f2fs: fix to avoid panic once fallocation fails for pinfile

[ Upstream commit 48ea8b200414ac69ea96f4c231f5c7ef1fbeffef ]

syzbot reports a f2fs bug as below:

------------[ cut here ]------------
kernel BUG at fs/f2fs/segment.c:2746!
CPU: 0 UID: 0 PID: 5323 Comm: syz.0.0 Not tainted 6.13.0-rc2-syzkaller-00018-g7cb1b4663150 #0
RIP: 0010:get_new_segment fs/f2fs/segment.c:2746 [inline]
RIP: 0010:new_curseg+0x1f52/0x1f70 fs/f2fs/segment.c:2876
Call Trace:
 <TASK>
 __allocate_new_segment+0x1ce/0x940 fs/f2fs/segment.c:3210
 f2fs_allocate_new_section fs/f2fs/segment.c:3224 [inline]
 f2fs_allocate_pinning_section+0xfa/0x4e0 fs/f2fs/segment.c:3238
 f2fs_expand_inode_data+0x696/0xca0 fs/f2fs/file.c:1830
 f2fs_fallocate+0x537/0xa10 fs/f2fs/file.c:1940
 vfs_fallocate+0x569/0x6e0 fs/open.c:327
 do_vfs_ioctl+0x258c/0x2e40 fs/ioctl.c:885
 __do_sys_ioctl fs/ioctl.c:904 [inline]
 __se_sys_ioctl+0x80/0x170 fs/ioctl.c:892
 do_syscall_x64 arch/x86/entry/common.c:52 [inline]
 do_syscall_64+0xf3/0x230 arch/x86/entry/common.c:83
 entry_SYSCALL_64_after_hwframe+0x77/0x7f

Concurrent pinfile allocation may run out of free section, result in
panic in get_new_segment(), let's expand pin_sem lock coverage to
include f2fs_gc(), so that we can make sure to reclaim enough free
space for following allocation.

In addition, do below changes to enhance error path handling:
- call f2fs_bug_on() only in non-pinfile allocation path in
get_new_segment().
- call reset_curseg_fields() to reset all fields of curseg in
new_curseg()

Fixes: f5a53edcf01e ("f2fs: support aligned pinned file")
Reported-by: syzbot+15669ec8c35ddf6c3d43@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/linux-f2fs-devel/675cd64e.050a0220.37aaf.00bb.GAE@google.com
Signed-off-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
Signed-off-by: Rajani Kantha <681739313@139.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 2a108c561e8bc002004e275a1ace0ce9ff52c7cd..6317dd523ecd1ad3f9fc772525baf245ffd485bf 100644 (file)
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -1836,18 +1836,20 @@ static int f2fs_expand_inode_data(struct inode *inode, loff_t offset,
 
                map.m_len = sec_blks;
 next_alloc:
+               f2fs_down_write(&sbi->pin_sem);
+
                if (has_not_enough_free_secs(sbi, 0, f2fs_sb_has_blkzoned(sbi) ?
                        ZONED_PIN_SEC_REQUIRED_COUNT :
                        GET_SEC_FROM_SEG(sbi, overprovision_segments(sbi)))) {
                        f2fs_down_write(&sbi->gc_lock);
                        stat_inc_gc_call_count(sbi, FOREGROUND);
                        err = f2fs_gc(sbi, &gc_control);
-                       if (err && err != -ENODATA)
+                       if (err && err != -ENODATA) {
+                               f2fs_up_write(&sbi->pin_sem);
                                goto out_err;
+                       }
                }
 
-               f2fs_down_write(&sbi->pin_sem);
-
                err = f2fs_allocate_pinning_section(sbi);
                if (err) {
                        f2fs_up_write(&sbi->pin_sem);

diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index e48b5e2efea281bc5aaa0eadb93cada95dbee778..8ac6206110a19458b5b5117ee68f9cec6819d58f 100644 (file)
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -2749,7 +2749,7 @@ find_other_zone:
                                                        MAIN_SECS(sbi));
                if (secno >= MAIN_SECS(sbi)) {
                        ret = -ENOSPC;
-                       f2fs_bug_on(sbi, 1);
+                       f2fs_bug_on(sbi, !pinning);
                        goto out_unlock;
                }
        }
@@ -2795,7 +2795,7 @@ got_it:
 out_unlock:
        spin_unlock(&free_i->segmap_lock);
 
-       if (ret == -ENOSPC)
+       if (ret == -ENOSPC && !pinning)
                f2fs_stop_checkpoint(sbi, false, STOP_CP_REASON_NO_SEGMENT);
        return ret;
 }
@@ -2868,6 +2868,13 @@ static unsigned int __get_next_segno(struct f2fs_sb_info *sbi, int type)
        return curseg->segno;
 }
 
+static void reset_curseg_fields(struct curseg_info *curseg)
+{
+       curseg->inited = false;
+       curseg->segno = NULL_SEGNO;
+       curseg->next_segno = 0;
+}
+
 /*
  * Allocate a current working segment.
  * This function always allocates a free segment in LFS manner.
@@ -2886,7 +2893,7 @@ static int new_curseg(struct f2fs_sb_info *sbi, int type, bool new_sec)
        ret = get_new_segment(sbi, &segno, new_sec, pinning);
        if (ret) {
                if (ret == -ENOSPC)
-                       curseg->segno = NULL_SEGNO;
+                       reset_curseg_fields(curseg);
                return ret;
        }
 
@@ -3640,13 +3647,6 @@ static void f2fs_randomize_chunk(struct f2fs_sb_info *sbi,
                get_random_u32_inclusive(1, sbi->max_fragment_hole);
 }
 
-static void reset_curseg_fields(struct curseg_info *curseg)
-{
-       curseg->inited = false;
-       curseg->segno = NULL_SEGNO;
-       curseg->next_segno = 0;
-}
-
 int f2fs_allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
                block_t old_blkaddr, block_t *new_blkaddr,
                struct f2fs_summary *sum, int type,