From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
To: linux-kernel@vger.kernel.org
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
stable@vger.kernel.org,
Olga Kornievskaia <olga.kornievskaia@gmail.com>,
Trond Myklebust <trond.myklebust@primarydata.com>,
Anna Schumaker <Anna.Schumaker@Netapp.com>
Subject: [PATCH 4.14 12/52] NFSv4.1: Fix up replays of interrupted requests
Date: Sun, 24 Jun 2018 23:21:05 +0800 [thread overview]
Message-ID: <20180624142745.138767678@linuxfoundation.org> (raw)
In-Reply-To: <20180624142744.234164867@linuxfoundation.org>
4.14-stable review patch. If anyone has any objections, please let me know.
------------------
From: Trond Myklebust <trond.myklebust@primarydata.com>
commit 3be0f80b5fe9c16eca2d538f799b94ca8aa59433 upstream.
If the previous request on a slot was interrupted before it was
processed by the server, then our slot sequence number may be out of whack,
and so we try the next operation using the old sequence number.
The problem with this, is that not all servers check to see that the
client is replaying the same operations as previously when they decide
to go to the replay cache, and so instead of the expected error of
NFS4ERR_SEQ_FALSE_RETRY, we get a replay of the old reply, which could
(if the operations match up) be mistaken by the client for a new reply.
To fix this, we attempt to send a COMPOUND containing only the SEQUENCE op
in order to resync our slot sequence number.
Cc: Olga Kornievskaia <olga.kornievskaia@gmail.com>
[olga.kornievskaia@gmail.com: fix an Oops]
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
fs/nfs/nfs4_fs.h | 2
fs/nfs/nfs4proc.c | 150 +++++++++++++++++++++++++++++++++++++-----------------
2 files changed, 104 insertions(+), 48 deletions(-)
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -465,7 +465,7 @@ extern void nfs_increment_open_seqid(int
extern void nfs_increment_lock_seqid(int status, struct nfs_seqid *seqid);
extern void nfs_release_seqid(struct nfs_seqid *seqid);
extern void nfs_free_seqid(struct nfs_seqid *seqid);
-extern int nfs4_setup_sequence(const struct nfs_client *client,
+extern int nfs4_setup_sequence(struct nfs_client *client,
struct nfs4_sequence_args *args,
struct nfs4_sequence_res *res,
struct rpc_task *task);
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -96,6 +96,10 @@ static int nfs4_do_setattr(struct inode
struct nfs_open_context *ctx, struct nfs4_label *ilabel,
struct nfs4_label *olabel);
#ifdef CONFIG_NFS_V4_1
+static struct rpc_task *_nfs41_proc_sequence(struct nfs_client *clp,
+ struct rpc_cred *cred,
+ struct nfs4_slot *slot,
+ bool is_privileged);
static int nfs41_test_stateid(struct nfs_server *, nfs4_stateid *,
struct rpc_cred *);
static int nfs41_free_stateid(struct nfs_server *, const nfs4_stateid *,
@@ -641,13 +645,14 @@ static int nfs40_sequence_done(struct rp
#if defined(CONFIG_NFS_V4_1)
-static void nfs41_sequence_free_slot(struct nfs4_sequence_res *res)
+static void nfs41_release_slot(struct nfs4_slot *slot)
{
struct nfs4_session *session;
struct nfs4_slot_table *tbl;
- struct nfs4_slot *slot = res->sr_slot;
bool send_new_highest_used_slotid = false;
+ if (!slot)
+ return;
tbl = slot->table;
session = tbl->session;
@@ -673,13 +678,18 @@ static void nfs41_sequence_free_slot(str
send_new_highest_used_slotid = false;
out_unlock:
spin_unlock(&tbl->slot_tbl_lock);
- res->sr_slot = NULL;
if (send_new_highest_used_slotid)
nfs41_notify_server(session->clp);
if (waitqueue_active(&tbl->slot_waitq))
wake_up_all(&tbl->slot_waitq);
}
+static void nfs41_sequence_free_slot(struct nfs4_sequence_res *res)
+{
+ nfs41_release_slot(res->sr_slot);
+ res->sr_slot = NULL;
+}
+
static int nfs41_sequence_process(struct rpc_task *task,
struct nfs4_sequence_res *res)
{
@@ -707,13 +717,6 @@ static int nfs41_sequence_process(struct
/* Check the SEQUENCE operation status */
switch (res->sr_status) {
case 0:
- /* If previous op on slot was interrupted and we reused
- * the seq# and got a reply from the cache, then retry
- */
- if (task->tk_status == -EREMOTEIO && interrupted) {
- ++slot->seq_nr;
- goto retry_nowait;
- }
/* Update the slot's sequence and clientid lease timer */
slot->seq_done = 1;
clp = session->clp;
@@ -747,16 +750,16 @@ static int nfs41_sequence_process(struct
* The slot id we used was probably retired. Try again
* using a different slot id.
*/
+ if (slot->seq_nr < slot->table->target_highest_slotid)
+ goto session_recover;
goto retry_nowait;
case -NFS4ERR_SEQ_MISORDERED:
/*
* Was the last operation on this sequence interrupted?
* If so, retry after bumping the sequence number.
*/
- if (interrupted) {
- ++slot->seq_nr;
- goto retry_nowait;
- }
+ if (interrupted)
+ goto retry_new_seq;
/*
* Could this slot have been previously retired?
* If so, then the server may be expecting seq_nr = 1!
@@ -765,10 +768,11 @@ static int nfs41_sequence_process(struct
slot->seq_nr = 1;
goto retry_nowait;
}
- break;
+ goto session_recover;
case -NFS4ERR_SEQ_FALSE_RETRY:
- ++slot->seq_nr;
- goto retry_nowait;
+ if (interrupted)
+ goto retry_new_seq;
+ goto session_recover;
default:
/* Just update the slot sequence no. */
slot->seq_done = 1;
@@ -778,6 +782,11 @@ out:
dprintk("%s: Error %d free the slot \n", __func__, res->sr_status);
out_noaction:
return ret;
+session_recover:
+ nfs4_schedule_session_recovery(session, res->sr_status);
+ goto retry_nowait;
+retry_new_seq:
+ ++slot->seq_nr;
retry_nowait:
if (rpc_restart_call_prepare(task)) {
nfs41_sequence_free_slot(res);
@@ -854,6 +863,17 @@ static const struct rpc_call_ops nfs41_c
.rpc_call_done = nfs41_call_sync_done,
};
+static void
+nfs4_sequence_process_interrupted(struct nfs_client *client,
+ struct nfs4_slot *slot, struct rpc_cred *cred)
+{
+ struct rpc_task *task;
+
+ task = _nfs41_proc_sequence(client, cred, slot, true);
+ if (!IS_ERR(task))
+ rpc_put_task_async(task);
+}
+
#else /* !CONFIG_NFS_V4_1 */
static int nfs4_sequence_process(struct rpc_task *task, struct nfs4_sequence_res *res)
@@ -874,9 +894,34 @@ int nfs4_sequence_done(struct rpc_task *
}
EXPORT_SYMBOL_GPL(nfs4_sequence_done);
+static void
+nfs4_sequence_process_interrupted(struct nfs_client *client,
+ struct nfs4_slot *slot, struct rpc_cred *cred)
+{
+ WARN_ON_ONCE(1);
+ slot->interrupted = 0;
+}
+
#endif /* !CONFIG_NFS_V4_1 */
-int nfs4_setup_sequence(const struct nfs_client *client,
+static
+void nfs4_sequence_attach_slot(struct nfs4_sequence_args *args,
+ struct nfs4_sequence_res *res,
+ struct nfs4_slot *slot)
+{
+ if (!slot)
+ return;
+ slot->privileged = args->sa_privileged ? 1 : 0;
+ args->sa_slot = slot;
+
+ res->sr_slot = slot;
+ res->sr_timestamp = jiffies;
+ res->sr_status_flags = 0;
+ res->sr_status = 1;
+
+}
+
+int nfs4_setup_sequence(struct nfs_client *client,
struct nfs4_sequence_args *args,
struct nfs4_sequence_res *res,
struct rpc_task *task)
@@ -894,30 +939,29 @@ int nfs4_setup_sequence(const struct nfs
task->tk_timeout = 0;
}
- spin_lock(&tbl->slot_tbl_lock);
- /* The state manager will wait until the slot table is empty */
- if (nfs4_slot_tbl_draining(tbl) && !args->sa_privileged)
- goto out_sleep;
-
- slot = nfs4_alloc_slot(tbl);
- if (IS_ERR(slot)) {
- /* Try again in 1/4 second */
- if (slot == ERR_PTR(-ENOMEM))
- task->tk_timeout = HZ >> 2;
- goto out_sleep;
- }
- spin_unlock(&tbl->slot_tbl_lock);
-
- slot->privileged = args->sa_privileged ? 1 : 0;
- args->sa_slot = slot;
+ for (;;) {
+ spin_lock(&tbl->slot_tbl_lock);
+ /* The state manager will wait until the slot table is empty */
+ if (nfs4_slot_tbl_draining(tbl) && !args->sa_privileged)
+ goto out_sleep;
+
+ slot = nfs4_alloc_slot(tbl);
+ if (IS_ERR(slot)) {
+ /* Try again in 1/4 second */
+ if (slot == ERR_PTR(-ENOMEM))
+ task->tk_timeout = HZ >> 2;
+ goto out_sleep;
+ }
+ spin_unlock(&tbl->slot_tbl_lock);
- res->sr_slot = slot;
- if (session) {
- res->sr_timestamp = jiffies;
- res->sr_status_flags = 0;
- res->sr_status = 1;
+ if (likely(!slot->interrupted))
+ break;
+ nfs4_sequence_process_interrupted(client,
+ slot, task->tk_msg.rpc_cred);
}
+ nfs4_sequence_attach_slot(args, res, slot);
+
trace_nfs4_setup_sequence(session, args);
out_start:
rpc_call_start(task);
@@ -8151,6 +8195,7 @@ static const struct rpc_call_ops nfs41_s
static struct rpc_task *_nfs41_proc_sequence(struct nfs_client *clp,
struct rpc_cred *cred,
+ struct nfs4_slot *slot,
bool is_privileged)
{
struct nfs4_sequence_data *calldata;
@@ -8164,15 +8209,18 @@ static struct rpc_task *_nfs41_proc_sequ
.callback_ops = &nfs41_sequence_ops,
.flags = RPC_TASK_ASYNC | RPC_TASK_TIMEOUT,
};
+ struct rpc_task *ret;
+ ret = ERR_PTR(-EIO);
if (!atomic_inc_not_zero(&clp->cl_count))
- return ERR_PTR(-EIO);
+ goto out_err;
+
+ ret = ERR_PTR(-ENOMEM);
calldata = kzalloc(sizeof(*calldata), GFP_NOFS);
- if (calldata == NULL) {
- nfs_put_client(clp);
- return ERR_PTR(-ENOMEM);
- }
+ if (calldata == NULL)
+ goto out_put_clp;
nfs4_init_sequence(&calldata->args, &calldata->res, 0);
+ nfs4_sequence_attach_slot(&calldata->args, &calldata->res, slot);
if (is_privileged)
nfs4_set_sequence_privileged(&calldata->args);
msg.rpc_argp = &calldata->args;
@@ -8180,7 +8228,15 @@ static struct rpc_task *_nfs41_proc_sequ
calldata->clp = clp;
task_setup_data.callback_data = calldata;
- return rpc_run_task(&task_setup_data);
+ ret = rpc_run_task(&task_setup_data);
+ if (IS_ERR(ret))
+ goto out_err;
+ return ret;
+out_put_clp:
+ nfs_put_client(clp);
+out_err:
+ nfs41_release_slot(slot);
+ return ret;
}
static int nfs41_proc_async_sequence(struct nfs_client *clp, struct rpc_cred *cred, unsigned renew_flags)
@@ -8190,7 +8246,7 @@ static int nfs41_proc_async_sequence(str
if ((renew_flags & NFS4_RENEW_TIMEOUT) == 0)
return -EAGAIN;
- task = _nfs41_proc_sequence(clp, cred, false);
+ task = _nfs41_proc_sequence(clp, cred, NULL, false);
if (IS_ERR(task))
ret = PTR_ERR(task);
else
@@ -8204,7 +8260,7 @@ static int nfs4_proc_sequence(struct nfs
struct rpc_task *task;
int ret;
- task = _nfs41_proc_sequence(clp, cred, true);
+ task = _nfs41_proc_sequence(clp, cred, NULL, true);
if (IS_ERR(task)) {
ret = PTR_ERR(task);
goto out;
next prev parent reply other threads:[~2018-06-24 15:28 UTC|newest]
Thread overview: 54+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-06-24 15:20 [PATCH 4.14 00/52] 4.14.52-stable review Greg Kroah-Hartman
2018-06-24 15:20 ` [PATCH 4.14 01/52] bonding: re-evaluate force_primary when the primary slave name changes Greg Kroah-Hartman
2018-06-24 15:20 ` [PATCH 4.14 03/52] ipv6: allow PMTU exceptions to local routes Greg Kroah-Hartman
2018-06-24 15:20 ` [PATCH 4.14 04/52] net: dsa: add error handling for pskb_trim_rcsum Greg Kroah-Hartman
2018-06-24 15:20 ` [PATCH 4.14 05/52] net/sched: act_simple: fix parsing of TCA_DEF_DATA Greg Kroah-Hartman
2018-06-24 15:20 ` [PATCH 4.14 06/52] tcp: verify the checksum of the first data segment in a new connection Greg Kroah-Hartman
2018-06-24 15:21 ` [PATCH 4.14 07/52] socket: close race condition between sock_close() and sockfs_setattr() Greg Kroah-Hartman
2018-06-24 15:21 ` [PATCH 4.14 08/52] udp: fix rx queue len reported by diag and proc interface Greg Kroah-Hartman
2018-06-24 15:21 ` [PATCH 4.14 09/52] net: in virtio_net_hdr only add VLAN_HLEN to csum_start if payload holds vlan Greg Kroah-Hartman
2018-06-24 15:21 ` [PATCH 4.14 10/52] hv_netvsc: Fix a network regression after ifdown/ifup Greg Kroah-Hartman
2018-06-24 15:21 ` [PATCH 4.14 11/52] tls: fix use-after-free in tls_push_record Greg Kroah-Hartman
2018-06-24 15:21 ` Greg Kroah-Hartman [this message]
2018-06-24 15:21 ` [PATCH 4.14 13/52] ext4: fix hole length detection in ext4_ind_map_blocks() Greg Kroah-Hartman
2018-06-24 15:21 ` [PATCH 4.14 14/52] ext4: update mtime in ext4_punch_hole even if no blocks are released Greg Kroah-Hartman
2018-06-24 15:21 ` [PATCH 4.14 15/52] ext4: do not allow external inodes for inline data Greg Kroah-Hartman
2018-06-24 15:21 ` [PATCH 4.14 16/52] ext4: bubble errors from ext4_find_inline_data_nolock() up to ext4_iget() Greg Kroah-Hartman
2018-06-24 15:21 ` [PATCH 4.14 17/52] ext4: correctly handle a zero-length xattr with a non-zero e_value_offs Greg Kroah-Hartman
2018-06-24 15:21 ` [PATCH 4.14 18/52] ext4: fix fencepost error in check for inode count overflow during resize Greg Kroah-Hartman
2018-06-24 15:21 ` [PATCH 4.14 19/52] driver core: Dont ignore class_dir_create_and_add() failure Greg Kroah-Hartman
2018-06-24 15:21 ` [PATCH 4.14 20/52] Btrfs: fix clone vs chattr NODATASUM race Greg Kroah-Hartman
2018-06-24 15:21 ` [PATCH 4.14 21/52] Btrfs: fix memory and mount leak in btrfs_ioctl_rm_dev_v2() Greg Kroah-Hartman
2018-06-24 15:21 ` [PATCH 4.14 22/52] btrfs: return error value if create_io_em failed in cow_file_range Greg Kroah-Hartman
2018-06-24 15:21 ` [PATCH 4.14 23/52] btrfs: scrub: Dont use inode pages for device replace Greg Kroah-Hartman
2018-06-24 15:21 ` [PATCH 4.14 24/52] ALSA: hda/realtek - Enable mic-mute hotkey for several Lenovo AIOs Greg Kroah-Hartman
2018-06-24 15:21 ` [PATCH 4.14 25/52] ALSA: hda/conexant - Add fixup for HP Z2 G4 workstation Greg Kroah-Hartman
2018-06-24 15:21 ` [PATCH 4.14 26/52] ALSA: hda - Handle kzalloc() failure in snd_hda_attach_pcm_stream() Greg Kroah-Hartman
2018-06-24 15:21 ` [PATCH 4.14 27/52] ALSA: hda: add dock and led support for HP EliteBook 830 G5 Greg Kroah-Hartman
2018-06-24 15:21 ` [PATCH 4.14 28/52] ALSA: hda: add dock and led support for HP ProBook 640 G4 Greg Kroah-Hartman
2018-06-24 15:21 ` [PATCH 4.14 29/52] x86/MCE: Fix stack out-of-bounds write in mce-inject.c: Flags_read() Greg Kroah-Hartman
2018-06-24 15:21 ` [PATCH 4.14 30/52] smb3: fix various xid leaks Greg Kroah-Hartman
2018-06-24 15:21 ` [PATCH 4.14 31/52] smb3: on reconnect set PreviousSessionId field Greg Kroah-Hartman
2018-06-24 15:21 ` [PATCH 4.14 32/52] CIFS: 511c54a2f69195b28afb9dd119f03787b1625bb4 adds a check for session expiry Greg Kroah-Hartman
2018-06-24 15:21 ` [PATCH 4.14 33/52] cifs: For SMB2 security informaion query, check for minimum sized security descriptor instead of sizeof FileAllInformation class Greg Kroah-Hartman
2018-06-24 15:21 ` [PATCH 4.14 34/52] nbd: fix nbd device deletion Greg Kroah-Hartman
2018-06-24 15:21 ` [PATCH 4.14 35/52] nbd: update size when connected Greg Kroah-Hartman
2018-06-24 15:21 ` [PATCH 4.14 36/52] nbd: use bd_set_size when updating disk size Greg Kroah-Hartman
2018-06-24 15:21 ` [PATCH 4.14 37/52] blk-mq: reinit q->tag_set_list entry only after grace period Greg Kroah-Hartman
2018-06-24 15:21 ` [PATCH 4.14 38/52] bdi: Move cgroup bdi_writeback to a dedicated low concurrency workqueue Greg Kroah-Hartman
2018-06-24 15:21 ` [PATCH 4.14 39/52] cpufreq: Fix new policy initialization during limits updates via sysfs Greg Kroah-Hartman
2018-06-24 15:21 ` [PATCH 4.14 40/52] cpufreq: governors: Fix long idle detection logic in load calculation Greg Kroah-Hartman
2018-06-24 15:21 ` [PATCH 4.14 41/52] libata: zpodd: small read overflow in eject_tray() Greg Kroah-Hartman
2018-06-24 15:21 ` [PATCH 4.14 42/52] libata: Drop SanDisk SD7UB3Q*G1001 NOLPM quirk Greg Kroah-Hartman
2018-06-24 15:21 ` [PATCH 4.14 43/52] w1: mxc_w1: Enable clock before calling clk_get_rate() on it Greg Kroah-Hartman
2018-06-24 15:21 ` [PATCH 4.14 44/52] x86/intel_rdt: Enable CMT and MBM on new Skylake stepping Greg Kroah-Hartman
2018-06-24 15:21 ` [PATCH 4.14 45/52] iwlwifi: fw: harden page loading code Greg Kroah-Hartman
2018-06-24 15:21 ` [PATCH 4.14 46/52] orangefs: set i_size on new symlink Greg Kroah-Hartman
2018-06-24 15:21 ` [PATCH 4.14 47/52] orangefs: report attributes_mask and attributes for statx Greg Kroah-Hartman
2018-06-24 15:21 ` [PATCH 4.14 48/52] HID: intel_ish-hid: ipc: register more pm callbacks to support hibernation Greg Kroah-Hartman
2018-06-24 15:21 ` [PATCH 4.14 49/52] HID: wacom: Correct logical maximum Y for 2nd-gen Intuos Pro large Greg Kroah-Hartman
2018-06-24 15:21 ` [PATCH 4.14 50/52] vhost: fix info leak due to uninitialized memory Greg Kroah-Hartman
2018-06-24 15:21 ` [PATCH 4.14 51/52] fs/binfmt_misc.c: do not allow offset overflow Greg Kroah-Hartman
2018-06-24 15:21 ` [PATCH 4.14 52/52] mm, page_alloc: do not break __GFP_THISNODE by zonelist reset Greg Kroah-Hartman
2018-06-25 6:43 ` [PATCH 4.14 00/52] 4.14.52-stable review Naresh Kamboju
2018-06-25 17:19 ` Guenter Roeck
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20180624142745.138767678@linuxfoundation.org \
--to=gregkh@linuxfoundation.org \
--cc=Anna.Schumaker@Netapp.com \
--cc=linux-kernel@vger.kernel.org \
--cc=olga.kornievskaia@gmail.com \
--cc=stable@vger.kernel.org \
--cc=trond.myklebust@primarydata.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).