f2fs: fix age extent cache insertion skip on counter overflow

The age extent cache uses last_blocks (derived from
allocated_data_blocks) to determine data age. However, there's a
conflict between the deletion
marker (last_blocks=0) and legitimate last_blocks=0 cases when
allocated_data_blocks overflows to 0 after reaching ULLONG_MAX.

In this case, valid extents are incorrectly skipped due to the
"if (!tei->last_blocks)" check in __update_extent_tree_range().

This patch fixes the issue by:
1. Reserving ULLONG_MAX as an invalid/deletion marker
2. Limiting allocated_data_blocks to range [0, ULLONG_MAX-1]
3. Using F2FS_EXTENT_AGE_INVALID for deletion scenarios
4. Adjusting overflow age calculation from ULLONG_MAX to (ULLONG_MAX-1)

Reproducer (using a patched kernel with allocated_data_blocks
initialized to ULLONG_MAX - 3 for quick testing):

Step 1: Mount and check initial state
  # dd if=/dev/zero of=/tmp/test.img bs=1M count=100
  # mkfs.f2fs -f /tmp/test.img
  # mkdir -p /mnt/f2fs_test
  # mount -t f2fs -o loop,age_extent_cache /tmp/test.img /mnt/f2fs_test
  # cat /sys/kernel/debug/f2fs/status | grep -A 4 "Block Age"
  Allocated Data Blocks: 18446744073709551612 # ULLONG_MAX - 3
  Inner Struct Count: tree: 1(0), node: 0

Step 2: Create files and write data to trigger overflow
  # touch /mnt/f2fs_test/{1,2,3,4}.txt; sync
  # cat /sys/kernel/debug/f2fs/status | grep -A 4 "Block Age"
  Allocated Data Blocks: 18446744073709551613 # ULLONG_MAX - 2
  Inner Struct Count: tree: 5(0), node: 1

  # dd if=/dev/urandom of=/mnt/f2fs_test/1.txt bs=4K count=1; sync
  # cat /sys/kernel/debug/f2fs/status | grep -A 4 "Block Age"
  Allocated Data Blocks: 18446744073709551614 # ULLONG_MAX - 1
  Inner Struct Count: tree: 5(0), node: 2

  # dd if=/dev/urandom of=/mnt/f2fs_test/2.txt bs=4K count=1; sync
  # cat /sys/kernel/debug/f2fs/status | grep -A 4 "Block Age"
  Allocated Data Blocks: 18446744073709551615 # ULLONG_MAX
  Inner Struct Count: tree: 5(0), node: 3

  # dd if=/dev/urandom of=/mnt/f2fs_test/3.txt bs=4K count=1; sync
  # cat /sys/kernel/debug/f2fs/status | grep -A 4 "Block Age"
  Allocated Data Blocks: 0 # Counter overflowed!
  Inner Struct Count: tree: 5(0), node: 4

Step 3: Trigger the bug - next write should create node but gets skipped
  # dd if=/dev/urandom of=/mnt/f2fs_test/4.txt bs=4K count=1; sync
  # cat /sys/kernel/debug/f2fs/status | grep -A 4 "Block Age"
  Allocated Data Blocks: 1
  Inner Struct Count: tree: 5(0), node: 4

  Expected: node: 5 (new extent node for 4.txt)
  Actual: node: 4 (extent insertion was incorrectly skipped due to
  last_blocks = allocated_data_blocks = 0 in __get_new_block_age)

After this fix, the extent node is correctly inserted and node count
becomes 5 as expected.

Fixes: 71644dff4811 ("f2fs: add block_age-based extent cache")
Cc: stable@kernel.org
Signed-off-by: Xiaole He <hexiaole1994@126.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>

diff --git a/fs/f2fs/extent_cache.c b/fs/f2fs/extent_cache.c
index 33e09c453c703390f79c4294f4a419f299292c6e..0ed84cc065a7eda66c50eae97d70e9ab93de31c3 100644 (file)
--- a/fs/f2fs/extent_cache.c
+++ b/fs/f2fs/extent_cache.c
@@ -808,7 +808,7 @@ static void __update_extent_tree_range(struct inode *inode,
        }
        goto out_read_extent_cache;
 update_age_extent_cache:
-       if (!tei->last_blocks)
+       if (tei->last_blocks == F2FS_EXTENT_AGE_INVALID)
                goto out_read_extent_cache;
 
        __set_extent_info(&ei, fofs, len, 0, false,
@@ -912,7 +912,7 @@ static int __get_new_block_age(struct inode *inode, struct extent_info *ei,
                        cur_age = cur_blocks - tei.last_blocks;
                else
                        /* allocated_data_blocks overflow */
-                       cur_age = ULLONG_MAX - tei.last_blocks + cur_blocks;
+                       cur_age = (ULLONG_MAX - 1) - tei.last_blocks + cur_blocks;
 
                if (tei.age)
                        ei->age = __calculate_block_age(sbi, cur_age, tei.age);
@@ -1114,6 +1114,7 @@ void f2fs_update_age_extent_cache_range(struct dnode_of_data *dn,
        struct extent_info ei = {
                .fofs = fofs,
                .len = len,
+               .last_blocks = F2FS_EXTENT_AGE_INVALID,
        };
 
        if (!__may_extent_tree(dn->inode, EX_BLOCK_AGE))

diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index c85384e8cf4208ef46157eff775935c53199c11c..d9b2777f09edee6b5b246833cbc415785f669480 100644 (file)
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -707,6 +707,12 @@ enum extent_type {
        NR_EXTENT_CACHES,
 };
 
+/*
+ * Reserved value to mark invalid age extents, hence valid block range
+ * from 0 to ULLONG_MAX-1
+ */
+#define F2FS_EXTENT_AGE_INVALID        ULLONG_MAX
+
 struct extent_info {
        unsigned int fofs;              /* start offset in a file */
        unsigned int len;               /* length of the extent */

diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index b45eace879d74b4ecb1131180311c6c565192351..a473cd1fb37d5d5e89157fd73b52ae6526ee0f6e 100644 (file)
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -3863,8 +3863,13 @@ skip_new_segment:
        locate_dirty_segment(sbi, GET_SEGNO(sbi, old_blkaddr));
        locate_dirty_segment(sbi, GET_SEGNO(sbi, *new_blkaddr));
 
-       if (IS_DATASEG(curseg->seg_type))
-               atomic64_inc(&sbi->allocated_data_blocks);
+       if (IS_DATASEG(curseg->seg_type)) {
+               unsigned long long new_val;
+
+               new_val = atomic64_inc_return(&sbi->allocated_data_blocks);
+               if (unlikely(new_val == ULLONG_MAX))
+                       atomic64_set(&sbi->allocated_data_blocks, 0);
+       }
 
        up_write(&sit_i->sentry_lock);