From: Baokun Li libaokun1@huawei.com

stable inclusion from stable-v6.6.36 commit 677ff4589f1501578fa903a25bb14831d0607992 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IAD018 CVE: CVE-2024-40955

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

commit 13df4d44a3aaabe61cd01d277b6ee23ead2a5206 upstream.

We can trigger a slab-out-of-bounds with the following commands:

mkfs.ext4 -F /dev/$disk 10G mount /dev/$disk /tmp/test echo 2147483647 > /sys/fs/ext4/$disk/mb_group_prealloc echo test > /tmp/test/file && sync

================================================================== BUG: KASAN: slab-out-of-bounds in ext4_mb_find_good_group_avg_frag_lists+0x8a/0x200 [ext4] Read of size 8 at addr ffff888121b9d0f0 by task kworker/u2:0/11 CPU: 0 PID: 11 Comm: kworker/u2:0 Tainted: GL 6.7.0-next-20240118 #521 Call Trace: dump_stack_lvl+0x2c/0x50 kasan_report+0xb6/0xf0 ext4_mb_find_good_group_avg_frag_lists+0x8a/0x200 [ext4] ext4_mb_regular_allocator+0x19e9/0x2370 [ext4] ext4_mb_new_blocks+0x88a/0x1370 [ext4] ext4_ext_map_blocks+0x14f7/0x2390 [ext4] ext4_map_blocks+0x569/0xea0 [ext4] ext4_do_writepages+0x10f6/0x1bc0 [ext4] [...] ==================================================================

The flow of issue triggering is as follows:

// Set s_mb_group_prealloc to 2147483647 via sysfs ext4_mb_new_blocks ext4_mb_normalize_request ext4_mb_normalize_group_request ac->ac_g_ex.fe_len = EXT4_SB(sb)->s_mb_group_prealloc ext4_mb_regular_allocator ext4_mb_choose_next_group ext4_mb_choose_next_group_best_avail mb_avg_fragment_size_order order = fls(len) - 2 = 29 ext4_mb_find_good_group_avg_frag_lists frag_list = &sbi->s_mb_avg_fragment_size[order] if (list_empty(frag_list)) // Trigger SOOB!

At 4k block size, the length of the s_mb_avg_fragment_size list is 14, but an oversized s_mb_group_prealloc is set, causing slab-out-of-bounds to be triggered by an attempt to access an element at index 29.

Add a new attr_id attr_clusters_in_group with values in the range [0, sbi->s_clusters_per_group] and declare mb_group_prealloc as that type to fix the issue. In addition avoid returning an order from mb_avg_fragment_size_order() greater than MB_NUM_ORDERS(sb) and reduce some useless loops.

Fixes: 7e170922f06b ("ext4: Add allocation criteria 1.5 (CR1_5)") CC: stable@vger.kernel.org Signed-off-by: Baokun Li libaokun1@huawei.com Reviewed-by: Jan Kara jack@suse.cz Reviewed-by: Ojaswin Mujoo ojaswin@linux.ibm.com Link: https://lore.kernel.org/r/20240319113325.3110393-5-libaokun1@huawei.com Signed-off-by: Theodore Ts'o tytso@mit.edu Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Yifan Qiao qiaoyifan4@huawei.com --- fs/ext4/mballoc.c | 4 ++++ fs/ext4/sysfs.c | 13 ++++++++++++- 2 files changed, 16 insertions(+), 1 deletion(-)

diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index f6e02978d0e6..9a65cdcc6417 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -834,6 +834,8 @@ static int mb_avg_fragment_size_order(struct super_block *sb, ext4_grpblk_t len) return 0; if (order == MB_NUM_ORDERS(sb)) order--; + if (WARN_ON_ONCE(order > MB_NUM_ORDERS(sb))) + order = MB_NUM_ORDERS(sb) - 1; return order; }

@@ -1011,6 +1013,8 @@ static void ext4_mb_choose_next_group_best_avail(struct ext4_allocation_context * goal length. */ order = fls(ac->ac_g_ex.fe_len) - 1; + if (WARN_ON_ONCE(order - 1 > MB_NUM_ORDERS(ac->ac_sb))) + order = MB_NUM_ORDERS(ac->ac_sb); min_order = order - sbi->s_mb_best_avail_max_trim_order; if (min_order < 0) min_order = 0; diff --git a/fs/ext4/sysfs.c b/fs/ext4/sysfs.c index ca820620b974..63cbda3700ea 100644 --- a/fs/ext4/sysfs.c +++ b/fs/ext4/sysfs.c @@ -29,6 +29,7 @@ typedef enum { attr_trigger_test_error, attr_first_error_time, attr_last_error_time, + attr_clusters_in_group, attr_feature, attr_pointer_ui, attr_pointer_ul, @@ -207,13 +208,14 @@ EXT4_ATTR_FUNC(sra_exceeded_retry_limit, 0444);

EXT4_ATTR_OFFSET(inode_readahead_blks, 0644, inode_readahead, ext4_sb_info, s_inode_readahead_blks); +EXT4_ATTR_OFFSET(mb_group_prealloc, 0644, clusters_in_group, + ext4_sb_info, s_mb_group_prealloc); EXT4_RW_ATTR_SBI_UI(inode_goal, s_inode_goal); EXT4_RW_ATTR_SBI_UI(mb_stats, s_mb_stats); EXT4_RW_ATTR_SBI_UI(mb_max_to_scan, s_mb_max_to_scan); EXT4_RW_ATTR_SBI_UI(mb_min_to_scan, s_mb_min_to_scan); EXT4_RW_ATTR_SBI_UI(mb_order2_req, s_mb_order2_reqs); EXT4_RW_ATTR_SBI_UI(mb_stream_req, s_mb_stream_request); -EXT4_RW_ATTR_SBI_UI(mb_group_prealloc, s_mb_group_prealloc); EXT4_RW_ATTR_SBI_UI(mb_max_linear_groups, s_mb_max_linear_groups); EXT4_RW_ATTR_SBI_UI(extent_max_zeroout_kb, s_extent_max_zeroout_kb); EXT4_ATTR(trigger_fs_error, 0200, trigger_test_error); @@ -392,6 +394,7 @@ static ssize_t ext4_attr_show(struct kobject *kobj, (unsigned long long) percpu_counter_sum(&sbi->s_sra_exceeded_retry_limit)); case attr_inode_readahead: + case attr_clusters_in_group: case attr_pointer_ui: if (!ptr) return 0; @@ -469,6 +472,14 @@ static ssize_t ext4_attr_store(struct kobject *kobj, else *((unsigned int *) ptr) = t; return len; + case attr_clusters_in_group: + ret = kstrtouint(skip_spaces(buf), 0, &t); + if (ret) + return ret; + if (t > sbi->s_clusters_per_group) + return -EINVAL; + *((unsigned int *) ptr) = t; + return len; case attr_pointer_ul: if (!ptr) return 0;