From 8a072a4d4c6a5b6ec32836c467d2996393c76c6f Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sun, 24 Apr 2011 19:06:17 +0000 Subject: xfs: reduce the number of pagb_lock roundtrips in xfs_alloc_clear_busy Instead of finding the per-ag and then taking and releasing the pagb_lock for every single busy extent completed sort the list of busy extents and only switch betweens AGs where nessecary. This becomes especially important with the online discard support which will hit this lock more often. Signed-off-by: Christoph Hellwig Signed-off-by: Alex Elder --- fs/xfs/linux-2.6/xfs_buf.c | 1 - 1 file changed, 1 deletion(-) (limited to 'fs/xfs/linux-2.6/xfs_buf.c') diff --git a/fs/xfs/linux-2.6/xfs_buf.c b/fs/xfs/linux-2.6/xfs_buf.c index 9ef9ed2cfe2..09889035765 100644 --- a/fs/xfs/linux-2.6/xfs_buf.c +++ b/fs/xfs/linux-2.6/xfs_buf.c @@ -33,7 +33,6 @@ #include #include #include -#include #include "xfs_sb.h" #include "xfs_inum.h" -- cgit v1.2.3-70-g09d2 From 44396476a0f24e5174768d3732f1958857c26d22 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Thu, 21 Apr 2011 09:34:27 +0000 Subject: xfs: reset buffer pointers before freeing them When we free a vmapped buffer, we need to ensure the vmap address and length we free is the same as when it was allocated. In various places in the log code we change the memory the buffer is pointing to before issuing IO, but we never reset the buffer to point back to it's original memory (or no memory, if that is the case for the buffer). As a result, when we free the buffer it points to memory that is owned by something else and attempts to unmap and free it. Because the range does not match any known mapped range, it can trigger BUG_ON() traps in the vmap code, and potentially corrupt the vmap area tracking. Fix this by always resetting these buffers to their original state before freeing them. Signed-off-by: Dave Chinner Reviewed-by: Christoph Hellwig Signed-off-by: Alex Elder --- fs/xfs/linux-2.6/xfs_buf.c | 21 +++++++++++++ fs/xfs/linux-2.6/xfs_buf.h | 1 + fs/xfs/xfs_log.c | 8 ++++- fs/xfs/xfs_log_recover.c | 75 +++++++++++++++++++++++----------------------- 4 files changed, 67 insertions(+), 38 deletions(-) (limited to 'fs/xfs/linux-2.6/xfs_buf.c') diff --git a/fs/xfs/linux-2.6/xfs_buf.c b/fs/xfs/linux-2.6/xfs_buf.c index 09889035765..52b2b5da566 100644 --- a/fs/xfs/linux-2.6/xfs_buf.c +++ b/fs/xfs/linux-2.6/xfs_buf.c @@ -708,6 +708,27 @@ xfs_buf_get_empty( return bp; } +/* + * Return a buffer allocated as an empty buffer and associated to external + * memory via xfs_buf_associate_memory() back to it's empty state. + */ +void +xfs_buf_set_empty( + struct xfs_buf *bp, + size_t len) +{ + if (bp->b_pages) + _xfs_buf_free_pages(bp); + + bp->b_pages = NULL; + bp->b_page_count = 0; + bp->b_addr = NULL; + bp->b_file_offset = 0; + bp->b_buffer_length = bp->b_count_desired = len; + bp->b_bn = XFS_BUF_DADDR_NULL; + bp->b_flags &= ~XBF_MAPPED; +} + static inline struct page * mem_to_page( void *addr) diff --git a/fs/xfs/linux-2.6/xfs_buf.h b/fs/xfs/linux-2.6/xfs_buf.h index a9a1c451264..50a7d5fb3b7 100644 --- a/fs/xfs/linux-2.6/xfs_buf.h +++ b/fs/xfs/linux-2.6/xfs_buf.h @@ -178,6 +178,7 @@ extern xfs_buf_t *xfs_buf_read(xfs_buftarg_t *, xfs_off_t, size_t, xfs_buf_flags_t); extern xfs_buf_t *xfs_buf_get_empty(size_t, xfs_buftarg_t *); +extern void xfs_buf_set_empty(struct xfs_buf *bp, size_t len); extern xfs_buf_t *xfs_buf_get_uncached(struct xfs_buftarg *, size_t, int); extern int xfs_buf_associate_memory(xfs_buf_t *, void *, size_t); extern void xfs_buf_hold(xfs_buf_t *); diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c index 18fd4beffcc..211930246f2 100644 --- a/fs/xfs/xfs_log.c +++ b/fs/xfs/xfs_log.c @@ -1449,6 +1449,13 @@ xlog_dealloc_log(xlog_t *log) xlog_cil_destroy(log); + /* + * always need to ensure that the extra buffer does not point to memory + * owned by another log buffer before we free it. + */ + xfs_buf_set_empty(log->l_xbuf, log->l_iclog_size); + xfs_buf_free(log->l_xbuf); + iclog = log->l_iclog; for (i=0; il_iclog_bufs; i++) { xfs_buf_free(iclog->ic_bp); @@ -1458,7 +1465,6 @@ xlog_dealloc_log(xlog_t *log) } spinlock_destroy(&log->l_icloglock); - xfs_buf_free(log->l_xbuf); log->l_mp->m_log = NULL; kmem_free(log); } /* xlog_dealloc_log */ diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c index 5cc464a17c9..04142caedb2 100644 --- a/fs/xfs/xfs_log_recover.c +++ b/fs/xfs/xfs_log_recover.c @@ -204,6 +204,35 @@ xlog_bread( return 0; } +/* + * Read at an offset into the buffer. Returns with the buffer in it's original + * state regardless of the result of the read. + */ +STATIC int +xlog_bread_offset( + xlog_t *log, + xfs_daddr_t blk_no, /* block to read from */ + int nbblks, /* blocks to read */ + xfs_buf_t *bp, + xfs_caddr_t offset) +{ + xfs_caddr_t orig_offset = XFS_BUF_PTR(bp); + int orig_len = bp->b_buffer_length; + int error, error2; + + error = XFS_BUF_SET_PTR(bp, offset, BBTOB(nbblks)); + if (error) + return error; + + error = xlog_bread_noalign(log, blk_no, nbblks, bp); + + /* must reset buffer pointer even on error */ + error2 = XFS_BUF_SET_PTR(bp, orig_offset, orig_len); + if (error) + return error; + return error2; +} + /* * Write out the buffer at the given block for the given number of blocks. * The buffer is kept locked across the write and is returned locked. @@ -1229,20 +1258,12 @@ xlog_write_log_records( */ ealign = round_down(end_block, sectbb); if (j == 0 && (start_block + endcount > ealign)) { - offset = XFS_BUF_PTR(bp); - balign = BBTOB(ealign - start_block); - error = XFS_BUF_SET_PTR(bp, offset + balign, - BBTOB(sectbb)); + offset = XFS_BUF_PTR(bp) + BBTOB(ealign - start_block); + error = xlog_bread_offset(log, ealign, sectbb, + bp, offset); if (error) break; - error = xlog_bread_noalign(log, ealign, sectbb, bp); - if (error) - break; - - error = XFS_BUF_SET_PTR(bp, offset, bufblks); - if (error) - break; } offset = xlog_align(log, start_block, endcount, bp); @@ -3448,19 +3469,9 @@ xlog_do_recovery_pass( * - order is important. */ wrapped_hblks = hblks - split_hblks; - error = XFS_BUF_SET_PTR(hbp, - offset + BBTOB(split_hblks), - BBTOB(hblks - split_hblks)); - if (error) - goto bread_err2; - - error = xlog_bread_noalign(log, 0, - wrapped_hblks, hbp); - if (error) - goto bread_err2; - - error = XFS_BUF_SET_PTR(hbp, offset, - BBTOB(hblks)); + error = xlog_bread_offset(log, 0, + wrapped_hblks, hbp, + offset + BBTOB(split_hblks)); if (error) goto bread_err2; } @@ -3511,19 +3522,9 @@ xlog_do_recovery_pass( * _first_, then the log start (LR header end) * - order is important. */ - error = XFS_BUF_SET_PTR(dbp, - offset + BBTOB(split_bblks), - BBTOB(bblks - split_bblks)); - if (error) - goto bread_err2; - - error = xlog_bread_noalign(log, wrapped_hblks, - bblks - split_bblks, - dbp); - if (error) - goto bread_err2; - - error = XFS_BUF_SET_PTR(dbp, offset, h_size); + error = xlog_bread_offset(log, 0, + bblks - split_bblks, hbp, + offset + BBTOB(split_bblks)); if (error) goto bread_err2; } -- cgit v1.2.3-70-g09d2 From 1495f230fa7750479c79e3656286b9183d662077 Mon Sep 17 00:00:00 2001 From: Ying Han Date: Tue, 24 May 2011 17:12:27 -0700 Subject: vmscan: change shrinker API by passing shrink_control struct Change each shrinker's API by consolidating the existing parameters into shrink_control struct. This will simplify any further features added w/o touching each file of shrinker. [akpm@linux-foundation.org: fix build] [akpm@linux-foundation.org: fix warning] [kosaki.motohiro@jp.fujitsu.com: fix up new shrinker API] [akpm@linux-foundation.org: fix xfs warning] [akpm@linux-foundation.org: update gfs2] Signed-off-by: Ying Han Cc: KOSAKI Motohiro Cc: Minchan Kim Acked-by: Pavel Emelyanov Cc: KAMEZAWA Hiroyuki Cc: Mel Gorman Acked-by: Rik van Riel Cc: Johannes Weiner Cc: Hugh Dickins Cc: Dave Hansen Cc: Steven Whitehouse Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/kvm/mmu.c | 3 ++- drivers/gpu/drm/i915/i915_gem.c | 9 +++------ drivers/gpu/drm/ttm/ttm_page_alloc.c | 4 +++- drivers/staging/zcache/zcache.c | 5 ++++- fs/dcache.c | 8 ++++++-- fs/drop_caches.c | 3 +-- fs/gfs2/glock.c | 5 ++++- fs/gfs2/quota.c | 12 +++++++----- fs/gfs2/quota.h | 4 +++- fs/inode.c | 6 +++++- fs/mbcache.c | 10 ++++++---- fs/nfs/dir.c | 5 ++++- fs/nfs/internal.h | 2 +- fs/quota/dquot.c | 5 ++++- fs/xfs/linux-2.6/xfs_buf.c | 4 ++-- fs/xfs/linux-2.6/xfs_sync.c | 5 +++-- fs/xfs/quota/xfs_qm.c | 6 +++--- include/linux/mm.h | 19 +++++++++++-------- mm/memory-failure.c | 3 +-- mm/vmscan.c | 34 +++++++++++++++++++--------------- net/sunrpc/auth.c | 4 +++- 21 files changed, 95 insertions(+), 61 deletions(-) (limited to 'fs/xfs/linux-2.6/xfs_buf.c') diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 28418054b88..bd14bb4c859 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -3545,10 +3545,11 @@ static int kvm_mmu_remove_some_alloc_mmu_pages(struct kvm *kvm, return kvm_mmu_prepare_zap_page(kvm, page, invalid_list); } -static int mmu_shrink(struct shrinker *shrink, int nr_to_scan, gfp_t gfp_mask) +static int mmu_shrink(struct shrinker *shrink, struct shrink_control *sc) { struct kvm *kvm; struct kvm *kvm_freed = NULL; + int nr_to_scan = sc->nr_to_scan; if (nr_to_scan == 0) goto out; diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index c6289034e29..0b2e167d2bc 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -56,9 +56,7 @@ static int i915_gem_phys_pwrite(struct drm_device *dev, static void i915_gem_free_object_tail(struct drm_i915_gem_object *obj); static int i915_gem_inactive_shrink(struct shrinker *shrinker, - int nr_to_scan, - gfp_t gfp_mask); - + struct shrink_control *sc); /* some bookkeeping */ static void i915_gem_info_add_obj(struct drm_i915_private *dev_priv, @@ -4092,9 +4090,7 @@ i915_gpu_is_active(struct drm_device *dev) } static int -i915_gem_inactive_shrink(struct shrinker *shrinker, - int nr_to_scan, - gfp_t gfp_mask) +i915_gem_inactive_shrink(struct shrinker *shrinker, struct shrink_control *sc) { struct drm_i915_private *dev_priv = container_of(shrinker, @@ -4102,6 +4098,7 @@ i915_gem_inactive_shrink(struct shrinker *shrinker, mm.inactive_shrinker); struct drm_device *dev = dev_priv->dev; struct drm_i915_gem_object *obj, *next; + int nr_to_scan = sc->nr_to_scan; int cnt; if (!mutex_trylock(&dev->struct_mutex)) diff --git a/drivers/gpu/drm/ttm/ttm_page_alloc.c b/drivers/gpu/drm/ttm/ttm_page_alloc.c index 9d9d92945f8..d948575717b 100644 --- a/drivers/gpu/drm/ttm/ttm_page_alloc.c +++ b/drivers/gpu/drm/ttm/ttm_page_alloc.c @@ -395,12 +395,14 @@ static int ttm_pool_get_num_unused_pages(void) /** * Callback for mm to request pool to reduce number of page held. */ -static int ttm_pool_mm_shrink(struct shrinker *shrink, int shrink_pages, gfp_t gfp_mask) +static int ttm_pool_mm_shrink(struct shrinker *shrink, + struct shrink_control *sc) { static atomic_t start_pool = ATOMIC_INIT(0); unsigned i; unsigned pool_offset = atomic_add_return(1, &start_pool); struct ttm_page_pool *pool; + int shrink_pages = sc->nr_to_scan; pool_offset = pool_offset % NUM_POOLS; /* select start pool in round robin fashion */ diff --git a/drivers/staging/zcache/zcache.c b/drivers/staging/zcache/zcache.c index b8a2b30a157..77ac2d4d3ef 100644 --- a/drivers/staging/zcache/zcache.c +++ b/drivers/staging/zcache/zcache.c @@ -1181,9 +1181,12 @@ static bool zcache_freeze; /* * zcache shrinker interface (only useful for ephemeral pages, so zbud only) */ -static int shrink_zcache_memory(struct shrinker *shrink, int nr, gfp_t gfp_mask) +static int shrink_zcache_memory(struct shrinker *shrink, + struct shrink_control *sc) { int ret = -1; + int nr = sc->nr_to_scan; + gfp_t gfp_mask = sc->gfp_mask; if (nr >= 0) { if (!(gfp_mask & __GFP_FS)) diff --git a/fs/dcache.c b/fs/dcache.c index 18b2a1f10ed..37f72ee5bf7 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -1220,7 +1220,7 @@ void shrink_dcache_parent(struct dentry * parent) EXPORT_SYMBOL(shrink_dcache_parent); /* - * Scan `nr' dentries and return the number which remain. + * Scan `sc->nr_slab_to_reclaim' dentries and return the number which remain. * * We need to avoid reentering the filesystem if the caller is performing a * GFP_NOFS allocation attempt. One example deadlock is: @@ -1231,8 +1231,12 @@ EXPORT_SYMBOL(shrink_dcache_parent); * * In this case we return -1 to tell the caller that we baled. */ -static int shrink_dcache_memory(struct shrinker *shrink, int nr, gfp_t gfp_mask) +static int shrink_dcache_memory(struct shrinker *shrink, + struct shrink_control *sc) { + int nr = sc->nr_to_scan; + gfp_t gfp_mask = sc->gfp_mask; + if (nr) { if (!(gfp_mask & __GFP_FS)) return -1; diff --git a/fs/drop_caches.c b/fs/drop_caches.c index 440999c2435..c00e055b628 100644 --- a/fs/drop_caches.c +++ b/fs/drop_caches.c @@ -42,11 +42,10 @@ static void drop_slab(void) int nr_objects; struct shrink_control shrink = { .gfp_mask = GFP_KERNEL, - .nr_scanned = 1000, }; do { - nr_objects = shrink_slab(&shrink, 1000); + nr_objects = shrink_slab(&shrink, 1000, 1000); } while (nr_objects > 10); } diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index a2a6abbccc0..2792a790e50 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -1346,11 +1346,14 @@ void gfs2_glock_complete(struct gfs2_glock *gl, int ret) } -static int gfs2_shrink_glock_memory(struct shrinker *shrink, int nr, gfp_t gfp_mask) +static int gfs2_shrink_glock_memory(struct shrinker *shrink, + struct shrink_control *sc) { struct gfs2_glock *gl; int may_demote; int nr_skipped = 0; + int nr = sc->nr_to_scan; + gfp_t gfp_mask = sc->gfp_mask; LIST_HEAD(skipped); if (nr == 0) diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c index e23d9864c41..42e8d23bc04 100644 --- a/fs/gfs2/quota.c +++ b/fs/gfs2/quota.c @@ -38,6 +38,7 @@ #include #include +#include #include #include #include @@ -77,19 +78,20 @@ static LIST_HEAD(qd_lru_list); static atomic_t qd_lru_count = ATOMIC_INIT(0); static DEFINE_SPINLOCK(qd_lru_lock); -int gfs2_shrink_qd_memory(struct shrinker *shrink, int nr, gfp_t gfp_mask) +int gfs2_shrink_qd_memory(struct shrinker *shrink, struct shrink_control *sc) { struct gfs2_quota_data *qd; struct gfs2_sbd *sdp; + int nr_to_scan = sc->nr_to_scan; - if (nr == 0) + if (nr_to_scan == 0) goto out; - if (!(gfp_mask & __GFP_FS)) + if (!(sc->gfp_mask & __GFP_FS)) return -1; spin_lock(&qd_lru_lock); - while (nr && !list_empty(&qd_lru_list)) { + while (nr_to_scan && !list_empty(&qd_lru_list)) { qd = list_entry(qd_lru_list.next, struct gfs2_quota_data, qd_reclaim); sdp = qd->qd_gl->gl_sbd; @@ -110,7 +112,7 @@ int gfs2_shrink_qd_memory(struct shrinker *shrink, int nr, gfp_t gfp_mask) spin_unlock(&qd_lru_lock); kmem_cache_free(gfs2_quotad_cachep, qd); spin_lock(&qd_lru_lock); - nr--; + nr_to_scan--; } spin_unlock(&qd_lru_lock); diff --git a/fs/gfs2/quota.h b/fs/gfs2/quota.h index e7d236ca48b..90bf1c302a9 100644 --- a/fs/gfs2/quota.h +++ b/fs/gfs2/quota.h @@ -12,6 +12,7 @@ struct gfs2_inode; struct gfs2_sbd; +struct shrink_control; #define NO_QUOTA_CHANGE ((u32)-1) @@ -51,7 +52,8 @@ static inline int gfs2_quota_lock_check(struct gfs2_inode *ip) return ret; } -extern int gfs2_shrink_qd_memory(struct shrinker *shrink, int nr, gfp_t gfp_mask); +extern int gfs2_shrink_qd_memory(struct shrinker *shrink, + struct shrink_control *sc); extern const struct quotactl_ops gfs2_quotactl_ops; #endif /* __QUOTA_DOT_H__ */ diff --git a/fs/inode.c b/fs/inode.c index 88aa3bcc768..990d284877a 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -751,8 +751,12 @@ static void prune_icache(int nr_to_scan) * This function is passed the number of inodes to scan, and it returns the * total number of remaining possibly-reclaimable inodes. */ -static int shrink_icache_memory(struct shrinker *shrink, int nr, gfp_t gfp_mask) +static int shrink_icache_memory(struct shrinker *shrink, + struct shrink_control *sc) { + int nr = sc->nr_to_scan; + gfp_t gfp_mask = sc->gfp_mask; + if (nr) { /* * Nasty deadlock avoidance. We may hold various FS locks, diff --git a/fs/mbcache.c b/fs/mbcache.c index 2f174be0655..8c32ef3ba88 100644 --- a/fs/mbcache.c +++ b/fs/mbcache.c @@ -90,7 +90,8 @@ static DEFINE_SPINLOCK(mb_cache_spinlock); * What the mbcache registers as to get shrunk dynamically. */ -static int mb_cache_shrink_fn(struct shrinker *shrink, int nr_to_scan, gfp_t gfp_mask); +static int mb_cache_shrink_fn(struct shrinker *shrink, + struct shrink_control *sc); static struct shrinker mb_cache_shrinker = { .shrink = mb_cache_shrink_fn, @@ -156,18 +157,19 @@ forget: * gets low. * * @shrink: (ignored) - * @nr_to_scan: Number of objects to scan - * @gfp_mask: (ignored) + * @sc: shrink_control passed from reclaim * * Returns the number of objects which are present in the cache. */ static int -mb_cache_shrink_fn(struct shrinker *shrink, int nr_to_scan, gfp_t gfp_mask) +mb_cache_shrink_fn(struct shrinker *shrink, struct shrink_control *sc) { LIST_HEAD(free_list); struct mb_cache *cache; struct mb_cache_entry *entry, *tmp; int count = 0; + int nr_to_scan = sc->nr_to_scan; + gfp_t gfp_mask = sc->gfp_mask; mb_debug("trying to free %d entries", nr_to_scan); spin_lock(&mb_cache_spinlock); diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 7237672216c..424e47773a8 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -2042,11 +2042,14 @@ static void nfs_access_free_list(struct list_head *head) } } -int nfs_access_cache_shrinker(struct shrinker *shrink, int nr_to_scan, gfp_t gfp_mask) +int nfs_access_cache_shrinker(struct shrinker *shrink, + struct shrink_control *sc) { LIST_HEAD(head); struct nfs_inode *nfsi, *next; struct nfs_access_entry *cache; + int nr_to_scan = sc->nr_to_scan; + gfp_t gfp_mask = sc->gfp_mask; if ((gfp_mask & GFP_KERNEL) != GFP_KERNEL) return (nr_to_scan == 0) ? 0 : -1; diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index ce118ce885d..2df6ca7b589 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -234,7 +234,7 @@ extern int nfs_init_client(struct nfs_client *clp, /* dir.c */ extern int nfs_access_cache_shrinker(struct shrinker *shrink, - int nr_to_scan, gfp_t gfp_mask); + struct shrink_control *sc); /* inode.c */ extern struct workqueue_struct *nfsiod_workqueue; diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index d3c032f5fa0..5b572c89e6c 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -691,8 +691,11 @@ static void prune_dqcache(int count) * This is called from kswapd when we think we need some * more memory */ -static int shrink_dqcache_memory(struct shrinker *shrink, int nr, gfp_t gfp_mask) +static int shrink_dqcache_memory(struct shrinker *shrink, + struct shrink_control *sc) { + int nr = sc->nr_to_scan; + if (nr) { spin_lock(&dq_list_lock); prune_dqcache(nr); diff --git a/fs/xfs/linux-2.6/xfs_buf.c b/fs/xfs/linux-2.6/xfs_buf.c index 52b2b5da566..5e68099db2a 100644 --- a/fs/xfs/linux-2.6/xfs_buf.c +++ b/fs/xfs/linux-2.6/xfs_buf.c @@ -1422,12 +1422,12 @@ restart: int xfs_buftarg_shrink( struct shrinker *shrink, - int nr_to_scan, - gfp_t mask) + struct shrink_control *sc) { struct xfs_buftarg *btp = container_of(shrink, struct xfs_buftarg, bt_shrinker); struct xfs_buf *bp; + int nr_to_scan = sc->nr_to_scan; LIST_HEAD(dispose); if (!nr_to_scan) diff --git a/fs/xfs/linux-2.6/xfs_sync.c b/fs/xfs/linux-2.6/xfs_sync.c index cb1bb2080e4..8ecad5ff9f9 100644 --- a/fs/xfs/linux-2.6/xfs_sync.c +++ b/fs/xfs/linux-2.6/xfs_sync.c @@ -1032,13 +1032,14 @@ xfs_reclaim_inodes( static int xfs_reclaim_inode_shrink( struct shrinker *shrink, - int nr_to_scan, - gfp_t gfp_mask) + struct shrink_control *sc) { struct xfs_mount *mp; struct xfs_perag *pag; xfs_agnumber_t ag; int reclaimable; + int nr_to_scan = sc->nr_to_scan; + gfp_t gfp_mask = sc->gfp_mask; mp = container_of(shrink, struct xfs_mount, m_inode_shrink); if (nr_to_scan) { diff --git a/fs/xfs/quota/xfs_qm.c b/fs/xfs/quota/xfs_qm.c index 69228aa8605..b94dace4e78 100644 --- a/fs/xfs/quota/xfs_qm.c +++ b/fs/xfs/quota/xfs_qm.c @@ -60,7 +60,7 @@ STATIC void xfs_qm_list_destroy(xfs_dqlist_t *); STATIC int xfs_qm_init_quotainos(xfs_mount_t *); STATIC int xfs_qm_init_quotainfo(xfs_mount_t *); -STATIC int xfs_qm_shake(struct shrinker *, int, gfp_t); +STATIC int xfs_qm_shake(struct shrinker *, struct shrink_control *); static struct shrinker xfs_qm_shaker = { .shrink = xfs_qm_shake, @@ -2009,10 +2009,10 @@ xfs_qm_shake_freelist( STATIC int xfs_qm_shake( struct shrinker *shrink, - int nr_to_scan, - gfp_t gfp_mask) + struct shrink_control *sc) { int ndqused, nfree, n; + gfp_t gfp_mask = sc->gfp_mask; if (!kmem_shake_allow(gfp_mask)) return 0; diff --git a/include/linux/mm.h b/include/linux/mm.h index 32cfa9602d0..5cbbf78eaac 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1166,18 +1166,20 @@ static inline void sync_mm_rss(struct task_struct *task, struct mm_struct *mm) * We consolidate the values for easier extention later. */ struct shrink_control { - unsigned long nr_scanned; gfp_t gfp_mask; + + /* How many slab objects shrinker() should scan and try to reclaim */ + unsigned long nr_to_scan; }; /* * A callback you can register to apply pressure to ageable caches. * - * 'shrink' is passed a count 'nr_to_scan' and a 'gfpmask'. It should - * look through the least-recently-used 'nr_to_scan' entries and - * attempt to free them up. It should return the number of objects - * which remain in the cache. If it returns -1, it means it cannot do - * any scanning at this time (eg. there is a risk of deadlock). + * 'sc' is passed shrink_control which includes a count 'nr_to_scan' + * and a 'gfpmask'. It should look through the least-recently-used + * 'nr_to_scan' entries and attempt to free them up. It should return + * the number of objects which remain in the cache. If it returns -1, it means + * it cannot do any scanning at this time (eg. there is a risk of deadlock). * * The 'gfpmask' refers to the allocation we are currently trying to * fulfil. @@ -1186,7 +1188,7 @@ struct shrink_control { * querying the cache size, so a fastpath for that case is appropriate. */ struct shrinker { - int (*shrink)(struct shrinker *, int nr_to_scan, gfp_t gfp_mask); + int (*shrink)(struct shrinker *, struct shrink_control *sc); int seeks; /* seeks to recreate an obj */ /* These are for internal use */ @@ -1640,7 +1642,8 @@ int in_gate_area_no_mm(unsigned long addr); int drop_caches_sysctl_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *); unsigned long shrink_slab(struct shrink_control *shrink, - unsigned long lru_pages); + unsigned long nr_pages_scanned, + unsigned long lru_pages); #ifndef CONFIG_MMU #define randomize_va_space 0 diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 341341b2b47..5c8f7e08928 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -241,10 +241,9 @@ void shake_page(struct page *p, int access) do { struct shrink_control shrink = { .gfp_mask = GFP_KERNEL, - .nr_scanned = 1000, }; - nr = shrink_slab(&shrink, 1000); + nr = shrink_slab(&shrink, 1000, 1000); if (page_count(p) == 1) break; } while (nr > 10); diff --git a/mm/vmscan.c b/mm/vmscan.c index e4e245ed1a5..7e0116150dc 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -202,6 +202,14 @@ void unregister_shrinker(struct shrinker *shrinker) } EXPORT_SYMBOL(unregister_shrinker); +static inline int do_shrinker_shrink(struct shrinker *shrinker, + struct shrink_control *sc, + unsigned long nr_to_scan) +{ + sc->nr_to_scan = nr_to_scan; + return (*shrinker->shrink)(shrinker, sc); +} + #define SHRINK_BATCH 128 /* * Call the shrink functions to age shrinkable caches @@ -223,15 +231,14 @@ EXPORT_SYMBOL(unregister_shrinker); * Returns the number of slab objects which we shrunk. */ unsigned long shrink_slab(struct shrink_control *shrink, + unsigned long nr_pages_scanned, unsigned long lru_pages) { struct shrinker *shrinker; unsigned long ret = 0; - unsigned long scanned = shrink->nr_scanned; - gfp_t gfp_mask = shrink->gfp_mask; - if (scanned == 0) - scanned = SWAP_CLUSTER_MAX; + if (nr_pages_scanned == 0) + nr_pages_scanned = SWAP_CLUSTER_MAX; if (!down_read_trylock(&shrinker_rwsem)) { /* Assume we'll be able to shrink next time */ @@ -244,8 +251,8 @@ unsigned long shrink_slab(struct shrink_control *shrink, unsigned long total_scan; unsigned long max_pass; - max_pass = (*shrinker->shrink)(shrinker, 0, gfp_mask); - delta = (4 * scanned) / shrinker->seeks; + max_pass = do_shrinker_shrink(shrinker, shrink, 0); + delta = (4 * nr_pages_scanned) / shrinker->seeks; delta *= max_pass; do_div(delta, lru_pages + 1); shrinker->nr += delta; @@ -272,9 +279,9 @@ unsigned long shrink_slab(struct shrink_control *shrink, int shrink_ret; int nr_before; - nr_before = (*shrinker->shrink)(shrinker, 0, gfp_mask); - shrink_ret = (*shrinker->shrink)(shrinker, this_scan, - gfp_mask); + nr_before = do_shrinker_shrink(shrinker, shrink, 0); + shrink_ret = do_shrinker_shrink(shrinker, shrink, + this_scan); if (shrink_ret == -1) break; if (shrink_ret < nr_before) @@ -2072,8 +2079,7 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist, lru_pages += zone_reclaimable_pages(zone); } - shrink->nr_scanned = sc->nr_scanned; - shrink_slab(shrink, lru_pages); + shrink_slab(shrink, sc->nr_scanned, lru_pages); if (reclaim_state) { sc->nr_reclaimed += reclaim_state->reclaimed_slab; reclaim_state->reclaimed_slab = 0; @@ -2456,8 +2462,7 @@ loop_again: end_zone, 0)) shrink_zone(priority, zone, &sc); reclaim_state->reclaimed_slab = 0; - shrink.nr_scanned = sc.nr_scanned; - nr_slab = shrink_slab(&shrink, lru_pages); + nr_slab = shrink_slab(&shrink, sc.nr_scanned, lru_pages); sc.nr_reclaimed += reclaim_state->reclaimed_slab; total_scanned += sc.nr_scanned; @@ -3025,7 +3030,6 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order) } nr_slab_pages0 = zone_page_state(zone, NR_SLAB_RECLAIMABLE); - shrink.nr_scanned = sc.nr_scanned; if (nr_slab_pages0 > zone->min_slab_pages) { /* * shrink_slab() does not currently allow us to determine how @@ -3041,7 +3045,7 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order) unsigned long lru_pages = zone_reclaimable_pages(zone); /* No reclaimable slab or very low memory pressure */ - if (!shrink_slab(&shrink, lru_pages)) + if (!shrink_slab(&shrink, sc.nr_scanned, lru_pages)) break; /* Freed enough memory */ diff --git a/net/sunrpc/auth.c b/net/sunrpc/auth.c index 67e31276682..cd6e4aa19db 100644 --- a/net/sunrpc/auth.c +++ b/net/sunrpc/auth.c @@ -326,10 +326,12 @@ rpcauth_prune_expired(struct list_head *free, int nr_to_scan) * Run memory cache shrinker. */ static int -rpcauth_cache_shrinker(struct shrinker *shrink, int nr_to_scan, gfp_t gfp_mask) +rpcauth_cache_shrinker(struct shrinker *shrink, struct shrink_control *sc) { LIST_HEAD(free); int res; + int nr_to_scan = sc->nr_to_scan; + gfp_t gfp_mask = sc->gfp_mask; if ((gfp_mask & GFP_KERNEL) != GFP_KERNEL) return (nr_to_scan == 0) ? 0 : -1; -- cgit v1.2.3-70-g09d2