From: Trond Myklebust <trondmy@gmail.com>
To: linux-nfs@vger.kernel.org
Subject: [PATCH 05/19] NFSv4.2: Add client support for the generic 'layouterror' RPC call
Date: Fri, 1 Mar 2019 14:24:41 -0500 [thread overview]
Message-ID: <20190301192455.104943-6-trond.myklebust@hammerspace.com> (raw)
In-Reply-To: <20190301192455.104943-5-trond.myklebust@hammerspace.com>
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
fs/nfs/nfs42.h | 3 +
fs/nfs/nfs42proc.c | 164 ++++++++++++++++++++++++++++++++++++++
fs/nfs/nfs42xdr.c | 99 +++++++++++++++++++++++
fs/nfs/nfs4proc.c | 3 +-
fs/nfs/nfs4xdr.c | 1 +
include/linux/nfs4.h | 1 +
include/linux/nfs_fs_sb.h | 1 +
include/linux/nfs_xdr.h | 35 ++++++++
8 files changed, 306 insertions(+), 1 deletion(-)
diff --git a/fs/nfs/nfs42.h b/fs/nfs/nfs42.h
index 19ec38f85ce0..901cca7542f9 100644
--- a/fs/nfs/nfs42.h
+++ b/fs/nfs/nfs42.h
@@ -20,5 +20,8 @@ loff_t nfs42_proc_llseek(struct file *, loff_t, int);
int nfs42_proc_layoutstats_generic(struct nfs_server *,
struct nfs42_layoutstat_data *);
int nfs42_proc_clone(struct file *, struct file *, loff_t, loff_t, loff_t);
+int nfs42_proc_layouterror(struct pnfs_layout_segment *lseg,
+ const struct nfs42_layout_error *errors,
+ size_t n);
#endif /* __LINUX_FS_NFS_NFS4_2_H */
diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c
index fed06fd9998d..ff6f85fb676b 100644
--- a/fs/nfs/nfs42proc.c
+++ b/fs/nfs/nfs42proc.c
@@ -672,6 +672,170 @@ int nfs42_proc_layoutstats_generic(struct nfs_server *server,
return 0;
}
+static struct nfs42_layouterror_data *
+nfs42_alloc_layouterror_data(struct pnfs_layout_segment *lseg, gfp_t gfp_flags)
+{
+ struct nfs42_layouterror_data *data;
+ struct inode *inode = lseg->pls_layout->plh_inode;
+
+ data = kzalloc(sizeof(*data), gfp_flags);
+ if (data) {
+ data->args.inode = data->inode = nfs_igrab_and_active(inode);
+ if (data->inode) {
+ data->lseg = pnfs_get_lseg(lseg);
+ if (data->lseg)
+ return data;
+ nfs_iput_and_deactive(data->inode);
+ }
+ kfree(data);
+ }
+ return NULL;
+}
+
+static void
+nfs42_free_layouterror_data(struct nfs42_layouterror_data *data)
+{
+ pnfs_put_lseg(data->lseg);
+ nfs_iput_and_deactive(data->inode);
+ kfree(data);
+}
+
+static void
+nfs42_layouterror_prepare(struct rpc_task *task, void *calldata)
+{
+ struct nfs42_layouterror_data *data = calldata;
+ struct inode *inode = data->inode;
+ struct nfs_server *server = NFS_SERVER(inode);
+ struct pnfs_layout_hdr *lo = data->lseg->pls_layout;
+ unsigned i;
+
+ spin_lock(&inode->i_lock);
+ if (!pnfs_layout_is_valid(lo)) {
+ spin_unlock(&inode->i_lock);
+ rpc_exit(task, 0);
+ return;
+ }
+ for (i = 0; i < data->args.num_errors; i++)
+ nfs4_stateid_copy(&data->args.errors[i].stateid,
+ &lo->plh_stateid);
+ spin_unlock(&inode->i_lock);
+ nfs4_setup_sequence(server->nfs_client, &data->args.seq_args,
+ &data->res.seq_res, task);
+}
+
+static void
+nfs42_layouterror_done(struct rpc_task *task, void *calldata)
+{
+ struct nfs42_layouterror_data *data = calldata;
+ struct inode *inode = data->inode;
+ struct pnfs_layout_hdr *lo = data->lseg->pls_layout;
+
+ if (!nfs4_sequence_done(task, &data->res.seq_res))
+ return;
+
+ switch (task->tk_status) {
+ case 0:
+ break;
+ case -NFS4ERR_BADHANDLE:
+ case -ESTALE:
+ pnfs_destroy_layout(NFS_I(inode));
+ break;
+ case -NFS4ERR_EXPIRED:
+ case -NFS4ERR_ADMIN_REVOKED:
+ case -NFS4ERR_DELEG_REVOKED:
+ case -NFS4ERR_STALE_STATEID:
+ case -NFS4ERR_BAD_STATEID:
+ spin_lock(&inode->i_lock);
+ if (pnfs_layout_is_valid(lo) &&
+ nfs4_stateid_match(&data->args.errors[0].stateid,
+ &lo->plh_stateid)) {
+ LIST_HEAD(head);
+
+ /*
+ * Mark the bad layout state as invalid, then retry
+ * with the current stateid.
+ */
+ pnfs_mark_layout_stateid_invalid(lo, &head);
+ spin_unlock(&inode->i_lock);
+ pnfs_free_lseg_list(&head);
+ nfs_commit_inode(inode, 0);
+ } else
+ spin_unlock(&inode->i_lock);
+ break;
+ case -NFS4ERR_OLD_STATEID:
+ spin_lock(&inode->i_lock);
+ if (pnfs_layout_is_valid(lo) &&
+ nfs4_stateid_match_other(&data->args.errors[0].stateid,
+ &lo->plh_stateid)) {
+ /* Do we need to delay before resending? */
+ if (!nfs4_stateid_is_newer(&lo->plh_stateid,
+ &data->args.errors[0].stateid))
+ rpc_delay(task, HZ);
+ rpc_restart_call_prepare(task);
+ }
+ spin_unlock(&inode->i_lock);
+ break;
+ case -ENOTSUPP:
+ case -EOPNOTSUPP:
+ NFS_SERVER(inode)->caps &= ~NFS_CAP_LAYOUTERROR;
+ }
+}
+
+static void
+nfs42_layouterror_release(void *calldata)
+{
+ struct nfs42_layouterror_data *data = calldata;
+
+ nfs42_free_layouterror_data(data);
+}
+
+static const struct rpc_call_ops nfs42_layouterror_ops = {
+ .rpc_call_prepare = nfs42_layouterror_prepare,
+ .rpc_call_done = nfs42_layouterror_done,
+ .rpc_release = nfs42_layouterror_release,
+};
+
+int nfs42_proc_layouterror(struct pnfs_layout_segment *lseg,
+ const struct nfs42_layout_error *errors, size_t n)
+{
+ struct inode *inode = lseg->pls_layout->plh_inode;
+ struct nfs42_layouterror_data *data;
+ struct rpc_task *task;
+ struct rpc_message msg = {
+ .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_LAYOUTERROR],
+ };
+ struct rpc_task_setup task_setup = {
+ .rpc_message = &msg,
+ .callback_ops = &nfs42_layouterror_ops,
+ .flags = RPC_TASK_ASYNC,
+ };
+ unsigned int i;
+
+ if (!nfs_server_capable(inode, NFS_CAP_LAYOUTERROR))
+ return -EOPNOTSUPP;
+ if (n > NFS42_LAYOUTERROR_MAX)
+ return -EINVAL;
+ data = nfs42_alloc_layouterror_data(lseg, GFP_NOFS);
+ if (!data)
+ return -ENOMEM;
+ for (i = 0; i < n; i++) {
+ data->args.errors[i] = errors[i];
+ data->args.num_errors++;
+ data->res.num_errors++;
+ }
+ msg.rpc_argp = &data->args;
+ msg.rpc_resp = &data->res;
+ task_setup.callback_data = data;
+ task_setup.rpc_client = NFS_SERVER(inode)->client;
+ nfs4_init_sequence(&data->args.seq_args, &data->res.seq_res, 0, 0);
+ task = rpc_run_task(&task_setup);
+ if (IS_ERR(task))
+ return PTR_ERR(task);
+ rpc_put_task(task);
+ return 0;
+}
+EXPORT_SYMBOL_GPL(nfs42_proc_layouterror);
+
static int _nfs42_proc_clone(struct rpc_message *msg, struct file *src_f,
struct file *dst_f, struct nfs_lock_context *src_lock,
struct nfs_lock_context *dst_lock, loff_t src_offset,
diff --git a/fs/nfs/nfs42xdr.c b/fs/nfs/nfs42xdr.c
index 22b3425df08f..fa5e796697fb 100644
--- a/fs/nfs/nfs42xdr.c
+++ b/fs/nfs/nfs42xdr.c
@@ -51,6 +51,15 @@
1 /* opaque devaddr4 length */ + \
XDR_QUADLEN(PNFS_LAYOUTSTATS_MAXSIZE))
#define decode_layoutstats_maxsz (op_decode_hdr_maxsz)
+#define encode_device_error_maxsz (XDR_QUADLEN(NFS4_DEVICEID4_SIZE) + \
+ 1 /* status */ + 1 /* opnum */)
+#define encode_layouterror_maxsz (op_decode_hdr_maxsz + \
+ 2 /* offset */ + \
+ 2 /* length */ + \
+ encode_stateid_maxsz + \
+ 1 /* Array size */ + \
+ encode_device_error_maxsz)
+#define decode_layouterror_maxsz (op_decode_hdr_maxsz)
#define encode_clone_maxsz (encode_stateid_maxsz + \
encode_stateid_maxsz + \
2 /* src offset */ + \
@@ -106,6 +115,16 @@
decode_sequence_maxsz + \
decode_putfh_maxsz + \
PNFS_LAYOUTSTATS_MAXDEV * decode_layoutstats_maxsz)
+#define NFS4_enc_layouterror_sz (compound_encode_hdr_maxsz + \
+ encode_sequence_maxsz + \
+ encode_putfh_maxsz + \
+ NFS42_LAYOUTERROR_MAX * \
+ encode_layouterror_maxsz)
+#define NFS4_dec_layouterror_sz (compound_decode_hdr_maxsz + \
+ decode_sequence_maxsz + \
+ decode_putfh_maxsz + \
+ NFS42_LAYOUTERROR_MAX * \
+ decode_layouterror_maxsz)
#define NFS4_enc_clone_sz (compound_encode_hdr_maxsz + \
encode_sequence_maxsz + \
encode_putfh_maxsz + \
@@ -223,6 +242,34 @@ static void encode_clone(struct xdr_stream *xdr,
xdr_encode_hyper(p, args->count);
}
+static void encode_device_error(struct xdr_stream *xdr,
+ const struct nfs42_device_error *error)
+{
+ __be32 *p;
+
+ p = reserve_space(xdr, NFS4_DEVICEID4_SIZE + 2*4);
+ p = xdr_encode_opaque_fixed(p, error->dev_id.data,
+ NFS4_DEVICEID4_SIZE);
+ *p++ = cpu_to_be32(error->status);
+ *p = cpu_to_be32(error->opnum);
+}
+
+static void encode_layouterror(struct xdr_stream *xdr,
+ const struct nfs42_layout_error *args,
+ struct compound_hdr *hdr)
+{
+ __be32 *p;
+
+ encode_op_hdr(xdr, OP_LAYOUTERROR, decode_layouterror_maxsz, hdr);
+ p = reserve_space(xdr, 8 + 8);
+ p = xdr_encode_hyper(p, args->offset);
+ p = xdr_encode_hyper(p, args->length);
+ encode_nfs4_stateid(xdr, &args->stateid);
+ p = reserve_space(xdr, 4);
+ *p = cpu_to_be32(1);
+ encode_device_error(xdr, &args->errors[0]);
+}
+
/*
* Encode ALLOCATE request
*/
@@ -381,6 +428,27 @@ static void nfs4_xdr_enc_clone(struct rpc_rqst *req,
encode_nops(&hdr);
}
+/*
+ * Encode LAYOUTERROR request
+ */
+static void nfs4_xdr_enc_layouterror(struct rpc_rqst *req,
+ struct xdr_stream *xdr,
+ const void *data)
+{
+ const struct nfs42_layouterror_args *args = data;
+ struct compound_hdr hdr = {
+ .minorversion = nfs4_xdr_minorversion(&args->seq_args),
+ };
+ int i;
+
+ encode_compound_hdr(xdr, req, &hdr);
+ encode_sequence(xdr, &args->seq_args, &hdr);
+ encode_putfh(xdr, NFS_FH(args->inode), &hdr);
+ for (i = 0; i < args->num_errors; i++)
+ encode_layouterror(xdr, &args->errors[i], &hdr);
+ encode_nops(&hdr);
+}
+
static int decode_allocate(struct xdr_stream *xdr, struct nfs42_falloc_res *res)
{
return decode_op_hdr(xdr, OP_ALLOCATE);
@@ -484,6 +552,11 @@ static int decode_clone(struct xdr_stream *xdr)
return decode_op_hdr(xdr, OP_CLONE);
}
+static int decode_layouterror(struct xdr_stream *xdr)
+{
+ return decode_op_hdr(xdr, OP_LAYOUTERROR);
+}
+
/*
* Decode ALLOCATE request
*/
@@ -693,4 +766,30 @@ static int nfs4_xdr_dec_clone(struct rpc_rqst *rqstp,
return status;
}
+/*
+ * Decode LAYOUTERROR request
+ */
+static int nfs4_xdr_dec_layouterror(struct rpc_rqst *rqstp,
+ struct xdr_stream *xdr,
+ void *data)
+{
+ struct nfs42_layouterror_res *res = data;
+ struct compound_hdr hdr;
+ int status, i;
+
+ status = decode_compound_hdr(xdr, &hdr);
+ if (status)
+ goto out;
+ status = decode_sequence(xdr, &res->seq_res, rqstp);
+ if (status)
+ goto out;
+ status = decode_putfh(xdr);
+
+ for (i = 0; i < res->num_errors && status == 0; i++)
+ status = decode_layouterror(xdr);
+out:
+ res->rpc_status = status;
+ return status;
+}
+
#endif /* __LINUX_FS_NFS_NFS4_2XDR_H */
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 5b980246b035..73889ea7d196 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -9690,7 +9690,8 @@ static const struct nfs4_minor_version_ops nfs_v4_2_minor_ops = {
| NFS_CAP_DEALLOCATE
| NFS_CAP_SEEK
| NFS_CAP_LAYOUTSTATS
- | NFS_CAP_CLONE,
+ | NFS_CAP_CLONE
+ | NFS_CAP_LAYOUTERROR,
.init_client = nfs41_init_client,
.shutdown_client = nfs41_shutdown_client,
.match_stateid = nfs41_match_stateid,
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 6d9d5e2f6308..cfcabc33e24d 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -7572,6 +7572,7 @@ const struct rpc_procinfo nfs4_procedures[] = {
PROC42(COPY, enc_copy, dec_copy),
PROC42(OFFLOAD_CANCEL, enc_offload_cancel, dec_offload_cancel),
PROC(LOOKUPP, enc_lookupp, dec_lookupp),
+ PROC42(LAYOUTERROR, enc_layouterror, dec_layouterror),
};
static unsigned int nfs_version4_counts[ARRAY_SIZE(nfs4_procedures)];
diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index 1b06f0b28453..22494d170619 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -538,6 +538,7 @@ enum {
NFSPROC4_CLNT_OFFLOAD_CANCEL,
NFSPROC4_CLNT_LOOKUPP,
+ NFSPROC4_CLNT_LAYOUTERROR,
};
/* nfs41 types */
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index 6aa8cc83c3b6..c827d31298cc 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -261,5 +261,6 @@ struct nfs_server {
#define NFS_CAP_CLONE (1U << 23)
#define NFS_CAP_COPY (1U << 24)
#define NFS_CAP_OFFLOAD_CANCEL (1U << 25)
+#define NFS_CAP_LAYOUTERROR (1U << 26)
#endif
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index b4bd2bf5f585..9b8324ec08f3 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -383,6 +383,41 @@ struct nfs42_layoutstat_data {
struct nfs42_layoutstat_res res;
};
+struct nfs42_device_error {
+ struct nfs4_deviceid dev_id;
+ int status;
+ enum nfs_opnum4 opnum;
+};
+
+struct nfs42_layout_error {
+ __u64 offset;
+ __u64 length;
+ nfs4_stateid stateid;
+ struct nfs42_device_error errors[1];
+};
+
+#define NFS42_LAYOUTERROR_MAX 5
+
+struct nfs42_layouterror_args {
+ struct nfs4_sequence_args seq_args;
+ struct inode *inode;
+ unsigned int num_errors;
+ struct nfs42_layout_error errors[NFS42_LAYOUTERROR_MAX];
+};
+
+struct nfs42_layouterror_res {
+ struct nfs4_sequence_res seq_res;
+ unsigned int num_errors;
+ int rpc_status;
+};
+
+struct nfs42_layouterror_data {
+ struct nfs42_layouterror_args args;
+ struct nfs42_layouterror_res res;
+ struct inode *inode;
+ struct pnfs_layout_segment *lseg;
+};
+
struct nfs42_clone_args {
struct nfs4_sequence_args seq_args;
struct nfs_fh *src_fh;
--
2.20.1
next prev parent reply other threads:[~2019-03-01 19:27 UTC|newest]
Thread overview: 21+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-03-01 19:24 [PATCH 00/19] Updates for pNFS/flexfiles Trond Myklebust
2019-03-01 19:24 ` [PATCH 01/19] NFSv4/flexfiles: Fix invalid deref in FF_LAYOUT_DEVID_NODE() Trond Myklebust
2019-03-01 19:24 ` [PATCH 02/19] NFS/flexfiles: Fix up sparse RCU annotations Trond Myklebust
2019-03-01 19:24 ` [PATCH 03/19] NFSv4/pnfs: Fix barriers in nfs4_mark_deviceid_unavailable() Trond Myklebust
2019-03-01 19:24 ` [PATCH 04/19] NFSv4/flexfiles: Abort I/O early if the layout segment was invalidated Trond Myklebust
2019-03-01 19:24 ` Trond Myklebust [this message]
2019-03-01 19:24 ` [PATCH 06/19] NFS/flexfiles: Send LAYOUTERROR when failing over mirrored reads Trond Myklebust
2019-03-01 19:24 ` [PATCH 07/19] NFSv4: Handle early exit in layoutget by returning an error Trond Myklebust
2019-03-01 19:24 ` [PATCH 08/19] NFS/flexfiles: refactor calls to fs4_ff_layout_prepare_ds() Trond Myklebust
2019-03-01 19:24 ` [PATCH 09/19] NFS/flexfiles: Avoid unnecessary layout invalidations Trond Myklebust
2019-03-01 19:24 ` [PATCH 10/19] NFS/flexfiles: Remove bogus checks for invalid deviceids Trond Myklebust
2019-03-01 19:24 ` [PATCH 11/19] NFS/flexfiles: Don't invalidate DS deviceids for being unresponsive Trond Myklebust
2019-03-01 19:24 ` [PATCH 12/19] NFS/flexfiles: Speed up read failover when DSes are down Trond Myklebust
2019-03-01 19:24 ` [PATCH 13/19] NFS/flexfiles: Simplify nfs4_ff_layout_select_ds_fh() Trond Myklebust
2019-03-01 19:24 ` [PATCH 14/19] NFS/flexfiles: Simplify nfs4_ff_find_or_create_ds_client() Trond Myklebust
2019-03-01 19:24 ` [PATCH 15/19] NFS/flexfiles: Simplify ff_layout_get_ds_cred() Trond Myklebust
2019-03-01 19:24 ` [PATCH 16/19] NFS/flexfile: Simplify nfs4_ff_layout_ds_version() Trond Myklebust
2019-03-01 19:24 ` [PATCH 17/19] NFS/flexfile: Simplify nfs4_ff_layout_select_ds_stateid() Trond Myklebust
2019-03-01 19:24 ` [PATCH 18/19] NFS/flexfiles: Remove dead code in ff_layout_mirror_valid() Trond Myklebust
2019-03-01 19:24 ` [PATCH 19/19] NFS/flexfiles: Clean up mirror DS initialisation Trond Myklebust
2019-03-18 10:58 ` [PATCH 06/19] NFS/flexfiles: Send LAYOUTERROR when failing over mirrored reads kbuild test robot
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=20190301192455.104943-6-trond.myklebust@hammerspace.com \
--to=trondmy@gmail.com \
--cc=linux-nfs@vger.kernel.org \
/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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.