aboutsummaryrefslogtreecommitdiffstatshomepage
diff options
context:
space:
mode:
-rw-r--r--.mailmap2
-rw-r--r--MAINTAINERS2
-rw-r--r--fs/nfsd/Kconfig2
-rw-r--r--fs/nfsd/Makefile1
-rw-r--r--fs/nfsd/debugfs.c47
-rw-r--r--fs/nfsd/export.c3
-rw-r--r--fs/nfsd/nfs3proc.c68
-rw-r--r--fs/nfsd/nfs4callback.c132
-rw-r--r--fs/nfsd/nfs4proc.c35
-rw-r--r--fs/nfsd/nfs4recover.c61
-rw-r--r--fs/nfsd/nfs4state.c40
-rw-r--r--fs/nfsd/nfs4xdr.c21
-rw-r--r--fs/nfsd/nfsctl.c25
-rw-r--r--fs/nfsd/nfsd.h34
-rw-r--r--fs/nfsd/nfsproc.c48
-rw-r--r--fs/nfsd/nfssvc.c8
-rw-r--r--fs/nfsd/nfsxdr.c4
-rw-r--r--fs/nfsd/state.h23
-rw-r--r--fs/nfsd/trace.h302
-rw-r--r--fs/nfsd/vfs.c90
-rw-r--r--fs/nfsd/vfs.h10
-rw-r--r--fs/nfsd/xdr4.h4
-rw-r--r--fs/nfsd/xdr4cb.h5
-rw-r--r--include/linux/sunrpc/svc.h44
-rw-r--r--include/linux/sunrpc/svc_rdma.h6
-rw-r--r--include/linux/sunrpc/svc_xprt.h1
-rw-r--r--include/linux/sunrpc/svcsock.h4
-rw-r--r--include/trace/events/sunrpc.h13
-rw-r--r--include/trace/misc/fs.h21
-rw-r--r--net/sunrpc/cache.c17
-rw-r--r--net/sunrpc/svc.c80
-rw-r--r--net/sunrpc/svc_xprt.c11
-rw-r--r--net/sunrpc/svcsock.c17
-rw-r--r--net/sunrpc/xdr.c1
-rw-r--r--net/sunrpc/xprtrdma/svc_rdma_recvfrom.c8
-rw-r--r--net/sunrpc/xprtrdma/svc_rdma_rw.c2
-rw-r--r--net/sunrpc/xprtrdma/svc_rdma_sendto.c16
-rw-r--r--net/sunrpc/xprtrdma/svc_rdma_transport.c15
-rw-r--r--tools/net/sunrpc/xdrgen/templates/C/pointer/encoder/variable_length_array.j22
-rw-r--r--tools/net/sunrpc/xdrgen/templates/C/struct/encoder/variable_length_array.j22
-rw-r--r--tools/net/sunrpc/xdrgen/templates/C/union/decoder/variable_length_array.j22
41 files changed, 848 insertions, 381 deletions
diff --git a/.mailmap b/.mailmap
index 9b0dc7c30e6d..6a6aa09e244b 100644
--- a/.mailmap
+++ b/.mailmap
@@ -546,6 +546,8 @@ Naveen N Rao <naveen@kernel.org> <naveen.n.rao@linux.vnet.ibm.com>
Neeraj Upadhyay <neeraj.upadhyay@kernel.org> <quic_neeraju@quicinc.com>
Neeraj Upadhyay <neeraj.upadhyay@kernel.org> <neeraju@codeaurora.org>
Neil Armstrong <neil.armstrong@linaro.org> <narmstrong@baylibre.com>
+NeilBrown <neil@brown.name> <neilb@suse.de>
+NeilBrown <neil@brown.name> <neilb@cse.unsw.edu.au>
Nguyen Anh Quynh <aquynh@gmail.com>
Nicholas Piggin <npiggin@gmail.com> <npiggen@suse.de>
Nicholas Piggin <npiggin@gmail.com> <npiggin@kernel.dk>
diff --git a/MAINTAINERS b/MAINTAINERS
index f847bf173b0e..db6562af259a 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -13005,7 +13005,7 @@ W: http://kernelnewbies.org/KernelJanitors
KERNEL NFSD, SUNRPC, AND LOCKD SERVERS
M: Chuck Lever <chuck.lever@oracle.com>
M: Jeff Layton <jlayton@kernel.org>
-R: Neil Brown <neilb@suse.de>
+R: NeilBrown <neil@brown.name>
R: Olga Kornievskaia <okorniev@redhat.com>
R: Dai Ngo <Dai.Ngo@oracle.com>
R: Tom Talpey <tom@talpey.com>
diff --git a/fs/nfsd/Kconfig b/fs/nfsd/Kconfig
index 731a88f6313e..879e0b104d1c 100644
--- a/fs/nfsd/Kconfig
+++ b/fs/nfsd/Kconfig
@@ -77,8 +77,8 @@ config NFSD_V4
select FS_POSIX_ACL
select RPCSEC_GSS_KRB5
select CRYPTO
+ select CRYPTO_LIB_SHA256
select CRYPTO_MD5
- select CRYPTO_SHA256
select GRACE_PERIOD
select NFS_V4_2_SSC_HELPER if NFS_V4_2
help
diff --git a/fs/nfsd/Makefile b/fs/nfsd/Makefile
index 2f687619f65b..55744bb786c9 100644
--- a/fs/nfsd/Makefile
+++ b/fs/nfsd/Makefile
@@ -24,6 +24,7 @@ nfsd-$(CONFIG_NFSD_BLOCKLAYOUT) += blocklayout.o blocklayoutxdr.o
nfsd-$(CONFIG_NFSD_SCSILAYOUT) += blocklayout.o blocklayoutxdr.o
nfsd-$(CONFIG_NFSD_FLEXFILELAYOUT) += flexfilelayout.o flexfilelayoutxdr.o
nfsd-$(CONFIG_NFS_LOCALIO) += localio.o
+nfsd-$(CONFIG_DEBUG_FS) += debugfs.o
.PHONY: xdrgen
diff --git a/fs/nfsd/debugfs.c b/fs/nfsd/debugfs.c
new file mode 100644
index 000000000000..84b0c8b559dc
--- /dev/null
+++ b/fs/nfsd/debugfs.c
@@ -0,0 +1,47 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/debugfs.h>
+
+#include "nfsd.h"
+
+static struct dentry *nfsd_top_dir __read_mostly;
+
+/*
+ * /sys/kernel/debug/nfsd/disable-splice-read
+ *
+ * Contents:
+ * %0: NFS READ is allowed to use page splicing
+ * %1: NFS READ uses only iov iter read
+ *
+ * The default value of this setting is zero (page splicing is
+ * allowed). This setting takes immediate effect for all NFS
+ * versions, all exports, and in all NFSD net namespaces.
+ */
+
+static int nfsd_dsr_get(void *data, u64 *val)
+{
+ *val = nfsd_disable_splice_read ? 1 : 0;
+ return 0;
+}
+
+static int nfsd_dsr_set(void *data, u64 val)
+{
+ nfsd_disable_splice_read = (val > 0) ? true : false;
+ return 0;
+}
+
+DEFINE_DEBUGFS_ATTRIBUTE(nfsd_dsr_fops, nfsd_dsr_get, nfsd_dsr_set, "%llu\n");
+
+void nfsd_debugfs_exit(void)
+{
+ debugfs_remove_recursive(nfsd_top_dir);
+ nfsd_top_dir = NULL;
+}
+
+void nfsd_debugfs_init(void)
+{
+ nfsd_top_dir = debugfs_create_dir("nfsd", NULL);
+
+ debugfs_create_file("disable-splice-read", S_IWUSR | S_IRUGO,
+ nfsd_top_dir, NULL, &nfsd_dsr_fops);
+}
diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c
index 0363720280d4..88ae410b4113 100644
--- a/fs/nfsd/export.c
+++ b/fs/nfsd/export.c
@@ -1124,7 +1124,8 @@ __be32 check_nfsd_access(struct svc_export *exp, struct svc_rqst *rqstp,
test_bit(XPT_PEER_AUTH, &xprt->xpt_flags))
goto ok;
}
- goto denied;
+ if (!may_bypass_gss)
+ goto denied;
ok:
/* legacy gss-only clients are always OK: */
diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c
index ac1731eb34ab..a817d8485d21 100644
--- a/fs/nfsd/nfs3proc.c
+++ b/fs/nfsd/nfs3proc.c
@@ -14,6 +14,7 @@
#include "xdr3.h"
#include "vfs.h"
#include "filecache.h"
+#include "trace.h"
#define NFSDDBG_FACILITY NFSDDBG_PROC
@@ -69,8 +70,7 @@ nfsd3_proc_getattr(struct svc_rqst *rqstp)
struct nfsd_fhandle *argp = rqstp->rq_argp;
struct nfsd3_attrstat *resp = rqstp->rq_resp;
- dprintk("nfsd: GETATTR(3) %s\n",
- SVCFH_fmt(&argp->fh));
+ trace_nfsd_vfs_getattr(rqstp, &argp->fh);
fh_copy(&resp->fh, &argp->fh);
resp->status = fh_verify(rqstp, &resp->fh, 0,
@@ -220,7 +220,6 @@ nfsd3_proc_write(struct svc_rqst *rqstp)
struct nfsd3_writeargs *argp = rqstp->rq_argp;
struct nfsd3_writeres *resp = rqstp->rq_resp;
unsigned long cnt = argp->len;
- unsigned int nvecs;
dprintk("nfsd: WRITE(3) %s %d bytes at %Lu%s\n",
SVCFH_fmt(&argp->fh),
@@ -235,10 +234,8 @@ nfsd3_proc_write(struct svc_rqst *rqstp)
fh_copy(&resp->fh, &argp->fh);
resp->committed = argp->stable;
- nvecs = svc_fill_write_vector(rqstp, &argp->payload);
-
resp->status = nfsd_write(rqstp, &resp->fh, argp->offset,
- rqstp->rq_vec, nvecs, &cnt,
+ &argp->payload, &cnt,
resp->committed, resp->verf);
resp->count = cnt;
resp->status = nfsd3_map_status(resp->status);
@@ -266,6 +263,8 @@ nfsd3_create_file(struct svc_rqst *rqstp, struct svc_fh *fhp,
__be32 status;
int host_err;
+ trace_nfsd_vfs_create(rqstp, fhp, S_IFREG, argp->name, argp->len);
+
if (isdotent(argp->name, argp->len))
return nfserr_exist;
if (!(iap->ia_valid & ATTR_MODE))
@@ -382,11 +381,6 @@ nfsd3_proc_create(struct svc_rqst *rqstp)
struct nfsd3_diropres *resp = rqstp->rq_resp;
svc_fh *dirfhp, *newfhp;
- dprintk("nfsd: CREATE(3) %s %.*s\n",
- SVCFH_fmt(&argp->fh),
- argp->len,
- argp->name);
-
dirfhp = fh_copy(&resp->dirfh, &argp->fh);
newfhp = fh_init(&resp->fh, NFS3_FHSIZE);
@@ -407,11 +401,6 @@ nfsd3_proc_mkdir(struct svc_rqst *rqstp)
.na_iattr = &argp->attrs,
};
- dprintk("nfsd: MKDIR(3) %s %.*s\n",
- SVCFH_fmt(&argp->fh),
- argp->len,
- argp->name);
-
argp->attrs.ia_valid &= ~ATTR_SIZE;
fh_copy(&resp->dirfh, &argp->fh);
fh_init(&resp->fh, NFS3_FHSIZE);
@@ -447,11 +436,6 @@ nfsd3_proc_symlink(struct svc_rqst *rqstp)
goto out;
}
- dprintk("nfsd: SYMLINK(3) %s %.*s -> %.*s\n",
- SVCFH_fmt(&argp->ffh),
- argp->flen, argp->fname,
- argp->tlen, argp->tname);
-
fh_copy(&resp->dirfh, &argp->ffh);
fh_init(&resp->fh, NFS3_FHSIZE);
resp->status = nfsd_symlink(rqstp, &resp->dirfh, argp->fname,
@@ -476,11 +460,6 @@ nfsd3_proc_mknod(struct svc_rqst *rqstp)
int type;
dev_t rdev = 0;
- dprintk("nfsd: MKNOD(3) %s %.*s\n",
- SVCFH_fmt(&argp->fh),
- argp->len,
- argp->name);
-
fh_copy(&resp->dirfh, &argp->fh);
fh_init(&resp->fh, NFS3_FHSIZE);
@@ -513,11 +492,6 @@ nfsd3_proc_remove(struct svc_rqst *rqstp)
struct nfsd3_diropargs *argp = rqstp->rq_argp;
struct nfsd3_attrstat *resp = rqstp->rq_resp;
- dprintk("nfsd: REMOVE(3) %s %.*s\n",
- SVCFH_fmt(&argp->fh),
- argp->len,
- argp->name);
-
/* Unlink. -S_IFDIR means file must not be a directory */
fh_copy(&resp->fh, &argp->fh);
resp->status = nfsd_unlink(rqstp, &resp->fh, -S_IFDIR,
@@ -535,11 +509,6 @@ nfsd3_proc_rmdir(struct svc_rqst *rqstp)
struct nfsd3_diropargs *argp = rqstp->rq_argp;
struct nfsd3_attrstat *resp = rqstp->rq_resp;
- dprintk("nfsd: RMDIR(3) %s %.*s\n",
- SVCFH_fmt(&argp->fh),
- argp->len,
- argp->name);
-
fh_copy(&resp->fh, &argp->fh);
resp->status = nfsd_unlink(rqstp, &resp->fh, S_IFDIR,
argp->name, argp->len);
@@ -553,15 +522,6 @@ nfsd3_proc_rename(struct svc_rqst *rqstp)
struct nfsd3_renameargs *argp = rqstp->rq_argp;
struct nfsd3_renameres *resp = rqstp->rq_resp;
- dprintk("nfsd: RENAME(3) %s %.*s ->\n",
- SVCFH_fmt(&argp->ffh),
- argp->flen,
- argp->fname);
- dprintk("nfsd: -> %s %.*s\n",
- SVCFH_fmt(&argp->tfh),
- argp->tlen,
- argp->tname);
-
fh_copy(&resp->ffh, &argp->ffh);
fh_copy(&resp->tfh, &argp->tfh);
resp->status = nfsd_rename(rqstp, &resp->ffh, argp->fname, argp->flen,
@@ -576,13 +536,6 @@ nfsd3_proc_link(struct svc_rqst *rqstp)
struct nfsd3_linkargs *argp = rqstp->rq_argp;
struct nfsd3_linkres *resp = rqstp->rq_resp;
- dprintk("nfsd: LINK(3) %s ->\n",
- SVCFH_fmt(&argp->ffh));
- dprintk("nfsd: -> %s %.*s\n",
- SVCFH_fmt(&argp->tfh),
- argp->tlen,
- argp->tname);
-
fh_copy(&resp->fh, &argp->ffh);
fh_copy(&resp->tfh, &argp->tfh);
resp->status = nfsd_link(rqstp, &resp->tfh, argp->tname, argp->tlen,
@@ -621,9 +574,7 @@ nfsd3_proc_readdir(struct svc_rqst *rqstp)
struct nfsd3_readdirres *resp = rqstp->rq_resp;
loff_t offset;
- dprintk("nfsd: READDIR(3) %s %d bytes at %d\n",
- SVCFH_fmt(&argp->fh),
- argp->count, (u32) argp->cookie);
+ trace_nfsd_vfs_readdir(rqstp, &argp->fh, argp->count, argp->cookie);
nfsd3_init_dirlist_pages(rqstp, resp, argp->count);
@@ -655,9 +606,7 @@ nfsd3_proc_readdirplus(struct svc_rqst *rqstp)
struct nfsd3_readdirres *resp = rqstp->rq_resp;
loff_t offset;
- dprintk("nfsd: READDIR+(3) %s %d bytes at %d\n",
- SVCFH_fmt(&argp->fh),
- argp->count, (u32) argp->cookie);
+ trace_nfsd_vfs_readdir(rqstp, &argp->fh, argp->count, argp->cookie);
nfsd3_init_dirlist_pages(rqstp, resp, argp->count);
@@ -698,9 +647,6 @@ nfsd3_proc_fsstat(struct svc_rqst *rqstp)
struct nfsd_fhandle *argp = rqstp->rq_argp;
struct nfsd3_fsstatres *resp = rqstp->rq_resp;
- dprintk("nfsd: FSSTAT(3) %s\n",
- SVCFH_fmt(&argp->fh));
-
resp->status = nfsd_statfs(rqstp, &argp->fh, &resp->stats, 0);
fh_put(&argp->fh);
resp->status = nfsd3_map_status(resp->status);
diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index ec6539cec0fe..ccb00aa93be0 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -417,6 +417,29 @@ static u32 highest_slotid(struct nfsd4_session *ses)
return idx;
}
+static void
+encode_referring_call4(struct xdr_stream *xdr,
+ const struct nfsd4_referring_call *rc)
+{
+ encode_uint32(xdr, rc->rc_sequenceid);
+ encode_uint32(xdr, rc->rc_slotid);
+}
+
+static void
+encode_referring_call_list4(struct xdr_stream *xdr,
+ const struct nfsd4_referring_call_list *rcl)
+{
+ struct nfsd4_referring_call *rc;
+ __be32 *p;
+
+ p = xdr_reserve_space(xdr, NFS4_MAX_SESSIONID_LEN);
+ xdr_encode_opaque_fixed(p, rcl->rcl_sessionid.data,
+ NFS4_MAX_SESSIONID_LEN);
+ encode_uint32(xdr, rcl->__nr_referring_calls);
+ list_for_each_entry(rc, &rcl->rcl_referring_calls, __list)
+ encode_referring_call4(xdr, rc);
+}
+
/*
* CB_SEQUENCE4args
*
@@ -434,6 +457,7 @@ static void encode_cb_sequence4args(struct xdr_stream *xdr,
struct nfs4_cb_compound_hdr *hdr)
{
struct nfsd4_session *session = cb->cb_clp->cl_cb_session;
+ struct nfsd4_referring_call_list *rcl;
__be32 *p;
if (hdr->minorversion == 0)
@@ -442,12 +466,16 @@ static void encode_cb_sequence4args(struct xdr_stream *xdr,
encode_nfs_cb_opnum4(xdr, OP_CB_SEQUENCE);
encode_sessionid4(xdr, session);
- p = xdr_reserve_space(xdr, 4 + 4 + 4 + 4 + 4);
+ p = xdr_reserve_space(xdr, XDR_UNIT * 4);
*p++ = cpu_to_be32(session->se_cb_seq_nr[cb->cb_held_slot]); /* csa_sequenceid */
*p++ = cpu_to_be32(cb->cb_held_slot); /* csa_slotid */
*p++ = cpu_to_be32(highest_slotid(session)); /* csa_highest_slotid */
*p++ = xdr_zero; /* csa_cachethis */
- xdr_encode_empty_array(p); /* csa_referring_call_lists */
+
+ /* csa_referring_call_lists */
+ encode_uint32(xdr, cb->cb_nr_referring_call_list);
+ list_for_each_entry(rcl, &cb->cb_referring_call_list, __list)
+ encode_referring_call_list4(xdr, rcl);
hdr->nops++;
}
@@ -1320,10 +1348,102 @@ static void nfsd41_destroy_cb(struct nfsd4_callback *cb)
nfsd41_cb_inflight_end(clp);
}
-/*
- * TODO: cb_sequence should support referring call lists, cachethis,
- * and mark callback channel down on communication errors.
+/**
+ * nfsd41_cb_referring_call - add a referring call to a callback operation
+ * @cb: context of callback to add the rc to
+ * @sessionid: referring call's session ID
+ * @slotid: referring call's session slot index
+ * @seqno: referring call's slot sequence number
+ *
+ * Caller serializes access to @cb.
+ *
+ * NB: If memory allocation fails, the referring call is not added.
*/
+void nfsd41_cb_referring_call(struct nfsd4_callback *cb,
+ struct nfs4_sessionid *sessionid,
+ u32 slotid, u32 seqno)
+{
+ struct nfsd4_referring_call_list *rcl;
+ struct nfsd4_referring_call *rc;
+ bool found;
+
+ might_sleep();
+
+ found = false;
+ list_for_each_entry(rcl, &cb->cb_referring_call_list, __list) {
+ if (!memcmp(rcl->rcl_sessionid.data, sessionid->data,
+ NFS4_MAX_SESSIONID_LEN)) {
+ found = true;
+ break;
+ }
+ }
+ if (!found) {
+ rcl = kmalloc(sizeof(*rcl), GFP_KERNEL);
+ if (!rcl)
+ return;
+ memcpy(rcl->rcl_sessionid.data, sessionid->data,
+ NFS4_MAX_SESSIONID_LEN);
+ rcl->__nr_referring_calls = 0;
+ INIT_LIST_HEAD(&rcl->rcl_referring_calls);
+ list_add(&rcl->__list, &cb->cb_referring_call_list);
+ cb->cb_nr_referring_call_list++;
+ }
+
+ found = false;
+ list_for_each_entry(rc, &rcl->rcl_referring_calls, __list) {
+ if (rc->rc_sequenceid == seqno && rc->rc_slotid == slotid) {
+ found = true;
+ break;
+ }
+ }
+ if (!found) {
+ rc = kmalloc(sizeof(*rc), GFP_KERNEL);
+ if (!rc)
+ goto out;
+ rc->rc_sequenceid = seqno;
+ rc->rc_slotid = slotid;
+ rcl->__nr_referring_calls++;
+ list_add(&rc->__list, &rcl->rcl_referring_calls);
+ }
+
+out:
+ if (!rcl->__nr_referring_calls) {
+ cb->cb_nr_referring_call_list--;
+ kfree(rcl);
+ }
+}
+
+/**
+ * nfsd41_cb_destroy_referring_call_list - release referring call info
+ * @cb: context of a callback that has completed
+ *
+ * Callers who allocate referring calls using nfsd41_cb_referring_call() must
+ * release those resources by calling nfsd41_cb_destroy_referring_call_list.
+ *
+ * Caller serializes access to @cb.
+ */
+void nfsd41_cb_destroy_referring_call_list(struct nfsd4_callback *cb)
+{
+ struct nfsd4_referring_call_list *rcl;
+ struct nfsd4_referring_call *rc;
+
+ while (!list_empty(&cb->cb_referring_call_list)) {
+ rcl = list_first_entry(&cb->cb_referring_call_list,
+ struct nfsd4_referring_call_list,
+ __list);
+
+ while (!list_empty(&rcl->rcl_referring_calls)) {
+ rc = list_first_entry(&rcl->rcl_referring_calls,
+ struct nfsd4_referring_call,
+ __list);
+ list_del(&rc->__list);
+ kfree(rc);
+ }
+ list_del(&rcl->__list);
+ kfree(rcl);
+ }
+}
+
static void nfsd4_cb_prepare(struct rpc_task *task, void *calldata)
{
struct nfsd4_callback *cb = calldata;
@@ -1643,6 +1763,8 @@ void nfsd4_init_cb(struct nfsd4_callback *cb, struct nfs4_client *clp,
INIT_WORK(&cb->cb_work, nfsd4_run_cb_work);
cb->cb_status = 0;
cb->cb_held_slot = -1;
+ cb->cb_nr_referring_call_list = 0;
+ INIT_LIST_HEAD(&cb->cb_referring_call_list);
}
/**
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index fd560dcf6059..f13abbb13b38 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -878,6 +878,8 @@ nfsd4_getattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
struct nfsd4_getattr *getattr = &u->getattr;
__be32 status;
+ trace_nfsd_vfs_getattr(rqstp, &cstate->current_fh);
+
status = fh_verify(rqstp, &cstate->current_fh, 0, NFSD_MAY_NOP);
if (status)
return status;
@@ -1000,6 +1002,9 @@ nfsd4_readdir(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
u64 cookie = readdir->rd_cookie;
static const nfs4_verifier zeroverf;
+ trace_nfsd_vfs_readdir(rqstp, &cstate->current_fh,
+ readdir->rd_maxcount, readdir->rd_cookie);
+
/* no need to check permission - this will be done in nfsd_readdir() */
if (readdir->rd_bmval[1] & NFSD_WRITEONLY_ATTRS_WORD1)
@@ -1213,7 +1218,6 @@ nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
struct nfsd_file *nf = NULL;
__be32 status = nfs_ok;
unsigned long cnt;
- int nvecs;
if (write->wr_offset > (u64)OFFSET_MAX ||
write->wr_offset + write->wr_buflen > (u64)OFFSET_MAX)
@@ -1228,13 +1232,9 @@ nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
return status;
write->wr_how_written = write->wr_stable_how;
-
- nvecs = svc_fill_write_vector(rqstp, &write->wr_payload);
- WARN_ON_ONCE(nvecs > ARRAY_SIZE(rqstp->rq_vec));
-
status = nfsd_vfs_write(rqstp, &cstate->current_fh, nf,
- write->wr_offset, rqstp->rq_vec, nvecs, &cnt,
- write->wr_how_written,
+ write->wr_offset, &write->wr_payload,
+ &cnt, write->wr_how_written,
(__be32 *)write->wr_verifier.data);
nfsd_file_put(nf);
@@ -1381,8 +1381,11 @@ static void nfs4_put_copy(struct nfsd4_copy *copy)
static void nfsd4_stop_copy(struct nfsd4_copy *copy)
{
trace_nfsd_copy_async_cancel(copy);
- if (!test_and_set_bit(NFSD4_COPY_F_STOPPED, &copy->cp_flags))
+ if (!test_and_set_bit(NFSD4_COPY_F_STOPPED, &copy->cp_flags)) {
kthread_stop(copy->copy_task);
+ copy->nfserr = nfs_ok;
+ set_bit(NFSD4_COPY_F_COMPLETED, &copy->cp_flags);
+ }
nfs4_put_copy(copy);
}
@@ -1711,10 +1714,11 @@ static int nfsd4_cb_offload_done(struct nfsd4_callback *cb,
switch (task->tk_status) {
case -NFS4ERR_DELAY:
if (cbo->co_retries--) {
- rpc_delay(task, 1 * HZ);
+ rpc_delay(task, HZ / 5);
return 0;
}
}
+ nfsd41_cb_destroy_referring_call_list(cb);
return 1;
}
@@ -1847,6 +1851,9 @@ static void nfsd4_send_cb_offload(struct nfsd4_copy *copy)
nfsd4_init_cb(&cbo->co_cb, copy->cp_clp, &nfsd4_cb_offload_ops,
NFSPROC4_CLNT_CB_OFFLOAD);
+ nfsd41_cb_referring_call(&cbo->co_cb, &cbo->co_referring_sessionid,
+ cbo->co_referring_slotid,
+ cbo->co_referring_seqno);
trace_nfsd_cb_offload(copy->cp_clp, &cbo->co_res.cb_stateid,
&cbo->co_fh, copy->cp_count, copy->nfserr);
nfsd4_try_run_cb(&cbo->co_cb);
@@ -1963,6 +1970,11 @@ nfsd4_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
memcpy(&result->cb_stateid, &copy->cp_stateid.cs_stid,
sizeof(result->cb_stateid));
dup_copy_fields(copy, async_copy);
+ memcpy(async_copy->cp_cb_offload.co_referring_sessionid.data,
+ cstate->session->se_sessionid.data,
+ NFS4_MAX_SESSIONID_LEN);
+ async_copy->cp_cb_offload.co_referring_slotid = cstate->slot->sl_index;
+ async_copy->cp_cb_offload.co_referring_seqno = cstate->slot->sl_seqid;
async_copy->copy_task = kthread_create(nfsd4_do_async_copy,
async_copy, "%s", "copy thread");
if (IS_ERR(async_copy->copy_task))
@@ -3768,7 +3780,8 @@ bool nfsd4_spo_must_allow(struct svc_rqst *rqstp)
struct nfs4_op_map *allow = &cstate->clp->cl_spo_must_allow;
u32 opiter;
- if (!cstate->minorversion)
+ if (rqstp->rq_procinfo != &nfsd_version4.vs_proc[NFSPROC4_COMPOUND] ||
+ cstate->minorversion == 0)
return false;
if (cstate->spo_must_allowed)
@@ -3834,7 +3847,7 @@ static const struct svc_procedure nfsd_procedures4[2] = {
.pc_ressize = sizeof(struct nfsd4_compoundres),
.pc_release = nfsd4_release_compoundargs,
.pc_cachetype = RC_NOCACHE,
- .pc_xdrressize = NFSD_BUFSIZE/4,
+ .pc_xdrressize = 3+NFSSVC_MAXBLKSIZE/4,
.pc_name = "COMPOUND",
},
};
diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c
index acde3edab733..82785db730d9 100644
--- a/fs/nfsd/nfs4recover.c
+++ b/fs/nfsd/nfs4recover.c
@@ -33,6 +33,7 @@
*/
#include <crypto/hash.h>
+#include <crypto/sha2.h>
#include <linux/file.h>
#include <linux/slab.h>
#include <linux/namei.h>
@@ -737,7 +738,6 @@ struct cld_net {
spinlock_t cn_lock;
struct list_head cn_list;
unsigned int cn_xid;
- struct crypto_shash *cn_tfm;
#ifdef CONFIG_NFSD_LEGACY_CLIENT_TRACKING
bool cn_has_legacy;
#endif
@@ -1063,8 +1063,6 @@ nfsd4_remove_cld_pipe(struct net *net)
nfsd4_cld_unregister_net(net, cn->cn_pipe);
rpc_destroy_pipe_data(cn->cn_pipe);
- if (cn->cn_tfm)
- crypto_free_shash(cn->cn_tfm);
kfree(nn->cld_net);
nn->cld_net = NULL;
}
@@ -1158,8 +1156,6 @@ nfsd4_cld_create_v2(struct nfs4_client *clp)
struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
struct cld_net *cn = nn->cld_net;
struct cld_msg_v2 *cmsg;
- struct crypto_shash *tfm = cn->cn_tfm;
- struct xdr_netobj cksum;
char *principal = NULL;
/* Don't upcall if it's already stored */
@@ -1182,22 +1178,9 @@ nfsd4_cld_create_v2(struct nfs4_client *clp)
else if (clp->cl_cred.cr_principal)
principal = clp->cl_cred.cr_principal;
if (principal) {
- cksum.len = crypto_shash_digestsize(tfm);
- cksum.data = kmalloc(cksum.len, GFP_KERNEL);
- if (cksum.data == NULL) {
- ret = -ENOMEM;
- goto out;
- }
- ret = crypto_shash_tfm_digest(tfm, principal, strlen(principal),
- cksum.data);
- if (ret) {
- kfree(cksum.data);
- goto out;
- }
- cmsg->cm_u.cm_clntinfo.cc_princhash.cp_len = cksum.len;
- memcpy(cmsg->cm_u.cm_clntinfo.cc_princhash.cp_data,
- cksum.data, cksum.len);
- kfree(cksum.data);
+ sha256(principal, strlen(principal),
+ cmsg->cm_u.cm_clntinfo.cc_princhash.cp_data);
+ cmsg->cm_u.cm_clntinfo.cc_princhash.cp_len = SHA256_DIGEST_SIZE;
} else
cmsg->cm_u.cm_clntinfo.cc_princhash.cp_len = 0;
@@ -1207,7 +1190,6 @@ nfsd4_cld_create_v2(struct nfs4_client *clp)
set_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags);
}
-out:
free_cld_upcall(cup);
out_err:
if (ret)
@@ -1346,12 +1328,11 @@ found:
static int
nfsd4_cld_check_v2(struct nfs4_client *clp)
{
- struct nfs4_client_reclaim *crp;
struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
+#ifdef CONFIG_NFSD_LEGACY_CLIENT_TRACKING
struct cld_net *cn = nn->cld_net;
- int status;
- struct crypto_shash *tfm = cn->cn_tfm;
- struct xdr_netobj cksum;
+#endif
+ struct nfs4_client_reclaim *crp;
char *principal = NULL;
/* did we already find that this client is stable? */
@@ -1367,6 +1348,7 @@ nfsd4_cld_check_v2(struct nfs4_client *clp)
if (cn->cn_has_legacy) {
struct xdr_netobj name;
char dname[HEXDIR_LEN];
+ int status;
status = nfs4_make_rec_clidname(dname, &clp->cl_name);
if (status)
@@ -1389,28 +1371,18 @@ nfsd4_cld_check_v2(struct nfs4_client *clp)
return -ENOENT;
found:
if (crp->cr_princhash.len) {
+ u8 digest[SHA256_DIGEST_SIZE];
+
if (clp->cl_cred.cr_raw_principal)
principal = clp->cl_cred.cr_raw_principal;
else if (clp->cl_cred.cr_principal)
principal = clp->cl_cred.cr_principal;
if (principal == NULL)
return -ENOENT;
- cksum.len = crypto_shash_digestsize(tfm);
- cksum.data = kmalloc(cksum.len, GFP_KERNEL);
- if (cksum.data == NULL)
- return -ENOENT;
- status = crypto_shash_tfm_digest(tfm, principal,
- strlen(principal), cksum.data);
- if (status) {
- kfree(cksum.data);
+ sha256(principal, strlen(principal), digest);
+ if (memcmp(crp->cr_princhash.data, digest,
+ crp->cr_princhash.len))
return -ENOENT;
- }
- if (memcmp(crp->cr_princhash.data, cksum.data,
- crp->cr_princhash.len)) {
- kfree(cksum.data);
- return -ENOENT;
- }
- kfree(cksum.data);
}
crp->cr_clp = clp;
return 0;
@@ -1590,7 +1562,6 @@ nfsd4_cld_tracking_init(struct net *net)
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
bool running;
int retries = 10;
- struct crypto_shash *tfm;
status = nfs4_cld_state_init(net);
if (status)
@@ -1615,12 +1586,6 @@ nfsd4_cld_tracking_init(struct net *net)
status = -ETIMEDOUT;
goto err_remove;
}
- tfm = crypto_alloc_shash("sha256", 0, 0);
- if (IS_ERR(tfm)) {
- status = PTR_ERR(tfm);
- goto err_remove;
- }
- nn->cld_net->cn_tfm = tfm;
status = nfsd4_cld_get_version(nn);
if (status == -EOPNOTSUPP)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 59a693f22452..d5694987f86f 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -1987,26 +1987,30 @@ reduce_session_slots(struct nfsd4_session *ses, int dec)
return ret;
}
-/*
- * We don't actually need to cache the rpc and session headers, so we
- * can allocate a little less for each slot:
- */
-static inline u32 slot_bytes(struct nfsd4_channel_attrs *ca)
+static struct nfsd4_slot *nfsd4_alloc_slot(struct nfsd4_channel_attrs *fattrs,
+ int index, gfp_t gfp)
{
- u32 size;
+ struct nfsd4_slot *slot;
+ size_t size;
- if (ca->maxresp_cached < NFSD_MIN_HDR_SEQ_SZ)
- size = 0;
- else
- size = ca->maxresp_cached - NFSD_MIN_HDR_SEQ_SZ;
- return size + sizeof(struct nfsd4_slot);
+ /*
+ * The RPC and NFS session headers are never saved in
+ * the slot reply cache buffer.
+ */
+ size = fattrs->maxresp_cached < NFSD_MIN_HDR_SEQ_SZ ?
+ 0 : fattrs->maxresp_cached - NFSD_MIN_HDR_SEQ_SZ;
+
+ slot = kzalloc(struct_size(slot, sl_data, size), gfp);
+ if (!slot)
+ return NULL;
+ slot->sl_index = index;
+ return slot;
}
static struct nfsd4_session *alloc_session(struct nfsd4_channel_attrs *fattrs,
struct nfsd4_channel_attrs *battrs)
{
int numslots = fattrs->maxreqs;
- int slotsize = slot_bytes(fattrs);
struct nfsd4_session *new;
struct nfsd4_slot *slot;
int i;
@@ -2015,14 +2019,14 @@ static struct nfsd4_session *alloc_session(struct nfsd4_channel_attrs *fattrs,
if (!new)
return NULL;
xa_init(&new->se_slots);
- /* allocate each struct nfsd4_slot and data cache in one piece */
- slot = kzalloc(slotsize, GFP_KERNEL);
+
+ slot = nfsd4_alloc_slot(fattrs, 0, GFP_KERNEL);
if (!slot || xa_is_err(xa_store(&new->se_slots, 0, slot, GFP_KERNEL)))
goto out_free;
for (i = 1; i < numslots; i++) {
const gfp_t gfp = GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN;
- slot = kzalloc(slotsize, gfp);
+ slot = nfsd4_alloc_slot(fattrs, i, gfp);
if (!slot)
break;
if (xa_is_err(xa_store(&new->se_slots, i, slot, gfp))) {
@@ -4402,7 +4406,7 @@ nfsd4_sequence(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
nfserr_rep_too_big;
if (xdr_restrict_buflen(xdr, buflen - rqstp->rq_auth_slack))
goto out_put_session;
- svc_reserve(rqstp, buflen);
+ svc_reserve_auth(rqstp, buflen);
status = nfs_ok;
/* Success! accept new slot seqid */
@@ -4438,8 +4442,8 @@ nfsd4_sequence(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
* spinlock, and only succeeds if there is
* plenty of memory.
*/
- slot = kzalloc(slot_bytes(&session->se_fchannel),
- GFP_NOWAIT);
+ slot = nfsd4_alloc_slot(&session->se_fchannel, s,
+ GFP_NOWAIT);
prev_slot = xa_load(&session->se_slots, s);
if (xa_is_value(prev_slot) && slot) {
slot->sl_seqid = xa_to_value(prev_slot);
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index fe876395985a..3afcdbed6e14 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -2564,7 +2564,7 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp)
/* Sessions make the DRC unnecessary: */
if (argp->minorversion)
cachethis = false;
- svc_reserve(argp->rqstp, max_reply + readbytes);
+ svc_reserve_auth(argp->rqstp, max_reply + readbytes);
argp->rqstp->rq_cachetype = cachethis ? RC_REPLBUFF : RC_NOCACHE;
argp->splice_ok = nfsd_read_splice_ok(argp->rqstp);
@@ -3391,6 +3391,23 @@ static __be32 nfsd4_encode_fattr4_suppattr_exclcreat(struct xdr_stream *xdr,
return nfsd4_encode_bitmap4(xdr, supp[0], supp[1], supp[2]);
}
+/*
+ * Copied from generic_remap_checks/generic_remap_file_range_prep.
+ *
+ * These generic functions use the file system's s_blocksize, but
+ * individual file systems aren't required to use
+ * generic_remap_file_range_prep. Until there is a mechanism for
+ * determining a particular file system's (or file's) clone block
+ * size, this is the best NFSD can do.
+ */
+static __be32 nfsd4_encode_fattr4_clone_blksize(struct xdr_stream *xdr,
+ const struct nfsd4_fattr_args *args)
+{
+ struct inode *inode = d_inode(args->dentry);
+
+ return nfsd4_encode_uint32_t(xdr, inode->i_sb->s_blocksize);
+}
+
#ifdef CONFIG_NFSD_V4_SECURITY_LABEL
static __be32 nfsd4_encode_fattr4_sec_label(struct xdr_stream *xdr,
const struct nfsd4_fattr_args *args)
@@ -3545,7 +3562,7 @@ static const nfsd4_enc_attr nfsd4_enc_fattr4_encode_ops[] = {
[FATTR4_MODE_SET_MASKED] = nfsd4_encode_fattr4__noop,
[FATTR4_SUPPATTR_EXCLCREAT] = nfsd4_encode_fattr4_suppattr_exclcreat,
[FATTR4_FS_CHARSET_CAP] = nfsd4_encode_fattr4__noop,
- [FATTR4_CLONE_BLKSIZE] = nfsd4_encode_fattr4__noop,
+ [FATTR4_CLONE_BLKSIZE] = nfsd4_encode_fattr4_clone_blksize,
[FATTR4_SPACE_FREED] = nfsd4_encode_fattr4__noop,
[FATTR4_CHANGE_ATTR_TYPE] = nfsd4_encode_fattr4__noop,
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index ac265d6fde35..3f3e9f6c4250 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -2281,6 +2281,8 @@ static int __init init_nfsd(void)
{
int retval;
+ nfsd_debugfs_init();
+
retval = nfsd4_init_slabs();
if (retval)
return retval;
@@ -2291,12 +2293,9 @@ static int __init init_nfsd(void)
if (retval)
goto out_free_pnfs;
nfsd_lockd_init(); /* lockd->nfsd callbacks */
- retval = create_proc_exports_entry();
- if (retval)
- goto out_free_lockd;
retval = register_pernet_subsys(&nfsd_net_ops);
if (retval < 0)
- goto out_free_exports;
+ goto out_free_lockd;
retval = register_cld_notifier();
if (retval)
goto out_free_subsys;
@@ -2305,22 +2304,26 @@ static int __init init_nfsd(void)
goto out_free_cld;
retval = register_filesystem(&nfsd_fs_type);
if (retval)
- goto out_free_all;
+ goto out_free_nfsd4;
retval = genl_register_family(&nfsd_nl_family);
if (retval)
+ goto out_free_filesystem;
+ retval = create_proc_exports_entry();
+ if (retval)
goto out_free_all;
nfsd_localio_ops_init();
return 0;
out_free_all:
+ genl_unregister_family(&nfsd_nl_family);
+out_free_filesystem:
+ unregister_filesystem(&nfsd_fs_type);
+out_free_nfsd4:
nfsd4_destroy_laundry_wq();
out_free_cld:
unregister_cld_notifier();
out_free_subsys:
unregister_pernet_subsys(&nfsd_net_ops);
-out_free_exports:
- remove_proc_entry("fs/nfs/exports", NULL);
- remove_proc_entry("fs/nfs", NULL);
out_free_lockd:
nfsd_lockd_shutdown();
nfsd_drc_slab_free();
@@ -2328,22 +2331,24 @@ out_free_pnfs:
nfsd4_exit_pnfs();
out_free_slabs:
nfsd4_free_slabs();
+ nfsd_debugfs_exit();
return retval;
}
static void __exit exit_nfsd(void)
{
+ remove_proc_entry("fs/nfs/exports", NULL);
+ remove_proc_entry("fs/nfs", NULL);
genl_unregister_family(&nfsd_nl_family);
unregister_filesystem(&nfsd_fs_type);
nfsd4_destroy_laundry_wq();
unregister_cld_notifier();
unregister_pernet_subsys(&nfsd_net_ops);
nfsd_drc_slab_free();
- remove_proc_entry("fs/nfs/exports", NULL);
- remove_proc_entry("fs/nfs", NULL);
nfsd_lockd_shutdown();
nfsd4_free_slabs();
nfsd4_exit_pnfs();
+ nfsd_debugfs_exit();
}
MODULE_AUTHOR("Olaf Kirch <okir@monad.swb.de>");
diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h
index e2997f0ffbc5..1bfd0b4e9af7 100644
--- a/fs/nfsd/nfsd.h
+++ b/fs/nfsd/nfsd.h
@@ -44,24 +44,14 @@ bool nfsd_support_version(int vers);
#include "stats.h"
/*
- * Maximum blocksizes supported by daemon under various circumstances.
+ * Default and maximum payload size (NFS READ or WRITE), in bytes.
+ * The default is historical, and the maximum is an implementation
+ * limit.
*/
-#define NFSSVC_MAXBLKSIZE RPCSVC_MAXPAYLOAD
-/* NFSv2 is limited by the protocol specification, see RFC 1094 */
-#define NFSSVC_MAXBLKSIZE_V2 (8*1024)
-
-
-/*
- * Largest number of bytes we need to allocate for an NFS
- * call or reply. Used to control buffer sizes. We use
- * the length of v3 WRITE, READDIR and READDIR replies
- * which are an RPC header, up to 26 XDR units of reply
- * data, and some page data.
- *
- * Note that accuracy here doesn't matter too much as the
- * size is rounded up to a page size when allocating space.
- */
-#define NFSD_BUFSIZE ((RPC_MAX_HEADER_WITH_AUTH+26)*XDR_UNIT + NFSSVC_MAXBLKSIZE)
+enum {
+ NFSSVC_DEFBLKSIZE = 1 * 1024 * 1024,
+ NFSSVC_MAXBLKSIZE = RPCSVC_MAXPAYLOAD,
+};
struct readdir_cd {
__be32 err; /* 0, nfserr, or nfserr_eof */
@@ -156,6 +146,16 @@ void nfsd_reset_versions(struct nfsd_net *nn);
int nfsd_create_serv(struct net *net);
void nfsd_destroy_serv(struct net *net);
+#ifdef CONFIG_DEBUG_FS
+void nfsd_debugfs_init(void);
+void nfsd_debugfs_exit(void);
+#else
+static inline void nfsd_debugfs_init(void) {}
+static inline void nfsd_debugfs_exit(void) {}
+#endif
+
+extern bool nfsd_disable_splice_read __read_mostly;
+
extern int nfsd_max_blksize;
static inline int nfsd_v4client(struct svc_rqst *rq)
diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c
index 6370ac0a85fd..c10fa8128a8a 100644
--- a/fs/nfsd/nfsproc.c
+++ b/fs/nfsd/nfsproc.c
@@ -10,6 +10,7 @@
#include "cache.h"
#include "xdr.h"
#include "vfs.h"
+#include "trace.h"
#define NFSDDBG_FACILITY NFSDDBG_PROC
@@ -54,7 +55,7 @@ nfsd_proc_getattr(struct svc_rqst *rqstp)
struct nfsd_fhandle *argp = rqstp->rq_argp;
struct nfsd_attrstat *resp = rqstp->rq_resp;
- dprintk("nfsd: GETATTR %s\n", SVCFH_fmt(&argp->fh));
+ trace_nfsd_vfs_getattr(rqstp, &argp->fh);
fh_copy(&resp->fh, &argp->fh);
resp->status = fh_verify(rqstp, &resp->fh, 0,
@@ -211,7 +212,7 @@ nfsd_proc_read(struct svc_rqst *rqstp)
SVCFH_fmt(&argp->fh),
argp->count, argp->offset);
- argp->count = min_t(u32, argp->count, NFSSVC_MAXBLKSIZE_V2);
+ argp->count = min_t(u32, argp->count, NFS_MAXDATA);
argp->count = min_t(u32, argp->count, rqstp->rq_res.buflen);
resp->pages = rqstp->rq_next_page;
@@ -250,17 +251,14 @@ nfsd_proc_write(struct svc_rqst *rqstp)
struct nfsd_writeargs *argp = rqstp->rq_argp;
struct nfsd_attrstat *resp = rqstp->rq_resp;
unsigned long cnt = argp->len;
- unsigned int nvecs;
dprintk("nfsd: WRITE %s %u bytes at %d\n",
SVCFH_fmt(&argp->fh),
argp->len, argp->offset);
- nvecs = svc_fill_write_vector(rqstp, &argp->payload);
-
- resp->status = nfsd_write(rqstp, fh_copy(&resp->fh, &argp->fh),
- argp->offset, rqstp->rq_vec, nvecs,
- &cnt, NFS_DATA_SYNC, NULL);
+ fh_copy(&resp->fh, &argp->fh);
+ resp->status = nfsd_write(rqstp, &resp->fh, argp->offset,
+ &argp->payload, &cnt, NFS_DATA_SYNC, NULL);
if (resp->status == nfs_ok)
resp->status = fh_getattr(&resp->fh, &resp->stat);
else if (resp->status == nfserr_jukebox)
@@ -292,9 +290,6 @@ nfsd_proc_create(struct svc_rqst *rqstp)
int hosterr;
dev_t rdev = 0, wanted = new_decode_dev(attr->ia_size);
- dprintk("nfsd: CREATE %s %.*s\n",
- SVCFH_fmt(dirfhp), argp->len, argp->name);
-
/* First verify the parent file handle */
resp->status = fh_verify(rqstp, dirfhp, S_IFDIR, NFSD_MAY_EXEC);
if (resp->status != nfs_ok)
@@ -446,9 +441,6 @@ nfsd_proc_remove(struct svc_rqst *rqstp)
struct nfsd_diropargs *argp = rqstp->rq_argp;
struct nfsd_stat *resp = rqstp->rq_resp;
- dprintk("nfsd: REMOVE %s %.*s\n", SVCFH_fmt(&argp->fh),
- argp->len, argp->name);
-
/* Unlink. -SIFDIR means file must not be a directory */
resp->status = nfsd_unlink(rqstp, &argp->fh, -S_IFDIR,
argp->name, argp->len);
@@ -463,11 +455,6 @@ nfsd_proc_rename(struct svc_rqst *rqstp)
struct nfsd_renameargs *argp = rqstp->rq_argp;
struct nfsd_stat *resp = rqstp->rq_resp;
- dprintk("nfsd: RENAME %s %.*s -> \n",
- SVCFH_fmt(&argp->ffh), argp->flen, argp->fname);
- dprintk("nfsd: -> %s %.*s\n",
- SVCFH_fmt(&argp->tfh), argp->tlen, argp->tname);
-
resp->status = nfsd_rename(rqstp, &argp->ffh, argp->fname, argp->flen,
&argp->tfh, argp->tname, argp->tlen);
fh_put(&argp->ffh);
@@ -482,13 +469,6 @@ nfsd_proc_link(struct svc_rqst *rqstp)
struct nfsd_linkargs *argp = rqstp->rq_argp;
struct nfsd_stat *resp = rqstp->rq_resp;
- dprintk("nfsd: LINK %s ->\n",
- SVCFH_fmt(&argp->ffh));
- dprintk("nfsd: %s %.*s\n",
- SVCFH_fmt(&argp->tfh),
- argp->tlen,
- argp->tname);
-
resp->status = nfsd_link(rqstp, &argp->tfh, argp->tname, argp->tlen,
&argp->ffh);
fh_put(&argp->ffh);
@@ -520,10 +500,6 @@ nfsd_proc_symlink(struct svc_rqst *rqstp)
goto out;
}
- dprintk("nfsd: SYMLINK %s %.*s -> %.*s\n",
- SVCFH_fmt(&argp->ffh), argp->flen, argp->fname,
- argp->tlen, argp->tname);
-
fh_init(&newfh, NFS_FHSIZE);
resp->status = nfsd_symlink(rqstp, &argp->ffh, argp->fname, argp->flen,
argp->tname, &attrs, &newfh);
@@ -549,8 +525,6 @@ nfsd_proc_mkdir(struct svc_rqst *rqstp)
.na_iattr = &argp->attrs,
};
- dprintk("nfsd: MKDIR %s %.*s\n", SVCFH_fmt(&argp->fh), argp->len, argp->name);
-
if (resp->fh.fh_dentry) {
printk(KERN_WARNING
"nfsd_proc_mkdir: response already verified??\n");
@@ -579,8 +553,6 @@ nfsd_proc_rmdir(struct svc_rqst *rqstp)
struct nfsd_diropargs *argp = rqstp->rq_argp;
struct nfsd_stat *resp = rqstp->rq_resp;
- dprintk("nfsd: RMDIR %s %.*s\n", SVCFH_fmt(&argp->fh), argp->len, argp->name);
-
resp->status = nfsd_unlink(rqstp, &argp->fh, S_IFDIR,
argp->name, argp->len);
fh_put(&argp->fh);
@@ -616,9 +588,7 @@ nfsd_proc_readdir(struct svc_rqst *rqstp)
struct nfsd_readdirres *resp = rqstp->rq_resp;
loff_t offset;
- dprintk("nfsd: READDIR %s %d bytes at %d\n",
- SVCFH_fmt(&argp->fh),
- argp->count, argp->cookie);
+ trace_nfsd_vfs_readdir(rqstp, &argp->fh, argp->count, argp->cookie);
nfsd_init_dirlist_pages(rqstp, resp, argp->count);
@@ -643,8 +613,6 @@ nfsd_proc_statfs(struct svc_rqst *rqstp)
struct nfsd_fhandle *argp = rqstp->rq_argp;
struct nfsd_statfsres *resp = rqstp->rq_resp;
- dprintk("nfsd: STATFS %s\n", SVCFH_fmt(&argp->fh));
-
resp->status = nfsd_statfs(rqstp, &argp->fh, &resp->stats,
NFSD_MAY_BYPASS_GSS_ON_ROOT);
fh_put(&argp->fh);
@@ -740,7 +708,7 @@ static const struct svc_procedure nfsd_procedures2[18] = {
.pc_argzero = sizeof(struct nfsd_readargs),
.pc_ressize = sizeof(struct nfsd_readres),
.pc_cachetype = RC_NOCACHE,
- .pc_xdrressize = ST+AT+1+NFSSVC_MAXBLKSIZE_V2/4,
+ .pc_xdrressize = ST+AT+1+NFS_MAXDATA/4,
.pc_name = "READ",
},
[NFSPROC_WRITECACHE] = {
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index 9b3d6cff0e1e..82b0111ac469 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -396,13 +396,13 @@ static int nfsd_startup_net(struct net *net, const struct cred *cred)
if (ret)
goto out_filecache;
+#ifdef CONFIG_NFSD_V4_2_INTER_SSC
+ nfsd4_ssc_init_umount_work(nn);
+#endif
ret = nfs4_state_start_net(net);
if (ret)
goto out_reply_cache;
-#ifdef CONFIG_NFSD_V4_2_INTER_SSC
- nfsd4_ssc_init_umount_work(nn);
-#endif
nn->nfsd_net_up = true;
return 0;
@@ -582,7 +582,7 @@ static int nfsd_get_default_max_blksize(void)
*/
target >>= 12;
- ret = NFSSVC_MAXBLKSIZE;
+ ret = NFSSVC_DEFBLKSIZE;
while (ret > target && ret >= 8*1024*2)
ret /= 2;
return ret;
diff --git a/fs/nfsd/nfsxdr.c b/fs/nfsd/nfsxdr.c
index 5777f40c7353..fc262ceafca9 100644
--- a/fs/nfsd/nfsxdr.c
+++ b/fs/nfsd/nfsxdr.c
@@ -336,7 +336,7 @@ nfssvc_decode_writeargs(struct svc_rqst *rqstp, struct xdr_stream *xdr)
/* opaque data */
if (xdr_stream_decode_u32(xdr, &args->len) < 0)
return false;
- if (args->len > NFSSVC_MAXBLKSIZE_V2)
+ if (args->len > NFS_MAXDATA)
return false;
return xdr_stream_subsegment(xdr, &args->payload, args->len);
@@ -540,7 +540,7 @@ nfssvc_encode_statfsres(struct svc_rqst *rqstp, struct xdr_stream *xdr)
p = xdr_reserve_space(xdr, XDR_UNIT * 5);
if (!p)
return false;
- *p++ = cpu_to_be32(NFSSVC_MAXBLKSIZE_V2);
+ *p++ = cpu_to_be32(NFS_MAXDATA);
*p++ = cpu_to_be32(stat->f_bsize);
*p++ = cpu_to_be32(stat->f_blocks);
*p++ = cpu_to_be32(stat->f_bfree);
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 290e29dd43eb..1995bca158b8 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -64,6 +64,21 @@ typedef struct {
refcount_t cs_count;
} copy_stateid_t;
+struct nfsd4_referring_call {
+ struct list_head __list;
+
+ u32 rc_sequenceid;
+ u32 rc_slotid;
+};
+
+struct nfsd4_referring_call_list {
+ struct list_head __list;
+
+ struct nfs4_sessionid rcl_sessionid;
+ int __nr_referring_calls;
+ struct list_head rcl_referring_calls;
+};
+
struct nfsd4_callback {
struct nfs4_client *cb_clp;
struct rpc_message cb_msg;
@@ -76,6 +91,9 @@ struct nfsd4_callback {
int cb_seq_status;
int cb_status;
int cb_held_slot;
+
+ int cb_nr_referring_call_list;
+ struct list_head cb_referring_call_list;
};
struct nfsd4_callback_ops {
@@ -260,6 +278,7 @@ struct nfsd4_slot {
u32 sl_seqid;
__be32 sl_status;
struct svc_cred sl_cred;
+ u32 sl_index;
u32 sl_datalen;
u16 sl_opcnt;
u16 sl_generation;
@@ -774,6 +793,10 @@ extern __be32 nfs4_check_open_reclaim(struct nfs4_client *);
extern void nfsd4_probe_callback(struct nfs4_client *clp);
extern void nfsd4_probe_callback_sync(struct nfs4_client *clp);
extern void nfsd4_change_callback(struct nfs4_client *clp, struct nfs4_cb_conn *);
+extern void nfsd41_cb_referring_call(struct nfsd4_callback *cb,
+ struct nfs4_sessionid *sessionid,
+ u32 slotid, u32 seqno);
+extern void nfsd41_cb_destroy_referring_call_list(struct nfsd4_callback *cb);
extern void nfsd4_init_cb(struct nfsd4_callback *cb, struct nfs4_client *clp,
const struct nfsd4_callback_ops *ops, enum nfsd4_cb_op op);
extern bool nfsd4_run_cb(struct nfsd4_callback *cb);
diff --git a/fs/nfsd/trace.h b/fs/nfsd/trace.h
index a7630e9f6577..3c5505ef5e3a 100644
--- a/fs/nfsd/trace.h
+++ b/fs/nfsd/trace.h
@@ -11,6 +11,7 @@
#include <linux/tracepoint.h>
#include <linux/sunrpc/clnt.h>
#include <linux/sunrpc/xprt.h>
+#include <trace/misc/fs.h>
#include <trace/misc/nfs.h>
#include <trace/misc/sunrpc.h>
@@ -18,22 +19,40 @@
#include "nfsfh.h"
#include "xdr4.h"
-#define NFSD_TRACE_PROC_RES_FIELDS \
+#define NFSD_TRACE_PROC_CALL_FIELDS(r) \
+ __field(unsigned int, netns_ino) \
+ __field(u32, xid) \
+ __sockaddr(server, (r)->rq_xprt->xpt_locallen) \
+ __sockaddr(client, (r)->rq_xprt->xpt_remotelen)
+
+#define NFSD_TRACE_PROC_CALL_ASSIGNMENTS(r) \
+ do { \
+ struct svc_xprt *xprt = (r)->rq_xprt; \
+ __entry->netns_ino = SVC_NET(r)->ns.inum; \
+ __entry->xid = be32_to_cpu((r)->rq_xid); \
+ __assign_sockaddr(server, &xprt->xpt_local, \
+ xprt->xpt_locallen); \
+ __assign_sockaddr(client, &xprt->xpt_remote, \
+ xprt->xpt_remotelen); \
+ } while (0)
+
+#define NFSD_TRACE_PROC_RES_FIELDS(r) \
__field(unsigned int, netns_ino) \
__field(u32, xid) \
__field(unsigned long, status) \
- __array(unsigned char, server, sizeof(struct sockaddr_in6)) \
- __array(unsigned char, client, sizeof(struct sockaddr_in6))
+ __sockaddr(server, (r)->rq_xprt->xpt_locallen) \
+ __sockaddr(client, (r)->rq_xprt->xpt_remotelen)
-#define NFSD_TRACE_PROC_RES_ASSIGNMENTS(error) \
+#define NFSD_TRACE_PROC_RES_ASSIGNMENTS(r, error) \
do { \
- __entry->netns_ino = SVC_NET(rqstp)->ns.inum; \
- __entry->xid = be32_to_cpu(rqstp->rq_xid); \
+ struct svc_xprt *xprt = (r)->rq_xprt; \
+ __entry->netns_ino = SVC_NET(r)->ns.inum; \
+ __entry->xid = be32_to_cpu((r)->rq_xid); \
__entry->status = be32_to_cpu(error); \
- memcpy(__entry->server, &rqstp->rq_xprt->xpt_local, \
- rqstp->rq_xprt->xpt_locallen); \
- memcpy(__entry->client, &rqstp->rq_xprt->xpt_remote, \
- rqstp->rq_xprt->xpt_remotelen); \
+ __assign_sockaddr(server, &xprt->xpt_local, \
+ xprt->xpt_locallen); \
+ __assign_sockaddr(client, &xprt->xpt_remote, \
+ xprt->xpt_remotelen); \
} while (0);
DECLARE_EVENT_CLASS(nfsd_xdr_err_class,
@@ -145,14 +164,14 @@ TRACE_EVENT(nfsd_compound_decode_err,
),
TP_ARGS(rqstp, args_opcnt, resp_opcnt, opnum, status),
TP_STRUCT__entry(
- NFSD_TRACE_PROC_RES_FIELDS
+ NFSD_TRACE_PROC_RES_FIELDS(rqstp)
__field(u32, args_opcnt)
__field(u32, resp_opcnt)
__field(u32, opnum)
),
TP_fast_assign(
- NFSD_TRACE_PROC_RES_ASSIGNMENTS(status)
+ NFSD_TRACE_PROC_RES_ASSIGNMENTS(rqstp, status)
__entry->args_opcnt = args_opcnt;
__entry->resp_opcnt = resp_opcnt;
@@ -171,12 +190,12 @@ DECLARE_EVENT_CLASS(nfsd_compound_err_class,
),
TP_ARGS(rqstp, opnum, status),
TP_STRUCT__entry(
- NFSD_TRACE_PROC_RES_FIELDS
+ NFSD_TRACE_PROC_RES_FIELDS(rqstp)
__field(u32, opnum)
),
TP_fast_assign(
- NFSD_TRACE_PROC_RES_ASSIGNMENTS(status)
+ NFSD_TRACE_PROC_RES_ASSIGNMENTS(rqstp, status)
__entry->opnum = opnum;
),
@@ -451,6 +470,8 @@ DEFINE_NFSD_IO_EVENT(write_start);
DEFINE_NFSD_IO_EVENT(write_opened);
DEFINE_NFSD_IO_EVENT(write_io_done);
DEFINE_NFSD_IO_EVENT(write_done);
+DEFINE_NFSD_IO_EVENT(commit_start);
+DEFINE_NFSD_IO_EVENT(commit_done);
DECLARE_EVENT_CLASS(nfsd_err_class,
TP_PROTO(struct svc_rqst *rqstp,
@@ -2335,6 +2356,259 @@ DEFINE_EVENT(nfsd_copy_async_done_class, \
DEFINE_COPY_ASYNC_DONE_EVENT(done);
DEFINE_COPY_ASYNC_DONE_EVENT(cancel);
+TRACE_EVENT(nfsd_vfs_setattr,
+ TP_PROTO(
+ const struct svc_rqst *rqstp,
+ const struct svc_fh *fhp,
+ const struct iattr *iap,
+ const struct timespec64 *guardtime
+ ),
+ TP_ARGS(rqstp, fhp, iap, guardtime),
+ TP_STRUCT__entry(
+ NFSD_TRACE_PROC_CALL_FIELDS(rqstp)
+ __field(u32, fh_hash)
+ __field(s64, gtime_tv_sec)
+ __field(u32, gtime_tv_nsec)
+ __field(unsigned int, ia_valid)
+ __field(loff_t, ia_size)
+ __field(uid_t, ia_uid)
+ __field(gid_t, ia_gid)
+ __field(umode_t, ia_mode)
+ ),
+ TP_fast_assign(
+ NFSD_TRACE_PROC_CALL_ASSIGNMENTS(rqstp);
+ __entry->fh_hash = knfsd_fh_hash(&fhp->fh_handle);
+ __entry->gtime_tv_sec = guardtime ? guardtime->tv_sec : 0;
+ __entry->gtime_tv_nsec = guardtime ? guardtime->tv_nsec : 0;
+ __entry->ia_valid = iap->ia_valid;
+ __entry->ia_size = iap->ia_size;
+ __entry->ia_uid = __kuid_val(iap->ia_uid);
+ __entry->ia_gid = __kgid_val(iap->ia_gid);
+ __entry->ia_mode = iap->ia_mode;
+ ),
+ TP_printk(
+ "xid=0x%08x fh_hash=0x%08x ia_valid=%s ia_size=%llu ia_mode=0%o ia_uid=%u ia_gid=%u guard_time=%lld.%u",
+ __entry->xid, __entry->fh_hash, show_ia_valid_flags(__entry->ia_valid),
+ __entry->ia_size, __entry->ia_mode, __entry->ia_uid, __entry->ia_gid,
+ __entry->gtime_tv_sec, __entry->gtime_tv_nsec
+ )
+)
+
+TRACE_EVENT(nfsd_vfs_lookup,
+ TP_PROTO(
+ const struct svc_rqst *rqstp,
+ const struct svc_fh *fhp,
+ const char *name,
+ unsigned int len
+ ),
+ TP_ARGS(rqstp, fhp, name, len),
+ TP_STRUCT__entry(
+ NFSD_TRACE_PROC_CALL_FIELDS(rqstp)
+ __field(u32, fh_hash)
+ __string_len(name, name, len)
+ ),
+ TP_fast_assign(
+ NFSD_TRACE_PROC_CALL_ASSIGNMENTS(rqstp);
+ __entry->fh_hash = knfsd_fh_hash(&fhp->fh_handle);
+ __assign_str(name);
+ ),
+ TP_printk("xid=0x%08x fh_hash=0x%08x name=%s",
+ __entry->xid, __entry->fh_hash, __get_str(name)
+ )
+);
+
+TRACE_EVENT(nfsd_vfs_create,
+ TP_PROTO(
+ const struct svc_rqst *rqstp,
+ const struct svc_fh *fhp,
+ umode_t type,
+ const char *name,
+ unsigned int len
+ ),
+ TP_ARGS(rqstp, fhp, type, name, len),
+ TP_STRUCT__entry(
+ NFSD_TRACE_PROC_CALL_FIELDS(rqstp)
+ __field(u32, fh_hash)
+ __field(umode_t, type)
+ __string_len(name, name, len)
+ ),
+ TP_fast_assign(
+ NFSD_TRACE_PROC_CALL_ASSIGNMENTS(rqstp);
+ __entry->fh_hash = knfsd_fh_hash(&fhp->fh_handle);
+ __entry->type = type;
+ __assign_str(name);
+ ),
+ TP_printk("xid=0x%08x fh_hash=0x%08x type=%s name=%s",
+ __entry->xid, __entry->fh_hash,
+ show_fs_file_type(__entry->type), __get_str(name)
+ )
+);
+
+TRACE_EVENT(nfsd_vfs_symlink,
+ TP_PROTO(
+ const struct svc_rqst *rqstp,
+ const struct svc_fh *fhp,
+ const char *name,
+ unsigned int namelen,
+ const char *target
+ ),
+ TP_ARGS(rqstp, fhp, name, namelen, target),
+ TP_STRUCT__entry(
+ NFSD_TRACE_PROC_CALL_FIELDS(rqstp)
+ __field(u32, fh_hash)
+ __string_len(name, name, namelen)
+ __string(target, target)
+ ),
+ TP_fast_assign(
+ NFSD_TRACE_PROC_CALL_ASSIGNMENTS(rqstp);
+ __entry->fh_hash = knfsd_fh_hash(&fhp->fh_handle);
+ __assign_str(name);
+ __assign_str(target);
+ ),
+ TP_printk("xid=0x%08x fh_hash=0x%08x name=%s target=%s",
+ __entry->xid, __entry->fh_hash,
+ __get_str(name), __get_str(target)
+ )
+);
+
+TRACE_EVENT(nfsd_vfs_link,
+ TP_PROTO(
+ const struct svc_rqst *rqstp,
+ const struct svc_fh *sfhp,
+ const struct svc_fh *tfhp,
+ const char *name,
+ unsigned int namelen
+ ),
+ TP_ARGS(rqstp, sfhp, tfhp, name, namelen),
+ TP_STRUCT__entry(
+ NFSD_TRACE_PROC_CALL_FIELDS(rqstp)
+ __field(u32, sfh_hash)
+ __field(u32, tfh_hash)
+ __string_len(name, name, namelen)
+ ),
+ TP_fast_assign(
+ NFSD_TRACE_PROC_CALL_ASSIGNMENTS(rqstp);
+ __entry->sfh_hash = knfsd_fh_hash(&sfhp->fh_handle);
+ __entry->tfh_hash = knfsd_fh_hash(&tfhp->fh_handle);
+ __assign_str(name);
+ ),
+ TP_printk("xid=0x%08x src_fh=0x%08x tgt_fh=0x%08x name=%s",
+ __entry->xid, __entry->sfh_hash, __entry->tfh_hash,
+ __get_str(name)
+ )
+);
+
+TRACE_EVENT(nfsd_vfs_unlink,
+ TP_PROTO(
+ const struct svc_rqst *rqstp,
+ const struct svc_fh *fhp,
+ const char *name,
+ unsigned int len
+ ),
+ TP_ARGS(rqstp, fhp, name, len),
+ TP_STRUCT__entry(
+ NFSD_TRACE_PROC_CALL_FIELDS(rqstp)
+ __field(u32, fh_hash)
+ __string_len(name, name, len)
+ ),
+ TP_fast_assign(
+ NFSD_TRACE_PROC_CALL_ASSIGNMENTS(rqstp);
+ __entry->fh_hash = knfsd_fh_hash(&fhp->fh_handle);
+ __assign_str(name);
+ ),
+ TP_printk("xid=0x%08x fh_hash=0x%08x name=%s",
+ __entry->xid, __entry->fh_hash,
+ __get_str(name)
+ )
+);
+
+TRACE_EVENT(nfsd_vfs_rename,
+ TP_PROTO(
+ const struct svc_rqst *rqstp,
+ const struct svc_fh *sfhp,
+ const struct svc_fh *tfhp,
+ const char *source,
+ unsigned int sourcelen,
+ const char *target,
+ unsigned int targetlen
+ ),
+ TP_ARGS(rqstp, sfhp, tfhp, source, sourcelen, target, targetlen),
+ TP_STRUCT__entry(
+ NFSD_TRACE_PROC_CALL_FIELDS(rqstp)
+ __field(u32, sfh_hash)
+ __field(u32, tfh_hash)
+ __string_len(source, source, sourcelen)
+ __string_len(target, target, targetlen)
+ ),
+ TP_fast_assign(
+ NFSD_TRACE_PROC_CALL_ASSIGNMENTS(rqstp);
+ __entry->sfh_hash = knfsd_fh_hash(&sfhp->fh_handle);
+ __entry->tfh_hash = knfsd_fh_hash(&tfhp->fh_handle);
+ __assign_str(source);
+ __assign_str(target);
+ ),
+ TP_printk("xid=0x%08x sfh_hash=0x%08x tfh_hash=0x%08x source=%s target=%s",
+ __entry->xid, __entry->sfh_hash, __entry->tfh_hash,
+ __get_str(source), __get_str(target)
+ )
+);
+
+TRACE_EVENT(nfsd_vfs_readdir,
+ TP_PROTO(
+ const struct svc_rqst *rqstp,
+ const struct svc_fh *fhp,
+ u32 count,
+ u64 offset
+ ),
+ TP_ARGS(rqstp, fhp, count, offset),
+ TP_STRUCT__entry(
+ NFSD_TRACE_PROC_CALL_FIELDS(rqstp)
+ __field(u32, fh_hash)
+ __field(u32, count)
+ __field(u64, offset)
+ ),
+ TP_fast_assign(
+ NFSD_TRACE_PROC_CALL_ASSIGNMENTS(rqstp);
+ __entry->fh_hash = knfsd_fh_hash(&fhp->fh_handle);
+ __entry->count = count;
+ __entry->offset = offset;
+ ),
+ TP_printk("xid=0x%08x fh_hash=0x%08x offset=%llu count=%u",
+ __entry->xid, __entry->fh_hash,
+ __entry->offset, __entry->count
+ )
+);
+
+DECLARE_EVENT_CLASS(nfsd_vfs_getattr_class,
+ TP_PROTO(
+ const struct svc_rqst *rqstp,
+ const struct svc_fh *fhp
+ ),
+ TP_ARGS(rqstp, fhp),
+ TP_STRUCT__entry(
+ NFSD_TRACE_PROC_CALL_FIELDS(rqstp)
+ __field(u32, fh_hash)
+ ),
+ TP_fast_assign(
+ NFSD_TRACE_PROC_CALL_ASSIGNMENTS(rqstp);
+ __entry->fh_hash = knfsd_fh_hash(&fhp->fh_handle);
+ ),
+ TP_printk("xid=0x%08x fh_hash=0x%08x",
+ __entry->xid, __entry->fh_hash
+ )
+);
+
+#define DEFINE_NFSD_VFS_GETATTR_EVENT(__name) \
+DEFINE_EVENT(nfsd_vfs_getattr_class, __name, \
+ TP_PROTO( \
+ const struct svc_rqst *rqstp, \
+ const struct svc_fh *fhp \
+ ), \
+ TP_ARGS(rqstp, fhp))
+
+DEFINE_NFSD_VFS_GETATTR_EVENT(nfsd_vfs_getattr);
+DEFINE_NFSD_VFS_GETATTR_EVENT(nfsd_vfs_statfs);
+
#endif /* _NFSD_TRACE_H */
#undef TRACE_INCLUDE_PATH
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 160a839af405..cd689df2ca5d 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -31,6 +31,7 @@
#include <linux/exportfs.h>
#include <linux/writeback.h>
#include <linux/security.h>
+#include <linux/sunrpc/xdr.h>
#include "xdr3.h"
@@ -47,6 +48,8 @@
#define NFSDDBG_FACILITY NFSDDBG_FILEOP
+bool nfsd_disable_splice_read __read_mostly;
+
/**
* nfserrno - Map Linux errnos to NFS errnos
* @errno: POSIX(-ish) error code to be mapped
@@ -244,7 +247,7 @@ nfsd_lookup_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp,
struct dentry *dentry;
int host_err;
- dprintk("nfsd: nfsd_lookup(fh %s, %.*s)\n", SVCFH_fmt(fhp), len,name);
+ trace_nfsd_vfs_lookup(rqstp, fhp, name, len);
dparent = fhp->fh_dentry;
exp = exp_get(fhp->fh_export);
@@ -500,6 +503,8 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp,
bool size_change = (iap->ia_valid & ATTR_SIZE);
int retries;
+ trace_nfsd_vfs_setattr(rqstp, fhp, iap, guardtime);
+
if (iap->ia_valid & ATTR_SIZE) {
accmode |= NFSD_MAY_WRITE|NFSD_MAY_OWNER_OVERRIDE;
ftype = S_IFREG;
@@ -1082,23 +1087,23 @@ __be32 nfsd_iter_read(struct svc_rqst *rqstp, struct svc_fh *fhp,
unsigned long v, total;
struct iov_iter iter;
loff_t ppos = offset;
- struct page *page;
ssize_t host_err;
+ size_t len;
v = 0;
total = *count;
while (total) {
- page = *(rqstp->rq_next_page++);
- rqstp->rq_vec[v].iov_base = page_address(page) + base;
- rqstp->rq_vec[v].iov_len = min_t(size_t, total, PAGE_SIZE - base);
- total -= rqstp->rq_vec[v].iov_len;
+ len = min_t(size_t, total, PAGE_SIZE - base);
+ bvec_set_page(&rqstp->rq_bvec[v], *(rqstp->rq_next_page++),
+ len, base);
+ total -= len;
++v;
base = 0;
}
- WARN_ON_ONCE(v > ARRAY_SIZE(rqstp->rq_vec));
+ WARN_ON_ONCE(v > rqstp->rq_maxpages);
trace_nfsd_read_vector(rqstp, fhp, offset, *count);
- iov_iter_kvec(&iter, ITER_DEST, rqstp->rq_vec, v, *count);
+ iov_iter_bvec(&iter, ITER_DEST, rqstp->rq_bvec, v, *count);
host_err = vfs_iter_read(file, &iter, &ppos, 0);
return nfsd_finish_read(rqstp, fhp, file, offset, count, eof, host_err);
}
@@ -1140,11 +1145,27 @@ static int wait_for_concurrent_writes(struct file *file)
return err;
}
+/**
+ * nfsd_vfs_write - write data to an already-open file
+ * @rqstp: RPC execution context
+ * @fhp: File handle of file to write into
+ * @nf: An open file matching @fhp
+ * @offset: Byte offset of start
+ * @payload: xdr_buf containing the write payload
+ * @cnt: IN: number of bytes to write, OUT: number of bytes actually written
+ * @stable: An NFS stable_how value
+ * @verf: NFS WRITE verifier
+ *
+ * Upon return, caller must invoke fh_put on @fhp.
+ *
+ * Return values:
+ * An nfsstat value in network byte order.
+ */
__be32
-nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct nfsd_file *nf,
- loff_t offset, struct kvec *vec, int vlen,
- unsigned long *cnt, int stable,
- __be32 *verf)
+nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp,
+ struct nfsd_file *nf, loff_t offset,
+ const struct xdr_buf *payload, unsigned long *cnt,
+ int stable, __be32 *verf)
{
struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
struct file *file = nf->nf_file;
@@ -1159,6 +1180,7 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct nfsd_file *nf,
unsigned int pflags = current->flags;
rwf_t flags = 0;
bool restore_flags = false;
+ unsigned int nvecs;
trace_nfsd_write_opened(rqstp, fhp, offset, *cnt);
@@ -1186,7 +1208,8 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct nfsd_file *nf,
if (stable && !fhp->fh_use_wgather)
flags |= RWF_SYNC;
- iov_iter_kvec(&iter, ITER_SOURCE, vec, vlen, *cnt);
+ nvecs = xdr_buf_to_bvec(rqstp->rq_bvec, rqstp->rq_maxpages, payload);
+ iov_iter_bvec(&iter, ITER_SOURCE, rqstp->rq_bvec, nvecs, *cnt);
since = READ_ONCE(file->f_wb_err);
if (verf)
nfsd_copy_write_verifier(verf, nn);
@@ -1237,6 +1260,8 @@ out_nfserr:
*/
bool nfsd_read_splice_ok(struct svc_rqst *rqstp)
{
+ if (nfsd_disable_splice_read)
+ return false;
switch (svc_auth_flavor(rqstp)) {
case RPC_AUTH_GSS_KRB5I:
case RPC_AUTH_GSS_KRB5P:
@@ -1284,14 +1309,24 @@ __be32 nfsd_read(struct svc_rqst *rqstp, struct svc_fh *fhp,
return err;
}
-/*
- * Write data to a file.
- * The stable flag requests synchronous writes.
- * N.B. After this call fhp needs an fh_put
+/**
+ * nfsd_write - open a file and write data to it
+ * @rqstp: RPC execution context
+ * @fhp: File handle of file to write into; nfsd_write() may modify it
+ * @offset: Byte offset of start
+ * @payload: xdr_buf containing the write payload
+ * @cnt: IN: number of bytes to write, OUT: number of bytes actually written
+ * @stable: An NFS stable_how value
+ * @verf: NFS WRITE verifier
+ *
+ * Upon return, caller must invoke fh_put on @fhp.
+ *
+ * Return values:
+ * An nfsstat value in network byte order.
*/
__be32
nfsd_write(struct svc_rqst *rqstp, struct svc_fh *fhp, loff_t offset,
- struct kvec *vec, int vlen, unsigned long *cnt, int stable,
+ const struct xdr_buf *payload, unsigned long *cnt, int stable,
__be32 *verf)
{
struct nfsd_file *nf;
@@ -1303,8 +1338,8 @@ nfsd_write(struct svc_rqst *rqstp, struct svc_fh *fhp, loff_t offset,
if (err)
goto out;
- err = nfsd_vfs_write(rqstp, fhp, nf, offset, vec,
- vlen, cnt, stable, verf);
+ err = nfsd_vfs_write(rqstp, fhp, nf, offset, payload, cnt,
+ stable, verf);
nfsd_file_put(nf);
out:
trace_nfsd_write_done(rqstp, fhp, offset, *cnt);
@@ -1340,6 +1375,8 @@ nfsd_commit(struct svc_rqst *rqstp, struct svc_fh *fhp, struct nfsd_file *nf,
loff_t start, end;
struct nfsd_net *nn;
+ trace_nfsd_commit_start(rqstp, fhp, offset, count);
+
/*
* Convert the client-provided (offset, count) range to a
* (start, end) range. If the client-provided range falls
@@ -1378,6 +1415,7 @@ nfsd_commit(struct svc_rqst *rqstp, struct svc_fh *fhp, struct nfsd_file *nf,
} else
nfsd_copy_write_verifier(verf, nn);
+ trace_nfsd_commit_done(rqstp, fhp, offset, count);
return err;
}
@@ -1541,6 +1579,8 @@ nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
__be32 err;
int host_err;
+ trace_nfsd_vfs_create(rqstp, fhp, type, fname, flen);
+
if (isdotent(fname, flen))
return nfserr_exist;
@@ -1641,6 +1681,8 @@ nfsd_symlink(struct svc_rqst *rqstp, struct svc_fh *fhp,
__be32 err, cerr;
int host_err;
+ trace_nfsd_vfs_symlink(rqstp, fhp, fname, flen, path);
+
err = nfserr_noent;
if (!flen || path[0] == '\0')
goto out;
@@ -1709,6 +1751,8 @@ nfsd_link(struct svc_rqst *rqstp, struct svc_fh *ffhp,
__be32 err;
int host_err;
+ trace_nfsd_vfs_link(rqstp, ffhp, tfhp, name, len);
+
err = fh_verify(rqstp, ffhp, S_IFDIR, NFSD_MAY_CREATE);
if (err)
goto out;
@@ -1826,6 +1870,8 @@ nfsd_rename(struct svc_rqst *rqstp, struct svc_fh *ffhp, char *fname, int flen,
int host_err;
bool close_cached = false;
+ trace_nfsd_vfs_rename(rqstp, ffhp, tfhp, fname, flen, tname, tlen);
+
err = fh_verify(rqstp, ffhp, S_IFDIR, NFSD_MAY_REMOVE);
if (err)
goto out;
@@ -1984,6 +2030,8 @@ nfsd_unlink(struct svc_rqst *rqstp, struct svc_fh *fhp, int type,
__be32 err;
int host_err;
+ trace_nfsd_vfs_unlink(rqstp, fhp, fname, flen);
+
err = nfserr_acces;
if (!flen || isdotent(fname, flen))
goto out;
@@ -2272,6 +2320,8 @@ nfsd_statfs(struct svc_rqst *rqstp, struct svc_fh *fhp, struct kstatfs *stat, in
{
__be32 err;
+ trace_nfsd_vfs_statfs(rqstp, fhp);
+
err = fh_verify(rqstp, fhp, 0, NFSD_MAY_NOP | access);
if (!err) {
struct path path = {
diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h
index f9b09b842856..eff04959606f 100644
--- a/fs/nfsd/vfs.h
+++ b/fs/nfsd/vfs.h
@@ -128,13 +128,13 @@ bool nfsd_read_splice_ok(struct svc_rqst *rqstp);
__be32 nfsd_read(struct svc_rqst *rqstp, struct svc_fh *fhp,
loff_t offset, unsigned long *count,
u32 *eof);
-__be32 nfsd_write(struct svc_rqst *, struct svc_fh *, loff_t,
- struct kvec *, int, unsigned long *,
- int stable, __be32 *verf);
+__be32 nfsd_write(struct svc_rqst *rqstp, struct svc_fh *fhp,
+ loff_t offset, const struct xdr_buf *payload,
+ unsigned long *cnt, int stable, __be32 *verf);
__be32 nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp,
struct nfsd_file *nf, loff_t offset,
- struct kvec *vec, int vlen, unsigned long *cnt,
- int stable, __be32 *verf);
+ const struct xdr_buf *payload,
+ unsigned long *cnt, int stable, __be32 *verf);
__be32 nfsd_readlink(struct svc_rqst *, struct svc_fh *,
char *, int *);
__be32 nfsd_symlink(struct svc_rqst *, struct svc_fh *,
diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h
index c26ba86dbdfd..aa2a356da784 100644
--- a/fs/nfsd/xdr4.h
+++ b/fs/nfsd/xdr4.h
@@ -676,6 +676,10 @@ struct nfsd4_cb_offload {
__be32 co_nfserr;
unsigned int co_retries;
struct knfsd_fh co_fh;
+
+ struct nfs4_sessionid co_referring_sessionid;
+ u32 co_referring_slotid;
+ u32 co_referring_seqno;
};
struct nfsd4_copy {
diff --git a/fs/nfsd/xdr4cb.h b/fs/nfsd/xdr4cb.h
index f1a315cd31b7..f4e29c0c701c 100644
--- a/fs/nfsd/xdr4cb.h
+++ b/fs/nfsd/xdr4cb.h
@@ -6,8 +6,11 @@
#define cb_compound_enc_hdr_sz 4
#define cb_compound_dec_hdr_sz (3 + (NFS4_MAXTAGLEN >> 2))
#define sessionid_sz (NFS4_MAX_SESSIONID_LEN >> 2)
+#define enc_referring_call4_sz (1 + 1)
+#define enc_referring_call_list4_sz (sessionid_sz + 1 + \
+ enc_referring_call4_sz)
#define cb_sequence_enc_sz (sessionid_sz + 4 + \
- 1 /* no referring calls list yet */)
+ enc_referring_call_list4_sz)
#define cb_sequence_dec_sz (op_dec_sz + sessionid_sz + 4)
#define op_enc_sz 1
diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index 74658cca0f38..48666b83fe68 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -119,14 +119,14 @@ void svc_destroy(struct svc_serv **svcp);
* Linux limit; someone who cares more about NFS/UDP performance
* can test a larger number.
*
- * For TCP transports we have more freedom. A size of 1MB is
- * chosen to match the client limit. Other OSes are known to
- * have larger limits, but those numbers are probably beyond
- * the point of diminishing returns.
+ * For non-UDP transports we have more freedom. A size of 4MB is
+ * chosen to accommodate clients that support larger I/O sizes.
*/
-#define RPCSVC_MAXPAYLOAD (1*1024*1024u)
-#define RPCSVC_MAXPAYLOAD_TCP RPCSVC_MAXPAYLOAD
-#define RPCSVC_MAXPAYLOAD_UDP (32*1024u)
+enum {
+ RPCSVC_MAXPAYLOAD = 4 * 1024 * 1024,
+ RPCSVC_MAXPAYLOAD_TCP = RPCSVC_MAXPAYLOAD,
+ RPCSVC_MAXPAYLOAD_UDP = 32 * 1024,
+};
extern u32 svc_max_payload(const struct svc_rqst *rqstp);
@@ -150,14 +150,24 @@ extern u32 svc_max_payload(const struct svc_rqst *rqstp);
* list. xdr_buf.tail points to the end of the first page.
* This assumes that the non-page part of an rpc reply will fit
* in a page - NFSd ensures this. lockd also has no trouble.
+ */
+
+/**
+ * svc_serv_maxpages - maximum count of pages needed for one RPC message
+ * @serv: RPC service context
+ *
+ * Returns a count of pages or vectors that can hold the maximum
+ * size RPC message for @serv.
*
- * Each request/reply pair can have at most one "payload", plus two pages,
- * one for the request, and one for the reply.
- * We using ->sendfile to return read data, we might need one extra page
- * if the request is not page-aligned. So add another '1'.
+ * Each request/reply pair can have at most one "payload", plus two
+ * pages, one for the request, and one for the reply.
+ * nfsd_splice_actor() might need an extra page when a READ payload
+ * is not page-aligned.
*/
-#define RPCSVC_MAXPAGES ((RPCSVC_MAXPAYLOAD+PAGE_SIZE-1)/PAGE_SIZE \
- + 2 + 1)
+static inline unsigned long svc_serv_maxpages(const struct svc_serv *serv)
+{
+ return DIV_ROUND_UP(serv->sv_max_mesg, PAGE_SIZE) + 2 + 1;
+}
/*
* The context of a single thread, including the request currently being
@@ -188,14 +198,14 @@ struct svc_rqst {
struct xdr_stream rq_res_stream;
struct page *rq_scratch_page;
struct xdr_buf rq_res;
- struct page *rq_pages[RPCSVC_MAXPAGES + 1];
+ unsigned long rq_maxpages; /* num of entries in rq_pages */
+ struct page * *rq_pages;
struct page * *rq_respages; /* points into rq_pages */
struct page * *rq_next_page; /* next reply page to use */
struct page * *rq_page_end; /* one past the last page */
struct folio_batch rq_fbatch;
- struct kvec rq_vec[RPCSVC_MAXPAGES]; /* generally useful.. */
- struct bio_vec rq_bvec[RPCSVC_MAXPAGES];
+ struct bio_vec *rq_bvec;
__be32 rq_xid; /* transmission id */
u32 rq_prog; /* program number */
@@ -452,8 +462,6 @@ const char * svc_proc_name(const struct svc_rqst *rqstp);
int svc_encode_result_payload(struct svc_rqst *rqstp,
unsigned int offset,
unsigned int length);
-unsigned int svc_fill_write_vector(struct svc_rqst *rqstp,
- struct xdr_buf *payload);
char *svc_fill_symlink_pathname(struct svc_rqst *rqstp,
struct kvec *first, void *p,
size_t total);
diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h
index 619fc0bd837a..22704c2e5b9b 100644
--- a/include/linux/sunrpc/svc_rdma.h
+++ b/include/linux/sunrpc/svc_rdma.h
@@ -202,7 +202,8 @@ struct svc_rdma_recv_ctxt {
struct svc_rdma_pcl rc_reply_pcl;
unsigned int rc_page_count;
- struct page *rc_pages[RPCSVC_MAXPAGES];
+ unsigned long rc_maxpages;
+ struct page *rc_pages[] __counted_by(rc_maxpages);
};
/*
@@ -244,7 +245,8 @@ struct svc_rdma_send_ctxt {
void *sc_xprt_buf;
int sc_page_count;
int sc_cur_sge_no;
- struct page *sc_pages[RPCSVC_MAXPAGES];
+ unsigned long sc_maxpages;
+ struct page **sc_pages;
struct ib_sge sc_sges[];
};
diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h
index 72be60952579..369a89aea186 100644
--- a/include/linux/sunrpc/svc_xprt.h
+++ b/include/linux/sunrpc/svc_xprt.h
@@ -53,6 +53,7 @@ struct svc_xprt {
struct svc_xprt_class *xpt_class;
const struct svc_xprt_ops *xpt_ops;
struct kref xpt_ref;
+ ktime_t xpt_qtime;
struct list_head xpt_list;
struct lwq_node xpt_ready;
unsigned long xpt_flags;
diff --git a/include/linux/sunrpc/svcsock.h b/include/linux/sunrpc/svcsock.h
index bf45d9e8492a..963bbe251e52 100644
--- a/include/linux/sunrpc/svcsock.h
+++ b/include/linux/sunrpc/svcsock.h
@@ -40,7 +40,9 @@ struct svc_sock {
struct completion sk_handshake_done;
- struct page * sk_pages[RPCSVC_MAXPAGES]; /* received data */
+ /* received data */
+ unsigned long sk_maxpages;
+ struct page * sk_pages[] __counted_by(sk_maxpages);
};
static inline u32 svc_sock_reclen(struct svc_sock *svsk)
diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h
index 5d331383047b..67db3f2953d5 100644
--- a/include/trace/events/sunrpc.h
+++ b/include/trace/events/sunrpc.h
@@ -2040,19 +2040,20 @@ TRACE_EVENT(svc_xprt_dequeue,
TP_STRUCT__entry(
SVC_XPRT_ENDPOINT_FIELDS(rqst->rq_xprt)
-
__field(unsigned long, wakeup)
+ __field(unsigned long, qtime)
),
TP_fast_assign(
- SVC_XPRT_ENDPOINT_ASSIGNMENTS(rqst->rq_xprt);
+ ktime_t ktime = ktime_get();
- __entry->wakeup = ktime_to_us(ktime_sub(ktime_get(),
- rqst->rq_qtime));
+ SVC_XPRT_ENDPOINT_ASSIGNMENTS(rqst->rq_xprt);
+ __entry->wakeup = ktime_to_us(ktime_sub(ktime, rqst->rq_qtime));
+ __entry->qtime = ktime_to_us(ktime_sub(ktime, rqst->rq_xprt->xpt_qtime));
),
- TP_printk(SVC_XPRT_ENDPOINT_FORMAT " wakeup-us=%lu",
- SVC_XPRT_ENDPOINT_VARARGS, __entry->wakeup)
+ TP_printk(SVC_XPRT_ENDPOINT_FORMAT " wakeup-us=%lu qtime-us=%lu",
+ SVC_XPRT_ENDPOINT_VARARGS, __entry->wakeup, __entry->qtime)
);
DECLARE_EVENT_CLASS(svc_xprt_event,
diff --git a/include/trace/misc/fs.h b/include/trace/misc/fs.h
index 738b97f22f36..0406ebe2a80a 100644
--- a/include/trace/misc/fs.h
+++ b/include/trace/misc/fs.h
@@ -120,3 +120,24 @@
{ LOOKUP_BENEATH, "BENEATH" }, \
{ LOOKUP_IN_ROOT, "IN_ROOT" }, \
{ LOOKUP_CACHED, "CACHED" })
+
+#define show_ia_valid_flags(flags) \
+ __print_flags(flags, "|", \
+ { ATTR_MODE, "MODE" }, \
+ { ATTR_UID, "UID" }, \
+ { ATTR_GID, "GID" }, \
+ { ATTR_SIZE, "SIZE" }, \
+ { ATTR_ATIME, "ATIME" }, \
+ { ATTR_MTIME, "MTIME" }, \
+ { ATTR_CTIME, "CTIME" }, \
+ { ATTR_ATIME_SET, "ATIME_SET" }, \
+ { ATTR_MTIME_SET, "MTIME_SET" }, \
+ { ATTR_FORCE, "FORCE" }, \
+ { ATTR_KILL_SUID, "KILL_SUID" }, \
+ { ATTR_KILL_SGID, "KILL_SGID" }, \
+ { ATTR_FILE, "FILE" }, \
+ { ATTR_KILL_PRIV, "KILL_PRIV" }, \
+ { ATTR_OPEN, "OPEN" }, \
+ { ATTR_TIMES_SET, "TIMES_SET" }, \
+ { ATTR_TOUCH, "TOUCH"}, \
+ { ATTR_DELEG, "DELEG"})
diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c
index 7ce5e28a6c03..131090f31e6a 100644
--- a/net/sunrpc/cache.c
+++ b/net/sunrpc/cache.c
@@ -135,6 +135,8 @@ static struct cache_head *sunrpc_cache_add_entry(struct cache_detail *detail,
hlist_add_head_rcu(&new->cache_list, head);
detail->entries++;
+ if (detail->nextcheck > new->expiry_time)
+ detail->nextcheck = new->expiry_time + 1;
cache_get(new);
spin_unlock(&detail->hash_lock);
@@ -462,24 +464,21 @@ static int cache_clean(void)
}
}
+ spin_lock(&current_detail->hash_lock);
+
/* find a non-empty bucket in the table */
- while (current_detail &&
- current_index < current_detail->hash_size &&
+ while (current_index < current_detail->hash_size &&
hlist_empty(&current_detail->hash_table[current_index]))
current_index++;
/* find a cleanable entry in the bucket and clean it, or set to next bucket */
-
- if (current_detail && current_index < current_detail->hash_size) {
+ if (current_index < current_detail->hash_size) {
struct cache_head *ch = NULL;
struct cache_detail *d;
struct hlist_head *head;
struct hlist_node *tmp;
- spin_lock(&current_detail->hash_lock);
-
/* Ok, now to clean this strand */
-
head = &current_detail->hash_table[current_index];
hlist_for_each_entry_safe(ch, tmp, head, cache_list) {
if (current_detail->nextcheck > ch->expiry_time)
@@ -500,8 +499,10 @@ static int cache_clean(void)
spin_unlock(&cache_list_lock);
if (ch)
sunrpc_end_cache_remove_entry(ch, d);
- } else
+ } else {
+ spin_unlock(&current_detail->hash_lock);
spin_unlock(&cache_list_lock);
+ }
return rv;
}
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index e7f9c295d13c..939b6239df8a 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -636,24 +636,22 @@ svc_destroy(struct svc_serv **servp)
EXPORT_SYMBOL_GPL(svc_destroy);
static bool
-svc_init_buffer(struct svc_rqst *rqstp, unsigned int size, int node)
+svc_init_buffer(struct svc_rqst *rqstp, const struct svc_serv *serv, int node)
{
- unsigned long pages, ret;
+ unsigned long ret;
- /* bc_xprt uses fore channel allocated buffers */
- if (svc_is_backchannel(rqstp))
- return true;
+ rqstp->rq_maxpages = svc_serv_maxpages(serv);
- pages = size / PAGE_SIZE + 1; /* extra page as we hold both request and reply.
- * We assume one is at most one page
- */
- WARN_ON_ONCE(pages > RPCSVC_MAXPAGES);
- if (pages > RPCSVC_MAXPAGES)
- pages = RPCSVC_MAXPAGES;
+ /* rq_pages' last entry is NULL for historical reasons. */
+ rqstp->rq_pages = kcalloc_node(rqstp->rq_maxpages + 1,
+ sizeof(struct page *),
+ GFP_KERNEL, node);
+ if (!rqstp->rq_pages)
+ return false;
- ret = alloc_pages_bulk_node(GFP_KERNEL, node, pages,
+ ret = alloc_pages_bulk_node(GFP_KERNEL, node, rqstp->rq_maxpages,
rqstp->rq_pages);
- return ret == pages;
+ return ret == rqstp->rq_maxpages;
}
/*
@@ -662,17 +660,19 @@ svc_init_buffer(struct svc_rqst *rqstp, unsigned int size, int node)
static void
svc_release_buffer(struct svc_rqst *rqstp)
{
- unsigned int i;
+ unsigned long i;
- for (i = 0; i < ARRAY_SIZE(rqstp->rq_pages); i++)
+ for (i = 0; i < rqstp->rq_maxpages; i++)
if (rqstp->rq_pages[i])
put_page(rqstp->rq_pages[i]);
+ kfree(rqstp->rq_pages);
}
static void
svc_rqst_free(struct svc_rqst *rqstp)
{
folio_batch_release(&rqstp->rq_fbatch);
+ kfree(rqstp->rq_bvec);
svc_release_buffer(rqstp);
if (rqstp->rq_scratch_page)
put_page(rqstp->rq_scratch_page);
@@ -708,7 +708,13 @@ svc_prepare_thread(struct svc_serv *serv, struct svc_pool *pool, int node)
if (!rqstp->rq_resp)
goto out_enomem;
- if (!svc_init_buffer(rqstp, serv->sv_max_mesg, node))
+ if (!svc_init_buffer(rqstp, serv, node))
+ goto out_enomem;
+
+ rqstp->rq_bvec = kcalloc_node(rqstp->rq_maxpages,
+ sizeof(struct bio_vec),
+ GFP_KERNEL, node);
+ if (!rqstp->rq_bvec)
goto out_enomem;
rqstp->rq_err = -EAGAIN; /* No error yet */
@@ -900,7 +906,7 @@ EXPORT_SYMBOL_GPL(svc_set_num_threads);
bool svc_rqst_replace_page(struct svc_rqst *rqstp, struct page *page)
{
struct page **begin = rqstp->rq_pages;
- struct page **end = &rqstp->rq_pages[RPCSVC_MAXPAGES];
+ struct page **end = &rqstp->rq_pages[rqstp->rq_maxpages];
if (unlikely(rqstp->rq_next_page < begin || rqstp->rq_next_page > end)) {
trace_svc_replace_page_err(rqstp);
@@ -1714,46 +1720,6 @@ int svc_encode_result_payload(struct svc_rqst *rqstp, unsigned int offset,
EXPORT_SYMBOL_GPL(svc_encode_result_payload);
/**
- * svc_fill_write_vector - Construct data argument for VFS write call
- * @rqstp: svc_rqst to operate on
- * @payload: xdr_buf containing only the write data payload
- *
- * Fills in rqstp::rq_vec, and returns the number of elements.
- */
-unsigned int svc_fill_write_vector(struct svc_rqst *rqstp,
- struct xdr_buf *payload)
-{
- struct page **pages = payload->pages;
- struct kvec *first = payload->head;
- struct kvec *vec = rqstp->rq_vec;
- size_t total = payload->len;
- unsigned int i;
-
- /* Some types of transport can present the write payload
- * entirely in rq_arg.pages. In this case, @first is empty.
- */
- i = 0;
- if (first->iov_len) {
- vec[i].iov_base = first->iov_base;
- vec[i].iov_len = min_t(size_t, total, first->iov_len);
- total -= vec[i].iov_len;
- ++i;
- }
-
- while (total) {
- vec[i].iov_base = page_address(*pages);
- vec[i].iov_len = min_t(size_t, total, PAGE_SIZE);
- total -= vec[i].iov_len;
- ++i;
- ++pages;
- }
-
- WARN_ON_ONCE(i > ARRAY_SIZE(rqstp->rq_vec));
- return i;
-}
-EXPORT_SYMBOL_GPL(svc_fill_write_vector);
-
-/**
* svc_fill_symlink_pathname - Construct pathname argument for VFS symlink call
* @rqstp: svc_rqst to operate on
* @first: buffer containing first section of pathname
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index ae25405d8bd2..cb14d6ddac6c 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -488,6 +488,7 @@ void svc_xprt_enqueue(struct svc_xprt *xprt)
pool = svc_pool_for_cpu(xprt->xpt_server);
percpu_counter_inc(&pool->sp_sockets_queued);
+ xprt->xpt_qtime = ktime_get();
lwq_enqueue(&xprt->xpt_ready, &pool->sp_xprts);
svc_pool_wake_idle_thread(pool);
@@ -651,18 +652,10 @@ static void svc_check_conn_limits(struct svc_serv *serv)
static bool svc_alloc_arg(struct svc_rqst *rqstp)
{
- struct svc_serv *serv = rqstp->rq_server;
struct xdr_buf *arg = &rqstp->rq_arg;
unsigned long pages, filled, ret;
- pages = (serv->sv_max_mesg + 2 * PAGE_SIZE) >> PAGE_SHIFT;
- if (pages > RPCSVC_MAXPAGES) {
- pr_warn_once("svc: warning: pages=%lu > RPCSVC_MAXPAGES=%lu\n",
- pages, RPCSVC_MAXPAGES);
- /* use as many pages as possible */
- pages = RPCSVC_MAXPAGES;
- }
-
+ pages = rqstp->rq_maxpages;
for (filled = 0; filled < pages; filled = ret) {
ret = alloc_pages_bulk(GFP_KERNEL, pages, rqstp->rq_pages);
if (ret > filled)
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index 72e5a01df3d3..e1c85123b445 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -713,8 +713,7 @@ static int svc_udp_sendto(struct svc_rqst *rqstp)
if (svc_xprt_is_dead(xprt))
goto out_notconn;
- count = xdr_buf_to_bvec(rqstp->rq_bvec,
- ARRAY_SIZE(rqstp->rq_bvec), xdr);
+ count = xdr_buf_to_bvec(rqstp->rq_bvec, rqstp->rq_maxpages, xdr);
iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, rqstp->rq_bvec,
count, rqstp->rq_res.len);
@@ -1219,8 +1218,8 @@ static int svc_tcp_sendmsg(struct svc_sock *svsk, struct svc_rqst *rqstp,
memcpy(buf, &marker, sizeof(marker));
bvec_set_virt(rqstp->rq_bvec, buf, sizeof(marker));
- count = xdr_buf_to_bvec(rqstp->rq_bvec + 1,
- ARRAY_SIZE(rqstp->rq_bvec) - 1, &rqstp->rq_res);
+ count = xdr_buf_to_bvec(rqstp->rq_bvec + 1, rqstp->rq_maxpages,
+ &rqstp->rq_res);
iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, rqstp->rq_bvec,
1 + count, sizeof(marker) + rqstp->rq_res.len);
@@ -1340,7 +1339,8 @@ static void svc_tcp_init(struct svc_sock *svsk, struct svc_serv *serv)
svsk->sk_marker = xdr_zero;
svsk->sk_tcplen = 0;
svsk->sk_datalen = 0;
- memset(&svsk->sk_pages[0], 0, sizeof(svsk->sk_pages));
+ memset(&svsk->sk_pages[0], 0,
+ svsk->sk_maxpages * sizeof(struct page *));
tcp_sock_set_nodelay(sk);
@@ -1379,10 +1379,13 @@ static struct svc_sock *svc_setup_socket(struct svc_serv *serv,
struct svc_sock *svsk;
struct sock *inet;
int pmap_register = !(flags & SVC_SOCK_ANONYMOUS);
+ unsigned long pages;
- svsk = kzalloc(sizeof(*svsk), GFP_KERNEL);
+ pages = svc_serv_maxpages(serv);
+ svsk = kzalloc(struct_size(svsk, sk_pages, pages), GFP_KERNEL);
if (!svsk)
return ERR_PTR(-ENOMEM);
+ svsk->sk_maxpages = pages;
inet = sock->sk;
@@ -1542,7 +1545,7 @@ static struct svc_xprt *svc_create_socket(struct svc_serv *serv,
if (protocol == IPPROTO_TCP) {
sk_net_refcnt_upgrade(sock->sk);
- if ((error = kernel_listen(sock, 64)) < 0)
+ if ((error = kernel_listen(sock, SOMAXCONN)) < 0)
goto bummer;
}
diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c
index 4e003cb516fe..2ea00e354ba6 100644
--- a/net/sunrpc/xdr.c
+++ b/net/sunrpc/xdr.c
@@ -213,6 +213,7 @@ bvec_overflow:
pr_warn_once("%s: bio_vec array overflow\n", __func__);
return count - 1;
}
+EXPORT_SYMBOL_GPL(xdr_buf_to_bvec);
/**
* xdr_inline_pages - Prepare receive buffer for a large reply
diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
index 292022f0976e..e7e4a39ca6c6 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
@@ -120,12 +120,16 @@ svc_rdma_recv_ctxt_alloc(struct svcxprt_rdma *rdma)
{
int node = ibdev_to_node(rdma->sc_cm_id->device);
struct svc_rdma_recv_ctxt *ctxt;
+ unsigned long pages;
dma_addr_t addr;
void *buffer;
- ctxt = kzalloc_node(sizeof(*ctxt), GFP_KERNEL, node);
+ pages = svc_serv_maxpages(rdma->sc_xprt.xpt_server);
+ ctxt = kzalloc_node(struct_size(ctxt, rc_pages, pages),
+ GFP_KERNEL, node);
if (!ctxt)
goto fail0;
+ ctxt->rc_maxpages = pages;
buffer = kmalloc_node(rdma->sc_max_req_size, GFP_KERNEL, node);
if (!buffer)
goto fail1;
@@ -497,7 +501,7 @@ static bool xdr_check_write_chunk(struct svc_rdma_recv_ctxt *rctxt)
* a computation, perform a simple range check. This is an
* arbitrary but sensible limit (ie, not architectural).
*/
- if (unlikely(segcount > RPCSVC_MAXPAGES))
+ if (unlikely(segcount > rctxt->rc_maxpages))
return false;
p = xdr_inline_decode(&rctxt->rc_stream,
diff --git a/net/sunrpc/xprtrdma/svc_rdma_rw.c b/net/sunrpc/xprtrdma/svc_rdma_rw.c
index 40797114d50a..661b3fe2779f 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_rw.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_rw.c
@@ -765,7 +765,7 @@ static int svc_rdma_build_read_segment(struct svc_rqst *rqstp,
}
len -= seg_len;
- if (len && ((head->rc_curpage + 1) > ARRAY_SIZE(rqstp->rq_pages)))
+ if (len && ((head->rc_curpage + 1) > rqstp->rq_maxpages))
goto out_overrun;
}
diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
index 96154a2367a1..914cd263c2f1 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
@@ -118,6 +118,7 @@ svc_rdma_send_ctxt_alloc(struct svcxprt_rdma *rdma)
{
int node = ibdev_to_node(rdma->sc_cm_id->device);
struct svc_rdma_send_ctxt *ctxt;
+ unsigned long pages;
dma_addr_t addr;
void *buffer;
int i;
@@ -126,13 +127,19 @@ svc_rdma_send_ctxt_alloc(struct svcxprt_rdma *rdma)
GFP_KERNEL, node);
if (!ctxt)
goto fail0;
+ pages = svc_serv_maxpages(rdma->sc_xprt.xpt_server);
+ ctxt->sc_pages = kcalloc_node(pages, sizeof(struct page *),
+ GFP_KERNEL, node);
+ if (!ctxt->sc_pages)
+ goto fail1;
+ ctxt->sc_maxpages = pages;
buffer = kmalloc_node(rdma->sc_max_req_size, GFP_KERNEL, node);
if (!buffer)
- goto fail1;
+ goto fail2;
addr = ib_dma_map_single(rdma->sc_pd->device, buffer,
rdma->sc_max_req_size, DMA_TO_DEVICE);
if (ib_dma_mapping_error(rdma->sc_pd->device, addr))
- goto fail2;
+ goto fail3;
svc_rdma_send_cid_init(rdma, &ctxt->sc_cid);
@@ -151,8 +158,10 @@ svc_rdma_send_ctxt_alloc(struct svcxprt_rdma *rdma)
ctxt->sc_sges[i].lkey = rdma->sc_pd->local_dma_lkey;
return ctxt;
-fail2:
+fail3:
kfree(buffer);
+fail2:
+ kfree(ctxt->sc_pages);
fail1:
kfree(ctxt);
fail0:
@@ -176,6 +185,7 @@ void svc_rdma_send_ctxts_destroy(struct svcxprt_rdma *rdma)
rdma->sc_max_req_size,
DMA_TO_DEVICE);
kfree(ctxt->sc_xprt_buf);
+ kfree(ctxt->sc_pages);
kfree(ctxt);
}
}
diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c
index aca8bdf65d72..3d7f1413df02 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_transport.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c
@@ -406,12 +406,12 @@ static void svc_rdma_xprt_done(struct rpcrdma_notification *rn)
*/
static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt)
{
+ unsigned int ctxts, rq_depth, maxpayload;
struct svcxprt_rdma *listen_rdma;
struct svcxprt_rdma *newxprt = NULL;
struct rdma_conn_param conn_param;
struct rpcrdma_connect_private pmsg;
struct ib_qp_init_attr qp_attr;
- unsigned int ctxts, rq_depth;
struct ib_device *dev;
int ret = 0;
RPC_IFDEBUG(struct sockaddr *sap);
@@ -462,12 +462,14 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt)
newxprt->sc_max_bc_requests = 2;
}
- /* Arbitrarily estimate the number of rw_ctxs needed for
- * this transport. This is enough rw_ctxs to make forward
- * progress even if the client is using one rkey per page
- * in each Read chunk.
+ /* Arbitrary estimate of the needed number of rdma_rw contexts.
*/
- ctxts = 3 * RPCSVC_MAXPAGES;
+ maxpayload = min(xprt->xpt_server->sv_max_payload,
+ RPCSVC_MAXPAYLOAD_RDMA);
+ ctxts = newxprt->sc_max_requests * 3 *
+ rdma_rw_mr_factor(dev, newxprt->sc_port_num,
+ maxpayload >> PAGE_SHIFT);
+
newxprt->sc_sq_depth = rq_depth + ctxts;
if (newxprt->sc_sq_depth > dev->attrs.max_qp_wr)
newxprt->sc_sq_depth = dev->attrs.max_qp_wr;
@@ -575,6 +577,7 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt)
if (newxprt->sc_qp && !IS_ERR(newxprt->sc_qp))
ib_destroy_qp(newxprt->sc_qp);
rdma_destroy_id(newxprt->sc_cm_id);
+ rpcrdma_rn_unregister(dev, &newxprt->sc_rn);
/* This call to put will destroy the transport */
svc_xprt_put(&newxprt->sc_xprt);
return NULL;
diff --git a/tools/net/sunrpc/xdrgen/templates/C/pointer/encoder/variable_length_array.j2 b/tools/net/sunrpc/xdrgen/templates/C/pointer/encoder/variable_length_array.j2
index 0ec8660d621a..b21476629679 100644
--- a/tools/net/sunrpc/xdrgen/templates/C/pointer/encoder/variable_length_array.j2
+++ b/tools/net/sunrpc/xdrgen/templates/C/pointer/encoder/variable_length_array.j2
@@ -2,8 +2,10 @@
{% if annotate %}
/* member {{ name }} (variable-length array) */
{% endif %}
+{% if maxsize != "0" %}
if (value->{{ name }}.count > {{ maxsize }})
return false;
+{% endif %}
if (xdr_stream_encode_u32(xdr, value->{{ name }}.count) != XDR_UNIT)
return false;
for (u32 i = 0; i < value->{{ name }}.count; i++)
diff --git a/tools/net/sunrpc/xdrgen/templates/C/struct/encoder/variable_length_array.j2 b/tools/net/sunrpc/xdrgen/templates/C/struct/encoder/variable_length_array.j2
index 0ec8660d621a..b21476629679 100644
--- a/tools/net/sunrpc/xdrgen/templates/C/struct/encoder/variable_length_array.j2
+++ b/tools/net/sunrpc/xdrgen/templates/C/struct/encoder/variable_length_array.j2
@@ -2,8 +2,10 @@
{% if annotate %}
/* member {{ name }} (variable-length array) */
{% endif %}
+{% if maxsize != "0" %}
if (value->{{ name }}.count > {{ maxsize }})
return false;
+{% endif %}
if (xdr_stream_encode_u32(xdr, value->{{ name }}.count) != XDR_UNIT)
return false;
for (u32 i = 0; i < value->{{ name }}.count; i++)
diff --git a/tools/net/sunrpc/xdrgen/templates/C/union/decoder/variable_length_array.j2 b/tools/net/sunrpc/xdrgen/templates/C/union/decoder/variable_length_array.j2
index 51ad736d2530..53dfaf9cec68 100644
--- a/tools/net/sunrpc/xdrgen/templates/C/union/decoder/variable_length_array.j2
+++ b/tools/net/sunrpc/xdrgen/templates/C/union/decoder/variable_length_array.j2
@@ -4,8 +4,10 @@
{% endif %}
if (xdr_stream_decode_u32(xdr, &count) < 0)
return false;
+{% if maxsize != "0" %}
if (count > {{ maxsize }})
return false;
+{% endif %}
for (u32 i = 0; i < count; i++) {
if (xdrgen_decode_{{ type }}(xdr, &ptr->{{ name }}.items[i]) < 0)
return false;