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 |