From b72f78cb63fb595af63fc781dced0a6fd354e572 Mon Sep 17 00:00:00 2001 From: Eric Sandeen Date: Thu, 8 Nov 2012 10:33:36 -0500 Subject: ext4: fix overhead calculations in ext4_stats, again "overhead" was a write-only variable in this function after commit 952fc18e; we set it to 0 for minixdf, or to sbi->s_overhead if !minixdf, but never read it again after that. We need to use it, not sbi->s_overhead, when subtracting out overhead for f_blocks, or we get the wrong answer for minixdf. Signed-off-by: Eric Sandeen Signed-off-by: "Theodore Ts'o" --- fs/ext4/super.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 80928f716850..1982d3cd9139 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -4790,7 +4790,7 @@ static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf) buf->f_type = EXT4_SUPER_MAGIC; buf->f_bsize = sb->s_blocksize; - buf->f_blocks = ext4_blocks_count(es) - EXT4_C2B(sbi, sbi->s_overhead); + buf->f_blocks = ext4_blocks_count(es) - EXT4_C2B(sbi, overhead); bfree = percpu_counter_sum_positive(&sbi->s_freeclusters_counter) - percpu_counter_sum_positive(&sbi->s_dirtyclusters_counter); /* prevent underflow in case that few free space is available */ -- cgit v1.2.2 From 6d138ced751d4e41e02c38ad55d1b3cd2913b150 Mon Sep 17 00:00:00 2001 From: Eric Sandeen Date: Thu, 8 Nov 2012 11:11:59 -0500 Subject: ext4: fix awful goto in ext4_mb_new_blocks() I think the whole function could be made prettier, but that goto really took the cake for too-clever-by-half. Signed-off-by: Eric Sandeen Signed-off-by: "Theodore Ts'o" --- fs/ext4/mballoc.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 526e55358606..27f421c8043d 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -4310,8 +4310,10 @@ ext4_fsblk_t ext4_mb_new_blocks(handle_t *handle, repeat: /* allocate space in core */ *errp = ext4_mb_regular_allocator(ac); - if (*errp) + if (*errp) { + ext4_discard_allocated_blocks(ac); goto errout; + } /* as we've just preallocated more space than * user requested orinally, we store allocated @@ -4333,10 +4335,10 @@ repeat: ac->ac_b_ex.fe_len = 0; ac->ac_status = AC_STATUS_CONTINUE; goto repeat; - } else if (*errp) - errout: + } else if (*errp) { ext4_discard_allocated_blocks(ac); - else { + goto errout; + } else { block = ext4_grp_offs_to_block(sb, &ac->ac_b_ex); ar->len = ac->ac_b_ex.fe_len; } @@ -4347,6 +4349,7 @@ repeat: *errp = -ENOSPC; } +errout: if (*errp) { ac->ac_b_ex.fe_len = 0; ar->len = 0; -- cgit v1.2.2 From 37be2f59d3149b95afaeeeff94edde2c07f165d2 Mon Sep 17 00:00:00 2001 From: Eric Sandeen Date: Thu, 8 Nov 2012 11:22:46 -0500 Subject: ext4: remove ext4_handle_release_buffer() ext4_handle_release_buffer() was intended to remove journal write access from a buffer, but it doesn't actually do anything at all other than add a BUFFER_TRACE point, but it's not reliably used for that either. Remove all the associated dead code. Signed-off-by: Eric Sandeen Signed-off-by: "Theodore Ts'o" Reviewed-by: Carlos Maiolino --- fs/ext4/ext4_jbd2.h | 7 ------- fs/ext4/resize.c | 17 +++-------------- fs/ext4/xattr.c | 1 - fs/jbd2/journal.c | 1 - fs/jbd2/transaction.c | 11 ----------- include/linux/jbd2.h | 1 - 6 files changed, 3 insertions(+), 35 deletions(-) diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h index 56d258c18303..7177f9b21cb2 100644 --- a/fs/ext4/ext4_jbd2.h +++ b/fs/ext4/ext4_jbd2.h @@ -254,13 +254,6 @@ static inline void ext4_handle_sync(handle_t *handle) handle->h_sync = 1; } -static inline void ext4_handle_release_buffer(handle_t *handle, - struct buffer_head *bh) -{ - if (ext4_handle_valid(handle)) - jbd2_journal_release_buffer(handle, bh); -} - static inline int ext4_handle_is_aborted(handle_t *handle) { if (ext4_handle_valid(handle)) diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index 47bf06a2765d..d99387b89edd 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -783,7 +783,7 @@ static int add_new_gdb(handle_t *handle, struct inode *inode, err = ext4_journal_get_write_access(handle, gdb_bh); if (unlikely(err)) - goto exit_sbh; + goto exit_dind; err = ext4_journal_get_write_access(handle, dind); if (unlikely(err)) @@ -792,7 +792,7 @@ static int add_new_gdb(handle_t *handle, struct inode *inode, /* ext4_reserve_inode_write() gets a reference on the iloc */ err = ext4_reserve_inode_write(handle, inode, &iloc); if (unlikely(err)) - goto exit_dindj; + goto exit_dind; n_group_desc = ext4_kvmalloc((gdb_num + 1) * sizeof(struct buffer_head *), @@ -846,12 +846,7 @@ static int add_new_gdb(handle_t *handle, struct inode *inode, exit_inode: ext4_kvfree(n_group_desc); - /* ext4_handle_release_buffer(handle, iloc.bh); */ brelse(iloc.bh); -exit_dindj: - /* ext4_handle_release_buffer(handle, dind); */ -exit_sbh: - /* ext4_handle_release_buffer(handle, EXT4_SB(sb)->s_sbh); */ exit_dind: brelse(dind); exit_bh: @@ -969,14 +964,8 @@ static int reserve_backup_gdb(handle_t *handle, struct inode *inode, } for (i = 0; i < reserved_gdb; i++) { - if ((err = ext4_journal_get_write_access(handle, primary[i]))) { - /* - int j; - for (j = 0; j < i; j++) - ext4_handle_release_buffer(handle, primary[j]); - */ + if ((err = ext4_journal_get_write_access(handle, primary[i]))) goto exit_bh; - } } if ((err = ext4_reserve_inode_write(handle, inode, &iloc))) diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 2cdb98d62980..b1adda1b750d 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -794,7 +794,6 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode, int offset = (char *)s->here - bs->bh->b_data; unlock_buffer(bs->bh); - ext4_handle_release_buffer(handle, bs->bh); if (ce) { mb_cache_entry_release(ce); ce = NULL; diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 484b8d1c6cb6..dbf41f9452db 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -60,7 +60,6 @@ EXPORT_SYMBOL(jbd2_journal_get_create_access); EXPORT_SYMBOL(jbd2_journal_get_undo_access); EXPORT_SYMBOL(jbd2_journal_set_triggers); EXPORT_SYMBOL(jbd2_journal_dirty_metadata); -EXPORT_SYMBOL(jbd2_journal_release_buffer); EXPORT_SYMBOL(jbd2_journal_forget); #if 0 EXPORT_SYMBOL(journal_sync_buffer); diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index a74ba4659549..deffd945c8e2 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -1207,17 +1207,6 @@ out: return ret; } -/* - * jbd2_journal_release_buffer: undo a get_write_access without any buffer - * updates, if the update decided in the end that it didn't need access. - * - */ -void -jbd2_journal_release_buffer(handle_t *handle, struct buffer_head *bh) -{ - BUFFER_TRACE(bh, "entry"); -} - /** * void jbd2_journal_forget() - bforget() for potentially-journaled buffers. * @handle: transaction handle diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 3efc43f3f162..de7f55682088 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -1096,7 +1096,6 @@ extern int jbd2_journal_get_undo_access(handle_t *, struct buffer_head *); void jbd2_journal_set_triggers(struct buffer_head *, struct jbd2_buffer_trigger_type *type); extern int jbd2_journal_dirty_metadata (handle_t *, struct buffer_head *); -extern void jbd2_journal_release_buffer (handle_t *, struct buffer_head *); extern int jbd2_journal_forget (handle_t *, struct buffer_head *); extern void journal_sync_buffer (struct buffer_head *); extern void jbd2_journal_invalidatepage(journal_t *, -- cgit v1.2.2 From fd47d3e1c2949838e858379aaf2bc20647be2912 Mon Sep 17 00:00:00 2001 From: Behan Webster Date: Thu, 8 Nov 2012 11:24:46 -0500 Subject: jbd2: remove VLAIS usage from JBD2 code The use of variable length arrays in structs (VLAIS) in the Linux Kernel code precludes the use of compilers which don't implement VLAIS (for instance the Clang compiler). Since ctx is always a 32-bit CRC, hard coding a size of 4 bytes accomplishes the same thing without the use of VLAIS. This is the same technique already employed in fs/ext4/ext4.h Signed-off-by: Mark Charlebois Signed-off-by: Behan Webster Signed-off-by: "Theodore Ts'o" --- include/linux/jbd2.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index de7f55682088..1be23d9fdacb 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -1302,15 +1302,21 @@ static inline int jbd_space_needed(journal_t *journal) extern int jbd_blocks_per_page(struct inode *inode); +/* JBD uses a CRC32 checksum */ +#define JBD_MAX_CHECKSUM_SIZE 4 + static inline u32 jbd2_chksum(journal_t *journal, u32 crc, const void *address, unsigned int length) { struct { struct shash_desc shash; - char ctx[crypto_shash_descsize(journal->j_chksum_driver)]; + char ctx[JBD_MAX_CHECKSUM_SIZE]; } desc; int err; + BUG_ON(crypto_shash_descsize(journal->j_chksum_driver) > + JBD_MAX_CHECKSUM_SIZE); + desc.shash.tfm = journal->j_chksum_driver; desc.shash.flags = 0; *(u32 *)desc.ctx = crc; -- cgit v1.2.2 From d339450ccad1acb942fc880ca0b44c956e6d2762 Mon Sep 17 00:00:00 2001 From: Zhao Hongjiang Date: Thu, 8 Nov 2012 12:07:33 -0500 Subject: ext4: get rid of redundant code in ext4_fill_super() Signed-off-by: Zhao Hongjiang Signed-off-by: "Theodore Ts'o" --- fs/ext4/super.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 1982d3cd9139..ea21231633eb 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -3272,9 +3272,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) } sb->s_fs_info = sbi; sbi->s_sb = sb; - sbi->s_mount_opt = 0; - sbi->s_resuid = make_kuid(&init_user_ns, EXT4_DEF_RESUID); - sbi->s_resgid = make_kgid(&init_user_ns, EXT4_DEF_RESGID); sbi->s_inode_readahead_blks = EXT4_DEF_INODE_READAHEAD_BLKS; sbi->s_sb_block = sb_block; if (sb->s_bdev->bd_part) -- cgit v1.2.2 From d8ec0c396083ef633a065629df1565246dbb2f33 Mon Sep 17 00:00:00 2001 From: Alan Cox Date: Thu, 8 Nov 2012 12:19:58 -0500 Subject: ext4: remove unused assignment Signed-off-by: Alan Cox Signed-off-by: "Theodore Ts'o" --- fs/ext4/mballoc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 27f421c8043d..442caae80a98 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -1373,7 +1373,7 @@ static int mb_find_extent(struct ext4_buddy *e4b, int block, ex->fe_start += next; while (needed > ex->fe_len && - (buddy = mb_find_buddy(e4b, order, &max))) { + mb_find_buddy(e4b, order, &max)) { if (block + 1 >= max) break; -- cgit v1.2.2 From 79add3a3f795e688e35d5e703d5a8cfa8ef923ac Mon Sep 17 00:00:00 2001 From: Lukas Czerner Date: Thu, 8 Nov 2012 13:28:29 -0500 Subject: ext4: notify when discard is not supported Notify user when mounting the file system with -o discard option, but the device does not support discard. Obviously we do not want to fail the mount or disable the options, because the underlying device might change in future even without file system remount. Reviewed-by: Carlos Maiolino Signed-off-by: Lukas Czerner Signed-off-by: "Theodore Ts'o" --- fs/ext4/super.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index ea21231633eb..6729470ee1a4 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -4015,6 +4015,14 @@ no_journal: } #endif /* CONFIG_QUOTA */ + if (test_opt(sb, DISCARD)) { + struct request_queue *q = bdev_get_queue(sb->s_bdev); + if (!blk_queue_discard(q)) + ext4_msg(sb, KERN_WARNING, + "mounting with \"discard\" option, but " + "the device does not support discard"); + } + ext4_msg(sb, KERN_INFO, "mounted filesystem with%s. " "Opts: %s%s%s", descr, sbi->s_es->s_mount_opts, *sbi->s_es->s_mount_opts ? "; " : "", orig_data); -- cgit v1.2.2 From d71c1ae23aa3e7822715c63dc242de6d73002541 Mon Sep 17 00:00:00 2001 From: Lukas Czerner Date: Thu, 8 Nov 2012 14:04:52 -0500 Subject: ext4: warn when discard request fails other than EOPNOTSUPP We should warn user then the discard request fails. However we need to exclude -EOPNOTSUPP case since parts of the device might not support it while other parts can. So print the kernel warning when the error != -EOPNOTSUPP is returned from ext4_issue_discard(). We should also handle error cases in batched discard, again excluding EOPNOTSUPP. Reviewed-by: Carlos Maiolino Signed-off-by: Lukas Czerner Signed-off-by: "Theodore Ts'o" --- fs/ext4/mballoc.c | 47 +++++++++++++++++++++++++++++++++++------------ 1 file changed, 35 insertions(+), 12 deletions(-) diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 442caae80a98..1bf6fe785c4f 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -2607,9 +2607,17 @@ static void ext4_free_data_callback(struct super_block *sb, mb_debug(1, "gonna free %u blocks in group %u (0x%p):", entry->efd_count, entry->efd_group, entry); - if (test_opt(sb, DISCARD)) - ext4_issue_discard(sb, entry->efd_group, - entry->efd_start_cluster, entry->efd_count); + if (test_opt(sb, DISCARD)) { + err = ext4_issue_discard(sb, entry->efd_group, + entry->efd_start_cluster, + entry->efd_count); + if (err && err != -EOPNOTSUPP) + ext4_msg(sb, KERN_WARNING, "discard request in" + " group:%d block:%d count:%d failed" + " with %d", entry->efd_group, + entry->efd_start_cluster, + entry->efd_count, err); + } err = ext4_mb_load_buddy(sb, entry->efd_group, &e4b); /* we expect to find existing buddy because it's pinned */ @@ -4659,8 +4667,16 @@ do_more: * with group lock held. generate_buddy look at * them with group lock_held */ - if (test_opt(sb, DISCARD)) - ext4_issue_discard(sb, block_group, bit, count); + if (test_opt(sb, DISCARD)) { + err = ext4_issue_discard(sb, block_group, bit, count); + if (err && err != -EOPNOTSUPP) + ext4_msg(sb, KERN_WARNING, "discard request in" + " group:%d block:%d count:%lu failed" + " with %d", block_group, bit, count, + err); + } + + ext4_lock_group(sb, block_group); mb_clear_bits(bitmap_bh->b_data, bit, count_clusters); mb_free_blocks(inode, &e4b, bit, count_clusters); @@ -4854,10 +4870,11 @@ error_return: * one will allocate those blocks, mark it as used in buddy bitmap. This must * be called with under the group lock. */ -static void ext4_trim_extent(struct super_block *sb, int start, int count, +static int ext4_trim_extent(struct super_block *sb, int start, int count, ext4_group_t group, struct ext4_buddy *e4b) { struct ext4_free_extent ex; + int ret = 0; trace_ext4_trim_extent(sb, group, start, count); @@ -4873,9 +4890,10 @@ static void ext4_trim_extent(struct super_block *sb, int start, int count, */ mb_mark_used(e4b, &ex); ext4_unlock_group(sb, group); - ext4_issue_discard(sb, group, start, count); + ret = ext4_issue_discard(sb, group, start, count); ext4_lock_group(sb, group); mb_free_blocks(NULL, e4b, start, ex.fe_len); + return ret; } /** @@ -4904,7 +4922,7 @@ ext4_trim_all_free(struct super_block *sb, ext4_group_t group, void *bitmap; ext4_grpblk_t next, count = 0, free_count = 0; struct ext4_buddy e4b; - int ret; + int ret = 0; trace_ext4_trim_all_free(sb, group, start, max); @@ -4931,8 +4949,11 @@ ext4_trim_all_free(struct super_block *sb, ext4_group_t group, next = mb_find_next_bit(bitmap, max + 1, start); if ((next - start) >= minblocks) { - ext4_trim_extent(sb, start, - next - start, group, &e4b); + ret = ext4_trim_extent(sb, start, + next - start, group, &e4b); + if (ret && ret != -EOPNOTSUPP) + break; + ret = 0; count += next - start; } free_count += next - start; @@ -4953,8 +4974,10 @@ ext4_trim_all_free(struct super_block *sb, ext4_group_t group, break; } - if (!ret) + if (!ret) { + ret = count; EXT4_MB_GRP_SET_TRIMMED(e4b.bd_info); + } out: ext4_unlock_group(sb, group); ext4_mb_unload_buddy(&e4b); @@ -4962,7 +4985,7 @@ out: ext4_debug("trimmed %d blocks in the group %d\n", count, group); - return count; + return ret; } /** -- cgit v1.2.2 From b5645534ce84c21695c2f82d4d4f67cf2a67229a Mon Sep 17 00:00:00 2001 From: Zheng Liu Date: Thu, 8 Nov 2012 14:33:43 -0500 Subject: ext4: print 'flags' in ext4_ext_handle_uninitialized_extents In trace_ext4_ext_handle_uninitialized_extents we don't care about the value of map->m_flags because this value is probably 0, and we prefer to get the value of flags because we can know how to handle this extent in this function. Reviewed-by: Lukas Czerner Signed-off-by: Zheng Liu Signed-off-by: "Theodore Ts'o" --- fs/ext4/extents.c | 4 ++-- include/trace/events/ext4.h | 8 ++++---- 2 files changed, 6 insertions(+), 6 deletions(-) diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 7011ac967208..59e6e12e0029 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -3663,8 +3663,8 @@ ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode, flags, allocated); ext4_ext_show_leaf(inode, path); - trace_ext4_ext_handle_uninitialized_extents(inode, map, allocated, - newblock); + trace_ext4_ext_handle_uninitialized_extents(inode, map, flags, + allocated, newblock); /* get_block() before submit the IO, split the extent */ if ((flags & EXT4_GET_BLOCKS_PRE_IO)) { diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h index d49b285385e8..25914e3002c7 100644 --- a/include/trace/events/ext4.h +++ b/include/trace/events/ext4.h @@ -1680,10 +1680,10 @@ DEFINE_EVENT(ext4__trim, ext4_trim_all_free, ); TRACE_EVENT(ext4_ext_handle_uninitialized_extents, - TP_PROTO(struct inode *inode, struct ext4_map_blocks *map, + TP_PROTO(struct inode *inode, struct ext4_map_blocks *map, int flags, unsigned int allocated, ext4_fsblk_t newblock), - TP_ARGS(inode, map, allocated, newblock), + TP_ARGS(inode, map, flags, allocated, newblock), TP_STRUCT__entry( __field( dev_t, dev ) @@ -1699,7 +1699,7 @@ TRACE_EVENT(ext4_ext_handle_uninitialized_extents, TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; - __entry->flags = map->m_flags; + __entry->flags = flags; __entry->lblk = map->m_lblk; __entry->pblk = map->m_pblk; __entry->len = map->m_len; @@ -1707,7 +1707,7 @@ TRACE_EVENT(ext4_ext_handle_uninitialized_extents, __entry->newblk = newblock; ), - TP_printk("dev %d,%d ino %lu m_lblk %u m_pblk %llu m_len %u flags %d" + TP_printk("dev %d,%d ino %lu m_lblk %u m_pblk %llu m_len %u flags %x " "allocated %d newblock %llu", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, -- cgit v1.2.2 From 19b303d8b5a0e8150a4697c01ca03e75a0a17469 Mon Sep 17 00:00:00 2001 From: Zheng Liu Date: Thu, 8 Nov 2012 14:34:04 -0500 Subject: ext4: print map->m_flags in trace_ext4_ext/ind_map_blocks_exit When we use trace_ext4_ext/ind_map_blocks_exit, print the value of map->m_flags in order that we can understand the extent's current status. Reviewed-by: Lukas Czerner Signed-off-by: Zheng Liu Signed-off-by: "Theodore Ts'o" --- fs/ext4/extents.c | 3 +-- fs/ext4/indirect.c | 3 +-- include/trace/events/ext4.h | 27 +++++++++++++-------------- 3 files changed, 15 insertions(+), 18 deletions(-) diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 59e6e12e0029..7a64c193b2af 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -4284,8 +4284,7 @@ out2: kfree(path); } - trace_ext4_ext_map_blocks_exit(inode, map->m_lblk, - newblock, map->m_len, err ? err : allocated); + trace_ext4_ext_map_blocks_exit(inode, map, err ? err : allocated); return err ? err : allocated; } diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c index 792e388e7b44..292337f27c9c 100644 --- a/fs/ext4/indirect.c +++ b/fs/ext4/indirect.c @@ -755,8 +755,7 @@ cleanup: partial--; } out: - trace_ext4_ind_map_blocks_exit(inode, map->m_lblk, - map->m_pblk, map->m_len, err); + trace_ext4_ind_map_blocks_exit(inode, map, err); return err; } diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h index 25914e3002c7..d2a125a6db8b 100644 --- a/include/trace/events/ext4.h +++ b/include/trace/events/ext4.h @@ -1519,10 +1519,9 @@ DEFINE_EVENT(ext4__map_blocks_enter, ext4_ind_map_blocks_enter, ); DECLARE_EVENT_CLASS(ext4__map_blocks_exit, - TP_PROTO(struct inode *inode, ext4_lblk_t lblk, - ext4_fsblk_t pblk, unsigned int len, int ret), + TP_PROTO(struct inode *inode, struct ext4_map_blocks *map, int ret), - TP_ARGS(inode, lblk, pblk, len, ret), + TP_ARGS(inode, map, ret), TP_STRUCT__entry( __field( dev_t, dev ) @@ -1530,37 +1529,37 @@ DECLARE_EVENT_CLASS(ext4__map_blocks_exit, __field( ext4_fsblk_t, pblk ) __field( ext4_lblk_t, lblk ) __field( unsigned int, len ) + __field( unsigned int, flags ) __field( int, ret ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; - __entry->pblk = pblk; - __entry->lblk = lblk; - __entry->len = len; + __entry->pblk = map->m_pblk; + __entry->lblk = map->m_lblk; + __entry->len = map->m_len; + __entry->flags = map->m_flags; __entry->ret = ret; ), - TP_printk("dev %d,%d ino %lu lblk %u pblk %llu len %u ret %d", + TP_printk("dev %d,%d ino %lu lblk %u pblk %llu len %u flags %x ret %d", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->lblk, __entry->pblk, - __entry->len, __entry->ret) + __entry->len, __entry->flags, __entry->ret) ); DEFINE_EVENT(ext4__map_blocks_exit, ext4_ext_map_blocks_exit, - TP_PROTO(struct inode *inode, ext4_lblk_t lblk, - ext4_fsblk_t pblk, unsigned len, int ret), + TP_PROTO(struct inode *inode, struct ext4_map_blocks *map, int ret), - TP_ARGS(inode, lblk, pblk, len, ret) + TP_ARGS(inode, map, ret) ); DEFINE_EVENT(ext4__map_blocks_exit, ext4_ind_map_blocks_exit, - TP_PROTO(struct inode *inode, ext4_lblk_t lblk, - ext4_fsblk_t pblk, unsigned len, int ret), + TP_PROTO(struct inode *inode, struct ext4_map_blocks *map, int ret), - TP_ARGS(inode, lblk, pblk, len, ret) + TP_ARGS(inode, map, ret) ); TRACE_EVENT(ext4_ext_load_extent, -- cgit v1.2.2 From 37794732467dd998a34bfce19738ad3ef1f37507 Mon Sep 17 00:00:00 2001 From: Zheng Liu Date: Thu, 8 Nov 2012 14:47:52 -0500 Subject: ext4: fix missing call to trace_ext4_ext_map_blocks_exit When ext4_ext_handle_uninitialized_extents(), we will directly return from ext4_ext_map_blocks(). The trace point of trace_ext4_ext_map_blocks_exit isn't called, and the user doesn't see any result. This patch tries to fix this problem. Meanwhile in ext4_ext_handle_uninitialized_extents it returns errors or the number of allocated blocks. So 'ret' variable can be removed due to previously modifications. Signed-off-by: Zheng Liu --- fs/ext4/extents.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 7a64c193b2af..dce97de6a409 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -3911,7 +3911,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, struct ext4_extent newex, *ex, *ex2; struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); ext4_fsblk_t newblock = 0; - int free_on_err = 0, err = 0, depth, ret; + int free_on_err = 0, err = 0, depth; unsigned int allocated = 0, offset = 0; unsigned int allocated_clusters = 0; struct ext4_allocation_request ar; @@ -4007,10 +4007,10 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, ee_len, ee_start); goto out; } - ret = ext4_ext_handle_uninitialized_extents( + allocated = ext4_ext_handle_uninitialized_extents( handle, inode, map, path, flags, allocated, newblock); - return ret; + goto out3; } } @@ -4284,6 +4284,7 @@ out2: kfree(path); } +out3: trace_ext4_ext_map_blocks_exit(inode, map, err ? err : allocated); return err ? err : allocated; -- cgit v1.2.2 From 8d8c1825709020c73b5e66f96c114f6a1f6461e7 Mon Sep 17 00:00:00 2001 From: Anatol Pomozov Date: Thu, 8 Nov 2012 14:53:35 -0500 Subject: ext4: use 'inode' variable that is already dereferenced Tested: xfs tests Reviewed-by: Zheng Liu Signed-off-by: Anatol Pomozov Signed-off-by: "Theodore Ts'o" --- fs/ext4/page-io.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c index 68e896e12a67..0fd16e653ebd 100644 --- a/fs/ext4/page-io.c +++ b/fs/ext4/page-io.c @@ -111,7 +111,7 @@ static int ext4_end_io(ext4_io_end_t *io) inode_dio_done(inode); /* Wake up anyone waiting on unwritten extent conversion */ if (atomic_dec_and_test(&EXT4_I(inode)->i_unwritten)) - wake_up_all(ext4_ioend_wq(io->inode)); + wake_up_all(ext4_ioend_wq(inode)); return ret; } -- cgit v1.2.2 From 8b0f165f790c897fa744e7fed6f0bfeb6eb6f494 Mon Sep 17 00:00:00 2001 From: Anatol Pomozov Date: Thu, 8 Nov 2012 15:07:16 -0500 Subject: ext4: remove code duplication in ext4_get_block_write_nolock() 729f52c6be51013 introduced function ext4_get_block_write_nolock() that is very similar to _ext4_get_block(). Eliminate code duplication by passing different flags to _ext4_get_block() Tested: xfs tests Reviewed-by: Zheng Liu Signed-off-by: Anatol Pomozov Signed-off-by: "Theodore Ts'o" --- fs/ext4/inode.c | 63 ++++++++++++++++++++++----------------------------------- 1 file changed, 24 insertions(+), 39 deletions(-) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index b3c243b9afa5..f84bfd6d1867 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -683,7 +683,7 @@ static int _ext4_get_block(struct inode *inode, sector_t iblock, map.m_lblk = iblock; map.m_len = bh->b_size >> inode->i_blkbits; - if (flags && !handle) { + if (flags && !(flags & EXT4_GET_BLOCKS_NO_LOCK) && !handle) { /* Direct IO write... */ if (map.m_len > DIO_MAX_BLOCKS) map.m_len = DIO_MAX_BLOCKS; @@ -880,6 +880,8 @@ static int do_journal_get_write_access(handle_t *handle, static int ext4_get_block_write(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create); +static int ext4_get_block_write_nolock(struct inode *inode, sector_t iblock, + struct buffer_head *bh_result, int create); static int ext4_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata) @@ -2850,29 +2852,12 @@ static int ext4_get_block_write(struct inode *inode, sector_t iblock, } static int ext4_get_block_write_nolock(struct inode *inode, sector_t iblock, - struct buffer_head *bh_result, int flags) + struct buffer_head *bh_result, int create) { - handle_t *handle = ext4_journal_current_handle(); - struct ext4_map_blocks map; - int ret = 0; - - ext4_debug("ext4_get_block_write_nolock: inode %lu, flag %d\n", - inode->i_ino, flags); - - flags = EXT4_GET_BLOCKS_NO_LOCK; - - map.m_lblk = iblock; - map.m_len = bh_result->b_size >> inode->i_blkbits; - - ret = ext4_map_blocks(handle, inode, &map, flags); - if (ret > 0) { - map_bh(bh_result, inode->i_sb, map.m_pblk); - bh_result->b_state = (bh_result->b_state & ~EXT4_MAP_FLAGS) | - map.m_flags; - bh_result->b_size = inode->i_sb->s_blocksize * map.m_len; - ret = 0; - } - return ret; + ext4_debug("ext4_get_block_write_nolock: inode %lu, create flag %d\n", + inode->i_ino, create); + return _ext4_get_block(inode, iblock, bh_result, + EXT4_GET_BLOCKS_NO_LOCK); } static void ext4_end_io_dio(struct kiocb *iocb, loff_t offset, @@ -3003,6 +2988,8 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb, loff_t final_size = offset + count; if (rw == WRITE && final_size <= inode->i_size) { int overwrite = 0; + get_block_t *get_block_func = NULL; + int dio_flags = 0; BUG_ON(iocb->private == NULL); @@ -3056,22 +3043,20 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb, ext4_inode_aio_set(inode, io_end); } - if (overwrite) - ret = __blockdev_direct_IO(rw, iocb, inode, - inode->i_sb->s_bdev, iov, - offset, nr_segs, - ext4_get_block_write_nolock, - ext4_end_io_dio, - NULL, - 0); - else - ret = __blockdev_direct_IO(rw, iocb, inode, - inode->i_sb->s_bdev, iov, - offset, nr_segs, - ext4_get_block_write, - ext4_end_io_dio, - NULL, - DIO_LOCKING); + if (overwrite) { + get_block_func = ext4_get_block_write_nolock; + } else { + get_block_func = ext4_get_block_write; + dio_flags = DIO_LOCKING; + } + ret = __blockdev_direct_IO(rw, iocb, inode, + inode->i_sb->s_bdev, iov, + offset, nr_segs, + get_block_func, + ext4_end_io_dio, + NULL, + dio_flags); + if (iocb->private) ext4_inode_aio_set(inode, NULL); /* -- cgit v1.2.2 From 24ec19b0ae83a385ad9c55520716da671274b96c Mon Sep 17 00:00:00 2001 From: Eugene Shatokhin Date: Thu, 8 Nov 2012 15:11:11 -0500 Subject: ext4: fix memory leak in ext4_xattr_set_acl()'s error path In ext4_xattr_set_acl(), if ext4_journal_start() returns an error, posix_acl_release() will not be called for 'acl' which may result in a memory leak. This patch fixes that. Reviewed-by: Lukas Czerner Signed-off-by: Eugene Shatokhin Signed-off-by: "Theodore Ts'o" Cc: stable@vger.kernel.org --- fs/ext4/acl.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/fs/ext4/acl.c b/fs/ext4/acl.c index d3c5b88fd89f..e6e0d988439b 100644 --- a/fs/ext4/acl.c +++ b/fs/ext4/acl.c @@ -423,8 +423,10 @@ ext4_xattr_set_acl(struct dentry *dentry, const char *name, const void *value, retry: handle = ext4_journal_start(inode, EXT4_DATA_TRANS_BLOCKS(inode->i_sb)); - if (IS_ERR(handle)) - return PTR_ERR(handle); + if (IS_ERR(handle)) { + error = PTR_ERR(handle); + goto release_and_out; + } error = ext4_set_acl(handle, inode, type, acl); ext4_journal_stop(handle); if (error == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)) -- cgit v1.2.2 From 07aa2ea13814ea60d12f7330b6d5ccfdb0c3ba4d Mon Sep 17 00:00:00 2001 From: Lukas Czerner Date: Thu, 8 Nov 2012 15:16:54 -0500 Subject: ext4: fix error handling in ext4_fill_super() There are some places in ext4_fill_super() where we would not return proper error code if something fails. The confusion is caused probably due to the fact that we have two "kind-of" return variables 'ret'and 'err'. 'ret' is used to return error code from ext4_fill_super() where err is used to store return values from other functions within ext4_fill_super(). However some places were missing the obligatory 'ret = err'. We could put the assignment where it is missing, but we can have better "future proof" solution. Or we could convert the code to use just one, but it would require more rewrites. This commit fixes the problem by returning value from 'err' variable if it is set and 'ret' otherwise in error handling branch of the ext4_fill_super(). The reasoning is that 'ret' value is often set to default "-EINVAL" or explicit value, where 'err' is used to store return value from other functions and should be otherwise zero. https://bugzilla.kernel.org/show_bug.cgi?id=48431 Signed-off-by: Lukas Czerner Signed-off-by: "Theodore Ts'o" --- fs/ext4/super.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 6729470ee1a4..18e89fafebd1 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -3256,7 +3256,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) unsigned int i; int needs_recovery, has_huge_files, has_bigalloc; __u64 blocks_count; - int err; + int err = 0; unsigned int journal_ioprio = DEFAULT_JOURNAL_IOPRIO; ext4_group_t first_not_zeroed; @@ -3282,6 +3282,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) for (cp = sb->s_id; (cp = strchr(cp, '/'));) *cp = '!'; + /* -EINVAL is default */ ret = -EINVAL; blocksize = sb_min_blocksize(sb, EXT4_MIN_BLOCK_SIZE); if (!blocksize) { @@ -3659,7 +3660,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) " too large to mount safely on this system"); if (sizeof(sector_t) < 8) ext4_msg(sb, KERN_WARNING, "CONFIG_LBDAF not enabled"); - ret = err; goto failed_mount; } @@ -3767,7 +3767,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) } if (err) { ext4_msg(sb, KERN_ERR, "insufficient memory"); - ret = err; goto failed_mount3; } @@ -3894,8 +3893,8 @@ no_journal: if (es->s_overhead_clusters) sbi->s_overhead = le32_to_cpu(es->s_overhead_clusters); else { - ret = ext4_calculate_overhead(sb); - if (ret) + err = ext4_calculate_overhead(sb); + if (err) goto failed_mount_wq; } @@ -3907,6 +3906,7 @@ no_journal: alloc_workqueue("ext4-dio-unwritten", WQ_MEM_RECLAIM | WQ_UNBOUND, 1); if (!EXT4_SB(sb)->dio_unwritten_wq) { printk(KERN_ERR "EXT4-fs: failed to create DIO workqueue\n"); + ret = -ENOMEM; goto failed_mount_wq; } @@ -4009,8 +4009,8 @@ no_journal: /* Enable quota usage during mount. */ if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA) && !(sb->s_flags & MS_RDONLY)) { - ret = ext4_enable_quotas(sb); - if (ret) + err = ext4_enable_quotas(sb); + if (err) goto failed_mount7; } #endif /* CONFIG_QUOTA */ @@ -4089,7 +4089,7 @@ out_fail: kfree(sbi); out_free_orig: kfree(orig_data); - return ret; + return err ? err : ret; } /* -- cgit v1.2.2 From c0677e6d0f9d991adff972b8d06cb83de1f8ee8e Mon Sep 17 00:00:00 2001 From: Zheng Liu Date: Thu, 8 Nov 2012 15:18:54 -0500 Subject: ext4: add data structures for the extent status tree This patch adds two structures that supports extent status tree, extent_status and ext4_es_tree. Currently extent_status is used to track a delay extent for an inode, which record the start block and the length of the delay extent. ext4_es_tree is used to store all extent_status for an inode in memory. Signed-off-by: Yongqiang Yang Signed-off-by: Allison Henderson Signed-off-by: Zheng Liu Signed-off-by: "Theodore Ts'o" --- fs/ext4/ext4.h | 6 ++++++ fs/ext4/extents_status.h | 25 +++++++++++++++++++++++++ 2 files changed, 31 insertions(+) create mode 100644 fs/ext4/extents_status.h diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 3c20de1d59d0..bcc634b26d46 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -811,6 +811,8 @@ struct ext4_ext_cache { __u32 ec_len; /* must be 32bit to return holes */ }; +#include "extents_status.h" + /* * fourth extended file system inode data in memory */ @@ -888,6 +890,10 @@ struct ext4_inode_info { struct list_head i_prealloc_list; spinlock_t i_prealloc_lock; + /* extents status tree */ + struct ext4_es_tree i_es_tree; + rwlock_t i_es_lock; + /* ialloc */ ext4_group_t i_last_alloc_group; diff --git a/fs/ext4/extents_status.h b/fs/ext4/extents_status.h new file mode 100644 index 000000000000..8be2ab9c9425 --- /dev/null +++ b/fs/ext4/extents_status.h @@ -0,0 +1,25 @@ +/* + * fs/ext4/extents_status.h + * + * Written by Yongqiang Yang + * Modified by + * Allison Henderson + * Zheng Liu + * + */ + +#ifndef _EXT4_EXTENTS_STATUS_H +#define _EXT4_EXTENTS_STATUS_H + +struct extent_status { + struct rb_node rb_node; + ext4_lblk_t start; /* first block extent covers */ + ext4_lblk_t len; /* length of extent in block */ +}; + +struct ext4_es_tree { + struct rb_root root; + struct extent_status *cache_es; /* recently accessed extent */ +}; + +#endif /* _EXT4_EXTENTS_STATUS_H */ -- cgit v1.2.2 From 654598bef3731c9ae9b068ac35e6b69674c02841 Mon Sep 17 00:00:00 2001 From: Zheng Liu Date: Thu, 8 Nov 2012 21:57:20 -0500 Subject: ext4: add operations on extent status tree This patch adds operations on a extent status tree. CC: Lukas Czerner Signed-off-by: Yongqiang Yang Signed-off-by: Allison Henderson Signed-off-by: Hugh Dickins Signed-off-by: Zheng Liu Signed-off-by: "Theodore Ts'o" --- fs/ext4/Makefile | 2 +- fs/ext4/extents_status.c | 492 +++++++++++++++++++++++++++++++++++++++++++++++ fs/ext4/extents_status.h | 20 ++ 3 files changed, 513 insertions(+), 1 deletion(-) create mode 100644 fs/ext4/extents_status.c diff --git a/fs/ext4/Makefile b/fs/ext4/Makefile index 56fd8f865930..41f22be2ffa4 100644 --- a/fs/ext4/Makefile +++ b/fs/ext4/Makefile @@ -7,7 +7,7 @@ obj-$(CONFIG_EXT4_FS) += ext4.o ext4-y := balloc.o bitmap.o dir.o file.o fsync.o ialloc.o inode.o page-io.o \ ioctl.o namei.o super.o symlink.o hash.o resize.o extents.o \ ext4_jbd2.o migrate.o mballoc.o block_validity.o move_extent.o \ - mmp.o indirect.o + mmp.o indirect.o extents_status.o ext4-$(CONFIG_EXT4_FS_XATTR) += xattr.o xattr_user.o xattr_trusted.o ext4-$(CONFIG_EXT4_FS_POSIX_ACL) += acl.o diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c new file mode 100644 index 000000000000..02c09be3d773 --- /dev/null +++ b/fs/ext4/extents_status.c @@ -0,0 +1,492 @@ +/* + * fs/ext4/extents_status.c + * + * Written by Yongqiang Yang + * Modified by + * Allison Henderson + * Hugh Dickins + * Zheng Liu + * + * Ext4 extents status tree core functions. + */ +#include +#include "ext4.h" +#include "extents_status.h" +#include "ext4_extents.h" + +/* + * According to previous discussion in Ext4 Developer Workshop, we + * will introduce a new structure called io tree to track all extent + * status in order to solve some problems that we have met + * (e.g. Reservation space warning), and provide extent-level locking. + * Delay extent tree is the first step to achieve this goal. It is + * original built by Yongqiang Yang. At that time it is called delay + * extent tree, whose goal is only track delay extent in memory to + * simplify the implementation of fiemap and bigalloc, and introduce + * lseek SEEK_DATA/SEEK_HOLE support. That is why it is still called + * delay extent tree at the following comment. But for better + * understand what it does, it has been rename to extent status tree. + * + * Currently the first step has been done. All delay extents are + * tracked in the tree. It maintains the delay extent when a delay + * allocation is issued, and the delay extent is written out or + * invalidated. Therefore the implementation of fiemap and bigalloc + * are simplified, and SEEK_DATA/SEEK_HOLE are introduced. + * + * The following comment describes the implemenmtation of extent + * status tree and future works. + */ + +/* + * extents status tree implementation for ext4. + * + * + * ========================================================================== + * Extents status encompass delayed extents and extent locks + * + * 1. Why delayed extent implementation ? + * + * Without delayed extent, ext4 identifies a delayed extent by looking + * up page cache, this has several deficiencies - complicated, buggy, + * and inefficient code. + * + * FIEMAP, SEEK_HOLE/DATA, bigalloc, punch hole and writeout all need + * to know if a block or a range of blocks are belonged to a delayed + * extent. + * + * Let us have a look at how they do without delayed extents implementation. + * -- FIEMAP + * FIEMAP looks up page cache to identify delayed allocations from holes. + * + * -- SEEK_HOLE/DATA + * SEEK_HOLE/DATA has the same problem as FIEMAP. + * + * -- bigalloc + * bigalloc looks up page cache to figure out if a block is + * already under delayed allocation or not to determine whether + * quota reserving is needed for the cluster. + * + * -- punch hole + * punch hole looks up page cache to identify a delayed extent. + * + * -- writeout + * Writeout looks up whole page cache to see if a buffer is + * mapped, If there are not very many delayed buffers, then it is + * time comsuming. + * + * With delayed extents implementation, FIEMAP, SEEK_HOLE/DATA, + * bigalloc and writeout can figure out if a block or a range of + * blocks is under delayed allocation(belonged to a delayed extent) or + * not by searching the delayed extent tree. + * + * + * ========================================================================== + * 2. ext4 delayed extents impelmentation + * + * -- delayed extent + * A delayed extent is a range of blocks which are contiguous + * logically and under delayed allocation. Unlike extent in + * ext4, delayed extent in ext4 is a in-memory struct, there is + * no corresponding on-disk data. There is no limit on length of + * delayed extent, so a delayed extent can contain as many blocks + * as they are contiguous logically. + * + * -- delayed extent tree + * Every inode has a delayed extent tree and all under delayed + * allocation blocks are added to the tree as delayed extents. + * Delayed extents in the tree are ordered by logical block no. + * + * -- operations on a delayed extent tree + * There are three operations on a delayed extent tree: find next + * delayed extent, adding a space(a range of blocks) and removing + * a space. + * + * -- race on a delayed extent tree + * Delayed extent tree is protected inode->i_es_lock. + * + * + * ========================================================================== + * 3. performance analysis + * -- overhead + * 1. There is a cache extent for write access, so if writes are + * not very random, adding space operaions are in O(1) time. + * + * -- gain + * 2. Code is much simpler, more readable, more maintainable and + * more efficient. + * + * + * ========================================================================== + * 4. TODO list + * -- Track all extent status + * + * -- Improve get block process + * + * -- Extent-level locking + */ + +static struct kmem_cache *ext4_es_cachep; + +int __init ext4_init_es(void) +{ + ext4_es_cachep = KMEM_CACHE(extent_status, SLAB_RECLAIM_ACCOUNT); + if (ext4_es_cachep == NULL) + return -ENOMEM; + return 0; +} + +void ext4_exit_es(void) +{ + if (ext4_es_cachep) + kmem_cache_destroy(ext4_es_cachep); +} + +void ext4_es_init_tree(struct ext4_es_tree *tree) +{ + tree->root = RB_ROOT; + tree->cache_es = NULL; +} + +#ifdef ES_DEBUG__ +static void ext4_es_print_tree(struct inode *inode) +{ + struct ext4_es_tree *tree; + struct rb_node *node; + + printk(KERN_DEBUG "status extents for inode %lu:", inode->i_ino); + tree = &EXT4_I(inode)->i_es_tree; + node = rb_first(&tree->root); + while (node) { + struct extent_status *es; + es = rb_entry(node, struct extent_status, rb_node); + printk(KERN_DEBUG " [%u/%u)", es->start, es->len); + node = rb_next(node); + } + printk(KERN_DEBUG "\n"); +} +#else +#define ext4_es_print_tree(inode) +#endif + +static inline ext4_lblk_t extent_status_end(struct extent_status *es) +{ + BUG_ON(es->start + es->len < es->start); + return es->start + es->len - 1; +} + +/* + * search through the tree for an delayed extent with a given offset. If + * it can't be found, try to find next extent. + */ +static struct extent_status *__es_tree_search(struct rb_root *root, + ext4_lblk_t offset) +{ + struct rb_node *node = root->rb_node; + struct extent_status *es = NULL; + + while (node) { + es = rb_entry(node, struct extent_status, rb_node); + if (offset < es->start) + node = node->rb_left; + else if (offset > extent_status_end(es)) + node = node->rb_right; + else + return es; + } + + if (es && offset < es->start) + return es; + + if (es && offset > extent_status_end(es)) { + node = rb_next(&es->rb_node); + return node ? rb_entry(node, struct extent_status, rb_node) : + NULL; + } + + return NULL; +} + +/* + * ext4_es_find_extent: find the 1st delayed extent covering @es->start + * if it exists, otherwise, the next extent after @es->start. + * + * @inode: the inode which owns delayed extents + * @es: delayed extent that we found + * + * Returns the first block of the next extent after es, otherwise + * EXT_MAX_BLOCKS if no delay extent is found. + * Delayed extent is returned via @es. + */ +ext4_lblk_t ext4_es_find_extent(struct inode *inode, struct extent_status *es) +{ + struct ext4_es_tree *tree = NULL; + struct extent_status *es1 = NULL; + struct rb_node *node; + ext4_lblk_t ret = EXT_MAX_BLOCKS; + + read_lock(&EXT4_I(inode)->i_es_lock); + tree = &EXT4_I(inode)->i_es_tree; + + /* find delay extent in cache firstly */ + if (tree->cache_es) { + es1 = tree->cache_es; + if (in_range(es->start, es1->start, es1->len)) { + es_debug("%u cached by [%u/%u)\n", + es->start, es1->start, es1->len); + goto out; + } + } + + es->len = 0; + es1 = __es_tree_search(&tree->root, es->start); + +out: + if (es1) { + tree->cache_es = es1; + es->start = es1->start; + es->len = es1->len; + node = rb_next(&es1->rb_node); + if (node) { + es1 = rb_entry(node, struct extent_status, rb_node); + ret = es1->start; + } + } + + read_unlock(&EXT4_I(inode)->i_es_lock); + return ret; +} + +static struct extent_status * +ext4_es_alloc_extent(ext4_lblk_t start, ext4_lblk_t len) +{ + struct extent_status *es; + es = kmem_cache_alloc(ext4_es_cachep, GFP_ATOMIC); + if (es == NULL) + return NULL; + es->start = start; + es->len = len; + return es; +} + +static void ext4_es_free_extent(struct extent_status *es) +{ + kmem_cache_free(ext4_es_cachep, es); +} + +static struct extent_status * +ext4_es_try_to_merge_left(struct ext4_es_tree *tree, struct extent_status *es) +{ + struct extent_status *es1; + struct rb_node *node; + + node = rb_prev(&es->rb_node); + if (!node) + return es; + + es1 = rb_entry(node, struct extent_status, rb_node); + if (es->start == extent_status_end(es1) + 1) { + es1->len += es->len; + rb_erase(&es->rb_node, &tree->root); + ext4_es_free_extent(es); + es = es1; + } + + return es; +} + +static struct extent_status * +ext4_es_try_to_merge_right(struct ext4_es_tree *tree, struct extent_status *es) +{ + struct extent_status *es1; + struct rb_node *node; + + node = rb_next(&es->rb_node); + if (!node) + return es; + + es1 = rb_entry(node, struct extent_status, rb_node); + if (es1->start == extent_status_end(es) + 1) { + es->len += es1->len; + rb_erase(node, &tree->root); + ext4_es_free_extent(es1); + } + + return es; +} + +static int __es_insert_extent(struct ext4_es_tree *tree, ext4_lblk_t offset, + ext4_lblk_t len) +{ + struct rb_node **p = &tree->root.rb_node; + struct rb_node *parent = NULL; + struct extent_status *es; + ext4_lblk_t end = offset + len - 1; + + BUG_ON(end < offset); + es = tree->cache_es; + if (es && offset == (extent_status_end(es) + 1)) { + es_debug("cached by [%u/%u)\n", es->start, es->len); + es->len += len; + es = ext4_es_try_to_merge_right(tree, es); + goto out; + } else if (es && es->start == end + 1) { + es_debug("cached by [%u/%u)\n", es->start, es->len); + es->start = offset; + es->len += len; + es = ext4_es_try_to_merge_left(tree, es); + goto out; + } else if (es && es->start <= offset && + end <= extent_status_end(es)) { + es_debug("cached by [%u/%u)\n", es->start, es->len); + goto out; + } + + while (*p) { + parent = *p; + es = rb_entry(parent, struct extent_status, rb_node); + + if (offset < es->start) { + if (es->start == end + 1) { + es->start = offset; + es->len += len; + es = ext4_es_try_to_merge_left(tree, es); + goto out; + } + p = &(*p)->rb_left; + } else if (offset > extent_status_end(es)) { + if (offset == extent_status_end(es) + 1) { + es->len += len; + es = ext4_es_try_to_merge_right(tree, es); + goto out; + } + p = &(*p)->rb_right; + } else { + if (extent_status_end(es) <= end) + es->len = offset - es->start + len; + goto out; + } + } + + es = ext4_es_alloc_extent(offset, len); + if (!es) + return -ENOMEM; + rb_link_node(&es->rb_node, parent, p); + rb_insert_color(&es->rb_node, &tree->root); + +out: + tree->cache_es = es; + return 0; +} + +/* + * ext4_es_insert_extent() adds a space to a delayed extent tree. + * Caller holds inode->i_es_lock. + * + * ext4_es_insert_extent is called by ext4_da_write_begin and + * ext4_es_remove_extent. + * + * Return 0 on success, error code on failure. + */ +int ext4_es_insert_extent(struct inode *inode, ext4_lblk_t offset, + ext4_lblk_t len) +{ + struct ext4_es_tree *tree; + int err = 0; + + es_debug("add [%u/%u) to extent status tree of inode %lu\n", + offset, len, inode->i_ino); + + write_lock(&EXT4_I(inode)->i_es_lock); + tree = &EXT4_I(inode)->i_es_tree; + err = __es_insert_extent(tree, offset, len); + write_unlock(&EXT4_I(inode)->i_es_lock); + + ext4_es_print_tree(inode); + + return err; +} + +/* + * ext4_es_remove_extent() removes a space from a delayed extent tree. + * Caller holds inode->i_es_lock. + * + * Return 0 on success, error code on failure. + */ +int ext4_es_remove_extent(struct inode *inode, ext4_lblk_t offset, + ext4_lblk_t len) +{ + struct rb_node *node; + struct ext4_es_tree *tree; + struct extent_status *es; + struct extent_status orig_es; + ext4_lblk_t len1, len2, end; + int err = 0; + + es_debug("remove [%u/%u) from extent status tree of inode %lu\n", + offset, len, inode->i_ino); + + end = offset + len - 1; + BUG_ON(end < offset); + write_lock(&EXT4_I(inode)->i_es_lock); + tree = &EXT4_I(inode)->i_es_tree; + es = __es_tree_search(&tree->root, offset); + if (!es) + goto out; + if (es->start > end) + goto out; + + /* Simply invalidate cache_es. */ + tree->cache_es = NULL; + + orig_es.start = es->start; + orig_es.len = es->len; + len1 = offset > es->start ? offset - es->start : 0; + len2 = extent_status_end(es) > end ? + extent_status_end(es) - end : 0; + if (len1 > 0) + es->len = len1; + if (len2 > 0) { + if (len1 > 0) { + err = __es_insert_extent(tree, end + 1, len2); + if (err) { + es->start = orig_es.start; + es->len = orig_es.len; + goto out; + } + } else { + es->start = end + 1; + es->len = len2; + } + goto out; + } + + if (len1 > 0) { + node = rb_next(&es->rb_node); + if (node) + es = rb_entry(node, struct extent_status, rb_node); + else + es = NULL; + } + + while (es && extent_status_end(es) <= end) { + node = rb_next(&es->rb_node); + rb_erase(&es->rb_node, &tree->root); + ext4_es_free_extent(es); + if (!node) { + es = NULL; + break; + } + es = rb_entry(node, struct extent_status, rb_node); + } + + if (es && es->start < end + 1) { + len1 = extent_status_end(es) - end; + es->start = end + 1; + es->len = len1; + } + +out: + write_unlock(&EXT4_I(inode)->i_es_lock); + ext4_es_print_tree(inode); + return err; +} diff --git a/fs/ext4/extents_status.h b/fs/ext4/extents_status.h index 8be2ab9c9425..077f82db092a 100644 --- a/fs/ext4/extents_status.h +++ b/fs/ext4/extents_status.h @@ -11,6 +11,15 @@ #ifndef _EXT4_EXTENTS_STATUS_H #define _EXT4_EXTENTS_STATUS_H +/* + * Turn on ES_DEBUG__ to get lots of info about extent status operations. + */ +#ifdef ES_DEBUG__ +#define es_debug(fmt, ...) printk(fmt, ##__VA_ARGS__) +#else +#define es_debug(fmt, ...) no_printk(fmt, ##__VA_ARGS__) +#endif + struct extent_status { struct rb_node rb_node; ext4_lblk_t start; /* first block extent covers */ @@ -22,4 +31,15 @@ struct ext4_es_tree { struct extent_status *cache_es; /* recently accessed extent */ }; +extern int __init ext4_init_es(void); +extern void ext4_exit_es(void); +extern void ext4_es_init_tree(struct ext4_es_tree *tree); + +extern int ext4_es_insert_extent(struct inode *inode, ext4_lblk_t start, + ext4_lblk_t len); +extern int ext4_es_remove_extent(struct inode *inode, ext4_lblk_t start, + ext4_lblk_t len); +extern ext4_lblk_t ext4_es_find_extent(struct inode *inode, + struct extent_status *es); + #endif /* _EXT4_EXTENTS_STATUS_H */ -- cgit v1.2.2 From 9a26b66175e1c221f39bbe09e2e1d0a31a14ba6d Mon Sep 17 00:00:00 2001 From: Zheng Liu Date: Thu, 8 Nov 2012 21:57:30 -0500 Subject: ext4: initialize extent status tree Let ext4 initialize extent status tree of an inode. Signed-off-by: Yongqiang Yang Signed-off-by: Allison Henderson Signed-off-by: Zheng Liu Signed-off-by: "Theodore Ts'o" --- fs/ext4/super.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 18e89fafebd1..6791d091fbc7 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -943,6 +943,8 @@ static struct inode *ext4_alloc_inode(struct super_block *sb) memset(&ei->i_cached_extent, 0, sizeof(struct ext4_ext_cache)); INIT_LIST_HEAD(&ei->i_prealloc_list); spin_lock_init(&ei->i_prealloc_lock); + ext4_es_init_tree(&ei->i_es_tree); + rwlock_init(&ei->i_es_lock); ei->i_reserved_data_blocks = 0; ei->i_reserved_meta_blocks = 0; ei->i_allocated_meta_blocks = 0; -- cgit v1.2.2 From 51865fda28e585bdcc164474ff6438a9ccdbfada Mon Sep 17 00:00:00 2001 From: Zheng Liu Date: Thu, 8 Nov 2012 21:57:32 -0500 Subject: ext4: let ext4 maintain extent status tree This patch lets ext4 maintain extent status tree. Currently it only tracks delay extent status in extent status tree. When a delay allocation is issued, the related delay extent will be inserted into extent status tree. When a delay extent is written out or invalidated, it will be removed from this tree. Signed-off-by: Yongqiang Yang Signed-off-by: Allison Henderson Signed-off-by: Zheng Liu Signed-off-by: "Theodore Ts'o" --- fs/ext4/extents.c | 4 ++++ fs/ext4/indirect.c | 1 + fs/ext4/inode.c | 38 +++++++++++++++++++++++++++++++++++--- fs/ext4/super.c | 12 +++++++++++- 4 files changed, 51 insertions(+), 4 deletions(-) diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index dce97de6a409..67660fa2a7e6 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -4344,6 +4344,8 @@ void ext4_ext_truncate(struct inode *inode) last_block = (inode->i_size + sb->s_blocksize - 1) >> EXT4_BLOCK_SIZE_BITS(sb); + err = ext4_es_remove_extent(inode, last_block, + EXT_MAX_BLOCKS - last_block); err = ext4_ext_remove_space(inode, last_block, EXT_MAX_BLOCKS - 1); /* In a multi-transaction truncate, we only make the final @@ -4971,6 +4973,8 @@ int ext4_ext_punch_hole(struct file *file, loff_t offset, loff_t length) ext4_ext_invalidate_cache(inode); ext4_discard_preallocations(inode); + err = ext4_es_remove_extent(inode, first_block, + stop_block - first_block); err = ext4_ext_remove_space(inode, first_block, stop_block - 1); ext4_ext_invalidate_cache(inode); diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c index 292337f27c9c..f6663c3a946d 100644 --- a/fs/ext4/indirect.c +++ b/fs/ext4/indirect.c @@ -1411,6 +1411,7 @@ void ext4_ind_truncate(struct inode *inode) down_write(&ei->i_data_sem); ext4_discard_preallocations(inode); + ext4_es_remove_extent(inode, last_block, EXT_MAX_BLOCKS - last_block); /* * The orphan list entry will now protect us from any crash which diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index f84bfd6d1867..1e92349272e0 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -574,7 +574,16 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode, up_read((&EXT4_I(inode)->i_data_sem)); if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) { - int ret = check_block_validity(inode, map); + int ret; + if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) { + /* delayed alloc may be allocated by fallocate and + * coverted to initialized by directIO. + * we need to handle delayed extent here. + */ + down_write((&EXT4_I(inode)->i_data_sem)); + goto delayed_mapped; + } + ret = check_block_validity(inode, map); if (ret != 0) return ret; } @@ -656,8 +665,16 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode, * set the BH_Da_Mapped bit on them. Its important to do this * under the protection of i_data_sem. */ - if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) + if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) { + int ret; set_buffers_da_mapped(inode, map); +delayed_mapped: + /* delayed allocation blocks has been allocated */ + ret = ext4_es_remove_extent(inode, map->m_lblk, + map->m_len); + if (ret < 0) + retval = ret; + } } up_write((&EXT4_I(inode)->i_data_sem)); @@ -1303,6 +1320,7 @@ static void ext4_da_page_release_reservation(struct page *page, struct inode *inode = page->mapping->host; struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); int num_clusters; + ext4_fsblk_t lblk; head = page_buffers(page); bh = head; @@ -1317,11 +1335,15 @@ static void ext4_da_page_release_reservation(struct page *page, curr_off = next_off; } while ((bh = bh->b_this_page) != head); + if (to_release) { + lblk = page->index << (PAGE_CACHE_SHIFT - inode->i_blkbits); + ext4_es_remove_extent(inode, lblk, to_release); + } + /* If we have released all the blocks belonging to a cluster, then we * need to release the reserved space for that cluster. */ num_clusters = EXT4_NUM_B2C(sbi, to_release); while (num_clusters > 0) { - ext4_fsblk_t lblk; lblk = (page->index << (PAGE_CACHE_SHIFT - inode->i_blkbits)) + ((num_clusters - 1) << sbi->s_cluster_bits); if (sbi->s_cluster_ratio == 1 || @@ -1502,9 +1524,15 @@ static void ext4_da_block_invalidatepages(struct mpage_da_data *mpd) struct pagevec pvec; struct inode *inode = mpd->inode; struct address_space *mapping = inode->i_mapping; + ext4_lblk_t start, last; index = mpd->first_page; end = mpd->next_page - 1; + + start = index << (PAGE_CACHE_SHIFT - inode->i_blkbits); + last = end << (PAGE_CACHE_SHIFT - inode->i_blkbits); + ext4_es_remove_extent(inode, start, last - start + 1); + while (index <= end) { nr_pages = pagevec_lookup(&pvec, mapping, index, PAGEVEC_SIZE); if (nr_pages == 0) @@ -1816,6 +1844,10 @@ static int ext4_da_map_blocks(struct inode *inode, sector_t iblock, goto out_unlock; } + retval = ext4_es_insert_extent(inode, map->m_lblk, map->m_len); + if (retval) + goto out_unlock; + /* Clear EXT4_MAP_FROM_CLUSTER flag since its purpose is served * and it should not appear on the bh->b_state. */ diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 6791d091fbc7..ad6cd8aeb946 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -50,6 +50,7 @@ #include "xattr.h" #include "acl.h" #include "mballoc.h" +#include "ext4_extents.h" #define CREATE_TRACE_POINTS #include @@ -1033,6 +1034,7 @@ void ext4_clear_inode(struct inode *inode) clear_inode(inode); dquot_drop(inode); ext4_discard_preallocations(inode); + ext4_es_remove_extent(inode, 0, EXT_MAX_BLOCKS); if (EXT4_I(inode)->jinode) { jbd2_journal_release_jbd_inode(EXT4_JOURNAL(inode), EXT4_I(inode)->jinode); @@ -5296,9 +5298,14 @@ static int __init ext4_init_fs(void) init_waitqueue_head(&ext4__ioend_wq[i]); } - err = ext4_init_pageio(); + err = ext4_init_es(); if (err) return err; + + err = ext4_init_pageio(); + if (err) + goto out7; + err = ext4_init_system_zone(); if (err) goto out6; @@ -5348,6 +5355,9 @@ out5: ext4_exit_system_zone(); out6: ext4_exit_pageio(); +out7: + ext4_exit_es(); + return err; } -- cgit v1.2.2 From 992e9fdd7b3f656ab8aea895f0038336950774ed Mon Sep 17 00:00:00 2001 From: Zheng Liu Date: Thu, 8 Nov 2012 21:57:33 -0500 Subject: ext4: add some tracepoints in extent status tree This patch adds some tracepoints in extent status tree. Signed-off-by: Zheng Liu Signed-off-by: "Theodore Ts'o" --- fs/ext4/extents_status.c | 8 ++++ include/trace/events/ext4.h | 101 ++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 109 insertions(+) diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c index 02c09be3d773..564d981a2fcc 100644 --- a/fs/ext4/extents_status.c +++ b/fs/ext4/extents_status.c @@ -14,6 +14,8 @@ #include "extents_status.h" #include "ext4_extents.h" +#include + /* * According to previous discussion in Ext4 Developer Workshop, we * will introduce a new structure called io tree to track all extent @@ -224,6 +226,8 @@ ext4_lblk_t ext4_es_find_extent(struct inode *inode, struct extent_status *es) struct rb_node *node; ext4_lblk_t ret = EXT_MAX_BLOCKS; + trace_ext4_es_find_extent_enter(inode, es->start); + read_lock(&EXT4_I(inode)->i_es_lock); tree = &EXT4_I(inode)->i_es_tree; @@ -253,6 +257,8 @@ out: } read_unlock(&EXT4_I(inode)->i_es_lock); + + trace_ext4_es_find_extent_exit(inode, es, ret); return ret; } @@ -393,6 +399,7 @@ int ext4_es_insert_extent(struct inode *inode, ext4_lblk_t offset, struct ext4_es_tree *tree; int err = 0; + trace_ext4_es_insert_extent(inode, offset, len); es_debug("add [%u/%u) to extent status tree of inode %lu\n", offset, len, inode->i_ino); @@ -422,6 +429,7 @@ int ext4_es_remove_extent(struct inode *inode, ext4_lblk_t offset, ext4_lblk_t len1, len2, end; int err = 0; + trace_ext4_es_remove_extent(inode, offset, len); es_debug("remove [%u/%u) from extent status tree of inode %lu\n", offset, len, inode->i_ino); diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h index d2a125a6db8b..f6372b011366 100644 --- a/include/trace/events/ext4.h +++ b/include/trace/events/ext4.h @@ -15,6 +15,7 @@ struct ext4_inode_info; struct mpage_da_data; struct ext4_map_blocks; struct ext4_extent; +struct extent_status; #define EXT4_I(inode) (container_of(inode, struct ext4_inode_info, vfs_inode)) @@ -2054,6 +2055,106 @@ TRACE_EVENT(ext4_ext_remove_space_done, (unsigned short) __entry->eh_entries) ); +TRACE_EVENT(ext4_es_insert_extent, + TP_PROTO(struct inode *inode, ext4_lblk_t start, ext4_lblk_t len), + + TP_ARGS(inode, start, len), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( ino_t, ino ) + __field( loff_t, start ) + __field( loff_t, len ) + ), + + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->ino = inode->i_ino; + __entry->start = start; + __entry->len = len; + ), + + TP_printk("dev %d,%d ino %lu es [%lld/%lld)", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long) __entry->ino, + __entry->start, __entry->len) +); + +TRACE_EVENT(ext4_es_remove_extent, + TP_PROTO(struct inode *inode, ext4_lblk_t start, ext4_lblk_t len), + + TP_ARGS(inode, start, len), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( ino_t, ino ) + __field( loff_t, start ) + __field( loff_t, len ) + ), + + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->ino = inode->i_ino; + __entry->start = start; + __entry->len = len; + ), + + TP_printk("dev %d,%d ino %lu es [%lld/%lld)", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long) __entry->ino, + __entry->start, __entry->len) +); + +TRACE_EVENT(ext4_es_find_extent_enter, + TP_PROTO(struct inode *inode, ext4_lblk_t start), + + TP_ARGS(inode, start), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( ino_t, ino ) + __field( ext4_lblk_t, start ) + ), + + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->ino = inode->i_ino; + __entry->start = start; + ), + + TP_printk("dev %d,%d ino %lu start %u