| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <20230811061905.301124-1-dongyangli@ddn.com>
Date: Fri, 11 Aug 2023 16:19:04 +1000
From: Li Dongyang <dongyangli@....com>
To: linux-ext4@...r.kernel.org
Cc: adilger@...ger.ca, sihara@....com, wangshilong1991@...il.com
Subject: [PATCH 1/2] ext4: introduce EXT4_BG_TRIMMED to optimize fstrim
Currently the flag indicating block group has done fstrim is not
persistent, and trim status will be lost after remount, as
a result fstrim can not skip the already trimmed groups, which
could be slow on very large devices.
This patch introduces a new block group flag EXT4_BG_TRIMMED,
we need 1 extra block group descriptor write after trimming each
block group.
When clearing the flag, the block group descriptor is journalled
already so no extra overhead.
Add a new super block flag EXT2_FLAGS_TRACK_TRIM, to indicate if
we should honour EXT4_BG_TRIMMED when doing fstrim.
The new super block flag can be turned on/off via tune2fs.
Cc: Shuichi Ihara <sihara@....com>
Cc: Andreas Dilger <adilger@...ger.ca>
Cc: Wang Shilong <wangshilong1991@...il.com>
Signed-off-by: Wang Shilong <wshilong@....com>
Signed-off-by: Li Dongyang <dongyangli@....com>
---
fs/ext4/ext4.h | 10 ++------
fs/ext4/ext4_jbd2.h | 3 ++-
fs/ext4/mballoc.c | 62 +++++++++++++++++++++++++++++++++++----------
3 files changed, 52 insertions(+), 23 deletions(-)
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 0a2d55faa095..a990fb49b24f 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -437,6 +437,7 @@ struct flex_groups {
#define EXT4_BG_INODE_UNINIT 0x0001 /* Inode table/bitmap not in use */
#define EXT4_BG_BLOCK_UNINIT 0x0002 /* Block bitmap not in use */
#define EXT4_BG_INODE_ZEROED 0x0004 /* On-disk itable initialized to zero */
+#define EXT4_BG_TRIMMED 0x0008 /* block group was trimmed */
/*
* Macro-instructions used to manage group descriptors
@@ -1166,6 +1167,7 @@ struct ext4_inode_info {
#define EXT2_FLAGS_SIGNED_HASH 0x0001 /* Signed dirhash in use */
#define EXT2_FLAGS_UNSIGNED_HASH 0x0002 /* Unsigned dirhash in use */
#define EXT2_FLAGS_TEST_FILESYS 0x0004 /* to test development code */
+#define EXT2_FLAGS_TRACK_TRIM 0x0008 /* Track trim status in each bg */
/*
* Mount flags set via mount options or defaults
@@ -3412,7 +3414,6 @@ struct ext4_group_info {
};
#define EXT4_GROUP_INFO_NEED_INIT_BIT 0
-#define EXT4_GROUP_INFO_WAS_TRIMMED_BIT 1
#define EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT 2
#define EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT 3
#define EXT4_GROUP_INFO_BBITMAP_CORRUPT \
@@ -3427,13 +3428,6 @@ struct ext4_group_info {
(test_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &((grp)->bb_state)))
#define EXT4_MB_GRP_IBITMAP_CORRUPT(grp) \
(test_bit(EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT, &((grp)->bb_state)))
-
-#define EXT4_MB_GRP_WAS_TRIMMED(grp) \
- (test_bit(EXT4_GROUP_INFO_WAS_TRIMMED_BIT, &((grp)->bb_state)))
-#define EXT4_MB_GRP_SET_TRIMMED(grp) \
- (set_bit(EXT4_GROUP_INFO_WAS_TRIMMED_BIT, &((grp)->bb_state)))
-#define EXT4_MB_GRP_CLEAR_TRIMMED(grp) \
- (clear_bit(EXT4_GROUP_INFO_WAS_TRIMMED_BIT, &((grp)->bb_state)))
#define EXT4_MB_GRP_TEST_AND_SET_READ(grp) \
(test_and_set_bit(EXT4_GROUP_INFO_BBITMAP_READ_BIT, &((grp)->bb_state)))
diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h
index 0c77697d5e90..ce529a454b2a 100644
--- a/fs/ext4/ext4_jbd2.h
+++ b/fs/ext4/ext4_jbd2.h
@@ -120,7 +120,8 @@
#define EXT4_HT_MOVE_EXTENTS 9
#define EXT4_HT_XATTR 10
#define EXT4_HT_EXT_CONVERT 11
-#define EXT4_HT_MAX 12
+#define EXT4_HT_FS_TRIM 12
+#define EXT4_HT_MAX 13
/**
* struct ext4_journal_cb_entry - Base structure for callback information.
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 21b903fe546e..80283be01363 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -3849,15 +3849,6 @@ static void ext4_free_data_in_buddy(struct super_block *sb,
rb_erase(&entry->efd_node, &(db->bb_free_root));
mb_free_blocks(NULL, &e4b, entry->efd_start_cluster, entry->efd_count);
- /*
- * Clear the trimmed flag for the group so that the next
- * ext4_trim_fs can trim it.
- * If the volume is mounted with -o discard, online discard
- * is supported and the free blocks will be trimmed online.
- */
- if (!test_opt(sb, DISCARD))
- EXT4_MB_GRP_CLEAR_TRIMMED(db);
-
if (!db->bb_free_root.rb_node) {
/* No more items in the per group rb tree
* balance refcounts from ext4_mb_free_metadata()
@@ -6587,8 +6578,7 @@ static void ext4_mb_clear_bb(handle_t *handle, struct inode *inode,
" group:%u block:%d count:%lu failed"
" with %d", block_group, bit, count,
err);
- } else
- EXT4_MB_GRP_CLEAR_TRIMMED(e4b.bd_info);
+ }
ext4_lock_group(sb, block_group);
mb_clear_bits(bitmap_bh->b_data, bit, count_clusters);
@@ -6598,6 +6588,14 @@ static void ext4_mb_clear_bb(handle_t *handle, struct inode *inode,
ret = ext4_free_group_clusters(sb, gdp) + count_clusters;
ext4_free_group_clusters_set(sb, gdp, ret);
ext4_block_bitmap_csum_set(sb, gdp, bitmap_bh);
+ /*
+ * Clear the trimmed flag for the group so that the next
+ * ext4_trim_fs can trim it.
+ * If the volume is mounted with -o discard, online discard
+ * is supported and the free blocks will be trimmed online.
+ */
+ if (!test_opt(sb, DISCARD))
+ gdp->bg_flags &= cpu_to_le16(~EXT4_BG_TRIMMED);
ext4_group_desc_csum_set(sb, block_group, gdp);
ext4_unlock_group(sb, block_group);
@@ -6995,10 +6993,19 @@ ext4_trim_all_free(struct super_block *sb, ext4_group_t group,
ext4_grpblk_t minblocks, bool set_trimmed)
{
struct ext4_buddy e4b;
+ struct ext4_super_block *es = EXT4_SB(sb)->s_es;
+ struct ext4_group_desc *gdp;
+ struct buffer_head *gd_bh;
int ret;
trace_ext4_trim_all_free(sb, group, start, max);
+ gdp = ext4_get_group_desc(sb, group, &gd_bh);
+ if (!gdp) {
+ ret = -EIO;
+ return ret;
+ }
+
ret = ext4_mb_load_buddy(sb, group, &e4b);
if (ret) {
ext4_warning(sb, "Error %d loading buddy information for %u",
@@ -7008,11 +7015,10 @@ ext4_trim_all_free(struct super_block *sb, ext4_group_t group,
ext4_lock_group(sb, group);
- if (!EXT4_MB_GRP_WAS_TRIMMED(e4b.bd_info) ||
+ if (!(es->s_flags & cpu_to_le16(EXT2_FLAGS_TRACK_TRIM) &&
+ gdp->bg_flags & cpu_to_le16(EXT4_BG_TRIMMED)) ||
minblocks < EXT4_SB(sb)->s_last_trim_minblks) {
ret = ext4_try_to_trim_range(sb, &e4b, start, max, minblocks);
- if (ret >= 0 && set_trimmed)
- EXT4_MB_GRP_SET_TRIMMED(e4b.bd_info);
} else {
ret = 0;
}
@@ -7020,6 +7026,34 @@ ext4_trim_all_free(struct super_block *sb, ext4_group_t group,
ext4_unlock_group(sb, group);
ext4_mb_unload_buddy(&e4b);
+ if (ret > 0 && set_trimmed) {
+ int err;
+ handle_t *handle;
+
+ handle = ext4_journal_start_sb(sb, EXT4_HT_FS_TRIM, 1);
+ if (IS_ERR(handle)) {
+ ret = PTR_ERR(handle);
+ goto out_return;
+ }
+ err = ext4_journal_get_write_access(handle, sb, gd_bh,
+ EXT4_JTR_NONE);
+ if (err) {
+ ret = err;
+ goto out_journal;
+ }
+ ext4_lock_group(sb, group);
+ gdp->bg_flags |= cpu_to_le16(EXT4_BG_TRIMMED);
+ ext4_group_desc_csum_set(sb, group, gdp);
+ ext4_unlock_group(sb, group);
+ err = ext4_handle_dirty_metadata(handle, NULL, gd_bh);
+ if (err)
+ ret = err;
+out_journal:
+ err = ext4_journal_stop(handle);
+ if (err)
+ ret = err;
+ }
+out_return:
ext4_debug("trimmed %d blocks in the group %d\n",
ret, group);
--
2.41.0
Powered by blists - more mailing lists