From: Harshad Shirwadkar <harshadshirwadkar@gmail.com>
To: linux-ext4@vger.kernel.org
Cc: Harshad Shirwadkar <harshadshirwadkar@gmail.com>,
kbuild test robot <lkp@intel.com>
Subject: [PATCH v5 17/20] ext4: add idempotent helpers to manipulate bitmaps
Date: Mon, 9 Mar 2020 00:05:23 -0700 [thread overview]
Message-ID: <20200309070526.218202-17-harshadshirwadkar@gmail.com> (raw)
In-Reply-To: <20200309070526.218202-1-harshadshirwadkar@gmail.com>
For fast commit replay path, we need idempotent helpers that mark
inodes used, data blocks as used or free. It's important these are
idempotent and that's because we can crash while we are replaying.
Signed-off-by: Harshad Shirwadkar <harshadshirwadkar@gmail.com>
Reported-by: kbuild test robot <lkp@intel.com>
---
fs/ext4/ext4.h | 1 +
fs/ext4/ialloc.c | 113 ++++++++++++++++++++++++++++++++++++++
fs/ext4/mballoc.c | 136 +++++++++++++++++++++++++++++++++++++++++++++-
fs/ext4/mballoc.h | 2 +
4 files changed, 251 insertions(+), 1 deletion(-)
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 6dacbb95cc52..ca1e7f100bc3 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -2691,6 +2691,7 @@ extern int ext4fs_dirhash(const struct inode *dir, const char *name, int len,
struct dx_hash_info *hinfo);
/* ialloc.c */
+extern int ext4_mark_inode_used(struct super_block *sb, int ino);
extern struct inode *__ext4_new_inode(handle_t *, struct inode *, umode_t,
const struct qstr *qstr, __u32 goal,
uid_t *owner, __u32 i_flags,
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index f95ee99091e4..f3c5b86c6a06 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -730,6 +730,119 @@ static int find_inode_bit(struct super_block *sb, ext4_group_t group,
return 1;
}
+int ext4_mark_inode_used(struct super_block *sb, int ino)
+{
+ unsigned long max_ino = le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count);
+ struct buffer_head *inode_bitmap_bh = NULL, *group_desc_bh = NULL;
+ struct ext4_group_desc *gdp;
+ ext4_group_t group;
+ int bit;
+ int err = -EFSCORRUPTED;
+
+ if (ino < EXT4_FIRST_INO(sb) || ino > max_ino)
+ goto out;
+
+ group = (ino - 1) / EXT4_INODES_PER_GROUP(sb);
+ bit = (ino - 1) % EXT4_INODES_PER_GROUP(sb);
+ inode_bitmap_bh = ext4_read_inode_bitmap(sb, group);
+ if (IS_ERR(inode_bitmap_bh))
+ return PTR_ERR(inode_bitmap_bh);
+
+ if (ext4_test_bit(bit, inode_bitmap_bh->b_data)) {
+ err = -EEXIST;
+ goto out;
+ }
+
+ gdp = ext4_get_group_desc(sb, group, &group_desc_bh);
+ if (!gdp || !group_desc_bh) {
+ err = -EINVAL;
+ goto out;
+ }
+
+ ext4_set_bit(bit, inode_bitmap_bh->b_data);
+
+ BUFFER_TRACE(inode_bitmap_bh, "call ext4_handle_dirty_metadata");
+ err = ext4_handle_dirty_metadata(NULL, NULL, inode_bitmap_bh);
+ if (err) {
+ ext4_std_error(sb, err);
+ goto out;
+ }
+ sync_dirty_buffer(inode_bitmap_bh);
+ BUFFER_TRACE(group_desc_bh, "get_write_access");
+
+ /* We may have to initialize the block bitmap if it isn't already */
+ if (ext4_has_group_desc_csum(sb) &&
+ gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
+ struct buffer_head *block_bitmap_bh;
+
+ block_bitmap_bh = ext4_read_block_bitmap(sb, group);
+ if (IS_ERR(block_bitmap_bh)) {
+ err = PTR_ERR(block_bitmap_bh);
+ goto out;
+ }
+
+ BUFFER_TRACE(block_bitmap_bh, "dirty block bitmap");
+ err = ext4_handle_dirty_metadata(NULL, NULL, block_bitmap_bh);
+ sync_dirty_buffer(block_bitmap_bh);
+
+ /* recheck and clear flag under lock if we still need to */
+ ext4_lock_group(sb, group);
+ if (ext4_has_group_desc_csum(sb) &&
+ (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT))) {
+ gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT);
+ ext4_free_group_clusters_set(sb, gdp,
+ ext4_free_clusters_after_init(sb, group, gdp));
+ ext4_block_bitmap_csum_set(sb, group, gdp,
+ block_bitmap_bh);
+ ext4_group_desc_csum_set(sb, group, gdp);
+ }
+ ext4_unlock_group(sb, group);
+ brelse(block_bitmap_bh);
+
+ if (err) {
+ ext4_std_error(sb, err);
+ goto out;
+ }
+ }
+
+ /* Update the relevant bg descriptor fields */
+ if (ext4_has_group_desc_csum(sb)) {
+ int free;
+
+ ext4_lock_group(sb, group); /* while we modify the bg desc */
+ free = EXT4_INODES_PER_GROUP(sb) -
+ ext4_itable_unused_count(sb, gdp);
+ if (gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT)) {
+ gdp->bg_flags &= cpu_to_le16(~EXT4_BG_INODE_UNINIT);
+ free = 0;
+ }
+
+ /*
+ * Check the relative inode number against the last used
+ * relative inode number in this group. if it is greater
+ * we need to update the bg_itable_unused count
+ */
+ if (bit >= free)
+ ext4_itable_unused_set(sb, gdp,
+ (EXT4_INODES_PER_GROUP(sb) - bit - 1));
+ } else {
+ ext4_lock_group(sb, group);
+ }
+
+ ext4_free_inodes_set(sb, gdp, ext4_free_inodes_count(sb, gdp) - 1);
+ if (ext4_has_group_desc_csum(sb)) {
+ ext4_inode_bitmap_csum_set(sb, group, gdp, inode_bitmap_bh,
+ EXT4_INODES_PER_GROUP(sb) / 8);
+ ext4_group_desc_csum_set(sb, group, gdp);
+ }
+
+ ext4_unlock_group(sb, group);
+ err = ext4_handle_dirty_metadata(NULL, NULL, group_desc_bh);
+ sync_dirty_buffer(group_desc_bh);
+out:
+ return err;
+}
+
/*
* There are two policies for allocating an inode. If the new inode is
* a directory, then a forward search is made for a block group with both
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 51a78eb65f3c..96be991718f1 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -3052,6 +3052,93 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
return err;
}
+void ext4_mb_mark_used(struct super_block *sb, ext4_fsblk_t block,
+ int len)
+{
+ struct buffer_head *bitmap_bh = NULL;
+ struct ext4_group_desc *gdp;
+ struct buffer_head *gdp_bh;
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
+ ext4_group_t group;
+ ext4_fsblk_t cluster;
+ ext4_grpblk_t blkoff;
+ int i, clen, err;
+ int already_allocated_count;
+
+ cluster = EXT4_B2C(sbi, block);
+ clen = EXT4_B2C(sbi, len);
+
+ ext4_get_group_no_and_offset(sb, block, &group, &blkoff);
+ bitmap_bh = ext4_read_block_bitmap(sb, group);
+ if (IS_ERR(bitmap_bh)) {
+ err = PTR_ERR(bitmap_bh);
+ bitmap_bh = NULL;
+ goto out_err;
+ }
+
+ err = -EIO;
+ gdp = ext4_get_group_desc(sb, group, &gdp_bh);
+ if (!gdp)
+ goto out_err;
+
+ if (!ext4_data_block_valid(sbi, block, len)) {
+ ext4_error(sb, "Allocating blks %llu-%llu which overlap mdata",
+ cluster, cluster+clen);
+ /* File system mounted not to panic on error
+ * Fix the bitmap and return EFSCORRUPTED
+ * We leak some of the blocks here.
+ */
+ ext4_lock_group(sb, group);
+ ext4_set_bits(bitmap_bh->b_data, blkoff, clen);
+ ext4_unlock_group(sb, group);
+ err = ext4_handle_dirty_metadata(NULL, NULL, bitmap_bh);
+ if (!err)
+ err = -EFSCORRUPTED;
+ sync_dirty_buffer(bitmap_bh);
+ goto out_err;
+ }
+
+ ext4_lock_group(sb, group);
+ already_allocated_count = 0;
+ for (i = 0; i < clen; i++)
+ if (mb_test_bit(blkoff + i, bitmap_bh->b_data))
+ already_allocated_count++;
+
+ ext4_set_bits(bitmap_bh->b_data, blkoff, clen);
+ if (ext4_has_group_desc_csum(sb) &&
+ (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT))) {
+ gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT);
+ ext4_free_group_clusters_set(sb, gdp,
+ ext4_free_clusters_after_init(sb,
+ group, gdp));
+ }
+ clen = ext4_free_group_clusters(sb, gdp) - clen +
+ already_allocated_count;
+ ext4_free_group_clusters_set(sb, gdp, clen);
+ ext4_block_bitmap_csum_set(sb, group, gdp, bitmap_bh);
+ ext4_group_desc_csum_set(sb, group, gdp);
+
+ ext4_unlock_group(sb, group);
+
+ if (sbi->s_log_groups_per_flex) {
+ ext4_group_t flex_group = ext4_flex_group(sbi, group);
+
+ atomic64_sub(len,
+ &sbi_array_rcu_deref(sbi, s_flex_groups,
+ flex_group)->free_clusters);
+ }
+
+ err = ext4_handle_dirty_metadata(NULL, NULL, bitmap_bh);
+ if (err)
+ goto out_err;
+ sync_dirty_buffer(bitmap_bh);
+ err = ext4_handle_dirty_metadata(NULL, NULL, gdp_bh);
+ sync_dirty_buffer(gdp_bh);
+
+out_err:
+ brelse(bitmap_bh);
+}
+
/*
* here we normalize request for locality group
* Group request are normalized to s_mb_group_prealloc, which goes to
@@ -4715,6 +4802,47 @@ ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b,
return 0;
}
+void ext4_free_blocks_simple(struct inode *inode, ext4_fsblk_t block,
+ unsigned long count)
+{
+ struct buffer_head *bitmap_bh;
+ struct super_block *sb = inode->i_sb;
+ struct ext4_group_desc *gdp;
+ struct buffer_head *gdp_bh;
+ ext4_group_t group;
+ ext4_grpblk_t blkoff;
+ int already_freed = 0, err, i;
+
+ ext4_get_group_no_and_offset(sb, block, &group, &blkoff);
+ bitmap_bh = ext4_read_block_bitmap(sb, group);
+ if (IS_ERR(bitmap_bh)) {
+ err = PTR_ERR(bitmap_bh);
+ pr_warn("Failed to read block bitmap\n");
+ return;
+ }
+ gdp = ext4_get_group_desc(sb, group, &gdp_bh);
+ if (!gdp)
+ return;
+
+ for (i = 0; i < count; i++) {
+ if (!mb_test_bit(blkoff + i, bitmap_bh->b_data))
+ already_freed++;
+ }
+ mb_clear_bits(bitmap_bh->b_data, blkoff, count);
+ err = ext4_handle_dirty_metadata(NULL, NULL, bitmap_bh);
+ if (err)
+ return;
+ ext4_free_group_clusters_set(
+ sb, gdp, ext4_free_group_clusters(sb, gdp) +
+ count - already_freed);
+ ext4_block_bitmap_csum_set(sb, group, gdp, bitmap_bh);
+ ext4_group_desc_csum_set(sb, group, gdp);
+ ext4_handle_dirty_metadata(NULL, NULL, gdp_bh);
+ sync_dirty_buffer(bitmap_bh);
+ sync_dirty_buffer(gdp_bh);
+ brelse(bitmap_bh);
+}
+
/**
* ext4_free_blocks() -- Free given blocks and update quota
* @handle: handle for this transaction
@@ -4741,6 +4869,13 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode,
int err = 0;
int ret;
+ sbi = EXT4_SB(sb);
+
+ if (sbi->s_mount_state & EXT4_FC_REPLAY) {
+ ext4_free_blocks_simple(inode, block, count);
+ return;
+ }
+
might_sleep();
if (bh) {
if (block)
@@ -4749,7 +4884,6 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode,
block = bh->b_blocknr;
}
- sbi = EXT4_SB(sb);
if (!(flags & EXT4_FREE_BLOCKS_VALIDATED) &&
!ext4_data_block_valid(sbi, block, count)) {
ext4_error(sb, "Freeing blocks not in datazone - "
diff --git a/fs/ext4/mballoc.h b/fs/ext4/mballoc.h
index 88c98f17e3d9..1881710041b6 100644
--- a/fs/ext4/mballoc.h
+++ b/fs/ext4/mballoc.h
@@ -215,4 +215,6 @@ ext4_mballoc_query_range(
ext4_mballoc_query_range_fn formatter,
void *priv);
+void ext4_mb_mark_used(struct super_block *sb, ext4_fsblk_t block,
+ int len);
#endif
--
2.25.1.481.gfbce0eb801-goog
next prev parent reply other threads:[~2020-03-09 7:06 UTC|newest]
Thread overview: 20+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <tytso@mit.edu>
2020-03-09 7:05 ` [PATCH v5 01/20] ext4: update docs for fast commit feature Harshad Shirwadkar
2020-03-09 7:05 ` [PATCH v5 02/20] ext4: add handling for extended mount options Harshad Shirwadkar
2020-03-09 7:05 ` [PATCH v5 03/20] ext4, jbd2: add fast commit initialization routines Harshad Shirwadkar
2020-03-09 7:05 ` [PATCH v5 04/20] jbd2: add fast commit block tracker variables Harshad Shirwadkar
2020-03-09 7:05 ` [PATCH v5 05/20] jbd2: disable fast commits if journal is empty Harshad Shirwadkar
2020-03-09 7:05 ` [PATCH v5 06/20] jbd2: fast commit main commit path changes Harshad Shirwadkar
2020-03-09 7:05 ` [PATCH v5 07/20] ext4: add generic diff tracking routines and range tracking Harshad Shirwadkar
2020-03-09 7:05 ` [PATCH v5 08/20] ext4: add directory entry tracking routines Harshad Shirwadkar
2020-03-09 7:05 ` [PATCH v5 09/20] ext4: add inode tracking and ineligible marking routines Harshad Shirwadkar
2020-03-09 7:05 ` [PATCH v5 10/20] ext4: break ext4_unlink() and ext4_link() Harshad Shirwadkar
2020-03-09 7:05 ` [PATCH v5 11/20] ext4: add fast commit track points Harshad Shirwadkar
2020-03-09 7:05 ` [PATCH v5 12/20] ext4: add fast commit on-disk format structs Harshad Shirwadkar
2020-03-09 7:05 ` [PATCH v5 13/20] jbd2: add new APIs for commit path of fast commits Harshad Shirwadkar
2020-03-09 7:05 ` [PATCH v5 14/20] ext4: main commit routine for " Harshad Shirwadkar
2020-03-09 7:05 ` [PATCH v5 15/20] jbd2: add fast commit recovery path support Harshad Shirwadkar
2020-03-09 7:05 ` [PATCH v5 16/20] ext4: fast commit recovery path preparation Harshad Shirwadkar
2020-03-09 7:05 ` Harshad Shirwadkar [this message]
2020-03-09 7:05 ` [PATCH v5 18/20] ext4: disable certain features in replay path Harshad Shirwadkar
2020-03-09 7:05 ` [PATCH v5 19/20] ext4: add fast commit " Harshad Shirwadkar
2020-03-09 7:05 ` [PATCH v5 20/20] ext4: add debug mount option to test fast commit replay Harshad Shirwadkar
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20200309070526.218202-17-harshadshirwadkar@gmail.com \
--to=harshadshirwadkar@gmail.com \
--cc=linux-ext4@vger.kernel.org \
--cc=lkp@intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).