTLS0CM(x) (0x012 + 0x60 * (x)) -#define SDW_SHIM_CTLS1CM(x) (0x014 + 0x60 * (x)) -#define SDW_SHIM_CTLS2CM(x) (0x016 + 0x60 * (x)) -#define SDW_SHIM_CTLS3CM(x) (0x018 + 0x60 * (x)) -#define SDW_SHIM_PCMSCAP(x) (0x020 + 0x60 * (x)) +#define SDW_SHIM_LCAP_LCOUNT_MASK GENMASK(2, 0) -#define SDW_SHIM_PCMSYCHM(x, y) (0x022 + (0x60 * (x)) + (0x2 * (y))) -#define SDW_SHIM_PCMSYCHC(x, y) (0x042 + (0x60 * (x)) + (0x2 * (y))) -#define SDW_SHIM_PDMSCAP(x) (0x062 + 0x60 * (x)) -#define SDW_SHIM_IOCTL(x) (0x06C + 0x60 * (x)) -#define SDW_SHIM_CTMCTL(x) (0x06E + 0x60 * (x)) - -#define SDW_SHIM_WAKEEN 0x190 -#define SDW_SHIM_WAKESTS 0x192 +/* LCTL */ +#define SDW_SHIM_LCTL 0x4 #define SDW_SHIM_LCTL_SPA BIT(0) #define SDW_SHIM_LCTL_SPA_MASK GENMASK(3, 0) #define SDW_SHIM_LCTL_CPA BIT(8) #define SDW_SHIM_LCTL_CPA_MASK GENMASK(11, 8) +/* SYNC */ +#define SDW_SHIM_SYNC 0xC + #define SDW_SHIM_SYNC_SYNCPRD_VAL_24 (24000 / SDW_CADENCE_GSYNC_KHZ - 1) #define SDW_SHIM_SYNC_SYNCPRD_VAL_38_4 (38400 / SDW_CADENCE_GSYNC_KHZ - 1) #define SDW_SHIM_SYNC_SYNCPRD GENMASK(14, 0) @@ -47,19 +38,33 @@ #define SDW_SHIM_SYNC_CMDSYNC BIT(16) #define SDW_SHIM_SYNC_SYNCGO BIT(24) +/* Control stream capabililities and channel mask */ +#define SDW_SHIM_CTLSCAP(x) (0x010 + 0x60 * (x)) +#define SDW_SHIM_CTLS0CM(x) (0x012 + 0x60 * (x)) +#define SDW_SHIM_CTLS1CM(x) (0x014 + 0x60 * (x)) +#define SDW_SHIM_CTLS2CM(x) (0x016 + 0x60 * (x)) +#define SDW_SHIM_CTLS3CM(x) (0x018 + 0x60 * (x)) + +/* PCM Stream capabilities */ +#define SDW_SHIM_PCMSCAP(x) (0x020 + 0x60 * (x)) + #define SDW_SHIM_PCMSCAP_ISS GENMASK(3, 0) #define SDW_SHIM_PCMSCAP_OSS GENMASK(7, 4) #define SDW_SHIM_PCMSCAP_BSS GENMASK(12, 8) +/* PCM Stream Channel Map */ +#define SDW_SHIM_PCMSYCHM(x, y) (0x022 + (0x60 * (x)) + (0x2 * (y))) + +/* PCM Stream Channel Count */ +#define SDW_SHIM_PCMSYCHC(x, y) (0x042 + (0x60 * (x)) + (0x2 * (y))) + #define SDW_SHIM_PCMSYCM_LCHN GENMASK(3, 0) #define SDW_SHIM_PCMSYCM_HCHN GENMASK(7, 4) #define SDW_SHIM_PCMSYCM_STREAM GENMASK(13, 8) #define SDW_SHIM_PCMSYCM_DIR BIT(15) -#define SDW_SHIM_PDMSCAP_ISS GENMASK(3, 0) -#define SDW_SHIM_PDMSCAP_OSS GENMASK(7, 4) -#define SDW_SHIM_PDMSCAP_BSS GENMASK(12, 8) -#define SDW_SHIM_PDMSCAP_CPSS GENMASK(15, 13) +/* IO control */ +#define SDW_SHIM_IOCTL(x) (0x06C + 0x60 * (x)) #define SDW_SHIM_IOCTL_MIF BIT(0) #define SDW_SHIM_IOCTL_CO BIT(1) @@ -71,13 +76,23 @@ #define SDW_SHIM_IOCTL_CIBD BIT(8) #define SDW_SHIM_IOCTL_DIBD BIT(9) -#define SDW_SHIM_CTMCTL_DACTQE BIT(0) -#define SDW_SHIM_CTMCTL_DODS BIT(1) -#define SDW_SHIM_CTMCTL_DOAIS GENMASK(4, 3) +/* Wake Enable*/ +#define SDW_SHIM_WAKEEN 0x190 #define SDW_SHIM_WAKEEN_ENABLE BIT(0) + +/* Wake Status */ +#define SDW_SHIM_WAKESTS 0x192 + #define SDW_SHIM_WAKESTS_STATUS BIT(0) +/* AC Timing control */ +#define SDW_SHIM_CTMCTL(x) (0x06E + 0x60 * (x)) + +#define SDW_SHIM_CTMCTL_DACTQE BIT(0) +#define SDW_SHIM_CTMCTL_DODS BIT(1) +#define SDW_SHIM_CTMCTL_DOAIS GENMASK(4, 3) + /* Intel ALH Register definitions */ #define SDW_ALH_STRMZCFG(x) (0x000 + (0x4 * (x))) #define SDW_ALH_NUM_STREAMS 64 @@ -92,7 +107,7 @@ * firmware. */ struct sdw_intel_stream_params_data { - struct snd_pcm_substream *substream; + int stream; struct snd_soc_dai *dai; struct snd_pcm_hw_params *hw_params; int link_id; @@ -105,7 +120,7 @@ struct sdw_intel_stream_params_data { * firmware. */ struct sdw_intel_stream_free_data { - struct snd_pcm_substream *substream; + int stream; struct snd_soc_dai *dai; int link_id; }; @@ -119,6 +134,7 @@ struct sdw_intel_ops { struct sdw_intel_stream_params_data *params_data); int (*free_stream)(struct device *dev, struct sdw_intel_stream_free_data *free_data); + int (*trigger)(struct snd_soc_dai *dai, int cmd, int stream); }; /** diff --git a/include/linux/spi/pxa2xx_spi.h b/include/linux/spi/pxa2xx_spi.h index ca74dce36706..4658e7801b42 100644 --- a/include/linux/spi/pxa2xx_spi.h +++ b/include/linux/spi/pxa2xx_spi.h @@ -42,7 +42,6 @@ struct pxa2xx_spi_chip { u8 rx_threshold; u8 dma_burst_size; u32 timeout; - int gpio_cs; }; #if defined(CONFIG_ARCH_PXA) || defined(CONFIG_ARCH_MMP) diff --git a/include/linux/spi/s3c24xx.h b/include/linux/spi/s3c24xx.h index 440a71593162..9b8bb22d5b0c 100644 --- a/include/linux/spi/s3c24xx.h +++ b/include/linux/spi/s3c24xx.h @@ -10,14 +10,9 @@ #define __LINUX_SPI_S3C24XX_H __FILE__ struct s3c2410_spi_info { - int pin_cs; /* simple gpio cs */ unsigned int num_cs; /* total chipselects */ int bus_num; /* bus number to use. */ - unsigned int use_fiq:1; /* use fiq */ - - void (*gpio_setup)(struct s3c2410_spi_info *spi, int enable); - void (*set_cs)(struct s3c2410_spi_info *spi, int cs, int pol); }; extern int s3c24xx_set_fiq(unsigned int irq, u32 *ack_ptr, bool on); diff --git a/include/linux/spi/spi-mem.h b/include/linux/spi/spi-mem.h index 85e2ff7b840d..8e984d75f5b6 100644 --- a/include/linux/spi/spi-mem.h +++ b/include/linux/spi/spi-mem.h @@ -89,6 +89,7 @@ enum spi_mem_data_dir { * @dummy.dtr: whether the dummy bytes should be sent in DTR mode or not * @data.buswidth: number of IO lanes used to send/receive the data * @data.dtr: whether the data should be sent in DTR mode or not + * @data.ecc: whether error correction is required or not * @data.dir: direction of the transfer * @data.nbytes: number of data bytes to send/receive. Can be zero if the * operation does not involve transferring data @@ -119,6 +120,7 @@ struct spi_mem_op { struct { u8 buswidth; u8 dtr : 1; + u8 ecc : 1; enum spi_mem_data_dir dir; unsigned int nbytes; union { @@ -223,7 +225,7 @@ static inline void *spi_mem_get_drvdata(struct spi_mem *mem) /** * struct spi_controller_mem_ops - SPI memory operations * @adjust_op_size: shrink the data xfer of an operation to match controller's - * limitations (can be alignment of max RX/TX size + * limitations (can be alignment or max RX/TX size * limitations) * @supports_op: check if an operation is supported by the controller * @exec_op: execute a SPI memory operation @@ -286,6 +288,19 @@ struct spi_controller_mem_ops { }; /** + * struct spi_controller_mem_caps - SPI memory controller capabilities + * @dtr: Supports DTR operations + * @ecc: Supports operations with error correction + */ +struct spi_controller_mem_caps { + bool dtr; + bool ecc; +}; + +#define spi_mem_controller_is_capable(ctlr, cap) \ + ((ctlr)->mem_caps && (ctlr)->mem_caps->cap) + +/** * struct spi_mem_driver - SPI memory driver * @spidrv: inherit from a SPI driver * @probe: probe a SPI memory. Usually where detection/initialization takes @@ -319,10 +334,6 @@ void spi_controller_dma_unmap_mem_op_data(struct spi_controller *ctlr, bool spi_mem_default_supports_op(struct spi_mem *mem, const struct spi_mem_op *op); - -bool spi_mem_dtr_supports_op(struct spi_mem *mem, - const struct spi_mem_op *op); - #else static inline int spi_controller_dma_map_mem_op_data(struct spi_controller *ctlr, @@ -345,13 +356,6 @@ bool spi_mem_default_supports_op(struct spi_mem *mem, { return false; } - -static inline -bool spi_mem_dtr_supports_op(struct spi_mem *mem, - const struct spi_mem_op *op) -{ - return false; -} #endif /* CONFIG_SPI_MEM */ int spi_mem_adjust_op_size(struct spi_mem *mem, struct spi_mem_op *op); diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 7ab3fed7b804..fbf8c0d95968 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -16,6 +16,8 @@ #include <linux/gpio/consumer.h> #include <uapi/linux/spi/spi.h> +#include <linux/acpi.h> +#include <linux/u64_stats_sync.h> struct dma_chan; struct software_node; @@ -23,6 +25,7 @@ struct ptp_system_timestamp; struct spi_controller; struct spi_transfer; struct spi_controller_mem_ops; +struct spi_controller_mem_caps; /* * INTERFACES between SPI master-side drivers and SPI slave protocol handlers, @@ -32,7 +35,8 @@ extern struct bus_type spi_bus_type; /** * struct spi_statistics - statistics for spi transfers - * @lock: lock protecting this structure + * @syncp: seqcount to protect members in this struct for per-cpu udate + * on 32-bit systems * * @messages: number of spi-messages handled * @transfers: number of spi_transfers handled @@ -57,37 +61,48 @@ extern struct bus_type spi_bus_type; * maxsize limit */ struct spi_statistics { - spinlock_t lock; /* lock for the whole structure */ + struct u64_stats_sync syncp; - unsigned long messages; - unsigned long transfers; - unsigned long errors; - unsigned long timedout; + u64_stats_t messages; + u64_stats_t transfers; + u64_stats_t errors; + u64_stats_t timedout; - unsigned long spi_sync; - unsigned long spi_sync_immediate; - unsigned long spi_async; + u64_stats_t spi_sync; + u64_stats_t spi_sync_immediate; + u64_stats_t spi_async; - unsigned long long bytes; - unsigned long long bytes_rx; - unsigned long long bytes_tx; + u64_stats_t bytes; + u64_stats_t bytes_rx; + u64_stats_t bytes_tx; #define SPI_STATISTICS_HISTO_SIZE 17 - unsigned long transfer_bytes_histo[SPI_STATISTICS_HISTO_SIZE]; + u64_stats_t transfer_bytes_histo[SPI_STATISTICS_HISTO_SIZE]; - unsigned long transfers_split_maxsize; + u64_stats_t transfers_split_maxsize; }; -#define SPI_STATISTICS_ADD_TO_FIELD(stats, field, count) \ - do { \ - unsigned long flags; \ - spin_lock_irqsave(&(stats)->lock, flags); \ - (stats)->field += count; \ - spin_unlock_irqrestore(&(stats)->lock, flags); \ +#define SPI_STATISTICS_ADD_TO_FIELD(pcpu_stats, field, count) \ + do { \ + struct spi_statistics *__lstats; \ + get_cpu(); \ + __lstats = this_cpu_ptr(pcpu_stats); \ + u64_stats_update_begin(&__lstats->syncp); \ + u64_stats_add(&__lstats->field, count); \ + u64_stats_update_end(&__lstats->syncp); \ + put_cpu(); \ } while (0) -#define SPI_STATISTICS_INCREMENT_FIELD(stats, field) \ - SPI_STATISTICS_ADD_TO_FIELD(stats, field, 1) +#define SPI_STATISTICS_INCREMENT_FIELD(pcpu_stats, field) \ + do { \ + struct spi_statistics *__lstats; \ + get_cpu(); \ + __lstats = this_cpu_ptr(pcpu_stats); \ + u64_stats_update_begin(&__lstats->syncp); \ + u64_stats_inc(&__lstats->field); \ + u64_stats_update_end(&__lstats->syncp); \ + put_cpu(); \ + } while (0) /** * struct spi_delay - SPI delay information @@ -136,9 +151,8 @@ extern int spi_delay_exec(struct spi_delay *_delay, struct spi_transfer *xfer); * for driver coldplugging, and in uevents used for hotplugging * @driver_override: If the name of a driver is written to this attribute, then * the device will bind to the named driver and only the named driver. - * @cs_gpio: LEGACY: gpio number of the chipselect line (optional, -ENOENT when - * not using a GPIO line) use cs_gpiod in new drivers by opting in on - * the spi_master. + * Do not set directly, because core frees it; use driver_set_override() to + * set or clear it. * @cs_gpiod: gpio descriptor of the chipselect line (optional, NULL when * not using a GPIO line) * @word_delay: delay to be inserted between consecutive @@ -148,7 +162,7 @@ extern int spi_delay_exec(struct spi_delay *_delay, struct spi_transfer *xfer); * @cs_inactive: delay to be introduced by the controller after CS is * deasserted. If @cs_change_delay is used from @spi_transfer, then the * two delays will be added up. - * @statistics: statistics for the spi_device + * @pcpu_statistics: statistics for the spi_device * * A @spi_device is used to interchange data between an SPI slave * (usually a discrete chip) and CPU memory. @@ -162,13 +176,13 @@ extern int spi_delay_exec(struct spi_delay *_delay, struct spi_transfer *xfer); struct spi_device { struct device dev; struct spi_controller *controller; - struct spi_controller *master; /* compatibility layer */ + struct spi_controller *master; /* Compatibility layer */ u32 max_speed_hz; u8 chip_select; u8 bits_per_word; bool rt; -#define SPI_NO_TX BIT(31) /* no transmit wire */ -#define SPI_NO_RX BIT(30) /* no receive wire */ +#define SPI_NO_TX BIT(31) /* No transmit wire */ +#define SPI_NO_RX BIT(30) /* No receive wire */ /* * All bits defined above should be covered by SPI_MODE_KERNEL_MASK. * The SPI_MODE_KERNEL_MASK has the SPI_MODE_USER_MASK counterpart, @@ -185,16 +199,15 @@ struct spi_device { void *controller_data; char modalias[SPI_NAME_SIZE]; const char *driver_override; - int cs_gpio; /* LEGACY: chip select gpio */ - struct gpio_desc *cs_gpiod; /* chip select gpio desc */ - struct spi_delay word_delay; /* inter-word delay */ + struct gpio_desc *cs_gpiod; /* Chip select gpio desc */ + struct spi_delay word_delay; /* Inter-word delay */ /* CS delays */ struct spi_delay cs_setup; struct spi_delay cs_hold; struct spi_delay cs_inactive; - /* the statistics */ - struct spi_statistics statistics; + /* The statistics */ + struct spi_statistics __percpu *pcpu_statistics; /* * likely need more hooks for more protocol options affecting how @@ -215,7 +228,7 @@ static inline struct spi_device *to_spi_device(struct device *dev) return dev ? container_of(dev, struct spi_device, dev) : NULL; } -/* most drivers won't need to care about device refcounting */ +/* Most drivers won't need to care about device refcounting */ static inline struct spi_device *spi_dev_get(struct spi_device *spi) { return (spi && get_device(&spi->dev)) ? spi : NULL; @@ -238,7 +251,7 @@ static inline void spi_set_ctldata(struct spi_device *spi, void *state) spi->controller_state = state; } -/* device driver data */ +/* Device driver data */ static inline void spi_set_drvdata(struct spi_device *spi, void *data) { @@ -280,7 +293,7 @@ struct spi_message; struct spi_driver { const struct spi_device_id *id_table; int (*probe)(struct spi_device *spi); - int (*remove)(struct spi_device *spi); + void (*remove)(struct spi_device *spi); void (*shutdown)(struct spi_device *spi); struct device_driver driver; }; @@ -305,7 +318,7 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv) extern struct spi_device *spi_new_ancillary_device(struct spi_device *spi, u8 chip_select); -/* use a define to avoid include chaining to get THIS_MODULE */ +/* Use a define to avoid include chaining to get THIS_MODULE */ #define spi_register_driver(driver) \ __spi_register_driver(THIS_MODULE, driver) @@ -349,6 +362,7 @@ extern struct spi_device *spi_new_ancillary_device(struct spi_device *spi, u8 ch * @max_message_size: function that returns the max message size for * a &spi_device; may be %NULL, so the default %SIZE_MAX will be used. * @io_mutex: mutex for physical bus access + * @add_lock: mutex to avoid adding devices to the same chipselect * @bus_lock_spinlock: spinlock for SPI bus locking * @bus_lock_mutex: mutex for exclusion of multiple callers * @bus_lock_flag: indicates that the SPI bus is locked for exclusive use @@ -363,17 +377,25 @@ extern struct spi_device *spi_new_ancillary_device(struct spi_device *spi, u8 ch * @transfer: adds a message to the controller's transfer queue. * @cleanup: frees controller-specific state * @can_dma: determine whether this controller supports DMA + * @dma_map_dev: device which can be used for DMA mapping + * @cur_rx_dma_dev: device which is currently used for RX DMA mapping + * @cur_tx_dma_dev: device which is currently used for TX DMA mapping * @queued: whether this controller is providing an internal message queue * @kworker: pointer to thread struct for message pump * @pump_messages: work struct for scheduling work to the message pump * @queue_lock: spinlock to syncronise access to message queue * @queue: message queue - * @idling: the device is entering idle state * @cur_msg: the currently in-flight message - * @cur_msg_prepared: spi_prepare_message was called for the currently - * in-flight message + * @cur_msg_completion: a completion for the current in-flight message + * @cur_msg_incomplete: Flag used internally to opportunistically skip + * the @cur_msg_completion. This flag is used to check if the driver has + * already called spi_finalize_current_message(). + * @cur_msg_need_completion: Flag used internally to opportunistically skip + * the @cur_msg_completion. This flag is used to signal the context that + * is running spi_finalize_current_message() that it needs to complete() * @cur_msg_mapped: message has been mapped for DMA - * @last_cs_enable: was enable true on the last call to set_cs. + * @last_cs: the last chip_select that is recorded by set_cs, -1 on non chip + * selected * @last_cs_mode_high: was (mode & SPI_CS_HIGH) true on the last call to set_cs. * @xfer_completion: used by core transfer_one_message() * @busy: message pump is busy @@ -415,26 +437,22 @@ extern struct spi_device *spi_new_ancillary_device(struct spi_device *spi, u8 ch * @mem_ops: optimized/dedicated operations for interactions with SPI memory. * This field is optional and should only be implemented if the * controller has native support for memory like operations. + * @mem_caps: controller capabilities for the handling of memory operations. * @unprepare_message: undo any work done by prepare_message(). * @slave_abort: abort the ongoing transfer request on an SPI slave controller - * @cs_gpios: LEGACY: array of GPIO descs to use as chip select lines; one per - * CS number. Any individual value may be -ENOENT for CS lines that - * are not GPIOs (driven by the SPI controller itself). Use the cs_gpiods - * in new drivers. * @cs_gpiods: Array of GPIO descs to use as chip select lines; one per CS * number. Any individual value may be NULL for CS lines that * are not GPIOs (driven by the SPI controller itself). * @use_gpio_descriptors: Turns on the code in the SPI core to parse and grab - * GPIO descriptors rather than using global GPIO numbers grabbed by the - * driver. This will fill in @cs_gpiods and @cs_gpios should not be used, - * and SPI devices will have the cs_gpiod assigned rather than cs_gpio. + * GPIO descriptors. This will fill in @cs_gpiods and SPI devices will have + * the cs_gpiod assigned if a GPIO line is found for the chipselect. * @unused_native_cs: When cs_gpiods is used, spi_register_controller() will * fill in this field with the first unused native CS, to be used by SPI * controller drivers that need to drive a native CS when using GPIO CS. * @max_native_cs: When cs_gpiods is used, and this field is filled in, * spi_register_controller() will validate all native CS (including the * unused native CS) against this value. - * @statistics: statistics for the spi_controller + * @pcpu_statistics: statistics for the spi_controller * @dma_tx: DMA transmit channel * @dma_rx: DMA receive channel * @dummy_rx: dummy receive buffer for full-duplex devices @@ -451,6 +469,9 @@ extern struct spi_device *spi_new_ancillary_device(struct spi_device *spi, u8 ch * @irq_flags: Interrupt enable state during PTP system timestamping * @fallback: fallback to pio if dma transfer return failure with * SPI_TRANS_FAIL_NO_START. + * @queue_empty: signal green light for opportunistically skipping the queue + * for spi_sync transfers. + * @must_async: disable all fast paths in the core * * Each SPI controller can communicate with one or more @spi_device * children. These make a small bus, sharing MOSI, MISO and SCK signals @@ -468,7 +489,7 @@ struct spi_controller { struct list_head list; - /* other than negative (== assign one dynamically), bus_num is fully + /* Other than negative (== assign one dynamically), bus_num is fully * board-specific. usually that simplifies to being SOC-specific. * example: one SOC has three SPI controllers, numbered 0..2, * and one board's schematics might show it using SPI-2. software @@ -481,7 +502,7 @@ struct spi_controller { */ u16 num_chipselect; - /* some SPI controllers pose alignment requirements on DMAable + /* Some SPI controllers pose alignment requirements on DMAable * buffers; let protocol drivers know about these requirements. */ u16 dma_alignment; @@ -492,29 +513,29 @@ struct spi_controller { /* spi_device.mode flags override flags for this controller */ u32 buswidth_override_bits; - /* bitmask of supported bits_per_word for transfers */ + /* Bitmask of supported bits_per_word for transfers */ u32 bits_per_word_mask; #define SPI_BPW_MASK(bits) BIT((bits) - 1) #define SPI_BPW_RANGE_MASK(min, max) GENMASK((max) - 1, (min) - 1) - /* limits on transfer speed */ + /* Limits on transfer speed */ u32 min_speed_hz; u32 max_speed_hz; - /* other constraints relevant to this driver */ + /* Other constraints relevant to this driver */ u16 flags; -#define SPI_CONTROLLER_HALF_DUPLEX BIT(0) /* can't do full duplex */ -#define SPI_CONTROLLER_NO_RX BIT(1) /* can't do buffer read */ -#define SPI_CONTROLLER_NO_TX BIT(2) /* can't do buffer write */ -#define SPI_CONTROLLER_MUST_RX BIT(3) /* requires rx */ -#define SPI_CONTROLLER_MUST_TX BIT(4) /* requires tx */ +#define SPI_CONTROLLER_HALF_DUPLEX BIT(0) /* Can't do full duplex */ +#define SPI_CONTROLLER_NO_RX BIT(1) /* Can't do buffer read */ +#define SPI_CONTROLLER_NO_TX BIT(2) /* Can't do buffer write */ +#define SPI_CONTROLLER_MUST_RX BIT(3) /* Requires rx */ +#define SPI_CONTROLLER_MUST_TX BIT(4) /* Requires tx */ #define SPI_MASTER_GPIO_SS BIT(5) /* GPIO CS must select slave */ - /* flag indicating if the allocation of this struct is devres-managed */ + /* Flag indicating if the allocation of this struct is devres-managed */ bool devm_allocated; - /* flag indicating this is an SPI slave controller */ + /* Flag indicating this is an SPI slave controller */ bool slave; /* @@ -530,11 +551,11 @@ struct spi_controller { /* Used to avoid adding the same CS twice */ struct mutex add_lock; - /* lock and mutex for SPI bus locking */ + /* Lock and mutex for SPI bus locking */ spinlock_t bus_lock_spinlock; struct mutex bus_lock_mutex; - /* flag indicating that the SPI bus is locked for exclusive use */ + /* Flag indicating that the SPI bus is locked for exclusive use */ bool bus_lock_flag; /* Setup mode and clock, etc (spi driver may call many times). @@ -555,7 +576,7 @@ struct spi_controller { */ int (*set_cs_timing)(struct spi_device *spi); - /* bidirectional bulk transfers + /* Bidirectional bulk transfers * * + The transfer() method may not sleep; its main role is * just to add the message to the queue. @@ -577,7 +598,7 @@ struct spi_controller { int (*transfer)(struct spi_device *spi, struct spi_message *mesg); - /* called on release() to free memory provided by spi_controller */ + /* Called on release() to free memory provided by spi_controller */ void (*cleanup)(struct spi_device *spi); /* @@ -591,6 +612,8 @@ struct spi_controller { struct spi_device *spi, struct spi_transfer *xfer); struct device *dma_map_dev; + struct device *cur_rx_dma_dev; + struct device *cur_tx_dma_dev; /* * These hooks are for drivers that want to use the generic @@ -604,14 +627,15 @@ struct spi_controller { spinlock_t queue_lock; struct list_head queue; struct spi_message *cur_msg; - bool idling; + struct completion cur_msg_completion; + bool cur_msg_incomplete; + bool cur_msg_need_completion; bool busy; bool running; bool rt; bool auto_runtime_pm; - bool cur_msg_prepared; bool cur_msg_mapped; - bool last_cs_enable; + char last_cs; bool last_cs_mode_high; bool fallback; struct completion xfer_completion; @@ -639,22 +663,22 @@ struct spi_controller { /* Optimized handlers for SPI memory-like operations. */ const struct spi_controller_mem_ops *mem_ops; + const struct spi_controller_mem_caps *mem_caps; /* gpio chip select */ - int *cs_gpios; struct gpio_desc **cs_gpiods; bool use_gpio_descriptors; s8 unused_native_cs; s8 max_native_cs; - /* statistics */ - struct spi_statistics statistics; + /* Statistics */ + struct spi_statistics __percpu *pcpu_statistics; /* DMA channels for use with core dmaengine helpers */ struct dma_chan *dma_tx; struct dma_chan *dma_rx; - /* dummy data for full duplex devices */ + /* Dummy data for full duplex devices */ void *dummy_rx; void *dummy_tx; @@ -668,6 +692,10 @@ struct spi_controller { /* Interrupt enable state during PTP system timestamping */ unsigned long irq_flags; + + /* Flag for enabling opportunistic skipping of the queue in spi_sync */ + bool queue_empty; + bool must_async; }; static inline void *spi_controller_get_devdata(struct spi_controller *ctlr) @@ -716,7 +744,7 @@ void spi_take_timestamp_post(struct spi_controller *ctlr, struct spi_transfer *xfer, size_t progress, bool irqs_off); -/* the spi driver core manages memory for the spi_controller classdev */ +/* The spi driver core manages memory for the spi_controller classdev */ extern struct spi_controller *__spi_alloc_controller(struct device *host, unsigned int size, bool slave); @@ -759,6 +787,13 @@ extern int devm_spi_register_controller(struct device *dev, struct spi_controller *ctlr); extern void spi_unregister_controller(struct spi_controller *ctlr); +#if IS_ENABLED(CONFIG_ACPI) +extern struct spi_device *acpi_spi_device_alloc(struct spi_controller *ctlr, + struct acpi_device *adev, + int index); +int acpi_spi_count_resources(struct acpi_device *adev); +#endif + /* * SPI resource management while processing a SPI message */ @@ -779,7 +814,7 @@ typedef void (*spi_res_release_t)(struct spi_controller *ctlr, struct spi_res { struct list_head entry; spi_res_release_t release; - unsigned long long data[]; /* guarantee ull alignment */ + unsigned long long data[]; /* Guarantee ull alignment */ }; /*---------------------------------------------------------------------------*/ @@ -817,6 +852,7 @@ struct spi_res { * @bits_per_word: select a bits_per_word other than the device default * for this transfer. If 0 the default (from @spi_device) is used. * @dummy_data: indicates transfer is dummy bytes transfer. + * @cs_off: performs the transfer with chipselect off. * @cs_change: affects chipselect after this transfer completes * @cs_change_delay: delay between cs deassert and assert when * @cs_change is set and @spi_transfer is not the last in @spi_message @@ -912,7 +948,7 @@ struct spi_res { * and its transfers, ignore them until its completion callback. */ struct spi_transfer { - /* it's ok if tx_buf == rx_buf (right?) + /* It's ok if tx_buf == rx_buf (right?) * for MicroWire, one buffer must be null * buffers must work with dma_*map_single() calls, unless * spi_message.is_dma_mapped reports a pre-existing mapping @@ -927,6 +963,7 @@ struct spi_transfer { struct sg_table rx_sg; unsigned dummy_data:1; + unsigned cs_off:1; unsigned cs_change:1; unsigned tx_nbits:3; unsigned rx_nbits:3; @@ -969,6 +1006,7 @@ struct spi_transfer { * @queue: for use by whichever driver currently owns the message * @state: for use by whichever driver currently owns the message * @resources: for resource management when the spi message is processed + * @prepared: spi_prepare_message was called for the this message * * A @spi_message is used to execute an atomic sequence of data transfers, * each represented by a struct spi_transfer. The sequence is "atomic" @@ -1002,22 +1040,25 @@ struct spi_message { * tell them about such special cases. */ - /* completion is reported through a callback */ + /* Completion is reported through a callback */ void (*complete)(void *context); void *context; unsigned frame_length; unsigned actual_length; int status; - /* for optional use by whatever driver currently owns the + /* For optional use by whatever driver currently owns the * spi_message ... between calls to spi_async and then later * complete(), that's the spi_controller controller driver. */ struct list_head queue; void *state; - /* list of spi_res reources when the spi message is processed */ + /* List of spi_res reources when the spi message is processed */ struct list_head resources; + + /* spi_prepare_message() was called for this message */ + bool prepared; }; static inline void spi_message_init_no_memset(struct spi_message *m) @@ -1121,7 +1162,7 @@ spi_max_transfer_size(struct spi_device *spi) if (ctlr->max_transfer_size) tr_max = ctlr->max_transfer_size(spi); - /* transfer size limit must not be greater than messsage size limit */ + /* Transfer size limit must not be greater than message size limit */ return min(tr_max, msg_max); } @@ -1272,7 +1313,7 @@ spi_read(struct spi_device *spi, void *buf, size_t len) return spi_sync_transfer(spi, &t, 1); } -/* this copies txbuf and rxbuf data; for small transfers only! */ +/* This copies txbuf and rxbuf data; for small transfers only! */ extern int spi_write_then_read(struct spi_device *spi, const void *txbuf, unsigned n_tx, void *rxbuf, unsigned n_rx); @@ -1295,7 +1336,7 @@ static inline ssize_t spi_w8r8(struct spi_device *spi, u8 cmd) status = spi_write_then_read(spi, &cmd, 1, &result, 1); - /* return negative errno or unsigned value */ + /* Return negative errno or unsigned value */ return (status < 0) ? status : result; } @@ -1320,7 +1361,7 @@ static inline ssize_t spi_w8r16(struct spi_device *spi, u8 cmd) status = spi_write_then_read(spi, &cmd, 1, &result, 2); - /* return negative errno or unsigned value */ + /* Return negative errno or unsigned value */ return (status < 0) ? status : result; } @@ -1400,7 +1441,7 @@ static inline ssize_t spi_w8r16be(struct spi_device *spi, u8 cmd) * are active in some dynamic board configuration models. */ struct spi_board_info { - /* the device name and module name are coupled, like platform_bus; + /* The device name and module name are coupled, like platform_bus; * "modalias" is normally the driver name. * * platform_data goes to spi_device.dev.platform_data, @@ -1413,7 +1454,7 @@ struct spi_board_info { void *controller_data; int irq; - /* slower signaling on noisy or low voltage boards */ + /* Slower signaling on noisy or low voltage boards */ u32 max_speed_hz; @@ -1442,7 +1483,7 @@ struct spi_board_info { extern int spi_register_board_info(struct spi_board_info const *info, unsigned n); #else -/* board init code may ignore whether SPI is configured or not */ +/* Board init code may ignore whether SPI is configured or not */ static inline int spi_register_board_info(struct spi_board_info const *info, unsigned n) { return 0; } @@ -1452,8 +1493,20 @@ spi_register_board_info(struct spi_board_info const *info, unsigned n) * use spi_new_device() to describe each device. You can also call * spi_unregister_device() to start making that device vanish, but * normally that would be handled by spi_unregister_controller(). + * + * You can also use spi_alloc_device() and spi_add_device() to use a two + * stage registration sequence for each spi_device. This gives the caller + * some more control over the spi_device structure before it is registered, + * but requires that caller to initialize fields that would otherwise + * be defined using the board info. */ extern struct spi_device * +spi_alloc_device(struct spi_controller *ctlr); + +extern int +spi_add_device(struct spi_device *spi); + +extern struct spi_device * spi_new_device(struct spi_controller *, struct spi_board_info *); extern void spi_unregister_device(struct spi_device *spi); diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h index 5c0c5174155d..1341f7d62da4 100644 --- a/include/linux/spinlock.h +++ b/include/linux/spinlock.h @@ -1,6 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_SPINLOCK_H #define __LINUX_SPINLOCK_H +#define __LINUX_INSIDE_SPINLOCK_H /* * include/linux/spinlock.h - generic spinlock/rwlock declarations @@ -492,4 +493,5 @@ int __alloc_bucket_spinlocks(spinlock_t **locks, unsigned int *lock_mask, void free_bucket_spinlocks(spinlock_t *locks); +#undef __LINUX_INSIDE_SPINLOCK_H #endif /* __LINUX_SPINLOCK_H */ diff --git a/include/linux/spinlock_api.h b/include/linux/spinlock_api.h new file mode 100644 index 000000000000..6338b27f98df --- /dev/null +++ b/include/linux/spinlock_api.h @@ -0,0 +1 @@ +#include <linux/spinlock.h> diff --git a/include/linux/spinlock_api_smp.h b/include/linux/spinlock_api_smp.h index 51fa0dab68c4..89eb6f4c659c 100644 --- a/include/linux/spinlock_api_smp.h +++ b/include/linux/spinlock_api_smp.h @@ -1,7 +1,7 @@ #ifndef __LINUX_SPINLOCK_API_SMP_H #define __LINUX_SPINLOCK_API_SMP_H -#ifndef __LINUX_SPINLOCK_H +#ifndef __LINUX_INSIDE_SPINLOCK_H # error "please don't include this file directly" #endif diff --git a/include/linux/spinlock_api_up.h b/include/linux/spinlock_api_up.h index d0d188861ad6..819aeba1c87e 100644 --- a/include/linux/spinlock_api_up.h +++ b/include/linux/spinlock_api_up.h @@ -1,7 +1,7 @@ #ifndef __LINUX_SPINLOCK_API_UP_H #define __LINUX_SPINLOCK_API_UP_H -#ifndef __LINUX_SPINLOCK_H +#ifndef __LINUX_INSIDE_SPINLOCK_H # error "please don't include this file directly" #endif @@ -59,6 +59,7 @@ #define _raw_spin_lock_nested(lock, subclass) __LOCK(lock) #define _raw_read_lock(lock) __LOCK(lock) #define _raw_write_lock(lock) __LOCK(lock) +#define _raw_write_lock_nested(lock, subclass) __LOCK(lock) #define _raw_spin_lock_bh(lock) __LOCK_BH(lock) #define _raw_read_lock_bh(lock) __LOCK_BH(lock) #define _raw_write_lock_bh(lock) __LOCK_BH(lock) diff --git a/include/linux/spinlock_rt.h b/include/linux/spinlock_rt.h index 835aedaf68ac..61c49b16f69a 100644 --- a/include/linux/spinlock_rt.h +++ b/include/linux/spinlock_rt.h @@ -2,7 +2,7 @@ #ifndef __LINUX_SPINLOCK_RT_H #define __LINUX_SPINLOCK_RT_H -#ifndef __LINUX_SPINLOCK_H +#ifndef __LINUX_INSIDE_SPINLOCK_H #error Do not include directly. Use spinlock.h #endif diff --git a/include/linux/spinlock_types_up.h b/include/linux/spinlock_types_up.h index c09b6407ae1b..7f86a2016ac5 100644 --- a/include/linux/spinlock_types_up.h +++ b/include/linux/spinlock_types_up.h @@ -1,7 +1,7 @@ #ifndef __LINUX_SPINLOCK_TYPES_UP_H #define __LINUX_SPINLOCK_TYPES_UP_H -#ifndef __LINUX_SPINLOCK_TYPES_H +#ifndef __LINUX_SPINLOCK_TYPES_RAW_H # error "please don't include this file directly" #endif diff --git a/include/linux/spinlock_up.h b/include/linux/spinlock_up.h index 16521074b6f7..c87204247592 100644 --- a/include/linux/spinlock_up.h +++ b/include/linux/spinlock_up.h @@ -1,7 +1,7 @@ #ifndef __LINUX_SPINLOCK_UP_H #define __LINUX_SPINLOCK_UP_H -#ifndef __LINUX_SPINLOCK_H +#ifndef __LINUX_INSIDE_SPINLOCK_H # error "please don't include this file directly" #endif diff --git a/include/linux/spmi.h b/include/linux/spmi.h index 729bcbf9f5ad..eac1956a8727 100644 --- a/include/linux/spmi.h +++ b/include/linux/spmi.h @@ -164,6 +164,9 @@ static inline void spmi_driver_unregister(struct spmi_driver *sdrv) module_driver(__spmi_driver, spmi_driver_register, \ spmi_driver_unregister) +struct device_node; + +struct spmi_device *spmi_device_from_of(struct device_node *np); int spmi_register_read(struct spmi_device *sdev, u8 addr, u8 *buf); int spmi_ext_register_read(struct spmi_device *sdev, u8 addr, u8 *buf, size_t len); diff --git a/include/linux/sram.h b/include/linux/sram.h index 4fb405fb0480..d7dee19505c6 100644 --- a/include/linux/sram.h +++ b/include/linux/sram.h @@ -1,15 +1,5 @@ -/* - * Generic SRAM Driver Interface - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation version 2. - * - * This program is distributed "as is" WITHOUT ANY WARRANTY of any - * kind, whether express or implied; without even the implied warranty - * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - */ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Generic SRAM Driver Interface */ #ifndef __LINUX_SRAM_H__ #define __LINUX_SRAM_H__ diff --git a/include/linux/srcutiny.h b/include/linux/srcutiny.h index 6cfaa0a9a9b9..5aa5e0faf6a1 100644 --- a/include/linux/srcutiny.h +++ b/include/linux/srcutiny.h @@ -15,10 +15,10 @@ struct srcu_struct { short srcu_lock_nesting[2]; /* srcu_read_lock() nesting depth. */ - unsigned short srcu_idx; /* Current reader array element in bit 0x2. */ - unsigned short srcu_idx_max; /* Furthest future srcu_idx request. */ u8 srcu_gp_running; /* GP workqueue running? */ u8 srcu_gp_waiting; /* GP waiting for readers? */ + unsigned long srcu_idx; /* Current reader array element in bit 0x2. */ + unsigned long srcu_idx_max; /* Furthest future srcu_idx request. */ struct swait_queue_head srcu_wq; /* Last srcu_read_unlock() wakes GP. */ struct rcu_head *srcu_cb_head; /* Pending callbacks: Head. */ @@ -82,10 +82,12 @@ static inline void srcu_torture_stats_print(struct srcu_struct *ssp, int idx; idx = ((data_race(READ_ONCE(ssp->srcu_idx)) + 1) & 0x2) >> 1; - pr_alert("%s%s Tiny SRCU per-CPU(idx=%d): (%hd,%hd)\n", + pr_alert("%s%s Tiny SRCU per-CPU(idx=%d): (%hd,%hd) gp: %lu->%lu\n", tt, tf, idx, data_race(READ_ONCE(ssp->srcu_lock_nesting[!idx])), - data_race(READ_ONCE(ssp->srcu_lock_nesting[idx]))); + data_race(READ_ONCE(ssp->srcu_lock_nesting[idx])), + data_race(READ_ONCE(ssp->srcu_idx)), + data_race(READ_ONCE(ssp->srcu_idx_max))); } #endif diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h index cb1f4351e8ba..e3014319d1ad 100644 --- a/include/linux/srcutree.h +++ b/include/linux/srcutree.h @@ -47,11 +47,9 @@ struct srcu_data { */ struct srcu_node { spinlock_t __private lock; - unsigned long srcu_have_cbs[4]; /* GP seq for children */ - /* having CBs, but only */ - /* is > ->srcu_gq_seq. */ - unsigned long srcu_data_have_cbs[4]; /* Which srcu_data structs */ - /* have CBs for given GP? */ + unsigned long srcu_have_cbs[4]; /* GP seq for children having CBs, but only */ + /* if greater than ->srcu_gq_seq. */ + unsigned long srcu_data_have_cbs[4]; /* Which srcu_data structs have CBs for given GP? */ unsigned long srcu_gp_seq_needed_exp; /* Furthest future exp GP. */ struct srcu_node *srcu_parent; /* Next up in tree. */ int grplo; /* Least CPU for node. */ @@ -62,18 +60,24 @@ struct srcu_node { * Per-SRCU-domain structure, similar in function to rcu_state. */ struct srcu_struct { - struct srcu_node node[NUM_RCU_NODES]; /* Combining tree. */ + struct srcu_node *node; /* Combining tree. */ struct srcu_node *level[RCU_NUM_LVLS + 1]; /* First node at each level. */ + int srcu_size_state; /* Small-to-big transition state. */ struct mutex srcu_cb_mutex; /* Serialize CB preparation. */ - spinlock_t __private lock; /* Protect counters */ + spinlock_t __private lock; /* Protect counters and size state. */ struct mutex srcu_gp_mutex; /* Serialize GP work. */ unsigned int srcu_idx; /* Current rdr array element. */ unsigned long srcu_gp_seq; /* Grace-period seq #. */ unsigned long srcu_gp_seq_needed; /* Latest gp_seq needed. */ unsigned long srcu_gp_seq_needed_exp; /* Furthest future exp GP. */ + unsigned long srcu_gp_start; /* Last GP start timestamp (jiffies) */ unsigned long srcu_last_gp_end; /* Last GP end timestamp (ns) */ + unsigned long srcu_size_jiffies; /* Current contention-measurement interval. */ + unsigned long srcu_n_lock_retries; /* Contention events in current interval. */ + unsigned long srcu_n_exp_nodelay; /* # expedited no-delays in current GP phase. */ struct srcu_data __percpu *sda; /* Per-CPU srcu_data array. */ + bool sda_is_static; /* May ->sda be passed to free_percpu()? */ unsigned long srcu_barrier_seq; /* srcu_barrier seq #. */ struct mutex srcu_barrier_mutex; /* Serialize barrier ops. */ struct completion srcu_barrier_completion; @@ -81,10 +85,23 @@ struct srcu_struct { atomic_t srcu_barrier_cpu_cnt; /* # CPUs not yet posting a */ /* callback for the barrier */ /* operation. */ + unsigned long reschedule_jiffies; + unsigned long reschedule_count; struct delayed_work work; struct lockdep_map dep_map; }; +/* Values for size state variable (->srcu_size_state). */ +#define SRCU_SIZE_SMALL 0 +#define SRCU_SIZE_ALLOC 1 +#define SRCU_SIZE_WAIT_BARRIER 2 +#define SRCU_SIZE_WAIT_CALL 3 +#define SRCU_SIZE_WAIT_CBS1 4 +#define SRCU_SIZE_WAIT_CBS2 5 +#define SRCU_SIZE_WAIT_CBS3 6 +#define SRCU_SIZE_WAIT_CBS4 7 +#define SRCU_SIZE_BIG 8 + /* Values for state variable (bottom bits of ->srcu_gp_seq). */ #define SRCU_STATE_IDLE 0 #define SRCU_STATE_SCAN1 1 @@ -121,6 +138,7 @@ struct srcu_struct { #ifdef MODULE # define __DEFINE_SRCU(name, is_static) \ is_static struct srcu_struct name; \ + extern struct srcu_struct * const __srcu_struct_##name; \ struct srcu_struct * const __srcu_struct_##name \ __section("___srcu_struct_ptrs") = &name #else diff --git a/include/linux/ssb/ssb_driver_gige.h b/include/linux/ssb/ssb_driver_gige.h index 15ba0df1ee0d..28c145a51e57 100644 --- a/include/linux/ssb/ssb_driver_gige.h +++ b/include/linux/ssb/ssb_driver_gige.h @@ -95,7 +95,7 @@ static inline bool ssb_gige_must_flush_posted_writes(struct pci_dev *pdev) struct ssb_gige *dev = pdev_to_ssb_gige(pdev); if (dev) return (dev->dev->bus->chip_id == 0x4785); - return 0; + return false; } /* Get the device MAC address */ diff --git a/include/linux/stackdepot.h b/include/linux/stackdepot.h index c34b55a6e554..9ca7798d7a31 100644 --- a/include/linux/stackdepot.h +++ b/include/linux/stackdepot.h @@ -14,29 +14,62 @@ #include <linux/gfp.h> typedef u32 depot_stack_handle_t; +/* + * Number of bits in the handle that stack depot doesn't use. Users may store + * information in them. + */ +#define STACK_DEPOT_EXTRA_BITS 5 depot_stack_handle_t __stack_depot_save(unsigned long *entries, unsigned int nr_entries, + unsigned int extra_bits, gfp_t gfp_flags, bool can_alloc); +/* + * Every user of stack depot has to call stack_depot_init() during its own init + * when it's decided that it will be calling stack_depot_save() later. This is + * recommended for e.g. modules initialized later in the boot process, when + * slab_is_available() is true. + * + * The alternative is to select STACKDEPOT_ALWAYS_INIT to have stack depot + * enabled as part of mm_init(), for subsystems where it's known at compile time + * that stack depot will be used. + * + * Another alternative is to call stack_depot_want_early_init(), when the + * decision to use stack depot is taken e.g. when evaluating kernel boot + * parameters, which precedes the enablement point in mm_init(). + * + * stack_depot_init() and stack_depot_want_early_init() can be called regardless + * of CONFIG_STACKDEPOT and are no-op when disabled. The actual save/fetch/print + * functions should only be called from code that makes sure CONFIG_STACKDEPOT + * is enabled. + */ +#ifdef CONFIG_STACKDEPOT +int stack_depot_init(void); + +void __init stack_depot_want_early_init(void); + +/* This is supposed to be called only from mm_init() */ +int __init stack_depot_early_init(void); +#else +static inline int stack_depot_init(void) { return 0; } + +static inline void stack_depot_want_early_init(void) { } + +static inline int stack_depot_early_init(void) { return 0; } +#endif + depot_stack_handle_t stack_depot_save(unsigned long *entries, unsigned int nr_entries, gfp_t gfp_flags); unsigned int stack_depot_fetch(depot_stack_handle_t handle, unsigned long **entries); +unsigned int stack_depot_get_extra_bits(depot_stack_handle_t handle); + int stack_depot_snprint(depot_stack_handle_t handle, char *buf, size_t size, int spaces); void stack_depot_print(depot_stack_handle_t stack); -#ifdef CONFIG_STACKDEPOT -int stack_depot_init(void); -#else -static inline int stack_depot_init(void) -{ - return 0; -} -#endif /* CONFIG_STACKDEPOT */ - #endif diff --git a/include/linux/stackleak.h b/include/linux/stackleak.h index a59db2f08e76..c36e7a3b45e7 100644 --- a/include/linux/stackleak.h +++ b/include/linux/stackleak.h @@ -15,19 +15,67 @@ #ifdef CONFIG_GCC_PLUGIN_STACKLEAK #include <asm/stacktrace.h> +/* + * The lowest address on tsk's stack which we can plausibly erase. + */ +static __always_inline unsigned long +stackleak_task_low_bound(const struct task_struct *tsk) +{ + /* + * The lowest unsigned long on the task stack contains STACK_END_MAGIC, + * which we must not corrupt. + */ + return (unsigned long)end_of_stack(tsk) + sizeof(unsigned long); +} + +/* + * The address immediately after the highest address on tsk's stack which we + * can plausibly erase. + */ +static __always_inline unsigned long +stackleak_task_high_bound(const struct task_struct *tsk) +{ + /* + * The task's pt_regs lives at the top of the task stack and will be + * overwritten by exception entry, so there's no need to erase them. + */ + return (unsigned long)task_pt_regs(tsk); +} + +/* + * Find the address immediately above the poisoned region of the stack, where + * that region falls between 'low' (inclusive) and 'high' (exclusive). + */ +static __always_inline unsigned long +stackleak_find_top_of_poison(const unsigned long low, const unsigned long high) +{ + const unsigned int depth = STACKLEAK_SEARCH_DEPTH / sizeof(unsigned long); + unsigned int poison_count = 0; + unsigned long poison_high = high; + unsigned long sp = high; + + while (sp > low && poison_count < depth) { + sp -= sizeof(unsigned long); + + if (*(unsigned long *)sp == STACKLEAK_POISON) { + poison_count++; + } else { + poison_count = 0; + poison_high = sp; + } + } + + return poison_high; +} + static inline void stackleak_task_init(struct task_struct *t) { - t->lowest_stack = (unsigned long)end_of_stack(t) + sizeof(unsigned long); + t->lowest_stack = stackleak_task_low_bound(t); # ifdef CONFIG_STACKLEAK_METRICS t->prev_lowest_stack = t->lowest_stack; # endif } -#ifdef CONFIG_STACKLEAK_RUNTIME_DISABLE -int stack_erasing_sysctl(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos); -#endif - #else /* !CONFIG_GCC_PLUGIN_STACKLEAK */ static inline void stackleak_task_init(struct task_struct *t) { } #endif diff --git a/include/linux/stat.h b/include/linux/stat.h index 7df06931f25d..ff277ced50e9 100644 --- a/include/linux/stat.h +++ b/include/linux/stat.h @@ -50,6 +50,8 @@ struct kstat { struct timespec64 btime; /* File creation time */ u64 blocks; u64 mnt_id; + u32 dio_mem_align; + u32 dio_offset_align; }; #endif diff --git a/include/linux/static_call.h b/include/linux/static_call.h index 3e56a9751c06..df53bed9d71f 100644 --- a/include/linux/static_call.h +++ b/include/linux/static_call.h @@ -180,13 +180,13 @@ extern int static_call_text_reserved(void *start, void *end); extern long __static_call_return0(void); -#define __DEFINE_STATIC_CALL(name, _func, _func_init) \ +#define DEFINE_STATIC_CALL(name, _func) \ DECLARE_STATIC_CALL(name, _func); \ struct static_call_key STATIC_CALL_KEY(name) = { \ - .func = _func_init, \ + .func = _func, \ .type = 1, \ }; \ - ARCH_DEFINE_STATIC_CALL_TRAMP(name, _func_init) + ARCH_DEFINE_STATIC_CALL_TRAMP(name, _func) #define DEFINE_STATIC_CALL_NULL(name, _func) \ DECLARE_STATIC_CALL(name, _func); \ @@ -196,6 +196,14 @@ extern long __static_call_return0(void); }; \ ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name) +#define DEFINE_STATIC_CALL_RET0(name, _func) \ + DECLARE_STATIC_CALL(name, _func); \ + struct static_call_key STATIC_CALL_KEY(name) = { \ + .func = __static_call_return0, \ + .type = 1, \ + }; \ + ARCH_DEFINE_STATIC_CALL_RET0_TRAMP(name) + #define static_call_cond(name) (void)__static_call(name) #define EXPORT_STATIC_CALL(name) \ @@ -217,12 +225,12 @@ extern long __static_call_return0(void); static inline int static_call_init(void) { return 0; } -#define __DEFINE_STATIC_CALL(name, _func, _func_init) \ +#define DEFINE_STATIC_CALL(name, _func) \ DECLARE_STATIC_CALL(name, _func); \ struct static_call_key STATIC_CALL_KEY(name) = { \ - .func = _func_init, \ + .func = _func, \ }; \ - ARCH_DEFINE_STATIC_CALL_TRAMP(name, _func_init) + ARCH_DEFINE_STATIC_CALL_TRAMP(name, _func) #define DEFINE_STATIC_CALL_NULL(name, _func) \ DECLARE_STATIC_CALL(name, _func); \ @@ -231,6 +239,12 @@ static inline int static_call_init(void) { return 0; } }; \ ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name) +#define DEFINE_STATIC_CALL_RET0(name, _func) \ + DECLARE_STATIC_CALL(name, _func); \ + struct static_call_key STATIC_CALL_KEY(name) = { \ + .func = __static_call_return0, \ + }; \ + ARCH_DEFINE_STATIC_CALL_RET0_TRAMP(name) #define static_call_cond(name) (void)__static_call(name) @@ -248,10 +262,7 @@ static inline int static_call_text_reserved(void *start, void *end) return 0; } -static inline long __static_call_return0(void) -{ - return 0; -} +extern long __static_call_return0(void); #define EXPORT_STATIC_CALL(name) \ EXPORT_SYMBOL(STATIC_CALL_KEY(name)); \ @@ -281,11 +292,14 @@ static inline long __static_call_return0(void) .func = _func_init, \ } +#define DEFINE_STATIC_CALL(name, _func) \ + __DEFINE_STATIC_CALL(name, _func, _func) + #define DEFINE_STATIC_CALL_NULL(name, _func) \ - DECLARE_STATIC_CALL(name, _func); \ - struct static_call_key STATIC_CALL_KEY(name) = { \ - .func = NULL, \ - } + __DEFINE_STATIC_CALL(name, _func, NULL) + +#define DEFINE_STATIC_CALL_RET0(name, _func) \ + __DEFINE_STATIC_CALL(name, _func, __static_call_return0) static inline void __static_call_nop(void) { } @@ -327,10 +341,4 @@ static inline int static_call_text_reserved(void *start, void *end) #endif /* CONFIG_HAVE_STATIC_CALL */ -#define DEFINE_STATIC_CALL(name, _func) \ - __DEFINE_STATIC_CALL(name, _func, _func) - -#define DEFINE_STATIC_CALL_RET0(name, _func) \ - __DEFINE_STATIC_CALL(name, _func, __static_call_return0) - #endif /* _LINUX_STATIC_CALL_H */ diff --git a/include/linux/stddef.h b/include/linux/stddef.h index ca507bd5f808..929d67710cc5 100644 --- a/include/linux/stddef.h +++ b/include/linux/stddef.h @@ -13,11 +13,7 @@ enum { }; #undef offsetof -#ifdef __compiler_offsetof -#define offsetof(TYPE, MEMBER) __compiler_offsetof(TYPE, MEMBER) -#else -#define offsetof(TYPE, MEMBER) ((size_t)&((TYPE *)0)->MEMBER) -#endif +#define offsetof(TYPE, MEMBER) __builtin_offsetof(TYPE, MEMBER) /** * sizeof_field() - Report the size of a struct field in bytes diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 24eea1b05ca2..fb2e88614f5d 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -257,9 +257,9 @@ struct plat_stmmacenet_data { u8 vlan_fail_q; unsigned int eee_usecs_rate; struct pci_dev *pdev; - bool has_crossts; int int_snapshot_num; int ext_snapshot_num; + bool int_snapshot_en; bool ext_snapshot_en; bool multi_msi_en; int msi_mac_vec; @@ -270,5 +270,6 @@ struct plat_stmmacenet_data { int msi_rx_base_vec; int msi_tx_base_vec; bool use_phy_wol; + bool sph_disable; }; #endif diff --git a/include/linux/stop_machine.h b/include/linux/stop_machine.h index 46fb3ebdd16e..ea7a74ea7389 100644 --- a/include/linux/stop_machine.h +++ b/include/linux/stop_machine.h @@ -124,6 +124,22 @@ int stop_machine(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus); */ int stop_machine_cpuslocked(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus); +/** + * stop_core_cpuslocked: - stop all threads on just one core + * @cpu: any cpu in the targeted core + * @fn: the function to run + * @data: the data ptr for @fn() + * + * Same as above, but instead of every CPU, only the logical CPUs of a + * single core are affected. + * + * Context: Must be called from within a cpus_read_lock() protected region. + * + * Return: 0 if all executions of @fn returned 0, any non zero return + * value if any returned non zero. + */ +int stop_core_cpuslocked(unsigned int cpu, cpu_stop_fn_t fn, void *data); + int stop_machine_from_inactive_cpu(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus); #else /* CONFIG_SMP || CONFIG_HOTPLUG_CPU */ diff --git a/include/linux/string.h b/include/linux/string.h index b6572aeca2f5..cf7607b32102 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -252,11 +252,58 @@ static inline const char *kbasename(const char *path) #if !defined(__NO_FORTIFY) && defined(__OPTIMIZE__) && defined(CONFIG_FORTIFY_SOURCE) #include <linux/fortify-string.h> #endif +#ifndef unsafe_memcpy +#define unsafe_memcpy(dst, src, bytes, justification) \ + memcpy(dst, src, bytes) +#endif void memcpy_and_pad(void *dest, size_t dest_len, const void *src, size_t count, int pad); /** + * strtomem_pad - Copy NUL-terminated string to non-NUL-terminated buffer + * + * @dest: Pointer of destination character array (marked as __nonstring) + * @src: Pointer to NUL-terminated string + * @pad: Padding character to fill any remaining bytes of @dest after copy + * + * This is a replacement for strncpy() uses where the destination is not + * a NUL-terminated string, but with bounds checking on the source size, and + * an explicit padding character. If padding is not required, use strtomem(). + * + * Note that the size of @dest is not an argument, as the length of @dest + * must be discoverable by the compiler. + */ +#define strtomem_pad(dest, src, pad) do { \ + const size_t _dest_len = __builtin_object_size(dest, 1); \ + \ + BUILD_BUG_ON(!__builtin_constant_p(_dest_len) || \ + _dest_len == (size_t)-1); \ + memcpy_and_pad(dest, _dest_len, src, strnlen(src, _dest_len), pad); \ +} while (0) + +/** + * strtomem - Copy NUL-terminated string to non-NUL-terminated buffer + * + * @dest: Pointer of destination character array (marked as __nonstring) + * @src: Pointer to NUL-terminated string + * + * This is a replacement for strncpy() uses where the destination is not + * a NUL-terminated string, but with bounds checking on the source size, and + * without trailing padding. If padding is required, use strtomem_pad(). + * + * Note that the size of @dest is not an argument, as the length of @dest + * must be discoverable by the compiler. + */ +#define strtomem(dest, src) do { \ + const size_t _dest_len = __builtin_object_size(dest, 1); \ + \ + BUILD_BUG_ON(!__builtin_constant_p(_dest_len) || \ + _dest_len == (size_t)-1); \ + memcpy(dest, src, min(_dest_len, strnlen(src, _dest_len))); \ +} while (0) + +/** * memset_after - Set a value after a struct member to the end of a struct * * @obj: Address of target struct instance diff --git a/include/linux/string_helpers.h b/include/linux/string_helpers.h index 4ba39e1403b2..8530c7328269 100644 --- a/include/linux/string_helpers.h +++ b/include/linux/string_helpers.h @@ -7,6 +7,7 @@ #include <linux/string.h> #include <linux/types.h> +struct device; struct file; struct task_struct; @@ -20,6 +21,8 @@ enum string_size_units { void string_get_size(u64 size, u64 blk_size, enum string_size_units units, char *buf, int len); +int parse_int_array_user(const char __user *from, size_t count, int **array); + #define UNESCAPE_SPACE BIT(0) #define UNESCAPE_OCTAL BIT(1) #define UNESCAPE_HEX BIT(2) @@ -100,6 +103,34 @@ char *kstrdup_quotable(const char *src, gfp_t gfp); char *kstrdup_quotable_cmdline(struct task_struct *task, gfp_t gfp); char *kstrdup_quotable_file(struct file *file, gfp_t gfp); +char **kasprintf_strarray(gfp_t gfp, const char *prefix, size_t n); void kfree_strarray(char **array, size_t n); +char **devm_kasprintf_strarray(struct device *dev, const char *prefix, size_t n); + +static inline const char *str_yes_no(bool v) +{ + return v ? "yes" : "no"; +} + +static inline const char *str_on_off(bool v) +{ + return v ? "on" : "off"; +} + +static inline const char *str_enable_disable(bool v) +{ + return v ? "enable" : "disable"; +} + +static inline const char *str_enabled_disabled(bool v) +{ + return v ? "enabled" : "disabled"; +} + +static inline const char *str_read_write(bool v) +{ + return v ? "read" : "write"; +} + #endif diff --git a/include/linux/sungem_phy.h b/include/linux/sungem_phy.h index 3a11fa41a131..c505f30e8b68 100644 --- a/include/linux/sungem_phy.h +++ b/include/linux/sungem_phy.h @@ -2,6 +2,8 @@ #ifndef __SUNGEM_PHY_H__ #define __SUNGEM_PHY_H__ +#include <linux/types.h> + struct mii_phy; /* Operations supported by any kind of PHY */ diff --git a/include/linux/sunrpc/auth.h b/include/linux/sunrpc/auth.h index 98da816b5fc2..3e6ce288a7fc 100644 --- a/include/linux/sunrpc/auth.h +++ b/include/linux/sunrpc/auth.h @@ -99,6 +99,7 @@ struct rpc_auth_create_args { /* Flags for rpcauth_lookupcred() */ #define RPCAUTH_LOOKUP_NEW 0x01 /* Accept an uninitialised cred */ +#define RPCAUTH_LOOKUP_ASYNC 0x02 /* Don't block waiting for memory */ /* * Client authentication ops diff --git a/include/linux/sunrpc/bc_xprt.h b/include/linux/sunrpc/bc_xprt.h index f07c334c599f..db30a159f9d5 100644 --- a/include/linux/sunrpc/bc_xprt.h +++ b/include/linux/sunrpc/bc_xprt.h @@ -1,22 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /****************************************************************************** (c) 2008 NetApp. All Rights Reserved. -NetApp provides this source code under the GPL v2 License. -The GPL v2 license is available at -https://opensource.org/licenses/gpl-license.php. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS -"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT -LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR -A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR -CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, -EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, -PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR -PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF -LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING -NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS -SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. ******************************************************************************/ @@ -83,4 +69,3 @@ static inline void xprt_free_bc_request(struct rpc_rqst *req) } #endif /* CONFIG_SUNRPC_BACKCHANNEL */ #endif /* _LINUX_SUNRPC_BC_XPRT_H */ - diff --git a/include/linux/sunrpc/cache.h b/include/linux/sunrpc/cache.h index b134b2b3371c..ec5a555df96f 100644 --- a/include/linux/sunrpc/cache.h +++ b/include/linux/sunrpc/cache.h @@ -121,17 +121,17 @@ struct cache_detail { struct net *net; }; - /* this must be embedded in any request structure that * identifies an object that will want a callback on * a cache fill */ struct cache_req { struct cache_deferred_req *(*defer)(struct cache_req *req); - int thread_wait; /* How long (jiffies) we can block the - * current thread to wait for updates. - */ + unsigned long thread_wait; /* How long (jiffies) we can block the + * current thread to wait for updates. + */ }; + /* this must be embedded in a deferred_request that is being * delayed awaiting cache-fill */ diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index 267b7aeaf1a6..770ef2cb5775 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -160,6 +160,7 @@ struct rpc_add_xprt_test { #define RPC_CLNT_CREATE_NO_RETRANS_TIMEOUT (1UL << 9) #define RPC_CLNT_CREATE_SOFTERR (1UL << 10) #define RPC_CLNT_CREATE_REUSEPORT (1UL << 11) +#define RPC_CLNT_CREATE_CONNECTED (1UL << 12) struct rpc_clnt *rpc_create(struct rpc_create_args *args); struct rpc_clnt *rpc_bind_new_program(struct rpc_clnt *, @@ -233,13 +234,19 @@ int rpc_clnt_setup_test_and_add_xprt(struct rpc_clnt *, struct rpc_xprt_switch *, struct rpc_xprt *, void *); +void rpc_clnt_manage_trunked_xprts(struct rpc_clnt *); +void rpc_clnt_probe_trunked_xprts(struct rpc_clnt *, + struct rpc_add_xprt_test *); const char *rpc_proc_name(const struct rpc_task *task); void rpc_clnt_xprt_switch_put(struct rpc_clnt *); void rpc_clnt_xprt_switch_add_xprt(struct rpc_clnt *, struct rpc_xprt *); +void rpc_clnt_xprt_switch_remove_xprt(struct rpc_clnt *, struct rpc_xprt *); bool rpc_clnt_xprt_switch_has_addr(struct rpc_clnt *clnt, const struct sockaddr *sap); +void rpc_clnt_xprt_set_online(struct rpc_clnt *clnt, struct rpc_xprt *xprt); +void rpc_clnt_disconnect(struct rpc_clnt *clnt); void rpc_cleanup_clids(void); static inline int rpc_reply_expected(struct rpc_task *task) diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index db964bb63912..b8ca3ecaf8d7 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -61,8 +61,6 @@ struct rpc_task { struct rpc_wait tk_wait; /* RPC wait */ } u; - int tk_rpc_status; /* Result of last RPC operation */ - /* * RPC call state */ @@ -82,6 +80,8 @@ struct rpc_task { ktime_t tk_start; /* RPC task init timestamp */ pid_t tk_owner; /* Process id for batching tasks */ + + int tk_rpc_status; /* Result of last RPC operation */ unsigned short tk_flags; /* misc flags */ unsigned short tk_timeouts; /* maj timeouts */ @@ -124,7 +124,6 @@ struct rpc_task_setup { #define RPC_TASK_MOVEABLE 0x0004 /* nfs4.1+ rpc tasks */ #define RPC_TASK_NULLCREDS 0x0010 /* Use AUTH_NULL credential */ #define RPC_CALL_MAJORSEEN 0x0020 /* major timeout seen */ -#define RPC_TASK_ROOTCREDS 0x0040 /* force root creds */ #define RPC_TASK_DYNAMIC 0x0080 /* task was kmalloc'ed */ #define RPC_TASK_NO_ROUND_ROBIN 0x0100 /* send requests on "main" xprt */ #define RPC_TASK_SOFT 0x0200 /* Use soft timeouts */ @@ -210,11 +209,17 @@ struct rpc_task *rpc_run_task(const struct rpc_task_setup *); struct rpc_task *rpc_run_bc_task(struct rpc_rqst *req); void rpc_put_task(struct rpc_task *); void rpc_put_task_async(struct rpc_task *); +bool rpc_task_set_rpc_status(struct rpc_task *task, int rpc_status); +void rpc_task_try_cancel(struct rpc_task *task, int error); void rpc_signal_task(struct rpc_task *); void rpc_exit_task(struct rpc_task *); void rpc_exit(struct rpc_task *, int); void rpc_release_calldata(const struct rpc_call_ops *, void *); void rpc_killall_tasks(struct rpc_clnt *); +unsigned long rpc_cancel_tasks(struct rpc_clnt *clnt, int error, + bool (*fnmatch)(const struct rpc_task *, + const void *), + const void *data); void rpc_execute(struct rpc_task *); void rpc_init_priority_wait_queue(struct rpc_wait_queue *, const char *); void rpc_init_wait_queue(struct rpc_wait_queue *, const char *); @@ -253,7 +258,7 @@ int rpc_malloc(struct rpc_task *); void rpc_free(struct rpc_task *); int rpciod_up(void); void rpciod_down(void); -int __rpc_wait_for_completion_task(struct rpc_task *task, wait_bit_action_f *); +int rpc_wait_for_completion_task(struct rpc_task *task); #if IS_ENABLED(CONFIG_SUNRPC_DEBUG) struct net; void rpc_show_tasks(struct net *); @@ -263,11 +268,7 @@ void rpc_destroy_mempool(void); extern struct workqueue_struct *rpciod_workqueue; extern struct workqueue_struct *xprtiod_workqueue; void rpc_prepare_task(struct rpc_task *task); - -static inline int rpc_wait_for_completion_task(struct rpc_task *task) -{ - return __rpc_wait_for_completion_task(task, NULL); -} +gfp_t rpc_task_gfp_mask(void); #if IS_ENABLED(CONFIG_SUNRPC_DEBUG) || IS_ENABLED(CONFIG_TRACEPOINTS) static inline const char * rpc_qname(const struct rpc_wait_queue *q) diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 0ae28ae6caf2..88de45491376 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -52,25 +52,6 @@ struct svc_pool { unsigned long sp_flags; } ____cacheline_aligned_in_smp; -struct svc_serv; - -struct svc_serv_ops { - /* Callback to use when last thread exits. */ - void (*svo_shutdown)(struct svc_serv *, struct net *); - - /* function for service threads to run */ - int (*svo_function)(void *); - - /* queue up a transport for servicing */ - void (*svo_enqueue_xprt)(struct svc_xprt *); - - /* set up thread (or whatever) execution context */ - int (*svo_setup)(struct svc_serv *, struct svc_pool *, int); - - /* optional module to count when adding threads (pooled svcs only) */ - struct module *svo_module; -}; - /* * RPC service. * @@ -85,6 +66,7 @@ struct svc_serv { struct svc_program * sv_program; /* RPC program */ struct svc_stat * sv_stats; /* RPC statistics */ spinlock_t sv_lock; + struct kref sv_refcnt; unsigned int sv_nrthreads; /* # of server threads */ unsigned int sv_maxconn; /* max connections allowed or * '0' causing max to be based @@ -102,7 +84,8 @@ struct svc_serv { unsigned int sv_nrpools; /* number of thread pools */ struct svc_pool * sv_pools; /* array of thread pools */ - const struct svc_serv_ops *sv_ops; /* server operations */ + int (*sv_threadfn)(void *data); + #if defined(CONFIG_SUNRPC_BACKCHANNEL) struct list_head sv_cb_list; /* queue for callback requests * that arrive over the same @@ -114,15 +97,43 @@ struct svc_serv { #endif /* CONFIG_SUNRPC_BACKCHANNEL */ }; -/* - * We use sv_nrthreads as a reference count. svc_destroy() drops - * this refcount, so we need to bump it up around operations that - * change the number of threads. Horrible, but there it is. - * Should be called with the "service mutex" held. +/** + * svc_get() - increment reference count on a SUNRPC serv + * @serv: the svc_serv to have count incremented + * + * Returns: the svc_serv that was passed in. + */ +static inline struct svc_serv *svc_get(struct svc_serv *serv) +{ + kref_get(&serv->sv_refcnt); + return serv; +} + +void svc_destroy(struct kref *); + +/** + * svc_put - decrement reference count on a SUNRPC serv + * @serv: the svc_serv to have count decremented + * + * When the reference count reaches zero, svc_destroy() + * is called to clean up and free the serv. */ -static inline void svc_get(struct svc_serv *serv) +static inline void svc_put(struct svc_serv *serv) { - serv->sv_nrthreads++; + kref_put(&serv->sv_refcnt, svc_destroy); +} + +/** + * svc_put_not_last - decrement non-final reference count on SUNRPC serv + * @serv: the svc_serv to have count decremented + * + * Returns: %true is refcount was decremented. + * + * If the refcount is 1, it is not decremented and instead failure is reported. + */ +static inline bool svc_put_not_last(struct svc_serv *serv) +{ + return refcount_dec_not_one(&serv->sv_refcnt.refcount); } /* @@ -246,7 +257,6 @@ struct svc_rqst { void * rq_xprt_ctxt; /* transport specific context ptr */ struct svc_deferred_req*rq_deferred; /* deferred request we are replaying */ - size_t rq_xprt_hlen; /* xprt header len */ struct xdr_buf rq_arg; struct xdr_stream rq_arg_stream; struct xdr_stream rq_res_stream; @@ -384,8 +394,8 @@ struct svc_deferred_req { size_t addrlen; struct sockaddr_storage daddr; /* where reply must come from */ size_t daddrlen; + void *xprt_ctxt; struct cache_deferred_req handle; - size_t xprt_hlen; int argslen; __be32 args[]; }; @@ -462,6 +472,7 @@ struct svc_procedure { /* XDR free result: */ void (*pc_release)(struct svc_rqst *); unsigned int pc_argsize; /* argument struct size */ + unsigned int pc_argzero; /* how much of argument to clear */ unsigned int pc_ressize; /* result struct size */ unsigned int pc_cachetype; /* cache info (NFS) */ unsigned int pc_xdrressize; /* maximum size of XDR reply */ @@ -469,53 +480,23 @@ struct svc_procedure { }; /* - * Mode for mapping cpus to pools. - */ -enum { - SVC_POOL_AUTO = -1, /* choose one of the others */ - SVC_POOL_GLOBAL, /* no mapping, just a single global pool - * (legacy & UP mode) */ - SVC_POOL_PERCPU, /* one pool per cpu */ - SVC_POOL_PERNODE /* one pool per numa node */ -}; - -struct svc_pool_map { - int count; /* How many svc_servs use us */ - int mode; /* Note: int not enum to avoid - * warnings about "enumeration value - * not handled in switch" */ - unsigned int npools; - unsigned int *pool_to; /* maps pool id to cpu or node */ - unsigned int *to_pool; /* maps cpu or node to pool id */ -}; - -extern struct svc_pool_map svc_pool_map; - -/* * Function prototypes. */ int svc_rpcb_setup(struct svc_serv *serv, struct net *net); void svc_rpcb_cleanup(struct svc_serv *serv, struct net *net); int svc_bind(struct svc_serv *serv, struct net *net); struct svc_serv *svc_create(struct svc_program *, unsigned int, - const struct svc_serv_ops *); + int (*threadfn)(void *data)); struct svc_rqst *svc_rqst_alloc(struct svc_serv *serv, struct svc_pool *pool, int node); -struct svc_rqst *svc_prepare_thread(struct svc_serv *serv, - struct svc_pool *pool, int node); void svc_rqst_replace_page(struct svc_rqst *rqstp, struct page *page); void svc_rqst_free(struct svc_rqst *); void svc_exit_thread(struct svc_rqst *); -unsigned int svc_pool_map_get(void); -void svc_pool_map_put(void); struct svc_serv * svc_create_pooled(struct svc_program *, unsigned int, - const struct svc_serv_ops *); + int (*threadfn)(void *data)); int svc_set_num_threads(struct svc_serv *, struct svc_pool *, int); -int svc_set_num_threads_sync(struct svc_serv *, struct svc_pool *, int); int svc_pool_stats_open(struct svc_serv *serv, struct file *file); -void svc_destroy(struct svc_serv *); -void svc_shutdown_net(struct svc_serv *, struct net *); int svc_process(struct svc_rqst *); int bc_svc_process(struct svc_serv *, struct rpc_rqst *, struct svc_rqst *); @@ -524,7 +505,7 @@ int svc_register(const struct svc_serv *, struct net *, const int, void svc_wake_up(struct svc_serv *); void svc_reserve(struct svc_rqst *rqstp, int space); -struct svc_pool * svc_pool_for_cpu(struct svc_serv *serv, int cpu); +struct svc_pool *svc_pool_for_cpu(struct svc_serv *serv); char * svc_print_addr(struct svc_rqst *, char *, size_t); const char * svc_proc_name(const struct svc_rqst *rqstp); int svc_encode_result_payload(struct svc_rqst *rqstp, @@ -564,16 +545,27 @@ static inline void svc_reserve_auth(struct svc_rqst *rqstp, int space) } /** - * svcxdr_init_decode - Prepare an xdr_stream for svc Call decoding + * svcxdr_init_decode - Prepare an xdr_stream for Call decoding * @rqstp: controlling server RPC transaction context * + * This function currently assumes the RPC header in rq_arg has + * already been decoded. Upon return, xdr->p points to the + * location of the upper layer header. */ static inline void svcxdr_init_decode(struct svc_rqst *rqstp) { struct xdr_stream *xdr = &rqstp->rq_arg_stream; - struct kvec *argv = rqstp->rq_arg.head; + struct xdr_buf *buf = &rqstp->rq_arg; + struct kvec *argv = buf->head; + + /* + * svc_getnl() and friends do not keep the xdr_buf's ::len + * field up to date. Refresh that field before initializing + * the argument decoding stream. + */ + buf->len = buf->head->iov_len + buf->page_len + buf->tail->iov_len; - xdr_init_decode(xdr, &rqstp->rq_arg, argv->iov_base, NULL); + xdr_init_decode(xdr, buf, argv->iov_base, NULL); xdr_set_scratch_page(xdr, rqstp->rq_scratch_page); } @@ -596,7 +588,7 @@ static inline void svcxdr_init_encode(struct svc_rqst *rqstp) xdr->end = resv->iov_base + PAGE_SIZE - rqstp->rq_auth_slack; buf->len = resv->iov_len; xdr->page_ptr = buf->pages - 1; - buf->buflen = PAGE_SIZE * (1 + rqstp->rq_page_end - buf->pages); + buf->buflen = PAGE_SIZE * (rqstp->rq_page_end - buf->pages); buf->buflen -= rqstp->rq_auth_slack; xdr->rqst = NULL; } diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h index 571f605bc91e..d42a75b3be10 100644 --- a/include/linux/sunrpc/svc_xprt.h +++ b/include/linux/sunrpc/svc_xprt.h @@ -28,6 +28,7 @@ struct svc_xprt_ops { void (*xpo_free)(struct svc_xprt *); void (*xpo_secure_port)(struct svc_rqst *rqstp); void (*xpo_kill_temp_xprt)(struct svc_xprt *); + void (*xpo_start_tls)(struct svc_xprt *); }; struct svc_xprt_class { @@ -88,6 +89,7 @@ struct svc_xprt { struct list_head xpt_users; /* callbacks on free */ struct net *xpt_net; + netns_tracker ns_tracker; const struct cred *xpt_cred; struct rpc_xprt *xpt_bc_xprt; /* NFSv4.1 backchannel */ struct rpc_xprt_switch *xpt_bc_xps; /* NFSv4.1 backchannel */ @@ -127,15 +129,16 @@ int svc_reg_xprt_class(struct svc_xprt_class *); void svc_unreg_xprt_class(struct svc_xprt_class *); void svc_xprt_init(struct net *, struct svc_xprt_class *, struct svc_xprt *, struct svc_serv *); -int svc_create_xprt(struct svc_serv *, const char *, struct net *, - const int, const unsigned short, int, - const struct cred *); +int svc_xprt_create(struct svc_serv *serv, const char *xprt_name, + struct net *net, const int family, + const unsigned short port, int flags, + const struct cred *cred); +void svc_xprt_destroy_all(struct svc_serv *serv, struct net *net); void svc_xprt_received(struct svc_xprt *xprt); -void svc_xprt_do_enqueue(struct svc_xprt *xprt); void svc_xprt_enqueue(struct svc_xprt *xprt); void svc_xprt_put(struct svc_xprt *xprt); void svc_xprt_copy_addrs(struct svc_rqst *rqstp, struct svc_xprt *xprt); -void svc_close_xprt(struct svc_xprt *xprt); +void svc_xprt_close(struct svc_xprt *xprt); int svc_port_is_privileged(struct sockaddr *sin); int svc_print_xprts(char *buf, int maxlen); struct svc_xprt *svc_find_xprt(struct svc_serv *serv, const char *xcl_name, diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index b519609af1d0..f84e2a1358e1 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -240,10 +240,12 @@ typedef int (*kxdrdproc_t)(struct rpc_rqst *rqstp, struct xdr_stream *xdr, extern void xdr_init_encode(struct xdr_stream *xdr, struct xdr_buf *buf, __be32 *p, struct rpc_rqst *rqst); +extern void xdr_init_encode_pages(struct xdr_stream *xdr, struct xdr_buf *buf, + struct page **pages, struct rpc_rqst *rqst); extern __be32 *xdr_reserve_space(struct xdr_stream *xdr, size_t nbytes); extern int xdr_reserve_space_vec(struct xdr_stream *xdr, struct kvec *vec, size_t nbytes); -extern void xdr_commit_encode(struct xdr_stream *xdr); +extern void __xdr_commit_encode(struct xdr_stream *xdr); extern void xdr_truncate_encode(struct xdr_stream *xdr, size_t len); extern int xdr_restrict_buflen(struct xdr_stream *xdr, int newbuflen); extern void xdr_write_pages(struct xdr_stream *xdr, struct page **pages, @@ -258,10 +260,13 @@ extern __be32 *xdr_inline_decode(struct xdr_stream *xdr, size_t nbytes); extern unsigned int xdr_read_pages(struct xdr_stream *xdr, unsigned int len); extern void xdr_enter_page(struct xdr_stream *xdr, unsigned int len); extern int xdr_process_buf(const struct xdr_buf *buf, unsigned int offset, unsigned int len, int (*actor)(struct scatterlist *, void *), void *data); -extern unsigned int xdr_align_data(struct xdr_stream *, unsigned int offset, unsigned int length); -extern unsigned int xdr_expand_hole(struct xdr_stream *, unsigned int offset, unsigned int length); +extern void xdr_set_pagelen(struct xdr_stream *, unsigned int len); extern bool xdr_stream_subsegment(struct xdr_stream *xdr, struct xdr_buf *subbuf, unsigned int len); +extern unsigned int xdr_stream_move_subsegment(struct xdr_stream *xdr, unsigned int offset, + unsigned int target, unsigned int length); +extern unsigned int xdr_stream_zero(struct xdr_stream *xdr, unsigned int offset, + unsigned int length); /** * xdr_set_scratch_buffer - Attach a scratch buffer for decoding data. @@ -307,6 +312,20 @@ xdr_reset_scratch_buffer(struct xdr_stream *xdr) } /** + * xdr_commit_encode - Ensure all data is written to xdr->buf + * @xdr: pointer to xdr_stream + * + * Handle encoding across page boundaries by giving the caller a + * temporary location to write to, then later copying the data into + * place. __xdr_commit_encode() does that copying. + */ +static inline void xdr_commit_encode(struct xdr_stream *xdr) +{ + if (unlikely(xdr->scratch.iov_len)) + __xdr_commit_encode(xdr); +} + +/** * xdr_stream_remaining - Return the number of bytes remaining in the stream * @xdr: pointer to struct xdr_stream * @@ -405,8 +424,8 @@ static inline int xdr_stream_encode_item_absent(struct xdr_stream *xdr) */ static inline __be32 *xdr_encode_bool(__be32 *p, u32 n) { - *p = n ? xdr_one : xdr_zero; - return p++; + *p++ = n ? xdr_one : xdr_zero; + return p; } /** @@ -731,6 +750,8 @@ xdr_stream_decode_uint32_array(struct xdr_stream *xdr, if (unlikely(xdr_stream_decode_u32(xdr, &len) < 0)) return -EBADMSG; + if (len > SIZE_MAX / sizeof(*p)) + return -EBADMSG; p = xdr_inline_decode(xdr, len * sizeof(*p)); if (unlikely(!p)) return -EBADMSG; diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 955ea4d7af0b..b9f59aabee53 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -139,9 +139,13 @@ struct rpc_xprt_ops { void (*rpcbind)(struct rpc_task *task); void (*set_port)(struct rpc_xprt *xprt, unsigned short port); void (*connect)(struct rpc_xprt *xprt, struct rpc_task *task); + int (*get_srcaddr)(struct rpc_xprt *xprt, char *buf, + size_t buflen); + unsigned short (*get_srcport)(struct rpc_xprt *xprt); int (*buf_alloc)(struct rpc_task *task); void (*buf_free)(struct rpc_task *task); - void (*prepare_request)(struct rpc_rqst *req); + int (*prepare_request)(struct rpc_rqst *req, + struct xdr_buf *buf); int (*send_request)(struct rpc_rqst *req); void (*wait_for_reply_request)(struct rpc_task *task); void (*timer)(struct rpc_xprt *xprt, struct rpc_task *task); @@ -284,6 +288,7 @@ struct rpc_xprt { } stat; struct net *xprt_net; + netns_tracker ns_tracker; const char *servername; const char *address_strings[RPC_DISPLAY_MAX]; #if IS_ENABLED(CONFIG_SUNRPC_DEBUG) @@ -354,10 +359,9 @@ int xprt_reserve_xprt_cong(struct rpc_xprt *xprt, struct rpc_task *task); void xprt_alloc_slot(struct rpc_xprt *xprt, struct rpc_task *task); void xprt_free_slot(struct rpc_xprt *xprt, struct rpc_rqst *req); -void xprt_request_prepare(struct rpc_rqst *req); bool xprt_prepare_transmit(struct rpc_task *task); void xprt_request_enqueue_transmit(struct rpc_task *task); -void xprt_request_enqueue_receive(struct rpc_task *task); +int xprt_request_enqueue_receive(struct rpc_task *task); void xprt_request_wait_receive(struct rpc_task *task); void xprt_request_dequeue_xprt(struct rpc_task *task); bool xprt_request_need_retransmit(struct rpc_task *task); @@ -502,4 +506,7 @@ static inline int xprt_test_and_set_binding(struct rpc_xprt *xprt) return test_and_set_bit(XPRT_BINDING, &xprt->state); } +void xprt_set_offline_locked(struct rpc_xprt *xprt, struct rpc_xprt_switch *xps); +void xprt_set_online_locked(struct rpc_xprt *xprt, struct rpc_xprt_switch *xps); +void xprt_delete_locked(struct rpc_xprt *xprt, struct rpc_xprt_switch *xps); #endif /* _LINUX_SUNRPC_XPRT_H */ diff --git a/include/linux/sunrpc/xprtmultipath.h b/include/linux/sunrpc/xprtmultipath.h index bbb8a5fa0816..c0514c684b2c 100644 --- a/include/linux/sunrpc/xprtmultipath.h +++ b/include/linux/sunrpc/xprtmultipath.h @@ -55,7 +55,7 @@ extern void rpc_xprt_switch_set_roundrobin(struct rpc_xprt_switch *xps); extern void rpc_xprt_switch_add_xprt(struct rpc_xprt_switch *xps, struct rpc_xprt *xprt); extern void rpc_xprt_switch_remove_xprt(struct rpc_xprt_switch *xps, - struct rpc_xprt *xprt); + struct rpc_xprt *xprt, bool offline); extern void xprt_iter_init(struct rpc_xprt_iter *xpi, struct rpc_xprt_switch *xps); @@ -63,8 +63,13 @@ extern void xprt_iter_init(struct rpc_xprt_iter *xpi, extern void xprt_iter_init_listall(struct rpc_xprt_iter *xpi, struct rpc_xprt_switch *xps); +extern void xprt_iter_init_listoffline(struct rpc_xprt_iter *xpi, + struct rpc_xprt_switch *xps); + extern void xprt_iter_destroy(struct rpc_xprt_iter *xpi); +extern void xprt_iter_rewind(struct rpc_xprt_iter *xpi); + extern struct rpc_xprt_switch *xprt_iter_xchg_switch( struct rpc_xprt_iter *xpi, struct rpc_xprt_switch *newswitch); diff --git a/include/linux/sunrpc/xprtsock.h b/include/linux/sunrpc/xprtsock.h index 8c2a712cb242..38284f25eddf 100644 --- a/include/linux/sunrpc/xprtsock.h +++ b/include/linux/sunrpc/xprtsock.h @@ -10,7 +10,6 @@ int init_socket_xprt(void); void cleanup_socket_xprt(void); -unsigned short get_srcport(struct rpc_xprt *); #define RPC_MIN_RESVPORT (1U) #define RPC_MAX_RESVPORT (65535U) @@ -89,5 +88,7 @@ struct sock_xprt { #define XPRT_SOCK_WAKE_WRITE (5) #define XPRT_SOCK_WAKE_PENDING (6) #define XPRT_SOCK_WAKE_DISCONNECT (7) +#define XPRT_SOCK_CONNECT_SENT (8) +#define XPRT_SOCK_NOSPACE (9) #endif /* _LINUX_SUNRPC_XPRTSOCK_H */ diff --git a/include/linux/surface_aggregator/controller.h b/include/linux/surface_aggregator/controller.h index 74bfdffaf7b0..d11a1c6e3186 100644 --- a/include/linux/surface_aggregator/controller.h +++ b/include/linux/surface_aggregator/controller.h @@ -470,6 +470,67 @@ struct ssam_request_spec_md { } /** + * SSAM_DEFINE_SYNC_REQUEST_WR() - Define synchronous SAM request function with + * both argument and return value. + * @name: Name of the generated function. + * @atype: Type of the request's argument. + * @rtype: Type of the request's return value. + * @spec: Specification (&struct ssam_request_spec) defining the request. + * + * Defines a function executing the synchronous SAM request specified by @spec, + * with the request taking an argument of type @atype and having a return value + * of type @rtype. The generated function takes care of setting up the request + * and response structs, buffer allocation, as well as execution of the request + * itself, returning once the request has been fully completed. The required + * transport buffer will be allocated on the stack. + * + * The generated function is defined as ``static int name(struct + * ssam_controller *ctrl, const atype *arg, rtype *ret)``, returning the status + * of the request, which is zero on success and negative on failure. The + * ``ctrl`` parameter is the controller via which the request is sent. The + * request argument is specified via the ``arg`` pointer. The request's return + * value is written to the memory pointed to by the ``ret`` parameter. + * + * Refer to ssam_request_sync_onstack() for more details on the behavior of + * the generated function. + */ +#define SSAM_DEFINE_SYNC_REQUEST_WR(name, atype, rtype, spec...) \ + static int name(struct ssam_controller *ctrl, const atype *arg, rtype *ret) \ + { \ + struct ssam_request_spec s = (struct ssam_request_spec)spec; \ + struct ssam_request rqst; \ + struct ssam_response rsp; \ + int status; \ + \ + rqst.target_category = s.target_category; \ + rqst.target_id = s.target_id; \ + rqst.command_id = s.command_id; \ + rqst.instance_id = s.instance_id; \ + rqst.flags = s.flags | SSAM_REQUEST_HAS_RESPONSE; \ + rqst.length = sizeof(atype); \ + rqst.payload = (u8 *)arg; \ + \ + rsp.capacity = sizeof(rtype); \ + rsp.length = 0; \ + rsp.pointer = (u8 *)ret; \ + \ + status = ssam_request_sync_onstack(ctrl, &rqst, &rsp, sizeof(atype)); \ + if (status) \ + return status; \ + \ + if (rsp.length != sizeof(rtype)) { \ + struct device *dev = ssam_controller_device(ctrl); \ + dev_err(dev, \ + "rqst: invalid response length, expected %zu, got %zu (tc: %#04x, cid: %#04x)", \ + sizeof(rtype), rsp.length, rqst.target_category,\ + rqst.command_id); \ + return -EIO; \ + } \ + \ + return 0; \ + } + +/** * SSAM_DEFINE_SYNC_REQUEST_MD_N() - Define synchronous multi-device SAM * request function with neither argument nor return value. * @name: Name of the generated function. @@ -613,6 +674,70 @@ struct ssam_request_spec_md { return 0; \ } +/** + * SSAM_DEFINE_SYNC_REQUEST_MD_WR() - Define synchronous multi-device SAM + * request function with both argument and return value. + * @name: Name of the generated function. + * @atype: Type of the request's argument. + * @rtype: Type of the request's return value. + * @spec: Specification (&struct ssam_request_spec_md) defining the request. + * + * Defines a function executing the synchronous SAM request specified by @spec, + * with the request taking an argument of type @atype and having a return value + * of type @rtype. Device specifying parameters are not hard-coded, but instead + * must be provided to the function. The generated function takes care of + * setting up the request and response structs, buffer allocation, as well as + * execution of the request itself, returning once the request has been fully + * completed. The required transport buffer will be allocated on the stack. + * + * The generated function is defined as ``static int name(struct + * ssam_controller *ctrl, u8 tid, u8 iid, const atype *arg, rtype *ret)``, + * returning the status of the request, which is zero on success and negative + * on failure. The ``ctrl`` parameter is the controller via which the request + * is sent, ``tid`` the target ID for the request, and ``iid`` the instance ID. + * The request argument is specified via the ``arg`` pointer. The request's + * return value is written to the memory pointed to by the ``ret`` parameter. + * + * Refer to ssam_request_sync_onstack() for more details on the behavior of + * the generated function. + */ +#define SSAM_DEFINE_SYNC_REQUEST_MD_WR(name, atype, rtype, spec...) \ + static int name(struct ssam_controller *ctrl, u8 tid, u8 iid, \ + const atype *arg, rtype *ret) \ + { \ + struct ssam_request_spec_md s = (struct ssam_request_spec_md)spec; \ + struct ssam_request rqst; \ + struct ssam_response rsp; \ + int status; \ + \ + rqst.target_category = s.target_category; \ + rqst.target_id = tid; \ + rqst.command_id = s.command_id; \ + rqst.instance_id = iid; \ + rqst.flags = s.flags | SSAM_REQUEST_HAS_RESPONSE; \ + rqst.length = sizeof(atype); \ + rqst.payload = (u8 *)arg; \ + \ + rsp.capacity = sizeof(rtype); \ + rsp.length = 0; \ + rsp.pointer = (u8 *)ret; \ + \ + status = ssam_request_sync_onstack(ctrl, &rqst, &rsp, sizeof(atype)); \ + if (status) \ + return status; \ + \ + if (rsp.length != sizeof(rtype)) { \ + struct device *dev = ssam_controller_device(ctrl); \ + dev_err(dev, \ + "rqst: invalid response length, expected %zu, got %zu (tc: %#04x, cid: %#04x)", \ + sizeof(rtype), rsp.length, rqst.target_category,\ + rqst.command_id); \ + return -EIO; \ + } \ + \ + return 0; \ + } + /* -- Event notifier/callbacks. --------------------------------------------- */ @@ -835,8 +960,28 @@ struct ssam_event_notifier { int ssam_notifier_register(struct ssam_controller *ctrl, struct ssam_event_notifier *n); -int ssam_notifier_unregister(struct ssam_controller *ctrl, - struct ssam_event_notifier *n); +int __ssam_notifier_unregister(struct ssam_controller *ctrl, + struct ssam_event_notifier *n, bool disable); + +/** + * ssam_notifier_unregister() - Unregister an event notifier. + * @ctrl: The controller the notifier has been registered on. + * @n: The event notifier to unregister. + * + * Unregister an event notifier. Decrement the usage counter of the associated + * SAM event if the notifier is not marked as an observer. If the usage counter + * reaches zero, the event will be disabled. + * + * Return: Returns zero on success, %-ENOENT if the given notifier block has + * not been registered on the controller. If the given notifier block was the + * last one associated with its specific event, returns the status of the + * event-disable EC-command. + */ +static inline int ssam_notifier_unregister(struct ssam_controller *ctrl, + struct ssam_event_notifier *n) +{ + return __ssam_notifier_unregister(ctrl, n, true); +} int ssam_controller_event_enable(struct ssam_controller *ctrl, struct ssam_event_registry reg, diff --git a/include/linux/surface_aggregator/device.h b/include/linux/surface_aggregator/device.h index cc257097eb05..46c45d1b6368 100644 --- a/include/linux/surface_aggregator/device.h +++ b/include/linux/surface_aggregator/device.h @@ -15,6 +15,7 @@ #include <linux/device.h> #include <linux/mod_devicetable.h> +#include <linux/property.h> #include <linux/types.h> #include <linux/surface_aggregator/controller.h> @@ -148,17 +149,30 @@ struct ssam_device_uid { #define SSAM_SDEV(cat, tid, iid, fun) \ SSAM_DEVICE(SSAM_DOMAIN_SERIALHUB, SSAM_SSH_TC_##cat, tid, iid, fun) +/* + * enum ssam_device_flags - Flags for SSAM client devices. + * @SSAM_DEVICE_HOT_REMOVED_BIT: + * The device has been hot-removed. Further communication with it may time + * out and should be avoided. + */ +enum ssam_device_flags { + SSAM_DEVICE_HOT_REMOVED_BIT = 0, +}; + /** * struct ssam_device - SSAM client device. - * @dev: Driver model representation of the device. - * @ctrl: SSAM controller managing this device. - * @uid: UID identifying the device. + * @dev: Driver model representation of the device. + * @ctrl: SSAM controller managing this device. + * @uid: UID identifying the device. + * @flags: Device state flags, see &enum ssam_device_flags. */ struct ssam_device { struct device dev; struct ssam_controller *ctrl; struct ssam_device_uid uid; + + unsigned long flags; }; /** @@ -177,6 +191,8 @@ struct ssam_device_driver { void (*remove)(struct ssam_device *sdev); }; +#ifdef CONFIG_SURFACE_AGGREGATOR_BUS + extern struct bus_type ssam_bus_type; extern const struct device_type ssam_device_type; @@ -193,6 +209,15 @@ static inline bool is_ssam_device(struct device *d) return d->type == &ssam_device_type; } +#else /* CONFIG_SURFACE_AGGREGATOR_BUS */ + +static inline bool is_ssam_device(struct device *d) +{ + return false; +} + +#endif /* CONFIG_SURFACE_AGGREGATOR_BUS */ + /** * to_ssam_device() - Casts the given device to a SSAM client device. * @d: The device to cast. @@ -241,6 +266,35 @@ int ssam_device_add(struct ssam_device *sdev); void ssam_device_remove(struct ssam_device *sdev); /** + * ssam_device_mark_hot_removed() - Mark the given device as hot-removed. + * @sdev: The device to mark as hot-removed. + * + * Mark the device as having been hot-removed. This signals drivers using the + * device that communication with the device should be avoided and may lead to + * timeouts. + */ +static inline void ssam_device_mark_hot_removed(struct ssam_device *sdev) +{ + dev_dbg(&sdev->dev, "marking device as hot-removed\n"); + set_bit(SSAM_DEVICE_HOT_REMOVED_BIT, &sdev->flags); +} + +/** + * ssam_device_is_hot_removed() - Check if the given device has been + * hot-removed. + * @sdev: The device to check. + * + * Checks if the given device has been marked as hot-removed. See + * ssam_device_mark_hot_removed() for more details. + * + * Return: Returns ``true`` if the device has been marked as hot-removed. + */ +static inline bool ssam_device_is_hot_removed(struct ssam_device *sdev) +{ + return test_bit(SSAM_DEVICE_HOT_REMOVED_BIT, &sdev->flags); +} + +/** * ssam_device_get() - Increment reference count of SSAM client device. * @sdev: The device to increment the reference count of. * @@ -322,11 +376,62 @@ void ssam_device_driver_unregister(struct ssam_device_driver *d); /* -- Helpers for controller and hub devices. ------------------------------- */ #ifdef CONFIG_SURFACE_AGGREGATOR_BUS + +int __ssam_register_clients(struct device *parent, struct ssam_controller *ctrl, + struct fwnode_handle *node); void ssam_remove_clients(struct device *dev); + #else /* CONFIG_SURFACE_AGGREGATOR_BUS */ + +static inline int __ssam_register_clients(struct device *parent, struct ssam_controller *ctrl, + struct fwnode_handle *node) +{ + return 0; +} + static inline void ssam_remove_clients(struct device *dev) {} + #endif /* CONFIG_SURFACE_AGGREGATOR_BUS */ +/** + * ssam_register_clients() - Register all client devices defined under the + * given parent device. + * @dev: The parent device under which clients should be registered. + * @ctrl: The controller with which client should be registered. + * + * Register all clients that have via firmware nodes been defined as children + * of the given (parent) device. The respective child firmware nodes will be + * associated with the correspondingly created child devices. + * + * The given controller will be used to instantiate the new devices. See + * ssam_device_add() for details. + * + * Return: Returns zero on success, nonzero on failure. + */ +static inline int ssam_register_clients(struct device *dev, struct ssam_controller *ctrl) +{ + return __ssam_register_clients(dev, ctrl, dev_fwnode(dev)); +} + +/** + * ssam_device_register_clients() - Register all client devices defined under + * the given SSAM parent device. + * @sdev: The parent device under which clients should be registered. + * + * Register all clients that have via firmware nodes been defined as children + * of the given (parent) device. The respective child firmware nodes will be + * associated with the correspondingly created child devices. + * + * The controller used by the parent device will be used to instantiate the new + * devices. See ssam_device_add() for details. + * + * Return: Returns zero on success, nonzero on failure. + */ +static inline int ssam_device_register_clients(struct ssam_device *sdev) +{ + return ssam_register_clients(&sdev->dev, sdev->ctrl); +} + /* -- Helpers for client-device requests. ----------------------------------- */ @@ -430,4 +535,106 @@ static inline void ssam_remove_clients(struct device *dev) {} sdev->uid.instance, ret); \ } +/** + * SSAM_DEFINE_SYNC_REQUEST_CL_WR() - Define synchronous client-device SAM + * request function with argument and return value. + * @name: Name of the generated function. + * @atype: Type of the request's argument. + * @rtype: Type of the request's return value. + * @spec: Specification (&struct ssam_request_spec_md) defining the request. + * + * Defines a function executing the synchronous SAM request specified by @spec, + * with the request taking an argument of type @atype and having a return value + * of type @rtype. Device specifying parameters are not hard-coded, but instead + * are provided via the client device, specifically its UID, supplied when + * calling this function. The generated function takes care of setting up the + * request struct, buffer allocation, as well as execution of the request + * itself, returning once the request has been fully completed. The required + * transport buffer will be allocated on the stack. + * + * The generated function is defined as ``static int name(struct ssam_device + * *sdev, const atype *arg, rtype *ret)``, returning the status of the request, + * which is zero on success and negative on failure. The ``sdev`` parameter + * specifies both the target device of the request and by association the + * controller via which the request is sent. The request's argument is + * specified via the ``arg`` pointer. The request's return value is written to + * the memory pointed to by the ``ret`` parameter. + * + * Refer to ssam_request_sync_onstack() for more details on the behavior of + * the generated function. + */ +#define SSAM_DEFINE_SYNC_REQUEST_CL_WR(name, atype, rtype, spec...) \ + SSAM_DEFINE_SYNC_REQUEST_MD_WR(__raw_##name, atype, rtype, spec) \ + static int name(struct ssam_device *sdev, const atype *arg, rtype *ret) \ + { \ + return __raw_##name(sdev->ctrl, sdev->uid.target, \ + sdev->uid.instance, arg, ret); \ + } + + +/* -- Helpers for client-device notifiers. ---------------------------------- */ + +/** + * ssam_device_notifier_register() - Register an event notifier for the + * specified client device. + * @sdev: The device the notifier should be registered on. + * @n: The event notifier to register. + * + * Register an event notifier. Increment the usage counter of the associated + * SAM event if the notifier is not marked as an observer. If the event is not + * marked as an observer and is currently not enabled, it will be enabled + * during this call. If the notifier is marked as an observer, no attempt will + * be made at enabling any event and no reference count will be modified. + * + * Notifiers marked as observers do not need to be associated with one specific + * event, i.e. as long as no event matching is performed, only the event target + * category needs to be set. + * + * Return: Returns zero on success, %-ENOSPC if there have already been + * %INT_MAX notifiers for the event ID/type associated with the notifier block + * registered, %-ENOMEM if the corresponding event entry could not be + * allocated, %-ENODEV if the device is marked as hot-removed. If this is the + * first time that a notifier block is registered for the specific associated + * event, returns the status of the event-enable EC-command. + */ +static inline int ssam_device_notifier_register(struct ssam_device *sdev, + struct ssam_event_notifier *n) +{ + /* + * Note that this check does not provide any guarantees whatsoever as + * hot-removal could happen at any point and we can't protect against + * it. Nevertheless, if we can detect hot-removal, bail early to avoid + * communication timeouts. + */ + if (ssam_device_is_hot_removed(sdev)) + return -ENODEV; + + return ssam_notifier_register(sdev->ctrl, n); +} + +/** + * ssam_device_notifier_unregister() - Unregister an event notifier for the + * specified client device. + * @sdev: The device the notifier has been registered on. + * @n: The event notifier to unregister. + * + * Unregister an event notifier. Decrement the usage counter of the associated + * SAM event if the notifier is not marked as an observer. If the usage counter + * reaches zero, the event will be disabled. + * + * In case the device has been marked as hot-removed, the event will not be + * disabled on the EC, as in those cases any attempt at doing so may time out. + * + * Return: Returns zero on success, %-ENOENT if the given notifier block has + * not been registered on the controller. If the given notifier block was the + * last one associated with its specific event, returns the status of the + * event-disable EC-command. + */ +static inline int ssam_device_notifier_unregister(struct ssam_device *sdev, + struct ssam_event_notifier *n) +{ + return __ssam_notifier_unregister(sdev->ctrl, n, + !ssam_device_is_hot_removed(sdev)); +} + #endif /* _LINUX_SURFACE_AGGREGATOR_DEVICE_H */ diff --git a/include/linux/surface_aggregator/serial_hub.h b/include/linux/surface_aggregator/serial_hub.h index c3de43edcffa..45501b6e54e8 100644 --- a/include/linux/surface_aggregator/serial_hub.h +++ b/include/linux/surface_aggregator/serial_hub.h @@ -201,7 +201,7 @@ static inline u16 ssh_crc(const u8 *buf, size_t len) * exception of zero, which is not an event ID. Thus, this is also the * absolute maximum number of event handlers that can be registered. */ -#define SSH_NUM_EVENTS 34 +#define SSH_NUM_EVENTS 38 /* * SSH_NUM_TARGETS - The number of communication targets used in the protocol. @@ -292,40 +292,45 @@ struct ssam_span { * Windows driver. */ enum ssam_ssh_tc { - /* Category 0x00 is invalid for EC use. */ - SSAM_SSH_TC_SAM = 0x01, /* Generic system functionality, real-time clock. */ - SSAM_SSH_TC_BAT = 0x02, /* Battery/power subsystem. */ - SSAM_SSH_TC_TMP = 0x03, /* Thermal subsystem. */ - SSAM_SSH_TC_PMC = 0x04, - SSAM_SSH_TC_FAN = 0x05, - SSAM_SSH_TC_PoM = 0x06, - SSAM_SSH_TC_DBG = 0x07, - SSAM_SSH_TC_KBD = 0x08, /* Legacy keyboard (Laptop 1/2). */ - SSAM_SSH_TC_FWU = 0x09, - SSAM_SSH_TC_UNI = 0x0a, - SSAM_SSH_TC_LPC = 0x0b, - SSAM_SSH_TC_TCL = 0x0c, - SSAM_SSH_TC_SFL = 0x0d, - SSAM_SSH_TC_KIP = 0x0e, - SSAM_SSH_TC_EXT = 0x0f, - SSAM_SSH_TC_BLD = 0x10, - SSAM_SSH_TC_BAS = 0x11, /* Detachment system (Surface Book 2/3). */ - SSAM_SSH_TC_SEN = 0x12, - SSAM_SSH_TC_SRQ = 0x13, - SSAM_SSH_TC_MCU = 0x14, - SSAM_SSH_TC_HID = 0x15, /* Generic HID input subsystem. */ - SSAM_SSH_TC_TCH = 0x16, - SSAM_SSH_TC_BKL = 0x17, - SSAM_SSH_TC_TAM = 0x18, - SSAM_SSH_TC_ACC = 0x19, - SSAM_SSH_TC_UFI = 0x1a, - SSAM_SSH_TC_USC = 0x1b, - SSAM_SSH_TC_PEN = 0x1c, - SSAM_SSH_TC_VID = 0x1d, - SSAM_SSH_TC_AUD = 0x1e, - SSAM_SSH_TC_SMC = 0x1f, - SSAM_SSH_TC_KPD = 0x20, - SSAM_SSH_TC_REG = 0x21, /* Extended event registry. */ + /* Category 0x00 is invalid for EC use. */ + SSAM_SSH_TC_SAM = 0x01, /* Generic system functionality, real-time clock. */ + SSAM_SSH_TC_BAT = 0x02, /* Battery/power subsystem. */ + SSAM_SSH_TC_TMP = 0x03, /* Thermal subsystem. */ + SSAM_SSH_TC_PMC = 0x04, + SSAM_SSH_TC_FAN = 0x05, + SSAM_SSH_TC_PoM = 0x06, + SSAM_SSH_TC_DBG = 0x07, + SSAM_SSH_TC_KBD = 0x08, /* Legacy keyboard (Laptop 1/2). */ + SSAM_SSH_TC_FWU = 0x09, + SSAM_SSH_TC_UNI = 0x0a, + SSAM_SSH_TC_LPC = 0x0b, + SSAM_SSH_TC_TCL = 0x0c, + SSAM_SSH_TC_SFL = 0x0d, + SSAM_SSH_TC_KIP = 0x0e, /* Manages detachable peripherals (Pro X/8 keyboard cover) */ + SSAM_SSH_TC_EXT = 0x0f, + SSAM_SSH_TC_BLD = 0x10, + SSAM_SSH_TC_BAS = 0x11, /* Detachment system (Surface Book 2/3). */ + SSAM_SSH_TC_SEN = 0x12, + SSAM_SSH_TC_SRQ = 0x13, + SSAM_SSH_TC_MCU = 0x14, + SSAM_SSH_TC_HID = 0x15, /* Generic HID input subsystem. */ + SSAM_SSH_TC_TCH = 0x16, + SSAM_SSH_TC_BKL = 0x17, + SSAM_SSH_TC_TAM = 0x18, + SSAM_SSH_TC_ACC0 = 0x19, + SSAM_SSH_TC_UFI = 0x1a, + SSAM_SSH_TC_USC = 0x1b, + SSAM_SSH_TC_PEN = 0x1c, + SSAM_SSH_TC_VID = 0x1d, + SSAM_SSH_TC_AUD = 0x1e, + SSAM_SSH_TC_SMC = 0x1f, + SSAM_SSH_TC_KPD = 0x20, + SSAM_SSH_TC_REG = 0x21, /* Extended event registry. */ + SSAM_SSH_TC_SPT = 0x22, + SSAM_SSH_TC_SYS = 0x23, + SSAM_SSH_TC_ACC1 = 0x24, + SSAM_SSH_TC_SHB = 0x25, + SSAM_SSH_TC_POS = 0x26, /* For obtaining Laptop Studio screen position. */ }; diff --git a/include/linux/suspend.h b/include/linux/suspend.h index 5785d909c321..cfe19a028918 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -75,7 +75,7 @@ extern struct suspend_stats suspend_stats; static inline void dpm_save_failed_dev(const char *name) { - strlcpy(suspend_stats.failed_devs[suspend_stats.last_failed_dev], + strscpy(suspend_stats.failed_devs[suspend_stats.last_failed_dev], name, sizeof(suspend_stats.failed_devs[0])); suspend_stats.last_failed_dev++; @@ -191,6 +191,7 @@ struct platform_s2idle_ops { int (*begin)(void); int (*prepare)(void); int (*prepare_late)(void); + void (*check)(void); bool (*wake)(void); void (*restore_early)(void); void (*restore)(void); @@ -430,15 +431,7 @@ struct platform_hibernation_ops { #ifdef CONFIG_HIBERNATION /* kernel/power/snapshot.c */ -extern void __register_nosave_region(unsigned long b, unsigned long e, int km); -static inline void __init register_nosave_region(unsigned long b, unsigned long e) -{ - __register_nosave_region(b, e, 0); -} -static inline void __init register_nosave_region_late(unsigned long b, unsigned long e) -{ - __register_nosave_region(b, e, 1); -} +extern void register_nosave_region(unsigned long b, unsigned long e); extern int swsusp_page_is_forbidden(struct page *); extern void swsusp_set_page_free(struct page *); extern void swsusp_unset_page_free(struct page *); @@ -458,7 +451,6 @@ int pfn_is_nosave(unsigned long pfn); int hibernate_quiet_exec(int (*func)(void *data), void *data); #else /* CONFIG_HIBERNATION */ static inline void register_nosave_region(unsigned long b, unsigned long e) {} -static inline void register_nosave_region_late(unsigned long b, unsigned long e) {} static inline int swsusp_page_is_forbidden(struct page *p) { return 0; } static inline void swsusp_set_page_free(struct page *p) {} static inline void swsusp_unset_page_free(struct page *p) {} @@ -506,21 +498,21 @@ extern void ksys_sync_helper(void); /* drivers/base/power/wakeup.c */ extern bool events_check_enabled; -extern unsigned int pm_wakeup_irq; extern suspend_state_t pm_suspend_target_state; extern bool pm_wakeup_pending(void); extern void pm_system_wakeup(void); extern void pm_system_cancel_wakeup(void); -extern void pm_wakeup_clear(bool reset); +extern void pm_wakeup_clear(unsigned int irq_number); extern void pm_system_irq_wakeup(unsigned int irq_number); +extern unsigned int pm_wakeup_irq(void); extern bool pm_get_wakeup_count(unsigned int *count, bool block); extern bool pm_save_wakeup_count(unsigned int count); extern void pm_wakep_autosleep_enabled(bool set); extern void pm_print_active_wakeup_sources(void); -extern void lock_system_sleep(void); -extern void unlock_system_sleep(void); +extern unsigned int lock_system_sleep(void); +extern void unlock_system_sleep(unsigned int); #else /* !CONFIG_PM_SLEEP */ @@ -543,30 +535,64 @@ static inline void pm_system_wakeup(void) {} static inline void pm_wakeup_clear(bool reset) {} static inline void pm_system_irq_wakeup(unsigned int irq_number) {} -static inline void lock_system_sleep(void) {} -static inline void unlock_system_sleep(void) {} +static inline unsigned int lock_system_sleep(void) { return 0; } +static inline void unlock_system_sleep(unsigned int flags) {} #endif /* !CONFIG_PM_SLEEP */ #ifdef CONFIG_PM_SLEEP_DEBUG extern bool pm_print_times_enabled; extern bool pm_debug_messages_on; -extern __printf(2, 3) void __pm_pr_dbg(bool defer, const char *fmt, ...); +static inline int pm_dyn_debug_messages_on(void) +{ +#ifdef CONFIG_DYNAMIC_DEBUG + return 1; +#else + return 0; +#endif +} +#ifndef pr_fmt +#define pr_fmt(fmt) "PM: " fmt +#endif +#define __pm_pr_dbg(fmt, ...) \ + do { \ + if (pm_debug_messages_on) \ + printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__); \ + else if (pm_dyn_debug_messages_on()) \ + pr_debug(fmt, ##__VA_ARGS__); \ + } while (0) +#define __pm_deferred_pr_dbg(fmt, ...) \ + do { \ + if (pm_debug_messages_on) \ + printk_deferred(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__); \ + } while (0) #else #define pm_print_times_enabled (false) #define pm_debug_messages_on (false) #include <linux/printk.h> -#define __pm_pr_dbg(defer, fmt, ...) \ - no_printk(KERN_DEBUG fmt, ##__VA_ARGS__) +#define __pm_pr_dbg(fmt, ...) \ + no_printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) +#define __pm_deferred_pr_dbg(fmt, ...) \ + no_printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) #endif +/** + * pm_pr_dbg - print pm sleep debug messages + * + * If pm_debug_messages_on is enabled, print message. + * If pm_debug_messages_on is disabled and CONFIG_DYNAMIC_DEBUG is enabled, + * print message only from instances explicitly enabled on dynamic debug's + * control. + * If pm_debug_messages_on is disabled and CONFIG_DYNAMIC_DEBUG is disabled, + * don't print message. + */ #define pm_pr_dbg(fmt, ...) \ - __pm_pr_dbg(false, fmt, ##__VA_ARGS__) + __pm_pr_dbg(fmt, ##__VA_ARGS__) #define pm_deferred_pr_dbg(fmt, ...) \ - __pm_pr_dbg(true, fmt, ##__VA_ARGS__) + __pm_deferred_pr_dbg(fmt, ##__VA_ARGS__) #ifdef CONFIG_PM_AUTOSLEEP diff --git a/include/linux/swab.h b/include/linux/swab.h index bcff5149861a..9b804dbb0d79 100644 --- a/include/linux/swab.h +++ b/include/linux/swab.h @@ -20,4 +20,29 @@ # define swab64s __swab64s # define swahw32s __swahw32s # define swahb32s __swahb32s + +static inline void swab16_array(u16 *buf, unsigned int words) +{ + while (words--) { + swab16s(buf); + buf++; + } +} + +static inline void swab32_array(u32 *buf, unsigned int words) +{ + while (words--) { + swab32s(buf); + buf++; + } +} + +static inline void swab64_array(u64 *buf, unsigned int words) +{ + while (words--) { + swab64s(buf); + buf++; + } +} + #endif /* _LINUX_SWAB_H */ diff --git a/include/linux/swait_api.h b/include/linux/swait_api.h new file mode 100644 index 000000000000..1eeaaaaa5ea7 --- /dev/null +++ b/include/linux/swait_api.h @@ -0,0 +1 @@ +#include <linux/swait.h> diff --git a/include/linux/swap.h b/include/linux/swap.h index d1ea44b31f19..a18cf4b7c724 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -55,9 +55,26 @@ static inline int current_is_kswapd(void) * actions on faults. */ +#define SWP_SWAPIN_ERROR_NUM 1 +#define SWP_SWAPIN_ERROR (MAX_SWAPFILES + SWP_HWPOISON_NUM + \ + SWP_MIGRATION_NUM + SWP_DEVICE_NUM + \ + SWP_PTE_MARKER_NUM) +/* + * PTE markers are used to persist information onto PTEs that are mapped with + * file-backed memories. As its name "PTE" hints, it should only be applied to + * the leaves of pgtables. + */ +#ifdef CONFIG_PTE_MARKER +#define SWP_PTE_MARKER_NUM 1 +#define SWP_PTE_MARKER (MAX_SWAPFILES + SWP_HWPOISON_NUM + \ + SWP_MIGRATION_NUM + SWP_DEVICE_NUM) +#else +#define SWP_PTE_MARKER_NUM 0 +#endif + /* * Unaddressable device memory support. See include/linux/hmm.h and - * Documentation/vm/hmm.rst. Short description is we need struct pages for + * Documentation/mm/hmm.rst. Short description is we need struct pages for * device memory that is unaddressable (inaccessible) by CPU, so that we can * migrate part of a process memory to device memory. * @@ -78,12 +95,19 @@ static inline int current_is_kswapd(void) #endif /* - * NUMA node memory migration support + * Page migration support. + * + * SWP_MIGRATION_READ_EXCLUSIVE is only applicable to anonymous pages and + * indicates that the referenced (part of) an anonymous page is exclusive to + * a single process. For SWP_MIGRATION_WRITE, that information is implicit: + * (part of) an anonymous page that are mapped writable are exclusive to a + * single process. */ #ifdef CONFIG_MIGRATION -#define SWP_MIGRATION_NUM 2 -#define SWP_MIGRATION_READ (MAX_SWAPFILES + SWP_HWPOISON_NUM) -#define SWP_MIGRATION_WRITE (MAX_SWAPFILES + SWP_HWPOISON_NUM + 1) +#define SWP_MIGRATION_NUM 3 +#define SWP_MIGRATION_READ (MAX_SWAPFILES + SWP_HWPOISON_NUM) +#define SWP_MIGRATION_READ_EXCLUSIVE (MAX_SWAPFILES + SWP_HWPOISON_NUM + 1) +#define SWP_MIGRATION_WRITE (MAX_SWAPFILES + SWP_HWPOISON_NUM + 2) #else #define SWP_MIGRATION_NUM 0 #endif @@ -100,7 +124,8 @@ static inline int current_is_kswapd(void) #define MAX_SWAPFILES \ ((1 << MAX_SWAPFILES_SHIFT) - SWP_DEVICE_NUM - \ - SWP_MIGRATION_NUM - SWP_HWPOISON_NUM) + SWP_MIGRATION_NUM - SWP_HWPOISON_NUM - \ + SWP_PTE_MARKER_NUM - SWP_SWAPIN_ERROR_NUM) /* * Magic header for a swap area. The first part of the union is @@ -137,6 +162,10 @@ union swap_header { */ struct reclaim_state { unsigned long reclaimed_slab; +#ifdef CONFIG_LRU_GEN + /* per-thread mm walk data */ + struct lru_gen_mm_walk *mm_walk; +#endif }; #ifdef __KERNEL__ @@ -148,8 +177,8 @@ struct zone; /* * A swap extent maps a range of a swapfile's PAGE_SIZE pages onto a range of - * disk blocks. A list of swap extents maps the entire swapfile. (Where the - * term `swapfile' refers to either a blockdevice or an IS_REG file. Apart + * disk blocks. A rbtree of swap extents maps the entire swapfile (Where the + * term `swapfile' refers to either a blockdevice or an IS_REG file). Apart * from setup, they're handled identically. * * We always assume that blocks are of size PAGE_SIZE. @@ -326,17 +355,25 @@ static inline swp_entry_t folio_swap_entry(struct folio *folio) return entry; } +static inline void folio_set_swap_entry(struct folio *folio, swp_entry_t entry) +{ + folio->private = (void *)entry.val; +} + /* linux/mm/workingset.c */ void workingset_age_nonresident(struct lruvec *lruvec, unsigned long nr_pages); -void *workingset_eviction(struct page *page, struct mem_cgroup *target_memcg); +void *workingset_eviction(struct folio *folio, struct mem_cgroup *target_memcg); void workingset_refault(struct folio *folio, void *shadow); void workingset_activation(struct folio *folio); /* Only track the nodes of mappings with shadow entries */ void workingset_update_node(struct xa_node *node); +extern struct list_lru shadow_nodes; #define mapping_set_update(xas, mapping) do { \ - if (!dax_mapping(mapping) && !shmem_mapping(mapping)) \ + if (!dax_mapping(mapping) && !shmem_mapping(mapping)) { \ xas_set_update(xas, workingset_update_node); \ + xas_set_lru(xas, &shadow_nodes); \ + } \ } while (0) /* linux/mm/page_alloc.c */ @@ -347,11 +384,11 @@ extern unsigned long totalreserve_pages; /* linux/mm/swap.c */ -extern void lru_note_cost(struct lruvec *lruvec, bool file, - unsigned int nr_pages); -extern void lru_note_cost_folio(struct folio *); -extern void folio_add_lru(struct folio *); -extern void lru_cache_add(struct page *); +void lru_note_cost(struct lruvec *lruvec, bool file, unsigned int nr_pages); +void lru_note_cost_folio(struct folio *); +void folio_add_lru(struct folio *); +void folio_add_lru_vma(struct folio *, struct vm_area_struct *); +void lru_cache_add(struct page *); void mark_page_accessed(struct page *); void folio_mark_accessed(struct folio *); @@ -372,7 +409,6 @@ extern void lru_add_drain(void); extern void lru_add_drain_cpu(int cpu); extern void lru_add_drain_cpu_zone(struct zone *zone); extern void lru_add_drain_all(void); -extern void deactivate_file_page(struct page *page); extern void deactivate_page(struct page *page); extern void mark_page_lazyfree(struct page *page); extern void swap_setup(void); @@ -384,18 +420,20 @@ extern void lru_cache_add_inactive_or_unevictable(struct page *page, extern unsigned long zone_reclaimable_pages(struct zone *zone); extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order, gfp_t gfp_mask, nodemask_t *mask); -extern bool __isolate_lru_page_prepare(struct page *page, isolate_mode_t mode); + +#define MEMCG_RECLAIM_MAY_SWAP (1 << 1) +#define MEMCG_RECLAIM_PROACTIVE (1 << 2) extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, unsigned long nr_pages, gfp_t gfp_mask, - bool may_swap); + unsigned int reclaim_options); extern unsigned long mem_cgroup_shrink_node(struct mem_cgroup *mem, gfp_t gfp_mask, bool noswap, pg_data_t *pgdat, unsigned long *nr_scanned); extern unsigned long shrink_all_memory(unsigned long nr_pages); extern int vm_swappiness; -extern int remove_mapping(struct address_space *mapping, struct page *page); +long remove_mapping(struct address_space *mapping, struct folio *folio); extern unsigned long reclaim_pages(struct list_head *page_list); #ifdef CONFIG_NUMA @@ -412,69 +450,27 @@ static inline bool node_reclaim_enabled(void) return node_reclaim_mode & (RECLAIM_ZONE|RECLAIM_WRITE|RECLAIM_UNMAP); } -extern void check_move_unevictable_pages(struct pagevec *pvec); +void check_move_unevictable_folios(struct folio_batch *fbatch); +void check_move_unevictable_pages(struct pagevec *pvec); extern void kswapd_run(int nid); extern void kswapd_stop(int nid); #ifdef CONFIG_SWAP -#include <linux/blk_types.h> /* for bio_end_io_t */ - -/* linux/mm/page_io.c */ -extern int swap_readpage(struct page *page, bool do_poll); -extern int swap_writepage(struct page *page, struct writeback_control *wbc); -extern void end_swap_bio_write(struct bio *bio); -extern int __swap_writepage(struct page *page, struct writeback_control *wbc, - bio_end_io_t end_write_func); -extern int swap_set_page_dirty(struct page *page); - int add_swap_extent(struct swap_info_struct *sis, unsigned long start_page, unsigned long nr_pages, sector_t start_block); int generic_swapfile_activate(struct swap_info_struct *, struct file *, sector_t *); -/* linux/mm/swap_state.c */ -/* One swap address space for each 64M swap space */ -#define SWAP_ADDRESS_SPACE_SHIFT 14 -#define SWAP_ADDRESS_SPACE_PAGES (1 << SWAP_ADDRESS_SPACE_SHIFT) -extern struct address_space *swapper_spaces[]; -#define swap_address_space(entry) \ - (&swapper_spaces[swp_type(entry)][swp_offset(entry) \ - >> SWAP_ADDRESS_SPACE_SHIFT]) static inline unsigned long total_swapcache_pages(void) { return global_node_page_state(NR_SWAPCACHE); } -extern void show_swap_cache_info(void); -extern int add_to_swap(struct page *page); -extern void *get_shadow_from_swap_cache(swp_entry_t entry); -extern int add_to_swap_cache(struct page *page, swp_entry_t entry, - gfp_t gfp, void **shadowp); -extern void __delete_from_swap_cache(struct page *page, - swp_entry_t entry, void *shadow); -extern void delete_from_swap_cache(struct page *); -extern void clear_shadow_from_swap_cache(int type, unsigned long begin, - unsigned long end); -extern void free_swap_cache(struct page *); +extern void free_swap_cache(struct page *page); extern void free_page_and_swap_cache(struct page *); extern void free_pages_and_swap_cache(struct page **, int); -extern struct page *lookup_swap_cache(swp_entry_t entry, - struct vm_area_struct *vma, - unsigned long addr); -struct page *find_get_incore_page(struct address_space *mapping, pgoff_t index); -extern struct page *read_swap_cache_async(swp_entry_t, gfp_t, - struct vm_area_struct *vma, unsigned long addr, - bool do_poll); -extern struct page *__read_swap_cache_async(swp_entry_t, gfp_t, - struct vm_area_struct *vma, unsigned long addr, - bool *new_page_allocated); -extern struct page *swap_cluster_readahead(swp_entry_t entry, gfp_t flag, - struct vm_fault *vmf); -extern struct page *swapin_readahead(swp_entry_t entry, gfp_t flag, - struct vm_fault *vmf); - /* linux/mm/swapfile.c */ extern atomic_long_t nr_swap_pages; extern long total_swap_pages; @@ -493,8 +489,9 @@ static inline long get_nr_swap_pages(void) } extern void si_swapinfo(struct sysinfo *); -extern swp_entry_t get_swap_page(struct page *page); -extern void put_swap_page(struct page *page, swp_entry_t entry); +swp_entry_t folio_alloc_swap(struct folio *folio); +bool folio_free_swap(struct folio *folio); +void put_swap_folio(struct folio *folio, swp_entry_t entry); extern swp_entry_t get_swap_page_of_type(int); extern int get_swap_pages(int n, swp_entry_t swp_entries[], int entry_size); extern int add_swap_count_continuation(swp_entry_t, gfp_t); @@ -508,14 +505,11 @@ int swap_type_of(dev_t device, sector_t offset); int find_first_swap(dev_t *device); extern unsigned int count_swap_pages(int, int); extern sector_t swapdev_block(int, pgoff_t); -extern int page_swapcount(struct page *); extern int __swap_count(swp_entry_t entry); extern int __swp_swapcount(swp_entry_t entry); extern int swp_swapcount(swp_entry_t entry); extern struct swap_info_struct *page_swap_info(struct page *); extern struct swap_info_struct *swp_swap_info(swp_entry_t entry); -extern bool reuse_swap_page(struct page *, int *); -extern int try_to_free_swap(struct page *); struct backing_dev_info; extern int init_swap_address_space(unsigned int type, unsigned long nr_pages); extern void exit_swap_address_space(unsigned int type); @@ -528,12 +522,6 @@ static inline void put_swap_device(struct swap_info_struct *si) } #else /* CONFIG_SWAP */ - -static inline int swap_readpage(struct page *page, bool do_poll) -{ - return 0; -} - static inline struct swap_info_struct *swp_swap_info(swp_entry_t entry) { return NULL; @@ -548,11 +536,6 @@ static inline void put_swap_device(struct swap_info_struct *si) { } -static inline struct address_space *swap_address_space(swp_entry_t entry) -{ - return NULL; -} - #define get_nr_swap_pages() 0L #define total_swap_pages 0L #define total_swapcache_pages() 0UL @@ -567,17 +550,13 @@ static inline struct address_space *swap_address_space(swp_entry_t entry) #define free_pages_and_swap_cache(pages, nr) \ release_pages((pages), (nr)); -static inline void free_swap_cache(struct page *page) -{ -} +/* used to sanity check ptes in zap_pte_range when CONFIG_SWAP=0 */ +#define free_swap_and_cache(e) is_pfn_swap_entry(e) -static inline void show_swap_cache_info(void) +static inline void free_swap_cache(struct page *page) { } -/* used to sanity check ptes in zap_pte_range when CONFIG_SWAP=0 */ -#define free_swap_and_cache(e) is_pfn_swap_entry(e) - static inline int add_swap_count_continuation(swp_entry_t swp, gfp_t gfp_mask) { return 0; @@ -596,73 +575,8 @@ static inline void swap_free(swp_entry_t swp) { } -static inline void put_swap_page(struct page *page, swp_entry_t swp) -{ -} - -static inline struct page *swap_cluster_readahead(swp_entry_t entry, - gfp_t gfp_mask, struct vm_fault *vmf) -{ - return NULL; -} - -static inline struct page *swapin_readahead(swp_entry_t swp, gfp_t gfp_mask, - struct vm_fault *vmf) +static inline void put_swap_folio(struct folio *folio, swp_entry_t swp) { - return NULL; -} - -static inline int swap_writepage(struct page *p, struct writeback_control *wbc) -{ - return 0; -} - -static inline struct page *lookup_swap_cache(swp_entry_t swp, - struct vm_area_struct *vma, - unsigned long addr) -{ - return NULL; -} - -static inline -struct page *find_get_incore_page(struct address_space *mapping, pgoff_t index) -{ - return find_get_page(mapping, index); -} - -static inline int add_to_swap(struct page *page) -{ - return 0; -} - -static inline void *get_shadow_from_swap_cache(swp_entry_t entry) -{ - return NULL; -} - -static inline int add_to_swap_cache(struct page *page, swp_entry_t entry, - gfp_t gfp_mask, void **shadowp) -{ - return -1; -} - -static inline void __delete_from_swap_cache(struct page *page, - swp_entry_t entry, void *shadow) -{ -} - -static inline void delete_from_swap_cache(struct page *page) -{ -} - -static inline void clear_shadow_from_swap_cache(int type, unsigned long begin, - unsigned long end) -{ -} - -static inline int page_swapcount(struct page *page) -{ - return 0; } static inline int __swap_count(swp_entry_t entry) @@ -680,21 +594,24 @@ static inline int swp_swapcount(swp_entry_t entry) return 0; } -#define reuse_swap_page(page, total_map_swapcount) \ - (page_trans_huge_mapcount(page, total_map_swapcount) == 1) - -static inline int try_to_free_swap(struct page *page) -{ - return 0; -} - -static inline swp_entry_t get_swap_page(struct page *page) +static inline swp_entry_t folio_alloc_swap(struct folio *folio) { swp_entry_t entry; entry.val = 0; return entry; } +static inline bool folio_free_swap(struct folio *folio) +{ + return false; +} + +static inline int add_swap_extent(struct swap_info_struct *sis, + unsigned long start_page, + unsigned long nr_pages, sector_t start_block) +{ + return -EINVAL; +} #endif /* CONFIG_SWAP */ #ifdef CONFIG_THP_SWAP @@ -726,6 +643,11 @@ static inline int mem_cgroup_swappiness(struct mem_cgroup *mem) } #endif +#ifdef CONFIG_ZSWAP +extern u64 zswap_pool_total_size; +extern atomic_t zswap_stored_pages; +#endif + #if defined(CONFIG_SWAP) && defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP) extern void __cgroup_throttle_swaprate(struct page *page, gfp_t gfp_mask); static inline void cgroup_throttle_swaprate(struct page *page, gfp_t gfp_mask) @@ -739,15 +661,20 @@ static inline void cgroup_throttle_swaprate(struct page *page, gfp_t gfp_mask) { } #endif +static inline void folio_throttle_swaprate(struct folio *folio, gfp_t gfp) +{ + cgroup_throttle_swaprate(&folio->page, gfp); +} -#ifdef CONFIG_MEMCG_SWAP -extern void mem_cgroup_swapout(struct page *page, swp_entry_t entry); -extern int __mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry); -static inline int mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry) +#if defined(CONFIG_MEMCG) && defined(CONFIG_SWAP) +void mem_cgroup_swapout(struct folio *folio, swp_entry_t entry); +int __mem_cgroup_try_charge_swap(struct folio *folio, swp_entry_t entry); +static inline int mem_cgroup_try_charge_swap(struct folio *folio, + swp_entry_t entry) { if (mem_cgroup_disabled()) return 0; - return __mem_cgroup_try_charge_swap(page, entry); + return __mem_cgroup_try_charge_swap(folio, entry); } extern void __mem_cgroup_uncharge_swap(swp_entry_t entry, unsigned int nr_pages); @@ -759,13 +686,13 @@ static inline void mem_cgroup_uncharge_swap(swp_entry_t entry, unsigned int nr_p } extern long mem_cgroup_get_nr_swap_pages(struct mem_cgroup *memcg); -extern bool mem_cgroup_swap_full(struct page *page); +extern bool mem_cgroup_swap_full(struct folio *folio); #else -static inline void mem_cgroup_swapout(struct page *page, swp_entry_t entry) +static inline void mem_cgroup_swapout(struct folio *folio, swp_entry_t entry) { } -static inline int mem_cgroup_try_charge_swap(struct page *page, +static inline int mem_cgroup_try_charge_swap(struct folio *folio, swp_entry_t entry) { return 0; @@ -781,7 +708,7 @@ static inline long mem_cgroup_get_nr_swap_pages(struct mem_cgroup *memcg) return get_nr_swap_pages(); } -static inline bool mem_cgroup_swap_full(struct page *page) +static inline bool mem_cgroup_swap_full(struct folio *folio) { return vm_swap_full(); } diff --git a/include/linux/swap_cgroup.h b/include/linux/swap_cgroup.h index a12dd1c3966c..ae73a87775b3 100644 --- a/include/linux/swap_cgroup.h +++ b/include/linux/swap_cgroup.h @@ -4,7 +4,7 @@ #include <linux/swap.h> -#ifdef CONFIG_MEMCG_SWAP +#if defined(CONFIG_MEMCG) && defined(CONFIG_SWAP) extern unsigned short swap_cgroup_cmpxchg(swp_entry_t ent, unsigned short old, unsigned short new); @@ -40,6 +40,6 @@ static inline void swap_cgroup_swapoff(int type) return; } -#endif /* CONFIG_MEMCG_SWAP */ +#endif #endif /* __LINUX_SWAP_CGROUP_H */ diff --git a/include/linux/swap_slots.h b/include/linux/swap_slots.h index 347f1a304190..15adfb8c813a 100644 --- a/include/linux/swap_slots.h +++ b/include/linux/swap_slots.h @@ -24,7 +24,7 @@ struct swap_slots_cache { void disable_swap_slots_cache_lock(void); void reenable_swap_slots_cache_unlock(void); void enable_swap_slots_cache(void); -int free_swap_slot(swp_entry_t entry); +void free_swap_slot(swp_entry_t entry); extern bool swap_slot_cache_enabled; diff --git a/include/linux/swapfile.h b/include/linux/swapfile.h index e06febf62978..7ed529a77c5b 100644 --- a/include/linux/swapfile.h +++ b/include/linux/swapfile.h @@ -6,11 +6,13 @@ * these were static in swapfile.c but frontswap.c needs them and we don't * want to expose them to the dozens of source files that include swap.h */ -extern spinlock_t swap_lock; -extern struct plist_head swap_active_head; extern struct swap_info_struct *swap_info[]; -extern int try_to_unuse(unsigned int, bool, unsigned long); extern unsigned long generic_max_swapfile_size(void); -extern unsigned long max_swapfile_size(void); +unsigned long arch_max_swapfile_size(void); + +/* Maximum swapfile size supported for the arch (not inclusive). */ +extern unsigned long swapfile_maximum_size; +/* Whether swap migration entry supports storing A/D bits for the arch */ +extern bool swap_migration_ad_supported; #endif /* _LINUX_SWAPFILE_H */ diff --git a/include/linux/swapops.h b/include/linux/swapops.h index d356ab4047f7..86b95ccb81bb 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -8,24 +8,69 @@ #ifdef CONFIG_MMU +#ifdef CONFIG_SWAP +#include <linux/swapfile.h> +#endif /* CONFIG_SWAP */ + /* * swapcache pages are stored in the swapper_space radix tree. We want to * get good packing density in that tree, so the index should be dense in * the low-order bits. * - * We arrange the `type' and `offset' fields so that `type' is at the seven + * We arrange the `type' and `offset' fields so that `type' is at the six * high-order bits of the swp_entry_t and `offset' is right-aligned in the * remaining bits. Although `type' itself needs only five bits, we allow for - * shmem/tmpfs to shift it all up a further two bits: see swp_to_radix_entry(). + * shmem/tmpfs to shift it all up a further one bit: see swp_to_radix_entry(). * * swp_entry_t's are *never* stored anywhere in their arch-dependent format. */ #define SWP_TYPE_SHIFT (BITS_PER_XA_VALUE - MAX_SWAPFILES_SHIFT) #define SWP_OFFSET_MASK ((1UL << SWP_TYPE_SHIFT) - 1) +/* + * Definitions only for PFN swap entries (see is_pfn_swap_entry()). To + * store PFN, we only need SWP_PFN_BITS bits. Each of the pfn swap entries + * can use the extra bits to store other information besides PFN. + */ +#ifdef MAX_PHYSMEM_BITS +#define SWP_PFN_BITS (MAX_PHYSMEM_BITS - PAGE_SHIFT) +#else /* MAX_PHYSMEM_BITS */ +#define SWP_PFN_BITS (BITS_PER_LONG - PAGE_SHIFT) +#endif /* MAX_PHYSMEM_BITS */ +#define SWP_PFN_MASK (BIT(SWP_PFN_BITS) - 1) + +/** + * Migration swap entry specific bitfield definitions. Layout: + * + * |----------+--------------------| + * | swp_type | swp_offset | + * |----------+--------+-+-+-------| + * | | resv |D|A| PFN | + * |----------+--------+-+-+-------| + * + * @SWP_MIG_YOUNG_BIT: Whether the page used to have young bit set (bit A) + * @SWP_MIG_DIRTY_BIT: Whether the page used to have dirty bit set (bit D) + * + * Note: A/D bits will be stored in migration entries iff there're enough + * free bits in arch specific swp offset. By default we'll ignore A/D bits + * when migrating a page. Please refer to migration_entry_supports_ad() + * for more information. If there're more bits besides PFN and A/D bits, + * they should be reserved and always be zeros. + */ +#define SWP_MIG_YOUNG_BIT (SWP_PFN_BITS) +#define SWP_MIG_DIRTY_BIT (SWP_PFN_BITS + 1) +#define SWP_MIG_TOTAL_BITS (SWP_PFN_BITS + 2) + +#define SWP_MIG_YOUNG BIT(SWP_MIG_YOUNG_BIT) +#define SWP_MIG_DIRTY BIT(SWP_MIG_DIRTY_BIT) + +static inline bool is_pfn_swap_entry(swp_entry_t entry); + /* Clear all flags but only keep swp_entry_t related information */ static inline pte_t pte_swp_clear_flags(pte_t pte) { + if (pte_swp_exclusive(pte)) + pte = pte_swp_clear_exclusive(pte); if (pte_swp_soft_dirty(pte)) pte = pte_swp_clear_soft_dirty(pte); if (pte_swp_uffd_wp(pte)) @@ -62,6 +107,17 @@ static inline pgoff_t swp_offset(swp_entry_t entry) return entry.val & SWP_OFFSET_MASK; } +/* + * This should only be called upon a pfn swap entry to get the PFN stored + * in the swap entry. Please refers to is_pfn_swap_entry() for definition + * of pfn swap entry. + */ +static inline unsigned long swp_offset_pfn(swp_entry_t entry) +{ + VM_BUG_ON(!is_pfn_swap_entry(entry)); + return swp_offset(entry) & SWP_PFN_MASK; +} + /* check whether a pte points to a swap entry */ static inline int is_swap_pte(pte_t pte) { @@ -106,6 +162,16 @@ static inline void *swp_to_radix_entry(swp_entry_t entry) return xa_mk_value(entry.val); } +static inline swp_entry_t make_swapin_error_entry(struct page *page) +{ + return swp_entry(SWP_SWAPIN_ERROR, page_to_pfn(page)); +} + +static inline int is_swapin_error_entry(swp_entry_t entry) +{ + return swp_type(entry) == SWP_SWAPIN_ERROR; +} + #if IS_ENABLED(CONFIG_DEVICE_PRIVATE) static inline swp_entry_t make_readable_device_private_entry(pgoff_t offset) { @@ -194,6 +260,7 @@ static inline bool is_writable_device_exclusive_entry(swp_entry_t entry) static inline int is_migration_entry(swp_entry_t entry) { return unlikely(swp_type(entry) == SWP_MIGRATION_READ || + swp_type(entry) == SWP_MIGRATION_READ_EXCLUSIVE || swp_type(entry) == SWP_MIGRATION_WRITE); } @@ -202,28 +269,96 @@ static inline int is_writable_migration_entry(swp_entry_t entry) return unlikely(swp_type(entry) == SWP_MIGRATION_WRITE); } +static inline int is_readable_migration_entry(swp_entry_t entry) +{ + return unlikely(swp_type(entry) == SWP_MIGRATION_READ); +} + +static inline int is_readable_exclusive_migration_entry(swp_entry_t entry) +{ + return unlikely(swp_type(entry) == SWP_MIGRATION_READ_EXCLUSIVE); +} + static inline swp_entry_t make_readable_migration_entry(pgoff_t offset) { return swp_entry(SWP_MIGRATION_READ, offset); } +static inline swp_entry_t make_readable_exclusive_migration_entry(pgoff_t offset) +{ + return swp_entry(SWP_MIGRATION_READ_EXCLUSIVE, offset); +} + static inline swp_entry_t make_writable_migration_entry(pgoff_t offset) { return swp_entry(SWP_MIGRATION_WRITE, offset); } +/* + * Returns whether the host has large enough swap offset field to support + * carrying over pgtable A/D bits for page migrations. The result is + * pretty much arch specific. + */ +static inline bool migration_entry_supports_ad(void) +{ +#ifdef CONFIG_SWAP + return swap_migration_ad_supported; +#else /* CONFIG_SWAP */ + return false; +#endif /* CONFIG_SWAP */ +} + +static inline swp_entry_t make_migration_entry_young(swp_entry_t entry) +{ + if (migration_entry_supports_ad()) + return swp_entry(swp_type(entry), + swp_offset(entry) | SWP_MIG_YOUNG); + return entry; +} + +static inline bool is_migration_entry_young(swp_entry_t entry) +{ + if (migration_entry_supports_ad()) + return swp_offset(entry) & SWP_MIG_YOUNG; + /* Keep the old behavior of aging page after migration */ + return false; +} + +static inline swp_entry_t make_migration_entry_dirty(swp_entry_t entry) +{ + if (migration_entry_supports_ad()) + return swp_entry(swp_type(entry), + swp_offset(entry) | SWP_MIG_DIRTY); + return entry; +} + +static inline bool is_migration_entry_dirty(swp_entry_t entry) +{ + if (migration_entry_supports_ad()) + return swp_offset(entry) & SWP_MIG_DIRTY; + /* Keep the old behavior of clean page after migration */ + return false; +} + extern void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep, spinlock_t *ptl); extern void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd, unsigned long address); -extern void migration_entry_wait_huge(struct vm_area_struct *vma, - struct mm_struct *mm, pte_t *pte); -#else +#ifdef CONFIG_HUGETLB_PAGE +extern void __migration_entry_wait_huge(pte_t *ptep, spinlock_t *ptl); +extern void migration_entry_wait_huge(struct vm_area_struct *vma, pte_t *pte); +#endif /* CONFIG_HUGETLB_PAGE */ +#else /* CONFIG_MIGRATION */ static inline swp_entry_t make_readable_migration_entry(pgoff_t offset) { return swp_entry(0, 0); } +static inline swp_entry_t make_readable_exclusive_migration_entry(pgoff_t offset) +{ + return swp_entry(0, 0); +} + static inline swp_entry_t make_writable_migration_entry(pgoff_t offset) { return swp_entry(0, 0); @@ -238,18 +373,122 @@ static inline void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep, spinlock_t *ptl) { } static inline void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd, unsigned long address) { } -static inline void migration_entry_wait_huge(struct vm_area_struct *vma, - struct mm_struct *mm, pte_t *pte) { } +#ifdef CONFIG_HUGETLB_PAGE +static inline void __migration_entry_wait_huge(pte_t *ptep, spinlock_t *ptl) { } +static inline void migration_entry_wait_huge(struct vm_area_struct *vma, pte_t *pte) { } +#endif /* CONFIG_HUGETLB_PAGE */ static inline int is_writable_migration_entry(swp_entry_t entry) { return 0; } +static inline int is_readable_migration_entry(swp_entry_t entry) +{ + return 0; +} + +static inline swp_entry_t make_migration_entry_young(swp_entry_t entry) +{ + return entry; +} + +static inline bool is_migration_entry_young(swp_entry_t entry) +{ + return false; +} + +static inline swp_entry_t make_migration_entry_dirty(swp_entry_t entry) +{ + return entry; +} + +static inline bool is_migration_entry_dirty(swp_entry_t entry) +{ + return false; +} +#endif /* CONFIG_MIGRATION */ + +typedef unsigned long pte_marker; + +#define PTE_MARKER_UFFD_WP BIT(0) +#define PTE_MARKER_MASK (PTE_MARKER_UFFD_WP) + +#ifdef CONFIG_PTE_MARKER + +static inline swp_entry_t make_pte_marker_entry(pte_marker marker) +{ + return swp_entry(SWP_PTE_MARKER, marker); +} + +static inline bool is_pte_marker_entry(swp_entry_t entry) +{ + return swp_type(entry) == SWP_PTE_MARKER; +} + +static inline pte_marker pte_marker_get(swp_entry_t entry) +{ + return swp_offset(entry) & PTE_MARKER_MASK; +} + +static inline bool is_pte_marker(pte_t pte) +{ + return is_swap_pte(pte) && is_pte_marker_entry(pte_to_swp_entry(pte)); +} + +#else /* CONFIG_PTE_MARKER */ + +static inline swp_entry_t make_pte_marker_entry(pte_marker marker) +{ + /* This should never be called if !CONFIG_PTE_MARKER */ + WARN_ON_ONCE(1); + return swp_entry(0, 0); +} + +static inline bool is_pte_marker_entry(swp_entry_t entry) +{ + return false; +} + +static inline pte_marker pte_marker_get(swp_entry_t entry) +{ + return 0; +} -#endif +static inline bool is_pte_marker(pte_t pte) +{ + return false; +} + +#endif /* CONFIG_PTE_MARKER */ + +static inline pte_t make_pte_marker(pte_marker marker) +{ + return swp_entry_to_pte(make_pte_marker_entry(marker)); +} + +/* + * This is a special version to check pte_none() just to cover the case when + * the pte is a pte marker. It existed because in many cases the pte marker + * should be seen as a none pte; it's just that we have stored some information + * onto the none pte so it becomes not-none any more. + * + * It should be used when the pte is file-backed, ram-based and backing + * userspace pages, like shmem. It is not needed upon pgtables that do not + * support pte markers at all. For example, it's not needed on anonymous + * memory, kernel-only memory (including when the system is during-boot), + * non-ram based generic file-system. It's fine to be used even there, but the + * extra pte marker check will be pure overhead. + * + * For systems configured with !CONFIG_PTE_MARKER this will be automatically + * optimized to pte_none(). + */ +static inline int pte_none_mostly(pte_t pte) +{ + return pte_none(pte) || is_pte_marker(pte); +} static inline struct page *pfn_swap_entry_to_page(swp_entry_t entry) { - struct page *p = pfn_to_page(swp_offset(entry)); + struct page *p = pfn_to_page(swp_offset_pfn(entry)); /* * Any use of migration entries may only occur while the @@ -267,6 +506,9 @@ static inline struct page *pfn_swap_entry_to_page(swp_entry_t entry) */ static inline bool is_pfn_swap_entry(swp_entry_t entry) { + /* Make sure the swp offset can always store the needed fields */ + BUILD_BUG_ON(SWP_TYPE_SHIFT < SWP_PFN_BITS); + return is_migration_entry(entry) || is_device_private_entry(entry) || is_device_exclusive_entry(entry); } @@ -274,7 +516,7 @@ static inline bool is_pfn_swap_entry(swp_entry_t entry) struct page_vma_mapped_walk; #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION -extern void set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw, +extern int set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw, struct page *page); extern void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, @@ -304,10 +546,10 @@ static inline pmd_t swp_entry_to_pmd(swp_entry_t entry) static inline int is_pmd_migration_entry(pmd_t pmd) { - return !pmd_present(pmd) && is_migration_entry(pmd_to_swp_entry(pmd)); + return is_swap_pmd(pmd) && is_migration_entry(pmd_to_swp_entry(pmd)); } -#else -static inline void set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw, +#else /* CONFIG_ARCH_ENABLE_THP_MIGRATION */ +static inline int set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw, struct page *page) { BUILD_BUG(); @@ -335,7 +577,7 @@ static inline int is_pmd_migration_entry(pmd_t pmd) { return 0; } -#endif +#endif /* CONFIG_ARCH_ENABLE_THP_MIGRATION */ #ifdef CONFIG_MEMORY_FAILURE @@ -355,22 +597,17 @@ static inline int is_hwpoison_entry(swp_entry_t entry) return swp_type(entry) == SWP_HWPOISON; } -static inline unsigned long hwpoison_entry_to_pfn(swp_entry_t entry) -{ - return swp_offset(entry); -} - static inline void num_poisoned_pages_inc(void) { atomic_long_inc(&num_poisoned_pages); } -static inline void num_poisoned_pages_dec(void) +static inline void num_poisoned_pages_sub(long i) { - atomic_long_dec(&num_poisoned_pages); + atomic_long_sub(i, &num_poisoned_pages); } -#else +#else /* CONFIG_MEMORY_FAILURE */ static inline swp_entry_t make_hwpoison_entry(struct page *page) { @@ -385,20 +622,16 @@ static inline int is_hwpoison_entry(swp_entry_t swp) static inline void num_poisoned_pages_inc(void) { } -#endif -#if defined(CONFIG_MEMORY_FAILURE) || defined(CONFIG_MIGRATION) || \ - defined(CONFIG_DEVICE_PRIVATE) -static inline int non_swap_entry(swp_entry_t entry) +static inline void num_poisoned_pages_sub(long i) { - return swp_type(entry) >= MAX_SWAPFILES; } -#else +#endif /* CONFIG_MEMORY_FAILURE */ + static inline int non_swap_entry(swp_entry_t entry) { - return 0; + return swp_type(entry) >= MAX_SWAPFILES; } -#endif #endif /* CONFIG_MMU */ #endif /* _LINUX_SWAPOPS_H */ diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index 569272871375..35bc4e281c21 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -13,11 +13,9 @@ struct device; struct page; struct scatterlist; -enum swiotlb_force { - SWIOTLB_NORMAL, /* Default - depending on HW DMA mask etc. */ - SWIOTLB_FORCE, /* swiotlb=force */ - SWIOTLB_NO_FORCE, /* swiotlb=noforce */ -}; +#define SWIOTLB_VERBOSE (1 << 0) /* verbose initialization */ +#define SWIOTLB_FORCE (1 << 1) /* force bounce buffering */ +#define SWIOTLB_ANY (1 << 2) /* allow any memory for the buffer */ /* * Maximum allowable number of contiguous slabs to map, @@ -36,11 +34,11 @@ enum swiotlb_force { /* default to 64MB */ #define IO_TLB_DEFAULT_SIZE (64UL<<20) -extern void swiotlb_init(int verbose); -int swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose); unsigned long swiotlb_size_or_default(void); -extern int swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs); -extern int swiotlb_late_init_with_default_size(size_t default_size); +void __init swiotlb_init_remap(bool addressing_limit, unsigned int flags, + int (*remap)(void *tlb, unsigned long nslabs)); +int swiotlb_init_late(size_t size, gfp_t gfp_mask, + int (*remap)(void *tlb, unsigned long nslabs)); extern void __init swiotlb_update_mem_attributes(void); phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, phys_addr_t phys, @@ -62,7 +60,6 @@ dma_addr_t swiotlb_map(struct device *dev, phys_addr_t phys, size_t size, enum dma_data_direction dir, unsigned long attrs); #ifdef CONFIG_SWIOTLB -extern enum swiotlb_force swiotlb_force; /** * struct io_tlb_mem - IO TLB Memory Pool Descriptor @@ -73,38 +70,38 @@ extern enum swiotlb_force swiotlb_force; * @end: The end address of the swiotlb memory pool. Used to do a quick * range check to see if the memory was in fact allocated by this * API. + * @vaddr: The vaddr of the swiotlb memory pool. The swiotlb memory pool + * may be remapped in the memory encrypted case and store virtual + * address for bounce buffer operation. * @nslabs: The number of IO TLB blocks (in groups of 64) between @start and * @end. For default swiotlb, this is command line adjustable via * setup_io_tlb_npages. * @used: The number of used IO TLB block. * @list: The free list describing the number of free entries available * from each index. - * @index: The index to start searching in the next round. * @orig_addr: The original address corresponding to a mapped entry. * @alloc_size: Size of the allocated buffer. - * @lock: The lock to protect the above data structures in the map and - * unmap calls. * @debugfs: The dentry to debugfs. * @late_alloc: %true if allocated using the page allocator * @force_bounce: %true if swiotlb bouncing is forced * @for_alloc: %true if the pool is used for memory allocation + * @nareas: The area number in the pool. + * @area_nslabs: The slot number in the area. */ struct io_tlb_mem { phys_addr_t start; phys_addr_t end; + void *vaddr; unsigned long nslabs; unsigned long used; - unsigned int index; - spinlock_t lock; struct dentry *debugfs; bool late_alloc; bool force_bounce; bool for_alloc; - struct io_tlb_slot { - phys_addr_t orig_addr; - size_t alloc_size; - unsigned int list; - } *slots; + unsigned int nareas; + unsigned int area_nslabs; + struct io_tlb_area *areas; + struct io_tlb_slot *slots; }; extern struct io_tlb_mem io_tlb_default_mem; @@ -122,13 +119,16 @@ static inline bool is_swiotlb_force_bounce(struct device *dev) return mem && mem->force_bounce; } +void swiotlb_init(bool addressing_limited, unsigned int flags); void __init swiotlb_exit(void); unsigned int swiotlb_max_segment(void); size_t swiotlb_max_mapping_size(struct device *dev); bool is_swiotlb_active(struct device *dev); void __init swiotlb_adjust_size(unsigned long size); #else -#define swiotlb_force SWIOTLB_NO_FORCE +static inline void swiotlb_init(bool addressing_limited, unsigned int flags) +{ +} static inline bool is_swiotlb_buffer(struct device *dev, phys_addr_t paddr) { return false; @@ -160,7 +160,6 @@ static inline void swiotlb_adjust_size(unsigned long size) #endif /* CONFIG_SWIOTLB */ extern void swiotlb_print_info(void); -extern void swiotlb_set_max_segment(unsigned int); #ifdef CONFIG_DMA_RESTRICTED_POOL struct page *swiotlb_alloc(struct device *dev, size_t size); @@ -186,4 +185,6 @@ static inline bool is_swiotlb_for_alloc(struct device *dev) } #endif /* CONFIG_DMA_RESTRICTED_POOL */ +extern phys_addr_t swiotlb_unencrypted_base; + #endif /* __LINUX_SWIOTLB_H */ diff --git a/include/linux/switchtec.h b/include/linux/switchtec.h index be24056ac00f..48fabe36509e 100644 --- a/include/linux/switchtec.h +++ b/include/linux/switchtec.h @@ -337,8 +337,6 @@ enum { NTB_CTRL_REQ_ID_EN = 1 << 0, NTB_CTRL_LUT_EN = 1 << 0, - - NTB_PART_CTRL_ID_PROT_DIS = 1 << 0, }; struct ntb_ctrl_regs { diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 528a478dbda8..a34b0f9a9972 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -290,10 +290,6 @@ static inline void addr_limit_user_check(void) return; #endif - if (CHECK_DATA_CORRUPTION(uaccess_kernel(), - "Invalid address limit on user-mode return")) - force_sig(SIGKILL); - #ifdef TIF_FSCHECK clear_thread_flag(TIF_FSCHECK); #endif @@ -1057,6 +1053,9 @@ asmlinkage long sys_landlock_add_rule(int ruleset_fd, enum landlock_rule_type ru const void __user *rule_attr, __u32 flags); asmlinkage long sys_landlock_restrict_self(int ruleset_fd, __u32 flags); asmlinkage long sys_memfd_secret(unsigned int flags); +asmlinkage long sys_set_mempolicy_home_node(unsigned long start, unsigned long len, + unsigned long home_node, + unsigned long flags); /* * Architecture-specific system calls diff --git a/include/linux/syscalls_api.h b/include/linux/syscalls_api.h new file mode 100644 index 000000000000..23e012b04db4 --- /dev/null +++ b/include/linux/syscalls_api.h @@ -0,0 +1 @@ +#include <linux/syscalls.h> diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 1fa2b69c6fc3..780690dc08cd 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -38,12 +38,29 @@ struct ctl_table_header; struct ctl_dir; /* Keep the same order as in fs/proc/proc_sysctl.c */ -#define SYSCTL_ZERO ((void *)&sysctl_vals[0]) -#define SYSCTL_ONE ((void *)&sysctl_vals[1]) -#define SYSCTL_INT_MAX ((void *)&sysctl_vals[2]) +#define SYSCTL_ZERO ((void *)&sysctl_vals[0]) +#define SYSCTL_ONE ((void *)&sysctl_vals[1]) +#define SYSCTL_TWO ((void *)&sysctl_vals[2]) +#define SYSCTL_THREE ((void *)&sysctl_vals[3]) +#define SYSCTL_FOUR ((void *)&sysctl_vals[4]) +#define SYSCTL_ONE_HUNDRED ((void *)&sysctl_vals[5]) +#define SYSCTL_TWO_HUNDRED ((void *)&sysctl_vals[6]) +#define SYSCTL_ONE_THOUSAND ((void *)&sysctl_vals[7]) +#define SYSCTL_THREE_THOUSAND ((void *)&sysctl_vals[8]) +#define SYSCTL_INT_MAX ((void *)&sysctl_vals[9]) + +/* this is needed for the proc_dointvec_minmax for [fs_]overflow UID and GID */ +#define SYSCTL_MAXOLDUID ((void *)&sysctl_vals[10]) +#define SYSCTL_NEG_ONE ((void *)&sysctl_vals[11]) extern const int sysctl_vals[]; +#define SYSCTL_LONG_ZERO ((void *)&sysctl_long_vals[0]) +#define SYSCTL_LONG_ONE ((void *)&sysctl_long_vals[1]) +#define SYSCTL_LONG_MAX ((void *)&sysctl_long_vals[2]) + +extern const unsigned long sysctl_long_vals[]; + typedef int proc_handler(struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos); @@ -58,6 +75,8 @@ int proc_douintvec_minmax(struct ctl_table *table, int write, void *buffer, int proc_dou8vec_minmax(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); int proc_dointvec_jiffies(struct ctl_table *, int, void *, size_t *, loff_t *); +int proc_dointvec_ms_jiffies_minmax(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos); int proc_dointvec_userhz_jiffies(struct ctl_table *, int, void *, size_t *, loff_t *); int proc_dointvec_ms_jiffies(struct ctl_table *, int, void *, size_t *, @@ -178,6 +197,20 @@ struct ctl_path { #ifdef CONFIG_SYSCTL +#define DECLARE_SYSCTL_BASE(_name, _table) \ +static struct ctl_table _name##_base_table[] = { \ + { \ + .procname = #_name, \ + .mode = 0555, \ + .child = _table, \ + }, \ + { }, \ +} + +extern int __register_sysctl_base(struct ctl_table *base_table); + +#define register_sysctl_base(_name) __register_sysctl_base(_name##_base_table) + void proc_sys_poll_notify(struct ctl_table_poll *poll); extern void setup_sysctl_set(struct ctl_table_set *p, @@ -198,8 +231,19 @@ struct ctl_table_header *register_sysctl_paths(const struct ctl_path *path, void unregister_sysctl_table(struct ctl_table_header * table); -extern int sysctl_init(void); +extern int sysctl_init_bases(void); +extern void __register_sysctl_init(const char *path, struct ctl_table *table, + const char *table_name); +#define register_sysctl_init(path, table) __register_sysctl_init(path, table, #table) +extern struct ctl_table_header *register_sysctl_mount_point(const char *path); + void do_sysctl_args(void); +int do_proc_douintvec(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos, + int (*conv)(unsigned long *lvalp, + unsigned int *valp, + int write, void *data), + void *data); extern int pwrsw_enabled; extern int unaligned_enabled; @@ -207,16 +251,32 @@ extern int unaligned_dump_stack; extern int no_unaligned_warning; extern struct ctl_table sysctl_mount_point[]; -extern struct ctl_table random_table[]; -extern struct ctl_table firmware_config_table[]; -extern struct ctl_table epoll_table[]; #else /* CONFIG_SYSCTL */ + +#define DECLARE_SYSCTL_BASE(_name, _table) + +static inline int __register_sysctl_base(struct ctl_table *base_table) +{ + return 0; +} + +#define register_sysctl_base(table) __register_sysctl_base(table) + static inline struct ctl_table_header *register_sysctl_table(struct ctl_table * table) { return NULL; } +static inline void register_sysctl_init(const char *path, struct ctl_table *table) +{ +} + +static inline struct ctl_table_header *register_sysctl_mount_point(const char *path) +{ + return NULL; +} + static inline struct ctl_table_header *register_sysctl_paths( const struct ctl_path *path, struct ctl_table *table) { diff --git a/include/linux/sysfb.h b/include/linux/sysfb.h index b0dcfa26d07b..8ba8b5be5567 100644 --- a/include/linux/sysfb.h +++ b/include/linux/sysfb.h @@ -55,6 +55,18 @@ struct efifb_dmi_info { int flags; }; +#ifdef CONFIG_SYSFB + +void sysfb_disable(void); + +#else /* CONFIG_SYSFB */ + +static inline void sysfb_disable(void) +{ +} + +#endif /* CONFIG_SYSFB */ + #ifdef CONFIG_EFI extern struct efifb_dmi_info efifb_dmi_list[]; @@ -72,8 +84,8 @@ static inline void sysfb_apply_efi_quirks(struct platform_device *pd) bool sysfb_parse_mode(const struct screen_info *si, struct simplefb_platform_data *mode); -int sysfb_create_simplefb(const struct screen_info *si, - const struct simplefb_platform_data *mode); +struct platform_device *sysfb_create_simplefb(const struct screen_info *si, + const struct simplefb_platform_data *mode); #else /* CONFIG_SYSFB_SIMPLE */ @@ -83,10 +95,10 @@ static inline bool sysfb_parse_mode(const struct screen_info *si, return false; } -static inline int sysfb_create_simplefb(const struct screen_info *si, - const struct simplefb_platform_data *mode) +static inline struct platform_device *sysfb_create_simplefb(const struct screen_info *si, + const struct simplefb_platform_data *mode) { - return -EINVAL; + return ERR_PTR(-EINVAL); } #endif /* CONFIG_SYSFB_SIMPLE */ diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index e3f1e8ac1f85..fd3fe5c8c17f 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -235,6 +235,22 @@ struct bin_attribute bin_attr_##_name = __BIN_ATTR_WO(_name, _size) #define BIN_ATTR_RW(_name, _size) \ struct bin_attribute bin_attr_##_name = __BIN_ATTR_RW(_name, _size) + +#define __BIN_ATTR_ADMIN_RO(_name, _size) { \ + .attr = { .name = __stringify(_name), .mode = 0400 }, \ + .read = _name##_read, \ + .size = _size, \ +} + +#define __BIN_ATTR_ADMIN_RW(_name, _size) \ + __BIN_ATTR(_name, 0600, _name##_read, _name##_write, _size) + +#define BIN_ATTR_ADMIN_RO(_name, _size) \ +struct bin_attribute bin_attr_##_name = __BIN_ATTR_ADMIN_RO(_name, _size) + +#define BIN_ATTR_ADMIN_RW(_name, _size) \ +struct bin_attribute bin_attr_##_name = __BIN_ATTR_ADMIN_RW(_name, _size) + struct sysfs_ops { ssize_t (*show)(struct kobject *, struct attribute *, char *); ssize_t (*store)(struct kobject *, struct attribute *, const char *, size_t); diff --git a/include/linux/syslog.h b/include/linux/syslog.h index 86af908e2663..955f80e34d4f 100644 --- a/include/linux/syslog.h +++ b/include/linux/syslog.h @@ -8,6 +8,8 @@ #ifndef _LINUX_SYSLOG_H #define _LINUX_SYSLOG_H +#include <linux/wait.h> + /* Close the log. Currently a NOP. */ #define SYSLOG_ACTION_CLOSE 0 /* Open the log. Currently a NOP. */ @@ -35,5 +37,6 @@ #define SYSLOG_FROM_PROC 1 int do_syslog(int type, char __user *buf, int count, int source); +extern wait_queue_head_t log_wait; #endif /* _LINUX_SYSLOG_H */ diff --git a/include/linux/t10-pi.h b/include/linux/t10-pi.h index c635c2e014e3..248f4ac95642 100644 --- a/include/linux/t10-pi.h +++ b/include/linux/t10-pi.h @@ -53,4 +53,33 @@ extern const struct blk_integrity_profile t10_pi_type1_ip; extern const struct blk_integrity_profile t10_pi_type3_crc; extern const struct blk_integrity_profile t10_pi_type3_ip; +struct crc64_pi_tuple { + __be64 guard_tag; + __be16 app_tag; + __u8 ref_tag[6]; +}; + +/** + * lower_48_bits() - return bits 0-47 of a number + * @n: the number we're accessing + */ +static inline u64 lower_48_bits(u64 n) +{ + return n & ((1ull << 48) - 1); +} + +static inline u64 ext_pi_ref_tag(struct request *rq) +{ + unsigned int shift = ilog2(queue_logical_block_size(rq->q)); + +#ifdef CONFIG_BLK_DEV_INTEGRITY + if (rq->q->integrity.interval_exp) + shift = rq->q->integrity.interval_exp; +#endif + return lower_48_bits(blk_rq_pos(rq) >> (shift - SECTOR_SHIFT)); +} + +extern const struct blk_integrity_profile ext_pi_type1_crc64; +extern const struct blk_integrity_profile ext_pi_type3_crc64; + #endif diff --git a/include/linux/task_work.h b/include/linux/task_work.h index 5b8a93f288bb..795ef5a68429 100644 --- a/include/linux/task_work.h +++ b/include/linux/task_work.h @@ -17,8 +17,14 @@ enum task_work_notify_mode { TWA_NONE, TWA_RESUME, TWA_SIGNAL, + TWA_SIGNAL_NO_IPI, }; +static inline bool task_work_pending(struct task_struct *task) +{ + return READ_ONCE(task->task_works); +} + int task_work_add(struct task_struct *task, struct callback_head *twork, enum task_work_notify_mode mode); diff --git a/include/linux/tboot.h b/include/linux/tboot.h index 5146d2574e85..d2279160ef39 100644 --- a/include/linux/tboot.h +++ b/include/linux/tboot.h @@ -126,7 +126,6 @@ extern void tboot_probe(void); extern void tboot_shutdown(u32 shutdown_type); extern struct acpi_table_header *tboot_get_dmar_table( struct acpi_table_header *dmar_tbl); -extern int tboot_force_iommu(void); #else @@ -136,7 +135,6 @@ extern int tboot_force_iommu(void); #define tboot_sleep(sleep_state, pm1a_control, pm1b_control) \ do { } while (0) #define tboot_get_dmar_table(dmar_tbl) (dmar_tbl) -#define tboot_force_iommu() 0 #endif /* !CONFIG_INTEL_TXT */ diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 78b91bb92f0d..41b1da621a45 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -46,6 +46,36 @@ static inline unsigned int inner_tcp_hdrlen(const struct sk_buff *skb) return inner_tcp_hdr(skb)->doff * 4; } +/** + * skb_tcp_all_headers - Returns size of all headers for a TCP packet + * @skb: buffer + * + * Used in TX path, for a packet known to be a TCP one. + * + * if (skb_is_gso(skb)) { + * int hlen = skb_tcp_all_headers(skb); + * ... + */ +static inline int skb_tcp_all_headers(const struct sk_buff *skb) +{ + return skb_transport_offset(skb) + tcp_hdrlen(skb); +} + +/** + * skb_inner_tcp_all_headers - Returns size of all headers for an encap TCP packet + * @skb: buffer + * + * Used in TX path, for a packet known to be a TCP one. + * + * if (skb_is_gso(skb) && skb->encapsulation) { + * int hlen = skb_inner_tcp_all_headers(skb); + * ... + */ +static inline int skb_inner_tcp_all_headers(const struct sk_buff *skb) +{ + return skb_inner_transport_offset(skb) + inner_tcp_hdrlen(skb); +} + static inline unsigned int tcp_optlen(const struct sk_buff *skb) { return (tcp_hdr(skb)->doff - 5) * 4; @@ -265,7 +295,7 @@ struct tcp_sock { u32 packets_out; /* Packets which are "in flight" */ u32 retrans_out; /* Retransmitted packets out */ u32 max_packets_out; /* max packets_out in last window */ - u32 max_packets_seq; /* right edge of max_packets_out flight */ + u32 cwnd_usage_seq; /* right edge of cwnd usage tracking flight */ u16 urg_data; /* Saved octet of OOB data and control flags */ u8 ecn_flags; /* ECN status bits. */ @@ -358,6 +388,12 @@ struct tcp_sock { u8 bpf_sock_ops_cb_flags; /* Control calling BPF programs * values defined in uapi/linux/tcp.h */ + u8 bpf_chg_cc_inprogress:1; /* In the middle of + * bpf_setsockopt(TCP_CONGESTION), + * it is to avoid the bpf_tcp_cc->init() + * to recur itself by calling + * bpf_setsockopt(TCP_CONGESTION, "itself"). + */ #define BPF_SOCK_OPS_TEST_FLAG(TP, ARG) (TP->bpf_sock_ops_cb_flags & ARG) #else #define BPF_SOCK_OPS_TEST_FLAG(TP, ARG) 0 @@ -394,6 +430,7 @@ struct tcp_sock { bool is_mptcp; #endif #if IS_ENABLED(CONFIG_SMC) + bool (*smc_hs_congested)(const struct sock *sk); bool syn_smc; /* SYN includes SMC */ #endif diff --git a/include/linux/tee_drv.h b/include/linux/tee_drv.h index 5e1533ee3785..17eb1c5205d3 100644 --- a/include/linux/tee_drv.h +++ b/include/linux/tee_drv.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* - * Copyright (c) 2015-2016, Linaro Limited + * Copyright (c) 2015-2022 Linaro Limited */ #ifndef __TEE_DRV_H @@ -20,14 +20,11 @@ * specific TEE driver. */ -#define TEE_SHM_MAPPED BIT(0) /* Memory mapped by the kernel */ -#define TEE_SHM_DMA_BUF BIT(1) /* Memory with dma-buf handle */ -#define TEE_SHM_EXT_DMA_BUF BIT(2) /* Memory with dma-buf handle */ -#define TEE_SHM_REGISTER BIT(3) /* Memory registered in secure world */ -#define TEE_SHM_USER_MAPPED BIT(4) /* Memory mapped in user space */ -#define TEE_SHM_POOL BIT(5) /* Memory allocated from pool */ -#define TEE_SHM_KERNEL_MAPPED BIT(6) /* Memory mapped in kernel space */ -#define TEE_SHM_PRIV BIT(7) /* Memory private to TEE driver */ +#define TEE_SHM_DYNAMIC BIT(0) /* Dynamic shared memory registered */ + /* in secure world */ +#define TEE_SHM_USER_MAPPED BIT(1) /* Memory mapped in user space */ +#define TEE_SHM_POOL BIT(2) /* Memory allocated from pool */ +#define TEE_SHM_PRIV BIT(3) /* Memory private to TEE driver */ struct device; struct tee_device; @@ -221,92 +218,39 @@ struct tee_shm { }; /** - * struct tee_shm_pool_mgr - shared memory manager + * struct tee_shm_pool - shared memory pool * @ops: operations * @private_data: private data for the shared memory manager */ -struct tee_shm_pool_mgr { - const struct tee_shm_pool_mgr_ops *ops; +struct tee_shm_pool { + const struct tee_shm_pool_ops *ops; void *private_data; }; /** - * struct tee_shm_pool_mgr_ops - shared memory pool manager operations + * struct tee_shm_pool_ops - shared memory pool operations * @alloc: called when allocating shared memory * @free: called when freeing shared memory - * @destroy_poolmgr: called when destroying the pool manager + * @destroy_pool: called when destroying the pool */ -struct tee_shm_pool_mgr_ops { - int (*alloc)(struct tee_shm_pool_mgr *poolmgr, struct tee_shm *shm, - size_t size); - void (*free)(struct tee_shm_pool_mgr *poolmgr, struct tee_shm *shm); - void (*destroy_poolmgr)(struct tee_shm_pool_mgr *poolmgr); +struct tee_shm_pool_ops { + int (*alloc)(struct tee_shm_pool *pool, struct tee_shm *shm, + size_t size, size_t align); + void (*free)(struct tee_shm_pool *pool, struct tee_shm *shm); + void (*destroy_pool)(struct tee_shm_pool *pool); }; -/** - * tee_shm_pool_alloc() - Create a shared memory pool from shm managers - * @priv_mgr: manager for driver private shared memory allocations - * @dmabuf_mgr: manager for dma-buf shared memory allocations - * - * Allocation with the flag TEE_SHM_DMA_BUF set will use the range supplied - * in @dmabuf, others will use the range provided by @priv. - * - * @returns pointer to a 'struct tee_shm_pool' or an ERR_PTR on failure. - */ -struct tee_shm_pool *tee_shm_pool_alloc(struct tee_shm_pool_mgr *priv_mgr, - struct tee_shm_pool_mgr *dmabuf_mgr); - /* - * tee_shm_pool_mgr_alloc_res_mem() - Create a shm manager for reserved - * memory + * tee_shm_pool_alloc_res_mem() - Create a shm manager for reserved memory * @vaddr: Virtual address of start of pool * @paddr: Physical address of start of pool * @size: Size in bytes of the pool * - * @returns pointer to a 'struct tee_shm_pool_mgr' or an ERR_PTR on failure. - */ -struct tee_shm_pool_mgr *tee_shm_pool_mgr_alloc_res_mem(unsigned long vaddr, - phys_addr_t paddr, - size_t size, - int min_alloc_order); - -/** - * tee_shm_pool_mgr_destroy() - Free a shared memory manager - */ -static inline void tee_shm_pool_mgr_destroy(struct tee_shm_pool_mgr *poolm) -{ - poolm->ops->destroy_poolmgr(poolm); -} - -/** - * struct tee_shm_pool_mem_info - holds information needed to create a shared - * memory pool - * @vaddr: Virtual address of start of pool - * @paddr: Physical address of start of pool - * @size: Size in bytes of the pool - */ -struct tee_shm_pool_mem_info { - unsigned long vaddr; - phys_addr_t paddr; - size_t size; -}; - -/** - * tee_shm_pool_alloc_res_mem() - Create a shared memory pool from reserved - * memory range - * @priv_info: Information for driver private shared memory pool - * @dmabuf_info: Information for dma-buf shared memory pool - * - * Start and end of pools will must be page aligned. - * - * Allocation with the flag TEE_SHM_DMA_BUF set will use the range supplied - * in @dmabuf, others will use the range provided by @priv. - * * @returns pointer to a 'struct tee_shm_pool' or an ERR_PTR on failure. */ -struct tee_shm_pool * -tee_shm_pool_alloc_res_mem(struct tee_shm_pool_mem_info *priv_info, - struct tee_shm_pool_mem_info *dmabuf_info); +struct tee_shm_pool *tee_shm_pool_alloc_res_mem(unsigned long vaddr, + phys_addr_t paddr, size_t size, + int min_alloc_order); /** * tee_shm_pool_free() - Free a shared memory pool @@ -315,7 +259,10 @@ tee_shm_pool_alloc_res_mem(struct tee_shm_pool_mem_info *priv_info, * The must be no remaining shared memory allocated from this pool when * this function is called. */ -void tee_shm_pool_free(struct tee_shm_pool *pool); +static inline void tee_shm_pool_free(struct tee_shm_pool *pool) +{ + pool->ops->destroy_pool(pool); +} /** * tee_get_drvdata() - Return driver_data pointer @@ -323,43 +270,20 @@ void tee_shm_pool_free(struct tee_shm_pool *pool); */ void *tee_get_drvdata(struct tee_device *teedev); -/** - * tee_shm_alloc() - Allocate shared memory - * @ctx: Context that allocates the shared memory - * @size: Requested size of shared memory - * @flags: Flags setting properties for the requested shared memory. - * - * Memory allocated as global shared memory is automatically freed when the - * TEE file pointer is closed. The @flags field uses the bits defined by - * TEE_SHM_* above. TEE_SHM_MAPPED must currently always be set. If - * TEE_SHM_DMA_BUF global shared memory will be allocated and associated - * with a dma-buf handle, else driver private memory. - * - * @returns a pointer to 'struct tee_shm' - */ -struct tee_shm *tee_shm_alloc(struct tee_context *ctx, size_t size, u32 flags); +struct tee_shm *tee_shm_alloc_priv_buf(struct tee_context *ctx, size_t size); struct tee_shm *tee_shm_alloc_kernel_buf(struct tee_context *ctx, size_t size); -/** - * tee_shm_register() - Register shared memory buffer - * @ctx: Context that registers the shared memory - * @addr: Address is userspace of the shared buffer - * @length: Length of the shared buffer - * @flags: Flags setting properties for the requested shared memory. - * - * @returns a pointer to 'struct tee_shm' - */ -struct tee_shm *tee_shm_register(struct tee_context *ctx, unsigned long addr, - size_t length, u32 flags); +struct tee_shm *tee_shm_register_kernel_buf(struct tee_context *ctx, + void *addr, size_t length); /** - * tee_shm_is_registered() - Check if shared memory object in registered in TEE + * tee_shm_is_dynamic() - Check if shared memory object is of the dynamic kind * @shm: Shared memory handle - * @returns true if object is registered in TEE + * @returns true if object is dynamic shared memory */ -static inline bool tee_shm_is_registered(struct tee_shm *shm) +static inline bool tee_shm_is_dynamic(struct tee_shm *shm) { - return shm && (shm->flags & TEE_SHM_REGISTER); + return shm && (shm->flags & TEE_SHM_DYNAMIC); } /** @@ -375,24 +299,6 @@ void tee_shm_free(struct tee_shm *shm); void tee_shm_put(struct tee_shm *shm); /** - * tee_shm_va2pa() - Get physical address of a virtual address - * @shm: Shared memory handle - * @va: Virtual address to tranlsate - * @pa: Returned physical address - * @returns 0 on success and < 0 on failure - */ -int tee_shm_va2pa(struct tee_shm *shm, void *va, phys_addr_t *pa); - -/** - * tee_shm_pa2va() - Get virtual address of a physical address - * @shm: Shared memory handle - * @pa: Physical address to tranlsate - * @va: Returned virtual address - * @returns 0 on success and < 0 on failure - */ -int tee_shm_pa2va(struct tee_shm *shm, phys_addr_t pa, void **va); - -/** * tee_shm_get_va() - Get virtual address of a shared memory plus an offset * @shm: Shared memory handle * @offs: Offset from start of this shared memory diff --git a/include/linux/termios_internal.h b/include/linux/termios_internal.h new file mode 100644 index 000000000000..d77f29e5e2b7 --- /dev/null +++ b/include/linux/termios_internal.h @@ -0,0 +1,49 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_TERMIOS_CONV_H +#define _LINUX_TERMIOS_CONV_H + +#include <linux/uaccess.h> +#include <asm/termios.h> + +/* intr=^C quit=^\ erase=del kill=^U + eof=^D vtime=\0 vmin=\1 sxtc=\0 + start=^Q stop=^S susp=^Z eol=\0 + reprint=^R discard=^O werase=^W lnext=^V + eol2=\0 +*/ + +#ifdef VDSUSP +#define INIT_C_CC_VDSUSP_EXTRA [VDSUSP] = 'Y'-0x40, +#else +#define INIT_C_CC_VDSUSP_EXTRA +#endif + +#define INIT_C_CC { \ + [VINTR] = 'C'-0x40, \ + [VQUIT] = '\\'-0x40, \ + [VERASE] = '\177', \ + [VKILL] = 'U'-0x40, \ + [VEOF] = 'D'-0x40, \ + [VSTART] = 'Q'-0x40, \ + [VSTOP] = 'S'-0x40, \ + [VSUSP] = 'Z'-0x40, \ + [VREPRINT] = 'R'-0x40, \ + [VDISCARD] = 'O'-0x40, \ + [VWERASE] = 'W'-0x40, \ + [VLNEXT] = 'V'-0x40, \ + INIT_C_CC_VDSUSP_EXTRA \ + [VMIN] = 1 } + +int user_termio_to_kernel_termios(struct ktermios *, struct termio __user *); +int kernel_termios_to_user_termio(struct termio __user *, struct ktermios *); +#ifdef TCGETS2 +int user_termios_to_kernel_termios(struct ktermios *, struct termios2 __user *); +int kernel_termios_to_user_termios(struct termios2 __user *, struct ktermios *); +int user_termios_to_kernel_termios_1(struct ktermios *, struct termios __user *); +int kernel_termios_to_user_termios_1(struct termios __user *, struct ktermios *); +#else /* TCGETS2 */ +int user_termios_to_kernel_termios(struct ktermios *, struct termios __user *); +int kernel_termios_to_user_termios(struct termios __user *, struct ktermios *); +#endif /* TCGETS2 */ + +#endif /* _LINUX_TERMIOS_CONV_H */ diff --git a/include/linux/thermal.h b/include/linux/thermal.h index c314893970b3..9ecc128944a1 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -17,8 +17,6 @@ #include <linux/workqueue.h> #include <uapi/linux/thermal.h> -#define THERMAL_MAX_TRIPS 12 - /* invalid cooling state */ #define THERMAL_CSTATE_INVALID -1UL @@ -40,8 +38,6 @@ enum thermal_trend { THERMAL_TREND_STABLE, /* temperature is stable */ THERMAL_TREND_RAISING, /* temperature is raising */ THERMAL_TREND_DROPPING, /* temperature is dropping */ - THERMAL_TREND_RAISE_FULL, /* apply highest cooling action */ - THERMAL_TREND_DROP_FULL, /* apply lowest cooling action */ }; /* Thermal notification reason */ @@ -80,6 +76,18 @@ struct thermal_zone_device_ops { void (*critical)(struct thermal_zone_device *); }; +/** + * struct thermal_trip - representation of a point in temperature domain + * @temperature: temperature value in miliCelsius + * @hysteresis: relative hysteresis in miliCelsius + * @type: trip point type + */ +struct thermal_trip { + int temperature; + int hysteresis; + enum thermal_trip_type type; +}; + struct thermal_cooling_device_ops { int (*get_max_state) (struct thermal_cooling_device *, unsigned long *); int (*get_cur_state) (struct thermal_cooling_device *, unsigned long *); @@ -113,7 +121,8 @@ struct thermal_cooling_device { * @trip_hyst_attrs: attributes for trip points for sysfs: trip hysteresis * @mode: current mode of this thermal zone * @devdata: private pointer for device private data - * @trips: number of trip points the thermal zone supports + * @trips: an array of struct thermal_trip + * @num_trips: number of trip points the thermal zone supports * @trips_disabled; bitmap for disabled trips * @passive_delay_jiffies: number of jiffies to wait between polls when * performing passive cooling. @@ -153,7 +162,8 @@ struct thermal_zone_device { struct thermal_attr *trip_hyst_attrs; enum thermal_device_mode mode; void *devdata; - int trips; + struct thermal_trip *trips; + int num_trips; unsigned long trips_disabled; /* bitmap for disabled trips */ unsigned long passive_delay_jiffies; unsigned long polling_delay_jiffies; @@ -284,87 +294,57 @@ struct thermal_zone_params { int offset; }; -/** - * struct thermal_zone_of_device_ops - callbacks for handling DT based zones - * - * Mandatory: - * @get_temp: a pointer to a function that reads the sensor temperature. - * - * Optional: - * @get_trend: a pointer to a function that reads the sensor temperature trend. - * @set_trips: a pointer to a function that sets a temperature window. When - * this window is left the driver must inform the thermal core via - * thermal_zone_device_update. - * @set_emul_temp: a pointer to a function that sets sensor emulated - * temperature. - * @set_trip_temp: a pointer to a function that sets the trip temperature on - * hardware. - */ -struct thermal_zone_of_device_ops { - int (*get_temp)(void *, int *); - int (*get_trend)(void *, int, enum thermal_trend *); - int (*set_trips)(void *, int, int); - int (*set_emul_temp)(void *, int); - int (*set_trip_temp)(void *, int, int); -}; - /* Function declarations */ #ifdef CONFIG_THERMAL_OF -int thermal_zone_of_get_sensor_id(struct device_node *tz_np, - struct device_node *sensor_np, - u32 *id); -struct thermal_zone_device * -thermal_zone_of_sensor_register(struct device *dev, int id, void *data, - const struct thermal_zone_of_device_ops *ops); -void thermal_zone_of_sensor_unregister(struct device *dev, - struct thermal_zone_device *tz); -struct thermal_zone_device *devm_thermal_zone_of_sensor_register( - struct device *dev, int id, void *data, - const struct thermal_zone_of_device_ops *ops); -void devm_thermal_zone_of_sensor_unregister(struct device *dev, - struct thermal_zone_device *tz); -#else +struct thermal_zone_device *thermal_of_zone_register(struct device_node *sensor, int id, void *data, + const struct thermal_zone_device_ops *ops); -static inline int thermal_zone_of_get_sensor_id(struct device_node *tz_np, - struct device_node *sensor_np, - u32 *id) -{ - return -ENOENT; -} -static inline struct thermal_zone_device * -thermal_zone_of_sensor_register(struct device *dev, int id, void *data, - const struct thermal_zone_of_device_ops *ops) +struct thermal_zone_device *devm_thermal_of_zone_register(struct device *dev, int id, void *data, + const struct thermal_zone_device_ops *ops); + +void thermal_of_zone_unregister(struct thermal_zone_device *tz); + +void devm_thermal_of_zone_unregister(struct device *dev, struct thermal_zone_device *tz); + +void thermal_of_zone_unregister(struct thermal_zone_device *tz); + +#else +static inline +struct thermal_zone_device *thermal_of_zone_register(struct device_node *sensor, int id, void *data, + const struct thermal_zone_device_ops *ops) { - return ERR_PTR(-ENODEV); + return ERR_PTR(-ENOTSUPP); } static inline -void thermal_zone_of_sensor_unregister(struct device *dev, - struct thermal_zone_device *tz) +struct thermal_zone_device *devm_thermal_of_zone_register(struct device *dev, int id, void *data, + const struct thermal_zone_device_ops *ops) { + return ERR_PTR(-ENOTSUPP); } -static inline struct thermal_zone_device *devm_thermal_zone_of_sensor_register( - struct device *dev, int id, void *data, - const struct thermal_zone_of_device_ops *ops) +static inline void thermal_of_zone_unregister(struct thermal_zone_device *tz) { - return ERR_PTR(-ENODEV); } -static inline -void devm_thermal_zone_of_sensor_unregister(struct device *dev, - struct thermal_zone_device *tz) +static inline void devm_thermal_of_zone_unregister(struct device *dev, + struct thermal_zone_device *tz) { } - #endif #ifdef CONFIG_THERMAL struct thermal_zone_device *thermal_zone_device_register(const char *, int, int, void *, struct thermal_zone_device_ops *, struct thermal_zone_params *, int, int); + void thermal_zone_device_unregister(struct thermal_zone_device *); +struct thermal_zone_device * +thermal_zone_device_register_with_trips(const char *, struct thermal_trip *, int, int, + void *, struct thermal_zone_device_ops *, + struct thermal_zone_params *, int, int); + int thermal_zone_bind_cooling_device(struct thermal_zone_device *, int, struct thermal_cooling_device *, unsigned long, unsigned long, diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h index 73a6f34b3847..9f392ec76f2b 100644 --- a/include/linux/thread_info.h +++ b/include/linux/thread_info.h @@ -209,9 +209,12 @@ __bad_copy_from(void); extern void __compiletime_error("copy destination size is too small") __bad_copy_to(void); +void __copy_overflow(int size, unsigned long count); + static inline void copy_overflow(int size, unsigned long count) { - WARN(1, "Buffer overflow detected (%d < %lu)!\n", size, count); + if (IS_ENABLED(CONFIG_BUG)) + __copy_overflow(size, count); } static __always_inline __must_check bool diff --git a/include/linux/thunderbolt.h b/include/linux/thunderbolt.h index 124e13cb1469..90cd08ab2f5d 100644 --- a/include/linux/thunderbolt.h +++ b/include/linux/thunderbolt.h @@ -187,6 +187,7 @@ void tb_unregister_property_dir(const char *key, struct tb_property_dir *dir); * @device_name: Name of the device (or %NULL if not known) * @link_speed: Speed of the link in Gb/s * @link_width: Width of the link (1 or 2) + * @link_usb4: Downstream link is USB4 * @is_unplugged: The XDomain is unplugged * @needs_uuid: If the XDomain does not have @remote_uuid it will be * queried first @@ -198,15 +199,15 @@ void tb_unregister_property_dir(const char *key, struct tb_property_dir *dir); * @local_property_block_len: Length of the @local_property_block in dwords * @remote_properties: Properties exported by the remote domain * @remote_property_block_gen: Generation of @remote_properties - * @get_uuid_work: Work used to retrieve @remote_uuid - * @uuid_retries: Number of times left @remote_uuid is requested before - * giving up - * @get_properties_work: Work used to get remote domain properties - * @properties_retries: Number of times left to read properties + * @state: Next XDomain discovery state to run + * @state_work: Work used to run the next state + * @state_retries: Number of retries remain for the state * @properties_changed_work: Work used to notify the remote domain that * our properties have changed * @properties_changed_retries: Number of times left to send properties * changed notification + * @bonding_possible: True if lane bonding is possible on local side + * @target_link_width: Target link width from the remote host * @link: Root switch link the remote domain is connected (ICM only) * @depth: Depth in the chain the remote domain is connected (ICM only) * @@ -234,6 +235,7 @@ struct tb_xdomain { const char *device_name; unsigned int link_speed; unsigned int link_width; + bool link_usb4; bool is_unplugged; bool needs_uuid; struct ida service_ids; @@ -244,12 +246,13 @@ struct tb_xdomain { u32 local_property_block_len; struct tb_property_dir *remote_properties; u32 remote_property_block_gen; - struct delayed_work get_uuid_work; - int uuid_retries; - struct delayed_work get_properties_work; - int properties_retries; + int state; + struct delayed_work state_work; + int state_retries; struct delayed_work properties_changed_work; int properties_changed_retries; + bool bonding_possible; + u8 target_link_width; u8 link; u8 depth; }; @@ -465,6 +468,7 @@ static inline struct tb_xdomain *tb_service_parent(struct tb_service *svc) * @msix_ida: Used to allocate MSI-X vectors for rings * @going_away: The host controller device is about to disappear so when * this flag is set, avoid touching the hardware anymore. + * @iommu_dma_protection: An IOMMU will isolate external-facing ports. * @interrupt_work: Work scheduled to handle ring interrupt when no * MSI-X is used. * @hop_count: Number of rings (end point hops) supported by NHI. @@ -479,6 +483,7 @@ struct tb_nhi { struct tb_ring **rx_rings; struct ida msix_ida; bool going_away; + bool iommu_dma_protection; struct work_struct interrupt_work; u32 hop_count; unsigned long quirks; diff --git a/include/linux/ti-emif-sram.h b/include/linux/ti-emif-sram.h index 2fc854155c27..441b2988e66a 100644 --- a/include/linux/ti-emif-sram.h +++ b/include/linux/ti-emif-sram.h @@ -1,17 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * TI AM33XX EMIF Routines * * Copyright (C) 2016-2017 Texas Instruments Inc. * Dave Gerlach - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation version 2. - * - * This program is distributed "as is" WITHOUT ANY WARRANTY of any - * kind, whether express or implied; without even the implied warranty - * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. */ #ifndef __LINUX_TI_EMIF_H #define __LINUX_TI_EMIF_H diff --git a/include/linux/time64.h b/include/linux/time64.h index 81b9686a2079..f1bcea8c124a 100644 --- a/include/linux/time64.h +++ b/include/linux/time64.h @@ -20,6 +20,9 @@ struct itimerspec64 { struct timespec64 it_value; }; +/* Parameters used to convert the timespec values: */ +#define PSEC_PER_NSEC 1000L + /* Located here for timespec[64]_valid_strict */ #define TIME64_MAX ((s64)~((u64)1 << 63)) #define TIME64_MIN (-TIME64_MAX - 1) @@ -142,7 +145,7 @@ static inline s64 timespec64_to_ns(const struct timespec64 *ts) * * Returns the timespec64 representation of the nsec parameter. */ -extern struct timespec64 ns_to_timespec64(const s64 nsec); +extern struct timespec64 ns_to_timespec64(s64 nsec); /** * timespec64_add_ns - Adds nanoseconds to a timespec64 diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index 78a98bdff76d..fe1e467ba046 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -177,6 +177,7 @@ static inline u64 ktime_get_raw_ns(void) extern u64 ktime_get_mono_fast_ns(void); extern u64 ktime_get_raw_fast_ns(void); extern u64 ktime_get_boot_fast_ns(void); +extern u64 ktime_get_tai_fast_ns(void); extern u64 ktime_get_real_fast_ns(void); /* diff --git a/include/linux/timer.h b/include/linux/timer.h index fda13c9d1256..648f00105f58 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -196,14 +196,6 @@ extern void init_timers(void); struct hrtimer; extern enum hrtimer_restart it_real_fn(struct hrtimer *); -#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON) -struct ctl_table; - -extern unsigned int sysctl_timer_migration; -int timer_migration_handler(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos); -#endif - unsigned long __round_jiffies(unsigned long j, int cpu); unsigned long __round_jiffies_relative(unsigned long j, int cpu); unsigned long round_jiffies(unsigned long j); diff --git a/include/linux/timex.h b/include/linux/timex.h index 059b18eb1f1f..3871b06bd302 100644 --- a/include/linux/timex.h +++ b/include/linux/timex.h @@ -62,6 +62,8 @@ #include <linux/types.h> #include <linux/param.h> +unsigned long random_get_entropy_fallback(void); + #include <asm/timex.h> #ifndef random_get_entropy @@ -74,8 +76,14 @@ * * By default we use get_cycles() for this purpose, but individual * architectures may override this in their asm/timex.h header file. + * If a given arch does not have get_cycles(), then we fallback to + * using random_get_entropy_fallback(). */ -#define random_get_entropy() get_cycles() +#ifdef get_cycles +#define random_get_entropy() ((unsigned long)get_cycles()) +#else +#define random_get_entropy() random_get_entropy_fallback() +#endif #endif /* diff --git a/include/linux/tnum.h b/include/linux/tnum.h index 498dbcedb451..1c3948a1d6ad 100644 --- a/include/linux/tnum.h +++ b/include/linux/tnum.h @@ -21,7 +21,12 @@ struct tnum { struct tnum tnum_const(u64 value); /* A completely unknown value */ extern const struct tnum tnum_unknown; -/* A value that's unknown except that @min <= value <= @max */ +/* An unknown value that is a superset of @min <= value <= @max. + * + * Could include values outside the range of [@min, @max]. + * For example tnum_range(0, 2) is represented by {0, 1, 2, *3*}, + * rather than the intended set of {0, 1, 2}. + */ struct tnum tnum_range(u64 min, u64 max); /* Arithmetic and logical ops */ @@ -73,7 +78,18 @@ static inline bool tnum_is_unknown(struct tnum a) */ bool tnum_is_aligned(struct tnum a, u64 size); -/* Returns true if @b represents a subset of @a. */ +/* Returns true if @b represents a subset of @a. + * + * Note that using tnum_range() as @a requires extra cautions as tnum_in() may + * return true unexpectedly due to tnum limited ability to represent tight + * range, e.g. + * + * tnum_in(tnum_range(0, 2), tnum_const(3)) == true + * + * As a rule of thumb, if @a is explicitly coded rather than coming from + * reg->var_off, it should be in form of tnum_const(), tnum_range(0, 2**n - 1), + * or tnum_range(2**n, 2**(n+1) - 1). + */ bool tnum_in(struct tnum a, struct tnum b); /* Formatting functions. These have snprintf-like semantics: they will write diff --git a/include/linux/topology.h b/include/linux/topology.h index 0b3704ad13c8..4564faafd0e1 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -180,6 +180,19 @@ static inline int cpu_to_mem(int cpu) #endif /* [!]CONFIG_HAVE_MEMORYLESS_NODES */ +#if defined(topology_die_id) && defined(topology_die_cpumask) +#define TOPOLOGY_DIE_SYSFS +#endif +#if defined(topology_cluster_id) && defined(topology_cluster_cpumask) +#define TOPOLOGY_CLUSTER_SYSFS +#endif +#if defined(topology_book_id) && defined(topology_book_cpumask) +#define TOPOLOGY_BOOK_SYSFS +#endif +#if defined(topology_drawer_id) && defined(topology_drawer_cpumask) +#define TOPOLOGY_DRAWER_SYSFS +#endif + #ifndef topology_physical_package_id #define topology_physical_package_id(cpu) ((void)(cpu), -1) #endif @@ -192,6 +205,15 @@ static inline int cpu_to_mem(int cpu) #ifndef topology_core_id #define topology_core_id(cpu) ((void)(cpu), 0) #endif +#ifndef topology_book_id +#define topology_book_id(cpu) ((void)(cpu), -1) +#endif +#ifndef topology_drawer_id +#define topology_drawer_id(cpu) ((void)(cpu), -1) +#endif +#ifndef topology_ppin +#define topology_ppin(cpu) ((void)(cpu), 0ull) +#endif #ifndef topology_sibling_cpumask #define topology_sibling_cpumask(cpu) cpumask_of(cpu) #endif @@ -204,6 +226,12 @@ static inline int cpu_to_mem(int cpu) #ifndef topology_die_cpumask #define topology_die_cpumask(cpu) cpumask_of(cpu) #endif +#ifndef topology_book_cpumask +#define topology_book_cpumask(cpu) cpumask_of(cpu) +#endif +#ifndef topology_drawer_cpumask +#define topology_drawer_cpumask(cpu) cpumask_of(cpu) +#endif #if defined(CONFIG_SCHED_SMT) && !defined(cpu_smt_mask) static inline const struct cpumask *cpu_smt_mask(int cpu) @@ -212,13 +240,6 @@ static inline const struct cpumask *cpu_smt_mask(int cpu) } #endif -#if defined(CONFIG_SCHED_CLUSTER) && !defined(cpu_cluster_mask) -static inline const struct cpumask *cpu_cluster_mask(int cpu) -{ - return topology_cluster_cpumask(cpu); -} -#endif - static inline const struct cpumask *cpu_cpu_mask(int cpu) { return cpumask_of_node(cpu_to_node(cpu)); diff --git a/include/linux/torture.h b/include/linux/torture.h index 63fa4196e51c..7038104463e4 100644 --- a/include/linux/torture.h +++ b/include/linux/torture.h @@ -118,7 +118,7 @@ void _torture_stop_kthread(char *m, struct task_struct **tp); _torture_stop_kthread("Stopping " #n " task", &(tp)) #ifdef CONFIG_PREEMPTION -#define torture_preempt_schedule() preempt_schedule() +#define torture_preempt_schedule() __preempt_schedule() #else #define torture_preempt_schedule() do { } while (0) #endif diff --git a/include/linux/tpm_eventlog.h b/include/linux/tpm_eventlog.h index 739ba9a03ec1..20c0ff54b7a0 100644 --- a/include/linux/tpm_eventlog.h +++ b/include/linux/tpm_eventlog.h @@ -157,7 +157,7 @@ struct tcg_algorithm_info { * Return: size of the event on success, 0 on failure */ -static inline int __calc_tpm2_event_size(struct tcg_pcr_event2_head *event, +static __always_inline int __calc_tpm2_event_size(struct tcg_pcr_event2_head *event, struct tcg_pcr_event *event_header, bool do_mapping) { diff --git a/include/linux/trace.h b/include/linux/trace.h index bf169612ffe1..b5e16e438448 100644 --- a/include/linux/trace.h +++ b/include/linux/trace.h @@ -2,8 +2,6 @@ #ifndef _LINUX_TRACE_H #define _LINUX_TRACE_H -#ifdef CONFIG_TRACING - #define TRACE_EXPORT_FUNCTION BIT(0) #define TRACE_EXPORT_EVENT BIT(1) #define TRACE_EXPORT_MARKER BIT(2) @@ -28,6 +26,8 @@ struct trace_export { int flags; }; +#ifdef CONFIG_TRACING + int register_ftrace_export(struct trace_export *export); int unregister_ftrace_export(struct trace_export *export); @@ -48,6 +48,38 @@ void osnoise_arch_unregister(void); void osnoise_trace_irq_entry(int id); void osnoise_trace_irq_exit(int id, const char *desc); +#else /* CONFIG_TRACING */ +static inline int register_ftrace_export(struct trace_export *export) +{ + return -EINVAL; +} +static inline int unregister_ftrace_export(struct trace_export *export) +{ + return 0; +} +static inline void trace_printk_init_buffers(void) +{ +} +static inline int trace_array_printk(struct trace_array *tr, unsigned long ip, + const char *fmt, ...) +{ + return 0; +} +static inline int trace_array_init_printk(struct trace_array *tr) +{ + return -EINVAL; +} +static inline void trace_array_put(struct trace_array *tr) +{ +} +static inline struct trace_array *trace_array_get_by_name(const char *name) +{ + return NULL; +} +static inline int trace_array_destroy(struct trace_array *tr) +{ + return 0; +} #endif /* CONFIG_TRACING */ #endif /* _LINUX_TRACE_H */ diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 2d167ac3452c..20749bd9db71 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -15,6 +15,7 @@ struct array_buffer; struct tracer; struct dentry; struct bpf_prog; +union bpf_attr; const char *trace_print_flags_seq(struct trace_seq *p, const char *delim, unsigned long flags, @@ -91,6 +92,7 @@ struct trace_iterator { unsigned int temp_size; char *fmt; /* modified format holder */ unsigned int fmt_size; + long wait_index; /* trace_seq for __print_flags() and __print_symbolic() etc. */ struct trace_seq tmp_seq; @@ -172,6 +174,7 @@ enum trace_flag_type { TRACE_FLAG_SOFTIRQ = 0x10, TRACE_FLAG_PREEMPT_RESCHED = 0x20, TRACE_FLAG_NMI = 0x40, + TRACE_FLAG_BH_OFF = 0x80, }; #ifdef CONFIG_TRACE_IRQFLAGS_SUPPORT @@ -314,6 +317,7 @@ enum { TRACE_EVENT_FL_KPROBE_BIT, TRACE_EVENT_FL_UPROBE_BIT, TRACE_EVENT_FL_EPROBE_BIT, + TRACE_EVENT_FL_CUSTOM_BIT, }; /* @@ -327,6 +331,9 @@ enum { * KPROBE - Event is a kprobe * UPROBE - Event is a uprobe * EPROBE - Event is an event probe + * CUSTOM - Event is a custom event (to be attached to an exsiting tracepoint) + * This is set when the custom event has not been attached + * to a tracepoint yet, then it is cleared when it is. */ enum { TRACE_EVENT_FL_FILTERED = (1 << TRACE_EVENT_FL_FILTERED_BIT), @@ -338,6 +345,7 @@ enum { TRACE_EVENT_FL_KPROBE = (1 << TRACE_EVENT_FL_KPROBE_BIT), TRACE_EVENT_FL_UPROBE = (1 << TRACE_EVENT_FL_UPROBE_BIT), TRACE_EVENT_FL_EPROBE = (1 << TRACE_EVENT_FL_EPROBE_BIT), + TRACE_EVENT_FL_CUSTOM = (1 << TRACE_EVENT_FL_CUSTOM_BIT), }; #define TRACE_EVENT_FL_UKPROBE (TRACE_EVENT_FL_KPROBE | TRACE_EVENT_FL_UPROBE) @@ -439,7 +447,9 @@ static inline bool bpf_prog_array_valid(struct trace_event_call *call) static inline const char * trace_event_name(struct trace_event_call *call) { - if (call->flags & TRACE_EVENT_FL_TRACEPOINT) + if (call->flags & TRACE_EVENT_FL_CUSTOM) + return call->name; + else if (call->flags & TRACE_EVENT_FL_TRACEPOINT) return call->tp ? call->tp->name : NULL; else return call->name; @@ -698,6 +708,8 @@ event_triggers_post_call(struct trace_event_file *file, bool trace_event_ignore_this_pid(struct trace_event_file *trace_file); +bool __trace_trigger_soft_disabled(struct trace_event_file *file); + /** * trace_trigger_soft_disabled - do triggers and test if soft disabled * @file: The file pointer of the event to test @@ -707,20 +719,20 @@ bool trace_event_ignore_this_pid(struct trace_event_file *trace_file); * triggers that require testing the fields, it will return true, * otherwise false. */ -static inline bool +static __always_inline bool trace_trigger_soft_disabled(struct trace_event_file *file) { unsigned long eflags = file->flags; - if (!(eflags & EVENT_FILE_FL_TRIGGER_COND)) { - if (eflags & EVENT_FILE_FL_TRIGGER_MODE) - event_triggers_call(file, NULL, NULL, NULL); - if (eflags & EVENT_FILE_FL_SOFT_DISABLED) - return true; - if (eflags & EVENT_FILE_FL_PID_FILTER) - return trace_event_ignore_this_pid(file); - } - return false; + if (likely(!(eflags & (EVENT_FILE_FL_TRIGGER_MODE | + EVENT_FILE_FL_SOFT_DISABLED | + EVENT_FILE_FL_PID_FILTER)))) + return false; + + if (likely(eflags & EVENT_FILE_FL_TRIGGER_COND)) + return false; + + return __trace_trigger_soft_disabled(file); } #ifdef CONFIG_BPF_EVENTS @@ -735,6 +747,7 @@ void bpf_put_raw_tracepoint(struct bpf_raw_event_map *btp); int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id, u32 *fd_type, const char **buf, u64 *probe_offset, u64 *probe_addr); +int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog); #else static inline unsigned int trace_call_bpf(struct trace_event_call *call, void *ctx) { @@ -776,12 +789,18 @@ static inline int bpf_get_perf_event_info(const struct perf_event *event, { return -EOPNOTSUPP; } +static inline int +bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) +{ + return -EOPNOTSUPP; +} #endif enum { FILTER_OTHER = 0, FILTER_STATIC_STRING, FILTER_DYN_STRING, + FILTER_RDYN_STRING, FILTER_PTR_STRING, FILTER_TRACE_FN, FILTER_COMM, @@ -796,8 +815,6 @@ extern int trace_add_event_call(struct trace_event_call *call); extern int trace_remove_event_call(struct trace_event_call *call); extern int trace_event_get_offsets(struct trace_event_call *call); -#define is_signed_type(type) (((type)(-1)) < (type)1) - int ftrace_set_clr_event(struct trace_array *tr, char *buf, int set); int trace_set_clr_event(const char *system, const char *event, int set); int trace_array_set_clr_event(struct trace_array *tr, const char *system, @@ -898,4 +915,37 @@ perf_trace_buf_submit(void *raw_data, int size, int rctx, u16 type, #endif +#define TRACE_EVENT_STR_MAX 512 + +/* + * gcc warns that you can not use a va_list in an inlined + * function. But lets me make it into a macro :-/ + */ +#define __trace_event_vstr_len(fmt, va) \ +({ \ + va_list __ap; \ + int __ret; \ + \ + va_copy(__ap, *(va)); \ + __ret = vsnprintf(NULL, 0, fmt, __ap) + 1; \ + va_end(__ap); \ + \ + min(__ret, TRACE_EVENT_STR_MAX); \ +}) + #endif /* _LINUX_TRACE_EVENT_H */ + +/* + * Note: we keep the TRACE_CUSTOM_EVENT outside the include file ifdef protection. + * This is due to the way trace custom events work. If a file includes two + * trace event headers under one "CREATE_CUSTOM_TRACE_EVENTS" the first include + * will override the TRACE_CUSTOM_EVENT and break the second include. + */ + +#ifndef TRACE_CUSTOM_EVENT + +#define DECLARE_CUSTOM_EVENT_CLASS(name, proto, args, tstruct, assign, print) +#define DEFINE_CUSTOM_EVENT(template, name, proto, args) +#define TRACE_CUSTOM_EVENT(name, proto, args, struct, assign, print) + +#endif /* ifdef TRACE_CUSTOM_EVENT (see note above) */ diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h deleted file mode 100644 index 2564b7434b4d..000000000000 --- a/include/linux/tracehook.h +++ /dev/null @@ -1,227 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Tracing hooks - * - * Copyright (C) 2008-2009 Red Hat, Inc. All rights reserved. - * - * This file defines hook entry points called by core code where - * user tracing/debugging support might need to do something. These - * entry points are called tracehook_*(). Each hook declared below - * has a detailed kerneldoc comment giving the context (locking et - * al) from which it is called, and the meaning of its return value. - * - * Each function here typically has only one call site, so it is ok - * to have some nontrivial tracehook_*() inlines. In all cases, the - * fast path when no tracing is enabled should be very short. - * - * The purpose of this file and the tracehook_* layer is to consolidate - * the interface that the kernel core and arch code uses to enable any - * user debugging or tracing facility (such as ptrace). The interfaces - * here are carefully documented so that maintainers of core and arch - * code do not need to think about the implementation details of the - * tracing facilities. Likewise, maintainers of the tracing code do not - * need to understand all the calling core or arch code in detail, just - * documented circumstances of each call, such as locking conditions. - * - * If the calling core code changes so that locking is different, then - * it is ok to change the interface documented here. The maintainer of - * core code changing should notify the maintainers of the tracing code - * that they need to work out the change. - * - * Some tracehook_*() inlines take arguments that the current tracing - * implementations might not necessarily use. These function signatures - * are chosen to pass in all the information that is on hand in the - * caller and might conceivably be relevant to a tracer, so that the - * core code won't have to be updated when tracing adds more features. - * If a call site changes so that some of those parameters are no longer - * already on hand without extra work, then the tracehook_* interface - * can change so there is no make-work burden on the core code. The - * maintainer of core code changing should notify the maintainers of the - * tracing code that they need to work out the change. - */ - -#ifndef _LINUX_TRACEHOOK_H -#define _LINUX_TRACEHOOK_H 1 - -#include <linux/sched.h> -#include <linux/ptrace.h> -#include <linux/security.h> -#include <linux/task_work.h> -#include <linux/memcontrol.h> -#include <linux/blk-cgroup.h> -struct linux_binprm; - -/* - * ptrace report for syscall entry and exit looks identical. - */ -static inline int ptrace_report_syscall(struct pt_regs *regs, - unsigned long message) -{ - int ptrace = current->ptrace; - - if (!(ptrace & PT_PTRACED)) - return 0; - - current->ptrace_message = message; - ptrace_notify(SIGTRAP | ((ptrace & PT_TRACESYSGOOD) ? 0x80 : 0)); - - /* - * this isn't the same as continuing with a signal, but it will do - * for normal use. strace only continues with a signal if the - * stopping signal is not SIGTRAP. -brl - */ - if (current->exit_code) { - send_sig(current->exit_code, current, 1); - current->exit_code = 0; - } - - current->ptrace_message = 0; - return fatal_signal_pending(current); -} - -/** - * tracehook_report_syscall_entry - task is about to attempt a system call - * @regs: user register state of current task - * - * This will be called if %SYSCALL_WORK_SYSCALL_TRACE or - * %SYSCALL_WORK_SYSCALL_EMU have been set, when the current task has just - * entered the kernel for a system call. Full user register state is - * available here. Changing the values in @regs can affect the system - * call number and arguments to be tried. It is safe to block here, - * preventing the system call from beginning. - * - * Returns zero normally, or nonzero if the calling arch code should abort - * the system call. That must prevent normal entry so no system call is - * made. If @task ever returns to user mode after this, its register state - * is unspecified, but should be something harmless like an %ENOSYS error - * return. It should preserve enough information so that syscall_rollback() - * can work (see asm-generic/syscall.h). - * - * Called without locks, just after entering kernel mode. - */ -static inline __must_check int tracehook_report_syscall_entry( - struct pt_regs *regs) -{ - return ptrace_report_syscall(regs, PTRACE_EVENTMSG_SYSCALL_ENTRY); -} - -/** - * tracehook_report_syscall_exit - task has just finished a system call - * @regs: user register state of current task - * @step: nonzero if simulating single-step or block-step - * - * This will be called if %SYSCALL_WORK_SYSCALL_TRACE has been set, when - * the current task has just finished an attempted system call. Full - * user register state is available here. It is safe to block here, - * preventing signals from being processed. - * - * If @step is nonzero, this report is also in lieu of the normal - * trap that would follow the system call instruction because - * user_enable_block_step() or user_enable_single_step() was used. - * In this case, %SYSCALL_WORK_SYSCALL_TRACE might not be set. - * - * Called without locks, just before checking for pending signals. - */ -static inline void tracehook_report_syscall_exit(struct pt_regs *regs, int step) -{ - if (step) - user_single_step_report(regs); - else - ptrace_report_syscall(regs, PTRACE_EVENTMSG_SYSCALL_EXIT); -} - -/** - * tracehook_signal_handler - signal handler setup is complete - * @stepping: nonzero if debugger single-step or block-step in use - * - * Called by the arch code after a signal handler has been set up. - * Register and stack state reflects the user handler about to run. - * Signal mask changes have already been made. - * - * Called without locks, shortly before returning to user mode - * (or handling more signals). - */ -static inline void tracehook_signal_handler(int stepping) -{ - if (stepping) - ptrace_notify(SIGTRAP); -} - -/** - * set_notify_resume - cause tracehook_notify_resume() to be called - * @task: task that will call tracehook_notify_resume() - * - * Calling this arranges that @task will call tracehook_notify_resume() - * before returning to user mode. If it's already running in user mode, - * it will enter the kernel and call tracehook_notify_resume() soon. - * If it's blocked, it will not be woken. - */ -static inline void set_notify_resume(struct task_struct *task) -{ -#ifdef TIF_NOTIFY_RESUME - if (!test_and_set_tsk_thread_flag(task, TIF_NOTIFY_RESUME)) - kick_process(task); -#endif -} - -/** - * tracehook_notify_resume - report when about to return to user mode - * @regs: user-mode registers of @current task - * - * This is called when %TIF_NOTIFY_RESUME has been set. Now we are - * about to return to user mode, and the user state in @regs can be - * inspected or adjusted. The caller in arch code has cleared - * %TIF_NOTIFY_RESUME before the call. If the flag gets set again - * asynchronously, this will be called again before we return to - * user mode. - * - * Called without locks. - */ -static inline void tracehook_notify_resume(struct pt_regs *regs) -{ - clear_thread_flag(TIF_NOTIFY_RESUME); - /* - * This barrier pairs with task_work_add()->set_notify_resume() after - * hlist_add_head(task->task_works); - */ - smp_mb__after_atomic(); - if (unlikely(current->task_works)) - task_work_run(); - -#ifdef CONFIG_KEYS_REQUEST_CACHE - if (unlikely(current->cached_requested_key)) { - key_put(current->cached_requested_key); - current->cached_requested_key = NULL; - } -#endif - - mem_cgroup_handle_over_high(); - blkcg_maybe_throttle_current(); - - rseq_handle_notify_resume(NULL, regs); -} - -/* - * called by exit_to_user_mode_loop() if ti_work & _TIF_NOTIFY_SIGNAL. This - * is currently used by TWA_SIGNAL based task_work, which requires breaking - * wait loops to ensure that task_work is noticed and run. - */ -static inline void tracehook_notify_signal(void) -{ - clear_thread_flag(TIF_NOTIFY_SIGNAL); - smp_mb__after_atomic(); - if (current->task_works) - task_work_run(); -} - -/* - * Called when we have work to process from exit_to_user_mode_loop() - */ -static inline void set_notify_signal(struct task_struct *task) -{ - if (!test_and_set_tsk_thread_flag(task, TIF_NOTIFY_SIGNAL) && - !wake_up_state(task, TASK_INTERRUPTIBLE)) - kick_process(task); -} - -#endif /* <linux/tracehook.h> */ diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index 28031b15f878..4b33b95eb8be 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -151,7 +151,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) /* * Individual subsystem my have a separate configuration to * enable their tracepoints. By default, this file will create - * the tracepoints if CONFIG_TRACEPOINT is defined. If a subsystem + * the tracepoints if CONFIG_TRACEPOINTS is defined. If a subsystem * wants to be able to disable its tracepoints from being created * it can define NOTRACE before including the tracepoint headers. */ @@ -200,13 +200,13 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) */ \ if (rcuidle) { \ __idx = srcu_read_lock_notrace(&tracepoint_srcu);\ - rcu_irq_enter_irqson(); \ + ct_irq_enter_irqson(); \ } \ \ __DO_TRACE_CALL(name, TP_ARGS(args)); \ \ if (rcuidle) { \ - rcu_irq_exit_irqson(); \ + ct_irq_exit_irqson(); \ srcu_read_unlock_notrace(&tracepoint_srcu, __idx);\ } \ \ diff --git a/include/linux/tty.h b/include/linux/tty.h index 5dbd7c5afac7..730c3301d710 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -122,33 +122,81 @@ struct tty_operations; /** * struct tty_struct - state associated with a tty while open * - * @flow.lock: lock for flow members - * @flow.stopped: tty stopped/started by tty_stop/tty_start - * @flow.tco_stopped: tty stopped/started by TCOOFF/TCOON ioctls (it has - * precedense over @flow.stopped) + * @kref: reference counting by tty_kref_get() and tty_kref_put(), reaching zero + * frees the structure + * @dev: class device or %NULL (e.g. ptys, serdev) + * @driver: &struct tty_driver operating this tty + * @ops: &struct tty_operations of @driver for this tty (open, close, etc.) + * @index: index of this tty (e.g. to construct @name like tty12) + * @ldisc_sem: protects line discipline changes (@ldisc) -- lock tty not pty + * @ldisc: the current line discipline for this tty (n_tty by default) + * @atomic_write_lock: protects against concurrent writers, i.e. locks + * @write_cnt, @write_buf and similar + * @legacy_mutex: leftover from history (BKL -> BTM -> @legacy_mutex), + * protecting several operations on this tty + * @throttle_mutex: protects against concurrent tty_throttle_safe() and + * tty_unthrottle_safe() (but not tty_unthrottle()) + * @termios_rwsem: protects @termios and @termios_locked + * @winsize_mutex: protects @winsize + * @termios: termios for the current tty, copied from/to @driver.termios + * @termios_locked: locked termios (by %TIOCGLCKTRMIOS and %TIOCSLCKTRMIOS + * ioctls) + * @name: name of the tty constructed by tty_line_name() (e.g. ttyS3) + * @flags: bitwise OR of %TTY_THROTTLED, %TTY_IO_ERROR, ... + * @count: count of open processes, reaching zero cancels all the work for + * this tty and drops a @kref too (but does not free this tty) + * @winsize: size of the terminal "window" (cf. @winsize_mutex) + * @flow: flow settings grouped together, see also @flow.unused + * @flow.lock: lock for @flow members + * @flow.stopped: tty stopped/started by stop_tty()/start_tty() + * @flow.tco_stopped: tty stopped/started by %TCOOFF/%TCOON ioctls (it has + * precedence over @flow.stopped) * @flow.unused: alignment for Alpha, so that no members other than @flow.* are * modified by the same 64b word store. The @flow's __aligned is * there for the very same reason. - * @ctrl.lock: lock for ctrl members + * @ctrl: control settings grouped together, see also @ctrl.unused + * @ctrl.lock: lock for @ctrl members * @ctrl.pgrp: process group of this tty (setpgrp(2)) * @ctrl.session: session of this tty (setsid(2)). Writes are protected by both - * @ctrl.lock and legacy mutex, readers must use at least one of + * @ctrl.lock and @legacy_mutex, readers must use at least one of * them. - * @ctrl.pktstatus: packet mode status (bitwise OR of TIOCPKT_* constants) + * @ctrl.pktstatus: packet mode status (bitwise OR of %TIOCPKT_ constants) * @ctrl.packet: packet mode enabled + * @ctrl.unused: alignment for Alpha, see @flow.unused for explanation + * @hw_stopped: not controlled by the tty layer, under @driver's control for CTS + * handling + * @receive_room: bytes permitted to feed to @ldisc without any being lost + * @flow_change: controls behavior of throttling, see tty_throttle_safe() and + * tty_unthrottle_safe() + * @link: link to another pty (master -> slave and vice versa) + * @fasync: state for %O_ASYNC (for %SIGIO); managed by fasync_helper() + * @write_wait: concurrent writers are waiting in this queue until they are + * allowed to write + * @read_wait: readers wait for data in this queue + * @hangup_work: normally a work to perform a hangup (do_tty_hangup()); while + * freeing the tty, (re)used to release_one_tty() + * @disc_data: pointer to @ldisc's private data (e.g. to &struct n_tty_data) + * @driver_data: pointer to @driver's private data (e.g. &struct uart_state) + * @files_lock: protects @tty_files list + * @tty_files: list of (re)openers of this tty (i.e. linked &struct + * tty_file_private) + * @closing: when set during close, n_tty processes only START & STOP chars + * @write_buf: temporary buffer used during tty_write() to copy user data to + * @write_cnt: count of bytes written in tty_write() to @write_buf + * @SAK_work: if the tty has a pending do_SAK, it is queued here + * @port: persistent storage for this device (i.e. &struct tty_port) * * All of the state associated with a tty while the tty is open. Persistent - * storage for tty devices is referenced here as @port in struct tty_port. + * storage for tty devices is referenced here as @port and is documented in + * &struct tty_port. */ struct tty_struct { - int magic; struct kref kref; - struct device *dev; /* class device or NULL (e.g. ptys, serdev) */ + struct device *dev; struct tty_driver *driver; const struct tty_operations *ops; int index; - /* Protects ldisc changes: Lock tty not pty */ struct ld_semaphore ldisc_sem; struct tty_ldisc *ldisc; @@ -157,12 +205,11 @@ struct tty_struct { struct mutex throttle_mutex; struct rw_semaphore termios_rwsem; struct mutex winsize_mutex; - /* Termios values are protected by the termios rwsem */ struct ktermios termios, termios_locked; char name[64]; unsigned long flags; int count; - struct winsize winsize; /* winsize_mutex */ + struct winsize winsize; struct { spinlock_t lock; @@ -181,7 +228,7 @@ struct tty_struct { } __aligned(sizeof(unsigned long)) ctrl; int hw_stopped; - unsigned int receive_room; /* Bytes free for queue */ + unsigned int receive_room; int flow_change; struct tty_struct *link; @@ -191,7 +238,7 @@ struct tty_struct { struct work_struct hangup_work; void *disc_data; void *driver_data; - spinlock_t files_lock; /* protects tty_files list */ + spinlock_t files_lock; struct list_head tty_files; #define N_TTY_BUF_SIZE 4096 @@ -199,7 +246,6 @@ struct tty_struct { int closing; unsigned char *write_buf; int write_cnt; - /* If the tty has a pending do_SAK, queue it here - akpm */ struct work_struct SAK_work; struct tty_port *port; } __randomize_layout; @@ -211,29 +257,72 @@ struct tty_file_private { struct list_head list; }; -/* tty magic number */ -#define TTY_MAGIC 0x5401 - -/* - * These bits are used in the flags field of the tty structure. +/** + * DOC: TTY Struct Flags + * + * These bits are used in the :c:member:`tty_struct.flags` field. * * So that interrupts won't be able to mess up the queues, * copy_to_cooked must be atomic with respect to itself, as must * tty->write. Thus, you must use the inline functions set_bit() and * clear_bit() to make things atomic. + * + * TTY_THROTTLED + * Driver input is throttled. The ldisc should call + * :c:member:`tty_driver.unthrottle()` in order to resume reception when + * it is ready to process more data (at threshold min). + * + * TTY_IO_ERROR + * If set, causes all subsequent userspace read/write calls on the tty to + * fail, returning -%EIO. (May be no ldisc too.) + * + * TTY_OTHER_CLOSED + * Device is a pty and the other side has closed. + * + * TTY_EXCLUSIVE + * Exclusive open mode (a single opener). + * + * TTY_DO_WRITE_WAKEUP + * If set, causes the driver to call the + * :c:member:`tty_ldisc_ops.write_wakeup()` method in order to resume + * transmission when it can accept more data to transmit. + * + * TTY_LDISC_OPEN + * Indicates that a line discipline is open. For debugging purposes only. + * + * TTY_PTY_LOCK + * A flag private to pty code to implement %TIOCSPTLCK/%TIOCGPTLCK logic. + * + * TTY_NO_WRITE_SPLIT + * Prevent driver from splitting up writes into smaller chunks (preserve + * write boundaries to driver). + * + * TTY_HUPPED + * The TTY was hung up. This is set post :c:member:`tty_driver.hangup()`. + * + * TTY_HUPPING + * The TTY is in the process of hanging up to abort potential readers. + * + * TTY_LDISC_CHANGING + * Line discipline for this TTY is being changed. I/O should not block + * when this is set. Use tty_io_nonblock() to check. + * + * TTY_LDISC_HALTED + * Line discipline for this TTY was stopped. No work should be queued to + * this ldisc. */ -#define TTY_THROTTLED 0 /* Call unthrottle() at threshold min */ -#define TTY_IO_ERROR 1 /* Cause an I/O error (may be no ldisc too) */ -#define TTY_OTHER_CLOSED 2 /* Other side (if any) has closed */ -#define TTY_EXCLUSIVE 3 /* Exclusive open mode */ -#define TTY_DO_WRITE_WAKEUP 5 /* Call write_wakeup after queuing new */ -#define TTY_LDISC_OPEN 11 /* Line discipline is open */ -#define TTY_PTY_LOCK 16 /* pty private */ -#define TTY_NO_WRITE_SPLIT 17 /* Preserve write boundaries to driver */ -#define TTY_HUPPED 18 /* Post driver->hangup() */ -#define TTY_HUPPING 19 /* Hangup in progress */ -#define TTY_LDISC_CHANGING 20 /* Change pending - non-block IO */ -#define TTY_LDISC_HALTED 22 /* Line discipline is halted */ +#define TTY_THROTTLED 0 +#define TTY_IO_ERROR 1 +#define TTY_OTHER_CLOSED 2 +#define TTY_EXCLUSIVE 3 +#define TTY_DO_WRITE_WAKEUP 5 +#define TTY_LDISC_OPEN 11 +#define TTY_PTY_LOCK 16 +#define TTY_NO_WRITE_SPLIT 17 +#define TTY_HUPPED 18 +#define TTY_HUPPING 19 +#define TTY_LDISC_CHANGING 20 +#define TTY_LDISC_HALTED 22 static inline bool tty_io_nonblock(struct tty_struct *tty, struct file *file) { @@ -339,7 +428,7 @@ int tty_hung_up_p(struct file *filp); void do_SAK(struct tty_struct *tty); void __do_SAK(struct tty_struct *tty); void no_tty(void); -speed_t tty_termios_baud_rate(struct ktermios *termios); +speed_t tty_termios_baud_rate(const struct ktermios *termios); void tty_termios_encode_baud_rate(struct ktermios *termios, speed_t ibaud, speed_t obaud); void tty_encode_baud_rate(struct tty_struct *tty, speed_t ibaud, @@ -363,7 +452,7 @@ static inline speed_t tty_get_baud_rate(struct tty_struct *tty) unsigned char tty_get_char_size(unsigned int cflag); unsigned char tty_get_frame_size(unsigned int cflag); -void tty_termios_copy_hw(struct ktermios *new, struct ktermios *old); +void tty_termios_copy_hw(struct ktermios *new, const struct ktermios *old); int tty_termios_hw_change(const struct ktermios *a, const struct ktermios *b); int tty_set_termios(struct tty_struct *tty, struct ktermios *kt); diff --git a/include/linux/tty_buffer.h b/include/linux/tty_buffer.h index 3b9d77604291..1796648c2907 100644 --- a/include/linux/tty_buffer.h +++ b/include/linux/tty_buffer.h @@ -15,6 +15,7 @@ struct tty_buffer { int used; int size; int commit; + int lookahead; /* Lazy update on recv, can become less than "read" */ int read; int flags; /* Data points here */ diff --git a/include/linux/tty_driver.h b/include/linux/tty_driver.h index 795b94ccdeb6..e00034118c7b 100644 --- a/include/linux/tty_driver.h +++ b/include/linux/tty_driver.h @@ -2,248 +2,351 @@ #ifndef _LINUX_TTY_DRIVER_H #define _LINUX_TTY_DRIVER_H -/* - * This structure defines the interface between the low-level tty - * driver and the tty routines. The following routines can be - * defined; unless noted otherwise, they are optional, and can be - * filled in with a null pointer. +#include <linux/export.h> +#include <linux/fs.h> +#include <linux/kref.h> +#include <linux/list.h> +#include <linux/cdev.h> +#include <linux/uaccess.h> +#include <linux/termios.h> +#include <linux/seq_file.h> + +struct tty_struct; +struct tty_driver; +struct serial_icounter_struct; +struct serial_struct; + +/** + * struct tty_operations -- interface between driver and tty + * + * @lookup: ``struct tty_struct *()(struct tty_driver *self, struct file *, + * int idx)`` * - * struct tty_struct * (*lookup)(struct tty_driver *self, struct file *, int idx) + * Return the tty device corresponding to @idx, %NULL if there is not + * one currently in use and an %ERR_PTR value on error. Called under + * %tty_mutex (for now!) * - * Return the tty device corresponding to idx, NULL if there is not - * one currently in use and an ERR_PTR value on error. Called under - * tty_mutex (for now!) + * Optional method. Default behaviour is to use the @self->ttys array. * - * Optional method. Default behaviour is to use the ttys array + * @install: ``int ()(struct tty_driver *self, struct tty_struct *tty)`` * - * int (*install)(struct tty_driver *self, struct tty_struct *tty) + * Install a new @tty into the @self's internal tables. Used in + * conjunction with @lookup and @remove methods. * - * Install a new tty into the tty driver internal tables. Used in - * conjunction with lookup and remove methods. + * Optional method. Default behaviour is to use the @self->ttys array. * - * Optional method. Default behaviour is to use the ttys array + * @remove: ``void ()(struct tty_driver *self, struct tty_struct *tty)`` * - * void (*remove)(struct tty_driver *self, struct tty_struct *tty) + * Remove a closed @tty from the @self's internal tables. Used in + * conjunction with @lookup and @remove methods. * - * Remove a closed tty from the tty driver internal tables. Used in - * conjunction with lookup and remove methods. + * Optional method. Default behaviour is to use the @self->ttys array. * - * Optional method. Default behaviour is to use the ttys array + * @open: ``int ()(struct tty_struct *tty, struct file *)`` * - * int (*open)(struct tty_struct * tty, struct file * filp); + * This routine is called when a particular @tty device is opened. This + * routine is mandatory; if this routine is not filled in, the attempted + * open will fail with %ENODEV. * - * This routine is called when a particular tty device is opened. - * This routine is mandatory; if this routine is not filled in, - * the attempted open will fail with ENODEV. + * Required method. Called with tty lock held. May sleep. * - * Required method. Called with tty lock held. + * @close: ``void ()(struct tty_struct *tty, struct file *)`` * - * void (*close)(struct tty_struct * tty, struct file * filp); + * This routine is called when a particular @tty device is closed. At the + * point of return from this call the driver must make no further ldisc + * calls of any kind. * - * This routine is called when a particular tty device is closed. - * Note: called even if the corresponding open() failed. + * Remark: called even if the corresponding @open() failed. * - * Required method. Called with tty lock held. + * Required method. Called with tty lock held. May sleep. * - * void (*shutdown)(struct tty_struct * tty); + * @shutdown: ``void ()(struct tty_struct *tty)`` * - * This routine is called under the tty lock when a particular tty device - * is closed for the last time. It executes before the tty resources - * are freed so may execute while another function holds a tty kref. + * This routine is called under the tty lock when a particular @tty device + * is closed for the last time. It executes before the @tty resources + * are freed so may execute while another function holds a @tty kref. * - * void (*cleanup)(struct tty_struct * tty); + * @cleanup: ``void ()(struct tty_struct *tty)`` * - * This routine is called asynchronously when a particular tty device + * This routine is called asynchronously when a particular @tty device * is closed for the last time freeing up the resources. This is * actually the second part of shutdown for routines that might sleep. * + * @write: ``int ()(struct tty_struct *tty, const unsigned char *buf, + * int count)`` * - * int (*write)(struct tty_struct * tty, - * const unsigned char *buf, int count); - * - * This routine is called by the kernel to write a series of - * characters to the tty device. The characters may come from - * user space or kernel space. This routine will return the + * This routine is called by the kernel to write a series (@count) of + * characters (@buf) to the @tty device. The characters may come from + * user space or kernel space. This routine will return the * number of characters actually accepted for writing. * - * Optional: Required for writable devices. + * May occur in parallel in special cases. Because this includes panic + * paths drivers generally shouldn't try and do clever locking here. * - * int (*put_char)(struct tty_struct *tty, unsigned char ch); + * Optional: Required for writable devices. May not sleep. * - * This routine is called by the kernel to write a single - * character to the tty device. If the kernel uses this routine, - * it must call the flush_chars() routine (if defined) when it is - * done stuffing characters into the driver. If there is no room - * in the queue, the character is ignored. + * @put_char: ``int ()(struct tty_struct *tty, unsigned char ch)`` * - * Optional: Kernel will use the write method if not provided. + * This routine is called by the kernel to write a single character @ch to + * the @tty device. If the kernel uses this routine, it must call the + * @flush_chars() routine (if defined) when it is done stuffing characters + * into the driver. If there is no room in the queue, the character is + * ignored. * - * Note: Do not call this function directly, call tty_put_char + * Optional: Kernel will use the @write method if not provided. Do not + * call this function directly, call tty_put_char(). * - * void (*flush_chars)(struct tty_struct *tty); + * @flush_chars: ``void ()(struct tty_struct *tty)`` * - * This routine is called by the kernel after it has written a - * series of characters to the tty device using put_char(). + * This routine is called by the kernel after it has written a + * series of characters to the tty device using @put_char(). * - * Optional: + * Optional. Do not call this function directly, call + * tty_driver_flush_chars(). * - * Note: Do not call this function directly, call tty_driver_flush_chars - * - * unsigned int (*write_room)(struct tty_struct *tty); + * @write_room: ``unsigned int ()(struct tty_struct *tty)`` * - * This routine returns the numbers of characters the tty driver - * will accept for queuing to be written. This number is subject - * to change as output buffers get emptied, or if the output flow + * This routine returns the numbers of characters the @tty driver + * will accept for queuing to be written. This number is subject + * to change as output buffers get emptied, or if the output flow * control is acted. * - * Required if write method is provided else not needed. + * The ldisc is responsible for being intelligent about multi-threading of + * write_room/write calls + * + * Required if @write method is provided else not needed. Do not call this + * function directly, call tty_write_room() + * + * @chars_in_buffer: ``unsigned int ()(struct tty_struct *tty)`` + * + * This routine returns the number of characters in the device private + * output queue. Used in tty_wait_until_sent() and for poll() + * implementation. * - * Note: Do not call this function directly, call tty_write_room - * - * int (*ioctl)(struct tty_struct *tty, unsigned int cmd, unsigned long arg); + * Optional: if not provided, it is assumed there is no queue on the + * device. Do not call this function directly, call tty_chars_in_buffer(). * - * This routine allows the tty driver to implement - * device-specific ioctls. If the ioctl number passed in cmd - * is not recognized by the driver, it should return ENOIOCTLCMD. + * @ioctl: ``int ()(struct tty_struct *tty, unsigned int cmd, + * unsigned long arg)`` * - * Optional + * This routine allows the @tty driver to implement device-specific + * ioctls. If the ioctl number passed in @cmd is not recognized by the + * driver, it should return %ENOIOCTLCMD. * - * long (*compat_ioctl)(struct tty_struct *tty,, - * unsigned int cmd, unsigned long arg); + * Optional. * - * implement ioctl processing for 32 bit process on 64 bit system + * @compat_ioctl: ``long ()(struct tty_struct *tty, unsigned int cmd, + * unsigned long arg)`` * - * Optional - * - * void (*set_termios)(struct tty_struct *tty, struct ktermios * old); + * Implement ioctl processing for 32 bit process on 64 bit system. * - * This routine allows the tty driver to be notified when - * device's termios settings have changed. + * Optional. * - * Optional: Called under the termios lock + * @set_termios: ``void ()(struct tty_struct *tty, const struct ktermios *old)`` * + * This routine allows the @tty driver to be notified when device's + * termios settings have changed. New settings are in @tty->termios. + * Previous settings are passed in the @old argument. * - * void (*set_ldisc)(struct tty_struct *tty); + * The API is defined such that the driver should return the actual modes + * selected. This means that the driver is responsible for modifying any + * bits in @tty->termios it cannot fulfill to indicate the actual modes + * being used. * - * This routine allows the tty driver to be notified when the - * device's termios settings have changed. + * Optional. Called under the @tty->termios_rwsem. May sleep. * - * Optional: Called under BKL (currently) - * - * void (*throttle)(struct tty_struct * tty); + * @set_ldisc: ``void ()(struct tty_struct *tty)`` * - * This routine notifies the tty driver that input buffers for - * the line discipline are close to full, and it should somehow - * signal that no more characters should be sent to the tty. + * This routine allows the @tty driver to be notified when the device's + * line discipline is being changed. At the point this is done the + * discipline is not yet usable. * - * Optional: Always invoke via tty_throttle_safe(), called under the - * termios lock. - * - * void (*unthrottle)(struct tty_struct * tty); + * Optional. Called under the @tty->ldisc_sem and @tty->termios_rwsem. * - * This routine notifies the tty drivers that it should signals - * that characters can now be sent to the tty without fear of - * overrunning the input buffers of the line disciplines. - * - * Optional: Always invoke via tty_unthrottle(), called under the - * termios lock. + * @throttle: ``void ()(struct tty_struct *tty)`` * - * void (*stop)(struct tty_struct *tty); + * This routine notifies the @tty driver that input buffers for the line + * discipline are close to full, and it should somehow signal that no more + * characters should be sent to the @tty. * - * This routine notifies the tty driver that it should stop - * outputting characters to the tty device. + * Serialization including with @unthrottle() is the job of the ldisc + * layer. * - * Called with ->flow.lock held. Serialized with start() method. + * Optional: Always invoke via tty_throttle_safe(). Called under the + * @tty->termios_rwsem. * - * Optional: + * @unthrottle: ``void ()(struct tty_struct *tty)`` * - * Note: Call stop_tty not this method. - * - * void (*start)(struct tty_struct *tty); + * This routine notifies the @tty driver that it should signal that + * characters can now be sent to the @tty without fear of overrunning the + * input buffers of the line disciplines. * - * This routine notifies the tty driver that it resume sending + * Optional. Always invoke via tty_unthrottle(). Called under the + * @tty->termios_rwsem. + * + * @stop: ``void ()(struct tty_struct *tty)`` + * + * This routine notifies the @tty driver that it should stop outputting * characters to the tty device. * - * Called with ->flow.lock held. Serialized with stop() method. + * Called with @tty->flow.lock held. Serialized with @start() method. + * + * Optional. Always invoke via stop_tty(). + * + * @start: ``void ()(struct tty_struct *tty)`` + * + * This routine notifies the @tty driver that it resumed sending + * characters to the @tty device. + * + * Called with @tty->flow.lock held. Serialized with stop() method. + * + * Optional. Always invoke via start_tty(). + * + * @hangup: ``void ()(struct tty_struct *tty)`` + * + * This routine notifies the @tty driver that it should hang up the @tty + * device. * - * Optional: + * Optional. Called with tty lock held. * - * Note: Call start_tty not this method. - * - * void (*hangup)(struct tty_struct *tty); + * @break_ctl: ``int ()(struct tty_struct *tty, int state)`` * - * This routine notifies the tty driver that it should hang up the - * tty device. + * This optional routine requests the @tty driver to turn on or off BREAK + * status on the RS-232 port. If @state is -1, then the BREAK status + * should be turned on; if @state is 0, then BREAK should be turned off. * - * Optional: + * If this routine is implemented, the high-level tty driver will handle + * the following ioctls: %TCSBRK, %TCSBRKP, %TIOCSBRK, %TIOCCBRK. * - * Called with tty lock held. + * If the driver sets %TTY_DRIVER_HARDWARE_BREAK in tty_alloc_driver(), + * then the interface will also be called with actual times and the + * hardware is expected to do the delay work itself. 0 and -1 are still + * used for on/off. * - * int (*break_ctl)(struct tty_struct *tty, int state); + * Optional: Required for %TCSBRK/%BRKP/etc. handling. May sleep. * - * This optional routine requests the tty driver to turn on or - * off BREAK status on the RS-232 port. If state is -1, - * then the BREAK status should be turned on; if state is 0, then - * BREAK should be turned off. + * @flush_buffer: ``void ()(struct tty_struct *tty)`` * - * If this routine is implemented, the high-level tty driver will - * handle the following ioctls: TCSBRK, TCSBRKP, TIOCSBRK, - * TIOCCBRK. + * This routine discards device private output buffer. Invoked on close, + * hangup, to implement %TCOFLUSH ioctl and similar. * - * If the driver sets TTY_DRIVER_HARDWARE_BREAK then the interface - * will also be called with actual times and the hardware is expected - * to do the delay work itself. 0 and -1 are still used for on/off. + * Optional: if not provided, it is assumed there is no queue on the + * device. Do not call this function directly, call + * tty_driver_flush_buffer(). * - * Optional: Required for TCSBRK/BRKP/etc handling. + * @wait_until_sent: ``void ()(struct tty_struct *tty, int timeout)`` * - * void (*wait_until_sent)(struct tty_struct *tty, int timeout); - * - * This routine waits until the device has written out all of the - * characters in its transmitter FIFO. + * This routine waits until the device has written out all of the + * characters in its transmitter FIFO. Or until @timeout (in jiffies) is + * reached. * - * Optional: If not provided the device is assumed to have no FIFO + * Optional: If not provided, the device is assumed to have no FIFO. + * Usually correct to invoke via tty_wait_until_sent(). May sleep. * - * Note: Usually correct to call tty_wait_until_sent + * @send_xchar: ``void ()(struct tty_struct *tty, char ch)`` * - * void (*send_xchar)(struct tty_struct *tty, char ch); + * This routine is used to send a high-priority XON/XOFF character (@ch) + * to the @tty device. * - * This routine is used to send a high-priority XON/XOFF - * character to the device. + * Optional: If not provided, then the @write method is called under + * the @tty->atomic_write_lock to keep it serialized with the ldisc. * - * Optional: If not provided then the write method is called under - * the atomic write lock to keep it serialized with the ldisc. + * @tiocmget: ``int ()(struct tty_struct *tty)`` * - * int (*resize)(struct tty_struct *tty, struct winsize *ws) + * This routine is used to obtain the modem status bits from the @tty + * driver. * - * Called when a termios request is issued which changes the - * requested terminal geometry. + * Optional: If not provided, then %ENOTTY is returned from the %TIOCMGET + * ioctl. Do not call this function directly, call tty_tiocmget(). + * + * @tiocmset: ``int ()(struct tty_struct *tty, + * unsigned int set, unsigned int clear)`` + * + * This routine is used to set the modem status bits to the @tty driver. + * First, @clear bits should be cleared, then @set bits set. + * + * Optional: If not provided, then %ENOTTY is returned from the %TIOCMSET + * ioctl. Do not call this function directly, call tty_tiocmset(). + * + * @resize: ``int ()(struct tty_struct *tty, struct winsize *ws)`` + * + * Called when a termios request is issued which changes the requested + * terminal geometry to @ws. * * Optional: the default action is to update the termios structure * without error. This is usually the correct behaviour. Drivers should - * not force errors here if they are not resizable objects (eg a serial + * not force errors here if they are not resizable objects (e.g. a serial * line). See tty_do_resize() if you need to wrap the standard method - * in your own logic - the usual case. + * in your own logic -- the usual case. + * + * @get_icount: ``int ()(struct tty_struct *tty, + * struct serial_icounter *icount)`` + * + * Called when the @tty device receives a %TIOCGICOUNT ioctl. Passed a + * kernel structure @icount to complete. + * + * Optional: called only if provided, otherwise %ENOTTY will be returned. + * + * @get_serial: ``int ()(struct tty_struct *tty, struct serial_struct *p)`` * - * int (*get_icount)(struct tty_struct *tty, struct serial_icounter *icount); + * Called when the @tty device receives a %TIOCGSERIAL ioctl. Passed a + * kernel structure @p (&struct serial_struct) to complete. * - * Called when the device receives a TIOCGICOUNT ioctl. Passed a kernel - * structure to complete. This method is optional and will only be called - * if provided (otherwise ENOTTY will be returned). + * Optional: called only if provided, otherwise %ENOTTY will be returned. + * Do not call this function directly, call tty_tiocgserial(). + * + * @set_serial: ``int ()(struct tty_struct *tty, struct serial_struct *p)`` + * + * Called when the @tty device receives a %TIOCSSERIAL ioctl. Passed a + * kernel structure @p (&struct serial_struct) to set the values from. + * + * Optional: called only if provided, otherwise %ENOTTY will be returned. + * Do not call this function directly, call tty_tiocsserial(). + * + * @show_fdinfo: ``void ()(struct tty_struct *tty, struct seq_file *m)`` + * + * Called when the @tty device file descriptor receives a fdinfo request + * from VFS (to show in /proc/<pid>/fdinfo/). @m should be filled with + * information. + * + * Optional: called only if provided, otherwise nothing is written to @m. + * Do not call this function directly, call tty_show_fdinfo(). + * + * @poll_init: ``int ()(struct tty_driver *driver, int line, char *options)`` + * + * kgdboc support (Documentation/dev-tools/kgdb.rst). This routine is + * called to initialize the HW for later use by calling @poll_get_char or + * @poll_put_char. + * + * Optional: called only if provided, otherwise skipped as a non-polling + * driver. + * + * @poll_get_char: ``int ()(struct tty_driver *driver, int line)`` + * + * kgdboc support (see @poll_init). @driver should read a character from a + * tty identified by @line and return it. + * + * Optional: called only if @poll_init provided. + * + * @poll_put_char: ``void ()(struct tty_driver *driver, int line, char ch)`` + * + * kgdboc support (see @poll_init). @driver should write character @ch to + * a tty identified by @line. + * + * Optional: called only if @poll_init provided. + * + * @proc_show: ``int ()(struct seq_file *m, void *driver)`` + * + * Driver @driver (cast to &struct tty_driver) can show additional info in + * /proc/tty/driver/<driver_name>. It is enough to fill in the information + * into @m. + * + * Optional: called only if provided, otherwise no /proc entry created. + * + * This structure defines the interface between the low-level tty driver and + * the tty routines. These routines can be defined. Unless noted otherwise, + * they are optional, and can be filled in with a %NULL pointer. */ - -#include <linux/export.h> -#include <linux/fs.h> -#include <linux/kref.h> -#include <linux/list.h> -#include <linux/cdev.h> -#include <linux/termios.h> -#include <linux/seq_file.h> - -struct tty_struct; -struct tty_driver; -struct serial_icounter_struct; -struct serial_struct; - struct tty_operations { struct tty_struct * (*lookup)(struct tty_driver *driver, struct file *filp, int idx); @@ -263,7 +366,7 @@ struct tty_operations { unsigned int cmd, unsigned long arg); long (*compat_ioctl)(struct tty_struct *tty, unsigned int cmd, unsigned long arg); - void (*set_termios)(struct tty_struct *tty, struct ktermios * old); + void (*set_termios)(struct tty_struct *tty, const struct ktermios *old); void (*throttle)(struct tty_struct * tty); void (*unthrottle)(struct tty_struct * tty); void (*stop)(struct tty_struct *tty); @@ -288,26 +391,62 @@ struct tty_operations { int (*poll_get_char)(struct tty_driver *driver, int line); void (*poll_put_char)(struct tty_driver *driver, int line, char ch); #endif - int (*proc_show)(struct seq_file *, void *); + int (*proc_show)(struct seq_file *m, void *driver); } __randomize_layout; +/** + * struct tty_driver -- driver for TTY devices + * + * @kref: reference counting. Reaching zero frees all the internals and the + * driver. + * @cdevs: allocated/registered character /dev devices + * @owner: modules owning this driver. Used drivers cannot be rmmod'ed. + * Automatically set by tty_alloc_driver(). + * @driver_name: name of the driver used in /proc/tty + * @name: used for constructing /dev node name + * @name_base: used as a number base for constructing /dev node name + * @major: major /dev device number (zero for autoassignment) + * @minor_start: the first minor /dev device number + * @num: number of devices allocated + * @type: type of tty driver (%TTY_DRIVER_TYPE_) + * @subtype: subtype of tty driver (%SYSTEM_TYPE_, %PTY_TYPE_, %SERIAL_TYPE_) + * @init_termios: termios to set to each tty initially (e.g. %tty_std_termios) + * @flags: tty driver flags (%TTY_DRIVER_) + * @proc_entry: proc fs entry, used internally + * @other: driver of the linked tty; only used for the PTY driver + * @ttys: array of active &struct tty_struct, set by tty_standard_install() + * @ports: array of &struct tty_port; can be set during initialization by + * tty_port_link_device() and similar + * @termios: storage for termios at each TTY close for the next open + * @driver_state: pointer to driver's arbitrary data + * @ops: driver hooks for TTYs. Set them using tty_set_operations(). Use &struct + * tty_port helpers in them as much as possible. + * @tty_drivers: used internally to link tty_drivers together + * + * The usual handling of &struct tty_driver is to allocate it by + * tty_alloc_driver(), set up all the necessary members, and register it by + * tty_register_driver(). At last, the driver is torn down by calling + * tty_unregister_driver() followed by tty_driver_kref_put(). + * + * The fields required to be set before calling tty_register_driver() include + * @driver_name, @name, @type, @subtype, @init_termios, and @ops. + */ struct tty_driver { - int magic; /* magic number for this structure */ - struct kref kref; /* Reference management */ + struct kref kref; struct cdev **cdevs; struct module *owner; const char *driver_name; const char *name; - int name_base; /* offset of printed name */ - int major; /* major device number */ - int minor_start; /* start of minor device number */ - unsigned int num; /* number of devices allocated */ - short type; /* type of tty driver */ - short subtype; /* subtype of tty driver */ - struct ktermios init_termios; /* Initial termios */ - unsigned long flags; /* tty driver flags */ - struct proc_dir_entry *proc_entry; /* /proc fs entry */ - struct tty_driver *other; /* only used for the PTY driver */ + int name_base; + int major; + int minor_start; + unsigned int num; + short type; + short subtype; + struct ktermios init_termios; + unsigned long flags; + struct proc_dir_entry *proc_entry; + struct tty_driver *other; /* * Pointer to the tty data structures @@ -349,52 +488,53 @@ static inline void tty_set_operations(struct tty_driver *driver, driver->ops = op; } -/* tty driver magic number */ -#define TTY_DRIVER_MAGIC 0x5402 - -/* - * tty driver flags - * - * TTY_DRIVER_RESET_TERMIOS --- requests the tty layer to reset the - * termios setting when the last process has closed the device. - * Used for PTY's, in particular. - * - * TTY_DRIVER_REAL_RAW --- if set, indicates that the driver will - * guarantee never to set any special character handling - * flags if ((IGNBRK || (!BRKINT && !PARMRK)) && (IGNPAR || - * !INPCK)). That is, if there is no reason for the driver to - * send notifications of parity and break characters up to the - * line driver, it won't do so. This allows the line driver to - * optimize for this case if this flag is set. (Note that there - * is also a promise, if the above case is true, not to signal - * overruns, either.) - * - * TTY_DRIVER_DYNAMIC_DEV --- if set, the individual tty devices need - * to be registered with a call to tty_register_device() when the - * device is found in the system and unregistered with a call to - * tty_unregister_device() so the devices will be show up - * properly in sysfs. If not set, driver->num entries will be - * created by the tty core in sysfs when tty_register_driver() is - * called. This is to be used by drivers that have tty devices - * that can appear and disappear while the main tty driver is - * registered with the tty core. - * - * TTY_DRIVER_DEVPTS_MEM -- don't use the standard arrays, instead - * use dynamic memory keyed through the devpts filesystem. This - * is only applicable to the pty driver. - * - * TTY_DRIVER_HARDWARE_BREAK -- hardware handles break signals. Pass - * the requested timeout to the caller instead of using a simple - * on/off interface. - * - * TTY_DRIVER_DYNAMIC_ALLOC -- do not allocate structures which are - * needed per line for this driver as it would waste memory. - * The driver will take care. - * - * TTY_DRIVER_UNNUMBERED_NODE -- do not create numbered /dev nodes. In - * other words create /dev/ttyprintk and not /dev/ttyprintk0. - * Applicable only when a driver for a single tty device is - * being allocated. +/** + * DOC: TTY Driver Flags + * + * TTY_DRIVER_RESET_TERMIOS + * Requests the tty layer to reset the termios setting when the last + * process has closed the device. Used for PTYs, in particular. + * + * TTY_DRIVER_REAL_RAW + * Indicates that the driver will guarantee not to set any special + * character handling flags if this is set for the tty: + * + * ``(IGNBRK || (!BRKINT && !PARMRK)) && (IGNPAR || !INPCK)`` + * + * That is, if there is no reason for the driver to + * send notifications of parity and break characters up to the line + * driver, it won't do so. This allows the line driver to optimize for + * this case if this flag is set. (Note that there is also a promise, if + * the above case is true, not to signal overruns, either.) + * + * TTY_DRIVER_DYNAMIC_DEV + * The individual tty devices need to be registered with a call to + * tty_register_device() when the device is found in the system and + * unregistered with a call to tty_unregister_device() so the devices will + * be show up properly in sysfs. If not set, all &tty_driver.num entries + * will be created by the tty core in sysfs when tty_register_driver() is + * called. This is to be used by drivers that have tty devices that can + * appear and disappear while the main tty driver is registered with the + * tty core. + * + * TTY_DRIVER_DEVPTS_MEM + * Don't use the standard arrays (&tty_driver.ttys and + * &tty_driver.termios), instead use dynamic memory keyed through the + * devpts filesystem. This is only applicable to the PTY driver. + * + * TTY_DRIVER_HARDWARE_BREAK + * Hardware handles break signals. Pass the requested timeout to the + * &tty_operations.break_ctl instead of using a simple on/off interface. + * + * TTY_DRIVER_DYNAMIC_ALLOC + * Do not allocate structures which are needed per line for this driver + * (&tty_driver.ports) as it would waste memory. The driver will take + * care. This is only applicable to the PTY driver. + * + * TTY_DRIVER_UNNUMBERED_NODE + * Do not create numbered ``/dev`` nodes. For example, create + * ``/dev/ttyprintk`` and not ``/dev/ttyprintk0``. Applicable only when a + * driver for a single tty device is being allocated. */ #define TTY_DRIVER_INSTALLED 0x0001 #define TTY_DRIVER_RESET_TERMIOS 0x0002 diff --git a/include/linux/tty_flip.h b/include/linux/tty_flip.h index 9916acb5de49..483d41cbcbb7 100644 --- a/include/linux/tty_flip.h +++ b/include/linux/tty_flip.h @@ -17,7 +17,6 @@ int tty_insert_flip_string_fixed_flag(struct tty_port *port, int tty_prepare_flip_string(struct tty_port *port, unsigned char **chars, size_t size); void tty_flip_buffer_push(struct tty_port *port); -void tty_schedule_flip(struct tty_port *port); int __tty_insert_flip_char(struct tty_port *port, unsigned char ch, char flag); static inline int tty_insert_flip_char(struct tty_port *port, diff --git a/include/linux/tty_ldisc.h b/include/linux/tty_ldisc.h index b85d84fb5f49..dcb61ec11424 100644 --- a/include/linux/tty_ldisc.h +++ b/include/linux/tty_ldisc.h @@ -4,127 +4,6 @@ struct tty_struct; -/* - * This structure defines the interface between the tty line discipline - * implementation and the tty routines. The following routines can be - * defined; unless noted otherwise, they are optional, and can be - * filled in with a null pointer. - * - * int (*open)(struct tty_struct *); - * - * This function is called when the line discipline is associated - * with the tty. The line discipline can use this as an - * opportunity to initialize any state needed by the ldisc routines. - * - * void (*close)(struct tty_struct *); - * - * This function is called when the line discipline is being - * shutdown, either because the tty is being closed or because - * the tty is being changed to use a new line discipline - * - * void (*flush_buffer)(struct tty_struct *tty); - * - * This function instructs the line discipline to clear its - * buffers of any input characters it may have queued to be - * delivered to the user mode process. - * - * ssize_t (*read)(struct tty_struct * tty, struct file * file, - * unsigned char * buf, size_t nr); - * - * This function is called when the user requests to read from - * the tty. The line discipline will return whatever characters - * it has buffered up for the user. If this function is not - * defined, the user will receive an EIO error. - * - * ssize_t (*write)(struct tty_struct * tty, struct file * file, - * const unsigned char * buf, size_t nr); - * - * This function is called when the user requests to write to the - * tty. The line discipline will deliver the characters to the - * low-level tty device for transmission, optionally performing - * some processing on the characters first. If this function is - * not defined, the user will receive an EIO error. - * - * int (*ioctl)(struct tty_struct * tty, struct file * file, - * unsigned int cmd, unsigned long arg); - * - * This function is called when the user requests an ioctl which - * is not handled by the tty layer or the low-level tty driver. - * It is intended for ioctls which affect line discpline - * operation. Note that the search order for ioctls is (1) tty - * layer, (2) tty low-level driver, (3) line discpline. So a - * low-level driver can "grab" an ioctl request before the line - * discpline has a chance to see it. - * - * int (*compat_ioctl)(struct tty_struct * tty, struct file * file, - * unsigned int cmd, unsigned long arg); - * - * Process ioctl calls from 32-bit process on 64-bit system - * - * NOTE: only ioctls that are neither "pointer to compatible - * structure" nor tty-generic. Something private that takes - * an integer or a pointer to wordsize-sensitive structure - * belongs here, but most of ldiscs will happily leave - * it NULL. - * - * void (*set_termios)(struct tty_struct *tty, struct ktermios * old); - * - * This function notifies the line discpline that a change has - * been made to the termios structure. - * - * int (*poll)(struct tty_struct * tty, struct file * file, - * poll_table *wait); - * - * This function is called when a user attempts to select/poll on a - * tty device. It is solely the responsibility of the line - * discipline to handle poll requests. - * - * void (*receive_buf)(struct tty_struct *, const unsigned char *cp, - * char *fp, int count); - * - * This function is called by the low-level tty driver to send - * characters received by the hardware to the line discpline for - * processing. <cp> is a pointer to the buffer of input - * character received by the device. <fp> is a pointer to a - * pointer of flag bytes which indicate whether a character was - * received with a parity error, etc. <fp> may be NULL to indicate - * all data received is TTY_NORMAL. - * - * void (*write_wakeup)(struct tty_struct *); - * - * This function is called by the low-level tty driver to signal - * that line discpline should try to send more characters to the - * low-level driver for transmission. If the line discpline does - * not have any more data to send, it can just return. If the line - * discipline does have some data to send, please arise a tasklet - * or workqueue to do the real data transfer. Do not send data in - * this hook, it may leads to a deadlock. - * - * int (*hangup)(struct tty_struct *) - * - * Called on a hangup. Tells the discipline that it should - * cease I/O to the tty driver. Can sleep. The driver should - * seek to perform this action quickly but should wait until - * any pending driver I/O is completed. - * - * void (*dcd_change)(struct tty_struct *tty, unsigned int status) - * - * Tells the discipline that the DCD pin has changed its status. - * Used exclusively by the N_PPS (Pulse-Per-Second) line discipline. - * - * int (*receive_buf2)(struct tty_struct *, const unsigned char *cp, - * char *fp, int count); - * - * This function is called by the low-level tty driver to send - * characters received by the hardware to the line discpline for - * processing. <cp> is a pointer to the buffer of input - * character received by the device. <fp> is a pointer to a - * pointer of flag bytes which indicate whether a character was - * received with a parity error, etc. <fp> may be NULL to indicate - * all data received is TTY_NORMAL. - * If assigned, prefer this function for automatic flow control. - */ - #include <linux/fs.h> #include <linux/wait.h> #include <linux/atomic.h> @@ -176,7 +55,159 @@ int ldsem_down_write_nested(struct ld_semaphore *sem, int subclass, ldsem_down_write(sem, timeout) #endif - +/** + * struct tty_ldisc_ops - ldisc operations + * + * @name: name of this ldisc rendered in /proc/tty/ldiscs + * @num: ``N_*`` number (%N_TTY, %N_HDLC, ...) reserved to this ldisc + * + * @open: [TTY] ``int ()(struct tty_struct *tty)`` + * + * This function is called when the line discipline is associated with the + * @tty. No other call into the line discipline for this tty will occur + * until it completes successfully. It should initialize any state needed + * by the ldisc, and set @tty->receive_room to the maximum amount of data + * the line discipline is willing to accept from the driver with a single + * call to @receive_buf(). Returning an error will prevent the ldisc from + * being attached. + * + * Can sleep. + * + * @close: [TTY] ``void ()(struct tty_struct *tty)`` + * + * This function is called when the line discipline is being shutdown, + * either because the @tty is being closed or because the @tty is being + * changed to use a new line discipline. At the point of execution no + * further users will enter the ldisc code for this tty. + * + * Can sleep. + * + * @flush_buffer: [TTY] ``void ()(struct tty_struct *tty)`` + * + * This function instructs the line discipline to clear its buffers of any + * input characters it may have queued to be delivered to the user mode + * process. It may be called at any point between open and close. + * + * @read: [TTY] ``ssize_t ()(struct tty_struct *tty, struct file *file, + * unsigned char *buf, size_t nr)`` + * + * This function is called when the user requests to read from the @tty. + * The line discipline will return whatever characters it has buffered up + * for the user. If this function is not defined, the user will receive + * an %EIO error. Multiple read calls may occur in parallel and the ldisc + * must deal with serialization issues. + * + * Can sleep. + * + * @write: [TTY] ``ssize_t ()(struct tty_struct *tty, struct file *file, + * const unsigned char *buf, size_t nr)`` + * + * This function is called when the user requests to write to the @tty. + * The line discipline will deliver the characters to the low-level tty + * device for transmission, optionally performing some processing on the + * characters first. If this function is not defined, the user will + * receive an %EIO error. + * + * Can sleep. + * + * @ioctl: [TTY] ``int ()(struct tty_struct *tty, unsigned int cmd, + * unsigned long arg)`` + * + * This function is called when the user requests an ioctl which is not + * handled by the tty layer or the low-level tty driver. It is intended + * for ioctls which affect line discpline operation. Note that the search + * order for ioctls is (1) tty layer, (2) tty low-level driver, (3) line + * discpline. So a low-level driver can "grab" an ioctl request before + * the line discpline has a chance to see it. + * + * @compat_ioctl: [TTY] ``int ()(struct tty_struct *tty, unsigned int cmd, + * unsigned long arg)`` + * + * Process ioctl calls from 32-bit process on 64-bit system. + * + * Note that only ioctls that are neither "pointer to compatible + * structure" nor tty-generic. Something private that takes an integer or + * a pointer to wordsize-sensitive structure belongs here, but most of + * ldiscs will happily leave it %NULL. + * + * @set_termios: [TTY] ``void ()(struct tty_struct *tty, const struct ktermios *old)`` + * + * This function notifies the line discpline that a change has been made + * to the termios structure. + * + * @poll: [TTY] ``int ()(struct tty_struct *tty, struct file *file, + * struct poll_table_struct *wait)`` + * + * This function is called when a user attempts to select/poll on a @tty + * device. It is solely the responsibility of the line discipline to + * handle poll requests. + * + * @hangup: [TTY] ``void ()(struct tty_struct *tty)`` + * + * Called on a hangup. Tells the discipline that it should cease I/O to + * the tty driver. The driver should seek to perform this action quickly + * but should wait until any pending driver I/O is completed. No further + * calls into the ldisc code will occur. + * + * Can sleep. + * + * @receive_buf: [DRV] ``void ()(struct tty_struct *tty, + * const unsigned char *cp, const char *fp, int count)`` + * + * This function is called by the low-level tty driver to send characters + * received by the hardware to the line discpline for processing. @cp is + * a pointer to the buffer of input character received by the device. @fp + * is a pointer to an array of flag bytes which indicate whether a + * character was received with a parity error, etc. @fp may be %NULL to + * indicate all data received is %TTY_NORMAL. + * + * @write_wakeup: [DRV] ``void ()(struct tty_struct *tty)`` + * + * This function is called by the low-level tty driver to signal that line + * discpline should try to send more characters to the low-level driver + * for transmission. If the line discpline does not have any more data to + * send, it can just return. If the line discipline does have some data to + * send, please arise a tasklet or workqueue to do the real data transfer. + * Do not send data in this hook, it may lead to a deadlock. + * + * @dcd_change: [DRV] ``void ()(struct tty_struct *tty, unsigned int status)`` + * + * Tells the discipline that the DCD pin has changed its status. Used + * exclusively by the %N_PPS (Pulse-Per-Second) line discipline. + * + * @receive_buf2: [DRV] ``int ()(struct tty_struct *tty, + * const unsigned char *cp, const char *fp, int count)`` + * + * This function is called by the low-level tty driver to send characters + * received by the hardware to the line discpline for processing. @cp is a + * pointer to the buffer of input character received by the device. @fp + * is a pointer to an array of flag bytes which indicate whether a + * character was received with a parity error, etc. @fp may be %NULL to + * indicate all data received is %TTY_NORMAL. If assigned, prefer this + * function for automatic flow control. + * + * @lookahead_buf: [DRV] ``void ()(struct tty_struct *tty, + * const unsigned char *cp, const char *fp, int count)`` + * + * This function is called by the low-level tty driver for characters + * not eaten by ->receive_buf() or ->receive_buf2(). It is useful for + * processing high-priority characters such as software flow-control + * characters that could otherwise get stuck into the intermediate + * buffer until tty has room to receive them. Ldisc must be able to + * handle later a ->receive_buf() or ->receive_buf2() call for the + * same characters (e.g. by skipping the actions for high-priority + * characters already handled by ->lookahead_buf()). + * + * @owner: module containting this ldisc (for reference counting) + * + * This structure defines the interface between the tty line discipline + * implementation and the tty routines. The above routines can be defined. + * Unless noted otherwise, they are optional, and can be filled in with a %NULL + * pointer. + * + * Hooks marked [TTY] are invoked from the TTY core, the [DRV] ones from the + * tty_driver side. + */ struct tty_ldisc_ops { char *name; int num; @@ -184,32 +215,34 @@ struct tty_ldisc_ops { /* * The following routines are called from above. */ - int (*open)(struct tty_struct *); - void (*close)(struct tty_struct *); + int (*open)(struct tty_struct *tty); + void (*close)(struct tty_struct *tty); void (*flush_buffer)(struct tty_struct *tty); ssize_t (*read)(struct tty_struct *tty, struct file *file, unsigned char *buf, size_t nr, void **cookie, unsigned long offset); ssize_t (*write)(struct tty_struct *tty, struct file *file, const unsigned char *buf, size_t nr); - int (*ioctl)(struct tty_struct *tty, struct file *file, - unsigned int cmd, unsigned long arg); - int (*compat_ioctl)(struct tty_struct *tty, struct file *file, - unsigned int cmd, unsigned long arg); - void (*set_termios)(struct tty_struct *tty, struct ktermios *old); - __poll_t (*poll)(struct tty_struct *, struct file *, - struct poll_table_struct *); + int (*ioctl)(struct tty_struct *tty, unsigned int cmd, + unsigned long arg); + int (*compat_ioctl)(struct tty_struct *tty, unsigned int cmd, + unsigned long arg); + void (*set_termios)(struct tty_struct *tty, const struct ktermios *old); + __poll_t (*poll)(struct tty_struct *tty, struct file *file, + struct poll_table_struct *wait); void (*hangup)(struct tty_struct *tty); /* * The following routines are called from below. */ - void (*receive_buf)(struct tty_struct *, const unsigned char *cp, + void (*receive_buf)(struct tty_struct *tty, const unsigned char *cp, const char *fp, int count); - void (*write_wakeup)(struct tty_struct *); - void (*dcd_change)(struct tty_struct *, unsigned int); - int (*receive_buf2)(struct tty_struct *, const unsigned char *cp, + void (*write_wakeup)(struct tty_struct *tty); + void (*dcd_change)(struct tty_struct *tty, unsigned int status); + int (*receive_buf2)(struct tty_struct *tty, const unsigned char *cp, const char *fp, int count); + void (*lookahead_buf)(struct tty_struct *tty, const unsigned char *cp, + const unsigned char *fp, unsigned int count); struct module *owner; }; diff --git a/include/linux/tty_port.h b/include/linux/tty_port.h index 6e86e9e118b6..fa3c3bdaa234 100644 --- a/include/linux/tty_port.h +++ b/include/linux/tty_port.h @@ -2,76 +2,124 @@ #ifndef _LINUX_TTY_PORT_H #define _LINUX_TTY_PORT_H +#include <linux/kfifo.h> #include <linux/kref.h> #include <linux/mutex.h> #include <linux/tty_buffer.h> #include <linux/wait.h> -/* - * Port level information. Each device keeps its own port level information - * so provide a common structure for those ports wanting to use common support - * routines. - * - * The tty port has a different lifetime to the tty so must be kept apart. - * In addition be careful as tty -> port mappings are valid for the life - * of the tty object but in many cases port -> tty mappings are valid only - * until a hangup so don't use the wrong path. - */ - struct attribute_group; struct tty_driver; struct tty_port; struct tty_struct; +/** + * struct tty_port_operations -- operations on tty_port + * @carrier_raised: return 1 if the carrier is raised on @port + * @dtr_rts: raise the DTR line if @raise is nonzero, otherwise lower DTR + * @shutdown: called when the last close completes or a hangup finishes IFF the + * port was initialized. Do not use to free resources. Turn off the device + * only. Called under the port mutex to serialize against @activate and + * @shutdown. + * @activate: called under the port mutex from tty_port_open(), serialized using + * the port mutex. Supposed to turn on the device. + * + * FIXME: long term getting the tty argument *out* of this would be good + * for consoles. + * + * @destruct: called on the final put of a port. Free resources, possibly incl. + * the port itself. + */ struct tty_port_operations { - /* Return 1 if the carrier is raised */ int (*carrier_raised)(struct tty_port *port); - /* Control the DTR line */ void (*dtr_rts)(struct tty_port *port, int raise); - /* Called when the last close completes or a hangup finishes - IFF the port was initialized. Do not use to free resources. Called - under the port mutex to serialize against activate/shutdowns */ void (*shutdown)(struct tty_port *port); - /* Called under the port mutex from tty_port_open, serialized using - the port mutex */ - /* FIXME: long term getting the tty argument *out* of this would be - good for consoles */ int (*activate)(struct tty_port *port, struct tty_struct *tty); - /* Called on the final put of a port */ void (*destruct)(struct tty_port *port); }; struct tty_port_client_operations { int (*receive_buf)(struct tty_port *port, const unsigned char *, const unsigned char *, size_t); + void (*lookahead_buf)(struct tty_port *port, const unsigned char *cp, + const unsigned char *fp, unsigned int count); void (*write_wakeup)(struct tty_port *port); }; extern const struct tty_port_client_operations tty_port_default_client_ops; +/** + * struct tty_port -- port level information + * + * @buf: buffer for this port, locked internally + * @tty: back pointer to &struct tty_struct, valid only if the tty is open. Use + * tty_port_tty_get() to obtain it (and tty_kref_put() to release). + * @itty: internal back pointer to &struct tty_struct. Avoid this. It should be + * eliminated in the long term. + * @ops: tty port operations (like activate, shutdown), see &struct + * tty_port_operations + * @client_ops: tty port client operations (like receive_buf, write_wakeup). + * By default, tty_port_default_client_ops is used. + * @lock: lock protecting @tty + * @blocked_open: # of procs waiting for open in tty_port_block_til_ready() + * @count: usage count + * @open_wait: open waiters queue (waiting e.g. for a carrier) + * @delta_msr_wait: modem status change queue (waiting for MSR changes) + * @flags: user TTY flags (%ASYNC_) + * @iflags: internal flags (%TTY_PORT_) + * @console: when set, the port is a console + * @mutex: locking, for open, shutdown and other port operations + * @buf_mutex: @xmit_buf alloc lock + * @xmit_buf: optional xmit buffer used by some drivers + * @xmit_fifo: optional xmit buffer used by some drivers + * @close_delay: delay in jiffies to wait when closing the port + * @closing_wait: delay in jiffies for output to be sent before closing + * @drain_delay: set to zero if no pure time based drain is needed else set to + * size of fifo + * @kref: references counter. Reaching zero calls @ops->destruct() if non-%NULL + * or frees the port otherwise. + * @client_data: pointer to private data, for @client_ops + * + * Each device keeps its own port level information. &struct tty_port was + * introduced as a common structure for such information. As every TTY device + * shall have a backing tty_port structure, every driver can use these members. + * + * The tty port has a different lifetime to the tty so must be kept apart. + * In addition be careful as tty -> port mappings are valid for the life + * of the tty object but in many cases port -> tty mappings are valid only + * until a hangup so don't use the wrong path. + * + * Tty port shall be initialized by tty_port_init() and shut down either by + * tty_port_destroy() (refcounting not used), or tty_port_put() (refcounting). + * + * There is a lot of helpers around &struct tty_port too. To name the most + * significant ones: tty_port_open(), tty_port_close() (or + * tty_port_close_start() and tty_port_close_end() separately if need be), and + * tty_port_hangup(). These call @ops->activate() and @ops->shutdown() as + * needed. + */ struct tty_port { - struct tty_bufhead buf; /* Locked internally */ - struct tty_struct *tty; /* Back pointer */ - struct tty_struct *itty; /* internal back ptr */ - const struct tty_port_operations *ops; /* Port operations */ - const struct tty_port_client_operations *client_ops; /* Port client operations */ - spinlock_t lock; /* Lock protecting tty field */ - int blocked_open; /* Waiting to open */ - int count; /* Usage count */ - wait_queue_head_t open_wait; /* Open waiters */ - wait_queue_head_t delta_msr_wait; /* Modem status change */ - unsigned long flags; /* User TTY flags ASYNC_ */ - unsigned long iflags; /* Internal flags TTY_PORT_ */ - unsigned char console:1; /* port is a console */ - struct mutex mutex; /* Locking */ - struct mutex buf_mutex; /* Buffer alloc lock */ - unsigned char *xmit_buf; /* Optional buffer */ - unsigned int close_delay; /* Close port delay */ - unsigned int closing_wait; /* Delay for output */ - int drain_delay; /* Set to zero if no pure time - based drain is needed else - set to size of fifo */ - struct kref kref; /* Ref counter */ - void *client_data; + struct tty_bufhead buf; + struct tty_struct *tty; + struct tty_struct *itty; + const struct tty_port_operations *ops; + const struct tty_port_client_operations *client_ops; + spinlock_t lock; + int blocked_open; + int count; + wait_queue_head_t open_wait; + wait_queue_head_t delta_msr_wait; + unsigned long flags; + unsigned long iflags; + unsigned char console:1; + struct mutex mutex; + struct mutex buf_mutex; + unsigned char *xmit_buf; + DECLARE_KFIFO_PTR(xmit_fifo, unsigned char); + unsigned int close_delay; + unsigned int closing_wait; + int drain_delay; + struct kref kref; + void *client_data; }; /* tty_port::iflags bits -- use atomic bit ops */ diff --git a/include/linux/types.h b/include/linux/types.h index ac825ad90e44..ea8cf60a8a79 100644 --- a/include/linux/types.h +++ b/include/linux/types.h @@ -226,6 +226,7 @@ struct callback_head { typedef void (*rcu_callback_t)(struct rcu_head *head); typedef void (*call_rcu_func_t)(struct rcu_head *head, rcu_callback_t func); +typedef void (*swap_r_func_t)(void *a, void *b, int size, const void *priv); typedef void (*swap_func_t)(void *a, void *b, int size); typedef int (*cmp_r_func_t)(const void *a, const void *b, const void *priv); diff --git a/include/linux/u64_stats_sync.h b/include/linux/u64_stats_sync.h index 6ad4e9032d53..46040d66334a 100644 --- a/include/linux/u64_stats_sync.h +++ b/include/linux/u64_stats_sync.h @@ -8,7 +8,7 @@ * * Key points : * - * - Use a seqcount on 32-bit SMP, only disable preemption for 32-bit UP. + * - Use a seqcount on 32-bit * - The whole thing is a no-op on 64-bit architectures. * * Usage constraints: @@ -20,7 +20,8 @@ * writer and also spin forever. * * 3) Write side must use the _irqsave() variant if other writers, or a reader, - * can be invoked from an IRQ context. + * can be invoked from an IRQ context. On 64bit systems this variant does not + * disable interrupts. * * 4) If reader fetches several counters, there is no guarantee the whole values * are consistent w.r.t. each other (remember point #2: seqcounts are not @@ -29,11 +30,6 @@ * 5) Readers are allowed to sleep or be preempted/interrupted: they perform * pure reads. * - * 6) Readers must use both u64_stats_fetch_{begin,retry}_irq() if the stats - * might be updated from a hardirq or softirq context (remember point #1: - * seqcounts are not used for UP kernels). 32-bit UP stat readers could read - * corrupted 64-bit values otherwise. - * * Usage : * * Stats producer (writer) should use following template granted it already got @@ -66,7 +62,7 @@ #include <linux/seqlock.h> struct u64_stats_sync { -#if BITS_PER_LONG == 32 && (defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT)) +#if BITS_PER_LONG == 32 seqcount_t seq; #endif }; @@ -98,7 +94,22 @@ static inline void u64_stats_inc(u64_stats_t *p) local64_inc(&p->v); } -#else +static inline void u64_stats_init(struct u64_stats_sync *syncp) { } +static inline void __u64_stats_update_begin(struct u64_stats_sync *syncp) { } +static inline void __u64_stats_update_end(struct u64_stats_sync *syncp) { } +static inline unsigned long __u64_stats_irqsave(void) { return 0; } +static inline void __u64_stats_irqrestore(unsigned long flags) { } +static inline unsigned int __u64_stats_fetch_begin(const struct u64_stats_sync *syncp) +{ + return 0; +} +static inline bool __u64_stats_fetch_retry(const struct u64_stats_sync *syncp, + unsigned int start) +{ + return false; +} + +#else /* 64 bit */ typedef struct { u64 v; @@ -123,123 +134,95 @@ static inline void u64_stats_inc(u64_stats_t *p) { p->v++; } -#endif -#if BITS_PER_LONG == 32 && (defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT)) -#define u64_stats_init(syncp) seqcount_init(&(syncp)->seq) -#else static inline void u64_stats_init(struct u64_stats_sync *syncp) { + seqcount_init(&syncp->seq); } -#endif -static inline void u64_stats_update_begin(struct u64_stats_sync *syncp) +static inline void __u64_stats_update_begin(struct u64_stats_sync *syncp) { -#if BITS_PER_LONG == 32 && (defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT)) - if (IS_ENABLED(CONFIG_PREEMPT_RT)) - preempt_disable(); + preempt_disable_nested(); write_seqcount_begin(&syncp->seq); -#endif } -static inline void u64_stats_update_end(struct u64_stats_sync *syncp) +static inline void __u64_stats_update_end(struct u64_stats_sync *syncp) { -#if BITS_PER_LONG == 32 && (defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT)) write_seqcount_end(&syncp->seq); - if (IS_ENABLED(CONFIG_PREEMPT_RT)) - preempt_enable(); -#endif + preempt_enable_nested(); } -static inline unsigned long -u64_stats_update_begin_irqsave(struct u64_stats_sync *syncp) +static inline unsigned long __u64_stats_irqsave(void) { - unsigned long flags = 0; + unsigned long flags; -#if BITS_PER_LONG == 32 && (defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT)) - if (IS_ENABLED(CONFIG_PREEMPT_RT)) - preempt_disable(); - else - local_irq_save(flags); - write_seqcount_begin(&syncp->seq); -#endif + local_irq_save(flags); return flags; } -static inline void -u64_stats_update_end_irqrestore(struct u64_stats_sync *syncp, - unsigned long flags) +static inline void __u64_stats_irqrestore(unsigned long flags) { -#if BITS_PER_LONG == 32 && (defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT)) - write_seqcount_end(&syncp->seq); - if (IS_ENABLED(CONFIG_PREEMPT_RT)) - preempt_enable(); - else - local_irq_restore(flags); -#endif + local_irq_restore(flags); } static inline unsigned int __u64_stats_fetch_begin(const struct u64_stats_sync *syncp) { -#if BITS_PER_LONG == 32 && (defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT)) return read_seqcount_begin(&syncp->seq); -#else - return 0; -#endif } -static inline unsigned int u64_stats_fetch_begin(const struct u64_stats_sync *syncp) +static inline bool __u64_stats_fetch_retry(const struct u64_stats_sync *syncp, + unsigned int start) { -#if BITS_PER_LONG == 32 && (!defined(CONFIG_SMP) && !defined(CONFIG_PREEMPT_RT)) - preempt_disable(); -#endif - return __u64_stats_fetch_begin(syncp); + return read_seqcount_retry(&syncp->seq, start); } +#endif /* !64 bit */ -static inline bool __u64_stats_fetch_retry(const struct u64_stats_sync *syncp, - unsigned int start) +static inline void u64_stats_update_begin(struct u64_stats_sync *syncp) { -#if BITS_PER_LONG == 32 && (defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT)) - return read_seqcount_retry(&syncp->seq, start); -#else - return false; -#endif + __u64_stats_update_begin(syncp); +} + +static inline void u64_stats_update_end(struct u64_stats_sync *syncp) +{ + __u64_stats_update_end(syncp); +} + +static inline unsigned long u64_stats_update_begin_irqsave(struct u64_stats_sync *syncp) +{ + unsigned long flags = __u64_stats_irqsave(); + + __u64_stats_update_begin(syncp); + return flags; +} + +static inline void u64_stats_update_end_irqrestore(struct u64_stats_sync *syncp, + unsigned long flags) +{ + __u64_stats_update_end(syncp); + __u64_stats_irqrestore(flags); +} + +static inline unsigned int u64_stats_fetch_begin(const struct u64_stats_sync *syncp) +{ + return __u64_stats_fetch_begin(syncp); } static inline bool u64_stats_fetch_retry(const struct u64_stats_sync *syncp, unsigned int start) { -#if BITS_PER_LONG == 32 && (!defined(CONFIG_SMP) && !defined(CONFIG_PREEMPT_RT)) - preempt_enable(); -#endif return __u64_stats_fetch_retry(syncp, start); } -/* - * In case irq handlers can update u64 counters, readers can use following helpers - * - SMP 32bit arches use seqcount protection, irq safe. - * - UP 32bit must disable irqs. - * - 64bit have no problem atomically reading u64 values, irq safe. - */ +/* Obsolete interfaces */ static inline unsigned int u64_stats_fetch_begin_irq(const struct u64_stats_sync *syncp) { -#if BITS_PER_LONG == 32 && defined(CONFIG_PREEMPT_RT) - preempt_disable(); -#elif BITS_PER_LONG == 32 && !defined(CONFIG_SMP) - local_irq_disable(); -#endif - return __u64_stats_fetch_begin(syncp); + return u64_stats_fetch_begin(syncp); } static inline bool u64_stats_fetch_retry_irq(const struct u64_stats_sync *syncp, unsigned int start) { -#if BITS_PER_LONG == 32 && defined(CONFIG_PREEMPT_RT) - preempt_enable(); -#elif BITS_PER_LONG == 32 && !defined(CONFIG_SMP) - local_irq_enable(); -#endif - return __u64_stats_fetch_retry(syncp, start); + return u64_stats_fetch_retry(syncp, start); } #endif /* _LINUX_U64_STATS_SYNC_H */ diff --git a/include/linux/u64_stats_sync_api.h b/include/linux/u64_stats_sync_api.h new file mode 100644 index 000000000000..c72ca63da44b --- /dev/null +++ b/include/linux/u64_stats_sync_api.h @@ -0,0 +1 @@ +#include <linux/u64_stats_sync.h> diff --git a/include/linux/uacce.h b/include/linux/uacce.h index 48e319f40275..9ce88c28b0a8 100644 --- a/include/linux/uacce.h +++ b/include/linux/uacce.h @@ -70,6 +70,7 @@ enum uacce_q_state { * @wait: wait queue head * @list: index into uacce queues list * @qfrs: pointer of qfr regions + * @mutex: protects queue state * @state: queue state machine * @pasid: pasid associated to the mm * @handle: iommu_sva handle returned by iommu_sva_bind_device() @@ -80,6 +81,7 @@ struct uacce_queue { wait_queue_head_t wait; struct list_head list; struct uacce_qfile_region *qfrs[UACCE_MAX_REGION]; + struct mutex mutex; enum uacce_q_state state; u32 pasid; struct iommu_sva *handle; @@ -97,9 +99,9 @@ struct uacce_queue { * @dev_id: id of the uacce device * @cdev: cdev of the uacce * @dev: dev of the uacce + * @mutex: protects uacce operation * @priv: private pointer of the uacce * @queues: list of queues - * @queues_lock: lock for queues list * @inode: core vfs */ struct uacce_device { @@ -113,9 +115,9 @@ struct uacce_device { u32 dev_id; struct cdev *cdev; struct device dev; + struct mutex mutex; void *priv; struct list_head queues; - struct mutex queues_lock; struct inode *inode; }; diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index ac0394087f7d..afb18f198843 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -10,46 +10,6 @@ #include <asm/uaccess.h> -#ifdef CONFIG_SET_FS -/* - * Force the uaccess routines to be wired up for actual userspace access, - * overriding any possible set_fs(KERNEL_DS) still lingering around. Undone - * using force_uaccess_end below. - */ -static inline mm_segment_t force_uaccess_begin(void) -{ - mm_segment_t fs = get_fs(); - - set_fs(USER_DS); - return fs; -} - -static inline void force_uaccess_end(mm_segment_t oldfs) -{ - set_fs(oldfs); -} -#else /* CONFIG_SET_FS */ -typedef struct { - /* empty dummy */ -} mm_segment_t; - -#ifndef TASK_SIZE_MAX -#define TASK_SIZE_MAX TASK_SIZE -#endif - -#define uaccess_kernel() (false) -#define user_addr_max() (TASK_SIZE_MAX) - -static inline mm_segment_t force_uaccess_begin(void) -{ - return (mm_segment_t) { }; -} - -static inline void force_uaccess_end(mm_segment_t oldfs) -{ -} -#endif /* CONFIG_SET_FS */ - /* * Architectures should provide two primitives (raw_copy_{to,from}_user()) * and get rid of their private instances of copy_{to,from}_user() and @@ -98,20 +58,28 @@ static inline void force_uaccess_end(mm_segment_t oldfs) static __always_inline __must_check unsigned long __copy_from_user_inatomic(void *to, const void __user *from, unsigned long n) { - instrument_copy_from_user(to, from, n); + unsigned long res; + + instrument_copy_from_user_before(to, from, n); check_object_size(to, n, false); - return raw_copy_from_user(to, from, n); + res = raw_copy_from_user(to, from, n); + instrument_copy_from_user_after(to, from, n, res); + return res; } static __always_inline __must_check unsigned long __copy_from_user(void *to, const void __user *from, unsigned long n) { + unsigned long res; + might_fault(); + instrument_copy_from_user_before(to, from, n); if (should_fail_usercopy()) return n; - instrument_copy_from_user(to, from, n); check_object_size(to, n, false); - return raw_copy_from_user(to, from, n); + res = raw_copy_from_user(to, from, n); + instrument_copy_from_user_after(to, from, n, res); + return res; } /** @@ -155,8 +123,9 @@ _copy_from_user(void *to, const void __user *from, unsigned long n) unsigned long res = n; might_fault(); if (!should_fail_usercopy() && likely(access_ok(from, n))) { - instrument_copy_from_user(to, from, n); + instrument_copy_from_user_before(to, from, n); res = raw_copy_from_user(to, from, n); + instrument_copy_from_user_after(to, from, n, res); } if (unlikely(res)) memset(to + (n - res), 0, res); @@ -188,7 +157,7 @@ _copy_to_user(void __user *, const void *, unsigned long); static __always_inline unsigned long __must_check copy_from_user(void *to, const void __user *from, unsigned long n) { - if (likely(check_copy_size(to, n, false))) + if (check_copy_size(to, n, false)) n = _copy_from_user(to, from, n); return n; } @@ -196,7 +165,7 @@ copy_from_user(void *to, const void __user *from, unsigned long n) static __always_inline unsigned long __must_check copy_to_user(void __user *to, const void *from, unsigned long n) { - if (likely(check_copy_size(from, n, true))) + if (check_copy_size(from, n, true)) n = _copy_to_user(to, from, n); return n; } @@ -271,6 +240,28 @@ static inline bool pagefault_disabled(void) */ #define faulthandler_disabled() (pagefault_disabled() || in_atomic()) +#ifndef CONFIG_ARCH_HAS_SUBPAGE_FAULTS + +/** + * probe_subpage_writeable: probe the user range for write faults at sub-page + * granularity (e.g. arm64 MTE) + * @uaddr: start of address range + * @size: size of address range + * + * Returns 0 on success, the number of bytes not probed on fault. + * + * It is expected that the caller checked for the write permission of each + * page in the range either by put_user() or GUP. The architecture port can + * implement a more efficient get_user() probing if the same sub-page faults + * are triggered by either a read or a write. + */ +static inline size_t probe_subpage_writeable(char __user *uaddr, size_t size) +{ + return 0; +} + +#endif /* CONFIG_ARCH_HAS_SUBPAGE_FAULTS */ + #ifndef ARCH_HAS_NOCACHE_UACCESS static inline __must_check unsigned long @@ -368,6 +359,25 @@ long strncpy_from_user_nofault(char *dst, const void __user *unsafe_addr, long count); long strnlen_user_nofault(const void __user *unsafe_addr, long count); +#ifndef __get_kernel_nofault +#define __get_kernel_nofault(dst, src, type, label) \ +do { \ + type __user *p = (type __force __user *)(src); \ + type data; \ + if (__get_user(data, p)) \ + goto label; \ + *(type *)dst = data; \ +} while (0) + +#define __put_kernel_nofault(dst, src, type, label) \ +do { \ + type __user *p = (type __force __user *)(dst); \ + type data = *(type *)src; \ + if (__put_user(data, p)) \ + goto label; \ +} while (0) +#endif + /** * get_kernel_nofault(): safely attempt to read from a location * @val: read into this variable @@ -401,8 +411,6 @@ static inline void user_access_restore(unsigned long flags) { } #endif #ifdef CONFIG_HARDENED_USERCOPY -void usercopy_warn(const char *name, const char *detail, bool to_user, - unsigned long offset, unsigned long len); void __noreturn usercopy_abort(const char *name, const char *detail, bool to_user, unsigned long offset, unsigned long len); diff --git a/include/linux/ucb1400.h b/include/linux/ucb1400.h index 0968ef458447..2516082cd3a9 100644 --- a/include/linux/ucb1400.h +++ b/include/linux/ucb1400.h @@ -23,7 +23,7 @@ #include <sound/ac97_codec.h> #include <linux/mutex.h> #include <linux/platform_device.h> -#include <linux/gpio.h> +#include <linux/gpio/driver.h> /* * UCB1400 AC-link registers @@ -84,8 +84,6 @@ struct ucb1400_gpio { struct gpio_chip gc; struct snd_ac97 *ac97; int gpio_offset; - int (*gpio_setup)(struct device *dev, int ngpio); - int (*gpio_teardown)(struct device *dev, int ngpio); }; struct ucb1400_ts { diff --git a/include/linux/udp.h b/include/linux/udp.h index ae66dadd8543..e96da4157d04 100644 --- a/include/linux/udp.h +++ b/include/linux/udp.h @@ -23,11 +23,6 @@ static inline struct udphdr *udp_hdr(const struct sk_buff *skb) return (struct udphdr *)skb_transport_header(skb); } -static inline struct udphdr *inner_udp_hdr(const struct sk_buff *skb) -{ - return (struct udphdr *)skb_inner_transport_header(skb); -} - #define UDP_HTABLE_SIZE_MIN (CONFIG_BASE_SMALL ? 128 : 256) static inline u32 udp_hashfn(const struct net *net, u32 num, u32 mask) @@ -75,6 +70,7 @@ struct udp_sock { * For encapsulation sockets. */ int (*encap_rcv)(struct sock *sk, struct sk_buff *skb); + void (*encap_err_rcv)(struct sock *sk, struct sk_buff *skb, unsigned int udp_offset); int (*encap_err_lookup)(struct sock *sk, struct sk_buff *skb); void (*encap_destroy)(struct sock *sk); diff --git a/include/linux/uio.h b/include/linux/uio.h index 6350354f97e9..2e3134b14ffd 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -7,6 +7,7 @@ #include <linux/kernel.h> #include <linux/thread_info.h> +#include <linux/mm_types.h> #include <uapi/linux/uio.h> struct page; @@ -25,6 +26,7 @@ enum iter_type { ITER_PIPE, ITER_XARRAY, ITER_DISCARD, + ITER_UBUF, }; struct iov_iter_state { @@ -37,7 +39,11 @@ struct iov_iter { u8 iter_type; bool nofault; bool data_source; - size_t iov_offset; + bool user_backed; + union { + size_t iov_offset; + int last_offset; + }; size_t count; union { const struct iovec *iov; @@ -45,6 +51,7 @@ struct iov_iter { const struct bio_vec *bvec; struct xarray *xarray; struct pipe_inode_info *pipe; + void __user *ubuf; }; union { unsigned long nr_segs; @@ -69,6 +76,11 @@ static inline void iov_iter_save_state(struct iov_iter *iter, state->nr_segs = iter->nr_segs; } +static inline bool iter_is_ubuf(const struct iov_iter *i) +{ + return iov_iter_type(i) == ITER_UBUF; +} + static inline bool iter_is_iovec(const struct iov_iter *i) { return iov_iter_type(i) == ITER_IOVEC; @@ -104,6 +116,11 @@ static inline unsigned char iov_iter_rw(const struct iov_iter *i) return i->data_source ? WRITE : READ; } +static inline bool user_backed_iter(const struct iov_iter *i) +{ + return i->user_backed; +} + /* * Total number of bytes covered by an iovec. * @@ -146,22 +163,26 @@ size_t _copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i); size_t _copy_from_iter(void *addr, size_t bytes, struct iov_iter *i); size_t _copy_from_iter_nocache(void *addr, size_t bytes, struct iov_iter *i); +static inline size_t copy_folio_to_iter(struct folio *folio, size_t offset, + size_t bytes, struct iov_iter *i) +{ + return copy_page_to_iter(&folio->page, offset, bytes, i); +} + static __always_inline __must_check size_t copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i) { - if (unlikely(!check_copy_size(addr, bytes, true))) - return 0; - else + if (check_copy_size(addr, bytes, true)) return _copy_to_iter(addr, bytes, i); + return 0; } static __always_inline __must_check size_t copy_from_iter(void *addr, size_t bytes, struct iov_iter *i) { - if (unlikely(!check_copy_size(addr, bytes, false))) - return 0; - else + if (check_copy_size(addr, bytes, false)) return _copy_from_iter(addr, bytes, i); + return 0; } static __always_inline __must_check @@ -177,10 +198,9 @@ bool copy_from_iter_full(void *addr, size_t bytes, struct iov_iter *i) static __always_inline __must_check size_t copy_from_iter_nocache(void *addr, size_t bytes, struct iov_iter *i) { - if (unlikely(!check_copy_size(addr, bytes, false))) - return 0; - else + if (check_copy_size(addr, bytes, false)) return _copy_from_iter_nocache(addr, bytes, i); + return 0; } static __always_inline __must_check @@ -196,7 +216,7 @@ bool copy_from_iter_full_nocache(void *addr, size_t bytes, struct iov_iter *i) #ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE /* * Note, users like pmem that depend on the stricter semantics of - * copy_from_iter_flushcache() than copy_from_iter_nocache() must check for + * _copy_from_iter_flushcache() than _copy_from_iter_nocache() must check for * IS_ENABLED(CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE) before assuming that the * destination is flushed from the cache on return. */ @@ -211,25 +231,9 @@ size_t _copy_mc_to_iter(const void *addr, size_t bytes, struct iov_iter *i); #define _copy_mc_to_iter _copy_to_iter #endif -static __always_inline __must_check -size_t copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i) -{ - if (unlikely(!check_copy_size(addr, bytes, false))) - return 0; - else - return _copy_from_iter_flushcache(addr, bytes, i); -} - -static __always_inline __must_check -size_t copy_mc_to_iter(void *addr, size_t bytes, struct iov_iter *i) -{ - if (unlikely(!check_copy_size(addr, bytes, true))) - return 0; - else - return _copy_mc_to_iter(addr, bytes, i); -} - size_t iov_iter_zero(size_t bytes, struct iov_iter *); +bool iov_iter_is_aligned(const struct iov_iter *i, unsigned addr_mask, + unsigned len_mask); unsigned long iov_iter_alignment(const struct iov_iter *i); unsigned long iov_iter_gap_alignment(const struct iov_iter *i); void iov_iter_init(struct iov_iter *i, unsigned int direction, const struct iovec *iov, @@ -243,9 +247,9 @@ void iov_iter_pipe(struct iov_iter *i, unsigned int direction, struct pipe_inode void iov_iter_discard(struct iov_iter *i, unsigned int direction, size_t count); void iov_iter_xarray(struct iov_iter *i, unsigned int direction, struct xarray *xarray, loff_t start, size_t count); -ssize_t iov_iter_get_pages(struct iov_iter *i, struct page **pages, +ssize_t iov_iter_get_pages2(struct iov_iter *i, struct page **pages, size_t maxsize, unsigned maxpages, size_t *start); -ssize_t iov_iter_get_pages_alloc(struct iov_iter *i, struct page ***pages, +ssize_t iov_iter_get_pages_alloc2(struct iov_iter *i, struct page ***pages, size_t maxsize, size_t *start); int iov_iter_npages(const struct iov_iter *i, int maxpages); void iov_iter_restore(struct iov_iter *i, struct iov_iter_state *state); @@ -284,6 +288,23 @@ static inline void iov_iter_reexpand(struct iov_iter *i, size_t count) i->count = count; } +static inline int +iov_iter_npages_cap(struct iov_iter *i, int maxpages, size_t max_bytes) +{ + size_t shorted = 0; + int npages; + + if (iov_iter_count(i) > max_bytes) { + shorted = iov_iter_count(i) - max_bytes; + iov_iter_truncate(i, max_bytes); + } + npages = iov_iter_npages(i, maxpages); + if (shorted) + iov_iter_reexpand(i, iov_iter_count(i) + shorted); + + return npages; +} + struct csum_state { __wsum csum; size_t off; @@ -317,4 +338,17 @@ ssize_t __import_iovec(int type, const struct iovec __user *uvec, int import_single_range(int type, void __user *buf, size_t len, struct iovec *iov, struct iov_iter *i); +static inline void iov_iter_ubuf(struct iov_iter *i, unsigned int direction, + void __user *buf, size_t count) +{ + WARN_ON(direction & ~(READ | WRITE)); + *i = (struct iov_iter) { + .iter_type = ITER_UBUF, + .user_backed = true, + .data_source = direction, + .ubuf = buf, + .count = count + }; +} + #endif diff --git a/include/linux/umh.h b/include/linux/umh.h index 244aff638220..5d1f6129b847 100644 --- a/include/linux/umh.h +++ b/include/linux/umh.h @@ -11,10 +11,11 @@ struct cred; struct file; -#define UMH_NO_WAIT 0 /* don't wait at all */ -#define UMH_WAIT_EXEC 1 /* wait for the exec, but not the process */ -#define UMH_WAIT_PROC 2 /* wait for the process to complete */ -#define UMH_KILLABLE 4 /* wait for EXEC/PROC killable */ +#define UMH_NO_WAIT 0x00 /* don't wait at all */ +#define UMH_WAIT_EXEC 0x01 /* wait for the exec, but not the process */ +#define UMH_WAIT_PROC 0x02 /* wait for the process to complete */ +#define UMH_KILLABLE 0x04 /* wait for EXEC/PROC killable */ +#define UMH_FREEZABLE 0x08 /* wait for EXEC/PROC freezable */ struct subprocess_info { struct work_struct work; diff --git a/include/linux/unaligned/packed_struct.h b/include/linux/unaligned/packed_struct.h index c0d817de4df2..f4c8eaf4d012 100644 --- a/include/linux/unaligned/packed_struct.h +++ b/include/linux/unaligned/packed_struct.h @@ -1,7 +1,7 @@ #ifndef _LINUX_UNALIGNED_PACKED_STRUCT_H #define _LINUX_UNALIGNED_PACKED_STRUCT_H -#include <linux/kernel.h> +#include <linux/types.h> struct __una_u16 { u16 x; } __packed; struct __una_u32 { u32 x; } __packed; diff --git a/include/linux/unicode.h b/include/linux/unicode.h index 74484d44c755..4d39e6e11a95 100644 --- a/include/linux/unicode.h +++ b/include/linux/unicode.h @@ -5,9 +5,52 @@ #include <linux/init.h> #include <linux/dcache.h> +struct utf8data; +struct utf8data_table; + +#define UNICODE_MAJ_SHIFT 16 +#define UNICODE_MIN_SHIFT 8 + +#define UNICODE_AGE(MAJ, MIN, REV) \ + (((unsigned int)(MAJ) << UNICODE_MAJ_SHIFT) | \ + ((unsigned int)(MIN) << UNICODE_MIN_SHIFT) | \ + ((unsigned int)(REV))) + +static inline u8 unicode_major(unsigned int age) +{ + return (age >> UNICODE_MAJ_SHIFT) & 0xff; +} + +static inline u8 unicode_minor(unsigned int age) +{ + return (age >> UNICODE_MIN_SHIFT) & 0xff; +} + +static inline u8 unicode_rev(unsigned int age) +{ + return age & 0xff; +} + +/* + * Two normalization forms are supported: + * 1) NFDI + * - Apply unicode normalization form NFD. + * - Remove any Default_Ignorable_Code_Point. + * 2) NFDICF + * - Apply unicode normalization form NFD. + * - Remove any Default_Ignorable_Code_Point. + * - Apply a full casefold (C + F). + */ +enum utf8_normalization { + UTF8_NFDI = 0, + UTF8_NFDICF, + UTF8_NMAX, +}; + struct unicode_map { - const char *charset; - int version; + unsigned int version; + const struct utf8data *ntab[UTF8_NMAX]; + const struct utf8data_table *tables; }; int utf8_validate(const struct unicode_map *um, const struct qstr *str); @@ -30,7 +73,7 @@ int utf8_casefold(const struct unicode_map *um, const struct qstr *str, int utf8_casefold_hash(const struct unicode_map *um, const void *salt, struct qstr *str); -struct unicode_map *utf8_load(const char *version); +struct unicode_map *utf8_load(unsigned int version); void utf8_unload(struct unicode_map *um); #endif /* _LINUX_UNICODE_H */ diff --git a/include/linux/units.h b/include/linux/units.h index 681fc652e3d7..2793a41e73a2 100644 --- a/include/linux/units.h +++ b/include/linux/units.h @@ -20,6 +20,9 @@ #define PICO 1000000000000ULL #define FEMTO 1000000000000000ULL +#define NANOHZ_PER_HZ 1000000000UL +#define MICROHZ_PER_HZ 1000000UL +#define MILLIHZ_PER_HZ 1000UL #define HZ_PER_KHZ 1000UL #define KHZ_PER_MHZ 1000UL #define HZ_PER_MHZ 1000000UL diff --git a/include/linux/usb.h b/include/linux/usb.h index 7ccaa76a9a96..9ff1ad4dfad1 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -575,6 +575,7 @@ struct usb3_lpm_parameters { * @devaddr: device address, XHCI: assigned by HW, others: same as devnum * @can_submit: URBs may be submitted * @persist_enabled: USB_PERSIST enabled for this device + * @reset_in_progress: the device is being reset * @have_langid: whether string_langid is valid * @authorized: policy has said we can use it; * (user space) policy determines if we authorize this device to be @@ -584,6 +585,7 @@ struct usb3_lpm_parameters { * @authenticated: Crypto authentication passed * @wusb: device is Wireless USB * @lpm_capable: device supports LPM + * @lpm_devinit_allow: Allow USB3 device initiated LPM, exit latency is in range * @usb2_hw_lpm_capable: device can perform USB2 hardware LPM * @usb2_hw_lpm_besl_capable: device can perform USB2 hardware BESL LPM * @usb2_hw_lpm_enabled: USB2 hardware LPM is enabled @@ -661,11 +663,13 @@ struct usb_device { unsigned can_submit:1; unsigned persist_enabled:1; + unsigned reset_in_progress:1; unsigned have_langid:1; unsigned authorized:1; unsigned authenticated:1; unsigned wusb:1; unsigned lpm_capable:1; + unsigned lpm_devinit_allow:1; unsigned usb2_hw_lpm_capable:1; unsigned usb2_hw_lpm_besl_capable:1; unsigned usb2_hw_lpm_enabled:1; @@ -875,15 +879,6 @@ extern struct usb_host_interface *usb_find_alt_setting( unsigned int iface_num, unsigned int alt_num); -#if IS_REACHABLE(CONFIG_USB) -int usb_for_each_port(void *data, int (*fn)(struct device *, void *)); -#else -static inline int usb_for_each_port(void *data, int (*fn)(struct device *, void *)) -{ - return 0; -} -#endif - /* port claiming functions */ int usb_hub_claim_port(struct usb_device *hdev, unsigned port1, struct usb_dev_state *owner); @@ -1978,21 +1973,10 @@ usb_pipe_endpoint(struct usb_device *dev, unsigned int pipe) return eps[usb_pipeendpoint(pipe)]; } -/*-------------------------------------------------------------------------*/ - -static inline __u16 -usb_maxpacket(struct usb_device *udev, int pipe, int is_out) +static inline u16 usb_maxpacket(struct usb_device *udev, int pipe) { - struct usb_host_endpoint *ep; - unsigned epnum = usb_pipeendpoint(pipe); + struct usb_host_endpoint *ep = usb_pipe_endpoint(udev, pipe); - if (is_out) { - WARN_ON(usb_pipein(pipe)); - ep = udev->ep_out[epnum]; - } else { - WARN_ON(usb_pipeout(pipe)); - ep = udev->ep_in[epnum]; - } if (!ep) return 0; @@ -2000,8 +1984,6 @@ usb_maxpacket(struct usb_device *udev, int pipe, int is_out) return usb_endpoint_maxp(&ep->desc); } -/* ----------------------------------------------------------------------- */ - /* translate USB error codes to codes user space understands */ static inline int usb_translate_errors(int error_code) { diff --git a/include/linux/usb/audio-v2.h b/include/linux/usb/audio-v2.h index 8fc2abd7aecb..ca796dc1a984 100644 --- a/include/linux/usb/audio-v2.h +++ b/include/linux/usb/audio-v2.h @@ -2,9 +2,6 @@ /* * Copyright (c) 2010 Daniel Mack <daniel@caiaq.de> * - * This software is distributed under the terms of the GNU General Public - * License ("GPL") version 2, as published by the Free Software Foundation. - * * This file holds USB constants and structures defined * by the USB Device Class Definition for Audio Devices in version 2.0. * Comments below reference relevant sections of the documents contained diff --git a/include/linux/usb/audio.h b/include/linux/usb/audio.h index 170acd500ea1..0747b24a1a7c 100644 --- a/include/linux/usb/audio.h +++ b/include/linux/usb/audio.h @@ -6,9 +6,6 @@ * Developed for Thumtronics by Grey Innovation * Ben Williamson <ben.williamson@greyinnovation.com> * - * This software is distributed under the terms of the GNU General Public - * License ("GPL") version 2, as published by the Free Software Foundation. - * * This file holds USB constants and structures defined * by the USB Device Class Definition for Audio Devices. * Comments below reference relevant sections of that document: diff --git a/include/linux/usb/c67x00.h b/include/linux/usb/c67x00.h index 2fc39e3b7281..45e0757e58f3 100644 --- a/include/linux/usb/c67x00.h +++ b/include/linux/usb/c67x00.h @@ -3,21 +3,6 @@ * usb_c67x00.h: platform definitions for the Cypress C67X00 USB chip * * Copyright (C) 2006-2008 Barco N.V. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, - * MA 02110-1301 USA. */ #ifndef _LINUX_USB_C67X00_H diff --git a/include/linux/usb/cdc-wdm.h b/include/linux/usb/cdc-wdm.h index 9f5a51f79ba5..85417f00a89a 100644 --- a/include/linux/usb/cdc-wdm.h +++ b/include/linux/usb/cdc-wdm.h @@ -3,10 +3,6 @@ * USB CDC Device Management subdriver * * Copyright (c) 2012 Bjørn Mork <bjorn@mork.no> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * version 2 as published by the Free Software Foundation. */ #ifndef __LINUX_USB_CDC_WDM_H diff --git a/include/linux/usb/cdc.h b/include/linux/usb/cdc.h index 35d784cf32a4..0af0db51bc89 100644 --- a/include/linux/usb/cdc.h +++ b/include/linux/usb/cdc.h @@ -3,10 +3,6 @@ * USB CDC common helpers * * Copyright (c) 2015 Oliver Neukum <oneukum@suse.com> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * version 2 as published by the Free Software Foundation. */ #ifndef __LINUX_USB_CDC_H #define __LINUX_USB_CDC_H diff --git a/include/linux/usb/cdc_ncm.h b/include/linux/usb/cdc_ncm.h index f7cb3ddce7fb..2d207cb4837d 100644 --- a/include/linux/usb/cdc_ncm.h +++ b/include/linux/usb/cdc_ncm.h @@ -53,8 +53,8 @@ #define USB_CDC_NCM_NDP32_LENGTH_MIN 0x20 /* Maximum NTB length */ -#define CDC_NCM_NTB_MAX_SIZE_TX 32768 /* bytes */ -#define CDC_NCM_NTB_MAX_SIZE_RX 32768 /* bytes */ +#define CDC_NCM_NTB_MAX_SIZE_TX 65536 /* bytes */ +#define CDC_NCM_NTB_MAX_SIZE_RX 65536 /* bytes */ /* Initial NTB length */ #define CDC_NCM_NTB_DEF_SIZE_TX 16384 /* bytes */ diff --git a/include/linux/usb/ch9.h b/include/linux/usb/ch9.h index 1cffa34740b0..969e7dba6358 100644 --- a/include/linux/usb/ch9.h +++ b/include/linux/usb/ch9.h @@ -33,7 +33,6 @@ #ifndef __LINUX_USB_CH9_H #define __LINUX_USB_CH9_H -#include <linux/device.h> #include <uapi/linux/usb/ch9.h> /* USB 3.2 SuperSpeed Plus phy signaling rate generation and lane count */ @@ -45,6 +44,8 @@ enum usb_ssp_rate { USB_SSP_GEN_2x2, }; +struct device; + extern const char *usb_ep_type_string(int ep_type); extern const char *usb_speed_string(enum usb_device_speed speed); extern enum usb_device_speed usb_get_maximum_speed(struct device *dev); diff --git a/include/linux/usb/chipidea.h b/include/linux/usb/chipidea.h index edf3342507f1..ee38835ed77c 100644 --- a/include/linux/usb/chipidea.h +++ b/include/linux/usb/chipidea.h @@ -62,6 +62,7 @@ struct ci_hdrc_platform_data { #define CI_HDRC_REQUIRES_ALIGNED_DMA BIT(13) #define CI_HDRC_IMX_IS_HSIC BIT(14) #define CI_HDRC_PMQOS BIT(15) +#define CI_HDRC_PHY_VBUS_CONTROL BIT(16) enum usb_dr_mode dr_mode; #define CI_HDRC_CONTROLLER_RESET_EVENT 0 #define CI_HDRC_CONTROLLER_STOPPED_EVENT 1 diff --git a/include/linux/usb/composite.h b/include/linux/usb/composite.h index 9d2762279286..43ac3fa760db 100644 --- a/include/linux/usb/composite.h +++ b/include/linux/usb/composite.h @@ -3,20 +3,6 @@ * composite.h -- framework for usb gadgets which are composite devices * * Copyright (C) 2006-2008 David Brownell - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA */ #ifndef __LINUX_USB_COMPOSITE_H diff --git a/include/linux/usb/ehci_def.h b/include/linux/usb/ehci_def.h index c892c5bc6638..fbabadd3b372 100644 --- a/include/linux/usb/ehci_def.h +++ b/include/linux/usb/ehci_def.h @@ -1,20 +1,6 @@ // SPDX-License-Identifier: GPL-2.0+ /* * Copyright (c) 2001-2002 by David Brownell - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the - * Free Software Foundation; either version 2 of the License, or (at your - * option) any later version. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY - * or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License - * for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software Foundation, - * Inc., 675 Mass Ave, Cambridge, MA 02139, USA. */ #ifndef __LINUX_USB_EHCI_DEF_H diff --git a/include/linux/usb/ehci_pdriver.h b/include/linux/usb/ehci_pdriver.h index 89fc901e778f..0f1b166f5aa0 100644 --- a/include/linux/usb/ehci_pdriver.h +++ b/include/linux/usb/ehci_pdriver.h @@ -1,20 +1,6 @@ // SPDX-License-Identifier: GPL-2.0+ /* * Copyright (C) 2012 Hauke Mehrtens <hauke@hauke-m.de> - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the - * Free Software Foundation; either version 2 of the License, or (at your - * option) any later version. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY - * or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License - * for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software Foundation, - * Inc., 675 Mass Ave, Cambridge, MA 02139, USA. */ #ifndef __USB_CORE_EHCI_PDRIVER_H diff --git a/include/linux/usb/g_hid.h b/include/linux/usb/g_hid.h index 7581e488c237..d56bfedeb079 100644 --- a/include/linux/usb/g_hid.h +++ b/include/linux/usb/g_hid.h @@ -3,20 +3,6 @@ * g_hid.h -- Header file for USB HID gadget driver * * Copyright (C) 2010 Fabien Chouteau <fabien.chouteau@barco.com> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef __LINUX_USB_G_HID_H diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h index 10fe57cf40be..dc3092cea99e 100644 --- a/include/linux/usb/gadget.h +++ b/include/linux/usb/gadget.h @@ -10,8 +10,6 @@ * * (C) Copyright 2002-2004 by David Brownell * All Rights Reserved. - * - * This software is licensed under the GNU GPL version 2. */ #ifndef __LINUX_USB_GADGET_H @@ -386,6 +384,7 @@ struct usb_gadget_ops { * @lpm_capable: If the gadget max_speed is FULL or HIGH, this flag * indicates that it supports LPM as per the LPM ECN & errata. * @irq: the interrupt number for device controller. + * @id_number: a unique ID number for ensuring that gadget names are distinct * * Gadgets have a mostly-portable "gadget driver" implementing device * functions, handling all usb configurations and interfaces. Gadget @@ -446,6 +445,7 @@ struct usb_gadget { unsigned connected:1; unsigned lpm_capable:1; int irq; + int id_number; }; #define work_to_gadget(w) (container_of((w), struct usb_gadget, work)) @@ -664,9 +664,9 @@ static inline int usb_gadget_check_config(struct usb_gadget *gadget) * @driver: Driver model state for this driver. * @udc_name: A name of UDC this driver should be bound to. If udc_name is NULL, * this driver will be bound to any available UDC. - * @pending: UDC core private data used for deferred probe of this driver. - * @match_existing_only: If udc is not found, return an error and don't add this - * gadget driver to list of pending driver + * @match_existing_only: If udc is not found, return an error and fail + * the driver registration + * @is_bound: Allow a driver to be bound to only one gadget * * Devices are disabled till a gadget driver successfully bind()s, which * means the driver will handle setup() requests needed to enumerate (and @@ -729,8 +729,8 @@ struct usb_gadget_driver { struct device_driver driver; char *udc_name; - struct list_head pending; unsigned match_existing_only:1; + bool is_bound:1; }; @@ -740,22 +740,30 @@ struct usb_gadget_driver { /* driver modules register and unregister, as usual. * these calls must be made in a context that can sleep. * - * these will usually be implemented directly by the hardware-dependent - * usb bus interface driver, which will only support a single driver. + * A gadget driver can be bound to only one gadget at a time. */ /** - * usb_gadget_probe_driver - probe a gadget driver + * usb_gadget_register_driver_owner - register a gadget driver * @driver: the driver being registered + * @owner: the driver module + * @mod_name: the driver module's build name * Context: can sleep * * Call this in your gadget driver's module initialization function, - * to tell the underlying usb controller driver about your driver. + * to tell the underlying UDC controller driver about your driver. * The @bind() function will be called to bind it to a gadget before this * registration call returns. It's expected that the @bind() function will * be in init sections. + * + * Use the macro defined below instead of calling this directly. */ -int usb_gadget_probe_driver(struct usb_gadget_driver *driver); +int usb_gadget_register_driver_owner(struct usb_gadget_driver *driver, + struct module *owner, const char *mod_name); + +/* use a define to avoid include chaining to get THIS_MODULE & friends */ +#define usb_gadget_register_driver(driver) \ + usb_gadget_register_driver_owner(driver, THIS_MODULE, KBUILD_MODNAME) /** * usb_gadget_unregister_driver - unregister a gadget driver diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h index 548a028f2dab..78cd566ee238 100644 --- a/include/linux/usb/hcd.h +++ b/include/linux/usb/hcd.h @@ -1,20 +1,6 @@ // SPDX-License-Identifier: GPL-2.0+ /* * Copyright (c) 2001-2002 by David Brownell - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the - * Free Software Foundation; either version 2 of the License, or (at your - * option) any later version. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY - * or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License - * for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software Foundation, - * Inc., 675 Mass Ave, Cambridge, MA 02139, USA. */ #ifndef __USB_CORE_HCD_H @@ -66,6 +52,7 @@ struct giveback_urb_bh { bool running; + bool high_prio; spinlock_t lock; struct list_head head; struct tasklet_struct bh; @@ -124,6 +111,7 @@ struct usb_hcd { #define HCD_FLAG_RH_RUNNING 5 /* root hub is running? */ #define HCD_FLAG_DEAD 6 /* controller has died? */ #define HCD_FLAG_INTF_AUTHORIZED 7 /* authorize interfaces? */ +#define HCD_FLAG_DEFER_RH_REGISTER 8 /* Defer roothub registration */ /* The flags can be tested using these macros; they are likely to * be slightly faster than test_bit(). @@ -134,6 +122,7 @@ struct usb_hcd { #define HCD_WAKEUP_PENDING(hcd) ((hcd)->flags & (1U << HCD_FLAG_WAKEUP_PENDING)) #define HCD_RH_RUNNING(hcd) ((hcd)->flags & (1U << HCD_FLAG_RH_RUNNING)) #define HCD_DEAD(hcd) ((hcd)->flags & (1U << HCD_FLAG_DEAD)) +#define HCD_DEFER_RH_REGISTER(hcd) ((hcd)->flags & (1U << HCD_FLAG_DEFER_RH_REGISTER)) /* * Specifies if interfaces are authorized by default @@ -490,7 +479,6 @@ static inline int ehset_single_step_set_feature(struct usb_hcd *hcd, int port) struct pci_dev; struct pci_device_id; extern int usb_hcd_pci_probe(struct pci_dev *dev, - const struct pci_device_id *id, const struct hc_driver *driver); extern void usb_hcd_pci_remove(struct pci_dev *dev); extern void usb_hcd_pci_shutdown(struct pci_dev *dev); diff --git a/include/linux/usb/input.h b/include/linux/usb/input.h index 974befa72ac0..5e759b2cf551 100644 --- a/include/linux/usb/input.h +++ b/include/linux/usb/input.h @@ -1,10 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2005 Dmitry Torokhov - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License version 2 as published by - * the Free Software Foundation. */ #ifndef __LINUX_USB_INPUT_H diff --git a/include/linux/usb/isp1301.h b/include/linux/usb/isp1301.h index dedb3b2473e8..fa986b926a12 100644 --- a/include/linux/usb/isp1301.h +++ b/include/linux/usb/isp1301.h @@ -3,16 +3,6 @@ * NXP ISP1301 USB transceiver driver * * Copyright (C) 2012 Roland Stigge <stigge@antcom.de> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; version 2 of the License. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * */ #ifndef __LINUX_USB_ISP1301_H diff --git a/include/linux/usb/m66592.h b/include/linux/usb/m66592.h index 2dfe68183495..5f04de2b47fd 100644 --- a/include/linux/usb/m66592.h +++ b/include/linux/usb/m66592.h @@ -3,20 +3,6 @@ * M66592 driver platform data * * Copyright (C) 2009 Renesas Solutions Corp. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; version 2 of the License. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * */ #ifndef __LINUX_USB_M66592_H diff --git a/include/linux/usb/musb-ux500.h b/include/linux/usb/musb-ux500.h index c4b7ad9850ca..d60dcfc56b5a 100644 --- a/include/linux/usb/musb-ux500.h +++ b/include/linux/usb/musb-ux500.h @@ -1,16 +1,6 @@ // SPDX-License-Identifier: GPL-2.0+ /* * Copyright (C) 2013 ST-Ericsson AB - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. */ #ifndef __MUSB_UX500_H__ diff --git a/include/linux/usb/net2280.h b/include/linux/usb/net2280.h index 08b85caecfaf..f29fe6a1f415 100644 --- a/include/linux/usb/net2280.h +++ b/include/linux/usb/net2280.h @@ -5,20 +5,6 @@ * * Copyright (C) 2002 NetChip Technology, Inc. (http://www.netchip.com) * Copyright (C) 2003 David Brownell - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef __LINUX_USB_NET2280_H diff --git a/include/linux/usb/of.h b/include/linux/usb/of.h index dba55ccb9b53..98487fd7ab11 100644 --- a/include/linux/usb/of.h +++ b/include/linux/usb/of.h @@ -1,8 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* * OF helpers for usb devices. - * - * This file is released under the GPLv2 */ #ifndef __LINUX_USB_OF_H diff --git a/include/linux/usb/ohci_pdriver.h b/include/linux/usb/ohci_pdriver.h index 7eb16cf587ee..2447c78b1766 100644 --- a/include/linux/usb/ohci_pdriver.h +++ b/include/linux/usb/ohci_pdriver.h @@ -1,20 +1,6 @@ // SPDX-License-Identifier: GPL-2.0+ /* * Copyright (C) 2012 Hauke Mehrtens <hauke@hauke-m.de> - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the - * Free Software Foundation; either version 2 of the License, or (at your - * option) any later version. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY - * or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License - * for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software Foundation, - * Inc., 675 Mass Ave, Cambridge, MA 02139, USA. */ #ifndef __USB_CORE_OHCI_PDRIVER_H diff --git a/include/linux/usb/onboard_hub.h b/include/linux/usb/onboard_hub.h new file mode 100644 index 000000000000..d9373230556e --- /dev/null +++ b/include/linux/usb/onboard_hub.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __LINUX_USB_ONBOARD_HUB_H +#define __LINUX_USB_ONBOARD_HUB_H + +struct usb_device; +struct list_head; + +#if IS_ENABLED(CONFIG_USB_ONBOARD_HUB) +void onboard_hub_create_pdevs(struct usb_device *parent_hub, struct list_head *pdev_list); +void onboard_hub_destroy_pdevs(struct list_head *pdev_list); +#else +static inline void onboard_hub_create_pdevs(struct usb_device *parent_hub, + struct list_head *pdev_list) {} +static inline void onboard_hub_destroy_pdevs(struct list_head *pdev_list) {} +#endif + +#endif /* __LINUX_USB_ONBOARD_HUB_H */ diff --git a/include/linux/usb/otg-fsm.h b/include/linux/usb/otg-fsm.h index 784659d4dc99..6135d076c53d 100644 --- a/include/linux/usb/otg-fsm.h +++ b/include/linux/usb/otg-fsm.h @@ -1,19 +1,6 @@ // SPDX-License-Identifier: GPL-2.0+ -/* Copyright (C) 2007,2008 Freescale Semiconductor, Inc. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the - * Free Software Foundation; either version 2 of the License, or (at your - * option) any later version. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, write to the Free Software Foundation, Inc., - * 675 Mass Ave, Cambridge, MA 02139, USA. +/* + * Copyright (C) 2007,2008 Freescale Semiconductor, Inc. */ #ifndef __LINUX_USB_OTG_FSM_H diff --git a/include/linux/usb/pd.h b/include/linux/usb/pd.h index 96b7ff66f074..c59fb79a42e8 100644 --- a/include/linux/usb/pd.h +++ b/include/linux/usb/pd.h @@ -495,4 +495,42 @@ static inline unsigned int rdo_max_power(u32 rdo) #define PD_P_SNK_STDBY_MW 2500 /* 2500 mW */ +#if IS_ENABLED(CONFIG_TYPEC) + +struct usb_power_delivery; + +/** + * usb_power_delivery_desc - USB Power Delivery Descriptor + * @revision: USB Power Delivery Specification Revision + * @version: USB Power Delivery Specicication Version - optional + */ +struct usb_power_delivery_desc { + u16 revision; + u16 version; +}; + +/** + * usb_power_delivery_capabilities_desc - Description of USB Power Delivery Capabilities Message + * @pdo: The Power Data Objects in the Capability Message + * @role: Power role of the capabilities + */ +struct usb_power_delivery_capabilities_desc { + u32 pdo[PDO_MAX_OBJECTS]; + enum typec_role role; +}; + +struct usb_power_delivery_capabilities * +usb_power_delivery_register_capabilities(struct usb_power_delivery *pd, + struct usb_power_delivery_capabilities_desc *desc); +void usb_power_delivery_unregister_capabilities(struct usb_power_delivery_capabilities *cap); + +struct usb_power_delivery *usb_power_delivery_register(struct device *parent, + struct usb_power_delivery_desc *desc); +void usb_power_delivery_unregister(struct usb_power_delivery *pd); + +int usb_power_delivery_link_device(struct usb_power_delivery *pd, struct device *dev); +void usb_power_delivery_unlink_device(struct usb_power_delivery *pd, struct device *dev); + +#endif /* CONFIG_TYPEC */ + #endif /* __LINUX_USB_PD_H */ diff --git a/include/linux/usb/pd_bdo.h b/include/linux/usb/pd_bdo.h index 033fe3e17141..7c25b88d79f9 100644 --- a/include/linux/usb/pd_bdo.h +++ b/include/linux/usb/pd_bdo.h @@ -15,7 +15,7 @@ #define BDO_MODE_CARRIER2 (5 << 28) #define BDO_MODE_CARRIER3 (6 << 28) #define BDO_MODE_EYE (7 << 28) -#define BDO_MODE_TESTDATA (8 << 28) +#define BDO_MODE_TESTDATA (8U << 28) #define BDO_MODE_MASK(mode) ((mode) & 0xf0000000) diff --git a/include/linux/usb/phy_companion.h b/include/linux/usb/phy_companion.h index 263196f05015..862aaeca2319 100644 --- a/include/linux/usb/phy_companion.h +++ b/include/linux/usb/phy_companion.h @@ -3,18 +3,8 @@ * phy-companion.h -- phy companion to indicate the comparator part of PHY * * Copyright (C) 2012 Texas Instruments Incorporated - https://www.ti.com - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. * * Author: Kishon Vijay Abraham I <kishon@ti.com> - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * */ #ifndef __DRIVERS_PHY_COMPANION_H diff --git a/include/linux/usb/r8a66597.h b/include/linux/usb/r8a66597.h index c0753d026bbf..f0fa7ddadbaa 100644 --- a/include/linux/usb/r8a66597.h +++ b/include/linux/usb/r8a66597.h @@ -5,20 +5,6 @@ * Copyright (C) 2009 Renesas Solutions Corp. * * Author : Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; version 2 of the License. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * */ #ifndef __LINUX_USB_R8A66597_H diff --git a/include/linux/usb/rndis_host.h b/include/linux/usb/rndis_host.h index 809bccd08455..489cfb1d00f6 100644 --- a/include/linux/usb/rndis_host.h +++ b/include/linux/usb/rndis_host.h @@ -2,20 +2,6 @@ /* * Host Side support for RNDIS Networking Links * Copyright (C) 2005 by David Brownell - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef __LINUX_USB_RNDIS_HOST_H @@ -197,6 +183,7 @@ struct rndis_keepalive_c { /* IN (optionally OUT) */ /* Flags for driver_info::data */ #define RNDIS_DRIVER_DATA_POLL_STATUS 1 /* poll status before control */ +#define RNDIS_DRIVER_DATA_DST_MAC_FIXUP 2 /* device ignores configured MAC address */ extern void rndis_status(struct usbnet *dev, struct urb *urb); extern int diff --git a/include/linux/usb/role.h b/include/linux/usb/role.h index 031f148ab373..b5deafd91f67 100644 --- a/include/linux/usb/role.h +++ b/include/linux/usb/role.h @@ -92,6 +92,12 @@ fwnode_usb_role_switch_get(struct fwnode_handle *node) static inline void usb_role_switch_put(struct usb_role_switch *sw) { } static inline struct usb_role_switch * +usb_role_switch_find_by_fwnode(const struct fwnode_handle *fwnode) +{ + return NULL; +} + +static inline struct usb_role_switch * usb_role_switch_register(struct device *parent, const struct usb_role_switch_desc *desc) { diff --git a/include/linux/usb/serial.h b/include/linux/usb/serial.h index 16ea5a4cc586..f7bfedb740f5 100644 --- a/include/linux/usb/serial.h +++ b/include/linux/usb/serial.h @@ -4,11 +4,6 @@ * * Copyright (C) 1999 - 2012 * Greg Kroah-Hartman (greg@kroah.com) - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; version 2 of the License. - * */ #ifndef __LINUX_USB_SERIAL_H @@ -281,8 +276,8 @@ struct usb_serial_driver { unsigned int cmd, unsigned long arg); void (*get_serial)(struct tty_struct *tty, struct serial_struct *ss); int (*set_serial)(struct tty_struct *tty, struct serial_struct *ss); - void (*set_termios)(struct tty_struct *tty, - struct usb_serial_port *port, struct ktermios *old); + void (*set_termios)(struct tty_struct *tty, struct usb_serial_port *port, + const struct ktermios *old); void (*break_ctl)(struct tty_struct *tty, int break_state); unsigned int (*chars_in_buffer)(struct tty_struct *tty); void (*wait_until_sent)(struct tty_struct *tty, long timeout); diff --git a/include/linux/usb/storage.h b/include/linux/usb/storage.h index e0240f864548..2827ce72e502 100644 --- a/include/linux/usb/storage.h +++ b/include/linux/usb/storage.h @@ -9,8 +9,6 @@ * * This file contains definitions taken from the * USB Mass Storage Class Specification Overview - * - * Distributed under the terms of the GNU GPL, version two. */ /* Storage subclass codes */ diff --git a/include/linux/usb/tcpci.h b/include/linux/usb/tcpci.h new file mode 100644 index 000000000000..17657451c762 --- /dev/null +++ b/include/linux/usb/tcpci.h @@ -0,0 +1,232 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * Copyright 2015-2017 Google, Inc + * + * USB Type-C Port Controller Interface. + */ + +#ifndef __LINUX_USB_TCPCI_H +#define __LINUX_USB_TCPCI_H + +#include <linux/usb/typec.h> +#include <linux/usb/tcpm.h> + +#define TCPC_VENDOR_ID 0x0 +#define TCPC_PRODUCT_ID 0x2 +#define TCPC_BCD_DEV 0x4 +#define TCPC_TC_REV 0x6 +#define TCPC_PD_REV 0x8 +#define TCPC_PD_INT_REV 0xa + +#define TCPC_ALERT 0x10 +#define TCPC_ALERT_EXTND BIT(14) +#define TCPC_ALERT_EXTENDED_STATUS BIT(13) +#define TCPC_ALERT_VBUS_DISCNCT BIT(11) +#define TCPC_ALERT_RX_BUF_OVF BIT(10) +#define TCPC_ALERT_FAULT BIT(9) +#define TCPC_ALERT_V_ALARM_LO BIT(8) +#define TCPC_ALERT_V_ALARM_HI BIT(7) +#define TCPC_ALERT_TX_SUCCESS BIT(6) +#define TCPC_ALERT_TX_DISCARDED BIT(5) +#define TCPC_ALERT_TX_FAILED BIT(4) +#define TCPC_ALERT_RX_HARD_RST BIT(3) +#define TCPC_ALERT_RX_STATUS BIT(2) +#define TCPC_ALERT_POWER_STATUS BIT(1) +#define TCPC_ALERT_CC_STATUS BIT(0) + +#define TCPC_ALERT_MASK 0x12 +#define TCPC_POWER_STATUS_MASK 0x14 +#define TCPC_FAULT_STATUS_MASK 0x15 + +#define TCPC_EXTENDED_STATUS_MASK 0x16 +#define TCPC_EXTENDED_STATUS_MASK_VSAFE0V BIT(0) + +#define TCPC_ALERT_EXTENDED_MASK 0x17 +#define TCPC_SINK_FAST_ROLE_SWAP BIT(0) + +#define TCPC_CONFIG_STD_OUTPUT 0x18 + +#define TCPC_TCPC_CTRL 0x19 +#define TCPC_TCPC_CTRL_ORIENTATION BIT(0) +#define PLUG_ORNT_CC1 0 +#define PLUG_ORNT_CC2 1 +#define TCPC_TCPC_CTRL_BIST_TM BIT(1) +#define TCPC_TCPC_CTRL_EN_LK4CONN_ALRT BIT(6) + +#define TCPC_EXTENDED_STATUS 0x20 +#define TCPC_EXTENDED_STATUS_VSAFE0V BIT(0) + +#define TCPC_ROLE_CTRL 0x1a +#define TCPC_ROLE_CTRL_DRP BIT(6) +#define TCPC_ROLE_CTRL_RP_VAL_SHIFT 4 +#define TCPC_ROLE_CTRL_RP_VAL_MASK 0x3 +#define TCPC_ROLE_CTRL_RP_VAL_DEF 0x0 +#define TCPC_ROLE_CTRL_RP_VAL_1_5 0x1 +#define TCPC_ROLE_CTRL_RP_VAL_3_0 0x2 +#define TCPC_ROLE_CTRL_CC2_SHIFT 2 +#define TCPC_ROLE_CTRL_CC2_MASK 0x3 +#define TCPC_ROLE_CTRL_CC1_SHIFT 0 +#define TCPC_ROLE_CTRL_CC1_MASK 0x3 +#define TCPC_ROLE_CTRL_CC_RA 0x0 +#define TCPC_ROLE_CTRL_CC_RP 0x1 +#define TCPC_ROLE_CTRL_CC_RD 0x2 +#define TCPC_ROLE_CTRL_CC_OPEN 0x3 + +#define TCPC_FAULT_CTRL 0x1b + +#define TCPC_POWER_CTRL 0x1c +#define TCPC_POWER_CTRL_VCONN_ENABLE BIT(0) +#define TCPC_POWER_CTRL_BLEED_DISCHARGE BIT(3) +#define TCPC_POWER_CTRL_AUTO_DISCHARGE BIT(4) +#define TCPC_DIS_VOLT_ALRM BIT(5) +#define TCPC_POWER_CTRL_VBUS_VOLT_MON BIT(6) +#define TCPC_FAST_ROLE_SWAP_EN BIT(7) + +#define TCPC_CC_STATUS 0x1d +#define TCPC_CC_STATUS_TOGGLING BIT(5) +#define TCPC_CC_STATUS_TERM BIT(4) +#define TCPC_CC_STATUS_TERM_RP 0 +#define TCPC_CC_STATUS_TERM_RD 1 +#define TCPC_CC_STATE_SRC_OPEN 0 +#define TCPC_CC_STATUS_CC2_SHIFT 2 +#define TCPC_CC_STATUS_CC2_MASK 0x3 +#define TCPC_CC_STATUS_CC1_SHIFT 0 +#define TCPC_CC_STATUS_CC1_MASK 0x3 + +#define TCPC_POWER_STATUS 0x1e +#define TCPC_POWER_STATUS_DBG_ACC_CON BIT(7) +#define TCPC_POWER_STATUS_UNINIT BIT(6) +#define TCPC_POWER_STATUS_SOURCING_VBUS BIT(4) +#define TCPC_POWER_STATUS_VBUS_DET BIT(3) +#define TCPC_POWER_STATUS_VBUS_PRES BIT(2) +#define TCPC_POWER_STATUS_VCONN_PRES BIT(1) +#define TCPC_POWER_STATUS_SINKING_VBUS BIT(0) + +#define TCPC_FAULT_STATUS 0x1f + +#define TCPC_ALERT_EXTENDED 0x21 + +#define TCPC_COMMAND 0x23 +#define TCPC_CMD_WAKE_I2C 0x11 +#define TCPC_CMD_DISABLE_VBUS_DETECT 0x22 +#define TCPC_CMD_ENABLE_VBUS_DETECT 0x33 +#define TCPC_CMD_DISABLE_SINK_VBUS 0x44 +#define TCPC_CMD_SINK_VBUS 0x55 +#define TCPC_CMD_DISABLE_SRC_VBUS 0x66 +#define TCPC_CMD_SRC_VBUS_DEFAULT 0x77 +#define TCPC_CMD_SRC_VBUS_HIGH 0x88 +#define TCPC_CMD_LOOK4CONNECTION 0x99 +#define TCPC_CMD_RXONEMORE 0xAA +#define TCPC_CMD_I2C_IDLE 0xFF + +#define TCPC_DEV_CAP_1 0x24 +#define TCPC_DEV_CAP_2 0x26 +#define TCPC_STD_INPUT_CAP 0x28 +#define TCPC_STD_OUTPUT_CAP 0x29 + +#define TCPC_MSG_HDR_INFO 0x2e +#define TCPC_MSG_HDR_INFO_DATA_ROLE BIT(3) +#define TCPC_MSG_HDR_INFO_PWR_ROLE BIT(0) +#define TCPC_MSG_HDR_INFO_REV_SHIFT 1 +#define TCPC_MSG_HDR_INFO_REV_MASK 0x3 + +#define TCPC_RX_DETECT 0x2f +#define TCPC_RX_DETECT_HARD_RESET BIT(5) +#define TCPC_RX_DETECT_SOP BIT(0) +#define TCPC_RX_DETECT_SOP1 BIT(1) +#define TCPC_RX_DETECT_SOP2 BIT(2) +#define TCPC_RX_DETECT_DBG1 BIT(3) +#define TCPC_RX_DETECT_DBG2 BIT(4) + +#define TCPC_RX_BYTE_CNT 0x30 +#define TCPC_RX_BUF_FRAME_TYPE 0x31 +#define TCPC_RX_BUF_FRAME_TYPE_SOP 0 +#define TCPC_RX_HDR 0x32 +#define TCPC_RX_DATA 0x34 /* through 0x4f */ + +#define TCPC_TRANSMIT 0x50 +#define TCPC_TRANSMIT_RETRY_SHIFT 4 +#define TCPC_TRANSMIT_RETRY_MASK 0x3 +#define TCPC_TRANSMIT_TYPE_SHIFT 0 +#define TCPC_TRANSMIT_TYPE_MASK 0x7 + +#define TCPC_TX_BYTE_CNT 0x51 +#define TCPC_TX_HDR 0x52 +#define TCPC_TX_DATA 0x54 /* through 0x6f */ + +#define TCPC_VBUS_VOLTAGE 0x70 +#define TCPC_VBUS_VOLTAGE_MASK 0x3ff +#define TCPC_VBUS_VOLTAGE_LSB_MV 25 +#define TCPC_VBUS_SINK_DISCONNECT_THRESH 0x72 +#define TCPC_VBUS_SINK_DISCONNECT_THRESH_LSB_MV 25 +#define TCPC_VBUS_SINK_DISCONNECT_THRESH_MAX 0x3ff +#define TCPC_VBUS_STOP_DISCHARGE_THRESH 0x74 +#define TCPC_VBUS_VOLTAGE_ALARM_HI_CFG 0x76 +#define TCPC_VBUS_VOLTAGE_ALARM_LO_CFG 0x78 + +/* I2C_WRITE_BYTE_COUNT + 1 when TX_BUF_BYTE_x is only accessible I2C_WRITE_BYTE_COUNT */ +#define TCPC_TRANSMIT_BUFFER_MAX_LEN 31 + +#define tcpc_presenting_rd(reg, cc) \ + (!(TCPC_ROLE_CTRL_DRP & (reg)) && \ + (((reg) & (TCPC_ROLE_CTRL_## cc ##_MASK << TCPC_ROLE_CTRL_## cc ##_SHIFT)) == \ + (TCPC_ROLE_CTRL_CC_RD << TCPC_ROLE_CTRL_## cc ##_SHIFT))) + +struct tcpci; + +/* + * @TX_BUF_BYTE_x_hidden: + * optional; Set when TX_BUF_BYTE_x can only be accessed through I2C_WRITE_BYTE_COUNT. + * @frs_sourcing_vbus: + * Optional; Callback to perform chip specific operations when FRS + * is sourcing vbus. + * @auto_discharge_disconnect: + * Optional; Enables TCPC to autonously discharge vbus on disconnect. + * @vbus_vsafe0v: + * optional; Set when TCPC can detect whether vbus is at VSAFE0V. + * @set_partner_usb_comm_capable: + * Optional; The USB Communications Capable bit indicates if port + * partner is capable of communication over the USB data lines + * (e.g. D+/- or SS Tx/Rx). Called to notify the status of the bit. + */ +struct tcpci_data { + struct regmap *regmap; + unsigned char TX_BUF_BYTE_x_hidden:1; + unsigned char auto_discharge_disconnect:1; + unsigned char vbus_vsafe0v:1; + + int (*init)(struct tcpci *tcpci, struct tcpci_data *data); + int (*set_vconn)(struct tcpci *tcpci, struct tcpci_data *data, + bool enable); + int (*start_drp_toggling)(struct tcpci *tcpci, struct tcpci_data *data, + enum typec_cc_status cc); + int (*set_vbus)(struct tcpci *tcpci, struct tcpci_data *data, bool source, bool sink); + void (*frs_sourcing_vbus)(struct tcpci *tcpci, struct tcpci_data *data); + void (*set_partner_usb_comm_capable)(struct tcpci *tcpci, struct tcpci_data *data, + bool capable); +}; + +struct tcpci *tcpci_register_port(struct device *dev, struct tcpci_data *data); +void tcpci_unregister_port(struct tcpci *tcpci); +irqreturn_t tcpci_irq(struct tcpci *tcpci); + +struct tcpm_port; +struct tcpm_port *tcpci_get_tcpm_port(struct tcpci *tcpci); + +static inline enum typec_cc_status tcpci_to_typec_cc(unsigned int cc, bool sink) +{ + switch (cc) { + case 0x1: + return sink ? TYPEC_CC_RP_DEF : TYPEC_CC_RA; + case 0x2: + return sink ? TYPEC_CC_RP_1_5 : TYPEC_CC_RD; + case 0x3: + if (sink) + return TYPEC_CC_RP_3_0; + fallthrough; + case 0x0: + default: + return TYPEC_CC_OPEN; + } +} +#endif /* __LINUX_USB_TCPCI_H */ diff --git a/include/linux/usb/tegra_usb_phy.h b/include/linux/usb/tegra_usb_phy.h index d3e65eb9e16f..46e73584b6e6 100644 --- a/include/linux/usb/tegra_usb_phy.h +++ b/include/linux/usb/tegra_usb_phy.h @@ -1,16 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2010 Google, Inc. - * - * This software is licensed under the terms of the GNU General Public - * License version 2, as published by the Free Software Foundation, and - * may be copied, distributed, and modified under those terms. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * */ #ifndef __TEGRA_USB_PHY_H diff --git a/include/linux/usb/typec.h b/include/linux/usb/typec.h index e2e44bb1dad8..7751bedcae5d 100644 --- a/include/linux/usb/typec.h +++ b/include/linux/usb/typec.h @@ -22,6 +22,8 @@ struct typec_altmode_ops; struct fwnode_handle; struct device; +struct usb_power_delivery; + enum typec_port_type { TYPEC_PORT_SRC, TYPEC_PORT_SNK, @@ -52,6 +54,16 @@ enum typec_role { TYPEC_SOURCE, }; +static inline int is_sink(enum typec_role role) +{ + return role == TYPEC_SINK; +} + +static inline int is_source(enum typec_role role) +{ + return role == TYPEC_SOURCE; +} + enum typec_pwr_opmode { TYPEC_PWR_MODE_USB, TYPEC_PWR_MODE_1_5A, @@ -213,6 +225,8 @@ struct typec_partner_desc { * @pr_set: Set Power Role * @vconn_set: Source VCONN * @port_type_set: Set port type + * @pd_get: Get available USB Power Delivery Capabilities. + * @pd_set: Set USB Power Delivery Capabilities. */ struct typec_operations { int (*try_role)(struct typec_port *port, int role); @@ -221,6 +235,8 @@ struct typec_operations { int (*vconn_set)(struct typec_port *port, enum typec_role role); int (*port_type_set)(struct typec_port *port, enum typec_port_type type); + struct usb_power_delivery **(*pd_get)(struct typec_port *port); + int (*pd_set)(struct typec_port *port, struct usb_power_delivery *pd); }; enum usb_pd_svdm_ver { @@ -240,6 +256,7 @@ enum usb_pd_svdm_ver { * @accessory: Supported Accessory Modes * @fwnode: Optional fwnode of the port * @driver_data: Private pointer for driver specific info + * @pd: Optional USB Power Delivery Support * @ops: Port operations vector * * Static capabilities of a single USB Type-C port. @@ -257,6 +274,8 @@ struct typec_capability { struct fwnode_handle *fwnode; void *driver_data; + struct usb_power_delivery *pd; + const struct typec_operations *ops; }; @@ -295,6 +314,9 @@ int typec_set_mode(struct typec_port *port, int mode); void *typec_get_drvdata(struct typec_port *port); +int typec_get_fw_cap(struct typec_capability *cap, + struct fwnode_handle *fwnode); + int typec_find_pwr_opmode(const char *name); int typec_find_orientation(const char *name); int typec_find_port_power_role(const char *name); @@ -305,16 +327,8 @@ void typec_partner_set_svdm_version(struct typec_partner *partner, enum usb_pd_svdm_ver svdm_version); int typec_get_negotiated_svdm_version(struct typec_port *port); -#if IS_REACHABLE(CONFIG_TYPEC) -int typec_link_port(struct device *port); -void typec_unlink_port(struct device *port); -#else -static inline int typec_link_port(struct device *port) -{ - return 0; -} - -static inline void typec_unlink_port(struct device *port) { } -#endif +int typec_port_set_usb_power_delivery(struct typec_port *port, struct usb_power_delivery *pd); +int typec_partner_set_usb_power_delivery(struct typec_partner *partner, + struct usb_power_delivery *pd); #endif /* __LINUX_USB_TYPEC_H */ diff --git a/include/linux/usb/typec_altmode.h b/include/linux/usb/typec_altmode.h index 65933cbe9129..350d49012659 100644 --- a/include/linux/usb/typec_altmode.h +++ b/include/linux/usb/typec_altmode.h @@ -124,7 +124,7 @@ struct typec_altmode *typec_match_altmode(struct typec_altmode **altmodes, /** * typec_altmode_get_orientation - Get cable plug orientation - * altmode: Handle to the alternate mode + * @altmode: Handle to the alternate mode */ static inline enum typec_orientation typec_altmode_get_orientation(struct typec_altmode *altmode) diff --git a/include/linux/usb/typec_dp.h b/include/linux/usb/typec_dp.h index cfb916cccd31..8d09c2f0a9b8 100644 --- a/include/linux/usb/typec_dp.h +++ b/include/linux/usb/typec_dp.h @@ -73,6 +73,11 @@ enum { #define DP_CAP_USB BIT(7) #define DP_CAP_DFP_D_PIN_ASSIGN(_cap_) (((_cap_) & GENMASK(15, 8)) >> 8) #define DP_CAP_UFP_D_PIN_ASSIGN(_cap_) (((_cap_) & GENMASK(23, 16)) >> 16) +/* Get pin assignment taking plug & receptacle into consideration */ +#define DP_CAP_PIN_ASSIGN_UFP_D(_cap_) ((_cap_ & DP_CAP_RECEPTACLE) ? \ + DP_CAP_UFP_D_PIN_ASSIGN(_cap_) : DP_CAP_DFP_D_PIN_ASSIGN(_cap_)) +#define DP_CAP_PIN_ASSIGN_DFP_D(_cap_) ((_cap_ & DP_CAP_RECEPTACLE) ? \ + DP_CAP_DFP_D_PIN_ASSIGN(_cap_) : DP_CAP_UFP_D_PIN_ASSIGN(_cap_)) /* DisplayPort Status Update VDO bits */ #define DP_STATUS_CONNECTION(_status_) ((_status_) & 3) diff --git a/include/linux/usb/typec_mux.h b/include/linux/usb/typec_mux.h index a9d9957933dc..9292f0e07846 100644 --- a/include/linux/usb/typec_mux.h +++ b/include/linux/usb/typec_mux.h @@ -8,11 +8,13 @@ struct device; struct typec_mux; +struct typec_mux_dev; struct typec_switch; +struct typec_switch_dev; struct typec_altmode; struct fwnode_handle; -typedef int (*typec_switch_set_fn_t)(struct typec_switch *sw, +typedef int (*typec_switch_set_fn_t)(struct typec_switch_dev *sw, enum typec_orientation orientation); struct typec_switch_desc { @@ -32,13 +34,13 @@ static inline struct typec_switch *typec_switch_get(struct device *dev) return fwnode_typec_switch_get(dev_fwnode(dev)); } -struct typec_switch * +struct typec_switch_dev * typec_switch_register(struct device *parent, const struct typec_switch_desc *desc); -void typec_switch_unregister(struct typec_switch *sw); +void typec_switch_unregister(struct typec_switch_dev *sw); -void typec_switch_set_drvdata(struct typec_switch *sw, void *data); -void *typec_switch_get_drvdata(struct typec_switch *sw); +void typec_switch_set_drvdata(struct typec_switch_dev *sw, void *data); +void *typec_switch_get_drvdata(struct typec_switch_dev *sw); struct typec_mux_state { struct typec_altmode *alt; @@ -46,7 +48,7 @@ struct typec_mux_state { void *data; }; -typedef int (*typec_mux_set_fn_t)(struct typec_mux *mux, +typedef int (*typec_mux_set_fn_t)(struct typec_mux_dev *mux, struct typec_mux_state *state); struct typec_mux_desc { @@ -56,22 +58,54 @@ struct typec_mux_desc { void *drvdata; }; +#if IS_ENABLED(CONFIG_TYPEC) + struct typec_mux *fwnode_typec_mux_get(struct fwnode_handle *fwnode, const struct typec_altmode_desc *desc); void typec_mux_put(struct typec_mux *mux); int typec_mux_set(struct typec_mux *mux, struct typec_mux_state *state); +struct typec_mux_dev * +typec_mux_register(struct device *parent, const struct typec_mux_desc *desc); +void typec_mux_unregister(struct typec_mux_dev *mux); + +void typec_mux_set_drvdata(struct typec_mux_dev *mux, void *data); +void *typec_mux_get_drvdata(struct typec_mux_dev *mux); + +#else + +static inline struct typec_mux *fwnode_typec_mux_get(struct fwnode_handle *fwnode, + const struct typec_altmode_desc *desc) +{ + return NULL; +} + +static inline void typec_mux_put(struct typec_mux *mux) {} + +static inline int typec_mux_set(struct typec_mux *mux, struct typec_mux_state *state) +{ + return 0; +} + +static inline struct typec_mux_dev * +typec_mux_register(struct device *parent, const struct typec_mux_desc *desc) +{ + return ERR_PTR(-EOPNOTSUPP); +} +static inline void typec_mux_unregister(struct typec_mux_dev *mux) {} + +static inline void typec_mux_set_drvdata(struct typec_mux_dev *mux, void *data) {} +static inline void *typec_mux_get_drvdata(struct typec_mux_dev *mux) +{ + return ERR_PTR(-EOPNOTSUPP); +} + +#endif /* CONFIG_TYPEC */ + static inline struct typec_mux * typec_mux_get(struct device *dev, const struct typec_altmode_desc *desc) { return fwnode_typec_mux_get(dev_fwnode(dev), desc); } -struct typec_mux * -typec_mux_register(struct device *parent, const struct typec_mux_desc *desc); -void typec_mux_unregister(struct typec_mux *mux); - -void typec_mux_set_drvdata(struct typec_mux *mux, void *data); -void *typec_mux_get_drvdata(struct typec_mux *mux); - #endif /* __USB_TYPEC_MUX */ diff --git a/include/linux/usb/typec_retimer.h b/include/linux/usb/typec_retimer.h new file mode 100644 index 000000000000..5e036b3360e2 --- /dev/null +++ b/include/linux/usb/typec_retimer.h @@ -0,0 +1,45 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __USB_TYPEC_RETIMER +#define __USB_TYPEC_RETIMER + +#include <linux/property.h> +#include <linux/usb/typec.h> + +struct device; +struct typec_retimer; +struct typec_altmode; +struct fwnode_handle; + +struct typec_retimer_state { + struct typec_altmode *alt; + unsigned long mode; + void *data; +}; + +typedef int (*typec_retimer_set_fn_t)(struct typec_retimer *retimer, + struct typec_retimer_state *state); + +struct typec_retimer_desc { + struct fwnode_handle *fwnode; + typec_retimer_set_fn_t set; + const char *name; + void *drvdata; +}; + +struct typec_retimer *fwnode_typec_retimer_get(struct fwnode_handle *fwnode); +void typec_retimer_put(struct typec_retimer *retimer); +int typec_retimer_set(struct typec_retimer *retimer, struct typec_retimer_state *state); + +static inline struct typec_retimer *typec_retimer_get(struct device *dev) +{ + return fwnode_typec_retimer_get(dev_fwnode(dev)); +} + +struct typec_retimer * +typec_retimer_register(struct device *parent, const struct typec_retimer_desc *desc); +void typec_retimer_unregister(struct typec_retimer *retimer); + +void *typec_retimer_get_drvdata(struct typec_retimer *retimer); + +#endif /* __USB_TYPEC_RETIMER */ diff --git a/include/linux/usb/ulpi.h b/include/linux/usb/ulpi.h index 36c2982780ad..5050f502c1ed 100644 --- a/include/linux/usb/ulpi.h +++ b/include/linux/usb/ulpi.h @@ -3,10 +3,6 @@ * ulpi.h -- ULPI defines and function prorotypes * * Copyright (C) 2010 Nokia Corporation - * - * This software is distributed under the terms of the GNU General - * Public License ("GPL") as published by the Free Software Foundation, - * version 2 of that License. */ #ifndef __LINUX_USB_ULPI_H diff --git a/include/linux/usb/usb338x.h b/include/linux/usb/usb338x.h index 20020c1336d5..70a7e3cdb3c9 100644 --- a/include/linux/usb/usb338x.h +++ b/include/linux/usb/usb338x.h @@ -6,17 +6,6 @@ * Copyright (C) 2002 NetChip Technology, Inc. (http://www.netchip.com) * Copyright (C) 2003 David Brownell * Copyright (C) 2014 Ricardo Ribalda - Qtechnology/AS - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * */ #ifndef __LINUX_USB_USB338X_H diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h index 8336e86ce606..9f08a584d707 100644 --- a/include/linux/usb/usbnet.h +++ b/include/linux/usb/usbnet.h @@ -4,25 +4,17 @@ * * Copyright (C) 2000-2005 by David Brownell <dbrownell@users.sourceforge.net> * Copyright (C) 2003-2005 David Hollis <dhollis@davehollis.com> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef __LINUX_USB_USBNET_H #define __LINUX_USB_USBNET_H +#include <linux/mii.h> +#include <linux/netdevice.h> +#include <linux/skbuff.h> +#include <linux/types.h> +#include <linux/usb.h> + /* interface from usbnet core to each USB networking link we handle */ struct usbnet { /* housekeeping */ @@ -214,6 +206,7 @@ extern int usbnet_ether_cdc_bind(struct usbnet *dev, struct usb_interface *intf) extern int usbnet_cdc_bind(struct usbnet *, struct usb_interface *); extern void usbnet_cdc_unbind(struct usbnet *, struct usb_interface *); extern void usbnet_cdc_status(struct usbnet *, struct urb *); +extern int usbnet_cdc_zte_rx_fixup(struct usbnet *dev, struct sk_buff *skb); /* CDC and RNDIS support the same host-chosen packet filters for IN transfers */ #define DEFAULT_FILTER (USB_CDC_PACKET_TYPE_BROADCAST \ diff --git a/include/linux/usb/xhci-dbgp.h b/include/linux/usb/xhci-dbgp.h index 0a37f1283bf0..171fd74b1cfc 100644 --- a/include/linux/usb/xhci-dbgp.h +++ b/include/linux/usb/xhci-dbgp.h @@ -5,17 +5,13 @@ * Copyright (C) 2016 Intel Corporation * * Author: Lu Baolu <baolu.lu@linux.intel.com> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #ifndef __LINUX_XHCI_DBGP_H #define __LINUX_XHCI_DBGP_H #ifdef CONFIG_EARLY_PRINTK_USB_XDBC -int __init early_xdbc_parse_parameter(char *s); +int __init early_xdbc_parse_parameter(char *s, int keep_early); int __init early_xdbc_setup_hardware(void); void __init early_xdbc_register_console(void); #else diff --git a/include/linux/user_events.h b/include/linux/user_events.h new file mode 100644 index 000000000000..592a3fbed98e --- /dev/null +++ b/include/linux/user_events.h @@ -0,0 +1,54 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * Copyright (c) 2021, Microsoft Corporation. + * + * Authors: + * Beau Belgrave <beaub@linux.microsoft.com> + */ +#ifndef _UAPI_LINUX_USER_EVENTS_H +#define _UAPI_LINUX_USER_EVENTS_H + +#include <linux/types.h> +#include <linux/ioctl.h> + +#ifdef __KERNEL__ +#include <linux/uio.h> +#else +#include <sys/uio.h> +#endif + +#define USER_EVENTS_SYSTEM "user_events" +#define USER_EVENTS_PREFIX "u:" + +/* Create dynamic location entry within a 32-bit value */ +#define DYN_LOC(offset, size) ((size) << 16 | (offset)) + +/* + * Describes an event registration and stores the results of the registration. + * This structure is passed to the DIAG_IOCSREG ioctl, callers at a minimum + * must set the size and name_args before invocation. + */ +struct user_reg { + + /* Input: Size of the user_reg structure being used */ + __u32 size; + + /* Input: Pointer to string with event name, description and flags */ + __u64 name_args; + + /* Output: Bitwise index of the event within the status page */ + __u32 status_bit; + + /* Output: Index of the event to use when writing data */ + __u32 write_index; +} __attribute__((__packed__)); + +#define DIAG_IOC_MAGIC '*' + +/* Requests to register a user_event */ +#define DIAG_IOCSREG _IOWR(DIAG_IOC_MAGIC, 0, struct user_reg*) + +/* Requests to delete a user_event */ +#define DIAG_IOCSDEL _IOW(DIAG_IOC_MAGIC, 1, char*) + +#endif /* _UAPI_LINUX_USER_EVENTS_H */ diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h index 33a4240e6a6f..45f09bec02c4 100644 --- a/include/linux/user_namespace.h +++ b/include/linux/user_namespace.h @@ -54,15 +54,17 @@ enum ucount_type { UCOUNT_FANOTIFY_GROUPS, UCOUNT_FANOTIFY_MARKS, #endif + UCOUNT_COUNTS, +}; + +enum rlimit_type { UCOUNT_RLIMIT_NPROC, UCOUNT_RLIMIT_MSGQUEUE, UCOUNT_RLIMIT_SIGPENDING, UCOUNT_RLIMIT_MEMLOCK, - UCOUNT_COUNTS, + UCOUNT_RLIMIT_COUNTS, }; -#define MAX_PER_NAMESPACE_UCOUNTS UCOUNT_RLIMIT_NPROC - struct user_namespace { struct uid_gid_map uid_map; struct uid_gid_map gid_map; @@ -99,6 +101,7 @@ struct user_namespace { #endif struct ucounts *ucounts; long ucount_max[UCOUNT_COUNTS]; + long rlimit_max[UCOUNT_RLIMIT_COUNTS]; } __randomize_layout; struct ucounts { @@ -107,6 +110,7 @@ struct ucounts { kuid_t uid; atomic_t count; atomic_long_t ucount[UCOUNT_COUNTS]; + atomic_long_t rlimit[UCOUNT_RLIMIT_COUNTS]; }; extern struct user_namespace init_user_ns; @@ -120,21 +124,26 @@ struct ucounts *alloc_ucounts(struct user_namespace *ns, kuid_t uid); struct ucounts * __must_check get_ucounts(struct ucounts *ucounts); void put_ucounts(struct ucounts *ucounts); -static inline long get_ucounts_value(struct ucounts *ucounts, enum ucount_type type) +static inline long get_rlimit_value(struct ucounts *ucounts, enum rlimit_type type) { - return atomic_long_read(&ucounts->ucount[type]); + return atomic_long_read(&ucounts->rlimit[type]); } -long inc_rlimit_ucounts(struct ucounts *ucounts, enum ucount_type type, long v); -bool dec_rlimit_ucounts(struct ucounts *ucounts, enum ucount_type type, long v); -long inc_rlimit_get_ucounts(struct ucounts *ucounts, enum ucount_type type); -void dec_rlimit_put_ucounts(struct ucounts *ucounts, enum ucount_type type); -bool is_ucounts_overlimit(struct ucounts *ucounts, enum ucount_type type, unsigned long max); +long inc_rlimit_ucounts(struct ucounts *ucounts, enum rlimit_type type, long v); +bool dec_rlimit_ucounts(struct ucounts *ucounts, enum rlimit_type type, long v); +long inc_rlimit_get_ucounts(struct ucounts *ucounts, enum rlimit_type type); +void dec_rlimit_put_ucounts(struct ucounts *ucounts, enum rlimit_type type); +bool is_rlimit_overlimit(struct ucounts *ucounts, enum rlimit_type type, unsigned long max); + +static inline long get_userns_rlimit_max(struct user_namespace *ns, enum rlimit_type type) +{ + return READ_ONCE(ns->rlimit_max[type]); +} -static inline void set_rlimit_ucount_max(struct user_namespace *ns, - enum ucount_type type, unsigned long max) +static inline void set_userns_rlimit_max(struct user_namespace *ns, + enum rlimit_type type, unsigned long max) { - ns->ucount_max[type] = max <= LONG_MAX ? max : LONG_MAX; + ns->rlimit_max[type] = max <= LONG_MAX ? max : LONG_MAX; } #ifdef CONFIG_USER_NS diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h index 33cea484d1ad..9df0b9a762cc 100644 --- a/include/linux/userfaultfd_k.h +++ b/include/linux/userfaultfd_k.h @@ -15,7 +15,10 @@ #include <linux/fcntl.h> #include <linux/mm.h> +#include <linux/swap.h> +#include <linux/swapops.h> #include <asm-generic/pgtable_uffd.h> +#include <linux/hugetlb_inline.h> /* The set of all possible UFFD-related VM flags. */ #define __VM_UFFD_FLAGS (VM_UFFD_MISSING | VM_UFFD_WP | VM_UFFD_MINOR) @@ -70,6 +73,8 @@ extern ssize_t mcopy_continue(struct mm_struct *dst_mm, unsigned long dst_start, extern int mwriteprotect_range(struct mm_struct *dst_mm, unsigned long start, unsigned long len, bool enable_wp, atomic_t *mmap_changing); +extern void uffd_wp_range(struct mm_struct *dst_mm, struct vm_area_struct *vma, + unsigned long start, unsigned long len, bool enable_wp); /* mm helpers */ static inline bool is_mergeable_vm_userfaultfd_ctx(struct vm_area_struct *vma, @@ -94,6 +99,18 @@ static inline bool uffd_disable_huge_pmd_share(struct vm_area_struct *vma) return vma->vm_flags & (VM_UFFD_WP | VM_UFFD_MINOR); } +/* + * Don't do fault around for either WP or MINOR registered uffd range. For + * MINOR registered range, fault around will be a total disaster and ptes can + * be installed without notifications; for WP it should mostly be fine as long + * as the fault around checks for pte_none() before the installation, however + * to be super safe we just forbid it. + */ +static inline bool uffd_disable_fault_around(struct vm_area_struct *vma) +{ + return vma->vm_flags & (VM_UFFD_WP | VM_UFFD_MINOR); +} + static inline bool userfaultfd_missing(struct vm_area_struct *vma) { return vma->vm_flags & VM_UFFD_MISSING; @@ -126,6 +143,25 @@ static inline bool userfaultfd_armed(struct vm_area_struct *vma) return vma->vm_flags & __VM_UFFD_FLAGS; } +static inline bool vma_can_userfault(struct vm_area_struct *vma, + unsigned long vm_flags) +{ + if ((vm_flags & VM_UFFD_MINOR) && + (!is_vm_hugetlb_page(vma) && !vma_is_shmem(vma))) + return false; +#ifndef CONFIG_PTE_MARKER_UFFD_WP + /* + * If user requested uffd-wp but not enabled pte markers for + * uffd-wp, then shmem & hugetlbfs are not supported but only + * anonymous. + */ + if ((vm_flags & VM_UFFD_WP) && !vma_is_anonymous(vma)) + return false; +#endif + return vma_is_anonymous(vma) || is_vm_hugetlb_page(vma) || + vma_is_shmem(vma); +} + extern int dup_userfaultfd(struct vm_area_struct *, struct list_head *); extern void dup_userfaultfd_complete(struct list_head *); @@ -139,9 +175,8 @@ extern bool userfaultfd_remove(struct vm_area_struct *vma, unsigned long start, unsigned long end); -extern int userfaultfd_unmap_prep(struct vm_area_struct *vma, - unsigned long start, unsigned long end, - struct list_head *uf); +extern int userfaultfd_unmap_prep(struct mm_struct *mm, unsigned long start, + unsigned long end, struct list_head *uf); extern void userfaultfd_unmap_complete(struct mm_struct *mm, struct list_head *uf); @@ -222,7 +257,7 @@ static inline bool userfaultfd_remove(struct vm_area_struct *vma, return true; } -static inline int userfaultfd_unmap_prep(struct vm_area_struct *vma, +static inline int userfaultfd_unmap_prep(struct mm_struct *mm, unsigned long start, unsigned long end, struct list_head *uf) { @@ -234,6 +269,56 @@ static inline void userfaultfd_unmap_complete(struct mm_struct *mm, { } +static inline bool uffd_disable_fault_around(struct vm_area_struct *vma) +{ + return false; +} + #endif /* CONFIG_USERFAULTFD */ +static inline bool pte_marker_entry_uffd_wp(swp_entry_t entry) +{ +#ifdef CONFIG_PTE_MARKER_UFFD_WP + return is_pte_marker_entry(entry) && + (pte_marker_get(entry) & PTE_MARKER_UFFD_WP); +#else + return false; +#endif +} + +static inline bool pte_marker_uffd_wp(pte_t pte) +{ +#ifdef CONFIG_PTE_MARKER_UFFD_WP + swp_entry_t entry; + + if (!is_swap_pte(pte)) + return false; + + entry = pte_to_swp_entry(pte); + + return pte_marker_entry_uffd_wp(entry); +#else + return false; +#endif +} + +/* + * Returns true if this is a swap pte and was uffd-wp wr-protected in either + * forms (pte marker or a normal swap pte), false otherwise. + */ +static inline bool pte_swp_uffd_wp_any(pte_t pte) +{ +#ifdef CONFIG_PTE_MARKER_UFFD_WP + if (!is_swap_pte(pte)) + return false; + + if (pte_swp_uffd_wp(pte)) + return true; + + if (pte_marker_uffd_wp(pte)) + return true; +#endif + return false; +} + #endif /* _LINUX_USERFAULTFD_K_H */ diff --git a/include/linux/utsname.h b/include/linux/utsname.h index 2b1737c9b244..bf7613ba412b 100644 --- a/include/linux/utsname.h +++ b/include/linux/utsname.h @@ -10,6 +10,7 @@ #include <uapi/linux/utsname.h> enum uts_proc { + UTS_PROC_ARCH, UTS_PROC_OSTYPE, UTS_PROC_OSRELEASE, UTS_PROC_VERSION, diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index c3011ccda430..6d0f5e4e82c2 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -64,10 +64,15 @@ struct vdpa_mgmt_dev; * struct vdpa_device - representation of a vDPA device * @dev: underlying device * @dma_dev: the actual device that is performing DMA + * @driver_override: driver name to force a match; do not set directly, + * because core frees it; use driver_set_override() to + * set or clear it. * @config: the configuration ops for this device. - * @cf_mutex: Protects get and set access to configuration layout. + * @cf_lock: Protects get and set access to configuration layout. * @index: device index * @features_valid: were features initialized? for legacy guests + * @ngroups: the number of virtqueue groups + * @nas: the number of address spaces * @use_va: indicate whether virtual address must be used by this device * @nvqs: maximum number of supported virtqueues * @mdev: management device pointer; caller must setup when registering device as part @@ -76,13 +81,16 @@ struct vdpa_mgmt_dev; struct vdpa_device { struct device dev; struct device *dma_dev; + const char *driver_override; const struct vdpa_config_ops *config; - struct mutex cf_mutex; /* Protects get/set config */ + struct rw_semaphore cf_lock; /* Protects get/set config */ unsigned int index; bool features_valid; bool use_va; - int nvqs; + u32 nvqs; struct vdpa_mgmt_dev *mdev; + unsigned int ngroups; + unsigned int nas; }; /** @@ -96,9 +104,11 @@ struct vdpa_iova_range { }; struct vdpa_dev_set_config { + u64 device_features; struct { u8 mac[ETH_ALEN]; u16 mtu; + u16 max_vq_pairs; } net; u64 mask; }; @@ -155,7 +165,7 @@ struct vdpa_map_file { * @vdev: vdpa device * @idx: virtqueue index * @state: pointer to returned state (last_avail_idx) - * @get_vq_notification: Get the notification area for a virtqueue + * @get_vq_notification: Get the notification area for a virtqueue (optional) * @vdev: vdpa device * @idx: virtqueue index * Returns the notifcation area @@ -169,14 +179,22 @@ struct vdpa_map_file { * for the device * @vdev: vdpa device * Returns virtqueue algin requirement - * @get_features: Get virtio features supported by the device + * @get_vq_group: Get the group id for a specific + * virtqueue (optional) + * @vdev: vdpa device + * @idx: virtqueue index + * Returns u32: group id for this virtqueue + * @get_device_features: Get virtio features supported by the device * @vdev: vdpa device * Returns the virtio features support by the * device - * @set_features: Set virtio features supported by the driver + * @set_driver_features: Set virtio features supported by the driver * @vdev: vdpa device * @features: feature support by the driver * Returns integer: success (0) or error (< 0) + * @get_driver_features: Get the virtio driver features in action + * @vdev: vdpa device + * Returns the virtio features accepted * @set_config_cb: Set the config interrupt callback * @vdev: vdpa device * @cb: virtio-vdev interrupt callback structure @@ -201,7 +219,11 @@ struct vdpa_map_file { * @reset: Reset device * @vdev: vdpa device * Returns integer: success (0) or error (< 0) - * @get_config_size: Get the size of the configuration space + * @suspend: Suspend or resume the device (optional) + * @vdev: vdpa device + * Returns integer: success (0) or error (< 0) + * @get_config_size: Get the size of the configuration space includes + * fields that are conditional on feature bits. * @vdev: vdpa device * Returns size_t: configuration size * @get_config: Read from device specific configuration space @@ -225,10 +247,17 @@ struct vdpa_map_file { * @vdev: vdpa device * Returns the iova range supported by * the device. + * @set_group_asid: Set address space identifier for a + * virtqueue group (optional) + * @vdev: vdpa device + * @group: virtqueue group + * @asid: address space id for this group + * Returns integer: success (0) or error (< 0) * @set_map: Set device memory mapping (optional) * Needed for device that using device * specific DMA translation (on-chip IOMMU) * @vdev: vdpa device + * @asid: address space identifier * @iotlb: vhost memory mapping to be * used by the vDPA * Returns integer: success (0) or error (< 0) @@ -237,6 +266,7 @@ struct vdpa_map_file { * specific DMA translation (on-chip IOMMU) * and preferring incremental map. * @vdev: vdpa device + * @asid: address space identifier * @iova: iova to be mapped * @size: size of the area * @pa: physical address for the map @@ -248,6 +278,7 @@ struct vdpa_map_file { * specific DMA translation (on-chip IOMMU) * and preferring incremental unmap. * @vdev: vdpa device + * @asid: address space identifier * @iova: iova to be unmapped * @size: size of the area * Returns integer: success (0) or error (< 0) @@ -269,6 +300,9 @@ struct vdpa_config_ops { const struct vdpa_vq_state *state); int (*get_vq_state)(struct vdpa_device *vdev, u16 idx, struct vdpa_vq_state *state); + int (*get_vendor_vq_stats)(struct vdpa_device *vdev, u16 idx, + struct sk_buff *msg, + struct netlink_ext_ack *extack); struct vdpa_notification_area (*get_vq_notification)(struct vdpa_device *vdev, u16 idx); /* vq irq is not expected to be changed once DRIVER_OK is set */ @@ -276,8 +310,10 @@ struct vdpa_config_ops { /* Device ops */ u32 (*get_vq_align)(struct vdpa_device *vdev); - u64 (*get_features)(struct vdpa_device *vdev); - int (*set_features)(struct vdpa_device *vdev, u64 features); + u32 (*get_vq_group)(struct vdpa_device *vdev, u16 idx); + u64 (*get_device_features)(struct vdpa_device *vdev); + int (*set_driver_features)(struct vdpa_device *vdev, u64 features); + u64 (*get_driver_features)(struct vdpa_device *vdev); void (*set_config_cb)(struct vdpa_device *vdev, struct vdpa_callback *cb); u16 (*get_vq_num_max)(struct vdpa_device *vdev); @@ -287,6 +323,7 @@ struct vdpa_config_ops { u8 (*get_status)(struct vdpa_device *vdev); void (*set_status)(struct vdpa_device *vdev, u8 status); int (*reset)(struct vdpa_device *vdev); + int (*suspend)(struct vdpa_device *vdev); size_t (*get_config_size)(struct vdpa_device *vdev); void (*get_config)(struct vdpa_device *vdev, unsigned int offset, void *buf, unsigned int len); @@ -296,10 +333,14 @@ struct vdpa_config_ops { struct vdpa_iova_range (*get_iova_range)(struct vdpa_device *vdev); /* DMA ops */ - int (*set_map)(struct vdpa_device *vdev, struct vhost_iotlb *iotlb); - int (*dma_map)(struct vdpa_device *vdev, u64 iova, u64 size, - u64 pa, u32 perm, void *opaque); - int (*dma_unmap)(struct vdpa_device *vdev, u64 iova, u64 size); + int (*set_map)(struct vdpa_device *vdev, unsigned int asid, + struct vhost_iotlb *iotlb); + int (*dma_map)(struct vdpa_device *vdev, unsigned int asid, + u64 iova, u64 size, u64 pa, u32 perm, void *opaque); + int (*dma_unmap)(struct vdpa_device *vdev, unsigned int asid, + u64 iova, u64 size); + int (*set_group_asid)(struct vdpa_device *vdev, unsigned int group, + unsigned int asid); /* Free device resources */ void (*free)(struct vdpa_device *vdev); @@ -307,6 +348,7 @@ struct vdpa_config_ops { struct vdpa_device *__vdpa_alloc_device(struct device *parent, const struct vdpa_config_ops *config, + unsigned int ngroups, unsigned int nas, size_t size, const char *name, bool use_va); @@ -317,23 +359,26 @@ struct vdpa_device *__vdpa_alloc_device(struct device *parent, * @member: the name of struct vdpa_device within the @dev_struct * @parent: the parent device * @config: the bus operations that is supported by this device + * @ngroups: the number of virtqueue groups supported by this device + * @nas: the number of address spaces * @name: name of the vdpa device * @use_va: indicate whether virtual address must be used by this device * * Return allocated data structure or ERR_PTR upon error */ -#define vdpa_alloc_device(dev_struct, member, parent, config, name, use_va) \ - container_of(__vdpa_alloc_device( \ - parent, config, \ - sizeof(dev_struct) + \ +#define vdpa_alloc_device(dev_struct, member, parent, config, ngroups, nas, \ + name, use_va) \ + container_of((__vdpa_alloc_device( \ + parent, config, ngroups, nas, \ + (sizeof(dev_struct) + \ BUILD_BUG_ON_ZERO(offsetof( \ - dev_struct, member)), name, use_va), \ + dev_struct, member))), name, use_va)), \ dev_struct, member) -int vdpa_register_device(struct vdpa_device *vdev, int nvqs); +int vdpa_register_device(struct vdpa_device *vdev, u32 nvqs); void vdpa_unregister_device(struct vdpa_device *vdev); -int _vdpa_register_device(struct vdpa_device *vdev, int nvqs); +int _vdpa_register_device(struct vdpa_device *vdev, u32 nvqs); void _vdpa_unregister_device(struct vdpa_device *vdev); /** @@ -385,23 +430,43 @@ static inline struct device *vdpa_get_dma_dev(struct vdpa_device *vdev) static inline int vdpa_reset(struct vdpa_device *vdev) { const struct vdpa_config_ops *ops = vdev->config; + int ret; + down_write(&vdev->cf_lock); vdev->features_valid = false; - return ops->reset(vdev); + ret = ops->reset(vdev); + up_write(&vdev->cf_lock); + return ret; } -static inline int vdpa_set_features(struct vdpa_device *vdev, u64 features) +static inline int vdpa_set_features_unlocked(struct vdpa_device *vdev, u64 features) { const struct vdpa_config_ops *ops = vdev->config; + int ret; vdev->features_valid = true; - return ops->set_features(vdev, features); + ret = ops->set_driver_features(vdev, features); + + return ret; +} + +static inline int vdpa_set_features(struct vdpa_device *vdev, u64 features) +{ + int ret; + + down_write(&vdev->cf_lock); + ret = vdpa_set_features_unlocked(vdev, features); + up_write(&vdev->cf_lock); + + return ret; } void vdpa_get_config(struct vdpa_device *vdev, unsigned int offset, void *buf, unsigned int len); void vdpa_set_config(struct vdpa_device *dev, unsigned int offset, const void *buf, unsigned int length); +void vdpa_set_status(struct vdpa_device *vdev, u8 status); + /** * struct vdpa_mgmtdev_ops - vdpa device ops * @dev_add: Add a vdpa device using alloc and register @@ -435,9 +500,11 @@ struct vdpa_mgmtdev_ops { struct vdpa_mgmt_dev { struct device *device; const struct vdpa_mgmtdev_ops *ops; - const struct virtio_device_id *id_table; + struct virtio_device_id *id_table; u64 config_attr_mask; struct list_head list; + u64 supported_features; + u32 max_supported_vqs; }; int vdpa_mgmtdev_register(struct vdpa_mgmt_dev *mdev); diff --git a/include/linux/verification.h b/include/linux/verification.h index a655923335ae..f34e50ebcf60 100644 --- a/include/linux/verification.h +++ b/include/linux/verification.h @@ -17,6 +17,14 @@ #define VERIFY_USE_SECONDARY_KEYRING ((struct key *)1UL) #define VERIFY_USE_PLATFORM_KEYRING ((struct key *)2UL) +static inline int system_keyring_id_check(u64 id) +{ + if (id > (unsigned long)VERIFY_USE_PLATFORM_KEYRING) + return -EINVAL; + + return 0; +} + /* * The use to which an asymmetric key is being put. */ diff --git a/include/linux/vermagic.h b/include/linux/vermagic.h index 329d63babaeb..a54046bf37e5 100644 --- a/include/linux/vermagic.h +++ b/include/linux/vermagic.h @@ -32,11 +32,11 @@ #else #define MODULE_VERMAGIC_MODVERSIONS "" #endif -#ifdef RANDSTRUCT_PLUGIN -#include <generated/randomize_layout_hash.h> -#define MODULE_RANDSTRUCT_PLUGIN "RANDSTRUCT_PLUGIN_" RANDSTRUCT_HASHED_SEED +#ifdef RANDSTRUCT +#include <generated/randstruct_hash.h> +#define MODULE_RANDSTRUCT "RANDSTRUCT_" RANDSTRUCT_HASHED_SEED #else -#define MODULE_RANDSTRUCT_PLUGIN +#define MODULE_RANDSTRUCT #endif #define VERMAGIC_STRING \ @@ -44,6 +44,6 @@ MODULE_VERMAGIC_SMP MODULE_VERMAGIC_PREEMPT \ MODULE_VERMAGIC_MODULE_UNLOAD MODULE_VERMAGIC_MODVERSIONS \ MODULE_ARCH_VERMAGIC \ - MODULE_RANDSTRUCT_PLUGIN + MODULE_RANDSTRUCT #endif /* _LINUX_VERMAGIC_H */ diff --git a/include/linux/vfio.h b/include/linux/vfio.h index 76191d7abed1..e7cebeb875dd 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -14,6 +14,9 @@ #include <linux/workqueue.h> #include <linux/poll.h> #include <uapi/linux/vfio.h> +#include <linux/iova_bitmap.h> + +struct kvm; /* * VFIO devices can be placed in a set, this allows all devices to share this @@ -30,20 +33,34 @@ struct vfio_device_set { struct vfio_device { struct device *dev; const struct vfio_device_ops *ops; + /* + * mig_ops/log_ops is a static property of the vfio_device which must + * be set prior to registering the vfio_device. + */ + const struct vfio_migration_ops *mig_ops; + const struct vfio_log_ops *log_ops; struct vfio_group *group; struct vfio_device_set *dev_set; struct list_head dev_set_list; + unsigned int migration_flags; + /* Driver must reference the kvm during open_device or never touch it */ + struct kvm *kvm; /* Members below here are private, not for driver use */ - refcount_t refcount; + unsigned int index; + struct device device; /* device.kref covers object life circle */ + refcount_t refcount; /* user count on registered device*/ unsigned int open_count; struct completion comp; struct list_head group_next; + struct list_head iommu_entry; }; /** * struct vfio_device_ops - VFIO bus driver device callbacks * + * @init: initialize private fields in device structure + * @release: Reclaim private fields in device structure * @open_device: Called when the first file descriptor is opened for this device * @close_device: Opposite of open_device * @read: Perform read(2) on device file descriptor @@ -55,9 +72,14 @@ struct vfio_device { * @match: Optional device name match callback (return: 0 for no-match, >0 for * match, -errno for abort (ex. match with insufficient or incorrect * additional args) + * @dma_unmap: Called when userspace unmaps IOVA from the container + * this device is attached to. + * @device_feature: Optional, fill in the VFIO_DEVICE_FEATURE ioctl */ struct vfio_device_ops { char *name; + int (*init)(struct vfio_device *vdev); + void (*release)(struct vfio_device *vdev); int (*open_device)(struct vfio_device *vdev); void (*close_device)(struct vfio_device *vdev); ssize_t (*read)(struct vfio_device *vdev, char __user *buf, @@ -69,72 +91,126 @@ struct vfio_device_ops { int (*mmap)(struct vfio_device *vdev, struct vm_area_struct *vma); void (*request)(struct vfio_device *vdev, unsigned int count); int (*match)(struct vfio_device *vdev, char *buf); + void (*dma_unmap)(struct vfio_device *vdev, u64 iova, u64 length); + int (*device_feature)(struct vfio_device *device, u32 flags, + void __user *arg, size_t argsz); +}; + +/** + * @migration_set_state: Optional callback to change the migration state for + * devices that support migration. It's mandatory for + * VFIO_DEVICE_FEATURE_MIGRATION migration support. + * The returned FD is used for data transfer according to the FSM + * definition. The driver is responsible to ensure that FD reaches end + * of stream or error whenever the migration FSM leaves a data transfer + * state or before close_device() returns. + * @migration_get_state: Optional callback to get the migration state for + * devices that support migration. It's mandatory for + * VFIO_DEVICE_FEATURE_MIGRATION migration support. + */ +struct vfio_migration_ops { + struct file *(*migration_set_state)( + struct vfio_device *device, + enum vfio_device_mig_state new_state); + int (*migration_get_state)(struct vfio_device *device, + enum vfio_device_mig_state *curr_state); +}; + +/** + * @log_start: Optional callback to ask the device start DMA logging. + * @log_stop: Optional callback to ask the device stop DMA logging. + * @log_read_and_clear: Optional callback to ask the device read + * and clear the dirty DMAs in some given range. + * + * The vfio core implementation of the DEVICE_FEATURE_DMA_LOGGING_ set + * of features does not track logging state relative to the device, + * therefore the device implementation of vfio_log_ops must handle + * arbitrary user requests. This includes rejecting subsequent calls + * to log_start without an intervening log_stop, as well as graceful + * handling of log_stop and log_read_and_clear from invalid states. + */ +struct vfio_log_ops { + int (*log_start)(struct vfio_device *device, + struct rb_root_cached *ranges, u32 nnodes, u64 *page_size); + int (*log_stop)(struct vfio_device *device); + int (*log_read_and_clear)(struct vfio_device *device, + unsigned long iova, unsigned long length, + struct iova_bitmap *dirty); }; -void vfio_init_group_dev(struct vfio_device *device, struct device *dev, - const struct vfio_device_ops *ops); -void vfio_uninit_group_dev(struct vfio_device *device); +/** + * vfio_check_feature - Validate user input for the VFIO_DEVICE_FEATURE ioctl + * @flags: Arg from the device_feature op + * @argsz: Arg from the device_feature op + * @supported_ops: Combination of VFIO_DEVICE_FEATURE_GET and SET the driver + * supports + * @minsz: Minimum data size the driver accepts + * + * For use in a driver's device_feature op. Checks that the inputs to the + * VFIO_DEVICE_FEATURE ioctl are correct for the driver's feature. Returns 1 if + * the driver should execute the get or set, otherwise the relevant + * value should be returned. + */ +static inline int vfio_check_feature(u32 flags, size_t argsz, u32 supported_ops, + size_t minsz) +{ + if ((flags & (VFIO_DEVICE_FEATURE_GET | VFIO_DEVICE_FEATURE_SET)) & + ~supported_ops) + return -EINVAL; + if (flags & VFIO_DEVICE_FEATURE_PROBE) + return 0; + /* Without PROBE one of GET or SET must be requested */ + if (!(flags & (VFIO_DEVICE_FEATURE_GET | VFIO_DEVICE_FEATURE_SET))) + return -EINVAL; + if (argsz < minsz) + return -EINVAL; + return 1; +} + +struct vfio_device *_vfio_alloc_device(size_t size, struct device *dev, + const struct vfio_device_ops *ops); +#define vfio_alloc_device(dev_struct, member, dev, ops) \ + container_of(_vfio_alloc_device(sizeof(struct dev_struct) + \ + BUILD_BUG_ON_ZERO(offsetof( \ + struct dev_struct, member)), \ + dev, ops), \ + struct dev_struct, member) + +int vfio_init_device(struct vfio_device *device, struct device *dev, + const struct vfio_device_ops *ops); +void vfio_free_device(struct vfio_device *device); +static inline void vfio_put_device(struct vfio_device *device) +{ + put_device(&device->device); +} + int vfio_register_group_dev(struct vfio_device *device); int vfio_register_emulated_iommu_dev(struct vfio_device *device); void vfio_unregister_group_dev(struct vfio_device *device); -extern struct vfio_device *vfio_device_get_from_dev(struct device *dev); -extern void vfio_device_put(struct vfio_device *device); int vfio_assign_device_set(struct vfio_device *device, void *set_id); +int vfio_mig_get_next_state(struct vfio_device *device, + enum vfio_device_mig_state cur_fsm, + enum vfio_device_mig_state new_fsm, + enum vfio_device_mig_state *next_fsm); + /* * External user API */ -extern struct vfio_group *vfio_group_get_external_user(struct file *filep); -extern void vfio_group_put_external_user(struct vfio_group *group); -extern struct vfio_group *vfio_group_get_external_user_from_dev(struct device - *dev); -extern bool vfio_external_group_match_file(struct vfio_group *group, - struct file *filep); -extern int vfio_external_user_iommu_id(struct vfio_group *group); -extern long vfio_external_check_extension(struct vfio_group *group, - unsigned long arg); +struct iommu_group *vfio_file_iommu_group(struct file *file); +bool vfio_file_is_group(struct file *file); +bool vfio_file_enforced_coherent(struct file *file); +void vfio_file_set_kvm(struct file *file, struct kvm *kvm); +bool vfio_file_has_dev(struct file *file, struct vfio_device *device); #define VFIO_PIN_PAGES_MAX_ENTRIES (PAGE_SIZE/sizeof(unsigned long)) -extern int vfio_pin_pages(struct device *dev, unsigned long *user_pfn, - int npage, int prot, unsigned long *phys_pfn); -extern int vfio_unpin_pages(struct device *dev, unsigned long *user_pfn, - int npage); - -extern int vfio_group_pin_pages(struct vfio_group *group, - unsigned long *user_iova_pfn, int npage, - int prot, unsigned long *phys_pfn); -extern int vfio_group_unpin_pages(struct vfio_group *group, - unsigned long *user_iova_pfn, int npage); - -extern int vfio_dma_rw(struct vfio_group *group, dma_addr_t user_iova, - void *data, size_t len, bool write); - -extern struct iommu_domain *vfio_group_iommu_domain(struct vfio_group *group); - -/* each type has independent events */ -enum vfio_notify_type { - VFIO_IOMMU_NOTIFY = 0, - VFIO_GROUP_NOTIFY = 1, -}; - -/* events for VFIO_IOMMU_NOTIFY */ -#define VFIO_IOMMU_NOTIFY_DMA_UNMAP BIT(0) - -/* events for VFIO_GROUP_NOTIFY */ -#define VFIO_GROUP_NOTIFY_SET_KVM BIT(0) - -extern int vfio_register_notifier(struct device *dev, - enum vfio_notify_type type, - unsigned long *required_events, - struct notifier_block *nb); -extern int vfio_unregister_notifier(struct device *dev, - enum vfio_notify_type type, - struct notifier_block *nb); - -struct kvm; -extern void vfio_group_set_kvm(struct vfio_group *group, struct kvm *kvm); +int vfio_pin_pages(struct vfio_device *device, dma_addr_t iova, + int npage, int prot, struct page **pages); +void vfio_unpin_pages(struct vfio_device *device, dma_addr_t iova, int npage); +int vfio_dma_rw(struct vfio_device *device, dma_addr_t iova, + void *data, size_t len, bool write); /* * Sub-module helpers @@ -143,25 +219,24 @@ struct vfio_info_cap { struct vfio_info_cap_header *buf; size_t size; }; -extern struct vfio_info_cap_header *vfio_info_cap_add( - struct vfio_info_cap *caps, size_t size, u16 id, u16 version); -extern void vfio_info_cap_shift(struct vfio_info_cap *caps, size_t offset); +struct vfio_info_cap_header *vfio_info_cap_add(struct vfio_info_cap *caps, + size_t size, u16 id, + u16 version); +void vfio_info_cap_shift(struct vfio_info_cap *caps, size_t offset); -extern int vfio_info_add_capability(struct vfio_info_cap *caps, - struct vfio_info_cap_header *cap, - size_t size); +int vfio_info_add_capability(struct vfio_info_cap *caps, + struct vfio_info_cap_header *cap, size_t size); -extern int vfio_set_irqs_validate_and_prepare(struct vfio_irq_set *hdr, - int num_irqs, int max_irq_type, - size_t *data_size); +int vfio_set_irqs_validate_and_prepare(struct vfio_irq_set *hdr, + int num_irqs, int max_irq_type, + size_t *data_size); struct pci_dev; #if IS_ENABLED(CONFIG_VFIO_SPAPR_EEH) -extern void vfio_spapr_pci_eeh_open(struct pci_dev *pdev); -extern void vfio_spapr_pci_eeh_release(struct pci_dev *pdev); -extern long vfio_spapr_iommu_eeh_ioctl(struct iommu_group *group, - unsigned int cmd, - unsigned long arg); +void vfio_spapr_pci_eeh_open(struct pci_dev *pdev); +void vfio_spapr_pci_eeh_release(struct pci_dev *pdev); +long vfio_spapr_iommu_eeh_ioctl(struct iommu_group *group, unsigned int cmd, + unsigned long arg); #else static inline void vfio_spapr_pci_eeh_open(struct pci_dev *pdev) { @@ -195,10 +270,9 @@ struct virqfd { struct virqfd **pvirqfd; }; -extern int vfio_virqfd_enable(void *opaque, - int (*handler)(void *, void *), - void (*thread)(void *, void *), - void *data, struct virqfd **pvirqfd, int fd); -extern void vfio_virqfd_disable(struct virqfd **pvirqfd); +int vfio_virqfd_enable(void *opaque, int (*handler)(void *, void *), + void (*thread)(void *, void *), void *data, + struct virqfd **pvirqfd, int fd); +void vfio_virqfd_disable(struct virqfd **pvirqfd); #endif /* VFIO_H */ diff --git a/include/linux/vfio_pci_core.h b/include/linux/vfio_pci_core.h index ef9a44b6cf5d..367fd79226a3 100644 --- a/include/linux/vfio_pci_core.h +++ b/include/linux/vfio_pci_core.h @@ -20,39 +20,10 @@ #define VFIO_PCI_CORE_H #define VFIO_PCI_OFFSET_SHIFT 40 - #define VFIO_PCI_OFFSET_TO_INDEX(off) (off >> VFIO_PCI_OFFSET_SHIFT) #define VFIO_PCI_INDEX_TO_OFFSET(index) ((u64)(index) << VFIO_PCI_OFFSET_SHIFT) #define VFIO_PCI_OFFSET_MASK (((u64)(1) << VFIO_PCI_OFFSET_SHIFT) - 1) -/* Special capability IDs predefined access */ -#define PCI_CAP_ID_INVALID 0xFF /* default raw access */ -#define PCI_CAP_ID_INVALID_VIRT 0xFE /* default virt access */ - -/* Cap maximum number of ioeventfds per device (arbitrary) */ -#define VFIO_PCI_IOEVENTFD_MAX 1000 - -struct vfio_pci_ioeventfd { - struct list_head next; - struct vfio_pci_core_device *vdev; - struct virqfd *virqfd; - void __iomem *addr; - uint64_t data; - loff_t pos; - int bar; - int count; - bool test_mem; -}; - -struct vfio_pci_irq_ctx { - struct eventfd_ctx *trigger; - struct virqfd *unmask; - struct virqfd *mask; - char *name; - bool masked; - struct irq_bypass_producer producer; -}; - struct vfio_pci_core_device; struct vfio_pci_region; @@ -78,23 +49,6 @@ struct vfio_pci_region { u32 flags; }; -struct vfio_pci_dummy_resource { - struct resource resource; - int index; - struct list_head res_next; -}; - -struct vfio_pci_vf_token { - struct mutex lock; - uuid_t uuid; - int users; -}; - -struct vfio_pci_mmap_vma { - struct vm_area_struct *vma; - struct list_head vma_next; -}; - struct vfio_pci_core_device { struct vfio_device vdev; struct pci_dev *pdev; @@ -124,102 +78,45 @@ struct vfio_pci_core_device { bool needs_reset; bool nointx; bool needs_pm_restore; + bool pm_intx_masked; + bool pm_runtime_engaged; struct pci_saved_state *pci_saved_state; struct pci_saved_state *pm_save; int ioeventfds_nr; struct eventfd_ctx *err_trigger; struct eventfd_ctx *req_trigger; + struct eventfd_ctx *pm_wake_eventfd_ctx; struct list_head dummy_resources_list; struct mutex ioeventfds_lock; struct list_head ioeventfds_list; struct vfio_pci_vf_token *vf_token; + struct list_head sriov_pfs_item; + struct vfio_pci_core_device *sriov_pf_core_dev; struct notifier_block nb; struct mutex vma_lock; struct list_head vma_list; struct rw_semaphore memory_lock; }; -#define is_intx(vdev) (vdev->irq_type == VFIO_PCI_INTX_IRQ_INDEX) -#define is_msi(vdev) (vdev->irq_type == VFIO_PCI_MSI_IRQ_INDEX) -#define is_msix(vdev) (vdev->irq_type == VFIO_PCI_MSIX_IRQ_INDEX) -#define is_irq_none(vdev) (!(is_intx(vdev) || is_msi(vdev) || is_msix(vdev))) -#define irq_is(vdev, type) (vdev->irq_type == type) - -extern void vfio_pci_intx_mask(struct vfio_pci_core_device *vdev); -extern void vfio_pci_intx_unmask(struct vfio_pci_core_device *vdev); - -extern int vfio_pci_set_irqs_ioctl(struct vfio_pci_core_device *vdev, - uint32_t flags, unsigned index, - unsigned start, unsigned count, void *data); - -extern ssize_t vfio_pci_config_rw(struct vfio_pci_core_device *vdev, - char __user *buf, size_t count, - loff_t *ppos, bool iswrite); - -extern ssize_t vfio_pci_bar_rw(struct vfio_pci_core_device *vdev, char __user *buf, - size_t count, loff_t *ppos, bool iswrite); - -extern ssize_t vfio_pci_vga_rw(struct vfio_pci_core_device *vdev, char __user *buf, - size_t count, loff_t *ppos, bool iswrite); - -extern long vfio_pci_ioeventfd(struct vfio_pci_core_device *vdev, loff_t offset, - uint64_t data, int count, int fd); - -extern int vfio_pci_init_perm_bits(void); -extern void vfio_pci_uninit_perm_bits(void); - -extern int vfio_config_init(struct vfio_pci_core_device *vdev); -extern void vfio_config_free(struct vfio_pci_core_device *vdev); - -extern int vfio_pci_register_dev_region(struct vfio_pci_core_device *vdev, - unsigned int type, unsigned int subtype, - const struct vfio_pci_regops *ops, - size_t size, u32 flags, void *data); - -extern int vfio_pci_set_power_state(struct vfio_pci_core_device *vdev, - pci_power_t state); - -extern bool __vfio_pci_memory_enabled(struct vfio_pci_core_device *vdev); -extern void vfio_pci_zap_and_down_write_memory_lock(struct vfio_pci_core_device - *vdev); -extern u16 vfio_pci_memory_lock_and_enable(struct vfio_pci_core_device *vdev); -extern void vfio_pci_memory_unlock_and_restore(struct vfio_pci_core_device *vdev, - u16 cmd); - -#ifdef CONFIG_VFIO_PCI_IGD -extern int vfio_pci_igd_init(struct vfio_pci_core_device *vdev); -#else -static inline int vfio_pci_igd_init(struct vfio_pci_core_device *vdev) -{ - return -ENODEV; -} -#endif - -#ifdef CONFIG_S390 -extern int vfio_pci_info_zdev_add_caps(struct vfio_pci_core_device *vdev, - struct vfio_info_cap *caps); -#else -static inline int vfio_pci_info_zdev_add_caps(struct vfio_pci_core_device *vdev, - struct vfio_info_cap *caps) -{ - return -ENODEV; -} -#endif - /* Will be exported for vfio pci drivers usage */ +int vfio_pci_core_register_dev_region(struct vfio_pci_core_device *vdev, + unsigned int type, unsigned int subtype, + const struct vfio_pci_regops *ops, + size_t size, u32 flags, void *data); void vfio_pci_core_set_params(bool nointxmask, bool is_disable_vga, bool is_disable_idle_d3); void vfio_pci_core_close_device(struct vfio_device *core_vdev); -void vfio_pci_core_init_device(struct vfio_pci_core_device *vdev, - struct pci_dev *pdev, - const struct vfio_device_ops *vfio_pci_ops); +int vfio_pci_core_init_dev(struct vfio_device *core_vdev); +void vfio_pci_core_release_dev(struct vfio_device *core_vdev); int vfio_pci_core_register_device(struct vfio_pci_core_device *vdev); -void vfio_pci_core_uninit_device(struct vfio_pci_core_device *vdev); void vfio_pci_core_unregister_device(struct vfio_pci_core_device *vdev); -int vfio_pci_core_sriov_configure(struct pci_dev *pdev, int nr_virtfn); extern const struct pci_error_handlers vfio_pci_core_err_handlers; +int vfio_pci_core_sriov_configure(struct vfio_pci_core_device *vdev, + int nr_virtfn); long vfio_pci_core_ioctl(struct vfio_device *core_vdev, unsigned int cmd, unsigned long arg); +int vfio_pci_core_ioctl_feature(struct vfio_device *device, u32 flags, + void __user *arg, size_t argsz); ssize_t vfio_pci_core_read(struct vfio_device *core_vdev, char __user *buf, size_t count, loff_t *ppos); ssize_t vfio_pci_core_write(struct vfio_device *core_vdev, const char __user *buf, @@ -230,10 +127,7 @@ int vfio_pci_core_match(struct vfio_device *core_vdev, char *buf); int vfio_pci_core_enable(struct vfio_pci_core_device *vdev); void vfio_pci_core_disable(struct vfio_pci_core_device *vdev); void vfio_pci_core_finish_enable(struct vfio_pci_core_device *vdev); - -static inline bool vfio_pci_is_vga(struct pci_dev *pdev) -{ - return (pdev->class >> 8) == PCI_CLASS_DISPLAY_VGA; -} +pci_ers_result_t vfio_pci_core_aer_err_detected(struct pci_dev *pdev, + pci_channel_state_t state); #endif /* VFIO_PCI_CORE_H */ diff --git a/include/linux/vhost_iotlb.h b/include/linux/vhost_iotlb.h index 2d0e2f52f938..e79a40838998 100644 --- a/include/linux/vhost_iotlb.h +++ b/include/linux/vhost_iotlb.h @@ -36,6 +36,8 @@ int vhost_iotlb_add_range(struct vhost_iotlb *iotlb, u64 start, u64 last, u64 addr, unsigned int perm); void vhost_iotlb_del_range(struct vhost_iotlb *iotlb, u64 start, u64 last); +void vhost_iotlb_init(struct vhost_iotlb *iotlb, unsigned int limit, + unsigned int flags); struct vhost_iotlb *vhost_iotlb_alloc(unsigned int limit, unsigned int flags); void vhost_iotlb_free(struct vhost_iotlb *iotlb); void vhost_iotlb_reset(struct vhost_iotlb *iotlb); diff --git a/include/linux/virtio.h b/include/linux/virtio.h index 41edbc01ffa4..dcab9c7e8784 100644 --- a/include/linux/virtio.h +++ b/include/linux/virtio.h @@ -11,7 +11,7 @@ #include <linux/gfp.h> /** - * virtqueue - a queue to register buffers for sending or receiving. + * struct virtqueue - a queue to register buffers for sending or receiving. * @list: the chain of virtqueues for this device * @callback: the function to call when buffers are consumed (can be NULL). * @name: the name of this virtqueue (mainly for debugging) @@ -19,6 +19,8 @@ * @priv: a pointer for the virtqueue implementation to use. * @index: the zero-based ordinal number for this queue. * @num_free: number of elements we expect to be able to fit. + * @num_max: the maximum number of elements supported by the device. + * @reset: vq is in reset state or not. * * A note on @num_free: with indirect buffers, each buffer needs one * element in the queue, otherwise a buffer will need one element per @@ -31,7 +33,9 @@ struct virtqueue { struct virtio_device *vdev; unsigned int index; unsigned int num_free; + unsigned int num_max; void *priv; + bool reset; }; int virtqueue_add_outbuf(struct virtqueue *vq, @@ -89,8 +93,11 @@ dma_addr_t virtqueue_get_desc_addr(struct virtqueue *vq); dma_addr_t virtqueue_get_avail_addr(struct virtqueue *vq); dma_addr_t virtqueue_get_used_addr(struct virtqueue *vq); +int virtqueue_resize(struct virtqueue *vq, u32 num, + void (*recycle)(struct virtqueue *vq, void *buf)); + /** - * virtio_device - representation of a device using virtio + * struct virtio_device - representation of a device using virtio * @index: unique position on the virtio bus * @failed: saved value for VIRTIO_CONFIG_S_FAILED bit (for restore) * @config_enabled: configuration change reporting enabled @@ -131,13 +138,17 @@ void unregister_virtio_device(struct virtio_device *dev); bool is_virtio_device(struct device *dev); void virtio_break_device(struct virtio_device *dev); +void __virtio_unbreak_device(struct virtio_device *dev); + +void __virtqueue_break(struct virtqueue *_vq); +void __virtqueue_unbreak(struct virtqueue *_vq); void virtio_config_changed(struct virtio_device *dev); -int virtio_finalize_features(struct virtio_device *dev); #ifdef CONFIG_PM_SLEEP int virtio_device_freeze(struct virtio_device *dev); int virtio_device_restore(struct virtio_device *dev); #endif +void virtio_reset_device(struct virtio_device *dev); size_t virtio_max_dma_size(struct virtio_device *vdev); @@ -145,7 +156,7 @@ size_t virtio_max_dma_size(struct virtio_device *vdev); list_for_each_entry(vq, &vdev->vqs, list) /** - * virtio_driver - operations for a virtio I/O driver + * struct virtio_driver - operations for a virtio I/O driver * @driver: underlying device driver (populate name and owner). * @id_table: the ids serviced by this driver. * @feature_table: an array of feature numbers supported by this driver. diff --git a/include/linux/virtio_anchor.h b/include/linux/virtio_anchor.h new file mode 100644 index 000000000000..432e6c00b3ca --- /dev/null +++ b/include/linux/virtio_anchor.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_VIRTIO_ANCHOR_H +#define _LINUX_VIRTIO_ANCHOR_H + +#ifdef CONFIG_VIRTIO_ANCHOR +struct virtio_device; + +bool virtio_require_restricted_mem_acc(struct virtio_device *dev); +extern bool (*virtio_check_mem_acc_cb)(struct virtio_device *dev); + +static inline void virtio_set_mem_acc_cb(bool (*func)(struct virtio_device *)) +{ + virtio_check_mem_acc_cb = func; +} +#else +#define virtio_set_mem_acc_cb(func) do { } while (0) +#endif + +#endif /* _LINUX_VIRTIO_ANCHOR_H */ diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h index 4d107ad31149..4b517649cfe8 100644 --- a/include/linux/virtio_config.h +++ b/include/linux/virtio_config.h @@ -23,8 +23,6 @@ struct virtio_shm_region { * any of @get/@set, @get_status/@set_status, or @get_features/ * @finalize_features are NOT safe to be called from an atomic * context. - * @enable_cbs: enable the callbacks - * vdev: the virtio_device * @get: read the value of a configuration field * vdev: the virtio_device * offset: the offset of the configuration field @@ -59,13 +57,19 @@ struct virtio_shm_region { * include a NULL entry for vqs unused by driver * Returns 0 on success or error status * @del_vqs: free virtqueues found by find_vqs(). + * @synchronize_cbs: synchronize with the virtqueue callbacks (optional) + * The function guarantees that all memory operations on the + * queue before it are visible to the vring_interrupt() that is + * called after it. + * vdev: the virtio_device * @get_features: get the array of feature bits for this device. * vdev: the virtio_device * Returns the first 64 feature bits (all we currently need). * @finalize_features: confirm what device features we'll be using. * vdev: the virtio_device - * This gives the final feature bits for the device: it can change + * This sends the driver feature bits to the device: it can change * the dev->feature bits if it wants. + * Note: despite the name this can be called any number of times. * Returns 0 on success or error status * @bus_name: return the bus name associated with the device (optional) * vdev: the virtio_device @@ -74,10 +78,21 @@ struct virtio_shm_region { * @set_vq_affinity: set the affinity for a virtqueue (optional). * @get_vq_affinity: get the affinity for a virtqueue (optional). * @get_shm_region: get a shared memory region based on the index. + * @disable_vq_and_reset: reset a queue individually (optional). + * vq: the virtqueue + * Returns 0 on success or error status + * disable_vq_and_reset will guarantee that the callbacks are disabled and + * synchronized. + * Except for the callback, the caller should guarantee that the vring is + * not accessed by any functions of virtqueue. + * @enable_vq_after_reset: enable a reset queue + * vq: the virtqueue + * Returns 0 on success or error status + * If disable_vq_and_reset is set, then enable_vq_after_reset must also be + * set. */ typedef void vq_callback_t(struct virtqueue *); struct virtio_config_ops { - void (*enable_cbs)(struct virtio_device *vdev); void (*get)(struct virtio_device *vdev, unsigned offset, void *buf, unsigned len); void (*set)(struct virtio_device *vdev, unsigned offset, @@ -91,6 +106,7 @@ struct virtio_config_ops { const char * const names[], const bool *ctx, struct irq_affinity *desc); void (*del_vqs)(struct virtio_device *); + void (*synchronize_cbs)(struct virtio_device *); u64 (*get_features)(struct virtio_device *vdev); int (*finalize_features)(struct virtio_device *vdev); const char *(*bus_name)(struct virtio_device *vdev); @@ -100,6 +116,8 @@ struct virtio_config_ops { int index); bool (*get_shm_region)(struct virtio_device *vdev, struct virtio_shm_region *region, u8 id); + int (*disable_vq_and_reset)(struct virtqueue *vq); + int (*enable_vq_after_reset)(struct virtqueue *vq); }; /* If driver didn't advertise the feature, it will never appear. */ @@ -220,8 +238,27 @@ int virtio_find_vqs_ctx(struct virtio_device *vdev, unsigned nvqs, } /** + * virtio_synchronize_cbs - synchronize with virtqueue callbacks + * @dev: the virtio device + */ +static inline +void virtio_synchronize_cbs(struct virtio_device *dev) +{ + if (dev->config->synchronize_cbs) { + dev->config->synchronize_cbs(dev); + } else { + /* + * A best effort fallback to synchronize with + * interrupts, preemption and softirq disabled + * regions. See comment above synchronize_rcu(). + */ + synchronize_rcu(); + } +} + +/** * virtio_device_ready - enable vq use in probe function - * @vdev: the device + * @dev: the virtio device * * Driver must call this to use vqs in the probe function. * @@ -232,10 +269,29 @@ void virtio_device_ready(struct virtio_device *dev) { unsigned status = dev->config->get_status(dev); - if (dev->config->enable_cbs) - dev->config->enable_cbs(dev); + WARN_ON(status & VIRTIO_CONFIG_S_DRIVER_OK); - BUG_ON(status & VIRTIO_CONFIG_S_DRIVER_OK); +#ifdef CONFIG_VIRTIO_HARDEN_NOTIFICATION + /* + * The virtio_synchronize_cbs() makes sure vring_interrupt() + * will see the driver specific setup if it sees vq->broken + * as false (even if the notifications come before DRIVER_OK). + */ + virtio_synchronize_cbs(dev); + __virtio_unbreak_device(dev); +#endif + /* + * The transport should ensure the visibility of vq->broken + * before setting DRIVER_OK. See the comments for the transport + * specific set_status() method. + * + * A well behaved device will only notify a virtqueue after + * DRIVER_OK, this means the device should "see" the coherenct + * memory write that set vq->broken as false which is done by + * the driver when it sees DRIVER_OK, then the following + * driver's vring_interrupt() will see vq->broken as false so + * we won't lose any notification. + */ dev->config->set_status(dev, status | VIRTIO_CONFIG_S_DRIVER_OK); } @@ -250,7 +306,7 @@ const char *virtio_bus_name(struct virtio_device *vdev) /** * virtqueue_set_affinity - setting affinity for a virtqueue * @vq: the virtqueue - * @cpu: the cpu no. + * @cpu_mask: the cpu mask * * Pay attention the function are best-effort: the affinity hint may not be set * due to config support, irq type and sharing. @@ -564,13 +620,4 @@ static inline void virtio_cwrite64(struct virtio_device *vdev, _r; \ }) -#ifdef CONFIG_ARCH_HAS_RESTRICTED_VIRTIO_MEMORY_ACCESS -int arch_has_restricted_virtio_memory_access(void); -#else -static inline int arch_has_restricted_virtio_memory_access(void) -{ - return 0; -} -#endif /* CONFIG_ARCH_HAS_RESTRICTED_VIRTIO_MEMORY_ACCESS */ - #endif /* _LINUX_VIRTIO_CONFIG_H */ diff --git a/include/linux/virtio_pci_legacy.h b/include/linux/virtio_pci_legacy.h index e5d665faf00e..a8dc757d0367 100644 --- a/include/linux/virtio_pci_legacy.h +++ b/include/linux/virtio_pci_legacy.h @@ -32,8 +32,6 @@ void vp_legacy_set_queue_address(struct virtio_pci_legacy_device *ldev, u16 index, u32 queue_pfn); bool vp_legacy_get_queue_enable(struct virtio_pci_legacy_device *ldev, u16 idx); -void vp_legacy_set_queue_size(struct virtio_pci_legacy_device *ldev, - u16 idx, u16 size); u16 vp_legacy_get_queue_size(struct virtio_pci_legacy_device *ldev, u16 idx); int vp_legacy_probe(struct virtio_pci_legacy_device *ldev); diff --git a/include/linux/virtio_pci_modern.h b/include/linux/virtio_pci_modern.h index eb2bd9b4077d..c4eeb79b0139 100644 --- a/include/linux/virtio_pci_modern.h +++ b/include/linux/virtio_pci_modern.h @@ -5,6 +5,13 @@ #include <linux/pci.h> #include <linux/virtio_pci.h> +struct virtio_pci_modern_common_cfg { + struct virtio_pci_common_cfg cfg; + + __le16 queue_notify_data; /* read-write */ + __le16 queue_reset; /* read-write */ +}; + struct virtio_pci_modern_device { struct pci_dev *pci_dev; @@ -106,4 +113,6 @@ void __iomem * vp_modern_map_vq_notify(struct virtio_pci_modern_device *mdev, u16 index, resource_size_t *pa); int vp_modern_probe(struct virtio_pci_modern_device *mdev); void vp_modern_remove(struct virtio_pci_modern_device *mdev); +int vp_modern_get_queue_reset(struct virtio_pci_modern_device *mdev, u16 index); +void vp_modern_set_queue_reset(struct virtio_pci_modern_device *mdev, u16 index); #endif diff --git a/include/linux/virtio_ring.h b/include/linux/virtio_ring.h index b485b13fa50b..8b8af1a38991 100644 --- a/include/linux/virtio_ring.h +++ b/include/linux/virtio_ring.h @@ -76,16 +76,6 @@ struct virtqueue *vring_create_virtqueue(unsigned int index, void (*callback)(struct virtqueue *vq), const char *name); -/* Creates a virtqueue with a custom layout. */ -struct virtqueue *__vring_new_virtqueue(unsigned int index, - struct vring vring, - struct virtio_device *vdev, - bool weak_barriers, - bool ctx, - bool (*notify)(struct virtqueue *), - void (*callback)(struct virtqueue *), - const char *name); - /* * Creates a virtqueue with a standard layout but a caller-allocated * ring. diff --git a/include/linux/visorbus.h b/include/linux/visorbus.h deleted file mode 100644 index 0d8bd6769b13..000000000000 --- a/include/linux/visorbus.h +++ /dev/null @@ -1,344 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0+ -/* - * Copyright (C) 2010 - 2013 UNISYS CORPORATION - * All rights reserved. - */ - -/* - * This header file is to be included by other kernel mode components that - * implement a particular kind of visor_device. Each of these other kernel - * mode components is called a visor device driver. Refer to visortemplate - * for a minimal sample visor device driver. - * - * There should be nothing in this file that is private to the visorbus - * bus implementation itself. - */ - -#ifndef __VISORBUS_H__ -#define __VISORBUS_H__ - -#include <linux/device.h> - -#define VISOR_CHANNEL_SIGNATURE ('L' << 24 | 'N' << 16 | 'C' << 8 | 'E') - -/* - * enum channel_serverstate - * @CHANNELSRV_UNINITIALIZED: Channel is in an undefined state. - * @CHANNELSRV_READY: Channel has been initialized by server. - */ -enum channel_serverstate { - CHANNELSRV_UNINITIALIZED = 0, - CHANNELSRV_READY = 1 -}; - -/* - * enum channel_clientstate - * @CHANNELCLI_DETACHED: - * @CHANNELCLI_DISABLED: Client can see channel but is NOT allowed to use it - * unless given TBD* explicit request - * (should actually be < DETACHED). - * @CHANNELCLI_ATTACHING: Legacy EFI client request for EFI server to attach. - * @CHANNELCLI_ATTACHED: Idle, but client may want to use channel any time. - * @CHANNELCLI_BUSY: Client either wants to use or is using channel. - * @CHANNELCLI_OWNED: "No worries" state - client can access channel - * anytime. - */ -enum channel_clientstate { - CHANNELCLI_DETACHED = 0, - CHANNELCLI_DISABLED = 1, - CHANNELCLI_ATTACHING = 2, - CHANNELCLI_ATTACHED = 3, - CHANNELCLI_BUSY = 4, - CHANNELCLI_OWNED = 5 -}; - -/* - * Values for VISOR_CHANNEL_PROTOCOL.Features: This define exists so that - * a guest can look at the FeatureFlags in the io channel, and configure the - * driver to use interrupts or not based on this setting. All feature bits for - * all channels should be defined here. The io channel feature bits are defined - * below. - */ -#define VISOR_DRIVER_ENABLES_INTS (0x1ULL << 1) -#define VISOR_CHANNEL_IS_POLLING (0x1ULL << 3) -#define VISOR_IOVM_OK_DRIVER_DISABLING_INTS (0x1ULL << 4) -#define VISOR_DRIVER_DISABLES_INTS (0x1ULL << 5) -#define VISOR_DRIVER_ENHANCED_RCVBUF_CHECKING (0x1ULL << 6) - -/* - * struct channel_header - Common Channel Header - * @signature: Signature. - * @legacy_state: DEPRECATED - being replaced by. - * @header_size: sizeof(struct channel_header). - * @size: Total size of this channel in bytes. - * @features: Flags to modify behavior. - * @chtype: Channel type: data, bus, control, etc.. - * @partition_handle: ID of guest partition. - * @handle: Device number of this channel in client. - * @ch_space_offset: Offset in bytes to channel specific area. - * @version_id: Struct channel_header Version ID. - * @partition_index: Index of guest partition. - * @zone_uuid: Guid of Channel's zone. - * @cli_str_offset: Offset from channel header to null-terminated - * ClientString (0 if ClientString not present). - * @cli_state_boot: CHANNEL_CLIENTSTATE of pre-boot EFI client of this - * channel. - * @cmd_state_cli: CHANNEL_COMMANDSTATE (overloaded in Windows drivers, see - * ServerStateUp, ServerStateDown, etc). - * @cli_state_os: CHANNEL_CLIENTSTATE of Guest OS client of this channel. - * @ch_characteristic: CHANNEL_CHARACTERISTIC_<xxx>. - * @cmd_state_srv: CHANNEL_COMMANDSTATE (overloaded in Windows drivers, see - * ServerStateUp, ServerStateDown, etc). - * @srv_state: CHANNEL_SERVERSTATE. - * @cli_error_boot: Bits to indicate err states for boot clients, so err - * messages can be throttled. - * @cli_error_os: Bits to indicate err states for OS clients, so err - * messages can be throttled. - * @filler: Pad out to 128 byte cacheline. - * @recover_channel: Please add all new single-byte values below here. - */ -struct channel_header { - u64 signature; - u32 legacy_state; - /* SrvState, CliStateBoot, and CliStateOS below */ - u32 header_size; - u64 size; - u64 features; - guid_t chtype; - u64 partition_handle; - u64 handle; - u64 ch_space_offset; - u32 version_id; - u32 partition_index; - guid_t zone_guid; - u32 cli_str_offset; - u32 cli_state_boot; - u32 cmd_state_cli; - u32 cli_state_os; - u32 ch_characteristic; - u32 cmd_state_srv; - u32 srv_state; - u8 cli_error_boot; - u8 cli_error_os; - u8 filler[1]; - u8 recover_channel; -} __packed; - -#define VISOR_CHANNEL_ENABLE_INTS (0x1ULL << 0) - -/* - * struct signal_queue_header - Subheader for the Signal Type variation of the - * Common Channel. - * @version: SIGNAL_QUEUE_HEADER Version ID. - * @chtype: Queue type: storage, network. - * @size: Total size of this queue in bytes. - * @sig_base_offset: Offset to signal queue area. - * @features: Flags to modify behavior. - * @num_sent: Total # of signals placed in this queue. - * @num_overflows: Total # of inserts failed due to full queue. - * @signal_size: Total size of a signal for this queue. - * @max_slots: Max # of slots in queue, 1 slot is always empty. - * @max_signals: Max # of signals in queue (MaxSignalSlots-1). - * @head: Queue head signal #. - * @num_received: Total # of signals removed from this queue. - * @tail: Queue tail signal. - * @reserved1: Reserved field. - * @reserved2: Reserved field. - * @client_queue: - * @num_irq_received: Total # of Interrupts received. This is incremented by the - * ISR in the guest windows driver. - * @num_empty: Number of times that visor_signal_remove is called and - * returned Empty Status. - * @errorflags: Error bits set during SignalReinit to denote trouble with - * client's fields. - * @filler: Pad out to 64 byte cacheline. - */ -struct signal_queue_header { - /* 1st cache line */ - u32 version; - u32 chtype; - u64 size; - u64 sig_base_offset; - u64 features; - u64 num_sent; - u64 num_overflows; - u32 signal_size; - u32 max_slots; - u32 max_signals; - u32 head; - /* 2nd cache line */ - u64 num_received; - u32 tail; - u32 reserved1; - u64 reserved2; - u64 client_queue; - u64 num_irq_received; - u64 num_empty; - u32 errorflags; - u8 filler[12]; -} __packed; - -/* VISORCHANNEL Guids */ -/* {414815ed-c58c-11da-95a9-00e08161165f} */ -#define VISOR_VHBA_CHANNEL_GUID \ - GUID_INIT(0x414815ed, 0xc58c, 0x11da, \ - 0x95, 0xa9, 0x0, 0xe0, 0x81, 0x61, 0x16, 0x5f) -#define VISOR_VHBA_CHANNEL_GUID_STR \ - "414815ed-c58c-11da-95a9-00e08161165f" -struct visorchipset_state { - u32 created:1; - u32 attached:1; - u32 configured:1; - u32 running:1; - /* Remaining bits in this 32-bit word are reserved. */ -}; - -/** - * struct visor_device - A device type for things "plugged" into the visorbus - * bus - * @visorchannel: Points to the channel that the device is - * associated with. - * @channel_type_guid: Identifies the channel type to the bus driver. - * @device: Device struct meant for use by the bus driver - * only. - * @list_all: Used by the bus driver to enumerate devices. - * @timer: Timer fired periodically to do interrupt-type - * activity. - * @being_removed: Indicates that the device is being removed from - * the bus. Private bus driver use only. - * @visordriver_callback_lock: Used by the bus driver to lock when adding and - * removing devices. - * @pausing: Indicates that a change towards a paused state. - * is in progress. Only modified by the bus driver. - * @resuming: Indicates that a change towards a running state - * is in progress. Only modified by the bus driver. - * @chipset_bus_no: Private field used by the bus driver. - * @chipset_dev_no: Private field used the bus driver. - * @state: Used to indicate the current state of the - * device. - * @inst: Unique GUID for this instance of the device. - * @name: Name of the device. - * @pending_msg_hdr: For private use by bus driver to respond to - * hypervisor requests. - * @vbus_hdr_info: A pointer to header info. Private use by bus - * driver. - * @partition_guid: Indicates client partion id. This should be the - * same across all visor_devices in the current - * guest. Private use by bus driver only. - */ -struct visor_device { - struct visorchannel *visorchannel; - guid_t channel_type_guid; - /* These fields are for private use by the bus driver only. */ - struct device device; - struct list_head list_all; - struct timer_list timer; - bool timer_active; - bool being_removed; - struct mutex visordriver_callback_lock; /* synchronize probe/remove */ - bool pausing; - bool resuming; - u32 chipset_bus_no; - u32 chipset_dev_no; - struct visorchipset_state state; - guid_t inst; - u8 *name; - struct controlvm_message_header *pending_msg_hdr; - void *vbus_hdr_info; - guid_t partition_guid; - struct dentry *debugfs_dir; - struct dentry *debugfs_bus_info; -}; - -#define to_visor_device(x) container_of(x, struct visor_device, device) - -typedef void (*visorbus_state_complete_func) (struct visor_device *dev, - int status); - -/* - * This struct describes a specific visor channel, by providing its GUID, name, - * and sizes. - */ -struct visor_channeltype_descriptor { - const guid_t guid; - const char *name; - u64 min_bytes; - u32 version; -}; - -/** - * struct visor_driver - Information provided by each visor driver when it - * registers with the visorbus driver - * @name: Name of the visor driver. - * @owner: The module owner. - * @channel_types: Types of channels handled by this driver, ending with - * a zero GUID. Our specialized BUS.match() method knows - * about this list, and uses it to determine whether this - * driver will in fact handle a new device that it has - * detected. - * @probe: Called when a new device comes online, by our probe() - * function specified by driver.probe() (triggered - * ultimately by some call to driver_register(), - * bus_add_driver(), or driver_attach()). - * @remove: Called when a new device is removed, by our remove() - * function specified by driver.remove() (triggered - * ultimately by some call to device_release_driver()). - * @channel_interrupt: Called periodically, whenever there is a possiblity - * that "something interesting" may have happened to the - * channel. - * @pause: Called to initiate a change of the device's state. If - * the return valu`e is < 0, there was an error and the - * state transition will NOT occur. If the return value - * is >= 0, then the state transition was INITIATED - * successfully, and complete_func() will be called (or - * was just called) with the final status when either the - * state transition fails or completes successfully. - * @resume: Behaves similar to pause. - * @driver: Private reference to the device driver. For use by bus - * driver only. - */ -struct visor_driver { - const char *name; - struct module *owner; - struct visor_channeltype_descriptor *channel_types; - int (*probe)(struct visor_device *dev); - void (*remove)(struct visor_device *dev); - void (*channel_interrupt)(struct visor_device *dev); - int (*pause)(struct visor_device *dev, - visorbus_state_complete_func complete_func); - int (*resume)(struct visor_device *dev, - visorbus_state_complete_func complete_func); - - /* These fields are for private use by the bus driver only. */ - struct device_driver driver; -}; - -#define to_visor_driver(x) (container_of(x, struct visor_driver, driver)) - -int visor_check_channel(struct channel_header *ch, struct device *dev, - const guid_t *expected_uuid, char *chname, - u64 expected_min_bytes, u32 expected_version, - u64 expected_signature); - -int visorbus_register_visor_driver(struct visor_driver *drv); -void visorbus_unregister_visor_driver(struct visor_driver *drv); -int visorbus_read_channel(struct visor_device *dev, - unsigned long offset, void *dest, - unsigned long nbytes); -int visorbus_write_channel(struct visor_device *dev, - unsigned long offset, void *src, - unsigned long nbytes); -int visorbus_enable_channel_interrupts(struct visor_device *dev); -void visorbus_disable_channel_interrupts(struct visor_device *dev); - -int visorchannel_signalremove(struct visorchannel *channel, u32 queue, - void *msg); -int visorchannel_signalinsert(struct visorchannel *channel, u32 queue, - void *msg); -bool visorchannel_signalempty(struct visorchannel *channel, u32 queue); -const guid_t *visorchannel_get_guid(struct visorchannel *channel); - -#define BUS_ROOT_DEVICE UINT_MAX -struct visor_device *visorbus_get_device_by_id(u32 bus_no, u32 dev_no, - struct visor_device *from); -#endif diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index a185cc75ff52..3518dba1e02f 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -20,12 +20,19 @@ #define HIGHMEM_ZONE(xx) #endif -#define FOR_ALL_ZONES(xx) DMA_ZONE(xx) DMA32_ZONE(xx) xx##_NORMAL, HIGHMEM_ZONE(xx) xx##_MOVABLE +#ifdef CONFIG_ZONE_DEVICE +#define DEVICE_ZONE(xx) xx##_DEVICE, +#else +#define DEVICE_ZONE(xx) +#endif + +#define FOR_ALL_ZONES(xx) DMA_ZONE(xx) DMA32_ZONE(xx) xx##_NORMAL, \ + HIGHMEM_ZONE(xx) xx##_MOVABLE, DEVICE_ZONE(xx) enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, - FOR_ALL_ZONES(PGALLOC), - FOR_ALL_ZONES(ALLOCSTALL), - FOR_ALL_ZONES(PGSCAN_SKIP), + FOR_ALL_ZONES(PGALLOC) + FOR_ALL_ZONES(ALLOCSTALL) + FOR_ALL_ZONES(PGSCAN_SKIP) PGFREE, PGACTIVATE, PGDEACTIVATE, PGLAZYFREE, PGFAULT, PGMAJFAULT, PGLAZYFREED, @@ -98,6 +105,9 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, THP_SPLIT_PAGE_FAILED, THP_DEFERRED_SPLIT_PAGE, THP_SPLIT_PMD, + THP_SCAN_EXCEED_NONE_PTE, + THP_SCAN_EXCEED_SWAP_PTE, + THP_SCAN_EXCEED_SHARED_PTE, #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD THP_SPLIT_PUD, #endif @@ -119,13 +129,19 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, NR_TLB_LOCAL_FLUSH_ALL, NR_TLB_LOCAL_FLUSH_ONE, #endif /* CONFIG_DEBUG_TLBFLUSH */ -#ifdef CONFIG_DEBUG_VM_VMACACHE - VMACACHE_FIND_CALLS, - VMACACHE_FIND_HITS, -#endif #ifdef CONFIG_SWAP SWAP_RA, SWAP_RA_HIT, +#ifdef CONFIG_KSM + KSM_SWPIN_COPY, +#endif +#endif +#ifdef CONFIG_KSM + COW_KSM, +#endif +#ifdef CONFIG_ZSWAP + ZSWPIN, + ZSWPOUT, #endif #ifdef CONFIG_X86 DIRECT_MAP_LEVEL2_SPLIT, diff --git a/include/linux/vmacache.h b/include/linux/vmacache.h deleted file mode 100644 index 6fce268a4588..000000000000 --- a/include/linux/vmacache.h +++ /dev/null @@ -1,28 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __LINUX_VMACACHE_H -#define __LINUX_VMACACHE_H - -#include <linux/sched.h> -#include <linux/mm.h> - -static inline void vmacache_flush(struct task_struct *tsk) -{ - memset(tsk->vmacache.vmas, 0, sizeof(tsk->vmacache.vmas)); -} - -extern void vmacache_update(unsigned long addr, struct vm_area_struct *newvma); -extern struct vm_area_struct *vmacache_find(struct mm_struct *mm, - unsigned long addr); - -#ifndef CONFIG_MMU -extern struct vm_area_struct *vmacache_find_exact(struct mm_struct *mm, - unsigned long start, - unsigned long end); -#endif - -static inline void vmacache_invalidate(struct mm_struct *mm) -{ - mm->vmacache_seqnum++; -} - -#endif /* __LINUX_VMACACHE_H */ diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 6e022cc712e6..096d48aa3437 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -26,18 +26,14 @@ struct notifier_block; /* in notifier.h */ #define VM_KASAN 0x00000080 /* has allocated kasan shadow memory */ #define VM_FLUSH_RESET_PERMS 0x00000100 /* reset direct map and flush TLB on unmap, can't be freed in atomic context */ #define VM_MAP_PUT_PAGES 0x00000200 /* put pages and free array in vfree */ -#define VM_NO_HUGE_VMAP 0x00000400 /* force PAGE_SIZE pte mapping */ +#define VM_ALLOW_HUGE_VMAP 0x00000400 /* Allow for huge pages on archs with HAVE_ARCH_HUGE_VMALLOC */ -/* - * VM_KASAN is used slightly differently depending on CONFIG_KASAN_VMALLOC. - * - * If IS_ENABLED(CONFIG_KASAN_VMALLOC), VM_KASAN is set on a vm_struct after - * shadow memory has been mapped. It's used to handle allocation errors so that - * we don't try to poison shadow on free if it was never allocated. - * - * Otherwise, VM_KASAN is set for kasan_module_alloc() allocations and used to - * determine which allocations need the module shadow freed. - */ +#if (defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)) && \ + !defined(CONFIG_KASAN_VMALLOC) +#define VM_DEFER_KMEMLEAK 0x00000800 /* defer kmemleak object creation */ +#else +#define VM_DEFER_KMEMLEAK 0 +#endif /* bits [20..32] reserved for arch specific ioremap internals */ @@ -73,8 +69,8 @@ struct vmap_area { /* * The following two variables can be packed, because * a vmap_area object can be either: - * 1) in "free" tree (root is vmap_area_root) - * 2) or "busy" tree (root is free_vmap_area_root) + * 1) in "free" tree (root is free_vmap_area_root) + * 2) or "busy" tree (root is vmap_area_root) */ union { unsigned long subtree_max_size; /* in "free" tree */ @@ -119,6 +115,13 @@ static inline int arch_vmap_pte_supported_shift(unsigned long size) } #endif +#ifndef arch_vmap_pgprot_tagged +static inline pgprot_t arch_vmap_pgprot_tagged(pgprot_t prot) +{ + return prot; +} +#endif + /* * Highlevel APIs for driver use */ @@ -150,7 +153,12 @@ extern void *__vmalloc_node_range(unsigned long size, unsigned long align, const void *caller) __alloc_size(1); void *__vmalloc_node(unsigned long size, unsigned long align, gfp_t gfp_mask, int node, const void *caller) __alloc_size(1); -void *vmalloc_no_huge(unsigned long size) __alloc_size(1); +void *vmalloc_huge(unsigned long size, gfp_t gfp_mask) __alloc_size(1); + +extern void *__vmalloc_array(size_t n, size_t size, gfp_t flags) __alloc_size(1, 2); +extern void *vmalloc_array(size_t n, size_t size) __alloc_size(1, 2); +extern void *__vcalloc(size_t n, size_t size, gfp_t flags) __alloc_size(1, 2); +extern void *vcalloc(size_t n, size_t size) __alloc_size(1, 2); extern void vfree(const void *addr); extern void vfree_atomic(const void *addr); @@ -207,6 +215,7 @@ extern struct vm_struct *__get_vm_area_caller(unsigned long size, void free_vm_area(struct vm_struct *area); extern struct vm_struct *remove_vm_area(const void *addr); extern struct vm_struct *find_vm_area(const void *addr); +struct vmap_area *find_vmap_area(unsigned long addr); static inline bool is_vm_area_hugepages(const void *addr) { diff --git a/include/linux/vme.h b/include/linux/vme.h deleted file mode 100644 index b204a9b4be1b..000000000000 --- a/include/linux/vme.h +++ /dev/null @@ -1,190 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _VME_H_ -#define _VME_H_ - -/* Resource Type */ -enum vme_resource_type { - VME_MASTER, - VME_SLAVE, - VME_DMA, - VME_LM -}; - -/* VME Address Spaces */ -#define VME_A16 0x1 -#define VME_A24 0x2 -#define VME_A32 0x4 -#define VME_A64 0x8 -#define VME_CRCSR 0x10 -#define VME_USER1 0x20 -#define VME_USER2 0x40 -#define VME_USER3 0x80 -#define VME_USER4 0x100 - -#define VME_A16_MAX 0x10000ULL -#define VME_A24_MAX 0x1000000ULL -#define VME_A32_MAX 0x100000000ULL -#define VME_A64_MAX 0x10000000000000000ULL -#define VME_CRCSR_MAX 0x1000000ULL - - -/* VME Cycle Types */ -#define VME_SCT 0x1 -#define VME_BLT 0x2 -#define VME_MBLT 0x4 -#define VME_2eVME 0x8 -#define VME_2eSST 0x10 -#define VME_2eSSTB 0x20 - -#define VME_2eSST160 0x100 -#define VME_2eSST267 0x200 -#define VME_2eSST320 0x400 - -#define VME_SUPER 0x1000 -#define VME_USER 0x2000 -#define VME_PROG 0x4000 -#define VME_DATA 0x8000 - -/* VME Data Widths */ -#define VME_D8 0x1 -#define VME_D16 0x2 -#define VME_D32 0x4 -#define VME_D64 0x8 - -/* Arbitration Scheduling Modes */ -#define VME_R_ROBIN_MODE 0x1 -#define VME_PRIORITY_MODE 0x2 - -#define VME_DMA_PATTERN (1<<0) -#define VME_DMA_PCI (1<<1) -#define VME_DMA_VME (1<<2) - -#define VME_DMA_PATTERN_BYTE (1<<0) -#define VME_DMA_PATTERN_WORD (1<<1) -#define VME_DMA_PATTERN_INCREMENT (1<<2) - -#define VME_DMA_VME_TO_MEM (1<<0) -#define VME_DMA_MEM_TO_VME (1<<1) -#define VME_DMA_VME_TO_VME (1<<2) -#define VME_DMA_MEM_TO_MEM (1<<3) -#define VME_DMA_PATTERN_TO_VME (1<<4) -#define VME_DMA_PATTERN_TO_MEM (1<<5) - -struct vme_dma_attr { - u32 type; - void *private; -}; - -struct vme_resource { - enum vme_resource_type type; - struct list_head *entry; -}; - -extern struct bus_type vme_bus_type; - -/* Number of VME interrupt vectors */ -#define VME_NUM_STATUSID 256 - -/* VME_MAX_BRIDGES comes from the type of vme_bus_numbers */ -#define VME_MAX_BRIDGES (sizeof(unsigned int)*8) -#define VME_MAX_SLOTS 32 - -#define VME_SLOT_CURRENT -1 -#define VME_SLOT_ALL -2 - -/** - * struct vme_dev - Structure representing a VME device - * @num: The device number - * @bridge: Pointer to the bridge device this device is on - * @dev: Internal device structure - * @drv_list: List of devices (per driver) - * @bridge_list: List of devices (per bridge) - */ -struct vme_dev { - int num; - struct vme_bridge *bridge; - struct device dev; - struct list_head drv_list; - struct list_head bridge_list; -}; - -/** - * struct vme_driver - Structure representing a VME driver - * @name: Driver name, should be unique among VME drivers and usually the same - * as the module name. - * @match: Callback used to determine whether probe should be run. - * @probe: Callback for device binding, called when new device is detected. - * @remove: Callback, called on device removal. - * @driver: Underlying generic device driver structure. - * @devices: List of VME devices (struct vme_dev) associated with this driver. - */ -struct vme_driver { - const char *name; - int (*match)(struct vme_dev *); - int (*probe)(struct vme_dev *); - void (*remove)(struct vme_dev *); - struct device_driver driver; - struct list_head devices; -}; - -void *vme_alloc_consistent(struct vme_resource *, size_t, dma_addr_t *); -void vme_free_consistent(struct vme_resource *, size_t, void *, - dma_addr_t); - -size_t vme_get_size(struct vme_resource *); -int vme_check_window(u32 aspace, unsigned long long vme_base, - unsigned long long size); - -struct vme_resource *vme_slave_request(struct vme_dev *, u32, u32); -int vme_slave_set(struct vme_resource *, int, unsigned long long, - unsigned long long, dma_addr_t, u32, u32); -int vme_slave_get(struct vme_resource *, int *, unsigned long long *, - unsigned long long *, dma_addr_t *, u32 *, u32 *); -void vme_slave_free(struct vme_resource *); - -struct vme_resource *vme_master_request(struct vme_dev *, u32, u32, u32); -int vme_master_set(struct vme_resource *, int, unsigned long long, - unsigned long long, u32, u32, u32); -int vme_master_get(struct vme_resource *, int *, unsigned long long *, - unsigned long long *, u32 *, u32 *, u32 *); -ssize_t vme_master_read(struct vme_resource *, void *, size_t, loff_t); -ssize_t vme_master_write(struct vme_resource *, void *, size_t, loff_t); -unsigned int vme_master_rmw(struct vme_resource *, unsigned int, unsigned int, - unsigned int, loff_t); -int vme_master_mmap(struct vme_resource *resource, struct vm_area_struct *vma); -void vme_master_free(struct vme_resource *); - -struct vme_resource *vme_dma_request(struct vme_dev *, u32); -struct vme_dma_list *vme_new_dma_list(struct vme_resource *); -struct vme_dma_attr *vme_dma_pattern_attribute(u32, u32); -struct vme_dma_attr *vme_dma_pci_attribute(dma_addr_t); -struct vme_dma_attr *vme_dma_vme_attribute(unsigned long long, u32, u32, u32); -void vme_dma_free_attribute(struct vme_dma_attr *); -int vme_dma_list_add(struct vme_dma_list *, struct vme_dma_attr *, - struct vme_dma_attr *, size_t); -int vme_dma_list_exec(struct vme_dma_list *); -int vme_dma_list_free(struct vme_dma_list *); -int vme_dma_free(struct vme_resource *); - -int vme_irq_request(struct vme_dev *, int, int, - void (*callback)(int, int, void *), void *); -void vme_irq_free(struct vme_dev *, int, int); -int vme_irq_generate(struct vme_dev *, int, int); - -struct vme_resource *vme_lm_request(struct vme_dev *); -int vme_lm_count(struct vme_resource *); -int vme_lm_set(struct vme_resource *, unsigned long long, u32, u32); -int vme_lm_get(struct vme_resource *, unsigned long long *, u32 *, u32 *); -int vme_lm_attach(struct vme_resource *, int, void (*callback)(void *), void *); -int vme_lm_detach(struct vme_resource *, int); -void vme_lm_free(struct vme_resource *); - -int vme_slot_num(struct vme_dev *); -int vme_bus_num(struct vme_dev *); - -int vme_register_driver(struct vme_driver *, unsigned int); -void vme_unregister_driver(struct vme_driver *); - - -#endif /* _VME_H_ */ - diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index bfe38869498d..19cf5b6892ce 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -125,12 +125,6 @@ static inline void vm_events_fold_cpu(int cpu) #define count_vm_tlb_events(x, y) do { (void)(y); } while (0) #endif -#ifdef CONFIG_DEBUG_VM_VMACACHE -#define count_vm_vmacache_event(x) count_vm_event(x) -#else -#define count_vm_vmacache_event(x) do {} while (0) -#endif - #define __count_zid_vm_events(item, zid, delta) \ __count_vm_events(item##_NORMAL - ZONE_NORMAL + zid, delta) diff --git a/include/linux/vmw_vmci_defs.h b/include/linux/vmw_vmci_defs.h index e36cb114c188..6fb663b36f72 100644 --- a/include/linux/vmw_vmci_defs.h +++ b/include/linux/vmw_vmci_defs.h @@ -12,15 +12,20 @@ #include <linux/bits.h> /* Register offsets. */ -#define VMCI_STATUS_ADDR 0x00 -#define VMCI_CONTROL_ADDR 0x04 -#define VMCI_ICR_ADDR 0x08 -#define VMCI_IMR_ADDR 0x0c -#define VMCI_DATA_OUT_ADDR 0x10 -#define VMCI_DATA_IN_ADDR 0x14 -#define VMCI_CAPS_ADDR 0x18 -#define VMCI_RESULT_LOW_ADDR 0x1c -#define VMCI_RESULT_HIGH_ADDR 0x20 +#define VMCI_STATUS_ADDR 0x00 +#define VMCI_CONTROL_ADDR 0x04 +#define VMCI_ICR_ADDR 0x08 +#define VMCI_IMR_ADDR 0x0c +#define VMCI_DATA_OUT_ADDR 0x10 +#define VMCI_DATA_IN_ADDR 0x14 +#define VMCI_CAPS_ADDR 0x18 +#define VMCI_RESULT_LOW_ADDR 0x1c +#define VMCI_RESULT_HIGH_ADDR 0x20 +#define VMCI_DATA_OUT_LOW_ADDR 0x24 +#define VMCI_DATA_OUT_HIGH_ADDR 0x28 +#define VMCI_DATA_IN_LOW_ADDR 0x2c +#define VMCI_DATA_IN_HIGH_ADDR 0x30 +#define VMCI_GUEST_PAGE_SHIFT 0x34 /* Max number of devices. */ #define VMCI_MAX_DEVICES 1 @@ -39,17 +44,27 @@ #define VMCI_CAPS_DATAGRAM BIT(2) #define VMCI_CAPS_NOTIFICATIONS BIT(3) #define VMCI_CAPS_PPN64 BIT(4) +#define VMCI_CAPS_DMA_DATAGRAM BIT(5) /* Interrupt Cause register bits. */ #define VMCI_ICR_DATAGRAM BIT(0) #define VMCI_ICR_NOTIFICATION BIT(1) +#define VMCI_ICR_DMA_DATAGRAM BIT(2) /* Interrupt Mask register bits. */ #define VMCI_IMR_DATAGRAM BIT(0) #define VMCI_IMR_NOTIFICATION BIT(1) +#define VMCI_IMR_DMA_DATAGRAM BIT(2) -/* Maximum MSI/MSI-X interrupt vectors in the device. */ -#define VMCI_MAX_INTRS 2 +/* + * Maximum MSI/MSI-X interrupt vectors in the device. + * If VMCI_CAPS_DMA_DATAGRAM is supported by the device, + * VMCI_MAX_INTRS_DMA_DATAGRAM vectors are available, + * otherwise only VMCI_MAX_INTRS_NOTIFICATION. + */ +#define VMCI_MAX_INTRS_NOTIFICATION 2 +#define VMCI_MAX_INTRS_DMA_DATAGRAM 3 +#define VMCI_MAX_INTRS VMCI_MAX_INTRS_DMA_DATAGRAM /* * Supported interrupt vectors. There is one for each ICR value above, @@ -58,6 +73,7 @@ enum { VMCI_INTR_DATAGRAM = 0, VMCI_INTR_NOTIFICATION = 1, + VMCI_INTR_DMA_DATAGRAM = 2, }; /* @@ -83,6 +99,52 @@ enum { #define VMCI_MAX_PINNED_QP_MEMORY ((size_t)(32 * 1024)) /* + * The version of the VMCI device that supports MMIO access to registers + * requests 256KB for BAR1 whereas the version of VMCI that supports + * MSI/MSI-X only requests 8KB. The layout of the larger 256KB region is: + * - the first 128KB are used for MSI/MSI-X. + * - the following 64KB are used for MMIO register access. + * - the remaining 64KB are unused. + */ +#define VMCI_WITH_MMIO_ACCESS_BAR_SIZE ((size_t)(256 * 1024)) +#define VMCI_MMIO_ACCESS_OFFSET ((size_t)(128 * 1024)) +#define VMCI_MMIO_ACCESS_SIZE ((size_t)(64 * 1024)) + +/* + * For VMCI devices supporting the VMCI_CAPS_DMA_DATAGRAM capability, the + * sending and receiving of datagrams can be performed using DMA to/from + * a driver allocated buffer. + * Sending and receiving will be handled as follows: + * - when sending datagrams, the driver initializes the buffer where the + * data part will refer to the outgoing VMCI datagram, sets the busy flag + * to 1 and writes the address of the buffer to VMCI_DATA_OUT_HIGH_ADDR + * and VMCI_DATA_OUT_LOW_ADDR. Writing to VMCI_DATA_OUT_LOW_ADDR triggers + * the device processing of the buffer. When the device has processed the + * buffer, it will write the result value to the buffer and then clear the + * busy flag. + * - when receiving datagrams, the driver initializes the buffer where the + * data part will describe the receive buffer, clears the busy flag and + * writes the address of the buffer to VMCI_DATA_IN_HIGH_ADDR and + * VMCI_DATA_IN_LOW_ADDR. Writing to VMCI_DATA_IN_LOW_ADDR triggers the + * device processing of the buffer. The device will copy as many available + * datagrams into the buffer as possible, and then sets the busy flag. + * When the busy flag is set, the driver will process the datagrams in the + * buffer. + */ +struct vmci_data_in_out_header { + uint32_t busy; + uint32_t opcode; + uint32_t size; + uint32_t rsvd; + uint64_t result; +}; + +struct vmci_sg_elem { + uint64_t addr; + uint64_t size; +}; + +/* * We have a fixed set of resource IDs available in the VMX. * This allows us to have a very simple implementation since we statically * know how many will create datagram handles. If a new caller arrives and diff --git a/include/linux/vt_kern.h b/include/linux/vt_kern.h index b5ab452fca5b..c1f5aebef170 100644 --- a/include/linux/vt_kern.h +++ b/include/linux/vt_kern.h @@ -30,7 +30,6 @@ struct vc_data *vc_deallocate(unsigned int console); void reset_palette(struct vc_data *vc); void do_blank_screen(int entering_gfx); void do_unblank_screen(int leaving_gfx); -void unblank_screen(void); void poke_blanked_console(void); int con_font_op(struct vc_data *vc, struct console_font_op *op); int con_set_cmap(unsigned char __user *cmap); diff --git a/include/linux/wait.h b/include/linux/wait.h index 851e07da2583..7f5a51aae0a7 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -281,7 +281,7 @@ static inline void wake_up_pollfree(struct wait_queue_head *wq_head) #define ___wait_is_interruptible(state) \ (!__builtin_constant_p(state) || \ - state == TASK_INTERRUPTIBLE || state == TASK_KILLABLE) \ + (state & (TASK_INTERRUPTIBLE | TASK_WAKEKILL))) extern void init_wait_entry(struct wait_queue_entry *wq_entry, int flags); @@ -361,8 +361,8 @@ do { \ } while (0) #define __wait_event_freezable(wq_head, condition) \ - ___wait_event(wq_head, condition, TASK_INTERRUPTIBLE, 0, 0, \ - freezable_schedule()) + ___wait_event(wq_head, condition, (TASK_INTERRUPTIBLE|TASK_FREEZABLE), \ + 0, 0, schedule()) /** * wait_event_freezable - sleep (or freeze) until a condition gets true @@ -420,8 +420,8 @@ do { \ #define __wait_event_freezable_timeout(wq_head, condition, timeout) \ ___wait_event(wq_head, ___wait_cond_timeout(condition), \ - TASK_INTERRUPTIBLE, 0, timeout, \ - __ret = freezable_schedule_timeout(__ret)) + (TASK_INTERRUPTIBLE|TASK_FREEZABLE), 0, timeout, \ + __ret = schedule_timeout(__ret)) /* * like wait_event_timeout() -- except it uses TASK_INTERRUPTIBLE to avoid @@ -544,10 +544,11 @@ do { \ \ hrtimer_init_sleeper_on_stack(&__t, CLOCK_MONOTONIC, \ HRTIMER_MODE_REL); \ - if ((timeout) != KTIME_MAX) \ - hrtimer_start_range_ns(&__t.timer, timeout, \ - current->timer_slack_ns, \ - HRTIMER_MODE_REL); \ + if ((timeout) != KTIME_MAX) { \ + hrtimer_set_expires_range_ns(&__t.timer, timeout, \ + current->timer_slack_ns); \ + hrtimer_sleeper_start_expires(&__t, HRTIMER_MODE_REL); \ + } \ \ __ret = ___wait_event(wq_head, condition, state, 0, 0, \ if (!__t.task) { \ @@ -641,8 +642,8 @@ do { \ #define __wait_event_freezable_exclusive(wq, condition) \ - ___wait_event(wq, condition, TASK_INTERRUPTIBLE, 1, 0, \ - freezable_schedule()) + ___wait_event(wq, condition, (TASK_INTERRUPTIBLE|TASK_FREEZABLE), 1, 0,\ + schedule()) #define wait_event_freezable_exclusive(wq, condition) \ ({ \ @@ -931,6 +932,34 @@ extern int do_wait_intr_irq(wait_queue_head_t *, wait_queue_entry_t *); __ret; \ }) +#define __wait_event_state(wq, condition, state) \ + ___wait_event(wq, condition, state, 0, 0, schedule()) + +/** + * wait_event_state - sleep until a condition gets true + * @wq_head: the waitqueue to wait on + * @condition: a C expression for the event to wait for + * @state: state to sleep in + * + * The process is put to sleep (@state) until the @condition evaluates to true + * or a signal is received (when allowed by @state). The @condition is checked + * each time the waitqueue @wq_head is woken up. + * + * wake_up() has to be called after changing any variable that could + * change the result of the wait condition. + * + * The function will return -ERESTARTSYS if it was interrupted by a signal + * (when allowed by @state) and 0 if @condition evaluated to true. + */ +#define wait_event_state(wq_head, condition, state) \ +({ \ + int __ret = 0; \ + might_sleep(); \ + if (!(condition)) \ + __ret = __wait_event_state(wq_head, condition, state); \ + __ret; \ +}) + #define __wait_event_killable_timeout(wq_head, condition, timeout) \ ___wait_event(wq_head, ___wait_cond_timeout(condition), \ TASK_KILLABLE, 0, timeout, \ diff --git a/include/linux/wait_api.h b/include/linux/wait_api.h new file mode 100644 index 000000000000..4e930548935a --- /dev/null +++ b/include/linux/wait_api.h @@ -0,0 +1 @@ +#include <linux/wait.h> diff --git a/include/linux/wait_bit.h b/include/linux/wait_bit.h index 7dec36aecbd9..7725b7579b78 100644 --- a/include/linux/wait_bit.h +++ b/include/linux/wait_bit.h @@ -71,7 +71,7 @@ static inline int wait_on_bit(unsigned long *word, int bit, unsigned mode) { might_sleep(); - if (!test_bit(bit, word)) + if (!test_bit_acquire(bit, word)) return 0; return out_of_line_wait_on_bit(word, bit, bit_wait, @@ -96,7 +96,7 @@ static inline int wait_on_bit_io(unsigned long *word, int bit, unsigned mode) { might_sleep(); - if (!test_bit(bit, word)) + if (!test_bit_acquire(bit, word)) return 0; return out_of_line_wait_on_bit(word, bit, bit_wait_io, @@ -123,7 +123,7 @@ wait_on_bit_timeout(unsigned long *word, int bit, unsigned mode, unsigned long timeout) { might_sleep(); - if (!test_bit(bit, word)) + if (!test_bit_acquire(bit, word)) return 0; return out_of_line_wait_on_bit_timeout(word, bit, bit_wait_timeout, @@ -151,7 +151,7 @@ wait_on_bit_action(unsigned long *word, int bit, wait_bit_action_f *action, unsigned mode) { might_sleep(); - if (!test_bit(bit, word)) + if (!test_bit_acquire(bit, word)) return 0; return out_of_line_wait_on_bit(word, bit, action, mode); } diff --git a/include/linux/watch_queue.h b/include/linux/watch_queue.h index c994d1b2cdba..fc6bba20273b 100644 --- a/include/linux/watch_queue.h +++ b/include/linux/watch_queue.h @@ -4,7 +4,7 @@ * Copyright (C) 2020 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) * - * See Documentation/watch_queue.rst + * See Documentation/core-api/watch_queue.rst */ #ifndef _LINUX_WATCH_QUEUE_H @@ -28,7 +28,8 @@ struct watch_type_filter { struct watch_filter { union { struct rcu_head rcu; - unsigned long type_filter[2]; /* Bitmask of accepted types */ + /* Bitmask of accepted types */ + DECLARE_BITMAP(type_filter, WATCH_TYPE__NR); }; u32 nr_filters; /* Number of filters */ struct watch_type_filter filters[]; diff --git a/include/linux/wireless.h b/include/linux/wireless.h index 2d1b54556eff..e6e34d74dda0 100644 --- a/include/linux/wireless.h +++ b/include/linux/wireless.h @@ -26,7 +26,15 @@ struct compat_iw_point { struct __compat_iw_event { __u16 len; /* Real length of this stuff */ __u16 cmd; /* Wireless IOCTL */ - compat_caddr_t pointer; + + union { + compat_caddr_t pointer; + + /* we need ptr_bytes to make memcpy() run-time destination + * buffer bounds checking happy, nothing special + */ + DECLARE_FLEX_ARRAY(__u8, ptr_bytes); + }; }; #define IW_EV_COMPAT_LCP_LEN offsetof(struct __compat_iw_event, pointer) #define IW_EV_COMPAT_POINT_OFF offsetof(struct compat_iw_point, length) diff --git a/include/linux/wkup_m3_ipc.h b/include/linux/wkup_m3_ipc.h index 3f496967b538..5e1b26f988e2 100644 --- a/include/linux/wkup_m3_ipc.h +++ b/include/linux/wkup_m3_ipc.h @@ -1,17 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * TI Wakeup M3 for AMx3 SoCs Power Management Routines * * Copyright (C) 2015 Texas Instruments Incorporated - https://www.ti.com/ * Dave Gerlach <d-gerlach@ti.com> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation version 2. - * - * This program is distributed "as is" WITHOUT ANY WARRANTY of any - * kind, whether express or implied; without even the implied warranty - * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. */ #ifndef _LINUX_WKUP_M3_IPC_H @@ -33,7 +25,13 @@ struct wkup_m3_ipc { int mem_type; unsigned long resume_addr; + int vtt_conf; + int isolation_conf; int state; + u32 halt; + + unsigned long volt_scale_offsets; + const char *sd_fw_name; struct completion sync_complete; struct mbox_client mbox_client; @@ -41,6 +39,7 @@ struct wkup_m3_ipc { struct wkup_m3_ipc_ops *ops; int is_rtc_only; + struct dentry *dbg_path; }; struct wkup_m3_wakeup_src { @@ -48,6 +47,12 @@ struct wkup_m3_wakeup_src { char src[10]; }; +struct wkup_m3_scale_data_header { + u16 magic; + u8 sleep_offset; + u8 wake_offset; +} __packed; + struct wkup_m3_ipc_ops { void (*set_mem_type)(struct wkup_m3_ipc *m3_ipc, int mem_type); void (*set_resume_address)(struct wkup_m3_ipc *m3_ipc, void *addr); diff --git a/include/linux/wm97xx.h b/include/linux/wm97xx.h index 462854f4f286..332d2b0f29b9 100644 --- a/include/linux/wm97xx.h +++ b/include/linux/wm97xx.h @@ -254,9 +254,6 @@ struct wm97xx_mach_ops { int (*acc_startup) (struct wm97xx *); void (*acc_shutdown) (struct wm97xx *); - /* interrupt mask control - required for accelerated operation */ - void (*irq_enable) (struct wm97xx *, int enable); - /* GPIO pin used for accelerated operation */ int irq_gpio; @@ -281,7 +278,6 @@ struct wm97xx { unsigned long ts_reader_min_interval; /* Minimum interval */ unsigned int pen_irq; /* Pen IRQ number in use */ struct workqueue_struct *ts_workq; - struct work_struct pen_event_work; u16 acc_slot; /* AC97 slot used for acc touch data */ u16 acc_rate; /* acc touch data rate */ unsigned pen_is_down:1; /* Pen is down */ diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 7fee9b6cfede..a0143dd24430 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -406,7 +406,7 @@ alloc_workqueue(const char *fmt, unsigned int flags, int max_active, ...); * alloc_ordered_workqueue - allocate an ordered workqueue * @fmt: printf format for the name of the workqueue * @flags: WQ_* flags (only WQ_FREEZABLE and WQ_MEM_RECLAIM are meaningful) - * @args...: args for @fmt + * @args: args for @fmt * * Allocate an ordered workqueue. An ordered workqueue executes at * most one work item at any given time in the queued order. They are @@ -445,7 +445,7 @@ extern bool mod_delayed_work_on(int cpu, struct workqueue_struct *wq, struct delayed_work *dwork, unsigned long delay); extern bool queue_rcu_work(struct workqueue_struct *wq, struct rcu_work *rwork); -extern void flush_workqueue(struct workqueue_struct *wq); +extern void __flush_workqueue(struct workqueue_struct *wq); extern void drain_workqueue(struct workqueue_struct *wq); extern int schedule_on_each_cpu(work_func_t func); @@ -453,6 +453,7 @@ extern int schedule_on_each_cpu(work_func_t func); int execute_in_process_context(work_func_t fn, struct execute_work *); extern bool flush_work(struct work_struct *work); +extern bool cancel_work(struct work_struct *work); extern bool cancel_work_sync(struct work_struct *work); extern bool flush_delayed_work(struct delayed_work *dwork); @@ -563,15 +564,23 @@ static inline bool schedule_work(struct work_struct *work) return queue_work(system_wq, work); } +/* + * Detect attempt to flush system-wide workqueues at compile time when possible. + * + * See https://lkml.kernel.org/r/49925af7-78a8-a3dd-bce6-cfc02e1a9236@I-love.SAKURA.ne.jp + * for reasons and steps for converting system-wide workqueues into local workqueues. + */ +extern void __warn_flushing_systemwide_wq(void) + __compiletime_warning("Please avoid flushing system-wide workqueues."); + /** * flush_scheduled_work - ensure that any scheduled work has run to completion. * * Forces execution of the kernel-global workqueue and blocks until its * completion. * - * Think twice before calling this function! It's very easy to get into - * trouble if you don't take great care. Either of the following situations - * will lead to deadlock: + * It's very easy to get into trouble if you don't take great care. + * Either of the following situations will lead to deadlock: * * One of the work items currently on the workqueue needs to acquire * a lock held by your code or its caller. @@ -586,11 +595,51 @@ static inline bool schedule_work(struct work_struct *work) * need to know that a particular work item isn't queued and isn't running. * In such cases you should use cancel_delayed_work_sync() or * cancel_work_sync() instead. + * + * Please stop calling this function! A conversion to stop flushing system-wide + * workqueues is in progress. This function will be removed after all in-tree + * users stopped calling this function. */ -static inline void flush_scheduled_work(void) -{ - flush_workqueue(system_wq); -} +/* + * The background of commit 771c035372a036f8 ("deprecate the + * '__deprecated' attribute warnings entirely and for good") is that, + * since Linus builds all modules between every single pull he does, + * the standard kernel build needs to be _clean_ in order to be able to + * notice when new problems happen. Therefore, don't emit warning while + * there are in-tree users. + */ +#define flush_scheduled_work() \ +({ \ + if (0) \ + __warn_flushing_systemwide_wq(); \ + __flush_workqueue(system_wq); \ +}) + +/* + * Although there is no longer in-tree caller, for now just emit warning + * in order to give out-of-tree callers time to update. + */ +#define flush_workqueue(wq) \ +({ \ + struct workqueue_struct *_wq = (wq); \ + \ + if ((__builtin_constant_p(_wq == system_wq) && \ + _wq == system_wq) || \ + (__builtin_constant_p(_wq == system_highpri_wq) && \ + _wq == system_highpri_wq) || \ + (__builtin_constant_p(_wq == system_long_wq) && \ + _wq == system_long_wq) || \ + (__builtin_constant_p(_wq == system_unbound_wq) && \ + _wq == system_unbound_wq) || \ + (__builtin_constant_p(_wq == system_freezable_wq) && \ + _wq == system_freezable_wq) || \ + (__builtin_constant_p(_wq == system_power_efficient_wq) && \ + _wq == system_power_efficient_wq) || \ + (__builtin_constant_p(_wq == system_freezable_power_efficient_wq) && \ + _wq == system_freezable_power_efficient_wq)) \ + __warn_flushing_systemwide_wq(); \ + __flush_workqueue(_wq); \ +}) /** * schedule_delayed_work_on - queue work in global workqueue on CPU after delay diff --git a/include/linux/workqueue_api.h b/include/linux/workqueue_api.h new file mode 100644 index 000000000000..77debb5d2760 --- /dev/null +++ b/include/linux/workqueue_api.h @@ -0,0 +1 @@ +#include <linux/workqueue.h> diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 3bfd487d1dd2..06f9291b6fd5 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -17,20 +17,12 @@ struct bio; DECLARE_PER_CPU(int, dirty_throttle_leaks); /* - * The 1/4 region under the global dirty thresh is for smooth dirty throttling: - * - * (thresh - thresh/DIRTY_FULL_SCOPE, thresh) - * - * Further beyond, all dirtier tasks will enter a loop waiting (possibly long - * time) for the dirty pages to drop, unless written enough pages. - * * The global dirty threshold is normally equal to the global dirty limit, * except when the system suddenly allocates a lot of anonymous memory and * knocks down the global dirty threshold quickly, in which case the global * dirty limit will follow down slowly to prevent livelocking all dirtier tasks. */ #define DIRTY_SCOPE 8 -#define DIRTY_FULL_SCOPE (DIRTY_SCOPE / 2) struct backing_dev_info; @@ -68,6 +60,7 @@ struct writeback_control { unsigned for_reclaim:1; /* Invoked from the page allocator */ unsigned range_cyclic:1; /* range_start is cyclic */ unsigned for_sync:1; /* sync(2) WB_SYNC_ALL writeback */ + unsigned unpinned_fscache_wb:1; /* Cleared I_PINNING_FSCACHE_WB */ /* * When writeback IOs are bounced through async layers, only the @@ -79,6 +72,13 @@ struct writeback_control { unsigned punt_to_cgroup:1; /* cgrp punting, see __REQ_CGROUP_PUNT */ + /* To enable batching of swap writes to non-block-device backends, + * "plug" can be set point to a 'struct swap_iocb *'. When all swap + * writes have been submitted, if with swap_iocb is not NULL, + * swap_write_unplug() should be called. + */ + struct swap_iocb **swap_plug; + #ifdef CONFIG_CGROUP_WRITEBACK struct bdi_writeback *wb; /* wb this writeback is issued under */ struct inode *inode; /* inode being written out */ @@ -93,9 +93,9 @@ struct writeback_control { #endif }; -static inline int wbc_to_write_flags(struct writeback_control *wbc) +static inline blk_opf_t wbc_to_write_flags(struct writeback_control *wbc) { - int flags = 0; + blk_opf_t flags = 0; if (wbc->punt_to_cgroup) flags = REQ_CGROUP_PUNT; @@ -344,34 +344,26 @@ void wb_domain_exit(struct wb_domain *dom); extern struct wb_domain global_wb_domain; /* These are exported to sysctl. */ -extern int dirty_background_ratio; -extern unsigned long dirty_background_bytes; -extern int vm_dirty_ratio; -extern unsigned long vm_dirty_bytes; extern unsigned int dirty_writeback_interval; extern unsigned int dirty_expire_interval; extern unsigned int dirtytime_expire_interval; -extern int vm_highmem_is_dirtyable; extern int laptop_mode; -int dirty_background_ratio_handler(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos); -int dirty_background_bytes_handler(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos); -int dirty_ratio_handler(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos); -int dirty_bytes_handler(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos); int dirtytime_interval_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); -int dirty_writeback_centisecs_handler(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos); void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty); unsigned long wb_calc_thresh(struct bdi_writeback *wb, unsigned long thresh); void wb_update_bandwidth(struct bdi_writeback *wb); + +/* Invoke balance dirty pages in async mode. */ +#define BDP_ASYNC 0x0001 + void balance_dirty_pages_ratelimited(struct address_space *mapping); +int balance_dirty_pages_ratelimited_flags(struct address_space *mapping, + unsigned int flags); + bool wb_over_bg_thresh(struct bdi_writeback *wb); typedef int (*writepage_t)(struct page *page, struct writeback_control *wbc, diff --git a/include/linux/wwan.h b/include/linux/wwan.h index afb3334ec8c5..5ce2acf444fb 100644 --- a/include/linux/wwan.h +++ b/include/linux/wwan.h @@ -174,11 +174,13 @@ void wwan_unregister_ops(struct device *parent); #ifdef CONFIG_WWAN_DEBUGFS struct dentry *wwan_get_debugfs_dir(struct device *parent); +void wwan_put_debugfs_dir(struct dentry *dir); #else static inline struct dentry *wwan_get_debugfs_dir(struct device *parent) { return ERR_PTR(-ENODEV); } +static inline void wwan_put_debugfs_dir(struct dentry *dir) {} #endif #endif /* __WWAN_H */ diff --git a/include/linux/xarray.h b/include/linux/xarray.h index a91e3d90df8a..44dd6d6e01bc 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -9,12 +9,14 @@ * See Documentation/core-api/xarray.rst for how to use the XArray. */ +#include <linux/bitmap.h> #include <linux/bug.h> #include <linux/compiler.h> #include <linux/gfp.h> #include <linux/kconfig.h> #include <linux/kernel.h> #include <linux/rcupdate.h> +#include <linux/sched/mm.h> #include <linux/spinlock.h> #include <linux/types.h> @@ -585,6 +587,7 @@ static inline void *xa_store_bh(struct xarray *xa, unsigned long index, { void *curr; + might_alloc(gfp); xa_lock_bh(xa); curr = __xa_store(xa, index, entry, gfp); xa_unlock_bh(xa); @@ -611,6 +614,7 @@ static inline void *xa_store_irq(struct xarray *xa, unsigned long index, { void *curr; + might_alloc(gfp); xa_lock_irq(xa); curr = __xa_store(xa, index, entry, gfp); xa_unlock_irq(xa); @@ -686,6 +690,7 @@ static inline void *xa_cmpxchg(struct xarray *xa, unsigned long index, { void *curr; + might_alloc(gfp); xa_lock(xa); curr = __xa_cmpxchg(xa, index, old, entry, gfp); xa_unlock(xa); @@ -713,6 +718,7 @@ static inline void *xa_cmpxchg_bh(struct xarray *xa, unsigned long index, { void *curr; + might_alloc(gfp); xa_lock_bh(xa); curr = __xa_cmpxchg(xa, index, old, entry, gfp); xa_unlock_bh(xa); @@ -740,6 +746,7 @@ static inline void *xa_cmpxchg_irq(struct xarray *xa, unsigned long index, { void *curr; + might_alloc(gfp); xa_lock_irq(xa); curr = __xa_cmpxchg(xa, index, old, entry, gfp); xa_unlock_irq(xa); @@ -769,6 +776,7 @@ static inline int __must_check xa_insert(struct xarray *xa, { int err; + might_alloc(gfp); xa_lock(xa); err = __xa_insert(xa, index, entry, gfp); xa_unlock(xa); @@ -798,6 +806,7 @@ static inline int __must_check xa_insert_bh(struct xarray *xa, { int err; + might_alloc(gfp); xa_lock_bh(xa); err = __xa_insert(xa, index, entry, gfp); xa_unlock_bh(xa); @@ -827,6 +836,7 @@ static inline int __must_check xa_insert_irq(struct xarray *xa, { int err; + might_alloc(gfp); xa_lock_irq(xa); err = __xa_insert(xa, index, entry, gfp); xa_unlock_irq(xa); @@ -856,6 +866,7 @@ static inline __must_check int xa_alloc(struct xarray *xa, u32 *id, { int err; + might_alloc(gfp); xa_lock(xa); err = __xa_alloc(xa, id, entry, limit, gfp); xa_unlock(xa); @@ -885,6 +896,7 @@ static inline int __must_check xa_alloc_bh(struct xarray *xa, u32 *id, { int err; + might_alloc(gfp); xa_lock_bh(xa); err = __xa_alloc(xa, id, entry, limit, gfp); xa_unlock_bh(xa); @@ -914,6 +926,7 @@ static inline int __must_check xa_alloc_irq(struct xarray *xa, u32 *id, { int err; + might_alloc(gfp); xa_lock_irq(xa); err = __xa_alloc(xa, id, entry, limit, gfp); xa_unlock_irq(xa); @@ -947,6 +960,7 @@ static inline int xa_alloc_cyclic(struct xarray *xa, u32 *id, void *entry, { int err; + might_alloc(gfp); xa_lock(xa); err = __xa_alloc_cyclic(xa, id, entry, limit, next, gfp); xa_unlock(xa); @@ -980,6 +994,7 @@ static inline int xa_alloc_cyclic_bh(struct xarray *xa, u32 *id, void *entry, { int err; + might_alloc(gfp); xa_lock_bh(xa); err = __xa_alloc_cyclic(xa, id, entry, limit, next, gfp); xa_unlock_bh(xa); @@ -1013,6 +1028,7 @@ static inline int xa_alloc_cyclic_irq(struct xarray *xa, u32 *id, void *entry, { int err; + might_alloc(gfp); xa_lock_irq(xa); err = __xa_alloc_cyclic(xa, id, entry, limit, next, gfp); xa_unlock_irq(xa); @@ -1317,6 +1333,7 @@ struct xa_state { struct xa_node *xa_node; struct xa_node *xa_alloc; xa_update_node_t xa_update; + struct list_lru *xa_lru; }; /* @@ -1336,7 +1353,8 @@ struct xa_state { .xa_pad = 0, \ .xa_node = XAS_RESTART, \ .xa_alloc = NULL, \ - .xa_update = NULL \ + .xa_update = NULL, \ + .xa_lru = NULL, \ } /** @@ -1505,6 +1523,7 @@ void *xas_find_marked(struct xa_state *, unsigned long max, xa_mark_t); void xas_init_marks(const struct xa_state *); bool xas_nomem(struct xa_state *, gfp_t); +void xas_destroy(struct xa_state *); void xas_pause(struct xa_state *); void xas_create_range(struct xa_state *); @@ -1581,6 +1600,24 @@ static inline void xas_set(struct xa_state *xas, unsigned long index) } /** + * xas_advance() - Skip over sibling entries. + * @xas: XArray operation state. + * @index: Index of last sibling entry. + * + * Move the operation state to refer to the last sibling entry. + * This is useful for loops that normally want to see sibling + * entries but sometimes want to skip them. Use xas_set() if you + * want to move to an index which is not part of this entry. + */ +static inline void xas_advance(struct xa_state *xas, unsigned long index) +{ + unsigned char shift = xas_is_node(xas) ? xas->xa_node->shift : 0; + + xas->xa_index = index; + xas->xa_offset = (index >> shift) & XA_CHUNK_MASK; +} + +/** * xas_set_order() - Set up XArray operation state for a multislot entry. * @xas: XArray operation state. * @index: Target of the operation. @@ -1613,6 +1650,11 @@ static inline void xas_set_update(struct xa_state *xas, xa_update_node_t update) xas->xa_update = update; } +static inline void xas_set_lru(struct xa_state *xas, struct list_lru *lru) +{ + xas->xa_lru = lru; +} + /** * xas_next_entry() - Advance iterator to next present entry. * @xas: XArray operation state. |