diff options
Diffstat (limited to 'fs/xfs/xfs_buf.c')
| -rw-r--r-- | fs/xfs/xfs_buf.c | 1282 |
1 files changed, 674 insertions, 608 deletions
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index 4dff85c7d7e..7a34a1ae655 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -34,19 +34,17 @@ #include <linux/backing-dev.h> #include <linux/freezer.h> +#include "xfs_log_format.h" +#include "xfs_trans_resv.h" #include "xfs_sb.h" -#include "xfs_inum.h" -#include "xfs_log.h" #include "xfs_ag.h" #include "xfs_mount.h" #include "xfs_trace.h" +#include "xfs_log.h" static kmem_zone_t *xfs_buf_zone; -STATIC int xfsbufd(void *); static struct workqueue_struct *xfslogd_workqueue; -struct workqueue_struct *xfsdatad_workqueue; -struct workqueue_struct *xfsconvertd_workqueue; #ifdef XFS_BUF_LOCK_TRACKING # define XB_SET_OWNER(bp) ((bp)->b_last_holder = current->pid) @@ -59,11 +57,7 @@ struct workqueue_struct *xfsconvertd_workqueue; #endif #define xb_to_gfp(flags) \ - ((((flags) & XBF_READ_AHEAD) ? __GFP_NORETRY : \ - ((flags) & XBF_DONT_BLOCK) ? GFP_NOFS : GFP_KERNEL) | __GFP_NOWARN) - -#define xb_to_km(flags) \ - (((flags) & XBF_DONT_BLOCK) ? KM_NOFS : KM_SLEEP) + ((((flags) & XBF_READ_AHEAD) ? __GFP_NORETRY : GFP_NOFS) | __GFP_NOWARN) static inline int @@ -73,11 +67,11 @@ xfs_buf_is_vmapped( /* * Return true if the buffer is vmapped. * - * The XBF_MAPPED flag is set if the buffer should be mapped, but the - * code is clever enough to know it doesn't have to map a single page, - * so the check has to be both for XBF_MAPPED and bp->b_page_count > 1. + * b_addr is null if the buffer is not mapped, but the code is clever + * enough to know it doesn't have to map a single page, so the check has + * to be both for b_addr and bp->b_page_count > 1. */ - return (bp->b_flags & XBF_MAPPED) && bp->b_page_count > 1; + return bp->b_addr && bp->b_page_count > 1; } static inline int @@ -88,100 +82,92 @@ xfs_buf_vmap_len( } /* - * xfs_buf_lru_add - add a buffer to the LRU. + * When we mark a buffer stale, we remove the buffer from the LRU and clear the + * b_lru_ref count so that the buffer is freed immediately when the buffer + * reference count falls to zero. If the buffer is already on the LRU, we need + * to remove the reference that LRU holds on the buffer. * - * The LRU takes a new reference to the buffer so that it will only be freed - * once the shrinker takes the buffer off the LRU. + * This prevents build-up of stale buffers on the LRU. */ -STATIC void -xfs_buf_lru_add( +void +xfs_buf_stale( struct xfs_buf *bp) { - struct xfs_buftarg *btp = bp->b_target; + ASSERT(xfs_buf_islocked(bp)); - spin_lock(&btp->bt_lru_lock); - if (list_empty(&bp->b_lru)) { - atomic_inc(&bp->b_hold); - list_add_tail(&bp->b_lru, &btp->bt_lru); - btp->bt_lru_nr++; - } - spin_unlock(&btp->bt_lru_lock); + bp->b_flags |= XBF_STALE; + + /* + * Clear the delwri status so that a delwri queue walker will not + * flush this buffer to disk now that it is stale. The delwri queue has + * a reference to the buffer, so this is safe to do. + */ + bp->b_flags &= ~_XBF_DELWRI_Q; + + spin_lock(&bp->b_lock); + atomic_set(&bp->b_lru_ref, 0); + if (!(bp->b_state & XFS_BSTATE_DISPOSE) && + (list_lru_del(&bp->b_target->bt_lru, &bp->b_lru))) + atomic_dec(&bp->b_hold); + + ASSERT(atomic_read(&bp->b_hold) >= 1); + spin_unlock(&bp->b_lock); } -/* - * xfs_buf_lru_del - remove a buffer from the LRU - * - * The unlocked check is safe here because it only occurs when there are not - * b_lru_ref counts left on the inode under the pag->pag_buf_lock. it is there - * to optimise the shrinker removing the buffer from the LRU and calling - * xfs_buf_free(). i.e. it removes an unnecessary round trip on the - * bt_lru_lock. - */ -STATIC void -xfs_buf_lru_del( - struct xfs_buf *bp) +static int +xfs_buf_get_maps( + struct xfs_buf *bp, + int map_count) { - struct xfs_buftarg *btp = bp->b_target; - - if (list_empty(&bp->b_lru)) - return; + ASSERT(bp->b_maps == NULL); + bp->b_map_count = map_count; - spin_lock(&btp->bt_lru_lock); - if (!list_empty(&bp->b_lru)) { - list_del_init(&bp->b_lru); - btp->bt_lru_nr--; + if (map_count == 1) { + bp->b_maps = &bp->__b_map; + return 0; } - spin_unlock(&btp->bt_lru_lock); + + bp->b_maps = kmem_zalloc(map_count * sizeof(struct xfs_buf_map), + KM_NOFS); + if (!bp->b_maps) + return ENOMEM; + return 0; } /* - * When we mark a buffer stale, we remove the buffer from the LRU and clear the - * b_lru_ref count so that the buffer is freed immediately when the buffer - * reference count falls to zero. If the buffer is already on the LRU, we need - * to remove the reference that LRU holds on the buffer. - * - * This prevents build-up of stale buffers on the LRU. + * Frees b_pages if it was allocated. */ -void -xfs_buf_stale( +static void +xfs_buf_free_maps( struct xfs_buf *bp) { - bp->b_flags |= XBF_STALE; - xfs_buf_delwri_dequeue(bp); - atomic_set(&(bp)->b_lru_ref, 0); - if (!list_empty(&bp->b_lru)) { - struct xfs_buftarg *btp = bp->b_target; - - spin_lock(&btp->bt_lru_lock); - if (!list_empty(&bp->b_lru)) { - list_del_init(&bp->b_lru); - btp->bt_lru_nr--; - atomic_dec(&bp->b_hold); - } - spin_unlock(&btp->bt_lru_lock); + if (bp->b_maps != &bp->__b_map) { + kmem_free(bp->b_maps); + bp->b_maps = NULL; } - ASSERT(atomic_read(&bp->b_hold) >= 1); } struct xfs_buf * -xfs_buf_alloc( +_xfs_buf_alloc( struct xfs_buftarg *target, - xfs_off_t range_base, - size_t range_length, + struct xfs_buf_map *map, + int nmaps, xfs_buf_flags_t flags) { struct xfs_buf *bp; + int error; + int i; - bp = kmem_zone_alloc(xfs_buf_zone, xb_to_km(flags)); + bp = kmem_zone_zalloc(xfs_buf_zone, KM_NOFS); if (unlikely(!bp)) return NULL; /* - * We don't want certain flags to appear in b_flags. + * We don't want certain flags to appear in b_flags unless they are + * specifically set by later operations on the buffer. */ - flags &= ~(XBF_LOCK|XBF_MAPPED|XBF_DONT_BLOCK|XBF_READ_AHEAD); + flags &= ~(XBF_UNMAPPED | XBF_TRYLOCK | XBF_ASYNC | XBF_READ_AHEAD); - memset(bp, 0, sizeof(xfs_buf_t)); atomic_set(&bp->b_hold, 1); atomic_set(&bp->b_lru_ref, 1); init_completion(&bp->b_iowait); @@ -189,17 +175,31 @@ xfs_buf_alloc( INIT_LIST_HEAD(&bp->b_list); RB_CLEAR_NODE(&bp->b_rbnode); sema_init(&bp->b_sema, 0); /* held, no waiters */ + spin_lock_init(&bp->b_lock); XB_SET_OWNER(bp); bp->b_target = target; - bp->b_file_offset = range_base; + bp->b_flags = flags; + /* - * Set buffer_length and count_desired to the same value initially. - * I/O routines should use count_desired, which will be the same in + * Set length and io_length to the same value initially. + * I/O routines should use io_length, which will be the same in * most cases but may be reset (e.g. XFS recovery). */ - bp->b_buffer_length = bp->b_count_desired = range_length; - bp->b_flags = flags; - bp->b_bn = XFS_BUF_DADDR_NULL; + error = xfs_buf_get_maps(bp, nmaps); + if (error) { + kmem_zone_free(xfs_buf_zone, bp); + return NULL; + } + + bp->b_bn = map[0].bm_bn; + bp->b_length = 0; + for (i = 0; i < nmaps; i++) { + bp->b_maps[i].bm_bn = map[i].bm_bn; + bp->b_maps[i].bm_len = map[i].bm_len; + bp->b_length += map[i].bm_len; + } + bp->b_io_length = bp->b_length; + atomic_set(&bp->b_pin_count, 0); init_waitqueue_head(&bp->b_waiters); @@ -216,18 +216,16 @@ xfs_buf_alloc( STATIC int _xfs_buf_get_pages( xfs_buf_t *bp, - int page_count, - xfs_buf_flags_t flags) + int page_count) { /* Make sure that we have a page list */ if (bp->b_pages == NULL) { - bp->b_offset = xfs_buf_poff(bp->b_file_offset); bp->b_page_count = page_count; if (page_count <= XB_PAGES) { bp->b_pages = bp->b_page_array; } else { bp->b_pages = kmem_alloc(sizeof(struct page *) * - page_count, xb_to_km(flags)); + page_count, KM_NOFS); if (bp->b_pages == NULL) return -ENOMEM; } @@ -253,7 +251,7 @@ _xfs_buf_free_pages( * Releases the specified buffer. * * The modification state of any associated pages is left unchanged. - * The buffer most not be on any hash - use xfs_buf_rele instead for + * The buffer must not be on any hash - use xfs_buf_rele instead for * hashed and refcounted buffers */ void @@ -279,6 +277,7 @@ xfs_buf_free( } else if (bp->b_flags & _XBF_KMEM) kmem_free(bp->b_addr); _xfs_buf_free_pages(bp); + xfs_buf_free_maps(bp); kmem_zone_free(xfs_buf_zone, bp); } @@ -290,11 +289,11 @@ xfs_buf_allocate_memory( xfs_buf_t *bp, uint flags) { - size_t size = bp->b_count_desired; + size_t size; size_t nbytes, offset; gfp_t gfp_mask = xb_to_gfp(flags); unsigned short page_count, i; - xfs_off_t end; + xfs_off_t start, end; int error; /* @@ -302,15 +301,15 @@ xfs_buf_allocate_memory( * the memory from the heap - there's no need for the complexity of * page arrays to keep allocation down to order 0. */ - if (bp->b_buffer_length < PAGE_SIZE) { - bp->b_addr = kmem_alloc(bp->b_buffer_length, xb_to_km(flags)); + size = BBTOB(bp->b_length); + if (size < PAGE_SIZE) { + bp->b_addr = kmem_alloc(size, KM_NOFS); if (!bp->b_addr) { /* low memory - use alloc_page loop instead */ goto use_alloc_page; } - if (((unsigned long)(bp->b_addr + bp->b_buffer_length - 1) & - PAGE_MASK) != + if (((unsigned long)(bp->b_addr + size - 1) & PAGE_MASK) != ((unsigned long)bp->b_addr & PAGE_MASK)) { /* b_addr spans two pages - use alloc_page instead */ kmem_free(bp->b_addr); @@ -321,14 +320,16 @@ xfs_buf_allocate_memory( bp->b_pages = bp->b_page_array; bp->b_pages[0] = virt_to_page(bp->b_addr); bp->b_page_count = 1; - bp->b_flags |= XBF_MAPPED | _XBF_KMEM; + bp->b_flags |= _XBF_KMEM; return 0; } use_alloc_page: - end = bp->b_file_offset + bp->b_buffer_length; - page_count = xfs_buf_btoc(end) - xfs_buf_btoct(bp->b_file_offset); - error = _xfs_buf_get_pages(bp, page_count, flags); + start = BBTOB(bp->b_maps[0].bm_bn) >> PAGE_SHIFT; + end = (BBTOB(bp->b_maps[0].bm_bn + bp->b_length) + PAGE_SIZE - 1) + >> PAGE_SHIFT; + page_count = end - start; + error = _xfs_buf_get_pages(bp, page_count); if (unlikely(error)) return error; @@ -390,10 +391,21 @@ _xfs_buf_map_pages( if (bp->b_page_count == 1) { /* A single page buffer is always mappable */ bp->b_addr = page_address(bp->b_pages[0]) + bp->b_offset; - bp->b_flags |= XBF_MAPPED; - } else if (flags & XBF_MAPPED) { + } else if (flags & XBF_UNMAPPED) { + bp->b_addr = NULL; + } else { int retried = 0; + unsigned noio_flag; + /* + * vm_map_ram() will allocate auxillary structures (e.g. + * pagetables) with GFP_KERNEL, yet we are likely to be under + * GFP_NOFS context here. Hence we need to tell memory reclaim + * that we are in such a context via PF_MEMALLOC_NOIO to prevent + * memory reclaim re-entering the filesystem here and + * potentially deadlocking. + */ + noio_flag = memalloc_noio_save(); do { bp->b_addr = vm_map_ram(bp->b_pages, bp->b_page_count, -1, PAGE_KERNEL); @@ -401,11 +413,11 @@ _xfs_buf_map_pages( break; vm_unmap_aliases(); } while (retried++ <= 1); + memalloc_noio_restore(noio_flag); if (!bp->b_addr) return -ENOMEM; bp->b_addr += bp->b_offset; - bp->b_flags |= XBF_MAPPED; } return 0; @@ -422,29 +434,51 @@ _xfs_buf_map_pages( */ xfs_buf_t * _xfs_buf_find( - xfs_buftarg_t *btp, /* block device target */ - xfs_off_t ioff, /* starting offset of range */ - size_t isize, /* length of range */ + struct xfs_buftarg *btp, + struct xfs_buf_map *map, + int nmaps, xfs_buf_flags_t flags, xfs_buf_t *new_bp) { - xfs_off_t range_base; - size_t range_length; + size_t numbytes; struct xfs_perag *pag; struct rb_node **rbp; struct rb_node *parent; xfs_buf_t *bp; + xfs_daddr_t blkno = map[0].bm_bn; + xfs_daddr_t eofs; + int numblks = 0; + int i; - range_base = (ioff << BBSHIFT); - range_length = (isize << BBSHIFT); + for (i = 0; i < nmaps; i++) + numblks += map[i].bm_len; + numbytes = BBTOB(numblks); /* Check for IOs smaller than the sector size / not sector aligned */ - ASSERT(!(range_length < (1 << btp->bt_sshift))); - ASSERT(!(range_base & (xfs_off_t)btp->bt_smask)); + ASSERT(!(numbytes < btp->bt_meta_sectorsize)); + ASSERT(!(BBTOB(blkno) & (xfs_off_t)btp->bt_meta_sectormask)); + + /* + * Corrupted block numbers can get through to here, unfortunately, so we + * have to check that the buffer falls within the filesystem bounds. + */ + eofs = XFS_FSB_TO_BB(btp->bt_mount, btp->bt_mount->m_sb.sb_dblocks); + if (blkno >= eofs) { + /* + * XXX (dgc): we should really be returning EFSCORRUPTED here, + * but none of the higher level infrastructure supports + * returning a specific error on buffer lookup failures. + */ + xfs_alert(btp->bt_mount, + "%s: Block out of range: block 0x%llx, EOFS 0x%llx ", + __func__, blkno, eofs); + WARN_ON(1); + return NULL; + } /* get tree root */ pag = xfs_perag_get(btp->bt_mount, - xfs_daddr_to_agno(btp->bt_mount, ioff)); + xfs_daddr_to_agno(btp->bt_mount, blkno)); /* walk tree */ spin_lock(&pag->pag_buf_lock); @@ -455,20 +489,20 @@ _xfs_buf_find( parent = *rbp; bp = rb_entry(parent, struct xfs_buf, b_rbnode); - if (range_base < bp->b_file_offset) + if (blkno < bp->b_bn) rbp = &(*rbp)->rb_left; - else if (range_base > bp->b_file_offset) + else if (blkno > bp->b_bn) rbp = &(*rbp)->rb_right; else { /* - * found a block offset match. If the range doesn't + * found a block number match. If the range doesn't * match, the only way this is allowed is if the buffer * in the cache is stale and the transaction that made * it stale has not yet committed. i.e. we are * reallocating a busy extent. Skip this buffer and * continue searching to the right for an exact match. */ - if (bp->b_buffer_length != range_length) { + if (bp->b_length != numblks) { ASSERT(bp->b_flags & XBF_STALE); rbp = &(*rbp)->rb_right; continue; @@ -513,7 +547,9 @@ found: */ if (bp->b_flags & XBF_STALE) { ASSERT((bp->b_flags & _XBF_DELWRI_Q) == 0); - bp->b_flags &= XBF_MAPPED | _XBF_KMEM | _XBF_PAGES; + ASSERT(bp->b_iodone == NULL); + bp->b_flags &= _XBF_KMEM | _XBF_PAGES; + bp->b_ops = NULL; } trace_xfs_buf_find(bp, flags, _RET_IP_); @@ -527,64 +563,53 @@ found: * more hits than misses. */ struct xfs_buf * -xfs_buf_get( - xfs_buftarg_t *target,/* target for buffer */ - xfs_off_t ioff, /* starting offset of range */ - size_t isize, /* length of range */ +xfs_buf_get_map( + struct xfs_buftarg *target, + struct xfs_buf_map *map, + int nmaps, xfs_buf_flags_t flags) { struct xfs_buf *bp; struct xfs_buf *new_bp; int error = 0; - bp = _xfs_buf_find(target, ioff, isize, flags, NULL); + bp = _xfs_buf_find(target, map, nmaps, flags, NULL); if (likely(bp)) goto found; - new_bp = xfs_buf_alloc(target, ioff << BBSHIFT, isize << BBSHIFT, - flags); + new_bp = _xfs_buf_alloc(target, map, nmaps, flags); if (unlikely(!new_bp)) return NULL; - bp = _xfs_buf_find(target, ioff, isize, flags, new_bp); - if (!bp) { - kmem_zone_free(xfs_buf_zone, new_bp); + error = xfs_buf_allocate_memory(new_bp, flags); + if (error) { + xfs_buf_free(new_bp); return NULL; } - if (bp == new_bp) { - error = xfs_buf_allocate_memory(bp, flags); - if (error) - goto no_buffer; - } else - kmem_zone_free(xfs_buf_zone, new_bp); + bp = _xfs_buf_find(target, map, nmaps, flags, new_bp); + if (!bp) { + xfs_buf_free(new_bp); + return NULL; + } - /* - * Now we have a workable buffer, fill in the block number so - * that we can do IO on it. - */ - bp->b_bn = ioff; - bp->b_count_desired = bp->b_buffer_length; + if (bp != new_bp) + xfs_buf_free(new_bp); found: - if (!(bp->b_flags & XBF_MAPPED)) { + if (!bp->b_addr) { error = _xfs_buf_map_pages(bp, flags); if (unlikely(error)) { xfs_warn(target->bt_mount, - "%s: failed to map pages\n", __func__); - goto no_buffer; + "%s: failed to map pagesn", __func__); + xfs_buf_relse(bp); + return NULL; } } XFS_STATS_INC(xb_get); trace_xfs_buf_get(bp, flags, _RET_IP_); return bp; - -no_buffer: - if (flags & (XBF_LOCK | XBF_TRYLOCK)) - xfs_buf_unlock(bp); - xfs_buf_rele(bp); - return NULL; } STATIC int @@ -592,44 +617,45 @@ _xfs_buf_read( xfs_buf_t *bp, xfs_buf_flags_t flags) { - int status; - - ASSERT(!(flags & (XBF_DELWRI|XBF_WRITE))); - ASSERT(bp->b_bn != XFS_BUF_DADDR_NULL); + ASSERT(!(flags & XBF_WRITE)); + ASSERT(bp->b_maps[0].bm_bn != XFS_BUF_DADDR_NULL); - bp->b_flags &= ~(XBF_WRITE | XBF_ASYNC | XBF_DELWRI | XBF_READ_AHEAD); + bp->b_flags &= ~(XBF_WRITE | XBF_ASYNC | XBF_READ_AHEAD); bp->b_flags |= flags & (XBF_READ | XBF_ASYNC | XBF_READ_AHEAD); - status = xfs_buf_iorequest(bp); - if (status || bp->b_error || (flags & XBF_ASYNC)) - return status; + xfs_buf_iorequest(bp); + if (flags & XBF_ASYNC) + return 0; return xfs_buf_iowait(bp); } xfs_buf_t * -xfs_buf_read( - xfs_buftarg_t *target, - xfs_off_t ioff, - size_t isize, - xfs_buf_flags_t flags) +xfs_buf_read_map( + struct xfs_buftarg *target, + struct xfs_buf_map *map, + int nmaps, + xfs_buf_flags_t flags, + const struct xfs_buf_ops *ops) { - xfs_buf_t *bp; + struct xfs_buf *bp; flags |= XBF_READ; - bp = xfs_buf_get(target, ioff, isize, flags); + bp = xfs_buf_get_map(target, map, nmaps, flags); if (bp) { trace_xfs_buf_read(bp, flags, _RET_IP_); if (!XFS_BUF_ISDONE(bp)) { XFS_STATS_INC(xb_get_read); + bp->b_ops = ops; _xfs_buf_read(bp, flags); } else if (flags & XBF_ASYNC) { /* * Read ahead call which is already satisfied, * drop the buffer */ - goto no_buffer; + xfs_buf_relse(bp); + return NULL; } else { /* We do not want read in the flags */ bp->b_flags &= ~XBF_READ; @@ -637,12 +663,6 @@ xfs_buf_read( } return bp; - - no_buffer: - if (flags & (XBF_LOCK | XBF_TRYLOCK)) - xfs_buf_unlock(bp); - xfs_buf_rele(bp); - return NULL; } /* @@ -650,16 +670,17 @@ xfs_buf_read( * safe manner. */ void -xfs_buf_readahead( - xfs_buftarg_t *target, - xfs_off_t ioff, - size_t isize) +xfs_buf_readahead_map( + struct xfs_buftarg *target, + struct xfs_buf_map *map, + int nmaps, + const struct xfs_buf_ops *ops) { if (bdi_read_congested(target->bt_bdi)) return; - xfs_buf_read(target, ioff, isize, - XBF_TRYLOCK|XBF_ASYNC|XBF_READ_AHEAD|XBF_DONT_BLOCK); + xfs_buf_read_map(target, map, nmaps, + XBF_TRYLOCK|XBF_ASYNC|XBF_READ_AHEAD, ops); } /* @@ -668,29 +689,31 @@ xfs_buf_readahead( */ struct xfs_buf * xfs_buf_read_uncached( - struct xfs_mount *mp, struct xfs_buftarg *target, xfs_daddr_t daddr, - size_t length, - int flags) + size_t numblks, + int flags, + const struct xfs_buf_ops *ops) { - xfs_buf_t *bp; - int error; + struct xfs_buf *bp; - bp = xfs_buf_get_uncached(target, length, flags); + bp = xfs_buf_get_uncached(target, numblks, flags); if (!bp) return NULL; /* set up the buffer for a read IO */ - XFS_BUF_SET_ADDR(bp, daddr); - XFS_BUF_READ(bp); + ASSERT(bp->b_map_count == 1); + bp->b_bn = daddr; + bp->b_maps[0].bm_bn = daddr; + bp->b_flags |= XBF_READ; + bp->b_ops = ops; - xfsbdstrat(mp, bp); - error = xfs_buf_iowait(bp); - if (error || bp->b_error) { + if (XFS_FORCED_SHUTDOWN(target->bt_mount)) { xfs_buf_relse(bp); return NULL; } + xfs_buf_iorequest(bp); + xfs_buf_iowait(bp); return bp; } @@ -701,7 +724,7 @@ xfs_buf_read_uncached( void xfs_buf_set_empty( struct xfs_buf *bp, - size_t len) + size_t numblks) { if (bp->b_pages) _xfs_buf_free_pages(bp); @@ -709,10 +732,13 @@ xfs_buf_set_empty( bp->b_pages = NULL; bp->b_page_count = 0; bp->b_addr = NULL; - bp->b_file_offset = 0; - bp->b_buffer_length = bp->b_count_desired = len; + bp->b_length = numblks; + bp->b_io_length = numblks; + + ASSERT(bp->b_map_count == 1); bp->b_bn = XFS_BUF_DADDR_NULL; - bp->b_flags &= ~XBF_MAPPED; + bp->b_maps[0].bm_bn = XFS_BUF_DADDR_NULL; + bp->b_maps[0].bm_len = bp->b_length; } static inline struct page * @@ -751,7 +777,7 @@ xfs_buf_associate_memory( bp->b_pages = NULL; bp->b_addr = mem; - rval = _xfs_buf_get_pages(bp, page_count, XBF_DONT_BLOCK); + rval = _xfs_buf_get_pages(bp, page_count); if (rval) return rval; @@ -762,9 +788,8 @@ xfs_buf_associate_memory( pageaddr += PAGE_SIZE; } - bp->b_count_desired = len; - bp->b_buffer_length = buflen; - bp->b_flags |= XBF_MAPPED; + bp->b_io_length = BTOBB(len); + bp->b_length = BTOBB(buflen); return 0; } @@ -772,18 +797,20 @@ xfs_buf_associate_memory( xfs_buf_t * xfs_buf_get_uncached( struct xfs_buftarg *target, - size_t len, + size_t numblks, int flags) { - unsigned long page_count = PAGE_ALIGN(len) >> PAGE_SHIFT; + unsigned long page_count; int error, i; - xfs_buf_t *bp; + struct xfs_buf *bp; + DEFINE_SINGLE_BUF_MAP(map, XFS_BUF_DADDR_NULL, numblks); - bp = xfs_buf_alloc(target, 0, len, 0); + bp = _xfs_buf_alloc(target, &map, 1, 0); if (unlikely(bp == NULL)) goto fail; - error = _xfs_buf_get_pages(bp, page_count, 0); + page_count = PAGE_ALIGN(numblks << BBSHIFT) >> PAGE_SHIFT; + error = _xfs_buf_get_pages(bp, page_count); if (error) goto fail_free_buf; @@ -794,10 +821,10 @@ xfs_buf_get_uncached( } bp->b_flags |= _XBF_PAGES; - error = _xfs_buf_map_pages(bp, XBF_MAPPED); + error = _xfs_buf_map_pages(bp, 0); if (unlikely(error)) { xfs_warn(target->bt_mount, - "%s: failed to map pages\n", __func__); + "%s: failed to map pages", __func__); goto fail_free_mem; } @@ -809,6 +836,7 @@ xfs_buf_get_uncached( __free_page(bp->b_pages[i]); _xfs_buf_free_pages(bp); fail_free_buf: + xfs_buf_free_maps(bp); kmem_zone_free(xfs_buf_zone, bp); fail: return NULL; @@ -851,13 +879,34 @@ xfs_buf_rele( ASSERT(atomic_read(&bp->b_hold) > 0); if (atomic_dec_and_lock(&bp->b_hold, &pag->pag_buf_lock)) { - if (!(bp->b_flags & XBF_STALE) && - atomic_read(&bp->b_lru_ref)) { - xfs_buf_lru_add(bp); + spin_lock(&bp->b_lock); + if (!(bp->b_flags & XBF_STALE) && atomic_read(&bp->b_lru_ref)) { + /* + * If the buffer is added to the LRU take a new + * reference to the buffer for the LRU and clear the + * (now stale) dispose list state flag + */ + if (list_lru_add(&bp->b_target->bt_lru, &bp->b_lru)) { + bp->b_state &= ~XFS_BSTATE_DISPOSE; + atomic_inc(&bp->b_hold); + } + spin_unlock(&bp->b_lock); spin_unlock(&pag->pag_buf_lock); } else { - xfs_buf_lru_del(bp); - ASSERT(!(bp->b_flags & (XBF_DELWRI|_XBF_DELWRI_Q))); + /* + * most of the time buffers will already be removed from + * the LRU, so optimise that case by checking for the + * XFS_BSTATE_DISPOSE flag indicating the last list the + * buffer was on was the disposal list + */ + if (!(bp->b_state & XFS_BSTATE_DISPOSE)) { + list_lru_del(&bp->b_target->bt_lru, &bp->b_lru); + } else { + ASSERT(list_empty(&bp->b_lru)); + } + spin_unlock(&bp->b_lock); + + ASSERT(!(bp->b_flags & _XBF_DELWRI_Q)); rb_erase(&bp->b_rbnode, &pag->pag_buf_tree); spin_unlock(&pag->pag_buf_lock); xfs_perag_put(pag); @@ -887,8 +936,6 @@ xfs_buf_trylock( locked = down_trylock(&bp->b_sema) == 0; if (locked) XB_SET_OWNER(bp); - else if (atomic_read(&bp->b_pin_count) && (bp->b_flags & XBF_STALE)) - xfs_log_force(bp->b_target->bt_mount, 0); trace_xfs_buf_trylock(bp, _RET_IP_); return locked; @@ -917,13 +964,6 @@ xfs_buf_lock( trace_xfs_buf_lock_done(bp, _RET_IP_); } -/* - * Releases the lock on the buffer object. - * If the buffer is marked delwri but is not queued, do so before we - * unlock the buffer as we need to set flags correctly. We also need to - * take a reference for the delwri queue because the unlocker is going to - * drop their's and they don't know we just queued it. - */ void xfs_buf_unlock( struct xfs_buf *bp) @@ -962,27 +1002,39 @@ STATIC void xfs_buf_iodone_work( struct work_struct *work) { - xfs_buf_t *bp = + struct xfs_buf *bp = container_of(work, xfs_buf_t, b_iodone_work); + bool read = !!(bp->b_flags & XBF_READ); + + bp->b_flags &= ~(XBF_READ | XBF_WRITE | XBF_READ_AHEAD); + + /* only validate buffers that were read without errors */ + if (read && bp->b_ops && !bp->b_error && (bp->b_flags & XBF_DONE)) + bp->b_ops->verify_read(bp); if (bp->b_iodone) (*(bp->b_iodone))(bp); else if (bp->b_flags & XBF_ASYNC) xfs_buf_relse(bp); + else { + ASSERT(read && bp->b_ops); + complete(&bp->b_iowait); + } } void xfs_buf_ioend( - xfs_buf_t *bp, - int schedule) + struct xfs_buf *bp, + int schedule) { + bool read = !!(bp->b_flags & XBF_READ); + trace_xfs_buf_iodone(bp, _RET_IP_); - bp->b_flags &= ~(XBF_READ | XBF_WRITE | XBF_READ_AHEAD); if (bp->b_error == 0) bp->b_flags |= XBF_DONE; - if ((bp->b_iodone) || (bp->b_flags & XBF_ASYNC)) { + if (bp->b_iodone || (read && bp->b_ops) || (bp->b_flags & XBF_ASYNC)) { if (schedule) { INIT_WORK(&bp->b_iodone_work, xfs_buf_iodone_work); queue_work(xfslogd_workqueue, &bp->b_iodone_work); @@ -990,6 +1042,7 @@ xfs_buf_ioend( xfs_buf_iodone_work(&bp->b_iodone_work); } } else { + bp->b_flags &= ~(XBF_READ | XBF_WRITE | XBF_READ_AHEAD); complete(&bp->b_iowait); } } @@ -1010,29 +1063,8 @@ xfs_buf_ioerror_alert( const char *func) { xfs_alert(bp->b_target->bt_mount, -"metadata I/O error: block 0x%llx (\"%s\") error %d buf count %zd", - (__uint64_t)XFS_BUF_ADDR(bp), func, - bp->b_error, XFS_BUF_COUNT(bp)); -} - -int -xfs_bwrite( - struct xfs_buf *bp) -{ - int error; - - bp->b_flags |= XBF_WRITE; - bp->b_flags &= ~(XBF_ASYNC | XBF_READ); - - xfs_buf_delwri_dequeue(bp); - xfs_bdstrat_cb(bp); - - error = xfs_buf_iowait(bp); - if (error) { - xfs_force_shutdown(bp->b_target->bt_mount, - SHUTDOWN_META_IO_ERROR); - } - return error; +"metadata I/O error: block 0x%llx (\"%s\") error %d numblks %d", + (__uint64_t)XFS_BUF_ADDR(bp), func, bp->b_error, bp->b_length); } /* @@ -1071,7 +1103,7 @@ xfs_bioerror( * This is meant for userdata errors; metadata bufs come with * iodone functions attached, so that we can track down errors. */ -STATIC int +int xfs_bioerror_relse( struct xfs_buf *bp) { @@ -1104,14 +1136,7 @@ xfs_bioerror_relse( return EIO; } - -/* - * All xfs metadata buffers except log state machine buffers - * get this attached as their b_bdstrat callback function. - * This is so that we can catch a buffer - * after prematurely unpinning it to forcibly shutdown the filesystem. - */ -int +STATIC int xfs_bdstrat_cb( struct xfs_buf *bp) { @@ -1132,23 +1157,25 @@ xfs_bdstrat_cb( return 0; } -/* - * Wrapper around bdstrat so that we can stop data from going to disk in case - * we are shutting down the filesystem. Typically user data goes thru this - * path; one of the exceptions is the superblock. - */ -void -xfsbdstrat( - struct xfs_mount *mp, +int +xfs_bwrite( struct xfs_buf *bp) { - if (XFS_FORCED_SHUTDOWN(mp)) { - trace_xfs_bdstrat_shut(bp, _RET_IP_); - xfs_bioerror_relse(bp); - return; - } + int error; - xfs_buf_iorequest(bp); + ASSERT(xfs_buf_islocked(bp)); + + bp->b_flags |= XBF_WRITE; + bp->b_flags &= ~(XBF_ASYNC | XBF_READ | _XBF_DELWRI_Q | XBF_WRITE_FAIL); + + xfs_bdstrat_cb(bp); + + error = xfs_buf_iowait(bp); + if (error) { + xfs_force_shutdown(bp->b_target->bt_mount, + SHUTDOWN_META_IO_ERROR); + } + return error; } STATIC void @@ -1167,45 +1194,53 @@ xfs_buf_bio_end_io( { xfs_buf_t *bp = (xfs_buf_t *)bio->bi_private; - xfs_buf_ioerror(bp, -error); + /* + * don't overwrite existing errors - otherwise we can lose errors on + * buffers that require multiple bios to complete. + */ + if (!bp->b_error) + xfs_buf_ioerror(bp, -error); - if (!error && xfs_buf_is_vmapped(bp) && (bp->b_flags & XBF_READ)) + if (!bp->b_error && xfs_buf_is_vmapped(bp) && (bp->b_flags & XBF_READ)) invalidate_kernel_vmap_range(bp->b_addr, xfs_buf_vmap_len(bp)); _xfs_buf_ioend(bp, 1); bio_put(bio); } -STATIC void -_xfs_buf_ioapply( - xfs_buf_t *bp) +static void +xfs_buf_ioapply_map( + struct xfs_buf *bp, + int map, + int *buf_offset, + int *count, + int rw) { - int rw, map_i, total_nr_pages, nr_pages; - struct bio *bio; - int offset = bp->b_offset; - int size = bp->b_count_desired; - sector_t sector = bp->b_bn; + int page_index; + int total_nr_pages = bp->b_page_count; + int nr_pages; + struct bio *bio; + sector_t sector = bp->b_maps[map].bm_bn; + int size; + int offset; total_nr_pages = bp->b_page_count; - map_i = 0; - if (bp->b_flags & XBF_WRITE) { - if (bp->b_flags & XBF_SYNCIO) - rw = WRITE_SYNC; - else - rw = WRITE; - if (bp->b_flags & XBF_FUA) - rw |= REQ_FUA; - if (bp->b_flags & XBF_FLUSH) - rw |= REQ_FLUSH; - } else if (bp->b_flags & XBF_READ_AHEAD) { - rw = READA; - } else { - rw = READ; + /* skip the pages in the buffer before the start offset */ + page_index = 0; + offset = *buf_offset; + while (offset >= PAGE_SIZE) { + page_index++; + offset -= PAGE_SIZE; } - /* we only use the buffer cache for meta-data */ - rw |= REQ_META; + /* + * Limit the IO size to the length of the current vector, and update the + * remaining IO count for the next time around. + */ + size = min_t(int, BBTOB(bp->b_maps[map].bm_len), *count); + *count -= size; + *buf_offset += size; next_chunk: atomic_inc(&bp->b_io_remaining); @@ -1215,28 +1250,29 @@ next_chunk: bio = bio_alloc(GFP_NOIO, nr_pages); bio->bi_bdev = bp->b_target->bt_bdev; - bio->bi_sector = sector; + bio->bi_iter.bi_sector = sector; bio->bi_end_io = xfs_buf_bio_end_io; bio->bi_private = bp; - for (; size && nr_pages; nr_pages--, map_i++) { + for (; size && nr_pages; nr_pages--, page_index++) { int rbytes, nbytes = PAGE_SIZE - offset; if (nbytes > size) nbytes = size; - rbytes = bio_add_page(bio, bp->b_pages[map_i], nbytes, offset); + rbytes = bio_add_page(bio, bp->b_pages[page_index], nbytes, + offset); if (rbytes < nbytes) break; offset = 0; - sector += nbytes >> BBSHIFT; + sector += BTOBB(nbytes); size -= nbytes; total_nr_pages--; } - if (likely(bio->bi_size)) { + if (likely(bio->bi_iter.bi_size)) { if (xfs_buf_is_vmapped(bp)) { flush_kernel_vmap_range(bp->b_addr, xfs_buf_vmap_len(bp)); @@ -1245,39 +1281,119 @@ next_chunk: if (size) goto next_chunk; } else { + /* + * This is guaranteed not to be the last io reference count + * because the caller (xfs_buf_iorequest) holds a count itself. + */ + atomic_dec(&bp->b_io_remaining); xfs_buf_ioerror(bp, EIO); bio_put(bio); } + } -int +STATIC void +_xfs_buf_ioapply( + struct xfs_buf *bp) +{ + struct blk_plug plug; + int rw; + int offset; + int size; + int i; + + /* + * Make sure we capture only current IO errors rather than stale errors + * left over from previous use of the buffer (e.g. failed readahead). + */ + bp->b_error = 0; + + if (bp->b_flags & XBF_WRITE) { + if (bp->b_flags & XBF_SYNCIO) + rw = WRITE_SYNC; + else + rw = WRITE; + if (bp->b_flags & XBF_FUA) + rw |= REQ_FUA; + if (bp->b_flags & XBF_FLUSH) + rw |= REQ_FLUSH; + + /* + * Run the write verifier callback function if it exists. If + * this function fails it will mark the buffer with an error and + * the IO should not be dispatched. + */ + if (bp->b_ops) { + bp->b_ops->verify_write(bp); + if (bp->b_error) { + xfs_force_shutdown(bp->b_target->bt_mount, + SHUTDOWN_CORRUPT_INCORE); + return; + } + } + } else if (bp->b_flags & XBF_READ_AHEAD) { + rw = READA; + } else { + rw = READ; + } + + /* we only use the buffer cache for meta-data */ + rw |= REQ_META; + + /* + * Walk all the vectors issuing IO on them. Set up the initial offset + * into the buffer and the desired IO size before we start - + * _xfs_buf_ioapply_vec() will modify them appropriately for each + * subsequent call. + */ + offset = bp->b_offset; + size = BBTOB(bp->b_io_length); + blk_start_plug(&plug); + for (i = 0; i < bp->b_map_count; i++) { + xfs_buf_ioapply_map(bp, i, &offset, &size, rw); + if (bp->b_error) + break; + if (size <= 0) + break; /* all done */ + } + blk_finish_plug(&plug); +} + +void xfs_buf_iorequest( xfs_buf_t *bp) { trace_xfs_buf_iorequest(bp, _RET_IP_); - ASSERT(!(bp->b_flags & XBF_DELWRI)); + ASSERT(!(bp->b_flags & _XBF_DELWRI_Q)); if (bp->b_flags & XBF_WRITE) xfs_buf_wait_unpin(bp); xfs_buf_hold(bp); - /* Set the count to 1 initially, this will stop an I/O + /* + * Set the count to 1 initially, this will stop an I/O * completion callout which happens before we have started * all the I/O from calling xfs_buf_ioend too early. */ atomic_set(&bp->b_io_remaining, 1); _xfs_buf_ioapply(bp); - _xfs_buf_ioend(bp, 0); + /* + * If _xfs_buf_ioapply failed, we'll get back here with + * only the reference we took above. _xfs_buf_ioend will + * drop it to zero, so we'd better not queue it for later, + * or we'll free it before it's done. + */ + _xfs_buf_ioend(bp, bp->b_error ? 0 : 1); xfs_buf_rele(bp); - return 0; } /* - * Waits for I/O to complete on the buffer supplied. - * It returns immediately if no I/O is pending. - * It returns the I/O error code, if any, or 0 if there was no error. + * Waits for I/O to complete on the buffer supplied. It returns immediately if + * no I/O is pending or there is already a pending error on the buffer, in which + * case nothing will ever complete. It returns the I/O error code, if any, or + * 0 if there was no error. */ int xfs_buf_iowait( @@ -1285,7 +1401,8 @@ xfs_buf_iowait( { trace_xfs_buf_iowait(bp, _RET_IP_); - wait_for_completion(&bp->b_iowait); + if (!bp->b_error) + wait_for_completion(&bp->b_iowait); trace_xfs_buf_iowait_done(bp, _RET_IP_); return bp->b_error; @@ -1298,7 +1415,7 @@ xfs_buf_offset( { struct page *page; - if (bp->b_flags & XBF_MAPPED) + if (bp->b_addr) return bp->b_addr + offset; offset += bp->b_offset; @@ -1317,27 +1434,30 @@ xfs_buf_iomove( void *data, /* data address */ xfs_buf_rw_t mode) /* read/write/zero flag */ { - size_t bend, cpoff, csize; - struct page *page; + size_t bend; bend = boff + bsize; while (boff < bend) { - page = bp->b_pages[xfs_buf_btoct(boff + bp->b_offset)]; - cpoff = xfs_buf_poff(boff + bp->b_offset); - csize = min_t(size_t, - PAGE_SIZE-cpoff, bp->b_count_desired-boff); + struct page *page; + int page_index, page_offset, csize; + + page_index = (boff + bp->b_offset) >> PAGE_SHIFT; + page_offset = (boff + bp->b_offset) & ~PAGE_MASK; + page = bp->b_pages[page_index]; + csize = min_t(size_t, PAGE_SIZE - page_offset, + BBTOB(bp->b_io_length) - boff); - ASSERT(((csize + cpoff) <= PAGE_SIZE)); + ASSERT((csize + page_offset) <= PAGE_SIZE); switch (mode) { case XBRW_ZERO: - memset(page_address(page) + cpoff, 0, csize); + memset(page_address(page) + page_offset, 0, csize); break; case XBRW_READ: - memcpy(data, page_address(page) + cpoff, csize); + memcpy(data, page_address(page) + page_offset, csize); break; case XBRW_WRITE: - memcpy(page_address(page) + cpoff, data, csize); + memcpy(page_address(page) + page_offset, data, csize); } boff += csize; @@ -1354,80 +1474,127 @@ xfs_buf_iomove( * returned. These buffers will have an elevated hold count, so wait on those * while freeing all the buffers only held by the LRU. */ +static enum lru_status +xfs_buftarg_wait_rele( + struct list_head *item, + spinlock_t *lru_lock, + void *arg) + +{ + struct xfs_buf *bp = container_of(item, struct xfs_buf, b_lru); + struct list_head *dispose = arg; + + if (atomic_read(&bp->b_hold) > 1) { + /* need to wait, so skip it this pass */ + trace_xfs_buf_wait_buftarg(bp, _RET_IP_); + return LRU_SKIP; + } + if (!spin_trylock(&bp->b_lock)) + return LRU_SKIP; + + /* + * clear the LRU reference count so the buffer doesn't get + * ignored in xfs_buf_rele(). + */ + atomic_set(&bp->b_lru_ref, 0); + bp->b_state |= XFS_BSTATE_DISPOSE; + list_move(item, dispose); + spin_unlock(&bp->b_lock); + return LRU_REMOVED; +} + void xfs_wait_buftarg( struct xfs_buftarg *btp) { - struct xfs_buf *bp; + LIST_HEAD(dispose); + int loop = 0; -restart: - spin_lock(&btp->bt_lru_lock); - while (!list_empty(&btp->bt_lru)) { - bp = list_first_entry(&btp->bt_lru, struct xfs_buf, b_lru); - if (atomic_read(&bp->b_hold) > 1) { - spin_unlock(&btp->bt_lru_lock); - delay(100); - goto restart; + /* loop until there is nothing left on the lru list. */ + while (list_lru_count(&btp->bt_lru)) { + list_lru_walk(&btp->bt_lru, xfs_buftarg_wait_rele, + &dispose, LONG_MAX); + + while (!list_empty(&dispose)) { + struct xfs_buf *bp; + bp = list_first_entry(&dispose, struct xfs_buf, b_lru); + list_del_init(&bp->b_lru); + if (bp->b_flags & XBF_WRITE_FAIL) { + xfs_alert(btp->bt_mount, +"Corruption Alert: Buffer at block 0x%llx had permanent write failures!\n" +"Please run xfs_repair to determine the extent of the problem.", + (long long)bp->b_bn); + } + xfs_buf_rele(bp); } - /* - * clear the LRU reference count so the buffer doesn't get - * ignored in xfs_buf_rele(). - */ - atomic_set(&bp->b_lru_ref, 0); - spin_unlock(&btp->bt_lru_lock); - xfs_buf_rele(bp); - spin_lock(&btp->bt_lru_lock); + if (loop++ != 0) + delay(100); } - spin_unlock(&btp->bt_lru_lock); } -int -xfs_buftarg_shrink( +static enum lru_status +xfs_buftarg_isolate( + struct list_head *item, + spinlock_t *lru_lock, + void *arg) +{ + struct xfs_buf *bp = container_of(item, struct xfs_buf, b_lru); + struct list_head *dispose = arg; + + /* + * we are inverting the lru lock/bp->b_lock here, so use a trylock. + * If we fail to get the lock, just skip it. + */ + if (!spin_trylock(&bp->b_lock)) + return LRU_SKIP; + /* + * Decrement the b_lru_ref count unless the value is already + * zero. If the value is already zero, we need to reclaim the + * buffer, otherwise it gets another trip through the LRU. + */ + if (!atomic_add_unless(&bp->b_lru_ref, -1, 0)) { + spin_unlock(&bp->b_lock); + return LRU_ROTATE; + } + + bp->b_state |= XFS_BSTATE_DISPOSE; + list_move(item, dispose); + spin_unlock(&bp->b_lock); + return LRU_REMOVED; +} + +static unsigned long +xfs_buftarg_shrink_scan( struct shrinker *shrink, struct shrink_control *sc) { struct xfs_buftarg *btp = container_of(shrink, struct xfs_buftarg, bt_shrinker); - struct xfs_buf *bp; - int nr_to_scan = sc->nr_to_scan; LIST_HEAD(dispose); + unsigned long freed; + unsigned long nr_to_scan = sc->nr_to_scan; - if (!nr_to_scan) - return btp->bt_lru_nr; - - spin_lock(&btp->bt_lru_lock); - while (!list_empty(&btp->bt_lru)) { - if (nr_to_scan-- <= 0) - break; - - bp = list_first_entry(&btp->bt_lru, struct xfs_buf, b_lru); - - /* - * Decrement the b_lru_ref count unless the value is already - * zero. If the value is already zero, we need to reclaim the - * buffer, otherwise it gets another trip through the LRU. - */ - if (!atomic_add_unless(&bp->b_lru_ref, -1, 0)) { - list_move_tail(&bp->b_lru, &btp->bt_lru); - continue; - } - - /* - * remove the buffer from the LRU now to avoid needing another - * lock round trip inside xfs_buf_rele(). - */ - list_move(&bp->b_lru, &dispose); - btp->bt_lru_nr--; - } - spin_unlock(&btp->bt_lru_lock); + freed = list_lru_walk_node(&btp->bt_lru, sc->nid, xfs_buftarg_isolate, + &dispose, &nr_to_scan); while (!list_empty(&dispose)) { + struct xfs_buf *bp; bp = list_first_entry(&dispose, struct xfs_buf, b_lru); list_del_init(&bp->b_lru); xfs_buf_rele(bp); } - return btp->bt_lru_nr; + return freed; +} + +static unsigned long +xfs_buftarg_shrink_count( + struct shrinker *shrink, + struct shrink_control *sc) +{ + struct xfs_buftarg *btp = container_of(shrink, + struct xfs_buftarg, bt_shrinker); + return list_lru_count_node(&btp->bt_lru, sc->nid); } void @@ -1436,25 +1603,22 @@ xfs_free_buftarg( struct xfs_buftarg *btp) { unregister_shrinker(&btp->bt_shrinker); + list_lru_destroy(&btp->bt_lru); - xfs_flush_buftarg(btp, 1); if (mp->m_flags & XFS_MOUNT_BARRIER) xfs_blkdev_issue_flush(btp); - kthread_stop(btp->bt_task); kmem_free(btp); } -STATIC int -xfs_setsize_buftarg_flags( +int +xfs_setsize_buftarg( xfs_buftarg_t *btp, - unsigned int blocksize, - unsigned int sectorsize, - int verbose) + unsigned int sectorsize) { - btp->bt_bsize = blocksize; - btp->bt_sshift = ffs(sectorsize) - 1; - btp->bt_smask = sectorsize - 1; + /* Set up metadata sector size info */ + btp->bt_meta_sectorsize = sectorsize; + btp->bt_meta_sectormask = sectorsize - 1; if (set_blocksize(btp->bt_bdev, sectorsize)) { char name[BDEVNAME_SIZE]; @@ -1462,61 +1626,39 @@ xfs_setsize_buftarg_flags( bdevname(btp->bt_bdev, name); xfs_warn(btp->bt_mount, - "Cannot set_blocksize to %u on device %s\n", + "Cannot set_blocksize to %u on device %s", sectorsize, name); return EINVAL; } + /* Set up device logical sector size mask */ + btp->bt_logical_sectorsize = bdev_logical_block_size(btp->bt_bdev); + btp->bt_logical_sectormask = bdev_logical_block_size(btp->bt_bdev) - 1; + return 0; } /* - * When allocating the initial buffer target we have not yet - * read in the superblock, so don't know what sized sectors - * are being used is at this early stage. Play safe. + * When allocating the initial buffer target we have not yet + * read in the superblock, so don't know what sized sectors + * are being used at this early stage. Play safe. */ STATIC int xfs_setsize_buftarg_early( xfs_buftarg_t *btp, struct block_device *bdev) { - return xfs_setsize_buftarg_flags(btp, - PAGE_SIZE, bdev_logical_block_size(bdev), 0); -} - -int -xfs_setsize_buftarg( - xfs_buftarg_t *btp, - unsigned int blocksize, - unsigned int sectorsize) -{ - return xfs_setsize_buftarg_flags(btp, blocksize, sectorsize, 1); -} - -STATIC int -xfs_alloc_delwri_queue( - xfs_buftarg_t *btp, - const char *fsname) -{ - INIT_LIST_HEAD(&btp->bt_delwri_queue); - spin_lock_init(&btp->bt_delwri_lock); - btp->bt_flags = 0; - btp->bt_task = kthread_run(xfsbufd, btp, "xfsbufd/%s", fsname); - if (IS_ERR(btp->bt_task)) - return PTR_ERR(btp->bt_task); - return 0; + return xfs_setsize_buftarg(btp, bdev_logical_block_size(bdev)); } xfs_buftarg_t * xfs_alloc_buftarg( struct xfs_mount *mp, - struct block_device *bdev, - int external, - const char *fsname) + struct block_device *bdev) { xfs_buftarg_t *btp; - btp = kmem_zalloc(sizeof(*btp), KM_SLEEP); + btp = kmem_zalloc(sizeof(*btp), KM_SLEEP | KM_NOFS); btp->bt_mount = mp; btp->bt_dev = bdev->bd_dev; @@ -1525,14 +1667,16 @@ xfs_alloc_buftarg( if (!btp->bt_bdi) goto error; - INIT_LIST_HEAD(&btp->bt_lru); - spin_lock_init(&btp->bt_lru_lock); if (xfs_setsize_buftarg_early(btp, bdev)) goto error; - if (xfs_alloc_delwri_queue(btp, fsname)) + + if (list_lru_init(&btp->bt_lru)) goto error; - btp->bt_shrinker.shrink = xfs_buftarg_shrink; + + btp->bt_shrinker.count_objects = xfs_buftarg_shrink_count; + btp->bt_shrinker.scan_objects = xfs_buftarg_shrink_scan; btp->bt_shrinker.seeks = DEFAULT_SEEKS; + btp->bt_shrinker.flags = SHRINKER_NUMA_AWARE; register_shrinker(&btp->bt_shrinker); return btp; @@ -1541,125 +1685,52 @@ error: return NULL; } - /* - * Delayed write buffer handling + * Add a buffer to the delayed write list. + * + * This queues a buffer for writeout if it hasn't already been. Note that + * neither this routine nor the buffer list submission functions perform + * any internal synchronization. It is expected that the lists are thread-local + * to the callers. + * + * Returns true if we queued up the buffer, or false if it already had + * been on the buffer list. */ -void +bool xfs_buf_delwri_queue( - xfs_buf_t *bp) + struct xfs_buf *bp, + struct list_head *list) { - struct xfs_buftarg *btp = bp->b_target; - - trace_xfs_buf_delwri_queue(bp, _RET_IP_); - + ASSERT(xfs_buf_islocked(bp)); ASSERT(!(bp->b_flags & XBF_READ)); - spin_lock(&btp->bt_delwri_lock); - if (!list_empty(&bp->b_list)) { - /* if already in the queue, move it to the tail */ - ASSERT(bp->b_flags & _XBF_DELWRI_Q); - list_move_tail(&bp->b_list, &btp->bt_delwri_queue); - } else { - /* start xfsbufd as it is about to have something to do */ - if (list_empty(&btp->bt_delwri_queue)) - wake_up_process(bp->b_target->bt_task); - - atomic_inc(&bp->b_hold); - bp->b_flags |= XBF_DELWRI | _XBF_DELWRI_Q | XBF_ASYNC; - list_add_tail(&bp->b_list, &btp->bt_delwri_queue); - } - bp->b_queuetime = jiffies; - spin_unlock(&btp->bt_delwri_lock); -} - -void -xfs_buf_delwri_dequeue( - xfs_buf_t *bp) -{ - int dequeued = 0; - - spin_lock(&bp->b_target->bt_delwri_lock); - if ((bp->b_flags & XBF_DELWRI) && !list_empty(&bp->b_list)) { - ASSERT(bp->b_flags & _XBF_DELWRI_Q); - list_del_init(&bp->b_list); - dequeued = 1; + /* + * If the buffer is already marked delwri it already is queued up + * by someone else for imediate writeout. Just ignore it in that + * case. + */ + if (bp->b_flags & _XBF_DELWRI_Q) { + trace_xfs_buf_delwri_queued(bp, _RET_IP_); + return false; } - bp->b_flags &= ~(XBF_DELWRI|_XBF_DELWRI_Q); - spin_unlock(&bp->b_target->bt_delwri_lock); - if (dequeued) - xfs_buf_rele(bp); - - trace_xfs_buf_delwri_dequeue(bp, _RET_IP_); -} - -/* - * If a delwri buffer needs to be pushed before it has aged out, then promote - * it to the head of the delwri queue so that it will be flushed on the next - * xfsbufd run. We do this by resetting the queuetime of the buffer to be older - * than the age currently needed to flush the buffer. Hence the next time the - * xfsbufd sees it is guaranteed to be considered old enough to flush. - */ -void -xfs_buf_delwri_promote( - struct xfs_buf *bp) -{ - struct xfs_buftarg *btp = bp->b_target; - long age = xfs_buf_age_centisecs * msecs_to_jiffies(10) + 1; - - ASSERT(bp->b_flags & XBF_DELWRI); - ASSERT(bp->b_flags & _XBF_DELWRI_Q); + trace_xfs_buf_delwri_queue(bp, _RET_IP_); /* - * Check the buffer age before locking the delayed write queue as we - * don't need to promote buffers that are already past the flush age. + * If a buffer gets written out synchronously or marked stale while it + * is on a delwri list we lazily remove it. To do this, the other party + * clears the _XBF_DELWRI_Q flag but otherwise leaves the buffer alone. + * It remains referenced and on the list. In a rare corner case it + * might get readded to a delwri list after the synchronous writeout, in + * which case we need just need to re-add the flag here. */ - if (bp->b_queuetime < jiffies - age) - return; - bp->b_queuetime = jiffies - age; - spin_lock(&btp->bt_delwri_lock); - list_move(&bp->b_list, &btp->bt_delwri_queue); - spin_unlock(&btp->bt_delwri_lock); -} - -/* - * Move as many buffers as specified to the supplied list - * idicating if we skipped any buffers to prevent deadlocks. - */ -STATIC int -xfs_buf_delwri_split( - xfs_buftarg_t *target, - struct list_head *list, - unsigned long age) -{ - xfs_buf_t *bp, *n; - int skipped = 0; - int force; - - force = test_and_clear_bit(XBT_FORCE_FLUSH, &target->bt_flags); - INIT_LIST_HEAD(list); - spin_lock(&target->bt_delwri_lock); - list_for_each_entry_safe(bp, n, &target->bt_delwri_queue, b_list) { - ASSERT(bp->b_flags & XBF_DELWRI); - - if (!xfs_buf_ispinned(bp) && xfs_buf_trylock(bp)) { - if (!force && - time_before(jiffies, bp->b_queuetime + age)) { - xfs_buf_unlock(bp); - break; - } - - bp->b_flags &= ~(XBF_DELWRI | _XBF_DELWRI_Q); - bp->b_flags |= XBF_WRITE; - list_move_tail(&bp->b_list, list); - trace_xfs_buf_delwri_split(bp, _RET_IP_); - } else - skipped++; + bp->b_flags |= _XBF_DELWRI_Q; + if (list_empty(&bp->b_list)) { + atomic_inc(&bp->b_hold); + list_add_tail(&bp->b_list, list); } - spin_unlock(&target->bt_delwri_lock); - return skipped; + return true; } /* @@ -1677,7 +1748,7 @@ xfs_buf_cmp( struct xfs_buf *bp = container_of(b, struct xfs_buf, b_list); xfs_daddr_t diff; - diff = ap->b_bn - bp->b_bn; + diff = ap->b_maps[0].bm_bn - bp->b_maps[0].bm_bn; if (diff < 0) return -1; if (diff > 0) @@ -1685,99 +1756,109 @@ xfs_buf_cmp( return 0; } -STATIC int -xfsbufd( - void *data) +static int +__xfs_buf_delwri_submit( + struct list_head *buffer_list, + struct list_head *io_list, + bool wait) { - xfs_buftarg_t *target = (xfs_buftarg_t *)data; - - current->flags |= PF_MEMALLOC; - - set_freezable(); + struct blk_plug plug; + struct xfs_buf *bp, *n; + int pinned = 0; + + list_for_each_entry_safe(bp, n, buffer_list, b_list) { + if (!wait) { + if (xfs_buf_ispinned(bp)) { + pinned++; + continue; + } + if (!xfs_buf_trylock(bp)) + continue; + } else { + xfs_buf_lock(bp); + } - do { - long age = xfs_buf_age_centisecs * msecs_to_jiffies(10); - long tout = xfs_buf_timer_centisecs * msecs_to_jiffies(10); - struct list_head tmp; - struct blk_plug plug; + /* + * Someone else might have written the buffer synchronously or + * marked it stale in the meantime. In that case only the + * _XBF_DELWRI_Q flag got cleared, and we have to drop the + * reference and remove it from the list here. + */ + if (!(bp->b_flags & _XBF_DELWRI_Q)) { + list_del_init(&bp->b_list); + xfs_buf_relse(bp); + continue; + } - if (unlikely(freezing(current))) - try_to_freeze(); + list_move_tail(&bp->b_list, io_list); + trace_xfs_buf_delwri_split(bp, _RET_IP_); + } - /* sleep for a long time if there is nothing to do. */ - if (list_empty(&target->bt_delwri_queue)) - tout = MAX_SCHEDULE_TIMEOUT; - schedule_timeout_interruptible(tout); + list_sort(NULL, io_list, xfs_buf_cmp); - xfs_buf_delwri_split(target, &tmp, age); - list_sort(NULL, &tmp, xfs_buf_cmp); + blk_start_plug(&plug); + list_for_each_entry_safe(bp, n, io_list, b_list) { + bp->b_flags &= ~(_XBF_DELWRI_Q | XBF_ASYNC | XBF_WRITE_FAIL); + bp->b_flags |= XBF_WRITE; - blk_start_plug(&plug); - while (!list_empty(&tmp)) { - struct xfs_buf *bp; - bp = list_first_entry(&tmp, struct xfs_buf, b_list); + if (!wait) { + bp->b_flags |= XBF_ASYNC; list_del_init(&bp->b_list); - xfs_bdstrat_cb(bp); } - blk_finish_plug(&plug); - } while (!kthread_should_stop()); + xfs_bdstrat_cb(bp); + } + blk_finish_plug(&plug); - return 0; + return pinned; } /* - * Go through all incore buffers, and release buffers if they belong to - * the given device. This is used in filesystem error handling to - * preserve the consistency of its metadata. + * Write out a buffer list asynchronously. + * + * This will take the @buffer_list, write all non-locked and non-pinned buffers + * out and not wait for I/O completion on any of the buffers. This interface + * is only safely useable for callers that can track I/O completion by higher + * level means, e.g. AIL pushing as the @buffer_list is consumed in this + * function. */ int -xfs_flush_buftarg( - xfs_buftarg_t *target, - int wait) +xfs_buf_delwri_submit_nowait( + struct list_head *buffer_list) { - xfs_buf_t *bp; - int pincount = 0; - LIST_HEAD(tmp_list); - LIST_HEAD(wait_list); - struct blk_plug plug; + LIST_HEAD (io_list); + return __xfs_buf_delwri_submit(buffer_list, &io_list, false); +} - flush_workqueue(xfslogd_workqueue); +/* + * Write out a buffer list synchronously. + * + * This will take the @buffer_list, write all buffers out and wait for I/O + * completion on all of the buffers. @buffer_list is consumed by the function, + * so callers must have some other way of tracking buffers if they require such + * functionality. + */ +int +xfs_buf_delwri_submit( + struct list_head *buffer_list) +{ + LIST_HEAD (io_list); + int error = 0, error2; + struct xfs_buf *bp; - set_bit(XBT_FORCE_FLUSH, &target->bt_flags); - pincount = xfs_buf_delwri_split(target, &tmp_list, 0); + __xfs_buf_delwri_submit(buffer_list, &io_list, true); - /* - * Dropped the delayed write list lock, now walk the temporary list. - * All I/O is issued async and then if we need to wait for completion - * we do that after issuing all the IO. - */ - list_sort(NULL, &tmp_list, xfs_buf_cmp); + /* Wait for IO to complete. */ + while (!list_empty(&io_list)) { + bp = list_first_entry(&io_list, struct xfs_buf, b_list); - blk_start_plug(&plug); - while (!list_empty(&tmp_list)) { - bp = list_first_entry(&tmp_list, struct xfs_buf, b_list); - ASSERT(target == bp->b_target); list_del_init(&bp->b_list); - if (wait) { - bp->b_flags &= ~XBF_ASYNC; - list_add(&bp->b_list, &wait_list); - } - xfs_bdstrat_cb(bp); - } - blk_finish_plug(&plug); - - if (wait) { - /* Wait for IO to complete. */ - while (!list_empty(&wait_list)) { - bp = list_first_entry(&wait_list, struct xfs_buf, b_list); - - list_del_init(&bp->b_list); - xfs_buf_iowait(bp); - xfs_buf_relse(bp); - } + error2 = xfs_buf_iowait(bp); + xfs_buf_relse(bp); + if (!error) + error = error2; } - return pincount; + return error; } int __init @@ -1793,21 +1874,8 @@ xfs_buf_init(void) if (!xfslogd_workqueue) goto out_free_buf_zone; - xfsdatad_workqueue = alloc_workqueue("xfsdatad", WQ_MEM_RECLAIM, 1); - if (!xfsdatad_workqueue) - goto out_destroy_xfslogd_workqueue; - - xfsconvertd_workqueue = alloc_workqueue("xfsconvertd", - WQ_MEM_RECLAIM, 1); - if (!xfsconvertd_workqueue) - goto out_destroy_xfsdatad_workqueue; - return 0; - out_destroy_xfsdatad_workqueue: - destroy_workqueue(xfsdatad_workqueue); - out_destroy_xfslogd_workqueue: - destroy_workqueue(xfslogd_workqueue); out_free_buf_zone: kmem_zone_destroy(xfs_buf_zone); out: @@ -1817,8 +1885,6 @@ xfs_buf_init(void) void xfs_buf_terminate(void) { - destroy_workqueue(xfsconvertd_workqueue); - destroy_workqueue(xfsdatad_workqueue); destroy_workqueue(xfslogd_workqueue); kmem_zone_destroy(xfs_buf_zone); } |