From 28251d81d723292a6813f93495f2c6c132938945 Mon Sep 17 00:00:00 2001 From: rob-wing <98866084+rob-wing@users.noreply.github.com> Date: Tue, 21 Feb 2023 16:26:33 -0900 Subject: [PATCH] FreeBSD: don't verify recycled vnode for zfs control directory Under certain loads, the following panic is hit: panic: page fault KDB: stack backtrace: #0 0xffffffff805db025 at kdb_backtrace+0x65 #1 0xffffffff8058e86f at vpanic+0x17f #2 0xffffffff8058e6e3 at panic+0x43 #3 0xffffffff808adc15 at trap_fatal+0x385 #4 0xffffffff808adc6f at trap_pfault+0x4f #5 0xffffffff80886da8 at calltrap+0x8 #6 0xffffffff80669186 at vgonel+0x186 #7 0xffffffff80669841 at vgone+0x31 #8 0xffffffff8065806d at vfs_hash_insert+0x26d #9 0xffffffff81a39069 at sfs_vgetx+0x149 #10 0xffffffff81a39c54 at zfsctl_snapdir_lookup+0x1e4 #11 0xffffffff8065a28c at lookup+0x45c #12 0xffffffff806594b9 at namei+0x259 #13 0xffffffff80676a33 at kern_statat+0xf3 #14 0xffffffff8067712f at sys_fstatat+0x2f #15 0xffffffff808ae50c at amd64_syscall+0x10c #16 0xffffffff808876bb at fast_syscall_common+0xf8 The page fault occurs because vgonel() will call VOP_CLOSE() for active vnodes. For this reason, define vop_close for zfsctl_ops_snapshot. While here, define vop_open for consistency. After adding the necessary vop, the bug progresses to the following panic: panic: VERIFY3(vrecycle(vp) == 1) failed (0 == 1) cpuid = 17 KDB: stack backtrace: #0 0xffffffff805e29c5 at kdb_backtrace+0x65 #1 0xffffffff8059620f at vpanic+0x17f #2 0xffffffff81a27f4a at spl_panic+0x3a #3 0xffffffff81a3a4d0 at zfsctl_snapshot_inactive+0x40 #4 0xffffffff8066fdee at vinactivef+0xde #5 0xffffffff80670b8a at vgonel+0x1ea #6 0xffffffff806711e1 at vgone+0x31 #7 0xffffffff8065fa0d at vfs_hash_insert+0x26d #8 0xffffffff81a39069 at sfs_vgetx+0x149 #9 0xffffffff81a39c54 at zfsctl_snapdir_lookup+0x1e4 #10 0xffffffff80661c2c at lookup+0x45c #11 0xffffffff80660e59 at namei+0x259 #12 0xffffffff8067e3d3 at kern_statat+0xf3 #13 0xffffffff8067eacf at sys_fstatat+0x2f #14 0xffffffff808b5ecc at amd64_syscall+0x10c #15 0xffffffff8088f07b at fast_syscall_common+0xf8 This is caused by a race condition that can occur when allocating a new vnode and adding that vnode to the vfs hash. If the newly created vnode loses the race when being inserted into the vfs hash, it will not be recycled as its usecount is greater than zero, hitting the above assertion. Fix this by dropping the assertion. FreeBSD-issue: https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=252700 Reviewed-by: Andriy Gapon Reviewed-by: Mateusz Guzik Reviewed-by: Alek Pinchuk Reviewed-by: Ryan Moeller Signed-off-by: Rob Wing Co-authored-by: Rob Wing Submitted-by: Klara, Inc. Sponsored-by: rsync.net Closes #14501 --- module/os/freebsd/zfs/zfs_ctldir.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/module/os/freebsd/zfs/zfs_ctldir.c b/module/os/freebsd/zfs/zfs_ctldir.c index 42bb7551e9..ca2f4419d1 100644 --- a/module/os/freebsd/zfs/zfs_ctldir.c +++ b/module/os/freebsd/zfs/zfs_ctldir.c @@ -1153,7 +1153,7 @@ zfsctl_snapshot_inactive(struct vop_inactive_args *ap) { vnode_t *vp = ap->a_vp; - VERIFY3S(vrecycle(vp), ==, 1); + vrecycle(vp); return (0); } @@ -1237,6 +1237,8 @@ static struct vop_vector zfsctl_ops_snapshot = { #if __FreeBSD_version >= 1300121 .vop_fplookup_vexec = VOP_EAGAIN, #endif + .vop_open = zfsctl_common_open, + .vop_close = zfsctl_common_close, .vop_inactive = zfsctl_snapshot_inactive, #if __FreeBSD_version >= 1300045 .vop_need_inactive = vop_stdneed_inactive,