Update Linux to v5.4.2
Change-Id: Idf6911045d9d382da2cfe01b1edff026404ac8fd
diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig
index 5f93cfa..295a7a2 100644
--- a/fs/nfs/Kconfig
+++ b/fs/nfs/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
config NFS_FS
tristate "NFS client support"
depends on INET && FILE_LOCKING && MULTIUSER
@@ -121,7 +122,6 @@
config PNFS_BLOCK
tristate
depends on NFS_V4_1 && BLK_DEV_DM
- depends on 64BIT || LBDAF
default NFS_V4
config PNFS_FLEXFILE_LAYOUT
diff --git a/fs/nfs/Makefile b/fs/nfs/Makefile
index c587e3c..34cdeae 100644
--- a/fs/nfs/Makefile
+++ b/fs/nfs/Makefile
@@ -8,7 +8,8 @@
CFLAGS_nfstrace.o += -I$(src)
nfs-y := client.o dir.o file.o getroot.o inode.o super.o \
io.o direct.o pagelist.o read.o symlink.o unlink.o \
- write.o namespace.o mount_clnt.o nfstrace.o export.o
+ write.o namespace.o mount_clnt.o nfstrace.o \
+ export.o sysfs.o
nfs-$(CONFIG_ROOT_NFS) += nfsroot.o
nfs-$(CONFIG_SYSCTL) += sysctl.o
nfs-$(CONFIG_NFS_FSCACHE) += fscache.o fscache-index.o
diff --git a/fs/nfs/blocklayout/Makefile b/fs/nfs/blocklayout/Makefile
index 3ca14c3..7668a1b 100644
--- a/fs/nfs/blocklayout/Makefile
+++ b/fs/nfs/blocklayout/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
#
# Makefile for the pNFS block layout driver kernel module
#
diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c
index 06cb0c1..6902217 100644
--- a/fs/nfs/blocklayout/blocklayout.c
+++ b/fs/nfs/blocklayout/blocklayout.c
@@ -584,7 +584,7 @@
static struct nfs4_deviceid_node *
bl_find_get_deviceid(struct nfs_server *server,
- const struct nfs4_deviceid *id, struct rpc_cred *cred,
+ const struct nfs4_deviceid *id, const struct cred *cred,
gfp_t gfp_mask)
{
struct nfs4_deviceid_node *node;
@@ -896,7 +896,7 @@
end = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
if (end != inode->i_mapping->nrpages) {
rcu_read_lock();
- end = page_cache_next_hole(mapping, idx + 1, ULONG_MAX);
+ end = page_cache_next_miss(mapping, idx + 1, ULONG_MAX);
rcu_read_unlock();
}
diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c
index 509dc5a..7817ad9 100644
--- a/fs/nfs/callback.c
+++ b/fs/nfs/callback.c
@@ -41,11 +41,13 @@
static int nfs4_callback_up_net(struct svc_serv *serv, struct net *net)
{
+ const struct cred *cred = current_cred();
int ret;
struct nfs_net *nn = net_generic(net, nfs_net_id);
ret = svc_create_xprt(serv, "tcp", net, PF_INET,
- nfs_callback_set_tcpport, SVC_SOCK_ANONYMOUS);
+ nfs_callback_set_tcpport, SVC_SOCK_ANONYMOUS,
+ cred);
if (ret <= 0)
goto out_err;
nn->nfs_callback_tcpport = ret;
@@ -53,10 +55,11 @@
nn->nfs_callback_tcpport, PF_INET, net->ns.inum);
ret = svc_create_xprt(serv, "tcp", net, PF_INET6,
- nfs_callback_set_tcpport, SVC_SOCK_ANONYMOUS);
+ nfs_callback_set_tcpport, SVC_SOCK_ANONYMOUS,
+ cred);
if (ret > 0) {
nn->nfs_callback_tcpport6 = ret;
- dprintk("NFS: Callback listener port = %u (af %u, net %x\n",
+ dprintk("NFS: Callback listener port = %u (af %u, net %x)\n",
nn->nfs_callback_tcpport6, PF_INET6, net->ns.inum);
} else if (ret != -EAFNOSUPPORT)
goto out_err;
@@ -206,11 +209,13 @@
goto err_bind;
}
- ret = -EPROTONOSUPPORT;
+ ret = 0;
if (!IS_ENABLED(CONFIG_NFS_V4_1) || minorversion == 0)
ret = nfs4_callback_up_net(serv, net);
- else if (xprt->ops->bc_up)
- ret = xprt->ops->bc_up(serv, net);
+ else if (xprt->ops->bc_setup)
+ set_bc_enabled(serv);
+ else
+ ret = -EPROTONOSUPPORT;
if (ret < 0) {
printk(KERN_ERR "NFS: callback service start failed\n");
@@ -455,4 +460,6 @@
.pg_class = "nfs", /* authentication class */
.pg_stats = &nfs4_callback_stats,
.pg_authenticate = nfs_callback_authenticate,
+ .pg_init_request = svc_generic_init_request,
+ .pg_rpcbind_set = svc_generic_rpcbind_set,
};
diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c
index 3159673..f39924b 100644
--- a/fs/nfs/callback_proc.c
+++ b/fs/nfs/callback_proc.c
@@ -414,27 +414,39 @@
validate_seqid(const struct nfs4_slot_table *tbl, const struct nfs4_slot *slot,
const struct cb_sequenceargs * args)
{
+ __be32 ret;
+
+ ret = cpu_to_be32(NFS4ERR_BADSLOT);
if (args->csa_slotid > tbl->server_highest_slotid)
- return htonl(NFS4ERR_BADSLOT);
+ goto out_err;
/* Replay */
if (args->csa_sequenceid == slot->seq_nr) {
+ ret = cpu_to_be32(NFS4ERR_DELAY);
if (nfs4_test_locked_slot(tbl, slot->slot_nr))
- return htonl(NFS4ERR_DELAY);
+ goto out_err;
+
/* Signal process_op to set this error on next op */
+ ret = cpu_to_be32(NFS4ERR_RETRY_UNCACHED_REP);
if (args->csa_cachethis == 0)
- return htonl(NFS4ERR_RETRY_UNCACHED_REP);
+ goto out_err;
/* Liar! We never allowed you to set csa_cachethis != 0 */
- return htonl(NFS4ERR_SEQ_FALSE_RETRY);
+ ret = cpu_to_be32(NFS4ERR_SEQ_FALSE_RETRY);
+ goto out_err;
}
/* Note: wraparound relies on seq_nr being of type u32 */
- if (likely(args->csa_sequenceid == slot->seq_nr + 1))
- return htonl(NFS4_OK);
-
/* Misordered request */
- return htonl(NFS4ERR_SEQ_MISORDERED);
+ ret = cpu_to_be32(NFS4ERR_SEQ_MISORDERED);
+ if (args->csa_sequenceid != slot->seq_nr + 1)
+ goto out_err;
+
+ return cpu_to_be32(NFS4_OK);
+
+out_err:
+ trace_nfs4_cb_seqid_err(args, ret);
+ return ret;
}
/*
diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c
index a87a562..73a5a5e 100644
--- a/fs/nfs/callback_xdr.c
+++ b/fs/nfs/callback_xdr.c
@@ -72,16 +72,6 @@
return xdr_ressize_check(rqstp, p);
}
-static __be32 *read_buf(struct xdr_stream *xdr, size_t nbytes)
-{
- __be32 *p;
-
- p = xdr_inline_decode(xdr, nbytes);
- if (unlikely(p == NULL))
- printk(KERN_WARNING "NFS: NFSv4 callback reply buffer overflowed!\n");
- return p;
-}
-
static __be32 decode_string(struct xdr_stream *xdr, unsigned int *len,
const char **str, size_t maxlen)
{
@@ -98,13 +88,13 @@
{
__be32 *p;
- p = read_buf(xdr, 4);
+ p = xdr_inline_decode(xdr, 4);
if (unlikely(p == NULL))
return htonl(NFS4ERR_RESOURCE);
fh->size = ntohl(*p);
if (fh->size > NFS4_FHSIZE)
return htonl(NFS4ERR_BADHANDLE);
- p = read_buf(xdr, fh->size);
+ p = xdr_inline_decode(xdr, fh->size);
if (unlikely(p == NULL))
return htonl(NFS4ERR_RESOURCE);
memcpy(&fh->data[0], p, fh->size);
@@ -117,11 +107,11 @@
__be32 *p;
unsigned int attrlen;
- p = read_buf(xdr, 4);
+ p = xdr_inline_decode(xdr, 4);
if (unlikely(p == NULL))
return htonl(NFS4ERR_RESOURCE);
attrlen = ntohl(*p);
- p = read_buf(xdr, attrlen << 2);
+ p = xdr_inline_decode(xdr, attrlen << 2);
if (unlikely(p == NULL))
return htonl(NFS4ERR_RESOURCE);
if (likely(attrlen > 0))
@@ -135,7 +125,7 @@
{
__be32 *p;
- p = read_buf(xdr, NFS4_STATEID_SIZE);
+ p = xdr_inline_decode(xdr, NFS4_STATEID_SIZE);
if (unlikely(p == NULL))
return htonl(NFS4ERR_RESOURCE);
memcpy(stateid->data, p, NFS4_STATEID_SIZE);
@@ -156,7 +146,7 @@
status = decode_string(xdr, &hdr->taglen, &hdr->tag, CB_OP_TAGLEN_MAXSZ);
if (unlikely(status != 0))
return status;
- p = read_buf(xdr, 12);
+ p = xdr_inline_decode(xdr, 12);
if (unlikely(p == NULL))
return htonl(NFS4ERR_RESOURCE);
hdr->minorversion = ntohl(*p++);
@@ -176,7 +166,7 @@
static __be32 decode_op_hdr(struct xdr_stream *xdr, unsigned int *op)
{
__be32 *p;
- p = read_buf(xdr, 4);
+ p = xdr_inline_decode(xdr, 4);
if (unlikely(p == NULL))
return htonl(NFS4ERR_RESOURCE_HDR);
*op = ntohl(*p);
@@ -205,7 +195,7 @@
status = decode_delegation_stateid(xdr, &args->stateid);
if (unlikely(status != 0))
return status;
- p = read_buf(xdr, 4);
+ p = xdr_inline_decode(xdr, 4);
if (unlikely(p == NULL))
return htonl(NFS4ERR_RESOURCE);
args->truncate = ntohl(*p);
@@ -227,7 +217,7 @@
__be32 status = 0;
uint32_t iomode;
- p = read_buf(xdr, 4 * sizeof(uint32_t));
+ p = xdr_inline_decode(xdr, 4 * sizeof(uint32_t));
if (unlikely(p == NULL))
return htonl(NFS4ERR_BADXDR);
@@ -245,14 +235,14 @@
if (unlikely(status != 0))
return status;
- p = read_buf(xdr, 2 * sizeof(uint64_t));
+ p = xdr_inline_decode(xdr, 2 * sizeof(uint64_t));
if (unlikely(p == NULL))
return htonl(NFS4ERR_BADXDR);
p = xdr_decode_hyper(p, &args->cbl_range.offset);
p = xdr_decode_hyper(p, &args->cbl_range.length);
return decode_layout_stateid(xdr, &args->cbl_stateid);
} else if (args->cbl_recall_type == RETURN_FSID) {
- p = read_buf(xdr, 2 * sizeof(uint64_t));
+ p = xdr_inline_decode(xdr, 2 * sizeof(uint64_t));
if (unlikely(p == NULL))
return htonl(NFS4ERR_BADXDR);
p = xdr_decode_hyper(p, &args->cbl_fsid.major);
@@ -275,7 +265,7 @@
args->ndevs = 0;
/* Num of device notifications */
- p = read_buf(xdr, sizeof(uint32_t));
+ p = xdr_inline_decode(xdr, sizeof(uint32_t));
if (unlikely(p == NULL)) {
status = htonl(NFS4ERR_BADXDR);
goto out;
@@ -298,7 +288,8 @@
for (i = 0; i < n; i++) {
struct cb_devicenotifyitem *dev = &args->devs[i];
- p = read_buf(xdr, (4 * sizeof(uint32_t)) + NFS4_DEVICEID4_SIZE);
+ p = xdr_inline_decode(xdr, (4 * sizeof(uint32_t)) +
+ NFS4_DEVICEID4_SIZE);
if (unlikely(p == NULL)) {
status = htonl(NFS4ERR_BADXDR);
goto err;
@@ -329,7 +320,7 @@
p += XDR_QUADLEN(NFS4_DEVICEID4_SIZE);
if (dev->cbd_layout_type == NOTIFY_DEVICEID4_CHANGE) {
- p = read_buf(xdr, sizeof(uint32_t));
+ p = xdr_inline_decode(xdr, sizeof(uint32_t));
if (unlikely(p == NULL)) {
status = htonl(NFS4ERR_BADXDR);
goto err;
@@ -359,7 +350,7 @@
{
__be32 *p;
- p = read_buf(xdr, NFS4_MAX_SESSIONID_LEN);
+ p = xdr_inline_decode(xdr, NFS4_MAX_SESSIONID_LEN);
if (unlikely(p == NULL))
return htonl(NFS4ERR_RESOURCE);
@@ -379,13 +370,13 @@
goto out;
status = htonl(NFS4ERR_RESOURCE);
- p = read_buf(xdr, sizeof(uint32_t));
+ p = xdr_inline_decode(xdr, sizeof(uint32_t));
if (unlikely(p == NULL))
goto out;
rc_list->rcl_nrefcalls = ntohl(*p++);
if (rc_list->rcl_nrefcalls) {
- p = read_buf(xdr,
+ p = xdr_inline_decode(xdr,
rc_list->rcl_nrefcalls * 2 * sizeof(uint32_t));
if (unlikely(p == NULL))
goto out;
@@ -418,7 +409,7 @@
if (status)
return status;
- p = read_buf(xdr, 5 * sizeof(uint32_t));
+ p = xdr_inline_decode(xdr, 5 * sizeof(uint32_t));
if (unlikely(p == NULL))
return htonl(NFS4ERR_RESOURCE);
@@ -461,7 +452,7 @@
uint32_t bitmap[2];
__be32 *p, status;
- p = read_buf(xdr, 4);
+ p = xdr_inline_decode(xdr, 4);
if (unlikely(p == NULL))
return htonl(NFS4ERR_BADXDR);
args->craa_objs_to_keep = ntohl(*p++);
@@ -480,7 +471,7 @@
struct cb_recallslotargs *args = argp;
__be32 *p;
- p = read_buf(xdr, 4);
+ p = xdr_inline_decode(xdr, 4);
if (unlikely(p == NULL))
return htonl(NFS4ERR_BADXDR);
args->crsa_target_highest_slotid = ntohl(*p++);
@@ -492,14 +483,14 @@
__be32 *p;
unsigned int len;
- p = read_buf(xdr, 12);
+ p = xdr_inline_decode(xdr, 12);
if (unlikely(p == NULL))
return htonl(NFS4ERR_BADXDR);
p = xdr_decode_hyper(p, &args->cbnl_owner.clientid);
len = be32_to_cpu(*p);
- p = read_buf(xdr, len);
+ p = xdr_inline_decode(xdr, len);
if (unlikely(p == NULL))
return htonl(NFS4ERR_BADXDR);
@@ -537,7 +528,7 @@
__be32 *p;
/* skip the always zero field */
- p = read_buf(xdr, 4);
+ p = xdr_inline_decode(xdr, 4);
if (unlikely(!p))
goto out;
p++;
@@ -577,7 +568,7 @@
return status;
/* decode status */
- p = read_buf(xdr, 4);
+ p = xdr_inline_decode(xdr, 4);
if (unlikely(!p))
goto out;
args->error = ntohl(*p++);
@@ -943,10 +934,11 @@
};
unsigned int nops = 0;
- xdr_init_decode(&xdr_in, &rqstp->rq_arg, rqstp->rq_arg.head[0].iov_base);
+ xdr_init_decode(&xdr_in, &rqstp->rq_arg,
+ rqstp->rq_arg.head[0].iov_base, NULL);
p = (__be32*)((char *)rqstp->rq_res.head[0].iov_base + rqstp->rq_res.head[0].iov_len);
- xdr_init_encode(&xdr_out, &rqstp->rq_res, p);
+ xdr_init_encode(&xdr_out, &rqstp->rq_res, p, NULL);
status = decode_compound_hdr_arg(&xdr_in, &hdr_arg);
if (status == htonl(NFS4ERR_RESOURCE))
@@ -991,7 +983,7 @@
out_invalidcred:
pr_warn_ratelimited("NFS: NFSv4 callback contains invalid cred\n");
- return rpc_autherr_badcred;
+ return svc_return_autherr(rqstp, rpc_autherr_badcred);
}
/*
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index 96d5f81..3083830 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
/* client.c: NFS client sharing and management code
*
* Copyright (C) 2006 Red Hat, Inc. All Rights Reserved.
* Written by David Howells (dhowells@redhat.com)
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
*/
@@ -53,6 +49,7 @@
#include "pnfs.h"
#include "nfs.h"
#include "netns.h"
+#include "sysfs.h"
#define NFSDBG_FACILITY NFSDBG_CLIENT
@@ -151,7 +148,6 @@
struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_init)
{
struct nfs_client *clp;
- struct rpc_cred *cred;
int err = -ENOMEM;
if ((clp = kzalloc(sizeof(*clp), GFP_KERNEL)) == NULL)
@@ -180,11 +176,10 @@
clp->cl_rpcclient = ERR_PTR(-EINVAL);
clp->cl_proto = cl_init->proto;
+ clp->cl_nconnect = cl_init->nconnect;
clp->cl_net = get_net(cl_init->net);
- cred = rpc_lookup_machine_cred("*");
- if (!IS_ERR(cred))
- clp->cl_machine_cred = cred;
+ clp->cl_principal = "*";
nfs_fscache_get_client_cookie(clp);
return clp;
@@ -199,7 +194,7 @@
EXPORT_SYMBOL_GPL(nfs_alloc_client);
#if IS_ENABLED(CONFIG_NFS_V4)
-void nfs_cleanup_cb_ident_idr(struct net *net)
+static void nfs_cleanup_cb_ident_idr(struct net *net)
{
struct nfs_net *nn = net_generic(net, nfs_net_id);
@@ -221,7 +216,7 @@
}
#else
-void nfs_cleanup_cb_ident_idr(struct net *net)
+static void nfs_cleanup_cb_ident_idr(struct net *net)
{
}
@@ -246,9 +241,6 @@
if (!IS_ERR(clp->cl_rpcclient))
rpc_shutdown_client(clp->cl_rpcclient);
- if (clp->cl_machine_cred != NULL)
- put_rpccred(clp->cl_machine_cred);
-
put_net(clp->cl_net);
put_nfs_version(clp->cl_nfs_mod);
kfree(clp->cl_hostname);
@@ -290,6 +282,7 @@
struct nfs_client *clp;
const struct sockaddr *sap = data->addr;
struct nfs_net *nn = net_generic(data->net, nfs_net_id);
+ int error;
again:
list_for_each_entry(clp, &nn->nfs_client_list, cl_share_link) {
@@ -302,9 +295,11 @@
if (clp->cl_cons_state > NFS_CS_READY) {
refcount_inc(&clp->cl_count);
spin_unlock(&nn->nfs_client_lock);
- nfs_wait_client_init_complete(clp);
+ error = nfs_wait_client_init_complete(clp);
nfs_put_client(clp);
spin_lock(&nn->nfs_client_lock);
+ if (error < 0)
+ return ERR_PTR(error);
goto again;
}
@@ -415,6 +410,8 @@
spin_unlock(&nn->nfs_client_lock);
if (new)
new->rpc_ops->free_client(new);
+ if (IS_ERR(clp))
+ return clp;
return nfs_found_client(cl_init, clp);
}
if (new) {
@@ -459,7 +456,7 @@
case XPRT_TRANSPORT_RDMA:
if (retrans == NFS_UNSPEC_RETRANS)
to->to_retries = NFS_DEF_TCP_RETRANS;
- if (timeo == NFS_UNSPEC_TIMEO || to->to_retries == 0)
+ if (timeo == NFS_UNSPEC_TIMEO || to->to_initval == 0)
to->to_initval = NFS_DEF_TCP_TIMEO * HZ / 10;
if (to->to_initval > NFS_MAX_TCP_TIMEOUT)
to->to_initval = NFS_MAX_TCP_TIMEOUT;
@@ -498,6 +495,7 @@
struct rpc_create_args args = {
.net = clp->cl_net,
.protocol = clp->cl_proto,
+ .nconnect = clp->cl_nconnect,
.address = (struct sockaddr *)&clp->cl_addr,
.addrsize = clp->cl_addrlen,
.timeout = cl_init->timeparms,
@@ -506,6 +504,7 @@
.program = &nfs_program,
.version = clp->rpc_ops->version,
.authflavor = flavor,
+ .cred = cl_init->cred,
};
if (test_bit(NFS_CS_DISCRTRY, &clp->cl_flags))
@@ -527,6 +526,7 @@
return PTR_ERR(clnt);
}
+ clnt->cl_principal = clp->cl_principal;
clp->cl_rpcclient = clnt;
return 0;
}
@@ -557,6 +557,7 @@
1 : 0,
.net = clp->cl_net,
.nlmclnt_ops = clp->cl_nfs_mod->rpc_ops->nlmclnt_ops,
+ .cred = current_cred(),
};
if (nlm_init.nfs_version > 3)
@@ -603,6 +604,8 @@
sizeof(server->client->cl_timeout_default));
server->client->cl_timeout = &server->client->cl_timeout_default;
server->client->cl_softrtry = 0;
+ if (server->flags & NFS_MOUNT_SOFTERR)
+ server->client->cl_softerr = 1;
if (server->flags & NFS_MOUNT_SOFT)
server->client->cl_softrtry = 1;
@@ -657,6 +660,8 @@
.proto = data->nfs_server.protocol,
.net = data->net,
.timeparms = &timeparms,
+ .cred = server->cred,
+ .nconnect = data->nfs_server.nconnect,
};
struct nfs_client *clp;
int error;
@@ -925,6 +930,7 @@
ida_destroy(&server->lockowner_id);
ida_destroy(&server->openowner_id);
nfs_free_iostats(server->io_stats);
+ put_cred(server->cred);
kfree(server);
nfs_release_automount_timer();
}
@@ -945,6 +951,8 @@
if (!server)
return ERR_PTR(-ENOMEM);
+ server->cred = get_cred(current_cred());
+
error = -ENOMEM;
fattr = nfs_alloc_fattr();
if (fattr == NULL)
@@ -1011,6 +1019,8 @@
if (!server)
return ERR_PTR(-ENOMEM);
+ server->cred = get_cred(source->cred);
+
error = -ENOMEM;
fattr_fsinfo = nfs_alloc_fattr();
if (fattr_fsinfo == NULL)
@@ -1066,6 +1076,18 @@
#endif
spin_lock_init(&nn->nfs_client_lock);
nn->boot_time = ktime_get_real();
+
+ nfs_netns_sysfs_setup(nn, net);
+}
+
+void nfs_clients_exit(struct net *net)
+{
+ struct nfs_net *nn = net_generic(net, nfs_net_id);
+
+ nfs_netns_sysfs_destroy(nn);
+ nfs_cleanup_cb_ident_idr(net);
+ WARN_ON_ONCE(!list_empty(&nn->nfs_client_list));
+ WARN_ON_ONCE(!list_empty(&nn->nfs_volume_list));
}
#ifdef CONFIG_PROC_FS
diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index 75fe92e..af549d7 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* linux/fs/nfs/delegation.c
*
@@ -26,10 +27,8 @@
static void nfs_free_delegation(struct nfs_delegation *delegation)
{
- if (delegation->cred) {
- put_rpccred(delegation->cred);
- delegation->cred = NULL;
- }
+ put_cred(delegation->cred);
+ delegation->cred = NULL;
kfree_rcu(delegation, rcu);
}
@@ -54,6 +53,16 @@
return false;
}
+struct nfs_delegation *nfs4_get_valid_delegation(const struct inode *inode)
+{
+ struct nfs_delegation *delegation;
+
+ delegation = rcu_dereference(NFS_I(inode)->delegation);
+ if (nfs4_is_valid_delegation(delegation, 0))
+ return delegation;
+ return NULL;
+}
+
static int
nfs4_do_check_delegation(struct inode *inode, fmode_t flags, bool mark)
{
@@ -93,7 +102,7 @@
return nfs4_do_check_delegation(inode, flags, false);
}
-static int nfs_delegation_claim_locks(struct nfs_open_context *ctx, struct nfs4_state *state, const nfs4_stateid *stateid)
+static int nfs_delegation_claim_locks(struct nfs4_state *state, const nfs4_stateid *stateid)
{
struct inode *inode = state->inode;
struct file_lock *fl;
@@ -108,7 +117,7 @@
spin_lock(&flctx->flc_lock);
restart:
list_for_each_entry(fl, list, fl_list) {
- if (nfs_file_open_context(fl->fl_file) != ctx)
+ if (nfs_file_open_context(fl->fl_file)->state != state)
continue;
spin_unlock(&flctx->flc_lock);
status = nfs4_lock_delegation_recall(fl, state, stateid);
@@ -136,8 +145,8 @@
int err;
again:
- spin_lock(&inode->i_lock);
- list_for_each_entry(ctx, &nfsi->open_files, list) {
+ rcu_read_lock();
+ list_for_each_entry_rcu(ctx, &nfsi->open_files, list) {
state = ctx->state;
if (state == NULL)
continue;
@@ -147,15 +156,16 @@
continue;
if (!nfs4_stateid_match(&state->stateid, stateid))
continue;
- get_nfs_open_context(ctx);
- spin_unlock(&inode->i_lock);
+ if (!get_nfs_open_context(ctx))
+ continue;
+ rcu_read_unlock();
sp = state->owner;
/* Block nfs4_proc_unlck */
mutex_lock(&sp->so_delegreturn_mutex);
seq = raw_seqcount_begin(&sp->so_reclaim_seqcount);
- err = nfs4_open_delegation_recall(ctx, state, stateid, type);
+ err = nfs4_open_delegation_recall(ctx, state, stateid);
if (!err)
- err = nfs_delegation_claim_locks(ctx, state, stateid);
+ err = nfs_delegation_claim_locks(state, stateid);
if (!err && read_seqcount_retry(&sp->so_reclaim_seqcount, seq))
err = -EAGAIN;
mutex_unlock(&sp->so_delegreturn_mutex);
@@ -164,7 +174,7 @@
return err;
goto again;
}
- spin_unlock(&inode->i_lock);
+ rcu_read_unlock();
return 0;
}
@@ -177,13 +187,13 @@
* @pagemod_limit: write delegation "space_limit"
*
*/
-void nfs_inode_reclaim_delegation(struct inode *inode, struct rpc_cred *cred,
+void nfs_inode_reclaim_delegation(struct inode *inode, const struct cred *cred,
fmode_t type,
const nfs4_stateid *stateid,
unsigned long pagemod_limit)
{
struct nfs_delegation *delegation;
- struct rpc_cred *oldcred = NULL;
+ const struct cred *oldcred = NULL;
rcu_read_lock();
delegation = rcu_dereference(NFS_I(inode)->delegation);
@@ -194,12 +204,12 @@
delegation->type = type;
delegation->pagemod_limit = pagemod_limit;
oldcred = delegation->cred;
- delegation->cred = get_rpccred(cred);
+ delegation->cred = get_cred(cred);
clear_bit(NFS_DELEGATION_NEED_RECLAIM,
&delegation->flags);
spin_unlock(&delegation->lock);
rcu_read_unlock();
- put_rpccred(oldcred);
+ put_cred(oldcred);
trace_nfs4_reclaim_delegation(inode, type);
return;
}
@@ -230,6 +240,8 @@
spin_lock(&delegation->lock);
if (delegation->inode != NULL)
inode = igrab(delegation->inode);
+ if (!inode)
+ set_bit(NFS_DELEGATION_INODE_FREEING, &delegation->flags);
spin_unlock(&delegation->lock);
return inode;
}
@@ -340,7 +352,7 @@
*
* Returns zero on success, or a negative errno value.
*/
-int nfs_inode_set_delegation(struct inode *inode, struct rpc_cred *cred,
+int nfs_inode_set_delegation(struct inode *inode, const struct cred *cred,
fmode_t type,
const nfs4_stateid *stateid,
unsigned long pagemod_limit)
@@ -359,7 +371,7 @@
delegation->type = type;
delegation->pagemod_limit = pagemod_limit;
delegation->change_attr = inode_peek_iversion_raw(inode);
- delegation->cred = get_rpccred(cred);
+ delegation->cred = get_cred(cred);
delegation->inode = inode;
delegation->flags = 1<<NFS_DELEGATION_REFERENCED;
spin_lock_init(&delegation->lock);
@@ -682,7 +694,7 @@
/**
* nfs_super_return_all_delegations - return delegations for one superblock
- * @sb: sb to process
+ * @server: pointer to nfs_server to process
*
*/
void nfs_server_return_all_delegations(struct nfs_server *server)
@@ -945,10 +957,11 @@
list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) {
list_for_each_entry_rcu(delegation, &server->delegations,
super_list) {
- if (test_bit(NFS_DELEGATION_RETURNING,
- &delegation->flags))
- continue;
- if (test_bit(NFS_DELEGATION_NEED_RECLAIM,
+ if (test_bit(NFS_DELEGATION_INODE_FREEING,
+ &delegation->flags) ||
+ test_bit(NFS_DELEGATION_RETURNING,
+ &delegation->flags) ||
+ test_bit(NFS_DELEGATION_NEED_RECLAIM,
&delegation->flags) == 0)
continue;
if (!nfs_sb_active(server->super))
@@ -1032,6 +1045,34 @@
}
/**
+ * nfs_test_expired_all_delegations - test all delegations for a client
+ * @clp: nfs_client to process
+ *
+ * Helper for handling "recallable state revoked" status from server.
+ */
+void nfs_test_expired_all_delegations(struct nfs_client *clp)
+{
+ nfs_mark_test_expired_all_delegations(clp);
+ nfs4_schedule_state_manager(clp);
+}
+
+static void
+nfs_delegation_test_free_expired(struct inode *inode,
+ nfs4_stateid *stateid,
+ const struct cred *cred)
+{
+ struct nfs_server *server = NFS_SERVER(inode);
+ const struct nfs4_minor_version_ops *ops = server->nfs_client->cl_mvops;
+ int status;
+
+ if (!cred)
+ return;
+ status = ops->test_and_free_expired(server, stateid, cred);
+ if (status == -NFS4ERR_EXPIRED || status == -NFS4ERR_BAD_STATEID)
+ nfs_remove_bad_delegation(inode, stateid);
+}
+
+/**
* nfs_reap_expired_delegations - reap expired delegations
* @clp: nfs_client to process
*
@@ -1042,11 +1083,10 @@
*/
void nfs_reap_expired_delegations(struct nfs_client *clp)
{
- const struct nfs4_minor_version_ops *ops = clp->cl_mvops;
struct nfs_delegation *delegation;
struct nfs_server *server;
struct inode *inode;
- struct rpc_cred *cred;
+ const struct cred *cred;
nfs4_stateid stateid;
restart:
@@ -1054,10 +1094,11 @@
list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) {
list_for_each_entry_rcu(delegation, &server->delegations,
super_list) {
- if (test_bit(NFS_DELEGATION_RETURNING,
- &delegation->flags))
- continue;
- if (test_bit(NFS_DELEGATION_TEST_EXPIRED,
+ if (test_bit(NFS_DELEGATION_INODE_FREEING,
+ &delegation->flags) ||
+ test_bit(NFS_DELEGATION_RETURNING,
+ &delegation->flags) ||
+ test_bit(NFS_DELEGATION_TEST_EXPIRED,
&delegation->flags) == 0)
continue;
if (!nfs_sb_active(server->super))
@@ -1068,16 +1109,12 @@
nfs_sb_deactive(server->super);
goto restart;
}
- cred = get_rpccred_rcu(delegation->cred);
+ cred = get_cred_rcu(delegation->cred);
nfs4_stateid_copy(&stateid, &delegation->stateid);
clear_bit(NFS_DELEGATION_TEST_EXPIRED, &delegation->flags);
rcu_read_unlock();
- if (cred != NULL &&
- ops->test_and_free_expired(server, &stateid, cred) < 0) {
- nfs_revoke_delegation(inode, &stateid);
- nfs_inode_find_state_and_recover(inode, &stateid);
- }
- put_rpccred(cred);
+ nfs_delegation_test_free_expired(inode, &stateid, cred);
+ put_cred(cred);
if (nfs4_server_rebooted(clp)) {
nfs_inode_mark_test_expired_delegation(server,inode);
iput(inode);
@@ -1154,7 +1191,7 @@
if (delegation != NULL &&
nfs4_stateid_match_other(dst, &delegation->stateid)) {
dst->seqid = delegation->stateid.seqid;
- return ret;
+ ret = true;
}
rcu_read_unlock();
out:
@@ -1172,7 +1209,7 @@
* otherwise "false" is returned.
*/
bool nfs4_copy_delegation_stateid(struct inode *inode, fmode_t flags,
- nfs4_stateid *dst, struct rpc_cred **cred)
+ nfs4_stateid *dst, const struct cred **cred)
{
struct nfs_inode *nfsi = NFS_I(inode);
struct nfs_delegation *delegation;
@@ -1186,7 +1223,7 @@
nfs4_stateid_copy(dst, &delegation->stateid);
nfs_mark_delegation_referenced(delegation);
if (cred)
- *cred = get_rpccred(delegation->cred);
+ *cred = get_cred(delegation->cred);
}
rcu_read_unlock();
return ret;
diff --git a/fs/nfs/delegation.h b/fs/nfs/delegation.h
index bb1ef8c..8b14d44 100644
--- a/fs/nfs/delegation.h
+++ b/fs/nfs/delegation.h
@@ -15,7 +15,7 @@
*/
struct nfs_delegation {
struct list_head super_list;
- struct rpc_cred *cred;
+ const struct cred *cred;
struct inode *inode;
nfs4_stateid stateid;
fmode_t type;
@@ -34,11 +34,12 @@
NFS_DELEGATION_RETURNING,
NFS_DELEGATION_REVOKED,
NFS_DELEGATION_TEST_EXPIRED,
+ NFS_DELEGATION_INODE_FREEING,
};
-int nfs_inode_set_delegation(struct inode *inode, struct rpc_cred *cred,
+int nfs_inode_set_delegation(struct inode *inode, const struct cred *cred,
fmode_t type, const nfs4_stateid *stateid, unsigned long pagemod_limit);
-void nfs_inode_reclaim_delegation(struct inode *inode, struct rpc_cred *cred,
+void nfs_inode_reclaim_delegation(struct inode *inode, const struct cred *cred,
fmode_t type, const nfs4_stateid *stateid, unsigned long pagemod_limit);
int nfs4_inode_return_delegation(struct inode *inode);
int nfs_async_inode_return_delegation(struct inode *inode, const nfs4_stateid *stateid);
@@ -57,15 +58,17 @@
void nfs_delegation_reap_unclaimed(struct nfs_client *clp);
void nfs_mark_test_expired_all_delegations(struct nfs_client *clp);
+void nfs_test_expired_all_delegations(struct nfs_client *clp);
void nfs_reap_expired_delegations(struct nfs_client *clp);
/* NFSv4 delegation-related procedures */
-int nfs4_proc_delegreturn(struct inode *inode, struct rpc_cred *cred, const nfs4_stateid *stateid, int issync);
-int nfs4_open_delegation_recall(struct nfs_open_context *ctx, struct nfs4_state *state, const nfs4_stateid *stateid, fmode_t type);
+int nfs4_proc_delegreturn(struct inode *inode, const struct cred *cred, const nfs4_stateid *stateid, int issync);
+int nfs4_open_delegation_recall(struct nfs_open_context *ctx, struct nfs4_state *state, const nfs4_stateid *stateid);
int nfs4_lock_delegation_recall(struct file_lock *fl, struct nfs4_state *state, const nfs4_stateid *stateid);
-bool nfs4_copy_delegation_stateid(struct inode *inode, fmode_t flags, nfs4_stateid *dst, struct rpc_cred **cred);
+bool nfs4_copy_delegation_stateid(struct inode *inode, fmode_t flags, nfs4_stateid *dst, const struct cred **cred);
bool nfs4_refresh_delegation_stateid(nfs4_stateid *dst, struct inode *inode);
+struct nfs_delegation *nfs4_get_valid_delegation(const struct inode *inode);
void nfs_mark_delegation_referenced(struct nfs_delegation *delegation);
int nfs4_have_delegation(struct inode *inode, fmode_t flags);
int nfs4_check_delegation(struct inode *inode, fmode_t flags);
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 8bfaa65..e180033 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* linux/fs/nfs/dir.c
*
@@ -67,7 +68,7 @@
.freepage = nfs_readdir_clear_array,
};
-static struct nfs_open_dir_context *alloc_nfs_open_dir_context(struct inode *dir, struct rpc_cred *cred)
+static struct nfs_open_dir_context *alloc_nfs_open_dir_context(struct inode *dir, const struct cred *cred)
{
struct nfs_inode *nfsi = NFS_I(dir);
struct nfs_open_dir_context *ctx;
@@ -77,8 +78,12 @@
ctx->attr_gencount = nfsi->attr_gencount;
ctx->dir_cookie = 0;
ctx->dup_cookie = 0;
- ctx->cred = get_rpccred(cred);
+ ctx->cred = get_cred(cred);
spin_lock(&dir->i_lock);
+ if (list_empty(&nfsi->open_files) &&
+ (nfsi->cache_validity & NFS_INO_DATA_INVAL_DEFER))
+ nfsi->cache_validity |= NFS_INO_INVALID_DATA |
+ NFS_INO_REVAL_FORCED;
list_add(&ctx->list, &nfsi->open_files);
spin_unlock(&dir->i_lock);
return ctx;
@@ -91,7 +96,7 @@
spin_lock(&dir->i_lock);
list_del(&ctx->list);
spin_unlock(&dir->i_lock);
- put_rpccred(ctx->cred);
+ put_cred(ctx->cred);
kfree(ctx);
}
@@ -103,23 +108,18 @@
{
int res = 0;
struct nfs_open_dir_context *ctx;
- struct rpc_cred *cred;
dfprintk(FILE, "NFS: open dir(%pD2)\n", filp);
nfs_inc_stats(inode, NFSIOS_VFSOPEN);
- cred = rpc_lookup_cred();
- if (IS_ERR(cred))
- return PTR_ERR(cred);
- ctx = alloc_nfs_open_dir_context(inode, cred);
+ ctx = alloc_nfs_open_dir_context(inode, current_cred());
if (IS_ERR(ctx)) {
res = PTR_ERR(ctx);
goto out;
}
filp->private_data = ctx;
out:
- put_rpccred(cred);
return res;
}
@@ -334,7 +334,7 @@
struct nfs_entry *entry, struct file *file, struct inode *inode)
{
struct nfs_open_dir_context *ctx = file->private_data;
- struct rpc_cred *cred = ctx->cred;
+ const struct cred *cred = ctx->cred;
unsigned long timestamp, gencount;
int error;
@@ -579,8 +579,8 @@
}
/*
- * nfs_readdir_large_page will allocate pages that must be freed with a call
- * to nfs_readdir_free_pagearray
+ * nfs_readdir_alloc_pages() will allocate pages that must be freed with a call
+ * to nfs_readdir_free_pages()
*/
static
int nfs_readdir_alloc_pages(struct page **pages, unsigned int npages)
@@ -664,8 +664,9 @@
* We only need to convert from xdr once so future lookups are much simpler
*/
static
-int nfs_readdir_filler(nfs_readdir_descriptor_t *desc, struct page* page)
+int nfs_readdir_filler(void *data, struct page* page)
{
+ nfs_readdir_descriptor_t *desc = data;
struct inode *inode = file_inode(desc->file);
int ret;
@@ -697,8 +698,8 @@
static
struct page *get_cache_page(nfs_readdir_descriptor_t *desc)
{
- return read_cache_page(desc->file->f_mapping,
- desc->page_index, (filler_t *)nfs_readdir_filler, desc);
+ return read_cache_page(desc->file->f_mapping, desc->page_index,
+ nfs_readdir_filler, desc);
}
/*
@@ -950,7 +951,7 @@
/**
* nfs_force_lookup_revalidate - Mark the directory as having changed
- * @dir - pointer to directory inode
+ * @dir: pointer to directory inode
*
* This forces the revalidation code in nfs_lookup_revalidate() to do a
* full lookup on all child dentries of 'dir' whenever a change occurs
@@ -1072,6 +1073,100 @@
return !nfs_check_verifier(dir, dentry, flags & LOOKUP_RCU);
}
+static int
+nfs_lookup_revalidate_done(struct inode *dir, struct dentry *dentry,
+ struct inode *inode, int error)
+{
+ switch (error) {
+ case 1:
+ dfprintk(LOOKUPCACHE, "NFS: %s(%pd2) is valid\n",
+ __func__, dentry);
+ return 1;
+ case 0:
+ nfs_mark_for_revalidate(dir);
+ if (inode && S_ISDIR(inode->i_mode)) {
+ /* Purge readdir caches. */
+ nfs_zap_caches(inode);
+ /*
+ * We can't d_drop the root of a disconnected tree:
+ * its d_hash is on the s_anon list and d_drop() would hide
+ * it from shrink_dcache_for_unmount(), leading to busy
+ * inodes on unmount and further oopses.
+ */
+ if (IS_ROOT(dentry))
+ return 1;
+ }
+ dfprintk(LOOKUPCACHE, "NFS: %s(%pd2) is invalid\n",
+ __func__, dentry);
+ return 0;
+ }
+ dfprintk(LOOKUPCACHE, "NFS: %s(%pd2) lookup returned error %d\n",
+ __func__, dentry, error);
+ return error;
+}
+
+static int
+nfs_lookup_revalidate_negative(struct inode *dir, struct dentry *dentry,
+ unsigned int flags)
+{
+ int ret = 1;
+ if (nfs_neg_need_reval(dir, dentry, flags)) {
+ if (flags & LOOKUP_RCU)
+ return -ECHILD;
+ ret = 0;
+ }
+ return nfs_lookup_revalidate_done(dir, dentry, NULL, ret);
+}
+
+static int
+nfs_lookup_revalidate_delegated(struct inode *dir, struct dentry *dentry,
+ struct inode *inode)
+{
+ nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
+ return nfs_lookup_revalidate_done(dir, dentry, inode, 1);
+}
+
+static int
+nfs_lookup_revalidate_dentry(struct inode *dir, struct dentry *dentry,
+ struct inode *inode)
+{
+ struct nfs_fh *fhandle;
+ struct nfs_fattr *fattr;
+ struct nfs4_label *label;
+ int ret;
+
+ ret = -ENOMEM;
+ fhandle = nfs_alloc_fhandle();
+ fattr = nfs_alloc_fattr();
+ label = nfs4_label_alloc(NFS_SERVER(inode), GFP_KERNEL);
+ if (fhandle == NULL || fattr == NULL || IS_ERR(label))
+ goto out;
+
+ ret = NFS_PROTO(dir)->lookup(dir, &dentry->d_name, fhandle, fattr, label);
+ if (ret < 0) {
+ if (ret == -ESTALE || ret == -ENOENT)
+ ret = 0;
+ goto out;
+ }
+ ret = 0;
+ if (nfs_compare_fh(NFS_FH(inode), fhandle))
+ goto out;
+ if (nfs_refresh_inode(inode, fattr) < 0)
+ goto out;
+
+ nfs_setsecurity(inode, fattr, label);
+ nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
+
+ /* set a readdirplus hint that we had a cache miss */
+ nfs_force_use_readdirplus(dir);
+ ret = 1;
+out:
+ nfs_free_fattr(fattr);
+ nfs_free_fhandle(fhandle);
+ nfs4_label_free(label);
+ return nfs_lookup_revalidate_done(dir, dentry, inode, ret);
+}
+
/*
* This is called every time the dcache has a lookup hit,
* and we should check whether we can really trust that
@@ -1083,58 +1178,36 @@
* If the parent directory is seen to have changed, we throw out the
* cached dentry and do a new lookup.
*/
-static int nfs_lookup_revalidate(struct dentry *dentry, unsigned int flags)
+static int
+nfs_do_lookup_revalidate(struct inode *dir, struct dentry *dentry,
+ unsigned int flags)
{
- struct inode *dir;
struct inode *inode;
- struct dentry *parent;
- struct nfs_fh *fhandle = NULL;
- struct nfs_fattr *fattr = NULL;
- struct nfs4_label *label = NULL;
int error;
- if (flags & LOOKUP_RCU) {
- parent = READ_ONCE(dentry->d_parent);
- dir = d_inode_rcu(parent);
- if (!dir)
- return -ECHILD;
- } else {
- parent = dget_parent(dentry);
- dir = d_inode(parent);
- }
nfs_inc_stats(dir, NFSIOS_DENTRYREVALIDATE);
inode = d_inode(dentry);
- if (!inode) {
- if (nfs_neg_need_reval(dir, dentry, flags)) {
- if (flags & LOOKUP_RCU)
- return -ECHILD;
- goto out_bad;
- }
- goto out_valid;
- }
+ if (!inode)
+ return nfs_lookup_revalidate_negative(dir, dentry, flags);
if (is_bad_inode(inode)) {
- if (flags & LOOKUP_RCU)
- return -ECHILD;
dfprintk(LOOKUPCACHE, "%s: %pd2 has dud inode\n",
__func__, dentry);
goto out_bad;
}
if (NFS_PROTO(dir)->have_delegation(inode, FMODE_READ))
- goto out_set_verifier;
+ return nfs_lookup_revalidate_delegated(dir, dentry, inode);
/* Force a full look up iff the parent directory has changed */
if (!(flags & (LOOKUP_EXCL | LOOKUP_REVAL)) &&
nfs_check_verifier(dir, dentry, flags & LOOKUP_RCU)) {
error = nfs_lookup_verify_inode(inode, flags);
if (error) {
- if (flags & LOOKUP_RCU)
- return -ECHILD;
if (error == -ESTALE)
- goto out_zap_parent;
- goto out_error;
+ nfs_zap_caches(dir);
+ goto out_bad;
}
nfs_advise_use_readdirplus(dir);
goto out_valid;
@@ -1146,81 +1219,45 @@
if (NFS_STALE(inode))
goto out_bad;
- error = -ENOMEM;
- fhandle = nfs_alloc_fhandle();
- fattr = nfs_alloc_fattr();
- if (fhandle == NULL || fattr == NULL)
- goto out_error;
-
- label = nfs4_label_alloc(NFS_SERVER(inode), GFP_NOWAIT);
- if (IS_ERR(label))
- goto out_error;
-
trace_nfs_lookup_revalidate_enter(dir, dentry, flags);
- error = NFS_PROTO(dir)->lookup(dir, &dentry->d_name, fhandle, fattr, label);
+ error = nfs_lookup_revalidate_dentry(dir, dentry, inode);
trace_nfs_lookup_revalidate_exit(dir, dentry, flags, error);
- if (error == -ESTALE || error == -ENOENT)
- goto out_bad;
- if (error)
- goto out_error;
- if (nfs_compare_fh(NFS_FH(inode), fhandle))
- goto out_bad;
- if ((error = nfs_refresh_inode(inode, fattr)) != 0)
- goto out_bad;
+ return error;
+out_valid:
+ return nfs_lookup_revalidate_done(dir, dentry, inode, 1);
+out_bad:
+ if (flags & LOOKUP_RCU)
+ return -ECHILD;
+ return nfs_lookup_revalidate_done(dir, dentry, inode, 0);
+}
- nfs_setsecurity(inode, fattr, label);
+static int
+__nfs_lookup_revalidate(struct dentry *dentry, unsigned int flags,
+ int (*reval)(struct inode *, struct dentry *, unsigned int))
+{
+ struct dentry *parent;
+ struct inode *dir;
+ int ret;
- nfs_free_fattr(fattr);
- nfs_free_fhandle(fhandle);
- nfs4_label_free(label);
-
- /* set a readdirplus hint that we had a cache miss */
- nfs_force_use_readdirplus(dir);
-
-out_set_verifier:
- nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
- out_valid:
if (flags & LOOKUP_RCU) {
+ parent = READ_ONCE(dentry->d_parent);
+ dir = d_inode_rcu(parent);
+ if (!dir)
+ return -ECHILD;
+ ret = reval(dir, dentry, flags);
if (parent != READ_ONCE(dentry->d_parent))
return -ECHILD;
- } else
+ } else {
+ parent = dget_parent(dentry);
+ ret = reval(d_inode(parent), dentry, flags);
dput(parent);
- dfprintk(LOOKUPCACHE, "NFS: %s(%pd2) is valid\n",
- __func__, dentry);
- return 1;
-out_zap_parent:
- nfs_zap_caches(dir);
- out_bad:
- WARN_ON(flags & LOOKUP_RCU);
- nfs_free_fattr(fattr);
- nfs_free_fhandle(fhandle);
- nfs4_label_free(label);
- nfs_mark_for_revalidate(dir);
- if (inode && S_ISDIR(inode->i_mode)) {
- /* Purge readdir caches. */
- nfs_zap_caches(inode);
- /*
- * We can't d_drop the root of a disconnected tree:
- * its d_hash is on the s_anon list and d_drop() would hide
- * it from shrink_dcache_for_unmount(), leading to busy
- * inodes on unmount and further oopses.
- */
- if (IS_ROOT(dentry))
- goto out_valid;
}
- dput(parent);
- dfprintk(LOOKUPCACHE, "NFS: %s(%pd2) is invalid\n",
- __func__, dentry);
- return 0;
-out_error:
- WARN_ON(flags & LOOKUP_RCU);
- nfs_free_fattr(fattr);
- nfs_free_fhandle(fhandle);
- nfs4_label_free(label);
- dput(parent);
- dfprintk(LOOKUPCACHE, "NFS: %s(%pd2) lookup returned error %d\n",
- __func__, dentry, error);
- return error;
+ return ret;
+}
+
+static int nfs_lookup_revalidate(struct dentry *dentry, unsigned int flags)
+{
+ return __nfs_lookup_revalidate(dentry, flags, nfs_do_lookup_revalidate);
}
/*
@@ -1450,7 +1487,7 @@
if (S_ISREG(file->f_path.dentry->d_inode->i_mode))
nfs_file_set_open_context(file, ctx);
else
- err = -ESTALE;
+ err = -EOPENSTALE;
out:
return err;
}
@@ -1579,70 +1616,61 @@
}
EXPORT_SYMBOL_GPL(nfs_atomic_open);
-static int nfs4_lookup_revalidate(struct dentry *dentry, unsigned int flags)
+static int
+nfs4_do_lookup_revalidate(struct inode *dir, struct dentry *dentry,
+ unsigned int flags)
{
struct inode *inode;
- int ret = 0;
if (!(flags & LOOKUP_OPEN) || (flags & LOOKUP_DIRECTORY))
- goto no_open;
+ goto full_reval;
if (d_mountpoint(dentry))
- goto no_open;
- if (NFS_SB(dentry->d_sb)->caps & NFS_CAP_ATOMIC_OPEN_V1)
- goto no_open;
+ goto full_reval;
inode = d_inode(dentry);
/* We can't create new files in nfs_open_revalidate(), so we
* optimize away revalidation of negative dentries.
*/
- if (inode == NULL) {
- struct dentry *parent;
- struct inode *dir;
+ if (inode == NULL)
+ goto full_reval;
- if (flags & LOOKUP_RCU) {
- parent = READ_ONCE(dentry->d_parent);
- dir = d_inode_rcu(parent);
- if (!dir)
- return -ECHILD;
- } else {
- parent = dget_parent(dentry);
- dir = d_inode(parent);
- }
- if (!nfs_neg_need_reval(dir, dentry, flags))
- ret = 1;
- else if (flags & LOOKUP_RCU)
- ret = -ECHILD;
- if (!(flags & LOOKUP_RCU))
- dput(parent);
- else if (parent != READ_ONCE(dentry->d_parent))
- return -ECHILD;
- goto out;
- }
+ if (NFS_PROTO(dir)->have_delegation(inode, FMODE_READ))
+ return nfs_lookup_revalidate_delegated(dir, dentry, inode);
/* NFS only supports OPEN on regular files */
if (!S_ISREG(inode->i_mode))
- goto no_open;
+ goto full_reval;
+
/* We cannot do exclusive creation on a positive dentry */
- if (flags & LOOKUP_EXCL)
- goto no_open;
+ if (flags & (LOOKUP_EXCL | LOOKUP_REVAL))
+ goto reval_dentry;
+
+ /* Check if the directory changed */
+ if (!nfs_check_verifier(dir, dentry, flags & LOOKUP_RCU))
+ goto reval_dentry;
/* Let f_op->open() actually open (and revalidate) the file */
- ret = 1;
+ return 1;
+reval_dentry:
+ if (flags & LOOKUP_RCU)
+ return -ECHILD;
+ return nfs_lookup_revalidate_dentry(dir, dentry, inode);
-out:
- return ret;
+full_reval:
+ return nfs_do_lookup_revalidate(dir, dentry, flags);
+}
-no_open:
- return nfs_lookup_revalidate(dentry, flags);
+static int nfs4_lookup_revalidate(struct dentry *dentry, unsigned int flags)
+{
+ return __nfs_lookup_revalidate(dentry, flags,
+ nfs4_do_lookup_revalidate);
}
#endif /* CONFIG_NFSV4 */
-/*
- * Code common to create, mkdir, and mknod.
- */
-int nfs_instantiate(struct dentry *dentry, struct nfs_fh *fhandle,
+struct dentry *
+nfs_add_or_obtain(struct dentry *dentry, struct nfs_fh *fhandle,
struct nfs_fattr *fattr,
struct nfs4_label *label)
{
@@ -1650,13 +1678,10 @@
struct inode *dir = d_inode(parent);
struct inode *inode;
struct dentry *d;
- int error = -EACCES;
+ int error;
d_drop(dentry);
- /* We may have been initialized further down */
- if (d_really_is_positive(dentry))
- goto out;
if (fhandle->size == 0) {
error = NFS_PROTO(dir)->lookup(dir, &dentry->d_name, fhandle, fattr, NULL);
if (error)
@@ -1672,18 +1697,32 @@
}
inode = nfs_fhget(dentry->d_sb, fhandle, fattr, label);
d = d_splice_alias(inode, dentry);
- if (IS_ERR(d)) {
- error = PTR_ERR(d);
- goto out_error;
- }
- dput(d);
out:
dput(parent);
- return 0;
+ return d;
out_error:
nfs_mark_for_revalidate(dir);
- dput(parent);
- return error;
+ d = ERR_PTR(error);
+ goto out;
+}
+EXPORT_SYMBOL_GPL(nfs_add_or_obtain);
+
+/*
+ * Code common to create, mkdir, and mknod.
+ */
+int nfs_instantiate(struct dentry *dentry, struct nfs_fh *fhandle,
+ struct nfs_fattr *fattr,
+ struct nfs4_label *label)
+{
+ struct dentry *d;
+
+ d = nfs_add_or_obtain(dentry, fhandle, fattr, label);
+ if (IS_ERR(d))
+ return PTR_ERR(d);
+
+ /* Callers don't care */
+ dput(d);
+ return 0;
}
EXPORT_SYMBOL_GPL(nfs_instantiate);
@@ -2110,7 +2149,7 @@
static void nfs_access_free_entry(struct nfs_access_entry *entry)
{
- put_rpccred(entry->cred);
+ put_cred(entry->cred);
kfree_rcu(entry, rcu_head);
smp_mb__before_atomic();
atomic_long_dec(&nfs_access_nr_entries);
@@ -2236,17 +2275,18 @@
}
EXPORT_SYMBOL_GPL(nfs_access_zap_cache);
-static struct nfs_access_entry *nfs_access_search_rbtree(struct inode *inode, struct rpc_cred *cred)
+static struct nfs_access_entry *nfs_access_search_rbtree(struct inode *inode, const struct cred *cred)
{
struct rb_node *n = NFS_I(inode)->access_cache.rb_node;
- struct nfs_access_entry *entry;
while (n != NULL) {
- entry = rb_entry(n, struct nfs_access_entry, rb_node);
+ struct nfs_access_entry *entry =
+ rb_entry(n, struct nfs_access_entry, rb_node);
+ int cmp = cred_fscmp(cred, entry->cred);
- if (cred < entry->cred)
+ if (cmp < 0)
n = n->rb_left;
- else if (cred > entry->cred)
+ else if (cmp > 0)
n = n->rb_right;
else
return entry;
@@ -2254,7 +2294,7 @@
return NULL;
}
-static int nfs_access_get_cached(struct inode *inode, struct rpc_cred *cred, struct nfs_access_entry *res, bool may_block)
+static int nfs_access_get_cached(struct inode *inode, const struct cred *cred, struct nfs_access_entry *res, bool may_block)
{
struct nfs_inode *nfsi = NFS_I(inode);
struct nfs_access_entry *cache;
@@ -2297,7 +2337,7 @@
return -ENOENT;
}
-static int nfs_access_get_cached_rcu(struct inode *inode, struct rpc_cred *cred, struct nfs_access_entry *res)
+static int nfs_access_get_cached_rcu(struct inode *inode, const struct cred *cred, struct nfs_access_entry *res)
{
/* Only check the most recently returned cache entry,
* but do it without locking.
@@ -2334,15 +2374,17 @@
struct rb_node **p = &root_node->rb_node;
struct rb_node *parent = NULL;
struct nfs_access_entry *entry;
+ int cmp;
spin_lock(&inode->i_lock);
while (*p != NULL) {
parent = *p;
entry = rb_entry(parent, struct nfs_access_entry, rb_node);
+ cmp = cred_fscmp(set->cred, entry->cred);
- if (set->cred < entry->cred)
+ if (cmp < 0)
p = &parent->rb_left;
- else if (set->cred > entry->cred)
+ else if (cmp > 0)
p = &parent->rb_right;
else
goto found;
@@ -2366,7 +2408,7 @@
if (cache == NULL)
return;
RB_CLEAR_NODE(&cache->rb_node);
- cache->cred = get_rpccred(set->cred);
+ cache->cred = get_cred(set->cred);
cache->mask = set->mask;
/* The above field assignments must be visible
@@ -2430,7 +2472,7 @@
}
EXPORT_SYMBOL_GPL(nfs_access_set_mask);
-static int nfs_do_access(struct inode *inode, struct rpc_cred *cred, int mask)
+static int nfs_do_access(struct inode *inode, const struct cred *cred, int mask)
{
struct nfs_access_entry cache;
bool may_block = (mask & MAY_NOT_BLOCK) == 0;
@@ -2494,7 +2536,7 @@
return mask;
}
-int nfs_may_open(struct inode *inode, struct rpc_cred *cred, int openflags)
+int nfs_may_open(struct inode *inode, const struct cred *cred, int openflags)
{
return nfs_do_access(inode, cred, nfs_open_permission_mask(openflags));
}
@@ -2519,7 +2561,7 @@
int nfs_permission(struct inode *inode, int mask)
{
- struct rpc_cred *cred;
+ const struct cred *cred = current_cred();
int res = 0;
nfs_inc_stats(inode, NFSIOS_VFSACCESS);
@@ -2553,20 +2595,11 @@
/* Always try fast lookups first */
rcu_read_lock();
- cred = rpc_lookup_cred_nonblock();
- if (!IS_ERR(cred))
- res = nfs_do_access(inode, cred, mask|MAY_NOT_BLOCK);
- else
- res = PTR_ERR(cred);
+ res = nfs_do_access(inode, cred, mask|MAY_NOT_BLOCK);
rcu_read_unlock();
if (res == -ECHILD && !(mask & MAY_NOT_BLOCK)) {
/* Fast lookup failed, try the slow way */
- cred = rpc_lookup_cred();
- if (!IS_ERR(cred)) {
- res = nfs_do_access(inode, cred, mask);
- put_rpccred(cred);
- } else
- res = PTR_ERR(cred);
+ res = nfs_do_access(inode, cred, mask);
}
out:
if (!res && (mask & MAY_EXEC))
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index 33824a0..040a50f 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* linux/fs/nfs/direct.c
*
@@ -63,13 +64,6 @@
static struct kmem_cache *nfs_direct_cachep;
-/*
- * This represents a set of asynchronous requests that we're waiting on
- */
-struct nfs_direct_mirror {
- ssize_t count;
-};
-
struct nfs_direct_req {
struct kref kref; /* release manager */
@@ -83,9 +77,6 @@
atomic_t io_count; /* i/os we're waiting for */
spinlock_t lock; /* protect completion state */
- struct nfs_direct_mirror mirrors[NFS_PAGEIO_DESCRIPTOR_MIRROR_MAX];
- int mirror_count;
-
loff_t io_start; /* Start offset for I/O */
ssize_t count, /* bytes actually processed */
max_count, /* max expected count */
@@ -122,34 +113,44 @@
}
static void
-nfs_direct_good_bytes(struct nfs_direct_req *dreq, struct nfs_pgio_header *hdr)
+nfs_direct_handle_truncated(struct nfs_direct_req *dreq,
+ const struct nfs_pgio_header *hdr,
+ ssize_t dreq_len)
{
- int i;
- ssize_t count;
+ if (!(test_bit(NFS_IOHDR_ERROR, &hdr->flags) ||
+ test_bit(NFS_IOHDR_EOF, &hdr->flags)))
+ return;
+ if (dreq->max_count >= dreq_len) {
+ dreq->max_count = dreq_len;
+ if (dreq->count > dreq_len)
+ dreq->count = dreq_len;
- WARN_ON_ONCE(dreq->count >= dreq->max_count);
-
- if (dreq->mirror_count == 1) {
- dreq->mirrors[hdr->pgio_mirror_idx].count += hdr->good_bytes;
- dreq->count += hdr->good_bytes;
- } else {
- /* mirrored writes */
- count = dreq->mirrors[hdr->pgio_mirror_idx].count;
- if (count + dreq->io_start < hdr->io_start + hdr->good_bytes) {
- count = hdr->io_start + hdr->good_bytes - dreq->io_start;
- dreq->mirrors[hdr->pgio_mirror_idx].count = count;
- }
- /* update the dreq->count by finding the minimum agreed count from all
- * mirrors */
- count = dreq->mirrors[0].count;
-
- for (i = 1; i < dreq->mirror_count; i++)
- count = min(count, dreq->mirrors[i].count);
-
- dreq->count = count;
+ if (test_bit(NFS_IOHDR_ERROR, &hdr->flags))
+ dreq->error = hdr->error;
+ else /* Clear outstanding error if this is EOF */
+ dreq->error = 0;
}
}
+static void
+nfs_direct_count_bytes(struct nfs_direct_req *dreq,
+ const struct nfs_pgio_header *hdr)
+{
+ loff_t hdr_end = hdr->io_start + hdr->good_bytes;
+ ssize_t dreq_len = 0;
+
+ if (hdr_end > dreq->io_start)
+ dreq_len = hdr_end - dreq->io_start;
+
+ nfs_direct_handle_truncated(dreq, hdr, dreq_len);
+
+ if (dreq_len > dreq->max_count)
+ dreq_len = dreq->max_count;
+
+ if (dreq->count < dreq_len)
+ dreq->count = dreq_len;
+}
+
/*
* nfs_direct_select_verf - select the right verifier
* @dreq - direct request possibly spanning multiple servers
@@ -292,18 +293,6 @@
cinfo->completion_ops = &nfs_direct_commit_completion_ops;
}
-static inline void nfs_direct_setup_mirroring(struct nfs_direct_req *dreq,
- struct nfs_pageio_descriptor *pgio,
- struct nfs_page *req)
-{
- int mirror_count = 1;
-
- if (pgio->pg_ops->pg_get_mirror_count)
- mirror_count = pgio->pg_ops->pg_get_mirror_count(pgio, req);
-
- dreq->mirror_count = mirror_count;
-}
-
static inline struct nfs_direct_req *nfs_direct_req_alloc(void)
{
struct nfs_direct_req *dreq;
@@ -318,7 +307,6 @@
INIT_LIST_HEAD(&dreq->mds_cinfo.list);
dreq->verf.committed = NFS_INVALID_STABLE_HOW; /* not set yet */
INIT_WORK(&dreq->work, nfs_direct_write_schedule_work);
- dreq->mirror_count = 1;
spin_lock_init(&dreq->lock);
return dreq;
@@ -400,15 +388,13 @@
unsigned long bytes = 0;
struct nfs_direct_req *dreq = hdr->dreq;
- if (test_bit(NFS_IOHDR_REDO, &hdr->flags))
- goto out_put;
-
spin_lock(&dreq->lock);
- if (test_bit(NFS_IOHDR_ERROR, &hdr->flags) && (hdr->good_bytes == 0))
- dreq->error = hdr->error;
- else
- nfs_direct_good_bytes(dreq, hdr);
+ if (test_bit(NFS_IOHDR_REDO, &hdr->flags)) {
+ spin_unlock(&dreq->lock);
+ goto out_put;
+ }
+ nfs_direct_count_bytes(dreq, hdr);
spin_unlock(&dreq->lock);
while (!list_empty(&hdr->pages)) {
@@ -428,7 +414,7 @@
hdr->release(hdr);
}
-static void nfs_read_sync_pgio_error(struct list_head *head)
+static void nfs_read_sync_pgio_error(struct list_head *head, int error)
{
struct nfs_page *req;
@@ -492,7 +478,7 @@
struct nfs_page *req;
unsigned int req_len = min_t(size_t, bytes, PAGE_SIZE - pgbase);
/* XXX do we need to do the eof zeroing found in async_filler? */
- req = nfs_create_request(dreq->ctx, pagevec[i], NULL,
+ req = nfs_create_request(dreq->ctx, pagevec[i],
pgbase, req_len);
if (IS_ERR(req)) {
result = PTR_ERR(req);
@@ -639,33 +625,27 @@
LIST_HEAD(reqs);
struct nfs_commit_info cinfo;
LIST_HEAD(failed);
- int i;
nfs_init_cinfo_from_dreq(&cinfo, dreq);
nfs_direct_write_scan_commit_list(dreq->inode, &reqs, &cinfo);
dreq->count = 0;
+ dreq->max_count = 0;
+ list_for_each_entry(req, &reqs, wb_list)
+ dreq->max_count += req->wb_bytes;
dreq->verf.committed = NFS_INVALID_STABLE_HOW;
nfs_clear_pnfs_ds_commit_verifiers(&dreq->ds_cinfo);
- for (i = 0; i < dreq->mirror_count; i++)
- dreq->mirrors[i].count = 0;
get_dreq(dreq);
nfs_pageio_init_write(&desc, dreq->inode, FLUSH_STABLE, false,
&nfs_direct_write_completion_ops);
desc.pg_dreq = dreq;
- req = nfs_list_entry(reqs.next);
- nfs_direct_setup_mirroring(dreq, &desc, req);
- if (desc.pg_error < 0) {
- list_splice_init(&reqs, &failed);
- goto out_failed;
- }
-
list_for_each_entry_safe(req, tmp, &reqs, wb_list) {
+ /* Bump the transmission count */
+ req->wb_nio++;
if (!nfs_pageio_add_request(&desc, req)) {
- nfs_list_remove_request(req);
- nfs_list_add_request(req, &failed);
+ nfs_list_move_request(req, &failed);
spin_lock(&cinfo.inode->i_lock);
dreq->flags = 0;
if (desc.pg_error < 0)
@@ -678,7 +658,6 @@
}
nfs_pageio_complete(&desc);
-out_failed:
while (!list_empty(&failed)) {
req = nfs_list_entry(failed.next);
nfs_list_remove_request(req);
@@ -704,6 +683,11 @@
req = nfs_list_entry(data->pages.next);
nfs_list_remove_request(req);
if (dreq->flags == NFS_ODIRECT_RESCHED_WRITES) {
+ /*
+ * Despite the reboot, the write was successful,
+ * so reset wb_nio.
+ */
+ req->wb_nio = 0;
/* Note the rewrite will go through mds */
nfs_mark_request_commit(req, NULL, &cinfo, 0);
} else
@@ -775,17 +759,16 @@
bool request_commit = false;
struct nfs_page *req = nfs_list_entry(hdr->pages.next);
- if (test_bit(NFS_IOHDR_REDO, &hdr->flags))
- goto out_put;
-
nfs_init_cinfo_from_dreq(&cinfo, dreq);
spin_lock(&dreq->lock);
+ if (test_bit(NFS_IOHDR_REDO, &hdr->flags)) {
+ spin_unlock(&dreq->lock);
+ goto out_put;
+ }
- if (test_bit(NFS_IOHDR_ERROR, &hdr->flags))
- dreq->error = hdr->error;
- if (dreq->error == 0) {
- nfs_direct_good_bytes(dreq, hdr);
+ nfs_direct_count_bytes(dreq, hdr);
+ if (hdr->good_bytes != 0) {
if (nfs_write_need_commit(hdr)) {
if (dreq->flags == NFS_ODIRECT_RESCHED_WRITES)
request_commit = true;
@@ -821,7 +804,7 @@
hdr->release(hdr);
}
-static void nfs_write_sync_pgio_error(struct list_head *head)
+static void nfs_write_sync_pgio_error(struct list_head *head, int error)
{
struct nfs_page *req;
@@ -900,14 +883,13 @@
struct nfs_page *req;
unsigned int req_len = min_t(size_t, bytes, PAGE_SIZE - pgbase);
- req = nfs_create_request(dreq->ctx, pagevec[i], NULL,
+ req = nfs_create_request(dreq->ctx, pagevec[i],
pgbase, req_len);
if (IS_ERR(req)) {
result = PTR_ERR(req);
break;
}
- nfs_direct_setup_mirroring(dreq, &desc, req);
if (desc.pg_error < 0) {
nfs_free_request(req);
result = desc.pg_error;
diff --git a/fs/nfs/dns_resolve.c b/fs/nfs/dns_resolve.c
index 060c658..aec769a 100644
--- a/fs/nfs/dns_resolve.c
+++ b/fs/nfs/dns_resolve.c
@@ -22,7 +22,8 @@
char *ip_addr = NULL;
int ip_len;
- ip_len = dns_query(NULL, name, namelen, NULL, &ip_addr, NULL);
+ ip_len = dns_query(net, NULL, name, namelen, NULL, &ip_addr, NULL,
+ false);
if (ip_len > 0)
ret = rpc_pton(net, ip_addr, ip_len, sa, salen);
else
@@ -65,6 +66,7 @@
struct sockaddr_storage addr;
size_t addrlen;
+ struct rcu_head rcu_head;
};
@@ -101,13 +103,21 @@
}
}
+static void nfs_dns_ent_free_rcu(struct rcu_head *head)
+{
+ struct nfs_dns_ent *item;
+
+ item = container_of(head, struct nfs_dns_ent, rcu_head);
+ kfree(item->hostname);
+ kfree(item);
+}
+
static void nfs_dns_ent_put(struct kref *ref)
{
struct nfs_dns_ent *item;
item = container_of(ref, struct nfs_dns_ent, h.ref);
- kfree(item->hostname);
- kfree(item);
+ call_rcu(&item->rcu_head, nfs_dns_ent_free_rcu);
}
static struct cache_head *nfs_dns_ent_alloc(void)
@@ -195,7 +205,7 @@
{
struct cache_head *ch;
- ch = sunrpc_cache_lookup(cd,
+ ch = sunrpc_cache_lookup_rcu(cd,
&key->h,
nfs_dns_hash(key));
if (!ch)
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 29553fd..95dc905 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* linux/fs/nfs/file.c
*
@@ -89,8 +90,8 @@
/**
* nfs_revalidate_size - Revalidate the file size
- * @inode - pointer to inode struct
- * @file - pointer to struct file
+ * @inode: pointer to inode struct
+ * @filp: pointer to struct file
*
* Revalidates the file length. This is basically a wrapper around
* nfs_revalidate_inode() that takes into account the fact that we may
@@ -147,7 +148,7 @@
return 0;
/* Flush writes to the server and return any errors */
- return vfs_fsync(file, 0);
+ return nfs_wb_all(inode);
}
ssize_t
@@ -199,13 +200,6 @@
* Flush any dirty pages for this process, and check for write errors.
* The return status from this call provides a reliable indication of
* whether any write errors occurred for this process.
- *
- * Notice that it clears the NFS_CONTEXT_ERROR_WRITE before synching to
- * disk, but it retrieves and clears ctx->error after synching, despite
- * the two being set at the same time in nfs_context_set_write_error().
- * This is because the former is used to notify the _next_ call to
- * nfs_file_write() that a write error occurred, and hence cause it to
- * fall back to doing a synchronous write.
*/
static int
nfs_file_fsync_commit(struct file *file, int datasync)
@@ -220,11 +214,8 @@
nfs_inc_stats(inode, NFSIOS_VFSFSYNC);
do_resend = test_and_clear_bit(NFS_CONTEXT_RESEND_WRITES, &ctx->flags);
status = nfs_commit_inode(inode, FLUSH_SYNC);
- if (test_bit(NFS_CONTEXT_ERROR_WRITE, &ctx->flags)) {
- ret = xchg(&ctx->error, 0);
- if (ret)
- goto out;
- }
+ if (status == 0)
+ status = file_check_and_advance_wb_err(file);
if (status < 0) {
ret = status;
goto out;
@@ -245,13 +236,7 @@
trace_nfs_fsync_enter(inode);
do {
- struct nfs_open_context *ctx = nfs_file_open_context(file);
- ret = filemap_write_and_wait_range(inode->i_mapping, start, end);
- if (test_and_clear_bit(NFS_CONTEXT_ERROR_WRITE, &ctx->flags)) {
- int ret2 = xchg(&ctx->error, 0);
- if (ret2)
- ret = ret2;
- }
+ ret = file_write_and_wait_range(file, start, end);
if (ret != 0)
break;
ret = nfs_file_fsync_commit(file, datasync);
@@ -276,6 +261,12 @@
* then a modify/write/read cycle when writing to a page in the
* page cache.
*
+ * Some pNFS layout drivers can only read/write at a certain block
+ * granularity like all block devices and therefore we must perform
+ * read/modify/write whenever a page hasn't read yet and the data
+ * to be written there is not aligned to a block boundary and/or
+ * smaller than the block size.
+ *
* The modify/write/read cycle may occur if a page is read before
* being completely filled by the writer. In this situation, the
* page must be completely written to stable storage on the server
@@ -291,26 +282,32 @@
* and that the new data won't completely replace the old data in
* that range of the file.
*/
-static int nfs_want_read_modify_write(struct file *file, struct page *page,
- loff_t pos, unsigned len)
+static bool nfs_full_page_write(struct page *page, loff_t pos, unsigned int len)
{
unsigned int pglen = nfs_page_length(page);
unsigned int offset = pos & (PAGE_SIZE - 1);
unsigned int end = offset + len;
- if (pnfs_ld_read_whole_page(file->f_mapping->host)) {
- if (!PageUptodate(page))
- return 1;
- return 0;
- }
+ return !pglen || (end >= pglen && !offset);
+}
- if ((file->f_mode & FMODE_READ) && /* open for read? */
- !PageUptodate(page) && /* Uptodate? */
- !PagePrivate(page) && /* i/o request already? */
- pglen && /* valid bytes of file? */
- (end < pglen || offset)) /* replace all valid bytes? */
- return 1;
- return 0;
+static bool nfs_want_read_modify_write(struct file *file, struct page *page,
+ loff_t pos, unsigned int len)
+{
+ /*
+ * Up-to-date pages, those with ongoing or full-page write
+ * don't need read/modify/write
+ */
+ if (PageUptodate(page) || PagePrivate(page) ||
+ nfs_full_page_write(page, pos, len))
+ return false;
+
+ if (pnfs_ld_read_whole_page(file->f_mapping->host))
+ return true;
+ /* Open for reading too? */
+ if (file->f_mode & FMODE_READ)
+ return true;
+ return false;
}
/*
@@ -588,8 +585,7 @@
struct nfs_open_context *ctx;
ctx = nfs_file_open_context(filp);
- if (test_bit(NFS_CONTEXT_ERROR_WRITE, &ctx->flags) ||
- nfs_ctx_key_to_expire(ctx, inode))
+ if (nfs_ctx_key_to_expire(ctx, inode))
return 1;
return 0;
}
@@ -643,7 +639,7 @@
/* Return error values */
if (nfs_need_check_write(file, inode)) {
- int err = vfs_fsync(file, 0);
+ int err = nfs_wb_all(inode);
if (err < 0)
result = err;
}
@@ -697,7 +693,7 @@
* Flush all pending writes before doing anything
* with locks..
*/
- vfs_fsync(filp, 0);
+ nfs_wb_all(inode);
l_ctx = nfs_get_lock_context(nfs_file_open_context(filp));
if (!IS_ERR(l_ctx)) {
diff --git a/fs/nfs/filelayout/Makefile b/fs/nfs/filelayout/Makefile
index 8516cdf..de05631 100644
--- a/fs/nfs/filelayout/Makefile
+++ b/fs/nfs/filelayout/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
#
# Makefile for the pNFS Files Layout Driver kernel module
#
diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c
index d175724..c9b605f 100644
--- a/fs/nfs/filelayout/filelayout.c
+++ b/fs/nfs/filelayout/filelayout.c
@@ -904,7 +904,7 @@
status = filelayout_check_deviceid(lo, fl, gfp_flags);
if (status) {
pnfs_put_lseg(lseg);
- lseg = ERR_PTR(status);
+ lseg = NULL;
}
out:
return lseg;
@@ -917,7 +917,7 @@
pnfs_generic_pg_check_layout(pgio);
if (!pgio->pg_lseg) {
pgio->pg_lseg = fl_pnfs_update_layout(pgio->pg_inode,
- req->wb_context,
+ nfs_req_openctx(req),
0,
NFS4_MAX_UINT64,
IOMODE_READ,
@@ -944,7 +944,7 @@
pnfs_generic_pg_check_layout(pgio);
if (!pgio->pg_lseg) {
pgio->pg_lseg = fl_pnfs_update_layout(pgio->pg_inode,
- req->wb_context,
+ nfs_req_openctx(req),
0,
NFS4_MAX_UINT64,
IOMODE_RW,
@@ -1164,6 +1164,8 @@
.id = LAYOUT_NFSV4_1_FILES,
.name = "LAYOUT_NFSV4_1_FILES",
.owner = THIS_MODULE,
+ .flags = PNFS_LAYOUTGET_ON_OPEN,
+ .max_layoutget_response = 4096, /* 1 page or so... */
.alloc_layout_hdr = filelayout_alloc_layout_hdr,
.free_layout_hdr = filelayout_free_layout_hdr,
.alloc_lseg = filelayout_alloc_lseg,
diff --git a/fs/nfs/flexfilelayout/Makefile b/fs/nfs/flexfilelayout/Makefile
index 1d2c9f6..49f0342 100644
--- a/fs/nfs/flexfilelayout/Makefile
+++ b/fs/nfs/flexfilelayout/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
#
# Makefile for the pNFS Flexfile Layout Driver kernel module
#
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c
index e0fe9a0..5657b7f 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.c
+++ b/fs/nfs/flexfilelayout/flexfilelayout.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* Module for pnfs flexfile layout driver.
*
@@ -7,8 +8,10 @@
*/
#include <linux/nfs_fs.h>
+#include <linux/nfs_mount.h>
#include <linux/nfs_page.h>
#include <linux/module.h>
+#include <linux/sched/mm.h>
#include <linux/sunrpc/metrics.h>
@@ -27,8 +30,7 @@
#define FF_LAYOUT_POLL_RETRY_MAX (15*HZ)
#define FF_LAYOUTRETURN_MAXERR 20
-
-static struct group_info *ff_zero_group;
+static unsigned short io_maxretrans;
static void ff_layout_read_record_layoutstats_done(struct rpc_task *task,
struct nfs_pgio_header *hdr);
@@ -226,16 +228,14 @@
static void ff_layout_free_mirror(struct nfs4_ff_layout_mirror *mirror)
{
- struct rpc_cred *cred;
+ const struct cred *cred;
ff_layout_remove_mirror(mirror);
kfree(mirror->fh_versions);
cred = rcu_access_pointer(mirror->ro_cred);
- if (cred)
- put_rpccred(cred);
+ put_cred(cred);
cred = rcu_access_pointer(mirror->rw_cred);
- if (cred)
- put_rpccred(cred);
+ put_cred(cred);
nfs4_ff_layout_put_deviceid(mirror->mirror_ds);
kfree(mirror);
}
@@ -413,8 +413,10 @@
for (i = 0; i < fls->mirror_array_cnt; i++) {
struct nfs4_ff_layout_mirror *mirror;
- struct auth_cred acred = { .group_info = ff_zero_group };
- struct rpc_cred __rcu *cred;
+ struct cred *kcred;
+ const struct cred __rcu *cred;
+ kuid_t uid;
+ kgid_t gid;
u32 ds_count, fh_count, id;
int j;
@@ -482,21 +484,28 @@
if (rc)
goto out_err_free;
- acred.uid = make_kuid(&init_user_ns, id);
+ uid = make_kuid(&init_user_ns, id);
/* group */
rc = decode_name(&stream, &id);
if (rc)
goto out_err_free;
- acred.gid = make_kgid(&init_user_ns, id);
+ gid = make_kgid(&init_user_ns, id);
- /* find the cred for it */
- rcu_assign_pointer(cred, rpc_lookup_generic_cred(&acred, 0, gfp_flags));
- if (IS_ERR(cred)) {
- rc = PTR_ERR(cred);
- goto out_err_free;
+ if (gfp_flags & __GFP_FS)
+ kcred = prepare_kernel_cred(NULL);
+ else {
+ unsigned int nofs_flags = memalloc_nofs_save();
+ kcred = prepare_kernel_cred(NULL);
+ memalloc_nofs_restore(nofs_flags);
}
+ rc = -ENOMEM;
+ if (!kcred)
+ goto out_err_free;
+ kcred->fsuid = uid;
+ kcred->fsgid = gid;
+ cred = RCU_INITIALIZER(kcred);
if (lgr->range.iomode == IOMODE_READ)
rcu_assign_pointer(fls->mirror_array[i]->ro_cred, cred);
@@ -519,8 +528,8 @@
dprintk("%s: iomode %s uid %u gid %u\n", __func__,
lgr->range.iomode == IOMODE_READ ? "READ" : "RW",
- from_kuid(&init_user_ns, acred.uid),
- from_kgid(&init_user_ns, acred.gid));
+ from_kuid(&init_user_ns, uid),
+ from_kgid(&init_user_ns, gid));
}
p = xdr_inline_decode(&stream, 4);
@@ -783,30 +792,82 @@
}
}
+static void
+ff_layout_mark_ds_unreachable(struct pnfs_layout_segment *lseg, int idx)
+{
+ struct nfs4_deviceid_node *devid = FF_LAYOUT_DEVID_NODE(lseg, idx);
+
+ if (devid)
+ nfs4_mark_deviceid_unavailable(devid);
+}
+
+static void
+ff_layout_mark_ds_reachable(struct pnfs_layout_segment *lseg, int idx)
+{
+ struct nfs4_deviceid_node *devid = FF_LAYOUT_DEVID_NODE(lseg, idx);
+
+ if (devid)
+ nfs4_mark_deviceid_available(devid);
+}
+
static struct nfs4_pnfs_ds *
-ff_layout_choose_best_ds_for_read(struct pnfs_layout_segment *lseg,
- int start_idx,
- int *best_idx)
+ff_layout_choose_ds_for_read(struct pnfs_layout_segment *lseg,
+ int start_idx, int *best_idx,
+ bool check_device)
{
struct nfs4_ff_layout_segment *fls = FF_LAYOUT_LSEG(lseg);
+ struct nfs4_ff_layout_mirror *mirror;
struct nfs4_pnfs_ds *ds;
bool fail_return = false;
int idx;
- /* mirrors are sorted by efficiency */
+ /* mirrors are initially sorted by efficiency */
for (idx = start_idx; idx < fls->mirror_array_cnt; idx++) {
if (idx+1 == fls->mirror_array_cnt)
- fail_return = true;
- ds = nfs4_ff_layout_prepare_ds(lseg, idx, fail_return);
- if (ds) {
- *best_idx = idx;
- return ds;
- }
+ fail_return = !check_device;
+
+ mirror = FF_LAYOUT_COMP(lseg, idx);
+ ds = nfs4_ff_layout_prepare_ds(lseg, mirror, fail_return);
+ if (!ds)
+ continue;
+
+ if (check_device &&
+ nfs4_test_deviceid_unavailable(&mirror->mirror_ds->id_node))
+ continue;
+
+ *best_idx = idx;
+ return ds;
}
return NULL;
}
+static struct nfs4_pnfs_ds *
+ff_layout_choose_any_ds_for_read(struct pnfs_layout_segment *lseg,
+ int start_idx, int *best_idx)
+{
+ return ff_layout_choose_ds_for_read(lseg, start_idx, best_idx, false);
+}
+
+static struct nfs4_pnfs_ds *
+ff_layout_choose_valid_ds_for_read(struct pnfs_layout_segment *lseg,
+ int start_idx, int *best_idx)
+{
+ return ff_layout_choose_ds_for_read(lseg, start_idx, best_idx, true);
+}
+
+static struct nfs4_pnfs_ds *
+ff_layout_choose_best_ds_for_read(struct pnfs_layout_segment *lseg,
+ int start_idx, int *best_idx)
+{
+ struct nfs4_pnfs_ds *ds;
+
+ ds = ff_layout_choose_valid_ds_for_read(lseg, start_idx, best_idx);
+ if (ds)
+ return ds;
+ return ff_layout_choose_any_ds_for_read(lseg, start_idx, best_idx);
+}
+
static void
ff_layout_pg_get_read(struct nfs_pageio_descriptor *pgio,
struct nfs_page *req,
@@ -814,7 +875,7 @@
{
pnfs_put_lseg(pgio->pg_lseg);
pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
- req->wb_context,
+ nfs_req_openctx(req),
0,
NFS4_MAX_UINT64,
IOMODE_READ,
@@ -868,13 +929,21 @@
pgm = &pgio->pg_mirrors[0];
pgm->pg_bsize = mirror->mirror_ds->ds_versions[0].rsize;
+ 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;
out_mds:
+ trace_pnfs_mds_fallback_pg_init_read(pgio->pg_inode,
+ 0, NFS4_MAX_UINT64, IOMODE_READ,
+ NFS_I(pgio->pg_inode)->layout,
+ pgio->pg_lseg);
pnfs_put_lseg(pgio->pg_lseg);
pgio->pg_lseg = NULL;
+ pgio->pg_maxretrans = 0;
nfs_pageio_reset_read_mds(pgio);
}
@@ -893,7 +962,7 @@
pnfs_generic_pg_check_layout(pgio);
if (!pgio->pg_lseg) {
pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
- req->wb_context,
+ nfs_req_openctx(req),
0,
NFS4_MAX_UINT64,
IOMODE_RW,
@@ -920,7 +989,8 @@
goto out_mds;
for (i = 0; i < pgio->pg_mirror_count; i++) {
- ds = nfs4_ff_layout_prepare_ds(pgio->pg_lseg, i, true);
+ mirror = FF_LAYOUT_COMP(pgio->pg_lseg, i);
+ ds = nfs4_ff_layout_prepare_ds(pgio->pg_lseg, mirror, true);
if (!ds) {
if (!ff_layout_no_fallback_to_mds(pgio->pg_lseg))
goto out_mds;
@@ -931,15 +1001,22 @@
goto retry;
}
pgm = &pgio->pg_mirrors[i];
- mirror = FF_LAYOUT_COMP(pgio->pg_lseg, i);
pgm->pg_bsize = mirror->mirror_ds->ds_versions[0].wsize;
}
+ if (NFS_SERVER(pgio->pg_inode)->flags &
+ (NFS_MOUNT_SOFT|NFS_MOUNT_SOFTERR))
+ pgio->pg_maxretrans = io_maxretrans;
return;
out_mds:
+ trace_pnfs_mds_fallback_pg_init_write(pgio->pg_inode,
+ 0, NFS4_MAX_UINT64, IOMODE_RW,
+ NFS_I(pgio->pg_inode)->layout,
+ pgio->pg_lseg);
pnfs_put_lseg(pgio->pg_lseg);
pgio->pg_lseg = NULL;
+ pgio->pg_maxretrans = 0;
nfs_pageio_reset_write_mds(pgio);
}
@@ -949,7 +1026,7 @@
{
if (!pgio->pg_lseg) {
pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
- req->wb_context,
+ nfs_req_openctx(req),
0,
NFS4_MAX_UINT64,
IOMODE_RW,
@@ -964,6 +1041,10 @@
if (pgio->pg_lseg)
return FF_LAYOUT_MIRROR_COUNT(pgio->pg_lseg);
+ trace_pnfs_mds_fallback_pg_get_mirror_count(pgio->pg_inode,
+ 0, NFS4_MAX_UINT64, IOMODE_RW,
+ NFS_I(pgio->pg_inode)->layout,
+ pgio->pg_lseg);
/* no lseg means that pnfs is not in use, so no mirroring here */
nfs_pageio_reset_write_mds(pgio);
out:
@@ -1013,6 +1094,10 @@
hdr->args.count,
(unsigned long long)hdr->args.offset);
+ trace_pnfs_mds_fallback_write_done(hdr->inode,
+ hdr->args.offset, hdr->args.count,
+ IOMODE_RW, NFS_I(hdr->inode)->layout,
+ hdr->lseg);
task->tk_status = pnfs_write_done_resend_to_mds(hdr);
}
}
@@ -1032,6 +1117,10 @@
hdr->args.count,
(unsigned long long)hdr->args.offset);
+ trace_pnfs_mds_fallback_read_done(hdr->inode,
+ hdr->args.offset, hdr->args.count,
+ IOMODE_READ, NFS_I(hdr->inode)->layout,
+ hdr->lseg);
task->tk_status = pnfs_read_done_resend_to_mds(hdr);
}
}
@@ -1153,8 +1242,10 @@
{
int vers = clp->cl_nfs_mod->rpc_vers->number;
- if (task->tk_status >= 0)
+ if (task->tk_status >= 0) {
+ ff_layout_mark_ds_reachable(lseg, idx);
return 0;
+ }
/* Handle the case of an invalid layout segment */
if (!pnfs_is_valid_lseg(lseg))
@@ -1217,6 +1308,8 @@
err = ff_layout_track_ds_error(FF_LAYOUT_FROM_HDR(lseg->pls_layout),
mirror, offset, length, status, opnum,
GFP_NOIO);
+ if (status == NFS4ERR_NXIO)
+ ff_layout_mark_ds_unreachable(lseg, idx);
pnfs_error_mark_layout_for_return(lseg->pls_layout->plh_inode, lseg);
dprintk("%s: err %d op %d status %u\n", __func__, err, opnum, status);
}
@@ -1225,6 +1318,7 @@
static int ff_layout_read_done_cb(struct rpc_task *task,
struct nfs_pgio_header *hdr)
{
+ int new_idx = hdr->pgio_mirror_idx;
int err;
trace_nfs4_pnfs_read(hdr, task->tk_status);
@@ -1243,8 +1337,8 @@
case -NFS4ERR_RESET_TO_PNFS:
if (ff_layout_choose_best_ds_for_read(hdr->lseg,
hdr->pgio_mirror_idx + 1,
- &hdr->pgio_mirror_idx))
- goto out_eagain;
+ &new_idx))
+ goto out_layouterror;
set_bit(NFS_IOHDR_RESEND_PNFS, &hdr->flags);
return task->tk_status;
case -NFS4ERR_RESET_TO_MDS:
@@ -1255,6 +1349,10 @@
}
return 0;
+out_layouterror:
+ ff_layout_read_record_layoutstats_done(task, hdr);
+ ff_layout_send_layouterror(hdr->lseg);
+ hdr->pgio_mirror_idx = new_idx;
out_eagain:
rpc_restart_call_prepare(task);
return -EAGAIN;
@@ -1288,15 +1386,6 @@
(unsigned long long) NFS_I(inode)->layout->plh_lwb);
}
-static bool
-ff_layout_device_unavailable(struct pnfs_layout_segment *lseg, int idx)
-{
- /* No mirroring for now */
- struct nfs4_deviceid_node *node = FF_LAYOUT_DEVID_NODE(lseg, idx);
-
- return ff_layout_test_devid_unavailable(node);
-}
-
static void ff_layout_read_record_layoutstats_start(struct rpc_task *task,
struct nfs_pgio_header *hdr)
{
@@ -1327,10 +1416,6 @@
rpc_exit(task, -EIO);
return -EIO;
}
- if (ff_layout_device_unavailable(hdr->lseg, hdr->pgio_mirror_idx)) {
- rpc_exit(task, -EHOSTDOWN);
- return -EAGAIN;
- }
ff_layout_read_record_layoutstats_start(task, hdr);
return 0;
@@ -1394,9 +1479,10 @@
struct nfs_pgio_header *hdr = data;
ff_layout_read_record_layoutstats_done(&hdr->task, hdr);
- if (test_bit(NFS_IOHDR_RESEND_PNFS, &hdr->flags))
+ if (test_bit(NFS_IOHDR_RESEND_PNFS, &hdr->flags)) {
+ ff_layout_send_layouterror(hdr->lseg);
pnfs_read_resend_pnfs(hdr);
- else if (test_bit(NFS_IOHDR_RESEND_MDS, &hdr->flags))
+ } else if (test_bit(NFS_IOHDR_RESEND_MDS, &hdr->flags))
ff_layout_reset_read(hdr);
pnfs_generic_rw_release(data);
}
@@ -1508,11 +1594,6 @@
return -EIO;
}
- if (ff_layout_device_unavailable(hdr->lseg, hdr->pgio_mirror_idx)) {
- rpc_exit(task, -EHOSTDOWN);
- return -EAGAIN;
- }
-
ff_layout_write_record_layoutstats_start(task, hdr);
return 0;
}
@@ -1568,9 +1649,10 @@
struct nfs_pgio_header *hdr = data;
ff_layout_write_record_layoutstats_done(&hdr->task, hdr);
- if (test_bit(NFS_IOHDR_RESEND_PNFS, &hdr->flags))
+ if (test_bit(NFS_IOHDR_RESEND_PNFS, &hdr->flags)) {
+ ff_layout_send_layouterror(hdr->lseg);
ff_layout_reset_write(hdr, true);
- else if (test_bit(NFS_IOHDR_RESEND_MDS, &hdr->flags))
+ } else if (test_bit(NFS_IOHDR_RESEND_MDS, &hdr->flags))
ff_layout_reset_write(hdr, false);
pnfs_generic_rw_release(data);
}
@@ -1698,7 +1780,8 @@
struct pnfs_layout_segment *lseg = hdr->lseg;
struct nfs4_pnfs_ds *ds;
struct rpc_clnt *ds_clnt;
- struct rpc_cred *ds_cred;
+ struct nfs4_ff_layout_mirror *mirror;
+ const struct cred *ds_cred;
loff_t offset = hdr->args.offset;
u32 idx = hdr->pgio_mirror_idx;
int vers;
@@ -1708,20 +1791,21 @@
__func__, hdr->inode->i_ino,
hdr->args.pgbase, (size_t)hdr->args.count, offset);
- ds = nfs4_ff_layout_prepare_ds(lseg, idx, false);
+ mirror = FF_LAYOUT_COMP(lseg, idx);
+ ds = nfs4_ff_layout_prepare_ds(lseg, mirror, false);
if (!ds)
goto out_failed;
- ds_clnt = nfs4_ff_find_or_create_ds_client(lseg, idx, ds->ds_clp,
+ ds_clnt = nfs4_ff_find_or_create_ds_client(mirror, ds->ds_clp,
hdr->inode);
if (IS_ERR(ds_clnt))
goto out_failed;
- ds_cred = ff_layout_get_ds_cred(lseg, idx, hdr->cred);
+ ds_cred = ff_layout_get_ds_cred(mirror, &lseg->pls_range, hdr->cred);
if (!ds_cred)
goto out_failed;
- vers = nfs4_ff_layout_ds_version(lseg, idx);
+ vers = nfs4_ff_layout_ds_version(mirror);
dprintk("%s USE DS: %s cl_count %d vers %d\n", __func__,
ds->ds_remotestr, refcount_read(&ds->ds_clp->cl_count), vers);
@@ -1729,13 +1813,11 @@
hdr->pgio_done_cb = ff_layout_read_done_cb;
refcount_inc(&ds->ds_clp->cl_count);
hdr->ds_clp = ds->ds_clp;
- fh = nfs4_ff_layout_select_ds_fh(lseg, idx);
+ fh = nfs4_ff_layout_select_ds_fh(mirror);
if (fh)
hdr->args.fh = fh;
- if (vers == 4 &&
- !nfs4_ff_layout_select_ds_stateid(lseg, idx, &hdr->args.stateid))
- goto out_failed;
+ nfs4_ff_layout_select_ds_stateid(mirror, &hdr->args.stateid);
/*
* Note that if we ever decide to split across DSes,
@@ -1749,12 +1831,15 @@
vers == 3 ? &ff_layout_read_call_ops_v3 :
&ff_layout_read_call_ops_v4,
0, RPC_TASK_SOFTCONN);
- put_rpccred(ds_cred);
+ put_cred(ds_cred);
return PNFS_ATTEMPTED;
out_failed:
if (ff_layout_avoid_mds_available_ds(lseg))
return PNFS_TRY_AGAIN;
+ trace_pnfs_mds_fallback_read_pagelist(hdr->inode,
+ hdr->args.offset, hdr->args.count,
+ IOMODE_READ, NFS_I(hdr->inode)->layout, lseg);
return PNFS_NOT_ATTEMPTED;
}
@@ -1765,26 +1850,28 @@
struct pnfs_layout_segment *lseg = hdr->lseg;
struct nfs4_pnfs_ds *ds;
struct rpc_clnt *ds_clnt;
- struct rpc_cred *ds_cred;
+ struct nfs4_ff_layout_mirror *mirror;
+ const struct cred *ds_cred;
loff_t offset = hdr->args.offset;
int vers;
struct nfs_fh *fh;
int idx = hdr->pgio_mirror_idx;
- ds = nfs4_ff_layout_prepare_ds(lseg, idx, true);
+ mirror = FF_LAYOUT_COMP(lseg, idx);
+ ds = nfs4_ff_layout_prepare_ds(lseg, mirror, true);
if (!ds)
goto out_failed;
- ds_clnt = nfs4_ff_find_or_create_ds_client(lseg, idx, ds->ds_clp,
+ ds_clnt = nfs4_ff_find_or_create_ds_client(mirror, ds->ds_clp,
hdr->inode);
if (IS_ERR(ds_clnt))
goto out_failed;
- ds_cred = ff_layout_get_ds_cred(lseg, idx, hdr->cred);
+ ds_cred = ff_layout_get_ds_cred(mirror, &lseg->pls_range, hdr->cred);
if (!ds_cred)
goto out_failed;
- vers = nfs4_ff_layout_ds_version(lseg, idx);
+ vers = nfs4_ff_layout_ds_version(mirror);
dprintk("%s ino %lu sync %d req %zu@%llu DS: %s cl_count %d vers %d\n",
__func__, hdr->inode->i_ino, sync, (size_t) hdr->args.count,
@@ -1795,13 +1882,11 @@
refcount_inc(&ds->ds_clp->cl_count);
hdr->ds_clp = ds->ds_clp;
hdr->ds_commit_idx = idx;
- fh = nfs4_ff_layout_select_ds_fh(lseg, idx);
+ fh = nfs4_ff_layout_select_ds_fh(mirror);
if (fh)
hdr->args.fh = fh;
- if (vers == 4 &&
- !nfs4_ff_layout_select_ds_stateid(lseg, idx, &hdr->args.stateid))
- goto out_failed;
+ nfs4_ff_layout_select_ds_stateid(mirror, &hdr->args.stateid);
/*
* Note that if we ever decide to split across DSes,
@@ -1814,12 +1899,15 @@
vers == 3 ? &ff_layout_write_call_ops_v3 :
&ff_layout_write_call_ops_v4,
sync, RPC_TASK_SOFTCONN);
- put_rpccred(ds_cred);
+ put_cred(ds_cred);
return PNFS_ATTEMPTED;
out_failed:
if (ff_layout_avoid_mds_available_ds(lseg))
return PNFS_TRY_AGAIN;
+ trace_pnfs_mds_fallback_write_pagelist(hdr->inode,
+ hdr->args.offset, hdr->args.count,
+ IOMODE_RW, NFS_I(hdr->inode)->layout, lseg);
return PNFS_NOT_ATTEMPTED;
}
@@ -1844,7 +1932,8 @@
struct pnfs_layout_segment *lseg = data->lseg;
struct nfs4_pnfs_ds *ds;
struct rpc_clnt *ds_clnt;
- struct rpc_cred *ds_cred;
+ struct nfs4_ff_layout_mirror *mirror;
+ const struct cred *ds_cred;
u32 idx;
int vers, ret;
struct nfs_fh *fh;
@@ -1854,20 +1943,21 @@
goto out_err;
idx = calc_ds_index_from_commit(lseg, data->ds_commit_index);
- ds = nfs4_ff_layout_prepare_ds(lseg, idx, true);
+ mirror = FF_LAYOUT_COMP(lseg, idx);
+ ds = nfs4_ff_layout_prepare_ds(lseg, mirror, true);
if (!ds)
goto out_err;
- ds_clnt = nfs4_ff_find_or_create_ds_client(lseg, idx, ds->ds_clp,
+ ds_clnt = nfs4_ff_find_or_create_ds_client(mirror, ds->ds_clp,
data->inode);
if (IS_ERR(ds_clnt))
goto out_err;
- ds_cred = ff_layout_get_ds_cred(lseg, idx, data->cred);
+ ds_cred = ff_layout_get_ds_cred(mirror, &lseg->pls_range, data->cred);
if (!ds_cred)
goto out_err;
- vers = nfs4_ff_layout_ds_version(lseg, idx);
+ vers = nfs4_ff_layout_ds_version(mirror);
dprintk("%s ino %lu, how %d cl_count %d vers %d\n", __func__,
data->inode->i_ino, how, refcount_read(&ds->ds_clp->cl_count),
@@ -1884,7 +1974,7 @@
vers == 3 ? &ff_layout_commit_call_ops_v3 :
&ff_layout_commit_call_ops_v4,
how, RPC_TASK_SOFTCONN);
- put_rpccred(ds_cred);
+ put_cred(ds_cred);
return ret;
out_err:
pnfs_generic_prepare_to_resend_writes(data);
@@ -2031,7 +2121,7 @@
dprintk("%s: Begin\n", __func__);
- xdr_init_encode(&tmp_xdr, &tmp_buf, NULL);
+ xdr_init_encode(&tmp_xdr, &tmp_buf, NULL, NULL);
ff_layout_encode_ioerr(&tmp_xdr, args, ff_args);
ff_layout_encode_iostats_array(&tmp_xdr, args, ff_args);
@@ -2097,6 +2187,52 @@
return -ENOMEM;
}
+#ifdef CONFIG_NFS_V4_2
+void
+ff_layout_send_layouterror(struct pnfs_layout_segment *lseg)
+{
+ struct pnfs_layout_hdr *lo = lseg->pls_layout;
+ struct nfs42_layout_error *errors;
+ LIST_HEAD(head);
+
+ if (!nfs_server_capable(lo->plh_inode, NFS_CAP_LAYOUTERROR))
+ return;
+ ff_layout_fetch_ds_ioerr(lo, &lseg->pls_range, &head, -1);
+ if (list_empty(&head))
+ return;
+
+ errors = kmalloc_array(NFS42_LAYOUTERROR_MAX,
+ sizeof(*errors), GFP_NOFS);
+ if (errors != NULL) {
+ const struct nfs4_ff_layout_ds_err *pos;
+ size_t n = 0;
+
+ list_for_each_entry(pos, &head, list) {
+ errors[n].offset = pos->offset;
+ errors[n].length = pos->length;
+ nfs4_stateid_copy(&errors[n].stateid, &pos->stateid);
+ errors[n].errors[0].dev_id = pos->deviceid;
+ errors[n].errors[0].status = pos->status;
+ errors[n].errors[0].opnum = pos->opnum;
+ n++;
+ if (!list_is_last(&pos->list, &head) &&
+ n < NFS42_LAYOUTERROR_MAX)
+ continue;
+ if (nfs42_proc_layouterror(lseg, errors, n) < 0)
+ break;
+ n = 0;
+ }
+ kfree(errors);
+ }
+ ff_layout_free_ds_ioerr(&head);
+}
+#else
+void
+ff_layout_send_layouterror(struct pnfs_layout_segment *lseg)
+{
+}
+#endif
+
static int
ff_layout_ntop4(const struct sockaddr *sap, char *buf, const size_t buflen)
{
@@ -2355,6 +2491,7 @@
.name = "LAYOUT_FLEX_FILES",
.owner = THIS_MODULE,
.flags = PNFS_LAYOUTGET_ON_OPEN,
+ .max_layoutget_response = 4096, /* 1 page or so... */
.set_layoutdriver = ff_layout_set_layoutdriver,
.alloc_layout_hdr = ff_layout_alloc_layout_hdr,
.free_layout_hdr = ff_layout_free_layout_hdr,
@@ -2382,11 +2519,6 @@
{
printk(KERN_INFO "%s: NFSv4 Flexfile Layout Driver Registering...\n",
__func__);
- if (!ff_zero_group) {
- ff_zero_group = groups_alloc(0);
- if (!ff_zero_group)
- return -ENOMEM;
- }
return pnfs_register_layoutdriver(&flexfilelayout_type);
}
@@ -2395,10 +2527,6 @@
printk(KERN_INFO "%s: NFSv4 Flexfile Layout Driver Unregistering...\n",
__func__);
pnfs_unregister_layoutdriver(&flexfilelayout_type);
- if (ff_zero_group) {
- put_group_info(ff_zero_group);
- ff_zero_group = NULL;
- }
}
MODULE_ALIAS("nfs-layouttype4-4");
@@ -2408,3 +2536,7 @@
module_init(nfs4flexfilelayout_init);
module_exit(nfs4flexfilelayout_exit);
+
+module_param(io_maxretrans, ushort, 0644);
+MODULE_PARM_DESC(io_maxretrans, "The number of times the NFSv4.1 client "
+ "retries an I/O request before returning an error. ");
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.h b/fs/nfs/flexfilelayout/flexfilelayout.h
index de50a34..2f36996 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.h
+++ b/fs/nfs/flexfilelayout/flexfilelayout.h
@@ -81,8 +81,8 @@
u32 fh_versions_cnt;
struct nfs_fh *fh_versions;
nfs4_stateid stateid;
- struct rpc_cred __rcu *ro_cred;
- struct rpc_cred __rcu *rw_cred;
+ const struct cred __rcu *ro_cred;
+ const struct cred __rcu *rw_cred;
refcount_t ref;
spinlock_t lock;
unsigned long flags;
@@ -132,16 +132,6 @@
generic_hdr);
}
-static inline struct nfs4_deviceid_node *
-FF_LAYOUT_DEVID_NODE(struct pnfs_layout_segment *lseg, u32 idx)
-{
- if (idx >= FF_LAYOUT_LSEG(lseg)->mirror_array_cnt ||
- FF_LAYOUT_LSEG(lseg)->mirror_array[idx] == NULL ||
- FF_LAYOUT_LSEG(lseg)->mirror_array[idx]->mirror_ds == NULL)
- return NULL;
- return &FF_LAYOUT_LSEG(lseg)->mirror_array[idx]->mirror_ds->id_node;
-}
-
static inline struct nfs4_ff_layout_ds *
FF_LAYOUT_MIRROR_DS(struct nfs4_deviceid_node *node)
{
@@ -151,9 +141,25 @@
static inline struct nfs4_ff_layout_mirror *
FF_LAYOUT_COMP(struct pnfs_layout_segment *lseg, u32 idx)
{
- if (idx >= FF_LAYOUT_LSEG(lseg)->mirror_array_cnt)
- return NULL;
- return FF_LAYOUT_LSEG(lseg)->mirror_array[idx];
+ struct nfs4_ff_layout_segment *fls = FF_LAYOUT_LSEG(lseg);
+
+ if (idx < fls->mirror_array_cnt)
+ return fls->mirror_array[idx];
+ return NULL;
+}
+
+static inline struct nfs4_deviceid_node *
+FF_LAYOUT_DEVID_NODE(struct pnfs_layout_segment *lseg, u32 idx)
+{
+ struct nfs4_ff_layout_mirror *mirror = FF_LAYOUT_COMP(lseg, idx);
+
+ if (mirror != NULL) {
+ struct nfs4_ff_layout_ds *mirror_ds = mirror->mirror_ds;
+
+ if (!IS_ERR_OR_NULL(mirror_ds))
+ return &mirror_ds->id_node;
+ }
+ return NULL;
}
static inline u32
@@ -174,28 +180,10 @@
return FF_LAYOUT_LSEG(lseg)->flags & FF_FLAGS_NO_READ_IO;
}
-static inline bool
-ff_layout_test_devid_unavailable(struct nfs4_deviceid_node *node)
-{
- /*
- * Flexfiles should never mark a DS unavailable, but if it does
- * print a (ratelimited) warning as this can affect performance.
- */
- if (nfs4_test_deviceid_unavailable(node)) {
- u32 *p = (u32 *)node->deviceid.data;
-
- pr_warn_ratelimited("NFS: flexfiles layout referencing an "
- "unavailable device [%x%x%x%x]\n",
- p[0], p[1], p[2], p[3]);
- return true;
- }
- return false;
-}
-
static inline int
-nfs4_ff_layout_ds_version(struct pnfs_layout_segment *lseg, u32 ds_idx)
+nfs4_ff_layout_ds_version(const struct nfs4_ff_layout_mirror *mirror)
{
- return FF_LAYOUT_COMP(lseg, ds_idx)->mirror_ds->ds_versions[0].version;
+ return mirror->mirror_ds->ds_versions[0].version;
}
struct nfs4_ff_layout_ds *
@@ -207,6 +195,7 @@
struct nfs4_ff_layout_mirror *mirror, u64 offset,
u64 length, int status, enum nfs_opnum4 opnum,
gfp_t gfp_flags);
+void ff_layout_send_layouterror(struct pnfs_layout_segment *lseg);
int ff_layout_encode_ds_ioerr(struct xdr_stream *xdr, const struct list_head *head);
void ff_layout_free_ds_ioerr(struct list_head *head);
unsigned int ff_layout_fetch_ds_ioerr(struct pnfs_layout_hdr *lo,
@@ -214,23 +203,23 @@
struct list_head *head,
unsigned int maxnum);
struct nfs_fh *
-nfs4_ff_layout_select_ds_fh(struct pnfs_layout_segment *lseg, u32 mirror_idx);
-int
-nfs4_ff_layout_select_ds_stateid(struct pnfs_layout_segment *lseg,
- u32 mirror_idx,
- nfs4_stateid *stateid);
+nfs4_ff_layout_select_ds_fh(struct nfs4_ff_layout_mirror *mirror);
+void
+nfs4_ff_layout_select_ds_stateid(const struct nfs4_ff_layout_mirror *mirror,
+ nfs4_stateid *stateid);
struct nfs4_pnfs_ds *
-nfs4_ff_layout_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx,
+nfs4_ff_layout_prepare_ds(struct pnfs_layout_segment *lseg,
+ struct nfs4_ff_layout_mirror *mirror,
bool fail_return);
struct rpc_clnt *
-nfs4_ff_find_or_create_ds_client(struct pnfs_layout_segment *lseg,
- u32 ds_idx,
+nfs4_ff_find_or_create_ds_client(struct nfs4_ff_layout_mirror *mirror,
struct nfs_client *ds_clp,
struct inode *inode);
-struct rpc_cred *ff_layout_get_ds_cred(struct pnfs_layout_segment *lseg,
- u32 ds_idx, struct rpc_cred *mdscred);
+const struct cred *ff_layout_get_ds_cred(struct nfs4_ff_layout_mirror *mirror,
+ const struct pnfs_layout_range *range,
+ const struct cred *mdscred);
bool ff_layout_avoid_mds_available_ds(struct pnfs_layout_segment *lseg);
bool ff_layout_avoid_read_on_rw(struct pnfs_layout_segment *lseg);
diff --git a/fs/nfs/flexfilelayout/flexfilelayoutdev.c b/fs/nfs/flexfilelayout/flexfilelayoutdev.c
index a8df2f4..3eda40a 100644
--- a/fs/nfs/flexfilelayout/flexfilelayoutdev.c
+++ b/fs/nfs/flexfilelayout/flexfilelayoutdev.c
@@ -18,7 +18,7 @@
#define NFSDBG_FACILITY NFSDBG_PNFS_LD
-static unsigned int dataserver_timeo = NFS_DEF_TCP_RETRANS;
+static unsigned int dataserver_timeo = NFS_DEF_TCP_TIMEO;
static unsigned int dataserver_retrans;
static bool ff_layout_has_available_ds(struct pnfs_layout_segment *lseg);
@@ -183,56 +183,6 @@
return NULL;
}
-static void ff_layout_mark_devid_invalid(struct pnfs_layout_segment *lseg,
- struct nfs4_deviceid_node *devid)
-{
- nfs4_delete_deviceid(devid->ld, devid->nfs_client, &devid->deviceid);
- if (!ff_layout_has_available_ds(lseg))
- pnfs_error_mark_layout_for_return(lseg->pls_layout->plh_inode,
- lseg);
-}
-
-static bool ff_layout_mirror_valid(struct pnfs_layout_segment *lseg,
- struct nfs4_ff_layout_mirror *mirror,
- bool create)
-{
- if (mirror == NULL || IS_ERR(mirror->mirror_ds))
- goto outerr;
- if (mirror->mirror_ds == NULL) {
- if (create) {
- struct nfs4_deviceid_node *node;
- struct pnfs_layout_hdr *lh = lseg->pls_layout;
- struct nfs4_ff_layout_ds *mirror_ds = ERR_PTR(-ENODEV);
-
- node = nfs4_find_get_deviceid(NFS_SERVER(lh->plh_inode),
- &mirror->devid, lh->plh_lc_cred,
- GFP_KERNEL);
- if (node)
- mirror_ds = FF_LAYOUT_MIRROR_DS(node);
-
- /* check for race with another call to this function */
- if (cmpxchg(&mirror->mirror_ds, NULL, mirror_ds) &&
- mirror_ds != ERR_PTR(-ENODEV))
- nfs4_put_deviceid_node(node);
- } else
- goto outerr;
- }
-
- if (IS_ERR(mirror->mirror_ds))
- goto outerr;
-
- if (mirror->mirror_ds->ds == NULL) {
- struct nfs4_deviceid_node *devid;
- devid = &mirror->mirror_ds->id_node;
- ff_layout_mark_devid_invalid(lseg, devid);
- return false;
- }
- return true;
-outerr:
- pnfs_error_mark_layout_for_return(lseg->pls_layout->plh_inode, lseg);
- return false;
-}
-
static void extend_ds_error(struct nfs4_ff_layout_ds_err *err,
u64 offset, u64 length)
{
@@ -307,7 +257,7 @@
if (status == 0)
return 0;
- if (mirror->mirror_ds == NULL)
+ if (IS_ERR_OR_NULL(mirror->mirror_ds))
return -EINVAL;
dserr = kmalloc(sizeof(*dserr), gfp_flags);
@@ -326,14 +276,13 @@
spin_lock(&flo->generic_hdr.plh_inode->i_lock);
ff_layout_add_ds_error_locked(flo, dserr);
spin_unlock(&flo->generic_hdr.plh_inode->i_lock);
-
return 0;
}
-static struct rpc_cred *
+static const struct cred *
ff_layout_get_mirror_cred(struct nfs4_ff_layout_mirror *mirror, u32 iomode)
{
- struct rpc_cred *cred, __rcu **pcred;
+ const struct cred *cred, __rcu **pcred;
if (iomode == IOMODE_READ)
pcred = &mirror->ro_cred;
@@ -346,53 +295,61 @@
if (!cred)
break;
- cred = get_rpccred_rcu(cred);
+ cred = get_cred_rcu(cred);
} while(!cred);
rcu_read_unlock();
return cred;
}
struct nfs_fh *
-nfs4_ff_layout_select_ds_fh(struct pnfs_layout_segment *lseg, u32 mirror_idx)
+nfs4_ff_layout_select_ds_fh(struct nfs4_ff_layout_mirror *mirror)
{
- struct nfs4_ff_layout_mirror *mirror = FF_LAYOUT_COMP(lseg, mirror_idx);
- struct nfs_fh *fh = NULL;
-
- if (!ff_layout_mirror_valid(lseg, mirror, false)) {
- pr_err_ratelimited("NFS: %s: No data server for mirror offset index %d\n",
- __func__, mirror_idx);
- goto out;
- }
-
/* FIXME: For now assume there is only 1 version available for the DS */
- fh = &mirror->fh_versions[0];
-out:
- return fh;
+ return &mirror->fh_versions[0];
}
-int
-nfs4_ff_layout_select_ds_stateid(struct pnfs_layout_segment *lseg,
- u32 mirror_idx,
- nfs4_stateid *stateid)
+void
+nfs4_ff_layout_select_ds_stateid(const struct nfs4_ff_layout_mirror *mirror,
+ nfs4_stateid *stateid)
{
- struct nfs4_ff_layout_mirror *mirror = FF_LAYOUT_COMP(lseg, mirror_idx);
+ if (nfs4_ff_layout_ds_version(mirror) == 4)
+ nfs4_stateid_copy(stateid, &mirror->stateid);
+}
- if (!ff_layout_mirror_valid(lseg, mirror, false)) {
- pr_err_ratelimited("NFS: %s: No data server for mirror offset index %d\n",
- __func__, mirror_idx);
- goto out;
+static bool
+ff_layout_init_mirror_ds(struct pnfs_layout_hdr *lo,
+ struct nfs4_ff_layout_mirror *mirror)
+{
+ if (mirror == NULL)
+ goto outerr;
+ if (mirror->mirror_ds == NULL) {
+ struct nfs4_deviceid_node *node;
+ struct nfs4_ff_layout_ds *mirror_ds = ERR_PTR(-ENODEV);
+
+ node = nfs4_find_get_deviceid(NFS_SERVER(lo->plh_inode),
+ &mirror->devid, lo->plh_lc_cred,
+ GFP_KERNEL);
+ if (node)
+ mirror_ds = FF_LAYOUT_MIRROR_DS(node);
+
+ /* check for race with another call to this function */
+ if (cmpxchg(&mirror->mirror_ds, NULL, mirror_ds) &&
+ mirror_ds != ERR_PTR(-ENODEV))
+ nfs4_put_deviceid_node(node);
}
- nfs4_stateid_copy(stateid, &mirror->stateid);
- return 1;
-out:
- return 0;
+ if (IS_ERR(mirror->mirror_ds))
+ goto outerr;
+
+ return true;
+outerr:
+ return false;
}
/**
* nfs4_ff_layout_prepare_ds - prepare a DS connection for an RPC call
* @lseg: the layout segment we're operating on
- * @ds_idx: index of the DS to use
+ * @mirror: layout mirror describing the DS to use
* @fail_return: return layout on connect failure?
*
* Try to prepare a DS connection to accept an RPC call. This involves
@@ -407,26 +364,18 @@
* Returns a pointer to a connected DS object on success or NULL on failure.
*/
struct nfs4_pnfs_ds *
-nfs4_ff_layout_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx,
+nfs4_ff_layout_prepare_ds(struct pnfs_layout_segment *lseg,
+ struct nfs4_ff_layout_mirror *mirror,
bool fail_return)
{
- struct nfs4_ff_layout_mirror *mirror = FF_LAYOUT_COMP(lseg, ds_idx);
struct nfs4_pnfs_ds *ds = NULL;
- struct nfs4_deviceid_node *devid;
struct inode *ino = lseg->pls_layout->plh_inode;
struct nfs_server *s = NFS_SERVER(ino);
unsigned int max_payload;
int status;
- if (!ff_layout_mirror_valid(lseg, mirror, true)) {
- pr_err_ratelimited("NFS: %s: No data server for offset index %d\n",
- __func__, ds_idx);
- goto out;
- }
-
- devid = &mirror->mirror_ds->id_node;
- if (ff_layout_test_devid_unavailable(devid))
- goto out_fail;
+ if (!ff_layout_init_mirror_ds(lseg->pls_layout, mirror))
+ goto noconnect;
ds = mirror->mirror_ds->ds;
/* matching smp_wmb() in _nfs4_pnfs_v3/4_ds_connect */
@@ -437,8 +386,8 @@
/* FIXME: For now we assume the server sent only one version of NFS
* to use for the DS.
*/
- status = nfs4_pnfs_ds_connect(s, ds, devid, dataserver_timeo,
- dataserver_retrans,
+ status = nfs4_pnfs_ds_connect(s, ds, &mirror->mirror_ds->id_node,
+ dataserver_timeo, dataserver_retrans,
mirror->mirror_ds->ds_versions[0].version,
mirror->mirror_ds->ds_versions[0].minor_version);
@@ -453,11 +402,12 @@
mirror->mirror_ds->ds_versions[0].wsize = max_payload;
goto out;
}
-out_fail:
+noconnect:
ff_layout_track_ds_error(FF_LAYOUT_FROM_HDR(lseg->pls_layout),
mirror, lseg->pls_range.offset,
lseg->pls_range.length, NFS4ERR_NXIO,
OP_ILLEGAL, GFP_NOIO);
+ ff_layout_send_layouterror(lseg);
if (fail_return || !ff_layout_has_available_ds(lseg))
pnfs_error_mark_layout_for_return(ino, lseg);
ds = NULL;
@@ -465,33 +415,36 @@
return ds;
}
-struct rpc_cred *
-ff_layout_get_ds_cred(struct pnfs_layout_segment *lseg, u32 ds_idx,
- struct rpc_cred *mdscred)
+const struct cred *
+ff_layout_get_ds_cred(struct nfs4_ff_layout_mirror *mirror,
+ const struct pnfs_layout_range *range,
+ const struct cred *mdscred)
{
- struct nfs4_ff_layout_mirror *mirror = FF_LAYOUT_COMP(lseg, ds_idx);
- struct rpc_cred *cred;
+ const struct cred *cred;
- if (mirror) {
- cred = ff_layout_get_mirror_cred(mirror, lseg->pls_range.iomode);
+ if (mirror && !mirror->mirror_ds->ds_versions[0].tightly_coupled) {
+ cred = ff_layout_get_mirror_cred(mirror, range->iomode);
if (!cred)
- cred = get_rpccred(mdscred);
+ cred = get_cred(mdscred);
} else {
- cred = get_rpccred(mdscred);
+ cred = get_cred(mdscred);
}
return cred;
}
/**
-* Find or create a DS rpc client with th MDS server rpc client auth flavor
-* in the nfs_client cl_ds_clients list.
-*/
+ * nfs4_ff_find_or_create_ds_client - Find or create a DS rpc client
+ * @mirror: pointer to the mirror
+ * @ds_clp: nfs_client for the DS
+ * @inode: pointer to inode
+ *
+ * Find or create a DS rpc client with th MDS server rpc client auth flavor
+ * in the nfs_client cl_ds_clients list.
+ */
struct rpc_clnt *
-nfs4_ff_find_or_create_ds_client(struct pnfs_layout_segment *lseg, u32 ds_idx,
+nfs4_ff_find_or_create_ds_client(struct nfs4_ff_layout_mirror *mirror,
struct nfs_client *ds_clp, struct inode *inode)
{
- struct nfs4_ff_layout_mirror *mirror = FF_LAYOUT_COMP(lseg, ds_idx);
-
switch (mirror->mirror_ds->ds_versions[0].version) {
case 3:
/* For NFSv3 DS, flavor is set when creating DS connections */
@@ -608,7 +561,7 @@
if (IS_ERR(mirror->mirror_ds))
continue;
devid = &mirror->mirror_ds->id_node;
- if (!ff_layout_test_devid_unavailable(devid))
+ if (!nfs4_test_deviceid_unavailable(devid))
return true;
}
}
@@ -629,7 +582,7 @@
if (!mirror->mirror_ds)
continue;
devid = &mirror->mirror_ds->id_node;
- if (ff_layout_test_devid_unavailable(devid))
+ if (nfs4_test_deviceid_unavailable(devid))
return false;
}
diff --git a/fs/nfs/fscache-index.c b/fs/nfs/fscache-index.c
index 666415d..15f2714 100644
--- a/fs/nfs/fscache-index.c
+++ b/fs/nfs/fscache-index.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
/* NFS FS-Cache index structure definition
*
* Copyright (C) 2008 Red Hat, Inc. All Rights Reserved.
* Written by David Howells (dhowells@redhat.com)
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public Licence
- * as published by the Free Software Foundation; either version
- * 2 of the Licence, or (at your option) any later version.
*/
#include <linux/init.h>
diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c
index 4dc8878..3800ab6 100644
--- a/fs/nfs/fscache.c
+++ b/fs/nfs/fscache.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
/* NFS filesystem cache interface
*
* Copyright (C) 2008 Red Hat, Inc. All Rights Reserved.
* Written by David Howells (dhowells@redhat.com)
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public Licence
- * as published by the Free Software Foundation; either version
- * 2 of the Licence, or (at your option) any later version.
*/
#include <linux/init.h>
@@ -118,6 +114,10 @@
struct rb_node **p, *parent;
int diff;
+ nfss->fscache_key = NULL;
+ nfss->fscache = NULL;
+ if (!(nfss->options & NFS_OPTION_FSCACHE))
+ return;
if (!uniq) {
uniq = "";
ulen = 1;
@@ -230,10 +230,11 @@
void nfs_fscache_init_inode(struct inode *inode)
{
struct nfs_fscache_inode_auxdata auxdata;
+ struct nfs_server *nfss = NFS_SERVER(inode);
struct nfs_inode *nfsi = NFS_I(inode);
nfsi->fscache = NULL;
- if (!S_ISREG(inode->i_mode))
+ if (!(nfss->fscache && S_ISREG(inode->i_mode)))
return;
memset(&auxdata, 0, sizeof(auxdata));
diff --git a/fs/nfs/fscache.h b/fs/nfs/fscache.h
index 161ba2e..ad041cf 100644
--- a/fs/nfs/fscache.h
+++ b/fs/nfs/fscache.h
@@ -1,12 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
/* NFS filesystem cache interface definitions
*
* Copyright (C) 2008 Red Hat, Inc. All Rights Reserved.
* Written by David Howells (dhowells@redhat.com)
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public Licence
- * as published by the Free Software Foundation; either version
- * 2 of the Licence, or (at your option) any later version.
*/
#ifndef _NFS_FSCACHE_H
@@ -186,7 +182,7 @@
*/
static inline const char *nfs_server_fscache_state(struct nfs_server *server)
{
- if (server->fscache && (server->options & NFS_OPTION_FSCACHE))
+ if (server->fscache)
return "yes";
return "no ";
}
diff --git a/fs/nfs/getroot.c b/fs/nfs/getroot.c
index 391dafa..878c4c5 100644
--- a/fs/nfs/getroot.c
+++ b/fs/nfs/getroot.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
/* getroot.c: get the root dentry for an NFS mount
*
* Copyright (C) 2006 Red Hat, Inc. All Rights Reserved.
* Written by David Howells (dhowells@redhat.com)
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
*/
#include <linux/module.h>
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index b65aee4..2a03bfe 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* linux/fs/nfs/inode.c
*
@@ -50,6 +51,7 @@
#include "pnfs.h"
#include "nfs.h"
#include "netns.h"
+#include "sysfs.h"
#include "nfstrace.h"
@@ -143,6 +145,7 @@
/**
* nfs_sync_mapping - helper to flush all mmapped dirty data to disk
+ * @mapping: pointer to struct address_space
*/
int nfs_sync_mapping(struct address_space *mapping)
{
@@ -206,7 +209,7 @@
}
if (inode->i_mapping->nrpages == 0)
- flags &= ~NFS_INO_INVALID_DATA;
+ flags &= ~(NFS_INO_INVALID_DATA|NFS_INO_DATA_INVAL_DEFER);
nfsi->cache_validity |= flags;
if (flags & NFS_INO_INVALID_DATA)
nfs_fscache_invalidate(inode);
@@ -650,7 +653,8 @@
i_size_write(inode, offset);
/* Optimisation */
if (offset == 0)
- NFS_I(inode)->cache_validity &= ~NFS_INO_INVALID_DATA;
+ NFS_I(inode)->cache_validity &= ~(NFS_INO_INVALID_DATA |
+ NFS_INO_DATA_INVAL_DEFER);
NFS_I(inode)->cache_validity &= ~NFS_INO_INVALID_SIZE;
spin_unlock(&inode->i_lock);
@@ -857,15 +861,14 @@
static struct nfs_lock_context *__nfs_find_lock_context(struct nfs_open_context *ctx)
{
- struct nfs_lock_context *head = &ctx->lock_context;
- struct nfs_lock_context *pos = head;
+ struct nfs_lock_context *pos;
- do {
+ list_for_each_entry_rcu(pos, &ctx->lock_context.list, list) {
if (pos->lockowner != current->files)
continue;
- refcount_inc(&pos->count);
- return pos;
- } while ((pos = list_entry(pos->list.next, typeof(*pos), list)) != head);
+ if (refcount_inc_not_zero(&pos->count))
+ return pos;
+ }
return NULL;
}
@@ -874,10 +877,10 @@
struct nfs_lock_context *res, *new = NULL;
struct inode *inode = d_inode(ctx->dentry);
- spin_lock(&inode->i_lock);
+ rcu_read_lock();
res = __nfs_find_lock_context(ctx);
+ rcu_read_unlock();
if (res == NULL) {
- spin_unlock(&inode->i_lock);
new = kmalloc(sizeof(*new), GFP_KERNEL);
if (new == NULL)
return ERR_PTR(-ENOMEM);
@@ -885,14 +888,18 @@
spin_lock(&inode->i_lock);
res = __nfs_find_lock_context(ctx);
if (res == NULL) {
- list_add_tail(&new->list, &ctx->lock_context.list);
- new->open_context = ctx;
- res = new;
- new = NULL;
+ new->open_context = get_nfs_open_context(ctx);
+ if (new->open_context) {
+ list_add_tail_rcu(&new->list,
+ &ctx->lock_context.list);
+ res = new;
+ new = NULL;
+ } else
+ res = ERR_PTR(-EBADF);
}
+ spin_unlock(&inode->i_lock);
+ kfree(new);
}
- spin_unlock(&inode->i_lock);
- kfree(new);
return res;
}
EXPORT_SYMBOL_GPL(nfs_get_lock_context);
@@ -904,9 +911,10 @@
if (!refcount_dec_and_lock(&l_ctx->count, &inode->i_lock))
return;
- list_del(&l_ctx->list);
+ list_del_rcu(&l_ctx->list);
spin_unlock(&inode->i_lock);
- kfree(l_ctx);
+ put_nfs_open_context(ctx);
+ kfree_rcu(l_ctx, rcu_head);
}
EXPORT_SYMBOL_GPL(nfs_put_lock_context);
@@ -951,18 +959,17 @@
struct file *filp)
{
struct nfs_open_context *ctx;
- struct rpc_cred *cred = rpc_lookup_cred();
- if (IS_ERR(cred))
- return ERR_CAST(cred);
+ const struct cred *cred = get_current_cred();
ctx = kmalloc(sizeof(*ctx), GFP_KERNEL);
if (!ctx) {
- put_rpccred(cred);
+ put_cred(cred);
return ERR_PTR(-ENOMEM);
}
nfs_sb_active(dentry->d_sb);
ctx->dentry = dget(dentry);
ctx->cred = cred;
+ ctx->ll_cred = NULL;
ctx->state = NULL;
ctx->mode = f_mode;
ctx->flags = 0;
@@ -978,9 +985,9 @@
struct nfs_open_context *get_nfs_open_context(struct nfs_open_context *ctx)
{
- if (ctx != NULL)
- refcount_inc(&ctx->lock_context.count);
- return ctx;
+ if (ctx != NULL && refcount_inc_not_zero(&ctx->lock_context.count))
+ return ctx;
+ return NULL;
}
EXPORT_SYMBOL_GPL(get_nfs_open_context);
@@ -989,21 +996,21 @@
struct inode *inode = d_inode(ctx->dentry);
struct super_block *sb = ctx->dentry->d_sb;
- if (!list_empty(&ctx->list)) {
- if (!refcount_dec_and_lock(&ctx->lock_context.count, &inode->i_lock))
- return;
- list_del(&ctx->list);
- spin_unlock(&inode->i_lock);
- } else if (!refcount_dec_and_test(&ctx->lock_context.count))
+ if (!refcount_dec_and_test(&ctx->lock_context.count))
return;
+ if (!list_empty(&ctx->list)) {
+ spin_lock(&inode->i_lock);
+ list_del_rcu(&ctx->list);
+ spin_unlock(&inode->i_lock);
+ }
if (inode != NULL)
NFS_PROTO(inode)->close_context(ctx, is_sync);
- if (ctx->cred != NULL)
- put_rpccred(ctx->cred);
+ put_cred(ctx->cred);
dput(ctx->dentry);
nfs_sb_deactive(sb);
+ put_rpccred(ctx->ll_cred);
kfree(ctx->mdsthreshold);
- kfree(ctx);
+ kfree_rcu(ctx, rcu_head);
}
void put_nfs_open_context(struct nfs_open_context *ctx)
@@ -1027,10 +1034,11 @@
struct nfs_inode *nfsi = NFS_I(inode);
spin_lock(&inode->i_lock);
- if (ctx->mode & FMODE_WRITE)
- list_add(&ctx->list, &nfsi->open_files);
- else
- list_add_tail(&ctx->list, &nfsi->open_files);
+ if (list_empty(&nfsi->open_files) &&
+ (nfsi->cache_validity & NFS_INO_DATA_INVAL_DEFER))
+ nfsi->cache_validity |= NFS_INO_INVALID_DATA |
+ NFS_INO_REVAL_FORCED;
+ list_add_tail_rcu(&ctx->list, &nfsi->open_files);
spin_unlock(&inode->i_lock);
}
EXPORT_SYMBOL_GPL(nfs_inode_attach_open_context);
@@ -1046,21 +1054,22 @@
/*
* Given an inode, search for an open context with the desired characteristics
*/
-struct nfs_open_context *nfs_find_open_context(struct inode *inode, struct rpc_cred *cred, fmode_t mode)
+struct nfs_open_context *nfs_find_open_context(struct inode *inode, const struct cred *cred, fmode_t mode)
{
struct nfs_inode *nfsi = NFS_I(inode);
struct nfs_open_context *pos, *ctx = NULL;
- spin_lock(&inode->i_lock);
- list_for_each_entry(pos, &nfsi->open_files, list) {
+ rcu_read_lock();
+ list_for_each_entry_rcu(pos, &nfsi->open_files, list) {
if (cred != NULL && pos->cred != cred)
continue;
if ((pos->mode & (FMODE_READ|FMODE_WRITE)) != mode)
continue;
ctx = get_nfs_open_context(pos);
- break;
+ if (ctx)
+ break;
}
- spin_unlock(&inode->i_lock);
+ rcu_read_unlock();
return ctx;
}
@@ -1078,9 +1087,6 @@
if (ctx->error < 0)
invalidate_inode_pages2(inode->i_mapping);
filp->private_data = NULL;
- spin_lock(&inode->i_lock);
- list_move_tail(&ctx->list, &NFS_I(inode)->open_files);
- spin_unlock(&inode->i_lock);
put_nfs_open_context_sync(ctx);
}
}
@@ -1100,6 +1106,7 @@
nfs_fscache_open_file(inode, filp);
return 0;
}
+EXPORT_SYMBOL_GPL(nfs_open);
/*
* This function is called whenever some part of NFS notices that
@@ -1191,8 +1198,8 @@
/**
* nfs_revalidate_inode - Revalidate the inode attributes
- * @server - pointer to nfs_server struct
- * @inode - pointer to inode struct
+ * @server: pointer to nfs_server struct
+ * @inode: pointer to inode struct
*
* Updates inode attribute information by retrieving the data from the server.
*/
@@ -1262,8 +1269,8 @@
/**
* nfs_revalidate_mapping - Revalidate the pagecache
- * @inode - pointer to host inode
- * @mapping - pointer to mapping
+ * @inode: pointer to host inode
+ * @mapping: pointer to mapping
*/
int nfs_revalidate_mapping(struct inode *inode,
struct address_space *mapping)
@@ -1312,7 +1319,8 @@
set_bit(NFS_INO_INVALIDATING, bitlock);
smp_wmb();
- nfsi->cache_validity &= ~NFS_INO_INVALID_DATA;
+ nfsi->cache_validity &= ~(NFS_INO_INVALID_DATA|
+ NFS_INO_DATA_INVAL_DEFER);
spin_unlock(&inode->i_lock);
trace_nfs_invalidate_mapping_enter(inode);
ret = nfs_invalidate_mapping(inode, mapping);
@@ -1329,19 +1337,11 @@
{
struct inode *inode = &nfsi->vfs_inode;
- assert_spin_locked(&inode->i_lock);
-
if (!S_ISREG(inode->i_mode))
return false;
if (list_empty(&nfsi->open_files))
return false;
- /* Note: This relies on nfsi->open_files being ordered with writers
- * being placed at the head of the list.
- * See nfs_inode_attach_open_context()
- */
- return (list_first_entry(&nfsi->open_files,
- struct nfs_open_context,
- list)->mode & FMODE_WRITE) == FMODE_WRITE;
+ return inode_is_open_for_write(inode);
}
static bool nfs_file_has_buffered_writers(struct nfs_inode *nfsi)
@@ -1386,8 +1386,8 @@
/**
* nfs_check_inode_attributes - verify consistency of the inode attribute cache
- * @inode - pointer to inode
- * @fattr - updated attributes
+ * @inode: pointer to inode
+ * @fattr: updated attributes
*
* Verifies the attribute cache. If we have just changed the attributes,
* so that fattr carries weak cache consistency data, then it may
@@ -1403,12 +1403,22 @@
if (NFS_PROTO(inode)->have_delegation(inode, FMODE_READ))
return 0;
+ if (!(fattr->valid & NFS_ATTR_FATTR_FILEID)) {
+ /* Only a mounted-on-fileid? Just exit */
+ if (fattr->valid & NFS_ATTR_FATTR_MOUNTED_ON_FILEID)
+ return 0;
/* Has the inode gone and changed behind our back? */
- if ((fattr->valid & NFS_ATTR_FATTR_FILEID) && nfsi->fileid != fattr->fileid)
+ } else if (nfsi->fileid != fattr->fileid) {
+ /* Is this perhaps the mounted-on fileid? */
+ if ((fattr->valid & NFS_ATTR_FATTR_MOUNTED_ON_FILEID) &&
+ nfsi->fileid == fattr->mounted_on_fileid)
+ return 0;
return -ESTALE;
+ }
if ((fattr->valid & NFS_ATTR_FATTR_TYPE) && (inode->i_mode & S_IFMT) != (fattr->mode & S_IFMT))
return -ESTALE;
+
if (!nfs_file_has_buffered_writers(nfsi)) {
/* Verify a few of the more important attributes */
if ((fattr->valid & NFS_ATTR_FATTR_CHANGE) != 0 && !inode_eq_iversion_raw(inode, fattr->change_attr))
@@ -1587,8 +1597,8 @@
/**
* nfs_inode_attrs_need_update - check if the inode attributes need updating
- * @inode - pointer to inode
- * @fattr - attributes
+ * @inode: pointer to inode
+ * @fattr: attributes
*
* Attempt to divine whether or not an RPC call reply carrying stale
* attributes got scheduled after another call carrying updated ones.
@@ -1629,8 +1639,8 @@
/**
* nfs_refresh_inode - try to update the inode attribute cache
- * @inode - pointer to inode
- * @fattr - updated attributes
+ * @inode: pointer to inode
+ * @fattr: updated attributes
*
* Check that an RPC call that returned attributes has not overlapped with
* other recent updates of the inode metadata, then decide whether it is
@@ -1664,8 +1674,8 @@
/**
* nfs_post_op_update_inode - try to update the inode attribute cache
- * @inode - pointer to inode
- * @fattr - updated attributes
+ * @inode: pointer to inode
+ * @fattr: updated attributes
*
* After an operation that has changed the inode metadata, mark the
* attribute cache as being invalid, then try to update it.
@@ -1694,8 +1704,8 @@
/**
* nfs_post_op_update_inode_force_wcc_locked - update the inode attribute cache
- * @inode - pointer to inode
- * @fattr - updated attributes
+ * @inode: pointer to inode
+ * @fattr: updated attributes
*
* After an operation that has changed the inode metadata, mark the
* attribute cache as being invalid, then try to update it. Fake up
@@ -1746,8 +1756,8 @@
/**
* nfs_post_op_update_inode_force_wcc - try to update the inode attribute cache
- * @inode - pointer to inode
- * @fattr - updated attributes
+ * @inode: pointer to inode
+ * @fattr: updated attributes
*
* After an operation that has changed the inode metadata, mark the
* attribute cache as being invalid, then try to update it. Fake up
@@ -1768,18 +1778,6 @@
EXPORT_SYMBOL_GPL(nfs_post_op_update_inode_force_wcc);
-static inline bool nfs_fileid_valid(struct nfs_inode *nfsi,
- struct nfs_fattr *fattr)
-{
- bool ret1 = true, ret2 = true;
-
- if (fattr->valid & NFS_ATTR_FATTR_FILEID)
- ret1 = (nfsi->fileid == fattr->fileid);
- if (fattr->valid & NFS_ATTR_FATTR_MOUNTED_ON_FILEID)
- ret2 = (nfsi->fileid == fattr->mounted_on_fileid);
- return ret1 || ret2;
-}
-
/*
* Many nfs protocol calls return the new file attributes after
* an operation. Here we update the inode to reflect the state
@@ -1810,7 +1808,16 @@
nfs_display_fhandle_hash(NFS_FH(inode)),
atomic_read(&inode->i_count), fattr->valid);
- if (!nfs_fileid_valid(nfsi, fattr)) {
+ if (!(fattr->valid & NFS_ATTR_FATTR_FILEID)) {
+ /* Only a mounted-on-fileid? Just exit */
+ if (fattr->valid & NFS_ATTR_FATTR_MOUNTED_ON_FILEID)
+ return 0;
+ /* Has the inode gone and changed behind our back? */
+ } else if (nfsi->fileid != fattr->fileid) {
+ /* Is this perhaps the mounted-on fileid? */
+ if ((fattr->valid & NFS_ATTR_FATTR_MOUNTED_ON_FILEID) &&
+ nfsi->fileid == fattr->mounted_on_fileid)
+ return 0;
printk(KERN_ERR "NFS: server %s error: fileid changed\n"
"fsid %s: expected fileid 0x%Lx, got 0x%Lx\n",
NFS_SERVER(inode)->nfs_client->cl_hostname,
@@ -1878,7 +1885,8 @@
dprintk("NFS: change_attr change on server for file %s/%ld\n",
inode->i_sb->s_id,
inode->i_ino);
- }
+ } else if (!have_delegation)
+ nfsi->cache_validity |= NFS_INO_DATA_INVAL_DEFER;
inode_set_iversion_raw(inode, fattr->change_attr);
attr_changed = true;
}
@@ -2069,17 +2077,11 @@
}
EXPORT_SYMBOL_GPL(nfs_alloc_inode);
-static void nfs_i_callback(struct rcu_head *head)
+void nfs_free_inode(struct inode *inode)
{
- struct inode *inode = container_of(head, struct inode, i_rcu);
kmem_cache_free(nfs_inode_cachep, NFS_I(inode));
}
-
-void nfs_destroy_inode(struct inode *inode)
-{
- call_rcu(&inode->i_rcu, nfs_i_callback);
-}
-EXPORT_SYMBOL_GPL(nfs_destroy_inode);
+EXPORT_SYMBOL_GPL(nfs_free_inode);
static inline void nfs4_init_once(struct nfs_inode *nfsi)
{
@@ -2173,12 +2175,8 @@
static void nfs_net_exit(struct net *net)
{
- struct nfs_net *nn = net_generic(net, nfs_net_id);
-
nfs_fs_proc_net_exit(net);
- nfs_cleanup_cb_ident_idr(net);
- WARN_ON_ONCE(!list_empty(&nn->nfs_client_list));
- WARN_ON_ONCE(!list_empty(&nn->nfs_volume_list));
+ nfs_clients_exit(net);
}
static struct pernet_operations nfs_net_ops = {
@@ -2195,6 +2193,10 @@
{
int err;
+ err = nfs_sysfs_init();
+ if (err < 0)
+ goto out10;
+
err = register_pernet_subsys(&nfs_net_ops);
if (err < 0)
goto out9;
@@ -2258,6 +2260,8 @@
out8:
unregister_pernet_subsys(&nfs_net_ops);
out9:
+ nfs_sysfs_exit();
+out10:
return err;
}
@@ -2274,6 +2278,7 @@
unregister_nfs_fs();
nfs_fs_proc_exit();
nfsiod_stop();
+ nfs_sysfs_exit();
}
/* Not quite true; I just maintain it */
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 8357ff6..447a3c1 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -16,14 +16,6 @@
struct nfs_string;
-/* Maximum number of readahead requests
- * FIXME: this should really be a sysctl so that users may tune it to suit
- * their needs. People that do NFS over a slow network, might for
- * instance want to reduce it to something closer to 1 for improved
- * interactive response.
- */
-#define NFS_MAX_READAHEAD (RPC_DEF_SLOT_TABLE - 1)
-
static inline void nfs_attr_check_mountpoint(struct super_block *parent, struct nfs_fattr *fattr)
{
if (!nfs_fsid_equal(&NFS_SB(parent)->fsid, &fattr->fsid))
@@ -81,8 +73,10 @@
struct nfs_subversion *nfs_mod;
int proto;
u32 minorversion;
+ unsigned int nconnect;
struct net *net;
const struct rpc_timeout *timeparms;
+ const struct cred *cred;
};
/*
@@ -121,9 +115,10 @@
char *export_path;
int port;
unsigned short protocol;
+ unsigned short nconnect;
} nfs_server;
- struct security_mnt_opts lsm_opts;
+ void *lsm_opts;
struct net *net;
};
@@ -156,6 +151,7 @@
/* client.c */
extern const struct rpc_program nfs_program;
extern void nfs_clients_init(struct net *net);
+extern void nfs_clients_exit(struct net *net);
extern struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *);
int nfs_create_rpc_client(struct nfs_client *, const struct nfs_client_initdata *, rpc_authflavor_t);
struct nfs_client *nfs_get_client(const struct nfs_client_initdata *);
@@ -168,7 +164,6 @@
struct nfs_server *nfs_alloc_server(void);
void nfs_server_copy_userdata(struct nfs_server *, struct nfs_server *);
-extern void nfs_cleanup_cb_ident_idr(struct net *);
extern void nfs_put_client(struct nfs_client *);
extern void nfs_free_client(struct nfs_client *);
extern struct nfs_client *nfs4_find_client_ident(struct net *, int);
@@ -254,7 +249,7 @@
void nfs_pgio_header_free(struct nfs_pgio_header *);
int nfs_generic_pgio(struct nfs_pageio_descriptor *, struct nfs_pgio_header *);
int nfs_initiate_pgio(struct rpc_clnt *clnt, struct nfs_pgio_header *hdr,
- struct rpc_cred *cred, const struct nfs_rpc_ops *rpc_ops,
+ const struct cred *cred, const struct nfs_rpc_ops *rpc_ops,
const struct rpc_call_ops *call_ops, int how, int flags);
void nfs_free_request(struct nfs_page *req);
struct nfs_pgio_mirror *
@@ -269,7 +264,7 @@
static inline bool nfs_match_open_context(const struct nfs_open_context *ctx1,
const struct nfs_open_context *ctx2)
{
- return ctx1->cred == ctx2->cred && ctx1->state == ctx2->state;
+ return cred_fscmp(ctx1->cred, ctx2->cred) == 0 && ctx1->state == ctx2->state;
}
/* nfs2xdr.c */
@@ -380,7 +375,7 @@
/* inode.c */
extern struct workqueue_struct *nfsiod_workqueue;
extern struct inode *nfs_alloc_inode(struct super_block *sb);
-extern void nfs_destroy_inode(struct inode *);
+extern void nfs_free_inode(struct inode *);
extern int nfs_write_inode(struct inode *, struct writeback_control *);
extern int nfs_drop_inode(struct inode *);
extern void nfs_clear_inode(struct inode *);
@@ -395,7 +390,6 @@
extern struct file_system_type nfs_fs_type;
extern struct file_system_type nfs_xdev_fs_type;
#if IS_ENABLED(CONFIG_NFS_V4)
-extern struct file_system_type nfs4_xdev_fs_type;
extern struct file_system_type nfs4_referral_fs_type;
#endif
bool nfs_auth_info_match(const struct nfs_auth_info *, rpc_authflavor_t);
@@ -565,13 +559,13 @@
const struct nfs_client_initdata *);
extern int nfs40_walk_client_list(struct nfs_client *clp,
struct nfs_client **result,
- struct rpc_cred *cred);
+ const struct cred *cred);
extern int nfs41_walk_client_list(struct nfs_client *clp,
struct nfs_client **result,
- struct rpc_cred *cred);
-extern int nfs4_test_session_trunk(struct rpc_clnt *,
- struct rpc_xprt *,
- void *);
+ const struct cred *cred);
+extern void nfs4_test_session_trunk(struct rpc_clnt *clnt,
+ struct rpc_xprt *xprt,
+ void *data);
static inline struct inode *nfs_igrab_and_active(struct inode *inode)
{
@@ -756,6 +750,7 @@
{
switch (err) {
case -ERESTARTSYS:
+ case -EINTR:
case -EACCES:
case -EDQUOT:
case -EFBIG:
@@ -764,15 +759,21 @@
case -EROFS:
case -ESTALE:
case -E2BIG:
+ case -ENOMEM:
+ case -ETIMEDOUT:
return true;
default:
return false;
}
}
-static inline void nfs_context_set_write_error(struct nfs_open_context *ctx, int error)
+static inline bool nfs_error_is_fatal_on_server(int err)
{
- ctx->error = error;
- smp_wmb();
- set_bit(NFS_CONTEXT_ERROR_WRITE, &ctx->flags);
+ switch (err) {
+ case 0:
+ case -ERESTARTSYS:
+ case -EINTR:
+ return false;
+ }
+ return nfs_error_is_fatal(err);
}
diff --git a/fs/nfs/io.c b/fs/nfs/io.c
index 9034b49..5088fda 100644
--- a/fs/nfs/io.c
+++ b/fs/nfs/io.c
@@ -25,7 +25,7 @@
/**
* nfs_start_io_read - declare the file is being used for buffered reads
- * @inode - file inode
+ * @inode: file inode
*
* Declare that a buffered read operation is about to start, and ensure
* that we block all direct I/O.
@@ -56,7 +56,7 @@
/**
* nfs_end_io_read - declare that the buffered read operation is done
- * @inode - file inode
+ * @inode: file inode
*
* Declare that a buffered read operation is done, and release the shared
* lock on inode->i_rwsem.
@@ -69,7 +69,7 @@
/**
* nfs_start_io_write - declare the file is being used for buffered writes
- * @inode - file inode
+ * @inode: file inode
*
* Declare that a buffered read operation is about to start, and ensure
* that we block all direct I/O.
@@ -83,7 +83,7 @@
/**
* nfs_end_io_write - declare that the buffered write operation is done
- * @inode - file inode
+ * @inode: file inode
*
* Declare that a buffered write operation is done, and release the
* lock on inode->i_rwsem.
@@ -105,7 +105,7 @@
/**
* nfs_end_io_direct - declare the file is being used for direct i/o
- * @inode - file inode
+ * @inode: file inode
*
* Declare that a direct I/O operation is about to start, and ensure
* that we block all buffered I/O.
@@ -136,7 +136,7 @@
/**
* nfs_end_io_direct - declare that the direct i/o operation is done
- * @inode - file inode
+ * @inode: file inode
*
* Declare that a direct I/O operation is done, and release the shared
* lock on inode->i_rwsem.
diff --git a/fs/nfs/mount_clnt.c b/fs/nfs/mount_clnt.c
index d979ff4..cb7c10e 100644
--- a/fs/nfs/mount_clnt.c
+++ b/fs/nfs/mount_clnt.c
@@ -163,6 +163,7 @@
.program = &mnt_program,
.version = info->version,
.authflavor = RPC_AUTH_UNIX,
+ .cred = current_cred(),
};
struct rpc_clnt *mnt_clnt;
int status;
@@ -249,6 +250,7 @@
.version = info->version,
.authflavor = RPC_AUTH_UNIX,
.flags = RPC_CLNT_CREATE_NOPING,
+ .cred = current_cred(),
};
struct rpc_message msg = {
.rpc_argp = info->dirpath,
diff --git a/fs/nfs/namespace.c b/fs/nfs/namespace.c
index e5686be..9287eb6 100644
--- a/fs/nfs/namespace.c
+++ b/fs/nfs/namespace.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* linux/fs/nfs/namespace.c
*
@@ -221,10 +222,10 @@
/**
* nfs_do_submount - set up mountpoint when crossing a filesystem boundary
- * @dentry - parent directory
- * @fh - filehandle for new root dentry
- * @fattr - attributes for new root inode
- * @authflavor - security flavor to use when performing the mount
+ * @dentry: parent directory
+ * @fh: filehandle for new root dentry
+ * @fattr: attributes for new root inode
+ * @authflavor: security flavor to use when performing the mount
*
*/
struct vfsmount *nfs_do_submount(struct dentry *dentry, struct nfs_fh *fh,
diff --git a/fs/nfs/netns.h b/fs/nfs/netns.h
index fc9978c..c8374f7 100644
--- a/fs/nfs/netns.h
+++ b/fs/nfs/netns.h
@@ -15,6 +15,8 @@
uint32_t major, minor;
};
+struct nfs_netns_client;
+
struct nfs_net {
struct cache_detail *nfs_dns_resolve;
struct rpc_pipe *bl_device_pipe;
@@ -29,6 +31,7 @@
unsigned short nfs_callback_tcpport6;
int cb_users[NFS4_MAX_MINOR_VERSION + 1];
#endif
+ struct nfs_netns_client *nfs_client;
spinlock_t nfs_client_lock;
ktime_t boot_time;
#ifdef CONFIG_PROC_FS
diff --git a/fs/nfs/nfs2super.c b/fs/nfs/nfs2super.c
index 0a9782c..467f21e 100644
--- a/fs/nfs/nfs2super.c
+++ b/fs/nfs/nfs2super.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (c) 2012 Netapp, Inc. All rights reserved.
*/
diff --git a/fs/nfs/nfs2xdr.c b/fs/nfs/nfs2xdr.c
index 350675e..cbc17a2 100644
--- a/fs/nfs/nfs2xdr.c
+++ b/fs/nfs/nfs2xdr.c
@@ -22,6 +22,7 @@
#include <linux/nfs.h>
#include <linux/nfs2.h>
#include <linux/nfs_fs.h>
+#include "nfstrace.h"
#include "internal.h"
#define NFSDBG_FACILITY NFSDBG_XDR
@@ -55,42 +56,16 @@
#define NFS_attrstat_sz (1+NFS_fattr_sz)
#define NFS_diropres_sz (1+NFS_fhandle_sz+NFS_fattr_sz)
-#define NFS_readlinkres_sz (2)
-#define NFS_readres_sz (1+NFS_fattr_sz+1)
+#define NFS_readlinkres_sz (2+1)
+#define NFS_readres_sz (1+NFS_fattr_sz+1+1)
#define NFS_writeres_sz (NFS_attrstat_sz)
#define NFS_stat_sz (1)
-#define NFS_readdirres_sz (1)
+#define NFS_readdirres_sz (1+1)
#define NFS_statfsres_sz (1+NFS_info_sz)
static int nfs_stat_to_errno(enum nfs_stat);
/*
- * While encoding arguments, set up the reply buffer in advance to
- * receive reply data directly into the page cache.
- */
-static void prepare_reply_buffer(struct rpc_rqst *req, struct page **pages,
- unsigned int base, unsigned int len,
- unsigned int bufsize)
-{
- struct rpc_auth *auth = req->rq_cred->cr_auth;
- unsigned int replen;
-
- replen = RPC_REPHDRSIZE + auth->au_rslack + bufsize;
- xdr_inline_pages(&req->rq_rcv_buf, replen << 2, pages, base, len);
-}
-
-/*
- * Handle decode buffer overflows out-of-line.
- */
-static void print_overflow_msg(const char *func, const struct xdr_stream *xdr)
-{
- dprintk("NFS: %s prematurely hit the end of our receive buffer. "
- "Remaining buffer length is %tu words.\n",
- func, xdr->end - xdr->p);
-}
-
-
-/*
* Encode/decode NFSv2 basic data types
*
* Basic NFSv2 data types are defined in section 2.3 of RFC 1094:
@@ -101,6 +76,20 @@
* or decoded inline.
*/
+static struct user_namespace *rpc_userns(const struct rpc_clnt *clnt)
+{
+ if (clnt && clnt->cl_cred)
+ return clnt->cl_cred->user_ns;
+ return &init_user_ns;
+}
+
+static struct user_namespace *rpc_rqst_userns(const struct rpc_rqst *rqstp)
+{
+ if (rqstp->rq_task)
+ return rpc_userns(rqstp->rq_task->tk_client);
+ return &init_user_ns;
+}
+
/*
* typedef opaque nfsdata<>;
*/
@@ -110,8 +99,8 @@
__be32 *p;
p = xdr_inline_decode(xdr, 4);
- if (unlikely(p == NULL))
- goto out_overflow;
+ if (unlikely(!p))
+ return -EIO;
count = be32_to_cpup(p);
recvd = xdr_read_pages(xdr, count);
if (unlikely(count > recvd))
@@ -125,9 +114,6 @@
"count %u > recvd %u\n", count, recvd);
count = recvd;
goto out;
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
}
/*
@@ -157,13 +143,16 @@
__be32 *p;
p = xdr_inline_decode(xdr, 4);
- if (unlikely(p == NULL))
- goto out_overflow;
- *status = be32_to_cpup(p);
+ if (unlikely(!p))
+ return -EIO;
+ if (unlikely(*p != cpu_to_be32(NFS_OK)))
+ goto out_status;
+ *status = 0;
return 0;
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
+out_status:
+ *status = be32_to_cpup(p);
+ trace_nfs_xdr_status(xdr, (int)*status);
+ return 0;
}
/*
@@ -205,14 +194,11 @@
__be32 *p;
p = xdr_inline_decode(xdr, NFS2_FHSIZE);
- if (unlikely(p == NULL))
- goto out_overflow;
+ if (unlikely(!p))
+ return -EIO;
fh->size = NFS2_FHSIZE;
memcpy(fh->data, p, NFS2_FHSIZE);
return 0;
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
}
/*
@@ -276,14 +262,15 @@
* };
*
*/
-static int decode_fattr(struct xdr_stream *xdr, struct nfs_fattr *fattr)
+static int decode_fattr(struct xdr_stream *xdr, struct nfs_fattr *fattr,
+ struct user_namespace *userns)
{
u32 rdev, type;
__be32 *p;
p = xdr_inline_decode(xdr, NFS_fattr_sz << 2);
- if (unlikely(p == NULL))
- goto out_overflow;
+ if (unlikely(!p))
+ return -EIO;
fattr->valid |= NFS_ATTR_FATTR_V2;
@@ -291,10 +278,10 @@
fattr->mode = be32_to_cpup(p++);
fattr->nlink = be32_to_cpup(p++);
- fattr->uid = make_kuid(&init_user_ns, be32_to_cpup(p++));
+ fattr->uid = make_kuid(userns, be32_to_cpup(p++));
if (!uid_valid(fattr->uid))
goto out_uid;
- fattr->gid = make_kgid(&init_user_ns, be32_to_cpup(p++));
+ fattr->gid = make_kgid(userns, be32_to_cpup(p++));
if (!gid_valid(fattr->gid))
goto out_gid;
@@ -325,9 +312,6 @@
out_gid:
dprintk("NFS: returned invalid gid\n");
return -EINVAL;
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
}
/*
@@ -352,7 +336,8 @@
return p;
}
-static void encode_sattr(struct xdr_stream *xdr, const struct iattr *attr)
+static void encode_sattr(struct xdr_stream *xdr, const struct iattr *attr,
+ struct user_namespace *userns)
{
struct timespec ts;
__be32 *p;
@@ -364,11 +349,11 @@
else
*p++ = cpu_to_be32(NFS2_SATTR_NOT_SET);
if (attr->ia_valid & ATTR_UID)
- *p++ = cpu_to_be32(from_kuid(&init_user_ns, attr->ia_uid));
+ *p++ = cpu_to_be32(from_kuid_munged(userns, attr->ia_uid));
else
*p++ = cpu_to_be32(NFS2_SATTR_NOT_SET);
if (attr->ia_valid & ATTR_GID)
- *p++ = cpu_to_be32(from_kgid(&init_user_ns, attr->ia_gid));
+ *p++ = cpu_to_be32(from_kgid_munged(userns, attr->ia_gid));
else
*p++ = cpu_to_be32(NFS2_SATTR_NOT_SET);
if (attr->ia_valid & ATTR_SIZE)
@@ -416,23 +401,20 @@
u32 count;
p = xdr_inline_decode(xdr, 4);
- if (unlikely(p == NULL))
- goto out_overflow;
+ if (unlikely(!p))
+ return -EIO;
count = be32_to_cpup(p);
if (count > NFS3_MAXNAMLEN)
goto out_nametoolong;
p = xdr_inline_decode(xdr, count);
- if (unlikely(p == NULL))
- goto out_overflow;
+ if (unlikely(!p))
+ return -EIO;
*name = (const char *)p;
*length = count;
return 0;
out_nametoolong:
dprintk("NFS: returned filename too long: %u\n", count);
return -ENAMETOOLONG;
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
}
/*
@@ -455,8 +437,8 @@
__be32 *p;
p = xdr_inline_decode(xdr, 4);
- if (unlikely(p == NULL))
- goto out_overflow;
+ if (unlikely(!p))
+ return -EIO;
length = be32_to_cpup(p);
if (unlikely(length >= xdr->buf->page_len || length > NFS_MAXPATHLEN))
goto out_size;
@@ -472,9 +454,6 @@
dprintk("NFS: server cheating in pathname result: "
"length %u > received %u\n", length, recvd);
return -EIO;
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
}
/*
@@ -488,7 +467,8 @@
* };
*/
static int decode_attrstat(struct xdr_stream *xdr, struct nfs_fattr *result,
- __u32 *op_status)
+ __u32 *op_status,
+ struct user_namespace *userns)
{
enum nfs_stat status;
int error;
@@ -500,7 +480,7 @@
*op_status = status;
if (status != NFS_OK)
goto out_default;
- error = decode_fattr(xdr, result);
+ error = decode_fattr(xdr, result, userns);
out:
return error;
out_default:
@@ -535,19 +515,21 @@
* void;
* };
*/
-static int decode_diropok(struct xdr_stream *xdr, struct nfs_diropok *result)
+static int decode_diropok(struct xdr_stream *xdr, struct nfs_diropok *result,
+ struct user_namespace *userns)
{
int error;
error = decode_fhandle(xdr, result->fh);
if (unlikely(error))
goto out;
- error = decode_fattr(xdr, result->fattr);
+ error = decode_fattr(xdr, result->fattr, userns);
out:
return error;
}
-static int decode_diropres(struct xdr_stream *xdr, struct nfs_diropok *result)
+static int decode_diropres(struct xdr_stream *xdr, struct nfs_diropok *result,
+ struct user_namespace *userns)
{
enum nfs_stat status;
int error;
@@ -557,7 +539,7 @@
goto out;
if (status != NFS_OK)
goto out_default;
- error = decode_diropok(xdr, result);
+ error = decode_diropok(xdr, result, userns);
out:
return error;
out_default:
@@ -596,7 +578,7 @@
const struct nfs_sattrargs *args = data;
encode_fhandle(xdr, args->fh);
- encode_sattr(xdr, args->sattr);
+ encode_sattr(xdr, args->sattr, rpc_rqst_userns(req));
}
static void nfs2_xdr_enc_diropargs(struct rpc_rqst *req,
@@ -615,8 +597,8 @@
const struct nfs_readlinkargs *args = data;
encode_fhandle(xdr, args->fh);
- prepare_reply_buffer(req, args->pages, args->pgbase,
- args->pglen, NFS_readlinkres_sz);
+ rpc_prepare_reply_pages(req, args->pages, args->pgbase,
+ args->pglen, NFS_readlinkres_sz);
}
/*
@@ -651,8 +633,8 @@
const struct nfs_pgio_args *args = data;
encode_readargs(xdr, args);
- prepare_reply_buffer(req, args->pages, args->pgbase,
- args->count, NFS_readres_sz);
+ rpc_prepare_reply_pages(req, args->pages, args->pgbase,
+ args->count, NFS_readres_sz);
req->rq_rcv_buf.flags |= XDRBUF_READ;
}
@@ -711,7 +693,7 @@
const struct nfs_createargs *args = data;
encode_diropargs(xdr, args->fh, args->name, args->len);
- encode_sattr(xdr, args->sattr);
+ encode_sattr(xdr, args->sattr, rpc_rqst_userns(req));
}
static void nfs2_xdr_enc_removeargs(struct rpc_rqst *req,
@@ -778,7 +760,7 @@
encode_diropargs(xdr, args->fromfh, args->fromname, args->fromlen);
encode_path(xdr, args->pages, args->pathlen);
- encode_sattr(xdr, args->sattr);
+ encode_sattr(xdr, args->sattr, rpc_rqst_userns(req));
}
/*
@@ -809,8 +791,8 @@
const struct nfs_readdirargs *args = data;
encode_readdirargs(xdr, args);
- prepare_reply_buffer(req, args->pages, 0,
- args->count, NFS_readdirres_sz);
+ rpc_prepare_reply_pages(req, args->pages, 0,
+ args->count, NFS_readdirres_sz);
}
/*
@@ -840,13 +822,13 @@
static int nfs2_xdr_dec_attrstat(struct rpc_rqst *req, struct xdr_stream *xdr,
void *result)
{
- return decode_attrstat(xdr, result, NULL);
+ return decode_attrstat(xdr, result, NULL, rpc_rqst_userns(req));
}
static int nfs2_xdr_dec_diropres(struct rpc_rqst *req, struct xdr_stream *xdr,
void *result)
{
- return decode_diropres(xdr, result);
+ return decode_diropres(xdr, result, rpc_rqst_userns(req));
}
/*
@@ -901,7 +883,7 @@
result->op_status = status;
if (status != NFS_OK)
goto out_default;
- error = decode_fattr(xdr, result->fattr);
+ error = decode_fattr(xdr, result->fattr, rpc_rqst_userns(req));
if (unlikely(error))
goto out;
error = decode_nfsdata(xdr, result);
@@ -918,7 +900,8 @@
/* All NFSv2 writes are "file sync" writes */
result->verf->committed = NFS_FILE_SYNC;
- return decode_attrstat(xdr, result->fattr, &result->op_status);
+ return decode_attrstat(xdr, result->fattr, &result->op_status,
+ rpc_rqst_userns(req));
}
/**
@@ -951,12 +934,12 @@
int error;
p = xdr_inline_decode(xdr, 4);
- if (unlikely(p == NULL))
- goto out_overflow;
+ if (unlikely(!p))
+ return -EAGAIN;
if (*p++ == xdr_zero) {
p = xdr_inline_decode(xdr, 4);
- if (unlikely(p == NULL))
- goto out_overflow;
+ if (unlikely(!p))
+ return -EAGAIN;
if (*p++ == xdr_zero)
return -EAGAIN;
entry->eof = 1;
@@ -964,8 +947,8 @@
}
p = xdr_inline_decode(xdr, 4);
- if (unlikely(p == NULL))
- goto out_overflow;
+ if (unlikely(!p))
+ return -EAGAIN;
entry->ino = be32_to_cpup(p);
error = decode_filename_inline(xdr, &entry->name, &entry->len);
@@ -978,17 +961,13 @@
*/
entry->prev_cookie = entry->cookie;
p = xdr_inline_decode(xdr, 4);
- if (unlikely(p == NULL))
- goto out_overflow;
+ if (unlikely(!p))
+ return -EAGAIN;
entry->cookie = be32_to_cpup(p);
entry->d_type = DT_UNKNOWN;
return 0;
-
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EAGAIN;
}
/*
@@ -1052,17 +1031,14 @@
__be32 *p;
p = xdr_inline_decode(xdr, NFS_info_sz << 2);
- if (unlikely(p == NULL))
- goto out_overflow;
+ if (unlikely(!p))
+ return -EIO;
result->tsize = be32_to_cpup(p++);
result->bsize = be32_to_cpup(p++);
result->blocks = be32_to_cpup(p++);
result->bfree = be32_to_cpup(p++);
result->bavail = be32_to_cpup(p);
return 0;
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
}
static int nfs2_xdr_dec_statfsres(struct rpc_rqst *req, struct xdr_stream *xdr,
diff --git a/fs/nfs/nfs3acl.c b/fs/nfs/nfs3acl.c
index 9fce185..c5c3fc6 100644
--- a/fs/nfs/nfs3acl.c
+++ b/fs/nfs/nfs3acl.c
@@ -222,8 +222,6 @@
switch (status) {
case 0:
status = nfs_refresh_inode(inode, fattr);
- set_cached_acl(inode, ACL_TYPE_ACCESS, acl);
- set_cached_acl(inode, ACL_TYPE_DEFAULT, dfacl);
break;
case -EPFNOSUPPORT:
case -EPROTONOSUPPORT:
diff --git a/fs/nfs/nfs3client.c b/fs/nfs/nfs3client.c
index 7879f2a..148ceb7 100644
--- a/fs/nfs/nfs3client.c
+++ b/fs/nfs/nfs3client.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
#include <linux/nfs_fs.h>
#include <linux/nfs_mount.h>
#include <linux/sunrpc/addr.h>
@@ -91,6 +92,7 @@
.proto = ds_proto,
.net = mds_clp->cl_net,
.timeparms = &ds_timeout,
+ .cred = mds_srv->cred,
};
struct nfs_client *clp;
char buf[INET6_ADDRSTRLEN + 1];
@@ -100,6 +102,9 @@
return ERR_PTR(-EINVAL);
cl_init.hostname = buf;
+ if (mds_clp->cl_nconnect > 1 && ds_proto == XPRT_TRANSPORT_TCP)
+ cl_init.nconnect = mds_clp->cl_nconnect;
+
if (mds_srv->flags & NFS_MOUNT_NORESVPORT)
set_bit(NFS_CS_NORESVPORT, &cl_init.init_flags);
diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c
index ec8a9ef..9eb2f1a 100644
--- a/fs/nfs/nfs3proc.c
+++ b/fs/nfs/nfs3proc.c
@@ -279,15 +279,17 @@
return data;
}
-static int nfs3_do_create(struct inode *dir, struct dentry *dentry, struct nfs3_createdata *data)
+static struct dentry *
+nfs3_do_create(struct inode *dir, struct dentry *dentry, struct nfs3_createdata *data)
{
int status;
status = rpc_call_sync(NFS_CLIENT(dir), &data->msg, 0);
nfs_post_op_update_inode(dir, data->res.dir_attr);
- if (status == 0)
- status = nfs_instantiate(dentry, data->res.fh, data->res.fattr, NULL);
- return status;
+ if (status != 0)
+ return ERR_PTR(status);
+
+ return nfs_add_or_obtain(dentry, data->res.fh, data->res.fattr, NULL);
}
static void nfs3_free_createdata(struct nfs3_createdata *data)
@@ -304,6 +306,7 @@
{
struct posix_acl *default_acl, *acl;
struct nfs3_createdata *data;
+ struct dentry *d_alias;
int status = -ENOMEM;
dprintk("NFS call create %pd\n", dentry);
@@ -330,7 +333,8 @@
goto out;
for (;;) {
- status = nfs3_do_create(dir, dentry, data);
+ d_alias = nfs3_do_create(dir, dentry, data);
+ status = PTR_ERR_OR_ZERO(d_alias);
if (status != -ENOTSUPP)
break;
@@ -355,6 +359,9 @@
if (status != 0)
goto out_release_acls;
+ if (d_alias)
+ dentry = d_alias;
+
/* When we created the file with exclusive semantics, make
* sure we set the attributes afterwards. */
if (data->arg.create.createmode == NFS3_CREATE_EXCLUSIVE) {
@@ -372,11 +379,13 @@
nfs_post_op_update_inode(d_inode(dentry), data->res.fattr);
dprintk("NFS reply setattr (post-create): %d\n", status);
if (status != 0)
- goto out_release_acls;
+ goto out_dput;
}
status = nfs3_proc_setacls(d_inode(dentry), acl, default_acl);
+out_dput:
+ dput(d_alias);
out_release_acls:
posix_acl_release(acl);
posix_acl_release(default_acl);
@@ -504,6 +513,7 @@
unsigned int len, struct iattr *sattr)
{
struct nfs3_createdata *data;
+ struct dentry *d_alias;
int status = -ENOMEM;
if (len > NFS3_MAXPATHLEN)
@@ -522,7 +532,11 @@
data->arg.symlink.pathlen = len;
data->arg.symlink.sattr = sattr;
- status = nfs3_do_create(dir, dentry, data);
+ d_alias = nfs3_do_create(dir, dentry, data);
+ status = PTR_ERR_OR_ZERO(d_alias);
+
+ if (status == 0)
+ dput(d_alias);
nfs3_free_createdata(data);
out:
@@ -535,6 +549,7 @@
{
struct posix_acl *default_acl, *acl;
struct nfs3_createdata *data;
+ struct dentry *d_alias;
int status = -ENOMEM;
dprintk("NFS call mkdir %pd\n", dentry);
@@ -553,12 +568,18 @@
data->arg.mkdir.len = dentry->d_name.len;
data->arg.mkdir.sattr = sattr;
- status = nfs3_do_create(dir, dentry, data);
+ d_alias = nfs3_do_create(dir, dentry, data);
+ status = PTR_ERR_OR_ZERO(d_alias);
+
if (status != 0)
goto out_release_acls;
+ if (d_alias)
+ dentry = d_alias;
+
status = nfs3_proc_setacls(d_inode(dentry), acl, default_acl);
+ dput(d_alias);
out_release_acls:
posix_acl_release(acl);
posix_acl_release(default_acl);
@@ -607,7 +628,7 @@
* readdirplus.
*/
static int
-nfs3_proc_readdir(struct dentry *dentry, struct rpc_cred *cred,
+nfs3_proc_readdir(struct dentry *dentry, const struct cred *cred,
u64 cookie, struct page **pages, unsigned int count, bool plus)
{
struct inode *dir = d_inode(dentry);
@@ -628,7 +649,7 @@
.rpc_proc = &nfs3_procedures[NFS3PROC_READDIR],
.rpc_argp = &arg,
.rpc_resp = &res,
- .rpc_cred = cred
+ .rpc_cred = cred,
};
int status = -ENOMEM;
@@ -660,6 +681,7 @@
{
struct posix_acl *default_acl, *acl;
struct nfs3_createdata *data;
+ struct dentry *d_alias;
int status = -ENOMEM;
dprintk("NFS call mknod %pd %u:%u\n", dentry,
@@ -698,12 +720,17 @@
goto out;
}
- status = nfs3_do_create(dir, dentry, data);
+ d_alias = nfs3_do_create(dir, dentry, data);
+ status = PTR_ERR_OR_ZERO(d_alias);
if (status != 0)
goto out_release_acls;
+ if (d_alias)
+ dentry = d_alias;
+
status = nfs3_proc_setacls(d_inode(dentry), acl, default_acl);
+ dput(d_alias);
out_release_acls:
posix_acl_release(acl);
posix_acl_release(default_acl);
@@ -786,6 +813,7 @@
static int nfs3_read_done(struct rpc_task *task, struct nfs_pgio_header *hdr)
{
struct inode *inode = hdr->inode;
+ struct nfs_server *server = NFS_SERVER(inode);
if (hdr->pgio_done_cb != NULL)
return hdr->pgio_done_cb(task, hdr);
@@ -793,6 +821,9 @@
if (nfs3_async_handle_jukebox(task, inode))
return -EAGAIN;
+ if (task->tk_status >= 0 && !server->read_hdrsize)
+ cmpxchg(&server->read_hdrsize, 0, hdr->res.replen);
+
nfs_invalidate_atime(inode);
nfs_refresh_inode(inode, &hdr->fattr);
return 0;
@@ -802,6 +833,7 @@
struct rpc_message *msg)
{
msg->rpc_proc = &nfs3_procedures[NFS3PROC_READ];
+ hdr->args.replen = NFS_SERVER(hdr->inode)->read_hdrsize;
}
static int nfs3_proc_pgio_rpc_prepare(struct rpc_task *task,
diff --git a/fs/nfs/nfs3super.c b/fs/nfs/nfs3super.c
index 5c4394e..7c58094 100644
--- a/fs/nfs/nfs3super.c
+++ b/fs/nfs/nfs3super.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (c) 2012 Netapp, Inc. All rights reserved.
*/
diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c
index 64e4fa3..6027678 100644
--- a/fs/nfs/nfs3xdr.c
+++ b/fs/nfs/nfs3xdr.c
@@ -21,6 +21,7 @@
#include <linux/nfs3.h>
#include <linux/nfs_fs.h>
#include <linux/nfsacl.h>
+#include "nfstrace.h"
#include "internal.h"
#define NFSDBG_FACILITY NFSDBG_XDR
@@ -68,13 +69,13 @@
#define NFS3_removeres_sz (NFS3_setattrres_sz)
#define NFS3_lookupres_sz (1+NFS3_fh_sz+(2 * NFS3_post_op_attr_sz))
#define NFS3_accessres_sz (1+NFS3_post_op_attr_sz+1)
-#define NFS3_readlinkres_sz (1+NFS3_post_op_attr_sz+1)
-#define NFS3_readres_sz (1+NFS3_post_op_attr_sz+3)
+#define NFS3_readlinkres_sz (1+NFS3_post_op_attr_sz+1+1)
+#define NFS3_readres_sz (1+NFS3_post_op_attr_sz+3+1)
#define NFS3_writeres_sz (1+NFS3_wcc_data_sz+4)
#define NFS3_createres_sz (1+NFS3_fh_sz+NFS3_post_op_attr_sz+NFS3_wcc_data_sz)
#define NFS3_renameres_sz (1+(2 * NFS3_wcc_data_sz))
#define NFS3_linkres_sz (1+NFS3_post_op_attr_sz+NFS3_wcc_data_sz)
-#define NFS3_readdirres_sz (1+NFS3_post_op_attr_sz+2)
+#define NFS3_readdirres_sz (1+NFS3_post_op_attr_sz+2+1)
#define NFS3_fsstatres_sz (1+NFS3_post_op_attr_sz+13)
#define NFS3_fsinfores_sz (1+NFS3_post_op_attr_sz+12)
#define NFS3_pathconfres_sz (1+NFS3_post_op_attr_sz+6)
@@ -84,7 +85,7 @@
#define ACL3_setaclargs_sz (NFS3_fh_sz+1+ \
XDR_QUADLEN(NFS_ACL_INLINE_BUFSIZE))
#define ACL3_getaclres_sz (1+NFS3_post_op_attr_sz+1+ \
- XDR_QUADLEN(NFS_ACL_INLINE_BUFSIZE))
+ XDR_QUADLEN(NFS_ACL_INLINE_BUFSIZE)+1)
#define ACL3_setaclres_sz (1+NFS3_post_op_attr_sz)
static int nfs3_stat_to_errno(enum nfs_stat);
@@ -103,32 +104,20 @@
[NF3FIFO] = S_IFIFO,
};
-/*
- * While encoding arguments, set up the reply buffer in advance to
- * receive reply data directly into the page cache.
- */
-static void prepare_reply_buffer(struct rpc_rqst *req, struct page **pages,
- unsigned int base, unsigned int len,
- unsigned int bufsize)
+static struct user_namespace *rpc_userns(const struct rpc_clnt *clnt)
{
- struct rpc_auth *auth = req->rq_cred->cr_auth;
- unsigned int replen;
-
- replen = RPC_REPHDRSIZE + auth->au_rslack + bufsize;
- xdr_inline_pages(&req->rq_rcv_buf, replen << 2, pages, base, len);
+ if (clnt && clnt->cl_cred)
+ return clnt->cl_cred->user_ns;
+ return &init_user_ns;
}
-/*
- * Handle decode buffer overflows out-of-line.
- */
-static void print_overflow_msg(const char *func, const struct xdr_stream *xdr)
+static struct user_namespace *rpc_rqst_userns(const struct rpc_rqst *rqstp)
{
- dprintk("NFS: %s prematurely hit the end of our receive buffer. "
- "Remaining buffer length is %tu words.\n",
- func, xdr->end - xdr->p);
+ if (rqstp->rq_task)
+ return rpc_userns(rqstp->rq_task->tk_client);
+ return &init_user_ns;
}
-
/*
* Encode/decode NFSv3 basic data types
*
@@ -151,13 +140,10 @@
__be32 *p;
p = xdr_inline_decode(xdr, 4);
- if (unlikely(p == NULL))
- goto out_overflow;
+ if (unlikely(!p))
+ return -EIO;
*value = be32_to_cpup(p);
return 0;
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
}
static int decode_uint64(struct xdr_stream *xdr, u64 *value)
@@ -165,13 +151,10 @@
__be32 *p;
p = xdr_inline_decode(xdr, 8);
- if (unlikely(p == NULL))
- goto out_overflow;
+ if (unlikely(!p))
+ return -EIO;
xdr_decode_hyper(p, value);
return 0;
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
}
/*
@@ -211,14 +194,14 @@
u32 count;
p = xdr_inline_decode(xdr, 4);
- if (unlikely(p == NULL))
- goto out_overflow;
+ if (unlikely(!p))
+ return -EIO;
count = be32_to_cpup(p);
if (count > NFS3_MAXNAMLEN)
goto out_nametoolong;
p = xdr_inline_decode(xdr, count);
- if (unlikely(p == NULL))
- goto out_overflow;
+ if (unlikely(!p))
+ return -EIO;
*name = (const char *)p;
*length = count;
return 0;
@@ -226,9 +209,6 @@
out_nametoolong:
dprintk("NFS: returned filename too long: %u\n", count);
return -ENAMETOOLONG;
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
}
/*
@@ -249,8 +229,8 @@
__be32 *p;
p = xdr_inline_decode(xdr, 4);
- if (unlikely(p == NULL))
- goto out_overflow;
+ if (unlikely(!p))
+ return -EIO;
count = be32_to_cpup(p);
if (unlikely(count >= xdr->buf->page_len || count > NFS3_MAXPATHLEN))
goto out_nametoolong;
@@ -267,9 +247,6 @@
dprintk("NFS: server cheating in pathname result: "
"count %u > recvd %u\n", count, recvd);
return -EIO;
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
}
/*
@@ -303,13 +280,10 @@
__be32 *p;
p = xdr_inline_decode(xdr, NFS3_COOKIEVERFSIZE);
- if (unlikely(p == NULL))
- goto out_overflow;
+ if (unlikely(!p))
+ return -EIO;
memcpy(verifier, p, NFS3_COOKIEVERFSIZE);
return 0;
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
}
/*
@@ -330,13 +304,10 @@
__be32 *p;
p = xdr_inline_decode(xdr, NFS3_WRITEVERFSIZE);
- if (unlikely(p == NULL))
- goto out_overflow;
+ if (unlikely(!p))
+ return -EIO;
memcpy(verifier->data, p, NFS3_WRITEVERFSIZE);
return 0;
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
}
/*
@@ -364,13 +335,16 @@
__be32 *p;
p = xdr_inline_decode(xdr, 4);
- if (unlikely(p == NULL))
- goto out_overflow;
- *status = be32_to_cpup(p);
+ if (unlikely(!p))
+ return -EIO;
+ if (unlikely(*p != cpu_to_be32(NFS3_OK)))
+ goto out_status;
+ *status = 0;
return 0;
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
+out_status:
+ *status = be32_to_cpup(p);
+ trace_nfs_xdr_status(xdr, (int)*status);
+ return 0;
}
/*
@@ -453,23 +427,20 @@
__be32 *p;
p = xdr_inline_decode(xdr, 4);
- if (unlikely(p == NULL))
- goto out_overflow;
+ if (unlikely(!p))
+ return -EIO;
length = be32_to_cpup(p++);
if (unlikely(length > NFS3_FHSIZE))
goto out_toobig;
p = xdr_inline_decode(xdr, length);
- if (unlikely(p == NULL))
- goto out_overflow;
+ if (unlikely(!p))
+ return -EIO;
fh->size = length;
memcpy(fh->data, p, length);
return 0;
out_toobig:
dprintk("NFS: file handle size (%u) too big\n", length);
return -E2BIG;
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
}
static void zero_nfs_fh3(struct nfs_fh *fh)
@@ -559,7 +530,8 @@
* set_mtime mtime;
* };
*/
-static void encode_sattr3(struct xdr_stream *xdr, const struct iattr *attr)
+static void encode_sattr3(struct xdr_stream *xdr, const struct iattr *attr,
+ struct user_namespace *userns)
{
struct timespec ts;
u32 nbytes;
@@ -594,13 +566,13 @@
if (attr->ia_valid & ATTR_UID) {
*p++ = xdr_one;
- *p++ = cpu_to_be32(from_kuid(&init_user_ns, attr->ia_uid));
+ *p++ = cpu_to_be32(from_kuid_munged(userns, attr->ia_uid));
} else
*p++ = xdr_zero;
if (attr->ia_valid & ATTR_GID) {
*p++ = xdr_one;
- *p++ = cpu_to_be32(from_kgid(&init_user_ns, attr->ia_gid));
+ *p++ = cpu_to_be32(from_kgid_munged(userns, attr->ia_gid));
} else
*p++ = xdr_zero;
@@ -649,23 +621,24 @@
* nfstime3 ctime;
* };
*/
-static int decode_fattr3(struct xdr_stream *xdr, struct nfs_fattr *fattr)
+static int decode_fattr3(struct xdr_stream *xdr, struct nfs_fattr *fattr,
+ struct user_namespace *userns)
{
umode_t fmode;
__be32 *p;
p = xdr_inline_decode(xdr, NFS3_fattr_sz << 2);
- if (unlikely(p == NULL))
- goto out_overflow;
+ if (unlikely(!p))
+ return -EIO;
p = xdr_decode_ftype3(p, &fmode);
fattr->mode = (be32_to_cpup(p++) & ~S_IFMT) | fmode;
fattr->nlink = be32_to_cpup(p++);
- fattr->uid = make_kuid(&init_user_ns, be32_to_cpup(p++));
+ fattr->uid = make_kuid(userns, be32_to_cpup(p++));
if (!uid_valid(fattr->uid))
goto out_uid;
- fattr->gid = make_kgid(&init_user_ns, be32_to_cpup(p++));
+ fattr->gid = make_kgid(userns, be32_to_cpup(p++));
if (!gid_valid(fattr->gid))
goto out_gid;
@@ -690,9 +663,6 @@
out_gid:
dprintk("NFS: returned invalid gid\n");
return -EINVAL;
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
}
/*
@@ -705,19 +675,17 @@
* void;
* };
*/
-static int decode_post_op_attr(struct xdr_stream *xdr, struct nfs_fattr *fattr)
+static int decode_post_op_attr(struct xdr_stream *xdr, struct nfs_fattr *fattr,
+ struct user_namespace *userns)
{
__be32 *p;
p = xdr_inline_decode(xdr, 4);
- if (unlikely(p == NULL))
- goto out_overflow;
+ if (unlikely(!p))
+ return -EIO;
if (*p != xdr_zero)
- return decode_fattr3(xdr, fattr);
+ return decode_fattr3(xdr, fattr, userns);
return 0;
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
}
/*
@@ -733,8 +701,8 @@
__be32 *p;
p = xdr_inline_decode(xdr, NFS3_wcc_attr_sz << 2);
- if (unlikely(p == NULL))
- goto out_overflow;
+ if (unlikely(!p))
+ return -EIO;
fattr->valid |= NFS_ATTR_FATTR_PRESIZE
| NFS_ATTR_FATTR_PRECHANGE
@@ -747,9 +715,6 @@
fattr->pre_change_attr = nfs_timespec_to_change_attr(&fattr->pre_ctime);
return 0;
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
}
/*
@@ -773,24 +738,22 @@
__be32 *p;
p = xdr_inline_decode(xdr, 4);
- if (unlikely(p == NULL))
- goto out_overflow;
+ if (unlikely(!p))
+ return -EIO;
if (*p != xdr_zero)
return decode_wcc_attr(xdr, fattr);
return 0;
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
}
-static int decode_wcc_data(struct xdr_stream *xdr, struct nfs_fattr *fattr)
+static int decode_wcc_data(struct xdr_stream *xdr, struct nfs_fattr *fattr,
+ struct user_namespace *userns)
{
int error;
error = decode_pre_op_attr(xdr, fattr);
if (unlikely(error))
goto out;
- error = decode_post_op_attr(xdr, fattr);
+ error = decode_post_op_attr(xdr, fattr, userns);
out:
return error;
}
@@ -808,15 +771,12 @@
static int decode_post_op_fh3(struct xdr_stream *xdr, struct nfs_fh *fh)
{
__be32 *p = xdr_inline_decode(xdr, 4);
- if (unlikely(p == NULL))
- goto out_overflow;
+ if (unlikely(!p))
+ return -EIO;
if (*p != xdr_zero)
return decode_nfs_fh3(xdr, fh);
zero_nfs_fh3(fh);
return 0;
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
}
/*
@@ -895,7 +855,7 @@
{
const struct nfs3_sattrargs *args = data;
encode_nfs_fh3(xdr, args->fh);
- encode_sattr3(xdr, args->sattr);
+ encode_sattr3(xdr, args->sattr, rpc_rqst_userns(req));
encode_sattrguard3(xdr, args);
}
@@ -953,8 +913,8 @@
const struct nfs3_readlinkargs *args = data;
encode_nfs_fh3(xdr, args->fh);
- prepare_reply_buffer(req, args->pages, args->pgbase,
- args->pglen, NFS3_readlinkres_sz);
+ rpc_prepare_reply_pages(req, args->pages, args->pgbase,
+ args->pglen, NFS3_readlinkres_sz);
}
/*
@@ -983,10 +943,11 @@
const void *data)
{
const struct nfs_pgio_args *args = data;
+ unsigned int replen = args->replen ? args->replen : NFS3_readres_sz;
encode_read3args(xdr, args);
- prepare_reply_buffer(req, args->pages, args->pgbase,
- args->count, NFS3_readres_sz);
+ rpc_prepare_reply_pages(req, args->pages, args->pgbase,
+ args->count, replen);
req->rq_rcv_buf.flags |= XDRBUF_READ;
}
@@ -1055,13 +1016,14 @@
* };
*/
static void encode_createhow3(struct xdr_stream *xdr,
- const struct nfs3_createargs *args)
+ const struct nfs3_createargs *args,
+ struct user_namespace *userns)
{
encode_uint32(xdr, args->createmode);
switch (args->createmode) {
case NFS3_CREATE_UNCHECKED:
case NFS3_CREATE_GUARDED:
- encode_sattr3(xdr, args->sattr);
+ encode_sattr3(xdr, args->sattr, userns);
break;
case NFS3_CREATE_EXCLUSIVE:
encode_createverf3(xdr, args->verifier);
@@ -1078,7 +1040,7 @@
const struct nfs3_createargs *args = data;
encode_diropargs3(xdr, args->fh, args->name, args->len);
- encode_createhow3(xdr, args);
+ encode_createhow3(xdr, args, rpc_rqst_userns(req));
}
/*
@@ -1096,7 +1058,7 @@
const struct nfs3_mkdirargs *args = data;
encode_diropargs3(xdr, args->fh, args->name, args->len);
- encode_sattr3(xdr, args->sattr);
+ encode_sattr3(xdr, args->sattr, rpc_rqst_userns(req));
}
/*
@@ -1113,11 +1075,12 @@
* };
*/
static void encode_symlinkdata3(struct xdr_stream *xdr,
- const void *data)
+ const void *data,
+ struct user_namespace *userns)
{
const struct nfs3_symlinkargs *args = data;
- encode_sattr3(xdr, args->sattr);
+ encode_sattr3(xdr, args->sattr, userns);
encode_nfspath3(xdr, args->pages, args->pathlen);
}
@@ -1128,7 +1091,7 @@
const struct nfs3_symlinkargs *args = data;
encode_diropargs3(xdr, args->fromfh, args->fromname, args->fromlen);
- encode_symlinkdata3(xdr, args);
+ encode_symlinkdata3(xdr, args, rpc_rqst_userns(req));
xdr->buf->flags |= XDRBUF_WRITE;
}
@@ -1157,24 +1120,26 @@
* };
*/
static void encode_devicedata3(struct xdr_stream *xdr,
- const struct nfs3_mknodargs *args)
+ const struct nfs3_mknodargs *args,
+ struct user_namespace *userns)
{
- encode_sattr3(xdr, args->sattr);
+ encode_sattr3(xdr, args->sattr, userns);
encode_specdata3(xdr, args->rdev);
}
static void encode_mknoddata3(struct xdr_stream *xdr,
- const struct nfs3_mknodargs *args)
+ const struct nfs3_mknodargs *args,
+ struct user_namespace *userns)
{
encode_ftype3(xdr, args->type);
switch (args->type) {
case NF3CHR:
case NF3BLK:
- encode_devicedata3(xdr, args);
+ encode_devicedata3(xdr, args, userns);
break;
case NF3SOCK:
case NF3FIFO:
- encode_sattr3(xdr, args->sattr);
+ encode_sattr3(xdr, args->sattr, userns);
break;
case NF3REG:
case NF3DIR:
@@ -1191,7 +1156,7 @@
const struct nfs3_mknodargs *args = data;
encode_diropargs3(xdr, args->fh, args->name, args->len);
- encode_mknoddata3(xdr, args);
+ encode_mknoddata3(xdr, args, rpc_rqst_userns(req));
}
/*
@@ -1278,7 +1243,7 @@
const struct nfs3_readdirargs *args = data;
encode_readdir3args(xdr, args);
- prepare_reply_buffer(req, args->pages, 0,
+ rpc_prepare_reply_pages(req, args->pages, 0,
args->count, NFS3_readdirres_sz);
}
@@ -1320,7 +1285,7 @@
const struct nfs3_readdirargs *args = data;
encode_readdirplus3args(xdr, args);
- prepare_reply_buffer(req, args->pages, 0,
+ rpc_prepare_reply_pages(req, args->pages, 0,
args->count, NFS3_readdirres_sz);
}
@@ -1364,10 +1329,12 @@
encode_nfs_fh3(xdr, args->fh);
encode_uint32(xdr, args->mask);
- if (args->mask & (NFS_ACL | NFS_DFACL))
- prepare_reply_buffer(req, args->pages, 0,
+ if (args->mask & (NFS_ACL | NFS_DFACL)) {
+ rpc_prepare_reply_pages(req, args->pages, 0,
NFSACL_MAXPAGES << PAGE_SHIFT,
ACL3_getaclres_sz);
+ req->rq_rcv_buf.flags |= XDRBUF_SPARSE_PAGES;
+ }
}
static void nfs3_xdr_enc_setacl3args(struct rpc_rqst *req,
@@ -1434,7 +1401,7 @@
goto out;
if (status != NFS3_OK)
goto out_default;
- error = decode_fattr3(xdr, result);
+ error = decode_fattr3(xdr, result, rpc_rqst_userns(req));
out:
return error;
out_default:
@@ -1469,7 +1436,7 @@
error = decode_nfsstat3(xdr, &status);
if (unlikely(error))
goto out;
- error = decode_wcc_data(xdr, result);
+ error = decode_wcc_data(xdr, result, rpc_rqst_userns(req));
if (unlikely(error))
goto out;
if (status != NFS3_OK)
@@ -1504,6 +1471,7 @@
struct xdr_stream *xdr,
void *data)
{
+ struct user_namespace *userns = rpc_rqst_userns(req);
struct nfs3_diropres *result = data;
enum nfs_stat status;
int error;
@@ -1516,14 +1484,14 @@
error = decode_nfs_fh3(xdr, result->fh);
if (unlikely(error))
goto out;
- error = decode_post_op_attr(xdr, result->fattr);
+ error = decode_post_op_attr(xdr, result->fattr, userns);
if (unlikely(error))
goto out;
- error = decode_post_op_attr(xdr, result->dir_attr);
+ error = decode_post_op_attr(xdr, result->dir_attr, userns);
out:
return error;
out_default:
- error = decode_post_op_attr(xdr, result->dir_attr);
+ error = decode_post_op_attr(xdr, result->dir_attr, userns);
if (unlikely(error))
goto out;
return nfs3_stat_to_errno(status);
@@ -1559,7 +1527,7 @@
error = decode_nfsstat3(xdr, &status);
if (unlikely(error))
goto out;
- error = decode_post_op_attr(xdr, result->fattr);
+ error = decode_post_op_attr(xdr, result->fattr, rpc_rqst_userns(req));
if (unlikely(error))
goto out;
if (status != NFS3_OK)
@@ -1600,7 +1568,7 @@
error = decode_nfsstat3(xdr, &status);
if (unlikely(error))
goto out;
- error = decode_post_op_attr(xdr, result);
+ error = decode_post_op_attr(xdr, result, rpc_rqst_userns(req));
if (unlikely(error))
goto out;
if (status != NFS3_OK)
@@ -1640,8 +1608,8 @@
__be32 *p;
p = xdr_inline_decode(xdr, 4 + 4 + 4);
- if (unlikely(p == NULL))
- goto out_overflow;
+ if (unlikely(!p))
+ return -EIO;
count = be32_to_cpup(p++);
eof = be32_to_cpup(p++);
ocount = be32_to_cpup(p++);
@@ -1664,27 +1632,27 @@
count = recvd;
eof = 0;
goto out;
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
}
static int nfs3_xdr_dec_read3res(struct rpc_rqst *req, struct xdr_stream *xdr,
void *data)
{
struct nfs_pgio_res *result = data;
+ unsigned int pos;
enum nfs_stat status;
int error;
+ pos = xdr_stream_pos(xdr);
error = decode_nfsstat3(xdr, &status);
if (unlikely(error))
goto out;
- error = decode_post_op_attr(xdr, result->fattr);
+ error = decode_post_op_attr(xdr, result->fattr, rpc_rqst_userns(req));
if (unlikely(error))
goto out;
result->op_status = status;
if (status != NFS3_OK)
goto out_status;
+ result->replen = 4 + ((xdr_stream_pos(xdr) - pos) >> 2);
error = decode_read3resok(xdr, result);
out:
return error;
@@ -1725,22 +1693,18 @@
__be32 *p;
p = xdr_inline_decode(xdr, 4 + 4);
- if (unlikely(p == NULL))
- goto out_overflow;
+ if (unlikely(!p))
+ return -EIO;
result->count = be32_to_cpup(p++);
result->verf->committed = be32_to_cpup(p++);
if (unlikely(result->verf->committed > NFS_FILE_SYNC))
goto out_badvalue;
if (decode_writeverf3(xdr, &result->verf->verifier))
- goto out_eio;
+ return -EIO;
return result->count;
out_badvalue:
dprintk("NFS: bad stable_how value: %u\n", result->verf->committed);
return -EIO;
-out_overflow:
- print_overflow_msg(__func__, xdr);
-out_eio:
- return -EIO;
}
static int nfs3_xdr_dec_write3res(struct rpc_rqst *req, struct xdr_stream *xdr,
@@ -1753,7 +1717,7 @@
error = decode_nfsstat3(xdr, &status);
if (unlikely(error))
goto out;
- error = decode_wcc_data(xdr, result->fattr);
+ error = decode_wcc_data(xdr, result->fattr, rpc_rqst_userns(req));
if (unlikely(error))
goto out;
result->op_status = status;
@@ -1787,14 +1751,15 @@
* };
*/
static int decode_create3resok(struct xdr_stream *xdr,
- struct nfs3_diropres *result)
+ struct nfs3_diropres *result,
+ struct user_namespace *userns)
{
int error;
error = decode_post_op_fh3(xdr, result->fh);
if (unlikely(error))
goto out;
- error = decode_post_op_attr(xdr, result->fattr);
+ error = decode_post_op_attr(xdr, result->fattr, userns);
if (unlikely(error))
goto out;
/* The server isn't required to return a file handle.
@@ -1803,7 +1768,7 @@
* values for the new object. */
if (result->fh->size == 0)
result->fattr->valid = 0;
- error = decode_wcc_data(xdr, result->dir_attr);
+ error = decode_wcc_data(xdr, result->dir_attr, userns);
out:
return error;
}
@@ -1812,6 +1777,7 @@
struct xdr_stream *xdr,
void *data)
{
+ struct user_namespace *userns = rpc_rqst_userns(req);
struct nfs3_diropres *result = data;
enum nfs_stat status;
int error;
@@ -1821,11 +1787,11 @@
goto out;
if (status != NFS3_OK)
goto out_default;
- error = decode_create3resok(xdr, result);
+ error = decode_create3resok(xdr, result, userns);
out:
return error;
out_default:
- error = decode_wcc_data(xdr, result->dir_attr);
+ error = decode_wcc_data(xdr, result->dir_attr, userns);
if (unlikely(error))
goto out;
return nfs3_stat_to_errno(status);
@@ -1860,7 +1826,7 @@
error = decode_nfsstat3(xdr, &status);
if (unlikely(error))
goto out;
- error = decode_wcc_data(xdr, result->dir_attr);
+ error = decode_wcc_data(xdr, result->dir_attr, rpc_rqst_userns(req));
if (unlikely(error))
goto out;
if (status != NFS3_OK)
@@ -1895,6 +1861,7 @@
struct xdr_stream *xdr,
void *data)
{
+ struct user_namespace *userns = rpc_rqst_userns(req);
struct nfs_renameres *result = data;
enum nfs_stat status;
int error;
@@ -1902,10 +1869,10 @@
error = decode_nfsstat3(xdr, &status);
if (unlikely(error))
goto out;
- error = decode_wcc_data(xdr, result->old_fattr);
+ error = decode_wcc_data(xdr, result->old_fattr, userns);
if (unlikely(error))
goto out;
- error = decode_wcc_data(xdr, result->new_fattr);
+ error = decode_wcc_data(xdr, result->new_fattr, userns);
if (unlikely(error))
goto out;
if (status != NFS3_OK)
@@ -1939,6 +1906,7 @@
static int nfs3_xdr_dec_link3res(struct rpc_rqst *req, struct xdr_stream *xdr,
void *data)
{
+ struct user_namespace *userns = rpc_rqst_userns(req);
struct nfs3_linkres *result = data;
enum nfs_stat status;
int error;
@@ -1946,10 +1914,10 @@
error = decode_nfsstat3(xdr, &status);
if (unlikely(error))
goto out;
- error = decode_post_op_attr(xdr, result->fattr);
+ error = decode_post_op_attr(xdr, result->fattr, userns);
if (unlikely(error))
goto out;
- error = decode_wcc_data(xdr, result->dir_attr);
+ error = decode_wcc_data(xdr, result->dir_attr, userns);
if (unlikely(error))
goto out;
if (status != NFS3_OK)
@@ -1998,18 +1966,19 @@
int nfs3_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry,
bool plus)
{
+ struct user_namespace *userns = rpc_userns(entry->server->client);
struct nfs_entry old = *entry;
__be32 *p;
int error;
u64 new_cookie;
p = xdr_inline_decode(xdr, 4);
- if (unlikely(p == NULL))
- goto out_overflow;
+ if (unlikely(!p))
+ return -EAGAIN;
if (*p == xdr_zero) {
p = xdr_inline_decode(xdr, 4);
- if (unlikely(p == NULL))
- goto out_overflow;
+ if (unlikely(!p))
+ return -EAGAIN;
if (*p == xdr_zero)
return -EAGAIN;
entry->eof = 1;
@@ -2032,7 +2001,7 @@
if (plus) {
entry->fattr->valid = 0;
- error = decode_post_op_attr(xdr, entry->fattr);
+ error = decode_post_op_attr(xdr, entry->fattr, userns);
if (unlikely(error))
return error;
if (entry->fattr->valid & NFS_ATTR_FATTR_V3)
@@ -2045,8 +2014,8 @@
/* In fact, a post_op_fh3: */
p = xdr_inline_decode(xdr, 4);
- if (unlikely(p == NULL))
- goto out_overflow;
+ if (unlikely(!p))
+ return -EAGAIN;
if (*p != xdr_zero) {
error = decode_nfs_fh3(xdr, entry->fh);
if (unlikely(error)) {
@@ -2063,9 +2032,6 @@
return 0;
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EAGAIN;
out_truncated:
dprintk("NFS: directory entry contains invalid file handle\n");
*entry = old;
@@ -2107,11 +2073,12 @@
}
static int decode_readdir3resok(struct xdr_stream *xdr,
- struct nfs3_readdirres *result)
+ struct nfs3_readdirres *result,
+ struct user_namespace *userns)
{
int error;
- error = decode_post_op_attr(xdr, result->dir_attr);
+ error = decode_post_op_attr(xdr, result->dir_attr, userns);
if (unlikely(error))
goto out;
/* XXX: do we need to check if result->verf != NULL ? */
@@ -2136,11 +2103,11 @@
goto out;
if (status != NFS3_OK)
goto out_default;
- error = decode_readdir3resok(xdr, result);
+ error = decode_readdir3resok(xdr, result, rpc_rqst_userns(req));
out:
return error;
out_default:
- error = decode_post_op_attr(xdr, result->dir_attr);
+ error = decode_post_op_attr(xdr, result->dir_attr, rpc_rqst_userns(req));
if (unlikely(error))
goto out;
return nfs3_stat_to_errno(status);
@@ -2177,8 +2144,8 @@
__be32 *p;
p = xdr_inline_decode(xdr, 8 * 6 + 4);
- if (unlikely(p == NULL))
- goto out_overflow;
+ if (unlikely(!p))
+ return -EIO;
p = xdr_decode_size3(p, &result->tbytes);
p = xdr_decode_size3(p, &result->fbytes);
p = xdr_decode_size3(p, &result->abytes);
@@ -2187,9 +2154,6 @@
xdr_decode_size3(p, &result->afiles);
/* ignore invarsec */
return 0;
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
}
static int nfs3_xdr_dec_fsstat3res(struct rpc_rqst *req,
@@ -2203,7 +2167,7 @@
error = decode_nfsstat3(xdr, &status);
if (unlikely(error))
goto out;
- error = decode_post_op_attr(xdr, result->fattr);
+ error = decode_post_op_attr(xdr, result->fattr, rpc_rqst_userns(req));
if (unlikely(error))
goto out;
if (status != NFS3_OK)
@@ -2249,8 +2213,8 @@
__be32 *p;
p = xdr_inline_decode(xdr, 4 * 7 + 8 + 8 + 4);
- if (unlikely(p == NULL))
- goto out_overflow;
+ if (unlikely(!p))
+ return -EIO;
result->rtmax = be32_to_cpup(p++);
result->rtpref = be32_to_cpup(p++);
result->rtmult = be32_to_cpup(p++);
@@ -2264,9 +2228,6 @@
/* ignore properties */
result->lease_time = 0;
return 0;
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
}
static int nfs3_xdr_dec_fsinfo3res(struct rpc_rqst *req,
@@ -2280,7 +2241,7 @@
error = decode_nfsstat3(xdr, &status);
if (unlikely(error))
goto out;
- error = decode_post_op_attr(xdr, result->fattr);
+ error = decode_post_op_attr(xdr, result->fattr, rpc_rqst_userns(req));
if (unlikely(error))
goto out;
if (status != NFS3_OK)
@@ -2322,15 +2283,12 @@
__be32 *p;
p = xdr_inline_decode(xdr, 4 * 6);
- if (unlikely(p == NULL))
- goto out_overflow;
+ if (unlikely(!p))
+ return -EIO;
result->max_link = be32_to_cpup(p++);
result->max_namelen = be32_to_cpup(p);
/* ignore remaining fields */
return 0;
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
}
static int nfs3_xdr_dec_pathconf3res(struct rpc_rqst *req,
@@ -2344,7 +2302,7 @@
error = decode_nfsstat3(xdr, &status);
if (unlikely(error))
goto out;
- error = decode_post_op_attr(xdr, result->fattr);
+ error = decode_post_op_attr(xdr, result->fattr, rpc_rqst_userns(req));
if (unlikely(error))
goto out;
if (status != NFS3_OK)
@@ -2386,7 +2344,7 @@
error = decode_nfsstat3(xdr, &status);
if (unlikely(error))
goto out;
- error = decode_wcc_data(xdr, result->fattr);
+ error = decode_wcc_data(xdr, result->fattr, rpc_rqst_userns(req));
if (unlikely(error))
goto out;
result->op_status = status;
@@ -2402,14 +2360,15 @@
#ifdef CONFIG_NFS_V3_ACL
static inline int decode_getacl3resok(struct xdr_stream *xdr,
- struct nfs3_getaclres *result)
+ struct nfs3_getaclres *result,
+ struct user_namespace *userns)
{
struct posix_acl **acl;
unsigned int *aclcnt;
size_t hdrlen;
int error;
- error = decode_post_op_attr(xdr, result->fattr);
+ error = decode_post_op_attr(xdr, result->fattr, userns);
if (unlikely(error))
goto out;
error = decode_uint32(xdr, &result->mask);
@@ -2457,7 +2416,7 @@
goto out;
if (status != NFS3_OK)
goto out_default;
- error = decode_getacl3resok(xdr, result);
+ error = decode_getacl3resok(xdr, result, rpc_rqst_userns(req));
out:
return error;
out_default:
@@ -2476,7 +2435,7 @@
goto out;
if (status != NFS3_OK)
goto out_default;
- error = decode_post_op_attr(xdr, result);
+ error = decode_post_op_attr(xdr, result, rpc_rqst_userns(req));
out:
return error;
out_default:
diff --git a/fs/nfs/nfs42.h b/fs/nfs/nfs42.h
index 19ec38f..901cca7 100644
--- a/fs/nfs/nfs42.h
+++ b/fs/nfs/nfs42.h
@@ -20,5 +20,8 @@
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 fed06fd..5196bfa 100644
--- a/fs/nfs/nfs42proc.c
+++ b/fs/nfs/nfs42proc.c
@@ -329,9 +329,6 @@
};
ssize_t err, err2;
- if (!nfs_server_capable(file_inode(dst), NFS_CAP_COPY))
- return -EOPNOTSUPP;
-
src_lock = nfs_get_lock_context(nfs_file_open_context(src));
if (IS_ERR(src_lock))
return PTR_ERR(src_lock);
@@ -672,6 +669,170 @@
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 69f72ed..aed865a 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 */ + \
@@ -59,43 +68,53 @@
#define decode_clone_maxsz (op_decode_hdr_maxsz)
#define NFS4_enc_allocate_sz (compound_encode_hdr_maxsz + \
+ encode_sequence_maxsz + \
encode_putfh_maxsz + \
encode_allocate_maxsz + \
encode_getattr_maxsz)
#define NFS4_dec_allocate_sz (compound_decode_hdr_maxsz + \
+ decode_sequence_maxsz + \
decode_putfh_maxsz + \
decode_allocate_maxsz + \
decode_getattr_maxsz)
#define NFS4_enc_copy_sz (compound_encode_hdr_maxsz + \
+ encode_sequence_maxsz + \
encode_putfh_maxsz + \
encode_savefh_maxsz + \
encode_putfh_maxsz + \
encode_copy_maxsz + \
encode_commit_maxsz)
#define NFS4_dec_copy_sz (compound_decode_hdr_maxsz + \
+ decode_sequence_maxsz + \
decode_putfh_maxsz + \
decode_savefh_maxsz + \
decode_putfh_maxsz + \
decode_copy_maxsz + \
decode_commit_maxsz)
#define NFS4_enc_offload_cancel_sz (compound_encode_hdr_maxsz + \
+ encode_sequence_maxsz + \
encode_putfh_maxsz + \
encode_offload_cancel_maxsz)
#define NFS4_dec_offload_cancel_sz (compound_decode_hdr_maxsz + \
+ decode_sequence_maxsz + \
decode_putfh_maxsz + \
decode_offload_cancel_maxsz)
#define NFS4_enc_deallocate_sz (compound_encode_hdr_maxsz + \
+ encode_sequence_maxsz + \
encode_putfh_maxsz + \
encode_deallocate_maxsz + \
encode_getattr_maxsz)
#define NFS4_dec_deallocate_sz (compound_decode_hdr_maxsz + \
+ decode_sequence_maxsz + \
decode_putfh_maxsz + \
decode_deallocate_maxsz + \
decode_getattr_maxsz)
#define NFS4_enc_seek_sz (compound_encode_hdr_maxsz + \
+ encode_sequence_maxsz + \
encode_putfh_maxsz + \
encode_seek_maxsz)
#define NFS4_dec_seek_sz (compound_decode_hdr_maxsz + \
+ decode_sequence_maxsz + \
decode_putfh_maxsz + \
decode_seek_maxsz)
#define NFS4_enc_layoutstats_sz (compound_encode_hdr_maxsz + \
@@ -106,6 +125,16 @@
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 +252,34 @@
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 +438,27 @@
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);
@@ -394,7 +472,7 @@
p = xdr_inline_decode(xdr, 4);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
count = be32_to_cpup(p);
if (count > 1)
return -EREMOTEIO;
@@ -402,18 +480,14 @@
status = decode_opaque_fixed(xdr, &res->stateid,
NFS4_STATEID_SIZE);
if (unlikely(status))
- goto out_overflow;
+ return -EIO;
}
p = xdr_inline_decode(xdr, 8 + 4);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
p = xdr_decode_hyper(p, &res->count);
res->verifier.committed = be32_to_cpup(p);
return decode_verifier(xdr, &res->verifier.verifier);
-
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
}
static int decode_copy_requirements(struct xdr_stream *xdr,
@@ -422,14 +496,11 @@
p = xdr_inline_decode(xdr, 4 + 4);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
res->consecutive = be32_to_cpup(p++);
res->synchronous = be32_to_cpup(p++);
return 0;
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
}
static int decode_copy(struct xdr_stream *xdr, struct nfs42_copy_res *res)
@@ -474,15 +545,11 @@
p = xdr_inline_decode(xdr, 4 + 8);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
res->sr_eof = be32_to_cpup(p++);
p = xdr_decode_hyper(p, &res->sr_offset);
return 0;
-
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
}
static int decode_layoutstats(struct xdr_stream *xdr)
@@ -495,6 +562,11 @@
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
*/
@@ -704,4 +776,30 @@
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/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index 63287d9..16b2e5c 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -62,10 +62,11 @@
void (*free_lock_state)(struct nfs_server *,
struct nfs4_lock_state *);
int (*test_and_free_expired)(struct nfs_server *,
- nfs4_stateid *, struct rpc_cred *);
+ nfs4_stateid *, const struct cred *);
struct nfs_seqid *
(*alloc_seqid)(struct nfs_seqid_counter *, gfp_t);
- int (*session_trunk)(struct rpc_clnt *, struct rpc_xprt *, void *);
+ void (*session_trunk)(struct rpc_clnt *clnt,
+ struct rpc_xprt *xprt, void *data);
const struct rpc_call_ops *call_sync_ops;
const struct nfs4_state_recovery_ops *reboot_recovery_ops;
const struct nfs4_state_recovery_ops *nograce_recovery_ops;
@@ -107,7 +108,7 @@
unsigned long so_expires;
struct rb_node so_server_node;
- struct rpc_cred *so_cred; /* Associated cred */
+ const struct cred *so_cred; /* Associated cred */
spinlock_t so_lock;
atomic_t so_count;
@@ -190,9 +191,10 @@
unsigned int n_wronly; /* Number of write-only references */
unsigned int n_rdwr; /* Number of read/write references */
fmode_t state; /* State on the server (R,W, or RW) */
- atomic_t count;
+ refcount_t count;
wait_queue_head_t waitq;
+ struct rcu_head rcu_head;
};
@@ -204,6 +206,7 @@
unsigned char delay : 1,
recovering : 1,
retry : 1;
+ bool interruptible;
};
struct nfs4_state_recovery_ops {
@@ -211,10 +214,10 @@
int state_flag_bit;
int (*recover_open)(struct nfs4_state_owner *, struct nfs4_state *);
int (*recover_lock)(struct nfs4_state *, struct file_lock *);
- int (*establish_clid)(struct nfs_client *, struct rpc_cred *);
- int (*reclaim_complete)(struct nfs_client *, struct rpc_cred *);
+ int (*establish_clid)(struct nfs_client *, const struct cred *);
+ int (*reclaim_complete)(struct nfs_client *, const struct cred *);
int (*detect_trunking)(struct nfs_client *, struct nfs_client **,
- struct rpc_cred *);
+ const struct cred *);
};
struct nfs4_opendata {
@@ -244,19 +247,19 @@
struct nfs4_add_xprt_data {
struct nfs_client *clp;
- struct rpc_cred *cred;
+ const struct cred *cred;
};
struct nfs4_state_maintenance_ops {
- int (*sched_state_renewal)(struct nfs_client *, struct rpc_cred *, unsigned);
- struct rpc_cred * (*get_state_renewal_cred_locked)(struct nfs_client *);
- int (*renew_lease)(struct nfs_client *, struct rpc_cred *);
+ int (*sched_state_renewal)(struct nfs_client *, const struct cred *, unsigned);
+ const struct cred * (*get_state_renewal_cred)(struct nfs_client *);
+ int (*renew_lease)(struct nfs_client *, const struct cred *);
};
struct nfs4_mig_recovery_ops {
int (*get_locations)(struct inode *, struct nfs4_fs_locations *,
- struct page *, struct rpc_cred *);
- int (*fsid_present)(struct inode *, struct rpc_cred *);
+ struct page *, const struct cred *);
+ int (*fsid_present)(struct inode *, const struct cred *);
};
extern const struct dentry_operations nfs4_dentry_operations;
@@ -285,21 +288,21 @@
struct rpc_message *, struct nfs4_sequence_args *,
struct nfs4_sequence_res *, int);
extern void nfs4_init_sequence(struct nfs4_sequence_args *, struct nfs4_sequence_res *, int, int);
-extern int nfs4_proc_setclientid(struct nfs_client *, u32, unsigned short, struct rpc_cred *, struct nfs4_setclientid_res *);
-extern int nfs4_proc_setclientid_confirm(struct nfs_client *, struct nfs4_setclientid_res *arg, struct rpc_cred *);
+extern int nfs4_proc_setclientid(struct nfs_client *, u32, unsigned short, const struct cred *, struct nfs4_setclientid_res *);
+extern int nfs4_proc_setclientid_confirm(struct nfs_client *, struct nfs4_setclientid_res *arg, const struct cred *);
extern int nfs4_proc_get_rootfh(struct nfs_server *, struct nfs_fh *, struct nfs_fsinfo *, bool);
-extern int nfs4_proc_bind_conn_to_session(struct nfs_client *, struct rpc_cred *cred);
-extern int nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred);
+extern int nfs4_proc_bind_conn_to_session(struct nfs_client *, const struct cred *cred);
+extern int nfs4_proc_exchange_id(struct nfs_client *clp, const struct cred *cred);
extern int nfs4_destroy_clientid(struct nfs_client *clp);
-extern int nfs4_init_clientid(struct nfs_client *, struct rpc_cred *);
-extern int nfs41_init_clientid(struct nfs_client *, struct rpc_cred *);
+extern int nfs4_init_clientid(struct nfs_client *, const struct cred *);
+extern int nfs41_init_clientid(struct nfs_client *, const struct cred *);
extern int nfs4_do_close(struct nfs4_state *state, gfp_t gfp_mask, int wait);
extern int nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *fhandle);
extern int nfs4_proc_fs_locations(struct rpc_clnt *, struct inode *, const struct qstr *,
struct nfs4_fs_locations *, struct page *);
extern int nfs4_proc_get_locations(struct inode *, struct nfs4_fs_locations *,
- struct page *page, struct rpc_cred *);
-extern int nfs4_proc_fsid_present(struct inode *, struct rpc_cred *);
+ struct page *page, const struct cred *);
+extern int nfs4_proc_fsid_present(struct inode *, const struct cred *);
extern struct rpc_clnt *nfs4_proc_lookup_mountpoint(struct inode *, const struct qstr *,
struct nfs_fh *, struct nfs_fattr *);
extern int nfs4_proc_secinfo(struct inode *, const struct qstr *, struct nfs4_secinfo_flavors *);
@@ -309,12 +312,12 @@
const struct nfs_lock_context *l_ctx,
fmode_t fmode);
-#if defined(CONFIG_NFS_V4_1)
-extern int nfs41_sequence_done(struct rpc_task *, struct nfs4_sequence_res *);
-extern int nfs4_proc_create_session(struct nfs_client *, struct rpc_cred *);
-extern int nfs4_proc_destroy_session(struct nfs4_session *, struct rpc_cred *);
extern int nfs4_proc_get_lease_time(struct nfs_client *clp,
struct nfs_fsinfo *fsinfo);
+#if defined(CONFIG_NFS_V4_1)
+extern int nfs41_sequence_done(struct rpc_task *, struct nfs4_sequence_res *);
+extern int nfs4_proc_create_session(struct nfs_client *, const struct cred *);
+extern int nfs4_proc_destroy_session(struct nfs4_session *, const struct cred *);
extern int nfs4_proc_layoutcommit(struct nfs4_layoutcommit_data *data,
bool sync);
extern int nfs4_detect_session_trunking(struct nfs_client *clp,
@@ -337,7 +340,6 @@
_nfs4_state_protect(struct nfs_client *clp, unsigned long sp4_mode,
struct rpc_clnt **clntp, struct rpc_message *msg)
{
- struct rpc_cred *newcred = NULL;
rpc_authflavor_t flavor;
if (sp4_mode == NFS_SP4_MACH_CRED_CLEANUP ||
@@ -352,13 +354,7 @@
return false;
}
if (test_bit(sp4_mode, &clp->cl_sp4_flags)) {
- spin_lock(&clp->cl_lock);
- if (clp->cl_machine_cred != NULL)
- /* don't call get_rpccred on the machine cred -
- * a reference will be held for life of clp */
- newcred = clp->cl_machine_cred;
- spin_unlock(&clp->cl_lock);
- msg->rpc_cred = newcred;
+ msg->rpc_cred = rpc_machine_cred();
flavor = clp->cl_rpcclient->cl_auth->au_flavor;
WARN_ON_ONCE(flavor != RPC_AUTH_GSS_KRB5I &&
@@ -449,16 +445,16 @@
/* nfs4state.c */
-struct rpc_cred *nfs4_get_clid_cred(struct nfs_client *clp);
-struct rpc_cred *nfs4_get_machine_cred_locked(struct nfs_client *clp);
-struct rpc_cred *nfs4_get_renew_cred_locked(struct nfs_client *clp);
+const struct cred *nfs4_get_clid_cred(struct nfs_client *clp);
+const struct cred *nfs4_get_machine_cred(struct nfs_client *clp);
+const struct cred *nfs4_get_renew_cred(struct nfs_client *clp);
int nfs4_discover_server_trunking(struct nfs_client *clp,
struct nfs_client **);
int nfs40_discover_server_trunking(struct nfs_client *clp,
- struct nfs_client **, struct rpc_cred *);
+ struct nfs_client **, const struct cred *);
#if defined(CONFIG_NFS_V4_1)
int nfs41_discover_server_trunking(struct nfs_client *clp,
- struct nfs_client **, struct rpc_cred *);
+ struct nfs_client **, const struct cred *);
extern void nfs4_schedule_session_recovery(struct nfs4_session *, int);
extern void nfs41_notify_server(struct nfs_client *);
#else
@@ -467,9 +463,10 @@
}
#endif /* CONFIG_NFS_V4_1 */
-extern struct nfs4_state_owner *nfs4_get_state_owner(struct nfs_server *, struct rpc_cred *, gfp_t);
+extern struct nfs4_state_owner *nfs4_get_state_owner(struct nfs_server *, const struct cred *, gfp_t);
extern void nfs4_put_state_owner(struct nfs4_state_owner *);
-extern void nfs4_purge_state_owners(struct nfs_server *);
+extern void nfs4_purge_state_owners(struct nfs_server *, struct list_head *);
+extern void nfs4_free_state_owners(struct list_head *head);
extern struct nfs4_state * nfs4_get_open_state(struct inode *, struct nfs4_state_owner *);
extern void nfs4_put_open_state(struct nfs4_state *);
extern void nfs4_close_state(struct nfs4_state *, fmode_t);
@@ -493,9 +490,7 @@
extern int nfs4_set_lock_state(struct nfs4_state *state, struct file_lock *fl);
extern int nfs4_select_rw_stateid(struct nfs4_state *, fmode_t,
const struct nfs_lock_context *, nfs4_stateid *,
- struct rpc_cred **);
-extern bool nfs4_refresh_open_stateid(nfs4_stateid *dst,
- struct nfs4_state *state);
+ const struct cred **);
extern bool nfs4_copy_open_stateid(nfs4_stateid *dst,
struct nfs4_state *state);
@@ -577,6 +572,15 @@
return (s32)(be32_to_cpu(s1->seqid) - be32_to_cpu(s2->seqid)) > 0;
}
+static inline void nfs4_stateid_seqid_inc(nfs4_stateid *s1)
+{
+ u32 seqid = be32_to_cpu(s1->seqid);
+
+ if (++seqid == 0)
+ ++seqid;
+ s1->seqid = cpu_to_be32(seqid);
+}
+
static inline bool nfs4_valid_open_stateid(const struct nfs4_state *state)
{
return test_bit(NFS_STATE_RECOVERY_FAILED, &state->flags) == 0;
diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index 8f53455..da62040 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (C) 2006 Red Hat, Inc. All Rights Reserved.
* Written by David Howells (dhowells@redhat.com)
@@ -42,7 +43,7 @@
}
#ifdef CONFIG_NFS_V4_1
-/**
+/*
* Per auth flavor data server rpc clients
*/
struct nfs4_ds_server {
@@ -51,7 +52,9 @@
};
/**
- * Common lookup case for DS I/O
+ * nfs4_find_ds_client - Common lookup case for DS I/O
+ * @ds_clp: pointer to the DS's nfs_client
+ * @flavor: rpc auth flavour to match
*/
static struct nfs4_ds_server *
nfs4_find_ds_client(struct nfs_client *ds_clp, rpc_authflavor_t flavor)
@@ -118,9 +121,13 @@
}
/**
-* Find or create a DS rpc client with th MDS server rpc client auth flavor
-* in the nfs_client cl_ds_clients list.
-*/
+ * nfs4_find_or_create_ds_client - Find or create a DS rpc client
+ * @ds_clp: pointer to the DS's nfs_client
+ * @inode: pointer to the inode
+ *
+ * Find or create a DS rpc client with th MDS server rpc client auth flavor
+ * in the nfs_client cl_ds_clients list.
+ */
struct rpc_clnt *
nfs4_find_or_create_ds_client(struct nfs_client *ds_clp, struct inode *inode)
{
@@ -145,7 +152,6 @@
nfs4_shutdown_ds_clients(struct nfs_client *clp)
{
struct nfs4_ds_server *dss;
- LIST_HEAD(shutdown_list);
while (!list_empty(&clp->cl_ds_clients)) {
dss = list_entry(clp->cl_ds_clients.next,
@@ -284,7 +290,7 @@
/**
* nfs40_init_client - nfs_client initialization tasks for NFSv4.0
- * @clp - nfs_client to initialize
+ * @clp: nfs_client to initialize
*
* Returns zero on success, or a negative errno if some error occurred.
*/
@@ -312,7 +318,7 @@
/**
* nfs41_init_client - nfs_client initialization tasks for NFSv4.1+
- * @clp - nfs_client to initialize
+ * @clp: nfs_client to initialize
*
* Returns zero on success, or a negative errno if some error occurred.
*/
@@ -360,9 +366,7 @@
* nfs4_init_client - Initialise an NFS4 client record
*
* @clp: nfs_client to initialise
- * @timeparms: timeout parameters for underlying RPC transport
- * @ip_addr: callback IP address in presentation format
- * @authflavor: authentication flavor for underlying RPC transport
+ * @cl_init: pointer to nfs_client_initdata
*
* Returns pointer to an NFS client, or an ERR_PTR value.
*/
@@ -545,7 +549,7 @@
*/
int nfs40_walk_client_list(struct nfs_client *new,
struct nfs_client **result,
- struct rpc_cred *cred)
+ const struct cred *cred)
{
struct nfs_net *nn = net_generic(new->cl_net, nfs_net_id);
struct nfs_client *pos, *prev = NULL;
@@ -649,13 +653,13 @@
/**
* nfs4_detect_session_trunking - Checks for session trunking.
- *
- * Called after a successful EXCHANGE_ID on a multi-addr connection.
- * Upon success, add the transport.
- *
* @clp: original mount nfs_client
* @res: result structure from an exchange_id using the original mount
* nfs_client with a new multi_addr transport
+ * @xprt: pointer to the transport to add.
+ *
+ * Called after a successful EXCHANGE_ID on a multi-addr connection.
+ * Upon success, add the transport.
*
* Returns zero on success, otherwise -EINVAL
*
@@ -711,7 +715,7 @@
*/
int nfs41_walk_client_list(struct nfs_client *new,
struct nfs_client **result,
- struct rpc_cred *cred)
+ const struct cred *cred)
{
struct nfs_net *nn = net_generic(new->cl_net, nfs_net_id);
struct nfs_client *pos, *prev = NULL;
@@ -754,9 +758,12 @@
static void nfs4_destroy_server(struct nfs_server *server)
{
+ LIST_HEAD(freeme);
+
nfs_server_return_all_delegations(server);
unset_pnfs_layoutdriver(server);
- nfs4_purge_state_owners(server);
+ nfs4_purge_state_owners(server, &freeme);
+ nfs4_free_state_owners(&freeme);
}
/*
@@ -855,7 +862,8 @@
const size_t addrlen,
const char *ip_addr,
int proto, const struct rpc_timeout *timeparms,
- u32 minorversion, struct net *net)
+ u32 minorversion, unsigned int nconnect,
+ struct net *net)
{
struct nfs_client_initdata cl_init = {
.hostname = hostname,
@@ -867,9 +875,12 @@
.minorversion = minorversion,
.net = net,
.timeparms = timeparms,
+ .cred = server->cred,
};
struct nfs_client *clp;
+ if (minorversion > 0 && proto == XPRT_TRANSPORT_TCP)
+ cl_init.nconnect = nconnect;
if (server->flags & NFS_MOUNT_NORESVPORT)
set_bit(NFS_CS_NORESVPORT, &cl_init.init_flags);
if (server->options & NFS_OPTION_MIGRATION)
@@ -928,6 +939,7 @@
.minorversion = minor_version,
.net = mds_clp->cl_net,
.timeparms = &ds_timeout,
+ .cred = mds_srv->cred,
};
char buf[INET6_ADDRSTRLEN + 1];
@@ -935,6 +947,9 @@
return ERR_PTR(-EINVAL);
cl_init.hostname = buf;
+ if (mds_clp->cl_nconnect > 1 && ds_proto == XPRT_TRANSPORT_TCP)
+ cl_init.nconnect = mds_clp->cl_nconnect;
+
if (mds_srv->flags & NFS_MOUNT_NORESVPORT)
__set_bit(NFS_CS_NORESVPORT, &cl_init.init_flags);
@@ -1068,6 +1083,7 @@
data->nfs_server.protocol,
&timeparms,
data->minorversion,
+ data->nfs_server.nconnect,
data->net);
if (error < 0)
return error;
@@ -1104,6 +1120,8 @@
if (!server)
return ERR_PTR(-ENOMEM);
+ server->cred = get_cred(current_cred());
+
auth_probe = mount_info->parsed->auth_info.flavor_len < 1;
/* set up the general RPC client */
@@ -1140,6 +1158,8 @@
parent_server = NFS_SB(data->sb);
parent_client = parent_server->nfs_client;
+ server->cred = get_cred(parent_server->cred);
+
/* Initialise the client representation from the parent server */
nfs_server_copy_userdata(server, parent_server);
@@ -1153,6 +1173,7 @@
XPRT_TRANSPORT_RDMA,
parent_server->client->cl_timeout,
parent_client->cl_mvops->minor_version,
+ parent_client->cl_nconnect,
parent_client->cl_net);
if (!error)
goto init_server;
@@ -1166,6 +1187,7 @@
XPRT_TRANSPORT_TCP,
parent_server->client->cl_timeout,
parent_client->cl_mvops->minor_version,
+ parent_client->cl_nconnect,
parent_client->cl_net);
if (error < 0)
goto error;
@@ -1261,7 +1283,8 @@
set_bit(NFS_MIG_TSM_POSSIBLE, &server->mig_status);
error = nfs4_set_client(server, hostname, sap, salen, buf,
clp->cl_proto, clnt->cl_timeout,
- clp->cl_minorversion, net);
+ clp->cl_minorversion,
+ clp->cl_nconnect, net);
clear_bit(NFS_MIG_TSM_POSSIBLE, &server->mig_status);
if (error != 0) {
nfs_server_insert_lists(server);
diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
index 4288a6e..339663d 100644
--- a/fs/nfs/nfs4file.c
+++ b/fs/nfs/nfs4file.c
@@ -49,7 +49,7 @@
return err;
if ((openflags & O_ACCMODE) == 3)
- openflags--;
+ return nfs_open(inode, filp);
/* We can't create new files here */
openflags &= ~(O_CREAT|O_EXCL);
@@ -73,13 +73,13 @@
if (IS_ERR(inode)) {
err = PTR_ERR(inode);
switch (err) {
- case -EPERM:
- case -EACCES:
- case -EDQUOT:
- case -ENOSPC:
- case -EROFS:
- goto out_put_ctx;
default:
+ goto out_put_ctx;
+ case -ENOENT:
+ case -ESTALE:
+ case -EISDIR:
+ case -ENOTDIR:
+ case -ELOOP:
goto out_drop;
}
}
@@ -125,22 +125,35 @@
return filemap_fdatawrite(file->f_mapping);
/* Flush writes to the server and return any errors */
- return vfs_fsync(file, 0);
+ return nfs_wb_all(inode);
}
#ifdef CONFIG_NFS_V4_2
+static ssize_t __nfs4_copy_file_range(struct file *file_in, loff_t pos_in,
+ struct file *file_out, loff_t pos_out,
+ size_t count, unsigned int flags)
+{
+ /* Only offload copy if superblock is the same */
+ if (file_inode(file_in)->i_sb != file_inode(file_out)->i_sb)
+ return -EXDEV;
+ if (!nfs_server_capable(file_inode(file_out), NFS_CAP_COPY))
+ return -EOPNOTSUPP;
+ if (file_inode(file_in) == file_inode(file_out))
+ return -EOPNOTSUPP;
+ return nfs42_proc_copy(file_in, pos_in, file_out, pos_out, count);
+}
+
static ssize_t nfs4_copy_file_range(struct file *file_in, loff_t pos_in,
struct file *file_out, loff_t pos_out,
size_t count, unsigned int flags)
{
ssize_t ret;
- if (file_inode(file_in) == file_inode(file_out))
- return -EINVAL;
-retry:
- ret = nfs42_proc_copy(file_in, pos_in, file_out, pos_out, count);
- if (ret == -EAGAIN)
- goto retry;
+ ret = __nfs4_copy_file_range(file_in, pos_in, file_out, pos_out, count,
+ flags);
+ if (ret == -EOPNOTSUPP || ret == -EXDEV)
+ ret = generic_copy_file_range(file_in, pos_in, file_out,
+ pos_out, count, flags);
return ret;
}
@@ -180,8 +193,9 @@
return nfs42_proc_allocate(filep, offset, len);
}
-static int nfs42_clone_file_range(struct file *src_file, loff_t src_off,
- struct file *dst_file, loff_t dst_off, u64 count)
+static loff_t nfs42_remap_file_range(struct file *src_file, loff_t src_off,
+ struct file *dst_file, loff_t dst_off, loff_t count,
+ unsigned int remap_flags)
{
struct inode *dst_inode = file_inode(dst_file);
struct nfs_server *server = NFS_SERVER(dst_inode);
@@ -190,6 +204,13 @@
bool same_inode = false;
int ret;
+ /* NFS does not support deduplication. */
+ if (remap_flags & REMAP_FILE_DEDUP)
+ return -EOPNOTSUPP;
+
+ if (remap_flags & ~REMAP_FILE_ADVISORY)
+ return -EINVAL;
+
/* check alignment w.r.t. clone_blksize */
ret = -EINVAL;
if (bs) {
@@ -240,7 +261,7 @@
inode_unlock(src_inode);
}
out:
- return ret;
+ return ret < 0 ? ret : count;
}
#endif /* CONFIG_NFS_V4_2 */
@@ -262,7 +283,7 @@
.copy_file_range = nfs4_copy_file_range,
.llseek = nfs4_file_llseek,
.fallocate = nfs42_fallocate,
- .clone_file_range = nfs42_clone_file_range,
+ .remap_file_range = nfs42_remap_file_range,
#else
.llseek = nfs_file_llseek,
#endif
diff --git a/fs/nfs/nfs4idmap.c b/fs/nfs/nfs4idmap.c
index 3f23b68..1e72963 100644
--- a/fs/nfs/nfs4idmap.c
+++ b/fs/nfs/nfs4idmap.c
@@ -44,6 +44,7 @@
#include <linux/keyctl.h>
#include <linux/key-type.h>
#include <keys/user-type.h>
+#include <keys/request_key_auth-type.h>
#include <linux/module.h>
#include "internal.h"
@@ -59,7 +60,7 @@
struct idmap_legacy_upcalldata {
struct rpc_pipe_msg pipe_msg;
struct idmap_msg idmap_msg;
- struct key_construction *key_cons;
+ struct key *authkey;
struct idmap *idmap;
};
@@ -68,8 +69,16 @@
struct rpc_pipe *idmap_pipe;
struct idmap_legacy_upcalldata *idmap_upcall_data;
struct mutex idmap_mutex;
+ const struct cred *cred;
};
+static struct user_namespace *idmap_userns(const struct idmap *idmap)
+{
+ if (idmap && idmap->cred)
+ return idmap->cred->user_ns;
+ return &init_user_ns;
+}
+
/**
* nfs_fattr_init_names - initialise the nfs_fattr owner_name/group_name fields
* @fattr: fully initialised struct nfs_fattr
@@ -270,18 +279,19 @@
const char *type, struct idmap *idmap)
{
char *desc;
- struct key *rkey;
+ struct key *rkey = ERR_PTR(-EAGAIN);
ssize_t ret;
ret = nfs_idmap_get_desc(name, namelen, type, strlen(type), &desc);
if (ret < 0)
return ERR_PTR(ret);
- rkey = request_key(&key_type_id_resolver, desc, "");
+ if (!idmap->cred || idmap->cred->user_ns == &init_user_ns)
+ rkey = request_key(&key_type_id_resolver, desc, "");
if (IS_ERR(rkey)) {
mutex_lock(&idmap->idmap_mutex);
rkey = request_key_with_auxdata(&key_type_id_resolver_legacy,
- desc, "", 0, idmap);
+ desc, NULL, "", 0, idmap);
mutex_unlock(&idmap->idmap_mutex);
}
if (!IS_ERR(rkey))
@@ -384,7 +394,7 @@
{ Opt_find_err, NULL }
};
-static int nfs_idmap_legacy_upcall(struct key_construction *, const char *, void *);
+static int nfs_idmap_legacy_upcall(struct key *, void *);
static ssize_t idmap_pipe_downcall(struct file *, const char __user *,
size_t);
static void idmap_release_pipe(struct inode *);
@@ -451,6 +461,9 @@
if (idmap == NULL)
return -ENOMEM;
+ mutex_init(&idmap->idmap_mutex);
+ idmap->cred = get_cred(clp->cl_rpcclient->cl_cred);
+
rpc_init_pipe_dir_object(&idmap->idmap_pdo,
&nfs_idmap_pipe_dir_object_ops,
idmap);
@@ -461,7 +474,6 @@
goto err;
}
idmap->idmap_pipe = pipe;
- mutex_init(&idmap->idmap_mutex);
error = rpc_add_pipe_dir_object(clp->cl_net,
&clp->cl_rpcclient->cl_pipedir_objects,
@@ -474,6 +486,7 @@
err_destroy_pipe:
rpc_destroy_pipe_data(idmap->idmap_pipe);
err:
+ put_cred(idmap->cred);
kfree(idmap);
return error;
}
@@ -490,6 +503,7 @@
&clp->cl_rpcclient->cl_pipedir_objects,
&idmap->idmap_pdo);
rpc_destroy_pipe_data(idmap->idmap_pipe);
+ put_cred(idmap->cred);
kfree(idmap);
}
@@ -549,11 +563,12 @@
static void
nfs_idmap_complete_pipe_upcall_locked(struct idmap *idmap, int ret)
{
- struct key_construction *cons = idmap->idmap_upcall_data->key_cons;
+ struct key *authkey = idmap->idmap_upcall_data->authkey;
kfree(idmap->idmap_upcall_data);
idmap->idmap_upcall_data = NULL;
- complete_request_key(cons, ret);
+ complete_request_key(authkey, ret);
+ key_put(authkey);
}
static void
@@ -563,15 +578,14 @@
nfs_idmap_complete_pipe_upcall_locked(idmap, ret);
}
-static int nfs_idmap_legacy_upcall(struct key_construction *cons,
- const char *op,
- void *aux)
+static int nfs_idmap_legacy_upcall(struct key *authkey, void *aux)
{
struct idmap_legacy_upcalldata *data;
+ struct request_key_auth *rka = get_request_key_auth(authkey);
struct rpc_pipe_msg *msg;
struct idmap_msg *im;
struct idmap *idmap = (struct idmap *)aux;
- struct key *key = cons->key;
+ struct key *key = rka->target_key;
int ret = -ENOKEY;
if (!aux)
@@ -586,7 +600,7 @@
msg = &data->pipe_msg;
im = &data->idmap_msg;
data->idmap = idmap;
- data->key_cons = cons;
+ data->authkey = key_get(authkey);
ret = nfs_idmap_prepare_message(key->description, idmap, im, msg);
if (ret < 0)
@@ -604,7 +618,7 @@
out2:
kfree(data);
out1:
- complete_request_key(cons, ret);
+ complete_request_key(authkey, ret);
return ret;
}
@@ -651,9 +665,10 @@
static ssize_t
idmap_pipe_downcall(struct file *filp, const char __user *src, size_t mlen)
{
+ struct request_key_auth *rka;
struct rpc_inode *rpci = RPC_I(file_inode(filp));
struct idmap *idmap = (struct idmap *)rpci->private;
- struct key_construction *cons;
+ struct key *authkey;
struct idmap_msg im;
size_t namelen_in;
int ret = -ENOKEY;
@@ -665,7 +680,8 @@
if (idmap->idmap_upcall_data == NULL)
goto out_noupcall;
- cons = idmap->idmap_upcall_data->key_cons;
+ authkey = idmap->idmap_upcall_data->authkey;
+ rka = get_request_key_auth(authkey);
if (mlen != sizeof(im)) {
ret = -ENOSPC;
@@ -690,9 +706,9 @@
ret = nfs_idmap_read_and_verify_message(&im,
&idmap->idmap_upcall_data->idmap_msg,
- cons->key, cons->authkey);
+ rka->target_key, authkey);
if (ret >= 0) {
- key_set_timeout(cons->key, nfs_idmap_cache_timeout);
+ key_set_timeout(rka->target_key, nfs_idmap_cache_timeout);
ret = mlen;
}
@@ -732,7 +748,7 @@
if (!nfs_map_string_to_numeric(name, namelen, &id))
ret = nfs_idmap_lookup_id(name, namelen, "uid", &id, idmap);
if (ret == 0) {
- *uid = make_kuid(&init_user_ns, id);
+ *uid = make_kuid(idmap_userns(idmap), id);
if (!uid_valid(*uid))
ret = -ERANGE;
}
@@ -749,7 +765,7 @@
if (!nfs_map_string_to_numeric(name, namelen, &id))
ret = nfs_idmap_lookup_id(name, namelen, "gid", &id, idmap);
if (ret == 0) {
- *gid = make_kgid(&init_user_ns, id);
+ *gid = make_kgid(idmap_userns(idmap), id);
if (!gid_valid(*gid))
ret = -ERANGE;
}
@@ -763,7 +779,7 @@
int ret = -EINVAL;
__u32 id;
- id = from_kuid(&init_user_ns, uid);
+ id = from_kuid_munged(idmap_userns(idmap), uid);
if (!(server->caps & NFS_CAP_UIDGID_NOMAP))
ret = nfs_idmap_lookup_name(id, "user", buf, buflen, idmap);
if (ret < 0)
@@ -777,7 +793,7 @@
int ret = -EINVAL;
__u32 id;
- id = from_kgid(&init_user_ns, gid);
+ id = from_kgid_munged(idmap_userns(idmap), gid);
if (!(server->caps & NFS_CAP_UIDGID_NOMAP))
ret = nfs_idmap_lookup_name(id, "group", buf, buflen, idmap);
if (ret < 0)
diff --git a/fs/nfs/nfs4namespace.c b/fs/nfs/nfs4namespace.c
index 24f06dc..2e460c3 100644
--- a/fs/nfs/nfs4namespace.c
+++ b/fs/nfs/nfs4namespace.c
@@ -137,6 +137,7 @@
/**
* nfs_find_best_sec - Find a security mechanism supported locally
+ * @clnt: pointer to rpc_clnt
* @server: NFS server struct
* @flavors: List of security tuples returned by SECINFO procedure
*
@@ -288,8 +289,8 @@
/**
* nfs_follow_referral - set up mountpoint when hitting a referral on moved error
- * @dentry - parent directory
- * @locations - array of NFSv4 server location information
+ * @dentry: parent directory
+ * @locations: array of NFSv4 server location information
*
*/
static struct vfsmount *nfs_follow_referral(struct dentry *dentry,
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 8220a16..caacf5e 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -93,19 +93,19 @@
static void nfs_fixup_referral_attributes(struct nfs_fattr *fattr);
static int nfs4_proc_getattr(struct nfs_server *, struct nfs_fh *, struct nfs_fattr *, struct nfs4_label *label, struct inode *inode);
static int _nfs4_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle, struct nfs_fattr *fattr, struct nfs4_label *label, struct inode *inode);
-static int nfs4_do_setattr(struct inode *inode, struct rpc_cred *cred,
+static int nfs4_do_setattr(struct inode *inode, const struct cred *cred,
struct nfs_fattr *fattr, struct iattr *sattr,
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,
+ const struct cred *cred,
struct nfs4_slot *slot,
bool is_privileged);
static int nfs41_test_stateid(struct nfs_server *, nfs4_stateid *,
- struct rpc_cred *);
+ const struct cred *);
static int nfs41_free_stateid(struct nfs_server *, const nfs4_stateid *,
- struct rpc_cred *, bool);
+ const struct cred *, bool);
#endif
#ifdef CONFIG_NFS_V4_SECURITY_LABEL
@@ -361,7 +361,7 @@
static void nfs4_test_and_free_stateid(struct nfs_server *server,
nfs4_stateid *stateid,
- struct rpc_cred *cred)
+ const struct cred *cred)
{
const struct nfs4_minor_version_ops *ops = server->nfs_client->cl_mvops;
@@ -370,7 +370,7 @@
static void __nfs4_free_revoked_stateid(struct nfs_server *server,
nfs4_stateid *stateid,
- struct rpc_cred *cred)
+ const struct cred *cred)
{
stateid->type = NFS4_REVOKED_STATEID_TYPE;
nfs4_test_and_free_stateid(server, stateid, cred);
@@ -378,7 +378,7 @@
static void nfs4_free_revoked_stateid(struct nfs_server *server,
const nfs4_stateid *stateid,
- struct rpc_cred *cred)
+ const struct cred *cred)
{
nfs4_stateid tmp;
@@ -400,17 +400,48 @@
return ret;
}
-static int nfs4_delay(struct rpc_clnt *clnt, long *timeout)
+static int nfs4_delay_killable(long *timeout)
{
- int res = 0;
-
might_sleep();
freezable_schedule_timeout_killable_unsafe(
nfs4_update_delay(timeout));
- if (fatal_signal_pending(current))
- res = -ERESTARTSYS;
- return res;
+ if (!__fatal_signal_pending(current))
+ return 0;
+ return -EINTR;
+}
+
+static int nfs4_delay_interruptible(long *timeout)
+{
+ might_sleep();
+
+ freezable_schedule_timeout_interruptible(nfs4_update_delay(timeout));
+ if (!signal_pending(current))
+ return 0;
+ return __fatal_signal_pending(current) ? -EINTR :-ERESTARTSYS;
+}
+
+static int nfs4_delay(long *timeout, bool interruptible)
+{
+ if (interruptible)
+ return nfs4_delay_interruptible(timeout);
+ return nfs4_delay_killable(timeout);
+}
+
+static const nfs4_stateid *
+nfs4_recoverable_stateid(const nfs4_stateid *stateid)
+{
+ if (!stateid)
+ return NULL;
+ switch (stateid->type) {
+ case NFS4_OPEN_STATEID_TYPE:
+ case NFS4_LOCK_STATEID_TYPE:
+ case NFS4_DELEGATION_STATEID_TYPE:
+ return stateid;
+ default:
+ break;
+ }
+ return NULL;
}
/* This is the error handling routine for processes that are allowed
@@ -421,7 +452,7 @@
{
struct nfs_client *clp = server->nfs_client;
struct nfs4_state *state = exception->state;
- const nfs4_stateid *stateid = exception->stateid;
+ const nfs4_stateid *stateid;
struct inode *inode = exception->inode;
int ret = errorcode;
@@ -429,8 +460,9 @@
exception->recovering = 0;
exception->retry = 0;
+ stateid = nfs4_recoverable_stateid(exception->stateid);
if (stateid == NULL && state != NULL)
- stateid = &state->stateid;
+ stateid = nfs4_recoverable_stateid(&state->stateid);
switch(errorcode) {
case 0:
@@ -546,7 +578,8 @@
ret = nfs4_do_handle_exception(server, errorcode, exception);
if (exception->delay) {
- ret = nfs4_delay(server->client, &exception->timeout);
+ ret = nfs4_delay(&exception->timeout,
+ exception->interruptible);
goto out_retry;
}
if (exception->recovering) {
@@ -730,33 +763,41 @@
res->sr_slot = NULL;
}
+static void nfs4_slot_sequence_record_sent(struct nfs4_slot *slot,
+ u32 seqnr)
+{
+ if ((s32)(seqnr - slot->seq_nr_highest_sent) > 0)
+ slot->seq_nr_highest_sent = seqnr;
+}
+static void nfs4_slot_sequence_acked(struct nfs4_slot *slot,
+ u32 seqnr)
+{
+ slot->seq_nr_highest_sent = seqnr;
+ slot->seq_nr_last_acked = seqnr;
+}
+
static int nfs41_sequence_process(struct rpc_task *task,
struct nfs4_sequence_res *res)
{
struct nfs4_session *session;
struct nfs4_slot *slot = res->sr_slot;
struct nfs_client *clp;
- bool interrupted = false;
int ret = 1;
if (slot == NULL)
goto out_noaction;
/* don't increment the sequence number if the task wasn't sent */
- if (!RPC_WAS_SENT(task))
+ if (!RPC_WAS_SENT(task) || slot->seq_done)
goto out;
session = slot->table->session;
- if (slot->interrupted) {
- if (res->sr_status != -NFS4ERR_DELAY)
- slot->interrupted = 0;
- interrupted = true;
- }
-
trace_nfs4_sequence_done(session, res);
/* Check the SEQUENCE operation status */
switch (res->sr_status) {
case 0:
+ /* Mark this sequence number as having been acked */
+ nfs4_slot_sequence_acked(slot, slot->seq_nr);
/* Update the slot's sequence and clientid lease timer */
slot->seq_done = 1;
clp = session->clp;
@@ -771,9 +812,9 @@
* sr_status remains 1 if an RPC level error occurred.
* The server may or may not have processed the sequence
* operation..
- * Mark the slot as having hosted an interrupted RPC call.
*/
- slot->interrupted = 1;
+ nfs4_slot_sequence_record_sent(slot, slot->seq_nr);
+ slot->seq_done = 1;
goto out;
case -NFS4ERR_DELAY:
/* The server detected a resend of the RPC call and
@@ -784,6 +825,7 @@
__func__,
slot->slot_nr,
slot->seq_nr);
+ nfs4_slot_sequence_acked(slot, slot->seq_nr);
goto out_retry;
case -NFS4ERR_RETRY_UNCACHED_REP:
case -NFS4ERR_SEQ_FALSE_RETRY:
@@ -791,6 +833,7 @@
* The server thinks we tried to replay a request.
* Retry the call after bumping the sequence ID.
*/
+ nfs4_slot_sequence_acked(slot, slot->seq_nr);
goto retry_new_seq;
case -NFS4ERR_BADSLOT:
/*
@@ -801,21 +844,28 @@
goto session_recover;
goto retry_nowait;
case -NFS4ERR_SEQ_MISORDERED:
+ nfs4_slot_sequence_record_sent(slot, slot->seq_nr);
/*
- * Was the last operation on this sequence interrupted?
- * If so, retry after bumping the sequence number.
+ * Were one or more calls using this slot interrupted?
+ * If the server never received the request, then our
+ * transmitted slot sequence number may be too high.
*/
- if (interrupted)
- goto retry_new_seq;
- /*
- * Could this slot have been previously retired?
- * If so, then the server may be expecting seq_nr = 1!
- */
- if (slot->seq_nr != 1) {
- slot->seq_nr = 1;
+ if ((s32)(slot->seq_nr - slot->seq_nr_last_acked) > 1) {
+ slot->seq_nr--;
goto retry_nowait;
}
- goto session_recover;
+ /*
+ * RFC5661:
+ * A retry might be sent while the original request is
+ * still in progress on the replier. The replier SHOULD
+ * deal with the issue by returning NFS4ERR_DELAY as the
+ * reply to SEQUENCE or CB_SEQUENCE operation, but
+ * implementations MAY return NFS4ERR_SEQ_MISORDERED.
+ *
+ * Restart the search after a delay.
+ */
+ slot->seq_nr = slot->seq_nr_highest_sent;
+ goto out_retry;
default:
/* Just update the slot sequence no. */
slot->seq_done = 1;
@@ -906,17 +956,6 @@
.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)
@@ -937,16 +976,15 @@
}
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 */
+static void nfs41_sequence_res_init(struct nfs4_sequence_res *res)
+{
+ res->sr_timestamp = jiffies;
+ res->sr_status_flags = 0;
+ res->sr_status = 1;
+}
+
static
void nfs4_sequence_attach_slot(struct nfs4_sequence_args *args,
struct nfs4_sequence_res *res,
@@ -958,10 +996,6 @@
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,
@@ -977,43 +1011,43 @@
if (res->sr_slot != NULL)
goto out_start;
- if (session) {
+ if (session)
tbl = &session->fc_slot_table;
- 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)) {
+ if (slot == ERR_PTR(-ENOMEM))
+ goto out_sleep_timeout;
+ goto out_sleep;
}
-
- 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);
-
- if (likely(!slot->interrupted))
- break;
- nfs4_sequence_process_interrupted(client,
- slot, task->tk_msg.rpc_cred);
- }
+ spin_unlock(&tbl->slot_tbl_lock);
nfs4_sequence_attach_slot(args, res, slot);
trace_nfs4_setup_sequence(session, args);
out_start:
+ nfs41_sequence_res_init(res);
rpc_call_start(task);
return 0;
-
+out_sleep_timeout:
+ /* Try again in 1/4 second */
+ if (args->sa_privileged)
+ rpc_sleep_on_priority_timeout(&tbl->slot_tbl_waitq, task,
+ jiffies + (HZ >> 2), RPC_PRIORITY_PRIVILEGED);
+ else
+ rpc_sleep_on_timeout(&tbl->slot_tbl_waitq, task,
+ NULL, jiffies + (HZ >> 2));
+ spin_unlock(&tbl->slot_tbl_lock);
+ return -EAGAIN;
out_sleep:
if (args->sa_privileged)
rpc_sleep_on_priority(&tbl->slot_tbl_waitq, task,
- NULL, RPC_PRIORITY_PRIVILEGED);
+ RPC_PRIORITY_PRIVILEGED);
else
rpc_sleep_on(&tbl->slot_tbl_waitq, task, NULL);
spin_unlock(&tbl->slot_tbl_lock);
@@ -1039,14 +1073,26 @@
.rpc_call_done = nfs40_call_sync_done,
};
+static int nfs4_call_sync_custom(struct rpc_task_setup *task_setup)
+{
+ int ret;
+ struct rpc_task *task;
+
+ task = rpc_run_task(task_setup);
+ if (IS_ERR(task))
+ return PTR_ERR(task);
+
+ ret = task->tk_status;
+ rpc_put_task(task);
+ return ret;
+}
+
static int nfs4_call_sync_sequence(struct rpc_clnt *clnt,
struct nfs_server *server,
struct rpc_message *msg,
struct nfs4_sequence_args *args,
struct nfs4_sequence_res *res)
{
- int ret;
- struct rpc_task *task;
struct nfs_client *clp = server->nfs_client;
struct nfs4_call_sync_data data = {
.seq_server = server,
@@ -1060,14 +1106,7 @@
.callback_data = &data
};
- task = rpc_run_task(&task_setup);
- if (IS_ERR(task))
- ret = PTR_ERR(task);
- else {
- ret = task->tk_status;
- rpc_put_task(task);
- }
- return ret;
+ return nfs4_call_sync_custom(&task_setup);
}
int nfs4_call_sync(struct rpc_clnt *clnt,
@@ -1148,6 +1187,18 @@
return true;
}
+static fmode_t _nfs4_ctx_to_accessmode(const struct nfs_open_context *ctx)
+{
+ return ctx->mode & (FMODE_READ|FMODE_WRITE|FMODE_EXEC);
+}
+
+static fmode_t _nfs4_ctx_to_openmode(const struct nfs_open_context *ctx)
+{
+ fmode_t ret = ctx->mode & (FMODE_READ|FMODE_WRITE);
+
+ return (ctx->mode & FMODE_EXEC) ? FMODE_READ | ret : ret;
+}
+
static u32
nfs4_map_atomic_open_share(struct nfs_server *server,
fmode_t fmode, int openflags)
@@ -1239,10 +1290,20 @@
atomic_inc(&sp->so_count);
p->o_arg.open_flags = flags;
p->o_arg.fmode = fmode & (FMODE_READ|FMODE_WRITE);
- p->o_arg.umask = current_umask();
p->o_arg.claim = nfs4_map_atomic_open_claim(server, claim);
p->o_arg.share_access = nfs4_map_atomic_open_share(server,
fmode, flags);
+ if (flags & O_CREAT) {
+ p->o_arg.umask = current_umask();
+ p->o_arg.label = nfs4_label_copy(p->a_label, label);
+ if (c->sattr != NULL && c->sattr->ia_valid != 0) {
+ p->o_arg.u.attrs = &p->attrs;
+ memcpy(&p->attrs, c->sattr, sizeof(p->attrs));
+
+ memcpy(p->o_arg.u.verifier.data, c->verf,
+ sizeof(p->o_arg.u.verifier.data));
+ }
+ }
/* don't put an ACCESS op in OPEN compound if O_EXCL, because ACCESS
* will return permission denied for all bits until close */
if (!(flags & O_EXCL)) {
@@ -1266,7 +1327,6 @@
p->o_arg.server = server;
p->o_arg.bitmask = nfs4_bitmask(server, label);
p->o_arg.open_bitmap = &nfs4_fattr_bitmap[0];
- p->o_arg.label = nfs4_label_copy(p->a_label, label);
switch (p->o_arg.claim) {
case NFS4_OPEN_CLAIM_NULL:
case NFS4_OPEN_CLAIM_DELEGATE_CUR:
@@ -1279,13 +1339,6 @@
case NFS4_OPEN_CLAIM_DELEG_PREV_FH:
p->o_arg.fh = NFS_FH(d_inode(dentry));
}
- if (c != NULL && c->sattr != NULL && c->sattr->ia_valid != 0) {
- p->o_arg.u.attrs = &p->attrs;
- memcpy(&p->attrs, c->sattr, sizeof(p->attrs));
-
- memcpy(p->o_arg.u.verifier.data, c->verf,
- sizeof(p->o_arg.u.verifier.data));
- }
p->c_arg.fh = &p->o_res.fh;
p->c_arg.stateid = &p->o_res.stateid;
p->c_arg.seqid = p->o_arg.seqid;
@@ -1349,12 +1402,20 @@
return false;
}
-static int can_open_cached(struct nfs4_state *state, fmode_t mode, int open_mode)
+static int can_open_cached(struct nfs4_state *state, fmode_t mode,
+ int open_mode, enum open_claim_type4 claim)
{
int ret = 0;
if (open_mode & (O_EXCL|O_TRUNC))
goto out;
+ switch (claim) {
+ case NFS4_OPEN_CLAIM_NULL:
+ case NFS4_OPEN_CLAIM_FH:
+ goto out;
+ default:
+ break;
+ }
switch (mode & (FMODE_READ|FMODE_WRITE)) {
case FMODE_READ:
ret |= test_bit(NFS_O_RDONLY_STATE, &state->flags) != 0
@@ -1379,8 +1440,6 @@
return 0;
if ((delegation->type & fmode) != fmode)
return 0;
- if (test_bit(NFS_DELEGATION_RETURNING, &delegation->flags))
- return 0;
switch (claim) {
case NFS4_OPEN_CLAIM_NULL:
case NFS4_OPEN_CLAIM_FH:
@@ -1547,6 +1606,10 @@
static void nfs_set_open_stateid_locked(struct nfs4_state *state,
const nfs4_stateid *stateid, nfs4_stateid *freeme)
+ __must_hold(&state->owner->so_lock)
+ __must_hold(&state->seqlock)
+ __must_hold(RCU)
+
{
DEFINE_WAIT(wait);
int status = 0;
@@ -1623,6 +1686,14 @@
write_sequnlock(&state->seqlock);
}
+static void nfs_state_clear_open_state_flags(struct nfs4_state *state)
+{
+ clear_bit(NFS_O_RDWR_STATE, &state->flags);
+ clear_bit(NFS_O_WRONLY_STATE, &state->flags);
+ clear_bit(NFS_O_RDONLY_STATE, &state->flags);
+ clear_bit(NFS_OPEN_STATE, &state->flags);
+}
+
static void nfs_state_set_delegation(struct nfs4_state *state,
const nfs4_stateid *deleg_stateid,
fmode_t fmode)
@@ -1737,7 +1808,6 @@
static struct nfs4_state *nfs4_try_open_cached(struct nfs4_opendata *opendata)
{
struct nfs4_state *state = opendata->state;
- struct nfs_inode *nfsi = NFS_I(state->inode);
struct nfs_delegation *delegation;
int open_mode = opendata->o_arg.open_flags;
fmode_t fmode = opendata->o_arg.fmode;
@@ -1747,14 +1817,14 @@
for (;;) {
spin_lock(&state->owner->so_lock);
- if (can_open_cached(state, fmode, open_mode)) {
+ if (can_open_cached(state, fmode, open_mode, claim)) {
update_open_stateflags(state, fmode);
spin_unlock(&state->owner->so_lock);
goto out_return_state;
}
spin_unlock(&state->owner->so_lock);
rcu_read_lock();
- delegation = rcu_dereference(nfsi->delegation);
+ delegation = nfs4_get_valid_delegation(state->inode);
if (!can_open_delegated(delegation, fmode, claim)) {
rcu_read_unlock();
break;
@@ -1777,7 +1847,7 @@
out:
return ERR_PTR(ret);
out_return_state:
- atomic_inc(&state->count);
+ refcount_inc(&state->count);
return state;
}
@@ -1847,9 +1917,10 @@
if (data->o_res.delegation_type != 0)
nfs4_opendata_check_deleg(data, state);
update:
- update_open_stateid(state, &data->o_res.stateid, NULL,
- data->o_arg.fmode);
- atomic_inc(&state->count);
+ if (!update_open_stateid(state, &data->o_res.stateid,
+ NULL, data->o_arg.fmode))
+ return ERR_PTR(-EAGAIN);
+ refcount_inc(&state->count);
return state;
}
@@ -1887,7 +1958,7 @@
return ERR_CAST(inode);
if (data->state != NULL && data->state->inode == inode) {
state = data->state;
- atomic_inc(&state->count);
+ refcount_inc(&state->count);
} else
state = nfs4_get_open_state(inode, data->owner);
iput(inode);
@@ -1913,8 +1984,11 @@
if (data->o_res.delegation_type != 0)
nfs4_opendata_check_deleg(data, state);
- update_open_stateid(state, &data->o_res.stateid, NULL,
- data->o_arg.fmode);
+ if (!update_open_stateid(state, &data->o_res.stateid,
+ NULL, data->o_arg.fmode)) {
+ nfs4_put_open_state(state);
+ state = ERR_PTR(-EAGAIN);
+ }
out:
nfs_release_seqid(data->o_arg.seqid);
return state;
@@ -1933,23 +2007,41 @@
return ret;
}
-static struct nfs_open_context *nfs4_state_find_open_context(struct nfs4_state *state)
+static struct nfs_open_context *
+nfs4_state_find_open_context_mode(struct nfs4_state *state, fmode_t mode)
{
struct nfs_inode *nfsi = NFS_I(state->inode);
struct nfs_open_context *ctx;
- spin_lock(&state->inode->i_lock);
- list_for_each_entry(ctx, &nfsi->open_files, list) {
+ rcu_read_lock();
+ list_for_each_entry_rcu(ctx, &nfsi->open_files, list) {
if (ctx->state != state)
continue;
- get_nfs_open_context(ctx);
- spin_unlock(&state->inode->i_lock);
+ if ((ctx->mode & mode) != mode)
+ continue;
+ if (!get_nfs_open_context(ctx))
+ continue;
+ rcu_read_unlock();
return ctx;
}
- spin_unlock(&state->inode->i_lock);
+ rcu_read_unlock();
return ERR_PTR(-ENOENT);
}
+static struct nfs_open_context *
+nfs4_state_find_open_context(struct nfs4_state *state)
+{
+ struct nfs_open_context *ctx;
+
+ ctx = nfs4_state_find_open_context_mode(state, FMODE_READ|FMODE_WRITE);
+ if (!IS_ERR(ctx))
+ return ctx;
+ ctx = nfs4_state_find_open_context_mode(state, FMODE_WRITE);
+ if (!IS_ERR(ctx))
+ return ctx;
+ return nfs4_state_find_open_context_mode(state, FMODE_READ);
+}
+
static struct nfs4_opendata *nfs4_open_recoverdata_alloc(struct nfs_open_context *ctx,
struct nfs4_state *state, enum open_claim_type4 claim)
{
@@ -1960,7 +2052,7 @@
if (opendata == NULL)
return ERR_PTR(-ENOMEM);
opendata->state = state;
- atomic_inc(&state->count);
+ refcount_inc(&state->count);
return opendata;
}
@@ -1996,13 +2088,7 @@
{
int ret;
- /* Don't trigger recovery in nfs_test_and_clear_all_open_stateid */
- clear_bit(NFS_O_RDWR_STATE, &state->flags);
- clear_bit(NFS_O_WRONLY_STATE, &state->flags);
- clear_bit(NFS_O_RDONLY_STATE, &state->flags);
/* memory barrier prior to reading state->n_* */
- clear_bit(NFS_DELEGATED_STATE, &state->flags);
- clear_bit(NFS_OPEN_STATE, &state->flags);
smp_rmb();
ret = nfs4_open_recover_helper(opendata, FMODE_READ|FMODE_WRITE);
if (ret != 0)
@@ -2078,6 +2164,8 @@
ctx = nfs4_state_find_open_context(state);
if (IS_ERR(ctx))
return -EAGAIN;
+ clear_bit(NFS_DELEGATED_STATE, &state->flags);
+ nfs_state_clear_open_state_flags(state);
ret = nfs4_do_open_reclaim(ctx, state);
put_nfs_open_context(ctx);
return ret;
@@ -2093,18 +2181,17 @@
case -ENOENT:
case -EAGAIN:
case -ESTALE:
+ case -ETIMEDOUT:
break;
case -NFS4ERR_BADSESSION:
case -NFS4ERR_BADSLOT:
case -NFS4ERR_BAD_HIGH_SLOT:
case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION:
case -NFS4ERR_DEADSESSION:
- set_bit(NFS_DELEGATED_STATE, &state->flags);
nfs4_schedule_session_recovery(server->nfs_client->cl_session, err);
return -EAGAIN;
case -NFS4ERR_STALE_CLIENTID:
case -NFS4ERR_STALE_STATEID:
- set_bit(NFS_DELEGATED_STATE, &state->flags);
/* Don't recall a delegation if it was lost */
nfs4_schedule_lease_recovery(server->nfs_client);
return -EAGAIN;
@@ -2125,7 +2212,6 @@
return -EAGAIN;
case -NFS4ERR_DELAY:
case -NFS4ERR_GRACE:
- set_bit(NFS_DELEGATED_STATE, &state->flags);
ssleep(1);
return -EAGAIN;
case -ENOMEM:
@@ -2141,8 +2227,7 @@
}
int nfs4_open_delegation_recall(struct nfs_open_context *ctx,
- struct nfs4_state *state, const nfs4_stateid *stateid,
- fmode_t type)
+ struct nfs4_state *state, const nfs4_stateid *stateid)
{
struct nfs_server *server = NFS_SERVER(state->inode);
struct nfs4_opendata *opendata;
@@ -2153,20 +2238,23 @@
if (IS_ERR(opendata))
return PTR_ERR(opendata);
nfs4_stateid_copy(&opendata->o_arg.u.delegation, stateid);
- nfs_state_clear_delegation(state);
- switch (type & (FMODE_READ|FMODE_WRITE)) {
- case FMODE_READ|FMODE_WRITE:
- case FMODE_WRITE:
+ if (!test_bit(NFS_O_RDWR_STATE, &state->flags)) {
err = nfs4_open_recover_helper(opendata, FMODE_READ|FMODE_WRITE);
if (err)
- break;
+ goto out;
+ }
+ if (!test_bit(NFS_O_WRONLY_STATE, &state->flags)) {
err = nfs4_open_recover_helper(opendata, FMODE_WRITE);
if (err)
- break;
- /* Fall through */
- case FMODE_READ:
- err = nfs4_open_recover_helper(opendata, FMODE_READ);
+ goto out;
}
+ if (!test_bit(NFS_O_RDONLY_STATE, &state->flags)) {
+ err = nfs4_open_recover_helper(opendata, FMODE_READ);
+ if (err)
+ goto out;
+ }
+ nfs_state_clear_delegation(state);
+out:
nfs4_opendata_put(opendata);
return nfs4_handle_delegation_recall_error(server, state, stateid, NULL, err);
}
@@ -2276,10 +2364,11 @@
if (data->state != NULL) {
struct nfs_delegation *delegation;
- if (can_open_cached(data->state, data->o_arg.fmode, data->o_arg.open_flags))
+ if (can_open_cached(data->state, data->o_arg.fmode,
+ data->o_arg.open_flags, claim))
goto out_no_action;
rcu_read_lock();
- delegation = rcu_dereference(NFS_I(data->state->inode)->delegation);
+ delegation = nfs4_get_valid_delegation(data->state->inode);
if (can_open_delegated(delegation, data->o_arg.fmode, claim))
goto unlock_no_action;
rcu_read_unlock();
@@ -2413,6 +2502,7 @@
if (!ctx) {
nfs4_init_sequence(&o_arg->seq_args, &o_res->seq_res, 1, 1);
data->is_recover = true;
+ task_setup_data.flags |= RPC_TASK_TIMEOUT;
} else {
nfs4_init_sequence(&o_arg->seq_args, &o_res->seq_res, 1, 0);
pnfs_lgopen_prepare(data, ctx);
@@ -2457,7 +2547,7 @@
* Note that in the non-execute case, we want to turn off permission
* checking if we just created a new file (POSIX open() semantics).
*/
-static int nfs4_opendata_access(struct rpc_cred *cred,
+static int nfs4_opendata_access(const struct cred *cred,
struct nfs4_opendata *opendata,
struct nfs4_state *state, fmode_t fmode,
int openflags)
@@ -2619,12 +2709,13 @@
{
/* NFSv4.0 doesn't allow for delegation recovery on open expire */
nfs40_clear_delegation_stateid(state);
+ nfs_state_clear_open_state_flags(state);
return nfs4_open_expired(sp, state);
}
static int nfs40_test_and_free_expired_stateid(struct nfs_server *server,
nfs4_stateid *stateid,
- struct rpc_cred *cred)
+ const struct cred *cred)
{
return -NFS4ERR_BAD_STATEID;
}
@@ -2632,7 +2723,7 @@
#if defined(CONFIG_NFS_V4_1)
static int nfs41_test_and_free_expired_stateid(struct nfs_server *server,
nfs4_stateid *stateid,
- struct rpc_cred *cred)
+ const struct cred *cred)
{
int status;
@@ -2661,13 +2752,13 @@
return -NFS4ERR_EXPIRED;
}
-static void nfs41_check_delegation_stateid(struct nfs4_state *state)
+static int nfs41_check_delegation_stateid(struct nfs4_state *state)
{
struct nfs_server *server = NFS_SERVER(state->inode);
nfs4_stateid stateid;
struct nfs_delegation *delegation;
- struct rpc_cred *cred;
- int status;
+ const struct cred *cred = NULL;
+ int status, ret = NFS_OK;
/* Get the delegation credential for use by test/free_stateid */
rcu_read_lock();
@@ -2675,30 +2766,42 @@
if (delegation == NULL) {
rcu_read_unlock();
nfs_state_clear_delegation(state);
- return;
+ return NFS_OK;
}
nfs4_stateid_copy(&stateid, &delegation->stateid);
- if (test_bit(NFS_DELEGATION_REVOKED, &delegation->flags)) {
- rcu_read_unlock();
- nfs_state_clear_delegation(state);
- return;
- }
if (!test_and_clear_bit(NFS_DELEGATION_TEST_EXPIRED,
&delegation->flags)) {
rcu_read_unlock();
- return;
+ return NFS_OK;
}
- cred = get_rpccred(delegation->cred);
+ if (delegation->cred)
+ cred = get_cred(delegation->cred);
rcu_read_unlock();
status = nfs41_test_and_free_expired_stateid(server, &stateid, cred);
trace_nfs4_test_delegation_stateid(state, NULL, status);
if (status == -NFS4ERR_EXPIRED || status == -NFS4ERR_BAD_STATEID)
nfs_finish_clear_delegation_stateid(state, &stateid);
+ else
+ ret = status;
- put_rpccred(cred);
+ put_cred(cred);
+ return ret;
+}
+
+static void nfs41_delegation_recover_stateid(struct nfs4_state *state)
+{
+ nfs4_stateid tmp;
+
+ if (test_bit(NFS_DELEGATED_STATE, &state->flags) &&
+ nfs4_copy_delegation_stateid(state->inode, state->state,
+ &tmp, NULL) &&
+ nfs4_stateid_match_other(&state->stateid, &tmp))
+ nfs_state_set_delegation(state, &tmp, state->state);
+ else
+ nfs_state_clear_delegation(state);
}
/**
@@ -2721,7 +2824,7 @@
spin_lock(&state->state_lock);
list_for_each_entry(lsp, &state->lock_states, ls_locks) {
if (test_bit(NFS_LOCK_INITIALIZED, &lsp->ls_flags)) {
- struct rpc_cred *cred = lsp->ls_state->owner->so_cred;
+ const struct cred *cred = lsp->ls_state->owner->so_cred;
refcount_inc(&lsp->ls_count);
spin_unlock(&state->state_lock);
@@ -2765,24 +2868,15 @@
{
struct nfs_server *server = NFS_SERVER(state->inode);
nfs4_stateid *stateid = &state->open_stateid;
- struct rpc_cred *cred = state->owner->so_cred;
+ const struct cred *cred = state->owner->so_cred;
int status;
- if (test_bit(NFS_OPEN_STATE, &state->flags) == 0) {
- if (test_bit(NFS_DELEGATED_STATE, &state->flags) == 0) {
- if (nfs4_have_delegation(state->inode, state->state))
- return NFS_OK;
- return -NFS4ERR_OPENMODE;
- }
+ if (test_bit(NFS_OPEN_STATE, &state->flags) == 0)
return -NFS4ERR_BAD_STATEID;
- }
status = nfs41_test_and_free_expired_stateid(server, stateid, cred);
trace_nfs4_test_open_stateid(state, NULL, status);
if (status == -NFS4ERR_EXPIRED || status == -NFS4ERR_BAD_STATEID) {
- clear_bit(NFS_O_RDONLY_STATE, &state->flags);
- clear_bit(NFS_O_WRONLY_STATE, &state->flags);
- clear_bit(NFS_O_RDWR_STATE, &state->flags);
- clear_bit(NFS_OPEN_STATE, &state->flags);
+ nfs_state_clear_open_state_flags(state);
stateid->type = NFS4_INVALID_STATEID_TYPE;
return status;
}
@@ -2795,7 +2889,11 @@
{
int status;
- nfs41_check_delegation_stateid(state);
+ status = nfs41_check_delegation_stateid(state);
+ if (status != NFS_OK)
+ return status;
+ nfs41_delegation_recover_stateid(state);
+
status = nfs41_check_expired_locks(state);
if (status != NFS_OK)
return status;
@@ -2848,14 +2946,13 @@
}
static int _nfs4_open_and_get_state(struct nfs4_opendata *opendata,
- fmode_t fmode,
- int flags,
- struct nfs_open_context *ctx)
+ int flags, struct nfs_open_context *ctx)
{
struct nfs4_state_owner *sp = opendata->owner;
struct nfs_server *server = sp->so_server;
struct dentry *dentry;
struct nfs4_state *state;
+ fmode_t acc_mode = _nfs4_ctx_to_accessmode(ctx);
unsigned int seq;
int ret;
@@ -2894,7 +2991,8 @@
/* Parse layoutget results before we check for access */
pnfs_parse_lgopen(state->inode, opendata->lgp, ctx);
- ret = nfs4_opendata_access(sp->so_cred, opendata, state, fmode, flags);
+ ret = nfs4_opendata_access(sp->so_cred, opendata, state,
+ acc_mode, flags);
if (ret != 0)
goto out;
@@ -2905,7 +3003,8 @@
}
out:
- nfs4_sequence_free_slot(&opendata->o_res.seq_res);
+ if (!opendata->cancelled)
+ nfs4_sequence_free_slot(&opendata->o_res.seq_res);
return ret;
}
@@ -2923,9 +3022,9 @@
struct nfs_server *server = NFS_SERVER(dir);
struct nfs4_opendata *opendata;
struct dentry *dentry = ctx->dentry;
- struct rpc_cred *cred = ctx->cred;
+ const struct cred *cred = ctx->cred;
struct nfs4_threshold **ctx_th = &ctx->mdsthreshold;
- fmode_t fmode = ctx->mode & (FMODE_READ|FMODE_WRITE|FMODE_EXEC);
+ fmode_t fmode = _nfs4_ctx_to_openmode(ctx);
enum open_claim_type4 claim = NFS4_OPEN_CLAIM_NULL;
struct iattr *sattr = c->sattr;
struct nfs4_label *label = c->label;
@@ -2971,7 +3070,7 @@
if (d_really_is_positive(dentry))
opendata->state = nfs4_get_open_state(d_inode(dentry), sp);
- status = _nfs4_open_and_get_state(opendata, fmode, flags, ctx);
+ status = _nfs4_open_and_get_state(opendata, flags, ctx);
if (status != 0)
goto err_free_label;
state = ctx->state;
@@ -3031,7 +3130,9 @@
int *opened)
{
struct nfs_server *server = NFS_SERVER(dir);
- struct nfs4_exception exception = { };
+ struct nfs4_exception exception = {
+ .interruptible = true,
+ };
struct nfs4_state *res;
struct nfs4_open_createattrs c = {
.label = label,
@@ -3093,7 +3194,7 @@
static int _nfs4_do_setattr(struct inode *inode,
struct nfs_setattrargs *arg,
struct nfs_setattrres *res,
- struct rpc_cred *cred,
+ const struct cred *cred,
struct nfs_open_context *ctx)
{
struct nfs_server *server = NFS_SERVER(inode);
@@ -3103,7 +3204,7 @@
.rpc_resp = res,
.rpc_cred = cred,
};
- struct rpc_cred *delegation_cred = NULL;
+ const struct cred *delegation_cred = NULL;
unsigned long timestamp = jiffies;
bool truncate;
int status;
@@ -3117,7 +3218,7 @@
if (nfs4_copy_delegation_stateid(inode, FMODE_WRITE, &arg->stateid, &delegation_cred)) {
/* Use that stateid */
- } else if (ctx != NULL) {
+ } else if (ctx != NULL && ctx->state) {
struct nfs_lock_context *l_ctx;
if (!nfs4_valid_open_stateid(ctx->state))
return -EBADF;
@@ -3138,14 +3239,14 @@
status = nfs4_call_sync(server->client, server, &msg, &arg->seq_args, &res->seq_res, 1);
- put_rpccred(delegation_cred);
+ put_cred(delegation_cred);
if (status == 0 && ctx != NULL)
renew_lease(server, timestamp);
trace_nfs4_setattr(inode, &arg->stateid, status);
return status;
}
-static int nfs4_do_setattr(struct inode *inode, struct rpc_cred *cred,
+static int nfs4_do_setattr(struct inode *inode, const struct cred *cred,
struct nfs_fattr *fattr, struct iattr *sattr,
struct nfs_open_context *ctx, struct nfs4_label *ilabel,
struct nfs4_label *olabel)
@@ -3209,6 +3310,75 @@
return pnfs_wait_on_layoutreturn(inode, task);
}
+/*
+ * Update the seqid of an open stateid
+ */
+static void nfs4_sync_open_stateid(nfs4_stateid *dst,
+ struct nfs4_state *state)
+{
+ __be32 seqid_open;
+ u32 dst_seqid;
+ int seq;
+
+ for (;;) {
+ if (!nfs4_valid_open_stateid(state))
+ break;
+ seq = read_seqbegin(&state->seqlock);
+ if (!nfs4_state_match_open_stateid_other(state, dst)) {
+ nfs4_stateid_copy(dst, &state->open_stateid);
+ if (read_seqretry(&state->seqlock, seq))
+ continue;
+ break;
+ }
+ seqid_open = state->open_stateid.seqid;
+ if (read_seqretry(&state->seqlock, seq))
+ continue;
+
+ dst_seqid = be32_to_cpu(dst->seqid);
+ if ((s32)(dst_seqid - be32_to_cpu(seqid_open)) < 0)
+ dst->seqid = seqid_open;
+ break;
+ }
+}
+
+/*
+ * Update the seqid of an open stateid after receiving
+ * NFS4ERR_OLD_STATEID
+ */
+static bool nfs4_refresh_open_old_stateid(nfs4_stateid *dst,
+ struct nfs4_state *state)
+{
+ __be32 seqid_open;
+ u32 dst_seqid;
+ bool ret;
+ int seq;
+
+ for (;;) {
+ ret = false;
+ if (!nfs4_valid_open_stateid(state))
+ break;
+ seq = read_seqbegin(&state->seqlock);
+ if (!nfs4_state_match_open_stateid_other(state, dst)) {
+ if (read_seqretry(&state->seqlock, seq))
+ continue;
+ break;
+ }
+ seqid_open = state->open_stateid.seqid;
+ if (read_seqretry(&state->seqlock, seq))
+ continue;
+
+ dst_seqid = be32_to_cpu(dst->seqid);
+ if ((s32)(dst_seqid - be32_to_cpu(seqid_open)) >= 0)
+ dst->seqid = cpu_to_be32(dst_seqid + 1);
+ else
+ dst->seqid = seqid_open;
+ ret = true;
+ break;
+ }
+
+ return ret;
+}
+
struct nfs4_closedata {
struct inode *inode;
struct nfs4_state *state;
@@ -3259,32 +3429,11 @@
trace_nfs4_close(state, &calldata->arg, &calldata->res, task->tk_status);
/* Handle Layoutreturn errors */
- if (calldata->arg.lr_args && task->tk_status != 0) {
- switch (calldata->res.lr_ret) {
- default:
- calldata->res.lr_ret = -NFS4ERR_NOMATCHING_LAYOUT;
- break;
- case 0:
- calldata->arg.lr_args = NULL;
- calldata->res.lr_res = NULL;
- break;
- case -NFS4ERR_OLD_STATEID:
- if (nfs4_layoutreturn_refresh_stateid(&calldata->arg.lr_args->stateid,
- &calldata->arg.lr_args->range,
- calldata->inode))
- goto lr_restart;
- /* Fallthrough */
- case -NFS4ERR_ADMIN_REVOKED:
- case -NFS4ERR_DELEG_REVOKED:
- case -NFS4ERR_EXPIRED:
- case -NFS4ERR_BAD_STATEID:
- case -NFS4ERR_UNKNOWN_LAYOUTTYPE:
- case -NFS4ERR_WRONG_CRED:
- calldata->arg.lr_args = NULL;
- calldata->res.lr_res = NULL;
- goto lr_restart;
- }
- }
+ if (pnfs_roc_done(task, calldata->inode,
+ &calldata->arg.lr_args,
+ &calldata->res.lr_res,
+ &calldata->res.lr_ret) == -EAGAIN)
+ goto out_restart;
/* hmm. we are done with the inode, and in the process of freeing
* the state_owner. we keep this around to process errors
@@ -3304,7 +3453,7 @@
break;
case -NFS4ERR_OLD_STATEID:
/* Did we race with OPEN? */
- if (nfs4_refresh_open_stateid(&calldata->arg.stateid,
+ if (nfs4_refresh_open_old_stateid(&calldata->arg.stateid,
state))
goto out_restart;
goto out_release;
@@ -3316,7 +3465,9 @@
task->tk_msg.rpc_cred);
/* Fallthrough */
case -NFS4ERR_BAD_STATEID:
- break;
+ if (calldata->arg.fmode == 0)
+ break;
+ /* Fallthrough */
default:
task->tk_status = nfs4_async_handle_exception(task,
server, task->tk_status, &exception);
@@ -3331,8 +3482,6 @@
nfs_refresh_inode(calldata->inode, &calldata->fattr);
dprintk("%s: done, ret = %d!\n", __func__, task->tk_status);
return;
-lr_restart:
- calldata->res.lr_ret = 0;
out_restart:
task->tk_status = 0;
rpc_restart_call_prepare(task);
@@ -3373,8 +3522,8 @@
} else if (is_rdwr)
calldata->arg.fmode |= FMODE_READ|FMODE_WRITE;
- if (!nfs4_valid_open_stateid(state) ||
- !nfs4_refresh_open_stateid(&calldata->arg.stateid, state))
+ nfs4_sync_open_stateid(&calldata->arg.stateid, state);
+ if (!nfs4_valid_open_stateid(state))
call_close = 0;
spin_unlock(&state->owner->so_lock);
@@ -3539,9 +3688,9 @@
if (ctx->state == NULL)
return;
if (is_sync)
- nfs4_close_sync(ctx->state, ctx->mode);
+ nfs4_close_sync(ctx->state, _nfs4_ctx_to_openmode(ctx));
else
- nfs4_close_state(ctx->state, ctx->mode);
+ nfs4_close_state(ctx->state, _nfs4_ctx_to_openmode(ctx));
}
#define FATTR4_WORD1_NFS40_MASK (2*FATTR4_WORD1_MOUNTED_ON_FILEID - 1UL)
@@ -3644,7 +3793,9 @@
int nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *fhandle)
{
- struct nfs4_exception exception = { };
+ struct nfs4_exception exception = {
+ .interruptible = true,
+ };
int err;
do {
err = nfs4_handle_exception(server,
@@ -3686,7 +3837,9 @@
static int nfs4_lookup_root(struct nfs_server *server, struct nfs_fh *fhandle,
struct nfs_fsinfo *info)
{
- struct nfs4_exception exception = { };
+ struct nfs4_exception exception = {
+ .interruptible = true,
+ };
int err;
do {
err = _nfs4_lookup_root(server, fhandle, info);
@@ -3761,7 +3914,7 @@
}
/*
- * -EACCESS could mean that the user doesn't have correct permissions
+ * -EACCES could mean that the user doesn't have correct permissions
* to access the mount. It could also mean that we tried to mount
* with a gss auth flavor, but rpc.gssd isn't running. Either way,
* existing mount programs don't handle -EACCES very well so it should
@@ -3913,7 +4066,9 @@
struct nfs_fattr *fattr, struct nfs4_label *label,
struct inode *inode)
{
- struct nfs4_exception exception = { };
+ struct nfs4_exception exception = {
+ .interruptible = true,
+ };
int err;
do {
err = _nfs4_proc_getattr(server, fhandle, fattr, label, inode);
@@ -3946,7 +4101,7 @@
struct iattr *sattr)
{
struct inode *inode = d_inode(dentry);
- struct rpc_cred *cred = NULL;
+ const struct cred *cred = NULL;
struct nfs_open_context *ctx = NULL;
struct nfs4_label *label = NULL;
int status;
@@ -4036,7 +4191,9 @@
const struct qstr *name, struct nfs_fh *fhandle,
struct nfs_fattr *fattr, struct nfs4_label *label)
{
- struct nfs4_exception exception = { };
+ struct nfs4_exception exception = {
+ .interruptible = true,
+ };
struct rpc_clnt *client = *clnt;
int err;
do {
@@ -4140,7 +4297,9 @@
static int nfs4_proc_lookupp(struct inode *inode, struct nfs_fh *fhandle,
struct nfs_fattr *fattr, struct nfs4_label *label)
{
- struct nfs4_exception exception = { };
+ struct nfs4_exception exception = {
+ .interruptible = true,
+ };
int err;
do {
err = _nfs4_proc_lookupp(inode, fhandle, fattr, label);
@@ -4175,7 +4334,6 @@
return -ENOMEM;
args.bitmask = server->cache_consistency_bitmask;
}
-
status = nfs4_call_sync(server->client, server, &msg, &args.seq_args, &res.seq_res, 0);
if (!status) {
nfs_access_set_mask(entry, res.access);
@@ -4188,7 +4346,9 @@
static int nfs4_proc_access(struct inode *inode, struct nfs_access_entry *entry)
{
- struct nfs4_exception exception = { };
+ struct nfs4_exception exception = {
+ .interruptible = true,
+ };
int err;
do {
err = _nfs4_proc_access(inode, entry);
@@ -4243,7 +4403,9 @@
static int nfs4_proc_readlink(struct inode *inode, struct page *page,
unsigned int pgbase, unsigned int pglen)
{
- struct nfs4_exception exception = { };
+ struct nfs4_exception exception = {
+ .interruptible = true,
+ };
int err;
do {
err = _nfs4_proc_readlink(inode, page, pgbase, pglen);
@@ -4319,7 +4481,9 @@
static int nfs4_proc_remove(struct inode *dir, struct dentry *dentry)
{
- struct nfs4_exception exception = { };
+ struct nfs4_exception exception = {
+ .interruptible = true,
+ };
struct inode *inode = d_inode(dentry);
int err;
@@ -4340,7 +4504,9 @@
static int nfs4_proc_rmdir(struct inode *dir, const struct qstr *name)
{
- struct nfs4_exception exception = { };
+ struct nfs4_exception exception = {
+ .interruptible = true,
+ };
int err;
do {
@@ -4499,7 +4665,9 @@
static int nfs4_proc_link(struct inode *inode, struct inode *dir, const struct qstr *name)
{
- struct nfs4_exception exception = { };
+ struct nfs4_exception exception = {
+ .interruptible = true,
+ };
int err;
do {
err = nfs4_handle_exception(NFS_SERVER(inode),
@@ -4606,7 +4774,9 @@
static int nfs4_proc_symlink(struct inode *dir, struct dentry *dentry,
struct page *page, unsigned int len, struct iattr *sattr)
{
- struct nfs4_exception exception = { };
+ struct nfs4_exception exception = {
+ .interruptible = true,
+ };
struct nfs4_label l, *label = NULL;
int err;
@@ -4645,7 +4815,9 @@
struct iattr *sattr)
{
struct nfs_server *server = NFS_SERVER(dir);
- struct nfs4_exception exception = { };
+ struct nfs4_exception exception = {
+ .interruptible = true,
+ };
struct nfs4_label l, *label = NULL;
int err;
@@ -4664,7 +4836,7 @@
return err;
}
-static int _nfs4_proc_readdir(struct dentry *dentry, struct rpc_cred *cred,
+static int _nfs4_proc_readdir(struct dentry *dentry, const struct cred *cred,
u64 cookie, struct page **pages, unsigned int count, bool plus)
{
struct inode *dir = d_inode(dentry);
@@ -4702,10 +4874,12 @@
return status;
}
-static int nfs4_proc_readdir(struct dentry *dentry, struct rpc_cred *cred,
+static int nfs4_proc_readdir(struct dentry *dentry, const struct cred *cred,
u64 cookie, struct page **pages, unsigned int count, bool plus)
{
- struct nfs4_exception exception = { };
+ struct nfs4_exception exception = {
+ .interruptible = true,
+ };
int err;
do {
err = _nfs4_proc_readdir(dentry, cred, cookie,
@@ -4756,7 +4930,9 @@
struct iattr *sattr, dev_t rdev)
{
struct nfs_server *server = NFS_SERVER(dir);
- struct nfs4_exception exception = { };
+ struct nfs4_exception exception = {
+ .interruptible = true,
+ };
struct nfs4_label l, *label = NULL;
int err;
@@ -4798,7 +4974,9 @@
static int nfs4_proc_statfs(struct nfs_server *server, struct nfs_fh *fhandle, struct nfs_fsstat *fsstat)
{
- struct nfs4_exception exception = { };
+ struct nfs4_exception exception = {
+ .interruptible = true,
+ };
int err;
do {
err = nfs4_handle_exception(server,
@@ -4829,7 +5007,9 @@
static int nfs4_do_fsinfo(struct nfs_server *server, struct nfs_fh *fhandle, struct nfs_fsinfo *fsinfo)
{
- struct nfs4_exception exception = { };
+ struct nfs4_exception exception = {
+ .interruptible = true,
+ };
unsigned long now = jiffies;
int err;
@@ -4891,7 +5071,9 @@
static int nfs4_proc_pathconf(struct nfs_server *server, struct nfs_fh *fhandle,
struct nfs_pathconf *pathconf)
{
- struct nfs4_exception exception = { };
+ struct nfs4_exception exception = {
+ .interruptible = true,
+ };
int err;
do {
@@ -5230,7 +5412,7 @@
.rpc_release = nfs4_renew_release,
};
-static int nfs4_proc_async_renew(struct nfs_client *clp, struct rpc_cred *cred, unsigned renew_flags)
+static int nfs4_proc_async_renew(struct nfs_client *clp, const struct cred *cred, unsigned renew_flags)
{
struct rpc_message msg = {
.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_RENEW],
@@ -5254,7 +5436,7 @@
&nfs4_renew_ops, data);
}
-static int nfs4_proc_renew(struct nfs_client *clp, struct rpc_cred *cred)
+static int nfs4_proc_renew(struct nfs_client *clp, const struct cred *cred)
{
struct rpc_message msg = {
.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_RENEW],
@@ -5460,7 +5642,9 @@
static ssize_t nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t buflen)
{
- struct nfs4_exception exception = { };
+ struct nfs4_exception exception = {
+ .interruptible = true,
+ };
ssize_t ret;
do {
ret = __nfs4_get_acl_uncached(inode, buf, buflen);
@@ -5594,7 +5778,9 @@
static int nfs4_get_security_label(struct inode *inode, void *buf,
size_t buflen)
{
- struct nfs4_exception exception = { };
+ struct nfs4_exception exception = {
+ .interruptible = true,
+ };
int err;
if (!nfs_server_capable(inode, NFS_CAP_SECURITY_LABEL))
@@ -5669,7 +5855,6 @@
{
struct nfs4_label ilabel, *olabel = NULL;
struct nfs_fattr fattr;
- struct rpc_cred *cred;
int status;
if (!nfs_server_capable(inode, NFS_CAP_SECURITY_LABEL))
@@ -5682,10 +5867,6 @@
ilabel.label = (char *)buf;
ilabel.len = buflen;
- cred = rpc_lookup_cred();
- if (IS_ERR(cred))
- return PTR_ERR(cred);
-
olabel = nfs4_label_alloc(NFS_SERVER(inode), GFP_KERNEL);
if (IS_ERR(olabel)) {
status = -PTR_ERR(olabel);
@@ -5698,7 +5879,6 @@
nfs4_label_free(olabel);
out:
- put_rpccred(cred);
return status;
}
#endif /* CONFIG_NFS_V4_SECURITY_LABEL */
@@ -5867,13 +6047,13 @@
* @clp: state data structure
* @program: RPC program for NFSv4 callback service
* @port: IP port number for NFS4 callback service
- * @cred: RPC credential to use for this call
+ * @cred: credential to use for this call
* @res: where to place the result
*
* Returns zero, a negative errno, or a negative NFS4ERR status code.
*/
int nfs4_proc_setclientid(struct nfs_client *clp, u32 program,
- unsigned short port, struct rpc_cred *cred,
+ unsigned short port, const struct cred *cred,
struct nfs4_setclientid_res *res)
{
nfs4_verifier sc_verifier;
@@ -5888,13 +6068,12 @@
.rpc_resp = res,
.rpc_cred = cred,
};
- struct rpc_task *task;
struct rpc_task_setup task_setup_data = {
.rpc_client = clp->cl_rpcclient,
.rpc_message = &msg,
.callback_ops = &nfs4_setclientid_ops,
.callback_data = &setclientid,
- .flags = RPC_TASK_TIMEOUT,
+ .flags = RPC_TASK_TIMEOUT | RPC_TASK_NO_ROUND_ROBIN,
};
int status;
@@ -5921,17 +6100,13 @@
dprintk("NFS call setclientid auth=%s, '%s'\n",
clp->cl_rpcclient->cl_auth->au_ops->au_name,
clp->cl_owner_id);
- task = rpc_run_task(&task_setup_data);
- if (IS_ERR(task)) {
- status = PTR_ERR(task);
- goto out;
- }
- status = task->tk_status;
+
+ status = nfs4_call_sync_custom(&task_setup_data);
if (setclientid.sc_cred) {
+ kfree(clp->cl_acceptor);
clp->cl_acceptor = rpcauth_stringify_acceptor(setclientid.sc_cred);
put_rpccred(setclientid.sc_cred);
}
- rpc_put_task(task);
out:
trace_nfs4_setclientid(clp, status);
dprintk("NFS reply setclientid: %d\n", status);
@@ -5941,14 +6116,14 @@
/**
* nfs4_proc_setclientid_confirm - Confirm client ID
* @clp: state data structure
- * @res: result of a previous SETCLIENTID
- * @cred: RPC credential to use for this call
+ * @arg: result of a previous SETCLIENTID
+ * @cred: credential to use for this call
*
* Returns zero, a negative errno, or a negative NFS4ERR status code.
*/
int nfs4_proc_setclientid_confirm(struct nfs_client *clp,
struct nfs4_setclientid_res *arg,
- struct rpc_cred *cred)
+ const struct cred *cred)
{
struct rpc_message msg = {
.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_SETCLIENTID_CONFIRM],
@@ -5960,7 +6135,8 @@
dprintk("NFS call setclientid_confirm auth=%s, (client ID %llx)\n",
clp->cl_rpcclient->cl_auth->au_ops->au_name,
clp->cl_clientid);
- status = rpc_call_sync(clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT);
+ status = rpc_call_sync(clp->cl_rpcclient, &msg,
+ RPC_TASK_TIMEOUT | RPC_TASK_NO_ROUND_ROBIN);
trace_nfs4_setclientid_confirm(clp, status);
dprintk("NFS reply setclientid_confirm: %d\n", status);
return status;
@@ -5998,32 +6174,11 @@
trace_nfs4_delegreturn_exit(&data->args, &data->res, task->tk_status);
/* Handle Layoutreturn errors */
- if (data->args.lr_args && task->tk_status != 0) {
- switch(data->res.lr_ret) {
- default:
- data->res.lr_ret = -NFS4ERR_NOMATCHING_LAYOUT;
- break;
- case 0:
- data->args.lr_args = NULL;
- data->res.lr_res = NULL;
- break;
- case -NFS4ERR_OLD_STATEID:
- if (nfs4_layoutreturn_refresh_stateid(&data->args.lr_args->stateid,
- &data->args.lr_args->range,
- data->inode))
- goto lr_restart;
- /* Fallthrough */
- case -NFS4ERR_ADMIN_REVOKED:
- case -NFS4ERR_DELEG_REVOKED:
- case -NFS4ERR_EXPIRED:
- case -NFS4ERR_BAD_STATEID:
- case -NFS4ERR_UNKNOWN_LAYOUTTYPE:
- case -NFS4ERR_WRONG_CRED:
- data->args.lr_args = NULL;
- data->res.lr_res = NULL;
- goto lr_restart;
- }
- }
+ if (pnfs_roc_done(task, data->inode,
+ &data->args.lr_args,
+ &data->res.lr_res,
+ &data->res.lr_ret) == -EAGAIN)
+ goto out_restart;
switch (task->tk_status) {
case 0:
@@ -6061,8 +6216,6 @@
}
data->rpc_status = task->tk_status;
return;
-lr_restart:
- data->res.lr_ret = 0;
out_restart:
task->tk_status = 0;
rpc_restart_call_prepare(task);
@@ -6111,7 +6264,7 @@
.rpc_release = nfs4_delegreturn_release,
};
-static int _nfs4_proc_delegreturn(struct inode *inode, struct rpc_cred *cred, const nfs4_stateid *stateid, int issync)
+static int _nfs4_proc_delegreturn(struct inode *inode, const struct cred *cred, const nfs4_stateid *stateid, int issync)
{
struct nfs4_delegreturndata *data;
struct nfs_server *server = NFS_SERVER(inode);
@@ -6178,7 +6331,7 @@
return status;
}
-int nfs4_proc_delegreturn(struct inode *inode, struct rpc_cred *cred, const nfs4_stateid *stateid, int issync)
+int nfs4_proc_delegreturn(struct inode *inode, const struct cred *cred, const nfs4_stateid *stateid, int issync)
{
struct nfs_server *server = NFS_SERVER(inode);
struct nfs4_exception exception = { };
@@ -6241,7 +6394,9 @@
static int nfs4_proc_getlk(struct nfs4_state *state, int cmd, struct file_lock *request)
{
- struct nfs4_exception exception = { };
+ struct nfs4_exception exception = {
+ .interruptible = true,
+ };
int err;
do {
@@ -6253,6 +6408,42 @@
return err;
}
+/*
+ * Update the seqid of a lock stateid after receiving
+ * NFS4ERR_OLD_STATEID
+ */
+static bool nfs4_refresh_lock_old_stateid(nfs4_stateid *dst,
+ struct nfs4_lock_state *lsp)
+{
+ struct nfs4_state *state = lsp->ls_state;
+ bool ret = false;
+
+ spin_lock(&state->state_lock);
+ if (!nfs4_stateid_match_other(dst, &lsp->ls_stateid))
+ goto out;
+ if (!nfs4_stateid_is_newer(&lsp->ls_stateid, dst))
+ nfs4_stateid_seqid_inc(dst);
+ else
+ dst->seqid = lsp->ls_stateid.seqid;
+ ret = true;
+out:
+ spin_unlock(&state->state_lock);
+ return ret;
+}
+
+static bool nfs4_sync_lock_stateid(nfs4_stateid *dst,
+ struct nfs4_lock_state *lsp)
+{
+ struct nfs4_state *state = lsp->ls_state;
+ bool ret;
+
+ spin_lock(&state->state_lock);
+ ret = !nfs4_stateid_match_other(dst, &lsp->ls_stateid);
+ nfs4_stateid_copy(dst, &lsp->ls_stateid);
+ spin_unlock(&state->state_lock);
+ return ret;
+}
+
struct nfs4_unlockdata {
struct nfs_locku_args arg;
struct nfs_locku_res res;
@@ -6270,7 +6461,8 @@
struct nfs_seqid *seqid)
{
struct nfs4_unlockdata *p;
- struct inode *inode = lsp->ls_state->inode;
+ struct nfs4_state *state = lsp->ls_state;
+ struct inode *inode = state->inode;
p = kzalloc(sizeof(*p), GFP_NOFS);
if (p == NULL)
@@ -6280,12 +6472,15 @@
p->arg.seqid = seqid;
p->res.seqid = seqid;
p->lsp = lsp;
- refcount_inc(&lsp->ls_count);
/* Ensure we don't close file until we're done freeing locks! */
p->ctx = get_nfs_open_context(ctx);
p->l_ctx = nfs_get_lock_context(ctx);
- memcpy(&p->fl, fl, sizeof(p->fl));
+ locks_init_lock(&p->fl);
+ locks_copy_lock(&p->fl, fl);
p->server = NFS_SERVER(inode);
+ spin_lock(&state->state_lock);
+ nfs4_stateid_copy(&p->arg.stateid, &lsp->ls_stateid);
+ spin_unlock(&state->state_lock);
return p;
}
@@ -6324,10 +6519,14 @@
task->tk_msg.rpc_cred);
/* Fall through */
case -NFS4ERR_BAD_STATEID:
- case -NFS4ERR_OLD_STATEID:
case -NFS4ERR_STALE_STATEID:
- if (!nfs4_stateid_match(&calldata->arg.stateid,
- &calldata->lsp->ls_stateid))
+ if (nfs4_sync_lock_stateid(&calldata->arg.stateid,
+ calldata->lsp))
+ rpc_restart_call_prepare(task);
+ break;
+ case -NFS4ERR_OLD_STATEID:
+ if (nfs4_refresh_lock_old_stateid(&calldata->arg.stateid,
+ calldata->lsp))
rpc_restart_call_prepare(task);
break;
default:
@@ -6350,7 +6549,6 @@
if (nfs_wait_on_sequence(calldata->arg.seqid, task) != 0)
goto out_wait;
- nfs4_stateid_copy(&calldata->arg.stateid, &calldata->lsp->ls_stateid);
if (test_bit(NFS_LOCK_INITIALIZED, &calldata->lsp->ls_flags) == 0) {
/* Note: exit _without_ running nfs4_locku_done */
goto out_no_action;
@@ -6504,9 +6702,9 @@
p->res.lock_seqid = p->arg.lock_seqid;
p->lsp = lsp;
p->server = server;
- refcount_inc(&lsp->ls_count);
p->ctx = get_nfs_open_context(ctx);
- memcpy(&p->fl, fl, sizeof(p->fl));
+ locks_init_lock(&p->fl);
+ locks_copy_lock(&p->fl, fl);
return p;
out_free_seqid:
nfs_free_seqid(p->arg.open_seqid);
@@ -6805,6 +7003,7 @@
struct nfs4_exception exception = {
.state = state,
.inode = state->inode,
+ .interruptible = true,
};
int err;
@@ -6845,7 +7044,6 @@
struct task_struct *task;
struct inode *inode;
struct nfs_lowner *owner;
- bool notified;
};
static int
@@ -6867,13 +7065,13 @@
/* Make sure it's for the right inode */
if (nfs_compare_fh(NFS_FH(waiter->inode), &cbnl->cbnl_fh))
return 0;
-
- waiter->notified = true;
}
/* override "private" so we can use default_wake_function */
wait->private = waiter->task;
- ret = autoremove_wake_function(wait, mode, flags, key);
+ ret = woken_wake_function(wait, mode, flags, key);
+ if (ret)
+ list_del_init(&wait->entry);
wait->private = waiter;
return ret;
}
@@ -6882,7 +7080,6 @@
nfs4_retry_setlk(struct nfs4_state *state, int cmd, struct file_lock *request)
{
int status = -ERESTARTSYS;
- unsigned long flags;
struct nfs4_lock_state *lsp = request->fl_u.nfs4_fl.owner;
struct nfs_server *server = NFS_SERVER(state->inode);
struct nfs_client *clp = server->nfs_client;
@@ -6892,8 +7089,7 @@
.s_dev = server->s_dev };
struct nfs4_lock_waiter waiter = { .task = current,
.inode = state->inode,
- .owner = &owner,
- .notified = false };
+ .owner = &owner};
wait_queue_entry_t wait;
/* Don't bother with waitqueue if we don't expect a callback */
@@ -6903,27 +7099,22 @@
init_wait(&wait);
wait.private = &waiter;
wait.func = nfs4_wake_lock_waiter;
- add_wait_queue(q, &wait);
while(!signalled()) {
- waiter.notified = false;
+ add_wait_queue(q, &wait);
status = nfs4_proc_setlk(state, cmd, request);
- if ((status != -EAGAIN) || IS_SETLK(cmd))
+ if ((status != -EAGAIN) || IS_SETLK(cmd)) {
+ finish_wait(q, &wait);
break;
+ }
status = -ERESTARTSYS;
- spin_lock_irqsave(&q->lock, flags);
- if (waiter.notified) {
- spin_unlock_irqrestore(&q->lock, flags);
- continue;
- }
- set_current_state(TASK_INTERRUPTIBLE);
- spin_unlock_irqrestore(&q->lock, flags);
-
- freezable_schedule_timeout(NFS4_LOCK_MAXTIMEOUT);
+ freezer_do_not_count();
+ wait_woken(&wait, TASK_INTERRUPTIBLE, NFS4_LOCK_MAXTIMEOUT);
+ freezer_count();
+ finish_wait(q, &wait);
}
- finish_wait(q, &wait);
return status;
}
#else /* !CONFIG_NFS_V4_1 */
@@ -7218,7 +7409,9 @@
struct nfs4_fs_locations *fs_locations,
struct page *page)
{
- struct nfs4_exception exception = { };
+ struct nfs4_exception exception = {
+ .interruptible = true,
+ };
int err;
do {
err = _nfs4_proc_fs_locations(client, dir, name,
@@ -7239,7 +7432,7 @@
*/
static int _nfs40_proc_get_locations(struct inode *inode,
struct nfs4_fs_locations *locations,
- struct page *page, struct rpc_cred *cred)
+ struct page *page, const struct cred *cred)
{
struct nfs_server *server = NFS_SERVER(inode);
struct rpc_clnt *clnt = server->client;
@@ -7296,7 +7489,7 @@
*/
static int _nfs41_proc_get_locations(struct inode *inode,
struct nfs4_fs_locations *locations,
- struct page *page, struct rpc_cred *cred)
+ struct page *page, const struct cred *cred)
{
struct nfs_server *server = NFS_SERVER(inode);
struct rpc_clnt *clnt = server->client;
@@ -7355,13 +7548,15 @@
*/
int nfs4_proc_get_locations(struct inode *inode,
struct nfs4_fs_locations *locations,
- struct page *page, struct rpc_cred *cred)
+ struct page *page, const struct cred *cred)
{
struct nfs_server *server = NFS_SERVER(inode);
struct nfs_client *clp = server->nfs_client;
const struct nfs4_mig_recovery_ops *ops =
clp->cl_mvops->mig_recovery_ops;
- struct nfs4_exception exception = { };
+ struct nfs4_exception exception = {
+ .interruptible = true,
+ };
int status;
dprintk("%s: FSID %llx:%llx on \"%s\"\n", __func__,
@@ -7386,7 +7581,7 @@
* is appended to this compound to identify the client ID which is
* performing recovery.
*/
-static int _nfs40_proc_fsid_present(struct inode *inode, struct rpc_cred *cred)
+static int _nfs40_proc_fsid_present(struct inode *inode, const struct cred *cred)
{
struct nfs_server *server = NFS_SERVER(inode);
struct nfs_client *clp = NFS_SERVER(inode)->nfs_client;
@@ -7432,7 +7627,7 @@
* this operation is identified in the SEQUENCE operation in this
* compound.
*/
-static int _nfs41_proc_fsid_present(struct inode *inode, struct rpc_cred *cred)
+static int _nfs41_proc_fsid_present(struct inode *inode, const struct cred *cred)
{
struct nfs_server *server = NFS_SERVER(inode);
struct rpc_clnt *clnt = server->client;
@@ -7479,13 +7674,15 @@
* NFS4ERR code if some error occurred on the server, or a
* negative errno if a local failure occurred.
*/
-int nfs4_proc_fsid_present(struct inode *inode, struct rpc_cred *cred)
+int nfs4_proc_fsid_present(struct inode *inode, const struct cred *cred)
{
struct nfs_server *server = NFS_SERVER(inode);
struct nfs_client *clp = server->nfs_client;
const struct nfs4_mig_recovery_ops *ops =
clp->cl_mvops->mig_recovery_ops;
- struct nfs4_exception exception = { };
+ struct nfs4_exception exception = {
+ .interruptible = true,
+ };
int status;
dprintk("%s: FSID %llx:%llx on \"%s\"\n", __func__,
@@ -7503,7 +7700,7 @@
return status;
}
-/**
+/*
* If 'use_integrity' is true and the state managment nfs_client
* cl_rpcclient is using krb5i/p, use the integrity protected cl_rpcclient
* and the machine credential as per RFC3530bis and RFC5661 Security
@@ -7513,6 +7710,8 @@
static int _nfs4_proc_secinfo(struct inode *dir, const struct qstr *name, struct nfs4_secinfo_flavors *flavors, bool use_integrity)
{
int status;
+ struct rpc_clnt *clnt = NFS_SERVER(dir)->client;
+ struct nfs_client *clp = NFS_SERVER(dir)->nfs_client;
struct nfs4_secinfo_arg args = {
.dir_fh = NFS_FH(dir),
.name = name,
@@ -7525,34 +7724,46 @@
.rpc_argp = &args,
.rpc_resp = &res,
};
- struct rpc_clnt *clnt = NFS_SERVER(dir)->client;
- struct rpc_cred *cred = NULL;
+ struct nfs4_call_sync_data data = {
+ .seq_server = NFS_SERVER(dir),
+ .seq_args = &args.seq_args,
+ .seq_res = &res.seq_res,
+ };
+ struct rpc_task_setup task_setup = {
+ .rpc_client = clnt,
+ .rpc_message = &msg,
+ .callback_ops = clp->cl_mvops->call_sync_ops,
+ .callback_data = &data,
+ .flags = RPC_TASK_NO_ROUND_ROBIN,
+ };
+ const struct cred *cred = NULL;
if (use_integrity) {
- clnt = NFS_SERVER(dir)->nfs_client->cl_rpcclient;
- cred = nfs4_get_clid_cred(NFS_SERVER(dir)->nfs_client);
+ clnt = clp->cl_rpcclient;
+ task_setup.rpc_client = clnt;
+
+ cred = nfs4_get_clid_cred(clp);
msg.rpc_cred = cred;
}
dprintk("NFS call secinfo %s\n", name->name);
- nfs4_state_protect(NFS_SERVER(dir)->nfs_client,
- NFS_SP4_MACH_CRED_SECINFO, &clnt, &msg);
+ nfs4_state_protect(clp, NFS_SP4_MACH_CRED_SECINFO, &clnt, &msg);
+ nfs4_init_sequence(&args.seq_args, &res.seq_res, 0, 0);
+ status = nfs4_call_sync_custom(&task_setup);
- status = nfs4_call_sync(clnt, NFS_SERVER(dir), &msg, &args.seq_args,
- &res.seq_res, 0);
dprintk("NFS reply secinfo: %d\n", status);
- if (cred)
- put_rpccred(cred);
-
+ put_cred(cred);
return status;
}
int nfs4_proc_secinfo(struct inode *dir, const struct qstr *name,
struct nfs4_secinfo_flavors *flavors)
{
- struct nfs4_exception exception = { };
+ struct nfs4_exception exception = {
+ .interruptible = true,
+ };
int err;
do {
err = -NFS4ERR_WRONGSEC;
@@ -7625,7 +7836,7 @@
int nfs4_proc_bind_one_conn_to_session(struct rpc_clnt *clnt,
struct rpc_xprt *xprt,
struct nfs_client *clp,
- struct rpc_cred *cred)
+ const struct cred *cred)
{
int status;
struct nfs41_bind_conn_to_session_args args = {
@@ -7687,7 +7898,7 @@
struct rpc_bind_conn_calldata {
struct nfs_client *clp;
- struct rpc_cred *cred;
+ const struct cred *cred;
};
static int
@@ -7700,7 +7911,7 @@
return nfs4_proc_bind_one_conn_to_session(clnt, xprt, p->clp, p->cred);
}
-int nfs4_proc_bind_conn_to_session(struct nfs_client *clp, struct rpc_cred *cred)
+int nfs4_proc_bind_conn_to_session(struct nfs_client *clp, const struct cred *cred)
{
struct rpc_bind_conn_calldata data = {
.clp = clp,
@@ -7866,7 +8077,7 @@
* Wrapper for EXCHANGE_ID operation.
*/
static struct rpc_task *
-nfs4_run_exchange_id(struct nfs_client *clp, struct rpc_cred *cred,
+nfs4_run_exchange_id(struct nfs_client *clp, const struct cred *cred,
u32 sp4_how, struct rpc_xprt *xprt)
{
struct rpc_message msg = {
@@ -7877,7 +8088,7 @@
.rpc_client = clp->cl_rpcclient,
.callback_ops = &nfs4_exchange_id_call_ops,
.rpc_message = &msg,
- .flags = RPC_TASK_TIMEOUT,
+ .flags = RPC_TASK_TIMEOUT | RPC_TASK_NO_ROUND_ROBIN,
};
struct nfs41_exchange_id_data *calldata;
int status;
@@ -7962,7 +8173,7 @@
*
* Wrapper for EXCHANGE_ID operation.
*/
-static int _nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred,
+static int _nfs4_proc_exchange_id(struct nfs_client *clp, const struct cred *cred,
u32 sp4_how)
{
struct rpc_task *task;
@@ -8029,7 +8240,7 @@
*
* Will attempt to negotiate SP4_MACH_CRED if krb5i / krb5p auth is used.
*/
-int nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred)
+int nfs4_proc_exchange_id(struct nfs_client *clp, const struct cred *cred)
{
rpc_authflavor_t authflavor = clp->cl_rpcclient->cl_auth->au_flavor;
int status;
@@ -8061,7 +8272,7 @@
* @xprt: the rpc_xprt to test
* @data: call data for _nfs4_proc_exchange_id.
*/
-int nfs4_test_session_trunk(struct rpc_clnt *clnt, struct rpc_xprt *xprt,
+void nfs4_test_session_trunk(struct rpc_clnt *clnt, struct rpc_xprt *xprt,
void *data)
{
struct nfs4_add_xprt_data *adata = (struct nfs4_add_xprt_data *)data;
@@ -8078,20 +8289,22 @@
/* Test connection for session trunking. Async exchange_id call */
task = nfs4_run_exchange_id(adata->clp, adata->cred, sp4_how, xprt);
if (IS_ERR(task))
- return PTR_ERR(task);
+ return;
status = task->tk_status;
if (status == 0)
status = nfs4_detect_session_trunking(adata->clp,
task->tk_msg.rpc_resp, xprt);
+ if (status == 0)
+ rpc_clnt_xprt_switch_add_xprt(clnt, xprt);
+
rpc_put_task(task);
- return status;
}
EXPORT_SYMBOL_GPL(nfs4_test_session_trunk);
static int _nfs4_proc_destroy_clientid(struct nfs_client *clp,
- struct rpc_cred *cred)
+ const struct cred *cred)
{
struct rpc_message msg = {
.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_DESTROY_CLIENTID],
@@ -8100,7 +8313,8 @@
};
int status;
- status = rpc_call_sync(clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT);
+ status = rpc_call_sync(clp->cl_rpcclient, &msg,
+ RPC_TASK_TIMEOUT | RPC_TASK_NO_ROUND_ROBIN);
trace_nfs4_destroy_clientid(clp, status);
if (status)
dprintk("NFS: Got error %d from the server %s on "
@@ -8109,7 +8323,7 @@
}
static int nfs4_proc_destroy_clientid(struct nfs_client *clp,
- struct rpc_cred *cred)
+ const struct cred *cred)
{
unsigned int loop;
int ret;
@@ -8130,7 +8344,7 @@
int nfs4_destroy_clientid(struct nfs_client *clp)
{
- struct rpc_cred *cred;
+ const struct cred *cred;
int ret = 0;
if (clp->cl_mvops->minor_version < 1)
@@ -8141,8 +8355,7 @@
goto out;
cred = nfs4_get_clid_cred(clp);
ret = nfs4_proc_destroy_clientid(clp, cred);
- if (cred)
- put_rpccred(cred);
+ put_cred(cred);
switch (ret) {
case 0:
case -NFS4ERR_STALE_CLIENTID:
@@ -8152,6 +8365,8 @@
return ret;
}
+#endif /* CONFIG_NFS_V4_1 */
+
struct nfs4_get_lease_time_data {
struct nfs4_get_lease_time_args *args;
struct nfs4_get_lease_time_res *res;
@@ -8184,7 +8399,7 @@
(struct nfs4_get_lease_time_data *)calldata;
dprintk("--> %s\n", __func__);
- if (!nfs41_sequence_done(task, &data->res->lr_seq_res))
+ if (!nfs4_sequence_done(task, &data->res->lr_seq_res))
return;
switch (task->tk_status) {
case -NFS4ERR_DELAY:
@@ -8207,7 +8422,6 @@
int nfs4_proc_get_lease_time(struct nfs_client *clp, struct nfs_fsinfo *fsinfo)
{
- struct rpc_task *task;
struct nfs4_get_lease_time_args args;
struct nfs4_get_lease_time_res res = {
.lr_fsinfo = fsinfo,
@@ -8229,19 +8443,13 @@
.callback_data = &data,
.flags = RPC_TASK_TIMEOUT,
};
- int status;
nfs4_init_sequence(&args.la_seq_args, &res.lr_seq_res, 0, 1);
- task = rpc_run_task(&task_setup);
-
- if (IS_ERR(task))
- return PTR_ERR(task);
-
- status = task->tk_status;
- rpc_put_task(task);
- return status;
+ return nfs4_call_sync_custom(&task_setup);
}
+#ifdef CONFIG_NFS_V4_1
+
/*
* Initialize the values to be used by the client in CREATE_SESSION
* If nfs4_init_session set the fore channel request and response sizes,
@@ -8256,6 +8464,7 @@
{
unsigned int max_rqst_sz, max_resp_sz;
unsigned int max_bc_payload = rpc_max_bc_payload(clnt);
+ unsigned int max_bc_slots = rpc_num_bc_slots(clnt);
max_rqst_sz = NFS_MAX_FILE_IO_SIZE + nfs41_maxwrite_overhead;
max_resp_sz = NFS_MAX_FILE_IO_SIZE + nfs41_maxread_overhead;
@@ -8278,6 +8487,8 @@
args->bc_attrs.max_resp_sz_cached = 0;
args->bc_attrs.max_ops = NFS4_MAX_BACK_CHANNEL_OPS;
args->bc_attrs.max_reqs = max_t(unsigned short, max_session_cb_slots, 1);
+ if (args->bc_attrs.max_reqs > max_bc_slots)
+ args->bc_attrs.max_reqs = max_bc_slots;
dprintk("%s: Back Channel : max_rqst_sz=%u max_resp_sz=%u "
"max_resp_sz_cached=%u max_ops=%u max_reqs=%u\n",
@@ -8358,7 +8569,7 @@
}
static int _nfs4_proc_create_session(struct nfs_client *clp,
- struct rpc_cred *cred)
+ const struct cred *cred)
{
struct nfs4_session *session = clp->cl_session;
struct nfs41_create_session_args args = {
@@ -8380,7 +8591,8 @@
nfs4_init_channel_attrs(&args, clp->cl_rpcclient);
args.flags = (SESSION4_PERSIST | SESSION4_BACK_CHAN);
- status = rpc_call_sync(session->clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT);
+ status = rpc_call_sync(session->clp->cl_rpcclient, &msg,
+ RPC_TASK_TIMEOUT | RPC_TASK_NO_ROUND_ROBIN);
trace_nfs4_create_session(clp, status);
switch (status) {
@@ -8410,7 +8622,7 @@
* It is the responsibility of the caller to verify the session is
* expired before calling this routine.
*/
-int nfs4_proc_create_session(struct nfs_client *clp, struct rpc_cred *cred)
+int nfs4_proc_create_session(struct nfs_client *clp, const struct cred *cred)
{
int status;
unsigned *ptr;
@@ -8441,7 +8653,7 @@
* The caller must serialize access to this routine.
*/
int nfs4_proc_destroy_session(struct nfs4_session *session,
- struct rpc_cred *cred)
+ const struct cred *cred)
{
struct rpc_message msg = {
.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_DESTROY_SESSION],
@@ -8456,7 +8668,8 @@
if (!test_and_clear_bit(NFS4_SESSION_ESTABLISHED, &session->session_state))
return 0;
- status = rpc_call_sync(session->clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT);
+ status = rpc_call_sync(session->clp->cl_rpcclient, &msg,
+ RPC_TASK_TIMEOUT | RPC_TASK_NO_ROUND_ROBIN);
trace_nfs4_destroy_session(session->clp, status);
if (status)
@@ -8543,7 +8756,7 @@
};
static struct rpc_task *_nfs41_proc_sequence(struct nfs_client *clp,
- struct rpc_cred *cred,
+ const struct cred *cred,
struct nfs4_slot *slot,
bool is_privileged)
{
@@ -8586,7 +8799,7 @@
return ret;
}
-static int nfs41_proc_async_sequence(struct nfs_client *clp, struct rpc_cred *cred, unsigned renew_flags)
+static int nfs41_proc_async_sequence(struct nfs_client *clp, const struct cred *cred, unsigned renew_flags)
{
struct rpc_task *task;
int ret = 0;
@@ -8602,7 +8815,7 @@
return ret;
}
-static int nfs4_proc_sequence(struct nfs_client *clp, struct rpc_cred *cred)
+static int nfs4_proc_sequence(struct nfs_client *clp, const struct cred *cred)
{
struct rpc_task *task;
int ret;
@@ -8698,10 +8911,9 @@
* Issue a global reclaim complete.
*/
static int nfs41_proc_reclaim_complete(struct nfs_client *clp,
- struct rpc_cred *cred)
+ const struct cred *cred)
{
struct nfs4_reclaim_complete_data *calldata;
- struct rpc_task *task;
struct rpc_message msg = {
.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_RECLAIM_COMPLETE],
.rpc_cred = cred,
@@ -8710,7 +8922,7 @@
.rpc_client = clp->cl_rpcclient,
.rpc_message = &msg,
.callback_ops = &nfs4_reclaim_complete_call_ops,
- .flags = RPC_TASK_ASYNC,
+ .flags = RPC_TASK_NO_ROUND_ROBIN,
};
int status = -ENOMEM;
@@ -8725,15 +8937,7 @@
msg.rpc_argp = &calldata->arg;
msg.rpc_resp = &calldata->res;
task_setup_data.callback_data = calldata;
- task = rpc_run_task(&task_setup_data);
- if (IS_ERR(task)) {
- status = PTR_ERR(task);
- goto out;
- }
- status = rpc_wait_for_completion_task(task);
- if (status == 0)
- status = task->tk_status;
- rpc_put_task(task);
+ status = nfs4_call_sync_custom(&task_setup_data);
out:
dprintk("<-- %s status=%d\n", __func__, status);
return status;
@@ -8913,10 +9117,12 @@
if (status != 0)
goto out;
- /* if layoutp->len is 0, nfs4_layoutget_prepare called rpc_exit */
- if (task->tk_status < 0 || lgp->res.layoutp->len == 0) {
+ if (task->tk_status < 0) {
status = nfs4_layoutget_handle_exception(task, lgp, &exception);
*timeout = exception.timeout;
+ } else if (lgp->res.layoutp->len == 0) {
+ status = -EAGAIN;
+ *timeout = nfs4_update_delay(&exception.timeout);
} else
lseg = pnfs_layout_process(lgp);
out:
@@ -8957,10 +9163,19 @@
if (!nfs41_sequence_process(task, &lrp->res.seq_res))
return;
+ /*
+ * Was there an RPC level error? Assume the call succeeded,
+ * and that we need to release the layout
+ */
+ if (task->tk_rpc_status != 0 && RPC_WAS_SENT(task)) {
+ lrp->res.lrs_present = 0;
+ return;
+ }
+
server = NFS_SERVER(lrp->args.inode);
switch (task->tk_status) {
case -NFS4ERR_OLD_STATEID:
- if (nfs4_layoutreturn_refresh_stateid(&lrp->args.stateid,
+ if (nfs4_layout_refresh_old_stateid(&lrp->args.stateid,
&lrp->args.range,
lrp->args.inode))
goto out_restart;
@@ -9051,7 +9266,7 @@
static int
_nfs4_proc_getdeviceinfo(struct nfs_server *server,
struct pnfs_device *pdev,
- struct rpc_cred *cred)
+ const struct cred *cred)
{
struct nfs4_getdeviceinfo_args args = {
.pdev = pdev,
@@ -9083,7 +9298,7 @@
int nfs4_proc_getdeviceinfo(struct nfs_server *server,
struct pnfs_device *pdev,
- struct rpc_cred *cred)
+ const struct cred *cred)
{
struct nfs4_exception exception = { };
int err;
@@ -9140,7 +9355,7 @@
pnfs_cleanup_layoutcommit(data);
nfs_post_op_update_inode_force_wcc(data->args.inode,
data->res.fattr);
- put_rpccred(data->cred);
+ put_cred(data->cred);
nfs_iput_and_deactive(data->inode);
kfree(data);
}
@@ -9195,7 +9410,7 @@
return status;
}
-/**
+/*
* Use the state managment nfs_client cl_rpcclient, which uses krb5i (if
* possible) as per RFC3530bis and RFC5661 Security Considerations sections
*/
@@ -9216,22 +9431,35 @@
.rpc_resp = &res,
};
struct rpc_clnt *clnt = server->client;
- struct rpc_cred *cred = NULL;
+ struct nfs4_call_sync_data data = {
+ .seq_server = server,
+ .seq_args = &args.seq_args,
+ .seq_res = &res.seq_res,
+ };
+ struct rpc_task_setup task_setup = {
+ .rpc_client = server->client,
+ .rpc_message = &msg,
+ .callback_ops = server->nfs_client->cl_mvops->call_sync_ops,
+ .callback_data = &data,
+ .flags = RPC_TASK_NO_ROUND_ROBIN,
+ };
+ const struct cred *cred = NULL;
int status;
if (use_integrity) {
clnt = server->nfs_client->cl_rpcclient;
+ task_setup.rpc_client = clnt;
+
cred = nfs4_get_clid_cred(server->nfs_client);
msg.rpc_cred = cred;
}
dprintk("--> %s\n", __func__);
- status = nfs4_call_sync(clnt, server, &msg, &args.seq_args,
- &res.seq_res, 0);
+ nfs4_init_sequence(&args.seq_args, &res.seq_res, 0, 0);
+ status = nfs4_call_sync_custom(&task_setup);
dprintk("<-- %s status=%d\n", __func__, status);
- if (cred)
- put_rpccred(cred);
+ put_cred(cred);
return status;
}
@@ -9240,7 +9468,9 @@
nfs41_proc_secinfo_no_name(struct nfs_server *server, struct nfs_fh *fhandle,
struct nfs_fsinfo *info, struct nfs4_secinfo_flavors *flavors)
{
- struct nfs4_exception exception = { };
+ struct nfs4_exception exception = {
+ .interruptible = true,
+ };
int err;
do {
/* first try using integrity protection */
@@ -9344,7 +9574,7 @@
static int _nfs41_test_stateid(struct nfs_server *server,
nfs4_stateid *stateid,
- struct rpc_cred *cred)
+ const struct cred *cred)
{
int status;
struct nfs41_test_stateid_args args = {
@@ -9405,9 +9635,11 @@
*/
static int nfs41_test_stateid(struct nfs_server *server,
nfs4_stateid *stateid,
- struct rpc_cred *cred)
+ const struct cred *cred)
{
- struct nfs4_exception exception = { };
+ struct nfs4_exception exception = {
+ .interruptible = true,
+ };
int err;
do {
err = _nfs41_test_stateid(server, stateid, cred);
@@ -9461,13 +9693,13 @@
* @server: server / transport on which to perform the operation
* @stateid: state ID to release
* @cred: credential
- * @is_recovery: set to true if this call needs to be privileged
+ * @privileged: set to true if this call needs to be privileged
*
* Note: this function is always asynchronous.
*/
static int nfs41_free_stateid(struct nfs_server *server,
const nfs4_stateid *stateid,
- struct rpc_cred *cred,
+ const struct cred *cred,
bool privileged)
{
struct rpc_message msg = {
@@ -9508,7 +9740,7 @@
static void
nfs41_free_lock_state(struct nfs_server *server, struct nfs4_lock_state *lsp)
{
- struct rpc_cred *cred = lsp->ls_state->owner->so_cred;
+ const struct cred *cred = lsp->ls_state->owner->so_cred;
nfs41_free_stateid(server, &lsp->ls_stateid, cred, false);
nfs4_free_lock_state(server, lsp);
@@ -9579,14 +9811,14 @@
static const struct nfs4_state_maintenance_ops nfs40_state_renewal_ops = {
.sched_state_renewal = nfs4_proc_async_renew,
- .get_state_renewal_cred_locked = nfs4_get_renew_cred_locked,
+ .get_state_renewal_cred = nfs4_get_renew_cred,
.renew_lease = nfs4_proc_renew,
};
#if defined(CONFIG_NFS_V4_1)
static const struct nfs4_state_maintenance_ops nfs41_state_renewal_ops = {
.sched_state_renewal = nfs41_proc_async_sequence,
- .get_state_renewal_cred_locked = nfs4_get_machine_cred_locked,
+ .get_state_renewal_cred = nfs4_get_machine_cred,
.renew_lease = nfs4_proc_sequence,
};
#endif
@@ -9668,7 +9900,8 @@
| 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/nfs4renewd.c b/fs/nfs/nfs4renewd.c
index 1f8c2ae..6ea431b 100644
--- a/fs/nfs/nfs4renewd.c
+++ b/fs/nfs/nfs4renewd.c
@@ -57,7 +57,7 @@
const struct nfs4_state_maintenance_ops *ops;
struct nfs_client *clp =
container_of(work, struct nfs_client, cl_renewd.work);
- struct rpc_cred *cred;
+ const struct cred *cred;
long lease;
unsigned long last, now;
unsigned renew_flags = 0;
@@ -68,7 +68,6 @@
if (test_bit(NFS_CS_STOP_RENEW, &clp->cl_res_state))
goto out;
- spin_lock(&clp->cl_lock);
lease = clp->cl_lease_time;
last = clp->cl_last_renewal;
now = jiffies;
@@ -79,8 +78,7 @@
renew_flags |= NFS4_RENEW_DELEGATION_CB;
if (renew_flags != 0) {
- cred = ops->get_state_renewal_cred_locked(clp);
- spin_unlock(&clp->cl_lock);
+ cred = ops->get_state_renewal_cred(clp);
if (cred == NULL) {
if (!(renew_flags & NFS4_RENEW_DELEGATION_CB)) {
set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state);
@@ -92,7 +90,7 @@
/* Queue an asynchronous RENEW. */
ret = ops->sched_state_renewal(clp, cred, renew_flags);
- put_rpccred(cred);
+ put_cred(cred);
switch (ret) {
default:
goto out_exp;
@@ -104,7 +102,6 @@
} else {
dprintk("%s: failed to call renewd. Reason: lease not expired \n",
__func__);
- spin_unlock(&clp->cl_lock);
}
nfs4_schedule_state_renewal(clp);
out_exp:
diff --git a/fs/nfs/nfs4session.c b/fs/nfs/nfs4session.c
index 769b856..4145a01 100644
--- a/fs/nfs/nfs4session.c
+++ b/fs/nfs/nfs4session.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* fs/nfs/nfs4session.c
*
@@ -55,7 +56,7 @@
/**
* nfs4_slot_tbl_drain_complete - wake waiters when drain is complete
- * @tbl - controlling slot table
+ * @tbl: controlling slot table
*
*/
void nfs4_slot_tbl_drain_complete(struct nfs4_slot_table *tbl)
@@ -110,6 +111,8 @@
slot->table = tbl;
slot->slot_nr = slotid;
slot->seq_nr = seq_init;
+ slot->seq_nr_highest_sent = seq_init;
+ slot->seq_nr_last_acked = seq_init - 1;
}
return slot;
}
@@ -276,7 +279,8 @@
p = &tbl->slots;
while (*p) {
(*p)->seq_nr = ivalue;
- (*p)->interrupted = 0;
+ (*p)->seq_nr_highest_sent = ivalue;
+ (*p)->seq_nr_last_acked = ivalue - 1;
p = &(*p)->next;
}
tbl->highest_used_slotid = NFS4_NO_SLOT;
@@ -573,12 +577,11 @@
void nfs4_destroy_session(struct nfs4_session *session)
{
struct rpc_xprt *xprt;
- struct rpc_cred *cred;
+ const struct cred *cred;
cred = nfs4_get_clid_cred(session->clp);
nfs4_proc_destroy_session(session, cred);
- if (cred)
- put_rpccred(cred);
+ put_cred(cred);
rcu_read_lock();
xprt = rcu_dereference(session->clp->cl_rpcclient->cl_xprt);
diff --git a/fs/nfs/nfs4session.h b/fs/nfs/nfs4session.h
index 3c550f2..b996ee2 100644
--- a/fs/nfs/nfs4session.h
+++ b/fs/nfs/nfs4session.h
@@ -10,7 +10,7 @@
/* maximum number of slots to use */
#define NFS4_DEF_SLOT_TABLE_SIZE (64U)
-#define NFS4_DEF_CB_SLOT_TABLE_SIZE (1U)
+#define NFS4_DEF_CB_SLOT_TABLE_SIZE (16U)
#define NFS4_MAX_SLOT_TABLE (1024U)
#define NFS4_NO_SLOT ((u32)-1)
@@ -23,8 +23,9 @@
unsigned long generation;
u32 slot_nr;
u32 seq_nr;
- unsigned int interrupted : 1,
- privileged : 1,
+ u32 seq_nr_last_acked;
+ u32 seq_nr_highest_sent;
+ unsigned int privileged : 1,
seq_done : 1;
};
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index d2f645d..0c6d53d 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -87,7 +87,28 @@
static DEFINE_MUTEX(nfs_clid_init_mutex);
-int nfs4_init_clientid(struct nfs_client *clp, struct rpc_cred *cred)
+static int nfs4_setup_state_renewal(struct nfs_client *clp)
+{
+ int status;
+ struct nfs_fsinfo fsinfo;
+ unsigned long now;
+
+ if (!test_bit(NFS_CS_CHECK_LEASE_TIME, &clp->cl_res_state)) {
+ nfs4_schedule_state_renewal(clp);
+ return 0;
+ }
+
+ now = jiffies;
+ status = nfs4_proc_get_lease_time(clp, &fsinfo);
+ if (status == 0) {
+ nfs4_set_lease_period(clp, fsinfo.lease_time * HZ, now);
+ nfs4_schedule_state_renewal(clp);
+ }
+
+ return status;
+}
+
+int nfs4_init_clientid(struct nfs_client *clp, const struct cred *cred)
{
struct nfs4_setclientid_res clid = {
.clientid = clp->cl_clientid,
@@ -114,7 +135,7 @@
if (status != 0)
goto out;
clear_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state);
- nfs4_schedule_state_renewal(clp);
+ nfs4_setup_state_renewal(clp);
out:
return status;
}
@@ -134,7 +155,7 @@
*/
int nfs40_discover_server_trunking(struct nfs_client *clp,
struct nfs_client **result,
- struct rpc_cred *cred)
+ const struct cred *cred)
{
struct nfs4_setclientid_res clid = {
.clientid = clp->cl_clientid,
@@ -159,37 +180,32 @@
/* Sustain the lease, even if it's empty. If the clientid4
* goes stale it's of no use for trunking discovery. */
nfs4_schedule_state_renewal(*result);
+
+ /* If the client state need to recover, do it. */
+ if (clp->cl_state)
+ nfs4_schedule_state_manager(clp);
}
out:
return status;
}
-struct rpc_cred *nfs4_get_machine_cred_locked(struct nfs_client *clp)
+const struct cred *nfs4_get_machine_cred(struct nfs_client *clp)
{
- struct rpc_cred *cred = NULL;
-
- if (clp->cl_machine_cred != NULL)
- cred = get_rpccred(clp->cl_machine_cred);
- return cred;
+ return get_cred(rpc_machine_cred());
}
static void nfs4_root_machine_cred(struct nfs_client *clp)
{
- struct rpc_cred *cred, *new;
- new = rpc_lookup_machine_cred(NULL);
- spin_lock(&clp->cl_lock);
- cred = clp->cl_machine_cred;
- clp->cl_machine_cred = new;
- spin_unlock(&clp->cl_lock);
- if (cred != NULL)
- put_rpccred(cred);
+ /* Force root creds instead of machine */
+ clp->cl_principal = NULL;
+ clp->cl_rpcclient->cl_principal = NULL;
}
-static struct rpc_cred *
+static const struct cred *
nfs4_get_renew_cred_server_locked(struct nfs_server *server)
{
- struct rpc_cred *cred = NULL;
+ const struct cred *cred = NULL;
struct nfs4_state_owner *sp;
struct rb_node *pos;
@@ -199,29 +215,30 @@
sp = rb_entry(pos, struct nfs4_state_owner, so_server_node);
if (list_empty(&sp->so_states))
continue;
- cred = get_rpccred(sp->so_cred);
+ cred = get_cred(sp->so_cred);
break;
}
return cred;
}
/**
- * nfs4_get_renew_cred_locked - Acquire credential for a renew operation
+ * nfs4_get_renew_cred - Acquire credential for a renew operation
* @clp: client state handle
*
* Returns an rpc_cred with reference count bumped, or NULL.
* Caller must hold clp->cl_lock.
*/
-struct rpc_cred *nfs4_get_renew_cred_locked(struct nfs_client *clp)
+const struct cred *nfs4_get_renew_cred(struct nfs_client *clp)
{
- struct rpc_cred *cred = NULL;
+ const struct cred *cred = NULL;
struct nfs_server *server;
/* Use machine credentials if available */
- cred = nfs4_get_machine_cred_locked(clp);
+ cred = nfs4_get_machine_cred(clp);
if (cred != NULL)
goto out;
+ spin_lock(&clp->cl_lock);
rcu_read_lock();
list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) {
cred = nfs4_get_renew_cred_server_locked(server);
@@ -229,6 +246,7 @@
break;
}
rcu_read_unlock();
+ spin_unlock(&clp->cl_lock);
out:
return cred;
@@ -289,37 +307,16 @@
#if defined(CONFIG_NFS_V4_1)
-static int nfs41_setup_state_renewal(struct nfs_client *clp)
-{
- int status;
- struct nfs_fsinfo fsinfo;
- unsigned long now;
-
- if (!test_bit(NFS_CS_CHECK_LEASE_TIME, &clp->cl_res_state)) {
- nfs4_schedule_state_renewal(clp);
- return 0;
- }
-
- now = jiffies;
- status = nfs4_proc_get_lease_time(clp, &fsinfo);
- if (status == 0) {
- nfs4_set_lease_period(clp, fsinfo.lease_time * HZ, now);
- nfs4_schedule_state_renewal(clp);
- }
-
- return status;
-}
-
static void nfs41_finish_session_reset(struct nfs_client *clp)
{
clear_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state);
clear_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state);
/* create_session negotiated new slot table */
clear_bit(NFS4CLNT_BIND_CONN_TO_SESSION, &clp->cl_state);
- nfs41_setup_state_renewal(clp);
+ nfs4_setup_state_renewal(clp);
}
-int nfs41_init_clientid(struct nfs_client *clp, struct rpc_cred *cred)
+int nfs41_init_clientid(struct nfs_client *clp, const struct cred *cred)
{
int status;
@@ -354,7 +351,7 @@
*/
int nfs41_discover_server_trunking(struct nfs_client *clp,
struct nfs_client **result,
- struct rpc_cred *cred)
+ const struct cred *cred)
{
int status;
@@ -392,32 +389,32 @@
* nfs4_get_clid_cred - Acquire credential for a setclientid operation
* @clp: client state handle
*
- * Returns an rpc_cred with reference count bumped, or NULL.
+ * Returns a cred with reference count bumped, or NULL.
*/
-struct rpc_cred *nfs4_get_clid_cred(struct nfs_client *clp)
+const struct cred *nfs4_get_clid_cred(struct nfs_client *clp)
{
- struct rpc_cred *cred;
+ const struct cred *cred;
- spin_lock(&clp->cl_lock);
- cred = nfs4_get_machine_cred_locked(clp);
- spin_unlock(&clp->cl_lock);
+ cred = nfs4_get_machine_cred(clp);
return cred;
}
static struct nfs4_state_owner *
-nfs4_find_state_owner_locked(struct nfs_server *server, struct rpc_cred *cred)
+nfs4_find_state_owner_locked(struct nfs_server *server, const struct cred *cred)
{
struct rb_node **p = &server->state_owners.rb_node,
*parent = NULL;
struct nfs4_state_owner *sp;
+ int cmp;
while (*p != NULL) {
parent = *p;
sp = rb_entry(parent, struct nfs4_state_owner, so_server_node);
+ cmp = cred_fscmp(cred, sp->so_cred);
- if (cred < sp->so_cred)
+ if (cmp < 0)
p = &parent->rb_left;
- else if (cred > sp->so_cred)
+ else if (cmp > 0)
p = &parent->rb_right;
else {
if (!list_empty(&sp->so_lru))
@@ -436,14 +433,16 @@
struct rb_node **p = &server->state_owners.rb_node,
*parent = NULL;
struct nfs4_state_owner *sp;
+ int cmp;
while (*p != NULL) {
parent = *p;
sp = rb_entry(parent, struct nfs4_state_owner, so_server_node);
+ cmp = cred_fscmp(new->so_cred, sp->so_cred);
- if (new->so_cred < sp->so_cred)
+ if (cmp < 0)
p = &parent->rb_left;
- else if (new->so_cred > sp->so_cred)
+ else if (cmp > 0)
p = &parent->rb_right;
else {
if (!list_empty(&sp->so_lru))
@@ -490,7 +489,7 @@
*/
static struct nfs4_state_owner *
nfs4_alloc_state_owner(struct nfs_server *server,
- struct rpc_cred *cred,
+ const struct cred *cred,
gfp_t gfp_flags)
{
struct nfs4_state_owner *sp;
@@ -505,7 +504,7 @@
return NULL;
}
sp->so_server = server;
- sp->so_cred = get_rpccred(cred);
+ sp->so_cred = get_cred(cred);
spin_lock_init(&sp->so_lock);
INIT_LIST_HEAD(&sp->so_states);
nfs4_init_seqid_counter(&sp->so_seqid);
@@ -534,7 +533,7 @@
static void nfs4_free_state_owner(struct nfs4_state_owner *sp)
{
nfs4_destroy_seqid_counter(&sp->so_seqid);
- put_rpccred(sp->so_cred);
+ put_cred(sp->so_cred);
ida_simple_remove(&sp->so_server->openowner_id, sp->so_seqid.owner_id);
kfree(sp);
}
@@ -568,11 +567,12 @@
* nfs4_get_state_owner - Look up a state owner given a credential
* @server: nfs_server to search
* @cred: RPC credential to match
+ * @gfp_flags: allocation mode
*
* Returns a pointer to an instantiated nfs4_state_owner struct, or NULL.
*/
struct nfs4_state_owner *nfs4_get_state_owner(struct nfs_server *server,
- struct rpc_cred *cred,
+ const struct cred *cred,
gfp_t gfp_flags)
{
struct nfs_client *clp = server->nfs_client;
@@ -624,24 +624,39 @@
/**
* nfs4_purge_state_owners - Release all cached state owners
* @server: nfs_server with cached state owners to release
+ * @head: resulting list of state owners
*
* Called at umount time. Remaining state owners will be on
* the LRU with ref count of zero.
+ * Note that the state owners are not freed, but are added
+ * to the list @head, which can later be used as an argument
+ * to nfs4_free_state_owners.
*/
-void nfs4_purge_state_owners(struct nfs_server *server)
+void nfs4_purge_state_owners(struct nfs_server *server, struct list_head *head)
{
struct nfs_client *clp = server->nfs_client;
struct nfs4_state_owner *sp, *tmp;
- LIST_HEAD(doomed);
spin_lock(&clp->cl_lock);
list_for_each_entry_safe(sp, tmp, &server->state_owners_lru, so_lru) {
- list_move(&sp->so_lru, &doomed);
+ list_move(&sp->so_lru, head);
nfs4_remove_state_owner_locked(sp);
}
spin_unlock(&clp->cl_lock);
+}
- list_for_each_entry_safe(sp, tmp, &doomed, so_lru) {
+/**
+ * nfs4_purge_state_owners - Release all cached state owners
+ * @head: resulting list of state owners
+ *
+ * Frees a list of state owners that was generated by
+ * nfs4_purge_state_owners
+ */
+void nfs4_free_state_owners(struct list_head *head)
+{
+ struct nfs4_state_owner *sp, *tmp;
+
+ list_for_each_entry_safe(sp, tmp, head, so_lru) {
list_del(&sp->so_lru);
nfs4_free_state_owner(sp);
}
@@ -655,7 +670,7 @@
state = kzalloc(sizeof(*state), GFP_NOFS);
if (!state)
return NULL;
- atomic_set(&state->count, 1);
+ refcount_set(&state->count, 1);
INIT_LIST_HEAD(&state->lock_states);
spin_lock_init(&state->state_lock);
seqlock_init(&state->seqlock);
@@ -684,12 +699,12 @@
struct nfs_inode *nfsi = NFS_I(inode);
struct nfs4_state *state;
- list_for_each_entry(state, &nfsi->open_states, inode_states) {
+ list_for_each_entry_rcu(state, &nfsi->open_states, inode_states) {
if (state->owner != owner)
continue;
if (!nfs4_valid_open_stateid(state))
continue;
- if (atomic_inc_not_zero(&state->count))
+ if (refcount_inc_not_zero(&state->count))
return state;
}
return NULL;
@@ -698,7 +713,7 @@
static void
nfs4_free_open_state(struct nfs4_state *state)
{
- kfree(state);
+ kfree_rcu(state, rcu_head);
}
struct nfs4_state *
@@ -707,9 +722,9 @@
struct nfs4_state *state, *new;
struct nfs_inode *nfsi = NFS_I(inode);
- spin_lock(&inode->i_lock);
+ rcu_read_lock();
state = __nfs4_find_state_byowner(inode, owner);
- spin_unlock(&inode->i_lock);
+ rcu_read_unlock();
if (state)
goto out;
new = nfs4_alloc_open_state();
@@ -720,7 +735,7 @@
state = new;
state->owner = owner;
atomic_inc(&owner->so_count);
- list_add(&state->inode_states, &nfsi->open_states);
+ list_add_rcu(&state->inode_states, &nfsi->open_states);
ihold(inode);
state->inode = inode;
spin_unlock(&inode->i_lock);
@@ -743,10 +758,10 @@
struct inode *inode = state->inode;
struct nfs4_state_owner *owner = state->owner;
- if (!atomic_dec_and_lock(&state->count, &owner->so_lock))
+ if (!refcount_dec_and_lock(&state->count, &owner->so_lock))
return;
spin_lock(&inode->i_lock);
- list_del(&state->inode_states);
+ list_del_rcu(&state->inode_states);
list_del(&state->open_states);
spin_unlock(&inode->i_lock);
spin_unlock(&owner->so_lock);
@@ -1000,22 +1015,6 @@
return ret;
}
-bool nfs4_refresh_open_stateid(nfs4_stateid *dst, struct nfs4_state *state)
-{
- bool ret;
- int seq;
-
- do {
- ret = false;
- seq = read_seqbegin(&state->seqlock);
- if (nfs4_state_match_open_stateid_other(state, dst)) {
- dst->seqid = state->open_stateid.seqid;
- ret = true;
- }
- } while (read_seqretry(&state->seqlock, seq));
- return ret;
-}
-
bool nfs4_copy_open_stateid(nfs4_stateid *dst, struct nfs4_state *state)
{
bool ret;
@@ -1041,7 +1040,7 @@
*/
int nfs4_select_rw_stateid(struct nfs4_state *state,
fmode_t fmode, const struct nfs_lock_context *l_ctx,
- nfs4_stateid *dst, struct rpc_cred **cred)
+ nfs4_stateid *dst, const struct cred **cred)
{
int ret;
@@ -1064,8 +1063,7 @@
* choose to use.
*/
goto out;
- nfs4_copy_open_stateid(dst, state);
- ret = 0;
+ ret = nfs4_copy_open_stateid(dst, state) ? 0 : -EAGAIN;
out:
if (nfs_server_capable(state->inode, NFS_CAP_STATEID_NFSV41))
dst->seqid = 0;
@@ -1438,8 +1436,8 @@
struct nfs4_state *state;
bool found = false;
- spin_lock(&inode->i_lock);
- list_for_each_entry(ctx, &nfsi->open_files, list) {
+ rcu_read_lock();
+ list_for_each_entry_rcu(ctx, &nfsi->open_files, list) {
state = ctx->state;
if (state == NULL)
continue;
@@ -1457,32 +1455,34 @@
nfs4_state_mark_reclaim_nograce(clp, state))
found = true;
}
- spin_unlock(&inode->i_lock);
+ rcu_read_unlock();
nfs_inode_find_delegation_state_and_recover(inode, stateid);
if (found)
nfs4_schedule_state_manager(clp);
}
-static void nfs4_state_mark_open_context_bad(struct nfs4_state *state)
+static void nfs4_state_mark_open_context_bad(struct nfs4_state *state, int err)
{
struct inode *inode = state->inode;
struct nfs_inode *nfsi = NFS_I(inode);
struct nfs_open_context *ctx;
- spin_lock(&inode->i_lock);
- list_for_each_entry(ctx, &nfsi->open_files, list) {
+ rcu_read_lock();
+ list_for_each_entry_rcu(ctx, &nfsi->open_files, list) {
if (ctx->state != state)
continue;
set_bit(NFS_CONTEXT_BAD, &ctx->flags);
+ pr_warn("NFSv4: state recovery failed for open file %pd2, "
+ "error = %d\n", ctx->dentry, err);
}
- spin_unlock(&inode->i_lock);
+ rcu_read_unlock();
}
static void nfs4_state_mark_recovery_failed(struct nfs4_state *state, int error)
{
set_bit(NFS_STATE_RECOVERY_FAILED, &state->flags);
- nfs4_state_mark_open_context_bad(state);
+ nfs4_state_mark_open_context_bad(state, error);
}
@@ -1513,6 +1513,7 @@
switch (status) {
case 0:
break;
+ case -ETIMEDOUT:
case -ESTALE:
case -NFS4ERR_ADMIN_REVOKED:
case -NFS4ERR_STALE_STATEID:
@@ -1550,10 +1551,63 @@
return status;
}
+#ifdef CONFIG_NFS_V4_2
+static void nfs42_complete_copies(struct nfs4_state_owner *sp, struct nfs4_state *state)
+{
+ struct nfs4_copy_state *copy;
+
+ if (!test_bit(NFS_CLNT_DST_SSC_COPY_STATE, &state->flags))
+ return;
+
+ spin_lock(&sp->so_server->nfs_client->cl_lock);
+ list_for_each_entry(copy, &sp->so_server->ss_copies, copies) {
+ if (!nfs4_stateid_match_other(&state->stateid, ©->parent_state->stateid))
+ continue;
+ copy->flags = 1;
+ complete(©->completion);
+ break;
+ }
+ spin_unlock(&sp->so_server->nfs_client->cl_lock);
+}
+#else /* !CONFIG_NFS_V4_2 */
+static inline void nfs42_complete_copies(struct nfs4_state_owner *sp,
+ struct nfs4_state *state)
+{
+}
+#endif /* CONFIG_NFS_V4_2 */
+
+static int __nfs4_reclaim_open_state(struct nfs4_state_owner *sp, struct nfs4_state *state,
+ const struct nfs4_state_recovery_ops *ops)
+{
+ struct nfs4_lock_state *lock;
+ int status;
+
+ status = ops->recover_open(sp, state);
+ if (status < 0)
+ return status;
+
+ status = nfs4_reclaim_locks(state, ops);
+ if (status < 0)
+ return status;
+
+ if (!test_bit(NFS_DELEGATED_STATE, &state->flags)) {
+ spin_lock(&state->state_lock);
+ list_for_each_entry(lock, &state->lock_states, ls_locks) {
+ if (!test_bit(NFS_LOCK_INITIALIZED, &lock->ls_flags))
+ pr_warn_ratelimited("NFS: %s: Lock reclaim failed!\n", __func__);
+ }
+ spin_unlock(&state->state_lock);
+ }
+
+ nfs42_complete_copies(sp, state);
+ clear_bit(NFS_STATE_RECLAIM_NOGRACE, &state->flags);
+ return status;
+}
+
static int nfs4_reclaim_open_state(struct nfs4_state_owner *sp, const struct nfs4_state_recovery_ops *ops)
{
struct nfs4_state *state;
- struct nfs4_lock_state *lock;
+ unsigned int loop = 0;
int status = 0;
/* Note: we rely on the sp->so_states list being ordered
@@ -1574,79 +1628,53 @@
continue;
if (state->state == 0)
continue;
- atomic_inc(&state->count);
+ refcount_inc(&state->count);
spin_unlock(&sp->so_lock);
- status = ops->recover_open(sp, state);
- if (status >= 0) {
- status = nfs4_reclaim_locks(state, ops);
- if (status >= 0) {
- if (!test_bit(NFS_DELEGATED_STATE, &state->flags)) {
- spin_lock(&state->state_lock);
- list_for_each_entry(lock, &state->lock_states, ls_locks) {
- if (!test_bit(NFS_LOCK_INITIALIZED, &lock->ls_flags))
- pr_warn_ratelimited("NFS: "
- "%s: Lock reclaim "
- "failed!\n", __func__);
- }
- spin_unlock(&state->state_lock);
- }
- clear_bit(NFS_STATE_RECLAIM_NOGRACE,
- &state->flags);
-#ifdef CONFIG_NFS_V4_2
- if (test_bit(NFS_CLNT_DST_SSC_COPY_STATE, &state->flags)) {
- struct nfs4_copy_state *copy;
+ status = __nfs4_reclaim_open_state(sp, state, ops);
- spin_lock(&sp->so_server->nfs_client->cl_lock);
- list_for_each_entry(copy, &sp->so_server->ss_copies, copies) {
- if (memcmp(&state->stateid.other, ©->parent_state->stateid.other, NFS4_STATEID_SIZE))
- continue;
- copy->flags = 1;
- complete(©->completion);
- printk("AGLO: server rebooted waking up the copy\n");
- break;
- }
- spin_unlock(&sp->so_server->nfs_client->cl_lock);
- }
-#endif /* CONFIG_NFS_V4_2 */
- nfs4_put_open_state(state);
- spin_lock(&sp->so_lock);
- goto restart;
- }
- }
switch (status) {
- default:
- printk(KERN_ERR "NFS: %s: unhandled error %d\n",
- __func__, status);
- /* Fall through */
- case -ENOENT:
- case -ENOMEM:
- case -EACCES:
- case -EROFS:
- case -EIO:
- case -ESTALE:
- /* Open state on this file cannot be recovered */
- nfs4_state_mark_recovery_failed(state, status);
+ default:
+ if (status >= 0) {
+ loop = 0;
break;
- case -EAGAIN:
- ssleep(1);
- /* Fall through */
- case -NFS4ERR_ADMIN_REVOKED:
- case -NFS4ERR_STALE_STATEID:
- case -NFS4ERR_OLD_STATEID:
- case -NFS4ERR_BAD_STATEID:
- case -NFS4ERR_RECLAIM_BAD:
- case -NFS4ERR_RECLAIM_CONFLICT:
- nfs4_state_mark_reclaim_nograce(sp->so_server->nfs_client, state);
+ }
+ printk(KERN_ERR "NFS: %s: unhandled error %d\n", __func__, status);
+ /* Fall through */
+ case -ENOENT:
+ case -ENOMEM:
+ case -EACCES:
+ case -EROFS:
+ case -EIO:
+ case -ESTALE:
+ /* Open state on this file cannot be recovered */
+ nfs4_state_mark_recovery_failed(state, status);
+ break;
+ case -EAGAIN:
+ ssleep(1);
+ if (loop++ < 10) {
+ set_bit(ops->state_flag_bit, &state->flags);
break;
- case -NFS4ERR_EXPIRED:
- case -NFS4ERR_NO_GRACE:
- nfs4_state_mark_reclaim_nograce(sp->so_server->nfs_client, state);
- case -NFS4ERR_STALE_CLIENTID:
- case -NFS4ERR_BADSESSION:
- case -NFS4ERR_BADSLOT:
- case -NFS4ERR_BAD_HIGH_SLOT:
- case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION:
- goto out_err;
+ }
+ /* Fall through */
+ case -NFS4ERR_ADMIN_REVOKED:
+ case -NFS4ERR_STALE_STATEID:
+ case -NFS4ERR_OLD_STATEID:
+ case -NFS4ERR_BAD_STATEID:
+ case -NFS4ERR_RECLAIM_BAD:
+ case -NFS4ERR_RECLAIM_CONFLICT:
+ nfs4_state_mark_reclaim_nograce(sp->so_server->nfs_client, state);
+ break;
+ case -NFS4ERR_EXPIRED:
+ case -NFS4ERR_NO_GRACE:
+ nfs4_state_mark_reclaim_nograce(sp->so_server->nfs_client, state);
+ /* Fall through */
+ case -NFS4ERR_STALE_CLIENTID:
+ case -NFS4ERR_BADSESSION:
+ case -NFS4ERR_BADSLOT:
+ case -NFS4ERR_BAD_HIGH_SLOT:
+ case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION:
+ case -ETIMEDOUT:
+ goto out_err;
}
nfs4_put_open_state(state);
spin_lock(&sp->so_lock);
@@ -1723,7 +1751,7 @@
static int nfs4_reclaim_complete(struct nfs_client *clp,
const struct nfs4_state_recovery_ops *ops,
- struct rpc_cred *cred)
+ const struct cred *cred)
{
/* Notify the server we're done reclaiming our state */
if (ops->reclaim_complete)
@@ -1774,7 +1802,7 @@
static void nfs4_state_end_reclaim_reboot(struct nfs_client *clp)
{
const struct nfs4_state_recovery_ops *ops;
- struct rpc_cred *cred;
+ const struct cred *cred;
int err;
if (!nfs4_state_clear_reclaim_reboot(clp))
@@ -1782,7 +1810,7 @@
ops = clp->cl_mvops->reboot_recovery_ops;
cred = nfs4_get_clid_cred(clp);
err = nfs4_reclaim_complete(clp, ops, cred);
- put_rpccred(cred);
+ put_cred(cred);
if (err == -NFS4ERR_CONN_NOT_BOUND_TO_SESSION)
set_bit(NFS4CLNT_RECLAIM_REBOOT, &clp->cl_state);
}
@@ -1796,38 +1824,38 @@
static int nfs4_recovery_handle_error(struct nfs_client *clp, int error)
{
switch (error) {
- case 0:
- break;
- case -NFS4ERR_CB_PATH_DOWN:
- nfs40_handle_cb_pathdown(clp);
- break;
- case -NFS4ERR_NO_GRACE:
- nfs4_state_end_reclaim_reboot(clp);
- break;
- case -NFS4ERR_STALE_CLIENTID:
- set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state);
- nfs4_state_start_reclaim_reboot(clp);
- break;
- case -NFS4ERR_EXPIRED:
- set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state);
- nfs4_state_start_reclaim_nograce(clp);
- break;
- case -NFS4ERR_BADSESSION:
- case -NFS4ERR_BADSLOT:
- case -NFS4ERR_BAD_HIGH_SLOT:
- case -NFS4ERR_DEADSESSION:
- case -NFS4ERR_SEQ_FALSE_RETRY:
- case -NFS4ERR_SEQ_MISORDERED:
- set_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state);
- /* Zero session reset errors */
- break;
- case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION:
- set_bit(NFS4CLNT_BIND_CONN_TO_SESSION, &clp->cl_state);
- break;
- default:
- dprintk("%s: failed to handle error %d for server %s\n",
- __func__, error, clp->cl_hostname);
- return error;
+ case 0:
+ break;
+ case -NFS4ERR_CB_PATH_DOWN:
+ nfs40_handle_cb_pathdown(clp);
+ break;
+ case -NFS4ERR_NO_GRACE:
+ nfs4_state_end_reclaim_reboot(clp);
+ break;
+ case -NFS4ERR_STALE_CLIENTID:
+ set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state);
+ nfs4_state_start_reclaim_reboot(clp);
+ break;
+ case -NFS4ERR_EXPIRED:
+ set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state);
+ nfs4_state_start_reclaim_nograce(clp);
+ break;
+ case -NFS4ERR_BADSESSION:
+ case -NFS4ERR_BADSLOT:
+ case -NFS4ERR_BAD_HIGH_SLOT:
+ case -NFS4ERR_DEADSESSION:
+ case -NFS4ERR_SEQ_FALSE_RETRY:
+ case -NFS4ERR_SEQ_MISORDERED:
+ set_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state);
+ /* Zero session reset errors */
+ break;
+ case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION:
+ set_bit(NFS4CLNT_BIND_CONN_TO_SESSION, &clp->cl_state);
+ break;
+ default:
+ dprintk("%s: failed to handle error %d for server %s\n",
+ __func__, error, clp->cl_hostname);
+ return error;
}
dprintk("%s: handled error %d for server %s\n", __func__, error,
clp->cl_hostname);
@@ -1839,12 +1867,13 @@
struct nfs4_state_owner *sp;
struct nfs_server *server;
struct rb_node *pos;
+ LIST_HEAD(freeme);
int status = 0;
restart:
rcu_read_lock();
list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) {
- nfs4_purge_state_owners(server);
+ nfs4_purge_state_owners(server, &freeme);
spin_lock(&clp->cl_lock);
for (pos = rb_first(&server->state_owners);
pos != NULL;
@@ -1873,12 +1902,13 @@
spin_unlock(&clp->cl_lock);
}
rcu_read_unlock();
+ nfs4_free_state_owners(&freeme);
return 0;
}
static int nfs4_check_lease(struct nfs_client *clp)
{
- struct rpc_cred *cred;
+ const struct cred *cred;
const struct nfs4_state_maintenance_ops *ops =
clp->cl_mvops->state_renewal_ops;
int status;
@@ -1886,9 +1916,7 @@
/* Is the client already known to have an expired lease? */
if (test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state))
return 0;
- spin_lock(&clp->cl_lock);
- cred = ops->get_state_renewal_cred_locked(clp);
- spin_unlock(&clp->cl_lock);
+ cred = ops->get_state_renewal_cred(clp);
if (cred == NULL) {
cred = nfs4_get_clid_cred(clp);
status = -ENOKEY;
@@ -1896,7 +1924,7 @@
goto out;
}
status = ops->renew_lease(clp, cred);
- put_rpccred(cred);
+ put_cred(cred);
if (status == -ETIMEDOUT) {
set_bit(NFS4CLNT_CHECK_LEASE, &clp->cl_state);
return 0;
@@ -1930,7 +1958,6 @@
return -EPERM;
case -EACCES:
case -NFS4ERR_DELAY:
- case -ETIMEDOUT:
case -EAGAIN:
ssleep(1);
break;
@@ -1956,7 +1983,7 @@
static int nfs4_establish_lease(struct nfs_client *clp)
{
- struct rpc_cred *cred;
+ const struct cred *cred;
const struct nfs4_state_recovery_ops *ops =
clp->cl_mvops->reboot_recovery_ops;
int status;
@@ -1968,7 +1995,7 @@
if (cred == NULL)
return -ENOENT;
status = ops->establish_clid(clp, cred);
- put_rpccred(cred);
+ put_cred(cred);
if (status != 0)
return status;
pnfs_destroy_all_layouts(clp);
@@ -2015,7 +2042,7 @@
*
* Returns zero or a negative NFS4ERR status code.
*/
-static int nfs4_try_migration(struct nfs_server *server, struct rpc_cred *cred)
+static int nfs4_try_migration(struct nfs_server *server, const struct cred *cred)
{
struct nfs_client *clp = server->nfs_client;
struct nfs4_fs_locations *locations = NULL;
@@ -2052,8 +2079,10 @@
}
status = nfs4_begin_drain_session(clp);
- if (status != 0)
- return status;
+ if (status != 0) {
+ result = status;
+ goto out;
+ }
status = nfs4_replace_transport(server, locations);
if (status != 0) {
@@ -2085,14 +2114,12 @@
const struct nfs4_state_maintenance_ops *ops =
clp->cl_mvops->state_renewal_ops;
struct nfs_server *server;
- struct rpc_cred *cred;
+ const struct cred *cred;
dprintk("%s: migration reported on \"%s\"\n", __func__,
clp->cl_hostname);
- spin_lock(&clp->cl_lock);
- cred = ops->get_state_renewal_cred_locked(clp);
- spin_unlock(&clp->cl_lock);
+ cred = ops->get_state_renewal_cred(clp);
if (cred == NULL)
return -NFS4ERR_NOENT;
@@ -2113,13 +2140,13 @@
rcu_read_unlock();
status = nfs4_try_migration(server, cred);
if (status < 0) {
- put_rpccred(cred);
+ put_cred(cred);
return status;
}
goto restart;
}
rcu_read_unlock();
- put_rpccred(cred);
+ put_cred(cred);
return 0;
}
@@ -2133,14 +2160,12 @@
const struct nfs4_state_maintenance_ops *ops =
clp->cl_mvops->state_renewal_ops;
struct nfs_server *server;
- struct rpc_cred *cred;
+ const struct cred *cred;
dprintk("%s: lease moved reported on \"%s\"\n", __func__,
clp->cl_hostname);
- spin_lock(&clp->cl_lock);
- cred = ops->get_state_renewal_cred_locked(clp);
- spin_unlock(&clp->cl_lock);
+ cred = ops->get_state_renewal_cred(clp);
if (cred == NULL)
return -NFS4ERR_NOENT;
@@ -2168,7 +2193,7 @@
rcu_read_unlock();
out:
- put_rpccred(cred);
+ put_cred(cred);
return 0;
}
@@ -2191,7 +2216,7 @@
const struct nfs4_state_recovery_ops *ops =
clp->cl_mvops->reboot_recovery_ops;
struct rpc_clnt *clnt;
- struct rpc_cred *cred;
+ const struct cred *cred;
int i, status;
dprintk("NFS: %s: testing '%s'\n", __func__, clp->cl_hostname);
@@ -2207,7 +2232,7 @@
goto out_unlock;
status = ops->detect_trunking(clp, result, cred);
- put_rpccred(cred);
+ put_cred(cred);
switch (status) {
case 0:
case -EINTR:
@@ -2338,8 +2363,7 @@
{
/* FIXME: For now, we destroy all layouts. */
pnfs_destroy_all_layouts(clp);
- /* FIXME: For now, we test all delegations+open state+locks. */
- nfs41_handle_some_state_revoked(clp);
+ nfs_test_expired_all_delegations(clp);
dprintk("%s: Recallable state revoked on server %s!\n", __func__,
clp->cl_hostname);
}
@@ -2398,7 +2422,7 @@
static int nfs4_reset_session(struct nfs_client *clp)
{
- struct rpc_cred *cred;
+ const struct cred *cred;
int status;
if (!nfs4_has_session(clp))
@@ -2436,14 +2460,13 @@
dprintk("%s: session reset was successful for server %s!\n",
__func__, clp->cl_hostname);
out:
- if (cred)
- put_rpccred(cred);
+ put_cred(cred);
return status;
}
static int nfs4_bind_conn_to_session(struct nfs_client *clp)
{
- struct rpc_cred *cred;
+ const struct cred *cred;
int ret;
if (!nfs4_has_session(clp))
@@ -2453,8 +2476,7 @@
return ret;
cred = nfs4_get_clid_cred(clp);
ret = nfs4_proc_bind_conn_to_session(clp, cred);
- if (cred)
- put_rpccred(cred);
+ put_cred(cred);
clear_bit(NFS4CLNT_BIND_CONN_TO_SESSION, &clp->cl_state);
switch (ret) {
case 0:
@@ -2566,7 +2588,7 @@
}
/* Now recover expired state... */
- if (test_and_clear_bit(NFS4CLNT_RECLAIM_NOGRACE, &clp->cl_state)) {
+ if (test_bit(NFS4CLNT_RECLAIM_NOGRACE, &clp->cl_state)) {
section = "reclaim nograce";
status = nfs4_do_reclaim(clp,
clp->cl_mvops->nograce_recovery_ops);
@@ -2574,6 +2596,7 @@
continue;
if (status < 0)
goto out_error;
+ clear_bit(NFS4CLNT_RECLAIM_NOGRACE, &clp->cl_state);
}
nfs4_end_drain_session(clp);
@@ -2592,7 +2615,7 @@
return;
if (test_and_set_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state) != 0)
return;
- } while (refcount_read(&clp->cl_count) > 1);
+ } while (refcount_read(&clp->cl_count) > 1 && !signalled());
goto out_drain;
out_error:
diff --git a/fs/nfs/nfs4super.c b/fs/nfs/nfs4super.c
index 6fb7cb6..04c5706 100644
--- a/fs/nfs/nfs4super.c
+++ b/fs/nfs/nfs4super.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (c) 2012 Bryan Schumaker <bjschuma@netapp.com>
*/
@@ -50,7 +51,7 @@
static const struct super_operations nfs4_sops = {
.alloc_inode = nfs_alloc_inode,
- .destroy_inode = nfs_destroy_inode,
+ .free_inode = nfs_free_inode,
.write_inode = nfs4_write_inode,
.drop_inode = nfs_drop_inode,
.statfs = nfs_statfs,
diff --git a/fs/nfs/nfs4trace.c b/fs/nfs/nfs4trace.c
index e9fb3e5..1a8f376 100644
--- a/fs/nfs/nfs4trace.c
+++ b/fs/nfs/nfs4trace.c
@@ -16,4 +16,12 @@
EXPORT_TRACEPOINT_SYMBOL_GPL(nfs4_pnfs_read);
EXPORT_TRACEPOINT_SYMBOL_GPL(nfs4_pnfs_write);
EXPORT_TRACEPOINT_SYMBOL_GPL(nfs4_pnfs_commit_ds);
+
+EXPORT_TRACEPOINT_SYMBOL_GPL(pnfs_mds_fallback_pg_init_read);
+EXPORT_TRACEPOINT_SYMBOL_GPL(pnfs_mds_fallback_pg_init_write);
+EXPORT_TRACEPOINT_SYMBOL_GPL(pnfs_mds_fallback_pg_get_mirror_count);
+EXPORT_TRACEPOINT_SYMBOL_GPL(pnfs_mds_fallback_read_done);
+EXPORT_TRACEPOINT_SYMBOL_GPL(pnfs_mds_fallback_write_done);
+EXPORT_TRACEPOINT_SYMBOL_GPL(pnfs_mds_fallback_read_pagelist);
+EXPORT_TRACEPOINT_SYMBOL_GPL(pnfs_mds_fallback_write_pagelist);
#endif
diff --git a/fs/nfs/nfs4trace.h b/fs/nfs/nfs4trace.h
index b1483b3..b2f395f 100644
--- a/fs/nfs/nfs4trace.h
+++ b/fs/nfs/nfs4trace.h
@@ -10,157 +10,302 @@
#include <linux/tracepoint.h>
+TRACE_DEFINE_ENUM(EPERM);
+TRACE_DEFINE_ENUM(ENOENT);
+TRACE_DEFINE_ENUM(EIO);
+TRACE_DEFINE_ENUM(ENXIO);
+TRACE_DEFINE_ENUM(EACCES);
+TRACE_DEFINE_ENUM(EEXIST);
+TRACE_DEFINE_ENUM(EXDEV);
+TRACE_DEFINE_ENUM(ENOTDIR);
+TRACE_DEFINE_ENUM(EISDIR);
+TRACE_DEFINE_ENUM(EFBIG);
+TRACE_DEFINE_ENUM(ENOSPC);
+TRACE_DEFINE_ENUM(EROFS);
+TRACE_DEFINE_ENUM(EMLINK);
+TRACE_DEFINE_ENUM(ENAMETOOLONG);
+TRACE_DEFINE_ENUM(ENOTEMPTY);
+TRACE_DEFINE_ENUM(EDQUOT);
+TRACE_DEFINE_ENUM(ESTALE);
+TRACE_DEFINE_ENUM(EBADHANDLE);
+TRACE_DEFINE_ENUM(EBADCOOKIE);
+TRACE_DEFINE_ENUM(ENOTSUPP);
+TRACE_DEFINE_ENUM(ETOOSMALL);
+TRACE_DEFINE_ENUM(EREMOTEIO);
+TRACE_DEFINE_ENUM(EBADTYPE);
+TRACE_DEFINE_ENUM(EAGAIN);
+TRACE_DEFINE_ENUM(ELOOP);
+TRACE_DEFINE_ENUM(EOPNOTSUPP);
+TRACE_DEFINE_ENUM(EDEADLK);
+TRACE_DEFINE_ENUM(ENOMEM);
+TRACE_DEFINE_ENUM(EKEYEXPIRED);
+TRACE_DEFINE_ENUM(ETIMEDOUT);
+TRACE_DEFINE_ENUM(ERESTARTSYS);
+TRACE_DEFINE_ENUM(ECONNREFUSED);
+TRACE_DEFINE_ENUM(ECONNRESET);
+TRACE_DEFINE_ENUM(ENETUNREACH);
+TRACE_DEFINE_ENUM(EHOSTUNREACH);
+TRACE_DEFINE_ENUM(EHOSTDOWN);
+TRACE_DEFINE_ENUM(EPIPE);
+TRACE_DEFINE_ENUM(EPFNOSUPPORT);
+TRACE_DEFINE_ENUM(EPROTONOSUPPORT);
+
+TRACE_DEFINE_ENUM(NFS4_OK);
+TRACE_DEFINE_ENUM(NFS4ERR_ACCESS);
+TRACE_DEFINE_ENUM(NFS4ERR_ATTRNOTSUPP);
+TRACE_DEFINE_ENUM(NFS4ERR_ADMIN_REVOKED);
+TRACE_DEFINE_ENUM(NFS4ERR_BACK_CHAN_BUSY);
+TRACE_DEFINE_ENUM(NFS4ERR_BADCHAR);
+TRACE_DEFINE_ENUM(NFS4ERR_BADHANDLE);
+TRACE_DEFINE_ENUM(NFS4ERR_BADIOMODE);
+TRACE_DEFINE_ENUM(NFS4ERR_BADLAYOUT);
+TRACE_DEFINE_ENUM(NFS4ERR_BADLABEL);
+TRACE_DEFINE_ENUM(NFS4ERR_BADNAME);
+TRACE_DEFINE_ENUM(NFS4ERR_BADOWNER);
+TRACE_DEFINE_ENUM(NFS4ERR_BADSESSION);
+TRACE_DEFINE_ENUM(NFS4ERR_BADSLOT);
+TRACE_DEFINE_ENUM(NFS4ERR_BADTYPE);
+TRACE_DEFINE_ENUM(NFS4ERR_BADXDR);
+TRACE_DEFINE_ENUM(NFS4ERR_BAD_COOKIE);
+TRACE_DEFINE_ENUM(NFS4ERR_BAD_HIGH_SLOT);
+TRACE_DEFINE_ENUM(NFS4ERR_BAD_RANGE);
+TRACE_DEFINE_ENUM(NFS4ERR_BAD_SEQID);
+TRACE_DEFINE_ENUM(NFS4ERR_BAD_SESSION_DIGEST);
+TRACE_DEFINE_ENUM(NFS4ERR_BAD_STATEID);
+TRACE_DEFINE_ENUM(NFS4ERR_CB_PATH_DOWN);
+TRACE_DEFINE_ENUM(NFS4ERR_CLID_INUSE);
+TRACE_DEFINE_ENUM(NFS4ERR_CLIENTID_BUSY);
+TRACE_DEFINE_ENUM(NFS4ERR_COMPLETE_ALREADY);
+TRACE_DEFINE_ENUM(NFS4ERR_CONN_NOT_BOUND_TO_SESSION);
+TRACE_DEFINE_ENUM(NFS4ERR_DEADLOCK);
+TRACE_DEFINE_ENUM(NFS4ERR_DEADSESSION);
+TRACE_DEFINE_ENUM(NFS4ERR_DELAY);
+TRACE_DEFINE_ENUM(NFS4ERR_DELEG_ALREADY_WANTED);
+TRACE_DEFINE_ENUM(NFS4ERR_DELEG_REVOKED);
+TRACE_DEFINE_ENUM(NFS4ERR_DENIED);
+TRACE_DEFINE_ENUM(NFS4ERR_DIRDELEG_UNAVAIL);
+TRACE_DEFINE_ENUM(NFS4ERR_DQUOT);
+TRACE_DEFINE_ENUM(NFS4ERR_ENCR_ALG_UNSUPP);
+TRACE_DEFINE_ENUM(NFS4ERR_EXIST);
+TRACE_DEFINE_ENUM(NFS4ERR_EXPIRED);
+TRACE_DEFINE_ENUM(NFS4ERR_FBIG);
+TRACE_DEFINE_ENUM(NFS4ERR_FHEXPIRED);
+TRACE_DEFINE_ENUM(NFS4ERR_FILE_OPEN);
+TRACE_DEFINE_ENUM(NFS4ERR_GRACE);
+TRACE_DEFINE_ENUM(NFS4ERR_HASH_ALG_UNSUPP);
+TRACE_DEFINE_ENUM(NFS4ERR_INVAL);
+TRACE_DEFINE_ENUM(NFS4ERR_IO);
+TRACE_DEFINE_ENUM(NFS4ERR_ISDIR);
+TRACE_DEFINE_ENUM(NFS4ERR_LAYOUTTRYLATER);
+TRACE_DEFINE_ENUM(NFS4ERR_LAYOUTUNAVAILABLE);
+TRACE_DEFINE_ENUM(NFS4ERR_LEASE_MOVED);
+TRACE_DEFINE_ENUM(NFS4ERR_LOCKED);
+TRACE_DEFINE_ENUM(NFS4ERR_LOCKS_HELD);
+TRACE_DEFINE_ENUM(NFS4ERR_LOCK_RANGE);
+TRACE_DEFINE_ENUM(NFS4ERR_MINOR_VERS_MISMATCH);
+TRACE_DEFINE_ENUM(NFS4ERR_MLINK);
+TRACE_DEFINE_ENUM(NFS4ERR_MOVED);
+TRACE_DEFINE_ENUM(NFS4ERR_NAMETOOLONG);
+TRACE_DEFINE_ENUM(NFS4ERR_NOENT);
+TRACE_DEFINE_ENUM(NFS4ERR_NOFILEHANDLE);
+TRACE_DEFINE_ENUM(NFS4ERR_NOMATCHING_LAYOUT);
+TRACE_DEFINE_ENUM(NFS4ERR_NOSPC);
+TRACE_DEFINE_ENUM(NFS4ERR_NOTDIR);
+TRACE_DEFINE_ENUM(NFS4ERR_NOTEMPTY);
+TRACE_DEFINE_ENUM(NFS4ERR_NOTSUPP);
+TRACE_DEFINE_ENUM(NFS4ERR_NOT_ONLY_OP);
+TRACE_DEFINE_ENUM(NFS4ERR_NOT_SAME);
+TRACE_DEFINE_ENUM(NFS4ERR_NO_GRACE);
+TRACE_DEFINE_ENUM(NFS4ERR_NXIO);
+TRACE_DEFINE_ENUM(NFS4ERR_OLD_STATEID);
+TRACE_DEFINE_ENUM(NFS4ERR_OPENMODE);
+TRACE_DEFINE_ENUM(NFS4ERR_OP_ILLEGAL);
+TRACE_DEFINE_ENUM(NFS4ERR_OP_NOT_IN_SESSION);
+TRACE_DEFINE_ENUM(NFS4ERR_PERM);
+TRACE_DEFINE_ENUM(NFS4ERR_PNFS_IO_HOLE);
+TRACE_DEFINE_ENUM(NFS4ERR_PNFS_NO_LAYOUT);
+TRACE_DEFINE_ENUM(NFS4ERR_RECALLCONFLICT);
+TRACE_DEFINE_ENUM(NFS4ERR_RECLAIM_BAD);
+TRACE_DEFINE_ENUM(NFS4ERR_RECLAIM_CONFLICT);
+TRACE_DEFINE_ENUM(NFS4ERR_REJECT_DELEG);
+TRACE_DEFINE_ENUM(NFS4ERR_REP_TOO_BIG);
+TRACE_DEFINE_ENUM(NFS4ERR_REP_TOO_BIG_TO_CACHE);
+TRACE_DEFINE_ENUM(NFS4ERR_REQ_TOO_BIG);
+TRACE_DEFINE_ENUM(NFS4ERR_RESOURCE);
+TRACE_DEFINE_ENUM(NFS4ERR_RESTOREFH);
+TRACE_DEFINE_ENUM(NFS4ERR_RETRY_UNCACHED_REP);
+TRACE_DEFINE_ENUM(NFS4ERR_RETURNCONFLICT);
+TRACE_DEFINE_ENUM(NFS4ERR_ROFS);
+TRACE_DEFINE_ENUM(NFS4ERR_SAME);
+TRACE_DEFINE_ENUM(NFS4ERR_SHARE_DENIED);
+TRACE_DEFINE_ENUM(NFS4ERR_SEQUENCE_POS);
+TRACE_DEFINE_ENUM(NFS4ERR_SEQ_FALSE_RETRY);
+TRACE_DEFINE_ENUM(NFS4ERR_SEQ_MISORDERED);
+TRACE_DEFINE_ENUM(NFS4ERR_SERVERFAULT);
+TRACE_DEFINE_ENUM(NFS4ERR_STALE);
+TRACE_DEFINE_ENUM(NFS4ERR_STALE_CLIENTID);
+TRACE_DEFINE_ENUM(NFS4ERR_STALE_STATEID);
+TRACE_DEFINE_ENUM(NFS4ERR_SYMLINK);
+TRACE_DEFINE_ENUM(NFS4ERR_TOOSMALL);
+TRACE_DEFINE_ENUM(NFS4ERR_TOO_MANY_OPS);
+TRACE_DEFINE_ENUM(NFS4ERR_UNKNOWN_LAYOUTTYPE);
+TRACE_DEFINE_ENUM(NFS4ERR_UNSAFE_COMPOUND);
+TRACE_DEFINE_ENUM(NFS4ERR_WRONGSEC);
+TRACE_DEFINE_ENUM(NFS4ERR_WRONG_CRED);
+TRACE_DEFINE_ENUM(NFS4ERR_WRONG_TYPE);
+TRACE_DEFINE_ENUM(NFS4ERR_XDEV);
+
#define show_nfsv4_errors(error) \
__print_symbolic(error, \
{ NFS4_OK, "OK" }, \
/* Mapped by nfs4_stat_to_errno() */ \
- { -EPERM, "EPERM" }, \
- { -ENOENT, "ENOENT" }, \
- { -EIO, "EIO" }, \
- { -ENXIO, "ENXIO" }, \
- { -EACCES, "EACCES" }, \
- { -EEXIST, "EEXIST" }, \
- { -EXDEV, "EXDEV" }, \
- { -ENOTDIR, "ENOTDIR" }, \
- { -EISDIR, "EISDIR" }, \
- { -EFBIG, "EFBIG" }, \
- { -ENOSPC, "ENOSPC" }, \
- { -EROFS, "EROFS" }, \
- { -EMLINK, "EMLINK" }, \
- { -ENAMETOOLONG, "ENAMETOOLONG" }, \
- { -ENOTEMPTY, "ENOTEMPTY" }, \
- { -EDQUOT, "EDQUOT" }, \
- { -ESTALE, "ESTALE" }, \
- { -EBADHANDLE, "EBADHANDLE" }, \
- { -EBADCOOKIE, "EBADCOOKIE" }, \
- { -ENOTSUPP, "ENOTSUPP" }, \
- { -ETOOSMALL, "ETOOSMALL" }, \
- { -EREMOTEIO, "EREMOTEIO" }, \
- { -EBADTYPE, "EBADTYPE" }, \
- { -EAGAIN, "EAGAIN" }, \
- { -ELOOP, "ELOOP" }, \
- { -EOPNOTSUPP, "EOPNOTSUPP" }, \
- { -EDEADLK, "EDEADLK" }, \
+ { EPERM, "EPERM" }, \
+ { ENOENT, "ENOENT" }, \
+ { EIO, "EIO" }, \
+ { ENXIO, "ENXIO" }, \
+ { EACCES, "EACCES" }, \
+ { EEXIST, "EEXIST" }, \
+ { EXDEV, "EXDEV" }, \
+ { ENOTDIR, "ENOTDIR" }, \
+ { EISDIR, "EISDIR" }, \
+ { EFBIG, "EFBIG" }, \
+ { ENOSPC, "ENOSPC" }, \
+ { EROFS, "EROFS" }, \
+ { EMLINK, "EMLINK" }, \
+ { ENAMETOOLONG, "ENAMETOOLONG" }, \
+ { ENOTEMPTY, "ENOTEMPTY" }, \
+ { EDQUOT, "EDQUOT" }, \
+ { ESTALE, "ESTALE" }, \
+ { EBADHANDLE, "EBADHANDLE" }, \
+ { EBADCOOKIE, "EBADCOOKIE" }, \
+ { ENOTSUPP, "ENOTSUPP" }, \
+ { ETOOSMALL, "ETOOSMALL" }, \
+ { EREMOTEIO, "EREMOTEIO" }, \
+ { EBADTYPE, "EBADTYPE" }, \
+ { EAGAIN, "EAGAIN" }, \
+ { ELOOP, "ELOOP" }, \
+ { EOPNOTSUPP, "EOPNOTSUPP" }, \
+ { EDEADLK, "EDEADLK" }, \
/* RPC errors */ \
- { -ENOMEM, "ENOMEM" }, \
- { -EKEYEXPIRED, "EKEYEXPIRED" }, \
- { -ETIMEDOUT, "ETIMEDOUT" }, \
- { -ERESTARTSYS, "ERESTARTSYS" }, \
- { -ECONNREFUSED, "ECONNREFUSED" }, \
- { -ECONNRESET, "ECONNRESET" }, \
- { -ENETUNREACH, "ENETUNREACH" }, \
- { -EHOSTUNREACH, "EHOSTUNREACH" }, \
- { -EHOSTDOWN, "EHOSTDOWN" }, \
- { -EPIPE, "EPIPE" }, \
- { -EPFNOSUPPORT, "EPFNOSUPPORT" }, \
- { -EPROTONOSUPPORT, "EPROTONOSUPPORT" }, \
+ { ENOMEM, "ENOMEM" }, \
+ { EKEYEXPIRED, "EKEYEXPIRED" }, \
+ { ETIMEDOUT, "ETIMEDOUT" }, \
+ { ERESTARTSYS, "ERESTARTSYS" }, \
+ { ECONNREFUSED, "ECONNREFUSED" }, \
+ { ECONNRESET, "ECONNRESET" }, \
+ { ENETUNREACH, "ENETUNREACH" }, \
+ { EHOSTUNREACH, "EHOSTUNREACH" }, \
+ { EHOSTDOWN, "EHOSTDOWN" }, \
+ { EPIPE, "EPIPE" }, \
+ { EPFNOSUPPORT, "EPFNOSUPPORT" }, \
+ { EPROTONOSUPPORT, "EPROTONOSUPPORT" }, \
/* NFSv4 native errors */ \
- { -NFS4ERR_ACCESS, "ACCESS" }, \
- { -NFS4ERR_ATTRNOTSUPP, "ATTRNOTSUPP" }, \
- { -NFS4ERR_ADMIN_REVOKED, "ADMIN_REVOKED" }, \
- { -NFS4ERR_BACK_CHAN_BUSY, "BACK_CHAN_BUSY" }, \
- { -NFS4ERR_BADCHAR, "BADCHAR" }, \
- { -NFS4ERR_BADHANDLE, "BADHANDLE" }, \
- { -NFS4ERR_BADIOMODE, "BADIOMODE" }, \
- { -NFS4ERR_BADLAYOUT, "BADLAYOUT" }, \
- { -NFS4ERR_BADLABEL, "BADLABEL" }, \
- { -NFS4ERR_BADNAME, "BADNAME" }, \
- { -NFS4ERR_BADOWNER, "BADOWNER" }, \
- { -NFS4ERR_BADSESSION, "BADSESSION" }, \
- { -NFS4ERR_BADSLOT, "BADSLOT" }, \
- { -NFS4ERR_BADTYPE, "BADTYPE" }, \
- { -NFS4ERR_BADXDR, "BADXDR" }, \
- { -NFS4ERR_BAD_COOKIE, "BAD_COOKIE" }, \
- { -NFS4ERR_BAD_HIGH_SLOT, "BAD_HIGH_SLOT" }, \
- { -NFS4ERR_BAD_RANGE, "BAD_RANGE" }, \
- { -NFS4ERR_BAD_SEQID, "BAD_SEQID" }, \
- { -NFS4ERR_BAD_SESSION_DIGEST, "BAD_SESSION_DIGEST" }, \
- { -NFS4ERR_BAD_STATEID, "BAD_STATEID" }, \
- { -NFS4ERR_CB_PATH_DOWN, "CB_PATH_DOWN" }, \
- { -NFS4ERR_CLID_INUSE, "CLID_INUSE" }, \
- { -NFS4ERR_CLIENTID_BUSY, "CLIENTID_BUSY" }, \
- { -NFS4ERR_COMPLETE_ALREADY, "COMPLETE_ALREADY" }, \
- { -NFS4ERR_CONN_NOT_BOUND_TO_SESSION, \
+ { NFS4ERR_ACCESS, "ACCESS" }, \
+ { NFS4ERR_ATTRNOTSUPP, "ATTRNOTSUPP" }, \
+ { NFS4ERR_ADMIN_REVOKED, "ADMIN_REVOKED" }, \
+ { NFS4ERR_BACK_CHAN_BUSY, "BACK_CHAN_BUSY" }, \
+ { NFS4ERR_BADCHAR, "BADCHAR" }, \
+ { NFS4ERR_BADHANDLE, "BADHANDLE" }, \
+ { NFS4ERR_BADIOMODE, "BADIOMODE" }, \
+ { NFS4ERR_BADLAYOUT, "BADLAYOUT" }, \
+ { NFS4ERR_BADLABEL, "BADLABEL" }, \
+ { NFS4ERR_BADNAME, "BADNAME" }, \
+ { NFS4ERR_BADOWNER, "BADOWNER" }, \
+ { NFS4ERR_BADSESSION, "BADSESSION" }, \
+ { NFS4ERR_BADSLOT, "BADSLOT" }, \
+ { NFS4ERR_BADTYPE, "BADTYPE" }, \
+ { NFS4ERR_BADXDR, "BADXDR" }, \
+ { NFS4ERR_BAD_COOKIE, "BAD_COOKIE" }, \
+ { NFS4ERR_BAD_HIGH_SLOT, "BAD_HIGH_SLOT" }, \
+ { NFS4ERR_BAD_RANGE, "BAD_RANGE" }, \
+ { NFS4ERR_BAD_SEQID, "BAD_SEQID" }, \
+ { NFS4ERR_BAD_SESSION_DIGEST, "BAD_SESSION_DIGEST" }, \
+ { NFS4ERR_BAD_STATEID, "BAD_STATEID" }, \
+ { NFS4ERR_CB_PATH_DOWN, "CB_PATH_DOWN" }, \
+ { NFS4ERR_CLID_INUSE, "CLID_INUSE" }, \
+ { NFS4ERR_CLIENTID_BUSY, "CLIENTID_BUSY" }, \
+ { NFS4ERR_COMPLETE_ALREADY, "COMPLETE_ALREADY" }, \
+ { NFS4ERR_CONN_NOT_BOUND_TO_SESSION, \
"CONN_NOT_BOUND_TO_SESSION" }, \
- { -NFS4ERR_DEADLOCK, "DEADLOCK" }, \
- { -NFS4ERR_DEADSESSION, "DEAD_SESSION" }, \
- { -NFS4ERR_DELAY, "DELAY" }, \
- { -NFS4ERR_DELEG_ALREADY_WANTED, \
+ { NFS4ERR_DEADLOCK, "DEADLOCK" }, \
+ { NFS4ERR_DEADSESSION, "DEAD_SESSION" }, \
+ { NFS4ERR_DELAY, "DELAY" }, \
+ { NFS4ERR_DELEG_ALREADY_WANTED, \
"DELEG_ALREADY_WANTED" }, \
- { -NFS4ERR_DELEG_REVOKED, "DELEG_REVOKED" }, \
- { -NFS4ERR_DENIED, "DENIED" }, \
- { -NFS4ERR_DIRDELEG_UNAVAIL, "DIRDELEG_UNAVAIL" }, \
- { -NFS4ERR_DQUOT, "DQUOT" }, \
- { -NFS4ERR_ENCR_ALG_UNSUPP, "ENCR_ALG_UNSUPP" }, \
- { -NFS4ERR_EXIST, "EXIST" }, \
- { -NFS4ERR_EXPIRED, "EXPIRED" }, \
- { -NFS4ERR_FBIG, "FBIG" }, \
- { -NFS4ERR_FHEXPIRED, "FHEXPIRED" }, \
- { -NFS4ERR_FILE_OPEN, "FILE_OPEN" }, \
- { -NFS4ERR_GRACE, "GRACE" }, \
- { -NFS4ERR_HASH_ALG_UNSUPP, "HASH_ALG_UNSUPP" }, \
- { -NFS4ERR_INVAL, "INVAL" }, \
- { -NFS4ERR_IO, "IO" }, \
- { -NFS4ERR_ISDIR, "ISDIR" }, \
- { -NFS4ERR_LAYOUTTRYLATER, "LAYOUTTRYLATER" }, \
- { -NFS4ERR_LAYOUTUNAVAILABLE, "LAYOUTUNAVAILABLE" }, \
- { -NFS4ERR_LEASE_MOVED, "LEASE_MOVED" }, \
- { -NFS4ERR_LOCKED, "LOCKED" }, \
- { -NFS4ERR_LOCKS_HELD, "LOCKS_HELD" }, \
- { -NFS4ERR_LOCK_RANGE, "LOCK_RANGE" }, \
- { -NFS4ERR_MINOR_VERS_MISMATCH, "MINOR_VERS_MISMATCH" }, \
- { -NFS4ERR_MLINK, "MLINK" }, \
- { -NFS4ERR_MOVED, "MOVED" }, \
- { -NFS4ERR_NAMETOOLONG, "NAMETOOLONG" }, \
- { -NFS4ERR_NOENT, "NOENT" }, \
- { -NFS4ERR_NOFILEHANDLE, "NOFILEHANDLE" }, \
- { -NFS4ERR_NOMATCHING_LAYOUT, "NOMATCHING_LAYOUT" }, \
- { -NFS4ERR_NOSPC, "NOSPC" }, \
- { -NFS4ERR_NOTDIR, "NOTDIR" }, \
- { -NFS4ERR_NOTEMPTY, "NOTEMPTY" }, \
- { -NFS4ERR_NOTSUPP, "NOTSUPP" }, \
- { -NFS4ERR_NOT_ONLY_OP, "NOT_ONLY_OP" }, \
- { -NFS4ERR_NOT_SAME, "NOT_SAME" }, \
- { -NFS4ERR_NO_GRACE, "NO_GRACE" }, \
- { -NFS4ERR_NXIO, "NXIO" }, \
- { -NFS4ERR_OLD_STATEID, "OLD_STATEID" }, \
- { -NFS4ERR_OPENMODE, "OPENMODE" }, \
- { -NFS4ERR_OP_ILLEGAL, "OP_ILLEGAL" }, \
- { -NFS4ERR_OP_NOT_IN_SESSION, "OP_NOT_IN_SESSION" }, \
- { -NFS4ERR_PERM, "PERM" }, \
- { -NFS4ERR_PNFS_IO_HOLE, "PNFS_IO_HOLE" }, \
- { -NFS4ERR_PNFS_NO_LAYOUT, "PNFS_NO_LAYOUT" }, \
- { -NFS4ERR_RECALLCONFLICT, "RECALLCONFLICT" }, \
- { -NFS4ERR_RECLAIM_BAD, "RECLAIM_BAD" }, \
- { -NFS4ERR_RECLAIM_CONFLICT, "RECLAIM_CONFLICT" }, \
- { -NFS4ERR_REJECT_DELEG, "REJECT_DELEG" }, \
- { -NFS4ERR_REP_TOO_BIG, "REP_TOO_BIG" }, \
- { -NFS4ERR_REP_TOO_BIG_TO_CACHE, \
+ { NFS4ERR_DELEG_REVOKED, "DELEG_REVOKED" }, \
+ { NFS4ERR_DENIED, "DENIED" }, \
+ { NFS4ERR_DIRDELEG_UNAVAIL, "DIRDELEG_UNAVAIL" }, \
+ { NFS4ERR_DQUOT, "DQUOT" }, \
+ { NFS4ERR_ENCR_ALG_UNSUPP, "ENCR_ALG_UNSUPP" }, \
+ { NFS4ERR_EXIST, "EXIST" }, \
+ { NFS4ERR_EXPIRED, "EXPIRED" }, \
+ { NFS4ERR_FBIG, "FBIG" }, \
+ { NFS4ERR_FHEXPIRED, "FHEXPIRED" }, \
+ { NFS4ERR_FILE_OPEN, "FILE_OPEN" }, \
+ { NFS4ERR_GRACE, "GRACE" }, \
+ { NFS4ERR_HASH_ALG_UNSUPP, "HASH_ALG_UNSUPP" }, \
+ { NFS4ERR_INVAL, "INVAL" }, \
+ { NFS4ERR_IO, "IO" }, \
+ { NFS4ERR_ISDIR, "ISDIR" }, \
+ { NFS4ERR_LAYOUTTRYLATER, "LAYOUTTRYLATER" }, \
+ { NFS4ERR_LAYOUTUNAVAILABLE, "LAYOUTUNAVAILABLE" }, \
+ { NFS4ERR_LEASE_MOVED, "LEASE_MOVED" }, \
+ { NFS4ERR_LOCKED, "LOCKED" }, \
+ { NFS4ERR_LOCKS_HELD, "LOCKS_HELD" }, \
+ { NFS4ERR_LOCK_RANGE, "LOCK_RANGE" }, \
+ { NFS4ERR_MINOR_VERS_MISMATCH, "MINOR_VERS_MISMATCH" }, \
+ { NFS4ERR_MLINK, "MLINK" }, \
+ { NFS4ERR_MOVED, "MOVED" }, \
+ { NFS4ERR_NAMETOOLONG, "NAMETOOLONG" }, \
+ { NFS4ERR_NOENT, "NOENT" }, \
+ { NFS4ERR_NOFILEHANDLE, "NOFILEHANDLE" }, \
+ { NFS4ERR_NOMATCHING_LAYOUT, "NOMATCHING_LAYOUT" }, \
+ { NFS4ERR_NOSPC, "NOSPC" }, \
+ { NFS4ERR_NOTDIR, "NOTDIR" }, \
+ { NFS4ERR_NOTEMPTY, "NOTEMPTY" }, \
+ { NFS4ERR_NOTSUPP, "NOTSUPP" }, \
+ { NFS4ERR_NOT_ONLY_OP, "NOT_ONLY_OP" }, \
+ { NFS4ERR_NOT_SAME, "NOT_SAME" }, \
+ { NFS4ERR_NO_GRACE, "NO_GRACE" }, \
+ { NFS4ERR_NXIO, "NXIO" }, \
+ { NFS4ERR_OLD_STATEID, "OLD_STATEID" }, \
+ { NFS4ERR_OPENMODE, "OPENMODE" }, \
+ { NFS4ERR_OP_ILLEGAL, "OP_ILLEGAL" }, \
+ { NFS4ERR_OP_NOT_IN_SESSION, "OP_NOT_IN_SESSION" }, \
+ { NFS4ERR_PERM, "PERM" }, \
+ { NFS4ERR_PNFS_IO_HOLE, "PNFS_IO_HOLE" }, \
+ { NFS4ERR_PNFS_NO_LAYOUT, "PNFS_NO_LAYOUT" }, \
+ { NFS4ERR_RECALLCONFLICT, "RECALLCONFLICT" }, \
+ { NFS4ERR_RECLAIM_BAD, "RECLAIM_BAD" }, \
+ { NFS4ERR_RECLAIM_CONFLICT, "RECLAIM_CONFLICT" }, \
+ { NFS4ERR_REJECT_DELEG, "REJECT_DELEG" }, \
+ { NFS4ERR_REP_TOO_BIG, "REP_TOO_BIG" }, \
+ { NFS4ERR_REP_TOO_BIG_TO_CACHE, \
"REP_TOO_BIG_TO_CACHE" }, \
- { -NFS4ERR_REQ_TOO_BIG, "REQ_TOO_BIG" }, \
- { -NFS4ERR_RESOURCE, "RESOURCE" }, \
- { -NFS4ERR_RESTOREFH, "RESTOREFH" }, \
- { -NFS4ERR_RETRY_UNCACHED_REP, "RETRY_UNCACHED_REP" }, \
- { -NFS4ERR_RETURNCONFLICT, "RETURNCONFLICT" }, \
- { -NFS4ERR_ROFS, "ROFS" }, \
- { -NFS4ERR_SAME, "SAME" }, \
- { -NFS4ERR_SHARE_DENIED, "SHARE_DENIED" }, \
- { -NFS4ERR_SEQUENCE_POS, "SEQUENCE_POS" }, \
- { -NFS4ERR_SEQ_FALSE_RETRY, "SEQ_FALSE_RETRY" }, \
- { -NFS4ERR_SEQ_MISORDERED, "SEQ_MISORDERED" }, \
- { -NFS4ERR_SERVERFAULT, "SERVERFAULT" }, \
- { -NFS4ERR_STALE, "STALE" }, \
- { -NFS4ERR_STALE_CLIENTID, "STALE_CLIENTID" }, \
- { -NFS4ERR_STALE_STATEID, "STALE_STATEID" }, \
- { -NFS4ERR_SYMLINK, "SYMLINK" }, \
- { -NFS4ERR_TOOSMALL, "TOOSMALL" }, \
- { -NFS4ERR_TOO_MANY_OPS, "TOO_MANY_OPS" }, \
- { -NFS4ERR_UNKNOWN_LAYOUTTYPE, "UNKNOWN_LAYOUTTYPE" }, \
- { -NFS4ERR_UNSAFE_COMPOUND, "UNSAFE_COMPOUND" }, \
- { -NFS4ERR_WRONGSEC, "WRONGSEC" }, \
- { -NFS4ERR_WRONG_CRED, "WRONG_CRED" }, \
- { -NFS4ERR_WRONG_TYPE, "WRONG_TYPE" }, \
- { -NFS4ERR_XDEV, "XDEV" })
+ { NFS4ERR_REQ_TOO_BIG, "REQ_TOO_BIG" }, \
+ { NFS4ERR_RESOURCE, "RESOURCE" }, \
+ { NFS4ERR_RESTOREFH, "RESTOREFH" }, \
+ { NFS4ERR_RETRY_UNCACHED_REP, "RETRY_UNCACHED_REP" }, \
+ { NFS4ERR_RETURNCONFLICT, "RETURNCONFLICT" }, \
+ { NFS4ERR_ROFS, "ROFS" }, \
+ { NFS4ERR_SAME, "SAME" }, \
+ { NFS4ERR_SHARE_DENIED, "SHARE_DENIED" }, \
+ { NFS4ERR_SEQUENCE_POS, "SEQUENCE_POS" }, \
+ { NFS4ERR_SEQ_FALSE_RETRY, "SEQ_FALSE_RETRY" }, \
+ { NFS4ERR_SEQ_MISORDERED, "SEQ_MISORDERED" }, \
+ { NFS4ERR_SERVERFAULT, "SERVERFAULT" }, \
+ { NFS4ERR_STALE, "STALE" }, \
+ { NFS4ERR_STALE_CLIENTID, "STALE_CLIENTID" }, \
+ { NFS4ERR_STALE_STATEID, "STALE_STATEID" }, \
+ { NFS4ERR_SYMLINK, "SYMLINK" }, \
+ { NFS4ERR_TOOSMALL, "TOOSMALL" }, \
+ { NFS4ERR_TOO_MANY_OPS, "TOO_MANY_OPS" }, \
+ { NFS4ERR_UNKNOWN_LAYOUTTYPE, "UNKNOWN_LAYOUTTYPE" }, \
+ { NFS4ERR_UNSAFE_COMPOUND, "UNSAFE_COMPOUND" }, \
+ { NFS4ERR_WRONGSEC, "WRONGSEC" }, \
+ { NFS4ERR_WRONG_CRED, "WRONG_CRED" }, \
+ { NFS4ERR_WRONG_TYPE, "WRONG_TYPE" }, \
+ { NFS4ERR_XDEV, "XDEV" })
#define show_open_flags(flags) \
__print_flags(flags, "|", \
@@ -203,7 +348,7 @@
TP_STRUCT__entry(
__string(dstaddr, clp->cl_hostname)
- __field(int, error)
+ __field(unsigned long, error)
),
TP_fast_assign(
@@ -212,8 +357,8 @@
),
TP_printk(
- "error=%d (%s) dstaddr=%s",
- __entry->error,
+ "error=%ld (%s) dstaddr=%s",
+ -__entry->error,
show_nfsv4_errors(__entry->error),
__get_str(dstaddr)
)
@@ -275,7 +420,7 @@
__field(unsigned int, highest_slotid)
__field(unsigned int, target_highest_slotid)
__field(unsigned int, status_flags)
- __field(int, error)
+ __field(unsigned long, error)
),
TP_fast_assign(
@@ -290,10 +435,10 @@
__entry->error = res->sr_status;
),
TP_printk(
- "error=%d (%s) session=0x%08x slot_nr=%u seq_nr=%u "
+ "error=%ld (%s) session=0x%08x slot_nr=%u seq_nr=%u "
"highest_slotid=%u target_highest_slotid=%u "
"status_flags=%u (%s)",
- __entry->error,
+ -__entry->error,
show_nfsv4_errors(__entry->error),
__entry->session,
__entry->slot_nr,
@@ -322,7 +467,7 @@
__field(unsigned int, seq_nr)
__field(unsigned int, highest_slotid)
__field(unsigned int, cachethis)
- __field(int, error)
+ __field(unsigned long, error)
),
TP_fast_assign(
@@ -331,13 +476,13 @@
__entry->seq_nr = args->csa_sequenceid;
__entry->highest_slotid = args->csa_highestslotid;
__entry->cachethis = args->csa_cachethis;
- __entry->error = -be32_to_cpu(status);
+ __entry->error = be32_to_cpu(status);
),
TP_printk(
- "error=%d (%s) session=0x%08x slot_nr=%u seq_nr=%u "
+ "error=%ld (%s) session=0x%08x slot_nr=%u seq_nr=%u "
"highest_slotid=%u",
- __entry->error,
+ -__entry->error,
show_nfsv4_errors(__entry->error),
__entry->session,
__entry->slot_nr,
@@ -345,6 +490,44 @@
__entry->highest_slotid
)
);
+
+TRACE_EVENT(nfs4_cb_seqid_err,
+ TP_PROTO(
+ const struct cb_sequenceargs *args,
+ __be32 status
+ ),
+ TP_ARGS(args, status),
+
+ TP_STRUCT__entry(
+ __field(unsigned int, session)
+ __field(unsigned int, slot_nr)
+ __field(unsigned int, seq_nr)
+ __field(unsigned int, highest_slotid)
+ __field(unsigned int, cachethis)
+ __field(unsigned long, error)
+ ),
+
+ TP_fast_assign(
+ __entry->session = nfs_session_id_hash(&args->csa_sessionid);
+ __entry->slot_nr = args->csa_slotid;
+ __entry->seq_nr = args->csa_sequenceid;
+ __entry->highest_slotid = args->csa_highestslotid;
+ __entry->cachethis = args->csa_cachethis;
+ __entry->error = be32_to_cpu(status);
+ ),
+
+ TP_printk(
+ "error=%ld (%s) session=0x%08x slot_nr=%u seq_nr=%u "
+ "highest_slotid=%u",
+ -__entry->error,
+ show_nfsv4_errors(__entry->error),
+ __entry->session,
+ __entry->slot_nr,
+ __entry->seq_nr,
+ __entry->highest_slotid
+ )
+);
+
#endif /* CONFIG_NFS_V4_1 */
TRACE_EVENT(nfs4_setup_sequence,
@@ -379,6 +562,42 @@
)
);
+TRACE_EVENT(nfs4_xdr_status,
+ TP_PROTO(
+ const struct xdr_stream *xdr,
+ u32 op,
+ int error
+ ),
+
+ TP_ARGS(xdr, op, error),
+
+ TP_STRUCT__entry(
+ __field(unsigned int, task_id)
+ __field(unsigned int, client_id)
+ __field(u32, xid)
+ __field(u32, op)
+ __field(unsigned long, error)
+ ),
+
+ TP_fast_assign(
+ const struct rpc_rqst *rqstp = xdr->rqst;
+ const struct rpc_task *task = rqstp->rq_task;
+
+ __entry->task_id = task->tk_pid;
+ __entry->client_id = task->tk_client->cl_clid;
+ __entry->xid = be32_to_cpu(rqstp->rq_xid);
+ __entry->op = op;
+ __entry->error = error;
+ ),
+
+ TP_printk(
+ "task:%u@%d xid=0x%08x error=%ld (%s) operation=%u",
+ __entry->task_id, __entry->client_id, __entry->xid,
+ -__entry->error, show_nfsv4_errors(__entry->error),
+ __entry->op
+ )
+);
+
DECLARE_EVENT_CLASS(nfs4_open_event,
TP_PROTO(
const struct nfs_open_context *ctx,
@@ -389,7 +608,7 @@
TP_ARGS(ctx, flags, error),
TP_STRUCT__entry(
- __field(int, error)
+ __field(unsigned long, error)
__field(unsigned int, flags)
__field(unsigned int, fmode)
__field(dev_t, dev)
@@ -407,7 +626,7 @@
const struct nfs4_state *state = ctx->state;
const struct inode *inode = NULL;
- __entry->error = error;
+ __entry->error = -error;
__entry->flags = flags;
__entry->fmode = (__force unsigned int)ctx->mode;
__entry->dev = ctx->dentry->d_sb->s_dev;
@@ -439,11 +658,11 @@
),
TP_printk(
- "error=%d (%s) flags=%d (%s) fmode=%s "
+ "error=%ld (%s) flags=%d (%s) fmode=%s "
"fileid=%02x:%02x:%llu fhandle=0x%08x "
"name=%02x:%02x:%llu/%s stateid=%d:0x%08x "
"openstateid=%d:0x%08x",
- __entry->error,
+ -__entry->error,
show_nfsv4_errors(__entry->error),
__entry->flags,
show_open_flags(__entry->flags),
@@ -525,7 +744,7 @@
__field(u32, fhandle)
__field(u64, fileid)
__field(unsigned int, fmode)
- __field(int, error)
+ __field(unsigned long, error)
__field(int, stateid_seq)
__field(u32, stateid_hash)
),
@@ -545,9 +764,9 @@
),
TP_printk(
- "error=%d (%s) fmode=%s fileid=%02x:%02x:%llu "
+ "error=%ld (%s) fmode=%s fileid=%02x:%02x:%llu "
"fhandle=0x%08x openstateid=%d:0x%08x",
- __entry->error,
+ -__entry->error,
show_nfsv4_errors(__entry->error),
__entry->fmode ? show_fmode_flags(__entry->fmode) :
"closed",
@@ -558,6 +777,13 @@
)
);
+TRACE_DEFINE_ENUM(F_GETLK);
+TRACE_DEFINE_ENUM(F_SETLK);
+TRACE_DEFINE_ENUM(F_SETLKW);
+TRACE_DEFINE_ENUM(F_RDLCK);
+TRACE_DEFINE_ENUM(F_WRLCK);
+TRACE_DEFINE_ENUM(F_UNLCK);
+
#define show_lock_cmd(type) \
__print_symbolic((int)type, \
{ F_GETLK, "GETLK" }, \
@@ -580,7 +806,7 @@
TP_ARGS(request, state, cmd, error),
TP_STRUCT__entry(
- __field(int, error)
+ __field(unsigned long, error)
__field(int, cmd)
__field(char, type)
__field(loff_t, start)
@@ -610,10 +836,10 @@
),
TP_printk(
- "error=%d (%s) cmd=%s:%s range=%lld:%lld "
+ "error=%ld (%s) cmd=%s:%s range=%lld:%lld "
"fileid=%02x:%02x:%llu fhandle=0x%08x "
"stateid=%d:0x%08x",
- __entry->error,
+ -__entry->error,
show_nfsv4_errors(__entry->error),
show_lock_cmd(__entry->cmd),
show_lock_type(__entry->type),
@@ -650,7 +876,7 @@
TP_ARGS(request, state, lockstateid, cmd, error),
TP_STRUCT__entry(
- __field(int, error)
+ __field(unsigned long, error)
__field(int, cmd)
__field(char, type)
__field(loff_t, start)
@@ -686,10 +912,10 @@
),
TP_printk(
- "error=%d (%s) cmd=%s:%s range=%lld:%lld "
+ "error=%ld (%s) cmd=%s:%s range=%lld:%lld "
"fileid=%02x:%02x:%llu fhandle=0x%08x "
"stateid=%d:0x%08x lockstateid=%d:0x%08x",
- __entry->error,
+ -__entry->error,
show_nfsv4_errors(__entry->error),
show_lock_cmd(__entry->cmd),
show_lock_type(__entry->type),
@@ -755,7 +981,7 @@
TP_STRUCT__entry(
__field(dev_t, dev)
__field(u32, fhandle)
- __field(int, error)
+ __field(unsigned long, error)
__field(int, stateid_seq)
__field(u32, stateid_hash)
),
@@ -771,9 +997,9 @@
),
TP_printk(
- "error=%d (%s) dev=%02x:%02x fhandle=0x%08x "
+ "error=%ld (%s) dev=%02x:%02x fhandle=0x%08x "
"stateid=%d:0x%08x",
- __entry->error,
+ -__entry->error,
show_nfsv4_errors(__entry->error),
MAJOR(__entry->dev), MINOR(__entry->dev),
__entry->fhandle,
@@ -792,7 +1018,7 @@
TP_ARGS(state, lsp, error),
TP_STRUCT__entry(
- __field(int, error)
+ __field(unsigned long, error)
__field(dev_t, dev)
__field(u32, fhandle)
__field(u64, fileid)
@@ -814,9 +1040,9 @@
),
TP_printk(
- "error=%d (%s) fileid=%02x:%02x:%llu fhandle=0x%08x "
+ "error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x "
"stateid=%d:0x%08x",
- __entry->error,
+ -__entry->error,
show_nfsv4_errors(__entry->error),
MAJOR(__entry->dev), MINOR(__entry->dev),
(unsigned long long)__entry->fileid,
@@ -849,7 +1075,7 @@
TP_STRUCT__entry(
__field(dev_t, dev)
- __field(int, error)
+ __field(unsigned long, error)
__field(u64, dir)
__string(name, name->name)
),
@@ -857,13 +1083,13 @@
TP_fast_assign(
__entry->dev = dir->i_sb->s_dev;
__entry->dir = NFS_FILEID(dir);
- __entry->error = error;
+ __entry->error = -error;
__assign_str(name, name->name);
),
TP_printk(
- "error=%d (%s) name=%02x:%02x:%llu/%s",
- __entry->error,
+ "error=%ld (%s) name=%02x:%02x:%llu/%s",
+ -__entry->error,
show_nfsv4_errors(__entry->error),
MAJOR(__entry->dev), MINOR(__entry->dev),
(unsigned long long)__entry->dir,
@@ -899,7 +1125,7 @@
TP_STRUCT__entry(
__field(dev_t, dev)
__field(u64, ino)
- __field(int, error)
+ __field(unsigned long, error)
),
TP_fast_assign(
@@ -909,8 +1135,8 @@
),
TP_printk(
- "error=%d (%s) inode=%02x:%02x:%llu",
- __entry->error,
+ "error=%ld (%s) inode=%02x:%02x:%llu",
+ -__entry->error,
show_nfsv4_errors(__entry->error),
MAJOR(__entry->dev), MINOR(__entry->dev),
(unsigned long long)__entry->ino
@@ -930,7 +1156,7 @@
TP_STRUCT__entry(
__field(dev_t, dev)
- __field(int, error)
+ __field(unsigned long, error)
__field(u64, olddir)
__string(oldname, oldname->name)
__field(u64, newdir)
@@ -947,9 +1173,9 @@
),
TP_printk(
- "error=%d (%s) oldname=%02x:%02x:%llu/%s "
+ "error=%ld (%s) oldname=%02x:%02x:%llu/%s "
"newname=%02x:%02x:%llu/%s",
- __entry->error,
+ -__entry->error,
show_nfsv4_errors(__entry->error),
MAJOR(__entry->dev), MINOR(__entry->dev),
(unsigned long long)__entry->olddir,
@@ -972,19 +1198,19 @@
__field(dev_t, dev)
__field(u32, fhandle)
__field(u64, fileid)
- __field(int, error)
+ __field(unsigned long, error)
),
TP_fast_assign(
__entry->dev = inode->i_sb->s_dev;
__entry->fileid = NFS_FILEID(inode);
__entry->fhandle = nfs_fhandle_hash(NFS_FH(inode));
- __entry->error = error;
+ __entry->error = error < 0 ? -error : 0;
),
TP_printk(
- "error=%d (%s) fileid=%02x:%02x:%llu fhandle=0x%08x",
- __entry->error,
+ "error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x",
+ -__entry->error,
show_nfsv4_errors(__entry->error),
MAJOR(__entry->dev), MINOR(__entry->dev),
(unsigned long long)__entry->fileid,
@@ -1023,7 +1249,7 @@
__field(dev_t, dev)
__field(u32, fhandle)
__field(u64, fileid)
- __field(int, error)
+ __field(unsigned long, error)
__field(int, stateid_seq)
__field(u32, stateid_hash)
),
@@ -1040,9 +1266,9 @@
),
TP_printk(
- "error=%d (%s) fileid=%02x:%02x:%llu fhandle=0x%08x "
+ "error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x "
"stateid=%d:0x%08x",
- __entry->error,
+ -__entry->error,
show_nfsv4_errors(__entry->error),
MAJOR(__entry->dev), MINOR(__entry->dev),
(unsigned long long)__entry->fileid,
@@ -1080,7 +1306,7 @@
__field(u32, fhandle)
__field(u64, fileid)
__field(unsigned int, valid)
- __field(int, error)
+ __field(unsigned long, error)
),
TP_fast_assign(
@@ -1092,9 +1318,9 @@
),
TP_printk(
- "error=%d (%s) fileid=%02x:%02x:%llu fhandle=0x%08x "
+ "error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x "
"valid=%s",
- __entry->error,
+ -__entry->error,
show_nfsv4_errors(__entry->error),
MAJOR(__entry->dev), MINOR(__entry->dev),
(unsigned long long)__entry->fileid,
@@ -1127,7 +1353,7 @@
TP_ARGS(clp, fhandle, inode, error),
TP_STRUCT__entry(
- __field(int, error)
+ __field(unsigned long, error)
__field(dev_t, dev)
__field(u32, fhandle)
__field(u64, fileid)
@@ -1148,9 +1374,9 @@
),
TP_printk(
- "error=%d (%s) fileid=%02x:%02x:%llu fhandle=0x%08x "
+ "error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x "
"dstaddr=%s",
- __entry->error,
+ -__entry->error,
show_nfsv4_errors(__entry->error),
MAJOR(__entry->dev), MINOR(__entry->dev),
(unsigned long long)__entry->fileid,
@@ -1182,7 +1408,7 @@
TP_ARGS(clp, fhandle, inode, stateid, error),
TP_STRUCT__entry(
- __field(int, error)
+ __field(unsigned long, error)
__field(dev_t, dev)
__field(u32, fhandle)
__field(u64, fileid)
@@ -1209,9 +1435,9 @@
),
TP_printk(
- "error=%d (%s) fileid=%02x:%02x:%llu fhandle=0x%08x "
+ "error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x "
"stateid=%d:0x%08x dstaddr=%s",
- __entry->error,
+ -__entry->error,
show_nfsv4_errors(__entry->error),
MAJOR(__entry->dev), MINOR(__entry->dev),
(unsigned long long)__entry->fileid,
@@ -1245,7 +1471,7 @@
TP_ARGS(name, len, id, error),
TP_STRUCT__entry(
- __field(int, error)
+ __field(unsigned long, error)
__field(u32, id)
__dynamic_array(char, name, len > 0 ? len + 1 : 1)
),
@@ -1260,8 +1486,8 @@
),
TP_printk(
- "error=%d id=%u name=%s",
- __entry->error,
+ "error=%ld (%s) id=%u name=%s",
+ -__entry->error, show_nfsv4_errors(__entry->error),
__entry->id,
__get_str(name)
)
@@ -1294,7 +1520,7 @@
__field(u64, fileid)
__field(loff_t, offset)
__field(size_t, count)
- __field(int, error)
+ __field(unsigned long, error)
__field(int, stateid_seq)
__field(u32, stateid_hash)
),
@@ -1308,7 +1534,7 @@
__entry->fhandle = nfs_fhandle_hash(NFS_FH(inode));
__entry->offset = hdr->args.offset;
__entry->count = hdr->args.count;
- __entry->error = error;
+ __entry->error = error < 0 ? -error : 0;
__entry->stateid_seq =
be32_to_cpu(state->stateid.seqid);
__entry->stateid_hash =
@@ -1316,9 +1542,9 @@
),
TP_printk(
- "error=%d (%s) fileid=%02x:%02x:%llu fhandle=0x%08x "
+ "error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x "
"offset=%lld count=%zu stateid=%d:0x%08x",
- __entry->error,
+ -__entry->error,
show_nfsv4_errors(__entry->error),
MAJOR(__entry->dev), MINOR(__entry->dev),
(unsigned long long)__entry->fileid,
@@ -1354,7 +1580,7 @@
__field(u64, fileid)
__field(loff_t, offset)
__field(size_t, count)
- __field(int, error)
+ __field(unsigned long, error)
__field(int, stateid_seq)
__field(u32, stateid_hash)
),
@@ -1368,7 +1594,7 @@
__entry->fhandle = nfs_fhandle_hash(NFS_FH(inode));
__entry->offset = hdr->args.offset;
__entry->count = hdr->args.count;
- __entry->error = error;
+ __entry->error = error < 0 ? -error : 0;
__entry->stateid_seq =
be32_to_cpu(state->stateid.seqid);
__entry->stateid_hash =
@@ -1376,9 +1602,9 @@
),
TP_printk(
- "error=%d (%s) fileid=%02x:%02x:%llu fhandle=0x%08x "
+ "error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x "
"offset=%lld count=%zu stateid=%d:0x%08x",
- __entry->error,
+ -__entry->error,
show_nfsv4_errors(__entry->error),
MAJOR(__entry->dev), MINOR(__entry->dev),
(unsigned long long)__entry->fileid,
@@ -1415,7 +1641,7 @@
__field(u64, fileid)
__field(loff_t, offset)
__field(size_t, count)
- __field(int, error)
+ __field(unsigned long, error)
),
TP_fast_assign(
@@ -1429,9 +1655,9 @@
),
TP_printk(
- "error=%d (%s) fileid=%02x:%02x:%llu fhandle=0x%08x "
+ "error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x "
"offset=%lld count=%zu",
- __entry->error,
+ -__entry->error,
show_nfsv4_errors(__entry->error),
MAJOR(__entry->dev), MINOR(__entry->dev),
(unsigned long long)__entry->fileid,
@@ -1451,6 +1677,10 @@
#ifdef CONFIG_NFS_V4_1
DEFINE_NFS4_COMMIT_EVENT(nfs4_pnfs_commit_ds);
+TRACE_DEFINE_ENUM(IOMODE_READ);
+TRACE_DEFINE_ENUM(IOMODE_RW);
+TRACE_DEFINE_ENUM(IOMODE_ANY);
+
#define show_pnfs_iomode(iomode) \
__print_symbolic(iomode, \
{ IOMODE_READ, "READ" }, \
@@ -1475,7 +1705,7 @@
__field(u32, iomode)
__field(u64, offset)
__field(u64, count)
- __field(int, error)
+ __field(unsigned long, error)
__field(int, stateid_seq)
__field(u32, stateid_hash)
__field(int, layoutstateid_seq)
@@ -1508,10 +1738,10 @@
),
TP_printk(
- "error=%d (%s) fileid=%02x:%02x:%llu fhandle=0x%08x "
+ "error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x "
"iomode=%s offset=%llu count=%llu stateid=%d:0x%08x "
"layoutstateid=%d:0x%08x",
- __entry->error,
+ -__entry->error,
show_nfsv4_errors(__entry->error),
MAJOR(__entry->dev), MINOR(__entry->dev),
(unsigned long long)__entry->fileid,
@@ -1528,6 +1758,21 @@
DEFINE_NFS4_INODE_STATEID_EVENT(nfs4_layoutreturn);
DEFINE_NFS4_INODE_EVENT(nfs4_layoutreturn_on_close);
+TRACE_DEFINE_ENUM(PNFS_UPDATE_LAYOUT_UNKNOWN);
+TRACE_DEFINE_ENUM(PNFS_UPDATE_LAYOUT_NO_PNFS);
+TRACE_DEFINE_ENUM(PNFS_UPDATE_LAYOUT_RD_ZEROLEN);
+TRACE_DEFINE_ENUM(PNFS_UPDATE_LAYOUT_MDSTHRESH);
+TRACE_DEFINE_ENUM(PNFS_UPDATE_LAYOUT_NOMEM);
+TRACE_DEFINE_ENUM(PNFS_UPDATE_LAYOUT_BULK_RECALL);
+TRACE_DEFINE_ENUM(PNFS_UPDATE_LAYOUT_IO_TEST_FAIL);
+TRACE_DEFINE_ENUM(PNFS_UPDATE_LAYOUT_FOUND_CACHED);
+TRACE_DEFINE_ENUM(PNFS_UPDATE_LAYOUT_RETURN);
+TRACE_DEFINE_ENUM(PNFS_UPDATE_LAYOUT_BLOCKED);
+TRACE_DEFINE_ENUM(PNFS_UPDATE_LAYOUT_INVALID_OPEN);
+TRACE_DEFINE_ENUM(PNFS_UPDATE_LAYOUT_RETRY);
+TRACE_DEFINE_ENUM(PNFS_UPDATE_LAYOUT_SEND_LAYOUTGET);
+TRACE_DEFINE_ENUM(PNFS_UPDATE_LAYOUT_EXIT);
+
#define show_pnfs_update_layout_reason(reason) \
__print_symbolic(reason, \
{ PNFS_UPDATE_LAYOUT_UNKNOWN, "unknown" }, \
@@ -1542,7 +1787,8 @@
{ PNFS_UPDATE_LAYOUT_BLOCKED, "layouts blocked" }, \
{ PNFS_UPDATE_LAYOUT_INVALID_OPEN, "invalid open" }, \
{ PNFS_UPDATE_LAYOUT_RETRY, "retrying" }, \
- { PNFS_UPDATE_LAYOUT_SEND_LAYOUTGET, "sent layoutget" })
+ { PNFS_UPDATE_LAYOUT_SEND_LAYOUTGET, "sent layoutget" }, \
+ { PNFS_UPDATE_LAYOUT_EXIT, "exit" })
TRACE_EVENT(pnfs_update_layout,
TP_PROTO(struct inode *inode,
@@ -1601,6 +1847,78 @@
)
);
+DECLARE_EVENT_CLASS(pnfs_layout_event,
+ TP_PROTO(struct inode *inode,
+ loff_t pos,
+ u64 count,
+ enum pnfs_iomode iomode,
+ struct pnfs_layout_hdr *lo,
+ struct pnfs_layout_segment *lseg
+ ),
+ TP_ARGS(inode, pos, count, iomode, lo, lseg),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(u64, fileid)
+ __field(u32, fhandle)
+ __field(loff_t, pos)
+ __field(u64, count)
+ __field(enum pnfs_iomode, iomode)
+ __field(int, layoutstateid_seq)
+ __field(u32, layoutstateid_hash)
+ __field(long, lseg)
+ ),
+ TP_fast_assign(
+ __entry->dev = inode->i_sb->s_dev;
+ __entry->fileid = NFS_FILEID(inode);
+ __entry->fhandle = nfs_fhandle_hash(NFS_FH(inode));
+ __entry->pos = pos;
+ __entry->count = count;
+ __entry->iomode = iomode;
+ if (lo != NULL) {
+ __entry->layoutstateid_seq =
+ be32_to_cpu(lo->plh_stateid.seqid);
+ __entry->layoutstateid_hash =
+ nfs_stateid_hash(&lo->plh_stateid);
+ } else {
+ __entry->layoutstateid_seq = 0;
+ __entry->layoutstateid_hash = 0;
+ }
+ __entry->lseg = (long)lseg;
+ ),
+ TP_printk(
+ "fileid=%02x:%02x:%llu fhandle=0x%08x "
+ "iomode=%s pos=%llu count=%llu "
+ "layoutstateid=%d:0x%08x lseg=0x%lx",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ (unsigned long long)__entry->fileid,
+ __entry->fhandle,
+ show_pnfs_iomode(__entry->iomode),
+ (unsigned long long)__entry->pos,
+ (unsigned long long)__entry->count,
+ __entry->layoutstateid_seq, __entry->layoutstateid_hash,
+ __entry->lseg
+ )
+);
+
+#define DEFINE_PNFS_LAYOUT_EVENT(name) \
+ DEFINE_EVENT(pnfs_layout_event, name, \
+ TP_PROTO(struct inode *inode, \
+ loff_t pos, \
+ u64 count, \
+ enum pnfs_iomode iomode, \
+ struct pnfs_layout_hdr *lo, \
+ struct pnfs_layout_segment *lseg \
+ ), \
+ TP_ARGS(inode, pos, count, iomode, lo, lseg))
+
+DEFINE_PNFS_LAYOUT_EVENT(pnfs_mds_fallback_pg_init_read);
+DEFINE_PNFS_LAYOUT_EVENT(pnfs_mds_fallback_pg_init_write);
+DEFINE_PNFS_LAYOUT_EVENT(pnfs_mds_fallback_pg_get_mirror_count);
+DEFINE_PNFS_LAYOUT_EVENT(pnfs_mds_fallback_read_done);
+DEFINE_PNFS_LAYOUT_EVENT(pnfs_mds_fallback_write_done);
+DEFINE_PNFS_LAYOUT_EVENT(pnfs_mds_fallback_read_pagelist);
+DEFINE_PNFS_LAYOUT_EVENT(pnfs_mds_fallback_write_pagelist);
+
#endif /* CONFIG_NFS_V4_1 */
#endif /* _TRACE_NFS4_H */
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index b7bde12..ab07db0 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -54,6 +54,7 @@
#include <linux/nfs_fs.h>
#include "nfs4_fs.h"
+#include "nfs4trace.h"
#include "internal.h"
#include "nfs4idmap.h"
#include "nfs4session.h"
@@ -214,14 +215,14 @@
nfs4_fattr_bitmap_maxsz)
#define encode_read_maxsz (op_encode_hdr_maxsz + \
encode_stateid_maxsz + 3)
-#define decode_read_maxsz (op_decode_hdr_maxsz + 2)
+#define decode_read_maxsz (op_decode_hdr_maxsz + 2 + 1)
#define encode_readdir_maxsz (op_encode_hdr_maxsz + \
2 + encode_verifier_maxsz + 5 + \
nfs4_label_maxsz)
#define decode_readdir_maxsz (op_decode_hdr_maxsz + \
- decode_verifier_maxsz)
+ decode_verifier_maxsz + 1)
#define encode_readlink_maxsz (op_encode_hdr_maxsz)
-#define decode_readlink_maxsz (op_decode_hdr_maxsz + 1)
+#define decode_readlink_maxsz (op_decode_hdr_maxsz + 1 + 1)
#define encode_write_maxsz (op_encode_hdr_maxsz + \
encode_stateid_maxsz + 4)
#define decode_write_maxsz (op_decode_hdr_maxsz + \
@@ -283,14 +284,14 @@
#define decode_delegreturn_maxsz (op_decode_hdr_maxsz)
#define encode_getacl_maxsz (encode_getattr_maxsz)
#define decode_getacl_maxsz (op_decode_hdr_maxsz + \
- nfs4_fattr_bitmap_maxsz + 1)
+ nfs4_fattr_bitmap_maxsz + 1 + 1)
#define encode_setacl_maxsz (op_encode_hdr_maxsz + \
encode_stateid_maxsz + 3)
#define decode_setacl_maxsz (decode_setattr_maxsz)
#define encode_fs_locations_maxsz \
(encode_getattr_maxsz)
#define decode_fs_locations_maxsz \
- (0)
+ (1)
#define encode_secinfo_maxsz (op_encode_hdr_maxsz + nfs4_name_maxsz)
#define decode_secinfo_maxsz (op_decode_hdr_maxsz + 1 + ((NFS_MAX_SECFLAVORS * (16 + GSS_OID_MAX_LEN)) / 4))
@@ -391,12 +392,13 @@
1 /* opaque devaddr4 length */ + \
/* devaddr4 payload is read into page */ \
1 /* notification bitmap length */ + \
- 1 /* notification bitmap, word 0 */)
+ 1 /* notification bitmap, word 0 */ + \
+ 1 /* possible XDR padding */)
#define encode_layoutget_maxsz (op_encode_hdr_maxsz + 10 + \
encode_stateid_maxsz)
#define decode_layoutget_maxsz (op_decode_hdr_maxsz + 8 + \
decode_stateid_maxsz + \
- XDR_QUADLEN(PNFS_LAYOUT_MAXSIZE))
+ XDR_QUADLEN(PNFS_LAYOUT_MAXSIZE) + 1)
#define encode_layoutcommit_maxsz (op_encode_hdr_maxsz + \
2 /* offset */ + \
2 /* length */ + \
@@ -835,6 +837,7 @@
#define NFS4_dec_sequence_sz \
(compound_decode_hdr_maxsz + \
decode_sequence_maxsz)
+#endif
#define NFS4_enc_get_lease_time_sz (compound_encode_hdr_maxsz + \
encode_sequence_maxsz + \
encode_putrootfh_maxsz + \
@@ -843,6 +846,7 @@
decode_sequence_maxsz + \
decode_putrootfh_maxsz + \
decode_fsinfo_maxsz)
+#if defined(CONFIG_NFS_V4_1)
#define NFS4_enc_reclaim_complete_sz (compound_encode_hdr_maxsz + \
encode_sequence_maxsz + \
encode_reclaim_complete_maxsz)
@@ -1015,12 +1019,11 @@
struct compound_hdr *hdr)
{
__be32 *p;
- struct rpc_auth *auth = req->rq_cred->cr_auth;
/* initialize running count of expected bytes in reply.
* NOTE: the replied tag SHOULD be the same is the one sent,
* but this is not required as a MUST for the server to do so. */
- hdr->replen = RPC_REPHDRSIZE + auth->au_rslack + 3 + hdr->taglen;
+ hdr->replen = 3 + hdr->taglen;
WARN_ON_ONCE(hdr->taglen > NFS4_MAXTAGLEN);
encode_string(xdr, hdr->taglen, hdr->tag);
@@ -1171,7 +1174,7 @@
} else
*p++ = cpu_to_be32(NFS4_SET_TO_SERVER_TIME);
}
- if (bmval[2] & FATTR4_WORD2_SECURITY_LABEL) {
+ if (label && (bmval[2] & FATTR4_WORD2_SECURITY_LABEL)) {
*p++ = cpu_to_be32(label->lfs);
*p++ = cpu_to_be32(label->pi);
*p++ = cpu_to_be32(label->len);
@@ -2340,9 +2343,9 @@
encode_getfattr_open(xdr, args->bitmask, args->open_bitmap, &hdr);
if (args->lg_args) {
encode_layoutget(xdr, args->lg_args, &hdr);
- xdr_inline_pages(&req->rq_rcv_buf, hdr.replen << 2,
- args->lg_args->layout.pages,
- 0, args->lg_args->layout.pglen);
+ rpc_prepare_reply_pages(req, args->lg_args->layout.pages, 0,
+ args->lg_args->layout.pglen,
+ hdr.replen);
}
encode_nops(&hdr);
}
@@ -2386,9 +2389,9 @@
encode_getfattr_open(xdr, args->bitmask, args->open_bitmap, &hdr);
if (args->lg_args) {
encode_layoutget(xdr, args->lg_args, &hdr);
- xdr_inline_pages(&req->rq_rcv_buf, hdr.replen << 2,
- args->lg_args->layout.pages,
- 0, args->lg_args->layout.pglen);
+ rpc_prepare_reply_pages(req, args->lg_args->layout.pages, 0,
+ args->lg_args->layout.pglen,
+ hdr.replen);
}
encode_nops(&hdr);
}
@@ -2498,8 +2501,8 @@
encode_putfh(xdr, args->fh, &hdr);
encode_readlink(xdr, args, req, &hdr);
- xdr_inline_pages(&req->rq_rcv_buf, hdr.replen << 2, args->pages,
- args->pgbase, args->pglen);
+ rpc_prepare_reply_pages(req, args->pages, args->pgbase,
+ args->pglen, hdr.replen);
encode_nops(&hdr);
}
@@ -2519,11 +2522,8 @@
encode_putfh(xdr, args->fh, &hdr);
encode_readdir(xdr, args, req, &hdr);
- xdr_inline_pages(&req->rq_rcv_buf, hdr.replen << 2, args->pages,
- args->pgbase, args->count);
- dprintk("%s: inlined page args = (%u, %p, %u, %u)\n",
- __func__, hdr.replen << 2, args->pages,
- args->pgbase, args->count);
+ rpc_prepare_reply_pages(req, args->pages, args->pgbase,
+ args->count, hdr.replen);
encode_nops(&hdr);
}
@@ -2543,8 +2543,8 @@
encode_putfh(xdr, args->fh, &hdr);
encode_read(xdr, args, &hdr);
- xdr_inline_pages(&req->rq_rcv_buf, hdr.replen << 2,
- args->pages, args->pgbase, args->count);
+ rpc_prepare_reply_pages(req, args->pages, args->pgbase,
+ args->count, hdr.replen);
req->rq_rcv_buf.flags |= XDRBUF_READ;
encode_nops(&hdr);
}
@@ -2590,9 +2590,8 @@
encode_getattr(xdr, nfs4_acl_bitmap, NULL,
ARRAY_SIZE(nfs4_acl_bitmap), &hdr);
- xdr_inline_pages(&req->rq_rcv_buf, replen << 2,
- args->acl_pages, 0, args->acl_len);
-
+ rpc_prepare_reply_pages(req, args->acl_pages, 0,
+ args->acl_len, replen + 1);
encode_nops(&hdr);
}
@@ -2813,9 +2812,8 @@
encode_fs_locations(xdr, args->bitmask, &hdr);
}
- /* Set up reply kvec to capture returned fs_locations array. */
- xdr_inline_pages(&req->rq_rcv_buf, replen << 2,
- (struct page **)&args->page, 0, PAGE_SIZE);
+ rpc_prepare_reply_pages(req, (struct page **)&args->page, 0,
+ PAGE_SIZE, replen + 1);
encode_nops(&hdr);
}
@@ -2961,6 +2959,8 @@
encode_nops(&hdr);
}
+#endif
+
/*
* a GET_LEASE_TIME request
*/
@@ -2981,6 +2981,8 @@
encode_nops(&hdr);
}
+#ifdef CONFIG_NFS_V4_1
+
/*
* a RECLAIM_COMPLETE request
*/
@@ -3017,10 +3019,8 @@
/* set up reply kvec. Subtract notification bitmap max size (2)
* so that notification bitmap is put in xdr_buf tail */
- xdr_inline_pages(&req->rq_rcv_buf, (hdr.replen - 2) << 2,
- args->pdev->pages, args->pdev->pgbase,
- args->pdev->pglen);
-
+ rpc_prepare_reply_pages(req, args->pdev->pages, args->pdev->pgbase,
+ args->pdev->pglen, hdr.replen - 2);
encode_nops(&hdr);
}
@@ -3041,9 +3041,8 @@
encode_putfh(xdr, NFS_FH(args->inode), &hdr);
encode_layoutget(xdr, args, &hdr);
- xdr_inline_pages(&req->rq_rcv_buf, hdr.replen << 2,
- args->layout.pages, 0, args->layout.pglen);
-
+ rpc_prepare_reply_pages(req, args->layout.pages, 0,
+ args->layout.pglen, hdr.replen);
encode_nops(&hdr);
}
@@ -3144,22 +3143,12 @@
}
#endif /* CONFIG_NFS_V4_1 */
-static void print_overflow_msg(const char *func, const struct xdr_stream *xdr)
-{
- dprintk("nfs: %s: prematurely hit end of receive buffer. "
- "Remaining buffer length is %tu words.\n",
- func, xdr->end - xdr->p);
-}
-
static int decode_opaque_inline(struct xdr_stream *xdr, unsigned int *len, char **string)
{
ssize_t ret = xdr_stream_decode_opaque_inline(xdr, (void **)string,
NFS4_OPAQUE_LIMIT);
- if (unlikely(ret < 0)) {
- if (ret == -EBADMSG)
- print_overflow_msg(__func__, xdr);
+ if (unlikely(ret < 0))
return -EIO;
- }
*len = ret;
return 0;
}
@@ -3170,22 +3159,19 @@
p = xdr_inline_decode(xdr, 8);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
hdr->status = be32_to_cpup(p++);
hdr->taglen = be32_to_cpup(p);
p = xdr_inline_decode(xdr, hdr->taglen + 4);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
hdr->tag = (char *)p;
p += XDR_QUADLEN(hdr->taglen);
hdr->nops = be32_to_cpup(p);
if (unlikely(hdr->nops < 1))
return nfs4_stat_to_errno(hdr->status);
return 0;
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
}
static bool __decode_op_hdr(struct xdr_stream *xdr, enum nfs_opnum4 expected,
@@ -3201,11 +3187,14 @@
opnum = be32_to_cpup(p++);
if (unlikely(opnum != expected))
goto out_bad_operation;
+ if (unlikely(*p != cpu_to_be32(NFS_OK)))
+ goto out_status;
+ *nfs_retval = 0;
+ return true;
+out_status:
nfserr = be32_to_cpup(p);
- if (nfserr == NFS_OK)
- *nfs_retval = 0;
- else
- *nfs_retval = nfs4_stat_to_errno(nfserr);
+ trace_nfs4_xdr_status(xdr, opnum, nfserr);
+ *nfs_retval = nfs4_stat_to_errno(nfserr);
return true;
out_bad_operation:
dprintk("nfs: Server returned operation"
@@ -3214,7 +3203,6 @@
*nfs_retval = -EREMOTEIO;
return false;
out_overflow:
- print_overflow_msg(__func__, xdr);
*nfs_retval = -EIO;
return false;
}
@@ -3235,10 +3223,9 @@
char *str;
p = xdr_inline_decode(xdr, 12);
- if (likely(p))
- return decode_opaque_inline(xdr, &strlen, &str);
- print_overflow_msg(__func__, xdr);
- return -EIO;
+ if (unlikely(!p))
+ return -EIO;
+ return decode_opaque_inline(xdr, &strlen, &str);
}
static ssize_t
@@ -3249,10 +3236,9 @@
ret = xdr_stream_decode_uint32_array(xdr, bitmap, sz);
if (likely(ret >= 0))
return ret;
- if (ret == -EMSGSIZE)
- return sz;
- print_overflow_msg(__func__, xdr);
- return -EIO;
+ if (ret != -EMSGSIZE)
+ return -EIO;
+ return sz;
}
static int decode_attr_bitmap(struct xdr_stream *xdr, uint32_t *bitmap)
@@ -3268,13 +3254,10 @@
p = xdr_inline_decode(xdr, 4);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
*attrlen = be32_to_cpup(p);
*savep = xdr_stream_pos(xdr);
return 0;
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
}
static int decode_attr_supported(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t *bitmask)
@@ -3303,7 +3286,7 @@
if (likely(bitmap[0] & FATTR4_WORD0_TYPE)) {
p = xdr_inline_decode(xdr, 4);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
*type = be32_to_cpup(p);
if (*type < NF4REG || *type > NF4NAMEDATTR) {
dprintk("%s: bad type %d\n", __func__, *type);
@@ -3314,9 +3297,6 @@
}
dprintk("%s: type=0%o\n", __func__, nfs_type2fmt[*type]);
return ret;
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
}
static int decode_attr_fh_expire_type(struct xdr_stream *xdr,
@@ -3330,15 +3310,12 @@
if (likely(bitmap[0] & FATTR4_WORD0_FH_EXPIRE_TYPE)) {
p = xdr_inline_decode(xdr, 4);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
*type = be32_to_cpup(p);
bitmap[0] &= ~FATTR4_WORD0_FH_EXPIRE_TYPE;
}
dprintk("%s: expire type=0x%x\n", __func__, *type);
return 0;
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
}
static int decode_attr_change(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t *change)
@@ -3352,7 +3329,7 @@
if (likely(bitmap[0] & FATTR4_WORD0_CHANGE)) {
p = xdr_inline_decode(xdr, 8);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
xdr_decode_hyper(p, change);
bitmap[0] &= ~FATTR4_WORD0_CHANGE;
ret = NFS_ATTR_FATTR_CHANGE;
@@ -3360,9 +3337,6 @@
dprintk("%s: change attribute=%Lu\n", __func__,
(unsigned long long)*change);
return ret;
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
}
static int decode_attr_size(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t *size)
@@ -3376,16 +3350,13 @@
if (likely(bitmap[0] & FATTR4_WORD0_SIZE)) {
p = xdr_inline_decode(xdr, 8);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
xdr_decode_hyper(p, size);
bitmap[0] &= ~FATTR4_WORD0_SIZE;
ret = NFS_ATTR_FATTR_SIZE;
}
dprintk("%s: file size=%Lu\n", __func__, (unsigned long long)*size);
return ret;
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
}
static int decode_attr_link_support(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t *res)
@@ -3398,15 +3369,12 @@
if (likely(bitmap[0] & FATTR4_WORD0_LINK_SUPPORT)) {
p = xdr_inline_decode(xdr, 4);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
*res = be32_to_cpup(p);
bitmap[0] &= ~FATTR4_WORD0_LINK_SUPPORT;
}
dprintk("%s: link support=%s\n", __func__, *res == 0 ? "false" : "true");
return 0;
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
}
static int decode_attr_symlink_support(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t *res)
@@ -3419,15 +3387,12 @@
if (likely(bitmap[0] & FATTR4_WORD0_SYMLINK_SUPPORT)) {
p = xdr_inline_decode(xdr, 4);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
*res = be32_to_cpup(p);
bitmap[0] &= ~FATTR4_WORD0_SYMLINK_SUPPORT;
}
dprintk("%s: symlink support=%s\n", __func__, *res == 0 ? "false" : "true");
return 0;
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
}
static int decode_attr_fsid(struct xdr_stream *xdr, uint32_t *bitmap, struct nfs_fsid *fsid)
@@ -3442,7 +3407,7 @@
if (likely(bitmap[0] & FATTR4_WORD0_FSID)) {
p = xdr_inline_decode(xdr, 16);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
p = xdr_decode_hyper(p, &fsid->major);
xdr_decode_hyper(p, &fsid->minor);
bitmap[0] &= ~FATTR4_WORD0_FSID;
@@ -3452,9 +3417,6 @@
(unsigned long long)fsid->major,
(unsigned long long)fsid->minor);
return ret;
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
}
static int decode_attr_lease_time(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t *res)
@@ -3467,15 +3429,12 @@
if (likely(bitmap[0] & FATTR4_WORD0_LEASE_TIME)) {
p = xdr_inline_decode(xdr, 4);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
*res = be32_to_cpup(p);
bitmap[0] &= ~FATTR4_WORD0_LEASE_TIME;
}
- dprintk("%s: file size=%u\n", __func__, (unsigned int)*res);
+ dprintk("%s: lease time=%u\n", __func__, (unsigned int)*res);
return 0;
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
}
static int decode_attr_error(struct xdr_stream *xdr, uint32_t *bitmap, int32_t *res)
@@ -3487,14 +3446,11 @@
if (likely(bitmap[0] & FATTR4_WORD0_RDATTR_ERROR)) {
p = xdr_inline_decode(xdr, 4);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
bitmap[0] &= ~FATTR4_WORD0_RDATTR_ERROR;
*res = -be32_to_cpup(p);
}
return 0;
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
}
static int decode_attr_exclcreat_supported(struct xdr_stream *xdr,
@@ -3516,7 +3472,7 @@
static int decode_attr_filehandle(struct xdr_stream *xdr, uint32_t *bitmap, struct nfs_fh *fh)
{
__be32 *p;
- int len;
+ u32 len;
if (fh != NULL)
memset(fh, 0, sizeof(*fh));
@@ -3526,13 +3482,13 @@
if (likely(bitmap[0] & FATTR4_WORD0_FILEHANDLE)) {
p = xdr_inline_decode(xdr, 4);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
len = be32_to_cpup(p);
if (len > NFS4_FHSIZE)
return -EIO;
p = xdr_inline_decode(xdr, len);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
if (fh != NULL) {
memcpy(fh->data, p, len);
fh->size = len;
@@ -3540,9 +3496,6 @@
bitmap[0] &= ~FATTR4_WORD0_FILEHANDLE;
}
return 0;
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
}
static int decode_attr_aclsupport(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t *res)
@@ -3555,15 +3508,12 @@
if (likely(bitmap[0] & FATTR4_WORD0_ACLSUPPORT)) {
p = xdr_inline_decode(xdr, 4);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
*res = be32_to_cpup(p);
bitmap[0] &= ~FATTR4_WORD0_ACLSUPPORT;
}
dprintk("%s: ACLs supported=%u\n", __func__, (unsigned int)*res);
return 0;
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
}
static int decode_attr_fileid(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t *fileid)
@@ -3577,16 +3527,13 @@
if (likely(bitmap[0] & FATTR4_WORD0_FILEID)) {
p = xdr_inline_decode(xdr, 8);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
xdr_decode_hyper(p, fileid);
bitmap[0] &= ~FATTR4_WORD0_FILEID;
ret = NFS_ATTR_FATTR_FILEID;
}
dprintk("%s: fileid=%Lu\n", __func__, (unsigned long long)*fileid);
return ret;
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
}
static int decode_attr_mounted_on_fileid(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t *fileid)
@@ -3600,16 +3547,13 @@
if (likely(bitmap[1] & FATTR4_WORD1_MOUNTED_ON_FILEID)) {
p = xdr_inline_decode(xdr, 8);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
xdr_decode_hyper(p, fileid);
bitmap[1] &= ~FATTR4_WORD1_MOUNTED_ON_FILEID;
ret = NFS_ATTR_FATTR_MOUNTED_ON_FILEID;
}
dprintk("%s: fileid=%Lu\n", __func__, (unsigned long long)*fileid);
return ret;
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
}
static int decode_attr_files_avail(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t *res)
@@ -3623,15 +3567,12 @@
if (likely(bitmap[0] & FATTR4_WORD0_FILES_AVAIL)) {
p = xdr_inline_decode(xdr, 8);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
xdr_decode_hyper(p, res);
bitmap[0] &= ~FATTR4_WORD0_FILES_AVAIL;
}
dprintk("%s: files avail=%Lu\n", __func__, (unsigned long long)*res);
return status;
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
}
static int decode_attr_files_free(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t *res)
@@ -3645,15 +3586,12 @@
if (likely(bitmap[0] & FATTR4_WORD0_FILES_FREE)) {
p = xdr_inline_decode(xdr, 8);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
xdr_decode_hyper(p, res);
bitmap[0] &= ~FATTR4_WORD0_FILES_FREE;
}
dprintk("%s: files free=%Lu\n", __func__, (unsigned long long)*res);
return status;
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
}
static int decode_attr_files_total(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t *res)
@@ -3667,15 +3605,12 @@
if (likely(bitmap[0] & FATTR4_WORD0_FILES_TOTAL)) {
p = xdr_inline_decode(xdr, 8);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
xdr_decode_hyper(p, res);
bitmap[0] &= ~FATTR4_WORD0_FILES_TOTAL;
}
dprintk("%s: files total=%Lu\n", __func__, (unsigned long long)*res);
return status;
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
}
static int decode_pathname(struct xdr_stream *xdr, struct nfs4_pathname *path)
@@ -3686,7 +3621,7 @@
p = xdr_inline_decode(xdr, 4);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
n = be32_to_cpup(p);
if (n == 0)
goto root_path;
@@ -3718,9 +3653,6 @@
dprintk(" status %d", status);
status = -EIO;
goto out;
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
}
static int decode_attr_fs_locations(struct xdr_stream *xdr, uint32_t *bitmap, struct nfs4_fs_locations *res)
@@ -3745,7 +3677,7 @@
goto out;
p = xdr_inline_decode(xdr, 4);
if (unlikely(!p))
- goto out_overflow;
+ goto out_eio;
n = be32_to_cpup(p);
if (n <= 0)
goto out_eio;
@@ -3758,7 +3690,7 @@
loc = &res->locations[res->nlocations];
p = xdr_inline_decode(xdr, 4);
if (unlikely(!p))
- goto out_overflow;
+ goto out_eio;
m = be32_to_cpup(p);
dprintk("%s: servers:\n", __func__);
@@ -3796,8 +3728,6 @@
out:
dprintk("%s: fs_locations done, error = %d\n", __func__, status);
return status;
-out_overflow:
- print_overflow_msg(__func__, xdr);
out_eio:
status = -EIO;
goto out;
@@ -3814,15 +3744,12 @@
if (likely(bitmap[0] & FATTR4_WORD0_MAXFILESIZE)) {
p = xdr_inline_decode(xdr, 8);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
xdr_decode_hyper(p, res);
bitmap[0] &= ~FATTR4_WORD0_MAXFILESIZE;
}
dprintk("%s: maxfilesize=%Lu\n", __func__, (unsigned long long)*res);
return status;
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
}
static int decode_attr_maxlink(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t *maxlink)
@@ -3836,15 +3763,12 @@
if (likely(bitmap[0] & FATTR4_WORD0_MAXLINK)) {
p = xdr_inline_decode(xdr, 4);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
*maxlink = be32_to_cpup(p);
bitmap[0] &= ~FATTR4_WORD0_MAXLINK;
}
dprintk("%s: maxlink=%u\n", __func__, *maxlink);
return status;
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
}
static int decode_attr_maxname(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t *maxname)
@@ -3858,15 +3782,12 @@
if (likely(bitmap[0] & FATTR4_WORD0_MAXNAME)) {
p = xdr_inline_decode(xdr, 4);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
*maxname = be32_to_cpup(p);
bitmap[0] &= ~FATTR4_WORD0_MAXNAME;
}
dprintk("%s: maxname=%u\n", __func__, *maxname);
return status;
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
}
static int decode_attr_maxread(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t *res)
@@ -3881,7 +3802,7 @@
uint64_t maxread;
p = xdr_inline_decode(xdr, 8);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
xdr_decode_hyper(p, &maxread);
if (maxread > 0x7FFFFFFF)
maxread = 0x7FFFFFFF;
@@ -3890,9 +3811,6 @@
}
dprintk("%s: maxread=%lu\n", __func__, (unsigned long)*res);
return status;
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
}
static int decode_attr_maxwrite(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t *res)
@@ -3907,7 +3825,7 @@
uint64_t maxwrite;
p = xdr_inline_decode(xdr, 8);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
xdr_decode_hyper(p, &maxwrite);
if (maxwrite > 0x7FFFFFFF)
maxwrite = 0x7FFFFFFF;
@@ -3916,9 +3834,6 @@
}
dprintk("%s: maxwrite=%lu\n", __func__, (unsigned long)*res);
return status;
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
}
static int decode_attr_mode(struct xdr_stream *xdr, uint32_t *bitmap, umode_t *mode)
@@ -3933,7 +3848,7 @@
if (likely(bitmap[1] & FATTR4_WORD1_MODE)) {
p = xdr_inline_decode(xdr, 4);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
tmp = be32_to_cpup(p);
*mode = tmp & ~S_IFMT;
bitmap[1] &= ~FATTR4_WORD1_MODE;
@@ -3941,9 +3856,6 @@
}
dprintk("%s: file mode=0%o\n", __func__, (unsigned int)*mode);
return ret;
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
}
static int decode_attr_nlink(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t *nlink)
@@ -3957,16 +3869,13 @@
if (likely(bitmap[1] & FATTR4_WORD1_NUMLINKS)) {
p = xdr_inline_decode(xdr, 4);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
*nlink = be32_to_cpup(p);
bitmap[1] &= ~FATTR4_WORD1_NUMLINKS;
ret = NFS_ATTR_FATTR_NLINK;
}
dprintk("%s: nlink=%u\n", __func__, (unsigned int)*nlink);
return ret;
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
}
static ssize_t decode_nfs4_string(struct xdr_stream *xdr,
@@ -4011,10 +3920,9 @@
return NFS_ATTR_FATTR_OWNER;
}
out:
- if (len != -EBADMSG)
- return 0;
- print_overflow_msg(__func__, xdr);
- return -EIO;
+ if (len == -EBADMSG)
+ return -EIO;
+ return 0;
}
static int decode_attr_group(struct xdr_stream *xdr, uint32_t *bitmap,
@@ -4046,10 +3954,9 @@
return NFS_ATTR_FATTR_GROUP;
}
out:
- if (len != -EBADMSG)
- return 0;
- print_overflow_msg(__func__, xdr);
- return -EIO;
+ if (len == -EBADMSG)
+ return -EIO;
+ return 0;
}
static int decode_attr_rdev(struct xdr_stream *xdr, uint32_t *bitmap, dev_t *rdev)
@@ -4066,7 +3973,7 @@
p = xdr_inline_decode(xdr, 8);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
major = be32_to_cpup(p++);
minor = be32_to_cpup(p);
tmp = MKDEV(major, minor);
@@ -4077,9 +3984,6 @@
}
dprintk("%s: rdev=(0x%x:0x%x)\n", __func__, major, minor);
return ret;
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
}
static int decode_attr_space_avail(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t *res)
@@ -4093,15 +3997,12 @@
if (likely(bitmap[1] & FATTR4_WORD1_SPACE_AVAIL)) {
p = xdr_inline_decode(xdr, 8);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
xdr_decode_hyper(p, res);
bitmap[1] &= ~FATTR4_WORD1_SPACE_AVAIL;
}
dprintk("%s: space avail=%Lu\n", __func__, (unsigned long long)*res);
return status;
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
}
static int decode_attr_space_free(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t *res)
@@ -4115,15 +4016,12 @@
if (likely(bitmap[1] & FATTR4_WORD1_SPACE_FREE)) {
p = xdr_inline_decode(xdr, 8);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
xdr_decode_hyper(p, res);
bitmap[1] &= ~FATTR4_WORD1_SPACE_FREE;
}
dprintk("%s: space free=%Lu\n", __func__, (unsigned long long)*res);
return status;
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
}
static int decode_attr_space_total(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t *res)
@@ -4137,15 +4035,12 @@
if (likely(bitmap[1] & FATTR4_WORD1_SPACE_TOTAL)) {
p = xdr_inline_decode(xdr, 8);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
xdr_decode_hyper(p, res);
bitmap[1] &= ~FATTR4_WORD1_SPACE_TOTAL;
}
dprintk("%s: space total=%Lu\n", __func__, (unsigned long long)*res);
return status;
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
}
static int decode_attr_space_used(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t *used)
@@ -4159,7 +4054,7 @@
if (likely(bitmap[1] & FATTR4_WORD1_SPACE_USED)) {
p = xdr_inline_decode(xdr, 8);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
xdr_decode_hyper(p, used);
bitmap[1] &= ~FATTR4_WORD1_SPACE_USED;
ret = NFS_ATTR_FATTR_SPACE_USED;
@@ -4167,9 +4062,6 @@
dprintk("%s: space used=%Lu\n", __func__,
(unsigned long long)*used);
return ret;
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
}
static __be32 *
@@ -4189,12 +4081,9 @@
p = xdr_inline_decode(xdr, nfstime4_maxsz << 2);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
xdr_decode_nfstime4(p, time);
return 0;
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
}
static int decode_attr_time_access(struct xdr_stream *xdr, uint32_t *bitmap, struct timespec *time)
@@ -4265,19 +4154,19 @@
if (likely(bitmap[2] & FATTR4_WORD2_SECURITY_LABEL)) {
p = xdr_inline_decode(xdr, 4);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
lfs = be32_to_cpup(p++);
p = xdr_inline_decode(xdr, 4);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
pi = be32_to_cpup(p++);
p = xdr_inline_decode(xdr, 4);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
len = be32_to_cpup(p++);
p = xdr_inline_decode(xdr, len);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
if (len < NFS4_MAXLABELLEN) {
if (label) {
memcpy(label->label, p, len);
@@ -4295,10 +4184,6 @@
dprintk("%s: label=%s, len=%d, PI=%d, LFS=%d\n", __func__,
(char *)label->label, label->len, label->pi, label->lfs);
return status;
-
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
}
static int decode_attr_time_modify(struct xdr_stream *xdr, uint32_t *bitmap, struct timespec *time)
@@ -4342,14 +4227,11 @@
p = xdr_inline_decode(xdr, 20);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
cinfo->atomic = be32_to_cpup(p++);
p = xdr_decode_hyper(p, &cinfo->before);
xdr_decode_hyper(p, &cinfo->after);
return 0;
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
}
static int decode_access(struct xdr_stream *xdr, u32 *supported, u32 *access)
@@ -4363,24 +4245,19 @@
return status;
p = xdr_inline_decode(xdr, 8);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
supp = be32_to_cpup(p++);
acc = be32_to_cpup(p);
*supported = supp;
*access = acc;
return 0;
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
}
static int decode_opaque_fixed(struct xdr_stream *xdr, void *buf, size_t len)
{
ssize_t ret = xdr_stream_decode_opaque_fixed(xdr, buf, len);
- if (unlikely(ret < 0)) {
- print_overflow_msg(__func__, xdr);
+ if (unlikely(ret < 0))
return -EIO;
- }
return 0;
}
@@ -4460,13 +4337,11 @@
return status;
p = xdr_inline_decode(xdr, 4);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
bmlen = be32_to_cpup(p);
p = xdr_inline_decode(xdr, bmlen << 2);
if (likely(p))
return 0;
-out_overflow:
- print_overflow_msg(__func__, xdr);
return -EIO;
}
@@ -4574,13 +4449,10 @@
if (likely(bitmap[0] & hint_bit)) {
p = xdr_inline_decode(xdr, 8);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
xdr_decode_hyper(p, res);
}
return 0;
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
}
static int decode_first_threshold_item4(struct xdr_stream *xdr,
@@ -4593,10 +4465,8 @@
/* layout type */
p = xdr_inline_decode(xdr, 4);
- if (unlikely(!p)) {
- print_overflow_msg(__func__, xdr);
+ if (unlikely(!p))
return -EIO;
- }
res->l_type = be32_to_cpup(p);
/* thi_hintset bitmap */
@@ -4654,7 +4524,7 @@
return -EREMOTEIO;
p = xdr_inline_decode(xdr, 4);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
num = be32_to_cpup(p);
if (num == 0)
return 0;
@@ -4667,9 +4537,6 @@
bitmap[2] &= ~FATTR4_WORD2_MDSTHRESHOLD;
}
return status;
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
}
static int decode_getfattr_attrs(struct xdr_stream *xdr, uint32_t *bitmap,
@@ -4857,7 +4724,7 @@
p = xdr_inline_decode(xdr, 4);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
fsinfo->nlayouttypes = be32_to_cpup(p);
/* pNFS is not supported by the underlying file system */
@@ -4867,7 +4734,7 @@
/* Decode and set first layout type, move xdr->p past unused types */
p = xdr_inline_decode(xdr, fsinfo->nlayouttypes * 4);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
/* If we get too many, then just cap it at the max */
if (fsinfo->nlayouttypes > NFS_MAX_LAYOUT_TYPES) {
@@ -4879,9 +4746,6 @@
for(i = 0; i < fsinfo->nlayouttypes; ++i)
fsinfo->layouttype[i] = be32_to_cpup(p++);
return 0;
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
}
/*
@@ -4915,10 +4779,8 @@
*res = 0;
if (bitmap[2] & FATTR4_WORD2_LAYOUT_BLKSIZE) {
p = xdr_inline_decode(xdr, 4);
- if (unlikely(!p)) {
- print_overflow_msg(__func__, xdr);
+ if (unlikely(!p))
return -EIO;
- }
*res = be32_to_cpup(p);
bitmap[2] &= ~FATTR4_WORD2_LAYOUT_BLKSIZE;
}
@@ -4937,10 +4799,8 @@
*res = 0;
if (bitmap[2] & FATTR4_WORD2_CLONE_BLKSIZE) {
p = xdr_inline_decode(xdr, 4);
- if (unlikely(!p)) {
- print_overflow_msg(__func__, xdr);
+ if (unlikely(!p))
return -EIO;
- }
*res = be32_to_cpup(p);
bitmap[2] &= ~FATTR4_WORD2_CLONE_BLKSIZE;
}
@@ -5016,19 +4876,16 @@
p = xdr_inline_decode(xdr, 4);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
len = be32_to_cpup(p);
if (len > NFS4_FHSIZE)
return -EIO;
fh->size = len;
p = xdr_inline_decode(xdr, len);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
memcpy(fh->data, p, len);
return 0;
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
}
static int decode_link(struct xdr_stream *xdr, struct nfs4_change_info *cinfo)
@@ -5052,7 +4909,7 @@
p = xdr_inline_decode(xdr, 32); /* read 32 bytes */
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
p = xdr_decode_hyper(p, &offset); /* read 2 8-byte long words */
p = xdr_decode_hyper(p, &length);
type = be32_to_cpup(p++); /* 4 byte read */
@@ -5069,11 +4926,9 @@
p = xdr_decode_hyper(p, &clientid); /* read 8 bytes */
namelen = be32_to_cpup(p); /* read 4 bytes */ /* have read all 32 bytes now */
p = xdr_inline_decode(xdr, namelen); /* variable size field */
- if (likely(p))
- return -NFS4ERR_DENIED;
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
+ if (likely(!p))
+ return -EIO;
+ return -NFS4ERR_DENIED;
}
static int decode_lock(struct xdr_stream *xdr, struct nfs_lock_res *res)
@@ -5142,7 +4997,7 @@
p = xdr_inline_decode(xdr, 12);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
limit_type = be32_to_cpup(p++);
switch (limit_type) {
case NFS4_LIMIT_SIZE:
@@ -5156,9 +5011,6 @@
maxsize >>= PAGE_SHIFT;
*pagemod_limit = min_t(u64, maxsize, ULONG_MAX);
return 0;
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
}
static int decode_rw_delegation(struct xdr_stream *xdr,
@@ -5173,7 +5025,7 @@
return status;
p = xdr_inline_decode(xdr, 4);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
res->do_recall = be32_to_cpup(p);
switch (delegation_type) {
@@ -5186,9 +5038,6 @@
return -EIO;
}
return decode_ace(xdr, NULL);
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
}
static int decode_no_delegation(struct xdr_stream *xdr, struct nfs_openres *res)
@@ -5198,7 +5047,7 @@
p = xdr_inline_decode(xdr, 4);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
why_no_delegation = be32_to_cpup(p);
switch (why_no_delegation) {
case WND4_CONTENTION:
@@ -5207,9 +5056,6 @@
/* Ignore for now */
}
return 0;
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
}
static int decode_delegation(struct xdr_stream *xdr, struct nfs_openres *res)
@@ -5219,7 +5065,7 @@
p = xdr_inline_decode(xdr, 4);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
delegation_type = be32_to_cpup(p);
res->delegation_type = 0;
switch (delegation_type) {
@@ -5232,9 +5078,6 @@
return decode_no_delegation(xdr, res);
}
return -EIO;
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
}
static int decode_open(struct xdr_stream *xdr, struct nfs_openres *res)
@@ -5256,7 +5099,7 @@
p = xdr_inline_decode(xdr, 8);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
res->rflags = be32_to_cpup(p++);
bmlen = be32_to_cpup(p);
if (bmlen > 10)
@@ -5264,7 +5107,7 @@
p = xdr_inline_decode(xdr, bmlen << 2);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
savewords = min_t(uint32_t, bmlen, NFS4_BITMAP_SIZE);
for (i = 0; i < savewords; ++i)
res->attrset[i] = be32_to_cpup(p++);
@@ -5275,9 +5118,6 @@
xdr_error:
dprintk("%s: Bitmap too large! Length = %u\n", __func__, bmlen);
return -EIO;
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
}
static int decode_open_confirm(struct xdr_stream *xdr, struct nfs_open_confirmres *res)
@@ -5326,7 +5166,7 @@
return status;
p = xdr_inline_decode(xdr, 8);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
eof = be32_to_cpup(p++);
count = be32_to_cpup(p);
recvd = xdr_read_pages(xdr, count);
@@ -5339,9 +5179,6 @@
res->eof = eof;
res->count = count;
return 0;
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
}
static int decode_readdir(struct xdr_stream *xdr, struct rpc_rqst *req, struct nfs4_readdir_res *readdir)
@@ -5374,7 +5211,7 @@
/* Convert length of symlink */
p = xdr_inline_decode(xdr, 4);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
len = be32_to_cpup(p);
if (len >= rcvbuf->page_len || len <= 0) {
dprintk("nfs: server returned giant symlink!\n");
@@ -5395,9 +5232,6 @@
*/
xdr_terminate_string(rcvbuf, len);
return 0;
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
}
static int decode_remove(struct xdr_stream *xdr, struct nfs4_change_info *cinfo)
@@ -5500,7 +5334,6 @@
return status;
if (decode_bitmap4(xdr, NULL, 0) >= 0)
return 0;
- print_overflow_msg(__func__, xdr);
return -EIO;
}
@@ -5512,7 +5345,7 @@
p = xdr_inline_decode(xdr, 8);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
opnum = be32_to_cpup(p++);
if (opnum != OP_SETCLIENTID) {
dprintk("nfs: decode_setclientid: Server returned operation"
@@ -5523,7 +5356,7 @@
if (nfserr == NFS_OK) {
p = xdr_inline_decode(xdr, 8 + NFS4_VERIFIER_SIZE);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
p = xdr_decode_hyper(p, &res->clientid);
memcpy(res->confirm.data, p, NFS4_VERIFIER_SIZE);
} else if (nfserr == NFSERR_CLID_INUSE) {
@@ -5532,28 +5365,25 @@
/* skip netid string */
p = xdr_inline_decode(xdr, 4);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
len = be32_to_cpup(p);
p = xdr_inline_decode(xdr, len);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
/* skip uaddr string */
p = xdr_inline_decode(xdr, 4);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
len = be32_to_cpup(p);
p = xdr_inline_decode(xdr, len);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
return -NFSERR_CLID_INUSE;
} else
return nfs4_stat_to_errno(nfserr);
return 0;
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
}
static int decode_setclientid_confirm(struct xdr_stream *xdr)
@@ -5572,13 +5402,10 @@
p = xdr_inline_decode(xdr, 8);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
res->count = be32_to_cpup(p++);
res->verf->committed = be32_to_cpup(p++);
return decode_write_verifier(xdr, &res->verf->verifier);
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
}
static int decode_delegreturn(struct xdr_stream *xdr)
@@ -5594,30 +5421,24 @@
p = xdr_inline_decode(xdr, 4);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
oid_len = be32_to_cpup(p);
if (oid_len > GSS_OID_MAX_LEN)
- goto out_err;
+ return -EINVAL;
p = xdr_inline_decode(xdr, oid_len);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
memcpy(flavor->flavor_info.oid.data, p, oid_len);
flavor->flavor_info.oid.len = oid_len;
p = xdr_inline_decode(xdr, 8);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
flavor->flavor_info.qop = be32_to_cpup(p++);
flavor->flavor_info.service = be32_to_cpup(p);
return 0;
-
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
-out_err:
- return -EINVAL;
}
static int decode_secinfo_common(struct xdr_stream *xdr, struct nfs4_secinfo_res *res)
@@ -5629,7 +5450,7 @@
p = xdr_inline_decode(xdr, 4);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
res->flavors->num_flavors = 0;
num_flavors = be32_to_cpup(p);
@@ -5641,7 +5462,7 @@
p = xdr_inline_decode(xdr, 4);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
sec_flavor->flavor = be32_to_cpup(p);
if (sec_flavor->flavor == RPC_AUTH_GSS) {
@@ -5655,9 +5476,6 @@
status = 0;
out:
return status;
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
}
static int decode_secinfo(struct xdr_stream *xdr, struct nfs4_secinfo_res *res)
@@ -5711,11 +5529,11 @@
p = xdr_inline_decode(xdr, 8);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
xdr_decode_hyper(p, &res->clientid);
p = xdr_inline_decode(xdr, 12);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
res->seqid = be32_to_cpup(p++);
res->flags = be32_to_cpup(p++);
@@ -5739,7 +5557,7 @@
/* server_owner4.so_minor_id */
p = xdr_inline_decode(xdr, 8);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
p = xdr_decode_hyper(p, &res->server_owner->minor_id);
/* server_owner4.so_major_id */
@@ -5759,7 +5577,7 @@
/* Implementation Id */
p = xdr_inline_decode(xdr, 4);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
impl_id_count = be32_to_cpup(p++);
if (impl_id_count) {
@@ -5778,16 +5596,13 @@
/* nii_date */
p = xdr_inline_decode(xdr, 12);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
p = xdr_decode_hyper(p, &res->impl_id->date.seconds);
res->impl_id->date.nseconds = be32_to_cpup(p);
/* if there's more than one entry, ignore the rest */
}
return 0;
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
}
static int decode_chan_attrs(struct xdr_stream *xdr,
@@ -5798,7 +5613,7 @@
p = xdr_inline_decode(xdr, 28);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
val = be32_to_cpup(p++); /* headerpadsz */
if (val)
return -EINVAL; /* no support for header padding yet */
@@ -5816,12 +5631,9 @@
if (nr_attrs == 1) {
p = xdr_inline_decode(xdr, 4); /* skip rdma_attrs */
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
}
return 0;
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
}
static int decode_sessionid(struct xdr_stream *xdr, struct nfs4_sessionid *sid)
@@ -5844,7 +5656,7 @@
/* dir flags, rdma mode bool */
p = xdr_inline_decode(xdr, 8);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
res->dir = be32_to_cpup(p++);
if (res->dir == 0 || res->dir > NFS4_CDFS4_BOTH)
@@ -5855,9 +5667,6 @@
res->use_conn_in_rdma_mode = true;
return 0;
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
}
static int decode_create_session(struct xdr_stream *xdr,
@@ -5875,7 +5684,7 @@
/* seqid, flags */
p = xdr_inline_decode(xdr, 8);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
res->seqid = be32_to_cpup(p++);
res->flags = be32_to_cpup(p);
@@ -5884,9 +5693,6 @@
if (!status)
status = decode_chan_attrs(xdr, &res->bc_attrs);
return status;
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
}
static int decode_destroy_session(struct xdr_stream *xdr, void *dummy)
@@ -5967,7 +5773,6 @@
res->sr_status = status;
return status;
out_overflow:
- print_overflow_msg(__func__, xdr);
status = -EIO;
goto out_err;
#else /* CONFIG_NFS_V4_1 */
@@ -5995,7 +5800,7 @@
if (status == -ETOOSMALL) {
p = xdr_inline_decode(xdr, 4);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
pdev->mincount = be32_to_cpup(p);
dprintk("%s: Min count too small. mincnt = %u\n",
__func__, pdev->mincount);
@@ -6005,7 +5810,7 @@
p = xdr_inline_decode(xdr, 8);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
type = be32_to_cpup(p++);
if (type != pdev->layout_type) {
dprintk("%s: layout mismatch req: %u pdev: %u\n",
@@ -6019,19 +5824,19 @@
*/
pdev->mincount = be32_to_cpup(p);
if (xdr_read_pages(xdr, pdev->mincount) != pdev->mincount)
- goto out_overflow;
+ return -EIO;
/* Parse notification bitmap, verifying that it is zero. */
p = xdr_inline_decode(xdr, 4);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
len = be32_to_cpup(p);
if (len) {
uint32_t i;
p = xdr_inline_decode(xdr, 4 * len);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
res->notification = be32_to_cpup(p++);
for (i = 1; i < len; i++) {
@@ -6043,9 +5848,6 @@
}
}
return 0;
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
}
static int decode_layoutget(struct xdr_stream *xdr, struct rpc_rqst *req,
@@ -6115,7 +5917,6 @@
res->status = status;
return status;
out_overflow:
- print_overflow_msg(__func__, xdr);
status = -EIO;
goto out;
}
@@ -6131,16 +5932,13 @@
return status;
p = xdr_inline_decode(xdr, 4);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
res->lrs_present = be32_to_cpup(p);
if (res->lrs_present)
status = decode_layout_stateid(xdr, &res->stateid);
else
nfs4_stateid_copy(&res->stateid, &invalid_stateid);
return status;
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
}
static int decode_layoutcommit(struct xdr_stream *xdr,
@@ -6158,19 +5956,16 @@
p = xdr_inline_decode(xdr, 4);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
sizechanged = be32_to_cpup(p);
if (sizechanged) {
/* throw away new size */
p = xdr_inline_decode(xdr, 8);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
}
return 0;
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
}
static int decode_test_stateid(struct xdr_stream *xdr,
@@ -6186,21 +5981,17 @@
p = xdr_inline_decode(xdr, 4);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
num_res = be32_to_cpup(p++);
if (num_res != 1)
- goto out;
+ return -EIO;
p = xdr_inline_decode(xdr, 4);
if (unlikely(!p))
- goto out_overflow;
+ return -EIO;
res->status = be32_to_cpup(p++);
return status;
-out_overflow:
- print_overflow_msg(__func__, xdr);
-out:
- return -EIO;
}
static int decode_free_stateid(struct xdr_stream *xdr,
@@ -7337,6 +7128,8 @@
return status;
}
+#endif
+
/*
* Decode GET_LEASE_TIME response
*/
@@ -7358,6 +7151,8 @@
return status;
}
+#ifdef CONFIG_NFS_V4_1
+
/*
* Decode RECLAIM_COMPLETE response
*/
@@ -7570,11 +7365,11 @@
uint64_t new_cookie;
__be32 *p = xdr_inline_decode(xdr, 4);
if (unlikely(!p))
- goto out_overflow;
+ return -EAGAIN;
if (*p == xdr_zero) {
p = xdr_inline_decode(xdr, 4);
if (unlikely(!p))
- goto out_overflow;
+ return -EAGAIN;
if (*p == xdr_zero)
return -EAGAIN;
entry->eof = 1;
@@ -7583,13 +7378,13 @@
p = xdr_inline_decode(xdr, 12);
if (unlikely(!p))
- goto out_overflow;
+ return -EAGAIN;
p = xdr_decode_hyper(p, &new_cookie);
entry->len = be32_to_cpup(p);
p = xdr_inline_decode(xdr, entry->len);
if (unlikely(!p))
- goto out_overflow;
+ return -EAGAIN;
entry->name = (const char *) p;
/*
@@ -7601,14 +7396,14 @@
entry->fattr->valid = 0;
if (decode_attr_bitmap(xdr, bitmap) < 0)
- goto out_overflow;
+ return -EAGAIN;
if (decode_attr_length(xdr, &len, &savep) < 0)
- goto out_overflow;
+ return -EAGAIN;
if (decode_getfattr_attrs(xdr, bitmap, entry->fattr, entry->fh,
NULL, entry->label, entry->server) < 0)
- goto out_overflow;
+ return -EAGAIN;
if (entry->fattr->valid & NFS_ATTR_FATTR_MOUNTED_ON_FILEID)
entry->ino = entry->fattr->mounted_on_fileid;
else if (entry->fattr->valid & NFS_ATTR_FATTR_FILEID)
@@ -7622,10 +7417,6 @@
entry->cookie = new_cookie;
return 0;
-
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EAGAIN;
}
/*
@@ -7770,7 +7561,7 @@
PROC41(CREATE_SESSION, enc_create_session, dec_create_session),
PROC41(DESTROY_SESSION, enc_destroy_session, dec_destroy_session),
PROC41(SEQUENCE, enc_sequence, dec_sequence),
- PROC41(GET_LEASE_TIME, enc_get_lease_time, dec_get_lease_time),
+ PROC(GET_LEASE_TIME, enc_get_lease_time, dec_get_lease_time),
PROC41(RECLAIM_COMPLETE,enc_reclaim_complete, dec_reclaim_complete),
PROC41(GETDEVICEINFO, enc_getdeviceinfo, dec_getdeviceinfo),
PROC41(LAYOUTGET, enc_layoutget, dec_layoutget),
@@ -7791,6 +7582,7 @@
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/fs/nfs/nfstrace.c b/fs/nfs/nfstrace.c
index b60d5fb..a90b363 100644
--- a/fs/nfs/nfstrace.c
+++ b/fs/nfs/nfstrace.c
@@ -11,3 +11,4 @@
EXPORT_TRACEPOINT_SYMBOL_GPL(nfs_fsync_enter);
EXPORT_TRACEPOINT_SYMBOL_GPL(nfs_fsync_exit);
+EXPORT_TRACEPOINT_SYMBOL_GPL(nfs_xdr_status);
diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h
index bd60f8d..361cc10 100644
--- a/fs/nfs/nfstrace.h
+++ b/fs/nfs/nfstrace.h
@@ -11,6 +11,16 @@
#include <linux/tracepoint.h>
#include <linux/iversion.h>
+TRACE_DEFINE_ENUM(DT_UNKNOWN);
+TRACE_DEFINE_ENUM(DT_FIFO);
+TRACE_DEFINE_ENUM(DT_CHR);
+TRACE_DEFINE_ENUM(DT_DIR);
+TRACE_DEFINE_ENUM(DT_BLK);
+TRACE_DEFINE_ENUM(DT_REG);
+TRACE_DEFINE_ENUM(DT_LNK);
+TRACE_DEFINE_ENUM(DT_SOCK);
+TRACE_DEFINE_ENUM(DT_WHT);
+
#define nfs_show_file_type(ftype) \
__print_symbolic(ftype, \
{ DT_UNKNOWN, "UNKNOWN" }, \
@@ -23,25 +33,57 @@
{ DT_SOCK, "SOCK" }, \
{ DT_WHT, "WHT" })
+TRACE_DEFINE_ENUM(NFS_INO_INVALID_DATA);
+TRACE_DEFINE_ENUM(NFS_INO_INVALID_ATIME);
+TRACE_DEFINE_ENUM(NFS_INO_INVALID_ACCESS);
+TRACE_DEFINE_ENUM(NFS_INO_INVALID_ACL);
+TRACE_DEFINE_ENUM(NFS_INO_REVAL_PAGECACHE);
+TRACE_DEFINE_ENUM(NFS_INO_REVAL_FORCED);
+TRACE_DEFINE_ENUM(NFS_INO_INVALID_LABEL);
+TRACE_DEFINE_ENUM(NFS_INO_INVALID_CHANGE);
+TRACE_DEFINE_ENUM(NFS_INO_INVALID_CTIME);
+TRACE_DEFINE_ENUM(NFS_INO_INVALID_MTIME);
+TRACE_DEFINE_ENUM(NFS_INO_INVALID_SIZE);
+TRACE_DEFINE_ENUM(NFS_INO_INVALID_OTHER);
+
#define nfs_show_cache_validity(v) \
__print_flags(v, "|", \
- { NFS_INO_INVALID_ATTR, "INVALID_ATTR" }, \
{ NFS_INO_INVALID_DATA, "INVALID_DATA" }, \
{ NFS_INO_INVALID_ATIME, "INVALID_ATIME" }, \
{ NFS_INO_INVALID_ACCESS, "INVALID_ACCESS" }, \
{ NFS_INO_INVALID_ACL, "INVALID_ACL" }, \
{ NFS_INO_REVAL_PAGECACHE, "REVAL_PAGECACHE" }, \
{ NFS_INO_REVAL_FORCED, "REVAL_FORCED" }, \
- { NFS_INO_INVALID_LABEL, "INVALID_LABEL" })
+ { NFS_INO_INVALID_LABEL, "INVALID_LABEL" }, \
+ { NFS_INO_INVALID_CHANGE, "INVALID_CHANGE" }, \
+ { NFS_INO_INVALID_CTIME, "INVALID_CTIME" }, \
+ { NFS_INO_INVALID_MTIME, "INVALID_MTIME" }, \
+ { NFS_INO_INVALID_SIZE, "INVALID_SIZE" }, \
+ { NFS_INO_INVALID_OTHER, "INVALID_OTHER" })
+
+TRACE_DEFINE_ENUM(NFS_INO_ADVISE_RDPLUS);
+TRACE_DEFINE_ENUM(NFS_INO_STALE);
+TRACE_DEFINE_ENUM(NFS_INO_ACL_LRU_SET);
+TRACE_DEFINE_ENUM(NFS_INO_INVALIDATING);
+TRACE_DEFINE_ENUM(NFS_INO_FSCACHE);
+TRACE_DEFINE_ENUM(NFS_INO_FSCACHE_LOCK);
+TRACE_DEFINE_ENUM(NFS_INO_LAYOUTCOMMIT);
+TRACE_DEFINE_ENUM(NFS_INO_LAYOUTCOMMITTING);
+TRACE_DEFINE_ENUM(NFS_INO_LAYOUTSTATS);
+TRACE_DEFINE_ENUM(NFS_INO_ODIRECT);
#define nfs_show_nfsi_flags(v) \
__print_flags(v, "|", \
- { 1 << NFS_INO_ADVISE_RDPLUS, "ADVISE_RDPLUS" }, \
- { 1 << NFS_INO_STALE, "STALE" }, \
- { 1 << NFS_INO_INVALIDATING, "INVALIDATING" }, \
- { 1 << NFS_INO_FSCACHE, "FSCACHE" }, \
- { 1 << NFS_INO_LAYOUTCOMMIT, "NEED_LAYOUTCOMMIT" }, \
- { 1 << NFS_INO_LAYOUTCOMMITTING, "LAYOUTCOMMIT" })
+ { BIT(NFS_INO_ADVISE_RDPLUS), "ADVISE_RDPLUS" }, \
+ { BIT(NFS_INO_STALE), "STALE" }, \
+ { BIT(NFS_INO_ACL_LRU_SET), "ACL_LRU_SET" }, \
+ { BIT(NFS_INO_INVALIDATING), "INVALIDATING" }, \
+ { BIT(NFS_INO_FSCACHE), "FSCACHE" }, \
+ { BIT(NFS_INO_FSCACHE_LOCK), "FSCACHE_LOCK" }, \
+ { BIT(NFS_INO_LAYOUTCOMMIT), "NEED_LAYOUTCOMMIT" }, \
+ { BIT(NFS_INO_LAYOUTCOMMITTING), "LAYOUTCOMMIT" }, \
+ { BIT(NFS_INO_LAYOUTSTATS), "LAYOUTSTATS" }, \
+ { BIT(NFS_INO_ODIRECT), "ODIRECT" })
DECLARE_EVENT_CLASS(nfs_inode_event,
TP_PROTO(
@@ -83,7 +125,7 @@
TP_ARGS(inode, error),
TP_STRUCT__entry(
- __field(int, error)
+ __field(unsigned long, error)
__field(dev_t, dev)
__field(u32, fhandle)
__field(unsigned char, type)
@@ -96,7 +138,7 @@
TP_fast_assign(
const struct nfs_inode *nfsi = NFS_I(inode);
- __entry->error = error;
+ __entry->error = error < 0 ? -error : 0;
__entry->dev = inode->i_sb->s_dev;
__entry->fileid = nfsi->fileid;
__entry->fhandle = nfs_fhandle_hash(&nfsi->fh);
@@ -108,10 +150,10 @@
),
TP_printk(
- "error=%d fileid=%02x:%02x:%llu fhandle=0x%08x "
+ "error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x "
"type=%u (%s) version=%llu size=%lld "
- "cache_validity=%lu (%s) nfs_flags=%ld (%s)",
- __entry->error,
+ "cache_validity=0x%lx (%s) nfs_flags=0x%lx (%s)",
+ -__entry->error, nfs_show_status(__entry->error),
MAJOR(__entry->dev), MINOR(__entry->dev),
(unsigned long long)__entry->fileid,
__entry->fhandle,
@@ -158,13 +200,39 @@
DEFINE_NFS_INODE_EVENT(nfs_access_enter);
DEFINE_NFS_INODE_EVENT_DONE(nfs_access_exit);
+TRACE_DEFINE_ENUM(LOOKUP_FOLLOW);
+TRACE_DEFINE_ENUM(LOOKUP_DIRECTORY);
+TRACE_DEFINE_ENUM(LOOKUP_AUTOMOUNT);
+TRACE_DEFINE_ENUM(LOOKUP_PARENT);
+TRACE_DEFINE_ENUM(LOOKUP_REVAL);
+TRACE_DEFINE_ENUM(LOOKUP_RCU);
+TRACE_DEFINE_ENUM(LOOKUP_NO_REVAL);
+TRACE_DEFINE_ENUM(LOOKUP_OPEN);
+TRACE_DEFINE_ENUM(LOOKUP_CREATE);
+TRACE_DEFINE_ENUM(LOOKUP_EXCL);
+TRACE_DEFINE_ENUM(LOOKUP_RENAME_TARGET);
+TRACE_DEFINE_ENUM(LOOKUP_JUMPED);
+TRACE_DEFINE_ENUM(LOOKUP_ROOT);
+TRACE_DEFINE_ENUM(LOOKUP_EMPTY);
+TRACE_DEFINE_ENUM(LOOKUP_DOWN);
+
#define show_lookup_flags(flags) \
- __print_flags((unsigned long)flags, "|", \
- { LOOKUP_AUTOMOUNT, "AUTOMOUNT" }, \
+ __print_flags(flags, "|", \
+ { LOOKUP_FOLLOW, "FOLLOW" }, \
{ LOOKUP_DIRECTORY, "DIRECTORY" }, \
+ { LOOKUP_AUTOMOUNT, "AUTOMOUNT" }, \
+ { LOOKUP_PARENT, "PARENT" }, \
+ { LOOKUP_REVAL, "REVAL" }, \
+ { LOOKUP_RCU, "RCU" }, \
+ { LOOKUP_NO_REVAL, "NO_REVAL" }, \
{ LOOKUP_OPEN, "OPEN" }, \
{ LOOKUP_CREATE, "CREATE" }, \
- { LOOKUP_EXCL, "EXCL" })
+ { LOOKUP_EXCL, "EXCL" }, \
+ { LOOKUP_RENAME_TARGET, "RENAME_TARGET" }, \
+ { LOOKUP_JUMPED, "JUMPED" }, \
+ { LOOKUP_ROOT, "ROOT" }, \
+ { LOOKUP_EMPTY, "EMPTY" }, \
+ { LOOKUP_DOWN, "DOWN" })
DECLARE_EVENT_CLASS(nfs_lookup_event,
TP_PROTO(
@@ -176,7 +244,7 @@
TP_ARGS(dir, dentry, flags),
TP_STRUCT__entry(
- __field(unsigned int, flags)
+ __field(unsigned long, flags)
__field(dev_t, dev)
__field(u64, dir)
__string(name, dentry->d_name.name)
@@ -190,7 +258,7 @@
),
TP_printk(
- "flags=%u (%s) name=%02x:%02x:%llu/%s",
+ "flags=0x%lx (%s) name=%02x:%02x:%llu/%s",
__entry->flags,
show_lookup_flags(__entry->flags),
MAJOR(__entry->dev), MINOR(__entry->dev),
@@ -219,8 +287,8 @@
TP_ARGS(dir, dentry, flags, error),
TP_STRUCT__entry(
- __field(int, error)
- __field(unsigned int, flags)
+ __field(unsigned long, error)
+ __field(unsigned long, flags)
__field(dev_t, dev)
__field(u64, dir)
__string(name, dentry->d_name.name)
@@ -229,14 +297,14 @@
TP_fast_assign(
__entry->dev = dir->i_sb->s_dev;
__entry->dir = NFS_FILEID(dir);
- __entry->error = error;
+ __entry->error = error < 0 ? -error : 0;
__entry->flags = flags;
__assign_str(name, dentry->d_name.name);
),
TP_printk(
- "error=%d flags=%u (%s) name=%02x:%02x:%llu/%s",
- __entry->error,
+ "error=%ld (%s) flags=0x%lx (%s) name=%02x:%02x:%llu/%s",
+ -__entry->error, nfs_show_status(__entry->error),
__entry->flags,
show_lookup_flags(__entry->flags),
MAJOR(__entry->dev), MINOR(__entry->dev),
@@ -260,15 +328,43 @@
DEFINE_NFS_LOOKUP_EVENT(nfs_lookup_revalidate_enter);
DEFINE_NFS_LOOKUP_EVENT_DONE(nfs_lookup_revalidate_exit);
+TRACE_DEFINE_ENUM(O_WRONLY);
+TRACE_DEFINE_ENUM(O_RDWR);
+TRACE_DEFINE_ENUM(O_CREAT);
+TRACE_DEFINE_ENUM(O_EXCL);
+TRACE_DEFINE_ENUM(O_NOCTTY);
+TRACE_DEFINE_ENUM(O_TRUNC);
+TRACE_DEFINE_ENUM(O_APPEND);
+TRACE_DEFINE_ENUM(O_NONBLOCK);
+TRACE_DEFINE_ENUM(O_DSYNC);
+TRACE_DEFINE_ENUM(O_DIRECT);
+TRACE_DEFINE_ENUM(O_LARGEFILE);
+TRACE_DEFINE_ENUM(O_DIRECTORY);
+TRACE_DEFINE_ENUM(O_NOFOLLOW);
+TRACE_DEFINE_ENUM(O_NOATIME);
+TRACE_DEFINE_ENUM(O_CLOEXEC);
+
#define show_open_flags(flags) \
- __print_flags((unsigned long)flags, "|", \
+ __print_flags(flags, "|", \
+ { O_WRONLY, "O_WRONLY" }, \
+ { O_RDWR, "O_RDWR" }, \
{ O_CREAT, "O_CREAT" }, \
{ O_EXCL, "O_EXCL" }, \
+ { O_NOCTTY, "O_NOCTTY" }, \
{ O_TRUNC, "O_TRUNC" }, \
{ O_APPEND, "O_APPEND" }, \
+ { O_NONBLOCK, "O_NONBLOCK" }, \
{ O_DSYNC, "O_DSYNC" }, \
{ O_DIRECT, "O_DIRECT" }, \
- { O_DIRECTORY, "O_DIRECTORY" })
+ { O_LARGEFILE, "O_LARGEFILE" }, \
+ { O_DIRECTORY, "O_DIRECTORY" }, \
+ { O_NOFOLLOW, "O_NOFOLLOW" }, \
+ { O_NOATIME, "O_NOATIME" }, \
+ { O_CLOEXEC, "O_CLOEXEC" })
+
+TRACE_DEFINE_ENUM(FMODE_READ);
+TRACE_DEFINE_ENUM(FMODE_WRITE);
+TRACE_DEFINE_ENUM(FMODE_EXEC);
#define show_fmode_flags(mode) \
__print_flags(mode, "|", \
@@ -286,7 +382,7 @@
TP_ARGS(dir, ctx, flags),
TP_STRUCT__entry(
- __field(unsigned int, flags)
+ __field(unsigned long, flags)
__field(unsigned int, fmode)
__field(dev_t, dev)
__field(u64, dir)
@@ -302,7 +398,7 @@
),
TP_printk(
- "flags=%u (%s) fmode=%s name=%02x:%02x:%llu/%s",
+ "flags=0x%lx (%s) fmode=%s name=%02x:%02x:%llu/%s",
__entry->flags,
show_open_flags(__entry->flags),
show_fmode_flags(__entry->fmode),
@@ -323,8 +419,8 @@
TP_ARGS(dir, ctx, flags, error),
TP_STRUCT__entry(
- __field(int, error)
- __field(unsigned int, flags)
+ __field(unsigned long, error)
+ __field(unsigned long, flags)
__field(unsigned int, fmode)
__field(dev_t, dev)
__field(u64, dir)
@@ -332,7 +428,7 @@
),
TP_fast_assign(
- __entry->error = error;
+ __entry->error = -error;
__entry->dev = dir->i_sb->s_dev;
__entry->dir = NFS_FILEID(dir);
__entry->flags = flags;
@@ -341,9 +437,9 @@
),
TP_printk(
- "error=%d flags=%u (%s) fmode=%s "
+ "error=%ld (%s) flags=0x%lx (%s) fmode=%s "
"name=%02x:%02x:%llu/%s",
- __entry->error,
+ -__entry->error, nfs_show_status(__entry->error),
__entry->flags,
show_open_flags(__entry->flags),
show_fmode_flags(__entry->fmode),
@@ -363,7 +459,7 @@
TP_ARGS(dir, dentry, flags),
TP_STRUCT__entry(
- __field(unsigned int, flags)
+ __field(unsigned long, flags)
__field(dev_t, dev)
__field(u64, dir)
__string(name, dentry->d_name.name)
@@ -377,7 +473,7 @@
),
TP_printk(
- "flags=%u (%s) name=%02x:%02x:%llu/%s",
+ "flags=0x%lx (%s) name=%02x:%02x:%llu/%s",
__entry->flags,
show_open_flags(__entry->flags),
MAJOR(__entry->dev), MINOR(__entry->dev),
@@ -397,15 +493,15 @@
TP_ARGS(dir, dentry, flags, error),
TP_STRUCT__entry(
- __field(int, error)
- __field(unsigned int, flags)
+ __field(unsigned long, error)
+ __field(unsigned long, flags)
__field(dev_t, dev)
__field(u64, dir)
__string(name, dentry->d_name.name)
),
TP_fast_assign(
- __entry->error = error;
+ __entry->error = -error;
__entry->dev = dir->i_sb->s_dev;
__entry->dir = NFS_FILEID(dir);
__entry->flags = flags;
@@ -413,8 +509,8 @@
),
TP_printk(
- "error=%d flags=%u (%s) name=%02x:%02x:%llu/%s",
- __entry->error,
+ "error=%ld (%s) flags=0x%lx (%s) name=%02x:%02x:%llu/%s",
+ -__entry->error, nfs_show_status(__entry->error),
__entry->flags,
show_open_flags(__entry->flags),
MAJOR(__entry->dev), MINOR(__entry->dev),
@@ -469,7 +565,7 @@
TP_ARGS(dir, dentry, error),
TP_STRUCT__entry(
- __field(int, error)
+ __field(unsigned long, error)
__field(dev_t, dev)
__field(u64, dir)
__string(name, dentry->d_name.name)
@@ -478,13 +574,13 @@
TP_fast_assign(
__entry->dev = dir->i_sb->s_dev;
__entry->dir = NFS_FILEID(dir);
- __entry->error = error;
+ __entry->error = error < 0 ? -error : 0;
__assign_str(name, dentry->d_name.name);
),
TP_printk(
- "error=%d name=%02x:%02x:%llu/%s",
- __entry->error,
+ "error=%ld (%s) name=%02x:%02x:%llu/%s",
+ -__entry->error, nfs_show_status(__entry->error),
MAJOR(__entry->dev), MINOR(__entry->dev),
(unsigned long long)__entry->dir,
__get_str(name)
@@ -557,7 +653,7 @@
TP_ARGS(inode, dir, dentry, error),
TP_STRUCT__entry(
- __field(int, error)
+ __field(unsigned long, error)
__field(dev_t, dev)
__field(u64, fileid)
__field(u64, dir)
@@ -568,13 +664,13 @@
__entry->dev = inode->i_sb->s_dev;
__entry->fileid = NFS_FILEID(inode);
__entry->dir = NFS_FILEID(dir);
- __entry->error = error;
+ __entry->error = error < 0 ? -error : 0;
__assign_str(name, dentry->d_name.name);
),
TP_printk(
- "error=%d fileid=%02x:%02x:%llu name=%02x:%02x:%llu/%s",
- __entry->error,
+ "error=%ld (%s) fileid=%02x:%02x:%llu name=%02x:%02x:%llu/%s",
+ -__entry->error, nfs_show_status(__entry->error),
MAJOR(__entry->dev), MINOR(__entry->dev),
__entry->fileid,
MAJOR(__entry->dev), MINOR(__entry->dev),
@@ -642,7 +738,7 @@
TP_STRUCT__entry(
__field(dev_t, dev)
- __field(int, error)
+ __field(unsigned long, error)
__field(u64, old_dir)
__string(old_name, old_dentry->d_name.name)
__field(u64, new_dir)
@@ -651,17 +747,17 @@
TP_fast_assign(
__entry->dev = old_dir->i_sb->s_dev;
+ __entry->error = -error;
__entry->old_dir = NFS_FILEID(old_dir);
__entry->new_dir = NFS_FILEID(new_dir);
- __entry->error = error;
__assign_str(old_name, old_dentry->d_name.name);
__assign_str(new_name, new_dentry->d_name.name);
),
TP_printk(
- "error=%d old_name=%02x:%02x:%llu/%s "
+ "error=%ld (%s) old_name=%02x:%02x:%llu/%s "
"new_name=%02x:%02x:%llu/%s",
- __entry->error,
+ -__entry->error, nfs_show_status(__entry->error),
MAJOR(__entry->dev), MINOR(__entry->dev),
(unsigned long long)__entry->old_dir,
__get_str(old_name),
@@ -697,7 +793,7 @@
TP_STRUCT__entry(
__field(dev_t, dev)
- __field(int, error)
+ __field(unsigned long, error)
__field(u64, dir)
__dynamic_array(char, name, data->args.name.len + 1)
),
@@ -707,15 +803,15 @@
size_t len = data->args.name.len;
__entry->dev = dir->i_sb->s_dev;
__entry->dir = NFS_FILEID(dir);
- __entry->error = error;
+ __entry->error = -error;
memcpy(__get_str(name),
data->args.name.name, len);
__get_str(name)[len] = 0;
),
TP_printk(
- "error=%d name=%02x:%02x:%llu/%s",
- __entry->error,
+ "error=%ld (%s) name=%02x:%02x:%llu/%s",
+ -__entry->error, nfs_show_status(__entry->error),
MAJOR(__entry->dev), MINOR(__entry->dev),
(unsigned long long)__entry->dir,
__get_str(name)
@@ -969,6 +1065,108 @@
)
);
+TRACE_DEFINE_ENUM(NFS_OK);
+TRACE_DEFINE_ENUM(NFSERR_PERM);
+TRACE_DEFINE_ENUM(NFSERR_NOENT);
+TRACE_DEFINE_ENUM(NFSERR_IO);
+TRACE_DEFINE_ENUM(NFSERR_NXIO);
+TRACE_DEFINE_ENUM(ECHILD);
+TRACE_DEFINE_ENUM(NFSERR_EAGAIN);
+TRACE_DEFINE_ENUM(NFSERR_ACCES);
+TRACE_DEFINE_ENUM(NFSERR_EXIST);
+TRACE_DEFINE_ENUM(NFSERR_XDEV);
+TRACE_DEFINE_ENUM(NFSERR_NODEV);
+TRACE_DEFINE_ENUM(NFSERR_NOTDIR);
+TRACE_DEFINE_ENUM(NFSERR_ISDIR);
+TRACE_DEFINE_ENUM(NFSERR_INVAL);
+TRACE_DEFINE_ENUM(NFSERR_FBIG);
+TRACE_DEFINE_ENUM(NFSERR_NOSPC);
+TRACE_DEFINE_ENUM(NFSERR_ROFS);
+TRACE_DEFINE_ENUM(NFSERR_MLINK);
+TRACE_DEFINE_ENUM(NFSERR_OPNOTSUPP);
+TRACE_DEFINE_ENUM(NFSERR_NAMETOOLONG);
+TRACE_DEFINE_ENUM(NFSERR_NOTEMPTY);
+TRACE_DEFINE_ENUM(NFSERR_DQUOT);
+TRACE_DEFINE_ENUM(NFSERR_STALE);
+TRACE_DEFINE_ENUM(NFSERR_REMOTE);
+TRACE_DEFINE_ENUM(NFSERR_WFLUSH);
+TRACE_DEFINE_ENUM(NFSERR_BADHANDLE);
+TRACE_DEFINE_ENUM(NFSERR_NOT_SYNC);
+TRACE_DEFINE_ENUM(NFSERR_BAD_COOKIE);
+TRACE_DEFINE_ENUM(NFSERR_NOTSUPP);
+TRACE_DEFINE_ENUM(NFSERR_TOOSMALL);
+TRACE_DEFINE_ENUM(NFSERR_SERVERFAULT);
+TRACE_DEFINE_ENUM(NFSERR_BADTYPE);
+TRACE_DEFINE_ENUM(NFSERR_JUKEBOX);
+
+#define nfs_show_status(x) \
+ __print_symbolic(x, \
+ { NFS_OK, "OK" }, \
+ { NFSERR_PERM, "PERM" }, \
+ { NFSERR_NOENT, "NOENT" }, \
+ { NFSERR_IO, "IO" }, \
+ { NFSERR_NXIO, "NXIO" }, \
+ { ECHILD, "CHILD" }, \
+ { NFSERR_EAGAIN, "AGAIN" }, \
+ { NFSERR_ACCES, "ACCES" }, \
+ { NFSERR_EXIST, "EXIST" }, \
+ { NFSERR_XDEV, "XDEV" }, \
+ { NFSERR_NODEV, "NODEV" }, \
+ { NFSERR_NOTDIR, "NOTDIR" }, \
+ { NFSERR_ISDIR, "ISDIR" }, \
+ { NFSERR_INVAL, "INVAL" }, \
+ { NFSERR_FBIG, "FBIG" }, \
+ { NFSERR_NOSPC, "NOSPC" }, \
+ { NFSERR_ROFS, "ROFS" }, \
+ { NFSERR_MLINK, "MLINK" }, \
+ { NFSERR_OPNOTSUPP, "OPNOTSUPP" }, \
+ { NFSERR_NAMETOOLONG, "NAMETOOLONG" }, \
+ { NFSERR_NOTEMPTY, "NOTEMPTY" }, \
+ { NFSERR_DQUOT, "DQUOT" }, \
+ { NFSERR_STALE, "STALE" }, \
+ { NFSERR_REMOTE, "REMOTE" }, \
+ { NFSERR_WFLUSH, "WFLUSH" }, \
+ { NFSERR_BADHANDLE, "BADHANDLE" }, \
+ { NFSERR_NOT_SYNC, "NOTSYNC" }, \
+ { NFSERR_BAD_COOKIE, "BADCOOKIE" }, \
+ { NFSERR_NOTSUPP, "NOTSUPP" }, \
+ { NFSERR_TOOSMALL, "TOOSMALL" }, \
+ { NFSERR_SERVERFAULT, "REMOTEIO" }, \
+ { NFSERR_BADTYPE, "BADTYPE" }, \
+ { NFSERR_JUKEBOX, "JUKEBOX" })
+
+TRACE_EVENT(nfs_xdr_status,
+ TP_PROTO(
+ const struct xdr_stream *xdr,
+ int error
+ ),
+
+ TP_ARGS(xdr, error),
+
+ TP_STRUCT__entry(
+ __field(unsigned int, task_id)
+ __field(unsigned int, client_id)
+ __field(u32, xid)
+ __field(unsigned long, error)
+ ),
+
+ TP_fast_assign(
+ const struct rpc_rqst *rqstp = xdr->rqst;
+ const struct rpc_task *task = rqstp->rq_task;
+
+ __entry->task_id = task->tk_pid;
+ __entry->client_id = task->tk_client->cl_clid;
+ __entry->xid = be32_to_cpu(rqstp->rq_xid);
+ __entry->error = error;
+ ),
+
+ TP_printk(
+ "task:%u@%d xid=0x%08x error=%ld (%s)",
+ __entry->task_id, __entry->client_id, __entry->xid,
+ -__entry->error, nfs_show_status(__entry->error)
+ )
+);
+
#endif /* _TRACE_NFS_H */
#undef TRACE_INCLUDE_PATH
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index 3dbd15b..20b3717 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* linux/fs/nfs/pagelist.c
*
@@ -16,8 +17,8 @@
#include <linux/nfs.h>
#include <linux/nfs3.h>
#include <linux/nfs4.h>
-#include <linux/nfs_page.h>
#include <linux/nfs_fs.h>
+#include <linux/nfs_page.h>
#include <linux/nfs_mount.h>
#include <linux/export.h>
@@ -47,7 +48,7 @@
hdr->req = nfs_list_entry(mirror->pg_list.next);
hdr->inode = desc->pg_inode;
- hdr->cred = hdr->req->wb_context->cred;
+ hdr->cred = nfs_req_openctx(hdr->req)->cred;
hdr->io_start = req_offset(hdr->req);
hdr->good_bytes = mirror->pg_count;
hdr->io_completion = desc->pg_io_completion;
@@ -63,20 +64,20 @@
void nfs_set_pgio_error(struct nfs_pgio_header *hdr, int error, loff_t pos)
{
- spin_lock(&hdr->lock);
- if (!test_and_set_bit(NFS_IOHDR_ERROR, &hdr->flags)
- || pos < hdr->io_start + hdr->good_bytes) {
+ unsigned int new = pos - hdr->io_start;
+
+ if (hdr->good_bytes > new) {
+ hdr->good_bytes = new;
clear_bit(NFS_IOHDR_EOF, &hdr->flags);
- hdr->good_bytes = pos - hdr->io_start;
- hdr->error = error;
+ if (!test_and_set_bit(NFS_IOHDR_ERROR, &hdr->flags))
+ hdr->error = error;
}
- spin_unlock(&hdr->lock);
}
static inline struct nfs_page *
nfs_page_alloc(void)
{
- struct nfs_page *p = kmem_cache_zalloc(nfs_page_cachep, GFP_NOIO);
+ struct nfs_page *p = kmem_cache_zalloc(nfs_page_cachep, GFP_KERNEL);
if (p)
INIT_LIST_HEAD(&p->wb_list);
return p;
@@ -295,25 +296,13 @@
nfs_release_request(head);
}
-/**
- * nfs_create_request - Create an NFS read/write request.
- * @ctx: open context to use
- * @page: page to write
- * @last: last nfs request created for this page group or NULL if head
- * @offset: starting offset within the page for the write
- * @count: number of bytes to read/write
- *
- * The page must be locked by the caller. This makes sure we never
- * create two different requests for the same page.
- * User should ensure it is safe to sleep in this function.
- */
-struct nfs_page *
-nfs_create_request(struct nfs_open_context *ctx, struct page *page,
- struct nfs_page *last, unsigned int offset,
+static struct nfs_page *
+__nfs_create_request(struct nfs_lock_context *l_ctx, struct page *page,
+ unsigned int pgbase, unsigned int offset,
unsigned int count)
{
struct nfs_page *req;
- struct nfs_lock_context *l_ctx;
+ struct nfs_open_context *ctx = l_ctx->open_context;
if (test_bit(NFS_CONTEXT_BAD, &ctx->flags))
return ERR_PTR(-EBADF);
@@ -322,13 +311,8 @@
if (req == NULL)
return ERR_PTR(-ENOMEM);
- /* get lock context early so we can deal with alloc failures */
- l_ctx = nfs_get_lock_context(ctx);
- if (IS_ERR(l_ctx)) {
- nfs_page_free(req);
- return ERR_CAST(l_ctx);
- }
req->wb_lock_context = l_ctx;
+ refcount_inc(&l_ctx->count);
atomic_inc(&l_ctx->io_count);
/* Initialize the request struct. Initially, we assume a
@@ -340,17 +324,61 @@
get_page(page);
}
req->wb_offset = offset;
- req->wb_pgbase = offset;
+ req->wb_pgbase = pgbase;
req->wb_bytes = count;
- req->wb_context = get_nfs_open_context(ctx);
kref_init(&req->wb_kref);
- nfs_page_group_init(req, last);
+ req->wb_nio = 0;
return req;
}
/**
+ * nfs_create_request - Create an NFS read/write request.
+ * @ctx: open context to use
+ * @page: page to write
+ * @offset: starting offset within the page for the write
+ * @count: number of bytes to read/write
+ *
+ * The page must be locked by the caller. This makes sure we never
+ * create two different requests for the same page.
+ * User should ensure it is safe to sleep in this function.
+ */
+struct nfs_page *
+nfs_create_request(struct nfs_open_context *ctx, struct page *page,
+ unsigned int offset, unsigned int count)
+{
+ struct nfs_lock_context *l_ctx = nfs_get_lock_context(ctx);
+ struct nfs_page *ret;
+
+ if (IS_ERR(l_ctx))
+ return ERR_CAST(l_ctx);
+ ret = __nfs_create_request(l_ctx, page, offset, offset, count);
+ if (!IS_ERR(ret))
+ nfs_page_group_init(ret, NULL);
+ nfs_put_lock_context(l_ctx);
+ return ret;
+}
+
+static struct nfs_page *
+nfs_create_subreq(struct nfs_page *req, struct nfs_page *last,
+ unsigned int pgbase, unsigned int offset,
+ unsigned int count)
+{
+ struct nfs_page *ret;
+
+ ret = __nfs_create_request(req->wb_lock_context, req->wb_page,
+ pgbase, offset, count);
+ if (!IS_ERR(ret)) {
+ nfs_lock_request(ret);
+ ret->wb_index = req->wb_index;
+ nfs_page_group_init(ret, last);
+ ret->wb_nio = req->wb_nio;
+ }
+ return ret;
+}
+
+/**
* nfs_unlock_request - Unlock request and wake up sleepers.
- * @req:
+ * @req: pointer to request
*/
void nfs_unlock_request(struct nfs_page *req)
{
@@ -368,7 +396,7 @@
/**
* nfs_unlock_and_release_request - Unlock request and release the nfs_page
- * @req:
+ * @req: pointer to request
*/
void nfs_unlock_and_release_request(struct nfs_page *req)
{
@@ -386,8 +414,8 @@
static void nfs_clear_request(struct nfs_page *req)
{
struct page *page = req->wb_page;
- struct nfs_open_context *ctx = req->wb_context;
struct nfs_lock_context *l_ctx = req->wb_lock_context;
+ struct nfs_open_context *ctx;
if (page != NULL) {
put_page(page);
@@ -396,16 +424,13 @@
if (l_ctx != NULL) {
if (atomic_dec_and_test(&l_ctx->io_count)) {
wake_up_var(&l_ctx->io_count);
+ ctx = l_ctx->open_context;
if (test_bit(NFS_CONTEXT_UNLOCK, &ctx->flags))
rpc_wake_up(&NFS_SERVER(d_inode(ctx->dentry))->uoc_rpcwaitq);
}
nfs_put_lock_context(l_ctx);
req->wb_lock_context = NULL;
}
- if (ctx != NULL) {
- put_nfs_open_context(ctx);
- req->wb_context = NULL;
- }
}
/**
@@ -461,7 +486,7 @@
* @prev: previous request in desc, or NULL
* @req: this request
*
- * Returns zero if @req can be coalesced into @desc, otherwise it returns
+ * Returns zero if @req cannot be coalesced into @desc, otherwise it returns
* the size of the request.
*/
size_t nfs_generic_pg_test(struct nfs_pageio_descriptor *desc,
@@ -494,7 +519,6 @@
if (hdr) {
INIT_LIST_HEAD(&hdr->pages);
- spin_lock_init(&hdr->lock);
hdr->rw_ops = ops;
}
return hdr;
@@ -532,7 +556,6 @@
* nfs_pgio_rpcsetup - Set up arguments for a pageio call
* @hdr: The pageio hdr
* @count: Number of bytes to read
- * @offset: Initial offset
* @how: How to commit data (writes only)
* @cinfo: Commit information for the call (writes only)
*/
@@ -552,7 +575,7 @@
hdr->args.pgbase = req->wb_pgbase;
hdr->args.pages = hdr->page_array.pagevec;
hdr->args.count = count;
- hdr->args.context = get_nfs_open_context(req->wb_context);
+ hdr->args.context = get_nfs_open_context(nfs_req_openctx(req));
hdr->args.lock_context = req->wb_lock_context;
hdr->args.stable = NFS_UNSTABLE;
switch (how & (FLUSH_STABLE | FLUSH_COND_STABLE)) {
@@ -567,7 +590,7 @@
}
hdr->res.fattr = &hdr->fattr;
- hdr->res.count = count;
+ hdr->res.count = 0;
hdr->res.eof = 0;
hdr->res.verf = &hdr->verf;
nfs_fattr_init(&hdr->fattr);
@@ -588,7 +611,7 @@
}
int nfs_initiate_pgio(struct rpc_clnt *clnt, struct nfs_pgio_header *hdr,
- struct rpc_cred *cred, const struct nfs_rpc_ops *rpc_ops,
+ const struct cred *cred, const struct nfs_rpc_ops *rpc_ops,
const struct rpc_call_ops *call_ops, int how, int flags)
{
struct rpc_task *task;
@@ -635,7 +658,6 @@
/**
* nfs_pgio_error - Clean up from a pageio error
- * @desc: IO descriptor
* @hdr: pageio header
*/
static void nfs_pgio_error(struct nfs_pgio_header *hdr)
@@ -701,6 +723,7 @@
desc->pg_mirrors_dynamic = NULL;
desc->pg_mirrors = desc->pg_mirrors_static;
nfs_pageio_mirror_init(&desc->pg_mirrors[0], bsize);
+ desc->pg_maxretrans = 0;
}
/**
@@ -752,8 +775,6 @@
if (pagecount <= ARRAY_SIZE(pg_array->page_array))
pg_array->pagevec = pg_array->page_array;
else {
- if (hdr->rw_mode == FMODE_WRITE)
- gfp_flags = GFP_NOIO;
pg_array->pagevec = kcalloc(pagecount, sizeof(struct page *), gfp_flags);
if (!pg_array->pagevec) {
pg_array->npages = 0;
@@ -769,8 +790,7 @@
pageused = 0;
while (!list_empty(head)) {
req = nfs_list_entry(head->next);
- nfs_list_remove_request(req);
- nfs_list_add_request(req, &hdr->pages);
+ nfs_list_move_request(req, &hdr->pages);
if (!last_page || last_page != req->wb_page) {
pageused++;
@@ -829,7 +849,7 @@
desc->pg_mirrors_dynamic = NULL;
if (mirror_count == 1)
return desc->pg_mirrors_static;
- ret = kmalloc_array(mirror_count, sizeof(*ret), GFP_NOFS);
+ ret = kmalloc_array(mirror_count, sizeof(*ret), GFP_KERNEL);
if (ret != NULL) {
for (i = 0; i < mirror_count; i++)
nfs_pageio_mirror_init(&ret[i], desc->pg_bsize);
@@ -894,6 +914,7 @@
* nfs_can_coalesce_requests - test two requests for compatibility
* @prev: pointer to nfs_page
* @req: pointer to nfs_page
+ * @pgio: pointer to nfs_pagio_descriptor
*
* The nfs_page structures 'prev' and 'req' are compared to ensure that the
* page data area they describe is contiguous, and that their RPC
@@ -909,9 +930,9 @@
struct file_lock_context *flctx;
if (prev) {
- if (!nfs_match_open_context(req->wb_context, prev->wb_context))
+ if (!nfs_match_open_context(nfs_req_openctx(req), nfs_req_openctx(prev)))
return false;
- flctx = d_inode(req->wb_context->dentry)->i_flctx;
+ flctx = d_inode(nfs_req_openctx(req)->dentry)->i_flctx;
if (flctx != NULL &&
!(list_empty_careful(&flctx->flc_posix) &&
list_empty_careful(&flctx->flc_flock)) &&
@@ -960,10 +981,18 @@
return 0;
mirror->pg_base = req->wb_pgbase;
}
+
+ if (desc->pg_maxretrans && req->wb_nio > desc->pg_maxretrans) {
+ if (NFS_SERVER(desc->pg_inode)->flags & NFS_MOUNT_SOFTERR)
+ desc->pg_error = -ETIMEDOUT;
+ else
+ desc->pg_error = -EIO;
+ return 0;
+ }
+
if (!nfs_can_coalesce_requests(prev, req, desc))
return 0;
- nfs_list_remove_request(req);
- nfs_list_add_request(req, &mirror->pg_list);
+ nfs_list_move_request(req, &mirror->pg_list);
mirror->pg_count += req->wb_bytes;
return 1;
}
@@ -989,6 +1018,16 @@
}
}
+static void
+nfs_pageio_cleanup_request(struct nfs_pageio_descriptor *desc,
+ struct nfs_page *req)
+{
+ LIST_HEAD(head);
+
+ nfs_list_move_request(req, &head);
+ desc->pg_completion_ops->error_cleanup(&head, desc->pg_error);
+}
+
/**
* nfs_pageio_add_request - Attempt to coalesce a request into a page list.
* @desc: destination io descriptor
@@ -1026,10 +1065,8 @@
nfs_page_group_unlock(req);
desc->pg_moreio = 1;
nfs_pageio_doio(desc);
- if (desc->pg_error < 0)
- return 0;
- if (mirror->pg_recoalesce)
- return 0;
+ if (desc->pg_error < 0 || mirror->pg_recoalesce)
+ goto out_cleanup_subreq;
/* retry add_request for this subreq */
nfs_page_group_lock(req);
continue;
@@ -1045,14 +1082,10 @@
pgbase += subreq->wb_bytes;
if (bytes_left) {
- subreq = nfs_create_request(req->wb_context,
- req->wb_page,
- subreq, pgbase, bytes_left);
+ subreq = nfs_create_subreq(req, subreq, pgbase,
+ offset, bytes_left);
if (IS_ERR(subreq))
goto err_ptr;
- nfs_lock_request(subreq);
- subreq->wb_offset = offset;
- subreq->wb_index = req->wb_index;
}
} while (bytes_left > 0);
@@ -1062,6 +1095,10 @@
desc->pg_error = PTR_ERR(subreq);
nfs_page_group_unlock(req);
return 0;
+out_cleanup_subreq:
+ if (req != subreq)
+ nfs_pageio_cleanup_request(desc, subreq);
+ return 0;
}
static int nfs_do_recoalesce(struct nfs_pageio_descriptor *desc)
@@ -1080,7 +1117,6 @@
struct nfs_page *req;
req = list_first_entry(&head, struct nfs_page, wb_list);
- nfs_list_remove_request(req);
if (__nfs_pageio_add_request(desc, req))
continue;
if (desc->pg_error < 0) {
@@ -1121,7 +1157,8 @@
for (midx = 0; midx < desc->pg_mirror_count; midx++) {
mirror = &desc->pg_mirrors[midx];
- desc->pg_completion_ops->error_cleanup(&mirror->pg_list);
+ desc->pg_completion_ops->error_cleanup(&mirror->pg_list,
+ desc->pg_error);
}
}
@@ -1150,35 +1187,29 @@
lastreq = lastreq->wb_this_page)
;
- dupreq = nfs_create_request(req->wb_context,
- req->wb_page, lastreq, pgbase, bytes);
+ dupreq = nfs_create_subreq(req, lastreq,
+ pgbase, offset, bytes);
+ nfs_page_group_unlock(req);
if (IS_ERR(dupreq)) {
- nfs_page_group_unlock(req);
desc->pg_error = PTR_ERR(dupreq);
goto out_failed;
}
-
- nfs_lock_request(dupreq);
- nfs_page_group_unlock(req);
- dupreq->wb_offset = offset;
- dupreq->wb_index = req->wb_index;
} else
dupreq = req;
if (nfs_pgio_has_mirroring(desc))
desc->pg_mirror_idx = midx;
if (!nfs_pageio_add_request_mirror(desc, dupreq))
- goto out_failed;
+ goto out_cleanup_subreq;
}
return 1;
+out_cleanup_subreq:
+ if (req != dupreq)
+ nfs_pageio_cleanup_request(desc, dupreq);
out_failed:
- /* remember fatal errors */
- if (nfs_error_is_fatal(desc->pg_error))
- nfs_context_set_write_error(req->wb_context,
- desc->pg_error);
nfs_pageio_error_cleanup(desc);
return 0;
}
@@ -1199,7 +1230,7 @@
desc->pg_mirror_idx = mirror_idx;
for (;;) {
nfs_pageio_doio(desc);
- if (!mirror->pg_recoalesce)
+ if (desc->pg_error < 0 || !mirror->pg_recoalesce)
break;
if (!nfs_do_recoalesce(desc))
break;
@@ -1220,21 +1251,23 @@
int nfs_pageio_resend(struct nfs_pageio_descriptor *desc,
struct nfs_pgio_header *hdr)
{
- LIST_HEAD(failed);
+ LIST_HEAD(pages);
desc->pg_io_completion = hdr->io_completion;
desc->pg_dreq = hdr->dreq;
- while (!list_empty(&hdr->pages)) {
- struct nfs_page *req = nfs_list_entry(hdr->pages.next);
+ list_splice_init(&hdr->pages, &pages);
+ while (!list_empty(&pages)) {
+ struct nfs_page *req = nfs_list_entry(pages.next);
- nfs_list_remove_request(req);
if (!nfs_pageio_add_request(desc, req))
- nfs_list_add_request(req, &failed);
+ break;
}
nfs_pageio_complete(desc);
- if (!list_empty(&failed)) {
- list_move(&failed, &hdr->pages);
- return desc->pg_error < 0 ? desc->pg_error : -EIO;
+ if (!list_empty(&pages)) {
+ int err = desc->pg_error < 0 ? desc->pg_error : -EIO;
+ hdr->completion_ops->error_cleanup(&pages, err);
+ nfs_set_pgio_error(hdr, err, hdr->io_start);
+ return err;
}
return 0;
}
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 7d9a51e..bb80034 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -275,7 +275,7 @@
list_del_init(&lo->plh_layouts);
spin_unlock(&clp->cl_lock);
}
- put_rpccred(lo->plh_lc_cred);
+ put_cred(lo->plh_lc_cred);
return ld->free_layout_hdr(lo);
}
@@ -359,9 +359,10 @@
}
/*
- * Update the seqid of a layout stateid
+ * Update the seqid of a layout stateid after receiving
+ * NFS4ERR_OLD_STATEID
*/
-bool nfs4_layoutreturn_refresh_stateid(nfs4_stateid *dst,
+bool nfs4_layout_refresh_old_stateid(nfs4_stateid *dst,
struct pnfs_layout_range *dst_range,
struct inode *inode)
{
@@ -377,7 +378,15 @@
spin_lock(&inode->i_lock);
lo = NFS_I(inode)->layout;
- if (lo && nfs4_stateid_match_other(dst, &lo->plh_stateid)) {
+ if (lo && pnfs_layout_is_valid(lo) &&
+ nfs4_stateid_match_other(dst, &lo->plh_stateid)) {
+ /* Is our call using the most recent seqid? If so, bump it */
+ if (!nfs4_stateid_is_newer(&lo->plh_stateid, dst)) {
+ nfs4_stateid_seqid_inc(dst);
+ ret = true;
+ goto out;
+ }
+ /* Try to update the seqid to the most recent */
err = pnfs_mark_matching_lsegs_return(lo, &head, &range, 0);
if (err != -EBUSY) {
dst->seqid = lo->plh_stateid.seqid;
@@ -385,6 +394,7 @@
ret = true;
}
}
+out:
spin_unlock(&inode->i_lock);
pnfs_free_lseg_list(&head);
return ret;
@@ -758,22 +768,35 @@
pnfs_layout_bulk_destroy_byserver_locked(struct nfs_client *clp,
struct nfs_server *server,
struct list_head *layout_list)
+ __must_hold(&clp->cl_lock)
+ __must_hold(RCU)
{
struct pnfs_layout_hdr *lo, *next;
struct inode *inode;
list_for_each_entry_safe(lo, next, &server->layouts, plh_layouts) {
- if (test_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags))
+ if (test_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags) ||
+ test_bit(NFS_LAYOUT_INODE_FREEING, &lo->plh_flags) ||
+ !list_empty(&lo->plh_bulk_destroy))
continue;
+ /* If the sb is being destroyed, just bail */
+ if (!nfs_sb_active(server->super))
+ break;
inode = igrab(lo->plh_inode);
- if (inode == NULL)
- continue;
- list_del_init(&lo->plh_layouts);
- if (pnfs_layout_add_bulk_destroy_list(inode, layout_list))
- continue;
- rcu_read_unlock();
- spin_unlock(&clp->cl_lock);
- iput(inode);
+ if (inode != NULL) {
+ list_del_init(&lo->plh_layouts);
+ if (pnfs_layout_add_bulk_destroy_list(inode,
+ layout_list))
+ continue;
+ rcu_read_unlock();
+ spin_unlock(&clp->cl_lock);
+ iput(inode);
+ } else {
+ rcu_read_unlock();
+ spin_unlock(&clp->cl_lock);
+ set_bit(NFS_LAYOUT_INODE_FREEING, &lo->plh_flags);
+ }
+ nfs_sb_deactive(server->super);
spin_lock(&clp->cl_lock);
rcu_read_lock();
return -EAGAIN;
@@ -811,7 +834,7 @@
/* Free all lsegs that are attached to commit buckets */
nfs_commit_inode(inode, 0);
pnfs_put_layout_hdr(lo);
- iput(inode);
+ nfs_iput_and_deactive(inode);
}
return ret;
}
@@ -965,7 +988,7 @@
struct page **pages;
int i;
- pages = kcalloc(size, sizeof(struct page *), gfp_flags);
+ pages = kmalloc_array(size, sizeof(struct page *), gfp_flags);
if (!pages) {
dprintk("%s: can't alloc array of %zu pages\n", __func__, size);
return NULL;
@@ -975,7 +998,7 @@
pages[i] = alloc_page(gfp_flags);
if (!pages[i]) {
dprintk("%s: failed to allocate page\n", __func__);
- nfs4_free_pages(pages, size);
+ nfs4_free_pages(pages, i);
return NULL;
}
}
@@ -991,6 +1014,7 @@
gfp_t gfp_flags)
{
struct nfs_server *server = pnfs_find_server(ino, ctx);
+ size_t max_reply_sz = server->pnfs_curr_ld->max_layoutget_response;
size_t max_pages = max_response_pages(server);
struct nfs4_layoutget *lgp;
@@ -1000,6 +1024,12 @@
if (lgp == NULL)
return NULL;
+ if (max_reply_sz) {
+ size_t npages = (max_reply_sz + PAGE_SIZE - 1) >> PAGE_SHIFT;
+ if (npages < max_pages)
+ max_pages = npages;
+ }
+
lgp->args.layout.pages = nfs4_alloc_pages(max_pages, gfp_flags);
if (!lgp->args.layout.pages) {
kfree(lgp);
@@ -1031,7 +1061,7 @@
lgp->args.ctx = get_nfs_open_context(ctx);
nfs4_stateid_copy(&lgp->args.stateid, stateid);
lgp->gfp_flags = gfp_flags;
- lgp->cred = get_rpccred(ctx->cred);
+ lgp->cred = get_cred(ctx->cred);
return lgp;
}
@@ -1042,7 +1072,7 @@
nfs4_free_pages(lgp->args.layout.pages, max_pages);
if (lgp->args.inode)
pnfs_put_layout_hdr(NFS_I(lgp->args.inode)->layout);
- put_rpccred(lgp->cred);
+ put_cred(lgp->cred);
put_nfs_open_context(lgp->args.ctx);
kfree(lgp);
}
@@ -1317,7 +1347,7 @@
bool pnfs_roc(struct inode *ino,
struct nfs4_layoutreturn_args *args,
struct nfs4_layoutreturn_res *res,
- const struct rpc_cred *cred)
+ const struct cred *cred)
{
struct nfs_inode *nfsi = NFS_I(ino);
struct nfs_open_context *ctx;
@@ -1332,6 +1362,7 @@
if (!nfs_have_layout(ino))
return false;
retry:
+ rcu_read_lock();
spin_lock(&ino->i_lock);
lo = nfsi->layout;
if (!lo || !pnfs_layout_is_valid(lo) ||
@@ -1342,6 +1373,7 @@
pnfs_get_layout_hdr(lo);
if (test_bit(NFS_LAYOUT_RETURN_LOCK, &lo->plh_flags)) {
spin_unlock(&ino->i_lock);
+ rcu_read_unlock();
wait_on_bit(&lo->plh_flags, NFS_LAYOUT_RETURN,
TASK_UNINTERRUPTIBLE);
pnfs_put_layout_hdr(lo);
@@ -1355,7 +1387,7 @@
skip_read = true;
}
- list_for_each_entry(ctx, &nfsi->open_files, list) {
+ list_for_each_entry_rcu(ctx, &nfsi->open_files, list) {
state = ctx->state;
if (state == NULL)
continue;
@@ -1403,6 +1435,7 @@
out_noroc:
spin_unlock(&ino->i_lock);
+ rcu_read_unlock();
pnfs_layoutcommit_inode(ino, true);
if (roc) {
struct pnfs_layoutdriver_type *ld = NFS_SERVER(ino)->pnfs_curr_ld;
@@ -1417,6 +1450,52 @@
return false;
}
+int pnfs_roc_done(struct rpc_task *task, struct inode *inode,
+ struct nfs4_layoutreturn_args **argpp,
+ struct nfs4_layoutreturn_res **respp,
+ int *ret)
+{
+ struct nfs4_layoutreturn_args *arg = *argpp;
+ int retval = -EAGAIN;
+
+ if (!arg)
+ return 0;
+ /* Handle Layoutreturn errors */
+ switch (*ret) {
+ case 0:
+ retval = 0;
+ break;
+ case -NFS4ERR_NOMATCHING_LAYOUT:
+ /* Was there an RPC level error? If not, retry */
+ if (task->tk_rpc_status == 0)
+ break;
+ /* If the call was not sent, let caller handle it */
+ if (!RPC_WAS_SENT(task))
+ return 0;
+ /*
+ * Otherwise, assume the call succeeded and
+ * that we need to release the layout
+ */
+ *ret = 0;
+ (*respp)->lrs_present = 0;
+ retval = 0;
+ break;
+ case -NFS4ERR_DELAY:
+ /* Let the caller handle the retry */
+ *ret = -NFS4ERR_NOMATCHING_LAYOUT;
+ return 0;
+ case -NFS4ERR_OLD_STATEID:
+ if (!nfs4_layout_refresh_old_stateid(&arg->stateid,
+ &arg->range, inode))
+ break;
+ *ret = -NFS4ERR_NOMATCHING_LAYOUT;
+ return -EAGAIN;
+ }
+ *argpp = NULL;
+ *respp = NULL;
+ return retval;
+}
+
void pnfs_roc_release(struct nfs4_layoutreturn_args *args,
struct nfs4_layoutreturn_res *res,
int ret)
@@ -1426,10 +1505,15 @@
const nfs4_stateid *res_stateid = NULL;
struct nfs4_xdr_opaque_data *ld_private = args->ld_private;
- if (ret == 0) {
- arg_stateid = &args->stateid;
+ switch (ret) {
+ case -NFS4ERR_NOMATCHING_LAYOUT:
+ break;
+ case 0:
if (res->lrs_present)
res_stateid = &res->stateid;
+ /* Fallthrough */
+ default:
+ arg_stateid = &args->stateid;
}
pnfs_layoutreturn_free_lsegs(lo, arg_stateid, &args->range,
res_stateid);
@@ -1573,7 +1657,7 @@
INIT_LIST_HEAD(&lo->plh_return_segs);
INIT_LIST_HEAD(&lo->plh_bulk_destroy);
lo->plh_inode = ino;
- lo->plh_lc_cred = get_rpccred(ctx->cred);
+ lo->plh_lc_cred = get_cred(ctx->cred);
lo->plh_flags |= 1 << NFS_LAYOUT_INVALID_STID;
return lo;
}
@@ -1866,8 +1950,8 @@
atomic_read(&lo->plh_outstanding) != 0) {
spin_unlock(&ino->i_lock);
lseg = ERR_PTR(wait_var_event_killable(&lo->plh_outstanding,
- atomic_read(&lo->plh_outstanding)));
- if (IS_ERR(lseg) || !list_empty(&lo->plh_segs))
+ !atomic_read(&lo->plh_outstanding)));
+ if (IS_ERR(lseg))
goto out_put_layout_hdr;
pnfs_put_layout_hdr(lo);
goto lookup_again;
@@ -1880,18 +1964,13 @@
goto out_unlock;
}
- if (!nfs4_valid_open_stateid(ctx->state)) {
- trace_pnfs_update_layout(ino, pos, count, iomode, lo, lseg,
- PNFS_UPDATE_LAYOUT_INVALID_OPEN);
- goto out_unlock;
- }
-
/*
* Choose a stateid for the LAYOUTGET. If we don't have a layout
* stateid, or it has been invalidated, then we must use the open
* stateid.
*/
if (test_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags)) {
+ int status;
/*
* The first layoutget for the file. Need to serialize per
@@ -1911,13 +1990,21 @@
}
first = true;
- if (nfs4_select_rw_stateid(ctx->state,
+ status = nfs4_select_rw_stateid(ctx->state,
iomode == IOMODE_RW ? FMODE_WRITE : FMODE_READ,
- NULL, &stateid, NULL) != 0) {
+ NULL, &stateid, NULL);
+ if (status != 0) {
+ lseg = ERR_PTR(status);
trace_pnfs_update_layout(ino, pos, count,
iomode, lo, lseg,
PNFS_UPDATE_LAYOUT_INVALID_OPEN);
- goto out_unlock;
+ if (status != -EAGAIN)
+ goto out_unlock;
+ spin_unlock(&ino->i_lock);
+ nfs4_schedule_stateid_recovery(server, ctx->state);
+ pnfs_clear_first_layoutget(lo);
+ pnfs_put_layout_hdr(lo);
+ goto lookup_again;
}
} else {
nfs4_stateid_copy(&stateid, &lo->plh_stateid);
@@ -2006,6 +2093,8 @@
out_put_layout_hdr:
if (first)
pnfs_clear_first_layoutget(lo);
+ trace_pnfs_update_layout(ino, pos, count, iomode, lo, lseg,
+ PNFS_UPDATE_LAYOUT_EXIT);
pnfs_put_layout_hdr(lo);
out:
dprintk("%s: inode %s/%llu pNFS layout segment %s for "
@@ -2413,7 +2502,7 @@
rd_size = nfs_dreq_bytes_left(pgio->pg_dreq);
pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
- req->wb_context,
+ nfs_req_openctx(req),
req_offset(req),
rd_size,
IOMODE_READ,
@@ -2440,12 +2529,12 @@
pnfs_generic_pg_check_range(pgio, req);
if (pgio->pg_lseg == NULL) {
pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
- req->wb_context,
+ nfs_req_openctx(req),
req_offset(req),
wb_size,
IOMODE_RW,
false,
- GFP_NOFS);
+ GFP_KERNEL);
if (IS_ERR(pgio->pg_lseg)) {
pgio->pg_error = PTR_ERR(pgio->pg_lseg);
pgio->pg_lseg = NULL;
@@ -2918,7 +3007,7 @@
spin_unlock(&inode->i_lock);
data->args.inode = inode;
- data->cred = get_rpccred(nfsi->layout->plh_lc_cred);
+ data->cred = get_cred(nfsi->layout->plh_lc_cred);
nfs_fattr_init(&data->fattr);
data->args.bitmask = NFS_SERVER(inode)->cache_consistency_bitmask;
data->res.fattr = &data->fattr;
@@ -2931,7 +3020,7 @@
if (ld->prepare_layoutcommit) {
status = ld->prepare_layoutcommit(&data->args);
if (status) {
- put_rpccred(data->cred);
+ put_cred(data->cred);
spin_lock(&inode->i_lock);
set_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags);
if (end_pos > nfsi->layout->plh_lwb)
diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h
index ece367e..f8a3806 100644
--- a/fs/nfs/pnfs.h
+++ b/fs/nfs/pnfs.h
@@ -104,6 +104,7 @@
NFS_LAYOUT_RETURN_REQUESTED, /* Return this layout ASAP */
NFS_LAYOUT_INVALID_STID, /* layout stateid id is invalid */
NFS_LAYOUT_FIRST_LAYOUTGET, /* Serialize first layoutget */
+ NFS_LAYOUT_INODE_FREEING, /* The inode is being freed */
};
enum layoutdriver_policy_flags {
@@ -125,6 +126,7 @@
struct module *owner;
unsigned flags;
unsigned max_deviceinfo_size;
+ unsigned max_layoutget_response;
int (*set_layoutdriver) (struct nfs_server *, const struct nfs_fh *);
int (*clear_layoutdriver) (struct nfs_server *);
@@ -199,7 +201,7 @@
u32 plh_return_seq;
enum pnfs_iomode plh_return_iomode;
loff_t plh_lwb; /* last write byte for layoutcommit */
- struct rpc_cred *plh_lc_cred; /* layoutcommit cred */
+ const struct cred *plh_lc_cred; /* layoutcommit cred */
struct inode *plh_inode;
};
@@ -229,7 +231,7 @@
extern size_t max_response_pages(struct nfs_server *server);
extern int nfs4_proc_getdeviceinfo(struct nfs_server *server,
struct pnfs_device *dev,
- struct rpc_cred *cred);
+ const struct cred *cred);
extern struct pnfs_layout_segment* nfs4_proc_layoutget(struct nfs4_layoutget *lgp, long *timeout);
extern int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp, bool sync);
@@ -259,7 +261,7 @@
bool is_recall);
int pnfs_destroy_layouts_byclid(struct nfs_client *clp,
bool is_recall);
-bool nfs4_layoutreturn_refresh_stateid(nfs4_stateid *dst,
+bool nfs4_layout_refresh_old_stateid(nfs4_stateid *dst,
struct pnfs_layout_range *dst_range,
struct inode *inode);
void pnfs_put_layout_hdr(struct pnfs_layout_hdr *lo);
@@ -279,7 +281,11 @@
bool pnfs_roc(struct inode *ino,
struct nfs4_layoutreturn_args *args,
struct nfs4_layoutreturn_res *res,
- const struct rpc_cred *cred);
+ const struct cred *cred);
+int pnfs_roc_done(struct rpc_task *task, struct inode *inode,
+ struct nfs4_layoutreturn_args **argpp,
+ struct nfs4_layoutreturn_res **respp,
+ int *ret);
void pnfs_roc_release(struct nfs4_layoutreturn_args *args,
struct nfs4_layoutreturn_res *res,
int ret);
@@ -342,12 +348,13 @@
struct nfs4_deviceid_node *
nfs4_find_get_deviceid(struct nfs_server *server,
- const struct nfs4_deviceid *id, struct rpc_cred *cred,
+ const struct nfs4_deviceid *id, const struct cred *cred,
gfp_t gfp_mask);
void nfs4_delete_deviceid(const struct pnfs_layoutdriver_type *, const struct nfs_client *, const struct nfs4_deviceid *);
void nfs4_init_deviceid_node(struct nfs4_deviceid_node *, struct nfs_server *,
const struct nfs4_deviceid *);
bool nfs4_put_deviceid_node(struct nfs4_deviceid_node *);
+void nfs4_mark_deviceid_available(struct nfs4_deviceid_node *node);
void nfs4_mark_deviceid_unavailable(struct nfs4_deviceid_node *node);
bool nfs4_test_deviceid_unavailable(struct nfs4_deviceid_node *node);
void nfs4_deviceid_purge_client(const struct nfs_client *);
@@ -456,7 +463,7 @@
pnfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg,
struct nfs_commit_info *cinfo, u32 ds_commit_idx)
{
- struct inode *inode = d_inode(req->wb_context->dentry);
+ struct inode *inode = d_inode(nfs_req_openctx(req)->dentry);
struct pnfs_layoutdriver_type *ld = NFS_SERVER(inode)->pnfs_curr_ld;
if (lseg == NULL || ld->mark_request_commit == NULL)
@@ -468,7 +475,7 @@
static inline bool
pnfs_clear_request_commit(struct nfs_page *req, struct nfs_commit_info *cinfo)
{
- struct inode *inode = d_inode(req->wb_context->dentry);
+ struct inode *inode = d_inode(nfs_req_openctx(req)->dentry);
struct pnfs_layoutdriver_type *ld = NFS_SERVER(inode)->pnfs_curr_ld;
if (ld == NULL || ld->clear_request_commit == NULL)
@@ -693,11 +700,20 @@
pnfs_roc(struct inode *ino,
struct nfs4_layoutreturn_args *args,
struct nfs4_layoutreturn_res *res,
- const struct rpc_cred *cred)
+ const struct cred *cred)
{
return false;
}
+static inline int
+pnfs_roc_done(struct rpc_task *task, struct inode *inode,
+ struct nfs4_layoutreturn_args **argpp,
+ struct nfs4_layoutreturn_res **respp,
+ int *ret)
+{
+ return 0;
+}
+
static inline void
pnfs_roc_release(struct nfs4_layoutreturn_args *args,
struct nfs4_layoutreturn_res *res,
@@ -782,7 +798,7 @@
{
}
-static inline bool nfs4_layoutreturn_refresh_stateid(nfs4_stateid *dst,
+static inline bool nfs4_layout_refresh_old_stateid(nfs4_stateid *dst,
struct pnfs_layout_range *dst_range,
struct inode *inode)
{
diff --git a/fs/nfs/pnfs_dev.c b/fs/nfs/pnfs_dev.c
index e8a07b3..537b80d 100644
--- a/fs/nfs/pnfs_dev.c
+++ b/fs/nfs/pnfs_dev.c
@@ -94,7 +94,7 @@
static struct nfs4_deviceid_node *
nfs4_get_device_info(struct nfs_server *server,
const struct nfs4_deviceid *dev_id,
- struct rpc_cred *cred, gfp_t gfp_flags)
+ const struct cred *cred, gfp_t gfp_flags)
{
struct nfs4_deviceid_node *d = NULL;
struct pnfs_device *pdev = NULL;
@@ -184,7 +184,7 @@
struct nfs4_deviceid_node *
nfs4_find_get_deviceid(struct nfs_server *server,
- const struct nfs4_deviceid *id, struct rpc_cred *cred,
+ const struct nfs4_deviceid *id, const struct cred *cred,
gfp_t gfp_mask)
{
long hash = nfs4_deviceid_hash(id);
@@ -284,10 +284,22 @@
EXPORT_SYMBOL_GPL(nfs4_put_deviceid_node);
void
+nfs4_mark_deviceid_available(struct nfs4_deviceid_node *node)
+{
+ if (test_bit(NFS_DEVICEID_UNAVAILABLE, &node->flags)) {
+ clear_bit(NFS_DEVICEID_UNAVAILABLE, &node->flags);
+ smp_mb__after_atomic();
+ }
+}
+EXPORT_SYMBOL_GPL(nfs4_mark_deviceid_available);
+
+void
nfs4_mark_deviceid_unavailable(struct nfs4_deviceid_node *node)
{
node->timestamp_unavailable = jiffies;
+ smp_mb__before_atomic();
set_bit(NFS_DEVICEID_UNAVAILABLE, &node->flags);
+ smp_mb__after_atomic();
}
EXPORT_SYMBOL_GPL(nfs4_mark_deviceid_unavailable);
@@ -302,6 +314,7 @@
if (time_in_range(node->timestamp_unavailable, start, end))
return true;
clear_bit(NFS_DEVICEID_UNAVAILABLE, &node->flags);
+ smp_mb__after_atomic();
}
return false;
}
diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c
index d5e4d3c..82af480 100644
--- a/fs/nfs/pnfs_nfs.c
+++ b/fs/nfs/pnfs_nfs.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* Common NFS I/O operations for the pnfs file based
* layout drivers.
@@ -626,11 +627,16 @@
/* Add this address as an alias */
rpc_clnt_add_xprt(clp->cl_rpcclient, &xprt_args,
rpc_clnt_test_and_add_xprt, NULL);
- } else
- clp = get_v3_ds_connect(mds_srv,
- (struct sockaddr *)&da->da_addr,
- da->da_addrlen, IPPROTO_TCP,
- timeo, retrans);
+ continue;
+ }
+ clp = get_v3_ds_connect(mds_srv,
+ (struct sockaddr *)&da->da_addr,
+ da->da_addrlen, IPPROTO_TCP,
+ timeo, retrans);
+ if (IS_ERR(clp))
+ continue;
+ clp->cl_rpcclient->cl_softerr = 0;
+ clp->cl_rpcclient->cl_softrtry = 0;
}
if (IS_ERR(clp)) {
@@ -686,7 +692,7 @@
rpc_clnt_setup_test_and_add_xprt,
&rpcdata);
if (xprtdata.cred)
- put_rpccred(xprtdata.cred);
+ put_cred(xprtdata.cred);
} else {
clp = nfs4_set_ds_client(mds_srv,
(struct sockaddr *)&da->da_addr,
diff --git a/fs/nfs/proc.c b/fs/nfs/proc.c
index e0c257b..0f7288b 100644
--- a/fs/nfs/proc.c
+++ b/fs/nfs/proc.c
@@ -490,7 +490,7 @@
* from nfs_readdir by calling the decode_entry function directly.
*/
static int
-nfs_proc_readdir(struct dentry *dentry, struct rpc_cred *cred,
+nfs_proc_readdir(struct dentry *dentry, const struct cred *cred,
u64 cookie, struct page **pages, unsigned int count, bool plus)
{
struct inode *dir = d_inode(dentry);
@@ -594,7 +594,8 @@
/* Emulate the eof flag, which isn't normally needed in NFSv2
* as it is guaranteed to always return the file attributes
*/
- if (hdr->args.offset + hdr->res.count >= hdr->res.fattr->size)
+ if ((hdr->res.count == 0 && hdr->args.count > 0) ||
+ hdr->args.offset + hdr->res.count >= hdr->res.fattr->size)
hdr->res.eof = 1;
}
return 0;
@@ -615,8 +616,10 @@
static int nfs_write_done(struct rpc_task *task, struct nfs_pgio_header *hdr)
{
- if (task->tk_status >= 0)
+ if (task->tk_status >= 0) {
+ hdr->res.count = hdr->args.count;
nfs_writeback_update_inode(hdr);
+ }
return 0;
}
diff --git a/fs/nfs/read.c b/fs/nfs/read.c
index 48d7277..cfe0b58 100644
--- a/fs/nfs/read.c
+++ b/fs/nfs/read.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* linux/fs/nfs/read.c
*
@@ -90,19 +91,25 @@
}
EXPORT_SYMBOL_GPL(nfs_pageio_reset_read_mds);
-static void nfs_readpage_release(struct nfs_page *req)
+static void nfs_readpage_release(struct nfs_page *req, int error)
{
- struct inode *inode = d_inode(req->wb_context->dentry);
+ struct inode *inode = d_inode(nfs_req_openctx(req)->dentry);
+ struct page *page = req->wb_page;
dprintk("NFS: read done (%s/%llu %d@%lld)\n", inode->i_sb->s_id,
(unsigned long long)NFS_FILEID(inode), req->wb_bytes,
(long long)req_offset(req));
+ if (nfs_error_is_fatal_on_server(error) && error != -ETIMEDOUT)
+ SetPageError(page);
if (nfs_page_group_sync_on_bit(req, PG_UNLOCKPAGE)) {
- if (PageUptodate(req->wb_page))
- nfs_readpage_to_fscache(inode, req->wb_page, 0);
+ struct address_space *mapping = page_file_mapping(page);
- unlock_page(req->wb_page);
+ if (PageUptodate(page))
+ nfs_readpage_to_fscache(inode, page, 0);
+ else if (!PageError(page) && !PagePrivate(page))
+ generic_error_remove_page(mapping, page);
+ unlock_page(page);
}
nfs_release_request(req);
}
@@ -118,7 +125,7 @@
len = nfs_page_length(page);
if (len == 0)
return nfs_return_empty_page(page);
- new = nfs_create_request(ctx, page, NULL, 0, len);
+ new = nfs_create_request(ctx, page, 0, len);
if (IS_ERR(new)) {
unlock_page(page);
return PTR_ERR(new);
@@ -130,7 +137,7 @@
&nfs_async_read_completion_ops);
if (!nfs_pageio_add_request(&pgio, new)) {
nfs_list_remove_request(new);
- nfs_readpage_release(new);
+ nfs_readpage_release(new, pgio.pg_error);
}
nfs_pageio_complete(&pgio);
@@ -152,6 +159,7 @@
static void nfs_read_completion(struct nfs_pgio_header *hdr)
{
unsigned long bytes = 0;
+ int error;
if (test_bit(NFS_IOHDR_REDO, &hdr->flags))
goto out;
@@ -178,14 +186,19 @@
zero_user_segment(page, start, end);
}
}
+ error = 0;
bytes += req->wb_bytes;
if (test_bit(NFS_IOHDR_ERROR, &hdr->flags)) {
if (bytes <= hdr->good_bytes)
nfs_page_group_set_uptodate(req);
+ else {
+ error = hdr->error;
+ xchg(&nfs_req_openctx(req)->error, error);
+ }
} else
nfs_page_group_set_uptodate(req);
nfs_list_remove_request(req);
- nfs_readpage_release(req);
+ nfs_readpage_release(req, error);
}
out:
hdr->release(hdr);
@@ -205,14 +218,14 @@
}
static void
-nfs_async_read_error(struct list_head *head)
+nfs_async_read_error(struct list_head *head, int error)
{
struct nfs_page *req;
while (!list_empty(head)) {
req = nfs_list_entry(head->next);
nfs_list_remove_request(req);
- nfs_readpage_release(req);
+ nfs_readpage_release(req, error);
}
}
@@ -276,16 +289,14 @@
struct nfs_pgio_header *hdr)
{
if (hdr->res.eof) {
- loff_t bound;
+ loff_t pos = hdr->args.offset + hdr->res.count;
+ unsigned int new = pos - hdr->io_start;
- bound = hdr->args.offset + hdr->res.count;
- spin_lock(&hdr->lock);
- if (bound < hdr->io_start + hdr->good_bytes) {
+ if (hdr->good_bytes > new) {
+ hdr->good_bytes = new;
set_bit(NFS_IOHDR_EOF, &hdr->flags);
clear_bit(NFS_IOHDR_ERROR, &hdr->flags);
- hdr->good_bytes = bound - hdr->io_start;
}
- spin_unlock(&hdr->lock);
} else if (hdr->res.count < hdr->args.count)
nfs_readpage_retry(task, hdr);
}
@@ -338,8 +349,13 @@
goto out;
}
+ xchg(&ctx->error, 0);
error = nfs_readpage_async(ctx, inode, page);
-
+ if (!error) {
+ error = wait_on_page_locked_killable(page);
+ if (!PageUptodate(page) && !error)
+ error = xchg(&ctx->error, 0);
+ }
out:
put_nfs_open_context(ctx);
return error;
@@ -365,7 +381,7 @@
if (len == 0)
return nfs_return_empty_page(page);
- new = nfs_create_request(desc->ctx, page, NULL, 0, len);
+ new = nfs_create_request(desc->ctx, page, 0, len);
if (IS_ERR(new))
goto out_error;
@@ -373,8 +389,8 @@
zero_user_segment(page, len, PAGE_SIZE);
if (!nfs_pageio_add_request(desc->pgio, new)) {
nfs_list_remove_request(new);
- nfs_readpage_release(new);
error = desc->pgio->pg_error;
+ nfs_readpage_release(new, error);
goto out;
}
return 0;
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index ac4b2f0..a84df7d 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* linux/fs/nfs/super.c
*
@@ -76,9 +77,11 @@
#define NFS_DEFAULT_VERSION 2
#endif
+#define NFS_MAX_CONNECTIONS 16
+
enum {
/* Mount options that take no arguments */
- Opt_soft, Opt_hard,
+ Opt_soft, Opt_softerr, Opt_hard,
Opt_posix, Opt_noposix,
Opt_cto, Opt_nocto,
Opt_ac, Opt_noac,
@@ -107,6 +110,7 @@
Opt_nfsvers,
Opt_sec, Opt_proto, Opt_mountproto, Opt_mounthost,
Opt_addr, Opt_mountaddr, Opt_clientaddr,
+ Opt_nconnect,
Opt_lookupcache,
Opt_fscache_uniq,
Opt_local_lock,
@@ -125,6 +129,7 @@
{ Opt_sloppy, "sloppy" },
{ Opt_soft, "soft" },
+ { Opt_softerr, "softerr" },
{ Opt_hard, "hard" },
{ Opt_deprecated, "intr" },
{ Opt_deprecated, "nointr" },
@@ -179,6 +184,8 @@
{ Opt_mounthost, "mounthost=%s" },
{ Opt_mountaddr, "mountaddr=%s" },
+ { Opt_nconnect, "nconnect=%s" },
+
{ Opt_lookupcache, "lookupcache=%s" },
{ Opt_fscache_uniq, "fsc=%s" },
{ Opt_local_lock, "local_lock=%s" },
@@ -309,7 +316,7 @@
const struct super_operations nfs_sops = {
.alloc_inode = nfs_alloc_inode,
- .destroy_inode = nfs_destroy_inode,
+ .free_inode = nfs_free_inode,
.write_inode = nfs_write_inode,
.drop_inode = nfs_drop_inode,
.statfs = nfs_statfs,
@@ -450,10 +457,8 @@
struct dentry *pd_dentry;
pd_dentry = dget_parent(dentry);
- if (pd_dentry != NULL) {
- nfs_zap_caches(d_inode(pd_dentry));
- dput(pd_dentry);
- }
+ nfs_zap_caches(d_inode(pd_dentry));
+ dput(pd_dentry);
}
nfs_free_fattr(res.fattr);
if (error < 0)
@@ -580,7 +585,7 @@
}
default:
if (showdefaults)
- seq_printf(m, ",mountaddr=unspecified");
+ seq_puts(m, ",mountaddr=unspecified");
}
if (nfss->mountd_version || showdefaults)
@@ -628,7 +633,8 @@
const char *str;
const char *nostr;
} nfs_info[] = {
- { NFS_MOUNT_SOFT, ",soft", ",hard" },
+ { NFS_MOUNT_SOFT, ",soft", "" },
+ { NFS_MOUNT_SOFTERR, ",softerr", "" },
{ NFS_MOUNT_POSIX, ",posix", "" },
{ NFS_MOUNT_NOCTO, ",nocto", "" },
{ NFS_MOUNT_NOAC, ",noac", "" },
@@ -658,6 +664,8 @@
seq_printf(m, ",acdirmin=%u", nfss->acdirmin/HZ);
if (nfss->acdirmax != NFS_DEF_ACDIRMAX*HZ || showdefaults)
seq_printf(m, ",acdirmax=%u", nfss->acdirmax/HZ);
+ if (!(nfss->flags & (NFS_MOUNT_SOFT|NFS_MOUNT_SOFTERR)))
+ seq_puts(m, ",hard");
for (nfs_infop = nfs_info; nfs_infop->flag; nfs_infop++) {
if (nfss->flags & nfs_infop->flag)
seq_puts(m, nfs_infop->str);
@@ -668,6 +676,8 @@
seq_printf(m, ",proto=%s",
rpc_peeraddr2str(nfss->client, RPC_DISPLAY_NETID));
rcu_read_unlock();
+ if (clp->cl_nconnect > 0)
+ seq_printf(m, ",nconnect=%u", clp->cl_nconnect);
if (version == 4) {
if (nfss->port != NFS_PORT)
seq_printf(m, ",port=%u", nfss->port);
@@ -685,29 +695,29 @@
nfs_show_nfsv4_options(m, nfss, showdefaults);
if (nfss->options & NFS_OPTION_FSCACHE)
- seq_printf(m, ",fsc");
+ seq_puts(m, ",fsc");
if (nfss->options & NFS_OPTION_MIGRATION)
- seq_printf(m, ",migration");
+ seq_puts(m, ",migration");
if (nfss->flags & NFS_MOUNT_LOOKUP_CACHE_NONEG) {
if (nfss->flags & NFS_MOUNT_LOOKUP_CACHE_NONE)
- seq_printf(m, ",lookupcache=none");
+ seq_puts(m, ",lookupcache=none");
else
- seq_printf(m, ",lookupcache=pos");
+ seq_puts(m, ",lookupcache=pos");
}
local_flock = nfss->flags & NFS_MOUNT_LOCAL_FLOCK;
local_fcntl = nfss->flags & NFS_MOUNT_LOCAL_FCNTL;
if (!local_flock && !local_fcntl)
- seq_printf(m, ",local_lock=none");
+ seq_puts(m, ",local_lock=none");
else if (local_flock && local_fcntl)
- seq_printf(m, ",local_lock=all");
+ seq_puts(m, ",local_lock=all");
else if (local_flock)
- seq_printf(m, ",local_lock=flock");
+ seq_puts(m, ",local_lock=flock");
else
- seq_printf(m, ",local_lock=posix");
+ seq_puts(m, ",local_lock=posix");
}
/*
@@ -730,11 +740,21 @@
EXPORT_SYMBOL_GPL(nfs_show_options);
#if IS_ENABLED(CONFIG_NFS_V4)
+static void show_lease(struct seq_file *m, struct nfs_server *server)
+{
+ struct nfs_client *clp = server->nfs_client;
+ unsigned long expire;
+
+ seq_printf(m, ",lease_time=%ld", clp->cl_lease_time / HZ);
+ expire = clp->cl_last_renewal + clp->cl_lease_time;
+ seq_printf(m, ",lease_expired=%ld",
+ time_after(expire, jiffies) ? 0 : (jiffies - expire) / HZ);
+}
#ifdef CONFIG_NFS_V4_1
static void show_sessions(struct seq_file *m, struct nfs_server *server)
{
if (nfs4_has_session(server->nfs_client))
- seq_printf(m, ",sessions");
+ seq_puts(m, ",sessions");
}
#else
static void show_sessions(struct seq_file *m, struct nfs_server *server) {}
@@ -811,7 +831,7 @@
/*
* Display all mount option settings
*/
- seq_printf(m, "\n\topts:\t");
+ seq_puts(m, "\n\topts:\t");
seq_puts(m, sb_rdonly(root->d_sb) ? "ro" : "rw");
seq_puts(m, root->d_sb->s_flags & SB_SYNCHRONOUS ? ",sync" : "");
seq_puts(m, root->d_sb->s_flags & SB_NOATIME ? ",noatime" : "");
@@ -822,7 +842,7 @@
show_implementation_id(m, nfss);
- seq_printf(m, "\n\tcaps:\t");
+ seq_puts(m, "\n\tcaps:\t");
seq_printf(m, "caps=0x%x", nfss->caps);
seq_printf(m, ",wtmult=%u", nfss->wtmult);
seq_printf(m, ",dtsize=%u", nfss->dtsize);
@@ -831,13 +851,14 @@
#if IS_ENABLED(CONFIG_NFS_V4)
if (nfss->nfs_client->rpc_ops->version == 4) {
- seq_printf(m, "\n\tnfsv4:\t");
+ seq_puts(m, "\n\tnfsv4:\t");
seq_printf(m, "bm0=0x%x", nfss->attr_bitmask[0]);
seq_printf(m, ",bm1=0x%x", nfss->attr_bitmask[1]);
seq_printf(m, ",bm2=0x%x", nfss->attr_bitmask[2]);
seq_printf(m, ",acl=0x%x", nfss->acl_bitmask);
show_sessions(m, nfss);
show_pnfs(m, nfss);
+ show_lease(m, nfss);
}
#endif
@@ -869,20 +890,20 @@
preempt_enable();
}
- seq_printf(m, "\n\tevents:\t");
+ seq_puts(m, "\n\tevents:\t");
for (i = 0; i < __NFSIOS_COUNTSMAX; i++)
seq_printf(m, "%lu ", totals.events[i]);
- seq_printf(m, "\n\tbytes:\t");
+ seq_puts(m, "\n\tbytes:\t");
for (i = 0; i < __NFSIOS_BYTESMAX; i++)
seq_printf(m, "%Lu ", totals.bytes[i]);
#ifdef CONFIG_NFS_FSCACHE
if (nfss->options & NFS_OPTION_FSCACHE) {
- seq_printf(m, "\n\tfsc:\t");
+ seq_puts(m, "\n\tfsc:\t");
for (i = 0; i < __NFSIOS_FSCACHEMAX; i++)
seq_printf(m, "%Lu ", totals.fscache[i]);
}
#endif
- seq_printf(m, "\n");
+ seq_putc(m, '\n');
rpc_clnt_show_stats(m, nfss->client);
@@ -929,7 +950,7 @@
data->minorversion = 0;
data->need_mount = true;
data->net = current->nsproxy->net_ns;
- security_init_mnt_opts(&data->lsm_opts);
+ data->lsm_opts = NULL;
}
return data;
}
@@ -1206,7 +1227,7 @@
static int nfs_parse_mount_options(char *raw,
struct nfs_parsed_mount_data *mnt)
{
- char *p, *string, *secdata;
+ char *p, *string;
int rc, sloppy = 0, invalid_option = 0;
unsigned short protofamily = AF_UNSPEC;
unsigned short mountfamily = AF_UNSPEC;
@@ -1217,20 +1238,10 @@
}
dfprintk(MOUNT, "NFS: nfs mount opts='%s'\n", raw);
- secdata = alloc_secdata();
- if (!secdata)
- goto out_nomem;
-
- rc = security_sb_copy_data(raw, secdata);
+ rc = security_sb_eat_lsm_opts(raw, &mnt->lsm_opts);
if (rc)
goto out_security_failure;
- rc = security_sb_parse_opts_str(secdata, &mnt->lsm_opts);
- if (rc)
- goto out_security_failure;
-
- free_secdata(secdata);
-
while ((p = strsep(&raw, ",")) != NULL) {
substring_t args[MAX_OPT_ARGS];
unsigned long option;
@@ -1249,9 +1260,14 @@
*/
case Opt_soft:
mnt->flags |= NFS_MOUNT_SOFT;
+ mnt->flags &= ~NFS_MOUNT_SOFTERR;
+ break;
+ case Opt_softerr:
+ mnt->flags |= NFS_MOUNT_SOFTERR;
+ mnt->flags &= ~NFS_MOUNT_SOFT;
break;
case Opt_hard:
- mnt->flags &= ~NFS_MOUNT_SOFT;
+ mnt->flags &= ~(NFS_MOUNT_SOFT|NFS_MOUNT_SOFTERR);
break;
case Opt_posix:
mnt->flags |= NFS_MOUNT_POSIX;
@@ -1549,6 +1565,11 @@
if (mnt->mount_server.addrlen == 0)
goto out_invalid_address;
break;
+ case Opt_nconnect:
+ if (nfs_get_option_ul_bound(args, &option, 1, NFS_MAX_CONNECTIONS))
+ goto out_invalid_value;
+ mnt->nfs_server.nconnect = option;
+ break;
case Opt_lookupcache:
string = match_strdup(args);
if (string == NULL)
@@ -1682,7 +1703,6 @@
printk(KERN_INFO "NFS: not enough memory to parse option\n");
return 0;
out_security_failure:
- free_secdata(secdata);
printk(KERN_INFO "NFS: security options invalid: %d\n", rc);
return 0;
}
@@ -1906,6 +1926,11 @@
size_t len;
char *end;
+ if (unlikely(!dev_name || !*dev_name)) {
+ dfprintk(MOUNT, "NFS: device name not specified\n");
+ return -EINVAL;
+ }
+
/* Is the host name protected with square brakcets? */
if (*dev_name == '[') {
end = strchr(++dev_name, ']');
@@ -1925,7 +1950,7 @@
/* kill possible hostname list: not supported */
comma = strchr(dev_name, ',');
if (comma != NULL && comma < end)
- *comma = 0;
+ len = comma - dev_name;
}
if (len > maxnamlen)
@@ -2047,7 +2072,8 @@
memcpy(sap, &data->addr, sizeof(data->addr));
args->nfs_server.addrlen = sizeof(data->addr);
args->nfs_server.port = ntohs(data->addr.sin_port);
- if (!nfs_verify_server_address(sap))
+ if (sap->sa_family != AF_INET ||
+ !nfs_verify_server_address(sap))
goto out_no_address;
if (!(data->flags & NFS_MOUNT_TCP))
@@ -2081,14 +2107,9 @@
if (data->context[0]){
#ifdef CONFIG_SECURITY_SELINUX
int rc;
- char *opts_str = kmalloc(sizeof(data->context) + 8, GFP_KERNEL);
- if (!opts_str)
- return -ENOMEM;
- strcpy(opts_str, "context=");
data->context[NFS_MAX_CONTEXT_LEN] = '\0';
- strcat(opts_str, &data->context[0]);
- rc = security_sb_parse_opts_str(opts_str, &args->lsm_opts);
- kfree(opts_str);
+ rc = security_add_mnt_opt("context", data->context,
+ strlen(data->context), &args->lsm_opts);
if (rc)
return rc;
#else
@@ -2168,7 +2189,10 @@
if (args->version == 4) {
#if IS_ENABLED(CONFIG_NFS_V4)
- port = NFS_PORT;
+ if (args->nfs_server.protocol == XPRT_TRANSPORT_RDMA)
+ port = NFS_RDMA_PORT;
+ else
+ port = NFS_PORT;
max_namelen = NFS4_MAXNAMLEN;
max_pathlen = NFS4_MAXPATHLEN;
nfs_validate_transport_protocol(args);
@@ -2178,8 +2202,11 @@
#else
goto out_v4_not_compiled;
#endif /* CONFIG_NFS_V4 */
- } else
+ } else {
nfs_set_mount_transport_protocol(args);
+ if (args->nfs_server.protocol == XPRT_TRANSPORT_RDMA)
+ port = NFS_RDMA_PORT;
+ }
nfs_set_port(sap, &args->nfs_server.port, port);
@@ -2233,6 +2260,7 @@
data->acdirmin != nfss->acdirmin / HZ ||
data->acdirmax != nfss->acdirmax / HZ ||
data->timeo != (10U * nfss->client->cl_timeout->to_initval / HZ) ||
+ (data->options & NFS_OPTION_FSCACHE) != (nfss->options & NFS_OPTION_FSCACHE) ||
data->nfs_server.port != nfss->port ||
data->nfs_server.addrlen != nfss->nfs_client->cl_addrlen ||
!rpc_cmp_addr((struct sockaddr *)&data->nfs_server.address,
@@ -2265,7 +2293,7 @@
options->version <= 6))))
return 0;
- data = kzalloc(sizeof(*data), GFP_KERNEL);
+ data = nfs_alloc_parsed_mount_data();
if (data == NULL)
return -ENOMEM;
@@ -2304,8 +2332,10 @@
/* compare new mount options with old ones */
error = nfs_compare_remount_data(nfss, data);
+ if (!error)
+ error = security_sb_remount(sb, data->lsm_opts);
out:
- kfree(data);
+ nfs_free_parsed_mount_data(data);
return error;
}
EXPORT_SYMBOL_GPL(nfs_remount);
@@ -2352,6 +2382,15 @@
sb->s_flags |= SB_POSIXACL;
sb->s_time_gran = 1;
sb->s_export_op = &nfs_export_ops;
+ } else
+ sb->s_time_gran = 1000;
+
+ if (server->nfs_client->rpc_ops->version != 4) {
+ sb->s_time_min = 0;
+ sb->s_time_max = U32_MAX;
+ } else {
+ sb->s_time_min = S64_MIN;
+ sb->s_time_max = S64_MAX;
}
nfs_initialise_sb(sb);
@@ -2372,7 +2411,6 @@
sb->s_maxbytes = old_sb->s_maxbytes;
sb->s_xattr = old_sb->s_xattr;
sb->s_op = old_sb->s_op;
- sb->s_time_gran = 1;
sb->s_export_op = old_sb->s_export_op;
if (server->nfs_client->rpc_ops->version != 2) {
@@ -2380,6 +2418,16 @@
* so ourselves when necessary.
*/
sb->s_flags |= SB_POSIXACL;
+ sb->s_time_gran = 1;
+ } else
+ sb->s_time_gran = 1000;
+
+ if (server->nfs_client->rpc_ops->version != 4) {
+ sb->s_time_min = 0;
+ sb->s_time_max = U32_MAX;
+ } else {
+ sb->s_time_min = S64_MIN;
+ sb->s_time_max = S64_MAX;
}
nfs_initialise_sb(sb);
@@ -2409,8 +2457,7 @@
goto Ebusy;
if (a->acdirmax != b->acdirmax)
goto Ebusy;
- if (b->auth_info.flavor_len > 0 &&
- clnt_a->cl_auth->au_flavor != clnt_b->cl_auth->au_flavor)
+ if (clnt_a->cl_auth->au_flavor != clnt_b->cl_auth->au_flavor)
goto Ebusy;
return 1;
Ebusy:
@@ -2479,6 +2526,21 @@
return 1;
}
+static int nfs_compare_userns(const struct nfs_server *old,
+ const struct nfs_server *new)
+{
+ const struct user_namespace *oldns = &init_user_ns;
+ const struct user_namespace *newns = &init_user_ns;
+
+ if (old->client && old->client->cl_cred)
+ oldns = old->client->cl_cred->user_ns;
+ if (new->client && new->client->cl_cred)
+ newns = new->client->cl_cred->user_ns;
+ if (oldns != newns)
+ return 0;
+ return 1;
+}
+
static int nfs_compare_super(struct super_block *sb, void *data)
{
struct nfs_sb_mountdata *sb_mntdata = data;
@@ -2492,6 +2554,8 @@
return 0;
if (memcmp(&old->fsid, &server->fsid, sizeof(old->fsid)) != 0)
return 0;
+ if (!nfs_compare_userns(old, server))
+ return 0;
return nfs_compare_mount_options(sb, server, mntflags);
}
@@ -2543,7 +2607,7 @@
if (NFS_SB(s)->caps & NFS_CAP_SECURITY_LABEL)
kflags |= SECURITY_LSM_NATIVE_LABELS;
- error = security_sb_set_mnt_opts(s, &mount_info->parsed->lsm_opts,
+ error = security_sb_set_mnt_opts(s, mount_info->parsed->lsm_opts,
kflags, &kflags_out);
if (error)
goto err;
@@ -2581,6 +2645,13 @@
}
EXPORT_SYMBOL_GPL(nfs_clone_sb_security);
+static void nfs_set_readahead(struct backing_dev_info *bdi,
+ unsigned long iomax_pages)
+{
+ bdi->ra_pages = VM_READAHEAD_PAGES;
+ bdi->io_pages = iomax_pages;
+}
+
struct dentry *nfs_fs_mount_common(struct nfs_server *server,
int flags, const char *dev_name,
struct nfs_mount_info *mount_info,
@@ -2623,7 +2694,7 @@
mntroot = ERR_PTR(error);
goto error_splat_super;
}
- s->s_bdi->ra_pages = server->rpages * NFS_MAX_READAHEAD;
+ nfs_set_readahead(s->s_bdi, server->rpages);
server->super = s;
}
diff --git a/fs/nfs/symlink.c b/fs/nfs/symlink.c
index 06eb44b..25ba299 100644
--- a/fs/nfs/symlink.c
+++ b/fs/nfs/symlink.c
@@ -26,8 +26,9 @@
* and straight-forward than readdir caching.
*/
-static int nfs_symlink_filler(struct inode *inode, struct page *page)
+static int nfs_symlink_filler(void *data, struct page *page)
{
+ struct inode *inode = data;
int error;
error = NFS_PROTO(inode)->readlink(inode, page, 0, PAGE_SIZE);
@@ -65,8 +66,8 @@
err = ERR_PTR(nfs_revalidate_mapping(inode, inode->i_mapping));
if (err)
return err;
- page = read_cache_page(&inode->i_data, 0,
- (filler_t *)nfs_symlink_filler, inode);
+ page = read_cache_page(&inode->i_data, 0, nfs_symlink_filler,
+ inode);
if (IS_ERR(page))
return ERR_CAST(page);
}
diff --git a/fs/nfs/sysfs.c b/fs/nfs/sysfs.c
new file mode 100644
index 0000000..4f3390b
--- /dev/null
+++ b/fs/nfs/sysfs.c
@@ -0,0 +1,187 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2019 Hammerspace Inc
+ */
+
+#include <linux/module.h>
+#include <linux/kobject.h>
+#include <linux/sysfs.h>
+#include <linux/fs.h>
+#include <linux/slab.h>
+#include <linux/netdevice.h>
+#include <linux/string.h>
+#include <linux/nfs_fs.h>
+#include <linux/rcupdate.h>
+
+#include "nfs4_fs.h"
+#include "netns.h"
+#include "sysfs.h"
+
+struct kobject *nfs_client_kobj;
+static struct kset *nfs_client_kset;
+
+static void nfs_netns_object_release(struct kobject *kobj)
+{
+ kfree(kobj);
+}
+
+static const struct kobj_ns_type_operations *nfs_netns_object_child_ns_type(
+ struct kobject *kobj)
+{
+ return &net_ns_type_operations;
+}
+
+static struct kobj_type nfs_netns_object_type = {
+ .release = nfs_netns_object_release,
+ .sysfs_ops = &kobj_sysfs_ops,
+ .child_ns_type = nfs_netns_object_child_ns_type,
+};
+
+static struct kobject *nfs_netns_object_alloc(const char *name,
+ struct kset *kset, struct kobject *parent)
+{
+ struct kobject *kobj;
+
+ kobj = kzalloc(sizeof(*kobj), GFP_KERNEL);
+ if (kobj) {
+ kobj->kset = kset;
+ if (kobject_init_and_add(kobj, &nfs_netns_object_type,
+ parent, "%s", name) == 0)
+ return kobj;
+ kobject_put(kobj);
+ }
+ return NULL;
+}
+
+int nfs_sysfs_init(void)
+{
+ nfs_client_kset = kset_create_and_add("nfs", NULL, fs_kobj);
+ if (!nfs_client_kset)
+ return -ENOMEM;
+ nfs_client_kobj = nfs_netns_object_alloc("net", nfs_client_kset, NULL);
+ if (!nfs_client_kobj) {
+ kset_unregister(nfs_client_kset);
+ nfs_client_kset = NULL;
+ return -ENOMEM;
+ }
+ return 0;
+}
+
+void nfs_sysfs_exit(void)
+{
+ kobject_put(nfs_client_kobj);
+ kset_unregister(nfs_client_kset);
+}
+
+static ssize_t nfs_netns_identifier_show(struct kobject *kobj,
+ struct kobj_attribute *attr, char *buf)
+{
+ struct nfs_netns_client *c = container_of(kobj,
+ struct nfs_netns_client,
+ kobject);
+ return scnprintf(buf, PAGE_SIZE, "%s\n", c->identifier);
+}
+
+/* Strip trailing '\n' */
+static size_t nfs_string_strip(const char *c, size_t len)
+{
+ while (len > 0 && c[len-1] == '\n')
+ --len;
+ return len;
+}
+
+static ssize_t nfs_netns_identifier_store(struct kobject *kobj,
+ struct kobj_attribute *attr,
+ const char *buf, size_t count)
+{
+ struct nfs_netns_client *c = container_of(kobj,
+ struct nfs_netns_client,
+ kobject);
+ const char *old;
+ char *p;
+ size_t len;
+
+ len = nfs_string_strip(buf, min_t(size_t, count, CONTAINER_ID_MAXLEN));
+ if (!len)
+ return 0;
+ p = kmemdup_nul(buf, len, GFP_KERNEL);
+ if (!p)
+ return -ENOMEM;
+ old = xchg(&c->identifier, p);
+ if (old) {
+ synchronize_rcu();
+ kfree(old);
+ }
+ return count;
+}
+
+static void nfs_netns_client_release(struct kobject *kobj)
+{
+ struct nfs_netns_client *c = container_of(kobj,
+ struct nfs_netns_client,
+ kobject);
+
+ if (c->identifier)
+ kfree(c->identifier);
+ kfree(c);
+}
+
+static const void *nfs_netns_client_namespace(struct kobject *kobj)
+{
+ return container_of(kobj, struct nfs_netns_client, kobject)->net;
+}
+
+static struct kobj_attribute nfs_netns_client_id = __ATTR(identifier,
+ 0644, nfs_netns_identifier_show, nfs_netns_identifier_store);
+
+static struct attribute *nfs_netns_client_attrs[] = {
+ &nfs_netns_client_id.attr,
+ NULL,
+};
+
+static struct kobj_type nfs_netns_client_type = {
+ .release = nfs_netns_client_release,
+ .default_attrs = nfs_netns_client_attrs,
+ .sysfs_ops = &kobj_sysfs_ops,
+ .namespace = nfs_netns_client_namespace,
+};
+
+static struct nfs_netns_client *nfs_netns_client_alloc(struct kobject *parent,
+ struct net *net)
+{
+ struct nfs_netns_client *p;
+
+ p = kzalloc(sizeof(*p), GFP_KERNEL);
+ if (p) {
+ p->net = net;
+ p->kobject.kset = nfs_client_kset;
+ if (kobject_init_and_add(&p->kobject, &nfs_netns_client_type,
+ parent, "nfs_client") == 0)
+ return p;
+ kobject_put(&p->kobject);
+ }
+ return NULL;
+}
+
+void nfs_netns_sysfs_setup(struct nfs_net *netns, struct net *net)
+{
+ struct nfs_netns_client *clp;
+
+ clp = nfs_netns_client_alloc(nfs_client_kobj, net);
+ if (clp) {
+ netns->nfs_client = clp;
+ kobject_uevent(&clp->kobject, KOBJ_ADD);
+ }
+}
+
+void nfs_netns_sysfs_destroy(struct nfs_net *netns)
+{
+ struct nfs_netns_client *clp = netns->nfs_client;
+
+ if (clp) {
+ kobject_uevent(&clp->kobject, KOBJ_REMOVE);
+ kobject_del(&clp->kobject);
+ kobject_put(&clp->kobject);
+ netns->nfs_client = NULL;
+ }
+}
diff --git a/fs/nfs/sysfs.h b/fs/nfs/sysfs.h
new file mode 100644
index 0000000..f1b2741
--- /dev/null
+++ b/fs/nfs/sysfs.h
@@ -0,0 +1,25 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2019 Hammerspace Inc
+ */
+
+#ifndef __NFS_SYSFS_H
+#define __NFS_SYSFS_H
+
+#define CONTAINER_ID_MAXLEN (64)
+
+struct nfs_netns_client {
+ struct kobject kobject;
+ struct net *net;
+ const char *identifier;
+};
+
+extern struct kobject *nfs_client_kobj;
+
+extern int nfs_sysfs_init(void);
+extern void nfs_sysfs_exit(void);
+
+void nfs_netns_sysfs_setup(struct nfs_net *netns, struct net *net);
+void nfs_netns_sysfs_destroy(struct nfs_net *netns);
+
+#endif
diff --git a/fs/nfs/unlink.c b/fs/nfs/unlink.c
index fd61bf0..0effeee 100644
--- a/fs/nfs/unlink.c
+++ b/fs/nfs/unlink.c
@@ -31,7 +31,7 @@
static void
nfs_free_unlinkdata(struct nfs_unlinkdata *data)
{
- put_rpccred(data->cred);
+ put_cred(data->cred);
kfree(data->args.name.name);
kfree(data);
}
@@ -39,6 +39,7 @@
/**
* nfs_async_unlink_done - Sillydelete post-processing
* @task: rpc_task of the sillydelete
+ * @calldata: pointer to nfs_unlinkdata
*
* Do the directory attribute update.
*/
@@ -54,7 +55,7 @@
/**
* nfs_async_unlink_release - Release the sillydelete data.
- * @task: rpc_task of the sillydelete
+ * @calldata: struct nfs_unlinkdata to release
*
* We need to call nfs_put_unlinkdata as a 'tk_release' task since the
* rpc_task would be freed too.
@@ -159,8 +160,8 @@
/**
* nfs_async_unlink - asynchronous unlinking of a file
- * @dir: parent directory of dentry
- * @dentry: dentry to unlink
+ * @dentry: parent directory of dentry
+ * @name: name of dentry to unlink
*/
static int
nfs_async_unlink(struct dentry *dentry, const struct qstr *name)
@@ -177,11 +178,7 @@
goto out_free;
data->args.name.len = name->len;
- data->cred = rpc_lookup_cred();
- if (IS_ERR(data->cred)) {
- status = PTR_ERR(data->cred);
- goto out_free_name;
- }
+ data->cred = get_current_cred();
data->res.dir_attr = &data->dir_attr;
init_waitqueue_head(&data->wq);
@@ -202,8 +199,7 @@
return 0;
out_unlock:
spin_unlock(&dentry->d_lock);
- put_rpccred(data->cred);
-out_free_name:
+ put_cred(data->cred);
kfree(data->args.name.name);
out_free:
kfree(data);
@@ -307,7 +303,7 @@
iput(data->old_dir);
iput(data->new_dir);
nfs_sb_deactive(sb);
- put_rpccred(data->cred);
+ put_cred(data->cred);
kfree(data);
}
@@ -329,6 +325,7 @@
* @new_dir: target directory for the rename
* @old_dentry: original dentry to be renamed
* @new_dentry: dentry to which the old_dentry should be renamed
+ * @complete: Function to run on successful completion
*
* It's expected that valid references to the dentries and inodes are held
*/
@@ -352,12 +349,7 @@
return ERR_PTR(-ENOMEM);
task_setup_data.callback_data = data;
- data->cred = rpc_lookup_cred();
- if (IS_ERR(data->cred)) {
- struct rpc_task *task = ERR_CAST(data->cred);
- kfree(data);
- return task;
- }
+ data->cred = get_current_cred();
msg.rpc_argp = &data->args;
msg.rpc_resp = &data->res;
@@ -404,12 +396,6 @@
nfs_cancel_async_unlink(dentry);
return;
}
-
- /*
- * vfs_unlink and the like do not issue this when a file is
- * sillyrenamed, so do it here.
- */
- fsnotify_nameremove(dentry, 0);
}
#define SILLYNAME_PREFIX ".nfs"
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 586726a..52cab65 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* linux/fs/nfs/write.c
*
@@ -26,6 +27,7 @@
#include <linux/iversion.h>
#include <linux/uaccess.h>
+#include <linux/sched/mm.h>
#include "delegation.h"
#include "internal.h"
@@ -55,6 +57,7 @@
static const struct nfs_pgio_completion_ops nfs_async_write_completion_ops;
static const struct nfs_commit_completion_ops nfs_commit_completion_ops;
static const struct nfs_rw_ops nfs_rw_write_ops;
+static void nfs_inode_remove_request(struct nfs_page *req);
static void nfs_clear_request_commit(struct nfs_page *req);
static void nfs_init_cinfo_from_inode(struct nfs_commit_info *cinfo,
struct inode *inode);
@@ -101,7 +104,7 @@
static struct nfs_pgio_header *nfs_writehdr_alloc(void)
{
- struct nfs_pgio_header *p = mempool_alloc(nfs_wdata_mempool, GFP_NOIO);
+ struct nfs_pgio_header *p = mempool_alloc(nfs_wdata_mempool, GFP_KERNEL);
memset(p, 0, sizeof(*p));
p->rw_mode = FMODE_WRITE;
@@ -238,9 +241,15 @@
}
/* A writeback failed: mark the page as bad, and invalidate the page cache */
-static void nfs_set_pageerror(struct page *page)
+static void nfs_set_pageerror(struct address_space *mapping)
{
- nfs_zap_mapping(page_file_mapping(page)->host, page_file_mapping(page));
+ nfs_zap_mapping(mapping->host, mapping);
+}
+
+static void nfs_mapping_set_error(struct page *page, int error)
+{
+ SetPageError(page);
+ mapping_set_error(page_file_mapping(page), error);
}
/*
@@ -581,26 +590,15 @@
return ERR_PTR(ret);
}
-static void nfs_write_error_remove_page(struct nfs_page *req)
+static void nfs_write_error(struct nfs_page *req, int error)
{
+ nfs_set_pageerror(page_file_mapping(req->wb_page));
+ nfs_mapping_set_error(req->wb_page, error);
+ nfs_inode_remove_request(req);
nfs_end_page_writeback(req);
- generic_error_remove_page(page_file_mapping(req->wb_page),
- req->wb_page);
nfs_release_request(req);
}
-static bool
-nfs_error_is_fatal_on_server(int err)
-{
- switch (err) {
- case 0:
- case -ERESTARTSYS:
- case -EINTR:
- return false;
- }
- return nfs_error_is_fatal(err);
-}
-
/*
* Find an associated nfs write request, and prepare to flush it out
* May return an error if the user signalled nfs_wait_on_request().
@@ -621,31 +619,32 @@
nfs_set_page_writeback(page);
WARN_ON_ONCE(test_bit(PG_CLEAN, &req->wb_flags));
- ret = 0;
/* If there is a fatal error that covers this write, just exit */
- if (nfs_error_is_fatal_on_server(req->wb_context->error))
+ ret = pgio->pg_error;
+ if (nfs_error_is_fatal_on_server(ret))
goto out_launder;
+ ret = 0;
if (!nfs_pageio_add_request(pgio, req)) {
ret = pgio->pg_error;
/*
* Remove the problematic req upon fatal errors on the server
*/
if (nfs_error_is_fatal(ret)) {
- nfs_context_set_write_error(req->wb_context, ret);
if (nfs_error_is_fatal_on_server(ret))
goto out_launder;
- }
+ } else
+ ret = -EAGAIN;
nfs_redirty_request(req);
- ret = -EAGAIN;
+ pgio->pg_error = 0;
} else
nfs_add_stats(page_file_mapping(page)->host,
NFSIOS_WRITEPAGES, 1);
out:
return ret;
out_launder:
- nfs_write_error_remove_page(req);
- return ret;
+ nfs_write_error(req, ret);
+ return 0;
}
static int nfs_do_writepage(struct page *page, struct writeback_control *wbc,
@@ -657,7 +656,7 @@
ret = nfs_page_async_flush(pgio, page);
if (ret == -EAGAIN) {
redirty_page_for_writepage(wbc, page);
- ret = 0;
+ ret = AOP_WRITEPAGE_ACTIVATE;
}
return ret;
}
@@ -676,10 +675,11 @@
nfs_pageio_init_write(&pgio, inode, 0,
false, &nfs_async_write_completion_ops);
err = nfs_do_writepage(page, wbc, &pgio);
+ pgio.pg_error = 0;
nfs_pageio_complete(&pgio);
if (err < 0)
return err;
- if (pgio.pg_error < 0)
+ if (nfs_error_is_fatal(pgio.pg_error))
return pgio.pg_error;
return 0;
}
@@ -689,7 +689,8 @@
int ret;
ret = nfs_writepage_locked(page, wbc);
- unlock_page(page);
+ if (ret != AOP_WRITEPAGE_ACTIVATE)
+ unlock_page(page);
return ret;
}
@@ -698,7 +699,8 @@
int ret;
ret = nfs_do_writepage(page, wbc, data);
- unlock_page(page);
+ if (ret != AOP_WRITEPAGE_ACTIVATE)
+ unlock_page(page);
return ret;
}
@@ -711,11 +713,12 @@
{
struct inode *inode = mapping->host;
struct nfs_pageio_descriptor pgio;
- struct nfs_io_completion *ioc = nfs_io_completion_alloc(GFP_NOFS);
+ struct nfs_io_completion *ioc;
int err;
nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGES);
+ ioc = nfs_io_completion_alloc(GFP_KERNEL);
if (ioc)
nfs_io_completion_init(ioc, nfs_io_completion_commit, inode);
@@ -723,13 +726,14 @@
&nfs_async_write_completion_ops);
pgio.pg_io_completion = ioc;
err = write_cache_pages(mapping, wbc, nfs_writepages_callback, &pgio);
+ pgio.pg_error = 0;
nfs_pageio_complete(&pgio);
nfs_io_completion_put(ioc);
if (err < 0)
goto out_err;
err = pgio.pg_error;
- if (err < 0)
+ if (nfs_error_is_fatal(err))
goto out_err;
return 0;
out_err:
@@ -782,7 +786,6 @@
struct nfs_inode *nfsi = NFS_I(inode);
struct nfs_page *head;
- atomic_long_dec(&nfsi->nrequests);
if (nfs_page_group_sync_on_bit(req, PG_REMOVE)) {
head = req->wb_head;
@@ -795,8 +798,10 @@
spin_unlock(&mapping->private_lock);
}
- if (test_and_clear_bit(PG_INODE_REF, &req->wb_flags))
+ if (test_and_clear_bit(PG_INODE_REF, &req->wb_flags)) {
nfs_release_request(req);
+ atomic_long_dec(&nfsi->nrequests);
+ }
}
static void
@@ -864,7 +869,6 @@
/**
* nfs_request_add_commit_list - add request to a commit list
* @req: pointer to a struct nfs_page
- * @dst: commit list head
* @cinfo: holds list lock and accounting info
*
* This sets the PG_CLEAN bit, updates the cinfo count of
@@ -953,7 +957,8 @@
nfs_clear_request_commit(struct nfs_page *req)
{
if (test_bit(PG_CLEAN, &req->wb_flags)) {
- struct inode *inode = d_inode(req->wb_context->dentry);
+ struct nfs_open_context *ctx = nfs_req_openctx(req);
+ struct inode *inode = d_inode(ctx->dentry);
struct nfs_commit_info cinfo;
nfs_init_cinfo_from_inode(&cinfo, inode);
@@ -993,11 +998,13 @@
nfs_list_remove_request(req);
if (test_bit(NFS_IOHDR_ERROR, &hdr->flags) &&
(hdr->good_bytes < bytes)) {
- nfs_set_pageerror(req->wb_page);
- nfs_context_set_write_error(req->wb_context, hdr->error);
+ nfs_set_pageerror(page_file_mapping(req->wb_page));
+ nfs_mapping_set_error(req->wb_page, hdr->error);
goto remove_req;
}
if (nfs_write_need_commit(hdr)) {
+ /* Reset wb_nio, since the write was successful. */
+ req->wb_nio = 0;
memcpy(&req->wb_verf, &hdr->verf.verifier, sizeof(req->wb_verf));
nfs_mark_request_commit(req, hdr->lseg, &cinfo,
hdr->pgio_mirror_idx);
@@ -1131,6 +1138,7 @@
req->wb_bytes = end - req->wb_offset;
else
req->wb_bytes = rqend - req->wb_offset;
+ req->wb_nio = 0;
return req;
out_flushme:
/*
@@ -1160,7 +1168,7 @@
req = nfs_try_to_update_request(inode, page, offset, bytes);
if (req != NULL)
goto out;
- req = nfs_create_request(ctx, page, NULL, offset, bytes);
+ req = nfs_create_request(ctx, page, offset, bytes);
if (IS_ERR(req))
goto out;
nfs_inode_add_request(inode, req);
@@ -1205,7 +1213,7 @@
return 0;
l_ctx = req->wb_lock_context;
do_flush = req->wb_page != page ||
- !nfs_match_open_context(req->wb_context, ctx);
+ !nfs_match_open_context(nfs_req_openctx(req), ctx);
if (l_ctx && flctx &&
!(list_empty_careful(&flctx->flc_posix) &&
list_empty_careful(&flctx->flc_flock))) {
@@ -1233,9 +1241,12 @@
nfs_key_timeout_notify(struct file *filp, struct inode *inode)
{
struct nfs_open_context *ctx = nfs_file_open_context(filp);
- struct rpc_auth *auth = NFS_SERVER(inode)->client->cl_auth;
- return rpcauth_key_timeout_notify(auth, ctx->cred);
+ if (nfs_ctx_key_to_expire(ctx, inode) &&
+ !ctx->ll_cred)
+ /* Already expired! */
+ return -EACCES;
+ return 0;
}
/*
@@ -1244,8 +1255,23 @@
bool nfs_ctx_key_to_expire(struct nfs_open_context *ctx, struct inode *inode)
{
struct rpc_auth *auth = NFS_SERVER(inode)->client->cl_auth;
+ struct rpc_cred *cred = ctx->ll_cred;
+ struct auth_cred acred = {
+ .cred = ctx->cred,
+ };
- return rpcauth_cred_key_to_expire(auth, ctx->cred);
+ if (cred && !cred->cr_ops->crmatch(&acred, cred, 0)) {
+ put_rpccred(cred);
+ ctx->ll_cred = NULL;
+ cred = NULL;
+ }
+ if (!cred)
+ cred = auth->au_ops->lookup_cred(auth, &acred, 0);
+ if (!cred || IS_ERR(cred))
+ return true;
+ ctx->ll_cred = cred;
+ return !!(cred->cr_ops->crkey_timeout &&
+ cred->cr_ops->crkey_timeout(cred));
}
/*
@@ -1329,7 +1355,8 @@
unsigned int offset, unsigned int count)
{
struct nfs_open_context *ctx = nfs_file_open_context(file);
- struct inode *inode = page_file_mapping(page)->host;
+ struct address_space *mapping = page_file_mapping(page);
+ struct inode *inode = mapping->host;
int status = 0;
nfs_inc_stats(inode, NFSIOS_VFSUPDATEPAGE);
@@ -1347,7 +1374,7 @@
status = nfs_writepage_setup(ctx, page, offset, count);
if (status < 0)
- nfs_set_pageerror(page);
+ nfs_set_pageerror(mapping);
else
__set_page_dirty_nobuffers(page);
out:
@@ -1386,26 +1413,31 @@
*/
static void nfs_redirty_request(struct nfs_page *req)
{
+ /* Bump the transmission count */
+ req->wb_nio++;
nfs_mark_request_dirty(req);
- set_bit(NFS_CONTEXT_RESEND_WRITES, &req->wb_context->flags);
+ set_bit(NFS_CONTEXT_RESEND_WRITES, &nfs_req_openctx(req)->flags);
nfs_end_page_writeback(req);
nfs_release_request(req);
}
-static void nfs_async_write_error(struct list_head *head)
+static void nfs_async_write_error(struct list_head *head, int error)
{
struct nfs_page *req;
while (!list_empty(head)) {
req = nfs_list_entry(head->next);
nfs_list_remove_request(req);
- nfs_redirty_request(req);
+ if (nfs_error_is_fatal(error))
+ nfs_write_error(req, error);
+ else
+ nfs_redirty_request(req);
}
}
static void nfs_async_write_reschedule_io(struct nfs_pgio_header *hdr)
{
- nfs_async_write_error(&hdr->pages);
+ nfs_async_write_error(&hdr->pages, 0);
filemap_fdatawrite_range(hdr->inode->i_mapping, hdr->args.offset,
hdr->args.offset + hdr->args.count - 1);
}
@@ -1704,7 +1736,8 @@
struct nfs_commit_info *cinfo)
{
struct nfs_page *first = nfs_list_entry(head->next);
- struct inode *inode = d_inode(first->wb_context->dentry);
+ struct nfs_open_context *ctx = nfs_req_openctx(first);
+ struct inode *inode = d_inode(ctx->dentry);
/* Set up the RPC argument and reply structs
* NB: take care not to mess about with data->commit et al. */
@@ -1712,7 +1745,7 @@
list_splice_init(head, &data->pages);
data->inode = inode;
- data->cred = first->wb_context->cred;
+ data->cred = ctx->cred;
data->lseg = lseg; /* reference transferred */
/* only set lwb for pnfs commit */
if (lseg)
@@ -1725,7 +1758,7 @@
/* Note: we always request a commit of the entire inode */
data->args.offset = 0;
data->args.count = 0;
- data->context = get_nfs_open_context(first->wb_context);
+ data->context = get_nfs_open_context(ctx);
data->res.fattr = &data->fattr;
data->res.verf = &data->verf;
nfs_fattr_init(&data->fattr);
@@ -1808,14 +1841,15 @@
nfs_clear_page_commit(req->wb_page);
dprintk("NFS: commit (%s/%llu %d@%lld)",
- req->wb_context->dentry->d_sb->s_id,
- (unsigned long long)NFS_FILEID(d_inode(req->wb_context->dentry)),
+ nfs_req_openctx(req)->dentry->d_sb->s_id,
+ (unsigned long long)NFS_FILEID(d_inode(nfs_req_openctx(req)->dentry)),
req->wb_bytes,
(long long)req_offset(req));
if (status < 0) {
- nfs_context_set_write_error(req->wb_context, status);
- if (req->wb_page)
+ if (req->wb_page) {
+ nfs_mapping_set_error(req->wb_page, status);
nfs_inode_remove_request(req);
+ }
dprintk_cont(", error = %d\n", status);
goto next;
}
@@ -1832,7 +1866,7 @@
/* We have a mismatch. Write the page again */
dprintk_cont(" mismatch\n");
nfs_mark_request_dirty(req);
- set_bit(NFS_CONTEXT_RESEND_WRITES, &req->wb_context->flags);
+ set_bit(NFS_CONTEXT_RESEND_WRITES, &nfs_req_openctx(req)->flags);
next:
nfs_unlock_and_release_request(req);
/* Latency breaker */
@@ -2121,7 +2155,7 @@
* This allows larger machines to have larger/more transfers.
* Limit the default to 256M
*/
- nfs_congestion_kb = (16*int_sqrt(totalram_pages)) << (PAGE_SHIFT-10);
+ nfs_congestion_kb = (16*int_sqrt(totalram_pages())) << (PAGE_SHIFT-10);
if (nfs_congestion_kb > 256*1024)
nfs_congestion_kb = 256*1024;