diff options
| author | Leon Romanovsky <leon@kernel.org> | 2026-03-30 12:02:58 +0300 |
|---|---|---|
| committer | Leon Romanovsky <leon@kernel.org> | 2026-03-30 20:47:44 +0300 |
| commit | e6fd2491789745ed8c3df86a660dfa7207129d22 (patch) | |
| tree | 62d79e06a87f78a9949c1e695386dec2ad0fcf22 /include/linux | |
| parent | adc09d7fbbb9d286057c98675994c445d81c27fa (diff) | |
| parent | 7aaa8047eafd0bd628065b15757d9b48c5f9c07d (diff) | |
| download | linux-e6fd2491789745ed8c3df86a660dfa7207129d22.tar.xz | |
Merge branch 'master' into rdma-next
Let's bring v7.0-rc6 to the -next branch, so we can merge the DMA
attributes fix [1] without merge conflicts.
[1] https://lore.kernel.org/all/20260323-umem-dma-attrs-v1-1-d6890f2e6a1e@nvidia.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
* master: (1688 commits)
Linux 7.0-rc6
...
Diffstat (limited to 'include/linux')
47 files changed, 416 insertions, 206 deletions
diff --git a/include/linux/auxvec.h b/include/linux/auxvec.h index 407f7005e6d6..8bcb9b726262 100644 --- a/include/linux/auxvec.h +++ b/include/linux/auxvec.h @@ -4,6 +4,6 @@ #include <uapi/linux/auxvec.h> -#define AT_VECTOR_SIZE_BASE 22 /* NEW_AUX_ENT entries in auxiliary table */ +#define AT_VECTOR_SIZE_BASE 24 /* NEW_AUX_ENT entries in auxiliary table */ /* number of "#define AT_.*" above, minus {AT_NULL, AT_IGNORE, AT_NOTELF} */ #endif /* _LINUX_AUXVEC_H */ diff --git a/include/linux/build_bug.h b/include/linux/build_bug.h index 2cfbb4c65c78..d3dc5dc5f916 100644 --- a/include/linux/build_bug.h +++ b/include/linux/build_bug.h @@ -32,7 +32,8 @@ /** * BUILD_BUG_ON_MSG - break compile if a condition is true & emit supplied * error message. - * @condition: the condition which the compiler should know is false. + * @cond: the condition which the compiler should know is false. + * @msg: build-time error message * * See BUILD_BUG_ON for description. */ @@ -60,6 +61,7 @@ /** * static_assert - check integer constant expression at build time + * @expr: expression to be checked * * static_assert() is a wrapper for the C11 _Static_assert, with a * little macro magic to make the message optional (defaulting to the diff --git a/include/linux/console_struct.h b/include/linux/console_struct.h index 13b35637bd5a..d5ca855116df 100644 --- a/include/linux/console_struct.h +++ b/include/linux/console_struct.h @@ -160,6 +160,7 @@ struct vc_data { struct uni_pagedict **uni_pagedict_loc; /* [!] Location of uni_pagedict variable for this console */ u32 **vc_uni_lines; /* unicode screen content */ u16 *vc_saved_screen; + u32 **vc_saved_uni_lines; unsigned int vc_saved_cols; unsigned int vc_saved_rows; /* additional information is in vt_kern.h */ diff --git a/include/linux/damon.h b/include/linux/damon.h index a4fea23da857..be3d198043ff 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -810,6 +810,12 @@ struct damon_ctx { struct damos_walk_control *walk_control; struct mutex walk_control_lock; + /* + * indicate if this may be corrupted. Currentonly this is set only for + * damon_commit_ctx() failure. + */ + bool maybe_corrupted; + /* Working thread of the given DAMON context */ struct task_struct *kdamond; /* Protects @kdamond field access */ diff --git a/include/linux/device.h b/include/linux/device.h index 0be95294b6e6..e65d564f01cd 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -483,6 +483,8 @@ struct device_physical_location { * on. This shrinks the "Board Support Packages" (BSPs) and * minimizes board-specific #ifdefs in drivers. * @driver_data: Private pointer for driver specific info. + * @driver_override: Driver name to force a match. Do not touch directly; use + * device_set_driver_override() instead. * @links: Links to suppliers and consumers of this device. * @power: For device power management. * See Documentation/driver-api/pm/devices.rst for details. @@ -576,6 +578,10 @@ struct device { core doesn't touch it */ void *driver_data; /* Driver data, set and get with dev_set_drvdata/dev_get_drvdata */ + struct { + const char *name; + spinlock_t lock; + } driver_override; struct mutex mutex; /* mutex to synchronize calls to * its driver. */ @@ -701,6 +707,54 @@ struct device_link { #define kobj_to_dev(__kobj) container_of_const(__kobj, struct device, kobj) +int __device_set_driver_override(struct device *dev, const char *s, size_t len); + +/** + * device_set_driver_override() - Helper to set or clear driver override. + * @dev: Device to change + * @s: NUL-terminated string, new driver name to force a match, pass empty + * string to clear it ("" or "\n", where the latter is only for sysfs + * interface). + * + * Helper to set or clear driver override of a device. + * + * Returns: 0 on success or a negative error code on failure. + */ +static inline int device_set_driver_override(struct device *dev, const char *s) +{ + return __device_set_driver_override(dev, s, s ? strlen(s) : 0); +} + +/** + * device_has_driver_override() - Check if a driver override has been set. + * @dev: device to check + * + * Returns true if a driver override has been set for this device. + */ +static inline bool device_has_driver_override(struct device *dev) +{ + guard(spinlock)(&dev->driver_override.lock); + return !!dev->driver_override.name; +} + +/** + * device_match_driver_override() - Match a driver against the device's driver_override. + * @dev: device to check + * @drv: driver to match against + * + * Returns > 0 if a driver override is set and matches the given driver, 0 if a + * driver override is set but does not match, or < 0 if a driver override is not + * set at all. + */ +static inline int device_match_driver_override(struct device *dev, + const struct device_driver *drv) +{ + guard(spinlock)(&dev->driver_override.lock); + if (dev->driver_override.name) + return !strcmp(dev->driver_override.name, drv->name); + return -1; +} + /** * device_iommu_mapped - Returns true when the device DMA is translated * by an IOMMU diff --git a/include/linux/device/bus.h b/include/linux/device/bus.h index 99c3c83ea520..c1b463cd6464 100644 --- a/include/linux/device/bus.h +++ b/include/linux/device/bus.h @@ -35,6 +35,8 @@ struct fwnode_handle; * otherwise. It may also return error code if determining that * the driver supports the device is not possible. In case of * -EPROBE_DEFER it will queue the device for deferred probing. + * Note: This callback may be invoked with or without the device + * lock held. * @uevent: Called when a device is added, removed, or a few other things * that generate uevents to add the environment variables. * @probe: Called when a new device or driver add to this bus, and callback @@ -63,6 +65,9 @@ struct fwnode_handle; * this bus. * @pm: Power management operations of this bus, callback the specific * device driver's pm-ops. + * @driver_override: Set to true if this bus supports the driver_override + * mechanism, which allows userspace to force a specific + * driver to bind to a device via a sysfs attribute. * @need_parent_lock: When probing or removing a device on this bus, the * device core should lock the device's parent. * @@ -104,6 +109,7 @@ struct bus_type { const struct dev_pm_ops *pm; + bool driver_override; bool need_parent_lock; }; diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 29973baa0581..99ef042ecdb4 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -80,11 +80,18 @@ #define DMA_ATTR_MMIO (1UL << 10) /* - * DMA_ATTR_CPU_CACHE_CLEAN: Indicates the CPU will not dirty any cacheline - * overlapping this buffer while it is mapped for DMA. All mappings sharing - * a cacheline must have this attribute for this to be considered safe. + * DMA_ATTR_DEBUGGING_IGNORE_CACHELINES: Indicates the CPU cache line can be + * overlapped. All mappings sharing a cacheline must have this attribute for + * this to be considered safe. */ -#define DMA_ATTR_CPU_CACHE_CLEAN (1UL << 11) +#define DMA_ATTR_DEBUGGING_IGNORE_CACHELINES (1UL << 11) + +/* + * DMA_ATTR_REQUIRE_COHERENT: Indicates that DMA coherency is required. + * All mappings that carry this attribute can't work with SWIOTLB and cache + * flushing. + */ +#define DMA_ATTR_REQUIRE_COHERENT (1UL << 12) /* * A dma_addr_t can hold any valid DMA or bus address for the platform. It can @@ -248,8 +255,8 @@ static inline void *dma_alloc_attrs(struct device *dev, size_t size, { return NULL; } -static void dma_free_attrs(struct device *dev, size_t size, void *cpu_addr, - dma_addr_t dma_handle, unsigned long attrs) +static inline void dma_free_attrs(struct device *dev, size_t size, + void *cpu_addr, dma_addr_t dma_handle, unsigned long attrs) { } static inline void *dmam_alloc_attrs(struct device *dev, size_t size, diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index 9a1eacf35d37..df8f88f63a70 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -42,7 +42,8 @@ extern const struct header_ops eth_header_ops; int eth_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, const void *daddr, const void *saddr, unsigned len); -int eth_header_parse(const struct sk_buff *skb, unsigned char *haddr); +int eth_header_parse(const struct sk_buff *skb, const struct net_device *dev, + unsigned char *haddr); int eth_header_cache(const struct neighbour *neigh, struct hh_cache *hh, __be16 type); void eth_header_cache_update(struct hh_cache *hh, const struct net_device *dev, diff --git a/include/linux/eventpoll.h b/include/linux/eventpoll.h index ccb478eb174b..ea9ca0e4172a 100644 --- a/include/linux/eventpoll.h +++ b/include/linux/eventpoll.h @@ -82,11 +82,14 @@ static inline struct epoll_event __user * epoll_put_uevent(__poll_t revents, __u64 data, struct epoll_event __user *uevent) { - if (__put_user(revents, &uevent->events) || - __put_user(data, &uevent->data)) - return NULL; - + scoped_user_write_access_size(uevent, sizeof(*uevent), efault) { + unsafe_put_user(revents, &uevent->events, efault); + unsafe_put_user(data, &uevent->data, efault); + } return uevent+1; + +efault: + return NULL; } #endif diff --git a/include/linux/firmware/intel/stratix10-svc-client.h b/include/linux/firmware/intel/stratix10-svc-client.h index d290060f4c73..91013161e9db 100644 --- a/include/linux/firmware/intel/stratix10-svc-client.h +++ b/include/linux/firmware/intel/stratix10-svc-client.h @@ -68,12 +68,12 @@ * timeout value used in Stratix10 FPGA manager driver. * timeout value used in RSU driver */ -#define SVC_RECONFIG_REQUEST_TIMEOUT_MS 300 -#define SVC_RECONFIG_BUFFER_TIMEOUT_MS 720 -#define SVC_RSU_REQUEST_TIMEOUT_MS 300 +#define SVC_RECONFIG_REQUEST_TIMEOUT_MS 5000 +#define SVC_RECONFIG_BUFFER_TIMEOUT_MS 5000 +#define SVC_RSU_REQUEST_TIMEOUT_MS 2000 #define SVC_FCS_REQUEST_TIMEOUT_MS 2000 #define SVC_COMPLETED_TIMEOUT_MS 30000 -#define SVC_HWMON_REQUEST_TIMEOUT_MS 300 +#define SVC_HWMON_REQUEST_TIMEOUT_MS 2000 struct stratix10_svc_chan; diff --git a/include/linux/fs/super_types.h b/include/linux/fs/super_types.h index fa7638b81246..383050e7fdf5 100644 --- a/include/linux/fs/super_types.h +++ b/include/linux/fs/super_types.h @@ -338,5 +338,6 @@ struct super_block { #define SB_I_NOUMASK 0x00001000 /* VFS does not apply umask */ #define SB_I_NOIDMAP 0x00002000 /* No idmapped mounts on this superblock */ #define SB_I_ALLOW_HSM 0x00004000 /* Allow HSM events on this superblock */ +#define SB_I_NO_DATA_INTEGRITY 0x00008000 /* fs cannot guarantee data persistence on sync */ #endif /* _LINUX_FS_SUPER_TYPES_H */ diff --git a/include/linux/hid.h b/include/linux/hid.h index dce862cafbbd..31324609af4d 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -682,6 +682,7 @@ struct hid_device { __s32 battery_charge_status; enum hid_battery_status battery_status; bool battery_avoid_query; + bool battery_present; ktime_t battery_ratelimit_time; #endif @@ -836,6 +837,12 @@ struct hid_usage_id { * raw_event and event should return negative on error, any other value will * pass the event on to .event() typically return 0 for success. * + * report_fixup must return a report descriptor pointer whose lifetime is at + * least that of the input rdesc. This is usually done by mutating the input + * rdesc and returning it or a sub-portion of it. In case a new buffer is + * allocated and returned, the implementation of report_fixup is responsible for + * freeing it later. + * * input_mapping shall return a negative value to completely ignore this usage * (e.g. doubled or invalid usage), zero to continue with parsing of this * usage by generic code (no special handling needed) or positive to skip diff --git a/include/linux/if_ether.h b/include/linux/if_ether.h index 61b7335aa037..ca9afa824aa4 100644 --- a/include/linux/if_ether.h +++ b/include/linux/if_ether.h @@ -40,7 +40,8 @@ static inline struct ethhdr *inner_eth_hdr(const struct sk_buff *skb) return (struct ethhdr *)skb_inner_mac_header(skb); } -int eth_header_parse(const struct sk_buff *skb, unsigned char *haddr); +int eth_header_parse(const struct sk_buff *skb, const struct net_device *dev, + unsigned char *haddr); extern ssize_t sysfs_format_mac(char *buf, const unsigned char *addr, int len); diff --git a/include/linux/indirect_call_wrapper.h b/include/linux/indirect_call_wrapper.h index 35227d47cfc9..dc272b514a01 100644 --- a/include/linux/indirect_call_wrapper.h +++ b/include/linux/indirect_call_wrapper.h @@ -16,22 +16,26 @@ */ #define INDIRECT_CALL_1(f, f1, ...) \ ({ \ - likely(f == f1) ? f1(__VA_ARGS__) : f(__VA_ARGS__); \ + typeof(f) __f1 = (f); \ + likely(__f1 == f1) ? f1(__VA_ARGS__) : __f1(__VA_ARGS__); \ }) #define INDIRECT_CALL_2(f, f2, f1, ...) \ ({ \ - likely(f == f2) ? f2(__VA_ARGS__) : \ - INDIRECT_CALL_1(f, f1, __VA_ARGS__); \ + typeof(f) __f2 = (f); \ + likely(__f2 == f2) ? f2(__VA_ARGS__) : \ + INDIRECT_CALL_1(__f2, f1, __VA_ARGS__); \ }) #define INDIRECT_CALL_3(f, f3, f2, f1, ...) \ ({ \ - likely(f == f3) ? f3(__VA_ARGS__) : \ - INDIRECT_CALL_2(f, f2, f1, __VA_ARGS__); \ + typeof(f) __f3 = (f); \ + likely(__f3 == f3) ? f3(__VA_ARGS__) : \ + INDIRECT_CALL_2(__f3, f2, f1, __VA_ARGS__); \ }) #define INDIRECT_CALL_4(f, f4, f3, f2, f1, ...) \ ({ \ - likely(f == f4) ? f4(__VA_ARGS__) : \ - INDIRECT_CALL_3(f, f3, f2, f1, __VA_ARGS__); \ + typeof(f) __f4 = (f); \ + likely(__f4 == f4) ? f4(__VA_ARGS__) : \ + INDIRECT_CALL_3(__f4, f3, f2, f1, __VA_ARGS__); \ }) #define INDIRECT_CALLABLE_DECLARE(f) f diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h index 7a1516011ccf..e19872e37e06 100644 --- a/include/linux/io-pgtable.h +++ b/include/linux/io-pgtable.h @@ -53,7 +53,7 @@ struct iommu_flush_ops { * tables. * @ias: Input address (iova) size, in bits. * @oas: Output address (paddr) size, in bits. - * @coherent_walk A flag to indicate whether or not page table walks made + * @coherent_walk: A flag to indicate whether or not page table walks made * by the IOMMU are coherent with the CPU caches. * @tlb: TLB management callbacks for this set of tables. * @iommu_dev: The device representing the DMA configuration for the @@ -136,6 +136,7 @@ struct io_pgtable_cfg { void (*free)(void *cookie, void *pages, size_t size); /* Low-level data specific to the table format */ + /* private: */ union { struct { u64 ttbr; @@ -203,6 +204,9 @@ struct arm_lpae_io_pgtable_walk_data { * @unmap_pages: Unmap a range of virtually contiguous pages of the same size. * @iova_to_phys: Translate iova to physical address. * @pgtable_walk: (optional) Perform a page table walk for a given iova. + * @read_and_clear_dirty: Record dirty info per IOVA. If an IOVA is dirty, + * clear its dirty state from the PTE unless the + * IOMMU_DIRTY_NO_CLEAR flag is passed in. * * These functions map directly onto the iommu_ops member functions with * the same names. @@ -231,7 +235,9 @@ struct io_pgtable_ops { * the configuration actually provided by the allocator (e.g. the * pgsize_bitmap may be restricted). * @cookie: An opaque token provided by the IOMMU driver and passed back to - * the callback routines in cfg->tlb. + * the callback routines. + * + * Returns: Pointer to the &struct io_pgtable_ops for this set of page tables. */ struct io_pgtable_ops *alloc_io_pgtable_ops(enum io_pgtable_fmt fmt, struct io_pgtable_cfg *cfg, diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index 3e4a82a6f817..214fdbd49052 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -388,6 +388,7 @@ struct io_ring_ctx { * regularly bounce b/w CPUs. */ struct { + struct io_rings __rcu *rings_rcu; struct llist_head work_llist; struct llist_head retry_llist; unsigned long check_cq; @@ -540,6 +541,7 @@ enum { REQ_F_BL_NO_RECYCLE_BIT, REQ_F_BUFFERS_COMMIT_BIT, REQ_F_BUF_NODE_BIT, + REQ_F_BUF_MORE_BIT, REQ_F_HAS_METADATA_BIT, REQ_F_IMPORT_BUFFER_BIT, REQ_F_SQE_COPIED_BIT, @@ -625,6 +627,8 @@ enum { REQ_F_BUFFERS_COMMIT = IO_REQ_FLAG(REQ_F_BUFFERS_COMMIT_BIT), /* buf node is valid */ REQ_F_BUF_NODE = IO_REQ_FLAG(REQ_F_BUF_NODE_BIT), + /* incremental buffer consumption, more space available */ + REQ_F_BUF_MORE = IO_REQ_FLAG(REQ_F_BUF_MORE_BIT), /* request has read/write metadata assigned */ REQ_F_HAS_METADATA = IO_REQ_FLAG(REQ_F_HAS_METADATA_BIT), /* diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 443053a76dcf..a7421382a916 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -333,7 +333,12 @@ struct tcp6_timewait_sock { }; #if IS_ENABLED(CONFIG_IPV6) -bool ipv6_mod_enabled(void); +extern int disable_ipv6_mod; + +static inline bool ipv6_mod_enabled(void) +{ + return disable_ipv6_mod == 0; +} static inline struct ipv6_pinfo *inet6_sk(const struct sock *__sk) { diff --git a/include/linux/kthread.h b/include/linux/kthread.h index c92c1149ee6e..a01a474719a7 100644 --- a/include/linux/kthread.h +++ b/include/linux/kthread.h @@ -7,6 +7,24 @@ struct mm_struct; +/* opaque kthread data */ +struct kthread; + +/* + * When "(p->flags & PF_KTHREAD)" is set the task is a kthread and will + * always remain a kthread. For kthreads p->worker_private always + * points to a struct kthread. For tasks that are not kthreads + * p->worker_private is used to point to other things. + * + * Return NULL for any task that is not a kthread. + */ +static inline struct kthread *tsk_is_kthread(struct task_struct *p) +{ + if (p->flags & PF_KTHREAD) + return p->worker_private; + return NULL; +} + __printf(4, 5) struct task_struct *kthread_create_on_node(int (*threadfn)(void *data), void *data, @@ -98,9 +116,10 @@ void *kthread_probe_data(struct task_struct *k); int kthread_park(struct task_struct *k); void kthread_unpark(struct task_struct *k); void kthread_parkme(void); -void kthread_exit(long result) __noreturn; +#define kthread_exit(result) do_exit(result) void kthread_complete_and_exit(struct completion *, long) __noreturn; int kthreads_update_housekeeping(void); +void kthread_do_exit(struct kthread *, long); int kthreadd(void *unused); extern struct task_struct *kthreadd_task; diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 34759a262b28..6b76e7a6f4c2 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1940,56 +1940,43 @@ enum kvm_stat_kind { struct kvm_stat_data { struct kvm *kvm; - const struct _kvm_stats_desc *desc; + const struct kvm_stats_desc *desc; enum kvm_stat_kind kind; }; -struct _kvm_stats_desc { - struct kvm_stats_desc desc; - char name[KVM_STATS_NAME_SIZE]; -}; - -#define STATS_DESC_COMMON(type, unit, base, exp, sz, bsz) \ - .flags = type | unit | base | \ - BUILD_BUG_ON_ZERO(type & ~KVM_STATS_TYPE_MASK) | \ - BUILD_BUG_ON_ZERO(unit & ~KVM_STATS_UNIT_MASK) | \ - BUILD_BUG_ON_ZERO(base & ~KVM_STATS_BASE_MASK), \ - .exponent = exp, \ - .size = sz, \ +#define STATS_DESC_COMMON(type, unit, base, exp, sz, bsz) \ + .flags = type | unit | base | \ + BUILD_BUG_ON_ZERO(type & ~KVM_STATS_TYPE_MASK) | \ + BUILD_BUG_ON_ZERO(unit & ~KVM_STATS_UNIT_MASK) | \ + BUILD_BUG_ON_ZERO(base & ~KVM_STATS_BASE_MASK), \ + .exponent = exp, \ + .size = sz, \ .bucket_size = bsz -#define VM_GENERIC_STATS_DESC(stat, type, unit, base, exp, sz, bsz) \ - { \ - { \ - STATS_DESC_COMMON(type, unit, base, exp, sz, bsz), \ - .offset = offsetof(struct kvm_vm_stat, generic.stat) \ - }, \ - .name = #stat, \ - } -#define VCPU_GENERIC_STATS_DESC(stat, type, unit, base, exp, sz, bsz) \ - { \ - { \ - STATS_DESC_COMMON(type, unit, base, exp, sz, bsz), \ - .offset = offsetof(struct kvm_vcpu_stat, generic.stat) \ - }, \ - .name = #stat, \ - } -#define VM_STATS_DESC(stat, type, unit, base, exp, sz, bsz) \ - { \ - { \ - STATS_DESC_COMMON(type, unit, base, exp, sz, bsz), \ - .offset = offsetof(struct kvm_vm_stat, stat) \ - }, \ - .name = #stat, \ - } -#define VCPU_STATS_DESC(stat, type, unit, base, exp, sz, bsz) \ - { \ - { \ - STATS_DESC_COMMON(type, unit, base, exp, sz, bsz), \ - .offset = offsetof(struct kvm_vcpu_stat, stat) \ - }, \ - .name = #stat, \ - } +#define VM_GENERIC_STATS_DESC(stat, type, unit, base, exp, sz, bsz) \ +{ \ + STATS_DESC_COMMON(type, unit, base, exp, sz, bsz), \ + .offset = offsetof(struct kvm_vm_stat, generic.stat), \ + .name = #stat, \ +} +#define VCPU_GENERIC_STATS_DESC(stat, type, unit, base, exp, sz, bsz) \ +{ \ + STATS_DESC_COMMON(type, unit, base, exp, sz, bsz), \ + .offset = offsetof(struct kvm_vcpu_stat, generic.stat), \ + .name = #stat, \ +} +#define VM_STATS_DESC(stat, type, unit, base, exp, sz, bsz) \ +{ \ + STATS_DESC_COMMON(type, unit, base, exp, sz, bsz), \ + .offset = offsetof(struct kvm_vm_stat, stat), \ + .name = #stat, \ +} +#define VCPU_STATS_DESC(stat, type, unit, base, exp, sz, bsz) \ +{ \ + STATS_DESC_COMMON(type, unit, base, exp, sz, bsz), \ + .offset = offsetof(struct kvm_vcpu_stat, stat), \ + .name = #stat, \ +} /* SCOPE: VM, VM_GENERIC, VCPU, VCPU_GENERIC */ #define STATS_DESC(SCOPE, stat, type, unit, base, exp, sz, bsz) \ SCOPE##_STATS_DESC(stat, type, unit, base, exp, sz, bsz) @@ -2066,7 +2053,7 @@ struct _kvm_stats_desc { STATS_DESC_IBOOLEAN(VCPU_GENERIC, blocking) ssize_t kvm_stats_read(char *id, const struct kvm_stats_header *header, - const struct _kvm_stats_desc *desc, + const struct kvm_stats_desc *desc, void *stats, size_t size_stats, char __user *user_buffer, size_t size, loff_t *offset); @@ -2111,9 +2098,9 @@ static inline void kvm_stats_log_hist_update(u64 *data, size_t size, u64 value) extern const struct kvm_stats_header kvm_vm_stats_header; -extern const struct _kvm_stats_desc kvm_vm_stats_desc[]; +extern const struct kvm_stats_desc kvm_vm_stats_desc[]; extern const struct kvm_stats_header kvm_vcpu_stats_header; -extern const struct _kvm_stats_desc kvm_vcpu_stats_desc[]; +extern const struct kvm_stats_desc kvm_vcpu_stats_desc[]; static inline int mmu_invalidate_retry(struct kvm *kvm, unsigned long mmu_seq) { diff --git a/include/linux/leafops.h b/include/linux/leafops.h index a9ff94b744f2..05673d3529e7 100644 --- a/include/linux/leafops.h +++ b/include/linux/leafops.h @@ -363,6 +363,23 @@ static inline unsigned long softleaf_to_pfn(softleaf_t entry) return swp_offset(entry) & SWP_PFN_MASK; } +static inline void softleaf_migration_sync(softleaf_t entry, + struct folio *folio) +{ + /* + * Ensure we do not race with split, which might alter tail pages into new + * folios and thus result in observing an unlocked folio. + * This matches the write barrier in __split_folio_to_order(). + */ + smp_rmb(); + + /* + * Any use of migration entries may only occur while the + * corresponding page is locked + */ + VM_WARN_ON_ONCE(!folio_test_locked(folio)); +} + /** * softleaf_to_page() - Obtains struct page for PFN encoded within leaf entry. * @entry: Leaf entry, softleaf_has_pfn(@entry) must return true. @@ -374,11 +391,8 @@ static inline struct page *softleaf_to_page(softleaf_t entry) struct page *page = pfn_to_page(softleaf_to_pfn(entry)); VM_WARN_ON_ONCE(!softleaf_has_pfn(entry)); - /* - * Any use of migration entries may only occur while the - * corresponding page is locked - */ - VM_WARN_ON_ONCE(softleaf_is_migration(entry) && !PageLocked(page)); + if (softleaf_is_migration(entry)) + softleaf_migration_sync(entry, page_folio(page)); return page; } @@ -394,12 +408,8 @@ static inline struct folio *softleaf_to_folio(softleaf_t entry) struct folio *folio = pfn_folio(softleaf_to_pfn(entry)); VM_WARN_ON_ONCE(!softleaf_has_pfn(entry)); - /* - * Any use of migration entries may only occur while the - * corresponding folio is locked. - */ - VM_WARN_ON_ONCE(softleaf_is_migration(entry) && - !folio_test_locked(folio)); + if (softleaf_is_migration(entry)) + softleaf_migration_sync(entry, folio); return folio; } diff --git a/include/linux/local_lock_internal.h b/include/linux/local_lock_internal.h index eff711bf973f..234be7f12c15 100644 --- a/include/linux/local_lock_internal.h +++ b/include/linux/local_lock_internal.h @@ -315,7 +315,7 @@ do { \ #endif /* CONFIG_PREEMPT_RT */ -#if defined(WARN_CONTEXT_ANALYSIS) +#if defined(WARN_CONTEXT_ANALYSIS) && !defined(__CHECKER__) /* * Because the compiler only knows about the base per-CPU variable, use this * helper function to make the compiler think we lock/unlock the @base variable, diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h index 0fe96f3ab3ef..65c732d440d2 100644 --- a/include/linux/mempolicy.h +++ b/include/linux/mempolicy.h @@ -55,6 +55,7 @@ struct mempolicy { nodemask_t cpuset_mems_allowed; /* relative to these nodes */ nodemask_t user_nodemask; /* nodemask passed by user */ } w; + struct rcu_head rcu; }; /* diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 26ca00c325d9..d5af2b7f577b 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -65,7 +65,7 @@ bool isolate_folio_to_list(struct folio *folio, struct list_head *list); int migrate_huge_page_move_mapping(struct address_space *mapping, struct folio *dst, struct folio *src); -void migration_entry_wait_on_locked(softleaf_t entry, spinlock_t *ptl) +void softleaf_entry_wait_on_locked(softleaf_t entry, spinlock_t *ptl) __releases(ptl); void folio_migrate_flags(struct folio *newfolio, struct folio *folio); int folio_migrate_mapping(struct address_space *mapping, @@ -97,6 +97,14 @@ static inline int set_movable_ops(const struct movable_operations *ops, enum pag return -ENOSYS; } +static inline void softleaf_entry_wait_on_locked(softleaf_t entry, spinlock_t *ptl) + __releases(ptl) +{ + WARN_ON_ONCE(1); + + spin_unlock(ptl); +} + #endif /* CONFIG_MIGRATION */ #ifdef CONFIG_NUMA_BALANCING diff --git a/include/linux/mm.h b/include/linux/mm.h index 5be3d8a8f806..abb4963c1f06 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3514,26 +3514,21 @@ static inline bool ptlock_init(struct ptdesc *ptdesc) { return true; } static inline void ptlock_free(struct ptdesc *ptdesc) {} #endif /* defined(CONFIG_SPLIT_PTE_PTLOCKS) */ -static inline unsigned long ptdesc_nr_pages(const struct ptdesc *ptdesc) -{ - return compound_nr(ptdesc_page(ptdesc)); -} - static inline void __pagetable_ctor(struct ptdesc *ptdesc) { - pg_data_t *pgdat = NODE_DATA(memdesc_nid(ptdesc->pt_flags)); + struct folio *folio = ptdesc_folio(ptdesc); - __SetPageTable(ptdesc_page(ptdesc)); - mod_node_page_state(pgdat, NR_PAGETABLE, ptdesc_nr_pages(ptdesc)); + __folio_set_pgtable(folio); + lruvec_stat_add_folio(folio, NR_PAGETABLE); } static inline void pagetable_dtor(struct ptdesc *ptdesc) { - pg_data_t *pgdat = NODE_DATA(memdesc_nid(ptdesc->pt_flags)); + struct folio *folio = ptdesc_folio(ptdesc); ptlock_free(ptdesc); - __ClearPageTable(ptdesc_page(ptdesc)); - mod_node_page_state(pgdat, NR_PAGETABLE, -ptdesc_nr_pages(ptdesc)); + __folio_clear_pgtable(folio); + lruvec_stat_sub_folio(folio, NR_PAGETABLE); } static inline void pagetable_dtor_free(struct ptdesc *ptdesc) diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h index 07a2bbaf86e9..8450e18a87c2 100644 --- a/include/linux/mmu_notifier.h +++ b/include/linux/mmu_notifier.h @@ -234,7 +234,7 @@ struct mmu_notifier { }; /** - * struct mmu_interval_notifier_ops + * struct mmu_interval_notifier_ops - callback for range notification * @invalidate: Upon return the caller must stop using any SPTEs within this * range. This function can sleep. Return false only if sleeping * was required but mmu_notifier_range_blockable(range) is false. @@ -309,8 +309,8 @@ void mmu_interval_notifier_remove(struct mmu_interval_notifier *interval_sub); /** * mmu_interval_set_seq - Save the invalidation sequence - * @interval_sub - The subscription passed to invalidate - * @cur_seq - The cur_seq passed to the invalidate() callback + * @interval_sub: The subscription passed to invalidate + * @cur_seq: The cur_seq passed to the invalidate() callback * * This must be called unconditionally from the invalidate callback of a * struct mmu_interval_notifier_ops under the same lock that is used to call @@ -329,8 +329,8 @@ mmu_interval_set_seq(struct mmu_interval_notifier *interval_sub, /** * mmu_interval_read_retry - End a read side critical section against a VA range - * interval_sub: The subscription - * seq: The return of the paired mmu_interval_read_begin() + * @interval_sub: The subscription + * @seq: The return of the paired mmu_interval_read_begin() * * This MUST be called under a user provided lock that is also held * unconditionally by op->invalidate() when it calls mmu_interval_set_seq(). @@ -338,7 +338,7 @@ mmu_interval_set_seq(struct mmu_interval_notifier *interval_sub, * Each call should be paired with a single mmu_interval_read_begin() and * should be used to conclude the read side. * - * Returns true if an invalidation collided with this critical section, and + * Returns: true if an invalidation collided with this critical section, and * the caller should retry. */ static inline bool @@ -350,20 +350,21 @@ mmu_interval_read_retry(struct mmu_interval_notifier *interval_sub, /** * mmu_interval_check_retry - Test if a collision has occurred - * interval_sub: The subscription - * seq: The return of the matching mmu_interval_read_begin() + * @interval_sub: The subscription + * @seq: The return of the matching mmu_interval_read_begin() * * This can be used in the critical section between mmu_interval_read_begin() - * and mmu_interval_read_retry(). A return of true indicates an invalidation - * has collided with this critical region and a future - * mmu_interval_read_retry() will return true. - * - * False is not reliable and only suggests a collision may not have - * occurred. It can be called many times and does not have to hold the user - * provided lock. + * and mmu_interval_read_retry(). * * This call can be used as part of loops and other expensive operations to * expedite a retry. + * It can be called many times and does not have to hold the user + * provided lock. + * + * Returns: true indicates an invalidation has collided with this critical + * region and a future mmu_interval_read_retry() will return true. + * False is not reliable and only suggests a collision may not have + * occurred. */ static inline bool mmu_interval_check_retry(struct mmu_interval_notifier *interval_sub, diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index d4e6e00bb90a..7ca01eb3f7d2 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -311,7 +311,9 @@ struct header_ops { int (*create) (struct sk_buff *skb, struct net_device *dev, unsigned short type, const void *daddr, const void *saddr, unsigned int len); - int (*parse)(const struct sk_buff *skb, unsigned char *haddr); + int (*parse)(const struct sk_buff *skb, + const struct net_device *dev, + unsigned char *haddr); int (*cache)(const struct neighbour *neigh, struct hh_cache *hh, __be16 type); void (*cache_update)(struct hh_cache *hh, const struct net_device *dev, @@ -2155,6 +2157,7 @@ struct net_device { unsigned long state; unsigned int flags; unsigned short hard_header_len; + enum netdev_stat_type pcpu_stat_type:8; netdev_features_t features; struct inet6_dev __rcu *ip6_ptr; __cacheline_group_end(net_device_read_txrx); @@ -2404,8 +2407,6 @@ struct net_device { void *ml_priv; enum netdev_ml_priv_type ml_priv_type; - enum netdev_stat_type pcpu_stat_type:8; - #if IS_ENABLED(CONFIG_GARP) struct garp_port __rcu *garp_port; #endif @@ -3446,7 +3447,7 @@ static inline int dev_parse_header(const struct sk_buff *skb, if (!dev->header_ops || !dev->header_ops->parse) return 0; - return dev->header_ops->parse(skb, haddr); + return dev->header_ops->parse(skb, dev, haddr); } static inline __be16 dev_parse_header_protocol(const struct sk_buff *skb) @@ -3576,17 +3577,49 @@ struct page_pool_bh { }; DECLARE_PER_CPU(struct page_pool_bh, system_page_pool); +#define XMIT_RECURSION_LIMIT 8 + #ifndef CONFIG_PREEMPT_RT static inline int dev_recursion_level(void) { return this_cpu_read(softnet_data.xmit.recursion); } + +static inline bool dev_xmit_recursion(void) +{ + return unlikely(__this_cpu_read(softnet_data.xmit.recursion) > + XMIT_RECURSION_LIMIT); +} + +static inline void dev_xmit_recursion_inc(void) +{ + __this_cpu_inc(softnet_data.xmit.recursion); +} + +static inline void dev_xmit_recursion_dec(void) +{ + __this_cpu_dec(softnet_data.xmit.recursion); +} #else static inline int dev_recursion_level(void) { return current->net_xmit.recursion; } +static inline bool dev_xmit_recursion(void) +{ + return unlikely(current->net_xmit.recursion > XMIT_RECURSION_LIMIT); +} + +static inline void dev_xmit_recursion_inc(void) +{ + current->net_xmit.recursion++; +} + +static inline void dev_xmit_recursion_dec(void) +{ + current->net_xmit.recursion--; +} #endif void __netif_schedule(struct Qdisc *q); @@ -4711,7 +4744,7 @@ 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); - /* Pairs with READ_ONCE() in __dev_queue_xmit() */ + /* Pairs with READ_ONCE() in netif_tx_owned() */ WRITE_ONCE(txq->xmit_lock_owner, cpu); } @@ -4729,7 +4762,7 @@ 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); - /* Pairs with READ_ONCE() in __dev_queue_xmit() */ + /* Pairs with READ_ONCE() in netif_tx_owned() */ WRITE_ONCE(txq->xmit_lock_owner, smp_processor_id()); } @@ -4738,7 +4771,7 @@ static inline bool __netif_tx_trylock(struct netdev_queue *txq) bool ok = spin_trylock(&txq->_xmit_lock); if (likely(ok)) { - /* Pairs with READ_ONCE() in __dev_queue_xmit() */ + /* Pairs with READ_ONCE() in netif_tx_owned() */ WRITE_ONCE(txq->xmit_lock_owner, smp_processor_id()); } return ok; @@ -4746,14 +4779,14 @@ static inline bool __netif_tx_trylock(struct netdev_queue *txq) static inline void __netif_tx_unlock(struct netdev_queue *txq) { - /* Pairs with READ_ONCE() in __dev_queue_xmit() */ + /* Pairs with READ_ONCE() in netif_tx_owned() */ WRITE_ONCE(txq->xmit_lock_owner, -1); spin_unlock(&txq->_xmit_lock); } static inline void __netif_tx_unlock_bh(struct netdev_queue *txq) { - /* Pairs with READ_ONCE() in __dev_queue_xmit() */ + /* Pairs with READ_ONCE() in netif_tx_owned() */ WRITE_ONCE(txq->xmit_lock_owner, -1); spin_unlock_bh(&txq->_xmit_lock); } @@ -4846,6 +4879,23 @@ static inline void netif_tx_disable(struct net_device *dev) local_bh_enable(); } +#ifndef CONFIG_PREEMPT_RT +static inline bool netif_tx_owned(struct netdev_queue *txq, unsigned int cpu) +{ + /* Other cpus might concurrently change txq->xmit_lock_owner + * to -1 or to their cpu id, but not to our id. + */ + return READ_ONCE(txq->xmit_lock_owner) == cpu; +} + +#else +static inline bool netif_tx_owned(struct netdev_queue *txq, unsigned int cpu) +{ + return rt_mutex_owner(&txq->_xmit_lock.lock) == current; +} + +#endif + static inline void netif_addr_lock(struct net_device *dev) { unsigned char nest_level = 0; diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 72ee7d210a74..ba17ac5bf356 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -140,7 +140,6 @@ struct netfs_io_stream { void (*issue_write)(struct netfs_io_subrequest *subreq); /* Collection tracking */ struct list_head subrequests; /* Contributory I/O operations */ - struct netfs_io_subrequest *front; /* Op being collected */ unsigned long long collected_to; /* Position we've collected results to */ size_t transferred; /* The amount transferred from this stream */ unsigned short error; /* Aggregate error for the stream */ diff --git a/include/linux/ns_common.h b/include/linux/ns_common.h index 825f5865bfc5..c8e227a3f9e2 100644 --- a/include/linux/ns_common.h +++ b/include/linux/ns_common.h @@ -55,6 +55,8 @@ static __always_inline bool is_ns_init_id(const struct ns_common *ns) #define ns_common_free(__ns) __ns_common_free(to_ns_common((__ns))) +bool may_see_all_namespaces(void); + static __always_inline __must_check int __ns_ref_active_read(const struct ns_common *ns) { return atomic_read(&ns->__ns_ref_active); diff --git a/include/linux/nvme-auth.h b/include/linux/nvme-auth.h index 60e069a6757f..e75c29c51464 100644 --- a/include/linux/nvme-auth.h +++ b/include/linux/nvme-auth.h @@ -11,7 +11,7 @@ struct nvme_dhchap_key { size_t len; u8 hash; - u8 key[]; + u8 key[] __counted_by(len); }; u32 nvme_auth_get_seqnum(void); diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index ec442af3f886..31a848485ad9 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -210,7 +210,6 @@ enum mapping_flags { AS_WRITEBACK_MAY_DEADLOCK_ON_RECLAIM = 9, AS_KERNEL_FILE = 10, /* mapping for a fake kernel file that shouldn't account usage to user cgroups */ - AS_NO_DATA_INTEGRITY = 11, /* no data integrity guarantees */ /* Bits 16-25 are used for FOLIO_ORDER */ AS_FOLIO_ORDER_BITS = 5, AS_FOLIO_ORDER_MIN = 16, @@ -346,16 +345,6 @@ static inline bool mapping_writeback_may_deadlock_on_reclaim(const struct addres return test_bit(AS_WRITEBACK_MAY_DEADLOCK_ON_RECLAIM, &mapping->flags); } -static inline void mapping_set_no_data_integrity(struct address_space *mapping) -{ - set_bit(AS_NO_DATA_INTEGRITY, &mapping->flags); -} - -static inline bool mapping_no_data_integrity(const struct address_space *mapping) -{ - return test_bit(AS_NO_DATA_INTEGRITY, &mapping->flags); -} - static inline gfp_t mapping_gfp_mask(const struct address_space *mapping) { return mapping->gfp_mask; diff --git a/include/linux/platform_data/mlxreg.h b/include/linux/platform_data/mlxreg.h index f6cca7a035c7..50b6be57da66 100644 --- a/include/linux/platform_data/mlxreg.h +++ b/include/linux/platform_data/mlxreg.h @@ -13,10 +13,10 @@ /** * enum mlxreg_wdt_type - type of HW watchdog * - * TYPE1 HW watchdog implementation exist in old systems. - * All new systems have TYPE2 HW watchdog. - * TYPE3 HW watchdog can exist on all systems with new CPLD. - * TYPE3 is selected by WD capability bit. + * @MLX_WDT_TYPE1: HW watchdog implementation in old systems. + * @MLX_WDT_TYPE2: All new systems have TYPE2 HW watchdog. + * @MLX_WDT_TYPE3: HW watchdog that can exist on all systems with new CPLD. + * TYPE3 is selected by WD capability bit. */ enum mlxreg_wdt_type { MLX_WDT_TYPE1, @@ -35,7 +35,7 @@ enum mlxreg_wdt_type { * @MLXREG_HOTPLUG_LC_SYNCED: entry for line card synchronization events, coming * after hardware-firmware synchronization handshake; * @MLXREG_HOTPLUG_LC_READY: entry for line card ready events, indicating line card - PHYs ready / unready state; + * PHYs ready / unready state; * @MLXREG_HOTPLUG_LC_ACTIVE: entry for line card active events, indicating firmware * availability / unavailability for the ports on line card; * @MLXREG_HOTPLUG_LC_THERMAL: entry for line card thermal shutdown events, positive @@ -123,8 +123,8 @@ struct mlxreg_hotplug_device { * @reg_pwr: attribute power register; * @reg_ena: attribute enable register; * @mode: access mode; - * @np - pointer to node platform associated with attribute; - * @hpdev - hotplug device data; + * @np: pointer to node platform associated with attribute; + * @hpdev: hotplug device data; * @notifier: pointer to event notifier block; * @health_cntr: dynamic device health indication counter; * @attached: true if device has been attached after good health indication; diff --git a/include/linux/platform_data/x86/int3472.h b/include/linux/platform_data/x86/int3472.h index b1b837583d54..dbe745dc88d5 100644 --- a/include/linux/platform_data/x86/int3472.h +++ b/include/linux/platform_data/x86/int3472.h @@ -26,6 +26,7 @@ #define INT3472_GPIO_TYPE_POWER_ENABLE 0x0b #define INT3472_GPIO_TYPE_CLK_ENABLE 0x0c #define INT3472_GPIO_TYPE_PRIVACY_LED 0x0d +#define INT3472_GPIO_TYPE_DOVDD 0x10 #define INT3472_GPIO_TYPE_HANDSHAKE 0x12 #define INT3472_GPIO_TYPE_HOTPLUG_DETECT 0x13 @@ -33,8 +34,8 @@ #define INT3472_MAX_SENSOR_GPIOS 3 #define INT3472_MAX_REGULATORS 3 -/* E.g. "avdd\0" */ -#define GPIO_SUPPLY_NAME_LENGTH 5 +/* E.g. "dovdd\0" */ +#define GPIO_SUPPLY_NAME_LENGTH 6 /* 12 chars for acpi_dev_name() + "-", e.g. "ABCD1234:00-" */ #define GPIO_REGULATOR_NAME_LENGTH (12 + GPIO_SUPPLY_NAME_LENGTH) /* lower- and upper-case mapping */ diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h index 813da101b5bf..ed1d50d1c3c1 100644 --- a/include/linux/platform_device.h +++ b/include/linux/platform_device.h @@ -31,11 +31,6 @@ struct platform_device { struct resource *resource; const struct platform_device_id *id_entry; - /* - * Driver name to force a match. Do not set directly, because core - * frees it. Use driver_set_override() to set or clear it. - */ - const char *driver_override; /* MFD cell pointer */ struct mfd_cell *mfd_cell; diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h index 876358cfe1b1..d862fa610270 100644 --- a/include/linux/ring_buffer.h +++ b/include/linux/ring_buffer.h @@ -248,6 +248,7 @@ int trace_rb_cpu_prepare(unsigned int cpu, struct hlist_node *node); int ring_buffer_map(struct trace_buffer *buffer, int cpu, struct vm_area_struct *vma); +void ring_buffer_map_dup(struct trace_buffer *buffer, int cpu); int ring_buffer_unmap(struct trace_buffer *buffer, int cpu); int ring_buffer_map_get_reader(struct trace_buffer *buffer, int cpu); #endif /* _LINUX_RING_BUFFER_H */ diff --git a/include/linux/rseq_types.h b/include/linux/rseq_types.h index da5fa6f40294..0b42045988db 100644 --- a/include/linux/rseq_types.h +++ b/include/linux/rseq_types.h @@ -133,10 +133,12 @@ struct rseq_data { }; * @active: MM CID is active for the task * @cid: The CID associated to the task either permanently or * borrowed from the CPU + * @node: Queued in the per MM MMCID list */ struct sched_mm_cid { unsigned int active; unsigned int cid; + struct hlist_node node; }; /** @@ -157,6 +159,7 @@ struct mm_cid_pcpu { * @work: Regular work to handle the affinity mode change case * @lock: Spinlock to protect against affinity setting which can't take @mutex * @mutex: Mutex to serialize forks and exits related to this mm + * @user_list: List of the MM CID users of a MM * @nr_cpus_allowed: The number of CPUs in the per MM allowed CPUs map. The map * is growth only. * @users: The number of tasks sharing this MM. Separate from mm::mm_users @@ -177,13 +180,14 @@ struct mm_mm_cid { raw_spinlock_t lock; struct mutex mutex; + struct hlist_head user_list; /* Low frequency modified */ unsigned int nr_cpus_allowed; unsigned int users; unsigned int pcpu_thrs; unsigned int update_deferred; -}____cacheline_aligned_in_smp; +} ____cacheline_aligned; #else /* CONFIG_SCHED_MM_CID */ struct mm_mm_cid { }; struct sched_mm_cid { }; diff --git a/include/linux/sched.h b/include/linux/sched.h index a7b4a980eb2f..5a5d3dbc9cdf 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2354,7 +2354,6 @@ static __always_inline void alloc_tag_restore(struct alloc_tag *tag, struct allo #ifdef CONFIG_SCHED_MM_CID void sched_mm_cid_before_execve(struct task_struct *t); void sched_mm_cid_after_execve(struct task_struct *t); -void sched_mm_cid_fork(struct task_struct *t); void sched_mm_cid_exit(struct task_struct *t); static __always_inline int task_mm_cid(struct task_struct *t) { @@ -2363,7 +2362,6 @@ static __always_inline int task_mm_cid(struct task_struct *t) #else static inline void sched_mm_cid_before_execve(struct task_struct *t) { } static inline void sched_mm_cid_after_execve(struct task_struct *t) { } -static inline void sched_mm_cid_fork(struct task_struct *t) { } static inline void sched_mm_cid_exit(struct task_struct *t) { } static __always_inline int task_mm_cid(struct task_struct *t) { diff --git a/include/linux/security.h b/include/linux/security.h index 83a646d72f6f..ee88dd2d2d1f 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -145,6 +145,7 @@ enum lockdown_reason { LOCKDOWN_BPF_WRITE_USER, LOCKDOWN_DBG_WRITE_KERNEL, LOCKDOWN_RTAS_ERROR_INJECTION, + LOCKDOWN_XEN_USER_ACTIONS, LOCKDOWN_INTEGRITY_MAX, LOCKDOWN_KCORE, LOCKDOWN_KPROBES, diff --git a/include/linux/serial_8250.h b/include/linux/serial_8250.h index 01efdce0fda0..a95b2d143d24 100644 --- a/include/linux/serial_8250.h +++ b/include/linux/serial_8250.h @@ -195,6 +195,7 @@ void serial8250_do_set_mctrl(struct uart_port *port, unsigned int mctrl); void serial8250_do_set_divisor(struct uart_port *port, unsigned int baud, unsigned int quot); int fsl8250_handle_irq(struct uart_port *port); +void serial8250_handle_irq_locked(struct uart_port *port, unsigned int iir); int serial8250_handle_irq(struct uart_port *port, unsigned int iir); u16 serial8250_rx_chars(struct uart_8250_port *up, u16 lsr); void serial8250_read_char(struct uart_8250_port *up, u16 lsr); diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index af7cfee7b8f6..0dc671c07d3a 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -159,10 +159,6 @@ extern void spi_transfer_cs_change_delay_exec(struct spi_message *msg, * @modalias: Name of the driver to use with this device, or an alias * for that name. This appears in the sysfs "modalias" attribute * for driver coldplugging, and in uevents used for hotplugging - * @driver_override: If the name of a driver is written to this attribute, then - * the device will bind to the named driver and only the named driver. - * Do not set directly, because core frees it; use driver_set_override() to - * set or clear it. * @pcpu_statistics: statistics for the spi_device * @word_delay: delay to be inserted between consecutive * words of a transfer @@ -224,7 +220,6 @@ struct spi_device { void *controller_state; void *controller_data; char modalias[SPI_NAME_SIZE]; - const char *driver_override; /* The statistics */ struct spi_statistics __percpu *pcpu_statistics; diff --git a/include/linux/srcutiny.h b/include/linux/srcutiny.h index dec7cbe015aa..905b629e8fa3 100644 --- a/include/linux/srcutiny.h +++ b/include/linux/srcutiny.h @@ -11,6 +11,7 @@ #ifndef _LINUX_SRCU_TINY_H #define _LINUX_SRCU_TINY_H +#include <linux/irq_work_types.h> #include <linux/swait.h> struct srcu_struct { @@ -24,18 +25,21 @@ struct srcu_struct { struct rcu_head *srcu_cb_head; /* Pending callbacks: Head. */ struct rcu_head **srcu_cb_tail; /* Pending callbacks: Tail. */ struct work_struct srcu_work; /* For driving grace periods. */ + struct irq_work srcu_irq_work; /* Defer schedule_work() to irq work. */ #ifdef CONFIG_DEBUG_LOCK_ALLOC struct lockdep_map dep_map; #endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ }; void srcu_drive_gp(struct work_struct *wp); +void srcu_tiny_irq_work(struct irq_work *irq_work); #define __SRCU_STRUCT_INIT(name, __ignored, ___ignored, ____ignored) \ { \ .srcu_wq = __SWAIT_QUEUE_HEAD_INITIALIZER(name.srcu_wq), \ .srcu_cb_tail = &name.srcu_cb_head, \ .srcu_work = __WORK_INITIALIZER(name.srcu_work, srcu_drive_gp), \ + .srcu_irq_work = { .func = srcu_tiny_irq_work }, \ __SRCU_DEP_MAP_INIT(name) \ } diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h index 958cb7ef41cb..be76fa4fc170 100644 --- a/include/linux/srcutree.h +++ b/include/linux/srcutree.h @@ -34,7 +34,7 @@ struct srcu_data { /* Values: SRCU_READ_FLAVOR_.* */ /* Update-side state. */ - spinlock_t __private lock ____cacheline_internodealigned_in_smp; + raw_spinlock_t __private lock ____cacheline_internodealigned_in_smp; struct rcu_segcblist srcu_cblist; /* List of callbacks.*/ unsigned long srcu_gp_seq_needed; /* Furthest future GP needed. */ unsigned long srcu_gp_seq_needed_exp; /* Furthest future exp GP. */ @@ -55,7 +55,7 @@ struct srcu_data { * Node in SRCU combining tree, similar in function to rcu_data. */ struct srcu_node { - spinlock_t __private lock; + raw_spinlock_t __private lock; unsigned long srcu_have_cbs[4]; /* GP seq for children having CBs, but only */ /* if greater than ->srcu_gp_seq. */ unsigned long srcu_data_have_cbs[4]; /* Which srcu_data structs have CBs for given GP? */ @@ -74,7 +74,7 @@ struct srcu_usage { /* First node at each level. */ int srcu_size_state; /* Small-to-big transition state. */ struct mutex srcu_cb_mutex; /* Serialize CB preparation. */ - spinlock_t __private lock; /* Protect counters and size state. */ + raw_spinlock_t __private lock; /* Protect counters and size state. */ struct mutex srcu_gp_mutex; /* Serialize GP work. */ unsigned long srcu_gp_seq; /* Grace-period seq #. */ unsigned long srcu_gp_seq_needed; /* Latest gp_seq needed. */ @@ -95,6 +95,7 @@ struct srcu_usage { unsigned long reschedule_jiffies; unsigned long reschedule_count; struct delayed_work work; + struct irq_work irq_work; struct srcu_struct *srcu_ssp; }; @@ -156,7 +157,7 @@ struct srcu_struct { #define __SRCU_USAGE_INIT(name) \ { \ - .lock = __SPIN_LOCK_UNLOCKED(name.lock), \ + .lock = __RAW_SPIN_LOCK_UNLOCKED(name.lock), \ .srcu_gp_seq = SRCU_GP_SEQ_INITIAL_VAL, \ .srcu_gp_seq_needed = SRCU_GP_SEQ_INITIAL_VAL_WITH_STATE, \ .srcu_gp_seq_needed_exp = SRCU_GP_SEQ_INITIAL_VAL, \ diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index 1f3804245c06..4fe63169d5a2 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -647,36 +647,22 @@ static inline void user_access_restore(unsigned long flags) { } /* Define RW variant so the below _mode macro expansion works */ #define masked_user_rw_access_begin(u) masked_user_access_begin(u) #define user_rw_access_begin(u, s) user_access_begin(u, s) -#define user_rw_access_end() user_access_end() /* Scoped user access */ -#define USER_ACCESS_GUARD(_mode) \ -static __always_inline void __user * \ -class_user_##_mode##_begin(void __user *ptr) \ -{ \ - return ptr; \ -} \ - \ -static __always_inline void \ -class_user_##_mode##_end(void __user *ptr) \ -{ \ - user_##_mode##_access_end(); \ -} \ - \ -DEFINE_CLASS(user_ ##_mode## _access, void __user *, \ - class_user_##_mode##_end(_T), \ - class_user_##_mode##_begin(ptr), void __user *ptr) \ - \ -static __always_inline class_user_##_mode##_access_t \ -class_user_##_mode##_access_ptr(void __user *scope) \ -{ \ - return scope; \ -} -USER_ACCESS_GUARD(read) -USER_ACCESS_GUARD(write) -USER_ACCESS_GUARD(rw) -#undef USER_ACCESS_GUARD +/* Cleanup wrapper functions */ +static __always_inline void __scoped_user_read_access_end(const void *p) +{ + user_read_access_end(); +}; +static __always_inline void __scoped_user_write_access_end(const void *p) +{ + user_write_access_end(); +}; +static __always_inline void __scoped_user_rw_access_end(const void *p) +{ + user_access_end(); +}; /** * __scoped_user_access_begin - Start a scoped user access @@ -750,13 +736,13 @@ USER_ACCESS_GUARD(rw) * * Don't use directly. Use scoped_masked_user_$MODE_access() instead. */ -#define __scoped_user_access(mode, uptr, size, elbl) \ -for (bool done = false; !done; done = true) \ - for (void __user *_tmpptr = __scoped_user_access_begin(mode, uptr, size, elbl); \ - !done; done = true) \ - for (CLASS(user_##mode##_access, scope)(_tmpptr); !done; done = true) \ - /* Force modified pointer usage within the scope */ \ - for (const typeof(uptr) uptr = _tmpptr; !done; done = true) +#define __scoped_user_access(mode, uptr, size, elbl) \ +for (bool done = false; !done; done = true) \ + for (auto _tmpptr = __scoped_user_access_begin(mode, uptr, size, elbl); \ + !done; done = true) \ + /* Force modified pointer usage within the scope */ \ + for (const auto uptr __cleanup(__scoped_user_##mode##_access_end) = \ + _tmpptr; !done; done = true) /** * scoped_user_read_access_size - Start a scoped user read access with given size @@ -806,7 +792,7 @@ for (bool done = false; !done; done = true) \ /** * scoped_user_rw_access_size - Start a scoped user read/write access with given size - * @uptr Pointer to the user space address to read from and write to + * @uptr: Pointer to the user space address to read from and write to * @size: Size of the access starting from @uptr * @elbl: Error label to goto when the access region is rejected * @@ -817,7 +803,7 @@ for (bool done = false; !done; done = true) \ /** * scoped_user_rw_access - Start a scoped user read/write access - * @uptr Pointer to the user space address to read from and write to + * @uptr: Pointer to the user space address to read from and write to * @elbl: Error label to goto when the access region is rejected * * The size of the access starting from @uptr is determined via sizeof(*@uptr)). diff --git a/include/linux/usb.h b/include/linux/usb.h index fbfcc70b07fb..04277af4bb9d 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -1862,14 +1862,18 @@ void usb_free_noncoherent(struct usb_device *dev, size_t size, * SYNCHRONOUS CALL SUPPORT * *-------------------------------------------------------------------*/ +/* Maximum value allowed for timeout in synchronous routines below */ +#define USB_MAX_SYNCHRONOUS_TIMEOUT 60000 /* ms */ + extern int usb_control_msg(struct usb_device *dev, unsigned int pipe, __u8 request, __u8 requesttype, __u16 value, __u16 index, void *data, __u16 size, int timeout); extern int usb_interrupt_msg(struct usb_device *usb_dev, unsigned int pipe, void *data, int len, int *actual_length, int timeout); extern int usb_bulk_msg(struct usb_device *usb_dev, unsigned int pipe, - void *data, int len, int *actual_length, - int timeout); + void *data, int len, int *actual_length, int timeout); +extern int usb_bulk_msg_killable(struct usb_device *usb_dev, unsigned int pipe, + void *data, int len, int *actual_length, int timeout); /* wrappers around usb_control_msg() for the most common standard requests */ int usb_control_msg_send(struct usb_device *dev, __u8 endpoint, __u8 request, diff --git a/include/linux/usb/quirks.h b/include/linux/usb/quirks.h index 2f7bd2fdc616..b3cc7beab4a3 100644 --- a/include/linux/usb/quirks.h +++ b/include/linux/usb/quirks.h @@ -78,4 +78,7 @@ /* skip BOS descriptor request */ #define USB_QUIRK_NO_BOS BIT(17) +/* Device claims zero configurations, forcing to 1 */ +#define USB_QUIRK_FORCE_ONE_CONFIG BIT(18) + #endif /* __LINUX_USB_QUIRKS_H */ diff --git a/include/linux/usb/r8152.h b/include/linux/usb/r8152.h index 2ca60828f28b..1502b2a355f9 100644 --- a/include/linux/usb/r8152.h +++ b/include/linux/usb/r8152.h @@ -32,6 +32,7 @@ #define VENDOR_ID_DLINK 0x2001 #define VENDOR_ID_DELL 0x413c #define VENDOR_ID_ASUS 0x0b05 +#define VENDOR_ID_TRENDNET 0x20f4 #if IS_REACHABLE(CONFIG_USB_RTL8152) extern u8 rtl8152_get_version(struct usb_interface *intf); diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h index b0e84896e6ac..bbf799ccf3b3 100644 --- a/include/linux/usb/usbnet.h +++ b/include/linux/usb/usbnet.h @@ -132,6 +132,7 @@ struct driver_info { #define FLAG_MULTI_PACKET 0x2000 #define FLAG_RX_ASSEMBLE 0x4000 /* rx packets may span >1 frames */ #define FLAG_NOARP 0x8000 /* device can't do ARP */ +#define FLAG_NOMAXMTU 0x10000 /* allow max_mtu above hard_mtu */ /* init device ... can sleep, or cause probe() failure */ int (*bind)(struct usbnet *, struct usb_interface *); diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h index 75dabb763c65..f36d21b5bc19 100644 --- a/include/linux/virtio_net.h +++ b/include/linux/virtio_net.h @@ -207,6 +207,39 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb, return __virtio_net_hdr_to_skb(skb, hdr, little_endian, hdr->gso_type); } +/* This function must be called after virtio_net_hdr_from_skb(). */ +static inline void __virtio_net_set_hdrlen(const struct sk_buff *skb, + struct virtio_net_hdr *hdr, + bool little_endian) +{ + u16 hdr_len; + + hdr_len = skb_transport_offset(skb); + + if (hdr->gso_type == VIRTIO_NET_HDR_GSO_UDP_L4) + hdr_len += sizeof(struct udphdr); + else + hdr_len += tcp_hdrlen(skb); + + hdr->hdr_len = __cpu_to_virtio16(little_endian, hdr_len); +} + +/* This function must be called after virtio_net_hdr_from_skb(). */ +static inline void __virtio_net_set_tnl_hdrlen(const struct sk_buff *skb, + struct virtio_net_hdr *hdr) +{ + u16 hdr_len; + + hdr_len = skb_inner_transport_offset(skb); + + if (hdr->gso_type == VIRTIO_NET_HDR_GSO_UDP_L4) + hdr_len += sizeof(struct udphdr); + else + hdr_len += inner_tcp_hdrlen(skb); + + hdr->hdr_len = __cpu_to_virtio16(true, hdr_len); +} + static inline int virtio_net_hdr_from_skb(const struct sk_buff *skb, struct virtio_net_hdr *hdr, bool little_endian, @@ -385,7 +418,8 @@ virtio_net_hdr_tnl_from_skb(const struct sk_buff *skb, bool tnl_hdr_negotiated, bool little_endian, int vlan_hlen, - bool has_data_valid) + bool has_data_valid, + bool feature_hdrlen) { struct virtio_net_hdr *hdr = (struct virtio_net_hdr *)vhdr; unsigned int inner_nh, outer_th; @@ -394,9 +428,17 @@ virtio_net_hdr_tnl_from_skb(const struct sk_buff *skb, tnl_gso_type = skb_shinfo(skb)->gso_type & (SKB_GSO_UDP_TUNNEL | SKB_GSO_UDP_TUNNEL_CSUM); - if (!tnl_gso_type) - return virtio_net_hdr_from_skb(skb, hdr, little_endian, - has_data_valid, vlan_hlen); + if (!tnl_gso_type) { + ret = virtio_net_hdr_from_skb(skb, hdr, little_endian, + has_data_valid, vlan_hlen); + if (ret) + return ret; + + if (feature_hdrlen && hdr->hdr_len) + __virtio_net_set_hdrlen(skb, hdr, little_endian); + + return ret; + } /* Tunnel support not negotiated but skb ask for it. */ if (!tnl_hdr_negotiated) @@ -414,6 +456,9 @@ virtio_net_hdr_tnl_from_skb(const struct sk_buff *skb, if (ret) return ret; + if (feature_hdrlen && hdr->hdr_len) + __virtio_net_set_tnl_hdrlen(skb, hdr); + if (skb->protocol == htons(ETH_P_IPV6)) hdr->gso_type |= VIRTIO_NET_HDR_GSO_UDP_TUNNEL_IPV6; else |
