nfsd4: fix race on client shutdown
J. Bruce Fields [Thu, 7 Mar 2013 22:26:18 +0000 (17:26 -0500)]
Dropping the session's reference count after the client's means we leave
a window where the session's se_client pointer is NULL.  An xpt_user
callback that encounters such a session may then crash:

[  303.956011] BUG: unable to handle kernel NULL pointer dereference at 0000000000000318
[  303.959061] IP: [<ffffffff81481a8e>] _raw_spin_lock+0x1e/0x40
[  303.959061] PGD 37811067 PUD 3d498067 PMD 0
[  303.959061] Oops: 0002 [#8] PREEMPT SMP
[  303.959061] Modules linked in: md5 nfsd auth_rpcgss nfs_acl snd_hda_intel snd_hda_codec snd_hwdep snd_pcm snd_page_alloc microcode psmouse snd_timer serio_raw pcspkr evdev snd soundcore i2c_piix4 i2c_core intel_agp intel_gtt processor button nfs lockd sunrpc fscache ata_generic pata_acpi ata_piix uhci_hcd libata btrfs usbcore usb_common crc32c scsi_mod libcrc32c zlib_deflate floppy virtio_balloon virtio_net virtio_pci virtio_blk virtio_ring virtio
[  303.959061] CPU 0
[  303.959061] Pid: 264, comm: nfsd Tainted: G      D      3.8.0-ARCH+ #156 Bochs Bochs
[  303.959061] RIP: 0010:[<ffffffff81481a8e>]  [<ffffffff81481a8e>] _raw_spin_lock+0x1e/0x40
[  303.959061] RSP: 0018:ffff880037877dd8  EFLAGS: 00010202
[  303.959061] RAX: 0000000000000100 RBX: ffff880037a2b698 RCX: ffff88003d879278
[  303.959061] RDX: ffff88003d879278 RSI: dead000000100100 RDI: 0000000000000318
[  303.959061] RBP: ffff880037877dd8 R08: ffff88003c5a0f00 R09: 0000000000000002
[  303.959061] R10: 0000000000000001 R11: 0000000000000000 R12: 0000000000000000
[  303.959061] R13: 0000000000000318 R14: ffff880037a2b680 R15: ffff88003c1cbe00
[  303.959061] FS:  0000000000000000(0000) GS:ffff88003fc00000(0000) knlGS:0000000000000000
[  303.959061] CS:  0010 DS: 0000 ES: 0000 CR0: 000000008005003b
[  303.959061] CR2: 0000000000000318 CR3: 000000003d49c000 CR4: 00000000000006f0
[  303.959061] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[  303.959061] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400
[  303.959061] Process nfsd (pid: 264, threadinfo ffff880037876000, task ffff88003c1fd0a0)
[  303.959061] Stack:
[  303.959061]  ffff880037877e08 ffffffffa03772ec ffff88003d879000 ffff88003d879278
[  303.959061]  ffff88003d879080 0000000000000000 ffff880037877e38 ffffffffa0222a1f
[  303.959061]  0000000000107ac0 ffff88003c22e000 ffff88003d879000 ffff88003c1cbe00
[  303.959061] Call Trace:
[  303.959061]  [<ffffffffa03772ec>] nfsd4_conn_lost+0x3c/0xa0 [nfsd]
[  303.959061]  [<ffffffffa0222a1f>] svc_delete_xprt+0x10f/0x180 [sunrpc]
[  303.959061]  [<ffffffffa0223d96>] svc_recv+0xe6/0x580 [sunrpc]
[  303.959061]  [<ffffffffa03587c5>] nfsd+0xb5/0x140 [nfsd]
[  303.959061]  [<ffffffffa0358710>] ? nfsd_destroy+0x90/0x90 [nfsd]
[  303.959061]  [<ffffffff8107ae00>] kthread+0xc0/0xd0
[  303.959061]  [<ffffffff81010000>] ? perf_trace_xen_mmu_set_pte_at+0x50/0x100
[  303.959061]  [<ffffffff8107ad40>] ? kthread_freezable_should_stop+0x70/0x70
[  303.959061]  [<ffffffff814898ec>] ret_from_fork+0x7c/0xb0
[  303.959061]  [<ffffffff8107ad40>] ? kthread_freezable_should_stop+0x70/0x70
[  303.959061] Code: ff ff 5d c3 90 90 90 90 90 90 90 90 90 0f 1f 44 00 00 55 65 48 8b 04 25 f0 c6 00 00 48 89 e5 83 80 44 e0 ff ff 01 b8 00 01 00 00 <3e> 66 0f c1 07 0f b6 d4 38 c2 74 0f 66 0f 1f 44 00 00 f3 90 0f
[  303.959061] RIP  [<ffffffff81481a8e>] _raw_spin_lock+0x1e/0x40
[  303.959061]  RSP <ffff880037877dd8>
[  303.959061] CR2: 0000000000000318
[  304.001218] ---[ end trace 2d809cd4a7931f5a ]---
[  304.001903] note: nfsd[264] exited with preempt_count 2

Reported-by: Bryan Schumaker <bjschuma@netapp.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>

fs/nfsd/nfs4state.c
fs/nfsd/nfs4xdr.c
fs/nfsd/state.h

index 2e27430..3e5cbfe 100644 (file)
@@ -864,7 +864,7 @@ static void free_session(struct kref *kref)
        __free_session(ses);
 }
 
-void nfsd4_put_session(struct nfsd4_session *ses)
+static void nfsd4_put_session(struct nfsd4_session *ses)
 {
        struct nfsd_net *nn = net_generic(ses->se_client->net, nfsd_net_id);
 
@@ -1057,12 +1057,16 @@ release_session_client(struct nfsd4_session *session)
        struct nfs4_client *clp = session->se_client;
        struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
 
+       nfsd4_put_session(session);
        if (!atomic_dec_and_lock(&clp->cl_refcount, &nn->client_lock))
                return;
-       if (is_client_expired(clp)) {
+       /*
+        * At this point we also know all sessions have refcnt 1,
+        * so free_client will delete them all if necessary:
+        */
+       if (is_client_expired(clp))
                free_client(clp);
-               session->se_client = NULL;
-       } else
+       else
                renew_client_locked(clp);
        spin_unlock(&nn->client_lock);
 }
index 229b3ac..9b02b66 100644 (file)
@@ -3685,7 +3685,6 @@ nfs4svc_encode_compoundres(struct svc_rqst *rqstp, __be32 *p, struct nfsd4_compo
                }
                /* Renew the clientid on success and on replay */
                release_session_client(cs->session);
-               nfsd4_put_session(cs->session);
        }
        return 1;
 }
index 1a8c739..327552b 100644 (file)
@@ -209,8 +209,6 @@ struct nfsd4_session {
        struct nfsd4_slot       *se_slots[];    /* forward channel slots */
 };
 
-extern void nfsd4_put_session(struct nfsd4_session *ses);
-
 /* formatted contents of nfs4_sessionid */
 struct nfsd4_sessionid {
        clientid_t      clientid;