From 0d1c7ae9d849bdd3146e322f1e46fd3300e66d5f Mon Sep 17 00:00:00 2001 From: Bob Peterson Date: Fri, 3 Mar 2017 12:37:14 -0500 Subject: [PATCH 01/10] GFS2: Prevent BUG from occurring when normal Withdraws occur When the GFS2 file system withdraws due to metadata corruption, it often has outstanding transactions in the journal and delayed work queued for its glocks. This patch adds some new checks for a withdrawn file system before proceeding with operations that would obviously cause a BUG() to be triggered. That allows GFS2 to be safely unmounted rather than cause the system to go down. Signed-off-by: Bob Peterson --- fs/gfs2/glock.c | 2 ++ fs/gfs2/super.c | 3 ++- 2 files changed, 4 insertions(+), 1 deletion(-) diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index ec0848fcca02..694167b4e512 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -449,6 +449,8 @@ __acquires(&gl->gl_lockref.lock) unsigned int lck_flags = (unsigned int)(gh ? gh->gh_flags : 0); int ret; + if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags))) + return; lck_flags &= (LM_FLAG_TRY | LM_FLAG_TRY_1CB | LM_FLAG_NOEXP | LM_FLAG_PRIORITY); GLOCK_BUG_ON(gl, gl->gl_state == target); diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c index 361796a84fce..2a9a830fb3d6 100644 --- a/fs/gfs2/super.c +++ b/fs/gfs2/super.c @@ -793,7 +793,8 @@ static void gfs2_dirty_inode(struct inode *inode, int flags) if (!(flags & (I_DIRTY_DATASYNC|I_DIRTY_SYNC))) return; - + if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags))) + return; if (!gfs2_glock_is_locked_by_me(ip->i_gl)) { ret = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh); if (ret) { From cc37a62785a584f4875788689f3fd1fa6e4eb291 Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Thu, 9 Mar 2017 09:38:51 -0500 Subject: [PATCH 02/10] gfs2: Replace rhashtable_walk_init with rhashtable_walk_enter Function rhashtable_walk_init is deprecated. Signed-off-by: Andreas Gruenbacher Signed-off-by: Bob Peterson --- fs/gfs2/glock.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index 694167b4e512..b2674dd4ce7c 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -1934,7 +1934,7 @@ static int gfs2_glocks_open(struct inode *inode, struct file *file) if (seq->buf) seq->size = GFS2_SEQ_GOODSIZE; gi->gl = NULL; - ret = rhashtable_walk_init(&gl_hash_table, &gi->hti, GFP_KERNEL); + rhashtable_walk_enter(&gl_hash_table, &gi->hti); } return ret; } From 92ecd73a887c4a2b94daf5fc35179d75d1c4ef95 Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Thu, 9 Mar 2017 09:48:05 -0500 Subject: [PATCH 03/10] gfs2: Deduplicate gfs2_{glocks,glstats}_open Both functions are identical except for the seq_operations used. Signed-off-by: Andreas Gruenbacher Signed-off-by: Bob Peterson --- fs/gfs2/glock.c | 26 +++++++++----------------- 1 file changed, 9 insertions(+), 17 deletions(-) diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index b2674dd4ce7c..b2638d8a2459 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -1920,10 +1920,10 @@ static const struct seq_operations gfs2_sbstats_seq_ops = { #define GFS2_SEQ_GOODSIZE min(PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER, 65536UL) -static int gfs2_glocks_open(struct inode *inode, struct file *file) +static int __gfs2_glocks_open(struct inode *inode, struct file *file, + const struct seq_operations *ops) { - int ret = seq_open_private(file, &gfs2_glock_seq_ops, - sizeof(struct gfs2_glock_iter)); + int ret = seq_open_private(file, ops, sizeof(struct gfs2_glock_iter)); if (ret == 0) { struct seq_file *seq = file->private_data; struct gfs2_glock_iter *gi = seq->private; @@ -1939,6 +1939,11 @@ static int gfs2_glocks_open(struct inode *inode, struct file *file) return ret; } +static int gfs2_glocks_open(struct inode *inode, struct file *file) +{ + return __gfs2_glocks_open(inode, file, &gfs2_glock_seq_ops); +} + static int gfs2_glocks_release(struct inode *inode, struct file *file) { struct seq_file *seq = file->private_data; @@ -1951,20 +1956,7 @@ static int gfs2_glocks_release(struct inode *inode, struct file *file) static int gfs2_glstats_open(struct inode *inode, struct file *file) { - int ret = seq_open_private(file, &gfs2_glstats_seq_ops, - sizeof(struct gfs2_glock_iter)); - if (ret == 0) { - struct seq_file *seq = file->private_data; - struct gfs2_glock_iter *gi = seq->private; - gi->sdp = inode->i_private; - gi->last_pos = 0; - seq->buf = kmalloc(GFS2_SEQ_GOODSIZE, GFP_KERNEL | __GFP_NOWARN); - if (seq->buf) - seq->size = GFS2_SEQ_GOODSIZE; - gi->gl = NULL; - ret = rhashtable_walk_init(&gl_hash_table, &gi->hti, GFP_KERNEL); - } - return ret; + return __gfs2_glocks_open(inode, file, &gfs2_glstats_seq_ops); } static int gfs2_sbstats_open(struct inode *inode, struct file *file) From 972b044eeca582ef173d063773e292bd9e8633d6 Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Thu, 16 Mar 2017 09:54:57 -0400 Subject: [PATCH 04/10] gfs2: Don't pack struct lm_lockname As per a suggestion by Linus, don't pack struct lm_lockname: we did that because the struct is used as a rhashtable key, but packing tells the compiler that the 64-bit fields in the struct may be unaligned, causing it to generate worse code on some architectures. Instead, rearrange the fields in the struct so that there is no padding between fields, and exclude any tail padding from the hash key size. Signed-off-by: Andreas Gruenbacher Signed-off-by: Bob Peterson --- fs/gfs2/glock.c | 2 +- fs/gfs2/incore.h | 8 ++++++-- 2 files changed, 7 insertions(+), 3 deletions(-) diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index b2638d8a2459..35f3b0a1d81b 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -73,7 +73,7 @@ static DEFINE_SPINLOCK(lru_lock); static struct rhashtable_params ht_parms = { .nelem_hint = GFS2_GL_HASH_SIZE * 3 / 4, - .key_len = sizeof(struct lm_lockname), + .key_len = offsetofend(struct lm_lockname, ln_type), .key_offset = offsetof(struct gfs2_glock, gl_name), .head_offset = offsetof(struct gfs2_glock, gl_node), }; diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h index 511e1ed7e2de..b7cf65d13561 100644 --- a/fs/gfs2/incore.h +++ b/fs/gfs2/incore.h @@ -203,11 +203,15 @@ enum { DFL_DLM_RECOVERY = 6, }; +/* + * We are using struct lm_lockname as an rhashtable key. Avoid holes within + * the struct; padding at the end is fine. + */ struct lm_lockname { - struct gfs2_sbd *ln_sbd; u64 ln_number; + struct gfs2_sbd *ln_sbd; unsigned int ln_type; -} __packed __aligned(sizeof(int)); +}; #define lm_name_equal(name1, name2) \ (((name1)->ln_number == (name2)->ln_number) && \ From cc963a11b67b796c25c5b827b25d2bcc92ce1779 Mon Sep 17 00:00:00 2001 From: Bob Peterson Date: Thu, 16 Mar 2017 15:29:13 -0400 Subject: [PATCH 05/10] GFS2: Temporarily zero i_no_addr when creating a dinode Before this patch i_no_addr was not initialized until after the return from allocating its block. That meant the i_no_addr was temporarily uninitialized storage. Ordinarily that's not a concern, but if inplace_reserve can't find space, it can call try_rgrp_unlink which references i_no_addr as a block to avoid. That can result in unpredictable behavior. More importantly, the trace point in gfs2_alloc_blocks references ip->i_no_addr before it is set, which is misleading when reading the kernel traces. This patch makes it look like the new dinode block was assigned in the name of inode 0 rather than a random inode that's completely unrelated. Signed-off-by: Bob Peterson --- fs/gfs2/inode.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index e279c3ce27be..4f405d43a86b 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -667,6 +667,7 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, ip->i_height = 0; ip->i_depth = 0; ip->i_entries = 0; + ip->i_no_addr = 0; /* Temporarily zero until real addr is assigned */ switch(mode & S_IFMT) { case S_IFREG: From 0a52aba7c2168636fc71635cf3ccb92a79a96c38 Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Tue, 21 Feb 2017 23:19:10 +0100 Subject: [PATCH 06/10] gfs2: Switch to rhashtable_lookup_get_insert_fast Switch from rhashtable_lookup_insert_fast + rhashtable_lookup_fast to rhashtable_lookup_get_insert_fast, which is cleaner and avoids an extra rhashtable lookup. At the same time, turn the retry loop in gfs2_glock_get into an infinite loop. The lookup or insert will eventually succeed, usually very fast, but there is no reason to give up trying at a fixed number of iterations. Signed-off-by: Andreas Gruenbacher Signed-off-by: Bob Peterson --- fs/gfs2/glock.c | 45 +++++++++++++++++++++------------------------ 1 file changed, 21 insertions(+), 24 deletions(-) diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index 35f3b0a1d81b..9e81219692c4 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -655,10 +655,10 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number, struct lm_lockname name = { .ln_number = number, .ln_type = glops->go_type, .ln_sbd = sdp }; - struct gfs2_glock *gl, *tmp = NULL; + struct gfs2_glock *gl, *tmp; struct address_space *mapping; struct kmem_cache *cachep; - int ret, tries = 0; + int ret = 0; rcu_read_lock(); gl = rhashtable_lookup_fast(&gl_hash_table, &name, ht_parms); @@ -723,35 +723,32 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number, } again: - ret = rhashtable_lookup_insert_fast(&gl_hash_table, &gl->gl_node, - ht_parms); - if (ret == 0) { + rcu_read_lock(); + tmp = rhashtable_lookup_get_insert_fast(&gl_hash_table, &gl->gl_node, + ht_parms); + if (!tmp) { *glp = gl; - return 0; + goto out; } + if (IS_ERR(tmp)) { + ret = PTR_ERR(tmp); + goto out_free; + } + if (lockref_get_not_dead(&tmp->gl_lockref)) { + *glp = tmp; + goto out_free; + } + rcu_read_unlock(); + cond_resched(); + goto again; - if (ret == -EEXIST) { - ret = 0; - rcu_read_lock(); - tmp = rhashtable_lookup_fast(&gl_hash_table, &name, ht_parms); - if (tmp == NULL || !lockref_get_not_dead(&tmp->gl_lockref)) { - if (++tries < 100) { - rcu_read_unlock(); - cond_resched(); - goto again; - } - tmp = NULL; - ret = -ENOMEM; - } - rcu_read_unlock(); - } else { - WARN_ON_ONCE(ret); - } +out_free: kfree(gl->gl_lksb.sb_lvbptr); kmem_cache_free(cachep, gl); atomic_dec(&sdp->sd_glock_disposal); - *glp = tmp; +out: + rcu_read_unlock(); return ret; } From d4da31986c5da14277b3ecc479f1b0682756b54c Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Wed, 22 Feb 2017 20:05:09 +0100 Subject: [PATCH 07/10] Revert "GFS2: Wait for iopen glock dequeues" Revert commit 86d067a797d4e8546a7c92b985f31e8cd3ec39ad: it turns out that waiting for iopen glock dequeues here isn't needed anymore because the bugs that commit was meant to fix have been fixed otherwise. In addition, we want to avoid waiting on glocks in gfs2_evict_inode in shrinker context because the shrinker may be invoked on behalf of DLM, in which case calling into DLM again would deadlock. This commit makes the described scenario less likely without completely avoiding it; it's still a step in the right direction, though. Signed-off-by: Andreas Gruenbacher Signed-off-by: Bob Peterson --- fs/gfs2/inode.c | 3 +-- fs/gfs2/super.c | 8 +++----- 2 files changed, 4 insertions(+), 7 deletions(-) diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index 4f405d43a86b..9f605ea4810c 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -202,8 +202,7 @@ struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned int type, fail_refresh: ip->i_iopen_gh.gh_flags |= GL_NOCACHE; ip->i_iopen_gh.gh_gl->gl_object = NULL; - gfs2_glock_dq_wait(&ip->i_iopen_gh); - gfs2_holder_uninit(&ip->i_iopen_gh); + gfs2_glock_dq_uninit(&ip->i_iopen_gh); fail_put: if (io_gl) gfs2_glock_put(io_gl); diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c index 2a9a830fb3d6..29b0473f6e74 100644 --- a/fs/gfs2/super.c +++ b/fs/gfs2/super.c @@ -1539,8 +1539,7 @@ static void gfs2_evict_inode(struct inode *inode) error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, GL_SKIP, &gh); if (unlikely(error)) { ip->i_iopen_gh.gh_flags |= GL_NOCACHE; - gfs2_glock_dq_wait(&ip->i_iopen_gh); - gfs2_holder_uninit(&ip->i_iopen_gh); + gfs2_glock_dq_uninit(&ip->i_iopen_gh); goto out; } @@ -1618,7 +1617,7 @@ static void gfs2_evict_inode(struct inode *inode) if (gfs2_holder_initialized(&ip->i_iopen_gh)) { if (test_bit(HIF_HOLDER, &ip->i_iopen_gh.gh_iflags)) { ip->i_iopen_gh.gh_flags |= GL_NOCACHE; - gfs2_glock_dq_wait(&ip->i_iopen_gh); + gfs2_glock_dq(&ip->i_iopen_gh); } gfs2_holder_uninit(&ip->i_iopen_gh); } @@ -1640,8 +1639,7 @@ static void gfs2_evict_inode(struct inode *inode) if (gfs2_holder_initialized(&ip->i_iopen_gh)) { ip->i_iopen_gh.gh_gl->gl_object = NULL; ip->i_iopen_gh.gh_flags |= GL_NOCACHE; - gfs2_glock_dq_wait(&ip->i_iopen_gh); - gfs2_holder_uninit(&ip->i_iopen_gh); + gfs2_glock_dq_uninit(&ip->i_iopen_gh); } } From d4d7fc12b642a16732adeacefdaebe684bcb2218 Mon Sep 17 00:00:00 2001 From: Andrew Price Date: Wed, 5 Apr 2017 11:45:26 -0400 Subject: [PATCH 08/10] gfs2: Re-enable fallocate for the rindex Commit 86066914edff2316cbed63aac8a87d5001441a16 "gfs2: Don't support fallocate on jdata files" removed the ability of gfs2_grow to reserve space at the end of the rindex, which could prevent a second gfs2_grow from succeeding if the fs is full. Allow fallocate to work on the rindex once again. Signed-off-by: Andrew Price Signed-off-by: Bob Peterson --- fs/gfs2/file.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index 6fe2a59c6a9a..c2062a108d19 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -911,11 +911,15 @@ static long __gfs2_fallocate(struct file *file, int mode, loff_t offset, loff_t static long gfs2_fallocate(struct file *file, int mode, loff_t offset, loff_t len) { struct inode *inode = file_inode(file); + struct gfs2_sbd *sdp = GFS2_SB(inode); struct gfs2_inode *ip = GFS2_I(inode); struct gfs2_holder gh; int ret; - if ((mode & ~FALLOC_FL_KEEP_SIZE) || gfs2_is_jdata(ip)) + if (mode & ~FALLOC_FL_KEEP_SIZE) + return -EOPNOTSUPP; + /* fallocate is needed by gfs2_grow to reserve space in the rindex */ + if (gfs2_is_jdata(ip) && inode != sdp->sd_rindex) return -EOPNOTSUPP; inode_lock(inode); From d552a2b9b33eafdb5eb16c643e745deb564dda7f Mon Sep 17 00:00:00 2001 From: Bob Peterson Date: Mon, 6 Feb 2017 08:28:32 -0500 Subject: [PATCH 09/10] GFS2: Non-recursive delete Implement truncate/delete as a non-recursive algorithm. The older algorithm was implemented with recursion to strip off each layer at a time (going by height, starting with the maximum height. This version tries to do the same thing but without recursion, and without needing to allocate new structures or lists in memory. For example, say you want to truncate a very large file to 1 byte, and its end-of-file metapath is: 0.505.463.428. The starting metapath would be 0.0.0.0. Since it's a truncate to non-zero, it needs to preserve that byte, and all metadata pointing to it. So it would start at 0.0.0.0, look up all its metadata buffers, then free all data blocks pointed to at the highest level. After that buffer is "swept", it moves on to 0.0.0.1, then 0.0.0.2, etc., reading in buffers and sweeping them clean. When it gets to the end of the 0.0.0 metadata buffer (for 4K blocks the last valid one is 0.0.0.508), it backs up to the previous height and starts working on 0.0.1.0, then 0.0.1.1, and so forth. After it reaches the end and sweeps 0.0.1.508, it continues with 0.0.2.0, and so on. When that height is exhausted, and it reaches 0.0.508.508 it backs up another level, to 0.1.0.0, then 0.1.0.1, through 0.1.0.508. So it has to keep marching backwards and forwards through the metadata until it's all swept clean. Once it has all the data blocks freed, it lowers the strip height, and begins the process all over again, but with one less height. This time it sweeps 0.0.0 through 0.505.463. When that's clean, it lowers the strip height again and works to free 0.505. Eventually it strips the lowest height, 0. For a delete or truncate to 0, all metadata for all heights of 0.0.0.0 would be freed. For a truncate to 1 byte, 0.0.0.0 would be preserved. This isn't much different from normal integer incrementing, where an integer gets incremented from 0000 (0.0.0.0) to 3021 (3.0.2.1). So 0000 gets increments to 0001, 0002, up to 0009, then on to 0010, 0011 up to 0099, then 0100 and so forth. It's just that each "digit" goes from 0 to 508 (for a total of 509 pointers) rather than from 0 to 9. Note that the dinode will only have 483 pointers due to the dinode structure itself. Also note: this is just an example. These numbers (509 and 483) are based on a standard 4K block size. Smaller block sizes will yield smaller numbers of indirect pointers accordingly. The truncation process is accomplished with the help of two major functions and a few helper functions. Functions do_strip and recursive_scan are obsolete, so removed. New function sweep_bh_for_rgrps cleans a buffer_head pointed to by the given metapath and height. By cleaning, I mean it frees all blocks starting at the offset passed in metapath. It starts at the first block in the buffer pointed to by the metapath and identifies its resource group (rgrp). From there it frees all subsequent block pointers that lie within that rgrp. If it's already inside a transaction, it stays within it as long as it can. In other words, it doesn't close a transaction until it knows it's freed what it can from the resource group. In this way, multiple buffers may be cleaned in a single transaction, as long as those blocks in the buffer all lie within the same rgrp. If it's not in a transaction, it starts one. If the buffer_head has references to blocks within multiple rgrps, it frees all the blocks inside the first rgrp it finds, then closes the transaction. Then it repeats the cycle: identifies the next unfreed block, uses it to find its rgrp, then starts a new transaction for that set. It repeats this process repeatedly until the buffer_head contains no more references to any blocks past the given metapath. Function trunc_dealloc has been reworked into a finite state automaton. It has basically 3 active states: DEALLOC_MP_FULL, DEALLOC_MP_LOWER, and DEALLOC_FILL_MP: The DEALLOC_MP_FULL state implies the metapath has a full set of buffers out to the "shrink height", and therefore, it can call function sweep_bh_for_rgrps to free the blocks within the highest height of the metapath. If it's just swept the lowest level (or an error has occurred) the state machine is ended. Otherwise it proceeds to the DEALLOC_MP_LOWER state. The DEALLOC_MP_LOWER state implies we are finished with a given buffer_head, which may now be released, and therefore we are then missing some buffer information from the metapath. So we need to find more buffers to read in. In most cases, this is just a matter of releasing the buffer_head and moving to the next pointer from the previous height, so it may be read in and swept as well. If it can't find another non-null pointer to process, it checks whether it's reached the end of a height and needs to lower the strip height, or whether it still needs move forward through the previous height's metadata. In this state, all zero-pointers are skipped. From this state, it can only loop around (once more backing up another height) or, once a valid metapath is found (one that has non-zero pointers), proceed to state DEALLOC_FILL_MP. The DEALLOC_FILL_MP state implies that we have a metapath but not all its buffers are read in. So we must proceed to read in buffer_heads until the metapath has a valid buffer for every height. If the previous state backed us up 3 heights, we may need to read in a buffer, increment the height, then repeat the process until buffers have been read in for all required heights. If it's successful reading a buffer, and it's at the highest height we need, it proceeds back to the DEALLOC_MP_FULL state. If it's unable to fill in a buffer, (encounters a hole, etc.) it tries to find another non-zero block pointer. If they're all zero, it lowers the height and returns to the DEALLOC_MP_LOWER state. If it finds a good non-null pointer, it loops around and reads it in, while keeping the metapath in lock-step with the pointers it examines. The state machine runs until the truncation request is satisfied. Then any transactions are ended, the quota and statfs data are updated, and the function is complete. Helper function metaptr1 was introduced to be an easy way to determine the start of a buffer_head's indirect pointers. Helper function lookup_mp_height was introduced to find a metapath index and read in the buffer that corresponds to it. In this way, function lookup_metapath becomes a simple loop to call it for every height. Helper function fillup_metapath is similar to lookup_metapath except it can do partial lookups. If the state machine backed up multiple levels (like 2999 wrapping to 3000) it needs to find out the next starting point and start issuing metadata reads at that point. Helper function hptrs is a shortcut to determine how many pointers should be expected in a buffer. Height 0 is the dinode which has fewer pointers than the others. Signed-off-by: Bob Peterson --- fs/gfs2/bmap.c | 741 ++++++++++++++++++++++++++++++------------------- fs/gfs2/rgrp.c | 7 - fs/gfs2/rgrp.h | 7 + 3 files changed, 463 insertions(+), 292 deletions(-) diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index 01b97c012c6e..3814a60e0aea 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -38,11 +38,6 @@ struct metapath { __u16 mp_list[GFS2_MAX_META_HEIGHT]; }; -struct strip_mine { - int sm_first; - unsigned int sm_height; -}; - /** * gfs2_unstuffer_page - unstuff a stuffed inode into a block cached by a page * @ip: the inode @@ -252,6 +247,19 @@ static inline unsigned int metapath_branch_start(const struct metapath *mp) return 1; } +/** + * metaptr1 - Return the first possible metadata pointer in a metaath buffer + * @height: The metadata height (0 = dinode) + * @mp: The metapath + */ +static inline __be64 *metaptr1(unsigned int height, const struct metapath *mp) +{ + struct buffer_head *bh = mp->mp_bh[height]; + if (height == 0) + return ((__be64 *)(bh->b_data + sizeof(struct gfs2_dinode))); + return ((__be64 *)(bh->b_data + sizeof(struct gfs2_meta_header))); +} + /** * metapointer - Return pointer to start of metadata in a buffer * @height: The metadata height (0 = dinode) @@ -264,10 +272,8 @@ static inline unsigned int metapath_branch_start(const struct metapath *mp) static inline __be64 *metapointer(unsigned int height, const struct metapath *mp) { - struct buffer_head *bh = mp->mp_bh[height]; - unsigned int head_size = (height > 0) ? - sizeof(struct gfs2_meta_header) : sizeof(struct gfs2_dinode); - return ((__be64 *)(bh->b_data + head_size)) + mp->mp_list[height]; + __be64 *p = metaptr1(height, mp); + return p + mp->mp_list[height]; } static void gfs2_metapath_ra(struct gfs2_glock *gl, @@ -295,6 +301,23 @@ static void gfs2_metapath_ra(struct gfs2_glock *gl, } } +/** + * lookup_mp_height - helper function for lookup_metapath + * @ip: the inode + * @mp: the metapath + * @h: the height which needs looking up + */ +static int lookup_mp_height(struct gfs2_inode *ip, struct metapath *mp, int h) +{ + __be64 *ptr = metapointer(h, mp); + u64 dblock = be64_to_cpu(*ptr); + + if (!dblock) + return h + 1; + + return gfs2_meta_indirect_buffer(ip, h + 1, dblock, &mp->mp_bh[h + 1]); +} + /** * lookup_metapath - Walk the metadata tree to a specific point * @ip: The inode @@ -316,17 +339,10 @@ static int lookup_metapath(struct gfs2_inode *ip, struct metapath *mp) { unsigned int end_of_metadata = ip->i_height - 1; unsigned int x; - __be64 *ptr; - u64 dblock; int ret; for (x = 0; x < end_of_metadata; x++) { - ptr = metapointer(x, mp); - dblock = be64_to_cpu(*ptr); - if (!dblock) - return x + 1; - - ret = gfs2_meta_indirect_buffer(ip, x+1, dblock, &mp->mp_bh[x+1]); + ret = lookup_mp_height(ip, mp, x); if (ret) return ret; } @@ -334,6 +350,35 @@ static int lookup_metapath(struct gfs2_inode *ip, struct metapath *mp) return ip->i_height; } +/** + * fillup_metapath - fill up buffers for the metadata path to a specific height + * @ip: The inode + * @mp: The metapath + * @h: The height to which it should be mapped + * + * Similar to lookup_metapath, but does lookups for a range of heights + * + * Returns: error or height of metadata tree + */ + +static int fillup_metapath(struct gfs2_inode *ip, struct metapath *mp, int h) +{ + unsigned int start_h = h - 1; + int ret; + + if (h) { + /* find the first buffer we need to look up. */ + while (start_h > 0 && mp->mp_bh[start_h] == NULL) + start_h--; + for (; start_h < h; start_h++) { + ret = lookup_mp_height(ip, mp, start_h); + if (ret) + return ret; + } + } + return ip->i_height; +} + static inline void release_metapath(struct metapath *mp) { int i; @@ -422,6 +467,13 @@ enum alloc_state { /* ALLOC_UNSTUFF = 3, TBD and rather complicated */ }; +static inline unsigned int hptrs(struct gfs2_sbd *sdp, const unsigned int hgt) +{ + if (hgt) + return sdp->sd_inptrs; + return sdp->sd_diptrs; +} + /** * gfs2_bmap_alloc - Build a metadata tree of the requested height * @inode: The GFS2 inode @@ -620,7 +672,7 @@ int gfs2_block_map(struct inode *inode, sector_t lblock, BUG_ON(maxlen == 0); - memset(mp.mp_bh, 0, sizeof(mp.mp_bh)); + memset(&mp, 0, sizeof(mp)); bmap_lock(ip, create); clear_buffer_mapped(bh_map); clear_buffer_new(bh_map); @@ -701,252 +753,6 @@ int gfs2_extent_map(struct inode *inode, u64 lblock, int *new, u64 *dblock, unsi return ret; } -/** - * do_strip - Look for a layer a particular layer of the file and strip it off - * @ip: the inode - * @dibh: the dinode buffer - * @bh: A buffer of pointers - * @top: The first pointer in the buffer - * @bottom: One more than the last pointer - * @height: the height this buffer is at - * @sm: a pointer to a struct strip_mine - * - * Returns: errno - */ - -static int do_strip(struct gfs2_inode *ip, struct buffer_head *dibh, - struct buffer_head *bh, __be64 *top, __be64 *bottom, - unsigned int height, struct strip_mine *sm) -{ - struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); - struct gfs2_rgrp_list rlist; - struct gfs2_trans *tr; - u64 bn, bstart; - u32 blen, btotal; - __be64 *p; - unsigned int rg_blocks = 0; - int metadata; - unsigned int revokes = 0; - int x; - int error; - int jblocks_rqsted; - - error = gfs2_rindex_update(sdp); - if (error) - return error; - - if (!*top) - sm->sm_first = 0; - - if (height != sm->sm_height) - return 0; - - if (sm->sm_first) { - top++; - sm->sm_first = 0; - } - - metadata = (height != ip->i_height - 1); - if (metadata) - revokes = (height) ? sdp->sd_inptrs : sdp->sd_diptrs; - else if (ip->i_depth) - revokes = sdp->sd_inptrs; - - memset(&rlist, 0, sizeof(struct gfs2_rgrp_list)); - bstart = 0; - blen = 0; - - for (p = top; p < bottom; p++) { - if (!*p) - continue; - - bn = be64_to_cpu(*p); - - if (bstart + blen == bn) - blen++; - else { - if (bstart) - gfs2_rlist_add(ip, &rlist, bstart); - - bstart = bn; - blen = 1; - } - } - - if (bstart) - gfs2_rlist_add(ip, &rlist, bstart); - else - goto out; /* Nothing to do */ - - gfs2_rlist_alloc(&rlist, LM_ST_EXCLUSIVE); - - for (x = 0; x < rlist.rl_rgrps; x++) { - struct gfs2_rgrpd *rgd; - rgd = rlist.rl_ghs[x].gh_gl->gl_object; - rg_blocks += rgd->rd_length; - } - - error = gfs2_glock_nq_m(rlist.rl_rgrps, rlist.rl_ghs); - if (error) - goto out_rlist; - - if (gfs2_rs_active(&ip->i_res)) /* needs to be done with the rgrp glock held */ - gfs2_rs_deltree(&ip->i_res); - -restart: - jblocks_rqsted = rg_blocks + RES_DINODE + - RES_INDIRECT + RES_STATFS + RES_QUOTA + - gfs2_struct2blk(sdp, revokes, sizeof(u64)); - if (jblocks_rqsted > atomic_read(&sdp->sd_log_thresh2)) - jblocks_rqsted = atomic_read(&sdp->sd_log_thresh2); - error = gfs2_trans_begin(sdp, jblocks_rqsted, revokes); - if (error) - goto out_rg_gunlock; - - tr = current->journal_info; - down_write(&ip->i_rw_mutex); - - gfs2_trans_add_meta(ip->i_gl, dibh); - gfs2_trans_add_meta(ip->i_gl, bh); - - bstart = 0; - blen = 0; - btotal = 0; - - for (p = top; p < bottom; p++) { - if (!*p) - continue; - - /* check for max reasonable journal transaction blocks */ - if (tr->tr_num_buf_new + RES_STATFS + - RES_QUOTA >= atomic_read(&sdp->sd_log_thresh2)) { - if (rg_blocks >= tr->tr_num_buf_new) - rg_blocks -= tr->tr_num_buf_new; - else - rg_blocks = 0; - break; - } - - bn = be64_to_cpu(*p); - - if (bstart + blen == bn) - blen++; - else { - if (bstart) { - __gfs2_free_blocks(ip, bstart, blen, metadata); - btotal += blen; - } - - bstart = bn; - blen = 1; - } - - *p = 0; - gfs2_add_inode_blocks(&ip->i_inode, -1); - } - if (p == bottom) - rg_blocks = 0; - - if (bstart) { - __gfs2_free_blocks(ip, bstart, blen, metadata); - btotal += blen; - } - - gfs2_statfs_change(sdp, 0, +btotal, 0); - gfs2_quota_change(ip, -(s64)btotal, ip->i_inode.i_uid, - ip->i_inode.i_gid); - - ip->i_inode.i_mtime = ip->i_inode.i_ctime = current_time(&ip->i_inode); - - gfs2_dinode_out(ip, dibh->b_data); - - up_write(&ip->i_rw_mutex); - - gfs2_trans_end(sdp); - - if (rg_blocks) - goto restart; - -out_rg_gunlock: - gfs2_glock_dq_m(rlist.rl_rgrps, rlist.rl_ghs); -out_rlist: - gfs2_rlist_free(&rlist); -out: - return error; -} - -/** - * recursive_scan - recursively scan through the end of a file - * @ip: the inode - * @dibh: the dinode buffer - * @mp: the path through the metadata to the point to start - * @height: the height the recursion is at - * @block: the indirect block to look at - * @first: 1 if this is the first block - * @sm: data opaque to this function to pass to @bc - * - * When this is first called @height and @block should be zero and - * @first should be 1. - * - * Returns: errno - */ - -static int recursive_scan(struct gfs2_inode *ip, struct buffer_head *dibh, - struct metapath *mp, unsigned int height, - u64 block, int first, struct strip_mine *sm) -{ - struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); - struct buffer_head *bh = NULL; - __be64 *top, *bottom; - u64 bn; - int error; - int mh_size = sizeof(struct gfs2_meta_header); - - if (!height) { - error = gfs2_meta_inode_buffer(ip, &bh); - if (error) - return error; - dibh = bh; - - top = (__be64 *)(bh->b_data + sizeof(struct gfs2_dinode)) + mp->mp_list[0]; - bottom = (__be64 *)(bh->b_data + sizeof(struct gfs2_dinode)) + sdp->sd_diptrs; - } else { - error = gfs2_meta_indirect_buffer(ip, height, block, &bh); - if (error) - return error; - - top = (__be64 *)(bh->b_data + mh_size) + - (first ? mp->mp_list[height] : 0); - - bottom = (__be64 *)(bh->b_data + mh_size) + sdp->sd_inptrs; - } - - error = do_strip(ip, dibh, bh, top, bottom, height, sm); - if (error) - goto out; - - if (height < ip->i_height - 1) { - - gfs2_metapath_ra(ip->i_gl, bh, top); - - for (; top < bottom; top++, first = 0) { - if (!*top) - continue; - - bn = be64_to_cpu(*top); - - error = recursive_scan(ip, dibh, mp, height + 1, bn, - first, sm); - if (error) - break; - } - } -out: - brelse(bh); - return error; -} - - /** * gfs2_block_truncate_page - Deal with zeroing out data for truncate * @@ -1106,41 +912,406 @@ static int trunc_start(struct inode *inode, u64 oldsize, u64 newsize) return error; } -static int trunc_dealloc(struct gfs2_inode *ip, u64 size) +/** + * sweep_bh_for_rgrps - find an rgrp in a meta buffer and free blocks therein + * @ip: inode + * @rg_gh: holder of resource group glock + * @mp: current metapath fully populated with buffers + * @btotal: place to keep count of total blocks freed + * @hgt: height we're processing + * @first: true if this is the first call to this function for this height + * + * We sweep a metadata buffer (provided by the metapath) for blocks we need to + * free, and free them all. However, we do it one rgrp at a time. If this + * block has references to multiple rgrps, we break it into individual + * transactions. This allows other processes to use the rgrps while we're + * focused on a single one, for better concurrency / performance. + * At every transaction boundary, we rewrite the inode into the journal. + * That way the bitmaps are kept consistent with the inode and we can recover + * if we're interrupted by power-outages. + * + * Returns: 0, or return code if an error occurred. + * *btotal has the total number of blocks freed + */ +static int sweep_bh_for_rgrps(struct gfs2_inode *ip, struct gfs2_holder *rd_gh, + const struct metapath *mp, u32 *btotal, int hgt, + bool preserve1) { struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); - unsigned int height = ip->i_height; - u64 lblock; - struct metapath mp; - int error; + struct gfs2_rgrpd *rgd; + struct gfs2_trans *tr; + struct buffer_head *bh = mp->mp_bh[hgt]; + __be64 *top, *bottom, *p; + int blks_outside_rgrp; + u64 bn, bstart, isize_blks; + s64 blen; /* needs to be s64 or gfs2_add_inode_blocks breaks */ + int meta = ((hgt != ip->i_height - 1) ? 1 : 0); + int ret = 0; + bool buf_in_tr = false; /* buffer was added to transaction */ - if (!size) + if (gfs2_metatype_check(sdp, bh, + (hgt ? GFS2_METATYPE_IN : GFS2_METATYPE_DI))) + return -EIO; + +more_rgrps: + blks_outside_rgrp = 0; + bstart = 0; + blen = 0; + top = metapointer(hgt, mp); /* first ptr from metapath */ + /* If we're keeping some data at the truncation point, we've got to + preserve the metadata tree by adding 1 to the starting metapath. */ + if (preserve1) + top++; + + bottom = (__be64 *)(bh->b_data + bh->b_size); + + for (p = top; p < bottom; p++) { + if (!*p) + continue; + bn = be64_to_cpu(*p); + if (gfs2_holder_initialized(rd_gh)) { + rgd = (struct gfs2_rgrpd *)rd_gh->gh_gl->gl_object; + gfs2_assert_withdraw(sdp, + gfs2_glock_is_locked_by_me(rd_gh->gh_gl)); + } else { + rgd = gfs2_blk2rgrpd(sdp, bn, false); + ret = gfs2_glock_nq_init(rgd->rd_gl, LM_ST_EXCLUSIVE, + 0, rd_gh); + if (ret) + goto out; + + /* Must be done with the rgrp glock held: */ + if (gfs2_rs_active(&ip->i_res) && + rgd == ip->i_res.rs_rbm.rgd) + gfs2_rs_deltree(&ip->i_res); + } + + if (!rgrp_contains_block(rgd, bn)) { + blks_outside_rgrp++; + continue; + } + + /* The size of our transactions will be unknown until we + actually process all the metadata blocks that relate to + the rgrp. So we estimate. We know it can't be more than + the dinode's i_blocks and we don't want to exceed the + journal flush threshold, sd_log_thresh2. */ + if (current->journal_info == NULL) { + unsigned int jblocks_rqsted, revokes; + + jblocks_rqsted = rgd->rd_length + RES_DINODE + + RES_INDIRECT; + isize_blks = gfs2_get_inode_blocks(&ip->i_inode); + if (isize_blks > atomic_read(&sdp->sd_log_thresh2)) + jblocks_rqsted += + atomic_read(&sdp->sd_log_thresh2); + else + jblocks_rqsted += isize_blks; + revokes = jblocks_rqsted; + if (meta) + revokes += hptrs(sdp, hgt); + else if (ip->i_depth) + revokes += sdp->sd_inptrs; + ret = gfs2_trans_begin(sdp, jblocks_rqsted, revokes); + if (ret) + goto out_unlock; + down_write(&ip->i_rw_mutex); + } + /* check if we will exceed the transaction blocks requested */ + tr = current->journal_info; + if (tr->tr_num_buf_new + RES_STATFS + + RES_QUOTA >= atomic_read(&sdp->sd_log_thresh2)) { + /* We set blks_outside_rgrp to ensure the loop will + be repeated for the same rgrp, but with a new + transaction. */ + blks_outside_rgrp++; + /* This next part is tricky. If the buffer was added + to the transaction, we've already set some block + pointers to 0, so we better follow through and free + them, or we will introduce corruption (so break). + This may be impossible, or at least rare, but I + decided to cover the case regardless. + + If the buffer was not added to the transaction + (this call), doing so would exceed our transaction + size, so we need to end the transaction and start a + new one (so goto). */ + + if (buf_in_tr) + break; + goto out_unlock; + } + + gfs2_trans_add_meta(ip->i_gl, bh); + buf_in_tr = true; + *p = 0; + if (bstart + blen == bn) { + blen++; + continue; + } + if (bstart) { + __gfs2_free_blocks(ip, bstart, (u32)blen, meta); + (*btotal) += blen; + gfs2_add_inode_blocks(&ip->i_inode, -blen); + } + bstart = bn; + blen = 1; + } + if (bstart) { + __gfs2_free_blocks(ip, bstart, (u32)blen, meta); + (*btotal) += blen; + gfs2_add_inode_blocks(&ip->i_inode, -blen); + } +out_unlock: + if (!ret && blks_outside_rgrp) { /* If buffer still has non-zero blocks + outside the rgrp we just processed, + do it all over again. */ + if (current->journal_info) { + struct buffer_head *dibh = mp->mp_bh[0]; + + /* Every transaction boundary, we rewrite the dinode + to keep its di_blocks current in case of failure. */ + ip->i_inode.i_mtime = ip->i_inode.i_ctime = + CURRENT_TIME; + gfs2_trans_add_meta(ip->i_gl, dibh); + gfs2_dinode_out(ip, dibh->b_data); + up_write(&ip->i_rw_mutex); + gfs2_trans_end(sdp); + } + gfs2_glock_dq_uninit(rd_gh); + cond_resched(); + goto more_rgrps; + } +out: + return ret; +} + +/** + * find_nonnull_ptr - find a non-null pointer given a metapath and height + * assumes the metapath is valid (with buffers) out to height h + * @mp: starting metapath + * @h: desired height to search + * + * Returns: true if a non-null pointer was found in the metapath buffer + * false if all remaining pointers are NULL in the buffer + */ +static bool find_nonnull_ptr(struct gfs2_sbd *sdp, struct metapath *mp, + unsigned int h) +{ + __be64 *ptr; + unsigned int ptrs = hptrs(sdp, h) - 1; + + while (true) { + ptr = metapointer(h, mp); + if (*ptr) /* if we have a non-null pointer */ + return true; + + if (mp->mp_list[h] < ptrs) + mp->mp_list[h]++; + else + return false; /* no more pointers in this buffer */ + } +} + +enum dealloc_states { + DEALLOC_MP_FULL = 0, /* Strip a metapath with all buffers read in */ + DEALLOC_MP_LOWER = 1, /* lower the metapath strip height */ + DEALLOC_FILL_MP = 2, /* Fill in the metapath to the given height. */ + DEALLOC_DONE = 3, /* process complete */ +}; + +/** + * trunc_dealloc - truncate a file down to a desired size + * @ip: inode to truncate + * @newsize: The desired size of the file + * + * This function truncates a file to newsize. It works from the + * bottom up, and from the right to the left. In other words, it strips off + * the highest layer (data) before stripping any of the metadata. Doing it + * this way is best in case the operation is interrupted by power failure, etc. + * The dinode is rewritten in every transaction to guarantee integrity. + */ +static int trunc_dealloc(struct gfs2_inode *ip, u64 newsize) +{ + struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); + struct metapath mp; + struct buffer_head *dibh, *bh; + struct gfs2_holder rd_gh; + u64 lblock; + __u16 nbof[GFS2_MAX_META_HEIGHT]; /* new beginning of truncation */ + unsigned int strip_h = ip->i_height - 1; + u32 btotal = 0; + int ret, state; + int mp_h; /* metapath buffers are read in to this height */ + sector_t last_ra = 0; + u64 prev_bnr = 0; + bool preserve1; /* need to preserve the first meta pointer? */ + + if (!newsize) lblock = 0; else - lblock = (size - 1) >> sdp->sd_sb.sb_bsize_shift; + lblock = (newsize - 1) >> sdp->sd_sb.sb_bsize_shift; + memset(&mp, 0, sizeof(mp)); find_metapath(sdp, lblock, &mp, ip->i_height); - error = gfs2_rindex_update(sdp); - if (error) - return error; - error = gfs2_quota_hold(ip, NO_UID_QUOTA_CHANGE, NO_GID_QUOTA_CHANGE); - if (error) - return error; + memcpy(&nbof, &mp.mp_list, sizeof(nbof)); - while (height--) { - struct strip_mine sm; - sm.sm_first = !!size; - sm.sm_height = height; + ret = gfs2_meta_inode_buffer(ip, &dibh); + if (ret) + return ret; - error = recursive_scan(ip, NULL, &mp, 0, 0, 1, &sm); - if (error) + mp.mp_bh[0] = dibh; + ret = lookup_metapath(ip, &mp); + if (ret == ip->i_height) + state = DEALLOC_MP_FULL; /* We have a complete metapath */ + else + state = DEALLOC_FILL_MP; /* deal with partial metapath */ + + ret = gfs2_rindex_update(sdp); + if (ret) + goto out_metapath; + + ret = gfs2_quota_hold(ip, NO_UID_QUOTA_CHANGE, NO_GID_QUOTA_CHANGE); + if (ret) + goto out_metapath; + gfs2_holder_mark_uninitialized(&rd_gh); + + mp_h = strip_h; + + while (state != DEALLOC_DONE) { + switch (state) { + /* Truncate a full metapath at the given strip height. + * Note that strip_h == mp_h in order to be in this state. */ + case DEALLOC_MP_FULL: + if (mp_h > 0) { /* issue read-ahead on metadata */ + __be64 *top; + + bh = mp.mp_bh[mp_h - 1]; + if (bh->b_blocknr != last_ra) { + last_ra = bh->b_blocknr; + top = metaptr1(mp_h - 1, &mp); + gfs2_metapath_ra(ip->i_gl, bh, top); + } + } + /* If we're truncating to a non-zero size and the mp is + at the beginning of file for the strip height, we + need to preserve the first metadata pointer. */ + preserve1 = (newsize && + (mp.mp_list[mp_h] == nbof[mp_h])); + bh = mp.mp_bh[mp_h]; + gfs2_assert_withdraw(sdp, bh); + if (gfs2_assert_withdraw(sdp, + prev_bnr != bh->b_blocknr)) { + printk(KERN_EMERG "GFS2: fsid=%s:inode %llu, " + "block:%llu, i_h:%u, s_h:%u, mp_h:%u\n", + sdp->sd_fsname, + (unsigned long long)ip->i_no_addr, + prev_bnr, ip->i_height, strip_h, mp_h); + } + prev_bnr = bh->b_blocknr; + ret = sweep_bh_for_rgrps(ip, &rd_gh, &mp, &btotal, + mp_h, preserve1); + /* If we hit an error or just swept dinode buffer, + just exit. */ + if (ret || !mp_h) { + state = DEALLOC_DONE; + break; + } + state = DEALLOC_MP_LOWER; break; + + /* lower the metapath strip height */ + case DEALLOC_MP_LOWER: + /* We're done with the current buffer, so release it, + unless it's the dinode buffer. Then back up to the + previous pointer. */ + if (mp_h) { + brelse(mp.mp_bh[mp_h]); + mp.mp_bh[mp_h] = NULL; + } + /* If we can't get any lower in height, we've stripped + off all we can. Next step is to back up and start + stripping the previous level of metadata. */ + if (mp_h == 0) { + strip_h--; + memcpy(&mp.mp_list, &nbof, sizeof(nbof)); + mp_h = strip_h; + state = DEALLOC_FILL_MP; + break; + } + mp.mp_list[mp_h] = 0; + mp_h--; /* search one metadata height down */ + if (mp.mp_list[mp_h] >= hptrs(sdp, mp_h) - 1) + break; /* loop around in the same state */ + mp.mp_list[mp_h]++; + /* Here we've found a part of the metapath that is not + * allocated. We need to search at that height for the + * next non-null pointer. */ + if (find_nonnull_ptr(sdp, &mp, mp_h)) { + state = DEALLOC_FILL_MP; + mp_h++; + } + /* No more non-null pointers at this height. Back up + to the previous height and try again. */ + break; /* loop around in the same state */ + + /* Fill the metapath with buffers to the given height. */ + case DEALLOC_FILL_MP: + /* Fill the buffers out to the current height. */ + ret = fillup_metapath(ip, &mp, mp_h); + if (ret < 0) + goto out; + + /* If buffers found for the entire strip height */ + if ((ret == ip->i_height) && (mp_h == strip_h)) { + state = DEALLOC_MP_FULL; + break; + } + if (ret < ip->i_height) /* We have a partial height */ + mp_h = ret - 1; + + /* If we find a non-null block pointer, crawl a bit + higher up in the metapath and try again, otherwise + we need to look lower for a new starting point. */ + if (find_nonnull_ptr(sdp, &mp, mp_h)) + mp_h++; + else + state = DEALLOC_MP_LOWER; + break; + } } - gfs2_quota_unhold(ip); + if (btotal) { + if (current->journal_info == NULL) { + ret = gfs2_trans_begin(sdp, RES_DINODE + RES_STATFS + + RES_QUOTA, 0); + if (ret) + goto out; + down_write(&ip->i_rw_mutex); + } + gfs2_statfs_change(sdp, 0, +btotal, 0); + gfs2_quota_change(ip, -(s64)btotal, ip->i_inode.i_uid, + ip->i_inode.i_gid); + ip->i_inode.i_mtime = ip->i_inode.i_ctime = CURRENT_TIME; + gfs2_trans_add_meta(ip->i_gl, dibh); + gfs2_dinode_out(ip, dibh->b_data); + up_write(&ip->i_rw_mutex); + gfs2_trans_end(sdp); + } - return error; +out: + if (gfs2_holder_initialized(&rd_gh)) + gfs2_glock_dq_uninit(&rd_gh); + if (current->journal_info) { + up_write(&ip->i_rw_mutex); + gfs2_trans_end(sdp); + cond_resched(); + } + gfs2_quota_unhold(ip); +out_metapath: + release_metapath(&mp); + return ret; } static int trunc_end(struct gfs2_inode *ip) diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c index 86ccc0159393..83c9909ff14a 100644 --- a/fs/gfs2/rgrp.c +++ b/fs/gfs2/rgrp.c @@ -483,13 +483,6 @@ void gfs2_rgrp_verify(struct gfs2_rgrpd *rgd) } } -static inline int rgrp_contains_block(struct gfs2_rgrpd *rgd, u64 block) -{ - u64 first = rgd->rd_data0; - u64 last = first + rgd->rd_data; - return first <= block && block < last; -} - /** * gfs2_blk2rgrpd - Find resource group for a given data/meta block number * @sdp: The GFS2 superblock diff --git a/fs/gfs2/rgrp.h b/fs/gfs2/rgrp.h index 66b51cf66dfa..e90478e2f545 100644 --- a/fs/gfs2/rgrp.h +++ b/fs/gfs2/rgrp.h @@ -83,5 +83,12 @@ static inline bool gfs2_rs_active(const struct gfs2_blkreserv *rs) return rs && !RB_EMPTY_NODE(&rs->rs_node); } +static inline int rgrp_contains_block(struct gfs2_rgrpd *rgd, u64 block) +{ + u64 first = rgd->rd_data0; + u64 last = first + rgd->rd_data; + return first <= block && block < last; +} + extern void check_and_update_goal(struct gfs2_inode *ip); #endif /* __RGRP_DOT_H__ */ From ed17545d01e4a40086f1622c88ce64cc0241cfc2 Mon Sep 17 00:00:00 2001 From: Bob Peterson Date: Fri, 5 May 2017 09:43:02 -0500 Subject: [PATCH 10/10] GFS2: Allow glocks to be unlocked after withdraw This bug fixes a regression introduced by patch 0d1c7ae9d8. The intent of the patch was to stop promoting glocks after a file system is withdrawn due to a variety of errors, because doing so results in a BUG(). (You should be able to unmount after a withdraw rather than having the kernel panic.) Unfortunately, it also stopped demotions, so glocks could not be unlocked after withdraw, which means the unmount would hang. This patch allows function do_xmote to demote locks to an unlocked state after a withdraw, but not promote them. Signed-off-by: Bob Peterson --- fs/gfs2/glock.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index 9e81219692c4..959a19ced4d5 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -449,7 +449,8 @@ __acquires(&gl->gl_lockref.lock) unsigned int lck_flags = (unsigned int)(gh ? gh->gh_flags : 0); int ret; - if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags))) + if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags)) && + target != LM_ST_UNLOCKED) return; lck_flags &= (LM_FLAG_TRY | LM_FLAG_TRY_1CB | LM_FLAG_NOEXP | LM_FLAG_PRIORITY); @@ -486,7 +487,8 @@ __acquires(&gl->gl_lockref.lock) } else if (ret) { pr_err("lm_lock ret %d\n", ret); - GLOCK_BUG_ON(gl, 1); + GLOCK_BUG_ON(gl, !test_bit(SDF_SHUTDOWN, + &sdp->sd_flags)); } } else { /* lock_nolock */ finish_xmote(gl, target);