ext4: fix BUG in ext4_mb_new_inode_pa() due to overflow

When we calculate the end position of ext4_free_extent, this position may
be exactly where ext4_lblk_t (i.e. uint) overflows. For example, if
ac_g_ex.fe_logical is 4294965248 and ac_orig_goal_len is 2048, then the
computed end is 0x100000000, which is 0. If ac->ac_o_ex.fe_logical is not
the first case of adjusting the best extent, that is, new_bex_end > 0, the
following BUG_ON will be triggered:

=========================================================
kernel BUG at fs/ext4/mballoc.c:5116!
invalid opcode: 0000 [#1] PREEMPT SMP PTI
CPU: 3 PID: 673 Comm: xfs_io Tainted: G E 6.5.0-rc1+ #279
RIP: 0010:ext4_mb_new_inode_pa+0xc5/0x430
Call Trace:
 <TASK>
 ext4_mb_use_best_found+0x203/0x2f0
 ext4_mb_try_best_found+0x163/0x240
 ext4_mb_regular_allocator+0x158/0x1550
 ext4_mb_new_blocks+0x86a/0xe10
 ext4_ext_map_blocks+0xb0c/0x13a0
 ext4_map_blocks+0x2cd/0x8f0
 ext4_iomap_begin+0x27b/0x400
 iomap_iter+0x222/0x3d0
 __iomap_dio_rw+0x243/0xcb0
 iomap_dio_rw+0x16/0x80
=========================================================

A simple reproducer demonstrating the problem:

	mkfs.ext4 -F /dev/sda -b 4096 100M
	mount /dev/sda /tmp/test
	fallocate -l1M /tmp/test/tmp
	fallocate -l10M /tmp/test/file
	fallocate -i -o 1M -l16777203M /tmp/test/file
	fsstress -d /tmp/test -l 0 -n 100000 -p 8 &
	sleep 10 && killall -9 fsstress
	rm -f /tmp/test/tmp
	xfs_io -c "open -ad /tmp/test/file" -c "pwrite -S 0xff 0 8192"

We simply refactor the logic for adjusting the best extent by adding
a temporary ext4_free_extent ex and use extent_logical_end() to avoid
overflow, which also simplifies the code.

Cc: stable@kernel.org # 6.4
Fixes: 93cdf49f6eca ("ext4: Fix best extent lstart adjustment logic in ext4_mb_new_inode_pa()")
Signed-off-by: Baokun Li <libaokun1@huawei.com>
Reviewed-by: Ritesh Harjani (IBM) <ritesh.list@gmail.com>
Link: https://lore.kernel.org/r/20230724121059.11834-3-libaokun1@huawei.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>

diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 4cb13b3e41b3fc56b7a1c633930e698be31be85c..86bce870dc5a3a7b63fbbb09fba5bd80d225c704 100644 (file)
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -5177,8 +5177,11 @@ ext4_mb_new_inode_pa(struct ext4_allocation_context *ac)
        pa = ac->ac_pa;
 
        if (ac->ac_b_ex.fe_len < ac->ac_orig_goal_len) {
-               int new_bex_start;
-               int new_bex_end;
+               struct ext4_free_extent ex = {
+                       .fe_logical = ac->ac_g_ex.fe_logical,
+                       .fe_len = ac->ac_orig_goal_len,
+               };
+               loff_t orig_goal_end = extent_logical_end(sbi, &ex);
 
                /* we can't allocate as much as normalizer wants.
                 * so, found space must get proper lstart
@@ -5197,29 +5200,23 @@ ext4_mb_new_inode_pa(struct ext4_allocation_context *ac)
                 *    still cover original start
                 * 3. Else, keep the best ex at start of original request.
                 */
-               new_bex_end = ac->ac_g_ex.fe_logical +
-                       EXT4_C2B(sbi, ac->ac_orig_goal_len);
-               new_bex_start = new_bex_end - EXT4_C2B(sbi, ac->ac_b_ex.fe_len);
-               if (ac->ac_o_ex.fe_logical >= new_bex_start)
-                       goto adjust_bex;
+               ex.fe_len = ac->ac_b_ex.fe_len;
 
-               new_bex_start = ac->ac_g_ex.fe_logical;
-               new_bex_end =
-                       new_bex_start + EXT4_C2B(sbi, ac->ac_b_ex.fe_len);
-               if (ac->ac_o_ex.fe_logical < new_bex_end)
+               ex.fe_logical = orig_goal_end - EXT4_C2B(sbi, ex.fe_len);
+               if (ac->ac_o_ex.fe_logical >= ex.fe_logical)
                        goto adjust_bex;
 
-               new_bex_start = ac->ac_o_ex.fe_logical;
-               new_bex_end =
-                       new_bex_start + EXT4_C2B(sbi, ac->ac_b_ex.fe_len);
+               ex.fe_logical = ac->ac_g_ex.fe_logical;
+               if (ac->ac_o_ex.fe_logical < extent_logical_end(sbi, &ex))
+                       goto adjust_bex;
 
+               ex.fe_logical = ac->ac_o_ex.fe_logical;
 adjust_bex:
-               ac->ac_b_ex.fe_logical = new_bex_start;
+               ac->ac_b_ex.fe_logical = ex.fe_logical;
 
                BUG_ON(ac->ac_o_ex.fe_logical < ac->ac_b_ex.fe_logical);
                BUG_ON(ac->ac_o_ex.fe_len > ac->ac_b_ex.fe_len);
-               BUG_ON(new_bex_end > (ac->ac_g_ex.fe_logical +
-                                     EXT4_C2B(sbi, ac->ac_orig_goal_len)));
+               BUG_ON(extent_logical_end(sbi, &ex) > orig_goal_end);
        }
 
        pa->pa_lstart = ac->ac_b_ex.fe_logical;