diff options
Diffstat (limited to 'include')
70 files changed, 413 insertions, 150 deletions
diff --git a/include/asm-generic/cacheflush.h b/include/asm-generic/cacheflush.h index fedc0dfa4877..4f07afacbc23 100644 --- a/include/asm-generic/cacheflush.h +++ b/include/asm-generic/cacheflush.h @@ -50,13 +50,7 @@ static inline void flush_dcache_page(struct page *page) { } -static inline void flush_dcache_folio(struct folio *folio) { } #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0 -#define ARCH_IMPLEMENTS_FLUSH_DCACHE_FOLIO -#endif - -#ifndef ARCH_IMPLEMENTS_FLUSH_DCACHE_FOLIO -void flush_dcache_folio(struct folio *folio); #endif #ifndef flush_dcache_mmap_lock diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 668d007f0917..b28f8790192a 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -1182,7 +1182,6 @@ int acpi_node_prop_get(const struct fwnode_handle *fwnode, const char *propname, struct fwnode_handle *acpi_get_next_subnode(const struct fwnode_handle *fwnode, struct fwnode_handle *child); -struct fwnode_handle *acpi_node_get_parent(const struct fwnode_handle *fwnode); struct acpi_probe_entry; typedef bool (*acpi_probe_entry_validate_subtbl)(struct acpi_subtable_header *, @@ -1288,12 +1287,6 @@ acpi_get_next_subnode(const struct fwnode_handle *fwnode, } static inline struct fwnode_handle * -acpi_node_get_parent(const struct fwnode_handle *fwnode) -{ - return NULL; -} - -static inline struct fwnode_handle * acpi_graph_get_next_endpoint(const struct fwnode_handle *fwnode, struct fwnode_handle *prev) { diff --git a/include/linux/bpf.h b/include/linux/bpf.h index e7a163a3146b..755f38e893be 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -732,6 +732,7 @@ int bpf_trampoline_unlink_prog(struct bpf_prog *prog, 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); #define BPF_DISPATCHER_INIT(_name) { \ .mutex = __MUTEX_INITIALIZER(_name.mutex), \ .func = &_name##_func, \ @@ -1352,28 +1353,16 @@ extern struct mutex bpf_stats_enabled_mutex; * kprobes, tracepoints) to prevent deadlocks on map operations as any of * these events can happen inside a region which holds a map bucket lock * and can deadlock on it. - * - * Use the preemption safe inc/dec variants on RT because migrate disable - * is preemptible on RT and preemption in the middle of the RMW operation - * might lead to inconsistent state. Use the raw variants for non RT - * kernels as migrate_disable() maps to preempt_disable() so the slightly - * more expensive save operation can be avoided. */ static inline void bpf_disable_instrumentation(void) { migrate_disable(); - if (IS_ENABLED(CONFIG_PREEMPT_RT)) - this_cpu_inc(bpf_prog_active); - else - __this_cpu_inc(bpf_prog_active); + this_cpu_inc(bpf_prog_active); } static inline void bpf_enable_instrumentation(void) { - if (IS_ENABLED(CONFIG_PREEMPT_RT)) - this_cpu_dec(bpf_prog_active); - else - __this_cpu_dec(bpf_prog_active); + this_cpu_dec(bpf_prog_active); migrate_enable(); } diff --git a/include/linux/btf.h b/include/linux/btf.h index 203eef993d76..0e1b6281fd8f 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -245,7 +245,10 @@ struct kfunc_btf_id_set { struct module *owner; }; -struct kfunc_btf_id_list; +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, @@ -254,6 +257,9 @@ 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) @@ -268,13 +274,13 @@ static inline bool bpf_check_mod_kfunc_call(struct kfunc_btf_id_list *klist, { return false; } + +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 } -extern struct kfunc_btf_id_list bpf_tcp_ca_kfunc_list; -extern struct kfunc_btf_id_list prog_test_kfunc_list; - #endif diff --git a/include/linux/cacheflush.h b/include/linux/cacheflush.h new file mode 100644 index 000000000000..fef8b607f97e --- /dev/null +++ b/include/linux/cacheflush.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_CACHEFLUSH_H +#define _LINUX_CACHEFLUSH_H + +#include <asm/cacheflush.h> + +#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE +#ifndef ARCH_IMPLEMENTS_FLUSH_DCACHE_FOLIO +void flush_dcache_folio(struct folio *folio); +#endif +#else +static inline void flush_dcache_folio(struct folio *folio) +{ +} +#define ARCH_IMPLEMENTS_FLUSH_DCACHE_FOLIO 0 +#endif /* ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE */ + +#endif /* _LINUX_CACHEFLUSH_H */ diff --git a/include/linux/cacheinfo.h b/include/linux/cacheinfo.h index 2f909ed084c6..4ff37cb763ae 100644 --- a/include/linux/cacheinfo.h +++ b/include/linux/cacheinfo.h @@ -3,7 +3,6 @@ #define _LINUX_CACHEINFO_H #include <linux/bitops.h> -#include <linux/cpu.h> #include <linux/cpumask.h> #include <linux/smp.h> diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 3d5af56337bd..429dcebe2b99 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -121,7 +121,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, asm volatile(__stringify_label(c) ":\n\t" \ ".pushsection .discard.reachable\n\t" \ ".long " __stringify_label(c) "b - .\n\t" \ - ".popsection\n\t"); \ + ".popsection\n\t" : : "i" (c)); \ }) #define annotate_reachable() __annotate_reachable(__COUNTER__) @@ -129,7 +129,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, asm volatile(__stringify_label(c) ":\n\t" \ ".pushsection .discard.unreachable\n\t" \ ".long " __stringify_label(c) "b - .\n\t" \ - ".popsection\n\t"); \ + ".popsection\n\t" : : "i" (c)); \ }) #define annotate_unreachable() __annotate_unreachable(__COUNTER__) diff --git a/include/linux/delay.h b/include/linux/delay.h index 8eacf67eb212..039e7e0c7378 100644 --- a/include/linux/delay.h +++ b/include/linux/delay.h @@ -20,6 +20,7 @@ */ #include <linux/math.h> +#include <linux/sched.h> extern unsigned long loops_per_jiffy; @@ -58,7 +59,18 @@ void calibrate_delay(void); void __attribute__((weak)) calibration_delay_done(void); void msleep(unsigned int msecs); unsigned long msleep_interruptible(unsigned int msecs); -void usleep_range(unsigned long min, unsigned long max); +void usleep_range_state(unsigned long min, unsigned long max, + unsigned int state); + +static inline void usleep_range(unsigned long min, unsigned long max) +{ + usleep_range_state(min, max, TASK_UNINTERRUPTIBLE); +} + +static inline void usleep_idle_range(unsigned long min, unsigned long max) +{ + usleep_range_state(min, max, TASK_IDLE); +} static inline void ssleep(unsigned int seconds) { diff --git a/include/linux/device/driver.h b/include/linux/device/driver.h index a498ebcf4993..15e7c5e15d62 100644 --- a/include/linux/device/driver.h +++ b/include/linux/device/driver.h @@ -18,6 +18,7 @@ #include <linux/klist.h> #include <linux/pm.h> #include <linux/device/bus.h> +#include <linux/module.h> /** * enum probe_type - device driver probe type to try diff --git a/include/linux/efi.h b/include/linux/efi.h index dbd39b20e034..ef8dbc0a1522 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -1283,4 +1283,10 @@ static inline struct efi_mokvar_table_entry *efi_mokvar_entry_find( } #endif +#ifdef CONFIG_SYSFB +extern void efifb_setup_from_dmi(struct screen_info *si, const char *opt); +#else +static inline void efifb_setup_from_dmi(struct screen_info *si, const char *opt) { } +#endif + #endif /* _LINUX_EFI_H */ diff --git a/include/linux/fb.h b/include/linux/fb.h index 6f3db99ab990..3da95842b207 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -610,6 +610,7 @@ extern int remove_conflicting_pci_framebuffers(struct pci_dev *pdev, const char *name); extern int remove_conflicting_framebuffers(struct apertures_struct *a, const char *name, bool primary); +extern bool is_firmware_framebuffer(struct apertures_struct *a); extern int fb_prepare_logo(struct fb_info *fb_info, int rotate); extern int fb_show_logo(struct fb_info *fb_info, int rotate); extern char* fb_get_buffer_offset(struct fb_info *info, struct fb_pixmap *buf, u32 size); diff --git a/include/linux/filter.h b/include/linux/filter.h index 24b7ed2677af..7f1e88e3e2b5 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -6,6 +6,7 @@ #define __LINUX_FILTER_H__ #include <linux/atomic.h> +#include <linux/bpf.h> #include <linux/refcount.h> #include <linux/compat.h> #include <linux/skbuff.h> @@ -26,7 +27,6 @@ #include <asm/byteorder.h> #include <uapi/linux/filter.h> -#include <uapi/linux/bpf.h> struct sk_buff; struct sock; @@ -640,9 +640,6 @@ static __always_inline u32 bpf_prog_run(const struct bpf_prog *prog, const void * This uses migrate_disable/enable() explicitly to document that the * invocation of a BPF program does not require reentrancy protection * against a BPF program which is invoked from a preempting task. - * - * For non RT enabled kernels migrate_disable/enable() maps to - * preempt_disable/enable(), i.e. it disables also preemption. */ static inline u32 bpf_prog_run_pin_on_cpu(const struct bpf_prog *prog, const void *ctx) diff --git a/include/linux/fs.h b/include/linux/fs.h index 1cb616fc1105..bbf812ce89a8 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2518,7 +2518,6 @@ struct file_system_type { #define FS_USERNS_MOUNT 8 /* Can be mounted by userns root */ #define FS_DISALLOW_NOTIFY_PERM 16 /* Disable fanotify permission events */ #define FS_ALLOW_IDMAP 32 /* FS has been updated to handle vfs idmappings. */ -#define FS_THP_SUPPORT 8192 /* Remove once all fs converted */ #define FS_RENAME_DOES_D_MOVE 32768 /* FS will handle d_move() during rename() internally. */ int (*init_fs_context)(struct fs_context *); const struct fs_parameter_spec *parameters; diff --git a/include/linux/gfp.h b/include/linux/gfp.h index b976c4177299..8fcc38467af6 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -624,7 +624,7 @@ extern unsigned long get_zeroed_page(gfp_t gfp_mask); void *alloc_pages_exact(size_t size, gfp_t gfp_mask) __alloc_size(1); void free_pages_exact(void *virt, size_t size); -__meminit void *alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask) __alloc_size(1); +__meminit void *alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask) __alloc_size(2); #define __get_free_page(gfp_mask) \ __get_free_pages((gfp_mask), 0) diff --git a/include/linux/hid.h b/include/linux/hid.h index 9e067f937dbc..f453be385bd4 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -840,6 +840,11 @@ static inline bool hid_is_using_ll_driver(struct hid_device *hdev, return hdev->ll_driver == driver; } +static inline bool hid_is_usb(struct hid_device *hdev) +{ + return hid_is_using_ll_driver(hdev, &usb_hid_driver); +} + #define PM_HINT_FULLON 1<<5 #define PM_HINT_NORMAL 1<<1 diff --git a/include/linux/highmem.h b/include/linux/highmem.h index 25aff0f2ed0b..39bb9b47fa9c 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -5,12 +5,11 @@ #include <linux/fs.h> #include <linux/kernel.h> #include <linux/bug.h> +#include <linux/cacheflush.h> #include <linux/mm.h> #include <linux/uaccess.h> #include <linux/hardirq.h> -#include <asm/cacheflush.h> - #include "highmem-internal.h" /** @@ -231,10 +230,10 @@ static inline void tag_clear_highpage(struct page *page) * If we pass in a base or tail page, we can zero up to PAGE_SIZE. * If we pass in a head page, we can zero up to the size of the compound page. */ -#if defined(CONFIG_HIGHMEM) && defined(CONFIG_TRANSPARENT_HUGEPAGE) +#ifdef CONFIG_HIGHMEM void zero_user_segments(struct page *page, unsigned start1, unsigned end1, unsigned start2, unsigned end2); -#else /* !HIGHMEM || !TRANSPARENT_HUGEPAGE */ +#else static inline void zero_user_segments(struct page *page, unsigned start1, unsigned end1, unsigned start2, unsigned end2) @@ -254,7 +253,7 @@ static inline void zero_user_segments(struct page *page, for (i = 0; i < compound_nr(page); i++) flush_dcache_page(page + i); } -#endif /* !HIGHMEM || !TRANSPARENT_HUGEPAGE */ +#endif static inline void zero_user_segment(struct page *page, unsigned start, unsigned end) @@ -364,4 +363,42 @@ static inline void memzero_page(struct page *page, size_t offset, size_t len) kunmap_local(addr); } +/** + * folio_zero_segments() - Zero two byte ranges in a folio. + * @folio: The folio to write to. + * @start1: The first byte to zero. + * @xend1: One more than the last byte in the first range. + * @start2: The first byte to zero in the second range. + * @xend2: One more than the last byte in the second range. + */ +static inline void folio_zero_segments(struct folio *folio, + size_t start1, size_t xend1, size_t start2, size_t xend2) +{ + zero_user_segments(&folio->page, start1, xend1, start2, xend2); +} + +/** + * folio_zero_segment() - Zero a byte range in a folio. + * @folio: The folio to write to. + * @start: The first byte to zero. + * @xend: One more than the last byte to zero. + */ +static inline void folio_zero_segment(struct folio *folio, + size_t start, size_t xend) +{ + zero_user_segments(&folio->page, start, xend, 0, 0); +} + +/** + * folio_zero_range() - Zero a byte range in a folio. + * @folio: The folio to write to. + * @start: The first byte to zero. + * @length: The number of bytes to zero. + */ +static inline void folio_zero_range(struct folio *folio, + size_t start, size_t length) +{ + zero_user_segments(&folio->page, start, start + length, 0, 0); +} + #endif /* _LINUX_HIGHMEM_H */ diff --git a/include/linux/instrumentation.h b/include/linux/instrumentation.h index fa2cd8c63dcc..24359b4a9605 100644 --- a/include/linux/instrumentation.h +++ b/include/linux/instrumentation.h @@ -11,7 +11,7 @@ asm volatile(__stringify(c) ": nop\n\t" \ ".pushsection .discard.instr_begin\n\t" \ ".long " __stringify(c) "b - .\n\t" \ - ".popsection\n\t"); \ + ".popsection\n\t" : : "i" (c)); \ }) #define instrumentation_begin() __instrumentation_begin(__COUNTER__) @@ -50,7 +50,7 @@ asm volatile(__stringify(c) ": nop\n\t" \ ".pushsection .discard.instr_end\n\t" \ ".long " __stringify(c) "b - .\n\t" \ - ".popsection\n\t"); \ + ".popsection\n\t" : : "i" (c)); \ }) #define instrumentation_end() __instrumentation_end(__COUNTER__) #else diff --git a/include/linux/intel-ish-client-if.h b/include/linux/intel-ish-client-if.h index aee8ff4739b1..f45f13304add 100644 --- a/include/linux/intel-ish-client-if.h +++ b/include/linux/intel-ish-client-if.h @@ -9,7 +9,7 @@ #define _INTEL_ISH_CLIENT_IF_H_ #include <linux/device.h> -#include <linux/uuid.h> +#include <linux/mod_devicetable.h> struct ishtp_cl_device; struct ishtp_device; @@ -40,7 +40,7 @@ enum cl_state { struct ishtp_cl_driver { struct device_driver driver; const char *name; - const guid_t *guid; + const struct ishtp_device_id *id; int (*probe)(struct ishtp_cl_device *dev); void (*remove)(struct ishtp_cl_device *dev); int (*reset)(struct ishtp_cl_device *dev); diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 20c1f968da7c..a59d25f19385 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -133,6 +133,7 @@ struct inet6_skb_parm { __u16 dsthao; #endif __u16 frag_max_size; + __u16 srhoff; #define IP6SKB_XFRM_TRANSFORMED 1 #define IP6SKB_FORWARDED 2 @@ -142,6 +143,7 @@ struct inet6_skb_parm { #define IP6SKB_HOPBYHOP 32 #define IP6SKB_L3SLAVE 64 #define IP6SKB_JUMBOGRAM 128 +#define IP6SKB_SEG6 256 }; #if defined(CONFIG_NET_L3_MASTER_DEV) diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index e974caf39d3e..8c8f7a4d93af 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -153,6 +153,8 @@ struct kretprobe { struct kretprobe_holder *rph; }; +#define KRETPROBE_MAX_DATA_SIZE 4096 + struct kretprobe_instance { union { struct freelist_node freelist; diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 8adcf1fa8096..9dc7cb239d21 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -405,8 +405,8 @@ phys_addr_t memblock_alloc_range_nid(phys_addr_t size, phys_addr_t end, int nid, bool exact_nid); phys_addr_t memblock_phys_alloc_try_nid(phys_addr_t size, phys_addr_t align, int nid); -static inline phys_addr_t memblock_phys_alloc(phys_addr_t size, - phys_addr_t align) +static __always_inline phys_addr_t memblock_phys_alloc(phys_addr_t size, + phys_addr_t align) { return memblock_phys_alloc_range(size, align, 0, MEMBLOCK_ALLOC_ACCESSIBLE); diff --git a/include/linux/mhi.h b/include/linux/mhi.h index 723985879035..a5cc4cdf9cc8 100644 --- a/include/linux/mhi.h +++ b/include/linux/mhi.h @@ -664,6 +664,19 @@ int mhi_pm_suspend(struct mhi_controller *mhi_cntrl); int mhi_pm_resume(struct mhi_controller *mhi_cntrl); /** + * mhi_pm_resume_force - Force resume MHI from suspended state + * @mhi_cntrl: MHI controller + * + * Resume the device irrespective of its MHI state. As per the MHI spec, devices + * has to be in M3 state during resume. But some devices seem to be in a + * different MHI state other than M3 but they continue working fine if allowed. + * This API is intented to be used for such devices. + * + * Return: 0 if the resume succeeds, a negative error code otherwise + */ +int mhi_pm_resume_force(struct mhi_controller *mhi_cntrl); + +/** * mhi_download_rddm_image - Download ramdump image from device for * debugging purpose. * @mhi_cntrl: MHI controller diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 3636df90899a..fbaab440a484 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -9698,7 +9698,10 @@ struct mlx5_ifc_mcam_access_reg_bits { u8 regs_84_to_68[0x11]; u8 tracer_registers[0x4]; - u8 regs_63_to_32[0x20]; + u8 regs_63_to_46[0x12]; + u8 mrtc[0x1]; + u8 regs_44_to_32[0xd]; + u8 regs_31_to_0[0x20]; }; diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 58e744b78c2c..936dc0b6c226 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -277,6 +277,7 @@ enum vmscan_throttle_state { VMSCAN_THROTTLE_WRITEBACK, VMSCAN_THROTTLE_ISOLATED, VMSCAN_THROTTLE_NOPROGRESS, + VMSCAN_THROTTLE_CONGESTED, NR_VMSCAN_THROTTLE, }; diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index ae2e75d15b21..4bb71979a8fd 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -895,4 +895,18 @@ struct dfl_device_id { kernel_ulong_t driver_data; }; +/* ISHTP (Integrated Sensor Hub Transport Protocol) */ + +#define ISHTP_MODULE_PREFIX "ishtp:" + +/** + * struct ishtp_device_id - ISHTP device identifier + * @guid: GUID of the device. + * @driver_data: pointer to driver specific data + */ +struct ishtp_device_id { + guid_t guid; + kernel_ulong_t driver_data; +}; + #endif /* LINUX_MOD_DEVICETABLE_H */ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 3ec42495a43a..6aadcc0ecb5b 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1937,7 +1937,7 @@ enum netdev_ml_priv_type { * @udp_tunnel_nic: UDP tunnel offload state * @xdp_state: stores info on attached XDP BPF programs * - * @nested_level: Used as as a parameter of spin_lock_nested() of + * @nested_level: Used as a parameter of spin_lock_nested() of * dev->addr_list_lock. * @unlink_list: As netif_addr_lock() can be called recursively, * keep a list of interfaces to be deleted. @@ -4404,7 +4404,8 @@ static inline u32 netif_msg_init(int debug_value, int default_msg_enable_bits) static inline void __netif_tx_lock(struct netdev_queue *txq, int cpu) { spin_lock(&txq->_xmit_lock); - txq->xmit_lock_owner = cpu; + /* Pairs with READ_ONCE() in __dev_queue_xmit() */ + WRITE_ONCE(txq->xmit_lock_owner, cpu); } static inline bool __netif_tx_acquire(struct netdev_queue *txq) @@ -4421,26 +4422,32 @@ static inline void __netif_tx_release(struct netdev_queue *txq) static inline void __netif_tx_lock_bh(struct netdev_queue *txq) { spin_lock_bh(&txq->_xmit_lock); - txq->xmit_lock_owner = smp_processor_id(); + /* Pairs with READ_ONCE() in __dev_queue_xmit() */ + WRITE_ONCE(txq->xmit_lock_owner, smp_processor_id()); } static inline bool __netif_tx_trylock(struct netdev_queue *txq) { bool ok = spin_trylock(&txq->_xmit_lock); - if (likely(ok)) - txq->xmit_lock_owner = smp_processor_id(); + + if (likely(ok)) { + /* Pairs with READ_ONCE() in __dev_queue_xmit() */ + WRITE_ONCE(txq->xmit_lock_owner, smp_processor_id()); + } return ok; } static inline void __netif_tx_unlock(struct netdev_queue *txq) { - txq->xmit_lock_owner = -1; + /* Pairs with READ_ONCE() in __dev_queue_xmit() */ + WRITE_ONCE(txq->xmit_lock_owner, -1); spin_unlock(&txq->_xmit_lock); } static inline void __netif_tx_unlock_bh(struct netdev_queue *txq) { - txq->xmit_lock_owner = -1; + /* Pairs with READ_ONCE() in __dev_queue_xmit() */ + WRITE_ONCE(txq->xmit_lock_owner, -1); spin_unlock_bh(&txq->_xmit_lock); } diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 52ec4b5e5615..b5f14d581113 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -686,13 +686,13 @@ static inline bool test_set_page_writeback(struct page *page) __PAGEFLAG(Head, head, PF_ANY) CLEARPAGEFLAG(Head, head, PF_ANY) -/* Whether there are one or multiple pages in a folio */ -static inline bool folio_test_single(struct folio *folio) -{ - return !folio_test_head(folio); -} - -static inline bool folio_test_multi(struct folio *folio) +/** + * folio_test_large() - Does this folio contain more than one page? + * @folio: The folio to test. + * + * Return: True if the folio is larger than one page. + */ +static inline bool folio_test_large(struct folio *folio) { return folio_test_head(folio); } diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 1a0c646eb6ff..d150a9082b31 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -84,7 +84,7 @@ enum mapping_flags { AS_EXITING = 4, /* final truncate in progress */ /* writeback related tags are not used */ AS_NO_WRITEBACK_TAGS = 5, - AS_THP_SUPPORT = 6, /* THPs supported */ + AS_LARGE_FOLIO_SUPPORT = 6, }; /** @@ -176,9 +176,25 @@ static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask) m->gfp_mask = mask; } -static inline bool mapping_thp_support(struct address_space *mapping) +/** + * mapping_set_large_folios() - Indicate the file supports large folios. + * @mapping: The file. + * + * The filesystem should call this function in its inode constructor to + * indicate that the VFS can use large folios to cache the contents of + * the file. + * + * Context: This should not be called while the inode is active as it + * is non-atomic. + */ +static inline void mapping_set_large_folios(struct address_space *mapping) +{ + __set_bit(AS_LARGE_FOLIO_SUPPORT, &mapping->flags); +} + +static inline bool mapping_large_folio_support(struct address_space *mapping) { - return test_bit(AS_THP_SUPPORT, &mapping->flags); + return test_bit(AS_LARGE_FOLIO_SUPPORT, &mapping->flags); } static inline int filemap_nr_thps(struct address_space *mapping) @@ -193,7 +209,7 @@ static inline int filemap_nr_thps(struct address_space *mapping) static inline void filemap_nr_thps_inc(struct address_space *mapping) { #ifdef CONFIG_READ_ONLY_THP_FOR_FS - if (!mapping_thp_support(mapping)) + if (!mapping_large_folio_support(mapping)) atomic_inc(&mapping->nr_thps); #else WARN_ON_ONCE(1); @@ -203,7 +219,7 @@ static inline void filemap_nr_thps_inc(struct address_space *mapping) static inline void filemap_nr_thps_dec(struct address_space *mapping) { #ifdef CONFIG_READ_ONLY_THP_FOR_FS - if (!mapping_thp_support(mapping)) + if (!mapping_large_folio_support(mapping)) atomic_dec(&mapping->nr_thps); #else WARN_ON_ONCE(1); @@ -269,7 +285,6 @@ static inline struct inode *folio_inode(struct folio *folio) static inline bool page_cache_add_speculative(struct page *page, int count) { - VM_BUG_ON_PAGE(PageTail(page), page); return folio_ref_try_add_rcu((struct folio *)page, count); } diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h index b31d3f3312ce..d73a1c08c3e3 100644 --- a/include/linux/percpu-refcount.h +++ b/include/linux/percpu-refcount.h @@ -51,9 +51,9 @@ #define _LINUX_PERCPU_REFCOUNT_H #include <linux/atomic.h> -#include <linux/kernel.h> #include <linux/percpu.h> #include <linux/rcupdate.h> +#include <linux/types.h> #include <linux/gfp.h> struct percpu_ref; diff --git a/include/linux/phy.h b/include/linux/phy.h index 96e43fbb2dd8..cbf03a5f9cf5 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -538,11 +538,12 @@ struct macsec_ops; * @mac_managed_pm: Set true if MAC driver takes of suspending/resuming PHY * @state: State of the PHY for management purposes * @dev_flags: Device-specific flags used by the PHY driver. - * Bits [15:0] are free to use by the PHY driver to communicate - * driver specific behavior. - * Bits [23:16] are currently reserved for future use. - * Bits [31:24] are reserved for defining generic - * PHY driver behavior. + * + * - Bits [15:0] are free to use by the PHY driver to communicate + * driver specific behavior. + * - Bits [23:16] are currently reserved for future use. + * - Bits [31:24] are reserved for defining generic + * PHY driver behavior. * @irq: IRQ number of the PHY's interrupt (-1 if none) * @phy_timer: The timer for handling the state machine * @phylink: Pointer to phylink instance for this PHY diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h index 222da43b7096..eddd66d426ca 100644 --- a/include/linux/pm_runtime.h +++ b/include/linux/pm_runtime.h @@ -129,7 +129,7 @@ static inline bool pm_runtime_suspended(struct device *dev) * pm_runtime_active - Check whether or not a device is runtime-active. * @dev: Target device. * - * Return %true if runtime PM is enabled for @dev and its runtime PM status is + * Return %true if runtime PM is disabled for @dev or its runtime PM status is * %RPM_ACTIVE, or %false otherwise. * * Note that the return value of this function can only be trusted if it is diff --git a/include/linux/ptp_classify.h b/include/linux/ptp_classify.h index ae04968a3a47..9afd34a2d36c 100644 --- a/include/linux/ptp_classify.h +++ b/include/linux/ptp_classify.h @@ -37,6 +37,7 @@ #define PTP_MSGTYPE_PDELAY_RESP 0x3 #define PTP_EV_PORT 319 +#define PTP_GEN_PORT 320 #define PTP_GEN_BIT 0x08 /* indicates general message, if set in message type */ #define OFF_PTP_SOURCE_UUID 22 /* PTPv1 only */ diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index bd7a73db2e66..54cf566616ae 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -499,7 +499,8 @@ struct regulator_irq_data { * best to shut-down regulator(s) or reboot the SOC if error * handling is repeatedly failing. If fatal_cnt is given the IRQ * handling is aborted if it fails for fatal_cnt times and die() - * callback (if populated) or BUG() is called to try to prevent + * callback (if populated) is called. If die() is not populated + * poweroff for the system is attempted in order to prevent any * further damage. * @reread_ms: The time which is waited before attempting to re-read status * at the worker if IC reading fails. Immediate re-read is done @@ -516,11 +517,12 @@ struct regulator_irq_data { * @data: Driver private data pointer which will be passed as such to * the renable, map_event and die callbacks in regulator_irq_data. * @die: Protection callback. If IC status reading or recovery actions - * fail fatal_cnt times this callback or BUG() is called. This - * callback should implement a final protection attempt like - * disabling the regulator. If protection succeeded this may - * return 0. If anything else is returned the core assumes final - * protection failed and calls BUG() as a last resort. + * fail fatal_cnt times this callback is called or system is + * powered off. This callback should implement a final protection + * attempt like disabling the regulator. If protection succeeded + * die() may return 0. If anything else is returned the core + * assumes final protection failed and attempts to perform a + * poweroff as a last resort. * @map_event: Driver callback to map IRQ status into regulator devices with * events / errors. NOTE: callback MUST initialize both the * errors and notifs for all rdevs which it signals having diff --git a/include/linux/sched/cputime.h b/include/linux/sched/cputime.h index 6c9f19a33865..ce3c58286062 100644 --- a/include/linux/sched/cputime.h +++ b/include/linux/sched/cputime.h @@ -18,15 +18,16 @@ #endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN -extern void task_cputime(struct task_struct *t, +extern bool task_cputime(struct task_struct *t, u64 *utime, u64 *stime); extern u64 task_gtime(struct task_struct *t); #else -static inline void task_cputime(struct task_struct *t, +static inline bool task_cputime(struct task_struct *t, u64 *utime, u64 *stime) { *utime = t->utime; *stime = t->stime; + return false; } static inline u64 task_gtime(struct task_struct *t) diff --git a/include/linux/siphash.h b/include/linux/siphash.h index bf21591a9e5e..0cda61855d90 100644 --- a/include/linux/siphash.h +++ b/include/linux/siphash.h @@ -27,9 +27,7 @@ static inline bool siphash_key_is_zero(const siphash_key_t *key) } u64 __siphash_aligned(const void *data, size_t len, const siphash_key_t *key); -#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS u64 __siphash_unaligned(const void *data, size_t len, const siphash_key_t *key); -#endif u64 siphash_1u64(const u64 a, const siphash_key_t *key); u64 siphash_2u64(const u64 a, const u64 b, const siphash_key_t *key); @@ -82,10 +80,9 @@ static inline u64 ___siphash_aligned(const __le64 *data, size_t len, static inline u64 siphash(const void *data, size_t len, const siphash_key_t *key) { -#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS - if (!IS_ALIGNED((unsigned long)data, SIPHASH_ALIGNMENT)) + if (IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) || + !IS_ALIGNED((unsigned long)data, SIPHASH_ALIGNMENT)) return __siphash_unaligned(data, len, key); -#endif return ___siphash_aligned(data, len, key); } @@ -96,10 +93,8 @@ typedef struct { u32 __hsiphash_aligned(const void *data, size_t len, const hsiphash_key_t *key); -#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS u32 __hsiphash_unaligned(const void *data, size_t len, const hsiphash_key_t *key); -#endif u32 hsiphash_1u32(const u32 a, const hsiphash_key_t *key); u32 hsiphash_2u32(const u32 a, const u32 b, const hsiphash_key_t *key); @@ -135,10 +130,9 @@ static inline u32 ___hsiphash_aligned(const __le32 *data, size_t len, static inline u32 hsiphash(const void *data, size_t len, const hsiphash_key_t *key) { -#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS - if (!IS_ALIGNED((unsigned long)data, HSIPHASH_ALIGNMENT)) + if (IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) || + !IS_ALIGNED((unsigned long)data, HSIPHASH_ALIGNMENT)) return __hsiphash_unaligned(data, len, key); -#endif return ___hsiphash_aligned(data, len, key); } diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index c8cb7e697d47..4507d77d6941 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -286,6 +286,7 @@ struct nf_bridge_info { struct tc_skb_ext { __u32 chain; __u16 mru; + __u16 zone; bool post_ct; }; #endif @@ -1380,7 +1381,7 @@ skb_flow_dissect_ct(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, u16 *ctinfo_map, size_t mapsize, - bool post_ct); + bool post_ct, u16 zone); void skb_flow_dissect_tunnel_info(const struct sk_buff *skb, struct flow_dissector *flow_dissector, diff --git a/include/linux/tee_drv.h b/include/linux/tee_drv.h index a1f03461369b..cf5999626e28 100644 --- a/include/linux/tee_drv.h +++ b/include/linux/tee_drv.h @@ -195,7 +195,7 @@ int tee_session_calc_client_uuid(uuid_t *uuid, u32 connection_method, * @offset: offset of buffer in user space * @pages: locked pages from userspace * @num_pages: number of locked pages - * @dmabuf: dmabuf used to for exporting to user space + * @refcount: reference counter * @flags: defined by TEE_SHM_* in tee_drv.h * @id: unique id of a shared memory object on this device, shared * with user space @@ -214,7 +214,7 @@ struct tee_shm { unsigned int offset; struct page **pages; size_t num_pages; - struct dma_buf *dmabuf; + refcount_t refcount; u32 flags; int id; u64 sec_world_id; diff --git a/include/linux/virtio.h b/include/linux/virtio.h index 44d0e09da2d9..41edbc01ffa4 100644 --- a/include/linux/virtio.h +++ b/include/linux/virtio.h @@ -152,7 +152,6 @@ size_t virtio_max_dma_size(struct virtio_device *vdev); * @feature_table_size: number of entries in the feature table array. * @feature_table_legacy: same as feature_table but when working in legacy mode. * @feature_table_size_legacy: number of entries in feature table legacy array. - * @suppress_used_validation: set to not have core validate used length * @probe: the function to call when a device is found. Returns 0 or -errno. * @scan: optional function to call after successful probe; intended * for virtio-scsi to invoke a scan. @@ -169,7 +168,6 @@ struct virtio_driver { unsigned int feature_table_size; const unsigned int *feature_table_legacy; unsigned int feature_table_size_legacy; - bool suppress_used_validation; int (*validate)(struct virtio_device *dev); int (*probe)(struct virtio_device *dev); void (*scan)(struct virtio_device *dev); diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h index 04e87f4b9417..a960de68ac69 100644 --- a/include/linux/virtio_net.h +++ b/include/linux/virtio_net.h @@ -7,9 +7,27 @@ #include <uapi/linux/udp.h> #include <uapi/linux/virtio_net.h> +static inline bool virtio_net_hdr_match_proto(__be16 protocol, __u8 gso_type) +{ + switch (gso_type & ~VIRTIO_NET_HDR_GSO_ECN) { + case VIRTIO_NET_HDR_GSO_TCPV4: + return protocol == cpu_to_be16(ETH_P_IP); + case VIRTIO_NET_HDR_GSO_TCPV6: + return protocol == cpu_to_be16(ETH_P_IPV6); + case VIRTIO_NET_HDR_GSO_UDP: + return protocol == cpu_to_be16(ETH_P_IP) || + protocol == cpu_to_be16(ETH_P_IPV6); + default: + return false; + } +} + static inline int virtio_net_hdr_set_proto(struct sk_buff *skb, const struct virtio_net_hdr *hdr) { + if (skb->protocol) + return 0; + switch (hdr->gso_type & ~VIRTIO_NET_HDR_GSO_ECN) { case VIRTIO_NET_HDR_GSO_TCPV4: case VIRTIO_NET_HDR_GSO_UDP: @@ -88,9 +106,12 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb, if (!skb->protocol) { __be16 protocol = dev_parse_header_protocol(skb); - virtio_net_hdr_set_proto(skb, hdr); - if (protocol && protocol != skb->protocol) + if (!protocol) + virtio_net_hdr_set_proto(skb, hdr); + else if (!virtio_net_hdr_match_proto(protocol, hdr->gso_type)) return -EINVAL; + else + skb->protocol = protocol; } retry: if (!skb_flow_dissect_flow_keys_basic(NULL, skb, &keys, diff --git a/include/linux/wait.h b/include/linux/wait.h index 2d0df57c9902..851e07da2583 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -217,6 +217,7 @@ void __wake_up_sync_key(struct wait_queue_head *wq_head, unsigned int mode, void void __wake_up_locked_sync_key(struct wait_queue_head *wq_head, unsigned int mode, void *key); void __wake_up_locked(struct wait_queue_head *wq_head, unsigned int mode, int nr); void __wake_up_sync(struct wait_queue_head *wq_head, unsigned int mode); +void __wake_up_pollfree(struct wait_queue_head *wq_head); #define wake_up(x) __wake_up(x, TASK_NORMAL, 1, NULL) #define wake_up_nr(x, nr) __wake_up(x, TASK_NORMAL, nr, NULL) @@ -245,6 +246,31 @@ void __wake_up_sync(struct wait_queue_head *wq_head, unsigned int mode); #define wake_up_interruptible_sync_poll_locked(x, m) \ __wake_up_locked_sync_key((x), TASK_INTERRUPTIBLE, poll_to_key(m)) +/** + * wake_up_pollfree - signal that a polled waitqueue is going away + * @wq_head: the wait queue head + * + * In the very rare cases where a ->poll() implementation uses a waitqueue whose + * lifetime is tied to a task rather than to the 'struct file' being polled, + * this function must be called before the waitqueue is freed so that + * non-blocking polls (e.g. epoll) are notified that the queue is going away. + * + * The caller must also RCU-delay the freeing of the wait_queue_head, e.g. via + * an explicit synchronize_rcu() or call_rcu(), or via SLAB_TYPESAFE_BY_RCU. + */ +static inline void wake_up_pollfree(struct wait_queue_head *wq_head) +{ + /* + * For performance reasons, we don't always take the queue lock here. + * Therefore, we might race with someone removing the last entry from + * the queue, and proceed while they still hold the queue lock. + * However, rcu_read_lock() is required to be held in such cases, so we + * can safely proceed with an RCU-delayed free. + */ + if (waitqueue_active(wq_head)) + __wake_up_pollfree(wq_head); +} + #define ___wait_cond_timeout(condition) \ ({ \ bool __cond = (condition); \ diff --git a/include/net/bond_alb.h b/include/net/bond_alb.h index f6af76c87a6c..191c36afa1f4 100644 --- a/include/net/bond_alb.h +++ b/include/net/bond_alb.h @@ -126,7 +126,7 @@ struct tlb_slave_info { struct alb_bond_info { struct tlb_client_info *tx_hashtbl; /* Dynamically allocated */ u32 unbalanced_load; - int tx_rebalance_counter; + atomic_t tx_rebalance_counter; int lp_counter; /* -------- rlb parameters -------- */ int rlb_enabled; diff --git a/include/net/busy_poll.h b/include/net/busy_poll.h index 4202c609bb0b..c4898fcbf923 100644 --- a/include/net/busy_poll.h +++ b/include/net/busy_poll.h @@ -133,6 +133,19 @@ static inline void sk_mark_napi_id(struct sock *sk, const struct sk_buff *skb) if (unlikely(READ_ONCE(sk->sk_napi_id) != skb->napi_id)) WRITE_ONCE(sk->sk_napi_id, skb->napi_id); #endif + sk_rx_queue_update(sk, skb); +} + +/* Variant of sk_mark_napi_id() for passive flow setup, + * as sk->sk_napi_id and sk->sk_rx_queue_mapping content + * needs to be set. + */ +static inline void sk_mark_napi_id_set(struct sock *sk, + const struct sk_buff *skb) +{ +#ifdef CONFIG_NET_RX_BUSY_POLL + WRITE_ONCE(sk->sk_napi_id, skb->napi_id); +#endif sk_rx_queue_set(sk, skb); } diff --git a/include/net/dst_cache.h b/include/net/dst_cache.h index 67634675e919..df6622a5fe98 100644 --- a/include/net/dst_cache.h +++ b/include/net/dst_cache.h @@ -80,6 +80,17 @@ static inline void dst_cache_reset(struct dst_cache *dst_cache) } /** + * dst_cache_reset_now - invalidate the cache contents immediately + * @dst_cache: the cache + * + * The caller must be sure there are no concurrent users, as this frees + * all dst_cache users immediately, rather than waiting for the next + * per-cpu usage like dst_cache_reset does. Most callers should use the + * higher speed lazily-freed dst_cache_reset function instead. + */ +void dst_cache_reset_now(struct dst_cache *dst_cache); + +/** * dst_cache_init - initialize the cache, allocating the required storage * @dst_cache: the cache * @gfp: allocation flags diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h index 4b10676c69d1..bd07484ab9dd 100644 --- a/include/net/fib_rules.h +++ b/include/net/fib_rules.h @@ -69,7 +69,7 @@ struct fib_rules_ops { int (*action)(struct fib_rule *, struct flowi *, int, struct fib_lookup_arg *); - bool (*suppress)(struct fib_rule *, + bool (*suppress)(struct fib_rule *, int, struct fib_lookup_arg *); int (*match)(struct fib_rule *, struct flowi *, int); @@ -218,7 +218,9 @@ INDIRECT_CALLABLE_DECLARE(int fib4_rule_action(struct fib_rule *rule, struct fib_lookup_arg *arg)); INDIRECT_CALLABLE_DECLARE(bool fib6_rule_suppress(struct fib_rule *rule, + int flags, struct fib_lookup_arg *arg)); INDIRECT_CALLABLE_DECLARE(bool fib4_rule_suppress(struct fib_rule *rule, + int flags, struct fib_lookup_arg *arg)); #endif diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index c412dde4d67d..83b8070d1cc9 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -485,6 +485,7 @@ int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh, struct fib6_config *cfg, gfp_t gfp_flags, struct netlink_ext_ack *extack); void fib6_nh_release(struct fib6_nh *fib6_nh); +void fib6_nh_release_dsts(struct fib6_nh *fib6_nh); int call_fib6_entry_notifiers(struct net *net, enum fib_event_type event_type, diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index ab5348e57db1..3417ba2d27ad 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -438,7 +438,7 @@ int fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, #ifdef CONFIG_IP_ROUTE_CLASSID static inline int fib_num_tclassid_users(struct net *net) { - return net->ipv4.fib_num_tclassid_users; + return atomic_read(&net->ipv4.fib_num_tclassid_users); } #else static inline int fib_num_tclassid_users(struct net *net) diff --git a/include/net/ipv6_stubs.h b/include/net/ipv6_stubs.h index afbce90c4480..45e0339be6fa 100644 --- a/include/net/ipv6_stubs.h +++ b/include/net/ipv6_stubs.h @@ -47,6 +47,7 @@ struct ipv6_stub { struct fib6_config *cfg, gfp_t gfp_flags, struct netlink_ext_ack *extack); void (*fib6_nh_release)(struct fib6_nh *fib6_nh); + void (*fib6_nh_release_dsts)(struct fib6_nh *fib6_nh); void (*fib6_update_sernum)(struct net *net, struct fib6_info *rt); int (*ip6_del_rt)(struct net *net, struct fib6_info *rt, bool skip_notify); void (*fib6_rt_update)(struct net *net, struct fib6_info *rt, diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index cc663c68ddc4..d24b0a34c8f0 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -276,14 +276,14 @@ static inline bool nf_is_loopback_packet(const struct sk_buff *skb) /* jiffies until ct expires, 0 if already expired */ static inline unsigned long nf_ct_expires(const struct nf_conn *ct) { - s32 timeout = ct->timeout - nfct_time_stamp; + s32 timeout = READ_ONCE(ct->timeout) - nfct_time_stamp; return timeout > 0 ? timeout : 0; } static inline bool nf_ct_is_expired(const struct nf_conn *ct) { - return (__s32)(ct->timeout - nfct_time_stamp) <= 0; + return (__s32)(READ_ONCE(ct->timeout) - nfct_time_stamp) <= 0; } /* use after obtaining a reference count */ @@ -302,7 +302,7 @@ static inline bool nf_ct_should_gc(const struct nf_conn *ct) static inline void nf_ct_offload_timeout(struct nf_conn *ct) { if (nf_ct_expires(ct) < NF_CT_DAY / 2) - ct->timeout = nfct_time_stamp + NF_CT_DAY; + WRITE_ONCE(ct->timeout, nfct_time_stamp + NF_CT_DAY); } struct kernel_param; diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 2f65701a43c9..6c5b2efc4f17 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -65,7 +65,7 @@ struct netns_ipv4 { bool fib_has_custom_local_routes; bool fib_offload_disabled; #ifdef CONFIG_IP_ROUTE_CLASSID - int fib_num_tclassid_users; + atomic_t fib_num_tclassid_users; #endif struct hlist_head *fib_table_hash; struct sock *fibnl; diff --git a/include/net/nl802154.h b/include/net/nl802154.h index ddcee128f5d9..145acb8f2509 100644 --- a/include/net/nl802154.h +++ b/include/net/nl802154.h @@ -19,6 +19,8 @@ * */ +#include <linux/types.h> + #define NL802154_GENL_NAME "nl802154" enum nl802154_commands { @@ -150,10 +152,9 @@ enum nl802154_attrs { }; enum nl802154_iftype { - /* for backwards compatibility TODO */ - NL802154_IFTYPE_UNSPEC = -1, + NL802154_IFTYPE_UNSPEC = (~(__u32)0), - NL802154_IFTYPE_NODE, + NL802154_IFTYPE_NODE = 0, NL802154_IFTYPE_MONITOR, NL802154_IFTYPE_COORD, diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h index bf79f3a890af..9e71691c491b 100644 --- a/include/net/pkt_sched.h +++ b/include/net/pkt_sched.h @@ -193,4 +193,20 @@ static inline void skb_txtime_consumed(struct sk_buff *skb) skb->tstamp = ktime_set(0, 0); } +struct tc_skb_cb { + struct qdisc_skb_cb qdisc_cb; + + u16 mru; + bool post_ct; + u16 zone; /* Only valid if post_ct = true */ +}; + +static inline struct tc_skb_cb *tc_skb_cb(const struct sk_buff *skb) +{ + struct tc_skb_cb *cb = (struct tc_skb_cb *)skb->cb; + + BUILD_BUG_ON(sizeof(*cb) > sizeof_field(struct sk_buff, cb)); + return cb; +} + #endif diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 22179b2fda72..c70e6d2b2fdd 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -447,8 +447,6 @@ struct qdisc_skb_cb { }; #define QDISC_CB_PRIV_LEN 20 unsigned char data[QDISC_CB_PRIV_LEN]; - u16 mru; - bool post_ct; }; typedef void tcf_chain_head_change_t(struct tcf_proto *tp_head, void *priv); diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h index 189fdb9db162..3ae61ce2eabd 100644 --- a/include/net/sctp/sctp.h +++ b/include/net/sctp/sctp.h @@ -105,19 +105,18 @@ extern struct percpu_counter sctp_sockets_allocated; int sctp_asconf_mgmt(struct sctp_sock *, struct sctp_sockaddr_entry *); struct sk_buff *sctp_skb_recv_datagram(struct sock *, int, int, int *); +typedef int (*sctp_callback_t)(struct sctp_endpoint *, struct sctp_transport *, void *); void sctp_transport_walk_start(struct rhashtable_iter *iter); void sctp_transport_walk_stop(struct rhashtable_iter *iter); struct sctp_transport *sctp_transport_get_next(struct net *net, struct rhashtable_iter *iter); struct sctp_transport *sctp_transport_get_idx(struct net *net, struct rhashtable_iter *iter, int pos); -int sctp_transport_lookup_process(int (*cb)(struct sctp_transport *, void *), - struct net *net, +int sctp_transport_lookup_process(sctp_callback_t cb, struct net *net, const union sctp_addr *laddr, const union sctp_addr *paddr, void *p); -int sctp_for_each_transport(int (*cb)(struct sctp_transport *, void *), - int (*cb_done)(struct sctp_transport *, void *), - struct net *net, int *pos, void *p); +int sctp_transport_traverse_process(sctp_callback_t cb, sctp_callback_t cb_done, + struct net *net, int *pos, void *p); int sctp_for_each_endpoint(int (*cb)(struct sctp_endpoint *, void *), void *p); int sctp_get_sctp_info(struct sock *sk, struct sctp_association *asoc, struct sctp_info *info); diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 899c29c326ba..8dabd8800006 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -1355,6 +1355,7 @@ struct sctp_endpoint { reconf_enable:1; __u8 strreset_enable; + struct rcu_head rcu; }; /* Recover the outter endpoint structure. */ @@ -1370,7 +1371,7 @@ static inline struct sctp_endpoint *sctp_ep(struct sctp_ep_common *base) struct sctp_endpoint *sctp_endpoint_new(struct sock *, gfp_t); void sctp_endpoint_free(struct sctp_endpoint *); void sctp_endpoint_put(struct sctp_endpoint *); -void sctp_endpoint_hold(struct sctp_endpoint *); +int sctp_endpoint_hold(struct sctp_endpoint *ep); void sctp_endpoint_add_asoc(struct sctp_endpoint *, struct sctp_association *); struct sctp_association *sctp_endpoint_lookup_assoc( const struct sctp_endpoint *ep, diff --git a/include/net/seg6.h b/include/net/seg6.h index 9d19c15e8545..af668f17b398 100644 --- a/include/net/seg6.h +++ b/include/net/seg6.h @@ -58,9 +58,30 @@ extern int seg6_local_init(void); extern void seg6_local_exit(void); extern bool seg6_validate_srh(struct ipv6_sr_hdr *srh, int len, bool reduced); +extern struct ipv6_sr_hdr *seg6_get_srh(struct sk_buff *skb, int flags); +extern void seg6_icmp_srh(struct sk_buff *skb, struct inet6_skb_parm *opt); extern int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto); extern int seg6_do_srh_inline(struct sk_buff *skb, struct ipv6_sr_hdr *osrh); extern int seg6_lookup_nexthop(struct sk_buff *skb, struct in6_addr *nhaddr, u32 tbl_id); + +/* If the packet which invoked an ICMP error contains an SRH return + * the true destination address from within the SRH, otherwise use the + * destination address in the IP header. + */ +static inline const struct in6_addr *seg6_get_daddr(struct sk_buff *skb, + struct inet6_skb_parm *opt) +{ + struct ipv6_sr_hdr *srh; + + if (opt->flags & IP6SKB_SEG6) { + srh = (struct ipv6_sr_hdr *)(skb->data + opt->srhoff); + return &srh->segments[0]; + } + + return NULL; +} + + #endif diff --git a/include/net/sock.h b/include/net/sock.h index b32906e1ab55..d47e9658da28 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -431,7 +431,7 @@ struct sock { #ifdef CONFIG_XFRM struct xfrm_policy __rcu *sk_policy[2]; #endif - struct dst_entry *sk_rx_dst; + struct dst_entry __rcu *sk_rx_dst; int sk_rx_dst_ifindex; u32 sk_rx_dst_cookie; @@ -1913,18 +1913,31 @@ static inline int sk_tx_queue_get(const struct sock *sk) return -1; } -static inline void sk_rx_queue_set(struct sock *sk, const struct sk_buff *skb) +static inline void __sk_rx_queue_set(struct sock *sk, + const struct sk_buff *skb, + bool force_set) { #ifdef CONFIG_SOCK_RX_QUEUE_MAPPING if (skb_rx_queue_recorded(skb)) { u16 rx_queue = skb_get_rx_queue(skb); - if (unlikely(READ_ONCE(sk->sk_rx_queue_mapping) != rx_queue)) + if (force_set || + unlikely(READ_ONCE(sk->sk_rx_queue_mapping) != rx_queue)) WRITE_ONCE(sk->sk_rx_queue_mapping, rx_queue); } #endif } +static inline void sk_rx_queue_set(struct sock *sk, const struct sk_buff *skb) +{ + __sk_rx_queue_set(sk, skb, true); +} + +static inline void sk_rx_queue_update(struct sock *sk, const struct sk_buff *skb) +{ + __sk_rx_queue_set(sk, skb, false); +} + static inline void sk_rx_queue_clear(struct sock *sk) { #ifdef CONFIG_SOCK_RX_QUEUE_MAPPING @@ -2430,19 +2443,22 @@ static inline void sk_stream_moderate_sndbuf(struct sock *sk) * @sk: socket * * Use the per task page_frag instead of the per socket one for - * optimization when we know that we're in the normal context and owns + * optimization when we know that we're in process context and own * everything that's associated with %current. * - * gfpflags_allow_blocking() isn't enough here as direct reclaim may nest - * inside other socket operations and end up recursing into sk_page_frag() - * while it's already in use. + * Both direct reclaim and page faults can nest inside other + * socket operations and end up recursing into sk_page_frag() + * while it's already in use: explicitly avoid task page_frag + * usage if the caller is potentially doing any of them. + * This assumes that page fault handlers use the GFP_NOFS flags. * * Return: a per task page_frag if context allows that, * otherwise a per socket one. */ static inline struct page_frag *sk_page_frag(struct sock *sk) { - if (gfpflags_normal_context(sk->sk_allocation)) + if ((sk->sk_allocation & (__GFP_DIRECT_RECLAIM | __GFP_MEMALLOC | __GFP_FS)) == + (__GFP_DIRECT_RECLAIM | __GFP_FS)) return ¤t->task_frag; return &sk->sk_frag; diff --git a/include/soc/mscc/ocelot_vcap.h b/include/soc/mscc/ocelot_vcap.h index eeb1142aa1b1..4d1dfa1136b2 100644 --- a/include/soc/mscc/ocelot_vcap.h +++ b/include/soc/mscc/ocelot_vcap.h @@ -703,6 +703,8 @@ int ocelot_vcap_filter_add(struct ocelot *ocelot, struct netlink_ext_ack *extack); int ocelot_vcap_filter_del(struct ocelot *ocelot, struct ocelot_vcap_filter *rule); +int ocelot_vcap_filter_replace(struct ocelot *ocelot, + struct ocelot_vcap_filter *filter); struct ocelot_vcap_filter * ocelot_vcap_block_find_filter_by_id(struct ocelot_vcap_block *block, unsigned long cookie, bool tc_offload); diff --git a/include/sound/soc-acpi.h b/include/sound/soc-acpi.h index 31f4c4f9aeea..ac0893df9c76 100644 --- a/include/sound/soc-acpi.h +++ b/include/sound/soc-acpi.h @@ -147,7 +147,7 @@ struct snd_soc_acpi_link_adr { */ /* Descriptor for SST ASoC machine driver */ struct snd_soc_acpi_mach { - const u8 id[ACPI_ID_LEN]; + u8 id[ACPI_ID_LEN]; const struct snd_soc_acpi_codecs *comp_ids; const u32 link_mask; const struct snd_soc_acpi_link_adr *links; diff --git a/include/trace/events/rpcgss.h b/include/trace/events/rpcgss.h index 3ba63319af3c..c9048f3e471b 100644 --- a/include/trace/events/rpcgss.h +++ b/include/trace/events/rpcgss.h @@ -8,7 +8,7 @@ #undef TRACE_SYSTEM #define TRACE_SYSTEM rpcgss -#if !defined(_TRACE_RPCRDMA_H) || defined(TRACE_HEADER_MULTI_READ) +#if !defined(_TRACE_RPCGSS_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_RPCGSS_H #include <linux/tracepoint.h> diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h index f25a6149d3ba..ca2e9009a651 100644 --- a/include/trace/events/vmscan.h +++ b/include/trace/events/vmscan.h @@ -30,12 +30,14 @@ #define _VMSCAN_THROTTLE_WRITEBACK (1 << VMSCAN_THROTTLE_WRITEBACK) #define _VMSCAN_THROTTLE_ISOLATED (1 << VMSCAN_THROTTLE_ISOLATED) #define _VMSCAN_THROTTLE_NOPROGRESS (1 << VMSCAN_THROTTLE_NOPROGRESS) +#define _VMSCAN_THROTTLE_CONGESTED (1 << VMSCAN_THROTTLE_CONGESTED) #define show_throttle_flags(flags) \ (flags) ? __print_flags(flags, "|", \ {_VMSCAN_THROTTLE_WRITEBACK, "VMSCAN_THROTTLE_WRITEBACK"}, \ {_VMSCAN_THROTTLE_ISOLATED, "VMSCAN_THROTTLE_ISOLATED"}, \ - {_VMSCAN_THROTTLE_NOPROGRESS, "VMSCAN_THROTTLE_NOPROGRESS"} \ + {_VMSCAN_THROTTLE_NOPROGRESS, "VMSCAN_THROTTLE_NOPROGRESS"}, \ + {_VMSCAN_THROTTLE_CONGESTED, "VMSCAN_THROTTLE_CONGESTED"} \ ) : "VMSCAN_THROTTLE_NONE" diff --git a/include/uapi/asm-generic/poll.h b/include/uapi/asm-generic/poll.h index 41b509f410bf..f9c520ce4bf4 100644 --- a/include/uapi/asm-generic/poll.h +++ b/include/uapi/asm-generic/poll.h @@ -29,7 +29,7 @@ #define POLLRDHUP 0x2000 #endif -#define POLLFREE (__force __poll_t)0x4000 /* currently only for epoll */ +#define POLLFREE (__force __poll_t)0x4000 #define POLL_BUSY_LOOP (__force __poll_t)0x8000 diff --git a/include/uapi/drm/virtgpu_drm.h b/include/uapi/drm/virtgpu_drm.h index a13e20cc66b4..0512fde5e697 100644 --- a/include/uapi/drm/virtgpu_drm.h +++ b/include/uapi/drm/virtgpu_drm.h @@ -196,6 +196,13 @@ struct drm_virtgpu_context_init { __u64 ctx_set_params; }; +/* + * Event code that's given when VIRTGPU_CONTEXT_PARAM_POLL_RINGS_MASK is in + * effect. The event size is sizeof(drm_event), since there is no additional + * payload. + */ +#define VIRTGPU_EVENT_FENCE_SIGNALED 0x90000000 + #define DRM_IOCTL_VIRTGPU_MAP \ DRM_IOWR(DRM_COMMAND_BASE + DRM_VIRTGPU_MAP, struct drm_virtgpu_map) diff --git a/include/uapi/linux/byteorder/big_endian.h b/include/uapi/linux/byteorder/big_endian.h index 2199adc6a6c2..80aa5c41a763 100644 --- a/include/uapi/linux/byteorder/big_endian.h +++ b/include/uapi/linux/byteorder/big_endian.h @@ -9,6 +9,7 @@ #define __BIG_ENDIAN_BITFIELD #endif +#include <linux/stddef.h> #include <linux/types.h> #include <linux/swab.h> diff --git a/include/uapi/linux/byteorder/little_endian.h b/include/uapi/linux/byteorder/little_endian.h index 601c904fd5cd..cd98982e7523 100644 --- a/include/uapi/linux/byteorder/little_endian.h +++ b/include/uapi/linux/byteorder/little_endian.h @@ -9,6 +9,7 @@ #define __LITTLE_ENDIAN_BITFIELD #endif +#include <linux/stddef.h> #include <linux/types.h> #include <linux/swab.h> diff --git a/include/uapi/linux/if_ether.h b/include/uapi/linux/if_ether.h index 5da4ee234e0b..c0c2f3ed5729 100644 --- a/include/uapi/linux/if_ether.h +++ b/include/uapi/linux/if_ether.h @@ -117,7 +117,7 @@ #define ETH_P_IFE 0xED3E /* ForCES inter-FE LFB type */ #define ETH_P_AF_IUCV 0xFBFB /* IBM af_iucv [ NOT AN OFFICIALLY REGISTERED ID ] */ -#define ETH_P_802_3_MIN 0x0600 /* If the value in the ethernet type is less than this value +#define ETH_P_802_3_MIN 0x0600 /* If the value in the ethernet type is more than this value * then the frame is Ethernet II. Else it is 802.3 */ /* diff --git a/include/uapi/linux/mptcp.h b/include/uapi/linux/mptcp.h index c8cc46f80a16..f106a3941cdf 100644 --- a/include/uapi/linux/mptcp.h +++ b/include/uapi/linux/mptcp.h @@ -136,19 +136,21 @@ struct mptcp_info { * MPTCP_EVENT_REMOVED: token, rem_id * An address has been lost by the peer. * - * MPTCP_EVENT_SUB_ESTABLISHED: token, family, saddr4 | saddr6, - * daddr4 | daddr6, sport, dport, backup, - * if_idx [, error] + * MPTCP_EVENT_SUB_ESTABLISHED: token, family, loc_id, rem_id, + * saddr4 | saddr6, daddr4 | daddr6, sport, + * dport, backup, if_idx [, error] * A new subflow has been established. 'error' should not be set. * - * MPTCP_EVENT_SUB_CLOSED: token, family, saddr4 | saddr6, daddr4 | daddr6, - * sport, dport, backup, if_idx [, error] + * MPTCP_EVENT_SUB_CLOSED: token, family, loc_id, rem_id, saddr4 | saddr6, + * daddr4 | daddr6, sport, dport, backup, if_idx + * [, error] * A subflow has been closed. An error (copy of sk_err) could be set if an * error has been detected for this subflow. * - * MPTCP_EVENT_SUB_PRIORITY: token, family, saddr4 | saddr6, daddr4 | daddr6, - * sport, dport, backup, if_idx [, error] - * The priority of a subflow has changed. 'error' should not be set. + * MPTCP_EVENT_SUB_PRIORITY: token, family, loc_id, rem_id, saddr4 | saddr6, + * daddr4 | daddr6, sport, dport, backup, if_idx + * [, error] + * The priority of a subflow has changed. 'error' should not be set. */ enum mptcp_event_type { MPTCP_EVENT_UNSPEC = 0, diff --git a/include/uapi/linux/nfc.h b/include/uapi/linux/nfc.h index f6e3c8c9c744..4fa4e979e948 100644 --- a/include/uapi/linux/nfc.h +++ b/include/uapi/linux/nfc.h @@ -263,7 +263,7 @@ enum nfc_sdp_attr { #define NFC_SE_ENABLED 0x1 struct sockaddr_nfc { - sa_family_t sa_family; + __kernel_sa_family_t sa_family; __u32 dev_idx; __u32 target_idx; __u32 nfc_protocol; @@ -271,14 +271,14 @@ struct sockaddr_nfc { #define NFC_LLCP_MAX_SERVICE_NAME 63 struct sockaddr_nfc_llcp { - sa_family_t sa_family; + __kernel_sa_family_t sa_family; __u32 dev_idx; __u32 target_idx; __u32 nfc_protocol; __u8 dsap; /* Destination SAP, if known */ __u8 ssap; /* Source SAP to be bound to */ char service_name[NFC_LLCP_MAX_SERVICE_NAME]; /* Service name URI */; - size_t service_name_len; + __kernel_size_t service_name_len; }; /* NFC socket protocols */ diff --git a/include/uapi/linux/resource.h b/include/uapi/linux/resource.h index 74ef57b38f9f..ac5d6a3031db 100644 --- a/include/uapi/linux/resource.h +++ b/include/uapi/linux/resource.h @@ -66,10 +66,17 @@ struct rlimit64 { #define _STK_LIM (8*1024*1024) /* - * GPG2 wants 64kB of mlocked memory, to make sure pass phrases - * and other sensitive information are never written to disk. + * Limit the amount of locked memory by some sane default: + * root can always increase this limit if needed. + * + * The main use-cases are (1) preventing sensitive memory + * from being swapped; (2) real-time operations; (3) via + * IOURING_REGISTER_BUFFERS. + * + * The first two don't need much. The latter will take as + * much as it can get. 8MB is a reasonably sane default. */ -#define MLOCK_LIMIT ((PAGE_SIZE > 64*1024) ? PAGE_SIZE : 64*1024) +#define MLOCK_LIMIT (8*1024*1024) /* * Due to binary compatibility, the actual resource numbers diff --git a/include/xen/events.h b/include/xen/events.h index c204262d9fc2..344081e71584 100644 --- a/include/xen/events.h +++ b/include/xen/events.h @@ -17,6 +17,7 @@ struct xenbus_device; unsigned xen_evtchn_nr_channels(void); int bind_evtchn_to_irq(evtchn_port_t evtchn); +int bind_evtchn_to_irq_lateeoi(evtchn_port_t evtchn); int bind_evtchn_to_irqhandler(evtchn_port_t evtchn, irq_handler_t handler, unsigned long irqflags, const char *devname, diff --git a/include/xen/xenbus.h b/include/xen/xenbus.h index b94074c82772..b13eb86395e0 100644 --- a/include/xen/xenbus.h +++ b/include/xen/xenbus.h @@ -112,6 +112,7 @@ struct xenbus_driver { const char *name; /* defaults to ids[0].devicetype */ const struct xenbus_device_id *ids; bool allow_rebind; /* avoid setting xenstore closed during remove */ + bool not_essential; /* is not mandatory for boot progress */ int (*probe)(struct xenbus_device *dev, const struct xenbus_device_id *id); void (*otherend_changed)(struct xenbus_device *dev, |