diff options
Diffstat (limited to 'fs/gfs2')
-rw-r--r-- | fs/gfs2/acl.c | 4 | ||||
-rw-r--r-- | fs/gfs2/acl.h | 2 | ||||
-rw-r--r-- | fs/gfs2/aops.c | 73 | ||||
-rw-r--r-- | fs/gfs2/aops.h | 4 | ||||
-rw-r--r-- | fs/gfs2/bmap.c | 38 | ||||
-rw-r--r-- | fs/gfs2/dentry.c | 18 | ||||
-rw-r--r-- | fs/gfs2/file.c | 5 | ||||
-rw-r--r-- | fs/gfs2/glock.c | 128 | ||||
-rw-r--r-- | fs/gfs2/glock.h | 4 | ||||
-rw-r--r-- | fs/gfs2/glops.c | 23 | ||||
-rw-r--r-- | fs/gfs2/incore.h | 11 | ||||
-rw-r--r-- | fs/gfs2/inode.c | 66 | ||||
-rw-r--r-- | fs/gfs2/inode.h | 4 | ||||
-rw-r--r-- | fs/gfs2/log.c | 13 | ||||
-rw-r--r-- | fs/gfs2/meta_io.c | 2 | ||||
-rw-r--r-- | fs/gfs2/ops_fstype.c | 71 | ||||
-rw-r--r-- | fs/gfs2/rgrp.c | 2 | ||||
-rw-r--r-- | fs/gfs2/super.c | 49 | ||||
-rw-r--r-- | fs/gfs2/sys.c | 8 | ||||
-rw-r--r-- | fs/gfs2/xattr.c | 2 |
20 files changed, 317 insertions, 210 deletions
diff --git a/fs/gfs2/acl.c b/fs/gfs2/acl.c index 3dcde4912413..a392aa0f041d 100644 --- a/fs/gfs2/acl.c +++ b/fs/gfs2/acl.c @@ -109,7 +109,7 @@ out: return error; } -int gfs2_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry, +int gfs2_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, struct posix_acl *acl, int type) { struct inode *inode = d_inode(dentry); @@ -135,7 +135,7 @@ int gfs2_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry, mode = inode->i_mode; if (type == ACL_TYPE_ACCESS && acl) { - ret = posix_acl_update_mode(&init_user_ns, inode, &mode, &acl); + ret = posix_acl_update_mode(&nop_mnt_idmap, inode, &mode, &acl); if (ret) goto unlock; } diff --git a/fs/gfs2/acl.h b/fs/gfs2/acl.h index b8de8c148f5c..d4deb2b19959 100644 --- a/fs/gfs2/acl.h +++ b/fs/gfs2/acl.h @@ -13,7 +13,7 @@ extern struct posix_acl *gfs2_get_acl(struct inode *inode, int type, bool rcu); extern int __gfs2_set_acl(struct inode *inode, struct posix_acl *acl, int type); -extern int gfs2_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry, +extern int gfs2_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, struct posix_acl *acl, int type); #endif /* __ACL_DOT_H__ */ diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c index e782b4f1d104..a5f4be6b9213 100644 --- a/fs/gfs2/aops.c +++ b/fs/gfs2/aops.c @@ -37,10 +37,10 @@ #include "aops.h" -void gfs2_page_add_databufs(struct gfs2_inode *ip, struct page *page, - unsigned int from, unsigned int len) +void gfs2_trans_add_databufs(struct gfs2_inode *ip, struct folio *folio, + unsigned int from, unsigned int len) { - struct buffer_head *head = page_buffers(page); + struct buffer_head *head = folio_buffers(folio); unsigned int bsize = head->b_size; struct buffer_head *bh; unsigned int to = from + len; @@ -127,7 +127,6 @@ static int __gfs2_jdata_writepage(struct page *page, struct writeback_control *w { struct inode *inode = page->mapping->host; struct gfs2_inode *ip = GFS2_I(inode); - struct gfs2_sbd *sdp = GFS2_SB(inode); if (PageChecked(page)) { ClearPageChecked(page); @@ -135,7 +134,7 @@ static int __gfs2_jdata_writepage(struct page *page, struct writeback_control *w create_empty_buffers(page, inode->i_sb->s_blocksize, BIT(BH_Dirty)|BIT(BH_Uptodate)); } - gfs2_page_add_databufs(ip, page, 0, sdp->sd_vfs->s_blocksize); + gfs2_trans_add_databufs(ip, page_folio(page), 0, PAGE_SIZE); } return gfs2_write_jdata_page(page, wbc); } @@ -195,67 +194,71 @@ static int gfs2_writepages(struct address_space *mapping, } /** - * gfs2_write_jdata_pagevec - Write back a pagevec's worth of pages + * gfs2_write_jdata_batch - Write back a folio batch's worth of folios * @mapping: The mapping * @wbc: The writeback control - * @pvec: The vector of pages - * @nr_pages: The number of pages to write + * @fbatch: The batch of folios * @done_index: Page index * * Returns: non-zero if loop should terminate, zero otherwise */ -static int gfs2_write_jdata_pagevec(struct address_space *mapping, +static int gfs2_write_jdata_batch(struct address_space *mapping, struct writeback_control *wbc, - struct pagevec *pvec, - int nr_pages, + struct folio_batch *fbatch, pgoff_t *done_index) { struct inode *inode = mapping->host; struct gfs2_sbd *sdp = GFS2_SB(inode); - unsigned nrblocks = nr_pages * (PAGE_SIZE >> inode->i_blkbits); + unsigned nrblocks; int i; int ret; + int nr_pages = 0; + int nr_folios = folio_batch_count(fbatch); + + for (i = 0; i < nr_folios; i++) + nr_pages += folio_nr_pages(fbatch->folios[i]); + nrblocks = nr_pages * (PAGE_SIZE >> inode->i_blkbits); ret = gfs2_trans_begin(sdp, nrblocks, nrblocks); if (ret < 0) return ret; - for(i = 0; i < nr_pages; i++) { - struct page *page = pvec->pages[i]; + for (i = 0; i < nr_folios; i++) { + struct folio *folio = fbatch->folios[i]; - *done_index = page->index; + *done_index = folio->index; - lock_page(page); + folio_lock(folio); - if (unlikely(page->mapping != mapping)) { + if (unlikely(folio->mapping != mapping)) { continue_unlock: - unlock_page(page); + folio_unlock(folio); continue; } - if (!PageDirty(page)) { + if (!folio_test_dirty(folio)) { /* someone wrote it for us */ goto continue_unlock; } - if (PageWriteback(page)) { + if (folio_test_writeback(folio)) { if (wbc->sync_mode != WB_SYNC_NONE) - wait_on_page_writeback(page); + folio_wait_writeback(folio); else goto continue_unlock; } - BUG_ON(PageWriteback(page)); - if (!clear_page_dirty_for_io(page)) + BUG_ON(folio_test_writeback(folio)); + if (!folio_clear_dirty_for_io(folio)) goto continue_unlock; trace_wbc_writepage(wbc, inode_to_bdi(inode)); - ret = __gfs2_jdata_writepage(page, wbc); + ret = __gfs2_jdata_writepage(&folio->page, wbc); if (unlikely(ret)) { if (ret == AOP_WRITEPAGE_ACTIVATE) { - unlock_page(page); + folio_unlock(folio); ret = 0; } else { @@ -268,7 +271,8 @@ continue_unlock: * not be suitable for data integrity * writeout). */ - *done_index = page->index + 1; + *done_index = folio->index + + folio_nr_pages(folio); ret = 1; break; } @@ -305,8 +309,8 @@ static int gfs2_write_cache_jdata(struct address_space *mapping, { int ret = 0; int done = 0; - struct pagevec pvec; - int nr_pages; + struct folio_batch fbatch; + int nr_folios; pgoff_t writeback_index; pgoff_t index; pgoff_t end; @@ -315,7 +319,7 @@ static int gfs2_write_cache_jdata(struct address_space *mapping, int range_whole = 0; xa_mark_t tag; - pagevec_init(&pvec); + folio_batch_init(&fbatch); if (wbc->range_cyclic) { writeback_index = mapping->writeback_index; /* prev offset */ index = writeback_index; @@ -341,17 +345,18 @@ retry: tag_pages_for_writeback(mapping, index, end); done_index = index; while (!done && (index <= end)) { - nr_pages = pagevec_lookup_range_tag(&pvec, mapping, &index, end, - tag); - if (nr_pages == 0) + nr_folios = filemap_get_folios_tag(mapping, &index, end, + tag, &fbatch); + if (nr_folios == 0) break; - ret = gfs2_write_jdata_pagevec(mapping, wbc, &pvec, nr_pages, &done_index); + ret = gfs2_write_jdata_batch(mapping, wbc, &fbatch, + &done_index); if (ret) done = 1; if (ret > 0) ret = 0; - pagevec_release(&pvec); + folio_batch_release(&fbatch); cond_resched(); } diff --git a/fs/gfs2/aops.h b/fs/gfs2/aops.h index ff9877a68780..09db1914425e 100644 --- a/fs/gfs2/aops.h +++ b/fs/gfs2/aops.h @@ -9,7 +9,7 @@ #include "incore.h" extern void adjust_fs_space(struct inode *inode); -extern void gfs2_page_add_databufs(struct gfs2_inode *ip, struct page *page, - unsigned int from, unsigned int len); +extern void gfs2_trans_add_databufs(struct gfs2_inode *ip, struct folio *folio, + unsigned int from, unsigned int len); #endif /* __AOPS_DOT_H__ */ diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index e7537fd305dd..eedf6926c652 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -956,26 +956,40 @@ hole_found: goto out; } -static int gfs2_iomap_page_prepare(struct inode *inode, loff_t pos, - unsigned len) +static struct folio * +gfs2_iomap_get_folio(struct iomap_iter *iter, loff_t pos, unsigned len) { + struct inode *inode = iter->inode; unsigned int blockmask = i_blocksize(inode) - 1; struct gfs2_sbd *sdp = GFS2_SB(inode); unsigned int blocks; + struct folio *folio; + int status; blocks = ((pos & blockmask) + len + blockmask) >> inode->i_blkbits; - return gfs2_trans_begin(sdp, RES_DINODE + blocks, 0); + status = gfs2_trans_begin(sdp, RES_DINODE + blocks, 0); + if (status) + return ERR_PTR(status); + + folio = iomap_get_folio(iter, pos); + if (IS_ERR(folio)) + gfs2_trans_end(sdp); + return folio; } -static void gfs2_iomap_page_done(struct inode *inode, loff_t pos, - unsigned copied, struct page *page) +static void gfs2_iomap_put_folio(struct inode *inode, loff_t pos, + unsigned copied, struct folio *folio) { struct gfs2_trans *tr = current->journal_info; struct gfs2_inode *ip = GFS2_I(inode); struct gfs2_sbd *sdp = GFS2_SB(inode); - if (page && !gfs2_is_stuffed(ip)) - gfs2_page_add_databufs(ip, page, offset_in_page(pos), copied); + if (!gfs2_is_stuffed(ip)) + gfs2_trans_add_databufs(ip, folio, offset_in_folio(folio, pos), + copied); + + folio_unlock(folio); + folio_put(folio); if (tr->tr_num_buf_new) __mark_inode_dirty(inode, I_DIRTY_DATASYNC); @@ -983,9 +997,9 @@ static void gfs2_iomap_page_done(struct inode *inode, loff_t pos, gfs2_trans_end(sdp); } -static const struct iomap_page_ops gfs2_iomap_page_ops = { - .page_prepare = gfs2_iomap_page_prepare, - .page_done = gfs2_iomap_page_done, +static const struct iomap_folio_ops gfs2_iomap_folio_ops = { + .get_folio = gfs2_iomap_get_folio, + .put_folio = gfs2_iomap_put_folio, }; static int gfs2_iomap_begin_write(struct inode *inode, loff_t pos, @@ -1061,7 +1075,7 @@ static int gfs2_iomap_begin_write(struct inode *inode, loff_t pos, } if (gfs2_is_stuffed(ip) || gfs2_is_jdata(ip)) - iomap->page_ops = &gfs2_iomap_page_ops; + iomap->folio_ops = &gfs2_iomap_folio_ops; return 0; out_trans_end: @@ -1277,7 +1291,7 @@ int gfs2_alloc_extent(struct inode *inode, u64 lblock, u64 *dblock, /* * NOTE: Never call gfs2_block_zero_range with an open transaction because it * uses iomap write to perform its actions, which begin their own transactions - * (iomap_begin, page_prepare, etc.) + * (iomap_begin, get_folio, etc.) */ static int gfs2_block_zero_range(struct inode *inode, loff_t from, unsigned int length) diff --git a/fs/gfs2/dentry.c b/fs/gfs2/dentry.c index 2e215e8c3c88..6fe9ca253b70 100644 --- a/fs/gfs2/dentry.c +++ b/fs/gfs2/dentry.c @@ -83,26 +83,8 @@ static int gfs2_dhash(const struct dentry *dentry, struct qstr *str) return 0; } -static int gfs2_dentry_delete(const struct dentry *dentry) -{ - struct gfs2_inode *ginode; - - if (d_really_is_negative(dentry)) - return 0; - - ginode = GFS2_I(d_inode(dentry)); - if (!gfs2_holder_initialized(&ginode->i_iopen_gh)) - return 0; - - if (test_bit(GLF_DEMOTE, &ginode->i_iopen_gh.gh_gl->gl_flags)) - return 1; - - return 0; -} - const struct dentry_operations gfs2_dops = { .d_revalidate = gfs2_drevalidate, .d_hash = gfs2_dhash, - .d_delete = gfs2_dentry_delete, }; diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index eea5be4fbf0e..300844f50dcd 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -15,6 +15,7 @@ #include <linux/mm.h> #include <linux/mount.h> #include <linux/fs.h> +#include <linux/filelock.h> #include <linux/gfs2_ondisk.h> #include <linux/falloc.h> #include <linux/swap.h> @@ -235,7 +236,7 @@ static int do_gfs2_set_flags(struct inode *inode, u32 reqflags, u32 mask) goto out; if (!IS_IMMUTABLE(inode)) { - error = gfs2_permission(&init_user_ns, inode, MAY_WRITE); + error = gfs2_permission(&nop_mnt_idmap, inode, MAY_WRITE); if (error) goto out; } @@ -273,7 +274,7 @@ out: return error; } -int gfs2_fileattr_set(struct user_namespace *mnt_userns, +int gfs2_fileattr_set(struct mnt_idmap *idmap, struct dentry *dentry, struct fileattr *fa) { struct inode *inode = d_inode(dentry); diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index 524f3c96b9a4..5adc7d85dbf3 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -67,7 +67,6 @@ static void handle_callback(struct gfs2_glock *gl, unsigned int state, static struct dentry *gfs2_root; static struct workqueue_struct *glock_workqueue; -struct workqueue_struct *gfs2_delete_workqueue; static LIST_HEAD(lru_list); static atomic_t lru_count = ATOMIC_INIT(0); static DEFINE_SPINLOCK(lru_lock); @@ -274,9 +273,8 @@ static void __gfs2_glock_put(struct gfs2_glock *gl) struct address_space *mapping = gfs2_glock2aspace(gl); lockref_mark_dead(&gl->gl_lockref); - - gfs2_glock_remove_from_lru(gl); spin_unlock(&gl->gl_lockref.lock); + gfs2_glock_remove_from_lru(gl); GLOCK_BUG_ON(gl, !list_empty(&gl->gl_holders)); if (mapping) { truncate_inode_pages_final(mapping); @@ -883,6 +881,7 @@ void glock_set_object(struct gfs2_glock *gl, void *object) /** * glock_clear_object - clear the gl_object field of a glock * @gl: the glock + * @object: object the glock currently points at */ void glock_clear_object(struct gfs2_glock *gl, void *object) { @@ -892,8 +891,7 @@ void glock_clear_object(struct gfs2_glock *gl, void *object) prev_object = gl->gl_object; gl->gl_object = NULL; spin_unlock(&gl->gl_lockref.lock); - if (gfs2_assert_warn(gl->gl_name.ln_sbd, - prev_object == object || prev_object == NULL)) { + if (gfs2_assert_warn(gl->gl_name.ln_sbd, prev_object == object)) { pr_warn("glock=%u/%llx\n", gl->gl_name.ln_type, (unsigned long long)gl->gl_name.ln_number); @@ -977,6 +975,26 @@ static bool gfs2_try_evict(struct gfs2_glock *gl) return evicted; } +bool gfs2_queue_try_to_evict(struct gfs2_glock *gl) +{ + struct gfs2_sbd *sdp = gl->gl_name.ln_sbd; + + if (test_and_set_bit(GLF_TRY_TO_EVICT, &gl->gl_flags)) + return false; + return queue_delayed_work(sdp->sd_delete_wq, + &gl->gl_delete, 0); +} + +static bool gfs2_queue_verify_evict(struct gfs2_glock *gl) +{ + struct gfs2_sbd *sdp = gl->gl_name.ln_sbd; + + if (test_and_set_bit(GLF_VERIFY_EVICT, &gl->gl_flags)) + return false; + return queue_delayed_work(sdp->sd_delete_wq, + &gl->gl_delete, 5 * HZ); +} + static void delete_work_func(struct work_struct *work) { struct delayed_work *dwork = to_delayed_work(work); @@ -985,11 +1003,7 @@ static void delete_work_func(struct work_struct *work) struct inode *inode; u64 no_addr = gl->gl_name.ln_number; - spin_lock(&gl->gl_lockref.lock); - clear_bit(GLF_PENDING_DELETE, &gl->gl_flags); - spin_unlock(&gl->gl_lockref.lock); - - if (test_bit(GLF_DEMOTE, &gl->gl_flags)) { + if (test_and_clear_bit(GLF_TRY_TO_EVICT, &gl->gl_flags)) { /* * If we can evict the inode, give the remote node trying to * delete the inode some time before verifying that the delete @@ -1008,22 +1022,28 @@ static void delete_work_func(struct work_struct *work) * step entirely. */ if (gfs2_try_evict(gl)) { - if (gfs2_queue_delete_work(gl, 5 * HZ)) + if (test_bit(SDF_DEACTIVATING, &sdp->sd_flags)) + goto out; + if (gfs2_queue_verify_evict(gl)) return; } goto out; } - inode = gfs2_lookup_by_inum(sdp, no_addr, gl->gl_no_formal_ino, - GFS2_BLKST_UNLINKED); - if (IS_ERR(inode)) { - if (PTR_ERR(inode) == -EAGAIN && - (gfs2_queue_delete_work(gl, 5 * HZ))) + if (test_and_clear_bit(GLF_VERIFY_EVICT, &gl->gl_flags)) { + inode = gfs2_lookup_by_inum(sdp, no_addr, gl->gl_no_formal_ino, + GFS2_BLKST_UNLINKED); + if (IS_ERR(inode)) { + if (PTR_ERR(inode) == -EAGAIN && + !test_bit(SDF_DEACTIVATING, &sdp->sd_flags) && + gfs2_queue_verify_evict(gl)) return; - } else { - d_prune_aliases(inode); - iput(inode); + } else { + d_prune_aliases(inode); + iput(inode); + } } + out: gfs2_glock_put(gl); } @@ -1985,26 +2005,26 @@ add_back_to_lru: static long gfs2_scan_glock_lru(int nr) { - struct gfs2_glock *gl; - LIST_HEAD(skipped); + struct gfs2_glock *gl, *next; LIST_HEAD(dispose); long freed = 0; spin_lock(&lru_lock); - while ((nr-- >= 0) && !list_empty(&lru_list)) { - gl = list_first_entry(&lru_list, struct gfs2_glock, gl_lru); - + list_for_each_entry_safe(gl, next, &lru_list, gl_lru) { + if (nr-- <= 0) + break; /* Test for being demotable */ if (!test_bit(GLF_LOCK, &gl->gl_flags)) { - list_move(&gl->gl_lru, &dispose); - atomic_dec(&lru_count); - freed++; - continue; + if (!spin_trylock(&gl->gl_lockref.lock)) + continue; + if (!gl->gl_lockref.count) { + list_move(&gl->gl_lru, &dispose); + atomic_dec(&lru_count); + freed++; + } + spin_unlock(&gl->gl_lockref.lock); } - - list_move(&gl->gl_lru, &skipped); } - list_splice(&skipped, &lru_list); if (!list_empty(&dispose)) gfs2_dispose_glock_lru(&dispose); spin_unlock(&lru_lock); @@ -2063,37 +2083,21 @@ static void glock_hash_walk(glock_examiner examiner, const struct gfs2_sbd *sdp) rhashtable_walk_exit(&iter); } -bool gfs2_queue_delete_work(struct gfs2_glock *gl, unsigned long delay) -{ - bool queued; - - spin_lock(&gl->gl_lockref.lock); - queued = queue_delayed_work(gfs2_delete_workqueue, - &gl->gl_delete, delay); - if (queued) - set_bit(GLF_PENDING_DELETE, &gl->gl_flags); - spin_unlock(&gl->gl_lockref.lock); - return queued; -} - void gfs2_cancel_delete_work(struct gfs2_glock *gl) { - if (cancel_delayed_work(&gl->gl_delete)) { - clear_bit(GLF_PENDING_DELETE, &gl->gl_flags); + clear_bit(GLF_TRY_TO_EVICT, &gl->gl_flags); + clear_bit(GLF_VERIFY_EVICT, &gl->gl_flags); + if (cancel_delayed_work(&gl->gl_delete)) gfs2_glock_put(gl); - } -} - -bool gfs2_delete_work_queued(const struct gfs2_glock *gl) -{ - return test_bit(GLF_PENDING_DELETE, &gl->gl_flags); } static void flush_delete_work(struct gfs2_glock *gl) { if (gl->gl_name.ln_type == LM_TYPE_IOPEN) { + struct gfs2_sbd *sdp = gl->gl_name.ln_sbd; + if (cancel_delayed_work(&gl->gl_delete)) { - queue_delayed_work(gfs2_delete_workqueue, + queue_delayed_work(sdp->sd_delete_wq, &gl->gl_delete, 0); } } @@ -2102,7 +2106,7 @@ static void flush_delete_work(struct gfs2_glock *gl) void gfs2_flush_delete_work(struct gfs2_sbd *sdp) { glock_hash_walk(flush_delete_work, sdp); - flush_workqueue(gfs2_delete_workqueue); + flush_workqueue(sdp->sd_delete_wq); } /** @@ -2308,14 +2312,16 @@ static const char *gflags2str(char *buf, const struct gfs2_glock *gl) *p++ = 'o'; if (test_bit(GLF_BLOCKING, gflags)) *p++ = 'b'; - if (test_bit(GLF_PENDING_DELETE, gflags)) - *p++ = 'P'; if (test_bit(GLF_FREEING, gflags)) *p++ = 'x'; if (test_bit(GLF_INSTANTIATE_NEEDED, gflags)) *p++ = 'n'; if (test_bit(GLF_INSTANTIATE_IN_PROG, gflags)) *p++ = 'N'; + if (test_bit(GLF_TRY_TO_EVICT, gflags)) + *p++ = 'e'; + if (test_bit(GLF_VERIFY_EVICT, gflags)) + *p++ = 'E'; *p = 0; return buf; } @@ -2465,18 +2471,9 @@ int __init gfs2_glock_init(void) rhashtable_destroy(&gl_hash_table); return -ENOMEM; } - gfs2_delete_workqueue = alloc_workqueue("delete_workqueue", - WQ_MEM_RECLAIM | WQ_FREEZABLE, - 0); - if (!gfs2_delete_workqueue) { - destroy_workqueue(glock_workqueue); - rhashtable_destroy(&gl_hash_table); - return -ENOMEM; - } ret = register_shrinker(&glock_shrinker, "gfs2-glock"); if (ret) { - destroy_workqueue(gfs2_delete_workqueue); destroy_workqueue(glock_workqueue); rhashtable_destroy(&gl_hash_table); return ret; @@ -2493,7 +2490,6 @@ void gfs2_glock_exit(void) unregister_shrinker(&glock_shrinker); rhashtable_destroy(&gl_hash_table); destroy_workqueue(glock_workqueue); - destroy_workqueue(gfs2_delete_workqueue); } static void gfs2_glock_iter_next(struct gfs2_glock_iter *gi, loff_t n) diff --git a/fs/gfs2/glock.h b/fs/gfs2/glock.h index f37ac087e2c1..1f1ba92c15a8 100644 --- a/fs/gfs2/glock.h +++ b/fs/gfs2/glock.h @@ -144,7 +144,6 @@ struct gfs2_glock_aspace { struct address_space mapping; }; -extern struct workqueue_struct *gfs2_delete_workqueue; static inline struct gfs2_holder *gfs2_glock_is_locked_by_me(struct gfs2_glock *gl) { struct gfs2_holder *gh; @@ -268,9 +267,8 @@ static inline int gfs2_glock_nq_init(struct gfs2_glock *gl, extern void gfs2_glock_cb(struct gfs2_glock *gl, unsigned int state); extern void gfs2_glock_complete(struct gfs2_glock *gl, int ret); -extern bool gfs2_queue_delete_work(struct gfs2_glock *gl, unsigned long delay); +extern bool gfs2_queue_try_to_evict(struct gfs2_glock *gl); extern void gfs2_cancel_delete_work(struct gfs2_glock *gl); -extern bool gfs2_delete_work_queued(const struct gfs2_glock *gl); extern void gfs2_flush_delete_work(struct gfs2_sbd *sdp); extern void gfs2_gl_hash_clear(struct gfs2_sbd *sdp); extern void gfs2_gl_dq_holders(struct gfs2_sbd *sdp); diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c index d78b61ecc1cd..4d99cc77a29b 100644 --- a/fs/gfs2/glops.c +++ b/fs/gfs2/glops.c @@ -39,7 +39,7 @@ static void gfs2_ail_error(struct gfs2_glock *gl, const struct buffer_head *bh) "AIL buffer %p: blocknr %llu state 0x%08lx mapping %p page " "state 0x%lx\n", bh, (unsigned long long)bh->b_blocknr, bh->b_state, - bh->b_page->mapping, bh->b_page->flags); + bh->b_folio->mapping, bh->b_folio->flags); fs_err(sdp, "AIL glock %u:%llu mapping %p\n", gl->gl_name.ln_type, gl->gl_name.ln_number, gfs2_glock2aspace(gl)); @@ -193,7 +193,7 @@ static int rgrp_go_sync(struct gfs2_glock *gl) struct gfs2_rgrpd *rgd = gfs2_glock2rgrp(gl); int error; - if (!test_and_clear_bit(GLF_DIRTY, &gl->gl_flags)) + if (!rgd || !test_and_clear_bit(GLF_DIRTY, &gl->gl_flags)) return 0; GLOCK_BUG_ON(gl, gl->gl_state != LM_ST_EXCLUSIVE); @@ -222,9 +222,12 @@ static void rgrp_go_inval(struct gfs2_glock *gl, int flags) struct address_space *mapping = &sdp->sd_aspace; struct gfs2_rgrpd *rgd = gfs2_glock2rgrp(gl); const unsigned bsize = sdp->sd_sb.sb_bsize; - loff_t start = (rgd->rd_addr * bsize) & PAGE_MASK; - loff_t end = PAGE_ALIGN((rgd->rd_addr + rgd->rd_length) * bsize) - 1; + loff_t start, end; + if (!rgd) + return; + start = (rgd->rd_addr * bsize) & PAGE_MASK; + end = PAGE_ALIGN((rgd->rd_addr + rgd->rd_length) * bsize) - 1; gfs2_rgrp_brelse(rgd); WARN_ON_ONCE(!(flags & DIO_METADATA)); truncate_inode_pages_range(mapping, start, end); @@ -645,23 +648,18 @@ static void iopen_go_callback(struct gfs2_glock *gl, bool remote) struct gfs2_inode *ip = gl->gl_object; struct gfs2_sbd *sdp = gl->gl_name.ln_sbd; - if (!remote || sb_rdonly(sdp->sd_vfs)) + if (!remote || sb_rdonly(sdp->sd_vfs) || + test_bit(SDF_DEACTIVATING, &sdp->sd_flags)) return; if (gl->gl_demote_state == LM_ST_UNLOCKED && gl->gl_state == LM_ST_SHARED && ip) { gl->gl_lockref.count++; - if (!queue_delayed_work(gfs2_delete_workqueue, - &gl->gl_delete, 0)) + if (!gfs2_queue_try_to_evict(gl)) gl->gl_lockref.count--; } } -static int iopen_go_demote_ok(const struct gfs2_glock *gl) -{ - return !gfs2_delete_work_queued(gl); -} - /** * inode_go_free - wake up anyone waiting for dlm's unlock ast to free it * @gl: glock being freed @@ -767,7 +765,6 @@ const struct gfs2_glock_operations gfs2_iopen_glops = { .go_type = LM_TYPE_IOPEN, .go_callback = iopen_go_callback, .go_dump = inode_go_dump, - .go_demote_ok = iopen_go_demote_ok, .go_flags = GLOF_LRU | GLOF_NONDISK, .go_subclass = 1, }; diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h index c26765080f28..79485329118b 100644 --- a/fs/gfs2/incore.h +++ b/fs/gfs2/incore.h @@ -329,8 +329,9 @@ enum { GLF_LRU = 13, GLF_OBJECT = 14, /* Used only for tracing */ GLF_BLOCKING = 15, - GLF_PENDING_DELETE = 17, - GLF_FREEING = 18, /* Wait for glock to be freed */ + GLF_FREEING = 16, /* Wait for glock to be freed */ + GLF_TRY_TO_EVICT = 17, /* iopen glocks only */ + GLF_VERIFY_EVICT = 18, /* iopen glocks only */ }; struct gfs2_glock { @@ -605,6 +606,8 @@ enum { SDF_REMOTE_WITHDRAW = 13, /* Performing remote recovery */ SDF_WITHDRAW_RECOVERY = 14, /* Wait for journal recovery when we are withdrawing */ + SDF_DEACTIVATING = 15, + SDF_EVICTING = 16, }; enum gfs2_freeze_state { @@ -771,6 +774,10 @@ struct gfs2_sbd { struct completion sd_journal_ready; + /* Workqueue stuff */ + + struct workqueue_struct *sd_delete_wq; + /* Daemon stuff */ struct task_struct *sd_logd_process; diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index 614db3055c02..1291b5ee3584 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -225,6 +225,10 @@ fail: gfs2_glock_dq_uninit(&ip->i_iopen_gh); if (gfs2_holder_initialized(&i_gh)) gfs2_glock_dq_uninit(&i_gh); + if (ip->i_gl) { + gfs2_glock_put(ip->i_gl); + ip->i_gl = NULL; + } iget_failed(inode); return ERR_PTR(error); } @@ -320,7 +324,7 @@ struct inode *gfs2_lookupi(struct inode *dir, const struct qstr *name, } if (!is_root) { - error = gfs2_permission(&init_user_ns, dir, MAY_EXEC); + error = gfs2_permission(&nop_mnt_idmap, dir, MAY_EXEC); if (error) goto out; } @@ -350,7 +354,7 @@ static int create_ok(struct gfs2_inode *dip, const struct qstr *name, { int error; - error = gfs2_permission(&init_user_ns, &dip->i_inode, + error = gfs2_permission(&nop_mnt_idmap, &dip->i_inode, MAY_WRITE | MAY_EXEC); if (error) return error; @@ -816,6 +820,10 @@ fail_gunlock3: fail_gunlock2: gfs2_glock_put(io_gl); fail_free_inode: + if (ip->i_gl) { + gfs2_glock_put(ip->i_gl); + ip->i_gl = NULL; + } gfs2_rs_deltree(&ip->i_res); gfs2_qa_put(ip); fail_free_acls: @@ -843,7 +851,7 @@ fail: /** * gfs2_create - Create a file - * @mnt_userns: User namespace of the mount the inode was found from + * @idmap: idmap of the mount the inode was found from * @dir: The directory in which to create the file * @dentry: The dentry of the new file * @mode: The mode of the new file @@ -852,7 +860,7 @@ fail: * Returns: errno */ -static int gfs2_create(struct user_namespace *mnt_userns, struct inode *dir, +static int gfs2_create(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { return gfs2_create_inode(dir, dentry, NULL, S_IFREG | mode, 0, NULL, 0, excl); @@ -960,7 +968,7 @@ static int gfs2_link(struct dentry *old_dentry, struct inode *dir, if (inode->i_nlink == 0) goto out_gunlock; - error = gfs2_permission(&init_user_ns, dir, MAY_WRITE | MAY_EXEC); + error = gfs2_permission(&nop_mnt_idmap, dir, MAY_WRITE | MAY_EXEC); if (error) goto out_gunlock; @@ -1078,7 +1086,7 @@ static int gfs2_unlink_ok(struct gfs2_inode *dip, const struct qstr *name, if (IS_APPEND(&dip->i_inode)) return -EPERM; - error = gfs2_permission(&init_user_ns, &dip->i_inode, + error = gfs2_permission(&nop_mnt_idmap, &dip->i_inode, MAY_WRITE | MAY_EXEC); if (error) return error; @@ -1207,7 +1215,7 @@ out_inodes: /** * gfs2_symlink - Create a symlink - * @mnt_userns: User namespace of the mount the inode was found from + * @idmap: idmap of the mount the inode was found from * @dir: The directory to create the symlink in * @dentry: The dentry to put the symlink in * @symname: The thing which the link points to @@ -1215,7 +1223,7 @@ out_inodes: * Returns: errno */ -static int gfs2_symlink(struct user_namespace *mnt_userns, struct inode *dir, +static int gfs2_symlink(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, const char *symname) { unsigned int size; @@ -1229,7 +1237,7 @@ static int gfs2_symlink(struct user_namespace *mnt_userns, struct inode *dir, /** * gfs2_mkdir - Make a directory - * @mnt_userns: User namespace of the mount the inode was found from + * @idmap: idmap of the mount the inode was found from * @dir: The parent directory of the new one * @dentry: The dentry of the new directory * @mode: The mode of the new directory @@ -1237,7 +1245,7 @@ static int gfs2_symlink(struct user_namespace *mnt_userns, struct inode *dir, * Returns: errno */ -static int gfs2_mkdir(struct user_namespace *mnt_userns, struct inode *dir, +static int gfs2_mkdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode) { unsigned dsize = gfs2_max_stuffed_size(GFS2_I(dir)); @@ -1246,7 +1254,7 @@ static int gfs2_mkdir(struct user_namespace *mnt_userns, struct inode *dir, /** * gfs2_mknod - Make a special file - * @mnt_userns: User namespace of the mount the inode was found from + * @idmap: idmap of the mount the inode was found from * @dir: The directory in which the special file will reside * @dentry: The dentry of the special file * @mode: The mode of the special file @@ -1254,7 +1262,7 @@ static int gfs2_mkdir(struct user_namespace *mnt_userns, struct inode *dir, * */ -static int gfs2_mknod(struct user_namespace *mnt_userns, struct inode *dir, +static int gfs2_mknod(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev) { return gfs2_create_inode(dir, dentry, NULL, mode, dev, NULL, 0, 0); @@ -1504,7 +1512,7 @@ static int gfs2_rename(struct inode *odir, struct dentry *odentry, } } } else { - error = gfs2_permission(&init_user_ns, ndir, + error = gfs2_permission(&nop_mnt_idmap, ndir, MAY_WRITE | MAY_EXEC); if (error) goto out_gunlock; @@ -1541,7 +1549,7 @@ static int gfs2_rename(struct inode *odir, struct dentry *odentry, /* Check out the dir to be renamed */ if (dir_rename) { - error = gfs2_permission(&init_user_ns, d_inode(odentry), + error = gfs2_permission(&nop_mnt_idmap, d_inode(odentry), MAY_WRITE); if (error) goto out_gunlock; @@ -1705,13 +1713,13 @@ static int gfs2_exchange(struct inode *odir, struct dentry *odentry, goto out_gunlock; if (S_ISDIR(old_mode)) { - error = gfs2_permission(&init_user_ns, odentry->d_inode, + error = gfs2_permission(&nop_mnt_idmap, odentry->d_inode, MAY_WRITE); if (error) goto out_gunlock; } if (S_ISDIR(new_mode)) { - error = gfs2_permission(&init_user_ns, ndentry->d_inode, + error = gfs2_permission(&nop_mnt_idmap, ndentry->d_inode, MAY_WRITE); if (error) goto out_gunlock; @@ -1766,7 +1774,7 @@ out: return error; } -static int gfs2_rename2(struct user_namespace *mnt_userns, struct inode *odir, +static int gfs2_rename2(struct mnt_idmap *idmap, struct inode *odir, struct dentry *odentry, struct inode *ndir, struct dentry *ndentry, unsigned int flags) { @@ -1841,7 +1849,7 @@ out: /** * gfs2_permission - * @mnt_userns: User namespace of the mount the inode was found from + * @idmap: idmap of the mount the inode was found from * @inode: The inode * @mask: The mask to be tested * @@ -1852,7 +1860,7 @@ out: * Returns: errno */ -int gfs2_permission(struct user_namespace *mnt_userns, struct inode *inode, +int gfs2_permission(struct mnt_idmap *idmap, struct inode *inode, int mask) { struct gfs2_inode *ip; @@ -1872,7 +1880,7 @@ int gfs2_permission(struct user_namespace *mnt_userns, struct inode *inode, if ((mask & MAY_WRITE) && IS_IMMUTABLE(inode)) error = -EPERM; else - error = generic_permission(&init_user_ns, inode, mask); + error = generic_permission(&nop_mnt_idmap, inode, mask); if (gfs2_holder_initialized(&i_gh)) gfs2_glock_dq_uninit(&i_gh); @@ -1881,7 +1889,7 @@ int gfs2_permission(struct user_namespace *mnt_userns, struct inode *inode, static int __gfs2_setattr_simple(struct inode *inode, struct iattr *attr) { - setattr_copy(&init_user_ns, inode, attr); + setattr_copy(&nop_mnt_idmap, inode, attr); mark_inode_dirty(inode); return 0; } @@ -1966,7 +1974,7 @@ out: /** * gfs2_setattr - Change attributes on an inode - * @mnt_userns: User namespace of the mount the inode was found from + * @idmap: idmap of the mount the inode was found from * @dentry: The dentry which is changing * @attr: The structure describing the change * @@ -1976,7 +1984,7 @@ out: * Returns: errno */ -static int gfs2_setattr(struct user_namespace *mnt_userns, +static int gfs2_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { struct inode *inode = d_inode(dentry); @@ -1992,11 +2000,11 @@ static int gfs2_setattr(struct user_namespace *mnt_userns, if (error) goto out; - error = may_setattr(&init_user_ns, inode, attr->ia_valid); + error = may_setattr(&nop_mnt_idmap, inode, attr->ia_valid); if (error) goto error; - error = setattr_prepare(&init_user_ns, dentry, attr); + error = setattr_prepare(&nop_mnt_idmap, dentry, attr); if (error) goto error; @@ -2007,7 +2015,7 @@ static int gfs2_setattr(struct user_namespace *mnt_userns, else { error = gfs2_setattr_simple(inode, attr); if (!error && attr->ia_valid & ATTR_MODE) - error = posix_acl_chmod(&init_user_ns, dentry, + error = posix_acl_chmod(&nop_mnt_idmap, dentry, inode->i_mode); } @@ -2022,7 +2030,7 @@ out: /** * gfs2_getattr - Read out an inode's attributes - * @mnt_userns: user namespace of the mount the inode was found from + * @idmap: idmap of the mount the inode was found from * @path: Object to query * @stat: The inode's stats * @request_mask: Mask of STATX_xxx flags indicating the caller's interests @@ -2037,7 +2045,7 @@ out: * Returns: errno */ -static int gfs2_getattr(struct user_namespace *mnt_userns, +static int gfs2_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int flags) { @@ -2066,7 +2074,7 @@ static int gfs2_getattr(struct user_namespace *mnt_userns, STATX_ATTR_IMMUTABLE | STATX_ATTR_NODUMP); - generic_fillattr(&init_user_ns, inode, stat); + generic_fillattr(&nop_mnt_idmap, inode, stat); if (gfs2_holder_initialized(&gh)) gfs2_glock_dq_uninit(&gh); diff --git a/fs/gfs2/inode.h b/fs/gfs2/inode.h index 0264d514dda7..c8c5814e7295 100644 --- a/fs/gfs2/inode.h +++ b/fs/gfs2/inode.h @@ -99,7 +99,7 @@ extern int gfs2_inode_refresh(struct gfs2_inode *ip); extern struct inode *gfs2_lookupi(struct inode *dir, const struct qstr *name, int is_root); -extern int gfs2_permission(struct user_namespace *mnt_userns, +extern int gfs2_permission(struct mnt_idmap *idmap, struct inode *inode, int mask); extern struct inode *gfs2_lookup_simple(struct inode *dip, const char *name); extern void gfs2_dinode_out(const struct gfs2_inode *ip, void *buf); @@ -111,7 +111,7 @@ extern const struct file_operations gfs2_file_fops_nolock; extern const struct file_operations gfs2_dir_fops_nolock; extern int gfs2_fileattr_get(struct dentry *dentry, struct fileattr *fa); -extern int gfs2_fileattr_set(struct user_namespace *mnt_userns, +extern int gfs2_fileattr_set(struct mnt_idmap *idmap, struct dentry *dentry, struct fileattr *fa); extern void gfs2_set_inode_flags(struct inode *inode); diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c index 723639376ae2..d750d1128bed 100644 --- a/fs/gfs2/log.c +++ b/fs/gfs2/log.c @@ -80,6 +80,15 @@ void gfs2_remove_from_ail(struct gfs2_bufdata *bd) brelse(bd->bd_bh); } +static int __gfs2_writepage(struct folio *folio, struct writeback_control *wbc, + void *data) +{ + struct address_space *mapping = data; + int ret = mapping->a_ops->writepage(&folio->page, wbc); + mapping_set_error(mapping, ret); + return ret; +} + /** * gfs2_ail1_start_one - Start I/O on a transaction * @sdp: The superblock @@ -127,11 +136,11 @@ __acquires(&sdp->sd_ail_lock) continue; gl = bd->bd_gl; list_move(&bd->bd_ail_st_list, &tr->tr_ail1_list); - mapping = bh->b_page->mapping; + mapping = bh->b_folio->mapping; if (!mapping) continue; spin_unlock(&sdp->sd_ail_lock); - ret = filemap_fdatawrite_wbc(mapping, wbc); + ret = write_cache_pages(mapping, wbc, __gfs2_writepage, mapping); if (need_resched()) { blk_finish_plug(plug); cond_resched(); diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c index 3c41b864ee5b..924361fa510b 100644 --- a/fs/gfs2/meta_io.c +++ b/fs/gfs2/meta_io.c @@ -334,7 +334,7 @@ int gfs2_meta_wait(struct gfs2_sbd *sdp, struct buffer_head *bh) void gfs2_remove_from_journal(struct buffer_head *bh, int meta) { - struct address_space *mapping = bh->b_page->mapping; + struct address_space *mapping = bh->b_folio->mapping; struct gfs2_sbd *sdp = gfs2_mapping2sbd(mapping); struct gfs2_bufdata *bd = bh->b_private; struct gfs2_trans *tr = current->journal_info; diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index c0cf1d2d0ef5..6de901c3b89b 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -1197,9 +1197,15 @@ static int gfs2_fill_super(struct super_block *sb, struct fs_context *fc) snprintf(sdp->sd_fsname, sizeof(sdp->sd_fsname), "%s", sdp->sd_table_name); + sdp->sd_delete_wq = alloc_workqueue("gfs2-delete/%s", + WQ_MEM_RECLAIM | WQ_FREEZABLE, 0, sdp->sd_fsname); + error = -ENOMEM; + if (!sdp->sd_delete_wq) + goto fail_free; + error = gfs2_sys_fs_add(sdp); if (error) - goto fail_free; + goto fail_delete_wq; gfs2_create_debugfs_file(sdp); @@ -1309,6 +1315,8 @@ fail_lm: fail_debug: gfs2_delete_debugfs_file(sdp); gfs2_sys_fs_del(sdp); +fail_delete_wq: + destroy_workqueue(sdp->sd_delete_wq); fail_free: free_sbd(sdp); sb->s_fs_info = NULL; @@ -1720,6 +1728,55 @@ static int gfs2_meta_init_fs_context(struct fs_context *fc) return 0; } +/** + * gfs2_evict_inodes - evict inodes cooperatively + * @sb: the superblock + * + * When evicting an inode with a zero link count, we are trying to upgrade the + * inode's iopen glock from SH to EX mode in order to determine if we can + * delete the inode. The other nodes are supposed to evict the inode from + * their caches if they can, and to poke the inode's inode glock if they cannot + * do so. Either behavior allows gfs2_upgrade_iopen_glock() to proceed + * quickly, but if the other nodes are not cooperating, the lock upgrading + * attempt will time out. Since inodes are evicted sequentially, this can add + * up quickly. + * + * Function evict_inodes() tries to keep the s_inode_list_lock list locked over + * a long time, which prevents other inodes from being evicted concurrently. + * This precludes the cooperative behavior we are looking for. This special + * version of evict_inodes() avoids that. + * + * Modeled after drop_pagecache_sb(). + */ +static void gfs2_evict_inodes(struct super_block *sb) +{ + struct inode *inode, *toput_inode = NULL; + struct gfs2_sbd *sdp = sb->s_fs_info; + + set_bit(SDF_EVICTING, &sdp->sd_flags); + + spin_lock(&sb->s_inode_list_lock); + list_for_each_entry(inode, &sb->s_inodes, i_sb_list) { + spin_lock(&inode->i_lock); + if ((inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) && + !need_resched()) { + spin_unlock(&inode->i_lock); + continue; + } + atomic_inc(&inode->i_count); + spin_unlock(&inode->i_lock); + spin_unlock(&sb->s_inode_list_lock); + + iput(toput_inode); + toput_inode = inode; + + cond_resched(); + spin_lock(&sb->s_inode_list_lock); + } + spin_unlock(&sb->s_inode_list_lock); + iput(toput_inode); +} + static void gfs2_kill_sb(struct super_block *sb) { struct gfs2_sbd *sdp = sb->s_fs_info; @@ -1735,6 +1792,18 @@ static void gfs2_kill_sb(struct super_block *sb) sdp->sd_root_dir = NULL; sdp->sd_master_dir = NULL; shrink_dcache_sb(sb); + + gfs2_evict_inodes(sb); + + /* + * Flush and then drain the delete workqueue here (via + * destroy_workqueue()) to ensure that any delete work that + * may be running will also see the SDF_DEACTIVATING flag. + */ + set_bit(SDF_DEACTIVATING, &sdp->sd_flags); + gfs2_flush_delete_work(sdp); + destroy_workqueue(sdp->sd_delete_wq); + kill_block_super(sb); } diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c index f602fb844951..3b9b76e980ad 100644 --- a/fs/gfs2/rgrp.c +++ b/fs/gfs2/rgrp.c @@ -1879,7 +1879,7 @@ static void try_rgrp_unlink(struct gfs2_rgrpd *rgd, u64 *last_unlinked, u64 skip */ ip = gl->gl_object; - if (ip || !gfs2_queue_delete_work(gl, 0)) + if (ip || !gfs2_queue_try_to_evict(gl)) gfs2_glock_put(gl); else found++; diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c index 999cc146d708..a83fa62106f0 100644 --- a/fs/gfs2/super.c +++ b/fs/gfs2/super.c @@ -138,8 +138,10 @@ int gfs2_make_fs_rw(struct gfs2_sbd *sdp) return -EIO; error = gfs2_find_jhead(sdp->sd_jdesc, &head, false); - if (error || gfs2_withdrawn(sdp)) + if (error) { + gfs2_consist(sdp); return error; + } if (!(head.lh_flags & GFS2_LOG_HEAD_UNMOUNT)) { gfs2_consist(sdp); @@ -151,7 +153,9 @@ int gfs2_make_fs_rw(struct gfs2_sbd *sdp) gfs2_log_pointers_init(sdp, head.lh_blkno); error = gfs2_quota_init(sdp); - if (!error && !gfs2_withdrawn(sdp)) + if (!error && gfs2_withdrawn(sdp)) + error = -EIO; + if (!error) set_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags); return error; } @@ -529,7 +533,9 @@ void gfs2_make_fs_ro(struct gfs2_sbd *sdp) { int log_write_allowed = test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags); - gfs2_flush_delete_work(sdp); + if (!test_bit(SDF_DEACTIVATING, &sdp->sd_flags)) + gfs2_flush_delete_work(sdp); + if (!log_write_allowed && current == sdp->sd_quotad_process) fs_warn(sdp, "The quotad daemon is withdrawing.\n"); else if (sdp->sd_quotad_process) @@ -933,6 +939,7 @@ static int gfs2_statfs(struct dentry *dentry, struct kstatfs *buf) static int gfs2_drop_inode(struct inode *inode) { struct gfs2_inode *ip = GFS2_I(inode); + struct gfs2_sbd *sdp = GFS2_SB(inode); if (inode->i_nlink && gfs2_holder_initialized(&ip->i_iopen_gh)) { @@ -952,11 +959,17 @@ static int gfs2_drop_inode(struct inode *inode) struct gfs2_glock *gl = ip->i_iopen_gh.gh_gl; gfs2_glock_hold(gl); - if (!gfs2_queue_delete_work(gl, 0)) + if (!gfs2_queue_try_to_evict(gl)) gfs2_glock_queue_put(gl); return 0; } + /* + * No longer cache inodes when trying to evict them all. + */ + if (test_bit(SDF_EVICTING, &sdp->sd_flags)) + return 1; + return generic_drop_inode(inode); } @@ -1175,15 +1188,23 @@ static bool gfs2_upgrade_iopen_glock(struct inode *inode) gfs2_glock_dq_wait(gh); /* - * If there are no other lock holders, we'll get the lock immediately. + * If there are no other lock holders, we will immediately get + * exclusive access to the iopen glock here. + * * Otherwise, the other nodes holding the lock will be notified about - * our locking request. If they don't have the inode open, they'll - * evict the cached inode and release the lock. Otherwise, if they - * poke the inode glock, we'll take this as an indication that they - * still need the iopen glock and that they'll take care of deleting - * the inode when they're done. As a last resort, if another node - * keeps holding the iopen glock without showing any activity on the - * inode glock, we'll eventually time out. + * our locking request. If they do not have the inode open, they are + * expected to evict the cached inode and release the lock, allowing us + * to proceed. + * + * Otherwise, if they cannot evict the inode, they are expected to poke + * the inode glock (note: not the iopen glock). We will notice that + * and stop waiting for the iopen glock immediately. The other node(s) + * are then expected to take care of deleting the inode when they no + * longer use it. + * + * As a last resort, if another node keeps holding the iopen glock + * without showing any activity on the inode glock, we will eventually + * time out and fail the iopen glock upgrade. * * Note that we're passing the LM_FLAG_TRY_1CB flag to the first * locking request as an optimization to notify lock holders as soon as @@ -1401,10 +1422,8 @@ static void gfs2_evict_inode(struct inode *inode) if (gfs2_rs_active(&ip->i_res)) gfs2_rs_deltree(&ip->i_res); - if (gfs2_holder_initialized(&gh)) { - glock_clear_object(ip->i_gl, ip); + if (gfs2_holder_initialized(&gh)) gfs2_glock_dq_uninit(&gh); - } if (ret && ret != GLR_TRYFAILED && ret != -EROFS) fs_warn(sdp, "gfs2_evict_inode: %d\n", ret); out: diff --git a/fs/gfs2/sys.c b/fs/gfs2/sys.c index d87ea98cf535..454dc2ff8b5e 100644 --- a/fs/gfs2/sys.c +++ b/fs/gfs2/sys.c @@ -87,6 +87,7 @@ static ssize_t status_show(struct gfs2_sbd *sdp, char *buf) "Withdraw In Prog: %d\n" "Remote Withdraw: %d\n" "Withdraw Recovery: %d\n" + "Deactivating: %d\n" "sd_log_error: %d\n" "sd_log_flush_lock: %d\n" "sd_log_num_revoke: %u\n" @@ -115,6 +116,7 @@ static ssize_t status_show(struct gfs2_sbd *sdp, char *buf) test_bit(SDF_WITHDRAW_IN_PROG, &f), test_bit(SDF_REMOTE_WITHDRAW, &f), test_bit(SDF_WITHDRAW_RECOVERY, &f), + test_bit(SDF_DEACTIVATING, &f), sdp->sd_log_error, rwsem_is_locked(&sdp->sd_log_flush_lock), sdp->sd_log_num_revoke, @@ -767,10 +769,10 @@ void gfs2_sys_fs_del(struct gfs2_sbd *sdp) wait_for_completion(&sdp->sd_kobj_unregister); } -static int gfs2_uevent(struct kobject *kobj, struct kobj_uevent_env *env) +static int gfs2_uevent(const struct kobject *kobj, struct kobj_uevent_env *env) { - struct gfs2_sbd *sdp = container_of(kobj, struct gfs2_sbd, sd_kobj); - struct super_block *s = sdp->sd_vfs; + const struct gfs2_sbd *sdp = container_of(kobj, struct gfs2_sbd, sd_kobj); + const struct super_block *s = sdp->sd_vfs; add_uevent_var(env, "LOCKTABLE=%s", sdp->sd_table_name); add_uevent_var(env, "LOCKPROTO=%s", sdp->sd_proto_name); diff --git a/fs/gfs2/xattr.c b/fs/gfs2/xattr.c index 518c0677e12a..adf6d17cf033 100644 --- a/fs/gfs2/xattr.c +++ b/fs/gfs2/xattr.c @@ -1225,7 +1225,7 @@ int __gfs2_xattr_set(struct inode *inode, const char *name, } static int gfs2_xattr_set(const struct xattr_handler *handler, - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, struct dentry *unused, struct inode *inode, const char *name, const void *value, size_t size, int flags) |