From d0164adc89f6bb374d304ffcc375c6d2652fe67d Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Fri, 6 Nov 2015 16:28:21 -0800 Subject: mm, page_alloc: distinguish between being unable to sleep, unwilling to sleep and avoiding waking kswapd __GFP_WAIT has been used to identify atomic context in callers that hold spinlocks or are in interrupts. They are expected to be high priority and have access one of two watermarks lower than "min" which can be referred to as the "atomic reserve". __GFP_HIGH users get access to the first lower watermark and can be called the "high priority reserve". Over time, callers had a requirement to not block when fallback options were available. Some have abused __GFP_WAIT leading to a situation where an optimisitic allocation with a fallback option can access atomic reserves. This patch uses __GFP_ATOMIC to identify callers that are truely atomic, cannot sleep and have no alternative. High priority users continue to use __GFP_HIGH. __GFP_DIRECT_RECLAIM identifies callers that can sleep and are willing to enter direct reclaim. __GFP_KSWAPD_RECLAIM to identify callers that want to wake kswapd for background reclaim. __GFP_WAIT is redefined as a caller that is willing to enter direct reclaim and wake kswapd for background reclaim. This patch then converts a number of sites o __GFP_ATOMIC is used by callers that are high priority and have memory pools for those requests. GFP_ATOMIC uses this flag. o Callers that have a limited mempool to guarantee forward progress clear __GFP_DIRECT_RECLAIM but keep __GFP_KSWAPD_RECLAIM. bio allocations fall into this category where kswapd will still be woken but atomic reserves are not used as there is a one-entry mempool to guarantee progress. o Callers that are checking if they are non-blocking should use the helper gfpflags_allow_blocking() where possible. This is because checking for __GFP_WAIT as was done historically now can trigger false positives. Some exceptions like dm-crypt.c exist where the code intent is clearer if __GFP_DIRECT_RECLAIM is used instead of the helper due to flag manipulations. o Callers that built their own GFP flags instead of starting with GFP_KERNEL and friends now also need to specify __GFP_KSWAPD_RECLAIM. The first key hazard to watch out for is callers that removed __GFP_WAIT and was depending on access to atomic reserves for inconspicuous reasons. In some cases it may be appropriate for them to use __GFP_HIGH. The second key hazard is callers that assembled their own combination of GFP flags instead of starting with something like GFP_KERNEL. They may now wish to specify __GFP_KSWAPD_RECLAIM. It's almost certainly harmless if it's missed in most cases as other activity will wake kswapd. Signed-off-by: Mel Gorman Acked-by: Vlastimil Babka Acked-by: Michal Hocko Acked-by: Johannes Weiner Cc: Christoph Lameter Cc: David Rientjes Cc: Vitaly Wool Cc: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/btrfs/disk-io.c | 2 +- fs/btrfs/extent_io.c | 14 +++++++------- fs/btrfs/volumes.c | 4 ++-- fs/ext4/super.c | 2 +- fs/fscache/cookie.c | 2 +- fs/fscache/page.c | 6 +++--- fs/jbd2/transaction.c | 4 ++-- fs/nfs/file.c | 6 +++--- fs/xfs/xfs_qm.c | 2 +- 9 files changed, 21 insertions(+), 21 deletions(-) (limited to 'fs') diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 1e60d00d4ea7..c339d561e596 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2572,7 +2572,7 @@ int open_ctree(struct super_block *sb, fs_info->commit_interval = BTRFS_DEFAULT_COMMIT_INTERVAL; fs_info->avg_delayed_ref_runtime = NSEC_PER_SEC >> 6; /* div by 64 */ /* readahead state */ - INIT_RADIX_TREE(&fs_info->reada_tree, GFP_NOFS & ~__GFP_WAIT); + INIT_RADIX_TREE(&fs_info->reada_tree, GFP_NOFS & ~__GFP_DIRECT_RECLAIM); spin_lock_init(&fs_info->reada_lock); fs_info->thread_pool_size = min_t(unsigned long, diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 3915c9473e94..032abfbebe76 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -594,7 +594,7 @@ int clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, if (bits & (EXTENT_IOBITS | EXTENT_BOUNDARY)) clear = 1; again: - if (!prealloc && (mask & __GFP_WAIT)) { + if (!prealloc && gfpflags_allow_blocking(mask)) { /* * Don't care for allocation failure here because we might end * up not needing the pre-allocated extent state at all, which @@ -718,7 +718,7 @@ search_again: if (start > end) goto out; spin_unlock(&tree->lock); - if (mask & __GFP_WAIT) + if (gfpflags_allow_blocking(mask)) cond_resched(); goto again; } @@ -850,7 +850,7 @@ __set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, bits |= EXTENT_FIRST_DELALLOC; again: - if (!prealloc && (mask & __GFP_WAIT)) { + if (!prealloc && gfpflags_allow_blocking(mask)) { prealloc = alloc_extent_state(mask); BUG_ON(!prealloc); } @@ -1028,7 +1028,7 @@ search_again: if (start > end) goto out; spin_unlock(&tree->lock); - if (mask & __GFP_WAIT) + if (gfpflags_allow_blocking(mask)) cond_resched(); goto again; } @@ -1076,7 +1076,7 @@ int convert_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, btrfs_debug_check_extent_io_range(tree, start, end); again: - if (!prealloc && (mask & __GFP_WAIT)) { + if (!prealloc && gfpflags_allow_blocking(mask)) { /* * Best effort, don't worry if extent state allocation fails * here for the first iteration. We might have a cached state @@ -1253,7 +1253,7 @@ search_again: if (start > end) goto out; spin_unlock(&tree->lock); - if (mask & __GFP_WAIT) + if (gfpflags_allow_blocking(mask)) cond_resched(); first_iteration = false; goto again; @@ -4319,7 +4319,7 @@ int try_release_extent_mapping(struct extent_map_tree *map, u64 start = page_offset(page); u64 end = start + PAGE_CACHE_SIZE - 1; - if ((mask & __GFP_WAIT) && + if (gfpflags_allow_blocking(mask) && page->mapping->host->i_size > 16 * 1024 * 1024) { u64 len; while (start <= end) { diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 6fc735869c18..e023919b4470 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -156,8 +156,8 @@ static struct btrfs_device *__alloc_device(void) spin_lock_init(&dev->reada_lock); atomic_set(&dev->reada_in_flight, 0); atomic_set(&dev->dev_stats_ccnt, 0); - INIT_RADIX_TREE(&dev->reada_zones, GFP_NOFS & ~__GFP_WAIT); - INIT_RADIX_TREE(&dev->reada_extents, GFP_NOFS & ~__GFP_WAIT); + INIT_RADIX_TREE(&dev->reada_zones, GFP_NOFS & ~__GFP_DIRECT_RECLAIM); + INIT_RADIX_TREE(&dev->reada_extents, GFP_NOFS & ~__GFP_DIRECT_RECLAIM); return dev; } diff --git a/fs/ext4/super.c b/fs/ext4/super.c index a63c7b0a10cf..49f6c78ee3af 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1058,7 +1058,7 @@ static int bdev_try_to_free_page(struct super_block *sb, struct page *page, return 0; if (journal) return jbd2_journal_try_to_free_buffers(journal, page, - wait & ~__GFP_WAIT); + wait & ~__GFP_DIRECT_RECLAIM); return try_to_free_buffers(page); } diff --git a/fs/fscache/cookie.c b/fs/fscache/cookie.c index d403c69bee08..4304072161aa 100644 --- a/fs/fscache/cookie.c +++ b/fs/fscache/cookie.c @@ -111,7 +111,7 @@ struct fscache_cookie *__fscache_acquire_cookie( /* radix tree insertion won't use the preallocation pool unless it's * told it may not wait */ - INIT_RADIX_TREE(&cookie->stores, GFP_NOFS & ~__GFP_WAIT); + INIT_RADIX_TREE(&cookie->stores, GFP_NOFS & ~__GFP_DIRECT_RECLAIM); switch (cookie->def->type) { case FSCACHE_COOKIE_TYPE_INDEX: diff --git a/fs/fscache/page.c b/fs/fscache/page.c index 483bbc613bf0..79483b3d8c6f 100644 --- a/fs/fscache/page.c +++ b/fs/fscache/page.c @@ -58,7 +58,7 @@ bool release_page_wait_timeout(struct fscache_cookie *cookie, struct page *page) /* * decide whether a page can be released, possibly by cancelling a store to it - * - we're allowed to sleep if __GFP_WAIT is flagged + * - we're allowed to sleep if __GFP_DIRECT_RECLAIM is flagged */ bool __fscache_maybe_release_page(struct fscache_cookie *cookie, struct page *page, @@ -122,7 +122,7 @@ page_busy: * allocator as the work threads writing to the cache may all end up * sleeping on memory allocation, so we may need to impose a timeout * too. */ - if (!(gfp & __GFP_WAIT) || !(gfp & __GFP_FS)) { + if (!(gfp & __GFP_DIRECT_RECLAIM) || !(gfp & __GFP_FS)) { fscache_stat(&fscache_n_store_vmscan_busy); return false; } @@ -132,7 +132,7 @@ page_busy: _debug("fscache writeout timeout page: %p{%lx}", page, page->index); - gfp &= ~__GFP_WAIT; + gfp &= ~__GFP_DIRECT_RECLAIM; goto try_again; } EXPORT_SYMBOL(__fscache_maybe_release_page); diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index 6b8338ec2464..89463eee6791 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -1937,8 +1937,8 @@ out: * @journal: journal for operation * @page: to try and free * @gfp_mask: we use the mask to detect how hard should we try to release - * buffers. If __GFP_WAIT and __GFP_FS is set, we wait for commit code to - * release the buffers. + * buffers. If __GFP_DIRECT_RECLAIM and __GFP_FS is set, we wait for commit + * code to release the buffers. * * * For all the buffers on this page, diff --git a/fs/nfs/file.c b/fs/nfs/file.c index 37f639d50af5..93e236429c5d 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -473,8 +473,8 @@ static int nfs_release_page(struct page *page, gfp_t gfp) dfprintk(PAGECACHE, "NFS: release_page(%p)\n", page); /* Always try to initiate a 'commit' if relevant, but only - * wait for it if __GFP_WAIT is set. Even then, only wait 1 - * second and only if the 'bdi' is not congested. + * wait for it if the caller allows blocking. Even then, + * only wait 1 second and only if the 'bdi' is not congested. * Waiting indefinitely can cause deadlocks when the NFS * server is on this machine, when a new TCP connection is * needed and in other rare cases. There is no particular @@ -484,7 +484,7 @@ static int nfs_release_page(struct page *page, gfp_t gfp) if (mapping) { struct nfs_server *nfss = NFS_SERVER(mapping->host); nfs_commit_inode(mapping->host, 0); - if ((gfp & __GFP_WAIT) && + if (gfpflags_allow_blocking(gfp) && !bdi_write_congested(&nfss->backing_dev_info)) { wait_on_page_bit_killable_timeout(page, PG_private, HZ); diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c index eac9549efd52..587174fd4f2c 100644 --- a/fs/xfs/xfs_qm.c +++ b/fs/xfs/xfs_qm.c @@ -525,7 +525,7 @@ xfs_qm_shrink_scan( unsigned long freed; int error; - if ((sc->gfp_mask & (__GFP_FS|__GFP_WAIT)) != (__GFP_FS|__GFP_WAIT)) + if ((sc->gfp_mask & (__GFP_FS|__GFP_DIRECT_RECLAIM)) != (__GFP_FS|__GFP_DIRECT_RECLAIM)) return 0; INIT_LIST_HEAD(&isol.buffers); -- cgit v1.2.3-70-g09d2 From 71baba4b92dc1fa1bc461742c6ab1942ec6034e9 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Fri, 6 Nov 2015 16:28:28 -0800 Subject: mm, page_alloc: rename __GFP_WAIT to __GFP_RECLAIM __GFP_WAIT was used to signal that the caller was in atomic context and could not sleep. Now it is possible to distinguish between true atomic context and callers that are not willing to sleep. The latter should clear __GFP_DIRECT_RECLAIM so kswapd will still wake. As clearing __GFP_WAIT behaves differently, there is a risk that people will clear the wrong flags. This patch renames __GFP_WAIT to __GFP_RECLAIM to clearly indicate what it does -- setting it allows all reclaim activity, clearing them prevents it. [akpm@linux-foundation.org: fix build] [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Mel Gorman Acked-by: Michal Hocko Acked-by: Vlastimil Babka Acked-by: Johannes Weiner Cc: Christoph Lameter Acked-by: David Rientjes Cc: Vitaly Wool Cc: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- block/blk-core.c | 4 ++-- block/blk-mq.c | 2 +- block/scsi_ioctl.c | 6 +++--- drivers/block/drbd/drbd_bitmap.c | 2 +- drivers/block/mtip32xx/mtip32xx.c | 2 +- drivers/block/paride/pd.c | 2 +- drivers/block/pktcdvd.c | 4 ++-- drivers/gpu/drm/i915/i915_gem.c | 2 +- drivers/ide/ide-atapi.c | 2 +- drivers/ide/ide-cd.c | 2 +- drivers/ide/ide-cd_ioctl.c | 2 +- drivers/ide/ide-devsets.c | 2 +- drivers/ide/ide-disk.c | 2 +- drivers/ide/ide-ioctls.c | 4 ++-- drivers/ide/ide-park.c | 2 +- drivers/ide/ide-pm.c | 4 ++-- drivers/ide/ide-tape.c | 4 ++-- drivers/ide/ide-taskfile.c | 4 ++-- drivers/infiniband/hw/qib/qib_init.c | 2 +- drivers/misc/vmw_balloon.c | 2 +- drivers/nvme/host/pci.c | 6 ++++-- drivers/scsi/scsi_error.c | 2 +- drivers/scsi/scsi_lib.c | 4 ++-- drivers/staging/rdma/hfi1/init.c | 2 +- drivers/staging/rdma/ipath/ipath_file_ops.c | 2 +- fs/cachefiles/internal.h | 2 +- fs/direct-io.c | 2 +- fs/nilfs2/mdt.h | 2 +- include/linux/gfp.h | 16 ++++++++-------- kernel/power/swap.c | 16 ++++++++-------- lib/percpu_ida.c | 2 +- mm/failslab.c | 8 ++++---- mm/filemap.c | 2 +- mm/huge_memory.c | 2 +- mm/memcontrol.c | 2 +- mm/migrate.c | 2 +- mm/page_alloc.c | 9 +++++---- security/integrity/ima/ima_crypto.c | 2 +- 38 files changed, 71 insertions(+), 68 deletions(-) (limited to 'fs') diff --git a/block/blk-core.c b/block/blk-core.c index 9e32f0868e36..590cca21c24a 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -638,7 +638,7 @@ int blk_queue_enter(struct request_queue *q, gfp_t gfp) if (percpu_ref_tryget_live(&q->q_usage_counter)) return 0; - if (!(gfp & __GFP_WAIT)) + if (!gfpflags_allow_blocking(gfp)) return -EBUSY; ret = wait_event_interruptible(q->mq_freeze_wq, @@ -2038,7 +2038,7 @@ void generic_make_request(struct bio *bio) do { struct request_queue *q = bdev_get_queue(bio->bi_bdev); - if (likely(blk_queue_enter(q, __GFP_WAIT) == 0)) { + if (likely(blk_queue_enter(q, __GFP_DIRECT_RECLAIM) == 0)) { q->make_request_fn(q, bio); diff --git a/block/blk-mq.c b/block/blk-mq.c index 68c0a3416b34..694f8703f83c 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -1186,7 +1186,7 @@ static struct request *blk_mq_map_request(struct request_queue *q, ctx = blk_mq_get_ctx(q); hctx = q->mq_ops->map_queue(q, ctx->cpu); blk_mq_set_alloc_data(&alloc_data, q, - __GFP_WAIT|__GFP_HIGH, false, ctx, hctx); + __GFP_RECLAIM|__GFP_HIGH, false, ctx, hctx); rq = __blk_mq_alloc_request(&alloc_data, rw); ctx = alloc_data.ctx; hctx = alloc_data.hctx; diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c index dda653ce7b24..0774799942e0 100644 --- a/block/scsi_ioctl.c +++ b/block/scsi_ioctl.c @@ -444,7 +444,7 @@ int sg_scsi_ioctl(struct request_queue *q, struct gendisk *disk, fmode_t mode, } - rq = blk_get_request(q, in_len ? WRITE : READ, __GFP_WAIT); + rq = blk_get_request(q, in_len ? WRITE : READ, __GFP_RECLAIM); if (IS_ERR(rq)) { err = PTR_ERR(rq); goto error_free_buffer; @@ -495,7 +495,7 @@ int sg_scsi_ioctl(struct request_queue *q, struct gendisk *disk, fmode_t mode, break; } - if (bytes && blk_rq_map_kern(q, rq, buffer, bytes, __GFP_WAIT)) { + if (bytes && blk_rq_map_kern(q, rq, buffer, bytes, __GFP_RECLAIM)) { err = DRIVER_ERROR << 24; goto error; } @@ -536,7 +536,7 @@ static int __blk_send_generic(struct request_queue *q, struct gendisk *bd_disk, struct request *rq; int err; - rq = blk_get_request(q, WRITE, __GFP_WAIT); + rq = blk_get_request(q, WRITE, __GFP_RECLAIM); if (IS_ERR(rq)) return PTR_ERR(rq); blk_rq_set_block_pc(rq); diff --git a/drivers/block/drbd/drbd_bitmap.c b/drivers/block/drbd/drbd_bitmap.c index e5e0f19ceda0..3dc53a16ed3a 100644 --- a/drivers/block/drbd/drbd_bitmap.c +++ b/drivers/block/drbd/drbd_bitmap.c @@ -1007,7 +1007,7 @@ static void bm_page_io_async(struct drbd_bm_aio_ctx *ctx, int page_nr) __must_ho bm_set_page_unchanged(b->bm_pages[page_nr]); if (ctx->flags & BM_AIO_COPY_PAGES) { - page = mempool_alloc(drbd_md_io_page_pool, __GFP_HIGHMEM|__GFP_WAIT); + page = mempool_alloc(drbd_md_io_page_pool, __GFP_HIGHMEM|__GFP_RECLAIM); copy_highpage(page, b->bm_pages[page_nr]); bm_store_page_idx(page, page_nr); } else diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c index f504232c1ee7..a28a562f7b7f 100644 --- a/drivers/block/mtip32xx/mtip32xx.c +++ b/drivers/block/mtip32xx/mtip32xx.c @@ -173,7 +173,7 @@ static struct mtip_cmd *mtip_get_int_command(struct driver_data *dd) { struct request *rq; - rq = blk_mq_alloc_request(dd->queue, 0, __GFP_WAIT, true); + rq = blk_mq_alloc_request(dd->queue, 0, __GFP_RECLAIM, true); return blk_mq_rq_to_pdu(rq); } diff --git a/drivers/block/paride/pd.c b/drivers/block/paride/pd.c index b9242d78283d..562b5a4ca7b7 100644 --- a/drivers/block/paride/pd.c +++ b/drivers/block/paride/pd.c @@ -723,7 +723,7 @@ static int pd_special_command(struct pd_unit *disk, struct request *rq; int err = 0; - rq = blk_get_request(disk->gd->queue, READ, __GFP_WAIT); + rq = blk_get_request(disk->gd->queue, READ, __GFP_RECLAIM); if (IS_ERR(rq)) return PTR_ERR(rq); diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c index 7be2375db7f2..5959c2981cc7 100644 --- a/drivers/block/pktcdvd.c +++ b/drivers/block/pktcdvd.c @@ -704,14 +704,14 @@ static int pkt_generic_packet(struct pktcdvd_device *pd, struct packet_command * int ret = 0; rq = blk_get_request(q, (cgc->data_direction == CGC_DATA_WRITE) ? - WRITE : READ, __GFP_WAIT); + WRITE : READ, __GFP_RECLAIM); if (IS_ERR(rq)) return PTR_ERR(rq); blk_rq_set_block_pc(rq); if (cgc->buflen) { ret = blk_rq_map_kern(q, rq, cgc->buffer, cgc->buflen, - __GFP_WAIT); + __GFP_RECLAIM); if (ret) goto out; } diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index d58cb9e034fe..7e505d4be7c0 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -2216,7 +2216,7 @@ i915_gem_object_get_pages_gtt(struct drm_i915_gem_object *obj) mapping = file_inode(obj->base.filp)->i_mapping; gfp = mapping_gfp_mask(mapping); gfp |= __GFP_NORETRY | __GFP_NOWARN; - gfp &= ~(__GFP_IO | __GFP_WAIT); + gfp &= ~(__GFP_IO | __GFP_RECLAIM); sg = st->sgl; st->nents = 0; for (i = 0; i < page_count; i++) { diff --git a/drivers/ide/ide-atapi.c b/drivers/ide/ide-atapi.c index 1362ad80a76c..05352f490d60 100644 --- a/drivers/ide/ide-atapi.c +++ b/drivers/ide/ide-atapi.c @@ -92,7 +92,7 @@ int ide_queue_pc_tail(ide_drive_t *drive, struct gendisk *disk, struct request *rq; int error; - rq = blk_get_request(drive->queue, READ, __GFP_WAIT); + rq = blk_get_request(drive->queue, READ, __GFP_RECLAIM); rq->cmd_type = REQ_TYPE_DRV_PRIV; rq->special = (char *)pc; diff --git a/drivers/ide/ide-cd.c b/drivers/ide/ide-cd.c index 64a6b827b3dd..ef907fd5ba98 100644 --- a/drivers/ide/ide-cd.c +++ b/drivers/ide/ide-cd.c @@ -441,7 +441,7 @@ int ide_cd_queue_pc(ide_drive_t *drive, const unsigned char *cmd, struct request *rq; int error; - rq = blk_get_request(drive->queue, write, __GFP_WAIT); + rq = blk_get_request(drive->queue, write, __GFP_RECLAIM); memcpy(rq->cmd, cmd, BLK_MAX_CDB); rq->cmd_type = REQ_TYPE_ATA_PC; diff --git a/drivers/ide/ide-cd_ioctl.c b/drivers/ide/ide-cd_ioctl.c index 066e39036518..474173eb31bb 100644 --- a/drivers/ide/ide-cd_ioctl.c +++ b/drivers/ide/ide-cd_ioctl.c @@ -303,7 +303,7 @@ int ide_cdrom_reset(struct cdrom_device_info *cdi) struct request *rq; int ret; - rq = blk_get_request(drive->queue, READ, __GFP_WAIT); + rq = blk_get_request(drive->queue, READ, __GFP_RECLAIM); rq->cmd_type = REQ_TYPE_DRV_PRIV; rq->cmd_flags = REQ_QUIET; ret = blk_execute_rq(drive->queue, cd->disk, rq, 0); diff --git a/drivers/ide/ide-devsets.c b/drivers/ide/ide-devsets.c index b05a74d78ef5..0dd43b4fcec6 100644 --- a/drivers/ide/ide-devsets.c +++ b/drivers/ide/ide-devsets.c @@ -165,7 +165,7 @@ int ide_devset_execute(ide_drive_t *drive, const struct ide_devset *setting, if (!(setting->flags & DS_SYNC)) return setting->set(drive, arg); - rq = blk_get_request(q, READ, __GFP_WAIT); + rq = blk_get_request(q, READ, __GFP_RECLAIM); rq->cmd_type = REQ_TYPE_DRV_PRIV; rq->cmd_len = 5; rq->cmd[0] = REQ_DEVSET_EXEC; diff --git a/drivers/ide/ide-disk.c b/drivers/ide/ide-disk.c index 56b9708894a5..37a8a907febe 100644 --- a/drivers/ide/ide-disk.c +++ b/drivers/ide/ide-disk.c @@ -477,7 +477,7 @@ static int set_multcount(ide_drive_t *drive, int arg) if (drive->special_flags & IDE_SFLAG_SET_MULTMODE) return -EBUSY; - rq = blk_get_request(drive->queue, READ, __GFP_WAIT); + rq = blk_get_request(drive->queue, READ, __GFP_RECLAIM); rq->cmd_type = REQ_TYPE_ATA_TASKFILE; drive->mult_req = arg; diff --git a/drivers/ide/ide-ioctls.c b/drivers/ide/ide-ioctls.c index aa2e9b77b20d..d05db2469209 100644 --- a/drivers/ide/ide-ioctls.c +++ b/drivers/ide/ide-ioctls.c @@ -125,7 +125,7 @@ static int ide_cmd_ioctl(ide_drive_t *drive, unsigned long arg) if (NULL == (void *) arg) { struct request *rq; - rq = blk_get_request(drive->queue, READ, __GFP_WAIT); + rq = blk_get_request(drive->queue, READ, __GFP_RECLAIM); rq->cmd_type = REQ_TYPE_ATA_TASKFILE; err = blk_execute_rq(drive->queue, NULL, rq, 0); blk_put_request(rq); @@ -221,7 +221,7 @@ static int generic_drive_reset(ide_drive_t *drive) struct request *rq; int ret = 0; - rq = blk_get_request(drive->queue, READ, __GFP_WAIT); + rq = blk_get_request(drive->queue, READ, __GFP_RECLAIM); rq->cmd_type = REQ_TYPE_DRV_PRIV; rq->cmd_len = 1; rq->cmd[0] = REQ_DRIVE_RESET; diff --git a/drivers/ide/ide-park.c b/drivers/ide/ide-park.c index c80868520488..2d7dca56dd24 100644 --- a/drivers/ide/ide-park.c +++ b/drivers/ide/ide-park.c @@ -31,7 +31,7 @@ static void issue_park_cmd(ide_drive_t *drive, unsigned long timeout) } spin_unlock_irq(&hwif->lock); - rq = blk_get_request(q, READ, __GFP_WAIT); + rq = blk_get_request(q, READ, __GFP_RECLAIM); rq->cmd[0] = REQ_PARK_HEADS; rq->cmd_len = 1; rq->cmd_type = REQ_TYPE_DRV_PRIV; diff --git a/drivers/ide/ide-pm.c b/drivers/ide/ide-pm.c index 081e43458d50..e34af488693a 100644 --- a/drivers/ide/ide-pm.c +++ b/drivers/ide/ide-pm.c @@ -18,7 +18,7 @@ int generic_ide_suspend(struct device *dev, pm_message_t mesg) } memset(&rqpm, 0, sizeof(rqpm)); - rq = blk_get_request(drive->queue, READ, __GFP_WAIT); + rq = blk_get_request(drive->queue, READ, __GFP_RECLAIM); rq->cmd_type = REQ_TYPE_ATA_PM_SUSPEND; rq->special = &rqpm; rqpm.pm_step = IDE_PM_START_SUSPEND; @@ -88,7 +88,7 @@ int generic_ide_resume(struct device *dev) } memset(&rqpm, 0, sizeof(rqpm)); - rq = blk_get_request(drive->queue, READ, __GFP_WAIT); + rq = blk_get_request(drive->queue, READ, __GFP_RECLAIM); rq->cmd_type = REQ_TYPE_ATA_PM_RESUME; rq->cmd_flags |= REQ_PREEMPT; rq->special = &rqpm; diff --git a/drivers/ide/ide-tape.c b/drivers/ide/ide-tape.c index f5d51d1d09ee..12fa04997dcc 100644 --- a/drivers/ide/ide-tape.c +++ b/drivers/ide/ide-tape.c @@ -852,7 +852,7 @@ static int idetape_queue_rw_tail(ide_drive_t *drive, int cmd, int size) BUG_ON(cmd != REQ_IDETAPE_READ && cmd != REQ_IDETAPE_WRITE); BUG_ON(size < 0 || size % tape->blk_size); - rq = blk_get_request(drive->queue, READ, __GFP_WAIT); + rq = blk_get_request(drive->queue, READ, __GFP_RECLAIM); rq->cmd_type = REQ_TYPE_DRV_PRIV; rq->cmd[13] = cmd; rq->rq_disk = tape->disk; @@ -860,7 +860,7 @@ static int idetape_queue_rw_tail(ide_drive_t *drive, int cmd, int size) if (size) { ret = blk_rq_map_kern(drive->queue, rq, tape->buf, size, - __GFP_WAIT); + __GFP_RECLAIM); if (ret) goto out_put; } diff --git a/drivers/ide/ide-taskfile.c b/drivers/ide/ide-taskfile.c index 0979e126fff1..a716693417a3 100644 --- a/drivers/ide/ide-taskfile.c +++ b/drivers/ide/ide-taskfile.c @@ -430,7 +430,7 @@ int ide_raw_taskfile(ide_drive_t *drive, struct ide_cmd *cmd, u8 *buf, int error; int rw = !(cmd->tf_flags & IDE_TFLAG_WRITE) ? READ : WRITE; - rq = blk_get_request(drive->queue, rw, __GFP_WAIT); + rq = blk_get_request(drive->queue, rw, __GFP_RECLAIM); rq->cmd_type = REQ_TYPE_ATA_TASKFILE; /* @@ -441,7 +441,7 @@ int ide_raw_taskfile(ide_drive_t *drive, struct ide_cmd *cmd, u8 *buf, */ if (nsect) { error = blk_rq_map_kern(drive->queue, rq, buf, - nsect * SECTOR_SIZE, __GFP_WAIT); + nsect * SECTOR_SIZE, __GFP_RECLAIM); if (error) goto put_req; } diff --git a/drivers/infiniband/hw/qib/qib_init.c b/drivers/infiniband/hw/qib/qib_init.c index 7e00470adc30..4ff340fe904f 100644 --- a/drivers/infiniband/hw/qib/qib_init.c +++ b/drivers/infiniband/hw/qib/qib_init.c @@ -1680,7 +1680,7 @@ int qib_setup_eagerbufs(struct qib_ctxtdata *rcd) * heavy filesystem activity makes these fail, and we can * use compound pages. */ - gfp_flags = __GFP_WAIT | __GFP_IO | __GFP_COMP; + gfp_flags = __GFP_RECLAIM | __GFP_IO | __GFP_COMP; egrcnt = rcd->rcvegrcnt; egroff = rcd->rcvegr_tid_base; diff --git a/drivers/misc/vmw_balloon.c b/drivers/misc/vmw_balloon.c index 89300870fefb..1e688bfec567 100644 --- a/drivers/misc/vmw_balloon.c +++ b/drivers/misc/vmw_balloon.c @@ -75,7 +75,7 @@ MODULE_LICENSE("GPL"); /* * Use __GFP_HIGHMEM to allow pages from HIGHMEM zone. We don't - * allow wait (__GFP_WAIT) for NOSLEEP page allocations. Use + * allow wait (__GFP_RECLAIM) for NOSLEEP page allocations. Use * __GFP_NOWARN, to suppress page allocation failure warnings. */ #define VMW_PAGE_ALLOC_NOSLEEP (__GFP_HIGHMEM|__GFP_NOWARN) diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index e878590e71b6..6c195554d94a 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -1025,11 +1025,13 @@ int __nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd, req->special = (void *)0; if (buffer && bufflen) { - ret = blk_rq_map_kern(q, req, buffer, bufflen, __GFP_WAIT); + ret = blk_rq_map_kern(q, req, buffer, bufflen, + __GFP_DIRECT_RECLAIM); if (ret) goto out; } else if (ubuffer && bufflen) { - ret = blk_rq_map_user(q, req, NULL, ubuffer, bufflen, __GFP_WAIT); + ret = blk_rq_map_user(q, req, NULL, ubuffer, bufflen, + __GFP_DIRECT_RECLAIM); if (ret) goto out; bio = req->bio; diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c index 66a96cd98b97..984ddcb4786d 100644 --- a/drivers/scsi/scsi_error.c +++ b/drivers/scsi/scsi_error.c @@ -1970,7 +1970,7 @@ static void scsi_eh_lock_door(struct scsi_device *sdev) struct request *req; /* - * blk_get_request with GFP_KERNEL (__GFP_WAIT) sleeps until a + * blk_get_request with GFP_KERNEL (__GFP_RECLAIM) sleeps until a * request becomes available */ req = blk_get_request(sdev->request_queue, READ, GFP_KERNEL); diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 126a48c6431e..dd8ad2a44510 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -222,13 +222,13 @@ int scsi_execute(struct scsi_device *sdev, const unsigned char *cmd, int write = (data_direction == DMA_TO_DEVICE); int ret = DRIVER_ERROR << 24; - req = blk_get_request(sdev->request_queue, write, __GFP_WAIT); + req = blk_get_request(sdev->request_queue, write, __GFP_RECLAIM); if (IS_ERR(req)) return ret; blk_rq_set_block_pc(req); if (bufflen && blk_rq_map_kern(sdev->request_queue, req, - buffer, bufflen, __GFP_WAIT)) + buffer, bufflen, __GFP_RECLAIM)) goto out; req->cmd_len = COMMAND_SIZE(cmd[0]); diff --git a/drivers/staging/rdma/hfi1/init.c b/drivers/staging/rdma/hfi1/init.c index 47a1202fcbdf..8666f3ad24e9 100644 --- a/drivers/staging/rdma/hfi1/init.c +++ b/drivers/staging/rdma/hfi1/init.c @@ -1560,7 +1560,7 @@ int hfi1_setup_eagerbufs(struct hfi1_ctxtdata *rcd) * heavy filesystem activity makes these fail, and we can * use compound pages. */ - gfp_flags = __GFP_WAIT | __GFP_IO | __GFP_COMP; + gfp_flags = __GFP_RECLAIM | __GFP_IO | __GFP_COMP; /* * The minimum size of the eager buffers is a groups of MTU-sized diff --git a/drivers/staging/rdma/ipath/ipath_file_ops.c b/drivers/staging/rdma/ipath/ipath_file_ops.c index 5d9b9dbd8fc4..13c3cd11ab92 100644 --- a/drivers/staging/rdma/ipath/ipath_file_ops.c +++ b/drivers/staging/rdma/ipath/ipath_file_ops.c @@ -905,7 +905,7 @@ static int ipath_create_user_egr(struct ipath_portdata *pd) * heavy filesystem activity makes these fail, and we can * use compound pages. */ - gfp_flags = __GFP_WAIT | __GFP_IO | __GFP_COMP; + gfp_flags = __GFP_RECLAIM | __GFP_IO | __GFP_COMP; egrcnt = dd->ipath_rcvegrcnt; /* TID number offset for this port */ diff --git a/fs/cachefiles/internal.h b/fs/cachefiles/internal.h index aecd0859eacb..9c4b737a54df 100644 --- a/fs/cachefiles/internal.h +++ b/fs/cachefiles/internal.h @@ -30,7 +30,7 @@ extern unsigned cachefiles_debug; #define CACHEFILES_DEBUG_KLEAVE 2 #define CACHEFILES_DEBUG_KDEBUG 4 -#define cachefiles_gfp (__GFP_WAIT | __GFP_NORETRY | __GFP_NOMEMALLOC) +#define cachefiles_gfp (__GFP_RECLAIM | __GFP_NORETRY | __GFP_NOMEMALLOC) /* * node records diff --git a/fs/direct-io.c b/fs/direct-io.c index 3ae0e0427191..18e7554cf94c 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -361,7 +361,7 @@ dio_bio_alloc(struct dio *dio, struct dio_submit *sdio, /* * bio_alloc() is guaranteed to return a bio when called with - * __GFP_WAIT and we request a valid number of vectors. + * __GFP_RECLAIM and we request a valid number of vectors. */ bio = bio_alloc(GFP_KERNEL, nr_vecs); diff --git a/fs/nilfs2/mdt.h b/fs/nilfs2/mdt.h index fe529a87a208..03246cac3338 100644 --- a/fs/nilfs2/mdt.h +++ b/fs/nilfs2/mdt.h @@ -72,7 +72,7 @@ static inline struct nilfs_mdt_info *NILFS_MDT(const struct inode *inode) } /* Default GFP flags using highmem */ -#define NILFS_MDT_GFP (__GFP_WAIT | __GFP_IO | __GFP_HIGHMEM) +#define NILFS_MDT_GFP (__GFP_RECLAIM | __GFP_IO | __GFP_HIGHMEM) int nilfs_mdt_get_block(struct inode *, unsigned long, int, void (*init_block)(struct inode *, diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 86f9f7da86ea..369227202ac2 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -107,7 +107,7 @@ struct vm_area_struct; * can be cleared when the reclaiming of pages would cause unnecessary * disruption. */ -#define __GFP_WAIT ((__force gfp_t)(___GFP_DIRECT_RECLAIM|___GFP_KSWAPD_RECLAIM)) +#define __GFP_RECLAIM ((__force gfp_t)(___GFP_DIRECT_RECLAIM|___GFP_KSWAPD_RECLAIM)) #define __GFP_DIRECT_RECLAIM ((__force gfp_t)___GFP_DIRECT_RECLAIM) /* Caller can reclaim */ #define __GFP_KSWAPD_RECLAIM ((__force gfp_t)___GFP_KSWAPD_RECLAIM) /* kswapd can wake */ @@ -126,12 +126,12 @@ struct vm_area_struct; */ #define GFP_ATOMIC (__GFP_HIGH|__GFP_ATOMIC|__GFP_KSWAPD_RECLAIM) #define GFP_NOWAIT (__GFP_KSWAPD_RECLAIM) -#define GFP_NOIO (__GFP_WAIT) -#define GFP_NOFS (__GFP_WAIT | __GFP_IO) -#define GFP_KERNEL (__GFP_WAIT | __GFP_IO | __GFP_FS) -#define GFP_TEMPORARY (__GFP_WAIT | __GFP_IO | __GFP_FS | \ +#define GFP_NOIO (__GFP_RECLAIM) +#define GFP_NOFS (__GFP_RECLAIM | __GFP_IO) +#define GFP_KERNEL (__GFP_RECLAIM | __GFP_IO | __GFP_FS) +#define GFP_TEMPORARY (__GFP_RECLAIM | __GFP_IO | __GFP_FS | \ __GFP_RECLAIMABLE) -#define GFP_USER (__GFP_WAIT | __GFP_IO | __GFP_FS | __GFP_HARDWALL) +#define GFP_USER (__GFP_RECLAIM | __GFP_IO | __GFP_FS | __GFP_HARDWALL) #define GFP_HIGHUSER (GFP_USER | __GFP_HIGHMEM) #define GFP_HIGHUSER_MOVABLE (GFP_HIGHUSER | __GFP_MOVABLE) #define GFP_TRANSHUGE ((GFP_HIGHUSER_MOVABLE | __GFP_COMP | \ @@ -143,12 +143,12 @@ struct vm_area_struct; #define GFP_MOVABLE_SHIFT 3 /* Control page allocator reclaim behavior */ -#define GFP_RECLAIM_MASK (__GFP_WAIT|__GFP_HIGH|__GFP_IO|__GFP_FS|\ +#define GFP_RECLAIM_MASK (__GFP_RECLAIM|__GFP_HIGH|__GFP_IO|__GFP_FS|\ __GFP_NOWARN|__GFP_REPEAT|__GFP_NOFAIL|\ __GFP_NORETRY|__GFP_MEMALLOC|__GFP_NOMEMALLOC) /* Control slab gfp mask during early boot */ -#define GFP_BOOT_MASK (__GFP_BITS_MASK & ~(__GFP_WAIT|__GFP_IO|__GFP_FS)) +#define GFP_BOOT_MASK (__GFP_BITS_MASK & ~(__GFP_RECLAIM|__GFP_IO|__GFP_FS)) /* Control allocation constraints */ #define GFP_CONSTRAINT_MASK (__GFP_HARDWALL|__GFP_THISNODE) diff --git a/kernel/power/swap.c b/kernel/power/swap.c index b2066fb5b10f..12cd989dadf6 100644 --- a/kernel/power/swap.c +++ b/kernel/power/swap.c @@ -257,7 +257,7 @@ static int hib_submit_io(int rw, pgoff_t page_off, void *addr, struct bio *bio; int error = 0; - bio = bio_alloc(__GFP_WAIT | __GFP_HIGH, 1); + bio = bio_alloc(__GFP_RECLAIM | __GFP_HIGH, 1); bio->bi_iter.bi_sector = page_off * (PAGE_SIZE >> 9); bio->bi_bdev = hib_resume_bdev; @@ -356,7 +356,7 @@ static int write_page(void *buf, sector_t offset, struct hib_bio_batch *hb) return -ENOSPC; if (hb) { - src = (void *)__get_free_page(__GFP_WAIT | __GFP_NOWARN | + src = (void *)__get_free_page(__GFP_RECLAIM | __GFP_NOWARN | __GFP_NORETRY); if (src) { copy_page(src, buf); @@ -364,7 +364,7 @@ static int write_page(void *buf, sector_t offset, struct hib_bio_batch *hb) ret = hib_wait_io(hb); /* Free pages */ if (ret) return ret; - src = (void *)__get_free_page(__GFP_WAIT | + src = (void *)__get_free_page(__GFP_RECLAIM | __GFP_NOWARN | __GFP_NORETRY); if (src) { @@ -672,7 +672,7 @@ static int save_image_lzo(struct swap_map_handle *handle, nr_threads = num_online_cpus() - 1; nr_threads = clamp_val(nr_threads, 1, LZO_THREADS); - page = (void *)__get_free_page(__GFP_WAIT | __GFP_HIGH); + page = (void *)__get_free_page(__GFP_RECLAIM | __GFP_HIGH); if (!page) { printk(KERN_ERR "PM: Failed to allocate LZO page\n"); ret = -ENOMEM; @@ -975,7 +975,7 @@ static int get_swap_reader(struct swap_map_handle *handle, last = tmp; tmp->map = (struct swap_map_page *) - __get_free_page(__GFP_WAIT | __GFP_HIGH); + __get_free_page(__GFP_RECLAIM | __GFP_HIGH); if (!tmp->map) { release_swap_reader(handle); return -ENOMEM; @@ -1242,9 +1242,9 @@ static int load_image_lzo(struct swap_map_handle *handle, for (i = 0; i < read_pages; i++) { page[i] = (void *)__get_free_page(i < LZO_CMP_PAGES ? - __GFP_WAIT | __GFP_HIGH : - __GFP_WAIT | __GFP_NOWARN | - __GFP_NORETRY); + __GFP_RECLAIM | __GFP_HIGH : + __GFP_RECLAIM | __GFP_NOWARN | + __GFP_NORETRY); if (!page[i]) { if (i < LZO_CMP_PAGES) { diff --git a/lib/percpu_ida.c b/lib/percpu_ida.c index f75715131f20..6d40944960de 100644 --- a/lib/percpu_ida.c +++ b/lib/percpu_ida.c @@ -135,7 +135,7 @@ static inline unsigned alloc_local_tag(struct percpu_ida_cpu *tags) * TASK_UNINTERRUPTIBLE | TASK_INTERRUPTIBLE, of course). * * @gfp indicates whether or not to wait until a free id is available (it's not - * used for internal memory allocations); thus if passed __GFP_WAIT we may sleep + * used for internal memory allocations); thus if passed __GFP_RECLAIM we may sleep * however long it takes until another thread frees an id (same semantics as a * mempool). * diff --git a/mm/failslab.c b/mm/failslab.c index 98fb490311eb..79171b4a5826 100644 --- a/mm/failslab.c +++ b/mm/failslab.c @@ -3,11 +3,11 @@ static struct { struct fault_attr attr; - bool ignore_gfp_wait; + bool ignore_gfp_reclaim; bool cache_filter; } failslab = { .attr = FAULT_ATTR_INITIALIZER, - .ignore_gfp_wait = true, + .ignore_gfp_reclaim = true, .cache_filter = false, }; @@ -16,7 +16,7 @@ bool should_failslab(size_t size, gfp_t gfpflags, unsigned long cache_flags) if (gfpflags & __GFP_NOFAIL) return false; - if (failslab.ignore_gfp_wait && (gfpflags & __GFP_WAIT)) + if (failslab.ignore_gfp_reclaim && (gfpflags & __GFP_RECLAIM)) return false; if (failslab.cache_filter && !(cache_flags & SLAB_FAILSLAB)) @@ -42,7 +42,7 @@ static int __init failslab_debugfs_init(void) return PTR_ERR(dir); if (!debugfs_create_bool("ignore-gfp-wait", mode, dir, - &failslab.ignore_gfp_wait)) + &failslab.ignore_gfp_reclaim)) goto fail; if (!debugfs_create_bool("cache-filter", mode, dir, &failslab.cache_filter)) diff --git a/mm/filemap.c b/mm/filemap.c index 58e04e26f996..6ef3674c0763 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2713,7 +2713,7 @@ EXPORT_SYMBOL(generic_file_write_iter); * page is known to the local caching routines. * * The @gfp_mask argument specifies whether I/O may be performed to release - * this page (__GFP_IO), and whether the call may block (__GFP_WAIT & __GFP_FS). + * this page (__GFP_IO), and whether the call may block (__GFP_RECLAIM & __GFP_FS). * */ int try_to_release_page(struct page *page, gfp_t gfp_mask) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index f5c08b46fef8..9812d4618651 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -786,7 +786,7 @@ static int __do_huge_pmd_anonymous_page(struct mm_struct *mm, static inline gfp_t alloc_hugepage_gfpmask(int defrag, gfp_t extra_gfp) { - return (GFP_TRANSHUGE & ~(defrag ? 0 : __GFP_WAIT)) | extra_gfp; + return (GFP_TRANSHUGE & ~(defrag ? 0 : __GFP_RECLAIM)) | extra_gfp; } /* Caller must hold page table lock. */ diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 05374f09339c..a5470674a477 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -2120,7 +2120,7 @@ done_restock: /* * If the hierarchy is above the normal consumption range, schedule * reclaim on returning to userland. We can perform reclaim here - * if __GFP_WAIT but let's always punt for simplicity and so that + * if __GFP_RECLAIM but let's always punt for simplicity and so that * GFP_KERNEL can consistently be used during reclaim. @memcg is * not recorded as it most likely matches current's and won't * change in the meantime. As high limit is checked again before diff --git a/mm/migrate.c b/mm/migrate.c index e60379eb23f8..7890d0bb5e23 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1752,7 +1752,7 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm, goto out_dropref; new_page = alloc_pages_node(node, - (GFP_TRANSHUGE | __GFP_THISNODE) & ~__GFP_WAIT, + (GFP_TRANSHUGE | __GFP_THISNODE) & ~__GFP_RECLAIM, HPAGE_PMD_ORDER); if (!new_page) goto out_fail; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 70461f3e3378..1b373096b990 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -2160,11 +2160,11 @@ static struct { struct fault_attr attr; bool ignore_gfp_highmem; - bool ignore_gfp_wait; + bool ignore_gfp_reclaim; u32 min_order; } fail_page_alloc = { .attr = FAULT_ATTR_INITIALIZER, - .ignore_gfp_wait = true, + .ignore_gfp_reclaim = true, .ignore_gfp_highmem = true, .min_order = 1, }; @@ -2183,7 +2183,8 @@ static bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order) return false; if (fail_page_alloc.ignore_gfp_highmem && (gfp_mask & __GFP_HIGHMEM)) return false; - if (fail_page_alloc.ignore_gfp_wait && (gfp_mask & __GFP_DIRECT_RECLAIM)) + if (fail_page_alloc.ignore_gfp_reclaim && + (gfp_mask & __GFP_DIRECT_RECLAIM)) return false; return should_fail(&fail_page_alloc.attr, 1 << order); @@ -2202,7 +2203,7 @@ static int __init fail_page_alloc_debugfs(void) return PTR_ERR(dir); if (!debugfs_create_bool("ignore-gfp-wait", mode, dir, - &fail_page_alloc.ignore_gfp_wait)) + &fail_page_alloc.ignore_gfp_reclaim)) goto fail; if (!debugfs_create_bool("ignore-gfp-highmem", mode, dir, &fail_page_alloc.ignore_gfp_highmem)) diff --git a/security/integrity/ima/ima_crypto.c b/security/integrity/ima/ima_crypto.c index e24121afb2f2..6eb62936c672 100644 --- a/security/integrity/ima/ima_crypto.c +++ b/security/integrity/ima/ima_crypto.c @@ -126,7 +126,7 @@ static void *ima_alloc_pages(loff_t max_size, size_t *allocated_size, { void *ptr; int order = ima_maxorder; - gfp_t gfp_mask = __GFP_WAIT | __GFP_NOWARN | __GFP_NORETRY; + gfp_t gfp_mask = __GFP_RECLAIM | __GFP_NOWARN | __GFP_NORETRY; if (order) order = min(get_order(max_size), order); -- cgit v1.2.3-70-g09d2 From c62d25556be6c965dc14288e796a576e8e39a7e9 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Fri, 6 Nov 2015 16:28:49 -0800 Subject: mm, fs: introduce mapping_gfp_constraint() There are many places which use mapping_gfp_mask to restrict a more generic gfp mask which would be used for allocations which are not directly related to the page cache but they are performed in the same context. Let's introduce a helper function which makes the restriction explicit and easier to track. This patch doesn't introduce any functional changes. [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Michal Hocko Suggested-by: Andrew Morton Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/gpu/drm/drm_gem.c | 2 +- drivers/gpu/drm/i915/i915_gem.c | 3 +-- fs/btrfs/compression.c | 7 +++---- fs/btrfs/ctree.h | 2 +- fs/btrfs/free-space-cache.c | 4 ++-- fs/buffer.c | 2 +- fs/ceph/addr.c | 7 ++++--- fs/cifs/file.c | 2 +- fs/ext4/inode.c | 2 +- fs/ext4/readpage.c | 2 +- fs/logfs/segment.c | 2 +- fs/mpage.c | 4 ++-- fs/namei.c | 2 +- fs/nilfs2/inode.c | 4 ++-- fs/ntfs/file.c | 4 ++-- fs/splice.c | 2 +- include/linux/pagemap.h | 7 +++++++ mm/filemap.c | 4 ++-- mm/readahead.c | 4 ++-- 19 files changed, 36 insertions(+), 30 deletions(-) (limited to 'fs') diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c index 3c2d4abd71c5..1d47d2e9487c 100644 --- a/drivers/gpu/drm/drm_gem.c +++ b/drivers/gpu/drm/drm_gem.c @@ -491,7 +491,7 @@ struct page **drm_gem_get_pages(struct drm_gem_object *obj) * __GFP_DMA32 to be set in mapping_gfp_mask(inode->i_mapping) * so shmem can relocate pages during swapin if required. */ - BUG_ON((mapping_gfp_mask(mapping) & __GFP_DMA32) && + BUG_ON(mapping_gfp_constraint(mapping, __GFP_DMA32) && (page_to_pfn(p) >= 0x00100000UL)); } diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 7e505d4be7c0..399aab265db3 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -2214,9 +2214,8 @@ i915_gem_object_get_pages_gtt(struct drm_i915_gem_object *obj) * Fail silently without starting the shrinker */ mapping = file_inode(obj->base.filp)->i_mapping; - gfp = mapping_gfp_mask(mapping); + gfp = mapping_gfp_constraint(mapping, ~(__GFP_IO | __GFP_RECLAIM)); gfp |= __GFP_NORETRY | __GFP_NOWARN; - gfp &= ~(__GFP_IO | __GFP_RECLAIM); sg = st->sgl; st->nents = 0; for (i = 0; i < page_count; i++) { diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c index 57ee8ca29b06..36dfeff2c1f4 100644 --- a/fs/btrfs/compression.c +++ b/fs/btrfs/compression.c @@ -482,13 +482,12 @@ static noinline int add_ra_bio_pages(struct inode *inode, goto next; } - page = __page_cache_alloc(mapping_gfp_mask(mapping) & - ~__GFP_FS); + page = __page_cache_alloc(mapping_gfp_constraint(mapping, + ~__GFP_FS)); if (!page) break; - if (add_to_page_cache_lru(page, mapping, pg_index, - GFP_NOFS)) { + if (add_to_page_cache_lru(page, mapping, pg_index, GFP_NOFS)) { page_cache_release(page); goto next; } diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 938efe33be80..eb90f0f1a124 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -3316,7 +3316,7 @@ static inline bool btrfs_mixed_space_info(struct btrfs_space_info *space_info) static inline gfp_t btrfs_alloc_write_mask(struct address_space *mapping) { - return mapping_gfp_mask(mapping) & ~__GFP_FS; + return mapping_gfp_constraint(mapping, ~__GFP_FS); } /* extent-tree.c */ diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index abe3a66bd3ba..ed05da1b977e 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -85,8 +85,8 @@ static struct inode *__lookup_free_space_inode(struct btrfs_root *root, } mapping_set_gfp_mask(inode->i_mapping, - mapping_gfp_mask(inode->i_mapping) & - ~(__GFP_FS | __GFP_HIGHMEM)); + mapping_gfp_constraint(inode->i_mapping, + ~(__GFP_FS | __GFP_HIGHMEM))); return inode; } diff --git a/fs/buffer.c b/fs/buffer.c index 82283abb2795..51aff0296ce2 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -999,7 +999,7 @@ grow_dev_page(struct block_device *bdev, sector_t block, int ret = 0; /* Will call free_more_memory() */ gfp_t gfp_mask; - gfp_mask = (mapping_gfp_mask(inode->i_mapping) & ~__GFP_FS) | gfp; + gfp_mask = mapping_gfp_constraint(inode->i_mapping, ~__GFP_FS) | gfp; /* * XXX: __getblk_slow() can not really deal with failure and diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 9d23e788d1df..b7d218a168fb 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -1283,8 +1283,8 @@ static int ceph_filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf) int ret1; struct address_space *mapping = inode->i_mapping; struct page *page = find_or_create_page(mapping, 0, - mapping_gfp_mask(mapping) & - ~__GFP_FS); + mapping_gfp_constraint(mapping, + ~__GFP_FS)); if (!page) { ret = VM_FAULT_OOM; goto out; @@ -1428,7 +1428,8 @@ void ceph_fill_inline_data(struct inode *inode, struct page *locked_page, if (i_size_read(inode) == 0) return; page = find_or_create_page(mapping, 0, - mapping_gfp_mask(mapping) & ~__GFP_FS); + mapping_gfp_constraint(mapping, + ~__GFP_FS)); if (!page) return; if (PageUptodate(page)) { diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 47c5c97e2dd3..0068e82217c3 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -3380,7 +3380,7 @@ readpages_get_pages(struct address_space *mapping, struct list_head *page_list, struct page *page, *tpage; unsigned int expected_index; int rc; - gfp_t gfp = GFP_KERNEL & mapping_gfp_mask(mapping); + gfp_t gfp = mapping_gfp_constraint(mapping, GFP_KERNEL); INIT_LIST_HEAD(tmplist); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 612fbcf76b5c..60aaecd5598b 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -3344,7 +3344,7 @@ static int __ext4_block_zero_page_range(handle_t *handle, int err = 0; page = find_or_create_page(mapping, from >> PAGE_CACHE_SHIFT, - mapping_gfp_mask(mapping) & ~__GFP_FS); + mapping_gfp_constraint(mapping, ~__GFP_FS)); if (!page) return -ENOMEM; diff --git a/fs/ext4/readpage.c b/fs/ext4/readpage.c index 560af0437704..1061611ae14d 100644 --- a/fs/ext4/readpage.c +++ b/fs/ext4/readpage.c @@ -166,7 +166,7 @@ int ext4_mpage_readpages(struct address_space *mapping, page = list_entry(pages->prev, struct page, lru); list_del(&page->lru); if (add_to_page_cache_lru(page, mapping, page->index, - GFP_KERNEL & mapping_gfp_mask(mapping))) + mapping_gfp_constraint(mapping, GFP_KERNEL))) goto next_page; } diff --git a/fs/logfs/segment.c b/fs/logfs/segment.c index 7f9b096d8d57..6de0fbfc6c00 100644 --- a/fs/logfs/segment.c +++ b/fs/logfs/segment.c @@ -57,7 +57,7 @@ static struct page *get_mapping_page(struct super_block *sb, pgoff_t index, filler_t *filler = super->s_devops->readpage; struct page *page; - BUG_ON(mapping_gfp_mask(mapping) & __GFP_FS); + BUG_ON(mapping_gfp_constraint(mapping, __GFP_FS)); if (use_filler) page = read_cache_page(mapping, index, filler, sb); else { diff --git a/fs/mpage.c b/fs/mpage.c index 09abba7653aa..1480d3a18037 100644 --- a/fs/mpage.c +++ b/fs/mpage.c @@ -361,7 +361,7 @@ mpage_readpages(struct address_space *mapping, struct list_head *pages, sector_t last_block_in_bio = 0; struct buffer_head map_bh; unsigned long first_logical_block = 0; - gfp_t gfp = GFP_KERNEL & mapping_gfp_mask(mapping); + gfp_t gfp = mapping_gfp_constraint(mapping, GFP_KERNEL); map_bh.b_state = 0; map_bh.b_size = 0; @@ -397,7 +397,7 @@ int mpage_readpage(struct page *page, get_block_t get_block) sector_t last_block_in_bio = 0; struct buffer_head map_bh; unsigned long first_logical_block = 0; - gfp_t gfp = GFP_KERNEL & mapping_gfp_mask(page->mapping); + gfp_t gfp = mapping_gfp_constraint(page->mapping, GFP_KERNEL); map_bh.b_state = 0; map_bh.b_size = 0; diff --git a/fs/namei.c b/fs/namei.c index 0d3340b32e14..3c18970a8899 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -4604,7 +4604,7 @@ EXPORT_SYMBOL(__page_symlink); int page_symlink(struct inode *inode, const char *symname, int len) { return __page_symlink(inode, symname, len, - !(mapping_gfp_mask(inode->i_mapping) & __GFP_FS)); + !mapping_gfp_constraint(inode->i_mapping, __GFP_FS)); } EXPORT_SYMBOL(page_symlink); diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index 4a73d6dffabf..ac2f64943ff4 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -356,7 +356,7 @@ struct inode *nilfs_new_inode(struct inode *dir, umode_t mode) goto failed; mapping_set_gfp_mask(inode->i_mapping, - mapping_gfp_mask(inode->i_mapping) & ~__GFP_FS); + mapping_gfp_constraint(inode->i_mapping, ~__GFP_FS)); root = NILFS_I(dir)->i_root; ii = NILFS_I(inode); @@ -522,7 +522,7 @@ static int __nilfs_read_inode(struct super_block *sb, up_read(&NILFS_MDT(nilfs->ns_dat)->mi_sem); nilfs_set_inode_flags(inode); mapping_set_gfp_mask(inode->i_mapping, - mapping_gfp_mask(inode->i_mapping) & ~__GFP_FS); + mapping_gfp_constraint(inode->i_mapping, ~__GFP_FS)); return 0; failed_unmap: diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c index 262561fea923..9d383e5eff0e 100644 --- a/fs/ntfs/file.c +++ b/fs/ntfs/file.c @@ -525,8 +525,8 @@ static inline int __ntfs_grab_cache_pages(struct address_space *mapping, } } err = add_to_page_cache_lru(*cached_page, mapping, - index, - GFP_KERNEL & mapping_gfp_mask(mapping)); + index, + mapping_gfp_constraint(mapping, GFP_KERNEL)); if (unlikely(err)) { if (err == -EEXIST) continue; diff --git a/fs/splice.c b/fs/splice.c index 5fc1e50a7f30..801c21cd77fe 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -360,7 +360,7 @@ __generic_file_splice_read(struct file *in, loff_t *ppos, break; error = add_to_page_cache_lru(page, mapping, index, - GFP_KERNEL & mapping_gfp_mask(mapping)); + mapping_gfp_constraint(mapping, GFP_KERNEL)); if (unlikely(error)) { page_cache_release(page); if (error == -EEXIST) diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index a6c78e00ea96..26eabf5ec718 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -69,6 +69,13 @@ static inline gfp_t mapping_gfp_mask(struct address_space * mapping) return (__force gfp_t)mapping->flags & __GFP_BITS_MASK; } +/* Restricts the given gfp_mask to what the mapping allows. */ +static inline gfp_t mapping_gfp_constraint(struct address_space *mapping, + gfp_t gfp_mask) +{ + return mapping_gfp_mask(mapping) & gfp_mask; +} + /* * This is non-atomic. Only to be used before the mapping is activated. * Probably needs a barrier... diff --git a/mm/filemap.c b/mm/filemap.c index 6ef3674c0763..1bb007624b53 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1722,7 +1722,7 @@ no_cached_page: goto out; } error = add_to_page_cache_lru(page, mapping, index, - GFP_KERNEL & mapping_gfp_mask(mapping)); + mapping_gfp_constraint(mapping, GFP_KERNEL)); if (error) { page_cache_release(page); if (error == -EEXIST) { @@ -1824,7 +1824,7 @@ static int page_cache_read(struct file *file, pgoff_t offset) return -ENOMEM; ret = add_to_page_cache_lru(page, mapping, offset, - GFP_KERNEL & mapping_gfp_mask(mapping)); + mapping_gfp_constraint(mapping, GFP_KERNEL)); if (ret == 0) ret = mapping->a_ops->readpage(file, page); else if (ret == -EEXIST) diff --git a/mm/readahead.c b/mm/readahead.c index 998ad592f408..ba22d7fe0afb 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -90,7 +90,7 @@ int read_cache_pages(struct address_space *mapping, struct list_head *pages, page = list_to_page(pages); list_del(&page->lru); if (add_to_page_cache_lru(page, mapping, page->index, - GFP_KERNEL & mapping_gfp_mask(mapping))) { + mapping_gfp_constraint(mapping, GFP_KERNEL))) { read_cache_pages_invalidate_page(mapping, page); continue; } @@ -128,7 +128,7 @@ static int read_pages(struct address_space *mapping, struct file *filp, struct page *page = list_to_page(pages); list_del(&page->lru); if (!add_to_page_cache_lru(page, mapping, page->index, - GFP_KERNEL & mapping_gfp_mask(mapping))) { + mapping_gfp_constraint(mapping, GFP_KERNEL))) { mapping->a_ops->readpage(filp, page); } page_cache_release(page); -- cgit v1.2.3-70-g09d2 From 23d0127096cb91cb6d354bdc71bd88a7bae3a1d5 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Fri, 6 Nov 2015 16:28:55 -0800 Subject: fs/sync.c: make sync_file_range(2) use WB_SYNC_NONE writeback sync_file_range(2) is documented to issue writeback only for pages that are not currently being written. After all the system call has been created for userspace to be able to issue background writeout and so waiting for in-flight IO is undesirable there. However commit ee53a891f474 ("mm: do_sync_mapping_range integrity fix") switched do_sync_mapping_range() and thus sync_file_range() to issue writeback in WB_SYNC_ALL mode since do_sync_mapping_range() was used by other code relying on WB_SYNC_ALL semantics. These days do_sync_mapping_range() went away and we can switch sync_file_range(2) back to issuing WB_SYNC_NONE writeback. That should help PostgreSQL avoid large latency spikes when flushing data in the background. Andres measured a 20% increase in transactions per second on an SSD disk. Signed-off-by: Jan Kara Reported-by: Andres Freund Tested-By: Andres Freund Cc: Al Viro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/sync.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/sync.c b/fs/sync.c index 4ec430ae2b0d..dd5d1711c7ac 100644 --- a/fs/sync.c +++ b/fs/sync.c @@ -348,7 +348,8 @@ SYSCALL_DEFINE4(sync_file_range, int, fd, loff_t, offset, loff_t, nbytes, } if (flags & SYNC_FILE_RANGE_WRITE) { - ret = filemap_fdatawrite_range(mapping, offset, endbyte); + ret = __filemap_fdatawrite_range(mapping, offset, endbyte, + WB_SYNC_NONE); if (ret < 0) goto out_put; } -- cgit v1.2.3-70-g09d2 From 3a49f3d2a10dfb27411d321900197a3d6c52405b Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 6 Nov 2015 16:30:03 -0800 Subject: fs/proc/array.c: set overflow flag in case of error For now in task_name() we ignore the return code of string_escape_str() call. This is not good if buffer suddenly becomes not big enough. Do the proper error handling there. Signed-off-by: Andy Shevchenko Cc: Alexander Viro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/array.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'fs') diff --git a/fs/proc/array.c b/fs/proc/array.c index eed2050db9be..d73291f5f0fc 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -91,18 +91,18 @@ static inline void task_name(struct seq_file *m, struct task_struct *p) { char *buf; + size_t size; char tcomm[sizeof(p->comm)]; + int ret; get_task_comm(tcomm, p); seq_puts(m, "Name:\t"); - buf = m->buf + m->count; - /* Ignore error for now */ - buf += string_escape_str(tcomm, buf, m->size - m->count, - ESCAPE_SPACE | ESCAPE_SPECIAL, "\n\\"); + size = seq_get_buf(m, &buf); + ret = string_escape_str(tcomm, buf, size, ESCAPE_SPACE | ESCAPE_SPECIAL, "\n\\"); + seq_commit(m, ret < size ? ret : -1); - m->count = buf - m->buf; seq_putc(m, '\n'); } -- cgit v1.2.3-70-g09d2 From 54708d2858e79a2bdda10bf8a20c80eb96c20613 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Fri, 6 Nov 2015 16:30:06 -0800 Subject: proc: actually make proc_fd_permission() thread-friendly The commit 96d0df79f264 ("proc: make proc_fd_permission() thread-friendly") fixed the access to /proc/self/fd from sub-threads, but introduced another problem: a sub-thread can't access /proc//fd/ or /proc/thread-self/fd if generic_permission() fails. Change proc_fd_permission() to check same_thread_group(pid_task(), current). Fixes: 96d0df79f264 ("proc: make proc_fd_permission() thread-friendly") Reported-by: "Jin, Yihua" Signed-off-by: Oleg Nesterov Cc: "Eric W. Biederman" Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/fd.c | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) (limited to 'fs') diff --git a/fs/proc/fd.c b/fs/proc/fd.c index 6e5fcd00733e..3c2a915c695a 100644 --- a/fs/proc/fd.c +++ b/fs/proc/fd.c @@ -291,11 +291,19 @@ static struct dentry *proc_lookupfd(struct inode *dir, struct dentry *dentry, */ int proc_fd_permission(struct inode *inode, int mask) { - int rv = generic_permission(inode, mask); + struct task_struct *p; + int rv; + + rv = generic_permission(inode, mask); if (rv == 0) - return 0; - if (task_tgid(current) == proc_pid(inode)) + return rv; + + rcu_read_lock(); + p = pid_task(proc_pid(inode), PIDTYPE_PID); + if (p && same_thread_group(p, current)) rv = 0; + rcu_read_unlock(); + return rv; } -- cgit v1.2.3-70-g09d2 From eac44a5e07be41a153e52c35c4d7dc0fec23adb3 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Fri, 6 Nov 2015 16:30:12 -0800 Subject: fs/jffs2/wbuf.c: remove stray semicolon Reported-by: Wu Fengguang Cc: Sasha Levin Cc: David Woodhouse Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/jffs2/wbuf.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/jffs2/wbuf.c b/fs/jffs2/wbuf.c index 09ed55190ee2..955da626ba6b 100644 --- a/fs/jffs2/wbuf.c +++ b/fs/jffs2/wbuf.c @@ -1264,7 +1264,7 @@ int jffs2_dataflash_setup(struct jffs2_sb_info *c) { if ((c->flash_size % c->sector_size) != 0) { c->flash_size = (c->flash_size / c->sector_size) * c->sector_size; pr_warn("flash size adjusted to %dKiB\n", c->flash_size); - }; + } c->wbuf_ofs = 0xFFFFFFFF; c->wbuf = kmalloc(c->wbuf_pagesize, GFP_KERNEL); -- cgit v1.2.3-70-g09d2 From da80a39fc962ceca085ddfb7d63e00309b305f17 Mon Sep 17 00:00:00 2001 From: Julia Lawall Date: Fri, 6 Nov 2015 16:31:40 -0800 Subject: nilfs2: drop null test before destroy functions Remove unneeded NULL test. The semantic patch that makes this change is as follows: (http://coccinelle.lip6.fr/) // @@ expression x; @@ -if (x != NULL) \(kmem_cache_destroy\|mempool_destroy\|dma_pool_destroy\)(x); // Signed-off-by: Julia Lawall Signed-off-by: Ryusuke Konishi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/nilfs2/super.c | 12 ++++-------- 1 file changed, 4 insertions(+), 8 deletions(-) (limited to 'fs') diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c index f47585bfeb01..c69455a543bc 100644 --- a/fs/nilfs2/super.c +++ b/fs/nilfs2/super.c @@ -1405,14 +1405,10 @@ static void nilfs_destroy_cachep(void) */ rcu_barrier(); - if (nilfs_inode_cachep) - kmem_cache_destroy(nilfs_inode_cachep); - if (nilfs_transaction_cachep) - kmem_cache_destroy(nilfs_transaction_cachep); - if (nilfs_segbuf_cachep) - kmem_cache_destroy(nilfs_segbuf_cachep); - if (nilfs_btree_path_cache) - kmem_cache_destroy(nilfs_btree_path_cache); + kmem_cache_destroy(nilfs_inode_cachep); + kmem_cache_destroy(nilfs_transaction_cachep); + kmem_cache_destroy(nilfs_segbuf_cachep); + kmem_cache_destroy(nilfs_btree_path_cache); } static int __init nilfs_init_cachep(void) -- cgit v1.2.3-70-g09d2 From b7bed712d090c340b97d455c5cb62d151e004503 Mon Sep 17 00:00:00 2001 From: Ryusuke Konishi Date: Fri, 6 Nov 2015 16:31:43 -0800 Subject: nilfs2: use nilfs_warning() in allocator implementation This uses nilfs_warning() to replace "printk(KERN_WARNING ...);" in the bitmap based allocator implementation of nilfs2. The warning messages are modified to include the device name and the inode number in each message. This makes it clear which metadata file of which device has output warnings such as "entry number xxxx already freed". Signed-off-by: Ryusuke Konishi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/nilfs2/alloc.c | 20 ++++++++++++-------- 1 file changed, 12 insertions(+), 8 deletions(-) (limited to 'fs') diff --git a/fs/nilfs2/alloc.c b/fs/nilfs2/alloc.c index 8df0f3b7839b..afe983643fdf 100644 --- a/fs/nilfs2/alloc.c +++ b/fs/nilfs2/alloc.c @@ -583,8 +583,10 @@ void nilfs_palloc_commit_free_entry(struct inode *inode, if (!nilfs_clear_bit_atomic(nilfs_mdt_bgl_lock(inode, group), group_offset, bitmap)) - printk(KERN_WARNING "%s: entry number %llu already freed\n", - __func__, (unsigned long long)req->pr_entry_nr); + nilfs_warning(inode->i_sb, __func__, + "entry number %llu already freed: ino=%lu\n", + (unsigned long long)req->pr_entry_nr, + (unsigned long)inode->i_ino); else nilfs_palloc_group_desc_add_entries(inode, group, desc, 1); @@ -620,8 +622,10 @@ void nilfs_palloc_abort_alloc_entry(struct inode *inode, bitmap = bitmap_kaddr + bh_offset(req->pr_bitmap_bh); if (!nilfs_clear_bit_atomic(nilfs_mdt_bgl_lock(inode, group), group_offset, bitmap)) - printk(KERN_WARNING "%s: entry number %llu already freed\n", - __func__, (unsigned long long)req->pr_entry_nr); + nilfs_warning(inode->i_sb, __func__, + "entry number %llu already freed: ino=%lu\n", + (unsigned long long)req->pr_entry_nr, + (unsigned long)inode->i_ino); else nilfs_palloc_group_desc_add_entries(inode, group, desc, 1); @@ -734,10 +738,10 @@ int nilfs_palloc_freev(struct inode *inode, __u64 *entry_nrs, size_t nitems) if (!nilfs_clear_bit_atomic( nilfs_mdt_bgl_lock(inode, group), group_offset, bitmap)) { - printk(KERN_WARNING - "%s: entry number %llu already freed\n", - __func__, - (unsigned long long)entry_nrs[j]); + nilfs_warning(inode->i_sb, __func__, + "entry number %llu already freed: ino=%lu\n", + (unsigned long long)entry_nrs[j], + (unsigned long)inode->i_ino); } else { n++; } -- cgit v1.2.3-70-g09d2 From 4e9e63a671fbe13f448fb2e69dfdbb6c2a008368 Mon Sep 17 00:00:00 2001 From: Ryusuke Konishi Date: Fri, 6 Nov 2015 16:31:45 -0800 Subject: nilfs2: do not call nilfs_mdt_bgl_lock() needlessly In the bitmap based allocator implementation, nilfs_mdt_bgl_lock() helper is frequently used to get a spinlock protecting a target block group. This reduces its usage and simplifies arguments of some related functions by directly passing a pointer to the spinlock. Signed-off-by: Ryusuke Konishi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/nilfs2/alloc.c | 84 ++++++++++++++++++++++++++----------------------------- 1 file changed, 40 insertions(+), 44 deletions(-) (limited to 'fs') diff --git a/fs/nilfs2/alloc.c b/fs/nilfs2/alloc.c index afe983643fdf..ff0d62ce165b 100644 --- a/fs/nilfs2/alloc.c +++ b/fs/nilfs2/alloc.c @@ -133,38 +133,34 @@ nilfs_palloc_bitmap_blkoff(const struct inode *inode, unsigned long group) /** * nilfs_palloc_group_desc_nfrees - get the number of free entries in a group - * @inode: inode of metadata file using this allocator - * @group: group number * @desc: pointer to descriptor structure for the group + * @lock: spin lock protecting @desc */ static unsigned long -nilfs_palloc_group_desc_nfrees(struct inode *inode, unsigned long group, - const struct nilfs_palloc_group_desc *desc) +nilfs_palloc_group_desc_nfrees(const struct nilfs_palloc_group_desc *desc, + spinlock_t *lock) { unsigned long nfree; - spin_lock(nilfs_mdt_bgl_lock(inode, group)); + spin_lock(lock); nfree = le32_to_cpu(desc->pg_nfrees); - spin_unlock(nilfs_mdt_bgl_lock(inode, group)); + spin_unlock(lock); return nfree; } /** * nilfs_palloc_group_desc_add_entries - adjust count of free entries - * @inode: inode of metadata file using this allocator - * @group: group number * @desc: pointer to descriptor structure for the group + * @lock: spin lock protecting @desc * @n: delta to be added */ static void -nilfs_palloc_group_desc_add_entries(struct inode *inode, - unsigned long group, - struct nilfs_palloc_group_desc *desc, - u32 n) +nilfs_palloc_group_desc_add_entries(struct nilfs_palloc_group_desc *desc, + spinlock_t *lock, u32 n) { - spin_lock(nilfs_mdt_bgl_lock(inode, group)); + spin_lock(lock); le32_add_cpu(&desc->pg_nfrees, n); - spin_unlock(nilfs_mdt_bgl_lock(inode, group)); + spin_unlock(lock); } /** @@ -332,17 +328,15 @@ void *nilfs_palloc_block_get_entry(const struct inode *inode, __u64 nr, /** * nilfs_palloc_find_available_slot - find available slot in a group - * @inode: inode of metadata file using this allocator - * @group: group number - * @target: offset number of an entry in the group (start point) * @bitmap: bitmap of the group + * @target: offset number of an entry in the group (start point) * @bsize: size in bits + * @lock: spin lock protecting @bitmap */ -static int nilfs_palloc_find_available_slot(struct inode *inode, - unsigned long group, +static int nilfs_palloc_find_available_slot(unsigned char *bitmap, unsigned long target, - unsigned char *bitmap, - int bsize) + int bsize, + spinlock_t *lock) { int curr, pos, end, i; @@ -351,12 +345,11 @@ static int nilfs_palloc_find_available_slot(struct inode *inode, if (end > bsize) end = bsize; pos = nilfs_find_next_zero_bit(bitmap, end, target); - if (pos < end && - !nilfs_set_bit_atomic( - nilfs_mdt_bgl_lock(inode, group), pos, bitmap)) + if (pos < end && !nilfs_set_bit_atomic(lock, pos, bitmap)) return pos; - } else + } else { end = 0; + } for (i = 0, curr = end; i < bsize; @@ -370,10 +363,8 @@ static int nilfs_palloc_find_available_slot(struct inode *inode, if (end > bsize) end = bsize; pos = nilfs_find_next_zero_bit(bitmap, end, curr); - if ((pos < end) && - !nilfs_set_bit_atomic( - nilfs_mdt_bgl_lock(inode, group), pos, - bitmap)) + if (pos < end && + !nilfs_set_bit_atomic(lock, pos, bitmap)) return pos; } } @@ -477,6 +468,7 @@ int nilfs_palloc_prepare_alloc_entry(struct inode *inode, unsigned long group_offset, maxgroup_offset; unsigned long n, entries_per_group, groups_per_desc_block; unsigned long i, j; + spinlock_t *lock; int pos, ret; ngroups = nilfs_palloc_groups_count(inode); @@ -501,8 +493,8 @@ int nilfs_palloc_prepare_alloc_entry(struct inode *inode, n = nilfs_palloc_rest_groups_in_desc_block(inode, group, maxgroup); for (j = 0; j < n; j++, desc++, group++) { - if (nilfs_palloc_group_desc_nfrees(inode, group, desc) - > 0) { + lock = nilfs_mdt_bgl_lock(inode, group); + if (nilfs_palloc_group_desc_nfrees(desc, lock) > 0) { ret = nilfs_palloc_get_bitmap_block( inode, group, 1, &bitmap_bh); if (ret < 0) @@ -510,12 +502,12 @@ int nilfs_palloc_prepare_alloc_entry(struct inode *inode, bitmap_kaddr = kmap(bitmap_bh->b_page); bitmap = bitmap_kaddr + bh_offset(bitmap_bh); pos = nilfs_palloc_find_available_slot( - inode, group, group_offset, bitmap, - entries_per_group); + bitmap, group_offset, + entries_per_group, lock); if (pos >= 0) { /* found a free entry */ nilfs_palloc_group_desc_add_entries( - inode, group, desc, -1); + desc, lock, -1); req->pr_entry_nr = entries_per_group * group + pos; kunmap(desc_bh->b_page); @@ -573,6 +565,7 @@ void nilfs_palloc_commit_free_entry(struct inode *inode, unsigned long group, group_offset; unsigned char *bitmap; void *desc_kaddr, *bitmap_kaddr; + spinlock_t *lock; group = nilfs_palloc_group(inode, req->pr_entry_nr, &group_offset); desc_kaddr = kmap(req->pr_desc_bh->b_page); @@ -580,15 +573,15 @@ void nilfs_palloc_commit_free_entry(struct inode *inode, req->pr_desc_bh, desc_kaddr); bitmap_kaddr = kmap(req->pr_bitmap_bh->b_page); bitmap = bitmap_kaddr + bh_offset(req->pr_bitmap_bh); + lock = nilfs_mdt_bgl_lock(inode, group); - if (!nilfs_clear_bit_atomic(nilfs_mdt_bgl_lock(inode, group), - group_offset, bitmap)) + if (!nilfs_clear_bit_atomic(lock, group_offset, bitmap)) nilfs_warning(inode->i_sb, __func__, "entry number %llu already freed: ino=%lu\n", (unsigned long long)req->pr_entry_nr, (unsigned long)inode->i_ino); else - nilfs_palloc_group_desc_add_entries(inode, group, desc, 1); + nilfs_palloc_group_desc_add_entries(desc, lock, 1); kunmap(req->pr_bitmap_bh->b_page); kunmap(req->pr_desc_bh->b_page); @@ -613,6 +606,7 @@ void nilfs_palloc_abort_alloc_entry(struct inode *inode, void *desc_kaddr, *bitmap_kaddr; unsigned char *bitmap; unsigned long group, group_offset; + spinlock_t *lock; group = nilfs_palloc_group(inode, req->pr_entry_nr, &group_offset); desc_kaddr = kmap(req->pr_desc_bh->b_page); @@ -620,14 +614,15 @@ void nilfs_palloc_abort_alloc_entry(struct inode *inode, req->pr_desc_bh, desc_kaddr); bitmap_kaddr = kmap(req->pr_bitmap_bh->b_page); bitmap = bitmap_kaddr + bh_offset(req->pr_bitmap_bh); - if (!nilfs_clear_bit_atomic(nilfs_mdt_bgl_lock(inode, group), - group_offset, bitmap)) + lock = nilfs_mdt_bgl_lock(inode, group); + + if (!nilfs_clear_bit_atomic(lock, group_offset, bitmap)) nilfs_warning(inode->i_sb, __func__, "entry number %llu already freed: ino=%lu\n", (unsigned long long)req->pr_entry_nr, (unsigned long)inode->i_ino); else - nilfs_palloc_group_desc_add_entries(inode, group, desc, 1); + nilfs_palloc_group_desc_add_entries(desc, lock, 1); kunmap(req->pr_bitmap_bh->b_page); kunmap(req->pr_desc_bh->b_page); @@ -712,6 +707,7 @@ int nilfs_palloc_freev(struct inode *inode, __u64 *entry_nrs, size_t nitems) unsigned char *bitmap; void *desc_kaddr, *bitmap_kaddr; unsigned long group, group_offset; + spinlock_t *lock; int i, j, n, ret; for (i = 0; i < nitems; i = j) { @@ -730,14 +726,14 @@ int nilfs_palloc_freev(struct inode *inode, __u64 *entry_nrs, size_t nitems) inode, group, desc_bh, desc_kaddr); bitmap_kaddr = kmap(bitmap_bh->b_page); bitmap = bitmap_kaddr + bh_offset(bitmap_bh); + lock = nilfs_mdt_bgl_lock(inode, group); for (j = i, n = 0; (j < nitems) && nilfs_palloc_group_is_in(inode, group, entry_nrs[j]); j++) { nilfs_palloc_group(inode, entry_nrs[j], &group_offset); - if (!nilfs_clear_bit_atomic( - nilfs_mdt_bgl_lock(inode, group), - group_offset, bitmap)) { + if (!nilfs_clear_bit_atomic(lock, group_offset, + bitmap)) { nilfs_warning(inode->i_sb, __func__, "entry number %llu already freed: ino=%lu\n", (unsigned long long)entry_nrs[j], @@ -746,7 +742,7 @@ int nilfs_palloc_freev(struct inode *inode, __u64 *entry_nrs, size_t nitems) n++; } } - nilfs_palloc_group_desc_add_entries(inode, group, desc, n); + nilfs_palloc_group_desc_add_entries(desc, lock, n); kunmap(bitmap_bh->b_page); kunmap(desc_bh->b_page); -- cgit v1.2.3-70-g09d2 From 18c41b37f0f16a0d6e5b1a73563d0c1333e7ef70 Mon Sep 17 00:00:00 2001 From: Ryusuke Konishi Date: Fri, 6 Nov 2015 16:31:48 -0800 Subject: nilfs2: refactor nilfs_palloc_find_available_slot() The current implementation of nilfs_palloc_find_available_slot() function is overkill. The underlying bit search routine is well optimized, so this uses it more simply in nilfs_palloc_find_available_slot(). Signed-off-by: Ryusuke Konishi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/nilfs2/alloc.c | 48 +++++++++++++++++++++--------------------------- 1 file changed, 21 insertions(+), 27 deletions(-) (limited to 'fs') diff --git a/fs/nilfs2/alloc.c b/fs/nilfs2/alloc.c index ff0d62ce165b..b15daf871f99 100644 --- a/fs/nilfs2/alloc.c +++ b/fs/nilfs2/alloc.c @@ -335,39 +335,33 @@ void *nilfs_palloc_block_get_entry(const struct inode *inode, __u64 nr, */ static int nilfs_palloc_find_available_slot(unsigned char *bitmap, unsigned long target, - int bsize, + unsigned bsize, spinlock_t *lock) { - int curr, pos, end, i; + int pos, end = bsize; - if (target > 0) { - end = (target + BITS_PER_LONG - 1) & ~(BITS_PER_LONG - 1); - if (end > bsize) - end = bsize; - pos = nilfs_find_next_zero_bit(bitmap, end, target); - if (pos < end && !nilfs_set_bit_atomic(lock, pos, bitmap)) - return pos; - } else { - end = 0; + if (likely(target < bsize)) { + pos = target; + do { + pos = nilfs_find_next_zero_bit(bitmap, end, pos); + if (pos >= end) + break; + if (!nilfs_set_bit_atomic(lock, pos, bitmap)) + return pos; + } while (++pos < end); + + end = target; } - for (i = 0, curr = end; - i < bsize; - i += BITS_PER_LONG, curr += BITS_PER_LONG) { - /* wrap around */ - if (curr >= bsize) - curr = 0; - while (*((unsigned long *)bitmap + curr / BITS_PER_LONG) - != ~0UL) { - end = curr + BITS_PER_LONG; - if (end > bsize) - end = bsize; - pos = nilfs_find_next_zero_bit(bitmap, end, curr); - if (pos < end && - !nilfs_set_bit_atomic(lock, pos, bitmap)) - return pos; - } + /* wrap around */ + for (pos = 0; pos < end; pos++) { + pos = nilfs_find_next_zero_bit(bitmap, end, pos); + if (pos >= end) + break; + if (!nilfs_set_bit_atomic(lock, pos, bitmap)) + return pos; } + return -ENOSPC; } -- cgit v1.2.3-70-g09d2 From b22580948c39d71fb150c1d53148a381011dd109 Mon Sep 17 00:00:00 2001 From: Ryusuke Konishi Date: Fri, 6 Nov 2015 16:31:51 -0800 Subject: nilfs2: get rid of nilfs_palloc_group_is_in() This unfolds nilfs_palloc_group_is_in() helper function into nilfs_palloc_freev() function to simplify a range check and an index calculation repeatedy performed in a loop of the function. Signed-off-by: Ryusuke Konishi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/nilfs2/alloc.c | 28 +++++++++------------------- 1 file changed, 9 insertions(+), 19 deletions(-) (limited to 'fs') diff --git a/fs/nilfs2/alloc.c b/fs/nilfs2/alloc.c index b15daf871f99..5b7ee36f84c7 100644 --- a/fs/nilfs2/alloc.c +++ b/fs/nilfs2/alloc.c @@ -672,22 +672,6 @@ void nilfs_palloc_abort_free_entry(struct inode *inode, req->pr_desc_bh = NULL; } -/** - * nilfs_palloc_group_is_in - judge if an entry is in a group - * @inode: inode of metadata file using this allocator - * @group: group number - * @nr: serial number of the entry (e.g. inode number) - */ -static int -nilfs_palloc_group_is_in(struct inode *inode, unsigned long group, __u64 nr) -{ - __u64 first, last; - - first = group * nilfs_palloc_entries_per_group(inode); - last = first + nilfs_palloc_entries_per_group(inode) - 1; - return (nr >= first) && (nr <= last); -} - /** * nilfs_palloc_freev - deallocate a set of persistent objects * @inode: inode of metadata file using this allocator @@ -701,6 +685,8 @@ int nilfs_palloc_freev(struct inode *inode, __u64 *entry_nrs, size_t nitems) unsigned char *bitmap; void *desc_kaddr, *bitmap_kaddr; unsigned long group, group_offset; + __u64 group_min_nr; + const unsigned long epg = nilfs_palloc_entries_per_group(inode); spinlock_t *lock; int i, j, n, ret; @@ -715,6 +701,10 @@ int nilfs_palloc_freev(struct inode *inode, __u64 *entry_nrs, size_t nitems) brelse(desc_bh); return ret; } + + /* Get the first entry number of the group */ + group_min_nr = (__u64)group * epg; + desc_kaddr = kmap(desc_bh->b_page); desc = nilfs_palloc_block_get_group_desc( inode, group, desc_bh, desc_kaddr); @@ -722,10 +712,10 @@ int nilfs_palloc_freev(struct inode *inode, __u64 *entry_nrs, size_t nitems) bitmap = bitmap_kaddr + bh_offset(bitmap_bh); lock = nilfs_mdt_bgl_lock(inode, group); for (j = i, n = 0; - (j < nitems) && nilfs_palloc_group_is_in(inode, group, - entry_nrs[j]); + j < nitems && entry_nrs[j] >= group_min_nr && + entry_nrs[j] < group_min_nr + epg; j++) { - nilfs_palloc_group(inode, entry_nrs[j], &group_offset); + group_offset = entry_nrs[j] - group_min_nr; if (!nilfs_clear_bit_atomic(lock, group_offset, bitmap)) { nilfs_warning(inode->i_sb, __func__, -- cgit v1.2.3-70-g09d2 From da019954dd821682d6b2a8330c9c90acb943c456 Mon Sep 17 00:00:00 2001 From: Ryusuke Konishi Date: Fri, 6 Nov 2015 16:31:54 -0800 Subject: nilfs2: add helper functions to delete blocks from dat file This adds delete functions for data blocks of metadata files using bitmap based allocator. nilfs_palloc_delete_entry_block() deletes an entry block (e.g. block storing dat entries), and nilfs_palloc_delete_bitmap_block() deletes a bitmap block, respectively. These helpers are intended to be used in the successive change on deallocator of block addresses ("nilfs2: free unused dat file blocks during garbage collection"). Signed-off-by: Ryusuke Konishi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/nilfs2/alloc.c | 50 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 50 insertions(+) (limited to 'fs') diff --git a/fs/nilfs2/alloc.c b/fs/nilfs2/alloc.c index 5b7ee36f84c7..225b79768865 100644 --- a/fs/nilfs2/alloc.c +++ b/fs/nilfs2/alloc.c @@ -235,6 +235,26 @@ static int nilfs_palloc_get_block(struct inode *inode, unsigned long blkoff, return ret; } +/** + * nilfs_palloc_delete_block - delete a block on the persistent allocator file + * @inode: inode of metadata file using this allocator + * @blkoff: block offset + * @prev: nilfs_bh_assoc struct of the last used buffer + * @lock: spin lock protecting @prev + */ +static int nilfs_palloc_delete_block(struct inode *inode, unsigned long blkoff, + struct nilfs_bh_assoc *prev, + spinlock_t *lock) +{ + spin_lock(lock); + if (prev->bh && blkoff == prev->blkoff) { + brelse(prev->bh); + prev->bh = NULL; + } + spin_unlock(lock); + return nilfs_mdt_delete_block(inode, blkoff); +} + /** * nilfs_palloc_get_desc_block - get buffer head of a group descriptor block * @inode: inode of metadata file using this allocator @@ -273,6 +293,22 @@ static int nilfs_palloc_get_bitmap_block(struct inode *inode, &cache->prev_bitmap, &cache->lock); } +/** + * nilfs_palloc_delete_bitmap_block - delete a bitmap block + * @inode: inode of metadata file using this allocator + * @group: group number + */ +static int nilfs_palloc_delete_bitmap_block(struct inode *inode, + unsigned long group) +{ + struct nilfs_palloc_cache *cache = NILFS_MDT(inode)->mi_palloc_cache; + + return nilfs_palloc_delete_block(inode, + nilfs_palloc_bitmap_blkoff(inode, + group), + &cache->prev_bitmap, &cache->lock); +} + /** * nilfs_palloc_get_entry_block - get buffer head of an entry block * @inode: inode of metadata file using this allocator @@ -291,6 +327,20 @@ int nilfs_palloc_get_entry_block(struct inode *inode, __u64 nr, &cache->prev_entry, &cache->lock); } +/** + * nilfs_palloc_delete_entry_block - delete an entry block + * @inode: inode of metadata file using this allocator + * @nr: serial number of the entry + */ +static int nilfs_palloc_delete_entry_block(struct inode *inode, __u64 nr) +{ + struct nilfs_palloc_cache *cache = NILFS_MDT(inode)->mi_palloc_cache; + + return nilfs_palloc_delete_block(inode, + nilfs_palloc_entry_blkoff(inode, nr), + &cache->prev_entry, &cache->lock); +} + /** * nilfs_palloc_block_get_group_desc - get kernel address of a group descriptor * @inode: inode of metadata file using this allocator -- cgit v1.2.3-70-g09d2 From d0c14a9ee79467cd6a04b281577e1e6f74806ab2 Mon Sep 17 00:00:00 2001 From: Ryusuke Konishi Date: Fri, 6 Nov 2015 16:31:56 -0800 Subject: nilfs2: free unused dat file blocks during garbage collection As a nilfs2 volume ages, the amount of available disk space decreases little by little due to bloat of DAT (disk address translation) metadata file. Even if we delete all files in a file system and free their block addresses from the DAT file through a garbage collection, empty DAT blocks are not freed. This fixes the issue by extending the deallocator of block addresses so that empty data blocks and empty bitmap blocks of DAT are deleted. The following comparison shows the effect of this patch. Each shows disk amount information of a nilfs2 volume that we cleaned out by deleting all files and running gc after having filled 90% of its capacity. Before: Filesystem 1K-blocks Used Available Use% Mounted on /dev/sda1 500105212 3022844 472072192 1% /test After: Filesystem 1K-blocks Used Available Use% Mounted on /dev/sda1 500105212 16380 475078656 1% /test Signed-off-by: Ryusuke Konishi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/nilfs2/alloc.c | 91 ++++++++++++++++++++++++++++++++++++++++++++----------- fs/nilfs2/alloc.h | 1 + 2 files changed, 75 insertions(+), 17 deletions(-) (limited to 'fs') diff --git a/fs/nilfs2/alloc.c b/fs/nilfs2/alloc.c index 225b79768865..b335a32e9561 100644 --- a/fs/nilfs2/alloc.c +++ b/fs/nilfs2/alloc.c @@ -154,13 +154,17 @@ nilfs_palloc_group_desc_nfrees(const struct nilfs_palloc_group_desc *desc, * @lock: spin lock protecting @desc * @n: delta to be added */ -static void +static u32 nilfs_palloc_group_desc_add_entries(struct nilfs_palloc_group_desc *desc, spinlock_t *lock, u32 n) { + u32 nfree; + spin_lock(lock); le32_add_cpu(&desc->pg_nfrees, n); + nfree = le32_to_cpu(desc->pg_nfrees); spin_unlock(lock); + return nfree; } /** @@ -735,12 +739,18 @@ int nilfs_palloc_freev(struct inode *inode, __u64 *entry_nrs, size_t nitems) unsigned char *bitmap; void *desc_kaddr, *bitmap_kaddr; unsigned long group, group_offset; - __u64 group_min_nr; + __u64 group_min_nr, last_nrs[8]; const unsigned long epg = nilfs_palloc_entries_per_group(inode); + const unsigned epb = NILFS_MDT(inode)->mi_entries_per_block; + unsigned entry_start, end, pos; spinlock_t *lock; - int i, j, n, ret; + int i, j, k, ret; + u32 nfree; for (i = 0; i < nitems; i = j) { + int change_group = false; + int nempties = 0, n = 0; + group = nilfs_palloc_group(inode, entry_nrs[i], &group_offset); ret = nilfs_palloc_get_desc_block(inode, group, 0, &desc_bh); if (ret < 0) @@ -755,17 +765,13 @@ int nilfs_palloc_freev(struct inode *inode, __u64 *entry_nrs, size_t nitems) /* Get the first entry number of the group */ group_min_nr = (__u64)group * epg; - desc_kaddr = kmap(desc_bh->b_page); - desc = nilfs_palloc_block_get_group_desc( - inode, group, desc_bh, desc_kaddr); bitmap_kaddr = kmap(bitmap_bh->b_page); bitmap = bitmap_kaddr + bh_offset(bitmap_bh); lock = nilfs_mdt_bgl_lock(inode, group); - for (j = i, n = 0; - j < nitems && entry_nrs[j] >= group_min_nr && - entry_nrs[j] < group_min_nr + epg; - j++) { - group_offset = entry_nrs[j] - group_min_nr; + + j = i; + entry_start = rounddown(group_offset, epb); + do { if (!nilfs_clear_bit_atomic(lock, group_offset, bitmap)) { nilfs_warning(inode->i_sb, __func__, @@ -775,18 +781,69 @@ int nilfs_palloc_freev(struct inode *inode, __u64 *entry_nrs, size_t nitems) } else { n++; } - } - nilfs_palloc_group_desc_add_entries(desc, lock, n); + + j++; + if (j >= nitems || entry_nrs[j] < group_min_nr || + entry_nrs[j] >= group_min_nr + epg) { + change_group = true; + } else { + group_offset = entry_nrs[j] - group_min_nr; + if (group_offset >= entry_start && + group_offset < entry_start + epb) { + /* This entry is in the same block */ + continue; + } + } + + /* Test if the entry block is empty or not */ + end = entry_start + epb; + pos = nilfs_find_next_bit(bitmap, end, entry_start); + if (pos >= end) { + last_nrs[nempties++] = entry_nrs[j - 1]; + if (nempties >= ARRAY_SIZE(last_nrs)) + break; + } + + if (change_group) + break; + + /* Go on to the next entry block */ + entry_start = rounddown(group_offset, epb); + } while (true); kunmap(bitmap_bh->b_page); - kunmap(desc_bh->b_page); + mark_buffer_dirty(bitmap_bh); + brelse(bitmap_bh); + for (k = 0; k < nempties; k++) { + ret = nilfs_palloc_delete_entry_block(inode, + last_nrs[k]); + if (ret && ret != -ENOENT) { + nilfs_warning(inode->i_sb, __func__, + "failed to delete block of entry %llu: ino=%lu, err=%d\n", + (unsigned long long)last_nrs[k], + (unsigned long)inode->i_ino, ret); + } + } + + desc_kaddr = kmap_atomic(desc_bh->b_page); + desc = nilfs_palloc_block_get_group_desc( + inode, group, desc_bh, desc_kaddr); + nfree = nilfs_palloc_group_desc_add_entries(desc, lock, n); + kunmap_atomic(desc_kaddr); mark_buffer_dirty(desc_bh); - mark_buffer_dirty(bitmap_bh); nilfs_mdt_mark_dirty(inode); - - brelse(bitmap_bh); brelse(desc_bh); + + if (nfree == nilfs_palloc_entries_per_group(inode)) { + ret = nilfs_palloc_delete_bitmap_block(inode, group); + if (ret && ret != -ENOENT) { + nilfs_warning(inode->i_sb, __func__, + "failed to delete bitmap block of group %lu: ino=%lu, err=%d\n", + group, + (unsigned long)inode->i_ino, ret); + } + } } return 0; } diff --git a/fs/nilfs2/alloc.h b/fs/nilfs2/alloc.h index 4bd6451b5703..6e6f49aa53df 100644 --- a/fs/nilfs2/alloc.h +++ b/fs/nilfs2/alloc.h @@ -77,6 +77,7 @@ int nilfs_palloc_freev(struct inode *, __u64 *, size_t); #define nilfs_set_bit_atomic ext2_set_bit_atomic #define nilfs_clear_bit_atomic ext2_clear_bit_atomic #define nilfs_find_next_zero_bit find_next_zero_bit_le +#define nilfs_find_next_bit find_next_bit_le /** * struct nilfs_bh_assoc - block offset and buffer head association -- cgit v1.2.3-70-g09d2 From 58497703837048ac501ce56056eb74b4361108fc Mon Sep 17 00:00:00 2001 From: Hitoshi Mitake Date: Fri, 6 Nov 2015 16:31:59 -0800 Subject: nilfs2: add a tracepoint for tracking stage transition of segment construction This patch adds a tracepoint for tracking stage transition of block collection in segment construction. With the tracepoint, we can analysis the behavior of segment construction in depth. It would be useful for bottleneck detection and debugging, etc. The tracepoint is created with the standard trace API of linux (like ext3, ext4, f2fs and btrfs). So we can analysis with existing tools easily. Of course, more detailed analysis will be possible if we can create nilfs specific analysis tools. Below is an example of event dump with Brendan Gregg's perf-tools (https://github.com/brendangregg/perf-tools). Time consumption between each stage can be obtained. $ sudo bin/tpoint nilfs2:nilfs2_collection_stage_transition Tracing nilfs2:nilfs2_collection_stage_transition. Ctrl-C to end. segctord-14875 [003] ...1 28311.067794: nilfs2_collection_stage_transition: sci = ffff8800ce6de000 stage = ST_INIT segctord-14875 [003] ...1 28311.068139: nilfs2_collection_stage_transition: sci = ffff8800ce6de000 stage = ST_GC segctord-14875 [003] ...1 28311.068139: nilfs2_collection_stage_transition: sci = ffff8800ce6de000 stage = ST_FILE segctord-14875 [003] ...1 28311.068486: nilfs2_collection_stage_transition: sci = ffff8800ce6de000 stage = ST_IFILE segctord-14875 [003] ...1 28311.068540: nilfs2_collection_stage_transition: sci = ffff8800ce6de000 stage = ST_CPFILE segctord-14875 [003] ...1 28311.068561: nilfs2_collection_stage_transition: sci = ffff8800ce6de000 stage = ST_SUFILE segctord-14875 [003] ...1 28311.068565: nilfs2_collection_stage_transition: sci = ffff8800ce6de000 stage = ST_DAT segctord-14875 [003] ...1 28311.068573: nilfs2_collection_stage_transition: sci = ffff8800ce6de000 stage = ST_SR segctord-14875 [003] ...1 28311.068574: nilfs2_collection_stage_transition: sci = ffff8800ce6de000 stage = ST_DONE For capturing transition correctly, this patch adds wrappers for the member scnt of nilfs_cstage. With this change, every transition of the stage can produce trace event in a correct manner. Signed-off-by: Hitoshi Mitake Signed-off-by: Ryusuke Konishi Cc: Steven Rostedt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/nilfs2/segment.c | 71 +++++++++++++++++++++++++++++++------------ fs/nilfs2/segment.h | 3 +- include/trace/events/nilfs2.h | 50 ++++++++++++++++++++++++++++++ 3 files changed, 103 insertions(+), 21 deletions(-) create mode 100644 include/trace/events/nilfs2.h (limited to 'fs') diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index c6abbad9b8e3..ef354043b87c 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -77,6 +77,36 @@ enum { NILFS_ST_DONE, }; +#define CREATE_TRACE_POINTS +#include + +/* + * nilfs_sc_cstage_inc(), nilfs_sc_cstage_set(), nilfs_sc_cstage_get() are + * wrapper functions of stage count (nilfs_sc_info->sc_stage.scnt). Users of + * the variable must use them because transition of stage count must involve + * trace events (trace_nilfs2_collection_stage_transition). + * + * nilfs_sc_cstage_get() isn't required for the above purpose because it doesn't + * produce tracepoint events. It is provided just for making the intention + * clear. + */ +static inline void nilfs_sc_cstage_inc(struct nilfs_sc_info *sci) +{ + sci->sc_stage.scnt++; + trace_nilfs2_collection_stage_transition(sci); +} + +static inline void nilfs_sc_cstage_set(struct nilfs_sc_info *sci, int next_scnt) +{ + sci->sc_stage.scnt = next_scnt; + trace_nilfs2_collection_stage_transition(sci); +} + +static inline int nilfs_sc_cstage_get(struct nilfs_sc_info *sci) +{ + return sci->sc_stage.scnt; +} + /* State flags of collection */ #define NILFS_CF_NODE 0x0001 /* Collecting node blocks */ #define NILFS_CF_IFILE_STARTED 0x0002 /* IFILE stage has started */ @@ -1062,7 +1092,7 @@ static int nilfs_segctor_collect_blocks(struct nilfs_sc_info *sci, int mode) size_t ndone; int err = 0; - switch (sci->sc_stage.scnt) { + switch (nilfs_sc_cstage_get(sci)) { case NILFS_ST_INIT: /* Pre-processes */ sci->sc_stage.flags = 0; @@ -1071,7 +1101,7 @@ static int nilfs_segctor_collect_blocks(struct nilfs_sc_info *sci, int mode) sci->sc_nblk_inc = 0; sci->sc_curseg->sb_sum.flags = NILFS_SS_LOGBGN; if (mode == SC_LSEG_DSYNC) { - sci->sc_stage.scnt = NILFS_ST_DSYNC; + nilfs_sc_cstage_set(sci, NILFS_ST_DSYNC); goto dsync_mode; } } @@ -1079,10 +1109,10 @@ static int nilfs_segctor_collect_blocks(struct nilfs_sc_info *sci, int mode) sci->sc_stage.dirty_file_ptr = NULL; sci->sc_stage.gc_inode_ptr = NULL; if (mode == SC_FLUSH_DAT) { - sci->sc_stage.scnt = NILFS_ST_DAT; + nilfs_sc_cstage_set(sci, NILFS_ST_DAT); goto dat_stage; } - sci->sc_stage.scnt++; /* Fall through */ + nilfs_sc_cstage_inc(sci); /* Fall through */ case NILFS_ST_GC: if (nilfs_doing_gc()) { head = &sci->sc_gc_inodes; @@ -1103,7 +1133,7 @@ static int nilfs_segctor_collect_blocks(struct nilfs_sc_info *sci, int mode) } sci->sc_stage.gc_inode_ptr = NULL; } - sci->sc_stage.scnt++; /* Fall through */ + nilfs_sc_cstage_inc(sci); /* Fall through */ case NILFS_ST_FILE: head = &sci->sc_dirty_files; ii = list_prepare_entry(sci->sc_stage.dirty_file_ptr, head, @@ -1125,10 +1155,10 @@ static int nilfs_segctor_collect_blocks(struct nilfs_sc_info *sci, int mode) } sci->sc_stage.dirty_file_ptr = NULL; if (mode == SC_FLUSH_FILE) { - sci->sc_stage.scnt = NILFS_ST_DONE; + nilfs_sc_cstage_set(sci, NILFS_ST_DONE); return 0; } - sci->sc_stage.scnt++; + nilfs_sc_cstage_inc(sci); sci->sc_stage.flags |= NILFS_CF_IFILE_STARTED; /* Fall through */ case NILFS_ST_IFILE: @@ -1136,7 +1166,7 @@ static int nilfs_segctor_collect_blocks(struct nilfs_sc_info *sci, int mode) &nilfs_sc_file_ops); if (unlikely(err)) break; - sci->sc_stage.scnt++; + nilfs_sc_cstage_inc(sci); /* Creating a checkpoint */ err = nilfs_segctor_create_checkpoint(sci); if (unlikely(err)) @@ -1147,7 +1177,7 @@ static int nilfs_segctor_collect_blocks(struct nilfs_sc_info *sci, int mode) &nilfs_sc_file_ops); if (unlikely(err)) break; - sci->sc_stage.scnt++; /* Fall through */ + nilfs_sc_cstage_inc(sci); /* Fall through */ case NILFS_ST_SUFILE: err = nilfs_sufile_freev(nilfs->ns_sufile, sci->sc_freesegs, sci->sc_nfreesegs, &ndone); @@ -1163,7 +1193,7 @@ static int nilfs_segctor_collect_blocks(struct nilfs_sc_info *sci, int mode) &nilfs_sc_file_ops); if (unlikely(err)) break; - sci->sc_stage.scnt++; /* Fall through */ + nilfs_sc_cstage_inc(sci); /* Fall through */ case NILFS_ST_DAT: dat_stage: err = nilfs_segctor_scan_file(sci, nilfs->ns_dat, @@ -1171,10 +1201,10 @@ static int nilfs_segctor_collect_blocks(struct nilfs_sc_info *sci, int mode) if (unlikely(err)) break; if (mode == SC_FLUSH_DAT) { - sci->sc_stage.scnt = NILFS_ST_DONE; + nilfs_sc_cstage_set(sci, NILFS_ST_DONE); return 0; } - sci->sc_stage.scnt++; /* Fall through */ + nilfs_sc_cstage_inc(sci); /* Fall through */ case NILFS_ST_SR: if (mode == SC_LSEG_SR) { /* Appending a super root */ @@ -1184,7 +1214,7 @@ static int nilfs_segctor_collect_blocks(struct nilfs_sc_info *sci, int mode) } /* End of a logical segment */ sci->sc_curseg->sb_sum.flags |= NILFS_SS_LOGEND; - sci->sc_stage.scnt = NILFS_ST_DONE; + nilfs_sc_cstage_set(sci, NILFS_ST_DONE); return 0; case NILFS_ST_DSYNC: dsync_mode: @@ -1197,7 +1227,7 @@ static int nilfs_segctor_collect_blocks(struct nilfs_sc_info *sci, int mode) if (unlikely(err)) break; sci->sc_curseg->sb_sum.flags |= NILFS_SS_LOGEND; - sci->sc_stage.scnt = NILFS_ST_DONE; + nilfs_sc_cstage_set(sci, NILFS_ST_DONE); return 0; case NILFS_ST_DONE: return 0; @@ -1442,7 +1472,8 @@ static int nilfs_segctor_collect(struct nilfs_sc_info *sci, goto failed; /* The current segment is filled up */ - if (mode != SC_LSEG_SR || sci->sc_stage.scnt < NILFS_ST_CPFILE) + if (mode != SC_LSEG_SR || + nilfs_sc_cstage_get(sci) < NILFS_ST_CPFILE) break; nilfs_clear_logs(&sci->sc_segbufs); @@ -1946,7 +1977,7 @@ static int nilfs_segctor_do_construct(struct nilfs_sc_info *sci, int mode) struct the_nilfs *nilfs = sci->sc_super->s_fs_info; int err; - sci->sc_stage.scnt = NILFS_ST_INIT; + nilfs_sc_cstage_set(sci, NILFS_ST_INIT); sci->sc_cno = nilfs->ns_cno; err = nilfs_segctor_collect_dirty_files(sci, nilfs); @@ -1974,7 +2005,7 @@ static int nilfs_segctor_do_construct(struct nilfs_sc_info *sci, int mode) goto failed; /* Avoid empty segment */ - if (sci->sc_stage.scnt == NILFS_ST_DONE && + if (nilfs_sc_cstage_get(sci) == NILFS_ST_DONE && nilfs_segbuf_empty(sci->sc_curseg)) { nilfs_segctor_abort_construction(sci, nilfs, 1); goto out; @@ -1988,7 +2019,7 @@ static int nilfs_segctor_do_construct(struct nilfs_sc_info *sci, int mode) nilfs_segctor_fill_in_file_bmap(sci); if (mode == SC_LSEG_SR && - sci->sc_stage.scnt >= NILFS_ST_CPFILE) { + nilfs_sc_cstage_get(sci) >= NILFS_ST_CPFILE) { err = nilfs_segctor_fill_in_checkpoint(sci); if (unlikely(err)) goto failed_to_write; @@ -2007,7 +2038,7 @@ static int nilfs_segctor_do_construct(struct nilfs_sc_info *sci, int mode) if (unlikely(err)) goto failed_to_write; - if (sci->sc_stage.scnt == NILFS_ST_DONE || + if (nilfs_sc_cstage_get(sci) == NILFS_ST_DONE || nilfs->ns_blocksize_bits != PAGE_CACHE_SHIFT) { /* * At this point, we avoid double buffering @@ -2020,7 +2051,7 @@ static int nilfs_segctor_do_construct(struct nilfs_sc_info *sci, int mode) if (err) goto failed_to_write; } - } while (sci->sc_stage.scnt != NILFS_ST_DONE); + } while (nilfs_sc_cstage_get(sci) != NILFS_ST_DONE); out: nilfs_segctor_drop_written_files(sci, nilfs); diff --git a/fs/nilfs2/segment.h b/fs/nilfs2/segment.h index a48d6de1e02c..0408b9b2814b 100644 --- a/fs/nilfs2/segment.h +++ b/fs/nilfs2/segment.h @@ -67,7 +67,8 @@ struct nilfs_recovery_info { /** * struct nilfs_cstage - Context of collection stage - * @scnt: Stage count + * @scnt: Stage count, must be accessed via wrappers: + * nilfs_sc_cstage_inc(), nilfs_sc_cstage_set(), nilfs_sc_cstage_get() * @flags: State flags * @dirty_file_ptr: Pointer on dirty_files list, or inode of a target file * @gc_inode_ptr: Pointer on the list of gc-inodes diff --git a/include/trace/events/nilfs2.h b/include/trace/events/nilfs2.h new file mode 100644 index 000000000000..573da00a486d --- /dev/null +++ b/include/trace/events/nilfs2.h @@ -0,0 +1,50 @@ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM nilfs2 + +#if !defined(_TRACE_NILFS2_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_NILFS2_H + +#include + +struct nilfs_sc_info; + +#define show_collection_stage(type) \ + __print_symbolic(type, \ + { NILFS_ST_INIT, "ST_INIT" }, \ + { NILFS_ST_GC, "ST_GC" }, \ + { NILFS_ST_FILE, "ST_FILE" }, \ + { NILFS_ST_IFILE, "ST_IFILE" }, \ + { NILFS_ST_CPFILE, "ST_CPFILE" }, \ + { NILFS_ST_SUFILE, "ST_SUFILE" }, \ + { NILFS_ST_DAT, "ST_DAT" }, \ + { NILFS_ST_SR, "ST_SR" }, \ + { NILFS_ST_DSYNC, "ST_DSYNC" }, \ + { NILFS_ST_DONE, "ST_DONE"}) + +TRACE_EVENT(nilfs2_collection_stage_transition, + + TP_PROTO(struct nilfs_sc_info *sci), + + TP_ARGS(sci), + + TP_STRUCT__entry( + __field(void *, sci) + __field(int, stage) + ), + + TP_fast_assign( + __entry->sci = sci; + __entry->stage = sci->sc_stage.scnt; + ), + + TP_printk("sci = %p stage = %s", + __entry->sci, + show_collection_stage(__entry->stage)) +); + +#endif /* _TRACE_NILFS2_H */ + +/* This part must be outside protection */ +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_FILE nilfs2 +#include -- cgit v1.2.3-70-g09d2 From 44fda114601fa5edebeacecb265f09d802670bc0 Mon Sep 17 00:00:00 2001 From: Hitoshi Mitake Date: Fri, 6 Nov 2015 16:32:02 -0800 Subject: nilfs2: add a tracepoint for transaction events This patch adds a tracepoint for transaction events of nilfs. With the tracepoint, these events can be tracked: begin, abort, commit, trylock, lock, and unlock. Basically, these events have corresponding functions e.g. begin event corresponds nilfs_transaction_begin(). The unlock event is an exception. It corresponds to the iteration in nilfs_transaction_lock(). Only one tracepoint is introcued: nilfs2_transaction_transition. The above events are distinguished with newly introduced enum. With this tracepoint, we can analyse a critical section of segment constructoin. Sample output by tpoint of perf-tools: cp-4457 [000] ...1 63.266220: nilfs2_transaction_transition: sb = ffff8802112b8800 ti = ffff8800bf5ccc58 count = 1 flags = 9 state = BEGIN cp-4457 [000] ...1 63.266221: nilfs2_transaction_transition: sb = ffff8802112b8800 ti = ffff8800bf5ccc58 count = 0 flags = 9 state = COMMIT cp-4457 [000] ...1 63.266221: nilfs2_transaction_transition: sb = ffff8802112b8800 ti = ffff8800bf5ccc58 count = 0 flags = 9 state = COMMIT segctord-4371 [001] ...1 68.261196: nilfs2_transaction_transition: sb = ffff8802112b8800 ti = ffff8800b889bdf8 count = 0 flags = 10 state = TRYLOCK segctord-4371 [001] ...1 68.261280: nilfs2_transaction_transition: sb = ffff8802112b8800 ti = ffff8800b889bdf8 count = 0 flags = 10 state = LOCK segctord-4371 [001] ...1 68.261877: nilfs2_transaction_transition: sb = ffff8802112b8800 ti = ffff8800b889bdf8 count = 1 flags = 10 state = BEGIN segctord-4371 [001] ...1 68.262116: nilfs2_transaction_transition: sb = ffff8802112b8800 ti = ffff8800b889bdf8 count = 0 flags = 18 state = COMMIT segctord-4371 [001] ...1 68.265032: nilfs2_transaction_transition: sb = ffff8802112b8800 ti = ffff8800b889bdf8 count = 0 flags = 18 state = UNLOCK segctord-4371 [001] ...1 132.376847: nilfs2_transaction_transition: sb = ffff8802112b8800 ti = ffff8800b889bdf8 count = 0 flags = 10 state = TRYLOCK This patch also does trivial cleaning of comma usage in collection stage transition event for consistent coding style. Signed-off-by: Hitoshi Mitake Signed-off-by: Ryusuke Konishi Cc: Steven Rostedt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/nilfs2/segment.c | 33 ++++++++++++++++++++++++++- include/trace/events/nilfs2.h | 53 +++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 85 insertions(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index ef354043b87c..3fc47326fbe1 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -214,11 +214,18 @@ int nilfs_transaction_begin(struct super_block *sb, { struct the_nilfs *nilfs; int ret = nilfs_prepare_segment_lock(ti); + struct nilfs_transaction_info *trace_ti; if (unlikely(ret < 0)) return ret; - if (ret > 0) + if (ret > 0) { + trace_ti = current->journal_info; + + trace_nilfs2_transaction_transition(sb, trace_ti, + trace_ti->ti_count, trace_ti->ti_flags, + TRACE_NILFS2_TRANSACTION_BEGIN); return 0; + } sb_start_intwrite(sb); @@ -229,6 +236,11 @@ int nilfs_transaction_begin(struct super_block *sb, ret = -ENOSPC; goto failed; } + + trace_ti = current->journal_info; + trace_nilfs2_transaction_transition(sb, trace_ti, trace_ti->ti_count, + trace_ti->ti_flags, + TRACE_NILFS2_TRANSACTION_BEGIN); return 0; failed: @@ -261,6 +273,8 @@ int nilfs_transaction_commit(struct super_block *sb) ti->ti_flags |= NILFS_TI_COMMIT; if (ti->ti_count > 0) { ti->ti_count--; + trace_nilfs2_transaction_transition(sb, ti, ti->ti_count, + ti->ti_flags, TRACE_NILFS2_TRANSACTION_COMMIT); return 0; } if (nilfs->ns_writer) { @@ -272,6 +286,9 @@ int nilfs_transaction_commit(struct super_block *sb) nilfs_segctor_do_flush(sci, 0); } up_read(&nilfs->ns_segctor_sem); + trace_nilfs2_transaction_transition(sb, ti, ti->ti_count, + ti->ti_flags, TRACE_NILFS2_TRANSACTION_COMMIT); + current->journal_info = ti->ti_save; if (ti->ti_flags & NILFS_TI_SYNC) @@ -290,10 +307,15 @@ void nilfs_transaction_abort(struct super_block *sb) BUG_ON(ti == NULL || ti->ti_magic != NILFS_TI_MAGIC); if (ti->ti_count > 0) { ti->ti_count--; + trace_nilfs2_transaction_transition(sb, ti, ti->ti_count, + ti->ti_flags, TRACE_NILFS2_TRANSACTION_ABORT); return; } up_read(&nilfs->ns_segctor_sem); + trace_nilfs2_transaction_transition(sb, ti, ti->ti_count, + ti->ti_flags, TRACE_NILFS2_TRANSACTION_ABORT); + current->journal_info = ti->ti_save; if (ti->ti_flags & NILFS_TI_DYNAMIC_ALLOC) kmem_cache_free(nilfs_transaction_cachep, ti); @@ -339,6 +361,9 @@ static void nilfs_transaction_lock(struct super_block *sb, current->journal_info = ti; for (;;) { + trace_nilfs2_transaction_transition(sb, ti, ti->ti_count, + ti->ti_flags, TRACE_NILFS2_TRANSACTION_TRYLOCK); + down_write(&nilfs->ns_segctor_sem); if (!test_bit(NILFS_SC_PRIOR_FLUSH, &sci->sc_flags)) break; @@ -350,6 +375,9 @@ static void nilfs_transaction_lock(struct super_block *sb, } if (gcflag) ti->ti_flags |= NILFS_TI_GC; + + trace_nilfs2_transaction_transition(sb, ti, ti->ti_count, + ti->ti_flags, TRACE_NILFS2_TRANSACTION_LOCK); } static void nilfs_transaction_unlock(struct super_block *sb) @@ -362,6 +390,9 @@ static void nilfs_transaction_unlock(struct super_block *sb) up_write(&nilfs->ns_segctor_sem); current->journal_info = ti->ti_save; + + trace_nilfs2_transaction_transition(sb, ti, ti->ti_count, + ti->ti_flags, TRACE_NILFS2_TRANSACTION_UNLOCK); } static void *nilfs_segctor_map_segsum_entry(struct nilfs_sc_info *sci, diff --git a/include/trace/events/nilfs2.h b/include/trace/events/nilfs2.h index 573da00a486d..e5649ac211ca 100644 --- a/include/trace/events/nilfs2.h +++ b/include/trace/events/nilfs2.h @@ -42,6 +42,59 @@ TRACE_EVENT(nilfs2_collection_stage_transition, show_collection_stage(__entry->stage)) ); +#ifndef TRACE_HEADER_MULTI_READ +enum nilfs2_transaction_transition_state { + TRACE_NILFS2_TRANSACTION_BEGIN, + TRACE_NILFS2_TRANSACTION_COMMIT, + TRACE_NILFS2_TRANSACTION_ABORT, + TRACE_NILFS2_TRANSACTION_TRYLOCK, + TRACE_NILFS2_TRANSACTION_LOCK, + TRACE_NILFS2_TRANSACTION_UNLOCK, +}; +#endif + +#define show_transaction_state(type) \ + __print_symbolic(type, \ + { TRACE_NILFS2_TRANSACTION_BEGIN, "BEGIN" }, \ + { TRACE_NILFS2_TRANSACTION_COMMIT, "COMMIT" }, \ + { TRACE_NILFS2_TRANSACTION_ABORT, "ABORT" }, \ + { TRACE_NILFS2_TRANSACTION_TRYLOCK, "TRYLOCK" }, \ + { TRACE_NILFS2_TRANSACTION_LOCK, "LOCK" }, \ + { TRACE_NILFS2_TRANSACTION_UNLOCK, "UNLOCK" }) + +TRACE_EVENT(nilfs2_transaction_transition, + TP_PROTO(struct super_block *sb, + struct nilfs_transaction_info *ti, + int count, + unsigned int flags, + enum nilfs2_transaction_transition_state state), + + TP_ARGS(sb, ti, count, flags, state), + + TP_STRUCT__entry( + __field(void *, sb) + __field(void *, ti) + __field(int, count) + __field(unsigned int, flags) + __field(int, state) + ), + + TP_fast_assign( + __entry->sb = sb; + __entry->ti = ti; + __entry->count = count; + __entry->flags = flags; + __entry->state = state; + ), + + TP_printk("sb = %p ti = %p count = %d flags = %x state = %s", + __entry->sb, + __entry->ti, + __entry->count, + __entry->flags, + show_transaction_state(__entry->state)) +); + #endif /* _TRACE_NILFS2_H */ /* This part must be outside protection */ -- cgit v1.2.3-70-g09d2 From 83eec5e6dd10f0b1ab83ee660c8be883b3da7ba8 Mon Sep 17 00:00:00 2001 From: Hitoshi Mitake Date: Fri, 6 Nov 2015 16:32:05 -0800 Subject: nilfs2: add tracepoints for analyzing sufile manipulation This patch adds tracepoints which would be useful for analyzing segment usage from a perspective of high level sufile manipulation (check, alloc, free). sufile is an important in-place updated metadata file, so analyzing the behavior would be useful for performance turning. example of usage (a case of allocation): $ sudo bin/tpoint nilfs2:nilfs2_segment_usage_allocated Tracing nilfs2:nilfs2_segment_usage_allocated. Ctrl-C to end. segctord-17800 [002] ...1 10671.867294: nilfs2_segment_usage_allocated: sufile = ffff880054f908a8 segnum = 2 segctord-17800 [002] ...1 10675.073477: nilfs2_segment_usage_allocated: sufile = ffff880054f908a8 segnum = 3 Signed-off-by: Hitoshi Mitake Signed-off-by: Ryusuke Konishi Cc: Steven Rostedt Cc: Benixon Dhas Cc: TK Kato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/nilfs2/sufile.c | 8 ++++++ include/trace/events/nilfs2.h | 67 +++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 75 insertions(+) (limited to 'fs') diff --git a/fs/nilfs2/sufile.c b/fs/nilfs2/sufile.c index 2a869c35c362..7ff8f15207ab 100644 --- a/fs/nilfs2/sufile.c +++ b/fs/nilfs2/sufile.c @@ -30,6 +30,8 @@ #include "mdt.h" #include "sufile.h" +#include + /** * struct nilfs_sufile_info - on-memory private data of sufile * @mi: on-memory private data of metadata file @@ -358,6 +360,7 @@ int nilfs_sufile_alloc(struct inode *sufile, __u64 *segnump) break; /* never happens */ } } + trace_nilfs2_segment_usage_check(sufile, segnum, cnt); ret = nilfs_sufile_get_segment_usage_block(sufile, segnum, 1, &su_bh); if (ret < 0) @@ -388,6 +391,9 @@ int nilfs_sufile_alloc(struct inode *sufile, __u64 *segnump) nilfs_mdt_mark_dirty(sufile); brelse(su_bh); *segnump = segnum; + + trace_nilfs2_segment_usage_allocated(sufile, segnum); + goto out_header; } @@ -490,6 +496,8 @@ void nilfs_sufile_do_free(struct inode *sufile, __u64 segnum, NILFS_SUI(sufile)->ncleansegs++; nilfs_mdt_mark_dirty(sufile); + + trace_nilfs2_segment_usage_freed(sufile, segnum); } /** diff --git a/include/trace/events/nilfs2.h b/include/trace/events/nilfs2.h index e5649ac211ca..1b65ba687925 100644 --- a/include/trace/events/nilfs2.h +++ b/include/trace/events/nilfs2.h @@ -95,6 +95,73 @@ TRACE_EVENT(nilfs2_transaction_transition, show_transaction_state(__entry->state)) ); +TRACE_EVENT(nilfs2_segment_usage_check, + TP_PROTO(struct inode *sufile, + __u64 segnum, + unsigned long cnt), + + TP_ARGS(sufile, segnum, cnt), + + TP_STRUCT__entry( + __field(struct inode *, sufile) + __field(__u64, segnum) + __field(unsigned long, cnt) + ), + + TP_fast_assign( + __entry->sufile = sufile; + __entry->segnum = segnum; + __entry->cnt = cnt; + ), + + TP_printk("sufile = %p segnum = %llu cnt = %lu", + __entry->sufile, + __entry->segnum, + __entry->cnt) +); + +TRACE_EVENT(nilfs2_segment_usage_allocated, + TP_PROTO(struct inode *sufile, + __u64 segnum), + + TP_ARGS(sufile, segnum), + + TP_STRUCT__entry( + __field(struct inode *, sufile) + __field(__u64, segnum) + ), + + TP_fast_assign( + __entry->sufile = sufile; + __entry->segnum = segnum; + ), + + TP_printk("sufile = %p segnum = %llu", + __entry->sufile, + __entry->segnum) +); + +TRACE_EVENT(nilfs2_segment_usage_freed, + TP_PROTO(struct inode *sufile, + __u64 segnum), + + TP_ARGS(sufile, segnum), + + TP_STRUCT__entry( + __field(struct inode *, sufile) + __field(__u64, segnum) + ), + + TP_fast_assign( + __entry->sufile = sufile; + __entry->segnum = segnum; + ), + + TP_printk("sufile = %p segnum = %llu", + __entry->sufile, + __entry->segnum) +); + #endif /* _TRACE_NILFS2_H */ /* This part must be outside protection */ -- cgit v1.2.3-70-g09d2 From a9cd207c23ca4fa5bd5f1092e867e87542e349a3 Mon Sep 17 00:00:00 2001 From: Hitoshi Mitake Date: Fri, 6 Nov 2015 16:32:08 -0800 Subject: nilfs2: add tracepoints for analyzing reading and writing metadata files This patch adds tracepoints for analyzing requests of reading and writing metadata files. The tracepoints cover every in-place mdt files (cpfile, sufile, and datfile). Example of tracing mdt_insert_new_block(): cp-14635 [000] ...1 30598.199309: nilfs2_mdt_insert_new_block: inode = ffff88022a8d0178 ino = 3 block = 155 cp-14635 [000] ...1 30598.199520: nilfs2_mdt_insert_new_block: inode = ffff88022a8d0178 ino = 3 block = 5 cp-14635 [000] ...1 30598.200828: nilfs2_mdt_insert_new_block: inode = ffff88022a8d0178 ino = 3 block = 253 Signed-off-by: Hitoshi Mitake Signed-off-by: Ryusuke Konishi Cc: Steven Rostedt Cc: TK Kato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/nilfs2/mdt.c | 6 +++++ include/trace/events/nilfs2.h | 54 +++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 60 insertions(+) (limited to 'fs') diff --git a/fs/nilfs2/mdt.c b/fs/nilfs2/mdt.c index dee34d990281..1125f40233ff 100644 --- a/fs/nilfs2/mdt.c +++ b/fs/nilfs2/mdt.c @@ -33,6 +33,7 @@ #include "page.h" #include "mdt.h" +#include #define NILFS_MDT_MAX_RA_BLOCKS (16 - 1) @@ -68,6 +69,9 @@ nilfs_mdt_insert_new_block(struct inode *inode, unsigned long block, set_buffer_uptodate(bh); mark_buffer_dirty(bh); nilfs_mdt_mark_dirty(inode); + + trace_nilfs2_mdt_insert_new_block(inode, inode->i_ino, block); + return 0; } @@ -158,6 +162,8 @@ nilfs_mdt_submit_block(struct inode *inode, unsigned long blkoff, get_bh(bh); submit_bh(mode, bh); ret = 0; + + trace_nilfs2_mdt_submit_block(inode, inode->i_ino, blkoff, mode); out: get_bh(bh); *out_bh = bh; diff --git a/include/trace/events/nilfs2.h b/include/trace/events/nilfs2.h index 1b65ba687925..c7805818fcc6 100644 --- a/include/trace/events/nilfs2.h +++ b/include/trace/events/nilfs2.h @@ -162,6 +162,60 @@ TRACE_EVENT(nilfs2_segment_usage_freed, __entry->segnum) ); +TRACE_EVENT(nilfs2_mdt_insert_new_block, + TP_PROTO(struct inode *inode, + unsigned long ino, + unsigned long block), + + TP_ARGS(inode, ino, block), + + TP_STRUCT__entry( + __field(struct inode *, inode) + __field(unsigned long, ino) + __field(unsigned long, block) + ), + + TP_fast_assign( + __entry->inode = inode; + __entry->ino = ino; + __entry->block = block; + ), + + TP_printk("inode = %p ino = %lu block = %lu", + __entry->inode, + __entry->ino, + __entry->block) +); + +TRACE_EVENT(nilfs2_mdt_submit_block, + TP_PROTO(struct inode *inode, + unsigned long ino, + unsigned long blkoff, + int mode), + + TP_ARGS(inode, ino, blkoff, mode), + + TP_STRUCT__entry( + __field(struct inode *, inode) + __field(unsigned long, ino) + __field(unsigned long, blkoff) + __field(int, mode) + ), + + TP_fast_assign( + __entry->inode = inode; + __entry->ino = ino; + __entry->blkoff = blkoff; + __entry->mode = mode; + ), + + TP_printk("inode = %p ino = %lu blkoff = %lu mode = %x", + __entry->inode, + __entry->ino, + __entry->blkoff, + __entry->mode) +); + #endif /* _TRACE_NILFS2_H */ /* This part must be outside protection */ -- cgit v1.2.3-70-g09d2 From 09ef29e0f6ac9f08ba4cc501ab4a3c33be526343 Mon Sep 17 00:00:00 2001 From: Ryusuke Konishi Date: Fri, 6 Nov 2015 16:32:14 -0800 Subject: nilfs2: fix gcc unused-but-set-variable warnings Fix the following build warnings: $ make W=1 [...] CC [M] fs/nilfs2/btree.o fs/nilfs2/btree.c: In function 'nilfs_btree_split': fs/nilfs2/btree.c:923:8: warning: variable 'newptr' set but not used [-Wunused-but-set-variable] __u64 newptr; ^ fs/nilfs2/btree.c:922:8: warning: variable 'newkey' set but not used [-Wunused-but-set-variable] __u64 newkey; ^ CC [M] fs/nilfs2/dat.o fs/nilfs2/dat.c: In function 'nilfs_dat_prepare_end': fs/nilfs2/dat.c:158:8: warning: variable 'start' set but not used [-Wunused-but-set-variable] __u64 start; ^ CC [M] fs/nilfs2/segment.o fs/nilfs2/segment.c: In function 'nilfs_segctor_do_immediate_flush': fs/nilfs2/segment.c:2433:6: warning: variable 'err' set but not used [-Wunused-but-set-variable] int err; ^ CC [M] fs/nilfs2/sufile.o fs/nilfs2/sufile.c: In function 'nilfs_sufile_alloc': fs/nilfs2/sufile.c:320:27: warning: variable 'ncleansegs' set but not used [-Wunused-but-set-variable] unsigned long nsegments, ncleansegs, nsus, cnt; ^ CC [M] fs/nilfs2/alloc.o fs/nilfs2/alloc.c: In function 'nilfs_palloc_prepare_alloc_entry': fs/nilfs2/alloc.c:478:38: warning: variable 'groups_per_desc_block' set but not used [-Wunused-but-set-variable] unsigned long n, entries_per_group, groups_per_desc_block; ^ Signed-off-by: Ryusuke Konishi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/nilfs2/alloc.c | 3 +-- fs/nilfs2/btree.c | 5 ----- fs/nilfs2/dat.c | 2 -- fs/nilfs2/segment.c | 3 +-- fs/nilfs2/sufile.c | 3 +-- 5 files changed, 3 insertions(+), 13 deletions(-) (limited to 'fs') diff --git a/fs/nilfs2/alloc.c b/fs/nilfs2/alloc.c index b335a32e9561..2ccbf5531554 100644 --- a/fs/nilfs2/alloc.c +++ b/fs/nilfs2/alloc.c @@ -514,7 +514,7 @@ int nilfs_palloc_prepare_alloc_entry(struct inode *inode, void *desc_kaddr, *bitmap_kaddr; unsigned long group, maxgroup, ngroups; unsigned long group_offset, maxgroup_offset; - unsigned long n, entries_per_group, groups_per_desc_block; + unsigned long n, entries_per_group; unsigned long i, j; spinlock_t *lock; int pos, ret; @@ -523,7 +523,6 @@ int nilfs_palloc_prepare_alloc_entry(struct inode *inode, maxgroup = ngroups - 1; group = nilfs_palloc_group(inode, req->pr_entry_nr, &group_offset); entries_per_group = nilfs_palloc_entries_per_group(inode); - groups_per_desc_block = nilfs_palloc_groups_per_desc_block(inode); for (i = 0; i < ngroups; i += n) { if (group >= ngroups) { diff --git a/fs/nilfs2/btree.c b/fs/nilfs2/btree.c index 919fd5bb14a8..f609a8532ec5 100644 --- a/fs/nilfs2/btree.c +++ b/fs/nilfs2/btree.c @@ -919,8 +919,6 @@ static void nilfs_btree_split(struct nilfs_bmap *btree, int level, __u64 *keyp, __u64 *ptrp) { struct nilfs_btree_node *node, *right; - __u64 newkey; - __u64 newptr; int nchildren, n, move, ncblk; node = nilfs_btree_get_nonroot_node(path, level); @@ -942,9 +940,6 @@ static void nilfs_btree_split(struct nilfs_bmap *btree, if (!buffer_dirty(path[level].bp_sib_bh)) mark_buffer_dirty(path[level].bp_sib_bh); - newkey = nilfs_btree_node_get_key(right, 0); - newptr = path[level].bp_newreq.bpr_ptr; - if (move) { path[level].bp_index -= nilfs_btree_node_get_nchildren(node); nilfs_btree_node_insert(right, path[level].bp_index, diff --git a/fs/nilfs2/dat.c b/fs/nilfs2/dat.c index 0d5fada91191..7dc23f100e57 100644 --- a/fs/nilfs2/dat.c +++ b/fs/nilfs2/dat.c @@ -155,7 +155,6 @@ void nilfs_dat_commit_start(struct inode *dat, struct nilfs_palloc_req *req, int nilfs_dat_prepare_end(struct inode *dat, struct nilfs_palloc_req *req) { struct nilfs_dat_entry *entry; - __u64 start; sector_t blocknr; void *kaddr; int ret; @@ -169,7 +168,6 @@ int nilfs_dat_prepare_end(struct inode *dat, struct nilfs_palloc_req *req) kaddr = kmap_atomic(req->pr_entry_bh->b_page); entry = nilfs_palloc_block_get_entry(dat, req->pr_entry_nr, req->pr_entry_bh, kaddr); - start = le64_to_cpu(entry->de_start); blocknr = le64_to_cpu(entry->de_blocknr); kunmap_atomic(kaddr); diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index 3fc47326fbe1..3b65adaae7e4 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -2492,7 +2492,6 @@ static void nilfs_segctor_thread_construct(struct nilfs_sc_info *sci, int mode) static void nilfs_segctor_do_immediate_flush(struct nilfs_sc_info *sci) { int mode = 0; - int err; spin_lock(&sci->sc_state_lock); mode = (sci->sc_flush_request & FLUSH_DAT_BIT) ? @@ -2500,7 +2499,7 @@ static void nilfs_segctor_do_immediate_flush(struct nilfs_sc_info *sci) spin_unlock(&sci->sc_state_lock); if (mode) { - err = nilfs_segctor_do_construct(sci, mode); + nilfs_segctor_do_construct(sci, mode); spin_lock(&sci->sc_state_lock); sci->sc_flush_request &= (mode == SC_FLUSH_FILE) ? diff --git a/fs/nilfs2/sufile.c b/fs/nilfs2/sufile.c index 7ff8f15207ab..52821ffc11f4 100644 --- a/fs/nilfs2/sufile.c +++ b/fs/nilfs2/sufile.c @@ -319,7 +319,7 @@ int nilfs_sufile_alloc(struct inode *sufile, __u64 *segnump) size_t susz = NILFS_MDT(sufile)->mi_entry_size; __u64 segnum, maxsegnum, last_alloc; void *kaddr; - unsigned long nsegments, ncleansegs, nsus, cnt; + unsigned long nsegments, nsus, cnt; int ret, j; down_write(&NILFS_MDT(sufile)->mi_sem); @@ -329,7 +329,6 @@ int nilfs_sufile_alloc(struct inode *sufile, __u64 *segnump) goto out_sem; kaddr = kmap_atomic(header_bh->b_page); header = kaddr + bh_offset(header_bh); - ncleansegs = le64_to_cpu(header->sh_ncleansegs); last_alloc = le64_to_cpu(header->sh_last_alloc); kunmap_atomic(kaddr); -- cgit v1.2.3-70-g09d2 From 4f05028f8d1af782cfd03d09e0a052e9745dc5ad Mon Sep 17 00:00:00 2001 From: Ryusuke Konishi Date: Fri, 6 Nov 2015 16:32:16 -0800 Subject: nilfs2: fix gcc uninitialized-variable warnings in powerpc build Some false positive warnings are reported for powerpc build. The following warnings are reported in http://kisskb.ellerman.id.au/kisskb/buildresult/12519703/ CC fs/nilfs2/super.o fs/nilfs2/super.c: In function 'nilfs_resize_fs': fs/nilfs2/super.c:376:2: warning: 'blocknr' may be used uninitialized in this function [-Wuninitialized] fs/nilfs2/super.c:362:11: note: 'blocknr' was declared here CC fs/nilfs2/recovery.o fs/nilfs2/recovery.c: In function 'nilfs_salvage_orphan_logs': fs/nilfs2/recovery.c:631:21: warning: 'sum' may be used uninitialized in this function [-Wuninitialized] fs/nilfs2/recovery.c:585:32: note: 'sum' was declared here fs/nilfs2/recovery.c: In function 'nilfs_search_super_root': fs/nilfs2/recovery.c:873:11: warning: 'sum' may be used uninitialized in this function [-Wuninitialized] Another similar warning is reported in http://kisskb.ellerman.id.au/kisskb/buildresult/12520079/ CC fs/nilfs2/btree.o fs/nilfs2/btree.c: In function 'nilfs_btree_convert_and_insert': include/asm-generic/bitops/non-atomic.h:105:20: warning: 'bh' may be used uninitialized in this function [-Wuninitialized] fs/nilfs2/btree.c:1859:22: note: 'bh' was declared here This cleans out these warnings by forcing the variables to be initialized. Signed-off-by: Ryusuke Konishi Reported-by: Geert Uytterhoeven Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/nilfs2/btree.c | 2 +- fs/nilfs2/recovery.c | 4 ++-- fs/nilfs2/super.c | 5 ++++- 3 files changed, 7 insertions(+), 4 deletions(-) (limited to 'fs') diff --git a/fs/nilfs2/btree.c b/fs/nilfs2/btree.c index f609a8532ec5..3a3821b00486 100644 --- a/fs/nilfs2/btree.c +++ b/fs/nilfs2/btree.c @@ -1851,7 +1851,7 @@ int nilfs_btree_convert_and_insert(struct nilfs_bmap *btree, __u64 key, __u64 ptr, const __u64 *keys, const __u64 *ptrs, int n) { - struct buffer_head *bh; + struct buffer_head *bh = NULL; union nilfs_bmap_ptr_req dreq, nreq, *di, *ni; struct nilfs_bmap_stats stats; int ret; diff --git a/fs/nilfs2/recovery.c b/fs/nilfs2/recovery.c index ff00a0b7acb9..9b4f205d1173 100644 --- a/fs/nilfs2/recovery.c +++ b/fs/nilfs2/recovery.c @@ -582,7 +582,7 @@ static int nilfs_do_roll_forward(struct the_nilfs *nilfs, struct nilfs_recovery_info *ri) { struct buffer_head *bh_sum = NULL; - struct nilfs_segment_summary *sum; + struct nilfs_segment_summary *sum = NULL; sector_t pseg_start; sector_t seg_start, seg_end; /* Starting/ending DBN of full segment */ unsigned long nsalvaged_blocks = 0; @@ -814,7 +814,7 @@ int nilfs_search_super_root(struct the_nilfs *nilfs, struct nilfs_recovery_info *ri) { struct buffer_head *bh_sum = NULL; - struct nilfs_segment_summary *sum; + struct nilfs_segment_summary *sum = NULL; sector_t pseg_start, pseg_end, sr_pseg_start = 0; sector_t seg_start, seg_end; /* range of full segment (block number) */ sector_t b, end; diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c index c69455a543bc..354013ea22ec 100644 --- a/fs/nilfs2/super.c +++ b/fs/nilfs2/super.c @@ -361,7 +361,7 @@ static int nilfs_move_2nd_super(struct super_block *sb, loff_t sb2off) struct nilfs_super_block *nsbp; sector_t blocknr, newblocknr; unsigned long offset; - int sb2i = -1; /* array index of the secondary superblock */ + int sb2i; /* array index of the secondary superblock */ int ret = 0; /* nilfs->ns_sem must be locked by the caller. */ @@ -372,6 +372,9 @@ static int nilfs_move_2nd_super(struct super_block *sb, loff_t sb2off) } else if (nilfs->ns_sbh[0]->b_blocknr > nilfs->ns_first_data_block) { sb2i = 0; blocknr = nilfs->ns_sbh[0]->b_blocknr; + } else { + sb2i = -1; + blocknr = 0; } if (sb2i >= 0 && (u64)blocknr << nilfs->ns_blocksize_bits == sb2off) goto out; /* super block location is unchanged */ -- cgit v1.2.3-70-g09d2 From be0e6f290f78b84a3b21b8c8c46819c4514fe632 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Fri, 6 Nov 2015 16:32:22 -0800 Subject: signal: turn dequeue_signal_lock() into kernel_dequeue_signal() 1. Rename dequeue_signal_lock() to kernel_dequeue_signal(). This matches another "for kthreads only" kernel_sigaction() helper. 2. Remove the "tsk" and "mask" arguments, they are always current and current->blocked. And it is simply wrong if tsk != current. 3. We could also remove the 3rd "siginfo_t *info" arg but it looks potentially useful. However we can simplify the callers if we change kernel_dequeue_signal() to accept info => NULL. 4. Remove _irqsave, it is never called from atomic context. Signed-off-by: Oleg Nesterov Reviewed-by: Tejun Heo Cc: David Woodhouse Cc: Felipe Balbi Cc: Markus Pargmann Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/block/nbd.c | 15 ++++----------- drivers/usb/gadget/function/f_mass_storage.c | 4 +--- fs/jffs2/background.c | 3 +-- include/linux/sched.h | 11 ++++++----- 4 files changed, 12 insertions(+), 21 deletions(-) (limited to 'fs') diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 1b87623381e2..93b3f99b6865 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -444,9 +444,7 @@ static int nbd_thread_recv(struct nbd_device *nbd) spin_unlock_irqrestore(&nbd->tasks_lock, flags); if (signal_pending(current)) { - siginfo_t info; - - ret = dequeue_signal_lock(current, ¤t->blocked, &info); + ret = kernel_dequeue_signal(NULL); dev_warn(nbd_to_dev(nbd), "pid %d, %s, got signal %d\n", task_pid_nr(current), current->comm, ret); mutex_lock(&nbd->tx_lock); @@ -560,11 +558,8 @@ static int nbd_thread_send(void *data) !list_empty(&nbd->waiting_queue)); if (signal_pending(current)) { - siginfo_t info; - int ret; + int ret = kernel_dequeue_signal(NULL); - ret = dequeue_signal_lock(current, ¤t->blocked, - &info); dev_warn(nbd_to_dev(nbd), "pid %d, %s, got signal %d\n", task_pid_nr(current), current->comm, ret); mutex_lock(&nbd->tx_lock); @@ -592,10 +587,8 @@ static int nbd_thread_send(void *data) spin_unlock_irqrestore(&nbd->tasks_lock, flags); /* Clear maybe pending signals */ - if (signal_pending(current)) { - siginfo_t info; - dequeue_signal_lock(current, ¤t->blocked, &info); - } + if (signal_pending(current)) + kernel_dequeue_signal(NULL); return 0; } diff --git a/drivers/usb/gadget/function/f_mass_storage.c b/drivers/usb/gadget/function/f_mass_storage.c index cd54e72a6c50..5ec533826621 100644 --- a/drivers/usb/gadget/function/f_mass_storage.c +++ b/drivers/usb/gadget/function/f_mass_storage.c @@ -2345,7 +2345,6 @@ static void fsg_disable(struct usb_function *f) static void handle_exception(struct fsg_common *common) { - siginfo_t info; int i; struct fsg_buffhd *bh; enum fsg_state old_state; @@ -2357,8 +2356,7 @@ static void handle_exception(struct fsg_common *common) * into a high-priority EXIT exception. */ for (;;) { - int sig = - dequeue_signal_lock(current, ¤t->blocked, &info); + int sig = kernel_dequeue_signal(NULL); if (!sig) break; if (sig != SIGUSR1) { diff --git a/fs/jffs2/background.c b/fs/jffs2/background.c index bb9cebc9ca8a..f3145fd86d86 100644 --- a/fs/jffs2/background.c +++ b/fs/jffs2/background.c @@ -121,13 +121,12 @@ static int jffs2_garbage_collect_thread(void *_c) /* Put_super will send a SIGKILL and then wait on the sem. */ while (signal_pending(current) || freezing(current)) { - siginfo_t info; unsigned long signr; if (try_to_freeze()) goto again; - signr = dequeue_signal_lock(current, ¤t->blocked, &info); + signr = kernel_dequeue_signal(NULL); switch(signr) { case SIGSTOP: diff --git a/include/linux/sched.h b/include/linux/sched.h index 923ec1a9b2b4..3d54924b4b86 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2462,14 +2462,15 @@ extern void ignore_signals(struct task_struct *); extern void flush_signal_handlers(struct task_struct *, int force_default); extern int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info); -static inline int dequeue_signal_lock(struct task_struct *tsk, sigset_t *mask, siginfo_t *info) +static inline int kernel_dequeue_signal(siginfo_t *info) { - unsigned long flags; + struct task_struct *tsk = current; + siginfo_t __info; int ret; - spin_lock_irqsave(&tsk->sighand->siglock, flags); - ret = dequeue_signal(tsk, mask, info); - spin_unlock_irqrestore(&tsk->sighand->siglock, flags); + spin_lock_irq(&tsk->sighand->siglock); + ret = dequeue_signal(tsk, &tsk->blocked, info ?: &__info); + spin_unlock_irq(&tsk->sighand->siglock); return ret; } -- cgit v1.2.3-70-g09d2 From 9a13049e83f346cb1cbd60c64e520a73c396af16 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Fri, 6 Nov 2015 16:32:25 -0800 Subject: signal: introduce kernel_signal_stop() to fix jffs2_garbage_collect_thread() jffs2_garbage_collect_thread() can race with SIGCONT and sleep in TASK_STOPPED state after it was already sent. Add the new helper, kernel_signal_stop(), which does this correctly. Signed-off-by: Oleg Nesterov Reviewed-by: Tejun Heo Cc: David Woodhouse Cc: Felipe Balbi Cc: Markus Pargmann Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/jffs2/background.c | 3 +-- include/linux/sched.h | 10 ++++++++++ 2 files changed, 11 insertions(+), 2 deletions(-) (limited to 'fs') diff --git a/fs/jffs2/background.c b/fs/jffs2/background.c index f3145fd86d86..53cc7350af33 100644 --- a/fs/jffs2/background.c +++ b/fs/jffs2/background.c @@ -132,8 +132,7 @@ static int jffs2_garbage_collect_thread(void *_c) case SIGSTOP: jffs2_dbg(1, "%s(): SIGSTOP received\n", __func__); - set_current_state(TASK_STOPPED); - schedule(); + kernel_signal_stop(); break; case SIGKILL: diff --git a/include/linux/sched.h b/include/linux/sched.h index 3d54924b4b86..4069febaa34a 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2475,6 +2475,16 @@ static inline int kernel_dequeue_signal(siginfo_t *info) return ret; } +static inline void kernel_signal_stop(void) +{ + spin_lock_irq(¤t->sighand->siglock); + if (current->jobctl & JOBCTL_STOP_DEQUEUED) + __set_current_state(TASK_STOPPED); + spin_unlock_irq(¤t->sighand->siglock); + + schedule(); +} + extern void release_task(struct task_struct * p); extern int send_sig_info(int, struct siginfo *, struct task_struct *); extern int force_sigsegv(int, struct task_struct *); -- cgit v1.2.3-70-g09d2 From 9317bb9696566e6759203ffcaa80481b725785b3 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Fri, 6 Nov 2015 16:32:28 -0800 Subject: signal: remove jffs2_garbage_collect_thread()->allow_signal(SIGCONT) jffs2_garbage_collect_thread() does allow_signal(SIGCONT) for no reason, SIGCONT will wake a stopped task up even if it is ignored. Signed-off-by: Oleg Nesterov Reviewed-by: Tejun Heo Cc: David Woodhouse Cc: Felipe Balbi Cc: Markus Pargmann Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/jffs2/background.c | 1 - 1 file changed, 1 deletion(-) (limited to 'fs') diff --git a/fs/jffs2/background.c b/fs/jffs2/background.c index 53cc7350af33..e5c1783ab64a 100644 --- a/fs/jffs2/background.c +++ b/fs/jffs2/background.c @@ -80,7 +80,6 @@ static int jffs2_garbage_collect_thread(void *_c) siginitset(&hupmask, sigmask(SIGHUP)); allow_signal(SIGKILL); allow_signal(SIGSTOP); - allow_signal(SIGCONT); allow_signal(SIGHUP); c->gc_task = current; -- cgit v1.2.3-70-g09d2 From 5fa534c987784c4811757a34c425aff3ce3b5037 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Fri, 6 Nov 2015 16:32:31 -0800 Subject: coredump: ensure all coredumping tasks have SIGNAL_GROUP_COREDUMP task_will_free_mem() is wrong in many ways, and in particular the SIGNAL_GROUP_COREDUMP check is not reliable: a task can participate in the coredumping without SIGNAL_GROUP_COREDUMP bit set. change zap_threads() paths to always set SIGNAL_GROUP_COREDUMP even if other CLONE_VM processes can't react to SIGKILL. Fortunately, at least oom-kill case if fine; it kills all tasks sharing the same mm, so it should also kill the process which actually dumps the core. The change in prepare_signal() is not strictly necessary, it just ensures that the patch does not bring another subtle behavioural change. But it reminds us that this SIGNAL_GROUP_EXIT/COREDUMP case needs more changes. Signed-off-by: Oleg Nesterov Cc: David Rientjes Cc: Kyle Walker Acked-by: Michal Hocko Cc: Stanislav Kozina Cc: Tetsuo Handa Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/coredump.c | 12 ++++++------ kernel/signal.c | 2 +- 2 files changed, 7 insertions(+), 7 deletions(-) (limited to 'fs') diff --git a/fs/coredump.c b/fs/coredump.c index a8f75640ac86..c66bb0572265 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -280,11 +280,13 @@ out: return ispipe; } -static int zap_process(struct task_struct *start, int exit_code) +static int zap_process(struct task_struct *start, int exit_code, int flags) { struct task_struct *t; int nr = 0; + /* ignore all signals except SIGKILL, see prepare_signal() */ + start->signal->flags = SIGNAL_GROUP_COREDUMP | flags; start->signal->group_exit_code = exit_code; start->signal->group_stop_count = 0; @@ -311,10 +313,8 @@ static int zap_threads(struct task_struct *tsk, struct mm_struct *mm, spin_lock_irq(&tsk->sighand->siglock); if (!signal_group_exit(tsk->signal)) { mm->core_state = core_state; - nr = zap_process(tsk, exit_code); tsk->signal->group_exit_task = tsk; - /* ignore all signals except SIGKILL, see prepare_signal() */ - tsk->signal->flags = SIGNAL_GROUP_COREDUMP; + nr = zap_process(tsk, exit_code, 0); clear_tsk_thread_flag(tsk, TIF_SIGPENDING); } spin_unlock_irq(&tsk->sighand->siglock); @@ -365,8 +365,8 @@ static int zap_threads(struct task_struct *tsk, struct mm_struct *mm, if (p->mm) { if (unlikely(p->mm == mm)) { lock_task_sighand(p, &flags); - nr += zap_process(p, exit_code); - p->signal->flags = SIGNAL_GROUP_EXIT; + nr += zap_process(p, exit_code, + SIGNAL_GROUP_EXIT); unlock_task_sighand(p, &flags); } break; diff --git a/kernel/signal.c b/kernel/signal.c index f2cbd4ed5cd4..c0b01fe24bbd 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -788,7 +788,7 @@ static bool prepare_signal(int sig, struct task_struct *p, bool force) sigset_t flush; if (signal->flags & (SIGNAL_GROUP_EXIT | SIGNAL_GROUP_COREDUMP)) { - if (signal->flags & SIGNAL_GROUP_COREDUMP) + if (!(signal->flags & SIGNAL_GROUP_EXIT)) return sig == SIGKILL; /* * The process is in the middle of dying, nothing to do. -- cgit v1.2.3-70-g09d2 From d61ba58953fcf708c850bfd90b2858f2ddfbc34c Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Fri, 6 Nov 2015 16:32:34 -0800 Subject: coredump: change zap_threads() and zap_process() to use for_each_thread() Change zap_threads() paths to use for_each_thread() rather than while_each_thread(). While at it, change zap_threads() to avoid the nested if's to make the code more readable and lessen the indentation. Signed-off-by: Oleg Nesterov Cc: David Rientjes Cc: Kyle Walker Cc: Michal Hocko Cc: Stanislav Kozina Cc: Tetsuo Handa Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/coredump.c | 27 +++++++++++++-------------- 1 file changed, 13 insertions(+), 14 deletions(-) (limited to 'fs') diff --git a/fs/coredump.c b/fs/coredump.c index c66bb0572265..1777331eee76 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -290,15 +290,14 @@ static int zap_process(struct task_struct *start, int exit_code, int flags) start->signal->group_exit_code = exit_code; start->signal->group_stop_count = 0; - t = start; - do { + for_each_thread(start, t) { task_clear_jobctl_pending(t, JOBCTL_PENDING_MASK); if (t != current && t->mm) { sigaddset(&t->pending.signal, SIGKILL); signal_wake_up(t, 1); nr++; } - } while_each_thread(start, t); + } return nr; } @@ -360,18 +359,18 @@ static int zap_threads(struct task_struct *tsk, struct mm_struct *mm, continue; if (g->flags & PF_KTHREAD) continue; - p = g; - do { - if (p->mm) { - if (unlikely(p->mm == mm)) { - lock_task_sighand(p, &flags); - nr += zap_process(p, exit_code, - SIGNAL_GROUP_EXIT); - unlock_task_sighand(p, &flags); - } - break; + + for_each_thread(g, p) { + if (unlikely(!p->mm)) + continue; + if (unlikely(p->mm == mm)) { + lock_task_sighand(p, &flags); + nr += zap_process(p, exit_code, + SIGNAL_GROUP_EXIT); + unlock_task_sighand(p, &flags); } - } while_each_thread(g, p); + break; + } } rcu_read_unlock(); done: -- cgit v1.2.3-70-g09d2 From 8b91a318e422a0201a7bd7ac2626eecec6b27ae1 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 6 Nov 2015 16:32:37 -0800 Subject: fs/seq_file: use seq_* helpers in seq_hex_dump() This improves code readability. Signed-off-by: Andy Shevchenko Cc: Alexander Viro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/seq_file.c | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) (limited to 'fs') diff --git a/fs/seq_file.c b/fs/seq_file.c index 225586e141ca..ad034fb49f30 100644 --- a/fs/seq_file.c +++ b/fs/seq_file.c @@ -773,6 +773,8 @@ void seq_hex_dump(struct seq_file *m, const char *prefix_str, int prefix_type, { const u8 *ptr = buf; int i, linelen, remaining = len; + char *buffer; + size_t size; int ret; if (rowsize != 16 && rowsize != 32) @@ -794,15 +796,12 @@ void seq_hex_dump(struct seq_file *m, const char *prefix_str, int prefix_type, break; } + size = seq_get_buf(m, &buffer); ret = hex_dump_to_buffer(ptr + i, linelen, rowsize, groupsize, - m->buf + m->count, m->size - m->count, - ascii); - if (ret >= m->size - m->count) { - seq_set_overflow(m); - } else { - m->count += ret; - seq_putc(m, '\n'); - } + buffer, size, ascii); + seq_commit(m, ret < size ? ret : -1); + + seq_putc(m, '\n'); } } EXPORT_SYMBOL(seq_hex_dump); -- cgit v1.2.3-70-g09d2 From 25c6bb76eafe37c8963ae58a6a1bcf4069caeedb Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 6 Nov 2015 16:32:40 -0800 Subject: seq_file: reuse string_escape_str() strint_escape_str() escapes input string by given criteria. In case of seq_escape() the criteria is to convert some characters to their octal representation. Signed-off-by: Andy Shevchenko Cc: Alexander Viro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/seq_file.c | 25 ++++++------------------- 1 file changed, 6 insertions(+), 19 deletions(-) (limited to 'fs') diff --git a/fs/seq_file.c b/fs/seq_file.c index ad034fb49f30..00bbe2bfc634 100644 --- a/fs/seq_file.c +++ b/fs/seq_file.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include @@ -377,26 +378,12 @@ EXPORT_SYMBOL(seq_release); */ void seq_escape(struct seq_file *m, const char *s, const char *esc) { - char *end = m->buf + m->size; - char *p; - char c; + char *buf; + size_t size = seq_get_buf(m, &buf); + int ret; - for (p = m->buf + m->count; (c = *s) != '\0' && p < end; s++) { - if (!strchr(esc, c)) { - *p++ = c; - continue; - } - if (p + 3 < end) { - *p++ = '\\'; - *p++ = '0' + ((c & 0300) >> 6); - *p++ = '0' + ((c & 070) >> 3); - *p++ = '0' + (c & 07); - continue; - } - seq_set_overflow(m); - return; - } - m->count = p - m->buf; + ret = string_escape_str(s, buf, size, ESCAPE_OCTAL, esc); + seq_commit(m, ret < size ? ret : -1); } EXPORT_SYMBOL(seq_escape); -- cgit v1.2.3-70-g09d2 From 0f930902eb8806cff8dcaef9ff9faf3cfa5fd748 Mon Sep 17 00:00:00 2001 From: Greg Thelen Date: Fri, 6 Nov 2015 16:32:42 -0800 Subject: fs, seqfile: always allow oom killer Since 5cec38ac866b ("fs, seq_file: fallback to vmalloc instead of oom kill processes") seq_buf_alloc() avoids calling the oom killer for PAGE_SIZE or smaller allocations; but larger allocations can use the oom killer via vmalloc(). Thus reads of small files can return ENOMEM, but larger files use the oom killer to avoid ENOMEM. The effect of this bug is that reads from /proc and other virtual filesystems can return ENOMEM instead of the preferred behavior - oom killing something (possibly the calling process). I don't know of anyone except Google who has noticed the issue. I suspect the fix is more needed in smaller systems where there isn't any reclaimable memory. But these seem like the kinds of systems which probably don't use the oom killer for production situations. Memory overcommit requires use of the oom killer to select a victim regardless of file size. Enable oom killer for small seq_buf_alloc() allocations. Fixes: 5cec38ac866b ("fs, seq_file: fallback to vmalloc instead of oom kill processes") Signed-off-by: David Rientjes Signed-off-by: Greg Thelen Acked-by: Eric Dumazet Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/seq_file.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) (limited to 'fs') diff --git a/fs/seq_file.c b/fs/seq_file.c index 00bbe2bfc634..e85664b7c7d9 100644 --- a/fs/seq_file.c +++ b/fs/seq_file.c @@ -26,12 +26,17 @@ static void seq_set_overflow(struct seq_file *m) static void *seq_buf_alloc(unsigned long size) { void *buf; + gfp_t gfp = GFP_KERNEL; /* - * __GFP_NORETRY to avoid oom-killings with high-order allocations - - * it's better to fall back to vmalloc() than to kill things. + * For high order allocations, use __GFP_NORETRY to avoid oom-killing - + * it's better to fall back to vmalloc() than to kill things. For small + * allocations, just use GFP_KERNEL which will oom kill, thus no need + * for vmalloc fallback. */ - buf = kmalloc(size, GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN); + if (size > PAGE_SIZE) + gfp |= __GFP_NORETRY | __GFP_NOWARN; + buf = kmalloc(size, gfp); if (!buf && size > PAGE_SIZE) buf = vmalloc(size); return buf; -- cgit v1.2.3-70-g09d2