diff options
Diffstat (limited to 'include/linux')
33 files changed, 476 insertions, 115 deletions
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 83695641bd5e..1ca8e8fd1078 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -739,7 +739,7 @@ static inline bool blk_queue_is_zoned(struct request_queue *q) } } -static inline unsigned int blk_queue_zone_size(struct request_queue *q) +static inline unsigned int blk_queue_zone_sectors(struct request_queue *q) { return blk_queue_is_zoned(q) ? q->limits.chunk_sectors : 0; } @@ -1000,6 +1000,19 @@ static inline unsigned int blk_rq_cur_sectors(const struct request *rq) return blk_rq_cur_bytes(rq) >> 9; } +/* + * Some commands like WRITE SAME have a payload or data transfer size which + * is different from the size of the request. Any driver that supports such + * commands using the RQF_SPECIAL_PAYLOAD flag needs to use this helper to + * calculate the data transfer size. + */ +static inline unsigned int blk_rq_payload_bytes(struct request *rq) +{ + if (rq->rq_flags & RQF_SPECIAL_PAYLOAD) + return rq->special_vec.bv_len; + return blk_rq_bytes(rq); +} + static inline unsigned int blk_queue_get_max_sectors(struct request_queue *q, int op) { @@ -1536,12 +1549,12 @@ static inline bool bdev_is_zoned(struct block_device *bdev) return false; } -static inline unsigned int bdev_zone_size(struct block_device *bdev) +static inline unsigned int bdev_zone_sectors(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); if (q) - return blk_queue_zone_size(q); + return blk_queue_zone_sectors(q); return 0; } diff --git a/include/linux/bpf.h b/include/linux/bpf.h index f74ae68086dc..05cf951df3fe 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -216,7 +216,7 @@ u64 bpf_tail_call(u64 ctx, u64 r2, u64 index, u64 r4, u64 r5); u64 bpf_get_stackid(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); bool bpf_prog_array_compatible(struct bpf_array *array, const struct bpf_prog *fp); -int bpf_prog_calc_digest(struct bpf_prog *fp); +int bpf_prog_calc_tag(struct bpf_prog *fp); const struct bpf_func_proto *bpf_get_trace_printk_proto(void); diff --git a/include/linux/coredump.h b/include/linux/coredump.h index d016a121a8c4..28ffa94aed6b 100644 --- a/include/linux/coredump.h +++ b/include/linux/coredump.h @@ -14,6 +14,7 @@ struct coredump_params; extern int dump_skip(struct coredump_params *cprm, size_t nr); extern int dump_emit(struct coredump_params *cprm, const void *addr, int nr); extern int dump_align(struct coredump_params *cprm, int align); +extern void dump_truncate(struct coredump_params *cprm); #ifdef CONFIG_COREDUMP extern void do_coredump(const siginfo_t *siginfo); #else diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 20bfefbe7594..d936a0021839 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -74,6 +74,8 @@ enum cpuhp_state { CPUHP_ZCOMP_PREPARE, CPUHP_TIMERS_DEAD, CPUHP_MIPS_SOC_PREPARE, + CPUHP_BP_PREPARE_DYN, + CPUHP_BP_PREPARE_DYN_END = CPUHP_BP_PREPARE_DYN + 20, CPUHP_BRINGUP_CPU, CPUHP_AP_IDLE_DEAD, CPUHP_AP_OFFLINE, diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index 8daeb3ce0016..bfb3704fc6fc 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -39,23 +39,6 @@ struct dma_buf_attachment; /** * struct dma_buf_ops - operations possible on struct dma_buf - * @attach: [optional] allows different devices to 'attach' themselves to the - * given buffer. It might return -EBUSY to signal that backing storage - * is already allocated and incompatible with the requirements - * of requesting device. - * @detach: [optional] detach a given device from this buffer. - * @map_dma_buf: returns list of scatter pages allocated, increases usecount - * of the buffer. Requires atleast one attach to be called - * before. Returned sg list should already be mapped into - * _device_ address space. This call may sleep. May also return - * -EINTR. Should return -EINVAL if attach hasn't been called yet. - * @unmap_dma_buf: decreases usecount of buffer, might deallocate scatter - * pages. - * @release: release this buffer; to be called after the last dma_buf_put. - * @begin_cpu_access: [optional] called before cpu access to invalidate cpu - * caches and allocate backing storage (if not yet done) - * respectively pin the object into memory. - * @end_cpu_access: [optional] called after cpu access to flush caches. * @kmap_atomic: maps a page from the buffer into kernel address * space, users may not block until the subsequent unmap call. * This callback must not sleep. @@ -63,43 +46,206 @@ struct dma_buf_attachment; * This Callback must not sleep. * @kmap: maps a page from the buffer into kernel address space. * @kunmap: [optional] unmaps a page from the buffer. - * @mmap: used to expose the backing storage to userspace. Note that the - * mapping needs to be coherent - if the exporter doesn't directly - * support this, it needs to fake coherency by shooting down any ptes - * when transitioning away from the cpu domain. * @vmap: [optional] creates a virtual mapping for the buffer into kernel * address space. Same restrictions as for vmap and friends apply. * @vunmap: [optional] unmaps a vmap from the buffer */ struct dma_buf_ops { + /** + * @attach: + * + * This is called from dma_buf_attach() to make sure that a given + * &device can access the provided &dma_buf. Exporters which support + * buffer objects in special locations like VRAM or device-specific + * carveout areas should check whether the buffer could be move to + * system memory (or directly accessed by the provided device), and + * otherwise need to fail the attach operation. + * + * The exporter should also in general check whether the current + * allocation fullfills the DMA constraints of the new device. If this + * is not the case, and the allocation cannot be moved, it should also + * fail the attach operation. + * + * Any exporter-private housekeeping data can be stored in the + * &dma_buf_attachment.priv pointer. + * + * This callback is optional. + * + * Returns: + * + * 0 on success, negative error code on failure. It might return -EBUSY + * to signal that backing storage is already allocated and incompatible + * with the requirements of requesting device. + */ int (*attach)(struct dma_buf *, struct device *, - struct dma_buf_attachment *); + struct dma_buf_attachment *); + /** + * @detach: + * + * This is called by dma_buf_detach() to release a &dma_buf_attachment. + * Provided so that exporters can clean up any housekeeping for an + * &dma_buf_attachment. + * + * This callback is optional. + */ void (*detach)(struct dma_buf *, struct dma_buf_attachment *); - /* For {map,unmap}_dma_buf below, any specific buffer attributes - * required should get added to device_dma_parameters accessible - * via dev->dma_params. + /** + * @map_dma_buf: + * + * This is called by dma_buf_map_attachment() and is used to map a + * shared &dma_buf into device address space, and it is mandatory. It + * can only be called if @attach has been called successfully. This + * essentially pins the DMA buffer into place, and it cannot be moved + * any more + * + * This call may sleep, e.g. when the backing storage first needs to be + * allocated, or moved to a location suitable for all currently attached + * devices. + * + * Note that any specific buffer attributes required for this function + * should get added to device_dma_parameters accessible via + * &device.dma_params from the &dma_buf_attachment. The @attach callback + * should also check these constraints. + * + * If this is being called for the first time, the exporter can now + * choose to scan through the list of attachments for this buffer, + * collate the requirements of the attached devices, and choose an + * appropriate backing storage for the buffer. + * + * Based on enum dma_data_direction, it might be possible to have + * multiple users accessing at the same time (for reading, maybe), or + * any other kind of sharing that the exporter might wish to make + * available to buffer-users. + * + * Returns: + * + * A &sg_table scatter list of or the backing storage of the DMA buffer, + * already mapped into the device address space of the &device attached + * with the provided &dma_buf_attachment. + * + * On failure, returns a negative error value wrapped into a pointer. + * May also return -EINTR when a signal was received while being + * blocked. */ struct sg_table * (*map_dma_buf)(struct dma_buf_attachment *, - enum dma_data_direction); + enum dma_data_direction); + /** + * @unmap_dma_buf: + * + * This is called by dma_buf_unmap_attachment() and should unmap and + * release the &sg_table allocated in @map_dma_buf, and it is mandatory. + * It should also unpin the backing storage if this is the last mapping + * of the DMA buffer, it the exporter supports backing storage + * migration. + */ void (*unmap_dma_buf)(struct dma_buf_attachment *, - struct sg_table *, - enum dma_data_direction); + struct sg_table *, + enum dma_data_direction); + /* TODO: Add try_map_dma_buf version, to return immed with -EBUSY * if the call would block. */ - /* after final dma_buf_put() */ + /** + * @release: + * + * Called after the last dma_buf_put to release the &dma_buf, and + * mandatory. + */ void (*release)(struct dma_buf *); + /** + * @begin_cpu_access: + * + * This is called from dma_buf_begin_cpu_access() and allows the + * exporter to ensure that the memory is actually available for cpu + * access - the exporter might need to allocate or swap-in and pin the + * backing storage. The exporter also needs to ensure that cpu access is + * coherent for the access direction. The direction can be used by the + * exporter to optimize the cache flushing, i.e. access with a different + * direction (read instead of write) might return stale or even bogus + * data (e.g. when the exporter needs to copy the data to temporary + * storage). + * + * This callback is optional. + * + * FIXME: This is both called through the DMA_BUF_IOCTL_SYNC command + * from userspace (where storage shouldn't be pinned to avoid handing + * de-factor mlock rights to userspace) and for the kernel-internal + * users of the various kmap interfaces, where the backing storage must + * be pinned to guarantee that the atomic kmap calls can succeed. Since + * there's no in-kernel users of the kmap interfaces yet this isn't a + * real problem. + * + * Returns: + * + * 0 on success or a negative error code on failure. This can for + * example fail when the backing storage can't be allocated. Can also + * return -ERESTARTSYS or -EINTR when the call has been interrupted and + * needs to be restarted. + */ int (*begin_cpu_access)(struct dma_buf *, enum dma_data_direction); + + /** + * @end_cpu_access: + * + * This is called from dma_buf_end_cpu_access() when the importer is + * done accessing the CPU. The exporter can use this to flush caches and + * unpin any resources pinned in @begin_cpu_access. + * The result of any dma_buf kmap calls after end_cpu_access is + * undefined. + * + * This callback is optional. + * + * Returns: + * + * 0 on success or a negative error code on failure. Can return + * -ERESTARTSYS or -EINTR when the call has been interrupted and needs + * to be restarted. + */ int (*end_cpu_access)(struct dma_buf *, enum dma_data_direction); void *(*kmap_atomic)(struct dma_buf *, unsigned long); void (*kunmap_atomic)(struct dma_buf *, unsigned long, void *); void *(*kmap)(struct dma_buf *, unsigned long); void (*kunmap)(struct dma_buf *, unsigned long, void *); + /** + * @mmap: + * + * This callback is used by the dma_buf_mmap() function + * + * Note that the mapping needs to be incoherent, userspace is expected + * to braket CPU access using the DMA_BUF_IOCTL_SYNC interface. + * + * Because dma-buf buffers have invariant size over their lifetime, the + * dma-buf core checks whether a vma is too large and rejects such + * mappings. The exporter hence does not need to duplicate this check. + * Drivers do not need to check this themselves. + * + * If an exporter needs to manually flush caches and hence needs to fake + * coherency for mmap support, it needs to be able to zap all the ptes + * pointing at the backing storage. Now linux mm needs a struct + * address_space associated with the struct file stored in vma->vm_file + * to do that with the function unmap_mapping_range. But the dma_buf + * framework only backs every dma_buf fd with the anon_file struct file, + * i.e. all dma_bufs share the same file. + * + * Hence exporters need to setup their own file (and address_space) + * association by setting vma->vm_file and adjusting vma->vm_pgoff in + * the dma_buf mmap callback. In the specific case of a gem driver the + * exporter could use the shmem file already provided by gem (and set + * vm_pgoff = 0). Exporters can then zap ptes by unmapping the + * corresponding range of the struct address_space associated with their + * own file. + * + * This callback is optional. + * + * Returns: + * + * 0 on success or a negative error code on failure. + */ int (*mmap)(struct dma_buf *, struct vm_area_struct *vma); void *(*vmap)(struct dma_buf *); @@ -124,6 +270,15 @@ struct dma_buf_ops { * @poll: for userspace poll support * @cb_excl: for userspace poll support * @cb_shared: for userspace poll support + * + * This represents a shared buffer, created by calling dma_buf_export(). The + * userspace representation is a normal file descriptor, which can be created by + * calling dma_buf_fd(). + * + * Shared dma buffers are reference counted using dma_buf_put() and + * get_dma_buf(). + * + * Device DMA access is handled by the separate &struct dma_buf_attachment. */ struct dma_buf { size_t size; @@ -160,6 +315,11 @@ struct dma_buf { * This structure holds the attachment information between the dma_buf buffer * and its user device(s). The list contains one attachment struct per device * attached to the buffer. + * + * An attachment is created by calling dma_buf_attach(), and released again by + * calling dma_buf_detach(). The DMA mapping itself needed to initiate a + * transfer is created by dma_buf_map_attachment() and freed again by calling + * dma_buf_unmap_attachment(). */ struct dma_buf_attachment { struct dma_buf *dmabuf; @@ -192,9 +352,11 @@ struct dma_buf_export_info { }; /** - * helper macro for exporters; zeros and fills in most common values - * + * DEFINE_DMA_BUF_EXPORT_INFO - helper macro for exporters * @name: export-info name + * + * DEFINE_DMA_BUF_EXPORT_INFO macro defines the &struct dma_buf_export_info, + * zeroes it out and pre-populates exp_name in it. */ #define DEFINE_DMA_BUF_EXPORT_INFO(name) \ struct dma_buf_export_info name = { .exp_name = KBUILD_MODNAME, \ diff --git a/include/linux/dma-fence.h b/include/linux/dma-fence.h index d51a7d23c358..6048fa404e57 100644 --- a/include/linux/dma-fence.h +++ b/include/linux/dma-fence.h @@ -47,7 +47,7 @@ struct dma_fence_cb; * can be compared to decide which fence would be signaled later. * @flags: A mask of DMA_FENCE_FLAG_* defined below * @timestamp: Timestamp when the fence was signaled. - * @status: Optional, only valid if < 0, must be set before calling + * @error: Optional, only valid if < 0, must be set before calling * dma_fence_signal, indicates that the fence has completed with an error. * * the flags member must be manipulated and read using the appropriate @@ -79,7 +79,7 @@ struct dma_fence { unsigned seqno; unsigned long flags; ktime_t timestamp; - int status; + int error; }; enum dma_fence_flag_bits { @@ -133,7 +133,7 @@ struct dma_fence_cb { * or some failure occurred that made it impossible to enable * signaling. True indicates successful enabling. * - * fence->status may be set in enable_signaling, but only when false is + * fence->error may be set in enable_signaling, but only when false is * returned. * * Calling dma_fence_signal before enable_signaling is called allows @@ -145,7 +145,7 @@ struct dma_fence_cb { * the second time will be a noop since it was already signaled. * * Notes on signaled: - * May set fence->status if returning true. + * May set fence->error if returning true. * * Notes on wait: * Must not be NULL, set to dma_fence_default_wait for default implementation. @@ -378,6 +378,50 @@ static inline struct dma_fence *dma_fence_later(struct dma_fence *f1, return dma_fence_is_signaled(f2) ? NULL : f2; } +/** + * dma_fence_get_status_locked - returns the status upon completion + * @fence: [in] the dma_fence to query + * + * Drivers can supply an optional error status condition before they signal + * the fence (to indicate whether the fence was completed due to an error + * rather than success). The value of the status condition is only valid + * if the fence has been signaled, dma_fence_get_status_locked() first checks + * the signal state before reporting the error status. + * + * Returns 0 if the fence has not yet been signaled, 1 if the fence has + * been signaled without an error condition, or a negative error code + * if the fence has been completed in err. + */ +static inline int dma_fence_get_status_locked(struct dma_fence *fence) +{ + if (dma_fence_is_signaled_locked(fence)) + return fence->error ?: 1; + else + return 0; +} + +int dma_fence_get_status(struct dma_fence *fence); + +/** + * dma_fence_set_error - flag an error condition on the fence + * @fence: [in] the dma_fence + * @error: [in] the error to store + * + * Drivers can supply an optional error status condition before they signal + * the fence, to indicate that the fence was completed due to an error + * rather than success. This must be set before signaling (so that the value + * is visible before any waiters on the signal callback are woken). This + * helper exists to help catching erroneous setting of #dma_fence.error. + */ +static inline void dma_fence_set_error(struct dma_fence *fence, + int error) +{ + BUG_ON(test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)); + BUG_ON(error >= 0 || error < -MAX_ERRNO); + + fence->error = error; +} + signed long dma_fence_wait_timeout(struct dma_fence *, bool intr, signed long timeout); signed long dma_fence_wait_any_timeout(struct dma_fence **fences, diff --git a/include/linux/efi.h b/include/linux/efi.h index a07a476178cd..5b1af30ece55 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -103,6 +103,7 @@ typedef struct { #define EFI_PAGE_SHIFT 12 #define EFI_PAGE_SIZE (1UL << EFI_PAGE_SHIFT) +#define EFI_PAGES_MAX (U64_MAX >> EFI_PAGE_SHIFT) typedef struct { u32 type; @@ -950,6 +951,7 @@ static inline efi_status_t efi_query_variable_store(u32 attributes, #endif extern void __iomem *efi_lookup_mapped_addr(u64 phys_addr); +extern phys_addr_t __init efi_memmap_alloc(unsigned int num_entries); extern int __init efi_memmap_init_early(struct efi_memory_map_data *data); extern int __init efi_memmap_init_late(phys_addr_t addr, unsigned long size); extern void __init efi_memmap_unmap(void); diff --git a/include/linux/filter.h b/include/linux/filter.h index a0934e6c9bab..e4eb2546339a 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -57,6 +57,8 @@ struct bpf_prog_aux; /* BPF program can access up to 512 bytes of stack space. */ #define MAX_BPF_STACK 512 +#define BPF_TAG_SIZE 8 + /* Helper macros for filter block array initializers. */ /* ALU ops on registers, bpf_add|sub|...: dst_reg += src_reg */ @@ -408,7 +410,7 @@ struct bpf_prog { kmemcheck_bitfield_end(meta); enum bpf_prog_type type; /* Type of BPF program */ u32 len; /* Number of filter blocks */ - u32 digest[SHA_DIGEST_WORDS]; /* Program digest */ + u8 tag[BPF_TAG_SIZE]; struct bpf_prog_aux *aux; /* Auxiliary fields */ struct sock_fprog_kern *orig_prog; /* Original BPF program */ unsigned int (*bpf_func)(const void *ctx, @@ -519,7 +521,7 @@ static inline u32 bpf_prog_insn_size(const struct bpf_prog *prog) return prog->len * sizeof(struct bpf_insn); } -static inline u32 bpf_prog_digest_scratch_size(const struct bpf_prog *prog) +static inline u32 bpf_prog_tag_scratch_size(const struct bpf_prog *prog) { return round_up(bpf_prog_insn_size(prog) + sizeof(__be64) + 1, SHA_MESSAGE_BYTES); diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 4175dca4ac39..0fe0b6295ab5 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -38,9 +38,8 @@ struct vm_area_struct; #define ___GFP_ACCOUNT 0x100000u #define ___GFP_NOTRACK 0x200000u #define ___GFP_DIRECT_RECLAIM 0x400000u -#define ___GFP_OTHER_NODE 0x800000u -#define ___GFP_WRITE 0x1000000u -#define ___GFP_KSWAPD_RECLAIM 0x2000000u +#define ___GFP_WRITE 0x800000u +#define ___GFP_KSWAPD_RECLAIM 0x1000000u /* If the above are modified, __GFP_BITS_SHIFT may need updating */ /* @@ -172,11 +171,6 @@ struct vm_area_struct; * __GFP_NOTRACK_FALSE_POSITIVE is an alias of __GFP_NOTRACK. It's a means of * distinguishing in the source between false positives and allocations that * cannot be supported (e.g. page tables). - * - * __GFP_OTHER_NODE is for allocations that are on a remote node but that - * should not be accounted for as a remote allocation in vmstat. A - * typical user would be khugepaged collapsing a huge page on a remote - * node. */ #define __GFP_COLD ((__force gfp_t)___GFP_COLD) #define __GFP_NOWARN ((__force gfp_t)___GFP_NOWARN) @@ -184,10 +178,9 @@ struct vm_area_struct; #define __GFP_ZERO ((__force gfp_t)___GFP_ZERO) #define __GFP_NOTRACK ((__force gfp_t)___GFP_NOTRACK) #define __GFP_NOTRACK_FALSE_POSITIVE (__GFP_NOTRACK) -#define __GFP_OTHER_NODE ((__force gfp_t)___GFP_OTHER_NODE) /* Room for N __GFP_FOO bits */ -#define __GFP_BITS_SHIFT 26 +#define __GFP_BITS_SHIFT 25 #define __GFP_BITS_MASK ((__force gfp_t)((1 << __GFP_BITS_SHIFT) - 1)) /* @@ -506,11 +499,10 @@ extern void free_hot_cold_page(struct page *page, bool cold); extern void free_hot_cold_page_list(struct list_head *list, bool cold); struct page_frag_cache; -extern void __page_frag_drain(struct page *page, unsigned int order, - unsigned int count); -extern void *__alloc_page_frag(struct page_frag_cache *nc, - unsigned int fragsz, gfp_t gfp_mask); -extern void __free_page_frag(void *addr); +extern void __page_frag_cache_drain(struct page *page, unsigned int count); +extern void *page_frag_alloc(struct page_frag_cache *nc, + unsigned int fragsz, gfp_t gfp_mask); +extern void page_frag_free(void *addr); #define __free_page(page) __free_pages((page), 0) #define free_page(addr) free_pages((addr), 0) diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index c2748accea71..e973faba69dc 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -274,37 +274,67 @@ void gpiochip_set_nested_irqchip(struct gpio_chip *gpiochip, struct irq_chip *irqchip, int parent_irq); -int _gpiochip_irqchip_add(struct gpio_chip *gpiochip, +int gpiochip_irqchip_add_key(struct gpio_chip *gpiochip, + struct irq_chip *irqchip, + unsigned int first_irq, + irq_flow_handler_t handler, + unsigned int type, + bool nested, + struct lock_class_key *lock_key); + +#ifdef CONFIG_LOCKDEP + +/* + * Lockdep requires that each irqchip instance be created with a + * unique key so as to avoid unnecessary warnings. This upfront + * boilerplate static inlines provides such a key for each + * unique instance. + */ +static inline int gpiochip_irqchip_add(struct gpio_chip *gpiochip, + struct irq_chip *irqchip, + unsigned int first_irq, + irq_flow_handler_t handler, + unsigned int type) +{ + static struct lock_class_key key; + + return gpiochip_irqchip_add_key(gpiochip, irqchip, first_irq, + handler, type, false, &key); +} + +static inline int gpiochip_irqchip_add_nested(struct gpio_chip *gpiochip, struct irq_chip *irqchip, unsigned int first_irq, irq_flow_handler_t handler, - unsigned int type, - bool nested, - struct lock_class_key *lock_key); + unsigned int type) +{ + + static struct lock_class_key key; + + return gpiochip_irqchip_add_key(gpiochip, irqchip, first_irq, + handler, type, true, &key); +} +#else +static inline int gpiochip_irqchip_add(struct gpio_chip *gpiochip, + struct irq_chip *irqchip, + unsigned int first_irq, + irq_flow_handler_t handler, + unsigned int type) +{ + return gpiochip_irqchip_add_key(gpiochip, irqchip, first_irq, + handler, type, false, NULL); +} -/* FIXME: I assume threaded IRQchips do not have the lockdep problem */ static inline int gpiochip_irqchip_add_nested(struct gpio_chip *gpiochip, struct irq_chip *irqchip, unsigned int first_irq, irq_flow_handler_t handler, unsigned int type) { - return _gpiochip_irqchip_add(gpiochip, irqchip, first_irq, - handler, type, true, NULL); + return gpiochip_irqchip_add_key(gpiochip, irqchip, first_irq, + handler, type, true, NULL); } - -#ifdef CONFIG_LOCKDEP -#define gpiochip_irqchip_add(...) \ -( \ - ({ \ - static struct lock_class_key _key; \ - _gpiochip_irqchip_add(__VA_ARGS__, false, &_key); \ - }) \ -) -#else -#define gpiochip_irqchip_add(...) \ - _gpiochip_irqchip_add(__VA_ARGS__, false, NULL) -#endif +#endif /* CONFIG_LOCKDEP */ #endif /* CONFIG_GPIOLIB_IRQCHIP */ diff --git a/include/linux/i2c.h b/include/linux/i2c.h index b2109c522dec..4b45ec46161f 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -665,6 +665,7 @@ i2c_unlock_adapter(struct i2c_adapter *adapter) #define I2C_CLIENT_TEN 0x10 /* we have a ten bit chip address */ /* Must equal I2C_M_TEN below */ #define I2C_CLIENT_SLAVE 0x20 /* we are the slave */ +#define I2C_CLIENT_HOST_NOTIFY 0x40 /* We want to use I2C host notify */ #define I2C_CLIENT_WAKE 0x80 /* for board_info; true iff can wake */ #define I2C_CLIENT_SCCB 0x9000 /* Use Omnivision SCCB protocol */ /* Must match I2C_M_STOP|IGNORE_NAK */ diff --git a/include/linux/jump_label_ratelimit.h b/include/linux/jump_label_ratelimit.h index 089f70f83e97..23da3af459fe 100644 --- a/include/linux/jump_label_ratelimit.h +++ b/include/linux/jump_label_ratelimit.h @@ -14,6 +14,7 @@ struct static_key_deferred { #ifdef HAVE_JUMP_LABEL extern void static_key_slow_dec_deferred(struct static_key_deferred *key); +extern void static_key_deferred_flush(struct static_key_deferred *key); extern void jump_label_rate_limit(struct static_key_deferred *key, unsigned long rl); @@ -26,6 +27,10 @@ static inline void static_key_slow_dec_deferred(struct static_key_deferred *key) STATIC_KEY_CHECK_USE(); static_key_slow_dec(&key->key); } +static inline void static_key_deferred_flush(struct static_key_deferred *key) +{ + STATIC_KEY_CHECK_USE(); +} static inline void jump_label_rate_limit(struct static_key_deferred *key, unsigned long rl) diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 56aec84237ad..cb09238f6d32 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -514,8 +514,8 @@ extern enum system_states { #define TAINT_FLAGS_COUNT 16 struct taint_flag { - char true; /* character printed when tainted */ - char false; /* character printed when not tainted */ + char c_true; /* character printed when tainted */ + char c_false; /* character printed when not tainted */ bool module; /* also show as a per-module taint flag */ }; diff --git a/include/linux/kref.h b/include/linux/kref.h index e15828fd71f1..62f0a84ae94e 100644 --- a/include/linux/kref.h +++ b/include/linux/kref.h @@ -133,6 +133,6 @@ static inline int kref_put_mutex(struct kref *kref, */ static inline int __must_check kref_get_unless_zero(struct kref *kref) { - return atomic_add_unless(&kref->refcount, 1, 0); + return atomic_inc_not_zero(&kref->refcount); } #endif /* _KREF_H_ */ diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 61d20c17f3b7..254698856b8f 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -120,7 +120,7 @@ struct mem_cgroup_reclaim_iter { */ struct mem_cgroup_per_node { struct lruvec lruvec; - unsigned long lru_size[NR_LRU_LISTS]; + unsigned long lru_zone_size[MAX_NR_ZONES][NR_LRU_LISTS]; struct mem_cgroup_reclaim_iter iter[DEF_PRIORITY + 1]; @@ -432,7 +432,7 @@ static inline bool mem_cgroup_online(struct mem_cgroup *memcg) int mem_cgroup_select_victim_node(struct mem_cgroup *memcg); void mem_cgroup_update_lru_size(struct lruvec *lruvec, enum lru_list lru, - int nr_pages); + int zid, int nr_pages); unsigned long mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg, int nid, unsigned int lru_mask); @@ -441,9 +441,23 @@ static inline unsigned long mem_cgroup_get_lru_size(struct lruvec *lruvec, enum lru_list lru) { struct mem_cgroup_per_node *mz; + unsigned long nr_pages = 0; + int zid; mz = container_of(lruvec, struct mem_cgroup_per_node, lruvec); - return mz->lru_size[lru]; + for (zid = 0; zid < MAX_NR_ZONES; zid++) + nr_pages += mz->lru_zone_size[zid][lru]; + return nr_pages; +} + +static inline +unsigned long mem_cgroup_get_zone_lru_size(struct lruvec *lruvec, + enum lru_list lru, int zone_idx) +{ + struct mem_cgroup_per_node *mz; + + mz = container_of(lruvec, struct mem_cgroup_per_node, lruvec); + return mz->lru_zone_size[zone_idx][lru]; } void mem_cgroup_handle_over_high(void); @@ -671,6 +685,12 @@ mem_cgroup_get_lru_size(struct lruvec *lruvec, enum lru_list lru) { return 0; } +static inline +unsigned long mem_cgroup_get_zone_lru_size(struct lruvec *lruvec, + enum lru_list lru, int zone_idx) +{ + return 0; +} static inline unsigned long mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg, diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 01033fadea47..c1784c0b4f35 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -284,7 +284,7 @@ extern void sparse_remove_one_section(struct zone *zone, struct mem_section *ms, unsigned long map_offset); extern struct page *sparse_decode_mem_map(unsigned long coded_mem_map, unsigned long pnum); -extern int zone_can_shift(unsigned long pfn, unsigned long nr_pages, - enum zone_type target); +extern bool zone_can_shift(unsigned long pfn, unsigned long nr_pages, + enum zone_type target, int *zone_shift); #endif /* __LINUX_MEMORY_HOTPLUG_H */ diff --git a/include/linux/mm.h b/include/linux/mm.h index fe6b4036664a..b84615b0f64c 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1210,8 +1210,8 @@ int copy_page_range(struct mm_struct *dst, struct mm_struct *src, struct vm_area_struct *vma); void unmap_mapping_range(struct address_space *mapping, loff_t const holebegin, loff_t const holelen, int even_cows); -int follow_pte(struct mm_struct *mm, unsigned long address, pte_t **ptepp, - spinlock_t **ptlp); +int follow_pte_pmd(struct mm_struct *mm, unsigned long address, + pte_t **ptepp, pmd_t **pmdpp, spinlock_t **ptlp); int follow_pfn(struct vm_area_struct *vma, unsigned long address, unsigned long *pfn); int follow_phys(struct vm_area_struct *vma, unsigned long address, diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index 71613e8a720f..41d376e7116d 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -39,7 +39,7 @@ static __always_inline void update_lru_size(struct lruvec *lruvec, { __update_lru_size(lruvec, lru, zid, nr_pages); #ifdef CONFIG_MEMCG - mem_cgroup_update_lru_size(lruvec, lru, nr_pages); + mem_cgroup_update_lru_size(lruvec, lru, zid, nr_pages); #endif } diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 36d9896fbc1e..f4aac87adcc3 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -972,12 +972,16 @@ static __always_inline struct zoneref *next_zones_zonelist(struct zoneref *z, * @zonelist - The zonelist to search for a suitable zone * @highest_zoneidx - The zone index of the highest zone to return * @nodes - An optional nodemask to filter the zonelist with - * @zone - The first suitable zone found is returned via this parameter + * @return - Zoneref pointer for the first suitable zone found (see below) * * This function returns the first zone at or below a given zone index that is * within the allowed nodemask. The zoneref returned is a cursor that can be * used to iterate the zonelist with next_zones_zonelist by advancing it by * one before calling. + * + * When no eligible zone is found, zoneref->zone is NULL (zoneref itself is + * never NULL). This may happen either genuinely, or due to concurrent nodemask + * update due to cpuset modification. */ static inline struct zoneref *first_zones_zonelist(struct zonelist *zonelist, enum zone_type highest_zoneidx, diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 994f7423a74b..9bde9558b596 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2477,14 +2477,19 @@ static inline int skb_gro_header_hard(struct sk_buff *skb, unsigned int hlen) return NAPI_GRO_CB(skb)->frag0_len < hlen; } +static inline void skb_gro_frag0_invalidate(struct sk_buff *skb) +{ + NAPI_GRO_CB(skb)->frag0 = NULL; + NAPI_GRO_CB(skb)->frag0_len = 0; +} + static inline void *skb_gro_header_slow(struct sk_buff *skb, unsigned int hlen, unsigned int offset) { if (!pskb_may_pull(skb, hlen)) return NULL; - NAPI_GRO_CB(skb)->frag0 = NULL; - NAPI_GRO_CB(skb)->frag0_len = 0; + skb_gro_frag0_invalidate(skb); return skb->data + offset; } diff --git a/include/linux/nmi.h b/include/linux/nmi.h index aacca824a6ae..0a3fadc32693 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -110,6 +110,7 @@ extern int watchdog_user_enabled; extern int watchdog_thresh; extern unsigned long watchdog_enabled; extern unsigned long *watchdog_cpumask_bits; +extern atomic_t watchdog_park_in_progress; #ifdef CONFIG_SMP extern int sysctl_softlockup_all_cpu_backtrace; extern int sysctl_hardlockup_all_cpu_backtrace; diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 4741ecdb9817..78ed8105e64d 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1259,6 +1259,7 @@ extern void perf_event_disable(struct perf_event *event); extern void perf_event_disable_local(struct perf_event *event); extern void perf_event_disable_inatomic(struct perf_event *event); extern void perf_event_task_tick(void); +extern int perf_event_account_interrupt(struct perf_event *event); #else /* !CONFIG_PERF_EVENTS: */ static inline void * perf_aux_output_begin(struct perf_output_handle *handle, diff --git a/include/linux/prime_numbers.h b/include/linux/prime_numbers.h new file mode 100644 index 000000000000..14ec4f567342 --- /dev/null +++ b/include/linux/prime_numbers.h @@ -0,0 +1,37 @@ +#ifndef __LINUX_PRIME_NUMBERS_H +#define __LINUX_PRIME_NUMBERS_H + +#include <linux/types.h> + +bool is_prime_number(unsigned long x); +unsigned long next_prime_number(unsigned long x); + +/** + * for_each_prime_number - iterate over each prime upto a value + * @prime: the current prime number in this iteration + * @max: the upper limit + * + * Starting from the first prime number 2 iterate over each prime number up to + * the @max value. On each iteration, @prime is set to the current prime number. + * @max should be less than ULONG_MAX to ensure termination. To begin with + * @prime set to 1 on the first iteration use for_each_prime_number_from() + * instead. + */ +#define for_each_prime_number(prime, max) \ + for_each_prime_number_from((prime), 2, (max)) + +/** + * for_each_prime_number_from - iterate over each prime upto a value + * @prime: the current prime number in this iteration + * @from: the initial value + * @max: the upper limit + * + * Starting from @from iterate over each successive prime number up to the + * @max value. On each iteration, @prime is set to the current prime number. + * @max should be less than ULONG_MAX, and @from less than @max, to ensure + * termination. + */ +#define for_each_prime_number_from(prime, from, max) \ + for (prime = (from); prime <= (max); prime = next_prime_number(prime)) + +#endif /* !__LINUX_PRIME_NUMBERS_H */ diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 321f9ed552a9..01f71e1d2e94 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -444,6 +444,10 @@ bool __rcu_is_watching(void); #error "Unknown RCU implementation specified to kernel configuration" #endif +#define RCU_SCHEDULER_INACTIVE 0 +#define RCU_SCHEDULER_INIT 1 +#define RCU_SCHEDULER_RUNNING 2 + /* * init_rcu_head_on_stack()/destroy_rcu_head_on_stack() are needed for dynamic * initialization and destruction of rcu_head on the stack. rcu_head structures diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index e2f3a3281d8f..8265d351c9f0 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -408,7 +408,8 @@ enum rproc_crash_type { * @crash_comp: completion used to sync crash handler and the rproc reload * @recovery_disabled: flag that state if recovery was disabled * @max_notifyid: largest allocated notify id. - * @table_ptr: our copy of the resource table + * @table_ptr: pointer to the resource table in effect + * @cached_table: copy of the resource table * @has_iommu: flag to indicate if remote processor is behind an MMU */ struct rproc { @@ -440,6 +441,7 @@ struct rproc { bool recovery_disabled; int max_notifyid; struct resource_table *table_ptr; + struct resource_table *cached_table; bool has_iommu; bool auto_boot; }; diff --git a/include/linux/reservation.h b/include/linux/reservation.h index d9706a6f5ae2..2b5a4679daea 100644 --- a/include/linux/reservation.h +++ b/include/linux/reservation.h @@ -145,6 +145,40 @@ reservation_object_get_list(struct reservation_object *obj) } /** + * reservation_object_lock - lock the reservation object + * @obj: the reservation object + * @ctx: the locking context + * + * Locks the reservation object for exclusive access and modification. Note, + * that the lock is only against other writers, readers will run concurrently + * with a writer under RCU. The seqlock is used to notify readers if they + * overlap with a writer. + * + * As the reservation object may be locked by multiple parties in an + * undefined order, a #ww_acquire_ctx is passed to unwind if a cycle + * is detected. See ww_mutex_lock() and ww_acquire_init(). A reservation + * object may be locked by itself by passing NULL as @ctx. + */ +static inline int +reservation_object_lock(struct reservation_object *obj, + struct ww_acquire_ctx *ctx) +{ + return ww_mutex_lock(&obj->lock, ctx); +} + +/** + * reservation_object_unlock - unlock the reservation object + * @obj: the reservation object + * + * Unlocks the reservation object following exclusive access. + */ +static inline void +reservation_object_unlock(struct reservation_object *obj) +{ + ww_mutex_unlock(&obj->lock); +} + +/** * reservation_object_get_excl - get the reservation object's * exclusive fence, with update-side lock held * @obj: the reservation object diff --git a/include/linux/sched.h b/include/linux/sched.h index 4d1905245c7a..ad3ec9ec61f7 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -854,6 +854,16 @@ struct signal_struct { #define SIGNAL_UNKILLABLE 0x00000040 /* for init: ignore fatal signals */ +#define SIGNAL_STOP_MASK (SIGNAL_CLD_MASK | SIGNAL_STOP_STOPPED | \ + SIGNAL_STOP_CONTINUED) + +static inline void signal_set_stop_flags(struct signal_struct *sig, + unsigned int flags) +{ + WARN_ON(sig->flags & (SIGNAL_GROUP_EXIT|SIGNAL_GROUP_COREDUMP)); + sig->flags = (sig->flags & ~SIGNAL_STOP_MASK) | flags; +} + /* If true, all threads except ->group_exit_task have pending SIGKILL */ static inline int signal_group_exit(const struct signal_struct *sig) { diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index b53c0cfd417e..a410715bbef8 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2480,7 +2480,7 @@ static inline struct sk_buff *netdev_alloc_skb_ip_align(struct net_device *dev, static inline void skb_free_frag(void *addr) { - __free_page_frag(addr); + page_frag_free(addr); } void *napi_alloc_frag(unsigned int fragsz); diff --git a/include/linux/slab.h b/include/linux/slab.h index 084b12bad198..4c5363566815 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -226,7 +226,7 @@ static inline const char *__check_heap_object(const void *ptr, * (PAGE_SIZE*2). Larger requests are passed to the page allocator. */ #define KMALLOC_SHIFT_HIGH (PAGE_SHIFT + 1) -#define KMALLOC_SHIFT_MAX (MAX_ORDER + PAGE_SHIFT) +#define KMALLOC_SHIFT_MAX (MAX_ORDER + PAGE_SHIFT - 1) #ifndef KMALLOC_SHIFT_LOW #define KMALLOC_SHIFT_LOW 3 #endif @@ -239,7 +239,7 @@ static inline const char *__check_heap_object(const void *ptr, * be allocated from the same page. */ #define KMALLOC_SHIFT_HIGH PAGE_SHIFT -#define KMALLOC_SHIFT_MAX 30 +#define KMALLOC_SHIFT_MAX (MAX_ORDER + PAGE_SHIFT - 1) #ifndef KMALLOC_SHIFT_LOW #define KMALLOC_SHIFT_LOW 3 #endif diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h index e5d193440374..7440290f64ac 100644 --- a/include/linux/sunrpc/svc_xprt.h +++ b/include/linux/sunrpc/svc_xprt.h @@ -66,6 +66,7 @@ struct svc_xprt { #define XPT_LISTENER 10 /* listening endpoint */ #define XPT_CACHE_AUTH 11 /* cache auth info */ #define XPT_LOCAL 12 /* connection from loopback interface */ +#define XPT_KILL_TEMP 13 /* call xpo_kill_temp_xprt before closing */ struct svc_serv *xpt_server; /* service for transport */ atomic_t xpt_reserved; /* space on outq that is rsvd */ diff --git a/include/linux/swap.h b/include/linux/swap.h index 09f4be179ff3..7f47b7098b1b 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -150,8 +150,9 @@ enum { SWP_FILE = (1 << 7), /* set after swap_activate success */ SWP_AREA_DISCARD = (1 << 8), /* single-time swap area discards */ SWP_PAGE_DISCARD = (1 << 9), /* freed swap page-cluster discards */ + SWP_STABLE_WRITES = (1 << 10), /* no overwrite PG_writeback pages */ /* add others here before... */ - SWP_SCANNING = (1 << 10), /* refcount in scan_swap_map */ + SWP_SCANNING = (1 << 11), /* refcount in scan_swap_map */ }; #define SWAP_CLUSTER_MAX 32UL diff --git a/include/linux/tcp.h b/include/linux/tcp.h index fc5848dad7a4..c93f4b3a59cb 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -62,8 +62,13 @@ static inline unsigned int tcp_optlen(const struct sk_buff *skb) /* TCP Fast Open Cookie as stored in memory */ struct tcp_fastopen_cookie { + union { + u8 val[TCP_FASTOPEN_COOKIE_MAX]; +#if IS_ENABLED(CONFIG_IPV6) + struct in6_addr addr; +#endif + }; s8 len; - u8 val[TCP_FASTOPEN_COOKIE_MAX]; bool exp; /* In RFC6994 experimental option format */ }; diff --git a/include/linux/timerfd.h b/include/linux/timerfd.h index bd36ce431e32..bab0b1ad0613 100644 --- a/include/linux/timerfd.h +++ b/include/linux/timerfd.h @@ -8,23 +8,7 @@ #ifndef _LINUX_TIMERFD_H #define _LINUX_TIMERFD_H -/* For O_CLOEXEC and O_NONBLOCK */ -#include <linux/fcntl.h> - -/* For _IO helpers */ -#include <linux/ioctl.h> - -/* - * CAREFUL: Check include/asm-generic/fcntl.h when defining - * new flags, since they might collide with O_* ones. We want - * to re-use O_* flags that couldn't possibly have a meaning - * from eventfd, in order to leave a free define-space for - * shared O_* flags. - */ -#define TFD_TIMER_ABSTIME (1 << 0) -#define TFD_TIMER_CANCEL_ON_SET (1 << 1) -#define TFD_CLOEXEC O_CLOEXEC -#define TFD_NONBLOCK O_NONBLOCK +#include <uapi/linux/timerfd.h> #define TFD_SHARED_FCNTL_FLAGS (TFD_CLOEXEC | TFD_NONBLOCK) /* Flags for timerfd_create. */ @@ -32,6 +16,4 @@ /* Flags for timerfd_settime. */ #define TFD_SETTIME_FLAGS (TFD_TIMER_ABSTIME | TFD_TIMER_CANCEL_ON_SET) -#define TFD_IOC_SET_TICKS _IOW('T', 0, u64) - #endif /* _LINUX_TIMERFD_H */ |
