diff options
Diffstat (limited to 'include')
42 files changed, 1637 insertions, 375 deletions
diff --git a/include/linux/acpi_dma.h b/include/linux/acpi_dma.h new file mode 100644 index 000000000000..d09deabc7bf6 --- /dev/null +++ b/include/linux/acpi_dma.h @@ -0,0 +1,116 @@ +/* + * ACPI helpers for DMA request / controller + * + * Based on of_dma.h + * + * Copyright (C) 2013, Intel Corporation + * Author: Andy Shevchenko <andriy.shevchenko@linux.intel.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef __LINUX_ACPI_DMA_H +#define __LINUX_ACPI_DMA_H + +#include <linux/list.h> +#include <linux/device.h> +#include <linux/dmaengine.h> + +/** + * struct acpi_dma_spec - slave device DMA resources + * @chan_id: channel unique id + * @slave_id: request line unique id + * @dev: struct device of the DMA controller to be used in the filter + * function + */ +struct acpi_dma_spec { + int chan_id; + int slave_id; + struct device *dev; +}; + +/** + * struct acpi_dma - representation of the registered DMAC + * @dma_controllers: linked list node + * @dev: struct device of this controller + * @acpi_dma_xlate: callback function to find a suitable channel + * @data: private data used by a callback function + */ +struct acpi_dma { + struct list_head dma_controllers; + struct device *dev; + struct dma_chan *(*acpi_dma_xlate) + (struct acpi_dma_spec *, struct acpi_dma *); + void *data; +}; + +/* Used with acpi_dma_simple_xlate() */ +struct acpi_dma_filter_info { + dma_cap_mask_t dma_cap; + dma_filter_fn filter_fn; +}; + +#ifdef CONFIG_DMA_ACPI + +int acpi_dma_controller_register(struct device *dev, + struct dma_chan *(*acpi_dma_xlate) + (struct acpi_dma_spec *, struct acpi_dma *), + void *data); +int acpi_dma_controller_free(struct device *dev); +int devm_acpi_dma_controller_register(struct device *dev, + struct dma_chan *(*acpi_dma_xlate) + (struct acpi_dma_spec *, struct acpi_dma *), + void *data); +void devm_acpi_dma_controller_free(struct device *dev); + +struct dma_chan *acpi_dma_request_slave_chan_by_index(struct device *dev, + size_t index); +struct dma_chan *acpi_dma_request_slave_chan_by_name(struct device *dev, + const char *name); + +struct dma_chan *acpi_dma_simple_xlate(struct acpi_dma_spec *dma_spec, + struct acpi_dma *adma); +#else + +static inline int acpi_dma_controller_register(struct device *dev, + struct dma_chan *(*acpi_dma_xlate) + (struct acpi_dma_spec *, struct acpi_dma *), + void *data) +{ + return -ENODEV; +} +static inline int acpi_dma_controller_free(struct device *dev) +{ + return -ENODEV; +} +static inline int devm_acpi_dma_controller_register(struct device *dev, + struct dma_chan *(*acpi_dma_xlate) + (struct acpi_dma_spec *, struct acpi_dma *), + void *data) +{ + return -ENODEV; +} +static inline void devm_acpi_dma_controller_free(struct device *dev) +{ +} + +static inline struct dma_chan *acpi_dma_request_slave_chan_by_index( + struct device *dev, size_t index) +{ + return NULL; +} +static inline struct dma_chan *acpi_dma_request_slave_chan_by_name( + struct device *dev, const char *name) +{ + return NULL; +} + +#define acpi_dma_simple_xlate NULL + +#endif + +#define acpi_dma_request_slave_channel acpi_dma_request_slave_chan_by_index + +#endif /* __LINUX_ACPI_DMA_H */ diff --git a/include/linux/aio.h b/include/linux/aio.h index 31ff6dba4872..1bdf965339f9 100644 --- a/include/linux/aio.h +++ b/include/linux/aio.h @@ -9,91 +9,32 @@ #include <linux/atomic.h> -#define AIO_MAXSEGS 4 -#define AIO_KIOGRP_NR_ATOMIC 8 - struct kioctx; +struct kiocb; -/* Notes on cancelling a kiocb: - * If a kiocb is cancelled, aio_complete may return 0 to indicate - * that cancel has not yet disposed of the kiocb. All cancel - * operations *must* call aio_put_req to dispose of the kiocb - * to guard against races with the completion code. - */ -#define KIOCB_C_CANCELLED 0x01 -#define KIOCB_C_COMPLETE 0x02 - -#define KIOCB_SYNC_KEY (~0U) +#define KIOCB_KEY 0 -/* ki_flags bits */ /* - * This may be used for cancel/retry serialization in the future, but - * for now it's unused and we probably don't want modules to even - * think they can use it. + * We use ki_cancel == KIOCB_CANCELLED to indicate that a kiocb has been either + * cancelled or completed (this makes a certain amount of sense because + * successful cancellation - io_cancel() - does deliver the completion to + * userspace). + * + * And since most things don't implement kiocb cancellation and we'd really like + * kiocb completion to be lockless when possible, we use ki_cancel to + * synchronize cancellation and completion - we only set it to KIOCB_CANCELLED + * with xchg() or cmpxchg(), see batch_complete_aio() and kiocb_cancel(). */ -/* #define KIF_LOCKED 0 */ -#define KIF_KICKED 1 -#define KIF_CANCELLED 2 - -#define kiocbTryLock(iocb) test_and_set_bit(KIF_LOCKED, &(iocb)->ki_flags) -#define kiocbTryKick(iocb) test_and_set_bit(KIF_KICKED, &(iocb)->ki_flags) +#define KIOCB_CANCELLED ((void *) (~0ULL)) -#define kiocbSetLocked(iocb) set_bit(KIF_LOCKED, &(iocb)->ki_flags) -#define kiocbSetKicked(iocb) set_bit(KIF_KICKED, &(iocb)->ki_flags) -#define kiocbSetCancelled(iocb) set_bit(KIF_CANCELLED, &(iocb)->ki_flags) +typedef int (kiocb_cancel_fn)(struct kiocb *, struct io_event *); -#define kiocbClearLocked(iocb) clear_bit(KIF_LOCKED, &(iocb)->ki_flags) -#define kiocbClearKicked(iocb) clear_bit(KIF_KICKED, &(iocb)->ki_flags) -#define kiocbClearCancelled(iocb) clear_bit(KIF_CANCELLED, &(iocb)->ki_flags) - -#define kiocbIsLocked(iocb) test_bit(KIF_LOCKED, &(iocb)->ki_flags) -#define kiocbIsKicked(iocb) test_bit(KIF_KICKED, &(iocb)->ki_flags) -#define kiocbIsCancelled(iocb) test_bit(KIF_CANCELLED, &(iocb)->ki_flags) - -/* is there a better place to document function pointer methods? */ -/** - * ki_retry - iocb forward progress callback - * @kiocb: The kiocb struct to advance by performing an operation. - * - * This callback is called when the AIO core wants a given AIO operation - * to make forward progress. The kiocb argument describes the operation - * that is to be performed. As the operation proceeds, perhaps partially, - * ki_retry is expected to update the kiocb with progress made. Typically - * ki_retry is set in the AIO core and it itself calls file_operations - * helpers. - * - * ki_retry's return value determines when the AIO operation is completed - * and an event is generated in the AIO event ring. Except the special - * return values described below, the value that is returned from ki_retry - * is transferred directly into the completion ring as the operation's - * resulting status. Once this has happened ki_retry *MUST NOT* reference - * the kiocb pointer again. - * - * If ki_retry returns -EIOCBQUEUED it has made a promise that aio_complete() - * will be called on the kiocb pointer in the future. The AIO core will - * not ask the method again -- ki_retry must ensure forward progress. - * aio_complete() must be called once and only once in the future, multiple - * calls may result in undefined behaviour. - * - * If ki_retry returns -EIOCBRETRY it has made a promise that kick_iocb() - * will be called on the kiocb pointer in the future. This may happen - * through generic helpers that associate kiocb->ki_wait with a wait - * queue head that ki_retry uses via current->io_wait. It can also happen - * with custom tracking and manual calls to kick_iocb(), though that is - * discouraged. In either case, kick_iocb() must be called once and only - * once. ki_retry must ensure forward progress, the AIO core will wait - * indefinitely for kick_iocb() to be called. - */ struct kiocb { - struct list_head ki_run_list; - unsigned long ki_flags; - int ki_users; - unsigned ki_key; /* id of this request */ + atomic_t ki_users; struct file *ki_filp; - struct kioctx *ki_ctx; /* may be NULL for sync ops */ - int (*ki_cancel)(struct kiocb *, struct io_event *); - ssize_t (*ki_retry)(struct kiocb *); + struct kioctx *ki_ctx; /* NULL for sync ops */ + kiocb_cancel_fn *ki_cancel; void (*ki_dtor)(struct kiocb *); union { @@ -117,7 +58,6 @@ struct kiocb { struct list_head ki_list; /* the aio core uses this * for cancellation */ - struct list_head ki_batch; /* batch allocation */ /* * If the aio_resfd field of the userspace iocb is not zero, @@ -128,106 +68,40 @@ struct kiocb { static inline bool is_sync_kiocb(struct kiocb *kiocb) { - return kiocb->ki_key == KIOCB_SYNC_KEY; + return kiocb->ki_ctx == NULL; } static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp) { *kiocb = (struct kiocb) { - .ki_users = 1, - .ki_key = KIOCB_SYNC_KEY, + .ki_users = ATOMIC_INIT(1), + .ki_ctx = NULL, .ki_filp = filp, .ki_obj.tsk = current, }; } -#define AIO_RING_MAGIC 0xa10a10a1 -#define AIO_RING_COMPAT_FEATURES 1 -#define AIO_RING_INCOMPAT_FEATURES 0 -struct aio_ring { - unsigned id; /* kernel internal index number */ - unsigned nr; /* number of io_events */ - unsigned head; - unsigned tail; - - unsigned magic; - unsigned compat_features; - unsigned incompat_features; - unsigned header_length; /* size of aio_ring */ - - - struct io_event io_events[0]; -}; /* 128 bytes + ring size */ - -#define AIO_RING_PAGES 8 -struct aio_ring_info { - unsigned long mmap_base; - unsigned long mmap_size; - - struct page **ring_pages; - spinlock_t ring_lock; - long nr_pages; - - unsigned nr, tail; - - struct page *internal_pages[AIO_RING_PAGES]; -}; - -static inline unsigned aio_ring_avail(struct aio_ring_info *info, - struct aio_ring *ring) -{ - return (ring->head + info->nr - 1 - ring->tail) % info->nr; -} - -struct kioctx { - atomic_t users; - int dead; - struct mm_struct *mm; - - /* This needs improving */ - unsigned long user_id; - struct hlist_node list; - - wait_queue_head_t wait; - - spinlock_t ctx_lock; - - int reqs_active; - struct list_head active_reqs; /* used for cancellation */ - struct list_head run_list; /* used for kicked reqs */ - - /* sys_io_setup currently limits this to an unsigned int */ - unsigned max_reqs; - - struct aio_ring_info ring_info; - - struct delayed_work wq; - - struct rcu_head rcu_head; -}; - /* prototypes */ -extern unsigned aio_max_size; - #ifdef CONFIG_AIO extern ssize_t wait_on_sync_kiocb(struct kiocb *iocb); -extern int aio_put_req(struct kiocb *iocb); -extern void kick_iocb(struct kiocb *iocb); -extern int aio_complete(struct kiocb *iocb, long res, long res2); +extern void aio_put_req(struct kiocb *iocb); +extern void aio_complete(struct kiocb *iocb, long res, long res2); struct mm_struct; extern void exit_aio(struct mm_struct *mm); extern long do_io_submit(aio_context_t ctx_id, long nr, struct iocb __user *__user *iocbpp, bool compat); +void kiocb_set_cancel_fn(struct kiocb *req, kiocb_cancel_fn *cancel); #else static inline ssize_t wait_on_sync_kiocb(struct kiocb *iocb) { return 0; } -static inline int aio_put_req(struct kiocb *iocb) { return 0; } -static inline void kick_iocb(struct kiocb *iocb) { } -static inline int aio_complete(struct kiocb *iocb, long res, long res2) { return 0; } +static inline void aio_put_req(struct kiocb *iocb) { } +static inline void aio_complete(struct kiocb *iocb, long res, long res2) { } struct mm_struct; static inline void exit_aio(struct mm_struct *mm) { } static inline long do_io_submit(aio_context_t ctx_id, long nr, struct iocb __user * __user *iocbpp, bool compat) { return 0; } +static inline void kiocb_set_cancel_fn(struct kiocb *req, + kiocb_cancel_fn *cancel) { } #endif /* CONFIG_AIO */ static inline struct kiocb *list_kiocb(struct list_head *h) diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 350459910fe1..c3881553f7d1 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -18,6 +18,7 @@ #include <linux/writeback.h> #include <linux/atomic.h> #include <linux/sysctl.h> +#include <linux/workqueue.h> struct page; struct device; @@ -27,7 +28,6 @@ struct dentry; * Bits in backing_dev_info.state */ enum bdi_state { - BDI_pending, /* On its way to being activated */ BDI_wb_alloc, /* Default embedded wb allocated */ BDI_async_congested, /* The async (write) queue is getting full */ BDI_sync_congested, /* The sync queue is getting full */ @@ -53,10 +53,8 @@ struct bdi_writeback { unsigned int nr; unsigned long last_old_flush; /* last old data flush */ - unsigned long last_active; /* last time bdi thread was active */ - struct task_struct *task; /* writeback thread */ - struct timer_list wakeup_timer; /* used for delayed bdi thread wakeup */ + struct delayed_work dwork; /* work item used for writeback */ struct list_head b_dirty; /* dirty inodes */ struct list_head b_io; /* parked for writeback */ struct list_head b_more_io; /* parked for more writeback */ @@ -123,14 +121,15 @@ int bdi_setup_and_register(struct backing_dev_info *, char *, unsigned int); void bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages, enum wb_reason reason); void bdi_start_background_writeback(struct backing_dev_info *bdi); -int bdi_writeback_thread(void *data); +void bdi_writeback_workfn(struct work_struct *work); int bdi_has_dirty_io(struct backing_dev_info *bdi); void bdi_wakeup_thread_delayed(struct backing_dev_info *bdi); void bdi_lock_two(struct bdi_writeback *wb1, struct bdi_writeback *wb2); extern spinlock_t bdi_lock; extern struct list_head bdi_list; -extern struct list_head bdi_pending_list; + +extern struct workqueue_struct *bdi_wq; static inline int wb_has_dirty_io(struct bdi_writeback *wb) { @@ -336,11 +335,6 @@ static inline bool bdi_cap_swap_backed(struct backing_dev_info *bdi) return bdi->capabilities & BDI_CAP_SWAP_BACKED; } -static inline bool bdi_cap_flush_forker(struct backing_dev_info *bdi) -{ - return bdi == &default_backing_dev_info; -} - static inline bool mapping_cap_writeback_dirty(struct address_space *mapping) { return bdi_cap_writeback_dirty(mapping->backing_dev_info); diff --git a/include/linux/bio.h b/include/linux/bio.h index 820e7aaad4fd..ef24466d8f82 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -67,6 +67,7 @@ #define bio_offset(bio) bio_iovec((bio))->bv_offset #define bio_segments(bio) ((bio)->bi_vcnt - (bio)->bi_idx) #define bio_sectors(bio) ((bio)->bi_size >> 9) +#define bio_end_sector(bio) ((bio)->bi_sector + bio_sectors((bio))) static inline unsigned int bio_cur_bytes(struct bio *bio) { @@ -84,11 +85,6 @@ static inline void *bio_data(struct bio *bio) return NULL; } -static inline int bio_has_allocated_vec(struct bio *bio) -{ - return bio->bi_io_vec && bio->bi_io_vec != bio->bi_inline_vecs; -} - /* * will die */ @@ -136,16 +132,27 @@ static inline int bio_has_allocated_vec(struct bio *bio) #define bio_io_error(bio) bio_endio((bio), -EIO) /* - * drivers should not use the __ version unless they _really_ want to - * run through the entire bio and not just pending pieces + * drivers should not use the __ version unless they _really_ know what + * they're doing */ #define __bio_for_each_segment(bvl, bio, i, start_idx) \ for (bvl = bio_iovec_idx((bio), (start_idx)), i = (start_idx); \ i < (bio)->bi_vcnt; \ bvl++, i++) +/* + * drivers should _never_ use the all version - the bio may have been split + * before it got to the driver and the driver won't own all of it + */ +#define bio_for_each_segment_all(bvl, bio, i) \ + for (i = 0; \ + bvl = bio_iovec_idx((bio), (i)), i < (bio)->bi_vcnt; \ + i++) + #define bio_for_each_segment(bvl, bio, i) \ - __bio_for_each_segment(bvl, bio, i, (bio)->bi_idx) + for (i = (bio)->bi_idx; \ + bvl = bio_iovec_idx((bio), (i)), i < (bio)->bi_vcnt; \ + i++) /* * get a reference to a bio, so it won't disappear. the intended use is @@ -180,9 +187,12 @@ struct bio_integrity_payload { unsigned short bip_slab; /* slab the bip came from */ unsigned short bip_vcnt; /* # of integrity bio_vecs */ unsigned short bip_idx; /* current bip_vec index */ + unsigned bip_owns_buf:1; /* should free bip_buf */ struct work_struct bip_work; /* I/O completion */ - struct bio_vec bip_vec[0]; /* embedded bvec array */ + + struct bio_vec *bip_vec; + struct bio_vec bip_inline_vecs[0];/* embedded bvec array */ }; #endif /* CONFIG_BLK_DEV_INTEGRITY */ @@ -211,6 +221,7 @@ extern void bio_pair_release(struct bio_pair *dbio); extern struct bio_set *bioset_create(unsigned int, unsigned int); extern void bioset_free(struct bio_set *); +extern mempool_t *biovec_create_pool(struct bio_set *bs, int pool_entries); extern struct bio *bio_alloc_bioset(gfp_t, int, struct bio_set *); extern void bio_put(struct bio *); @@ -245,6 +256,9 @@ extern void bio_endio(struct bio *, int); struct request_queue; extern int bio_phys_segments(struct request_queue *, struct bio *); +extern int submit_bio_wait(int rw, struct bio *bio); +extern void bio_advance(struct bio *, unsigned); + extern void bio_init(struct bio *); extern void bio_reset(struct bio *); @@ -279,6 +293,9 @@ static inline void bio_flush_dcache_pages(struct bio *bi) } #endif +extern void bio_copy_data(struct bio *dst, struct bio *src); +extern int bio_alloc_pages(struct bio *bio, gfp_t gfp); + extern struct bio *bio_copy_user(struct request_queue *, struct rq_map_data *, unsigned long, unsigned int, int, gfp_t); extern struct bio *bio_copy_user_iov(struct request_queue *, @@ -286,8 +303,8 @@ extern struct bio *bio_copy_user_iov(struct request_queue *, int, int, gfp_t); extern int bio_uncopy_user(struct bio *); void zero_fill_bio(struct bio *bio); -extern struct bio_vec *bvec_alloc_bs(gfp_t, int, unsigned long *, struct bio_set *); -extern void bvec_free_bs(struct bio_set *, struct bio_vec *, unsigned int); +extern struct bio_vec *bvec_alloc(gfp_t, int, unsigned long *, mempool_t *); +extern void bvec_free(mempool_t *, struct bio_vec *, unsigned int); extern unsigned int bvec_nr_vecs(unsigned short idx); #ifdef CONFIG_BLK_CGROUP @@ -298,39 +315,6 @@ static inline int bio_associate_current(struct bio *bio) { return -ENOENT; } static inline void bio_disassociate_task(struct bio *bio) { } #endif /* CONFIG_BLK_CGROUP */ -/* - * bio_set is used to allow other portions of the IO system to - * allocate their own private memory pools for bio and iovec structures. - * These memory pools in turn all allocate from the bio_slab - * and the bvec_slabs[]. - */ -#define BIO_POOL_SIZE 2 -#define BIOVEC_NR_POOLS 6 -#define BIOVEC_MAX_IDX (BIOVEC_NR_POOLS - 1) - -struct bio_set { - struct kmem_cache *bio_slab; - unsigned int front_pad; - - mempool_t *bio_pool; -#if defined(CONFIG_BLK_DEV_INTEGRITY) - mempool_t *bio_integrity_pool; -#endif - mempool_t *bvec_pool; -}; - -struct biovec_slab { - int nr_vecs; - char *name; - struct kmem_cache *slab; -}; - -/* - * a small number of entries is fine, not going to be performance critical. - * basically we just need to survive - */ -#define BIO_SPLIT_ENTRIES 2 - #ifdef CONFIG_HIGHMEM /* * remember never ever reenable interrupts between a bvec_kmap_irq and @@ -527,6 +511,49 @@ static inline struct bio *bio_list_get(struct bio_list *bl) return bio; } +/* + * bio_set is used to allow other portions of the IO system to + * allocate their own private memory pools for bio and iovec structures. + * These memory pools in turn all allocate from the bio_slab + * and the bvec_slabs[]. + */ +#define BIO_POOL_SIZE 2 +#define BIOVEC_NR_POOLS 6 +#define BIOVEC_MAX_IDX (BIOVEC_NR_POOLS - 1) + +struct bio_set { + struct kmem_cache *bio_slab; + unsigned int front_pad; + + mempool_t *bio_pool; + mempool_t *bvec_pool; +#if defined(CONFIG_BLK_DEV_INTEGRITY) + mempool_t *bio_integrity_pool; + mempool_t *bvec_integrity_pool; +#endif + + /* + * Deadlock avoidance for stacking block drivers: see comments in + * bio_alloc_bioset() for details + */ + spinlock_t rescue_lock; + struct bio_list rescue_list; + struct work_struct rescue_work; + struct workqueue_struct *rescue_workqueue; +}; + +struct biovec_slab { + int nr_vecs; + char *name; + struct kmem_cache *slab; +}; + +/* + * a small number of entries is fine, not going to be performance critical. + * basically we just need to survive + */ +#define BIO_SPLIT_ENTRIES 2 + #if defined(CONFIG_BLK_DEV_INTEGRITY) #define bip_vec_idx(bip, idx) (&(bip->bip_vec[(idx)])) diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 22990cf4439d..fa1abeb45b76 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -118,6 +118,7 @@ struct bio { * BIO_POOL_IDX() */ #define BIO_RESET_BITS 13 +#define BIO_OWNS_VEC 13 /* bio_free() should free bvec */ #define bio_flagged(bio, flag) ((bio)->bi_flags & (1 << (flag))) @@ -176,6 +177,7 @@ enum rq_flag_bits { __REQ_IO_STAT, /* account I/O stat */ __REQ_MIXED_MERGE, /* merge of different types, fail separately */ __REQ_KERNEL, /* direct IO to kernel pages */ + __REQ_PM, /* runtime pm request */ __REQ_NR_BITS, /* stops here */ }; @@ -198,6 +200,8 @@ enum rq_flag_bits { REQ_SECURE) #define REQ_CLONE_MASK REQ_COMMON_MASK +#define BIO_NO_ADVANCE_ITER_MASK (REQ_DISCARD|REQ_WRITE_SAME) + /* This mask is used for both bio and request merge checking */ #define REQ_NOMERGE_FLAGS \ (REQ_NOMERGE | REQ_STARTED | REQ_SOFTBARRIER | REQ_FLUSH | REQ_FUA) @@ -224,5 +228,6 @@ enum rq_flag_bits { #define REQ_MIXED_MERGE (1 << __REQ_MIXED_MERGE) #define REQ_SECURE (1 << __REQ_SECURE) #define REQ_KERNEL (1 << __REQ_KERNEL) +#define REQ_PM (1 << __REQ_PM) #endif /* __LINUX_BLK_TYPES_H */ diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 78feda9bbae2..2fdb4a451b49 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -361,6 +361,12 @@ struct request_queue { */ struct kobject kobj; +#ifdef CONFIG_PM_RUNTIME + struct device *dev; + int rpm_status; + unsigned int nr_pending; +#endif + /* * queue settings */ @@ -838,7 +844,7 @@ static inline unsigned int blk_queue_get_max_sectors(struct request_queue *q, unsigned int cmd_flags) { if (unlikely(cmd_flags & REQ_DISCARD)) - return q->limits.max_discard_sectors; + return min(q->limits.max_discard_sectors, UINT_MAX >> 9); if (unlikely(cmd_flags & REQ_WRITE_SAME)) return q->limits.max_write_same_sectors; @@ -961,6 +967,27 @@ struct request_queue *blk_alloc_queue_node(gfp_t, int); extern void blk_put_queue(struct request_queue *); /* + * block layer runtime pm functions + */ +#ifdef CONFIG_PM_RUNTIME +extern void blk_pm_runtime_init(struct request_queue *q, struct device *dev); +extern int blk_pre_runtime_suspend(struct request_queue *q); +extern void blk_post_runtime_suspend(struct request_queue *q, int err); +extern void blk_pre_runtime_resume(struct request_queue *q); +extern void blk_post_runtime_resume(struct request_queue *q, int err); +#else +static inline void blk_pm_runtime_init(struct request_queue *q, + struct device *dev) {} +static inline int blk_pre_runtime_suspend(struct request_queue *q) +{ + return -ENOSYS; +} +static inline void blk_post_runtime_suspend(struct request_queue *q, int err) {} +static inline void blk_pre_runtime_resume(struct request_queue *q) {} +static inline void blk_post_runtime_resume(struct request_queue *q, int err) {} +#endif + +/* * blk_plug permits building a queue of related requests by holding the I/O * fragments for a short period. This allows merging of sequential requests * into single larger request. As the requests are moved from a per-task list to @@ -1484,7 +1511,7 @@ static inline bool blk_integrity_is_initialized(struct gendisk *g) struct block_device_operations { int (*open) (struct block_device *, fmode_t); - int (*release) (struct gendisk *, fmode_t); + void (*release) (struct gendisk *, fmode_t); int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); int (*direct_access) (struct block_device *, sector_t, diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 3bff9ce09cf7..5047355b9a0f 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -28,6 +28,7 @@ struct cgroup_subsys; struct inode; struct cgroup; struct css_id; +struct eventfd_ctx; extern int cgroup_init_early(void); extern int cgroup_init(void); diff --git a/include/linux/cgroup_subsys.h b/include/linux/cgroup_subsys.h index f204a7a9cf38..6e7ec64b69ab 100644 --- a/include/linux/cgroup_subsys.h +++ b/include/linux/cgroup_subsys.h @@ -78,3 +78,9 @@ SUBSYS(hugetlb) #endif /* */ + +#ifdef CONFIG_CGROUP_BCACHE +SUBSYS(bcache) +#endif + +/* */ diff --git a/include/linux/cpu_cooling.h b/include/linux/cpu_cooling.h index 40b4ef54cc7d..282e27028418 100644 --- a/include/linux/cpu_cooling.h +++ b/include/linux/cpu_cooling.h @@ -25,34 +25,39 @@ #define __CPU_COOLING_H__ #include <linux/thermal.h> +#include <linux/cpumask.h> -#define CPUFREQ_COOLING_START 0 -#define CPUFREQ_COOLING_STOP 1 - -#if defined(CONFIG_CPU_THERMAL) || defined(CONFIG_CPU_THERMAL_MODULE) +#ifdef CONFIG_CPU_THERMAL /** * cpufreq_cooling_register - function to create cpufreq cooling device. * @clip_cpus: cpumask of cpus where the frequency constraints will happen */ -struct thermal_cooling_device *cpufreq_cooling_register( - const struct cpumask *clip_cpus); +struct thermal_cooling_device * +cpufreq_cooling_register(const struct cpumask *clip_cpus); /** * cpufreq_cooling_unregister - function to remove cpufreq cooling device. * @cdev: thermal cooling device pointer. */ void cpufreq_cooling_unregister(struct thermal_cooling_device *cdev); + +unsigned long cpufreq_cooling_get_level(unsigned int, unsigned int); #else /* !CONFIG_CPU_THERMAL */ -static inline struct thermal_cooling_device *cpufreq_cooling_register( - const struct cpumask *clip_cpus) +static inline struct thermal_cooling_device * +cpufreq_cooling_register(const struct cpumask *clip_cpus) { return NULL; } -static inline void cpufreq_cooling_unregister( - struct thermal_cooling_device *cdev) +static inline +void cpufreq_cooling_unregister(struct thermal_cooling_device *cdev) { return; } +static inline +unsigned long cpufreq_cooling_get_level(unsigned int, unsigned int) +{ + return THERMAL_CSTATE_INVALID; +} #endif /* CONFIG_CPU_THERMAL */ #endif /* __CPU_COOLING_H__ */ diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 91ac8da25020..96d3e4ab11a9 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -967,8 +967,9 @@ enum dma_status dma_sync_wait(struct dma_chan *chan, dma_cookie_t cookie); #ifdef CONFIG_DMA_ENGINE enum dma_status dma_wait_for_async_tx(struct dma_async_tx_descriptor *tx); void dma_issue_pending_all(void); -struct dma_chan *__dma_request_channel(dma_cap_mask_t *mask, dma_filter_fn fn, void *fn_param); -struct dma_chan *dma_request_slave_channel(struct device *dev, char *name); +struct dma_chan *__dma_request_channel(const dma_cap_mask_t *mask, + dma_filter_fn fn, void *fn_param); +struct dma_chan *dma_request_slave_channel(struct device *dev, const char *name); void dma_release_channel(struct dma_chan *chan); #else static inline enum dma_status dma_wait_for_async_tx(struct dma_async_tx_descriptor *tx) @@ -978,13 +979,13 @@ static inline enum dma_status dma_wait_for_async_tx(struct dma_async_tx_descript static inline void dma_issue_pending_all(void) { } -static inline struct dma_chan *__dma_request_channel(dma_cap_mask_t *mask, +static inline struct dma_chan *__dma_request_channel(const dma_cap_mask_t *mask, dma_filter_fn fn, void *fn_param) { return NULL; } static inline struct dma_chan *dma_request_slave_channel(struct device *dev, - char *name) + const char *name) { return NULL; } @@ -1005,9 +1006,9 @@ struct dma_chan *net_dma_find_channel(void); __dma_request_slave_channel_compat(&(mask), x, y, dev, name) static inline struct dma_chan -*__dma_request_slave_channel_compat(dma_cap_mask_t *mask, dma_filter_fn fn, - void *fn_param, struct device *dev, - char *name) +*__dma_request_slave_channel_compat(const dma_cap_mask_t *mask, + dma_filter_fn fn, void *fn_param, + struct device *dev, char *name) { struct dma_chan *chan; diff --git a/include/linux/drbd.h b/include/linux/drbd.h index 0c5a18ec322c..1b4d4ee1168f 100644 --- a/include/linux/drbd.h +++ b/include/linux/drbd.h @@ -52,7 +52,7 @@ #endif extern const char *drbd_buildtag(void); -#define REL_VERSION "8.4.2" +#define REL_VERSION "8.4.3" #define API_VERSION 1 #define PRO_VERSION_MIN 86 #define PRO_VERSION_MAX 101 @@ -319,7 +319,8 @@ enum drbd_state_rv { SS_IN_TRANSIENT_STATE = -18, /* Retry after the next state change */ SS_CONCURRENT_ST_CHG = -19, /* Concurrent cluster side state change! */ SS_O_VOL_PEER_PRI = -20, - SS_AFTER_LAST_ERROR = -21, /* Keep this at bottom */ + SS_OUTDATE_WO_CONN = -21, + SS_AFTER_LAST_ERROR = -22, /* Keep this at bottom */ }; /* from drbd_strings.c */ diff --git a/include/linux/drbd_limits.h b/include/linux/drbd_limits.h index 1fa19c5f5e64..1fedf2b17cc8 100644 --- a/include/linux/drbd_limits.h +++ b/include/linux/drbd_limits.h @@ -126,13 +126,12 @@ #define DRBD_RESYNC_RATE_DEF 250 #define DRBD_RESYNC_RATE_SCALE 'k' /* kilobytes */ - /* less than 7 would hit performance unnecessarily. - * 919 slots context information per transaction, - * 32k activity log, 4k transaction size, - * one transaction in flight: - * 919 * 7 = 6433 */ + /* less than 7 would hit performance unnecessarily. */ #define DRBD_AL_EXTENTS_MIN 7 -#define DRBD_AL_EXTENTS_MAX 6433 + /* we use u16 as "slot number", (u16)~0 is "FREE". + * If you use >= 292 kB on-disk ring buffer, + * this is the maximum you can use: */ +#define DRBD_AL_EXTENTS_MAX 0xfffe #define DRBD_AL_EXTENTS_DEF 1237 #define DRBD_AL_EXTENTS_SCALE '1' diff --git a/include/linux/errno.h b/include/linux/errno.h index f6bf082d4d4f..89627b9187f9 100644 --- a/include/linux/errno.h +++ b/include/linux/errno.h @@ -28,6 +28,5 @@ #define EBADTYPE 527 /* Type not supported by server */ #define EJUKEBOX 528 /* Request initiated, but will not complete before timeout */ #define EIOCBQUEUED 529 /* iocb queued, will get completion event */ -#define EIOCBRETRY 530 /* iocb queued, will trigger a retry */ #endif diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index f9a12f6243a5..df6fab82f87e 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -139,7 +139,7 @@ struct f2fs_extent { __le32 len; /* lengh of the extent */ } __packed; -#define F2FS_MAX_NAME_LEN 256 +#define F2FS_NAME_LEN 255 #define ADDRS_PER_INODE 923 /* Address Pointers in an Inode */ #define ADDRS_PER_BLOCK 1018 /* Address Pointers in a Direct Block */ #define NIDS_PER_BLOCK 1018 /* Node IDs in an Indirect Block */ @@ -165,7 +165,8 @@ struct f2fs_inode { __le32 i_flags; /* file attributes */ __le32 i_pino; /* parent inode number */ __le32 i_namelen; /* file name length */ - __u8 i_name[F2FS_MAX_NAME_LEN]; /* file name for SPOR */ + __u8 i_name[F2FS_NAME_LEN]; /* file name for SPOR */ + __u8 i_reserved2; /* for backward compatibility */ struct f2fs_extent i_ext; /* caching a largest extent */ @@ -362,10 +363,10 @@ struct f2fs_summary_block { typedef __le32 f2fs_hash_t; /* One directory entry slot covers 8bytes-long file name */ -#define F2FS_NAME_LEN 8 -#define F2FS_NAME_LEN_BITS 3 +#define F2FS_SLOT_LEN 8 +#define F2FS_SLOT_LEN_BITS 3 -#define GET_DENTRY_SLOTS(x) ((x + F2FS_NAME_LEN - 1) >> F2FS_NAME_LEN_BITS) +#define GET_DENTRY_SLOTS(x) ((x + F2FS_SLOT_LEN - 1) >> F2FS_SLOT_LEN_BITS) /* the number of dentry in a block */ #define NR_DENTRY_IN_BLOCK 214 @@ -377,10 +378,10 @@ typedef __le32 f2fs_hash_t; #define SIZE_OF_DENTRY_BITMAP ((NR_DENTRY_IN_BLOCK + BITS_PER_BYTE - 1) / \ BITS_PER_BYTE) #define SIZE_OF_RESERVED (PAGE_SIZE - ((SIZE_OF_DIR_ENTRY + \ - F2FS_NAME_LEN) * \ + F2FS_SLOT_LEN) * \ NR_DENTRY_IN_BLOCK + SIZE_OF_DENTRY_BITMAP)) -/* One directory entry slot representing F2FS_NAME_LEN-sized file name */ +/* One directory entry slot representing F2FS_SLOT_LEN-sized file name */ struct f2fs_dir_entry { __le32 hash_code; /* hash code of file name */ __le32 ino; /* inode number */ @@ -394,7 +395,7 @@ struct f2fs_dentry_block { __u8 dentry_bitmap[SIZE_OF_DENTRY_BITMAP]; __u8 reserved[SIZE_OF_RESERVED]; struct f2fs_dir_entry dentry[NR_DENTRY_IN_BLOCK]; - __u8 filename[NR_DENTRY_IN_BLOCK][F2FS_NAME_LEN]; + __u8 filename[NR_DENTRY_IN_BLOCK][F2FS_SLOT_LEN]; } __packed; /* file types used in inode_info->flags */ diff --git a/include/linux/fs.h b/include/linux/fs.h index b5a24ba83b6f..43db02e9c9fa 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2091,7 +2091,7 @@ extern struct block_device *blkdev_get_by_path(const char *path, fmode_t mode, void *holder); extern struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder); -extern int blkdev_put(struct block_device *bdev, fmode_t mode); +extern void blkdev_put(struct block_device *bdev, fmode_t mode); #ifdef CONFIG_SYSFS extern int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk); extern void bd_unlink_disk_holder(struct block_device *bdev, diff --git a/include/linux/gpio.h b/include/linux/gpio.h index f6c7ae3e223b..552e3f46e4a3 100644 --- a/include/linux/gpio.h +++ b/include/linux/gpio.h @@ -39,7 +39,7 @@ struct gpio { const char *label; }; -#ifdef CONFIG_GENERIC_GPIO +#ifdef CONFIG_GPIOLIB #ifdef CONFIG_ARCH_HAVE_CUSTOM_GPIO_H #include <asm/gpio.h> @@ -74,7 +74,7 @@ static inline int irq_to_gpio(unsigned int irq) #endif /* ! CONFIG_ARCH_HAVE_CUSTOM_GPIO_H */ -#else /* ! CONFIG_GENERIC_GPIO */ +#else /* ! CONFIG_GPIOLIB */ #include <linux/kernel.h> #include <linux/types.h> @@ -226,7 +226,7 @@ gpiochip_remove_pin_ranges(struct gpio_chip *chip) WARN_ON(1); } -#endif /* ! CONFIG_GENERIC_GPIO */ +#endif /* ! CONFIG_GPIOLIB */ struct device; diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 3a62df310f2e..6b4890fa57e7 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -189,8 +189,7 @@ static inline struct hugetlbfs_sb_info *HUGETLBFS_SB(struct super_block *sb) extern const struct file_operations hugetlbfs_file_operations; extern const struct vm_operations_struct hugetlb_vm_ops; -struct file *hugetlb_file_setup(const char *name, unsigned long addr, - size_t size, vm_flags_t acct, +struct file *hugetlb_file_setup(const char *name, size_t size, vm_flags_t acct, struct user_struct **user, int creat_flags, int page_size_log); @@ -209,8 +208,8 @@ static inline int is_file_hugepages(struct file *file) #define is_file_hugepages(file) 0 static inline struct file * -hugetlb_file_setup(const char *name, unsigned long addr, size_t size, - vm_flags_t acctflag, struct user_struct **user, int creat_flags, +hugetlb_file_setup(const char *name, size_t size, vm_flags_t acctflag, + struct user_struct **user, int creat_flags, int page_size_log) { return ERR_PTR(-ENOSYS); @@ -288,6 +287,13 @@ static inline struct hstate *hstate_file(struct file *f) return hstate_inode(file_inode(f)); } +static inline struct hstate *hstate_sizelog(int page_size_log) +{ + if (!page_size_log) + return &default_hstate; + return size_to_hstate(1 << page_size_log); +} + static inline struct hstate *hstate_vma(struct vm_area_struct *vma) { return hstate_file(vma->vm_file); @@ -352,11 +358,12 @@ static inline int hstate_index(struct hstate *h) return h - hstates; } -#else +#else /* CONFIG_HUGETLB_PAGE */ struct hstate {}; #define alloc_huge_page_node(h, nid) NULL #define alloc_bootmem_huge_page(h) NULL #define hstate_file(f) NULL +#define hstate_sizelog(s) NULL #define hstate_vma(v) NULL #define hstate_inode(i) NULL #define huge_page_size(h) PAGE_SIZE @@ -371,6 +378,6 @@ static inline unsigned int pages_per_huge_page(struct hstate *h) } #define hstate_index_to_shift(index) 0 #define hstate_index(h) 0 -#endif +#endif /* CONFIG_HUGETLB_PAGE */ #endif /* _LINUX_HUGETLB_H */ diff --git a/include/linux/idr.h b/include/linux/idr.h index a470ac3ef49d..871a213a8477 100644 --- a/include/linux/idr.h +++ b/include/linux/idr.h @@ -124,11 +124,13 @@ static inline void *idr_find(struct idr *idr, int id) * @idp: idr handle * @entry: the type * to use as cursor * @id: id entry's key + * + * @entry and @id do not need to be initialized before the loop, and + * after normal terminatinon @entry is left with the value NULL. This + * is convenient for a "not found" value. */ -#define idr_for_each_entry(idp, entry, id) \ - for (id = 0, entry = (typeof(entry))idr_get_next((idp), &(id)); \ - entry != NULL; \ - ++id, entry = (typeof(entry))idr_get_next((idp), &(id))) +#define idr_for_each_entry(idp, entry, id) \ + for (id = 0; ((entry) = idr_get_next(idp, &(id))) != NULL; ++id) /* * Don't use the following functions. These exist only to suppress diff --git a/include/linux/kref.h b/include/linux/kref.h index 4972e6e9ca93..e15828fd71f1 100644 --- a/include/linux/kref.h +++ b/include/linux/kref.h @@ -39,8 +39,11 @@ static inline void kref_init(struct kref *kref) */ static inline void kref_get(struct kref *kref) { - WARN_ON(!atomic_read(&kref->refcount)); - atomic_inc(&kref->refcount); + /* If refcount was 0 before incrementing then we have a race + * condition when this kref is freeing by some other thread right now. + * In this case one should use kref_get_unless_zero() + */ + WARN_ON_ONCE(atomic_inc_return(&kref->refcount) < 2); } /** @@ -100,7 +103,7 @@ static inline int kref_put_mutex(struct kref *kref, struct mutex *lock) { WARN_ON(release == NULL); - if (unlikely(!atomic_add_unless(&kref->refcount, -1, 1))) { + if (unlikely(!atomic_add_unless(&kref->refcount, -1, 1))) { mutex_lock(lock); if (unlikely(!atomic_dec_and_test(&kref->refcount))) { mutex_unlock(lock); diff --git a/include/linux/lru_cache.h b/include/linux/lru_cache.h index 4019013c6593..46262284de47 100644 --- a/include/linux/lru_cache.h +++ b/include/linux/lru_cache.h @@ -256,6 +256,7 @@ extern void lc_destroy(struct lru_cache *lc); extern void lc_set(struct lru_cache *lc, unsigned int enr, int index); extern void lc_del(struct lru_cache *lc, struct lc_element *element); +extern struct lc_element *lc_get_cumulative(struct lru_cache *lc, unsigned int enr); extern struct lc_element *lc_try_get(struct lru_cache *lc, unsigned int enr); extern struct lc_element *lc_find(struct lru_cache *lc, unsigned int enr); extern struct lc_element *lc_get(struct lru_cache *lc, unsigned int enr); diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 53acaf64189f..a51b0134ce18 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -903,11 +903,12 @@ static inline int map_hw_to_sw_id(u16 header_id) } enum mlx4_net_trans_promisc_mode { - MLX4_FS_PROMISC_NONE = 0, - MLX4_FS_PROMISC_UPLINK, - /* For future use. Not implemented yet */ - MLX4_FS_PROMISC_FUNCTION_PORT, - MLX4_FS_PROMISC_ALL_MULTI, + MLX4_FS_REGULAR = 1, + MLX4_FS_ALL_DEFAULT, + MLX4_FS_MC_DEFAULT, + MLX4_FS_UC_SNIFFER, + MLX4_FS_MC_SNIFFER, + MLX4_FS_MODE_NUM, /* should be last */ }; struct mlx4_spec_eth { @@ -936,7 +937,7 @@ struct mlx4_spec_ipv4 { }; struct mlx4_spec_ib { - __be32 r_qpn; + __be32 l3_qpn; __be32 qpn_msk; u8 dst_gid[16]; u8 dst_gid_msk[16]; @@ -969,6 +970,92 @@ struct mlx4_net_trans_rule { u32 qpn; }; +struct mlx4_net_trans_rule_hw_ctrl { + __be16 prio; + u8 type; + u8 flags; + u8 rsvd1; + u8 funcid; + u8 vep; + u8 port; + __be32 qpn; + __be32 rsvd2; +}; + +struct mlx4_net_trans_rule_hw_ib { + u8 size; + u8 rsvd1; + __be16 id; + u32 rsvd2; + __be32 l3_qpn; + __be32 qpn_mask; + u8 dst_gid[16]; + u8 dst_gid_msk[16]; +} __packed; + +struct mlx4_net_trans_rule_hw_eth { + u8 size; + u8 rsvd; + __be16 id; + u8 rsvd1[6]; + u8 dst_mac[6]; + u16 rsvd2; + u8 dst_mac_msk[6]; + u16 rsvd3; + u8 src_mac[6]; + u16 rsvd4; + u8 src_mac_msk[6]; + u8 rsvd5; + u8 ether_type_enable; + __be16 ether_type; + __be16 vlan_tag_msk; + __be16 vlan_tag; +} __packed; + +struct mlx4_net_trans_rule_hw_tcp_udp { + u8 size; + u8 rsvd; + __be16 id; + __be16 rsvd1[3]; + __be16 dst_port; + __be16 rsvd2; + __be16 dst_port_msk; + __be16 rsvd3; + __be16 src_port; + __be16 rsvd4; + __be16 src_port_msk; +} __packed; + +struct mlx4_net_trans_rule_hw_ipv4 { + u8 size; + u8 rsvd; + __be16 id; + __be32 rsvd1; + __be32 dst_ip; + __be32 dst_ip_msk; + __be32 src_ip; + __be32 src_ip_msk; +} __packed; + +struct _rule_hw { + union { + struct { + u8 size; + u8 rsvd; + __be16 id; + }; + struct mlx4_net_trans_rule_hw_eth eth; + struct mlx4_net_trans_rule_hw_ib ib; + struct mlx4_net_trans_rule_hw_ipv4 ipv4; + struct mlx4_net_trans_rule_hw_tcp_udp tcp_udp; + }; +}; + +/* translating DMFS verbs sniffer rule to the FW API would need two reg IDs */ +struct mlx4_flow_handle { + u64 reg_id[2]; +}; + int mlx4_flow_steer_promisc_add(struct mlx4_dev *dev, u8 port, u32 qpn, enum mlx4_net_trans_promisc_mode mode); int mlx4_flow_steer_promisc_remove(struct mlx4_dev *dev, u8 port, @@ -1018,6 +1105,11 @@ void mlx4_counter_free(struct mlx4_dev *dev, u32 idx); int mlx4_flow_attach(struct mlx4_dev *dev, struct mlx4_net_trans_rule *rule, u64 *reg_id); int mlx4_flow_detach(struct mlx4_dev *dev, u64 reg_id); +int mlx4_map_sw_to_hw_steering_mode(struct mlx4_dev *dev, + enum mlx4_net_trans_promisc_mode flow_type); +int mlx4_map_sw_to_hw_steering_id(struct mlx4_dev *dev, + enum mlx4_net_trans_rule_id id); +int mlx4_hw_rule_sz(struct mlx4_dev *dev, enum mlx4_net_trans_rule_id id); void mlx4_sync_pkey_table(struct mlx4_dev *dev, int slave, int port, int i, int val); diff --git a/include/linux/mlx4/srq.h b/include/linux/mlx4/srq.h index 799a0697a383..192e0f7784f2 100644 --- a/include/linux/mlx4/srq.h +++ b/include/linux/mlx4/srq.h @@ -39,4 +39,6 @@ struct mlx4_wqe_srq_next_seg { u32 reserved2[3]; }; +struct mlx4_srq *mlx4_srq_lookup(struct mlx4_dev *dev, u32 srqn); + #endif /* MLX4_SRQ_H */ diff --git a/include/linux/mm.h b/include/linux/mm.h index 1a7f19e7f1a0..e0c8528a41a4 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -951,13 +951,19 @@ void unmap_vmas(struct mmu_gather *tlb, struct vm_area_struct *start_vma, * (see walk_page_range for more details) */ struct mm_walk { - int (*pgd_entry)(pgd_t *, unsigned long, unsigned long, struct mm_walk *); - int (*pud_entry)(pud_t *, unsigned long, unsigned long, struct mm_walk *); - int (*pmd_entry)(pmd_t *, unsigned long, unsigned long, struct mm_walk *); - int (*pte_entry)(pte_t *, unsigned long, unsigned long, struct mm_walk *); - int (*pte_hole)(unsigned long, unsigned long, struct mm_walk *); - int (*hugetlb_entry)(pte_t *, unsigned long, - unsigned long, unsigned long, struct mm_walk *); + int (*pgd_entry)(pgd_t *pgd, unsigned long addr, + unsigned long next, struct mm_walk *walk); + int (*pud_entry)(pud_t *pud, unsigned long addr, + unsigned long next, struct mm_walk *walk); + int (*pmd_entry)(pmd_t *pmd, unsigned long addr, + unsigned long next, struct mm_walk *walk); + int (*pte_entry)(pte_t *pte, unsigned long addr, + unsigned long next, struct mm_walk *walk); + int (*pte_hole)(unsigned long addr, unsigned long next, + struct mm_walk *walk); + int (*hugetlb_entry)(pte_t *pte, unsigned long hmask, + unsigned long addr, unsigned long next, + struct mm_walk *walk); struct mm_struct *mm; void *private; }; diff --git a/include/linux/mtd/blktrans.h b/include/linux/mtd/blktrans.h index 4eb0a50d0c55..e93837f647de 100644 --- a/include/linux/mtd/blktrans.h +++ b/include/linux/mtd/blktrans.h @@ -74,7 +74,7 @@ struct mtd_blktrans_ops { /* Called with mtd_table_mutex held; no race with add/remove */ int (*open)(struct mtd_blktrans_dev *dev); - int (*release)(struct mtd_blktrans_dev *dev); + void (*release)(struct mtd_blktrans_dev *dev); /* Called on {de,}registration and on subsequent addition/removal of devices, with mtd_table_mutex held. */ diff --git a/include/linux/mtd/mtd.h b/include/linux/mtd/mtd.h index f9ac2897b86b..a5cf4e8d6818 100644 --- a/include/linux/mtd/mtd.h +++ b/include/linux/mtd/mtd.h @@ -362,10 +362,10 @@ struct mtd_partition; struct mtd_part_parser_data; extern int mtd_device_parse_register(struct mtd_info *mtd, - const char **part_probe_types, - struct mtd_part_parser_data *parser_data, - const struct mtd_partition *defparts, - int defnr_parts); + const char * const *part_probe_types, + struct mtd_part_parser_data *parser_data, + const struct mtd_partition *defparts, + int defnr_parts); #define mtd_device_register(master, parts, nr_parts) \ mtd_device_parse_register(master, NULL, NULL, parts, nr_parts) extern int mtd_device_unregister(struct mtd_info *master); diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index ef52d9c91459..ab6363443ce8 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -86,7 +86,6 @@ extern int nand_unlock(struct mtd_info *mtd, loff_t ofs, uint64_t len); #define NAND_CMD_READOOB 0x50 #define NAND_CMD_ERASE1 0x60 #define NAND_CMD_STATUS 0x70 -#define NAND_CMD_STATUS_MULTI 0x71 #define NAND_CMD_SEQIN 0x80 #define NAND_CMD_RNDIN 0x85 #define NAND_CMD_READID 0x90 @@ -105,25 +104,6 @@ extern int nand_unlock(struct mtd_info *mtd, loff_t ofs, uint64_t len); #define NAND_CMD_RNDOUTSTART 0xE0 #define NAND_CMD_CACHEDPROG 0x15 -/* Extended commands for AG-AND device */ -/* - * Note: the command for NAND_CMD_DEPLETE1 is really 0x00 but - * there is no way to distinguish that from NAND_CMD_READ0 - * until the remaining sequence of commands has been completed - * so add a high order bit and mask it off in the command. - */ -#define NAND_CMD_DEPLETE1 0x100 -#define NAND_CMD_DEPLETE2 0x38 -#define NAND_CMD_STATUS_MULTI 0x71 -#define NAND_CMD_STATUS_ERROR 0x72 -/* multi-bank error status (banks 0-3) */ -#define NAND_CMD_STATUS_ERROR0 0x73 -#define NAND_CMD_STATUS_ERROR1 0x74 -#define NAND_CMD_STATUS_ERROR2 0x75 -#define NAND_CMD_STATUS_ERROR3 0x76 -#define NAND_CMD_STATUS_RESET 0x7f -#define NAND_CMD_STATUS_CLEAR 0xff - #define NAND_CMD_NONE -1 /* Status bits */ @@ -165,28 +145,8 @@ typedef enum { */ /* Buswidth is 16 bit */ #define NAND_BUSWIDTH_16 0x00000002 -/* Device supports partial programming without padding */ -#define NAND_NO_PADDING 0x00000004 /* Chip has cache program function */ #define NAND_CACHEPRG 0x00000008 -/* Chip has copy back function */ -#define NAND_COPYBACK 0x00000010 -/* - * AND Chip which has 4 banks and a confusing page / block - * assignment. See Renesas datasheet for further information. - */ -#define NAND_IS_AND 0x00000020 -/* - * Chip has a array of 4 pages which can be read without - * additional ready /busy waits. - */ -#define NAND_4PAGE_ARRAY 0x00000040 -/* - * Chip requires that BBT is periodically rewritten to prevent - * bits from adjacent blocks from 'leaking' in altering data. - * This happens with the Renesas AG-AND chips, possibly others. - */ -#define BBT_AUTO_REFRESH 0x00000080 /* * Chip requires ready check on read (for auto-incremented sequential read). * True only for small page devices; large page devices do not support @@ -207,13 +167,10 @@ typedef enum { #define NAND_SUBPAGE_READ 0x00001000 /* Options valid for Samsung large page devices */ -#define NAND_SAMSUNG_LP_OPTIONS \ - (NAND_NO_PADDING | NAND_CACHEPRG | NAND_COPYBACK) +#define NAND_SAMSUNG_LP_OPTIONS NAND_CACHEPRG /* Macros to identify the above */ -#define NAND_MUST_PAD(chip) (!(chip->options & NAND_NO_PADDING)) #define NAND_HAS_CACHEPROG(chip) ((chip->options & NAND_CACHEPRG)) -#define NAND_HAS_COPYBACK(chip) ((chip->options & NAND_COPYBACK)) #define NAND_HAS_SUBPAGE_READ(chip) ((chip->options & NAND_SUBPAGE_READ)) /* Non chip related options */ @@ -361,6 +318,7 @@ struct nand_hw_control { * any single ECC step, 0 if bitflips uncorrectable, -EIO hw error * @read_subpage: function to read parts of the page covered by ECC; * returns same as read_page() + * @write_subpage: function to write parts of the page covered by ECC. * @write_page: function to write a page according to the ECC generator * requirements. * @write_oob_raw: function to write chip OOB data without ECC @@ -392,6 +350,9 @@ struct nand_ecc_ctrl { uint8_t *buf, int oob_required, int page); int (*read_subpage)(struct mtd_info *mtd, struct nand_chip *chip, uint32_t offs, uint32_t len, uint8_t *buf); + int (*write_subpage)(struct mtd_info *mtd, struct nand_chip *chip, + uint32_t offset, uint32_t data_len, + const uint8_t *data_buf, int oob_required); int (*write_page)(struct mtd_info *mtd, struct nand_chip *chip, const uint8_t *buf, int oob_required); int (*write_oob_raw)(struct mtd_info *mtd, struct nand_chip *chip, @@ -527,8 +488,8 @@ struct nand_chip { int (*errstat)(struct mtd_info *mtd, struct nand_chip *this, int state, int status, int page); int (*write_page)(struct mtd_info *mtd, struct nand_chip *chip, - const uint8_t *buf, int oob_required, int page, - int cached, int raw); + uint32_t offset, int data_len, const uint8_t *buf, + int oob_required, int page, int cached, int raw); int (*onfi_set_features)(struct mtd_info *mtd, struct nand_chip *chip, int feature_addr, uint8_t *subfeature_para); int (*onfi_get_features)(struct mtd_info *mtd, struct nand_chip *chip, @@ -589,25 +550,65 @@ struct nand_chip { #define NAND_MFR_MACRONIX 0xc2 #define NAND_MFR_EON 0x92 +/* The maximum expected count of bytes in the NAND ID sequence */ +#define NAND_MAX_ID_LEN 8 + +/* + * A helper for defining older NAND chips where the second ID byte fully + * defined the chip, including the geometry (chip size, eraseblock size, page + * size). All these chips have 512 bytes NAND page size. + */ +#define LEGACY_ID_NAND(nm, devid, chipsz, erasesz, opts) \ + { .name = (nm), {{ .dev_id = (devid) }}, .pagesize = 512, \ + .chipsize = (chipsz), .erasesize = (erasesz), .options = (opts) } + +/* + * A helper for defining newer chips which report their page size and + * eraseblock size via the extended ID bytes. + * + * The real difference between LEGACY_ID_NAND and EXTENDED_ID_NAND is that with + * EXTENDED_ID_NAND, manufacturers overloaded the same device ID so that the + * device ID now only represented a particular total chip size (and voltage, + * buswidth), and the page size, eraseblock size, and OOB size could vary while + * using the same device ID. + */ +#define EXTENDED_ID_NAND(nm, devid, chipsz, opts) \ + { .name = (nm), {{ .dev_id = (devid) }}, .chipsize = (chipsz), \ + .options = (opts) } + /** * struct nand_flash_dev - NAND Flash Device ID Structure - * @name: Identify the device type - * @id: device ID code - * @pagesize: Pagesize in bytes. Either 256 or 512 or 0 - * If the pagesize is 0, then the real pagesize - * and the eraseize are determined from the - * extended id bytes in the chip - * @erasesize: Size of an erase block in the flash device. - * @chipsize: Total chipsize in Mega Bytes - * @options: Bitfield to store chip relevant options + * @name: a human-readable name of the NAND chip + * @dev_id: the device ID (the second byte of the full chip ID array) + * @mfr_id: manufecturer ID part of the full chip ID array (refers the same + * memory address as @id[0]) + * @dev_id: device ID part of the full chip ID array (refers the same memory + * address as @id[1]) + * @id: full device ID array + * @pagesize: size of the NAND page in bytes; if 0, then the real page size (as + * well as the eraseblock size) is determined from the extended NAND + * chip ID array) + * @chipsize: total chip size in MiB + * @erasesize: eraseblock size in bytes (determined from the extended ID if 0) + * @options: stores various chip bit options + * @id_len: The valid length of the @id. + * @oobsize: OOB size */ struct nand_flash_dev { char *name; - int id; - unsigned long pagesize; - unsigned long chipsize; - unsigned long erasesize; - unsigned long options; + union { + struct { + uint8_t mfr_id; + uint8_t dev_id; + }; + uint8_t id[NAND_MAX_ID_LEN]; + }; + unsigned int pagesize; + unsigned int chipsize; + unsigned int erasesize; + unsigned int options; + uint16_t id_len; + uint16_t oobsize; }; /** diff --git a/include/linux/mtd/physmap.h b/include/linux/mtd/physmap.h index d2887e76b7f6..aa6a2633c2da 100644 --- a/include/linux/mtd/physmap.h +++ b/include/linux/mtd/physmap.h @@ -30,7 +30,7 @@ struct physmap_flash_data { unsigned int pfow_base; char *probe_type; struct mtd_partition *parts; - const char **part_probe_types; + const char * const *part_probe_types; }; #endif /* __LINUX_MTD_PHYSMAP__ */ diff --git a/include/linux/mtd/plat-ram.h b/include/linux/mtd/plat-ram.h index e07890aff1cf..44212d65aa97 100644 --- a/include/linux/mtd/plat-ram.h +++ b/include/linux/mtd/plat-ram.h @@ -20,8 +20,8 @@ struct platdata_mtd_ram { const char *mapname; - const char **map_probes; - const char **probes; + const char * const *map_probes; + const char * const *probes; struct mtd_partition *partitions; int nr_partitions; int bankwidth; diff --git a/include/linux/of_dma.h b/include/linux/of_dma.h index d15073e080dd..364dda734877 100644 --- a/include/linux/of_dma.h +++ b/include/linux/of_dma.h @@ -25,7 +25,6 @@ struct of_dma { struct dma_chan *(*of_dma_xlate) (struct of_phandle_args *, struct of_dma *); void *of_dma_data; - int use_count; }; struct of_dma_filter_info { @@ -38,9 +37,9 @@ extern int of_dma_controller_register(struct device_node *np, struct dma_chan *(*of_dma_xlate) (struct of_phandle_args *, struct of_dma *), void *data); -extern int of_dma_controller_free(struct device_node *np); +extern void of_dma_controller_free(struct device_node *np); extern struct dma_chan *of_dma_request_slave_channel(struct device_node *np, - char *name); + const char *name); extern struct dma_chan *of_dma_simple_xlate(struct of_phandle_args *dma_spec, struct of_dma *ofdma); #else @@ -52,13 +51,12 @@ static inline int of_dma_controller_register(struct device_node *np, return -ENODEV; } -static inline int of_dma_controller_free(struct device_node *np) +static inline void of_dma_controller_free(struct device_node *np) { - return -ENODEV; } static inline struct dma_chan *of_dma_request_slave_channel(struct device_node *np, - char *name) + const char *name) { return NULL; } diff --git a/include/linux/pid_namespace.h b/include/linux/pid_namespace.h index 731e4ecee3bd..e2772666f004 100644 --- a/include/linux/pid_namespace.h +++ b/include/linux/pid_namespace.h @@ -4,6 +4,7 @@ #include <linux/sched.h> #include <linux/bug.h> #include <linux/mm.h> +#include <linux/workqueue.h> #include <linux/threads.h> #include <linux/nsproxy.h> #include <linux/kref.h> diff --git a/include/linux/platform_data/elm.h b/include/linux/platform_data/elm.h index 1bd5244d1dcd..bf0a83b7ed9d 100644 --- a/include/linux/platform_data/elm.h +++ b/include/linux/platform_data/elm.h @@ -50,5 +50,5 @@ struct elm_errorvec { void elm_decode_bch_error_page(struct device *dev, u8 *ecc_calc, struct elm_errorvec *err_vec); -void elm_config(struct device *dev, enum bch_ecc bch_type); +int elm_config(struct device *dev, enum bch_ecc bch_type); #endif /* __ELM_H */ diff --git a/include/linux/random.h b/include/linux/random.h index 347ce553a306..3b9377d6b7a5 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -29,13 +29,6 @@ u32 prandom_u32(void); void prandom_bytes(void *buf, int nbytes); void prandom_seed(u32 seed); -/* - * These macros are preserved for backward compatibility and should be - * removed as soon as a transition is finished. - */ -#define random32() prandom_u32() -#define srandom32(seed) prandom_seed(seed) - u32 prandom_u32_state(struct rnd_state *); void prandom_bytes_state(struct rnd_state *state, void *buf, int nbytes); diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h index 8da67d625e13..0616ffe45702 100644 --- a/include/linux/rwsem.h +++ b/include/linux/rwsem.h @@ -133,10 +133,20 @@ do { \ _down_write_nest_lock(sem, &(nest_lock)->dep_map); \ } while (0); +/* + * Take/release a lock when not the owner will release it. + * + * [ This API should be avoided as much as possible - the + * proper abstraction for this case is completions. ] + */ +extern void down_read_non_owner(struct rw_semaphore *sem); +extern void up_read_non_owner(struct rw_semaphore *sem); #else # define down_read_nested(sem, subclass) down_read(sem) # define down_write_nest_lock(sem, nest_lock) down_write(sem) # define down_write_nested(sem, subclass) down_write(sem) +# define down_read_non_owner(sem) down_read(sem) +# define up_read_non_owner(sem) up_read(sem) #endif #endif /* _LINUX_RWSEM_H */ diff --git a/include/linux/sched.h b/include/linux/sched.h index 4800e9d1864c..caa8f4d0186b 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -313,8 +313,6 @@ extern void schedule_preempt_disabled(void); struct nsproxy; struct user_namespace; -#include <linux/aio.h> - #ifdef CONFIG_MMU extern void arch_pick_mmap_layout(struct mm_struct *mm); extern unsigned long @@ -1413,6 +1411,10 @@ struct task_struct { #ifdef CONFIG_UPROBES struct uprobe_task *utask; #endif +#if defined(CONFIG_BCACHE) || defined(CONFIG_BCACHE_MODULE) + unsigned int sequential_io; + unsigned int sequential_io_avg; +#endif }; /* Future-safe accessor for struct task_struct's cpus_allowed. */ diff --git a/include/linux/sudmac.h b/include/linux/sudmac.h new file mode 100644 index 000000000000..377b8a5788fa --- /dev/null +++ b/include/linux/sudmac.h @@ -0,0 +1,52 @@ +/* + * Header for the SUDMAC driver + * + * Copyright (C) 2013 Renesas Solutions Corp. + * + * This is free software; you can redistribute it and/or modify + * it under the terms of version 2 of the GNU General Public License as + * published by the Free Software Foundation. + */ +#ifndef SUDMAC_H +#define SUDMAC_H + +#include <linux/dmaengine.h> +#include <linux/shdma-base.h> +#include <linux/types.h> + +/* Used by slave DMA clients to request DMA to/from a specific peripheral */ +struct sudmac_slave { + struct shdma_slave shdma_slave; /* Set by the platform */ +}; + +/* + * Supplied by platforms to specify, how a DMA channel has to be configured for + * a certain peripheral + */ +struct sudmac_slave_config { + int slave_id; +}; + +struct sudmac_channel { + unsigned long offset; + unsigned long config; + unsigned long wait; /* The configuable range is 0 to 3 */ + unsigned long dint_end_bit; +}; + +struct sudmac_pdata { + const struct sudmac_slave_config *slave; + int slave_num; + const struct sudmac_channel *channel; + int channel_num; +}; + +/* Definitions for the sudmac_channel.config */ +#define SUDMAC_TX_BUFFER_MODE BIT(0) +#define SUDMAC_RX_END_MODE BIT(1) + +/* Definitions for the sudmac_channel.dint_end_bit */ +#define SUDMAC_DMA_BIT_CH0 BIT(0) +#define SUDMAC_DMA_BIT_CH1 BIT(1) + +#endif diff --git a/include/linux/thermal.h b/include/linux/thermal.h index e3c0ae9bb1fa..a386a1cbb6e1 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -33,8 +33,11 @@ #define THERMAL_MAX_TRIPS 12 #define THERMAL_NAME_LENGTH 20 +/* invalid cooling state */ +#define THERMAL_CSTATE_INVALID -1UL + /* No upper/lower limit requirement */ -#define THERMAL_NO_LIMIT -1UL +#define THERMAL_NO_LIMIT THERMAL_CSTATE_INVALID /* Unit conversion macros */ #define KELVIN_TO_CELSIUS(t) (long)(((long)t-2732 >= 0) ? \ @@ -184,7 +187,6 @@ struct thermal_governor { char name[THERMAL_NAME_LENGTH]; int (*throttle)(struct thermal_zone_device *tz, int trip); struct list_head governor_list; - struct module *owner; }; /* Structure that holds binding parameters for a zone */ @@ -237,21 +239,20 @@ void thermal_zone_device_update(struct thermal_zone_device *); struct thermal_cooling_device *thermal_cooling_device_register(char *, void *, const struct thermal_cooling_device_ops *); void thermal_cooling_device_unregister(struct thermal_cooling_device *); +struct thermal_zone_device *thermal_zone_get_zone_by_name(const char *name); +int thermal_zone_get_temp(struct thermal_zone_device *tz, unsigned long *temp); int get_tz_trend(struct thermal_zone_device *, int); struct thermal_instance *get_thermal_instance(struct thermal_zone_device *, struct thermal_cooling_device *, int); void thermal_cdev_update(struct thermal_cooling_device *); -void notify_thermal_framework(struct thermal_zone_device *, int); - -int thermal_register_governor(struct thermal_governor *); -void thermal_unregister_governor(struct thermal_governor *); +void thermal_notify_framework(struct thermal_zone_device *, int); #ifdef CONFIG_NET extern int thermal_generate_netlink_event(struct thermal_zone_device *tz, enum events event); #else -static int thermal_generate_netlink_event(struct thermal_zone_device *tz, +static inline int thermal_generate_netlink_event(struct thermal_zone_device *tz, enum events event) { return 0; diff --git a/include/linux/wait.h b/include/linux/wait.h index 7cb64d4b499d..ac38be2692d8 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -330,6 +330,92 @@ do { \ __ret; \ }) +#define __wait_event_hrtimeout(wq, condition, timeout, state) \ +({ \ + int __ret = 0; \ + DEFINE_WAIT(__wait); \ + struct hrtimer_sleeper __t; \ + \ + hrtimer_init_on_stack(&__t.timer, CLOCK_MONOTONIC, \ + HRTIMER_MODE_REL); \ + hrtimer_init_sleeper(&__t, current); \ + if ((timeout).tv64 != KTIME_MAX) \ + hrtimer_start_range_ns(&__t.timer, timeout, \ + current->timer_slack_ns, \ + HRTIMER_MODE_REL); \ + \ + for (;;) { \ + prepare_to_wait(&wq, &__wait, state); \ + if (condition) \ + break; \ + if (state == TASK_INTERRUPTIBLE && \ + signal_pending(current)) { \ + __ret = -ERESTARTSYS; \ + break; \ + } \ + if (!__t.task) { \ + __ret = -ETIME; \ + break; \ + } \ + schedule(); \ + } \ + \ + hrtimer_cancel(&__t.timer); \ + destroy_hrtimer_on_stack(&__t.timer); \ + finish_wait(&wq, &__wait); \ + __ret; \ +}) + +/** + * wait_event_hrtimeout - sleep until a condition gets true or a timeout elapses + * @wq: the waitqueue to wait on + * @condition: a C expression for the event to wait for + * @timeout: timeout, as a ktime_t + * + * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the + * @condition evaluates to true or a signal is received. + * The @condition is checked each time the waitqueue @wq is woken up. + * + * wake_up() has to be called after changing any variable that could + * change the result of the wait condition. + * + * The function returns 0 if @condition became true, or -ETIME if the timeout + * elapsed. + */ +#define wait_event_hrtimeout(wq, condition, timeout) \ +({ \ + int __ret = 0; \ + if (!(condition)) \ + __ret = __wait_event_hrtimeout(wq, condition, timeout, \ + TASK_UNINTERRUPTIBLE); \ + __ret; \ +}) + +/** + * wait_event_interruptible_hrtimeout - sleep until a condition gets true or a timeout elapses + * @wq: the waitqueue to wait on + * @condition: a C expression for the event to wait for + * @timeout: timeout, as a ktime_t + * + * The process is put to sleep (TASK_INTERRUPTIBLE) until the + * @condition evaluates to true or a signal is received. + * The @condition is checked each time the waitqueue @wq is woken up. + * + * wake_up() has to be called after changing any variable that could + * change the result of the wait condition. + * + * The function returns 0 if @condition became true, -ERESTARTSYS if it was + * interrupted by a signal, or -ETIME if the timeout elapsed. + */ +#define wait_event_interruptible_hrtimeout(wq, condition, timeout) \ +({ \ + long __ret = 0; \ + if (!(condition)) \ + __ret = __wait_event_hrtimeout(wq, condition, timeout, \ + TASK_INTERRUPTIBLE); \ + __ret; \ +}) + #define __wait_event_interruptible_exclusive(wq, condition, ret) \ do { \ DEFINE_WAIT(__wait); \ diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 9a9367c0c076..579a5007c696 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -5,6 +5,7 @@ #define WRITEBACK_H #include <linux/sched.h> +#include <linux/workqueue.h> #include <linux/fs.h> DECLARE_PER_CPU(int, dirty_throttle_leaks); diff --git a/include/trace/events/bcache.h b/include/trace/events/bcache.h new file mode 100644 index 000000000000..3cc5a0b278c3 --- /dev/null +++ b/include/trace/events/bcache.h @@ -0,0 +1,271 @@ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM bcache + +#if !defined(_TRACE_BCACHE_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_BCACHE_H + +#include <linux/tracepoint.h> + +struct search; + +DECLARE_EVENT_CLASS(bcache_request, + + TP_PROTO(struct search *s, struct bio *bio), + + TP_ARGS(s, bio), + + TP_STRUCT__entry( + __field(dev_t, dev ) + __field(unsigned int, orig_major ) + __field(unsigned int, orig_minor ) + __field(sector_t, sector ) + __field(dev_t, orig_sector ) + __field(unsigned int, nr_sector ) + __array(char, rwbs, 6 ) + __array(char, comm, TASK_COMM_LEN ) + ), + + TP_fast_assign( + __entry->dev = bio->bi_bdev->bd_dev; + __entry->orig_major = s->d->disk->major; + __entry->orig_minor = s->d->disk->first_minor; + __entry->sector = bio->bi_sector; + __entry->orig_sector = bio->bi_sector - 16; + __entry->nr_sector = bio->bi_size >> 9; + blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_size); + memcpy(__entry->comm, current->comm, TASK_COMM_LEN); + ), + + TP_printk("%d,%d %s %llu + %u [%s] (from %d,%d @ %llu)", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->rwbs, + (unsigned long long)__entry->sector, + __entry->nr_sector, __entry->comm, + __entry->orig_major, __entry->orig_minor, + (unsigned long long)__entry->orig_sector) +); + +DEFINE_EVENT(bcache_request, bcache_request_start, + + TP_PROTO(struct search *s, struct bio *bio), + + TP_ARGS(s, bio) +); + +DEFINE_EVENT(bcache_request, bcache_request_end, + + TP_PROTO(struct search *s, struct bio *bio), + + TP_ARGS(s, bio) +); + +DECLARE_EVENT_CLASS(bcache_bio, + + TP_PROTO(struct bio *bio), + + TP_ARGS(bio), + + TP_STRUCT__entry( + __field(dev_t, dev ) + __field(sector_t, sector ) + __field(unsigned int, nr_sector ) + __array(char, rwbs, 6 ) + __array(char, comm, TASK_COMM_LEN ) + ), + + TP_fast_assign( + __entry->dev = bio->bi_bdev->bd_dev; + __entry->sector = bio->bi_sector; + __entry->nr_sector = bio->bi_size >> 9; + blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_size); + memcpy(__entry->comm, current->comm, TASK_COMM_LEN); + ), + + TP_printk("%d,%d %s %llu + %u [%s]", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->rwbs, + (unsigned long long)__entry->sector, + __entry->nr_sector, __entry->comm) +); + + +DEFINE_EVENT(bcache_bio, bcache_passthrough, + + TP_PROTO(struct bio *bio), + + TP_ARGS(bio) +); + +DEFINE_EVENT(bcache_bio, bcache_cache_hit, + + TP_PROTO(struct bio *bio), + + TP_ARGS(bio) +); + +DEFINE_EVENT(bcache_bio, bcache_cache_miss, + + TP_PROTO(struct bio *bio), + + TP_ARGS(bio) +); + +DEFINE_EVENT(bcache_bio, bcache_read_retry, + + TP_PROTO(struct bio *bio), + + TP_ARGS(bio) +); + +DEFINE_EVENT(bcache_bio, bcache_writethrough, + + TP_PROTO(struct bio *bio), + + TP_ARGS(bio) +); + +DEFINE_EVENT(bcache_bio, bcache_writeback, + + TP_PROTO(struct bio *bio), + + TP_ARGS(bio) +); + +DEFINE_EVENT(bcache_bio, bcache_write_skip, + + TP_PROTO(struct bio *bio), + + TP_ARGS(bio) +); + +DEFINE_EVENT(bcache_bio, bcache_btree_read, + + TP_PROTO(struct bio *bio), + + TP_ARGS(bio) +); + +DEFINE_EVENT(bcache_bio, bcache_btree_write, + + TP_PROTO(struct bio *bio), + + TP_ARGS(bio) +); + +DEFINE_EVENT(bcache_bio, bcache_write_dirty, + + TP_PROTO(struct bio *bio), + + TP_ARGS(bio) +); + +DEFINE_EVENT(bcache_bio, bcache_read_dirty, + + TP_PROTO(struct bio *bio), + + TP_ARGS(bio) +); + +DEFINE_EVENT(bcache_bio, bcache_write_moving, + + TP_PROTO(struct bio *bio), + + TP_ARGS(bio) +); + +DEFINE_EVENT(bcache_bio, bcache_read_moving, + + TP_PROTO(struct bio *bio), + + TP_ARGS(bio) +); + +DEFINE_EVENT(bcache_bio, bcache_journal_write, + + TP_PROTO(struct bio *bio), + + TP_ARGS(bio) +); + +DECLARE_EVENT_CLASS(bcache_cache_bio, + + TP_PROTO(struct bio *bio, + sector_t orig_sector, + struct block_device* orig_bdev), + + TP_ARGS(bio, orig_sector, orig_bdev), + + TP_STRUCT__entry( + __field(dev_t, dev ) + __field(dev_t, orig_dev ) + __field(sector_t, sector ) + __field(sector_t, orig_sector ) + __field(unsigned int, nr_sector ) + __array(char, rwbs, 6 ) + __array(char, comm, TASK_COMM_LEN ) + ), + + TP_fast_assign( + __entry->dev = bio->bi_bdev->bd_dev; + __entry->orig_dev = orig_bdev->bd_dev; + __entry->sector = bio->bi_sector; + __entry->orig_sector = orig_sector; + __entry->nr_sector = bio->bi_size >> 9; + blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_size); + memcpy(__entry->comm, current->comm, TASK_COMM_LEN); + ), + + TP_printk("%d,%d %s %llu + %u [%s] (from %d,%d %llu)", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->rwbs, + (unsigned long long)__entry->sector, + __entry->nr_sector, __entry->comm, + MAJOR(__entry->orig_dev), MINOR(__entry->orig_dev), + (unsigned long long)__entry->orig_sector) +); + +DEFINE_EVENT(bcache_cache_bio, bcache_cache_insert, + + TP_PROTO(struct bio *bio, + sector_t orig_sector, + struct block_device *orig_bdev), + + TP_ARGS(bio, orig_sector, orig_bdev) +); + +DECLARE_EVENT_CLASS(bcache_gc, + + TP_PROTO(uint8_t *uuid), + + TP_ARGS(uuid), + + TP_STRUCT__entry( + __field(uint8_t *, uuid) + ), + + TP_fast_assign( + __entry->uuid = uuid; + ), + + TP_printk("%pU", __entry->uuid) +); + + +DEFINE_EVENT(bcache_gc, bcache_gc_start, + + TP_PROTO(uint8_t *uuid), + + TP_ARGS(uuid) +); + +DEFINE_EVENT(bcache_gc, bcache_gc_end, + + TP_PROTO(uint8_t *uuid), + + TP_ARGS(uuid) +); + +#endif /* _TRACE_BCACHE_H */ + +/* This part must be outside protection */ +#include <trace/define_trace.h> diff --git a/include/trace/events/block.h b/include/trace/events/block.h index 9c1467357b03..60ae7c3db912 100644 --- a/include/trace/events/block.h +++ b/include/trace/events/block.h @@ -244,7 +244,7 @@ TRACE_EVENT(block_bio_bounce, __entry->dev = bio->bi_bdev ? bio->bi_bdev->bd_dev : 0; __entry->sector = bio->bi_sector; - __entry->nr_sector = bio->bi_size >> 9; + __entry->nr_sector = bio_sectors(bio); blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_size); memcpy(__entry->comm, current->comm, TASK_COMM_LEN); ), @@ -281,7 +281,7 @@ TRACE_EVENT(block_bio_complete, TP_fast_assign( __entry->dev = bio->bi_bdev->bd_dev; __entry->sector = bio->bi_sector; - __entry->nr_sector = bio->bi_size >> 9; + __entry->nr_sector = bio_sectors(bio); __entry->error = error; blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_size); ), @@ -309,7 +309,7 @@ DECLARE_EVENT_CLASS(block_bio_merge, TP_fast_assign( __entry->dev = bio->bi_bdev->bd_dev; __entry->sector = bio->bi_sector; - __entry->nr_sector = bio->bi_size >> 9; + __entry->nr_sector = bio_sectors(bio); blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_size); memcpy(__entry->comm, current->comm, TASK_COMM_LEN); ), @@ -376,7 +376,7 @@ TRACE_EVENT(block_bio_queue, TP_fast_assign( __entry->dev = bio->bi_bdev->bd_dev; __entry->sector = bio->bi_sector; - __entry->nr_sector = bio->bi_size >> 9; + __entry->nr_sector = bio_sectors(bio); blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_size); memcpy(__entry->comm, current->comm, TASK_COMM_LEN); ), @@ -404,7 +404,7 @@ DECLARE_EVENT_CLASS(block_get_rq, TP_fast_assign( __entry->dev = bio ? bio->bi_bdev->bd_dev : 0; __entry->sector = bio ? bio->bi_sector : 0; - __entry->nr_sector = bio ? bio->bi_size >> 9 : 0; + __entry->nr_sector = bio ? bio_sectors(bio) : 0; blk_fill_rwbs(__entry->rwbs, bio ? bio->bi_rw : 0, __entry->nr_sector); memcpy(__entry->comm, current->comm, TASK_COMM_LEN); @@ -580,7 +580,7 @@ TRACE_EVENT(block_bio_remap, TP_fast_assign( __entry->dev = bio->bi_bdev->bd_dev; __entry->sector = bio->bi_sector; - __entry->nr_sector = bio->bi_size >> 9; + __entry->nr_sector = bio_sectors(bio); __entry->old_dev = dev; __entry->old_sector = from; blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_size); diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h new file mode 100644 index 000000000000..52ae54828eda --- /dev/null +++ b/include/trace/events/f2fs.h @@ -0,0 +1,682 @@ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM f2fs + +#if !defined(_TRACE_F2FS_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_F2FS_H + +#include <linux/tracepoint.h> + +#define show_dev(entry) MAJOR(entry->dev), MINOR(entry->dev) +#define show_dev_ino(entry) show_dev(entry), (unsigned long)entry->ino + +#define show_block_type(type) \ + __print_symbolic(type, \ + { NODE, "NODE" }, \ + { DATA, "DATA" }, \ + { META, "META" }, \ + { META_FLUSH, "META_FLUSH" }) + +#define show_bio_type(type) \ + __print_symbolic(type, \ + { READ, "READ" }, \ + { READA, "READAHEAD" }, \ + { READ_SYNC, "READ_SYNC" }, \ + { WRITE, "WRITE" }, \ + { WRITE_SYNC, "WRITE_SYNC" }, \ + { WRITE_FLUSH, "WRITE_FLUSH" }, \ + { WRITE_FUA, "WRITE_FUA" }) + +#define show_data_type(type) \ + __print_symbolic(type, \ + { CURSEG_HOT_DATA, "Hot DATA" }, \ + { CURSEG_WARM_DATA, "Warm DATA" }, \ + { CURSEG_COLD_DATA, "Cold DATA" }, \ + { CURSEG_HOT_NODE, "Hot NODE" }, \ + { CURSEG_WARM_NODE, "Warm NODE" }, \ + { CURSEG_COLD_NODE, "Cold NODE" }, \ + { NO_CHECK_TYPE, "No TYPE" }) + +#define show_gc_type(type) \ + __print_symbolic(type, \ + { FG_GC, "Foreground GC" }, \ + { BG_GC, "Background GC" }) + +#define show_alloc_mode(type) \ + __print_symbolic(type, \ + { LFS, "LFS-mode" }, \ + { SSR, "SSR-mode" }) + +#define show_victim_policy(type) \ + __print_symbolic(type, \ + { GC_GREEDY, "Greedy" }, \ + { GC_CB, "Cost-Benefit" }) + +struct victim_sel_policy; + +DECLARE_EVENT_CLASS(f2fs__inode, + + TP_PROTO(struct inode *inode), + + TP_ARGS(inode), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(ino_t, ino) + __field(ino_t, pino) + __field(umode_t, mode) + __field(loff_t, size) + __field(unsigned int, nlink) + __field(blkcnt_t, blocks) + __field(__u8, advise) + ), + + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->ino = inode->i_ino; + __entry->pino = F2FS_I(inode)->i_pino; + __entry->mode = inode->i_mode; + __entry->nlink = inode->i_nlink; + __entry->size = inode->i_size; + __entry->blocks = inode->i_blocks; + __entry->advise = F2FS_I(inode)->i_advise; + ), + + TP_printk("dev = (%d,%d), ino = %lu, pino = %lu, i_mode = 0x%hx, " + "i_size = %lld, i_nlink = %u, i_blocks = %llu, i_advise = 0x%x", + show_dev_ino(__entry), + (unsigned long)__entry->pino, + __entry->mode, + __entry->size, + (unsigned int)__entry->nlink, + (unsigned long long)__entry->blocks, + (unsigned char)__entry->advise) +); + +DECLARE_EVENT_CLASS(f2fs__inode_exit, + + TP_PROTO(struct inode *inode, int ret), + + TP_ARGS(inode, ret), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(ino_t, ino) + __field(int, ret) + ), + + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->ino = inode->i_ino; + __entry->ret = ret; + ), + + TP_printk("dev = (%d,%d), ino = %lu, ret = %d", + show_dev_ino(__entry), + __entry->ret) +); + +DEFINE_EVENT(f2fs__inode, f2fs_sync_file_enter, + + TP_PROTO(struct inode *inode), + + TP_ARGS(inode) +); + +TRACE_EVENT(f2fs_sync_file_exit, + + TP_PROTO(struct inode *inode, bool need_cp, int datasync, int ret), + + TP_ARGS(inode, need_cp, datasync, ret), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(ino_t, ino) + __field(bool, need_cp) + __field(int, datasync) + __field(int, ret) + ), + + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->ino = inode->i_ino; + __entry->need_cp = need_cp; + __entry->datasync = datasync; + __entry->ret = ret; + ), + + TP_printk("dev = (%d,%d), ino = %lu, checkpoint is %s, " + "datasync = %d, ret = %d", + show_dev_ino(__entry), + __entry->need_cp ? "needed" : "not needed", + __entry->datasync, + __entry->ret) +); + +TRACE_EVENT(f2fs_sync_fs, + + TP_PROTO(struct super_block *sb, int wait), + + TP_ARGS(sb, wait), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(int, dirty) + __field(int, wait) + ), + + TP_fast_assign( + __entry->dev = sb->s_dev; + __entry->dirty = F2FS_SB(sb)->s_dirty; + __entry->wait = wait; + ), + + TP_printk("dev = (%d,%d), superblock is %s, wait = %d", + show_dev(__entry), + __entry->dirty ? "dirty" : "not dirty", + __entry->wait) +); + +DEFINE_EVENT(f2fs__inode, f2fs_iget, + + TP_PROTO(struct inode *inode), + + TP_ARGS(inode) +); + +DEFINE_EVENT(f2fs__inode_exit, f2fs_iget_exit, + + TP_PROTO(struct inode *inode, int ret), + + TP_ARGS(inode, ret) +); + +DEFINE_EVENT(f2fs__inode, f2fs_evict_inode, + + TP_PROTO(struct inode *inode), + + TP_ARGS(inode) +); + +DEFINE_EVENT(f2fs__inode_exit, f2fs_new_inode, + + TP_PROTO(struct inode *inode, int ret), + + TP_ARGS(inode, ret) +); + +TRACE_EVENT(f2fs_unlink_enter, + + TP_PROTO(struct inode *dir, struct dentry *dentry), + + TP_ARGS(dir, dentry), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(ino_t, ino) + __field(loff_t, size) + __field(blkcnt_t, blocks) + __field(const char *, name) + ), + + TP_fast_assign( + __entry->dev = dir->i_sb->s_dev; + __entry->ino = dir->i_ino; + __entry->size = dir->i_size; + __entry->blocks = dir->i_blocks; + __entry->name = dentry->d_name.name; + ), + + TP_printk("dev = (%d,%d), dir ino = %lu, i_size = %lld, " + "i_blocks = %llu, name = %s", + show_dev_ino(__entry), + __entry->size, + (unsigned long long)__entry->blocks, + __entry->name) +); + +DEFINE_EVENT(f2fs__inode_exit, f2fs_unlink_exit, + + TP_PROTO(struct inode *inode, int ret), + + TP_ARGS(inode, ret) +); + +DEFINE_EVENT(f2fs__inode, f2fs_truncate, + + TP_PROTO(struct inode *inode), + + TP_ARGS(inode) +); + +TRACE_EVENT(f2fs_truncate_data_blocks_range, + + TP_PROTO(struct inode *inode, nid_t nid, unsigned int ofs, int free), + + TP_ARGS(inode, nid, ofs, free), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(ino_t, ino) + __field(nid_t, nid) + __field(unsigned int, ofs) + __field(int, free) + ), + + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->ino = inode->i_ino; + __entry->nid = nid; + __entry->ofs = ofs; + __entry->free = free; + ), + + TP_printk("dev = (%d,%d), ino = %lu, nid = %u, offset = %u, freed = %d", + show_dev_ino(__entry), + (unsigned int)__entry->nid, + __entry->ofs, + __entry->free) +); + +DECLARE_EVENT_CLASS(f2fs__truncate_op, + + TP_PROTO(struct inode *inode, u64 from), + + TP_ARGS(inode, from), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(ino_t, ino) + __field(loff_t, size) + __field(blkcnt_t, blocks) + __field(u64, from) + ), + + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->ino = inode->i_ino; + __entry->size = inode->i_size; + __entry->blocks = inode->i_blocks; + __entry->from = from; + ), + + TP_printk("dev = (%d,%d), ino = %lu, i_size = %lld, i_blocks = %llu, " + "start file offset = %llu", + show_dev_ino(__entry), + __entry->size, + (unsigned long long)__entry->blocks, + (unsigned long long)__entry->from) +); + +DEFINE_EVENT(f2fs__truncate_op, f2fs_truncate_blocks_enter, + + TP_PROTO(struct inode *inode, u64 from), + + TP_ARGS(inode, from) +); + +DEFINE_EVENT(f2fs__inode_exit, f2fs_truncate_blocks_exit, + + TP_PROTO(struct inode *inode, int ret), + + TP_ARGS(inode, ret) +); + +DEFINE_EVENT(f2fs__truncate_op, f2fs_truncate_inode_blocks_enter, + + TP_PROTO(struct inode *inode, u64 from), + + TP_ARGS(inode, from) +); + +DEFINE_EVENT(f2fs__inode_exit, f2fs_truncate_inode_blocks_exit, + + TP_PROTO(struct inode *inode, int ret), + + TP_ARGS(inode, ret) +); + +DECLARE_EVENT_CLASS(f2fs__truncate_node, + + TP_PROTO(struct inode *inode, nid_t nid, block_t blk_addr), + + TP_ARGS(inode, nid, blk_addr), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(ino_t, ino) + __field(nid_t, nid) + __field(block_t, blk_addr) + ), + + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->ino = inode->i_ino; + __entry->nid = nid; + __entry->blk_addr = blk_addr; + ), + + TP_printk("dev = (%d,%d), ino = %lu, nid = %u, block_address = 0x%llx", + show_dev_ino(__entry), + (unsigned int)__entry->nid, + (unsigned long long)__entry->blk_addr) +); + +DEFINE_EVENT(f2fs__truncate_node, f2fs_truncate_nodes_enter, + + TP_PROTO(struct inode *inode, nid_t nid, block_t blk_addr), + + TP_ARGS(inode, nid, blk_addr) +); + +DEFINE_EVENT(f2fs__inode_exit, f2fs_truncate_nodes_exit, + + TP_PROTO(struct inode *inode, int ret), + + TP_ARGS(inode, ret) +); + +DEFINE_EVENT(f2fs__truncate_node, f2fs_truncate_node, + + TP_PROTO(struct inode *inode, nid_t nid, block_t blk_addr), + + TP_ARGS(inode, nid, blk_addr) +); + +TRACE_EVENT(f2fs_truncate_partial_nodes, + + TP_PROTO(struct inode *inode, nid_t nid[], int depth, int err), + + TP_ARGS(inode, nid, depth, err), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(ino_t, ino) + __field(nid_t, nid[3]) + __field(int, depth) + __field(int, err) + ), + + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->ino = inode->i_ino; + __entry->nid[0] = nid[0]; + __entry->nid[1] = nid[1]; + __entry->nid[2] = nid[2]; + __entry->depth = depth; + __entry->err = err; + ), + + TP_printk("dev = (%d,%d), ino = %lu, " + "nid[0] = %u, nid[1] = %u, nid[2] = %u, depth = %d, err = %d", + show_dev_ino(__entry), + (unsigned int)__entry->nid[0], + (unsigned int)__entry->nid[1], + (unsigned int)__entry->nid[2], + __entry->depth, + __entry->err) +); + +TRACE_EVENT_CONDITION(f2fs_readpage, + + TP_PROTO(struct page *page, sector_t blkaddr, int type), + + TP_ARGS(page, blkaddr, type), + + TP_CONDITION(page->mapping), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(ino_t, ino) + __field(pgoff_t, index) + __field(sector_t, blkaddr) + __field(int, type) + ), + + TP_fast_assign( + __entry->dev = page->mapping->host->i_sb->s_dev; + __entry->ino = page->mapping->host->i_ino; + __entry->index = page->index; + __entry->blkaddr = blkaddr; + __entry->type = type; + ), + + TP_printk("dev = (%d,%d), ino = %lu, page_index = 0x%lx, " + "blkaddr = 0x%llx, bio_type = %s", + show_dev_ino(__entry), + (unsigned long)__entry->index, + (unsigned long long)__entry->blkaddr, + show_bio_type(__entry->type)) +); + +TRACE_EVENT(f2fs_get_data_block, + TP_PROTO(struct inode *inode, sector_t iblock, + struct buffer_head *bh, int ret), + + TP_ARGS(inode, iblock, bh, ret), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(ino_t, ino) + __field(sector_t, iblock) + __field(sector_t, bh_start) + __field(size_t, bh_size) + __field(int, ret) + ), + + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->ino = inode->i_ino; + __entry->iblock = iblock; + __entry->bh_start = bh->b_blocknr; + __entry->bh_size = bh->b_size; + __entry->ret = ret; + ), + + TP_printk("dev = (%d,%d), ino = %lu, file offset = %llu, " + "start blkaddr = 0x%llx, len = 0x%llx bytes, err = %d", + show_dev_ino(__entry), + (unsigned long long)__entry->iblock, + (unsigned long long)__entry->bh_start, + (unsigned long long)__entry->bh_size, + __entry->ret) +); + +TRACE_EVENT(f2fs_get_victim, + + TP_PROTO(struct super_block *sb, int type, int gc_type, + struct victim_sel_policy *p, unsigned int pre_victim, + unsigned int prefree, unsigned int free), + + TP_ARGS(sb, type, gc_type, p, pre_victim, prefree, free), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(int, type) + __field(int, gc_type) + __field(int, alloc_mode) + __field(int, gc_mode) + __field(unsigned int, victim) + __field(unsigned int, ofs_unit) + __field(unsigned int, pre_victim) + __field(unsigned int, prefree) + __field(unsigned int, free) + ), + + TP_fast_assign( + __entry->dev = sb->s_dev; + __entry->type = type; + __entry->gc_type = gc_type; + __entry->alloc_mode = p->alloc_mode; + __entry->gc_mode = p->gc_mode; + __entry->victim = p->min_segno; + __entry->ofs_unit = p->ofs_unit; + __entry->pre_victim = pre_victim; + __entry->prefree = prefree; + __entry->free = free; + ), + + TP_printk("dev = (%d,%d), type = %s, policy = (%s, %s, %s), victim = %u " + "ofs_unit = %u, pre_victim_secno = %d, prefree = %u, free = %u", + show_dev(__entry), + show_data_type(__entry->type), + show_gc_type(__entry->gc_type), + show_alloc_mode(__entry->alloc_mode), + show_victim_policy(__entry->gc_mode), + __entry->victim, + __entry->ofs_unit, + (int)__entry->pre_victim, + __entry->prefree, + __entry->free) +); + +TRACE_EVENT(f2fs_fallocate, + + TP_PROTO(struct inode *inode, int mode, + loff_t offset, loff_t len, int ret), + + TP_ARGS(inode, mode, offset, len, ret), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(ino_t, ino) + __field(int, mode) + __field(loff_t, offset) + __field(loff_t, len) + __field(loff_t, size) + __field(blkcnt_t, blocks) + __field(int, ret) + ), + + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->ino = inode->i_ino; + __entry->mode = mode; + __entry->offset = offset; + __entry->len = len; + __entry->size = inode->i_size; + __entry->blocks = inode->i_blocks; + __entry->ret = ret; + ), + + TP_printk("dev = (%d,%d), ino = %lu, mode = %x, offset = %lld, " + "len = %lld, i_size = %lld, i_blocks = %llu, ret = %d", + show_dev_ino(__entry), + __entry->mode, + (unsigned long long)__entry->offset, + (unsigned long long)__entry->len, + (unsigned long long)__entry->size, + (unsigned long long)__entry->blocks, + __entry->ret) +); + +TRACE_EVENT(f2fs_reserve_new_block, + + TP_PROTO(struct inode *inode, nid_t nid, unsigned int ofs_in_node), + + TP_ARGS(inode, nid, ofs_in_node), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(nid_t, nid) + __field(unsigned int, ofs_in_node) + ), + + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->nid = nid; + __entry->ofs_in_node = ofs_in_node; + ), + + TP_printk("dev = (%d,%d), nid = %u, ofs_in_node = %u", + show_dev(__entry), + (unsigned int)__entry->nid, + __entry->ofs_in_node) +); + +TRACE_EVENT(f2fs_do_submit_bio, + + TP_PROTO(struct super_block *sb, int btype, bool sync, struct bio *bio), + + TP_ARGS(sb, btype, sync, bio), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(int, btype) + __field(bool, sync) + __field(sector_t, sector) + __field(unsigned int, size) + ), + + TP_fast_assign( + __entry->dev = sb->s_dev; + __entry->btype = btype; + __entry->sync = sync; + __entry->sector = bio->bi_sector; + __entry->size = bio->bi_size; + ), + + TP_printk("dev = (%d,%d), type = %s, io = %s, sector = %lld, size = %u", + show_dev(__entry), + show_block_type(__entry->btype), + __entry->sync ? "sync" : "no sync", + (unsigned long long)__entry->sector, + __entry->size) +); + +TRACE_EVENT(f2fs_submit_write_page, + + TP_PROTO(struct page *page, block_t blk_addr, int type), + + TP_ARGS(page, blk_addr, type), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(ino_t, ino) + __field(int, type) + __field(pgoff_t, index) + __field(block_t, block) + ), + + TP_fast_assign( + __entry->dev = page->mapping->host->i_sb->s_dev; + __entry->ino = page->mapping->host->i_ino; + __entry->type = type; + __entry->index = page->index; + __entry->block = blk_addr; + ), + + TP_printk("dev = (%d,%d), ino = %lu, %s, index = %lu, blkaddr = 0x%llx", + show_dev_ino(__entry), + show_block_type(__entry->type), + (unsigned long)__entry->index, + (unsigned long long)__entry->block) +); + +TRACE_EVENT(f2fs_write_checkpoint, + + TP_PROTO(struct super_block *sb, bool is_umount, char *msg), + + TP_ARGS(sb, is_umount, msg), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(bool, is_umount) + __field(char *, msg) + ), + + TP_fast_assign( + __entry->dev = sb->s_dev; + __entry->is_umount = is_umount; + __entry->msg = msg; + ), + + TP_printk("dev = (%d,%d), checkpoint for %s, state = %s", + show_dev(__entry), + __entry->is_umount ? "clean umount" : "consistency", + __entry->msg) +); + +#endif /* _TRACE_F2FS_H */ + + /* This part must be outside protection */ +#include <trace/define_trace.h> diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h index 6a16fd2e70ed..464ea82e10db 100644 --- a/include/trace/events/writeback.h +++ b/include/trace/events/writeback.h @@ -183,7 +183,6 @@ DECLARE_EVENT_CLASS(writeback_work_class, DEFINE_EVENT(writeback_work_class, name, \ TP_PROTO(struct backing_dev_info *bdi, struct wb_writeback_work *work), \ TP_ARGS(bdi, work)) -DEFINE_WRITEBACK_WORK_EVENT(writeback_nothread); DEFINE_WRITEBACK_WORK_EVENT(writeback_queue); DEFINE_WRITEBACK_WORK_EVENT(writeback_exec); DEFINE_WRITEBACK_WORK_EVENT(writeback_start); @@ -222,12 +221,8 @@ DEFINE_EVENT(writeback_class, name, \ DEFINE_WRITEBACK_EVENT(writeback_nowork); DEFINE_WRITEBACK_EVENT(writeback_wake_background); -DEFINE_WRITEBACK_EVENT(writeback_wake_thread); -DEFINE_WRITEBACK_EVENT(writeback_wake_forker_thread); DEFINE_WRITEBACK_EVENT(writeback_bdi_register); DEFINE_WRITEBACK_EVENT(writeback_bdi_unregister); -DEFINE_WRITEBACK_EVENT(writeback_thread_start); -DEFINE_WRITEBACK_EVENT(writeback_thread_stop); DECLARE_EVENT_CLASS(wbc_class, TP_PROTO(struct writeback_control *wbc, struct backing_dev_info *bdi), |