summaryrefslogtreecommitdiff
path: root/fs/nfs/flexfilelayout
diff options
context:
space:
mode:
Diffstat (limited to 'fs/nfs/flexfilelayout')
-rw-r--r--fs/nfs/flexfilelayout/flexfilelayout.c128
-rw-r--r--fs/nfs/flexfilelayout/flexfilelayout.h1
-rw-r--r--fs/nfs/flexfilelayout/flexfilelayoutdev.c12
3 files changed, 106 insertions, 35 deletions
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c
index 3e724cb7ef01..e6909cafab68 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.c
+++ b/fs/nfs/flexfilelayout/flexfilelayout.c
@@ -11,6 +11,7 @@
#include <linux/nfs_mount.h>
#include <linux/nfs_page.h>
#include <linux/module.h>
+#include <linux/file.h>
#include <linux/sched/mm.h>
#include <linux/sunrpc/metrics.h>
@@ -162,6 +163,20 @@ decode_name(struct xdr_stream *xdr, u32 *id)
return 0;
}
+static struct nfsd_file *
+ff_local_open_fh(struct pnfs_layout_segment *lseg, u32 ds_idx,
+ struct nfs_client *clp, const struct cred *cred,
+ struct nfs_fh *fh, fmode_t mode)
+{
+#if IS_ENABLED(CONFIG_NFS_LOCALIO)
+ struct nfs4_ff_layout_mirror *mirror = FF_LAYOUT_COMP(lseg, ds_idx);
+
+ return nfs_local_open_fh(clp, cred, fh, &mirror->nfl, mode);
+#else
+ return NULL;
+#endif
+}
+
static bool ff_mirror_match_fh(const struct nfs4_ff_layout_mirror *m1,
const struct nfs4_ff_layout_mirror *m2)
{
@@ -231,16 +246,18 @@ static struct nfs4_ff_layout_mirror *ff_layout_alloc_mirror(gfp_t gfp_flags)
spin_lock_init(&mirror->lock);
refcount_set(&mirror->ref, 1);
INIT_LIST_HEAD(&mirror->mirrors);
+ nfs_localio_file_init(&mirror->nfl);
}
return mirror;
}
static void ff_layout_free_mirror(struct nfs4_ff_layout_mirror *mirror)
{
- const struct cred *cred;
+ const struct cred *cred;
ff_layout_remove_mirror(mirror);
kfree(mirror->fh_versions);
+ nfs_close_local_fh(&mirror->nfl);
cred = rcu_access_pointer(mirror->ro_cred);
put_cred(cred);
cred = rcu_access_pointer(mirror->rw_cred);
@@ -823,14 +840,6 @@ ff_layout_pg_get_read(struct nfs_pageio_descriptor *pgio,
}
static void
-ff_layout_pg_check_layout(struct nfs_pageio_descriptor *pgio,
- struct nfs_page *req)
-{
- pnfs_generic_pg_check_layout(pgio);
- pnfs_generic_pg_check_range(pgio, req);
-}
-
-static void
ff_layout_pg_init_read(struct nfs_pageio_descriptor *pgio,
struct nfs_page *req)
{
@@ -839,8 +848,11 @@ ff_layout_pg_init_read(struct nfs_pageio_descriptor *pgio,
struct nfs4_pnfs_ds *ds;
u32 ds_idx;
+ if (NFS_SERVER(pgio->pg_inode)->flags &
+ (NFS_MOUNT_SOFT|NFS_MOUNT_SOFTERR))
+ pgio->pg_maxretrans = io_maxretrans;
retry:
- ff_layout_pg_check_layout(pgio, req);
+ pnfs_generic_pg_check_layout(pgio, req);
/* Use full layout for now */
if (!pgio->pg_lseg) {
ff_layout_pg_get_read(pgio, req, false);
@@ -852,6 +864,8 @@ retry:
if (!pgio->pg_lseg)
goto out_nolseg;
}
+ /* Reset wb_nio, since getting layout segment was successful */
+ req->wb_nio = 0;
ds = ff_layout_get_ds_for_read(pgio, &ds_idx);
if (!ds) {
@@ -868,14 +882,24 @@ retry:
pgm->pg_bsize = mirror->mirror_ds->ds_versions[0].rsize;
pgio->pg_mirror_idx = ds_idx;
-
- if (NFS_SERVER(pgio->pg_inode)->flags &
- (NFS_MOUNT_SOFT|NFS_MOUNT_SOFTERR))
- pgio->pg_maxretrans = io_maxretrans;
return;
out_nolseg:
- if (pgio->pg_error < 0)
- return;
+ if (pgio->pg_error < 0) {
+ if (pgio->pg_error != -EAGAIN)
+ return;
+ /* Retry getting layout segment if lower layer returned -EAGAIN */
+ if (pgio->pg_maxretrans && req->wb_nio++ > pgio->pg_maxretrans) {
+ if (NFS_SERVER(pgio->pg_inode)->flags & NFS_MOUNT_SOFTERR)
+ pgio->pg_error = -ETIMEDOUT;
+ else
+ pgio->pg_error = -EIO;
+ return;
+ }
+ pgio->pg_error = 0;
+ /* Sleep for 1 second before retrying */
+ ssleep(1);
+ goto retry;
+ }
out_mds:
trace_pnfs_mds_fallback_pg_init_read(pgio->pg_inode,
0, NFS4_MAX_UINT64, IOMODE_READ,
@@ -895,7 +919,7 @@ ff_layout_pg_init_write(struct nfs_pageio_descriptor *pgio,
u32 i;
retry:
- ff_layout_pg_check_layout(pgio, req);
+ pnfs_generic_pg_check_layout(pgio, req);
if (!pgio->pg_lseg) {
pgio->pg_lseg =
pnfs_update_layout(pgio->pg_inode, nfs_req_openctx(req),
@@ -1130,10 +1154,14 @@ static int ff_layout_async_handle_error_v4(struct rpc_task *task,
rpc_wake_up(&tbl->slot_tbl_waitq);
goto reset;
/* RPC connection errors */
+ case -ENETDOWN:
+ case -ENETUNREACH:
+ if (test_bit(NFS_CS_NETUNREACH_FATAL, &clp->cl_flags))
+ return -NFS4ERR_FATAL_IOERROR;
+ fallthrough;
case -ECONNREFUSED:
case -EHOSTDOWN:
case -EHOSTUNREACH:
- case -ENETUNREACH:
case -EIO:
case -ETIMEDOUT:
case -EPIPE:
@@ -1159,6 +1187,7 @@ reset:
/* Retry all errors through either pNFS or MDS except for -EJUKEBOX */
static int ff_layout_async_handle_error_v3(struct rpc_task *task,
+ struct nfs_client *clp,
struct pnfs_layout_segment *lseg,
u32 idx)
{
@@ -1176,6 +1205,11 @@ static int ff_layout_async_handle_error_v3(struct rpc_task *task,
case -EJUKEBOX:
nfs_inc_stats(lseg->pls_layout->plh_inode, NFSIOS_DELAY);
goto out_retry;
+ case -ENETDOWN:
+ case -ENETUNREACH:
+ if (test_bit(NFS_CS_NETUNREACH_FATAL, &clp->cl_flags))
+ return -NFS4ERR_FATAL_IOERROR;
+ fallthrough;
default:
dprintk("%s DS connection error %d\n", __func__,
task->tk_status);
@@ -1210,7 +1244,7 @@ static int ff_layout_async_handle_error(struct rpc_task *task,
switch (vers) {
case 3:
- return ff_layout_async_handle_error_v3(task, lseg, idx);
+ return ff_layout_async_handle_error_v3(task, clp, lseg, idx);
case 4:
return ff_layout_async_handle_error_v4(task, state, clp,
lseg, idx);
@@ -1240,6 +1274,7 @@ static void ff_layout_io_track_ds_error(struct pnfs_layout_segment *lseg,
case -ECONNRESET:
case -EHOSTDOWN:
case -EHOSTUNREACH:
+ case -ENETDOWN:
case -ENETUNREACH:
case -EADDRINUSE:
case -ENOBUFS:
@@ -1294,7 +1329,7 @@ static int ff_layout_read_done_cb(struct rpc_task *task,
hdr->args.offset, hdr->args.count,
&hdr->res.op_status, OP_READ,
task->tk_status);
- trace_ff_layout_read_error(hdr);
+ trace_ff_layout_read_error(hdr, task->tk_status);
}
err = ff_layout_async_handle_error(task, hdr->args.context->state,
@@ -1313,6 +1348,9 @@ static int ff_layout_read_done_cb(struct rpc_task *task,
return task->tk_status;
case -EAGAIN:
goto out_eagain;
+ case -NFS4ERR_FATAL_IOERROR:
+ task->tk_status = -EIO;
+ return 0;
}
return 0;
@@ -1464,7 +1502,7 @@ static int ff_layout_write_done_cb(struct rpc_task *task,
hdr->args.offset, hdr->args.count,
&hdr->res.op_status, OP_WRITE,
task->tk_status);
- trace_ff_layout_write_error(hdr);
+ trace_ff_layout_write_error(hdr, task->tk_status);
}
err = ff_layout_async_handle_error(task, hdr->args.context->state,
@@ -1483,6 +1521,9 @@ static int ff_layout_write_done_cb(struct rpc_task *task,
return task->tk_status;
case -EAGAIN:
return -EAGAIN;
+ case -NFS4ERR_FATAL_IOERROR:
+ task->tk_status = -EIO;
+ return 0;
}
if (hdr->res.verf->committed == NFS_FILE_SYNC ||
@@ -1510,7 +1551,7 @@ static int ff_layout_commit_done_cb(struct rpc_task *task,
data->args.offset, data->args.count,
&data->res.op_status, OP_COMMIT,
task->tk_status);
- trace_ff_layout_commit_error(data);
+ trace_ff_layout_commit_error(data, task->tk_status);
}
err = ff_layout_async_handle_error(task, NULL, data->ds_clp,
@@ -1527,6 +1568,9 @@ static int ff_layout_commit_done_cb(struct rpc_task *task,
case -EAGAIN:
rpc_restart_call_prepare(task);
return -EAGAIN;
+ case -NFS4ERR_FATAL_IOERROR:
+ task->tk_status = -EIO;
+ return 0;
}
ff_layout_set_layoutcommit(data->inode, data->lseg, data->lwb);
@@ -1764,6 +1808,7 @@ ff_layout_read_pagelist(struct nfs_pgio_header *hdr)
struct pnfs_layout_segment *lseg = hdr->lseg;
struct nfs4_pnfs_ds *ds;
struct rpc_clnt *ds_clnt;
+ struct nfsd_file *localio;
struct nfs4_ff_layout_mirror *mirror;
const struct cred *ds_cred;
loff_t offset = hdr->args.offset;
@@ -1810,11 +1855,18 @@ ff_layout_read_pagelist(struct nfs_pgio_header *hdr)
hdr->args.offset = offset;
hdr->mds_offset = offset;
+ /* Start IO accounting for local read */
+ localio = ff_local_open_fh(lseg, idx, ds->ds_clp, ds_cred, fh, FMODE_READ);
+ if (localio) {
+ hdr->task.tk_start = ktime_get();
+ ff_layout_read_record_layoutstats_start(&hdr->task, hdr);
+ }
+
/* Perform an asynchronous read to ds */
nfs_initiate_pgio(ds_clnt, hdr, ds_cred, ds->ds_clp->rpc_ops,
vers == 3 ? &ff_layout_read_call_ops_v3 :
&ff_layout_read_call_ops_v4,
- 0, RPC_TASK_SOFTCONN);
+ 0, RPC_TASK_SOFTCONN, localio);
put_cred(ds_cred);
return PNFS_ATTEMPTED;
@@ -1834,6 +1886,7 @@ ff_layout_write_pagelist(struct nfs_pgio_header *hdr, int sync)
struct pnfs_layout_segment *lseg = hdr->lseg;
struct nfs4_pnfs_ds *ds;
struct rpc_clnt *ds_clnt;
+ struct nfsd_file *localio;
struct nfs4_ff_layout_mirror *mirror;
const struct cred *ds_cred;
loff_t offset = hdr->args.offset;
@@ -1878,11 +1931,19 @@ ff_layout_write_pagelist(struct nfs_pgio_header *hdr, int sync)
*/
hdr->args.offset = offset;
+ /* Start IO accounting for local write */
+ localio = ff_local_open_fh(lseg, idx, ds->ds_clp, ds_cred, fh,
+ FMODE_READ|FMODE_WRITE);
+ if (localio) {
+ hdr->task.tk_start = ktime_get();
+ ff_layout_write_record_layoutstats_start(&hdr->task, hdr);
+ }
+
/* Perform an asynchronous write */
nfs_initiate_pgio(ds_clnt, hdr, ds_cred, ds->ds_clp->rpc_ops,
vers == 3 ? &ff_layout_write_call_ops_v3 :
&ff_layout_write_call_ops_v4,
- sync, RPC_TASK_SOFTCONN);
+ sync, RPC_TASK_SOFTCONN, localio);
put_cred(ds_cred);
return PNFS_ATTEMPTED;
@@ -1916,6 +1977,7 @@ static int ff_layout_initiate_commit(struct nfs_commit_data *data, int how)
struct pnfs_layout_segment *lseg = data->lseg;
struct nfs4_pnfs_ds *ds;
struct rpc_clnt *ds_clnt;
+ struct nfsd_file *localio;
struct nfs4_ff_layout_mirror *mirror;
const struct cred *ds_cred;
u32 idx;
@@ -1954,10 +2016,18 @@ static int ff_layout_initiate_commit(struct nfs_commit_data *data, int how)
if (fh)
data->args.fh = fh;
+ /* Start IO accounting for local commit */
+ localio = ff_local_open_fh(lseg, idx, ds->ds_clp, ds_cred, fh,
+ FMODE_READ|FMODE_WRITE);
+ if (localio) {
+ data->task.tk_start = ktime_get();
+ ff_layout_commit_record_layoutstats_start(&data->task, data);
+ }
+
ret = nfs_initiate_commit(ds_clnt, data, ds->ds_clp->rpc_ops,
vers == 3 ? &ff_layout_commit_call_ops_v3 :
&ff_layout_commit_call_ops_v4,
- how, RPC_TASK_SOFTCONN);
+ how, RPC_TASK_SOFTCONN, localio);
put_cred(ds_cred);
return ret;
out_err:
@@ -2095,12 +2165,6 @@ static int ff_layout_encode_ioerr(struct xdr_stream *xdr,
}
static void
-encode_opaque_fixed(struct xdr_stream *xdr, const void *buf, size_t len)
-{
- WARN_ON_ONCE(xdr_stream_encode_opaque_fixed(xdr, buf, len) < 0);
-}
-
-static void
ff_layout_encode_ff_iostat_head(struct xdr_stream *xdr,
const nfs4_stateid *stateid,
const struct nfs42_layoutstat_devinfo *devinfo)
@@ -2556,7 +2620,7 @@ ff_layout_set_layoutdriver(struct nfs_server *server,
const struct nfs_fh *dummy)
{
#if IS_ENABLED(CONFIG_NFS_V4_2)
- server->caps |= NFS_CAP_LAYOUTSTATS;
+ server->caps |= NFS_CAP_LAYOUTSTATS | NFS_CAP_REBOOT_LAYOUTRETURN;
#endif
return 0;
}
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.h b/fs/nfs/flexfilelayout/flexfilelayout.h
index f84b3fb0dddd..095df09017a5 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.h
+++ b/fs/nfs/flexfilelayout/flexfilelayout.h
@@ -83,6 +83,7 @@ struct nfs4_ff_layout_mirror {
nfs4_stateid stateid;
const struct cred __rcu *ro_cred;
const struct cred __rcu *rw_cred;
+ struct nfs_file_localio nfl;
refcount_t ref;
spinlock_t lock;
unsigned long flags;
diff --git a/fs/nfs/flexfilelayout/flexfilelayoutdev.c b/fs/nfs/flexfilelayout/flexfilelayoutdev.c
index e028f5a0ef5f..4a304cf17c4b 100644
--- a/fs/nfs/flexfilelayout/flexfilelayoutdev.c
+++ b/fs/nfs/flexfilelayout/flexfilelayoutdev.c
@@ -49,6 +49,7 @@ nfs4_ff_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,
struct nfs4_pnfs_ds_addr *da;
struct nfs4_ff_layout_ds *new_ds = NULL;
struct nfs4_ff_ds_version *ds_versions = NULL;
+ struct net *net = server->nfs_client->cl_net;
u32 mp_count;
u32 version_count;
__be32 *p;
@@ -80,8 +81,7 @@ nfs4_ff_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,
for (i = 0; i < mp_count; i++) {
/* multipath ds */
- da = nfs4_decode_mp_ds_addr(server->nfs_client->cl_net,
- &stream, gfp_flags);
+ da = nfs4_decode_mp_ds_addr(net, &stream, gfp_flags);
if (da)
list_add_tail(&da->da_node, &dsaddrs);
}
@@ -149,7 +149,7 @@ nfs4_ff_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,
new_ds->ds_versions = ds_versions;
new_ds->ds_versions_cnt = version_count;
- new_ds->ds = nfs4_pnfs_ds_add(&dsaddrs, gfp_flags);
+ new_ds->ds = nfs4_pnfs_ds_add(net, &dsaddrs, gfp_flags);
if (!new_ds->ds)
goto out_err_drain_dsaddrs;
@@ -395,6 +395,12 @@ nfs4_ff_layout_prepare_ds(struct pnfs_layout_segment *lseg,
/* connect success, check rsize/wsize limit */
if (!status) {
+ /*
+ * ds_clp is put in destroy_ds().
+ * keep ds_clp even if DS is local, so that if local IO cannot
+ * proceed somehow, we can fall back to NFS whenever we want.
+ */
+ nfs_local_probe(ds->ds_clp);
max_payload =
nfs_block_size(rpc_max_payload(ds->ds_clp->cl_rpcclient),
NULL);
generated by cgit (git 2.34.1) at 2025-07-23 10:07:27 +0000