summaryrefslogtreecommitdiff
path: root/fs/nfsd
diff options
context:
space:
mode:
Diffstat (limited to 'fs/nfsd')
-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.c86
-rw-r--r--fs/nfsd/export.h5
-rw-r--r--fs/nfsd/filecache.c57
-rw-r--r--fs/nfsd/filecache.h5
-rw-r--r--fs/nfsd/flexfilelayout.c4
-rw-r--r--fs/nfsd/flexfilelayoutxdr.c3
-rw-r--r--fs/nfsd/localio.c17
-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/nfsctl.c139
-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/nfssvc.c7
-rw-r--r--fs/nfsd/pnfs.h5
-rw-r--r--fs/nfsd/state.h16
-rw-r--r--fs/nfsd/trace.h27
-rw-r--r--fs/nfsd/vfs.c36
-rw-r--r--fs/nfsd/vfs.h33
-rw-r--r--fs/nfsd/xdr4.h39
30 files changed, 740 insertions, 373 deletions
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 cadfc2bae60e..9d55512d0cc9 100644
--- a/fs/nfsd/export.c
+++ b/fs/nfsd/export.c
@@ -402,7 +402,7 @@ static struct svc_export *svc_export_update(struct svc_export *new,
struct svc_export *old);
static struct svc_export *svc_export_lookup(struct svc_export *);
-static int check_export(struct path *path, int *flags, unsigned char *uuid)
+static int check_export(const struct path *path, int *flags, unsigned char *uuid)
{
struct inode *inode = d_inode(path->dentry);
@@ -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;
@@ -1181,7 +1213,7 @@ denied:
* use exp_get_by_name() or exp_find().
*/
struct svc_export *
-rqst_exp_get_by_name(struct svc_rqst *rqstp, struct path *path)
+rqst_exp_get_by_name(struct svc_rqst *rqstp, const struct path *path)
{
struct svc_export *gssexp, *exp = ERR_PTR(-ENOENT);
struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
diff --git a/fs/nfsd/export.h b/fs/nfsd/export.h
index b9c0adb3ce09..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);
@@ -111,7 +114,7 @@ int nfsd_export_init(struct net *);
void nfsd_export_shutdown(struct net *);
void nfsd_export_flush(struct net *);
struct svc_export * rqst_exp_get_by_name(struct svc_rqst *,
- struct path *);
+ const struct path *);
struct svc_export * rqst_exp_parent(struct svc_rqst *,
struct path *);
struct svc_export * rqst_find_fsidzero_export(struct svc_rqst *);
diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c
index 732abf6b92a5..a238b6725008 100644
--- a/fs/nfsd/filecache.c
+++ b/fs/nfsd/filecache.c
@@ -113,7 +113,7 @@ static void
nfsd_file_schedule_laundrette(void)
{
if (test_bit(NFSD_FILE_CACHE_UP, &nfsd_file_flags))
- queue_delayed_work(system_unbound_wq, &nfsd_filecache_laundrette,
+ queue_delayed_work(system_dfl_wq, &nfsd_filecache_laundrette,
NFSD_LAUNDRETTE_DELAY);
}
@@ -231,6 +231,9 @@ nfsd_file_alloc(struct net *net, struct inode *inode, unsigned char need,
refcount_set(&nf->nf_ref, 1);
nf->nf_may = need;
nf->nf_mark = NULL;
+ nf->nf_dio_mem_align = 0;
+ nf->nf_dio_offset_align = 0;
+ nf->nf_dio_read_offset_align = 0;
return nf;
}
@@ -392,27 +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.
*
@@ -1070,6 +1052,35 @@ nfsd_file_is_cached(struct inode *inode)
}
static __be32
+nfsd_file_get_dio_attrs(const struct svc_fh *fhp, struct nfsd_file *nf)
+{
+ struct inode *inode = file_inode(nf->nf_file);
+ struct kstat stat;
+ __be32 status;
+
+ /* Currently only need to get DIO alignment info for regular files */
+ if (!S_ISREG(inode->i_mode))
+ return nfs_ok;
+
+ status = fh_getattr(fhp, &stat);
+ if (status != nfs_ok)
+ return status;
+
+ trace_nfsd_file_get_dio_attrs(inode, &stat);
+
+ if (stat.result_mask & STATX_DIOALIGN) {
+ nf->nf_dio_mem_align = stat.dio_mem_align;
+ nf->nf_dio_offset_align = stat.dio_offset_align;
+ }
+ if (stat.result_mask & STATX_DIO_READ_ALIGN)
+ nf->nf_dio_read_offset_align = stat.dio_read_offset_align;
+ else
+ nf->nf_dio_read_offset_align = nf->nf_dio_offset_align;
+
+ return nfs_ok;
+}
+
+static __be32
nfsd_file_do_acquire(struct svc_rqst *rqstp, struct net *net,
struct svc_cred *cred,
struct auth_domain *client,
@@ -1187,6 +1198,8 @@ open_file:
}
status = nfserrno(ret);
trace_nfsd_file_open(nf, status);
+ if (status == nfs_ok)
+ status = nfsd_file_get_dio_attrs(fhp, nf);
}
} else
status = nfserr_jukebox;
diff --git a/fs/nfsd/filecache.h b/fs/nfsd/filecache.h
index 722b26c71e45..e3d6ca2b6030 100644
--- a/fs/nfsd/filecache.h
+++ b/fs/nfsd/filecache.h
@@ -54,6 +54,10 @@ struct nfsd_file {
struct list_head nf_gc;
struct rcu_head nf_rcu;
ktime_t nf_birthtime;
+
+ u32 nf_dio_mem_align;
+ u32 nf_dio_offset_align;
+ u32 nf_dio_read_offset_align;
};
int nfsd_file_cache_init(void);
@@ -63,7 +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 4f6468eb2adf..be710d809a3b 100644
--- a/fs/nfsd/localio.c
+++ b/fs/nfsd/localio.c
@@ -103,10 +103,11 @@ nfsd_open_local_fh(struct net *net, struct auth_domain *dom,
if (nfsd_file_get(new) == NULL)
goto again;
/*
- * Drop the ref we were going to install and the
- * one we were going to return.
+ * Drop the ref we were going to install (both file and
+ * net) and the one we were going to return (only file).
*/
nfsd_file_put(localio);
+ nfsd_net_put(net);
nfsd_file_put(localio);
localio = new;
}
@@ -116,13 +117,23 @@ nfsd_open_local_fh(struct net *net, struct auth_domain *dom,
return localio;
}
+static void nfsd_file_dio_alignment(struct nfsd_file *nf,
+ u32 *nf_dio_mem_align,
+ u32 *nf_dio_offset_align,
+ u32 *nf_dio_read_offset_align)
+{
+ *nf_dio_mem_align = nf->nf_dio_mem_align;
+ *nf_dio_offset_align = nf->nf_dio_offset_align;
+ *nf_dio_read_offset_align = nf->nf_dio_read_offset_align;
+}
+
static const struct nfsd_localio_operations nfsd_localio_ops = {
.nfsd_net_try_get = nfsd_net_try_get,
.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,
};
void nfsd_localio_ops_init(void)
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 @@ nlm_fopen(struct svc_rqst *rqstp, struct nfs_fh *f, struct file **filp,
switch (nfserr) {
case nfs_ok:
return 0;
- case nfserr_dropit:
+ case nfserr_jukebox:
+ /* this error can indicate a presence of a conflicting
+ * delegation to an NLM lock request. Options are:
+ * (1) For now, drop this request and make the client
+ * retry. When delegation is returned, client's lock retry
+ * will complete.
+ * (2) NLM4_DENIED as per "spec" signals to the client
+ * that the lock is unavailable now but client can retry.
+ * Linux client implementation does not. It treats
+ * NLM4_DENIED same as NLM4_FAILED and errors the request.
+ * (3) For the future, treat this as blocked lock and try
+ * to callback when the delegation is returned but might
+ * not have a proper lock request to block on.
+ */
return nlm_drop_reply;
case nfserr_stale:
return nlm_stale_fh;
diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c
index aea905fcaf87..683bd1130afe 100644
--- a/fs/nfsd/nfs4layouts.c
+++ b/fs/nfsd/nfs4layouts.c
@@ -120,7 +120,6 @@ nfsd4_set_deviceid(struct nfsd4_deviceid *id, const struct svc_fh *fhp,
id->fsid_idx = fhp->fh_export->ex_devid_map->idx;
id->generation = device_generation;
- id->pad = 0;
return 0;
}
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 71b428efcbb5..e466cf52d7d7 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -1133,6 +1133,35 @@ nfsd4_secinfo_no_name_release(union nfsd4_op_u *u)
exp_put(u->secinfo_no_name.sin_exp);
}
+/*
+ * Validate that the requested timestamps are within the acceptable range. If
+ * timestamp appears to be in the future, then it will be clamped to
+ * current_time().
+ */
+static void
+vet_deleg_attrs(struct nfsd4_setattr *setattr, struct nfs4_delegation *dp)
+{
+ struct timespec64 now = current_time(dp->dl_stid.sc_file->fi_inode);
+ struct iattr *iattr = &setattr->sa_iattr;
+
+ if ((setattr->sa_bmval[2] & FATTR4_WORD2_TIME_DELEG_ACCESS) &&
+ !nfsd4_vet_deleg_time(&iattr->ia_atime, &dp->dl_atime, &now))
+ iattr->ia_valid &= ~(ATTR_ATIME | ATTR_ATIME_SET);
+
+ if (setattr->sa_bmval[2] & FATTR4_WORD2_TIME_DELEG_MODIFY) {
+ if (nfsd4_vet_deleg_time(&iattr->ia_mtime, &dp->dl_mtime, &now)) {
+ iattr->ia_ctime = iattr->ia_mtime;
+ if (nfsd4_vet_deleg_time(&iattr->ia_ctime, &dp->dl_ctime, &now))
+ dp->dl_setattr = true;
+ else
+ iattr->ia_valid &= ~(ATTR_CTIME | ATTR_CTIME_SET);
+ } else {
+ iattr->ia_valid &= ~(ATTR_CTIME | ATTR_CTIME_SET |
+ ATTR_MTIME | ATTR_MTIME_SET);
+ }
+ }
+}
+
static __be32
nfsd4_setattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
union nfsd4_op_u *u)
@@ -1170,8 +1199,10 @@ nfsd4_setattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
struct nfs4_delegation *dp = delegstateid(st);
/* Only for *_ATTRS_DELEG flavors */
- if (deleg_attrs_deleg(dp->dl_type))
+ if (deleg_attrs_deleg(dp->dl_type)) {
+ vet_deleg_attrs(setattr, dp);
status = nfs_ok;
+ }
}
}
if (st)
@@ -1209,12 +1240,26 @@ out:
return status;
}
+static void nfsd4_file_mark_deleg_written(struct nfs4_file *fi)
+{
+ spin_lock(&fi->fi_lock);
+ if (!list_empty(&fi->fi_delegations)) {
+ struct nfs4_delegation *dp = list_first_entry(&fi->fi_delegations,
+ struct nfs4_delegation, dl_perfile);
+
+ if (dp->dl_type == OPEN_DELEGATE_WRITE_ATTRS_DELEG)
+ dp->dl_written = true;
+ }
+ spin_unlock(&fi->fi_lock);
+}
+
static __be32
nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
union nfsd4_op_u *u)
{
struct nfsd4_write *write = &u->write;
stateid_t *stateid = &write->wr_stateid;
+ struct nfs4_stid *stid = NULL;
struct nfsd_file *nf = NULL;
__be32 status = nfs_ok;
unsigned long cnt;
@@ -1227,10 +1272,15 @@ nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
trace_nfsd_write_start(rqstp, &cstate->current_fh,
write->wr_offset, cnt);
status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh,
- stateid, WR_STATE, &nf, NULL);
+ stateid, WR_STATE, &nf, &stid);
if (status)
return status;
+ if (stid) {
+ nfsd4_file_mark_deleg_written(stid->sc_file);
+ nfs4_put_stid(stid);
+ }
+
write->wr_how_written = write->wr_stable_how;
status = nfsd_vfs_write(rqstp, &cstate->current_fh, nf,
write->wr_offset, &write->wr_payload,
@@ -1469,7 +1519,7 @@ try_again:
return 0;
}
if (work) {
- strscpy(work->nsui_ipaddr, ipaddr, sizeof(work->nsui_ipaddr) - 1);
+ strscpy(work->nsui_ipaddr, ipaddr, sizeof(work->nsui_ipaddr));
refcount_set(&work->nsui_refcnt, 2);
work->nsui_busy = true;
list_add_tail(&work->nsui_list, &nn->nfsd_ssc_mount_list);
@@ -2447,7 +2497,7 @@ nfsd4_layoutget(struct svc_rqst *rqstp,
if (atomic_read(&ls->ls_stid.sc_file->fi_lo_recalls))
goto out_put_stid;
- nfserr = ops->proc_layoutget(d_inode(current_fh->fh_dentry),
+ nfserr = ops->proc_layoutget(rqstp, d_inode(current_fh->fh_dentry),
current_fh, lgp);
if (nfserr)
goto out_put_stid;
@@ -2471,11 +2521,11 @@ static __be32
nfsd4_layoutcommit(struct svc_rqst *rqstp,
struct nfsd4_compound_state *cstate, union nfsd4_op_u *u)
{
+ struct net *net = SVC_NET(rqstp);
struct nfsd4_layoutcommit *lcp = &u->layoutcommit;
const struct nfsd4_layout_seg *seg = &lcp->lc_seg;
struct svc_fh *current_fh = &cstate->current_fh;
const struct nfsd4_layout_ops *ops;
- loff_t new_size = lcp->lc_last_wr + 1;
struct inode *inode;
struct nfs4_layout_stateid *ls;
__be32 nfserr;
@@ -2491,43 +2541,50 @@ nfsd4_layoutcommit(struct svc_rqst *rqstp,
goto out;
inode = d_inode(current_fh->fh_dentry);
- nfserr = nfserr_inval;
- if (new_size <= seg->offset) {
- dprintk("pnfsd: last write before layout segment\n");
- goto out;
+ lcp->lc_size_chg = false;
+ if (lcp->lc_newoffset) {
+ loff_t new_size = lcp->lc_last_wr + 1;
+
+ nfserr = nfserr_inval;
+ if (new_size <= seg->offset)
+ goto out;
+ if (new_size > seg->offset + seg->length)
+ goto out;
+
+ if (new_size > i_size_read(inode)) {
+ lcp->lc_size_chg = true;
+ lcp->lc_newsize = new_size;
+ }
}
- if (new_size > seg->offset + seg->length) {
- dprintk("pnfsd: last write beyond layout segment\n");
+
+ nfserr = nfserr_grace;
+ if (locks_in_grace(net) && !lcp->lc_reclaim)
goto out;
- }
- if (!lcp->lc_newoffset && new_size > i_size_read(inode)) {
- dprintk("pnfsd: layoutcommit beyond EOF\n");
+ nfserr = nfserr_no_grace;
+ if (!locks_in_grace(net) && lcp->lc_reclaim)
goto out;
- }
- nfserr = nfsd4_preprocess_layout_stateid(rqstp, cstate, &lcp->lc_sid,
- false, lcp->lc_layout_type,
- &ls);
- if (nfserr) {
- trace_nfsd_layout_commit_lookup_fail(&lcp->lc_sid);
- /* fixup error code as per RFC5661 */
- if (nfserr == nfserr_bad_stateid)
- nfserr = nfserr_badlayout;
- goto out;
+ if (!lcp->lc_reclaim) {
+ nfserr = nfsd4_preprocess_layout_stateid(rqstp, cstate,
+ &lcp->lc_sid, false, lcp->lc_layout_type, &ls);
+ if (nfserr) {
+ trace_nfsd_layout_commit_lookup_fail(&lcp->lc_sid);
+ /* fixup error code as per RFC5661 */
+ if (nfserr == nfserr_bad_stateid)
+ nfserr = nfserr_badlayout;
+ goto out;
+ }
+
+ /* LAYOUTCOMMIT does not require any serialization */
+ mutex_unlock(&ls->ls_mutex);
}
- /* LAYOUTCOMMIT does not require any serialization */
- mutex_unlock(&ls->ls_mutex);
+ nfserr = ops->proc_layoutcommit(inode, rqstp, lcp);
- if (new_size > i_size_read(inode)) {
- lcp->lc_size_chg = true;
- lcp->lc_newsize = new_size;
- } else {
- lcp->lc_size_chg = false;
+ if (!lcp->lc_reclaim) {
+ nfsd4_file_mark_deleg_written(ls->ls_stid.sc_file);
+ nfs4_put_stid(&ls->ls_stid);
}
-
- nfserr = ops->proc_layoutcommit(inode, lcp);
- nfs4_put_stid(&ls->ls_stid);
out:
return nfserr;
}
diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c
index 2231192ec33f..e2b9472e5c78 100644
--- a/fs/nfsd/nfs4recover.c
+++ b/fs/nfsd/nfs4recover.c
@@ -92,24 +92,10 @@ nfs4_reset_creds(const struct cred *original)
put_cred(revert_creds(original));
}
-static void
-md5_to_hex(char *out, char *md5)
-{
- int i;
-
- for (i=0; i<16; i++) {
- unsigned char c = md5[i];
-
- *out++ = '0' + ((c&0xf0)>>4) + (c>=0xa0)*('a'-'9'-1);
- *out++ = '0' + (c&0x0f) + ((c&0x0f)>=0x0a)*('a'-'9'-1);
- }
- *out = '\0';
-}
-
static int
-nfs4_make_rec_clidname(char *dname, const struct xdr_netobj *clname)
+nfs4_make_rec_clidname(char dname[HEXDIR_LEN], const struct xdr_netobj *clname)
{
- struct xdr_netobj cksum;
+ u8 digest[MD5_DIGEST_SIZE];
struct crypto_shash *tfm;
int status;
@@ -121,23 +107,16 @@ nfs4_make_rec_clidname(char *dname, const struct xdr_netobj *clname)
goto out_no_tfm;
}
- cksum.len = crypto_shash_digestsize(tfm);
- cksum.data = kmalloc(cksum.len, GFP_KERNEL);
- if (cksum.data == NULL) {
- status = -ENOMEM;
- goto out;
- }
-
status = crypto_shash_tfm_digest(tfm, clname->data, clname->len,
- cksum.data);
+ digest);
if (status)
goto out;
- md5_to_hex(dname, cksum.data);
+ static_assert(HEXDIR_LEN == 2 * MD5_DIGEST_SIZE + 1);
+ sprintf(dname, "%*phN", MD5_DIGEST_SIZE, digest);
status = 0;
out:
- kfree(cksum.data);
crypto_free_shash(tfm);
out_no_tfm:
return status;
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 88c347957da5..81fa7cc6c77b 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -1222,6 +1222,42 @@ static void put_deleg_file(struct nfs4_file *fp)
nfs4_file_put_access(fp, NFS4_SHARE_ACCESS_READ);
}
+static void nfsd4_finalize_deleg_timestamps(struct nfs4_delegation *dp, struct file *f)
+{
+ struct iattr ia = { .ia_valid = ATTR_ATIME | ATTR_CTIME | ATTR_MTIME };
+ struct inode *inode = file_inode(f);
+ int ret;
+
+ /* don't do anything if FMODE_NOCMTIME isn't set */
+ if ((READ_ONCE(f->f_mode) & FMODE_NOCMTIME) == 0)
+ return;
+
+ spin_lock(&f->f_lock);
+ f->f_mode &= ~FMODE_NOCMTIME;
+ spin_unlock(&f->f_lock);
+
+ /* was it never written? */
+ if (!dp->dl_written)
+ return;
+
+ /* did it get a setattr for the timestamps at some point? */
+ if (dp->dl_setattr)
+ return;
+
+ /* Stamp everything to "now" */
+ inode_lock(inode);
+ ret = notify_change(&nop_mnt_idmap, f->f_path.dentry, &ia, NULL);
+ inode_unlock(inode);
+ if (ret) {
+ struct inode *inode = file_inode(f);
+
+ pr_notice_ratelimited("Unable to update timestamps on inode %02x:%02x:%lu: %d\n",
+ MAJOR(inode->i_sb->s_dev),
+ MINOR(inode->i_sb->s_dev),
+ inode->i_ino, ret);
+ }
+}
+
static void nfs4_unlock_deleg_lease(struct nfs4_delegation *dp)
{
struct nfs4_file *fp = dp->dl_stid.sc_file;
@@ -1229,6 +1265,7 @@ static void nfs4_unlock_deleg_lease(struct nfs4_delegation *dp)
WARN_ON_ONCE(!fp->fi_delegees);
+ nfsd4_finalize_deleg_timestamps(dp, nf->nf_file);
kernel_setlease(nf->nf_file, F_UNLCK, NULL, (void **)&dp);
put_deleg_file(fp);
}
@@ -6157,7 +6194,8 @@ nfs4_delegation_stat(struct nfs4_delegation *dp, struct svc_fh *currentfh,
path.dentry = file_dentry(nf->nf_file);
rc = vfs_getattr(&path, stat,
- (STATX_MODE | STATX_SIZE | STATX_CTIME | STATX_CHANGE_COOKIE),
+ STATX_MODE | STATX_SIZE | STATX_ATIME |
+ STATX_MTIME | STATX_CTIME | STATX_CHANGE_COOKIE,
AT_STATX_SYNC_AS_STAT);
nfsd_file_put(nf);
@@ -6264,6 +6302,8 @@ nfs4_open_delegation(struct svc_rqst *rqstp, struct nfsd4_open *open,
memcpy(&open->op_delegate_stateid, &dp->dl_stid.sc_stateid, sizeof(dp->dl_stid.sc_stateid));
if (open->op_share_access & NFS4_SHARE_ACCESS_WRITE) {
+ struct file *f = dp->dl_stid.sc_file->fi_deleg_file->nf_file;
+
if (!nfsd4_add_rdaccess_to_wrdeleg(rqstp, open, fh, stp) ||
!nfs4_delegation_stat(dp, currentfh, &stat)) {
nfs4_put_stid(&dp->dl_stid);
@@ -6274,10 +6314,17 @@ nfs4_open_delegation(struct svc_rqst *rqstp, struct nfsd4_open *open,
OPEN_DELEGATE_WRITE;
dp->dl_cb_fattr.ncf_cur_fsize = stat.size;
dp->dl_cb_fattr.ncf_initial_cinfo = nfsd4_change_attribute(&stat);
+ dp->dl_atime = stat.atime;
+ dp->dl_ctime = stat.ctime;
+ dp->dl_mtime = stat.mtime;
+ spin_lock(&f->f_lock);
+ f->f_mode |= FMODE_NOCMTIME;
+ spin_unlock(&f->f_lock);
trace_nfsd_deleg_write(&dp->dl_stid.sc_stateid);
} else {
- open->op_delegate_type = deleg_ts ? OPEN_DELEGATE_READ_ATTRS_DELEG :
- OPEN_DELEGATE_READ;
+ open->op_delegate_type = deleg_ts && nfs4_delegation_stat(dp, currentfh, &stat) ?
+ OPEN_DELEGATE_READ_ATTRS_DELEG : OPEN_DELEGATE_READ;
+ dp->dl_atime = stat.atime;
trace_nfsd_deleg_read(&dp->dl_stid.sc_stateid);
}
nfs4_put_stid(&dp->dl_stid);
@@ -9130,25 +9177,25 @@ nfsd4_get_writestateid(struct nfsd4_compound_state *cstate,
}
/**
- * set_cb_time - vet and set the timespec for a cb_getattr update
- * @cb: timestamp from the CB_GETATTR response
+ * nfsd4_vet_deleg_time - vet and set the timespec for a delegated timestamp update
+ * @req: timestamp from the client
* @orig: original timestamp in the inode
* @now: current time
*
- * Given a timestamp in a CB_GETATTR response, check it against the
+ * Given a timestamp from the client response, check it against the
* current timestamp in the inode and the current time. Returns true
* if the inode's timestamp needs to be updated, and false otherwise.
- * @cb may also be changed if the timestamp needs to be clamped.
+ * @req may also be changed if the timestamp needs to be clamped.
*/
-static bool set_cb_time(struct timespec64 *cb, const struct timespec64 *orig,
- const struct timespec64 *now)
+bool nfsd4_vet_deleg_time(struct timespec64 *req, const struct timespec64 *orig,
+ const struct timespec64 *now)
{
/*
* "When the time presented is before the original time, then the
* update is ignored." Also no need to update if there is no change.
*/
- if (timespec64_compare(cb, orig) <= 0)
+ if (timespec64_compare(req, orig) <= 0)
return false;
/*
@@ -9156,10 +9203,8 @@ static bool set_cb_time(struct timespec64 *cb, const struct timespec64 *orig,
* clamp the new time to the current time, or it may
* return NFS4ERR_DELAY to the client, allowing it to retry."
*/
- if (timespec64_compare(cb, now) > 0) {
- /* clamp it */
- *cb = *now;
- }
+ if (timespec64_compare(req, now) > 0)
+ *req = *now;
return true;
}
@@ -9167,28 +9212,27 @@ static bool set_cb_time(struct timespec64 *cb, const struct timespec64 *orig,
static int cb_getattr_update_times(struct dentry *dentry, struct nfs4_delegation *dp)
{
struct inode *inode = d_inode(dentry);
- struct timespec64 now = current_time(inode);
struct nfs4_cb_fattr *ncf = &dp->dl_cb_fattr;
struct iattr attrs = { };
int ret;
if (deleg_attrs_deleg(dp->dl_type)) {
- struct timespec64 atime = inode_get_atime(inode);
- struct timespec64 mtime = inode_get_mtime(inode);
+ struct timespec64 now = current_time(inode);
attrs.ia_atime = ncf->ncf_cb_atime;
attrs.ia_mtime = ncf->ncf_cb_mtime;
- if (set_cb_time(&attrs.ia_atime, &atime, &now))
+ if (nfsd4_vet_deleg_time(&attrs.ia_atime, &dp->dl_atime, &now))
attrs.ia_valid |= ATTR_ATIME | ATTR_ATIME_SET;
- if (set_cb_time(&attrs.ia_mtime, &mtime, &now)) {
- attrs.ia_valid |= ATTR_CTIME | ATTR_MTIME | ATTR_MTIME_SET;
+ if (nfsd4_vet_deleg_time(&attrs.ia_mtime, &dp->dl_mtime, &now)) {
+ attrs.ia_valid |= ATTR_MTIME | ATTR_MTIME_SET;
attrs.ia_ctime = attrs.ia_mtime;
+ if (nfsd4_vet_deleg_time(&attrs.ia_ctime, &dp->dl_ctime, &now))
+ attrs.ia_valid |= ATTR_CTIME | ATTR_CTIME_SET;
}
} else {
attrs.ia_valid |= ATTR_MTIME | ATTR_CTIME;
- attrs.ia_mtime = attrs.ia_ctime = now;
}
if (!attrs.ia_valid)
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index ea91bad4eee2..c0a3c6a7c8bb 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -538,8 +538,9 @@ nfsd4_decode_fattr4(struct nfsd4_compoundargs *argp, u32 *bmval, u32 bmlen,
iattr->ia_mtime.tv_sec = modify.seconds;
iattr->ia_mtime.tv_nsec = modify.nseconds;
iattr->ia_ctime.tv_sec = modify.seconds;
- iattr->ia_ctime.tv_nsec = modify.seconds;
- iattr->ia_valid |= ATTR_CTIME | ATTR_MTIME | ATTR_MTIME_SET | ATTR_DELEG;
+ iattr->ia_ctime.tv_nsec = modify.nseconds;
+ iattr->ia_valid |= ATTR_CTIME | ATTR_CTIME_SET |
+ ATTR_MTIME | ATTR_MTIME_SET | ATTR_DELEG;
}
/* request sanity: did attrlist4 contain the expected number of words? */
@@ -587,23 +588,13 @@ nfsd4_decode_state_owner4(struct nfsd4_compoundargs *argp,
}
#ifdef CONFIG_NFSD_PNFS
-static __be32
-nfsd4_decode_deviceid4(struct nfsd4_compoundargs *argp,
- struct nfsd4_deviceid *devid)
-{
- __be32 *p;
-
- p = xdr_inline_decode(argp->xdr, NFS4_DEVICEID4_SIZE);
- if (!p)
- return nfserr_bad_xdr;
- memcpy(devid, p, sizeof(*devid));
- return nfs_ok;
-}
static __be32
nfsd4_decode_layoutupdate4(struct nfsd4_compoundargs *argp,
struct nfsd4_layoutcommit *lcp)
{
+ u32 len;
+
if (xdr_stream_decode_u32(argp->xdr, &lcp->lc_layout_type) < 0)
return nfserr_bad_xdr;
if (lcp->lc_layout_type < LAYOUT_NFSV4_1_FILES)
@@ -611,13 +602,10 @@ nfsd4_decode_layoutupdate4(struct nfsd4_compoundargs *argp,
if (lcp->lc_layout_type >= LAYOUT_TYPE_MAX)
return nfserr_bad_xdr;
- if (xdr_stream_decode_u32(argp->xdr, &lcp->lc_up_len) < 0)
+ if (xdr_stream_decode_u32(argp->xdr, &len) < 0)
+ return nfserr_bad_xdr;
+ if (!xdr_stream_subsegment(argp->xdr, &lcp->lc_up_layout, len))
return nfserr_bad_xdr;
- if (lcp->lc_up_len > 0) {
- lcp->lc_up_layout = xdr_inline_decode(argp->xdr, lcp->lc_up_len);
- if (!lcp->lc_up_layout)
- return nfserr_bad_xdr;
- }
return nfs_ok;
}
@@ -1783,7 +1771,7 @@ nfsd4_decode_getdeviceinfo(struct nfsd4_compoundargs *argp,
__be32 status;
memset(gdev, 0, sizeof(*gdev));
- status = nfsd4_decode_deviceid4(argp, &gdev->gd_devid);
+ status = nfsd4_decode_deviceid4(argp->xdr, &gdev->gd_devid);
if (status)
return status;
if (xdr_stream_decode_u32(argp->xdr, &gdev->gd_layout_type) < 0)
@@ -1814,7 +1802,7 @@ nfsd4_decode_layoutcommit(struct nfsd4_compoundargs *argp,
status = nfsd4_decode_stateid4(argp, &lcp->lc_sid);
if (status)
return status;
- if (xdr_stream_decode_u32(argp->xdr, &lcp->lc_newoffset) < 0)
+ if (xdr_stream_decode_bool(argp->xdr, &lcp->lc_newoffset) < 0)
return nfserr_bad_xdr;
if (lcp->lc_newoffset) {
if (xdr_stream_decode_u64(argp->xdr, &lcp->lc_last_wr) < 0)
diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c
index ba9d326b3de6..ab13ee9c7fd8 100644
--- a/fs/nfsd/nfscache.c
+++ b/fs/nfsd/nfscache.c
@@ -27,7 +27,7 @@
* cache size, the idea being that when the cache is at its maximum number
* of entries, then this should be the average number of entries per bucket.
*/
-#define TARGET_BUCKET_SIZE 64
+#define TARGET_BUCKET_SIZE 8
struct nfsd_drc_bucket {
struct rb_root rb_head;
@@ -237,10 +237,6 @@ void nfsd_reply_cache_shutdown(struct nfsd_net *nn)
}
-/*
- * Move cache entry to end of LRU list, and queue the cleaner to run if it's
- * not already scheduled.
- */
static void
lru_put_end(struct nfsd_drc_bucket *b, struct nfsd_cacherep *rp)
{
@@ -272,13 +268,6 @@ nfsd_prune_bucket_locked(struct nfsd_net *nn, struct nfsd_drc_bucket *b,
/* The bucket LRU is ordered oldest-first. */
list_for_each_entry_safe(rp, tmp, &b->lru_head, c_lru) {
- /*
- * Don't free entries attached to calls that are still
- * in-progress, but do keep scanning the list.
- */
- if (rp->c_state == RC_INPROG)
- continue;
-
if (atomic_read(&nn->num_drc_entries) <= nn->max_drc_entries &&
time_before(expiry, rp->c_timestamp))
break;
@@ -453,8 +442,6 @@ out:
nn->longest_chain_cachesize,
atomic_read(&nn->num_drc_entries));
}
-
- lru_put_end(b, ret);
return ret;
}
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index bc6b776fc657..2b79129703d5 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -1103,89 +1103,48 @@ static ssize_t write_v4_end_grace(struct file *file, char *buf, size_t size)
* populating the filesystem.
*/
-/* Basically copying rpc_get_inode. */
static struct inode *nfsd_get_inode(struct super_block *sb, umode_t mode)
{
struct inode *inode = new_inode(sb);
- if (!inode)
- return NULL;
- /* Following advice from simple_fill_super documentation: */
- inode->i_ino = iunique(sb, NFSD_MaxReserved);
- inode->i_mode = mode;
- simple_inode_init_ts(inode);
- switch (mode & S_IFMT) {
- case S_IFDIR:
- inode->i_fop = &simple_dir_operations;
- inode->i_op = &simple_dir_inode_operations;
- inc_nlink(inode);
- break;
- case S_IFLNK:
- inode->i_op = &simple_symlink_inode_operations;
- break;
- default:
- break;
+ if (inode) {
+ /* Following advice from simple_fill_super documentation: */
+ inode->i_ino = iunique(sb, NFSD_MaxReserved);
+ inode->i_mode = mode;
+ simple_inode_init_ts(inode);
}
return inode;
}
-static int __nfsd_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode, struct nfsdfs_client *ncl)
+static struct dentry *nfsd_mkdir(struct dentry *parent, struct nfsdfs_client *ncl, char *name)
{
+ struct inode *dir = parent->d_inode;
+ struct dentry *dentry;
struct inode *inode;
- inode = nfsd_get_inode(dir->i_sb, mode);
+ inode = nfsd_get_inode(parent->d_sb, S_IFDIR | 0600);
if (!inode)
- return -ENOMEM;
+ return ERR_PTR(-ENOMEM);
+
+ dentry = simple_start_creating(parent, name);
+ if (IS_ERR(dentry)) {
+ iput(inode);
+ return dentry;
+ }
+ inode->i_fop = &simple_dir_operations;
+ inode->i_op = &simple_dir_inode_operations;
+ inc_nlink(inode);
if (ncl) {
inode->i_private = ncl;
kref_get(&ncl->cl_ref);
}
- d_add(dentry, inode);
+ d_instantiate(dentry, inode);
inc_nlink(dir);
fsnotify_mkdir(dir, dentry);
- return 0;
-}
-
-static struct dentry *nfsd_mkdir(struct dentry *parent, struct nfsdfs_client *ncl, char *name)
-{
- struct inode *dir = parent->d_inode;
- struct dentry *dentry;
- int ret = -ENOMEM;
-
- inode_lock(dir);
- dentry = d_alloc_name(parent, name);
- if (!dentry)
- goto out_err;
- ret = __nfsd_mkdir(d_inode(parent), dentry, S_IFDIR | 0600, ncl);
- if (ret)
- goto out_err;
-out:
inode_unlock(dir);
return dentry;
-out_err:
- dput(dentry);
- dentry = ERR_PTR(ret);
- goto out;
}
#if IS_ENABLED(CONFIG_SUNRPC_GSS)
-static int __nfsd_symlink(struct inode *dir, struct dentry *dentry,
- umode_t mode, const char *content)
-{
- struct inode *inode;
-
- inode = nfsd_get_inode(dir->i_sb, mode);
- if (!inode)
- return -ENOMEM;
-
- inode->i_link = (char *)content;
- inode->i_size = strlen(content);
-
- d_add(dentry, inode);
- inc_nlink(dir);
- fsnotify_create(dir, dentry);
- return 0;
-}
-
/*
* @content is assumed to be a NUL-terminated string that lives
* longer than the symlink itself.
@@ -1194,17 +1153,25 @@ static void _nfsd_symlink(struct dentry *parent, const char *name,
const char *content)
{
struct inode *dir = parent->d_inode;
+ struct inode *inode;
struct dentry *dentry;
- int ret;
- inode_lock(dir);
- dentry = d_alloc_name(parent, name);
- if (!dentry)
- goto out;
- ret = __nfsd_symlink(d_inode(parent), dentry, S_IFLNK | 0777, content);
- if (ret)
- dput(dentry);
-out:
+ inode = nfsd_get_inode(dir->i_sb, S_IFLNK | 0777);
+ if (!inode)
+ return;
+
+ dentry = simple_start_creating(parent, name);
+ if (IS_ERR(dentry)) {
+ iput(inode);
+ return;
+ }
+
+ inode->i_op = &simple_symlink_inode_operations;
+ inode->i_link = (char *)content;
+ inode->i_size = strlen(content);
+
+ d_instantiate(dentry, inode);
+ fsnotify_create(dir, dentry);
inode_unlock(dir);
}
#else
@@ -1240,40 +1207,34 @@ struct nfsdfs_client *get_nfsdfs_client(struct inode *inode)
/* XXX: cut'n'paste from simple_fill_super; figure out if we could share
* code instead. */
-static int nfsdfs_create_files(struct dentry *root,
+static int nfsdfs_create_files(struct dentry *root,
const struct tree_descr *files,
struct nfsdfs_client *ncl,
struct dentry **fdentries)
{
struct inode *dir = d_inode(root);
- struct inode *inode;
struct dentry *dentry;
- int i;
- inode_lock(dir);
- for (i = 0; files->name && files->name[0]; i++, files++) {
- dentry = d_alloc_name(root, files->name);
- if (!dentry)
- goto out;
- inode = nfsd_get_inode(d_inode(root)->i_sb,
- S_IFREG | files->mode);
- if (!inode) {
- dput(dentry);
- goto out;
+ for (int i = 0; files->name && files->name[0]; i++, files++) {
+ struct inode *inode = nfsd_get_inode(root->d_sb,
+ S_IFREG | files->mode);
+ if (!inode)
+ return -ENOMEM;
+ dentry = simple_start_creating(root, files->name);
+ if (IS_ERR(dentry)) {
+ iput(inode);
+ return PTR_ERR(dentry);
}
kref_get(&ncl->cl_ref);
inode->i_fop = files->ops;
inode->i_private = ncl;
- d_add(dentry, inode);
+ d_instantiate(dentry, inode);
fsnotify_create(dir, dentry);
if (fdentries)
fdentries[i] = dentry;
+ inode_unlock(dir);
}
- inode_unlock(dir);
return 0;
-out:
- inode_unlock(dir);
- return -ENOMEM;
}
/* on success, returns positive number unique to that client. */
@@ -1993,7 +1954,7 @@ int nfsd_nl_listener_set_doit(struct sk_buff *skb, struct genl_info *info)
* remaining listeners and recreate the list.
*/
if (delete)
- svc_xprt_destroy_all(serv, net);
+ svc_xprt_destroy_all(serv, net, false);
/* walk list of addrs again, open any that still don't exist */
nlmsg_for_each_attr_type(attr, NFSD_A_SERVER_SOCK_ADDR, info->nlhdr,
diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h
index 1cd0bed57bc2..ea87b42894dd 100644
--- a/fs/nfsd/nfsd.h
+++ b/fs/nfsd/nfsd.h
@@ -153,6 +153,15 @@ static inline void nfsd_debugfs_exit(void) {}
extern bool nfsd_disable_splice_read __read_mostly;
+enum {
+ /* Any new NFSD_IO enum value must be added at the end */
+ NFSD_IO_BUFFERED,
+ NFSD_IO_DONTCACHE,
+};
+
+extern u64 nfsd_io_cache_read __read_mostly;
+extern u64 nfsd_io_cache_write __read_mostly;
+
extern int nfsd_max_blksize;
static inline int nfsd_v4client(struct svc_rqst *rq)
@@ -335,14 +344,8 @@ void nfsd_lockd_shutdown(void);
* cannot conflict with any existing be32 nfserr value.
*/
enum {
- NFSERR_DROPIT = NFS4ERR_FIRST_FREE,
-/* if a request fails due to kmalloc failure, it gets dropped.
- * Client should resend eventually
- */
-#define nfserr_dropit cpu_to_be32(NFSERR_DROPIT)
-
/* end-of-file indicator in readdir */
- NFSERR_EOF,
+ NFSERR_EOF = NFS4ERR_FIRST_FREE,
#define nfserr_eof cpu_to_be32(NFSERR_EOF)
/* replay detected */
diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c
index 74cf1f4de174..3eb724ec9566 100644
--- a/fs/nfsd/nfsfh.c
+++ b/fs/nfsd/nfsfh.c
@@ -364,10 +364,30 @@ __fh_verify(struct svc_rqst *rqstp,
if (error)
goto out;
+ /*
+ * 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. Skip both the xprtsec policy and the security flavor
+ * checks.
+ */
+ if (!rqstp)
+ goto check_permissions;
+
if ((access & NFSD_MAY_NLM) && (exp->ex_flags & NFSEXP_NOAUTHNLM))
/* NLM is allowed to fully bypass authentication */
goto out;
+ /*
+ * NLM is allowed to bypass the xprtsec policy check because lockd
+ * doesn't support xprtsec.
+ */
+ if (!(access & NFSD_MAY_NLM)) {
+ error = check_xprtsec_policy(exp, rqstp);
+ if (error)
+ goto out;
+ }
+
if (access & NFSD_MAY_BYPASS_GSS)
may_bypass_gss = true;
/*
@@ -379,13 +399,13 @@ __fh_verify(struct svc_rqst *rqstp,
&& exp->ex_path.dentry == dentry)
may_bypass_gss = true;
- error = check_nfsd_access(exp, rqstp, may_bypass_gss);
+ error = check_security_flavor(exp, rqstp, may_bypass_gss);
if (error)
goto out;
- /* During LOCALIO call to fh_verify will be called with a NULL rqstp */
- if (rqstp)
- svc_xprt_set_valid(rqstp->rq_xprt);
+ svc_xprt_set_valid(rqstp->rq_xprt);
+
+check_permissions:
/* Finally, check access permissions. */
error = nfsd_permission(cred, exp, dentry, access);
out:
@@ -663,6 +683,33 @@ out_negative:
}
/**
+ * fh_getattr - Retrieve attributes on a local file
+ * @fhp: File handle of target file
+ * @stat: Caller-supplied kstat buffer to be filled in
+ *
+ * Returns nfs_ok on success, otherwise an NFS status code is
+ * returned.
+ */
+__be32 fh_getattr(const struct svc_fh *fhp, struct kstat *stat)
+{
+ struct path p = {
+ .mnt = fhp->fh_export->ex_path.mnt,
+ .dentry = fhp->fh_dentry,
+ };
+ struct inode *inode = d_inode(p.dentry);
+ u32 request_mask = STATX_BASIC_STATS;
+
+ if (S_ISREG(inode->i_mode))
+ request_mask |= (STATX_DIOALIGN | STATX_DIO_READ_ALIGN);
+
+ if (fhp->fh_maxsize == NFS4_FHSIZE)
+ request_mask |= (STATX_BTIME | STATX_CHANGE_COOKIE);
+
+ return nfserrno(vfs_getattr(&p, stat, request_mask,
+ AT_STATX_SYNC_AS_STAT));
+}
+
+/**
* fh_fill_pre_attrs - Fill in pre-op attributes
* @fhp: file handle to be updated
*
diff --git a/fs/nfsd/nfsfh.h b/fs/nfsd/nfsfh.h
index 1cf979722521..5ef7191f8ad8 100644
--- a/fs/nfsd/nfsfh.h
+++ b/fs/nfsd/nfsfh.h
@@ -14,6 +14,8 @@
#include <linux/exportfs.h>
#include <linux/nfs4.h>
+#include "export.h"
+
/*
* The file handle starts with a sequence of four-byte words.
* The first word contains a version number (1) and three descriptor bytes
@@ -220,6 +222,7 @@ extern char * SVCFH_fmt(struct svc_fh *fhp);
__be32 fh_verify(struct svc_rqst *, struct svc_fh *, umode_t, int);
__be32 fh_verify_local(struct net *, struct svc_cred *, struct auth_domain *,
struct svc_fh *, umode_t, int);
+__be32 fh_getattr(const struct svc_fh *fhp, struct kstat *stat);
__be32 fh_compose(struct svc_fh *, struct svc_export *, struct dentry *, struct svc_fh *);
__be32 fh_update(struct svc_fh *);
void fh_put(struct svc_fh *);
@@ -272,6 +275,41 @@ static inline bool fh_fsid_match(const struct knfsd_fh *fh1,
}
/**
+ * fh_want_write - Get write access to an export
+ * @fhp: File handle of file to be written
+ *
+ * Caller must invoke fh_drop_write() when its write operation
+ * is complete.
+ *
+ * Returns 0 if the file handle's export can be written to. Otherwise
+ * the export is not prepared for updates, and the returned negative
+ * errno value reflects the reason for the failure.
+ */
+static inline int fh_want_write(struct svc_fh *fhp)
+{
+ int ret;
+
+ if (fhp->fh_want_write)
+ return 0;
+ ret = mnt_want_write(fhp->fh_export->ex_path.mnt);
+ if (!ret)
+ fhp->fh_want_write = true;
+ return ret;
+}
+
+/**
+ * fh_drop_write - Release write access on an export
+ * @fhp: File handle of file on which fh_want_write() was previously called
+ */
+static inline void fh_drop_write(struct svc_fh *fhp)
+{
+ if (fhp->fh_want_write) {
+ fhp->fh_want_write = false;
+ mnt_drop_write(fhp->fh_export->ex_path.mnt);
+ }
+}
+
+/**
* knfsd_fh_hash - calculate the crc32 hash for the filehandle
* @fh - pointer to filehandle
*
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index 82b0111ac469..7057ddd7a0a8 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -535,16 +535,13 @@ void nfsd_destroy_serv(struct net *net)
#endif
}
- svc_xprt_destroy_all(serv, net);
-
/*
* write_ports can create the server without actually starting
- * any threads--if we get shut down before any threads are
+ * any threads. If we get shut down before any threads are
* started, then nfsd_destroy_serv will be run before any of this
* other initialization has been done except the rpcb information.
*/
- svc_rpcb_cleanup(serv, net);
-
+ svc_xprt_destroy_all(serv, net, true);
nfsd_shutdown_net(net);
svc_destroy(&serv);
}
diff --git a/fs/nfsd/pnfs.h b/fs/nfsd/pnfs.h
index 925817f66917..db9af780438b 100644
--- a/fs/nfsd/pnfs.h
+++ b/fs/nfsd/pnfs.h
@@ -29,12 +29,13 @@ struct nfsd4_layout_ops {
__be32 (*encode_getdeviceinfo)(struct xdr_stream *xdr,
const struct nfsd4_getdeviceinfo *gdevp);
- __be32 (*proc_layoutget)(struct inode *, const struct svc_fh *fhp,
- struct nfsd4_layoutget *lgp);
+ __be32 (*proc_layoutget)(struct svc_rqst *rqstp, struct inode *inode,
+ const struct svc_fh *fhp, struct nfsd4_layoutget *lgp);
__be32 (*encode_layoutget)(struct xdr_stream *xdr,
const struct nfsd4_layoutget *lgp);
__be32 (*proc_layoutcommit)(struct inode *inode,
+ struct svc_rqst *rqstp,
struct nfsd4_layoutcommit *lcp);
void (*fence_client)(struct nfs4_layout_stateid *ls,
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 8adc2550129e..1e736f402426 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -35,6 +35,7 @@
#ifndef _NFSD4_STATE_H
#define _NFSD4_STATE_H
+#include <crypto/md5.h>
#include <linux/idr.h>
#include <linux/refcount.h>
#include <linux/sunrpc/svc_xprt.h>
@@ -217,13 +218,20 @@ struct nfs4_delegation {
struct nfs4_clnt_odstate *dl_clnt_odstate;
time64_t dl_time;
u32 dl_type;
-/* For recall: */
+ /* For recall: */
int dl_retries;
struct nfsd4_callback dl_recall;
bool dl_recalled;
+ bool dl_written;
+ bool dl_setattr;
/* for CB_GETATTR */
struct nfs4_cb_fattr dl_cb_fattr;
+
+ /* For delegated timestamps */
+ struct timespec64 dl_atime;
+ struct timespec64 dl_mtime;
+ struct timespec64 dl_ctime;
};
static inline bool deleg_is_read(u32 dl_type)
@@ -242,6 +250,9 @@ static inline bool deleg_attrs_deleg(u32 dl_type)
dl_type == OPEN_DELEGATE_WRITE_ATTRS_DELEG;
}
+bool nfsd4_vet_deleg_time(struct timespec64 *cb, const struct timespec64 *orig,
+ const struct timespec64 *now);
+
#define cb_to_delegation(cb) \
container_of(cb, struct nfs4_delegation, dl_recall)
@@ -381,7 +392,8 @@ struct nfsd4_sessionid {
u32 reserved;
};
-#define HEXDIR_LEN 33 /* hex version of 16 byte md5 of cl_name plus '\0' */
+/* Length of MD5 digest as hex, plus terminating '\0' */
+#define HEXDIR_LEN (2 * MD5_DIGEST_SIZE + 1)
/*
* State Meaning Where set
diff --git a/fs/nfsd/trace.h b/fs/nfsd/trace.h
index a664fdf1161e..6e2c8e2aab10 100644
--- a/fs/nfsd/trace.h
+++ b/fs/nfsd/trace.h
@@ -1133,6 +1133,33 @@ TRACE_EVENT(nfsd_file_alloc,
)
);
+TRACE_EVENT(nfsd_file_get_dio_attrs,
+ TP_PROTO(
+ const struct inode *inode,
+ const struct kstat *stat
+ ),
+ TP_ARGS(inode, stat),
+ TP_STRUCT__entry(
+ __field(const void *, inode)
+ __field(unsigned long, mask)
+ __field(u32, mem_align)
+ __field(u32, offset_align)
+ __field(u32, read_offset_align)
+ ),
+ TP_fast_assign(
+ __entry->inode = inode;
+ __entry->mask = stat->result_mask;
+ __entry->mem_align = stat->dio_mem_align;
+ __entry->offset_align = stat->dio_offset_align;
+ __entry->read_offset_align = stat->dio_read_offset_align;
+ ),
+ TP_printk("inode=%p flags=%s mem_align=%u offset_align=%u read_offset_align=%u",
+ __entry->inode, show_statx_mask(__entry->mask),
+ __entry->mem_align, __entry->offset_align,
+ __entry->read_offset_align
+ )
+);
+
TRACE_EVENT(nfsd_file_acquire,
TP_PROTO(
const struct svc_rqst *rqstp,
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 98ab55ba3ced..9cb20d4aeab1 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -49,6 +49,8 @@
#define NFSDDBG_FACILITY NFSDDBG_FILEOP
bool nfsd_disable_splice_read __read_mostly;
+u64 nfsd_io_cache_read __read_mostly = NFSD_IO_BUFFERED;
+u64 nfsd_io_cache_write __read_mostly = NFSD_IO_BUFFERED;
/**
* nfserrno - Map Linux errnos to NFS errnos
@@ -467,10 +469,18 @@ static int __nfsd_setattr(struct dentry *dentry, struct iattr *iap)
return 0;
}
- if (!iap->ia_valid)
+ if ((iap->ia_valid & ~ATTR_DELEG) == 0)
return 0;
- iap->ia_valid |= ATTR_CTIME;
+ /*
+ * If ATTR_DELEG is set, then this is an update from a client that
+ * holds a delegation. If this is an update for only the atime, the
+ * ctime should not be changed. If the update contains the mtime
+ * too, then ATTR_CTIME should already be set.
+ */
+ if (!(iap->ia_valid & ATTR_DELEG))
+ iap->ia_valid |= ATTR_CTIME;
+
return notify_change(&nop_mnt_idmap, dentry, iap, NULL);
}
@@ -1091,6 +1101,16 @@ __be32 nfsd_iter_read(struct svc_rqst *rqstp, struct svc_fh *fhp,
size_t len;
init_sync_kiocb(&kiocb, file);
+
+ switch (nfsd_io_cache_read) {
+ case NFSD_IO_BUFFERED:
+ break;
+ case NFSD_IO_DONTCACHE:
+ if (file->f_op->fop_flags & FOP_DONTCACHE)
+ kiocb.ki_flags = IOCB_DONTCACHE;
+ break;
+ }
+
kiocb.ki_pos = offset;
v = 0;
@@ -1216,6 +1236,15 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp,
since = READ_ONCE(file->f_wb_err);
if (verf)
nfsd_copy_write_verifier(verf, nn);
+
+ switch (nfsd_io_cache_write) {
+ case NFSD_IO_BUFFERED:
+ break;
+ case NFSD_IO_DONTCACHE:
+ if (file->f_op->fop_flags & FOP_DONTCACHE)
+ kiocb.ki_flags |= IOCB_DONTCACHE;
+ break;
+ }
host_err = vfs_iocb_iter_write(file, &kiocb, &iter);
if (host_err < 0) {
commit_reset_write_verifier(nn, rqstp, host_err);
@@ -1943,10 +1972,9 @@ retry:
goto out_dput_old;
} else {
struct renamedata rd = {
- .old_mnt_idmap = &nop_mnt_idmap,
+ .mnt_idmap = &nop_mnt_idmap,
.old_parent = fdentry,
.old_dentry = odentry,
- .new_mnt_idmap = &nop_mnt_idmap,
.new_parent = tdentry,
.new_dentry = ndentry,
};
diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h
index eff04959606f..0c0292611c6d 100644
--- a/fs/nfsd/vfs.h
+++ b/fs/nfsd/vfs.h
@@ -160,37 +160,4 @@ __be32 nfsd_permission(struct svc_cred *cred, struct svc_export *exp,
void nfsd_filp_close(struct file *fp);
-static inline int fh_want_write(struct svc_fh *fh)
-{
- int ret;
-
- if (fh->fh_want_write)
- return 0;
- ret = mnt_want_write(fh->fh_export->ex_path.mnt);
- if (!ret)
- fh->fh_want_write = true;
- return ret;
-}
-
-static inline void fh_drop_write(struct svc_fh *fh)
-{
- if (fh->fh_want_write) {
- fh->fh_want_write = false;
- mnt_drop_write(fh->fh_export->ex_path.mnt);
- }
-}
-
-static inline __be32 fh_getattr(const struct svc_fh *fh, struct kstat *stat)
-{
- u32 request_mask = STATX_BASIC_STATS;
- struct path p = {.mnt = fh->fh_export->ex_path.mnt,
- .dentry = fh->fh_dentry};
-
- if (fh->fh_maxsize == NFS4_FHSIZE)
- request_mask |= (STATX_BTIME | STATX_CHANGE_COOKIE);
-
- return nfserrno(vfs_getattr(&p, stat, request_mask,
- AT_STATX_SYNC_AS_STAT));
-}
-
#endif /* LINUX_NFSD_VFS_H */
diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h
index a23bc56051ca..d4b48602b2b0 100644
--- a/fs/nfsd/xdr4.h
+++ b/fs/nfsd/xdr4.h
@@ -595,9 +595,43 @@ struct nfsd4_reclaim_complete {
struct nfsd4_deviceid {
u64 fsid_idx;
u32 generation;
- u32 pad;
};
+static inline __be32 *
+svcxdr_encode_deviceid4(__be32 *p, const struct nfsd4_deviceid *devid)
+{
+ __be64 *q = (__be64 *)p;
+
+ *q = (__force __be64)devid->fsid_idx;
+ p += 2;
+ *p++ = (__force __be32)devid->generation;
+ *p++ = xdr_zero;
+ return p;
+}
+
+static inline __be32 *
+svcxdr_decode_deviceid4(__be32 *p, struct nfsd4_deviceid *devid)
+{
+ __be64 *q = (__be64 *)p;
+
+ devid->fsid_idx = (__force u64)(*q);
+ p += 2;
+ devid->generation = (__force u32)(*p++);
+ p++; /* NFSD does not use the remaining octets */
+ return p;
+}
+
+static inline __be32
+nfsd4_decode_deviceid4(struct xdr_stream *xdr, struct nfsd4_deviceid *devid)
+{
+ __be32 *p = xdr_inline_decode(xdr, NFS4_DEVICEID4_SIZE);
+
+ if (unlikely(!p))
+ return nfserr_bad_xdr;
+ svcxdr_decode_deviceid4(p, devid);
+ return nfs_ok;
+}
+
struct nfsd4_layout_seg {
u32 iomode;
u64 offset;
@@ -630,8 +664,7 @@ struct nfsd4_layoutcommit {
u64 lc_last_wr; /* request */
struct timespec64 lc_mtime; /* request */
u32 lc_layout_type; /* request */
- u32 lc_up_len; /* layout length */
- void *lc_up_layout; /* decoded by callback */
+ struct xdr_buf lc_up_layout; /* decoded by callback */
bool lc_size_chg; /* response */
u64 lc_newsize; /* response */
};
generated by cgit (git 2.34.1) at 2025-10-07 07:41:29 +0000