summaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2025-10-06 13:22:21 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2025-10-06 13:22:21 -0700
commit81538c8e42806eed71ce125723877a7c2307370c (patch)
tree71abd849602e6a97e156d17bb5d93f27ba74cbe2 /fs
parent256e3417065b2721f77bcd37331796b59483ef3b (diff)
parent73cc6ec1a89a6c443a77b9b93ddcea63b7cea223 (diff)
downloadlinux-81538c8e42806eed71ce125723877a7c2307370c.tar.gz
linux-81538c8e42806eed71ce125723877a7c2307370c.tar.bz2
linux-81538c8e42806eed71ce125723877a7c2307370c.zip
Merge tag 'nfsd-6.18' of git://git.kernel.org/pub/scm/linux/kernel/git/cel/linux
Pull nfsd updates from Chuck Lever: "Mike Snitzer has prototyped a mechanism for disabling I/O caching in NFSD. This is introduced in v6.18 as an experimental feature. This enables scaling NFSD in /both/ directions: - NFS service can be supported on systems with small memory footprints, such as low-cost cloud instances - Large NFS workloads will be less likely to force the eviction of server-local activity, helping it avoid thrashing Jeff Layton contributed a number of fixes to the new attribute delegation implementation (based on a pending Internet RFC) that we hope will make attribute delegation reliable enough to enable by default, as it is on the Linux NFS client. The remaining patches in this pull request are clean-ups and minor optimizations. Many thanks to the contributors, reviewers, testers, and bug reporters who participated during the v6.18 NFSD development cycle" * tag 'nfsd-6.18' of git://git.kernel.org/pub/scm/linux/kernel/git/cel/linux: (42 commits) nfsd: discard nfserr_dropit SUNRPC: Make RPCSEC_GSS_KRB5 select CRYPTO instead of depending on it NFSD: Add io_cache_{read,write} controls to debugfs NFSD: Do the grace period check in ->proc_layoutget nfsd: delete unnecessary NULL check in __fh_verify() NFSD: Allow layoutcommit during grace period NFSD: Disallow layoutget during grace period sunrpc: fix "occurence"->"occurrence" nfsd: Don't force CRYPTO_LIB_SHA256 to be built-in nfsd: nfserr_jukebox in nlm_fopen should lead to a retry NFSD: Reduce DRC bucket size NFSD: Delay adding new entries to LRU SUNRPC: Move the svc_rpcb_cleanup() call sites NFS: Remove rpcbind cleanup for NFSv4.0 callback nfsd: unregister with rpcbind when deleting a transport NFSD: Drop redundant conversion to bool sunrpc: eliminate return pointer in svc_tcp_sendmsg() sunrpc: fix pr_notice in svc_tcp_sendto() to show correct length nfsd: decouple the xprtsec policy check from check_nfsd_access() NFSD: Fix destination buffer size in nfsd4_ssc_setup_dul() ...
Diffstat (limited to 'fs')
-rw-r--r--fs/attr.c44
-rw-r--r--fs/lockd/svclock.c2
-rw-r--r--fs/nfsd/Kconfig2
-rw-r--r--fs/nfsd/blocklayout.c32
-rw-r--r--fs/nfsd/blocklayoutxdr.c86
-rw-r--r--fs/nfsd/blocklayoutxdr.h4
-rw-r--r--fs/nfsd/debugfs.c95
-rw-r--r--fs/nfsd/export.c82
-rw-r--r--fs/nfsd/export.h3
-rw-r--r--fs/nfsd/filecache.c21
-rw-r--r--fs/nfsd/filecache.h1
-rw-r--r--fs/nfsd/flexfilelayout.c4
-rw-r--r--fs/nfsd/flexfilelayoutxdr.c3
-rw-r--r--fs/nfsd/localio.c1
-rw-r--r--fs/nfsd/lockd.c15
-rw-r--r--fs/nfsd/nfs4layouts.c1
-rw-r--r--fs/nfsd/nfs4proc.c125
-rw-r--r--fs/nfsd/nfs4recover.c31
-rw-r--r--fs/nfsd/nfs4state.c86
-rw-r--r--fs/nfsd/nfs4xdr.c32
-rw-r--r--fs/nfsd/nfscache.c15
-rw-r--r--fs/nfsd/nfsd.h17
-rw-r--r--fs/nfsd/nfsfh.c55
-rw-r--r--fs/nfsd/nfsfh.h38
-rw-r--r--fs/nfsd/pnfs.h5
-rw-r--r--fs/nfsd/state.h16
-rw-r--r--fs/nfsd/vfs.c23
-rw-r--r--fs/nfsd/vfs.h37
-rw-r--r--fs/nfsd/xdr4.h39
29 files changed, 615 insertions, 300 deletions
diff --git a/fs/attr.c b/fs/attr.c
index 5425c1dbbff9..795f231d00e8 100644
--- a/fs/attr.c
+++ b/fs/attr.c
@@ -286,20 +286,12 @@ static void setattr_copy_mgtime(struct inode *inode, const struct iattr *attr)
unsigned int ia_valid = attr->ia_valid;
struct timespec64 now;
- if (ia_valid & ATTR_CTIME) {
- /*
- * In the case of an update for a write delegation, we must respect
- * the value in ia_ctime and not use the current time.
- */
- if (ia_valid & ATTR_DELEG)
- now = inode_set_ctime_deleg(inode, attr->ia_ctime);
- else
- now = inode_set_ctime_current(inode);
- } else {
- /* If ATTR_CTIME isn't set, then ATTR_MTIME shouldn't be either. */
- WARN_ON_ONCE(ia_valid & ATTR_MTIME);
+ if (ia_valid & ATTR_CTIME_SET)
+ now = inode_set_ctime_deleg(inode, attr->ia_ctime);
+ else if (ia_valid & ATTR_CTIME)
+ now = inode_set_ctime_current(inode);
+ else
now = current_time(inode);
- }
if (ia_valid & ATTR_ATIME_SET)
inode_set_atime_to_ts(inode, attr->ia_atime);
@@ -359,12 +351,11 @@ void setattr_copy(struct mnt_idmap *idmap, struct inode *inode,
inode_set_atime_to_ts(inode, attr->ia_atime);
if (ia_valid & ATTR_MTIME)
inode_set_mtime_to_ts(inode, attr->ia_mtime);
- if (ia_valid & ATTR_CTIME) {
- if (ia_valid & ATTR_DELEG)
- inode_set_ctime_deleg(inode, attr->ia_ctime);
- else
- inode_set_ctime_to_ts(inode, attr->ia_ctime);
- }
+
+ if (ia_valid & ATTR_CTIME_SET)
+ inode_set_ctime_deleg(inode, attr->ia_ctime);
+ else if (ia_valid & ATTR_CTIME)
+ inode_set_ctime_to_ts(inode, attr->ia_ctime);
}
EXPORT_SYMBOL(setattr_copy);
@@ -463,15 +454,18 @@ int notify_change(struct mnt_idmap *idmap, struct dentry *dentry,
now = current_time(inode);
- attr->ia_ctime = now;
- if (!(ia_valid & ATTR_ATIME_SET))
- attr->ia_atime = now;
- else
+ if (ia_valid & ATTR_ATIME_SET)
attr->ia_atime = timestamp_truncate(attr->ia_atime, inode);
- if (!(ia_valid & ATTR_MTIME_SET))
- attr->ia_mtime = now;
else
+ attr->ia_atime = now;
+ if (ia_valid & ATTR_CTIME_SET)
+ attr->ia_ctime = timestamp_truncate(attr->ia_ctime, inode);
+ else
+ attr->ia_ctime = now;
+ if (ia_valid & ATTR_MTIME_SET)
attr->ia_mtime = timestamp_truncate(attr->ia_mtime, inode);
+ else
+ attr->ia_mtime = now;
if (ia_valid & ATTR_KILL_PRIV) {
error = security_inode_need_killpriv(dentry);
diff --git a/fs/lockd/svclock.c b/fs/lockd/svclock.c
index c1315df4b350..a31dc9588eb8 100644
--- a/fs/lockd/svclock.c
+++ b/fs/lockd/svclock.c
@@ -980,7 +980,7 @@ nlmsvc_grant_reply(struct nlm_cookie *cookie, __be32 status)
struct file_lock *fl;
int error;
- dprintk("grant_reply: looking for cookie %x, s=%d \n",
+ dprintk("grant_reply: looking for cookie %x, s=%d\n",
*(unsigned int *)(cookie->data), status);
if (!(block = nlmsvc_find_block(cookie)))
return;
diff --git a/fs/nfsd/Kconfig b/fs/nfsd/Kconfig
index 879e0b104d1c..e134dce45e35 100644
--- a/fs/nfsd/Kconfig
+++ b/fs/nfsd/Kconfig
@@ -5,6 +5,7 @@ config NFSD
depends on FILE_LOCKING
depends on FSNOTIFY
select CRC32
+ select CRYPTO_LIB_SHA256 if NFSD_V4
select LOCKD
select SUNRPC
select EXPORTFS
@@ -77,7 +78,6 @@ config NFSD_V4
select FS_POSIX_ACL
select RPCSEC_GSS_KRB5
select CRYPTO
- select CRYPTO_LIB_SHA256
select CRYPTO_MD5
select GRACE_PERIOD
select NFS_V4_2_SSC_HELPER if NFS_V4_2
diff --git a/fs/nfsd/blocklayout.c b/fs/nfsd/blocklayout.c
index 19078a043e85..fde5539cf6a6 100644
--- a/fs/nfsd/blocklayout.c
+++ b/fs/nfsd/blocklayout.c
@@ -18,8 +18,8 @@
static __be32
-nfsd4_block_proc_layoutget(struct inode *inode, const struct svc_fh *fhp,
- struct nfsd4_layoutget *args)
+nfsd4_block_proc_layoutget(struct svc_rqst *rqstp, struct inode *inode,
+ const struct svc_fh *fhp, struct nfsd4_layoutget *args)
{
struct nfsd4_layout_seg *seg = &args->lg_seg;
struct super_block *sb = inode->i_sb;
@@ -29,6 +29,9 @@ nfsd4_block_proc_layoutget(struct inode *inode, const struct svc_fh *fhp,
u32 device_generation = 0;
int error;
+ if (locks_in_grace(SVC_NET(rqstp)))
+ return nfserr_grace;
+
if (seg->offset & (block_size - 1)) {
dprintk("pnfsd: I/O misaligned\n");
goto out_layoutunavailable;
@@ -118,7 +121,6 @@ nfsd4_block_commit_blocks(struct inode *inode, struct nfsd4_layoutcommit *lcp,
struct iomap *iomaps, int nr_iomaps)
{
struct timespec64 mtime = inode_get_mtime(inode);
- loff_t new_size = lcp->lc_last_wr + 1;
struct iattr iattr = { .ia_valid = 0 };
int error;
@@ -128,9 +130,9 @@ nfsd4_block_commit_blocks(struct inode *inode, struct nfsd4_layoutcommit *lcp,
iattr.ia_valid |= ATTR_ATIME | ATTR_CTIME | ATTR_MTIME;
iattr.ia_atime = iattr.ia_ctime = iattr.ia_mtime = lcp->lc_mtime;
- if (new_size > i_size_read(inode)) {
+ if (lcp->lc_size_chg) {
iattr.ia_valid |= ATTR_SIZE;
- iattr.ia_size = new_size;
+ iattr.ia_size = lcp->lc_newsize;
}
error = inode->i_sb->s_export_op->commit_blocks(inode, iomaps,
@@ -173,16 +175,18 @@ nfsd4_block_proc_getdeviceinfo(struct super_block *sb,
}
static __be32
-nfsd4_block_proc_layoutcommit(struct inode *inode,
+nfsd4_block_proc_layoutcommit(struct inode *inode, struct svc_rqst *rqstp,
struct nfsd4_layoutcommit *lcp)
{
struct iomap *iomaps;
int nr_iomaps;
__be32 nfserr;
- nfserr = nfsd4_block_decode_layoutupdate(lcp->lc_up_layout,
- lcp->lc_up_len, &iomaps, &nr_iomaps,
- i_blocksize(inode));
+ rqstp->rq_arg = lcp->lc_up_layout;
+ svcxdr_init_decode(rqstp);
+
+ nfserr = nfsd4_block_decode_layoutupdate(&rqstp->rq_arg_stream,
+ &iomaps, &nr_iomaps, i_blocksize(inode));
if (nfserr != nfs_ok)
return nfserr;
@@ -313,16 +317,18 @@ nfsd4_scsi_proc_getdeviceinfo(struct super_block *sb,
return nfserrno(nfsd4_block_get_device_info_scsi(sb, clp, gdp));
}
static __be32
-nfsd4_scsi_proc_layoutcommit(struct inode *inode,
+nfsd4_scsi_proc_layoutcommit(struct inode *inode, struct svc_rqst *rqstp,
struct nfsd4_layoutcommit *lcp)
{
struct iomap *iomaps;
int nr_iomaps;
__be32 nfserr;
- nfserr = nfsd4_scsi_decode_layoutupdate(lcp->lc_up_layout,
- lcp->lc_up_len, &iomaps, &nr_iomaps,
- i_blocksize(inode));
+ rqstp->rq_arg = lcp->lc_up_layout;
+ svcxdr_init_decode(rqstp);
+
+ nfserr = nfsd4_scsi_decode_layoutupdate(&rqstp->rq_arg_stream,
+ &iomaps, &nr_iomaps, i_blocksize(inode));
if (nfserr != nfs_ok)
return nfserr;
diff --git a/fs/nfsd/blocklayoutxdr.c b/fs/nfsd/blocklayoutxdr.c
index bcf21fde9120..e50afe340737 100644
--- a/fs/nfsd/blocklayoutxdr.c
+++ b/fs/nfsd/blocklayoutxdr.c
@@ -29,8 +29,7 @@ nfsd4_block_encode_layoutget(struct xdr_stream *xdr,
*p++ = cpu_to_be32(len);
*p++ = cpu_to_be32(1); /* we always return a single extent */
- p = xdr_encode_opaque_fixed(p, &b->vol_id,
- sizeof(struct nfsd4_deviceid));
+ p = svcxdr_encode_deviceid4(p, &b->vol_id);
p = xdr_encode_hyper(p, b->foff);
p = xdr_encode_hyper(p, b->len);
p = xdr_encode_hyper(p, b->soff);
@@ -114,8 +113,7 @@ nfsd4_block_encode_getdeviceinfo(struct xdr_stream *xdr,
/**
* nfsd4_block_decode_layoutupdate - decode the block layout extent array
- * @p: pointer to the xdr data
- * @len: number of bytes to decode
+ * @xdr: subbuf set to the encoded array
* @iomapp: pointer to store the decoded extent array
* @nr_iomapsp: pointer to store the number of extents
* @block_size: alignment of extent offset and length
@@ -128,25 +126,24 @@ nfsd4_block_encode_getdeviceinfo(struct xdr_stream *xdr,
*
* Return values:
* %nfs_ok: Successful decoding, @iomapp and @nr_iomapsp are valid
- * %nfserr_bad_xdr: The encoded array in @p is invalid
+ * %nfserr_bad_xdr: The encoded array in @xdr is invalid
* %nfserr_inval: An unaligned extent found
* %nfserr_delay: Failed to allocate memory for @iomapp
*/
__be32
-nfsd4_block_decode_layoutupdate(__be32 *p, u32 len, struct iomap **iomapp,
+nfsd4_block_decode_layoutupdate(struct xdr_stream *xdr, struct iomap **iomapp,
int *nr_iomapsp, u32 block_size)
{
struct iomap *iomaps;
- u32 nr_iomaps, i;
+ u32 nr_iomaps, expected, len, i;
+ __be32 nfserr;
- if (len < sizeof(u32))
- return nfserr_bad_xdr;
- len -= sizeof(u32);
- if (len % PNFS_BLOCK_EXTENT_SIZE)
+ if (xdr_stream_decode_u32(xdr, &nr_iomaps))
return nfserr_bad_xdr;
- nr_iomaps = be32_to_cpup(p++);
- if (nr_iomaps != len / PNFS_BLOCK_EXTENT_SIZE)
+ len = sizeof(__be32) + xdr_stream_remaining(xdr);
+ expected = sizeof(__be32) + nr_iomaps * PNFS_BLOCK_EXTENT_SIZE;
+ if (len != expected)
return nfserr_bad_xdr;
iomaps = kcalloc(nr_iomaps, sizeof(*iomaps), GFP_KERNEL);
@@ -156,23 +153,44 @@ nfsd4_block_decode_layoutupdate(__be32 *p, u32 len, struct iomap **iomapp,
for (i = 0; i < nr_iomaps; i++) {
struct pnfs_block_extent bex;
- memcpy(&bex.vol_id, p, sizeof(struct nfsd4_deviceid));
- p += XDR_QUADLEN(sizeof(struct nfsd4_deviceid));
+ if (nfsd4_decode_deviceid4(xdr, &bex.vol_id)) {
+ nfserr = nfserr_bad_xdr;
+ goto fail;
+ }
- p = xdr_decode_hyper(p, &bex.foff);
+ if (xdr_stream_decode_u64(xdr, &bex.foff)) {
+ nfserr = nfserr_bad_xdr;
+ goto fail;
+ }
if (bex.foff & (block_size - 1)) {
+ nfserr = nfserr_inval;
+ goto fail;
+ }
+
+ if (xdr_stream_decode_u64(xdr, &bex.len)) {
+ nfserr = nfserr_bad_xdr;
goto fail;
}
- p = xdr_decode_hyper(p, &bex.len);
if (bex.len & (block_size - 1)) {
+ nfserr = nfserr_inval;
+ goto fail;
+ }
+
+ if (xdr_stream_decode_u64(xdr, &bex.soff)) {
+ nfserr = nfserr_bad_xdr;
goto fail;
}
- p = xdr_decode_hyper(p, &bex.soff);
if (bex.soff & (block_size - 1)) {
+ nfserr = nfserr_inval;
+ goto fail;
+ }
+
+ if (xdr_stream_decode_u32(xdr, &bex.es)) {
+ nfserr = nfserr_bad_xdr;
goto fail;
}
- bex.es = be32_to_cpup(p++);
if (bex.es != PNFS_BLOCK_READWRITE_DATA) {
+ nfserr = nfserr_inval;
goto fail;
}
@@ -185,13 +203,12 @@ nfsd4_block_decode_layoutupdate(__be32 *p, u32 len, struct iomap **iomapp,
return nfs_ok;
fail:
kfree(iomaps);
- return nfserr_inval;
+ return nfserr;
}
/**
* nfsd4_scsi_decode_layoutupdate - decode the scsi layout extent array
- * @p: pointer to the xdr data
- * @len: number of bytes to decode
+ * @xdr: subbuf set to the encoded array
* @iomapp: pointer to store the decoded extent array
* @nr_iomapsp: pointer to store the number of extents
* @block_size: alignment of extent offset and length
@@ -203,21 +220,22 @@ fail:
*
* Return values:
* %nfs_ok: Successful decoding, @iomapp and @nr_iomapsp are valid
- * %nfserr_bad_xdr: The encoded array in @p is invalid
+ * %nfserr_bad_xdr: The encoded array in @xdr is invalid
* %nfserr_inval: An unaligned extent found
* %nfserr_delay: Failed to allocate memory for @iomapp
*/
__be32
-nfsd4_scsi_decode_layoutupdate(__be32 *p, u32 len, struct iomap **iomapp,
+nfsd4_scsi_decode_layoutupdate(struct xdr_stream *xdr, struct iomap **iomapp,
int *nr_iomapsp, u32 block_size)
{
struct iomap *iomaps;
- u32 nr_iomaps, expected, i;
+ u32 nr_iomaps, expected, len, i;
+ __be32 nfserr;
- if (len < sizeof(u32))
+ if (xdr_stream_decode_u32(xdr, &nr_iomaps))
return nfserr_bad_xdr;
- nr_iomaps = be32_to_cpup(p++);
+ len = sizeof(__be32) + xdr_stream_remaining(xdr);
expected = sizeof(__be32) + nr_iomaps * PNFS_SCSI_RANGE_SIZE;
if (len != expected)
return nfserr_bad_xdr;
@@ -229,14 +247,22 @@ nfsd4_scsi_decode_layoutupdate(__be32 *p, u32 len, struct iomap **iomapp,
for (i = 0; i < nr_iomaps; i++) {
u64 val;
- p = xdr_decode_hyper(p, &val);
+ if (xdr_stream_decode_u64(xdr, &val)) {
+ nfserr = nfserr_bad_xdr;
+ goto fail;
+ }
if (val & (block_size - 1)) {
+ nfserr = nfserr_inval;
goto fail;
}
iomaps[i].offset = val;
- p = xdr_decode_hyper(p, &val);
+ if (xdr_stream_decode_u64(xdr, &val)) {
+ nfserr = nfserr_bad_xdr;
+ goto fail;
+ }
if (val & (block_size - 1)) {
+ nfserr = nfserr_inval;
goto fail;
}
iomaps[i].length = val;
@@ -247,5 +273,5 @@ nfsd4_scsi_decode_layoutupdate(__be32 *p, u32 len, struct iomap **iomapp,
return nfs_ok;
fail:
kfree(iomaps);
- return nfserr_inval;
+ return nfserr;
}
diff --git a/fs/nfsd/blocklayoutxdr.h b/fs/nfsd/blocklayoutxdr.h
index 15b3569f3d9a..7d25ef689671 100644
--- a/fs/nfsd/blocklayoutxdr.h
+++ b/fs/nfsd/blocklayoutxdr.h
@@ -54,9 +54,9 @@ __be32 nfsd4_block_encode_getdeviceinfo(struct xdr_stream *xdr,
const struct nfsd4_getdeviceinfo *gdp);
__be32 nfsd4_block_encode_layoutget(struct xdr_stream *xdr,
const struct nfsd4_layoutget *lgp);
-__be32 nfsd4_block_decode_layoutupdate(__be32 *p, u32 len,
+__be32 nfsd4_block_decode_layoutupdate(struct xdr_stream *xdr,
struct iomap **iomapp, int *nr_iomapsp, u32 block_size);
-__be32 nfsd4_scsi_decode_layoutupdate(__be32 *p, u32 len,
+__be32 nfsd4_scsi_decode_layoutupdate(struct xdr_stream *xdr,
struct iomap **iomapp, int *nr_iomapsp, u32 block_size);
#endif /* _NFSD_BLOCKLAYOUTXDR_H */
diff --git a/fs/nfsd/debugfs.c b/fs/nfsd/debugfs.c
index 84b0c8b559dc..ed2b9e066206 100644
--- a/fs/nfsd/debugfs.c
+++ b/fs/nfsd/debugfs.c
@@ -26,12 +26,99 @@ static int nfsd_dsr_get(void *data, u64 *val)
static int nfsd_dsr_set(void *data, u64 val)
{
- nfsd_disable_splice_read = (val > 0) ? true : false;
+ nfsd_disable_splice_read = (val > 0);
+ if (!nfsd_disable_splice_read) {
+ /*
+ * Must use buffered I/O if splice_read is enabled.
+ */
+ nfsd_io_cache_read = NFSD_IO_BUFFERED;
+ }
return 0;
}
DEFINE_DEBUGFS_ATTRIBUTE(nfsd_dsr_fops, nfsd_dsr_get, nfsd_dsr_set, "%llu\n");
+/*
+ * /sys/kernel/debug/nfsd/io_cache_read
+ *
+ * Contents:
+ * %0: NFS READ will use buffered IO
+ * %1: NFS READ will use dontcache (buffered IO w/ dropbehind)
+ *
+ * This setting takes immediate effect for all NFS versions,
+ * all exports, and in all NFSD net namespaces.
+ */
+
+static int nfsd_io_cache_read_get(void *data, u64 *val)
+{
+ *val = nfsd_io_cache_read;
+ return 0;
+}
+
+static int nfsd_io_cache_read_set(void *data, u64 val)
+{
+ int ret = 0;
+
+ switch (val) {
+ case NFSD_IO_BUFFERED:
+ nfsd_io_cache_read = NFSD_IO_BUFFERED;
+ break;
+ case NFSD_IO_DONTCACHE:
+ /*
+ * Must disable splice_read when enabling
+ * NFSD_IO_DONTCACHE.
+ */
+ nfsd_disable_splice_read = true;
+ nfsd_io_cache_read = val;
+ break;
+ default:
+ ret = -EINVAL;
+ break;
+ }
+
+ return ret;
+}
+
+DEFINE_DEBUGFS_ATTRIBUTE(nfsd_io_cache_read_fops, nfsd_io_cache_read_get,
+ nfsd_io_cache_read_set, "%llu\n");
+
+/*
+ * /sys/kernel/debug/nfsd/io_cache_write
+ *
+ * Contents:
+ * %0: NFS WRITE will use buffered IO
+ * %1: NFS WRITE will use dontcache (buffered IO w/ dropbehind)
+ *
+ * This setting takes immediate effect for all NFS versions,
+ * all exports, and in all NFSD net namespaces.
+ */
+
+static int nfsd_io_cache_write_get(void *data, u64 *val)
+{
+ *val = nfsd_io_cache_write;
+ return 0;
+}
+
+static int nfsd_io_cache_write_set(void *data, u64 val)
+{
+ int ret = 0;
+
+ switch (val) {
+ case NFSD_IO_BUFFERED:
+ case NFSD_IO_DONTCACHE:
+ nfsd_io_cache_write = val;
+ break;
+ default:
+ ret = -EINVAL;
+ break;
+ }
+
+ return ret;
+}
+
+DEFINE_DEBUGFS_ATTRIBUTE(nfsd_io_cache_write_fops, nfsd_io_cache_write_get,
+ nfsd_io_cache_write_set, "%llu\n");
+
void nfsd_debugfs_exit(void)
{
debugfs_remove_recursive(nfsd_top_dir);
@@ -44,4 +131,10 @@ void nfsd_debugfs_init(void)
debugfs_create_file("disable-splice-read", S_IWUSR | S_IRUGO,
nfsd_top_dir, NULL, &nfsd_dsr_fops);
+
+ debugfs_create_file("io_cache_read", 0644, nfsd_top_dir, NULL,
+ &nfsd_io_cache_read_fops);
+
+ debugfs_create_file("io_cache_write", 0644, nfsd_top_dir, NULL,
+ &nfsd_io_cache_write_fops);
}
diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c
index caa695c06efb..9d55512d0cc9 100644
--- a/fs/nfsd/export.c
+++ b/fs/nfsd/export.c
@@ -1082,50 +1082,62 @@ static struct svc_export *exp_find(struct cache_detail *cd,
}
/**
- * check_nfsd_access - check if access to export is allowed.
+ * check_xprtsec_policy - check if access to export is allowed by the
+ * xprtsec policy
* @exp: svc_export that is being accessed.
- * @rqstp: svc_rqst attempting to access @exp (will be NULL for LOCALIO).
- * @may_bypass_gss: reduce strictness of authorization check
+ * @rqstp: svc_rqst attempting to access @exp.
+ *
+ * Helper function for check_nfsd_access(). Note that callers should be
+ * using check_nfsd_access() instead of calling this function directly. The
+ * one exception is __fh_verify() since it has logic that may result in one
+ * or both of the helpers being skipped.
*
* Return values:
* %nfs_ok if access is granted, or
* %nfserr_wrongsec if access is denied
*/
-__be32 check_nfsd_access(struct svc_export *exp, struct svc_rqst *rqstp,
- bool may_bypass_gss)
+__be32 check_xprtsec_policy(struct svc_export *exp, struct svc_rqst *rqstp)
{
- struct exp_flavor_info *f, *end = exp->ex_flavors + exp->ex_nflavors;
- struct svc_xprt *xprt;
-
- /*
- * If rqstp is NULL, this is a LOCALIO request which will only
- * ever use a filehandle/credential pair for which access has
- * been affirmed (by ACCESS or OPEN NFS requests) over the
- * wire. So there is no need for further checks here.
- */
- if (!rqstp)
- return nfs_ok;
-
- xprt = rqstp->rq_xprt;
+ struct svc_xprt *xprt = rqstp->rq_xprt;
if (exp->ex_xprtsec_modes & NFSEXP_XPRTSEC_NONE) {
if (!test_bit(XPT_TLS_SESSION, &xprt->xpt_flags))
- goto ok;
+ return nfs_ok;
}
if (exp->ex_xprtsec_modes & NFSEXP_XPRTSEC_TLS) {
if (test_bit(XPT_TLS_SESSION, &xprt->xpt_flags) &&
!test_bit(XPT_PEER_AUTH, &xprt->xpt_flags))
- goto ok;
+ return nfs_ok;
}
if (exp->ex_xprtsec_modes & NFSEXP_XPRTSEC_MTLS) {
if (test_bit(XPT_TLS_SESSION, &xprt->xpt_flags) &&
test_bit(XPT_PEER_AUTH, &xprt->xpt_flags))
- goto ok;
+ return nfs_ok;
}
- if (!may_bypass_gss)
- goto denied;
+ return nfserr_wrongsec;
+}
+
+/**
+ * check_security_flavor - check if access to export is allowed by the
+ * security flavor
+ * @exp: svc_export that is being accessed.
+ * @rqstp: svc_rqst attempting to access @exp.
+ * @may_bypass_gss: reduce strictness of authorization check
+ *
+ * Helper function for check_nfsd_access(). Note that callers should be
+ * using check_nfsd_access() instead of calling this function directly. The
+ * one exception is __fh_verify() since it has logic that may result in one
+ * or both of the helpers being skipped.
+ *
+ * Return values:
+ * %nfs_ok if access is granted, or
+ * %nfserr_wrongsec if access is denied
+ */
+__be32 check_security_flavor(struct svc_export *exp, struct svc_rqst *rqstp,
+ bool may_bypass_gss)
+{
+ struct exp_flavor_info *f, *end = exp->ex_flavors + exp->ex_nflavors;
-ok:
/* legacy gss-only clients are always OK: */
if (exp->ex_client == rqstp->rq_gssclient)
return nfs_ok;
@@ -1167,10 +1179,30 @@ ok:
}
}
-denied:
return nfserr_wrongsec;
}
+/**
+ * check_nfsd_access - check if access to export is allowed.
+ * @exp: svc_export that is being accessed.
+ * @rqstp: svc_rqst attempting to access @exp.
+ * @may_bypass_gss: reduce strictness of authorization check
+ *
+ * Return values:
+ * %nfs_ok if access is granted, or
+ * %nfserr_wrongsec if access is denied
+ */
+__be32 check_nfsd_access(struct svc_export *exp, struct svc_rqst *rqstp,
+ bool may_bypass_gss)
+{
+ __be32 status;
+
+ status = check_xprtsec_policy(exp, rqstp);
+ if (status != nfs_ok)
+ return status;
+ return check_security_flavor(exp, rqstp, may_bypass_gss);
+}
+
/*
* Uses rq_client and rq_gssclient to find an export; uses rq_client (an
* auth_unix client) if it's available and has secinfo information;
diff --git a/fs/nfsd/export.h b/fs/nfsd/export.h
index cb36e6cce829..d2b09cd76145 100644
--- a/fs/nfsd/export.h
+++ b/fs/nfsd/export.h
@@ -101,6 +101,9 @@ struct svc_expkey {
struct svc_cred;
int nfsexp_flags(struct svc_cred *cred, struct svc_export *exp);
+__be32 check_xprtsec_policy(struct svc_export *exp, struct svc_rqst *rqstp);
+__be32 check_security_flavor(struct svc_export *exp, struct svc_rqst *rqstp,
+ bool may_bypass_gss);
__be32 check_nfsd_access(struct svc_export *exp, struct svc_rqst *rqstp,
bool may_bypass_gss);
diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c
index e010d90aeb27..a238b6725008 100644
--- a/fs/nfsd/filecache.c
+++ b/fs/nfsd/filecache.c
@@ -395,27 +395,6 @@ nfsd_file_put_local(struct nfsd_file __rcu **pnf)
}
/**
- * nfsd_file_get_local - get nfsd_file reference and reference to net
- * @nf: nfsd_file of which to put the reference
- *
- * Get reference to both the nfsd_file and nf->nf_net.
- */
-struct nfsd_file *
-nfsd_file_get_local(struct nfsd_file *nf)
-{
- struct net *net = nf->nf_net;
-
- if (nfsd_net_try_get(net)) {
- nf = nfsd_file_get(nf);
- if (!nf)
- nfsd_net_put(net);
- } else {
- nf = NULL;
- }
- return nf;
-}
-
-/**
* nfsd_file_file - get the backing file of an nfsd_file
* @nf: nfsd_file of which to access the backing file.
*
diff --git a/fs/nfsd/filecache.h b/fs/nfsd/filecache.h
index 237a05c74211..e3d6ca2b6030 100644
--- a/fs/nfsd/filecache.h
+++ b/fs/nfsd/filecache.h
@@ -67,7 +67,6 @@ int nfsd_file_cache_start_net(struct net *net);
void nfsd_file_cache_shutdown_net(struct net *net);
void nfsd_file_put(struct nfsd_file *nf);
struct net *nfsd_file_put_local(struct nfsd_file __rcu **nf);
-struct nfsd_file *nfsd_file_get_local(struct nfsd_file *nf);
struct nfsd_file *nfsd_file_get(struct nfsd_file *nf);
struct file *nfsd_file_file(struct nfsd_file *nf);
void nfsd_file_close_inode_sync(struct inode *inode);
diff --git a/fs/nfsd/flexfilelayout.c b/fs/nfsd/flexfilelayout.c
index 3ca5304440ff..c318cf74e388 100644
--- a/fs/nfsd/flexfilelayout.c
+++ b/fs/nfsd/flexfilelayout.c
@@ -20,8 +20,8 @@
#define NFSDDBG_FACILITY NFSDDBG_PNFS
static __be32
-nfsd4_ff_proc_layoutget(struct inode *inode, const struct svc_fh *fhp,
- struct nfsd4_layoutget *args)
+nfsd4_ff_proc_layoutget(struct svc_rqst *rqstp, struct inode *inode,
+ const struct svc_fh *fhp, struct nfsd4_layoutget *args)
{
struct nfsd4_layout_seg *seg = &args->lg_seg;
u32 device_generation = 0;
diff --git a/fs/nfsd/flexfilelayoutxdr.c b/fs/nfsd/flexfilelayoutxdr.c
index aeb71c10ff1b..f9f7e38cba13 100644
--- a/fs/nfsd/flexfilelayoutxdr.c
+++ b/fs/nfsd/flexfilelayoutxdr.c
@@ -54,8 +54,7 @@ nfsd4_ff_encode_layoutget(struct xdr_stream *xdr,
*p++ = cpu_to_be32(1); /* single mirror */
*p++ = cpu_to_be32(1); /* single data server */
- p = xdr_encode_opaque_fixed(p, &fl->deviceid,
- sizeof(struct nfsd4_deviceid));
+ p = svcxdr_encode_deviceid4(p, &fl->deviceid);
*p++ = cpu_to_be32(1); /* efficiency */
diff --git a/fs/nfsd/localio.c b/fs/nfsd/localio.c
index 9e0a37cd29d8..be710d809a3b 100644
--- a/fs/nfsd/localio.c
+++ b/fs/nfsd/localio.c
@@ -132,7 +132,6 @@ static const struct nfsd_localio_operations nfsd_localio_ops = {
.nfsd_net_put = nfsd_net_put,
.nfsd_open_local_fh = nfsd_open_local_fh,
.nfsd_file_put_local = nfsd_file_put_local,
- .nfsd_file_get_local = nfsd_file_get_local,
.nfsd_file_file = nfsd_file_file,
.nfsd_file_dio_alignment = nfsd_file_dio_alignment,
};
diff --git a/fs/nfsd/lockd.c b/fs/nfsd/lockd.c
index edc9f75dc75c..c774ce9aa296 100644
--- a/fs/nfsd/lockd.c
+++ b/fs/nfsd/lockd.c
@@ -57,7 +57,20 @@ n