hollalinux
/
linux-sg2042
mirror of https://github.com/sophgo/linux-riscv.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Highlights: 

- Improve support for re-exporting NFS mounts
 - Replace NFSv4 XDR decoding C macros with xdr_stream helpers
 - Support for multiple RPC/RDMA chunks per RPC transaction
 -----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCAAdFiEEKLLlsBKG3yQ88j7+M2qzM29mf5cFAl/Q4dIACgkQM2qzM29m
 f5fInw//eDrmXBEhxbzcgeqNilGU5Qkn4INJtAcOGwPcw5Kjp4UVNGFpZNPqIDSf
 FP0Yw0d/rW7UggwCviPcs/adLTasU9skq1jgAv8d0ig4DtPbeqFo6BvbY+G2JxVF
 EfTeHzr6w6er8HRqyuLN4hjm1rQIpQlDHaYU4QcMs4fjPVv88eYLiwnYGYf3X46i
 vBYstu1IRxHhg2x4O833xmiL6VbkZDQoWwDjGICylxUBcNUtAmq/sETjTa4JVEJj
 4vgXdcJmAFjNgAOrmoR3DISsr9mvCvKN9g3C0+hHiRERTGEon//HzvscWH74wT48
 o0LUW0ZWgpmunTcmiSNeeiHNsUXJyy3A/xyEdteqqnvSxulxlqkQzb15Eb+92+6n
 BHGT/sOz1zz+/l9NCpdeEl5AkSA9plV8Iqd/kzwFwe1KwHMjldeMw/mhMut8EM2j
 b54EMsp40ipITAwBHvcygCXiWAn/mPex6bCr17Dijo6MsNLsyd+cDsazntbNzwz3
 RMGMf2TPOi8tWswrTUS9J5xKk5LAEWX/6Z/hTA1YlsB3PfrhXO97ztrytxvoO/bp
 M0NREA+NNMn/JyyL8FT3ID5peaLVHhA1GHw9CcUw3C7OVzmsEg29D4zNo02dF1TC
 LIyekp0kbSGGY1jLOeMLsa6Jr+2+40CcctsooVkRA+3rN0tJQvw=
 =1uP3
 -----END PGP SIGNATURE-----

Merge tag 'nfsd-5.11' of git://git.linux-nfs.org/projects/cel/cel-2.6

Pull nfsd updates from Chuck Lever:
 "Several substantial changes this time around:

   - Previously, exporting an NFS mount via NFSD was considered to be an
     unsupported feature. With v5.11, the community has attempted to
     make re-exporting a first-class feature of NFSD.

     This would enable the Linux in-kernel NFS server to be used as an
     intermediate cache for a remotely-located primary NFS server, for
     example, even with other NFS server implementations, like a NetApp
     filer, as the primary.

   - A short series of patches brings support for multiple RPC/RDMA data
     chunks per RPC transaction to the Linux NFS server's RPC/RDMA
     transport implementation.

     This is a part of the RPC/RDMA spec that the other premiere
     NFS/RDMA implementation (Solaris) has had for a very long time, and
     completes the implementation of RPC/RDMA version 1 in the Linux
     kernel's NFS server.

   - Long ago, NFSv4 support was introduced to NFSD using a series of C
     macros that hid dprintk's and goto's. Over time, the kernel's XDR
     implementation has been greatly improved, but these C macros have
     remained and become fallow. A series of patches in this pull
     request completely replaces those macros with the use of current
     kernel XDR infrastructure. Benefits include:

       - More robust input sanitization in NFSD's NFSv4 XDR decoders.

       - Make it easier to use common kernel library functions that use
         XDR stream APIs (for example, GSS-API).

       - Align the structure of the source code with the RFCs so it is
         easier to learn, verify, and maintain our XDR implementation.

       - Removal of more than a hundred hidden dprintk() call sites.

       - Removal of some explicit manipulation of pages to help make the
         eventual transition to xdr->bvec smoother.

   - On top of several related fixes in 5.10-rc, there are a few more
     fixes to get the Linux NFSD implementation of NFSv4.2 inter-server
     copy up to speed.

  And as usual, there is a pinch of seasoning in the form of a
  collection of unrelated minor bug fixes and clean-ups.

  Many thanks to all who contributed this time around!"

* tag 'nfsd-5.11' of git://git.linux-nfs.org/projects/cel/cel-2.6: (131 commits)
  nfsd: Record NFSv4 pre/post-op attributes as non-atomic
  nfsd: Set PF_LOCAL_THROTTLE on local filesystems only
  nfsd: Fix up nfsd to ensure that timeout errors don't result in ESTALE
  exportfs: Add a function to return the raw output from fh_to_dentry()
  nfsd: close cached files prior to a REMOVE or RENAME that would replace target
  nfsd: allow filesystems to opt out of subtree checking
  nfsd: add a new EXPORT_OP_NOWCC flag to struct export_operations
  Revert "nfsd4: support change_attr_type attribute"
  nfsd4: don't query change attribute in v2/v3 case
  nfsd: minor nfsd4_change_attribute cleanup
  nfsd: simplify nfsd4_change_info
  nfsd: only call inode_query_iversion in the I_VERSION case
  nfs_common: need lock during iterate through the list
  NFSD: Fix 5 seconds delay when doing inter server copy
  NFSD: Fix sparse warning in nfs4proc.c
  SUNRPC: Remove XDRBUF_SPARSE_PAGES flag in gss_proxy upcall
  sunrpc: clean-up cache downcall
  nfsd: Fix message level for normal termination
  NFSD: Remove macros that are no longer used
  NFSD: Replace READ* macros in nfsd4_decode_compound()
  ...
This commit is contained in:
Linus Torvalds 2020-12-15 18:52:30 -08:00
parent 9867cb1fd5 716a8bc7f7
commit 1a50ede2b3
58 changed files with 3536 additions and 2261 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

52
Documentation/filesystems/nfs/exporting.rst
View File

@ -154,6 +154,11 @@ struct which has the following members:
to find potential names, and matches inode numbers to find the correct
match.
flags
Some filesystems may need to be handled differently than others. The
export_operations struct also includes a flags field that allows the
filesystem to communicate such information to nfsd. See the Export
Operations Flags section below for more explanation.
A filehandle fragment consists of an array of 1 or more 4byte words,
together with a one byte "type".
@ -163,3 +168,50 @@ generated by encode_fh, in which case it will have been padded with
nuls. Rather, the encode_fh routine should choose a "type" which
indicates the decode_fh how much of the filehandle is valid, and how
it should be interpreted.
Export Operations Flags
-----------------------
In addition to the operation vector pointers, struct export_operations also
contains a "flags" field that allows the filesystem to communicate to nfsd
that it may want to do things differently when dealing with it. The
following flags are defined:
EXPORT_OP_NOWCC - disable NFSv3 WCC attributes on this filesystem
RFC 1813 recommends that servers always send weak cache consistency
(WCC) data to the client after each operation. The server should
atomically collect attributes about the inode, do an operation on it,
and then collect the attributes afterward. This allows the client to
skip issuing GETATTRs in some situations but means that the server
is calling vfs_getattr for almost all RPCs. On some filesystems
(particularly those that are clustered or networked) this is expensive
and atomicity is difficult to guarantee. This flag indicates to nfsd
that it should skip providing WCC attributes to the client in NFSv3
replies when doing operations on this filesystem. Consider enabling
this on filesystems that have an expensive ->getattr inode operation,
or when atomicity between pre and post operation attribute collection
is impossible to guarantee.
EXPORT_OP_NOSUBTREECHK - disallow subtree checking on this fs
Many NFS operations deal with filehandles, which the server must then
vet to ensure that they live inside of an exported tree. When the
export consists of an entire filesystem, this is trivial. nfsd can just
ensure that the filehandle live on the filesystem. When only part of a
filesystem is exported however, then nfsd must walk the ancestors of the
inode to ensure that it's within an exported subtree. This is an
expensive operation and not all filesystems can support it properly.
This flag exempts the filesystem from subtree checking and causes
exportfs to get back an error if it tries to enable subtree checking
on it.
EXPORT_OP_CLOSE_BEFORE_UNLINK - always close cached files before unlinking
On some exportable filesystems (such as NFS) unlinking a file that
is still open can cause a fair bit of extra work. For instance,
the NFS client will do a "sillyrename" to ensure that the file
sticks around while it's still open. When reexporting, that open
file is held by nfsd so we usually end up doing a sillyrename, and
then immediately deleting the sillyrenamed file just afterward when
the link count actually goes to zero. Sometimes this delete can race
with other operations (for instance an rmdir of the parent directory).
This flag causes nfsd to close any open files for this inode _before_
calling into the vfs to do an unlink or a rename that would replace
an existing file.

32
fs/exportfs/expfs.c
View File

@ -417,9 +417,11 @@ int exportfs_encode_fh(struct dentry *dentry, struct fid *fid, int *max_len,
}
EXPORT_SYMBOL_GPL(exportfs_encode_fh);
struct dentry *exportfs_decode_fh(struct vfsmount *mnt, struct fid *fid,
int fh_len, int fileid_type,
int (*acceptable)(void *, struct dentry *), void *context)
struct dentry *
exportfs_decode_fh_raw(struct vfsmount *mnt, struct fid *fid, int fh_len,
int fileid_type,
int (*acceptable)(void *, struct dentry *),
void *context)
{
const struct export_operations *nop = mnt->mnt_sb->s_export_op;
struct dentry *result, *alias;
@ -432,10 +434,8 @@ struct dentry *exportfs_decode_fh(struct vfsmount *mnt, struct fid *fid,
if (!nop || !nop->fh_to_dentry)
return ERR_PTR(-ESTALE);
result = nop->fh_to_dentry(mnt->mnt_sb, fid, fh_len, fileid_type);
if (PTR_ERR(result) == -ENOMEM)
return ERR_CAST(result);
if (IS_ERR_OR_NULL(result))
return ERR_PTR(-ESTALE);
return result;
/*
* If no acceptance criteria was specified by caller, a disconnected
@ -561,10 +561,26 @@ struct dentry *exportfs_decode_fh(struct vfsmount *mnt, struct fid *fid,
err_result:
dput(result);
if (err != -ENOMEM)
err = -ESTALE;
return ERR_PTR(err);
}
EXPORT_SYMBOL_GPL(exportfs_decode_fh_raw);
struct dentry *exportfs_decode_fh(struct vfsmount *mnt, struct fid *fid,
int fh_len, int fileid_type,
int (*acceptable)(void *, struct dentry *),
void *context)
{
struct dentry *ret;
ret = exportfs_decode_fh_raw(mnt, fid, fh_len, fileid_type,
acceptable, context);
if (IS_ERR_OR_NULL(ret)) {
if (ret == ERR_PTR(-ENOMEM))
return ret;
return ERR_PTR(-ESTALE);
}
return ret;
}
EXPORT_SYMBOL_GPL(exportfs_decode_fh);
MODULE_LICENSE("GPL");

2
fs/nfs/blocklayout/blocklayout.c
View File

@ -697,7 +697,7 @@ bl_alloc_lseg(struct pnfs_layout_hdr *lo, struct nfs4_layoutget_res *lgr,
xdr_init_decode_pages(&xdr, &buf,
lgr->layoutp->pages, lgr->layoutp->len);
xdr_set_scratch_buffer(&xdr, page_address(scratch), PAGE_SIZE);
xdr_set_scratch_page(&xdr, scratch);
status = -EIO;
p = xdr_inline_decode(&xdr, 4);

2
fs/nfs/blocklayout/dev.c
View File

@ -510,7 +510,7 @@ bl_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,
goto out;
xdr_init_decode_pages(&xdr, &buf, pdev->pages, pdev->pglen);
xdr_set_scratch_buffer(&xdr, page_address(scratch), PAGE_SIZE);
xdr_set_scratch_page(&xdr, scratch);
p = xdr_inline_decode(&xdr, sizeof(__be32));
if (!p)

2
fs/nfs/dir.c
View File

@ -576,7 +576,7 @@ int nfs_readdir_page_filler(nfs_readdir_descriptor_t *desc, struct nfs_entry *en
goto out_nopages;
xdr_init_decode_pages(&stream, &buf, xdr_pages, buflen);
xdr_set_scratch_buffer(&stream, page_address(scratch), PAGE_SIZE);
xdr_set_scratch_page(&stream, scratch);
do {
if (entry->label)

3
fs/nfs/export.c
View File

@ -171,4 +171,7 @@ const struct export_operations nfs_export_ops = {
.encode_fh = nfs_encode_fh,
.fh_to_dentry = nfs_fh_to_dentry,
.get_parent = nfs_get_parent,
.flags = EXPORT_OP_NOWCC|EXPORT_OP_NOSUBTREECHK|
EXPORT_OP_CLOSE_BEFORE_UNLINK|EXPORT_OP_REMOTE_FS|
EXPORT_OP_NOATOMIC_ATTR,
};

2
fs/nfs/filelayout/filelayout.c
View File

@ -666,7 +666,7 @@ filelayout_decode_layout(struct pnfs_layout_hdr *flo,
return -ENOMEM;
xdr_init_decode_pages(&stream, &buf, lgr->layoutp->pages, lgr->layoutp->len);
xdr_set_scratch_buffer(&stream, page_address(scratch), PAGE_SIZE);
xdr_set_scratch_page(&stream, scratch);
/* 20 = ufl_util (4), first_stripe_index (4), pattern_offset (8),
* num_fh (4) */

2
fs/nfs/filelayout/filelayoutdev.c
View File

@ -82,7 +82,7 @@ nfs4_fl_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,
goto out_err;
xdr_init_decode_pages(&stream, &buf, pdev->pages, pdev->pglen);
xdr_set_scratch_buffer(&stream, page_address(scratch), PAGE_SIZE);
xdr_set_scratch_page(&stream, scratch);
/* Get the stripe count (number of stripe index) */
p = xdr_inline_decode(&stream, 4);

2
fs/nfs/flexfilelayout/flexfilelayout.c
View File

@ -378,7 +378,7 @@ ff_layout_alloc_lseg(struct pnfs_layout_hdr *lh,
xdr_init_decode_pages(&stream, &buf, lgr->layoutp->pages,
lgr->layoutp->len);
xdr_set_scratch_buffer(&stream, page_address(scratch), PAGE_SIZE);
xdr_set_scratch_page(&stream, scratch);
/* stripe unit and mirror_array_cnt */
rc = -EIO;

2
fs/nfs/flexfilelayout/flexfilelayoutdev.c
View File

@ -69,7 +69,7 @@ nfs4_ff_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,
INIT_LIST_HEAD(&dsaddrs);
xdr_init_decode_pages(&stream, &buf, pdev->pages, pdev->pglen);
xdr_set_scratch_buffer(&stream, page_address(scratch), PAGE_SIZE);
xdr_set_scratch_page(&stream, scratch);
/* multipath count */
p = xdr_inline_decode(&stream, 4);

2
fs/nfs/nfs42xdr.c
View File

@ -1539,7 +1539,7 @@ static int nfs4_xdr_dec_listxattrs(struct rpc_rqst *rqstp,
struct compound_hdr hdr;
int status;
xdr_set_scratch_buffer(xdr, page_address(res->scratch), PAGE_SIZE);
xdr_set_scratch_page(xdr, res->scratch);
status = decode_compound_hdr(xdr, &hdr);
if (status)

6
fs/nfs/nfs4xdr.c
View File

@ -6403,10 +6403,8 @@ nfs4_xdr_dec_getacl(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
struct compound_hdr hdr;
int status;
if (res->acl_scratch != NULL) {
void *p = page_address(res->acl_scratch);
xdr_set_scratch_buffer(xdr, p, PAGE_SIZE);
}
if (res->acl_scratch != NULL)
xdr_set_scratch_page(xdr, res->acl_scratch);
status = decode_compound_hdr(xdr, &hdr);
if (status)
goto out;

6
fs/nfs_common/grace.c
View File

@ -69,10 +69,14 @@ __state_in_grace(struct net *net, bool open)
if (!open)
return !list_empty(grace_list);
spin_lock(&grace_lock);
list_for_each_entry(lm, grace_list, list) {
if (lm->block_opens)
if (lm->block_opens) {
spin_unlock(&grace_lock);
return true;
}
}
spin_unlock(&grace_lock);
return false;
}

6
fs/nfsd/export.c
View File

@ -408,6 +408,12 @@ static int check_export(struct inode *inode, int *flags, unsigned char *uuid)
return -EINVAL;
}
if (inode->i_sb->s_export_op->flags & EXPORT_OP_NOSUBTREECHK &&
!(*flags & NFSEXP_NOSUBTREECHECK)) {
dprintk("%s: %s does not support subtree checking!\n",
__func__, inode->i_sb->s_type->name);
return -EINVAL;
}
return 0;
}

1
fs/nfsd/filecache.c
View File

@ -685,6 +685,7 @@ nfsd_file_cache_init(void)
if (IS_ERR(nfsd_file_fsnotify_group)) {
pr_err("nfsd: unable to create fsnotify group: %ld\n",
PTR_ERR(nfsd_file_fsnotify_group));
ret = PTR_ERR(nfsd_file_fsnotify_group);
nfsd_file_fsnotify_group = NULL;
goto out_notifier;
}

21
fs/nfsd/nfs2acl.c
View File

@ -185,10 +185,6 @@ out:
/*
* XDR decode functions
*/
static int nfsaclsvc_decode_voidarg(struct svc_rqst *rqstp, __be32 *p)
{
return 1;
}
static int nfsaclsvc_decode_getaclargs(struct svc_rqst *rqstp, __be32 *p)
{
@ -255,15 +251,6 @@ static int nfsaclsvc_decode_accessargs(struct svc_rqst *rqstp, __be32 *p)
* XDR encode functions
*/
/*
* There must be an encoding function for void results so svc_process
* will work properly.
*/
static int nfsaclsvc_encode_voidres(struct svc_rqst *rqstp, __be32 *p)
{
return xdr_ressize_check(rqstp, p);
}
/* GETACL */
static int nfsaclsvc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p)
{
@ -378,10 +365,10 @@ struct nfsd3_voidargs { int dummy; };
static const struct svc_procedure nfsd_acl_procedures2[5] = {
[ACLPROC2_NULL] = {
.pc_func = nfsacld_proc_null,
.pc_decode = nfsaclsvc_decode_voidarg,
.pc_encode = nfsaclsvc_encode_voidres,
.pc_argsize = sizeof(struct nfsd3_voidargs),
.pc_ressize = sizeof(struct nfsd3_voidargs),
.pc_decode = nfssvc_decode_voidarg,
.pc_encode = nfssvc_encode_voidres,
.pc_argsize = sizeof(struct nfsd_voidargs),
.pc_ressize = sizeof(struct nfsd_voidres),
.pc_cachetype = RC_NOCACHE,
.pc_xdrressize = ST,
},

8
fs/nfsd/nfs3acl.c
View File

@ -245,10 +245,10 @@ struct nfsd3_voidargs { int dummy; };
static const struct svc_procedure nfsd_acl_procedures3[3] = {
[ACLPROC3_NULL] = {
.pc_func = nfsd3_proc_null,
.pc_decode = nfs3svc_decode_voidarg,
.pc_encode = nfs3svc_encode_voidres,
.pc_argsize = sizeof(struct nfsd3_voidargs),
.pc_ressize = sizeof(struct nfsd3_voidargs),
.pc_decode = nfssvc_decode_voidarg,
.pc_encode = nfssvc_encode_voidres,
.pc_argsize = sizeof(struct nfsd_voidargs),
.pc_ressize = sizeof(struct nfsd_voidres),
.pc_cachetype = RC_NOCACHE,
.pc_xdrressize = ST,
},

11
fs/nfsd/nfs3proc.c
View File

@ -689,12 +689,9 @@ out:
#define nfsd3_mkdirargs nfsd3_createargs
#define nfsd3_readdirplusargs nfsd3_readdirargs
#define nfsd3_fhandleargs nfsd_fhandle
#define nfsd3_fhandleres nfsd3_attrstat
#define nfsd3_attrstatres nfsd3_attrstat
#define nfsd3_wccstatres nfsd3_attrstat
#define nfsd3_createres nfsd3_diropres
#define nfsd3_voidres nfsd3_voidargs
struct nfsd3_voidargs { int dummy; };
#define ST 1 /* status*/
#define FH 17 /* filehandle with length */
@ -705,10 +702,10 @@ struct nfsd3_voidargs { int dummy; };
static const struct svc_procedure nfsd_procedures3[22] = {
[NFS3PROC_NULL] = {
.pc_func = nfsd3_proc_null,
.pc_decode = nfs3svc_decode_voidarg,
.pc_encode = nfs3svc_encode_voidres,
.pc_argsize = sizeof(struct nfsd3_voidargs),
.pc_ressize = sizeof(struct nfsd3_voidres),
.pc_decode = nfssvc_decode_voidarg,
.pc_encode = nfssvc_encode_voidres,
.pc_argsize = sizeof(struct nfsd_voidargs),
.pc_ressize = sizeof(struct nfsd_voidres),
.pc_cachetype = RC_NOCACHE,
.pc_xdrressize = ST,
},

40
fs/nfsd/nfs3xdr.c
View File

@ -206,7 +206,7 @@ static __be32 *
encode_post_op_attr(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp)
{
struct dentry *dentry = fhp->fh_dentry;
if (dentry && d_really_is_positive(dentry)) {
if (!fhp->fh_no_wcc && dentry && d_really_is_positive(dentry)) {
__be32 err;
struct kstat stat;
@ -259,11 +259,11 @@ void fill_pre_wcc(struct svc_fh *fhp)
{
struct inode *inode;
struct kstat stat;
bool v4 = (fhp->fh_maxsize == NFS4_FHSIZE);
__be32 err;
if (fhp->fh_pre_saved)
if (fhp->fh_no_wcc || fhp->fh_pre_saved)
return;
inode = d_inode(fhp->fh_dentry);
err = fh_getattr(fhp, &stat);
if (err) {
@ -272,11 +272,12 @@ void fill_pre_wcc(struct svc_fh *fhp)
stat.ctime = inode->i_ctime;
stat.size = inode->i_size;
}
if (v4)
fhp->fh_pre_change = nfsd4_change_attribute(&stat, inode);
fhp->fh_pre_mtime = stat.mtime;
fhp->fh_pre_ctime = stat.ctime;
fhp->fh_pre_size = stat.size;
fhp->fh_pre_change = nfsd4_change_attribute(&stat, inode);
fhp->fh_pre_saved = true;
}
@ -285,30 +286,30 @@ void fill_pre_wcc(struct svc_fh *fhp)
*/
void fill_post_wcc(struct svc_fh *fhp)
{
bool v4 = (fhp->fh_maxsize == NFS4_FHSIZE);
struct inode *inode = d_inode(fhp->fh_dentry);
__be32 err;
if (fhp->fh_no_wcc)
return;
if (fhp->fh_post_saved)
printk("nfsd: inode locked twice during operation.\n");
err = fh_getattr(fhp, &fhp->fh_post_attr);
fhp->fh_post_change = nfsd4_change_attribute(&fhp->fh_post_attr,
d_inode(fhp->fh_dentry));
if (err) {
fhp->fh_post_saved = false;
/* Grab the ctime anyway - set_change_info might use it */
fhp->fh_post_attr.ctime = d_inode(fhp->fh_dentry)->i_ctime;
fhp->fh_post_attr.ctime = inode->i_ctime;
} else
fhp->fh_post_saved = true;
if (v4)
fhp->fh_post_change =
nfsd4_change_attribute(&fhp->fh_post_attr, inode);
}
/*
* XDR decode functions
*/
int
nfs3svc_decode_voidarg(struct svc_rqst *rqstp, __be32 *p)
{
return 1;
}
int
nfs3svc_decode_fhandle(struct svc_rqst *rqstp, __be32 *p)
@ -642,12 +643,6 @@ nfs3svc_decode_commitargs(struct svc_rqst *rqstp, __be32 *p)
* XDR encode functions
*/
int
nfs3svc_encode_voidres(struct svc_rqst *rqstp, __be32 *p)
{
return xdr_ressize_check(rqstp, p);
}
/* GETATTR */
int
nfs3svc_encode_attrstat(struct svc_rqst *rqstp, __be32 *p)
@ -707,6 +702,7 @@ int
nfs3svc_encode_readlinkres(struct svc_rqst *rqstp, __be32 *p)
{
struct nfsd3_readlinkres *resp = rqstp->rq_resp;
struct kvec *head = rqstp->rq_res.head;
*p++ = resp->status;
p = encode_post_op_attr(rqstp, p, &resp->fh);
@ -720,6 +716,8 @@ nfs3svc_encode_readlinkres(struct svc_rqst *rqstp, __be32 *p)
*p = 0;
rqstp->rq_res.tail[0].iov_len = 4 - (resp->len&3);
}
if (svc_encode_result_payload(rqstp, head->iov_len, resp->len))
return 0;
return 1;
} else
return xdr_ressize_check(rqstp, p);
@ -730,6 +728,7 @@ int
nfs3svc_encode_readres(struct svc_rqst *rqstp, __be32 *p)
{
struct nfsd3_readres *resp = rqstp->rq_resp;
struct kvec *head = rqstp->rq_res.head;
*p++ = resp->status;
p = encode_post_op_attr(rqstp, p, &resp->fh);
@ -746,6 +745,9 @@ nfs3svc_encode_readres(struct svc_rqst *rqstp, __be32 *p)
*p = 0;
rqstp->rq_res.tail[0].iov_len = 4 - (resp->count & 3);
}
if (svc_encode_result_payload(rqstp, head->iov_len,
resp->count))
return 0;
return 1;
} else
return xdr_ressize_check(rqstp, p);

35
fs/nfsd/nfs4proc.c
View File

@ -257,8 +257,8 @@ do_open_lookup(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, stru
* in NFSv4 as in v3 except EXCLUSIVE4_1.
*/
current->fs->umask = open->op_umask;
status = do_nfsd_create(rqstp, current_fh, open->op_fname.data,
open->op_fname.len, &open->op_iattr,
status = do_nfsd_create(rqstp, current_fh, open->op_fname,
open->op_fnamelen, &open->op_iattr,
*resfh, open->op_createmode,
(u32 *)open->op_verf.data,
&open->op_truncate, &open->op_created);
@ -283,7 +283,7 @@ do_open_lookup(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, stru
* a chance to an acquire a delegation if appropriate.
*/
status = nfsd_lookup(rqstp, current_fh,
open->op_fname.data, open->op_fname.len, *resfh);
open->op_fname, open->op_fnamelen, *resfh);
if (status)
goto out;
status = nfsd_check_obj_isreg(*resfh);
@ -360,7 +360,7 @@ nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
bool reclaim = false;
dprintk("NFSD: nfsd4_open filename %.*s op_openowner %p\n",
(int)open->op_fname.len, open->op_fname.data,
(int)open->op_fnamelen, open->op_fname,
open->op_openowner);
/* This check required by spec. */
@ -1023,8 +1023,8 @@ nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
write->wr_how_written = write->wr_stable_how;
nvecs = svc_fill_write_vector(rqstp, write->wr_pagelist,
&write->wr_head, write->wr_buflen);
nvecs = svc_fill_write_vector(rqstp, write->wr_payload.pages,
write->wr_payload.head, write->wr_buflen);
WARN_ON_ONCE(nvecs > ARRAY_SIZE(rqstp->rq_vec));
status = nfsd_vfs_write(rqstp, &cstate->current_fh, nf,
@ -1425,7 +1425,7 @@ static __be32 nfsd4_do_copy(struct nfsd4_copy *copy, bool sync)
return status;
}
static int dup_copy_fields(struct nfsd4_copy *src, struct nfsd4_copy *dst)
static void dup_copy_fields(struct nfsd4_copy *src, struct nfsd4_copy *dst)
{
dst->cp_src_pos = src->cp_src_pos;
dst->cp_dst_pos = src->cp_dst_pos;
@ -1444,8 +1444,6 @@ static int dup_copy_fields(struct nfsd4_copy *src, struct nfsd4_copy *dst)
memcpy(&dst->stateid, &src->stateid, sizeof(src->stateid));
memcpy(&dst->c_fh, &src->c_fh, sizeof(src->c_fh));
dst->ss_mnt = src->ss_mnt;
return 0;
}
static void cleanup_async_copy(struct nfsd4_copy *copy)
@ -1539,9 +1537,7 @@ nfsd4_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
refcount_set(&async_copy->refcount, 1);
memcpy(&copy->cp_res.cb_stateid, &copy->cp_stateid,
sizeof(copy->cp_stateid));
status = dup_copy_fields(copy, async_copy);
if (status)
goto out_err;
dup_copy_fields(copy, async_copy);
async_copy->copy_task = kthread_create(nfsd4_do_async_copy,
async_copy, "%s", "copy thread");
if (IS_ERR(async_copy->copy_task))
@ -2276,7 +2272,7 @@ static void svcxdr_init_encode(struct svc_rqst *rqstp,
xdr->end = head->iov_base + PAGE_SIZE - rqstp->rq_auth_slack;
/* Tail and page_len should be zero at this point: */
buf->len = buf->head[0].iov_len;
xdr->scratch.iov_len = 0;
xdr_reset_scratch_buffer(xdr);
xdr->page_ptr = buf->pages - 1;
buf->buflen = PAGE_SIZE * (1 + rqstp->rq_page_end - buf->pages)
- rqstp->rq_auth_slack;
@ -3282,7 +3278,7 @@ int nfsd4_max_reply(struct svc_rqst *rqstp, struct nfsd4_op *op)
void warn_on_nonidempotent_op(struct nfsd4_op *op)
{
if (OPDESC(op)->op_flags & OP_MODIFIES_SOMETHING) {
pr_err("unable to encode reply to nonidempotent op %d (%s)\n",
pr_err("unable to encode reply to nonidempotent op %u (%s)\n",
op->opnum, nfsd4_op_name(op->opnum));
WARN_ON_ONCE(1);
}
@ -3295,16 +3291,13 @@ static const char *nfsd4_op_name(unsigned opnum)
return "unknown_operation";
}
#define nfsd4_voidres nfsd4_voidargs
struct nfsd4_voidargs { int dummy; };
static const struct svc_procedure nfsd_procedures4[2] = {
[NFSPROC4_NULL] = {
.pc_func = nfsd4_proc_null,
.pc_decode = nfs4svc_decode_voidarg,
.pc_encode = nfs4svc_encode_voidres,
.pc_argsize = sizeof(struct nfsd4_voidargs),
.pc_ressize = sizeof(struct nfsd4_voidres),
.pc_decode = nfssvc_decode_voidarg,
.pc_encode = nfssvc_encode_voidres,
.pc_argsize = sizeof(struct nfsd_voidargs),
.pc_ressize = sizeof(struct nfsd_voidres),
.pc_cachetype = RC_NOCACHE,
.pc_xdrressize = 1,
},

3
fs/nfsd/nfs4state.c
View File

@ -769,6 +769,7 @@ static int nfs4_init_cp_state(struct nfsd_net *nn, copy_stateid_t *stid,
spin_lock(&nn->s2s_cp_lock);
new_id = idr_alloc_cyclic(&nn->s2s_cp_stateids, stid, 0, 0, GFP_NOWAIT);
stid->stid.si_opaque.so_id = new_id;
stid->stid.si_generation = 1;
spin_unlock(&nn->s2s_cp_lock);
idr_preload_end();
if (new_id < 0)
@ -3066,7 +3067,7 @@ nfsd4_exchange_id(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
rpc_ntop(sa, addr_str, sizeof(addr_str));
dprintk("%s rqstp=%p exid=%p clname.len=%u clname.data=%p "
"ip_addr=%s flags %x, spa_how %d\n",
"ip_addr=%s flags %x, spa_how %u\n",
__func__, rqstp, exid, exid->clname.len, exid->clname.data,
addr_str, exid->flags, exid->spa_how);

2665
fs/nfsd/nfs4xdr.c
View File

File diff suppressed because it is too large Load Diff

9
fs/nfsd/nfsd.h
View File

@ -73,6 +73,14 @@ extern unsigned long nfsd_drc_mem_used;
extern const struct seq_operations nfs_exports_op;
/*
* Common void argument and result helpers
*/
struct nfsd_voidargs { };
struct nfsd_voidres { };
int nfssvc_decode_voidarg(struct svc_rqst *rqstp, __be32 *p);
int nfssvc_encode_voidres(struct svc_rqst *rqstp, __be32 *p);
/*
* Function prototypes.
*/
@ -387,7 +395,6 @@ void nfsd_lockd_shutdown(void);
#define NFSD4_2_SUPPORTED_ATTRS_WORD2 \
(NFSD4_1_SUPPORTED_ATTRS_WORD2 | \
FATTR4_WORD2_CHANGE_ATTR_TYPE | \
FATTR4_WORD2_MODE_UMASK | \
NFSD4_2_SECURITY_ATTRS | \
FATTR4_WORD2_XATTR_SUPPORT)

34
fs/nfsd/nfsfh.c
View File

@ -268,12 +268,20 @@ static __be32 nfsd_set_fh_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp)
if (fileid_type == FILEID_ROOT)
dentry = dget(exp->ex_path.dentry);
else {
dentry = exportfs_decode_fh(exp->ex_path.mnt, fid,
data_left, fileid_type,
nfsd_acceptable, exp);
if (IS_ERR_OR_NULL(dentry))
dentry = exportfs_decode_fh_raw(exp->ex_path.mnt, fid,
data_left, fileid_type,
nfsd_acceptable, exp);
if (IS_ERR_OR_NULL(dentry)) {
trace_nfsd_set_fh_dentry_badhandle(rqstp, fhp,
dentry ? PTR_ERR(dentry) : -ESTALE);
switch (PTR_ERR(dentry)) {
case -ENOMEM:
case -ETIMEDOUT:
break;
default:
dentry = ERR_PTR(-ESTALE);
}
}
}
if (dentry == NULL)
goto out;
@ -291,6 +299,20 @@ static __be32 nfsd_set_fh_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp)
fhp->fh_dentry = dentry;
fhp->fh_export = exp;
switch (rqstp->rq_vers) {
case 4:
if (dentry->d_sb->s_export_op->flags & EXPORT_OP_NOATOMIC_ATTR)
fhp->fh_no_atomic_attr = true;
break;
case 3:
if (dentry->d_sb->s_export_op->flags & EXPORT_OP_NOWCC)
fhp->fh_no_wcc = true;
break;
case 2:
fhp->fh_no_wcc = true;
}
return 0;
out:
exp_put(exp);
@ -559,6 +581,9 @@ fh_compose(struct svc_fh *fhp, struct svc_export *exp, struct dentry *dentry,
*/
set_version_and_fsid_type(fhp, exp, ref_fh);
/* If we have a ref_fh, then copy the fh_no_wcc setting from it. */
fhp->fh_no_wcc = ref_fh ? ref_fh->fh_no_wcc : false;
if (ref_fh == fhp)
fh_put(ref_fh);
@ -662,6 +687,7 @@ fh_put(struct svc_fh *fhp)
exp_put(exp);
fhp->fh_export = NULL;
}
fhp->fh_no_wcc = false;
return;
}

22
fs/nfsd/nfsfh.h
View File

@ -35,6 +35,12 @@ typedef struct svc_fh {
bool fh_locked; /* inode locked by us */
bool fh_want_write; /* remount protection taken */
bool fh_no_wcc; /* no wcc data needed */
bool fh_no_atomic_attr;
/*
* wcc data is not atomic with
* operation
*/
int fh_flags; /* FH flags */
#ifdef CONFIG_NFSD_V3
bool fh_post_saved; /* post-op attrs saved */
@ -54,7 +60,6 @@ typedef struct svc_fh {
struct kstat fh_post_attr; /* full attrs after operation */
u64 fh_post_change; /* nfsv4 change; see above */
#endif /* CONFIG_NFSD_V3 */
} svc_fh;
#define NFSD4_FH_FOREIGN (1<<0)
#define SET_FH_FLAG(c, f) ((c)->fh_flags |= (f))
@ -259,13 +264,16 @@ fh_clear_wcc(struct svc_fh *fhp)
static inline u64 nfsd4_change_attribute(struct kstat *stat,
struct inode *inode)
{
u64 chattr;
if (IS_I_VERSION(inode)) {
u64 chattr;
chattr = stat->ctime.tv_sec;
chattr <<= 30;
chattr += stat->ctime.tv_nsec;
chattr += inode_query_iversion(inode);
return chattr;
chattr = stat->ctime.tv_sec;
chattr <<= 30;
chattr += stat->ctime.tv_nsec;
chattr += inode_query_iversion(inode);
return chattr;
} else
return time_to_chattr(&stat->ctime);
}
extern void fill_pre_wcc(struct svc_fh *fhp);

25
fs/nfsd/nfsproc.c
View File

@ -609,7 +609,6 @@ nfsd_proc_statfs(struct svc_rqst *rqstp)
* NFSv2 Server procedures.
* Only the results of non-idempotent operations are cached.
*/
struct nfsd_void { int dummy; };
#define ST 1 /* status */
#define FH 8 /* filehandle */
@ -618,10 +617,10 @@ struct nfsd_void { int dummy; };
static const struct svc_procedure nfsd_procedures2[18] = {
[NFSPROC_NULL] = {
.pc_func = nfsd_proc_null,
.pc_decode = nfssvc_decode_void,
.pc_encode = nfssvc_encode_void,
.pc_argsize = sizeof(struct nfsd_void),
.pc_ressize = sizeof(struct nfsd_void),
.pc_decode = nfssvc_decode_voidarg,
.pc_encode = nfssvc_encode_voidres,
.pc_argsize = sizeof(struct nfsd_voidargs),
.pc_ressize = sizeof(struct nfsd_voidres),
.pc_cachetype = RC_NOCACHE,
.pc_xdrressize = 0,
},
@ -647,10 +646,10 @@ static const struct svc_procedure nfsd_procedures2[18] = {
},
[NFSPROC_ROOT] = {
.pc_func = nfsd_proc_root,
.pc_decode = nfssvc_decode_void,
.pc_encode = nfssvc_encode_void,
.pc_argsize = sizeof(struct nfsd_void),
.pc_ressize = sizeof(struct nfsd_void),
.pc_decode = nfssvc_decode_voidarg,
.pc_encode = nfssvc_encode_voidres,
.pc_argsize = sizeof(struct nfsd_voidargs),
.pc_ressize = sizeof(struct nfsd_voidres),
.pc_cachetype = RC_NOCACHE,
.pc_xdrressize = 0,
},
@ -685,10 +684,10 @@ static const struct svc_procedure nfsd_procedures2[18] = {
},
[NFSPROC_WRITECACHE] = {
.pc_func = nfsd_proc_writecache,
.pc_decode = nfssvc_decode_void,
.pc_encode = nfssvc_encode_void,
.pc_argsize = sizeof(struct nfsd_void),
.pc_ressize = sizeof(struct nfsd_void),
.pc_decode = nfssvc_decode_voidarg,
.pc_encode = nfssvc_encode_voidres,
.pc_argsize = sizeof(struct nfsd_voidargs),
.pc_ressize = sizeof(struct nfsd_voidres),
.pc_cachetype = RC_NOCACHE,
.pc_xdrressize = 0,
},

50
fs/nfsd/nfssvc.c
View File

@ -29,6 +29,8 @@
#include "netns.h"
#include "filecache.h"
#include "trace.h"
#define NFSDDBG_FACILITY NFSDDBG_SVC
bool inter_copy_offload_enable;
@ -527,8 +529,7 @@ static void nfsd_last_thread(struct svc_serv *serv, struct net *net)
return;
nfsd_shutdown_net(net);
printk(KERN_WARNING "nfsd: last server has exited, flushing export "
"cache\n");
pr_info("nfsd: last server has exited, flushing export cache\n");
nfsd_export_flush(net);
}
@ -1009,17 +1010,16 @@ int nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp)
struct kvec *resv = &rqstp->rq_res.head[0];
__be32 *p;
dprintk("nfsd_dispatch: vers %d proc %d\n",
rqstp->rq_vers, rqstp->rq_proc);
if (nfs_request_too_big(rqstp, proc))
goto out_too_large;
goto out_decode_err;
/*
* Give the xdr decoder a chance to change this if it wants
* (necessary in the NFSv4.0 compound case)
*/
rqstp->rq_cachetype = proc->pc_cachetype;
svcxdr_init_decode(rqstp);
if (!proc->pc_decode(rqstp, argv->iov_base))
goto out_decode_err;
@ -1050,29 +1050,51 @@ int nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp)
out_cached_reply:
return 1;
out_too_large:
dprintk("nfsd: NFSv%d argument too large\n", rqstp->rq_vers);
*statp = rpc_garbage_args;
return 1;
out_decode_err:
dprintk("nfsd: failed to decode arguments!\n");
trace_nfsd_garbage_args_err(rqstp);
*statp = rpc_garbage_args;
return 1;
out_update_drop:
dprintk("nfsd: Dropping request; may be revisited later\n");
nfsd_cache_update(rqstp, RC_NOCACHE, NULL);
out_dropit:
return 0;
out_encode_err:
dprintk("nfsd: failed to encode result!\n");
trace_nfsd_cant_encode_err(rqstp);
nfsd_cache_update(rqstp, RC_NOCACHE, NULL);
*statp = rpc_system_err;
return 1;
}
/**
* nfssvc_decode_voidarg - Decode void arguments
* @rqstp: Server RPC transaction context
* @p: buffer containing arguments to decode
*
* Return values:
* %0: Arguments were not valid
* %1: Decoding was successful
*/
int nfssvc_decode_voidarg(struct svc_rqst *rqstp, __be32 *p)
{
return 1;
}
/**
* nfssvc_encode_voidres - Encode void results
* @rqstp: Server RPC transaction context
* @p: buffer in which to encode results
*
* Return values:
* %0: Local error while encoding
* %1: Encoding was successful
*/
int nfssvc_encode_voidres(struct svc_rqst *rqstp, __be32 *p)
{
return xdr_ressize_check(rqstp, p);
}
int nfsd_pool_stats_open(struct inode *inode, struct file *file)
{
int ret;

16
fs/nfsd/nfsxdr.c
View File

@ -192,11 +192,6 @@ __be32 *nfs2svc_encode_fattr(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *f
/*
* XDR decode functions
*/
int
nfssvc_decode_void(struct svc_rqst *rqstp, __be32 *p)
{
return xdr_argsize_check(rqstp, p);
}
int
nfssvc_decode_fhandle(struct svc_rqst *rqstp, __be32 *p)
@ -423,11 +418,6 @@ nfssvc_decode_readdirargs(struct svc_rqst *rqstp, __be32 *p)
/*
* XDR encode functions
*/
int
nfssvc_encode_void(struct svc_rqst *rqstp, __be32 *p)
{
return xdr_ressize_check(rqstp, p);
}
int
nfssvc_encode_stat(struct svc_rqst *rqstp, __be32 *p)
@ -469,6 +459,7 @@ int
nfssvc_encode_readlinkres(struct svc_rqst *rqstp, __be32 *p)
{
struct nfsd_readlinkres *resp = rqstp->rq_resp;
struct kvec *head = rqstp->rq_res.head;
*p++ = resp->status;
if (resp->status != nfs_ok)
@ -483,6 +474,8 @@ nfssvc_encode_readlinkres(struct svc_rqst *rqstp, __be32 *p)
*p = 0;
rqstp->rq_res.tail[0].iov_len = 4 - (resp->len&3);
}
if (svc_encode_result_payload(rqstp, head->iov_len, resp->len))
return 0;
return 1;
}
@ -490,6 +483,7 @@ int
nfssvc_encode_readres(struct svc_rqst *rqstp, __be32 *p)
{
struct nfsd_readres *resp = rqstp->rq_resp;
struct kvec *head = rqstp->rq_res.head;
*p++ = resp->status;
if (resp->status != nfs_ok)
@ -507,6 +501,8 @@ nfssvc_encode_readres(struct svc_rqst *rqstp, __be32 *p)
*p = 0;
rqstp->rq_res.tail[0].iov_len = 4 - (resp->count&3);
}
if (svc_encode_result_payload(rqstp, head->iov_len, resp->count))
return 0;
return 1;
}

1
fs/nfsd/trace.c
View File

@ -1,3 +1,4 @@
// SPDX-License-Identifier: GPL-2.0
#define CREATE_TRACE_POINTS
#include "trace.h"

176
fs/nfsd/trace.h
View File

@ -12,6 +12,100 @@
#include "export.h"
#include "nfsfh.h"
#define NFSD_TRACE_PROC_ARG_FIELDS \
__field(unsigned int, netns_ino) \
__field(u32, xid) \
__array(unsigned char, server, sizeof(struct sockaddr_in6)) \
__array(unsigned char, client, sizeof(struct sockaddr_in6))
#define NFSD_TRACE_PROC_ARG_ASSIGNMENTS \
do { \
__entry->netns_ino = SVC_NET(rqstp)->ns.inum; \
__entry->xid = be32_to_cpu(rqstp->rq_xid); \
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); \
} while (0);
#define NFSD_TRACE_PROC_RES_FIELDS \
__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))
#define NFSD_TRACE_PROC_RES_ASSIGNMENTS(error) \
do { \
__entry->netns_ino = SVC_NET(rqstp)->ns.inum; \
__entry->xid = be32_to_cpu(rqstp->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); \
} while (0);
TRACE_EVENT(nfsd_garbage_args_err,
TP_PROTO(
const struct svc_rqst *rqstp
),
TP_ARGS(rqstp),
TP_STRUCT__entry(
NFSD_TRACE_PROC_ARG_FIELDS
__field(u32, vers)
__field(u32, proc)
),
TP_fast_assign(
NFSD_TRACE_PROC_ARG_ASSIGNMENTS
__entry->vers = rqstp->rq_vers;
__entry->proc = rqstp->rq_proc;
),
TP_printk("xid=0x%08x vers=%u proc=%u",
__entry->xid, __entry->vers, __entry->proc
)
);
TRACE_EVENT(nfsd_cant_encode_err,
TP_PROTO(
const struct svc_rqst *rqstp
),
TP_ARGS(rqstp),
TP_STRUCT__entry(
NFSD_TRACE_PROC_ARG_FIELDS
__field(u32, vers)
__field(u32, proc)
),
TP_fast_assign(
NFSD_TRACE_PROC_ARG_ASSIGNMENTS
__entry->vers = rqstp->rq_vers;
__entry->proc = rqstp->rq_proc;
),
TP_printk("xid=0x%08x vers=%u proc=%u",
__entry->xid, __entry->vers, __entry->proc
)
);
#define show_nfsd_may_flags(x) \
__print_flags(x, "|", \
{ NFSD_MAY_EXEC, "EXEC" }, \
{ NFSD_MAY_WRITE, "WRITE" }, \
{ NFSD_MAY_READ, "READ" }, \
{ NFSD_MAY_SATTR, "SATTR" }, \
{ NFSD_MAY_TRUNC, "TRUNC" }, \
{ NFSD_MAY_LOCK, "LOCK" }, \
{ NFSD_MAY_OWNER_OVERRIDE, "OWNER_OVERRIDE" }, \
{ NFSD_MAY_LOCAL_ACCESS, "LOCAL_ACCESS" }, \
{ NFSD_MAY_BYPASS_GSS_ON_ROOT, "BYPASS_GSS_ON_ROOT" }, \
{ NFSD_MAY_NOT_BREAK_LEASE, "NOT_BREAK_LEASE" }, \
{ NFSD_MAY_BYPASS_GSS, "BYPASS_GSS" }, \
{ NFSD_MAY_READ_IF_EXEC, "READ_IF_EXEC" }, \
{ NFSD_MAY_64BIT_COOKIE, "64BIT_COOKIE" })
TRACE_EVENT(nfsd_compound,
TP_PROTO(const struct svc_rqst *rqst,
u32 args_opcnt),
@ -51,6 +145,56 @@ TRACE_EVENT(nfsd_compound_status,
__get_str(name), __entry->status)
)
TRACE_EVENT(nfsd_compound_decode_err,
TP_PROTO(
const struct svc_rqst *rqstp,
u32 args_opcnt,
u32 resp_opcnt,
u32 opnum,
__be32 status
),
TP_ARGS(rqstp, args_opcnt, resp_opcnt, opnum, status),
TP_STRUCT__entry(
NFSD_TRACE_PROC_RES_FIELDS
__field(u32, args_opcnt)
__field(u32, resp_opcnt)
__field(u32, opnum)
),
TP_fast_assign(
NFSD_TRACE_PROC_RES_ASSIGNMENTS(status)
__entry->args_opcnt = args_opcnt;
__entry->resp_opcnt = resp_opcnt;
__entry->opnum = opnum;
),
TP_printk("op=%u/%u opnum=%u status=%lu",
__entry->resp_opcnt, __entry->args_opcnt,
__entry->opnum, __entry->status)
);
TRACE_EVENT(nfsd_compound_encode_err,
TP_PROTO(
const struct svc_rqst *rqstp,
u32 opnum,
__be32 status
),
TP_ARGS(rqstp, opnum, status),
TP_STRUCT__entry(
NFSD_TRACE_PROC_RES_FIELDS
__field(u32, opnum)
),
TP_fast_assign(
NFSD_TRACE_PROC_RES_ASSIGNMENTS(status)
__entry->opnum = opnum;
),
TP_printk("opnum=%u status=%lu",
__entry->opnum, __entry->status)
);
DECLARE_EVENT_CLASS(nfsd_fh_err_class,
TP_PROTO(struct svc_rqst *rqstp,
struct svc_fh *fhp,
@ -421,6 +565,9 @@ TRACE_EVENT(nfsd_clid_inuse_err,
__entry->cl_boot, __entry->cl_id)
)
/*
* from fs/nfsd/filecache.h
*/
TRACE_DEFINE_ENUM(NFSD_FILE_HASHED);
TRACE_DEFINE_ENUM(NFSD_FILE_PENDING);
TRACE_DEFINE_ENUM(NFSD_FILE_BREAK_READ);
@ -435,13 +582,6 @@ TRACE_DEFINE_ENUM(NFSD_FILE_REFERENCED);
{ 1 << NFSD_FILE_BREAK_WRITE, "BREAK_WRITE" }, \
{ 1 << NFSD_FILE_REFERENCED, "REFERENCED"})
/* FIXME: This should probably be fleshed out in the future. */
#define show_nf_may(val) \
__print_flags(val, "|", \
{ NFSD_MAY_READ, "READ" }, \
{ NFSD_MAY_WRITE, "WRITE" }, \
{ NFSD_MAY_NOT_BREAK_LEASE, "NOT_BREAK_LEASE" })
DECLARE_EVENT_CLASS(nfsd_file_class,
TP_PROTO(struct nfsd_file *nf),
TP_ARGS(nf),
@ -461,12 +601,12 @@ DECLARE_EVENT_CLASS(nfsd_file_class,
__entry->nf_may = nf->nf_may;
__entry->nf_file = nf->nf_file;
),
TP_printk("hash=0x%x inode=0x%p ref=%d flags=%s may=%s file=%p",
TP_printk("hash=0x%x inode=%p ref=%d flags=%s may=%s file=%p",
__entry->nf_hashval,
__entry->nf_inode,
__entry->nf_ref,
show_nf_flags(__entry->nf_flags),
show_nf_may(__entry->nf_may),
show_nfsd_may_flags(__entry->nf_may),
__entry->nf_file)
)
@ -492,10 +632,10 @@ TRACE_EVENT(nfsd_file_acquire,
__field(u32, xid)
__field(unsigned int, hash)
__field(void *, inode)
__field(unsigned int, may_flags)
__field(unsigned long, may_flags)
__field(int, nf_ref)
__field(unsigned long, nf_flags)
__field(unsigned char, nf_may)
__field(unsigned long, nf_may)
__field(struct file *, nf_file)
__field(u32, status)
),
@ -512,12 +652,12 @@ TRACE_EVENT(nfsd_file_acquire,
__entry->status = be32_to_cpu(status);
),
TP_printk("xid=0x%x hash=0x%x inode=0x%p may_flags=%s ref=%d nf_flags=%s nf_may=%s nf_file=0x%p status=%u",
TP_printk("xid=0x%x hash=0x%x inode=%p may_flags=%s ref=%d nf_flags=%s nf_may=%s nf_file=%p status=%u",
__entry->xid, __entry->hash, __entry->inode,
show_nf_may(__entry->may_flags), __entry->nf_ref,
show_nf_flags(__entry->nf_flags),
show_nf_may(__entry->nf_may), __entry->nf_file,
__entry->status)
show_nfsd_may_flags(__entry->may_flags),
__entry->nf_ref, show_nf_flags(__entry->nf_flags),
show_nfsd_may_flags(__entry->nf_may),
__entry->nf_file, __entry->status)
);
DECLARE_EVENT_CLASS(nfsd_file_search_class,
@ -533,7 +673,7 @@ DECLARE_EVENT_CLASS(nfsd_file_search_class,
__entry->hash = hash;
__entry->found = found;
),
TP_printk("hash=0x%x inode=0x%p found=%d", __entry->hash,
TP_printk("hash=0x%x inode=%p found=%d", __entry->hash,
__entry->inode, __entry->found)
);
@ -561,7 +701,7 @@ TRACE_EVENT(nfsd_file_fsnotify_handle_event,
__entry->mode = inode->i_mode;
__entry->mask = mask;
),
TP_printk("inode=0x%p nlink=%u mode=0%ho mask=0x%x", __entry->inode,
TP_printk("inode=%p nlink=%u mode=0%ho mask=0x%x", __entry->inode,
__entry->nlink, __entry->mode, __entry->mask)
);

29
fs/nfsd/vfs.c
View File

@ -978,18 +978,25 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct nfsd_file *nf,
__be32 *verf)
{
struct file *file = nf->nf_file;
struct super_block *sb = file_inode(file)->i_sb;
struct svc_export *exp;
struct iov_iter iter;
__be32 nfserr;
int host_err;
int use_wgather;
loff_t pos = offset;
unsigned long exp_op_flags = 0;
unsigned int pflags = current->flags;
rwf_t flags = 0;
bool restore_flags = false;
trace_nfsd_write_opened(rqstp, fhp, offset, *cnt);
if (test_bit(RQ_LOCAL, &rqstp->rq_flags))
if (sb->s_export_op)
exp_op_flags = sb->s_export_op->flags;
if (test_bit(RQ_LOCAL, &rqstp->rq_flags) &&
!(exp_op_flags & EXPORT_OP_REMOTE_FS)) {
/*
* We want throttling in balance_dirty_pages()
* and shrink_inactive_list() to only consider
@ -998,6 +1005,8 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct nfsd_file *nf,
* the client's dirty pages or its congested queue.
*/
current->flags |= PF_LOCAL_THROTTLE;
restore_flags = true;
}
exp = fhp->fh_export;
use_wgather = (rqstp->rq_vers == 2) && EX_WGATHER(exp);
@ -1049,7 +1058,7 @@ out_nfserr:
trace_nfsd_write_err(rqstp, fhp, offset, host_err);
nfserr = nfserrno(host_err);
}
if (test_bit(RQ_LOCAL, &rqstp->rq_flags))
if (restore_flags)
current_restore_flags(pflags, PF_LOCAL_THROTTLE);
return nfserr;
}
@ -1724,7 +1733,7 @@ nfsd_rename(struct svc_rqst *rqstp, struct svc_fh *ffhp, char *fname, int flen,
struct inode *fdir, *tdir;
__be32 err;
int host_err;
bool has_cached = false;
bool close_cached = false;
err = fh_verify(rqstp, ffhp, S_IFDIR, NFSD_MAY_REMOVE);
if (err)
@ -1783,8 +1792,9 @@ retry:
if (ffhp->fh_export->ex_path.dentry != tfhp->fh_export->ex_path.dentry)
goto out_dput_new;
if (nfsd_has_cached_files(ndentry)) {
has_cached = true;
if ((ndentry->d_sb->s_export_op->flags & EXPORT_OP_CLOSE_BEFORE_UNLINK) &&
nfsd_has_cached_files(ndentry)) {
close_cached = true;
goto out_dput_old;
} else {
host_err = vfs_rename(fdir, odentry, tdir, ndentry, NULL, 0);
@ -1805,7 +1815,7 @@ retry:
* as that would do the wrong thing if the two directories
* were the same, so again we do it by hand.
*/
if (!has_cached) {
if (!close_cached) {
fill_post_wcc(ffhp);
fill_post_wcc(tfhp);
}
@ -1819,8 +1829,8 @@ retry:
* shouldn't be done with locks held however, so we delay it until this
* point and then reattempt the whole shebang.
*/
if (has_cached) {
has_cached = false;
if (close_cached) {
close_cached = false;
nfsd_close_cached_files(ndentry);
dput(ndentry);
goto retry;
@ -1872,7 +1882,8 @@ nfsd_unlink(struct svc_rqst *rqstp, struct svc_fh *fhp, int type,
type = d_inode(rdentry)->i_mode & S_IFMT;
if (type != S_IFDIR) {
nfsd_close_cached_files(rdentry);
if (rdentry->d_sb->s_export_op->flags & EXPORT_OP_CLOSE_BEFORE_UNLINK)
nfsd_close_cached_files(rdentry);
host_err = vfs_unlink(dirp, rdentry, NULL);
} else {
host_err = vfs_rmdir(dirp, rdentry);

2
fs/nfsd/xdr.h
View File

@ -144,7 +144,6 @@ union nfsd_xdrstore {
#define NFS2_SVC_XDRSIZE sizeof(union nfsd_xdrstore)
int nfssvc_decode_void(struct svc_rqst *, __be32 *);
int nfssvc_decode_fhandle(struct svc_rqst *, __be32 *);
int nfssvc_decode_sattrargs(struct svc_rqst *, __be32 *);
int nfssvc_decode_diropargs(struct svc_rqst *, __be32 *);
@ -156,7 +155,6 @@ int nfssvc_decode_readlinkargs(struct svc_rqst *, __be32 *);
int nfssvc_decode_linkargs(struct svc_rqst *, __be32 *);
int nfssvc_decode_symlinkargs(struct svc_rqst *, __be32 *);
int nfssvc_decode_readdirargs(struct svc_rqst *, __be32 *);
int nfssvc_encode_void(struct svc_rqst *, __be32 *);
int nfssvc_encode_stat(struct svc_rqst *, __be32 *);
int nfssvc_encode_attrstat(struct svc_rqst *, __be32 *);
int nfssvc_encode_diropres(struct svc_rqst *, __be32 *);

2
fs/nfsd/xdr3.h
View File

@ -273,7 +273,6 @@ union nfsd3_xdrstore {
#define NFS3_SVC_XDRSIZE sizeof(union nfsd3_xdrstore)
int nfs3svc_decode_voidarg(struct svc_rqst *, __be32 *);
int nfs3svc_decode_fhandle(struct svc_rqst *, __be32 *);
int nfs3svc_decode_sattrargs(struct svc_rqst *, __be32 *);
int nfs3svc_decode_diropargs(struct svc_rqst *, __be32 *);
@ -290,7 +289,6 @@ int nfs3svc_decode_symlinkargs(struct svc_rqst *, __be32 *);
int nfs3svc_decode_readdirargs(struct svc_rqst *, __be32 *);
int nfs3svc_decode_readdirplusargs(struct svc_rqst *, __be32 *);
int nfs3svc_decode_commitargs(struct svc_rqst *, __be32 *);
int nfs3svc_encode_voidres(struct svc_rqst *, __be32 *);
int nfs3svc_encode_attrstat(struct svc_rqst *, __be32 *);
int nfs3svc_encode_wccstat(struct svc_rqst *, __be32 *);
int nfs3svc_encode_diropres(struct svc_rqst *, __be32 *);

43
fs/nfsd/xdr4.h
View File

@ -76,12 +76,7 @@ static inline bool nfsd4_has_session(struct nfsd4_compound_state *cs)
struct nfsd4_change_info {
u32 atomic;
bool change_supported;
u32 before_ctime_sec;
u32 before_ctime_nsec;
u64 before_change;
u32 after_ctime_sec;
u32 after_ctime_nsec;
u64 after_change;
};
@ -252,7 +247,8 @@ struct nfsd4_listxattrs {
struct nfsd4_open {
u32 op_claim_type; /* request */
struct xdr_netobj op_fname; /* request - everything but CLAIM_PREV */
u32 op_fnamelen;
char * op_fname; /* request - everything but CLAIM_PREV */
u32 op_delegate_type; /* request - CLAIM_PREV only */
stateid_t op_delegate_stateid; /* request - response */
u32 op_why_no_deleg; /* response - DELEG_NONE_EXT only */
@ -385,13 +381,6 @@ struct nfsd4_setclientid_confirm {
nfs4_verifier sc_confirm;
};
struct nfsd4_saved_compoundargs {
__be32 *p;
__be32 *end;
int pagelen;
struct page **pagelist;
};
struct nfsd4_test_stateid_id {
__be32 ts_id_status;
stateid_t ts_id_stateid;
@ -419,8 +408,7 @@ struct nfsd4_write {
u64 wr_offset; /* request */
u32 wr_stable_how; /* request */
u32 wr_buflen; /* request */
struct kvec wr_head;
struct page ** wr_pagelist; /* request */
struct xdr_buf wr_payload; /* request */
u32 wr_bytes_written; /* response */
u32 wr_how_written; /* response */
@ -433,7 +421,7 @@ struct nfsd4_exchange_id {
u32 flags;
clientid_t clientid;
u32 seqid;
int spa_how;
u32 spa_how;
u32 spo_must_enforce[3];
u32 spo_must_allow[3];
struct xdr_netobj nii_domain;
@ -554,7 +542,7 @@ struct nfsd4_copy {
bool cp_intra;
/* both */
bool cp_synchronous;
u32 cp_synchronous;
/* response */
struct nfsd42_write_res cp_res;
@ -615,7 +603,7 @@ struct nfsd4_copy_notify {
};
struct nfsd4_op {
int opnum;
u32 opnum;
const struct nfsd4_operation * opdesc;
__be32 status;
union nfsd4_op_u {
@ -696,15 +684,8 @@ struct svcxdr_tmpbuf {
struct nfsd4_compoundargs {
/* scratch variables for XDR decode */
__be32 * p;
__be32 * end;
struct page ** pagelist;
int pagelen;
bool tail;
__be32 tmp[8];
__be32 * tmpp;
struct xdr_stream *xdr;
struct svcxdr_tmpbuf *to_free;
struct svc_rqst *rqstp;
u32 taglen;
@ -767,22 +748,14 @@ static inline void
set_change_info(struct nfsd4_change_info *cinfo, struct svc_fh *fhp)
{
BUG_ON(!fhp->fh_pre_saved);
cinfo->atomic = (u32)fhp->fh_post_saved;
cinfo->change_supported = IS_I_VERSION(d_inode(fhp->fh_dentry));
cinfo->atomic = (u32)(fhp->fh_post_saved && !fhp->fh_no_atomic_attr);
cinfo->before_change = fhp->fh_pre_change;
cinfo->after_change = fhp->fh_post_change;
cinfo->before_ctime_sec = fhp->fh_pre_ctime.tv_sec;
cinfo->before_ctime_nsec = fhp->fh_pre_ctime.tv_nsec;
cinfo->after_ctime_sec = fhp->fh_post_attr.ctime.tv_sec;
cinfo->after_ctime_nsec = fhp->fh_post_attr.ctime.tv_nsec;
}
bool nfsd4_mach_creds_match(struct nfs4_client *cl, struct svc_rqst *rqstp);
int nfs4svc_decode_voidarg(struct svc_rqst *, __be32 *);
int nfs4svc_encode_voidres(struct svc_rqst *, __be32 *);
int nfs4svc_decode_compoundargs(struct svc_rqst *, __be32 *);
int nfs4svc_encode_compoundres(struct svc_rqst *, __be32 *);
__be32 nfsd4_check_resp_size(struct nfsd4_compoundres *, u32);

13
include/linux/exportfs.h
View File

@ -213,12 +213,25 @@ struct export_operations {
bool write, u32 *device_generation);
int (*commit_blocks)(struct inode *inode, struct iomap *iomaps,
int nr_iomaps, struct iattr *iattr);
#define EXPORT_OP_NOWCC (0x1) /* don't collect v3 wcc data */
#define EXPORT_OP_NOSUBTREECHK (0x2) /* no subtree checking */
#define EXPORT_OP_CLOSE_BEFORE_UNLINK (0x4) /* close files before unlink */
#define EXPORT_OP_REMOTE_FS (0x8) /* Filesystem is remote */
#define EXPORT_OP_NOATOMIC_ATTR (0x10) /* Filesystem cannot supply
atomic attribute updates
*/
unsigned long flags;
};
extern int exportfs_encode_inode_fh(struct inode *inode, struct fid *fid,
int *max_len, struct inode *parent);
extern int exportfs_encode_fh(struct dentry *dentry, struct fid *fid,
int *max_len, int connectable);
extern struct dentry *exportfs_decode_fh_raw(struct vfsmount *mnt,
struct fid *fid, int fh_len,
int fileid_type,
int (*acceptable)(void *, struct dentry *),
void *context);
extern struct dentry *exportfs_decode_fh(struct vfsmount *mnt, struct fid *fid,
int fh_len, int fileid_type, int (*acceptable)(void *, struct dentry *),
void *context);

13
include/linux/iversion.h
View File

@ -328,6 +328,19 @@ inode_query_iversion(struct inode *inode)
return cur >> I_VERSION_QUERIED_SHIFT;
}
/*
* For filesystems without any sort of change attribute, the best we can
* do is fake one up from the ctime:
*/
static inline u64 time_to_chattr(struct timespec64 *t)
{
u64 chattr = t->tv_sec;
chattr <<= 32;
chattr += t->tv_nsec;
return chattr;
}
/**
* inode_eq_iversion_raw - check whether the raw i_version counter has changed
* @inode: inode to check

8
include/linux/nfs4.h
View File

@ -385,13 +385,6 @@ enum lock_type4 {
NFS4_WRITEW_LT = 4
};
enum change_attr_type4 {
NFS4_CHANGE_TYPE_IS_MONOTONIC_INCR = 0,
NFS4_CHANGE_TYPE_IS_VERSION_COUNTER = 1,
NFS4_CHANGE_TYPE_IS_VERSION_COUNTER_NOPNFS = 2,
NFS4_CHANGE_TYPE_IS_TIME_METADATA = 3,
NFS4_CHANGE_TYPE_IS_UNDEFINED = 4
};
/* Mandatory Attributes */
#define FATTR4_WORD0_SUPPORTED_ATTRS (1UL << 0)
@ -459,7 +452,6 @@ enum change_attr_type4 {
#define FATTR4_WORD2_LAYOUT_BLKSIZE (1UL << 1)
#define FATTR4_WORD2_MDSTHRESHOLD (1UL << 4)
#define FATTR4_WORD2_CLONE_BLKSIZE (1UL << 13)
#define FATTR4_WORD2_CHANGE_ATTR_TYPE (1UL << 15)
#define FATTR4_WORD2_SECURITY_LABEL (1UL << 16)
#define FATTR4_WORD2_MODE_UMASK (1UL << 17)
#define FATTR4_WORD2_XATTR_SUPPORT (1UL << 18)

22
include/linux/sunrpc/svc.h
View File

@ -247,6 +247,8 @@ struct svc_rqst {
size_t rq_xprt_hlen; /* xprt header len */
struct xdr_buf rq_arg;
struct xdr_stream rq_arg_stream;
struct page *rq_scratch_page;
struct xdr_buf rq_res;
struct page *rq_pages[RPCSVC_MAXPAGES + 1];
struct page * *rq_respages; /* points into rq_pages */
@ -519,9 +521,9 @@ void svc_wake_up(struct svc_serv *);
void svc_reserve(struct svc_rqst *rqstp, int space);
struct svc_pool * svc_pool_for_cpu(struct svc_serv *serv, int cpu);
char * svc_print_addr(struct svc_rqst *, char *, size_t);
int svc_encode_read_payload(struct svc_rqst *rqstp,
unsigned int offset,
unsigned int length);
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 page **pages,
struct kvec *first, size_t total);
@ -557,4 +559,18 @@ static inline void svc_reserve_auth(struct svc_rqst *rqstp, int space)
svc_reserve(rqstp, space + rqstp->rq_auth_slack);
}
/**
* svcxdr_init_decode - Prepare an xdr_stream for svc Call decoding
* @rqstp: controlling server RPC transaction context
*
*/
static inline void svcxdr_init_decode(struct svc_rqst *rqstp)
{
struct xdr_stream *xdr = &rqstp->rq_arg_stream;
struct kvec *argv = rqstp->rq_arg.head;
xdr_init_decode(xdr, &rqstp->rq_arg, argv->iov_base, NULL);
xdr_set_scratch_page(xdr, rqstp->rq_scratch_page);
}
#endif /* SUNRPC_SVC_H */

36
include/linux/sunrpc/svc_rdma.h
View File

@ -47,6 +47,8 @@
#include <linux/sunrpc/svcsock.h>
#include <linux/sunrpc/rpc_rdma.h>
#include <linux/sunrpc/rpc_rdma_cid.h>
#include <linux/sunrpc/svc_rdma_pcl.h>
#include <rdma/ib_verbs.h>
#include <rdma/rdma_cm.h>
@ -142,10 +144,15 @@ struct svc_rdma_recv_ctxt {
unsigned int rc_page_count;
unsigned int rc_hdr_count;
u32 rc_inv_rkey;
__be32 *rc_write_list;
__be32 *rc_reply_chunk;
unsigned int rc_read_payload_offset;
unsigned int rc_read_payload_length;
__be32 rc_msgtype;
struct svc_rdma_pcl rc_call_pcl;
struct svc_rdma_pcl rc_read_pcl;
struct svc_rdma_chunk *rc_cur_result_payload;
struct svc_rdma_pcl rc_write_pcl;
struct svc_rdma_pcl rc_reply_pcl;
struct page *rc_pages[RPCSVC_MAXPAGES];
};
@ -171,6 +178,8 @@ extern void svc_rdma_handle_bc_reply(struct svc_rqst *rqstp,
/* svc_rdma_recvfrom.c */
extern void svc_rdma_recv_ctxts_destroy(struct svcxprt_rdma *rdma);
extern bool svc_rdma_post_recvs(struct svcxprt_rdma *rdma);
extern struct svc_rdma_recv_ctxt *
svc_rdma_recv_ctxt_get(struct svcxprt_rdma *rdma);
extern void svc_rdma_recv_ctxt_put(struct svcxprt_rdma *rdma,
struct svc_rdma_recv_ctxt *ctxt);
extern void svc_rdma_flush_recv_queues(struct svcxprt_rdma *rdma);
@ -179,16 +188,15 @@ extern int svc_rdma_recvfrom(struct svc_rqst *);
/* svc_rdma_rw.c */
extern void svc_rdma_destroy_rw_ctxts(struct svcxprt_rdma *rdma);
extern int svc_rdma_recv_read_chunk(struct svcxprt_rdma *rdma,
struct svc_rqst *rqstp,
struct svc_rdma_recv_ctxt *head, __be32 *p);
extern int svc_rdma_send_write_chunk(struct svcxprt_rdma *rdma,
__be32 *wr_ch, struct xdr_buf *xdr,
unsigned int offset,
unsigned long length);
const struct svc_rdma_chunk *chunk,
const struct xdr_buf *xdr);
extern int svc_rdma_send_reply_chunk(struct svcxprt_rdma *rdma,
const struct svc_rdma_recv_ctxt *rctxt,
struct xdr_buf *xdr);
const struct xdr_buf *xdr);
extern int svc_rdma_process_read_list(struct svcxprt_rdma *rdma,
struct svc_rqst *rqstp,
struct svc_rdma_recv_ctxt *head);
/* svc_rdma_sendto.c */
extern void svc_rdma_send_ctxts_destroy(struct svcxprt_rdma *rdma);
@ -201,14 +209,14 @@ extern int svc_rdma_send(struct svcxprt_rdma *rdma,
extern int svc_rdma_map_reply_msg(struct svcxprt_rdma *rdma,
struct svc_rdma_send_ctxt *sctxt,
const struct svc_rdma_recv_ctxt *rctxt,
struct xdr_buf *xdr);
const struct xdr_buf *xdr);
extern void svc_rdma_send_error_msg(struct svcxprt_rdma *rdma,
struct svc_rdma_send_ctxt *sctxt,
struct svc_rdma_recv_ctxt *rctxt,
int status);
extern int svc_rdma_sendto(struct svc_rqst *);
extern int svc_rdma_read_payload(struct svc_rqst *rqstp, unsigned int offset,
unsigned int length);
extern int svc_rdma_result_payload(struct svc_rqst *rqstp, unsigned int offset,
unsigned int length);
/* svc_rdma_transport.c */
extern struct svc_xprt_class svc_rdma_class;

128
include/linux/sunrpc/svc_rdma_pcl.h Normal file
View File

@ -0,0 +1,128 @@
/* SPDX-License-Identifier: GPL-2.0 */
/*
* Copyright (c) 2020, Oracle and/or its affiliates
*/
#ifndef SVC_RDMA_PCL_H
#define SVC_RDMA_PCL_H
#include <linux/list.h>
struct svc_rdma_segment {
u32 rs_handle;
u32 rs_length;
u64 rs_offset;
};
struct svc_rdma_chunk {
struct list_head ch_list;
u32 ch_position;
u32 ch_length;
u32 ch_payload_length;
u32 ch_segcount;
struct svc_rdma_segment ch_segments[];
};
struct svc_rdma_pcl {
unsigned int cl_count;
struct list_head cl_chunks;
};
/**
* pcl_init - Initialize a parsed chunk list
* @pcl: parsed chunk list to initialize
*
*/
static inline void pcl_init(struct svc_rdma_pcl *pcl)
{
INIT_LIST_HEAD(&pcl->cl_chunks);
}
/**
* pcl_is_empty - Return true if parsed chunk list is empty
* @pcl: parsed chunk list
*
*/
static inline bool pcl_is_empty(const struct svc_rdma_pcl *pcl)
{
return list_empty(&pcl->cl_chunks);
}
/**
* pcl_first_chunk - Return first chunk in a parsed chunk list
* @pcl: parsed chunk list
*
* Returns the first chunk in the list, or NULL if the list is empty.
*/
static inline struct svc_rdma_chunk *
pcl_first_chunk(const struct svc_rdma_pcl *pcl)
{
if (pcl_is_empty(pcl))
return NULL;
return list_first_entry(&pcl->cl_chunks, struct svc_rdma_chunk,
ch_list);
}
/**
* pcl_next_chunk - Return next chunk in a parsed chunk list
* @pcl: a parsed chunk list
* @chunk: chunk in @pcl
*
* Returns the next chunk in the list, or NULL if @chunk is already last.
*/
static inline struct svc_rdma_chunk *
pcl_next_chunk(const struct svc_rdma_pcl *pcl, struct svc_rdma_chunk *chunk)
{
if (list_is_last(&chunk->ch_list, &pcl->cl_chunks))
return NULL;
return list_next_entry(chunk, ch_list);
}
/**
* pcl_for_each_chunk - Iterate over chunks in a parsed chunk list
* @pos: the loop cursor
* @pcl: a parsed chunk list
*/
#define pcl_for_each_chunk(pos, pcl) \
for (pos = list_first_entry(&(pcl)->cl_chunks, struct svc_rdma_chunk, ch_list); \
&pos->ch_list != &(pcl)->cl_chunks; \
pos = list_next_entry(pos, ch_list))
/**
* pcl_for_each_segment - Iterate over segments in a parsed chunk
* @pos: the loop cursor
* @chunk: a parsed chunk
*/
#define pcl_for_each_segment(pos, chunk) \
for (pos = &(chunk)->ch_segments[0]; \
pos <= &(chunk)->ch_segments[(chunk)->ch_segcount - 1]; \
pos++)
/**
* pcl_chunk_end_offset - Return offset of byte range following @chunk
* @chunk: chunk in @pcl
*
* Returns starting offset of the region just after @chunk
*/
static inline unsigned int
pcl_chunk_end_offset(const struct svc_rdma_chunk *chunk)
{
return xdr_align_size(chunk->ch_position + chunk->ch_payload_length);
}
struct svc_rdma_recv_ctxt;
extern void pcl_free(struct svc_rdma_pcl *pcl);
extern bool pcl_alloc_call(struct svc_rdma_recv_ctxt *rctxt, __be32 *p);
extern bool pcl_alloc_read(struct svc_rdma_recv_ctxt *rctxt, __be32 *p);
extern bool pcl_alloc_write(struct svc_rdma_recv_ctxt *rctxt,
struct svc_rdma_pcl *pcl, __be32 *p);
extern int pcl_process_nonpayloads(const struct svc_rdma_pcl *pcl,
const struct xdr_buf *xdr,
int (*actor)(const struct xdr_buf *,
void *),
void *data);
#endif /* SVC_RDMA_PCL_H */

4
include/linux/sunrpc/svc_xprt.h
View File

@ -21,8 +21,8 @@ struct svc_xprt_ops {
int (*xpo_has_wspace)(struct svc_xprt *);
int (*xpo_recvfrom)(struct svc_rqst *);
int (*xpo_sendto)(struct svc_rqst *);
int (*xpo_read_payload)(struct svc_rqst *, unsigned int,
unsigned int);
int (*xpo_result_payload)(struct svc_rqst *, unsigned int,
unsigned int);
void (*xpo_release_rqst)(struct svc_rqst *);
void (*xpo_detach)(struct svc_xprt *);
void (*xpo_free)(struct svc_xprt *);

91
include/linux/sunrpc/xdr.h
View File

@ -183,7 +183,8 @@ xdr_adjust_iovec(struct kvec *iov, __be32 *p)
*/
extern void xdr_shift_buf(struct xdr_buf *, size_t);
extern void xdr_buf_from_iov(struct kvec *, struct xdr_buf *);
extern int xdr_buf_subsegment(struct xdr_buf *, struct xdr_buf *, unsigned int, unsigned int);
extern int xdr_buf_subsegment(const struct xdr_buf *buf, struct xdr_buf *subbuf,
unsigned int base, unsigned int len);
extern void xdr_buf_trim(struct xdr_buf *, unsigned int);
extern int read_bytes_from_xdr_buf(struct xdr_buf *, unsigned int, void *, unsigned int);
extern int write_bytes_to_xdr_buf(struct xdr_buf *, unsigned int, void *, unsigned int);
@ -247,13 +248,57 @@ extern void xdr_init_decode(struct xdr_stream *xdr, struct xdr_buf *buf,
__be32 *p, struct rpc_rqst *rqst);
extern void xdr_init_decode_pages(struct xdr_stream *xdr, struct xdr_buf *buf,
struct page **pages, unsigned int len);
extern void xdr_set_scratch_buffer(struct xdr_stream *xdr, void *buf, size_t buflen);
extern __be32 *xdr_inline_decode(struct xdr_stream *xdr, size_t nbytes);
extern unsigned int xdr_read_pages(struct xdr_stream *xdr, unsigned int len);
extern void xdr_enter_page(struct xdr_stream *xdr, unsigned int len);
extern int xdr_process_buf(struct xdr_buf *buf, unsigned int offset, unsigned int len, int (*actor)(struct scatterlist *, void *), void *data);
extern uint64_t xdr_align_data(struct xdr_stream *, uint64_t, uint32_t);
extern uint64_t xdr_expand_hole(struct xdr_stream *, uint64_t, uint64_t);
extern bool xdr_stream_subsegment(struct xdr_stream *xdr, struct xdr_buf *subbuf,
unsigned int len);
/**
* xdr_set_scratch_buffer - Attach a scratch buffer for decoding data.
* @xdr: pointer to xdr_stream struct
* @buf: pointer to an empty buffer
* @buflen: size of 'buf'
*
* The scratch buffer is used when decoding from an array of pages.
* If an xdr_inline_decode() call spans across page boundaries, then
* we copy the data into the scratch buffer in order to allow linear
* access.
*/
static inline void
xdr_set_scratch_buffer(struct xdr_stream *xdr, void *buf, size_t buflen)
{
xdr->scratch.iov_base = buf;
xdr->scratch.iov_len = buflen;
}
/**
* xdr_set_scratch_page - Attach a scratch buffer for decoding data
* @xdr: pointer to xdr_stream struct
* @page: an anonymous page
*
* See xdr_set_scratch_buffer().
*/
static inline void
xdr_set_scratch_page(struct xdr_stream *xdr, struct page *page)
{
xdr_set_scratch_buffer(xdr, page_address(page), PAGE_SIZE);
}
/**
* xdr_reset_scratch_buffer - Clear scratch buffer information
* @xdr: pointer to xdr_stream struct
*
* See xdr_set_scratch_buffer().
*/
static inline void
xdr_reset_scratch_buffer(struct xdr_stream *xdr)
{
xdr_set_scratch_buffer(xdr, NULL, 0);
}
/**
* xdr_stream_remaining - Return the number of bytes remaining in the stream
@ -505,6 +550,27 @@ static inline bool xdr_item_is_present(const __be32 *p)
return *p != xdr_zero;
}
/**
* xdr_stream_decode_bool - Decode a boolean
* @xdr: pointer to xdr_stream
* @ptr: pointer to a u32 in which to store the result
*
* Return values:
* %0 on success
* %-EBADMSG on XDR buffer overflow
*/
static inline ssize_t
xdr_stream_decode_bool(struct xdr_stream *xdr, __u32 *ptr)
{
const size_t count = sizeof(*ptr);
__be32 *p = xdr_inline_decode(xdr, count);
if (unlikely(!p))
return -EBADMSG;
*ptr = (*p != xdr_zero);
return 0;
}
/**
* xdr_stream_decode_u32 - Decode a 32-bit integer
* @xdr: pointer to xdr_stream
@ -526,6 +592,27 @@ xdr_stream_decode_u32(struct xdr_stream *xdr, __u32 *ptr)
return 0;
}
/**
* xdr_stream_decode_u64 - Decode a 64-bit integer
* @xdr: pointer to xdr_stream
* @ptr: location to store 64-bit integer
*
* Return values:
* %0 on success
* %-EBADMSG on XDR buffer overflow
*/
static inline ssize_t
xdr_stream_decode_u64(struct xdr_stream *xdr, __u64 *ptr)
{
const size_t count = sizeof(*ptr);
__be32 *p = xdr_inline_decode(xdr, count);
if (unlikely(!p))
return -EBADMSG;
xdr_decode_hyper(p, ptr);
return 0;
}
/**
* xdr_stream_decode_opaque_fixed - Decode fixed length opaque xdr data
* @xdr: pointer to xdr_stream

171
include/trace/events/rpcrdma.h
View File

@ -1410,101 +1410,112 @@ DEFINE_BADREQ_EVENT(drop);
DEFINE_BADREQ_EVENT(badproc);
DEFINE_BADREQ_EVENT(parse);
DECLARE_EVENT_CLASS(svcrdma_segment_event,
TRACE_EVENT(svcrdma_encode_wseg,
TP_PROTO(
const struct svc_rdma_send_ctxt *ctxt,
u32 segno,
u32 handle,
u32 length,
u64 offset
),
TP_ARGS(handle, length, offset),
TP_ARGS(ctxt, segno, handle, length, offset),
TP_STRUCT__entry(
__field(u32, cq_id)
__field(int, completion_id)
__field(u32, segno)
__field(u32, handle)
__field(u32, length)
__field(u64, offset)
),
TP_fast_assign(
__entry->cq_id = ctxt->sc_cid.ci_queue_id;
__entry->completion_id = ctxt->sc_cid.ci_completion_id;
__entry->segno = segno;
__entry->handle = handle;
__entry->length = length;
__entry->offset = offset;
),
TP_printk("%u@0x%016llx:0x%08x",
__entry->length, (unsigned long long)__entry->offset,
__entry->handle
TP_printk("cq_id=%u cid=%d segno=%u %u@0x%016llx:0x%08x",
__entry->cq_id, __entry->completion_id,
__entry->segno, __entry->length,
(unsigned long long)__entry->offset, __entry->handle
)
);
#define DEFINE_SEGMENT_EVENT(name) \
DEFINE_EVENT(svcrdma_segment_event, svcrdma_##name,\
TP_PROTO( \
u32 handle, \
u32 length, \
u64 offset \
), \
TP_ARGS(handle, length, offset))
DEFINE_SEGMENT_EVENT(decode_wseg);
DEFINE_SEGMENT_EVENT(encode_rseg);
DEFINE_SEGMENT_EVENT(send_rseg);
DEFINE_SEGMENT_EVENT(encode_wseg);
DEFINE_SEGMENT_EVENT(send_wseg);
DECLARE_EVENT_CLASS(svcrdma_chunk_event,
TRACE_EVENT(svcrdma_decode_rseg,
TP_PROTO(
u32 length
const struct rpc_rdma_cid *cid,
const struct svc_rdma_chunk *chunk,
const struct svc_rdma_segment *segment
),
TP_ARGS(length),
TP_ARGS(cid, chunk, segment),
TP_STRUCT__entry(
__field(u32, length)
),
TP_fast_assign(
__entry->length = length;
),
TP_printk("length=%u",
__entry->length
)
);
#define DEFINE_CHUNK_EVENT(name) \
DEFINE_EVENT(svcrdma_chunk_event, svcrdma_##name, \
TP_PROTO( \
u32 length \
), \
TP_ARGS(length))
DEFINE_CHUNK_EVENT(send_pzr);
DEFINE_CHUNK_EVENT(encode_write_chunk);
DEFINE_CHUNK_EVENT(send_write_chunk);
DEFINE_CHUNK_EVENT(encode_read_chunk);
DEFINE_CHUNK_EVENT(send_reply_chunk);
TRACE_EVENT(svcrdma_send_read_chunk,
TP_PROTO(
u32 length,
u32 position
),
TP_ARGS(length, position),
TP_STRUCT__entry(
__field(u32, length)
__field(u32, cq_id)
__field(int, completion_id)
__field(u32, segno)
__field(u32, position)
__field(u32, handle)
__field(u32, length)
__field(u64, offset)
),
TP_fast_assign(
__entry->length = length;
__entry->position = position;
__entry->cq_id = cid->ci_queue_id;
__entry->completion_id = cid->ci_completion_id;
__entry->segno = chunk->ch_segcount;
__entry->position = chunk->ch_position;
__entry->handle = segment->rs_handle;
__entry->length = segment->rs_length;
__entry->offset = segment->rs_offset;
),
TP_printk("length=%u position=%u",
__entry->length, __entry->position
TP_printk("cq_id=%u cid=%d segno=%u position=%u %u@0x%016llx:0x%08x",
__entry->cq_id, __entry->completion_id,
__entry->segno, __entry->position, __entry->length,
(unsigned long long)__entry->offset, __entry->handle
)
);
TRACE_EVENT(svcrdma_decode_wseg,
TP_PROTO(
const struct rpc_rdma_cid *cid,
const struct svc_rdma_chunk *chunk,
u32 segno
),
TP_ARGS(cid, chunk, segno),
TP_STRUCT__entry(
__field(u32, cq_id)
__field(int, completion_id)
__field(u32, segno)
__field(u32, handle)
__field(u32, length)
__field(u64, offset)
),
TP_fast_assign(
const struct svc_rdma_segment *segment =
&chunk->ch_segments[segno];
__entry->cq_id = cid->ci_queue_id;
__entry->completion_id = cid->ci_completion_id;
__entry->segno = segno;
__entry->handle = segment->rs_handle;
__entry->length = segment->rs_length;
__entry->offset = segment->rs_offset;
),
TP_printk("cq_id=%u cid=%d segno=%u %u@0x%016llx:0x%08x",
__entry->cq_id, __entry->completion_id,
__entry->segno, __entry->length,
(unsigned long long)__entry->offset, __entry->handle
)
);
@ -1581,6 +1592,7 @@ DECLARE_EVENT_CLASS(svcrdma_dma_map_class,
TP_ARGS(rdma, dma_addr, length))
DEFINE_SVC_DMA_EVENT(dma_map_page);
DEFINE_SVC_DMA_EVENT(dma_map_err);
DEFINE_SVC_DMA_EVENT(dma_unmap_page);
TRACE_EVENT(svcrdma_dma_map_rw_err,
@ -1699,20 +1711,30 @@ TRACE_EVENT(svcrdma_small_wrch_err,
TRACE_EVENT(svcrdma_send_pullup,
TP_PROTO(
unsigned int len
const struct svc_rdma_send_ctxt *ctxt,
unsigned int msglen
),
TP_ARGS(len),
TP_ARGS(ctxt, msglen),
TP_STRUCT__entry(
__field(unsigned int, len)
__field(u32, cq_id)
__field(int, completion_id)
__field(unsigned int, hdrlen)
__field(unsigned int, msglen)
),
TP_fast_assign(
__entry->len = len;
__entry->cq_id = ctxt->sc_cid.ci_queue_id;
__entry->completion_id = ctxt->sc_cid.ci_completion_id;
__entry->hdrlen = ctxt->sc_hdrbuf.len,
__entry->msglen = msglen;
),
TP_printk("len=%u", __entry->len)
TP_printk("cq_id=%u cid=%d hdr=%u msg=%u (total %u)",
__entry->cq_id, __entry->completion_id,
__entry->hdrlen, __entry->msglen,
__entry->hdrlen + __entry->msglen)
);
TRACE_EVENT(svcrdma_send_err,
@ -1819,7 +1841,7 @@ TRACE_EVENT(svcrdma_rq_post_err,
)
);
TRACE_EVENT(svcrdma_post_chunk,
DECLARE_EVENT_CLASS(svcrdma_post_chunk_class,
TP_PROTO(
const struct rpc_rdma_cid *cid,
int sqecount
@ -1845,6 +1867,19 @@ TRACE_EVENT(svcrdma_post_chunk,
)
);
#define DEFINE_POST_CHUNK_EVENT(name) \
DEFINE_EVENT(svcrdma_post_chunk_class, \
svcrdma_post_##name##_chunk, \
TP_PROTO( \
const struct rpc_rdma_cid *cid, \
int sqecount \
), \
TP_ARGS(cid, sqecount))
DEFINE_POST_CHUNK_EVENT(read);
DEFINE_POST_CHUNK_EVENT(write);
DEFINE_POST_CHUNK_EVENT(reply);
DEFINE_COMPLETION_EVENT(svcrdma_wc_read);
DEFINE_COMPLETION_EVENT(svcrdma_wc_write);

24
include/trace/events/sunrpc.h
View File

@ -1500,30 +1500,6 @@ SVC_RQST_FLAG_LIST
#define show_rqstp_flags(flags) \
__print_flags(flags, "|", SVC_RQST_FLAG_LIST)
TRACE_EVENT(svc_recv,
TP_PROTO(struct svc_rqst *rqst, int len),
TP_ARGS(rqst, len),
TP_STRUCT__entry(
__field(u32, xid)
__field(int, len)
__field(unsigned long, flags)
__string(addr, rqst->rq_xprt->xpt_remotebuf)
),
TP_fast_assign(
__entry->xid = be32_to_cpu(rqst->rq_xid);
__entry->len = len;
__entry->flags = rqst->rq_flags;
__assign_str(addr, rqst->rq_xprt->xpt_remotebuf);
),
TP_printk("addr=%s xid=0x%08x len=%d flags=%s",
__get_str(addr), __entry->xid, __entry->len,
show_rqstp_flags(__entry->flags))
);
TRACE_DEFINE_ENUM(SVC_GARBAGE);
TRACE_DEFINE_ENUM(SVC_SYSERR);
TRACE_DEFINE_ENUM(SVC_VALID);

15
net/sunrpc/auth_gss/gss_rpc_upcall.c
View File

@ -200,7 +200,7 @@ static int gssp_call(struct net *net, struct rpc_message *msg)
static void gssp_free_receive_pages(struct gssx_arg_accept_sec_context *arg)
{
int i;
unsigned int i;
for (i = 0; i < arg->npages && arg->pages[i]; i++)
__free_page(arg->pages[i]);
@ -210,14 +210,19 @@ static void gssp_free_receive_pages(struct gssx_arg_accept_sec_context *arg)
static int gssp_alloc_receive_pages(struct gssx_arg_accept_sec_context *arg)
{
unsigned int i;
arg->npages = DIV_ROUND_UP(NGROUPS_MAX * 4, PAGE_SIZE);
arg->pages = kcalloc(arg->npages, sizeof(struct page *), GFP_KERNEL);
/*
* XXX: actual pages are allocated by xdr layer in
* xdr_partial_copy_from_skb.
*/
if (!arg->pages)
return -ENOMEM;
for (i = 0; i < arg->npages; i++) {
arg->pages[i] = alloc_page(GFP_KERNEL);
if (!arg->pages[i]) {
gssp_free_receive_pages(arg);
return -ENOMEM;
}
}
return 0;
}

3
net/sunrpc/auth_gss/gss_rpc_xdr.c
View File

@ -771,7 +771,6 @@ void gssx_enc_accept_sec_context(struct rpc_rqst *req,
xdr_inline_pages(&req->rq_rcv_buf,
PAGE_SIZE/2 /* pretty arbitrary */,
arg->pages, 0 /* page base */, arg->npages * PAGE_SIZE);
req->rq_rcv_buf.flags |= XDRBUF_SPARSE_PAGES;
done:
if (err)
dprintk("RPC: gssx_enc_accept_sec_context: %d\n", err);
@ -789,7 +788,7 @@ int gssx_dec_accept_sec_context(struct rpc_rqst *rqstp,
scratch = alloc_page(GFP_KERNEL);
if (!scratch)
return -ENOMEM;
xdr_set_scratch_buffer(xdr, page_address(scratch), PAGE_SIZE);
xdr_set_scratch_page(xdr, scratch);
/* res->status */
err = gssx_dec_status(xdr, &res->status);

41
net/sunrpc/cache.c
View File

@ -778,7 +778,6 @@ void cache_clean_deferred(void *owner)
*/
static DEFINE_SPINLOCK(queue_lock);
static DEFINE_MUTEX(queue_io_mutex);
struct cache_queue {
struct list_head list;
@ -906,44 +905,26 @@ static ssize_t cache_do_downcall(char *kaddr, const char __user *buf,
return ret;
}
static ssize_t cache_slow_downcall(const char __user *buf,
size_t count, struct cache_detail *cd)
{
static char write_buf[32768]; /* protected by queue_io_mutex */
ssize_t ret = -EINVAL;
if (count >= sizeof(write_buf))
goto out;
mutex_lock(&queue_io_mutex);
ret = cache_do_downcall(write_buf, buf, count, cd);
mutex_unlock(&queue_io_mutex);
out:
return ret;
}
static ssize_t cache_downcall(struct address_space *mapping,
const char __user *buf,
size_t count, struct cache_detail *cd)
{
struct page *page;
char *kaddr;
char *write_buf;
ssize_t ret = -ENOMEM;
if (count >= PAGE_SIZE)
goto out_slow;
if (count >= 32768) { /* 32k is max userland buffer, lets check anyway */
ret = -EINVAL;
goto out;
}
page = find_or_create_page(mapping, 0, GFP_KERNEL);
if (!page)
goto out_slow;
write_buf = kvmalloc(count + 1, GFP_KERNEL);
if (!write_buf)
goto out;
kaddr = kmap(page);
ret = cache_do_downcall(kaddr, buf, count, cd);
kunmap(page);
unlock_page(page);
put_page(page);
ret = cache_do_downcall(write_buf, buf, count, cd);
kvfree(write_buf);
out:
return ret;
out_slow:
return cache_slow_downcall(buf, count, cd);
}
static ssize_t cache_write(struct file *filp, const char __user *buf,

16
net/sunrpc/svc.c
View File

@ -614,6 +614,10 @@ svc_rqst_alloc(struct svc_serv *serv, struct svc_pool *pool, int node)
rqstp->rq_server = serv;
rqstp->rq_pool = pool;
rqstp->rq_scratch_page = alloc_pages_node(node, GFP_KERNEL, 0);
if (!rqstp->rq_scratch_page)
goto out_enomem;
rqstp->rq_argp = kmalloc_node(serv->sv_xdrsize, GFP_KERNEL, node);
if (!rqstp->rq_argp)
goto out_enomem;
@ -842,6 +846,7 @@ void
svc_rqst_free(struct svc_rqst *rqstp)
{
svc_release_buffer(rqstp);
put_page(rqstp->rq_scratch_page);
kfree(rqstp->rq_resp);
kfree(rqstp->rq_argp);
kfree(rqstp->rq_auth_data);
@ -1622,7 +1627,7 @@ u32 svc_max_payload(const struct svc_rqst *rqstp)
EXPORT_SYMBOL_GPL(svc_max_payload);
/**
* svc_encode_read_payload - mark a range of bytes as a READ payload
* svc_encode_result_payload - mark a range of bytes as a result payload
* @rqstp: svc_rqst to operate on
* @offset: payload's byte offset in rqstp->rq_res
* @length: size of payload, in bytes
@ -1630,12 +1635,13 @@ EXPORT_SYMBOL_GPL(svc_max_payload);
* Returns zero on success, or a negative errno if a permanent
* error occurred.
*/
int svc_encode_read_payload(struct svc_rqst *rqstp, unsigned int offset,
unsigned int length)
int svc_encode_result_payload(struct svc_rqst *rqstp, unsigned int offset,
unsigned int length)
{
return rqstp->rq_xprt->xpt_ops->xpo_read_payload(rqstp, offset, length);
return rqstp->rq_xprt->xpt_ops->xpo_result_payload(rqstp, offset,
length);
}
EXPORT_SYMBOL_GPL(svc_encode_read_payload);
EXPORT_SYMBOL_GPL(svc_encode_result_payload);
/**
* svc_fill_write_vector - Construct data argument for VFS write call

4
net/sunrpc/svc_xprt.c
View File

@ -813,8 +813,6 @@ static int svc_handle_xprt(struct svc_rqst *rqstp, struct svc_xprt *xprt)
len = svc_deferred_recv(rqstp);
else
len = xprt->xpt_ops->xpo_recvfrom(rqstp);
if (len > 0)
trace_svc_xdr_recvfrom(rqstp, &rqstp->rq_arg);
rqstp->rq_stime = ktime_get();
rqstp->rq_reserved = serv->sv_max_mesg;
atomic_add(rqstp->rq_reserved, &xprt->xpt_reserved);
@ -868,7 +866,7 @@ int svc_recv(struct svc_rqst *rqstp, long timeout)
if (serv->sv_stats)
serv->sv_stats->netcnt++;
trace_svc_recv(rqstp, len);
trace_svc_xdr_recvfrom(rqstp, &rqstp->rq_arg);
return len;
out_release:
rqstp->rq_res.len = 0;

8
net/sunrpc/svcsock.c
View File

@ -181,8 +181,8 @@ static void svc_set_cmsg_data(struct svc_rqst *rqstp, struct cmsghdr *cmh)
}
}
static int svc_sock_read_payload(struct svc_rqst *rqstp, unsigned int offset,
unsigned int length)
static int svc_sock_result_payload(struct svc_rqst *rqstp, unsigned int offset,
unsigned int length)
{
return 0;
}
@ -635,7 +635,7 @@ static const struct svc_xprt_ops svc_udp_ops = {
.xpo_create = svc_udp_create,
.xpo_recvfrom = svc_udp_recvfrom,
.xpo_sendto = svc_udp_sendto,
.xpo_read_payload = svc_sock_read_payload,
.xpo_result_payload = svc_sock_result_payload,
.xpo_release_rqst = svc_udp_release_rqst,
.xpo_detach = svc_sock_detach,
.xpo_free = svc_sock_free,
@ -1123,7 +1123,7 @@ static const struct svc_xprt_ops svc_tcp_ops = {
.xpo_create = svc_tcp_create,
.xpo_recvfrom = svc_tcp_recvfrom,
.xpo_sendto = svc_tcp_sendto,
.xpo_read_payload = svc_sock_read_payload,
.xpo_result_payload = svc_sock_result_payload,
.xpo_release_rqst = svc_tcp_release_rqst,
.xpo_detach = svc_tcp_sock_detach,
.xpo_free = svc_sock_free,

78
net/sunrpc/xdr.c
View File

@ -669,7 +669,7 @@ void xdr_init_encode(struct xdr_stream *xdr, struct xdr_buf *buf, __be32 *p,
struct kvec *iov = buf->head;
int scratch_len = buf->buflen - buf->page_len - buf->tail[0].iov_len;
xdr_set_scratch_buffer(xdr, NULL, 0);
xdr_reset_scratch_buffer(xdr);
BUG_ON(scratch_len < 0);
xdr->buf = buf;
xdr->iov = iov;
@ -713,7 +713,7 @@ inline void xdr_commit_encode(struct xdr_stream *xdr)
page = page_address(*xdr->page_ptr);
memcpy(xdr->scratch.iov_base, page, shift);
memmove(page, page + shift, (void *)xdr->p - page);
xdr->scratch.iov_len = 0;
xdr_reset_scratch_buffer(xdr);
}
EXPORT_SYMBOL_GPL(xdr_commit_encode);
@ -743,8 +743,7 @@ static __be32 *xdr_get_next_encode_buffer(struct xdr_stream *xdr,
* the "scratch" iov to track any temporarily unused fragment of
* space at the end of the previous buffer:
*/
xdr->scratch.iov_base = xdr->p;
xdr->scratch.iov_len = frag1bytes;
xdr_set_scratch_buffer(xdr, xdr->p, frag1bytes);
p = page_address(*xdr->page_ptr);
/*
* Note this is where the next encode will start after we've
@ -1052,8 +1051,7 @@ void xdr_init_decode(struct xdr_stream *xdr, struct xdr_buf *buf, __be32 *p,
struct rpc_rqst *rqst)
{
xdr->buf = buf;
xdr->scratch.iov_base = NULL;
xdr->scratch.iov_len = 0;
xdr_reset_scratch_buffer(xdr);
xdr->nwords = XDR_QUADLEN(buf->len);
if (buf->head[0].iov_len != 0)
xdr_set_iov(xdr, buf->head, buf->len);
@ -1101,24 +1099,6 @@ static __be32 * __xdr_inline_decode(struct xdr_stream *xdr, size_t nbytes)
return p;
}
/**
* xdr_set_scratch_buffer - Attach a scratch buffer for decoding data.
* @xdr: pointer to xdr_stream struct
* @buf: pointer to an empty buffer
* @buflen: size of 'buf'
*
* The scratch buffer is used when decoding from an array of pages.
* If an xdr_inline_decode() call spans across page boundaries, then
* we copy the data into the scratch buffer in order to allow linear
* access.
*/
void xdr_set_scratch_buffer(struct xdr_stream *xdr, void *buf, size_t buflen)
{
xdr->scratch.iov_base = buf;
xdr->scratch.iov_len = buflen;
}
EXPORT_SYMBOL_GPL(xdr_set_scratch_buffer);
static __be32 *xdr_copy_to_scratch(struct xdr_stream *xdr, size_t nbytes)
{
__be32 *p;
@ -1379,9 +1359,8 @@ EXPORT_SYMBOL_GPL(xdr_buf_from_iov);
*
* Returns -1 if base of length are out of bounds.
*/
int
xdr_buf_subsegment(struct xdr_buf *buf, struct xdr_buf *subbuf,
unsigned int base, unsigned int len)
int xdr_buf_subsegment(const struct xdr_buf *buf, struct xdr_buf *subbuf,
unsigned int base, unsigned int len)
{
subbuf->buflen = subbuf->len = len;
if (base < buf->head[0].iov_len) {
@ -1428,6 +1407,51 @@ xdr_buf_subsegment(struct xdr_buf *buf, struct xdr_buf *subbuf,
}
EXPORT_SYMBOL_GPL(xdr_buf_subsegment);
/**
* xdr_stream_subsegment - set @subbuf to a portion of @xdr
* @xdr: an xdr_stream set up for decoding
* @subbuf: the result buffer
* @nbytes: length of @xdr to extract, in bytes
*
* Sets up @subbuf to represent a portion of @xdr. The portion
* starts at the current offset in @xdr, and extends for a length
* of @nbytes. If this is successful, @xdr is advanced to the next
* position following that portion.
*
* Return values:
* %true: @subbuf has been initialized, and @xdr has been advanced.
* %false: a bounds error has occurred
*/
bool xdr_stream_subsegment(struct xdr_stream *xdr, struct xdr_buf *subbuf,
unsigned int nbytes)
{
unsigned int remaining, offset, len;
if (xdr_buf_subsegment(xdr->buf, subbuf, xdr_stream_pos(xdr), nbytes))
return false;
if (subbuf->head[0].iov_len)
if (!__xdr_inline_decode(xdr, subbuf->head[0].iov_len))
return false;
remaining = subbuf->page_len;
offset = subbuf->page_base;
while (remaining) {
len = min_t(unsigned int, remaining, PAGE_SIZE) - offset;
if (xdr->p == xdr->end && !xdr_set_next_buffer(xdr))
return false;
if (!__xdr_inline_decode(xdr, len))
return false;
remaining -= len;
offset = 0;
}
return true;
}
EXPORT_SYMBOL_GPL(xdr_stream_subsegment);
/**
* xdr_buf_trim - lop at most "len" bytes off the end of "buf"
* @buf: buf to be trimmed

2
net/sunrpc/xprtrdma/Makefile
View File

@ -4,5 +4,5 @@ obj-$(CONFIG_SUNRPC_XPRT_RDMA) += rpcrdma.o
rpcrdma-y := transport.o rpc_rdma.o verbs.o frwr_ops.o \
svc_rdma.o svc_rdma_backchannel.o svc_rdma_transport.o \
svc_rdma_sendto.o svc_rdma_recvfrom.o svc_rdma_rw.o \
module.o
svc_rdma_pcl.o module.o
rpcrdma-$(CONFIG_SUNRPC_BACKCHANNEL) += backchannel.o

14
net/sunrpc/xprtrdma/svc_rdma_backchannel.c
View File

@ -74,11 +74,17 @@ out_unlock:
*/
static int svc_rdma_bc_sendto(struct svcxprt_rdma *rdma,
struct rpc_rqst *rqst,
struct svc_rdma_send_ctxt *ctxt)
struct svc_rdma_send_ctxt *sctxt)
{
struct svc_rdma_recv_ctxt *rctxt;
int ret;
ret = svc_rdma_map_reply_msg(rdma, ctxt, NULL, &rqst->rq_snd_buf);
rctxt = svc_rdma_recv_ctxt_get(rdma);
if (!rctxt)
return -EIO;
ret = svc_rdma_map_reply_msg(rdma, sctxt, rctxt, &rqst->rq_snd_buf);
svc_rdma_recv_ctxt_put(rdma, rctxt);
if (ret < 0)
return -EIO;
@ -86,8 +92,8 @@ static int svc_rdma_bc_sendto(struct svcxprt_rdma *rdma,
* the rq_buffer before all retransmits are complete.
*/
get_page(virt_to_page(rqst->rq_buffer));
ctxt->sc_send_wr.opcode = IB_WR_SEND;
return svc_rdma_send(rdma, ctxt);
sctxt->sc_send_wr.opcode = IB_WR_SEND;
return svc_rdma_send(rdma, sctxt);
}
/* Server-side transport endpoint wants a whole page for its send

306
net/sunrpc/xprtrdma/svc_rdma_pcl.c Normal file
View File

@ -0,0 +1,306 @@
// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (c) 2020 Oracle. All rights reserved.
*/
#include <linux/sunrpc/svc_rdma.h>
#include <linux/sunrpc/rpc_rdma.h>
#include "xprt_rdma.h"
#include <trace/events/rpcrdma.h>
/**
* pcl_free - Release all memory associated with a parsed chunk list
* @pcl: parsed chunk list
*
*/
void pcl_free(struct svc_rdma_pcl *pcl)
{
while (!list_empty(&pcl->cl_chunks)) {
struct svc_rdma_chunk *chunk;
chunk = pcl_first_chunk(pcl);
list_del(&chunk->ch_list);
kfree(chunk);
}
}
static struct svc_rdma_chunk *pcl_alloc_chunk(u32 segcount, u32 position)
{
struct svc_rdma_chunk *chunk;
chunk = kmalloc(struct_size(chunk, ch_segments, segcount), GFP_KERNEL);
if (!chunk)
return NULL;
chunk->ch_position = position;
chunk->ch_length = 0;
chunk->ch_payload_length = 0;
chunk->ch_segcount = 0;
return chunk;
}
static struct svc_rdma_chunk *
pcl_lookup_position(struct svc_rdma_pcl *pcl, u32 position)
{
struct svc_rdma_chunk *pos;
pcl_for_each_chunk(pos, pcl) {
if (pos->ch_position == position)
return pos;
}
return NULL;
}
static void pcl_insert_position(struct svc_rdma_pcl *pcl,
struct svc_rdma_chunk *chunk)
{
struct svc_rdma_chunk *pos;
pcl_for_each_chunk(pos, pcl) {
if (pos->ch_position > chunk->ch_position)
break;
}
__list_add(&chunk->ch_list, pos->ch_list.prev, &pos->ch_list);
pcl->cl_count++;
}
static void pcl_set_read_segment(const struct svc_rdma_recv_ctxt *rctxt,
struct svc_rdma_chunk *chunk,
u32 handle, u32 length, u64 offset)
{
struct svc_rdma_segment *segment;
segment = &chunk->ch_segments[chunk->ch_segcount];
segment->rs_handle = handle;
segment->rs_length = length;
segment->rs_offset = offset;
trace_svcrdma_decode_rseg(&rctxt->rc_cid, chunk, segment);
chunk->ch_length += length;
chunk->ch_segcount++;
}
/**
* pcl_alloc_call - Construct a parsed chunk list for the Call body
* @rctxt: Ingress receive context
* @p: Start of an un-decoded Read list
*
* Assumptions:
* - The incoming Read list has already been sanity checked.
* - cl_count is already set to the number of segments in
* the un-decoded list.
* - The list might not be in order by position.
*
* Return values:
* %true: Parsed chunk list was successfully constructed, and
* cl_count is updated to be the number of chunks (ie.
* unique positions) in the Read list.
* %false: Memory allocation failed.
*/
bool pcl_alloc_call(struct svc_rdma_recv_ctxt *rctxt, __be32 *p)
{
struct svc_rdma_pcl *pcl = &rctxt->rc_call_pcl;
unsigned int i, segcount = pcl->cl_count;
pcl->cl_count = 0;
for (i = 0; i < segcount; i++) {
struct svc_rdma_chunk *chunk;
u32 position, handle, length;
u64 offset;
p++; /* skip the list discriminator */
p = xdr_decode_read_segment(p, &position, &handle,
&length, &offset);
if (position != 0)
continue;
if (pcl_is_empty(pcl)) {
chunk = pcl_alloc_chunk(segcount, position);
if (!chunk)
return false;
pcl_insert_position(pcl, chunk);
} else {
chunk = list_first_entry(&pcl->cl_chunks,
struct svc_rdma_chunk,
ch_list);
}
pcl_set_read_segment(rctxt, chunk, handle, length, offset);
}
return true;
}
/**
* pcl_alloc_read - Construct a parsed chunk list for normal Read chunks
* @rctxt: Ingress receive context
* @p: Start of an un-decoded Read list
*
* Assumptions:
* - The incoming Read list has already been sanity checked.
* - cl_count is already set to the number of segments in
* the un-decoded list.
* - The list might not be in order by position.
*
* Return values:
* %true: Parsed chunk list was successfully constructed, and
* cl_count is updated to be the number of chunks (ie.
* unique position values) in the Read list.
* %false: Memory allocation failed.
*
* TODO:
* - Check for chunk range overlaps
*/
bool pcl_alloc_read(struct svc_rdma_recv_ctxt *rctxt, __be32 *p)
{
struct svc_rdma_pcl *pcl = &rctxt->rc_read_pcl;
unsigned int i, segcount = pcl->cl_count;
pcl->cl_count = 0;
for (i = 0; i < segcount; i++) {
struct svc_rdma_chunk *chunk;
u32 position, handle, length;
u64 offset;
p++; /* skip the list discriminator */
p = xdr_decode_read_segment(p, &position, &handle,
&length, &offset);
if (position == 0)
continue;
chunk = pcl_lookup_position(pcl, position);
if (!chunk) {
chunk = pcl_alloc_chunk(segcount, position);
if (!chunk)
return false;
pcl_insert_position(pcl, chunk);
}
pcl_set_read_segment(rctxt, chunk, handle, length, offset);
}
return true;
}
/**
* pcl_alloc_write - Construct a parsed chunk list from a Write list
* @rctxt: Ingress receive context
* @pcl: Parsed chunk list to populate
* @p: Start of an un-decoded Write list
*
* Assumptions:
* - The incoming Write list has already been sanity checked, and
* - cl_count is set to the number of chunks in the un-decoded list.
*
* Return values:
* %true: Parsed chunk list was successfully constructed.
* %false: Memory allocation failed.
*/
bool pcl_alloc_write(struct svc_rdma_recv_ctxt *rctxt,
struct svc_rdma_pcl *pcl, __be32 *p)
{
struct svc_rdma_segment *segment;
struct svc_rdma_chunk *chunk;
unsigned int i, j;
u32 segcount;
for (i = 0; i < pcl->cl_count; i++) {
p++; /* skip the list discriminator */
segcount = be32_to_cpup(p++);
chunk = pcl_alloc_chunk(segcount, 0);
if (!chunk)
return false;
list_add_tail(&chunk->ch_list, &pcl->cl_chunks);
for (j = 0; j < segcount; j++) {
segment = &chunk->ch_segments[j];
p = xdr_decode_rdma_segment(p, &segment->rs_handle,
&segment->rs_length,
&segment->rs_offset);
trace_svcrdma_decode_wseg(&rctxt->rc_cid, chunk, j);
chunk->ch_length += segment->rs_length;
chunk->ch_segcount++;
}
}
return true;
}
static int pcl_process_region(const struct xdr_buf *xdr,
unsigned int offset, unsigned int length,
int (*actor)(const struct xdr_buf *, void *),
void *data)
{
struct xdr_buf subbuf;
if (!length)
return 0;
if (xdr_buf_subsegment(xdr, &subbuf, offset, length))
return -EMSGSIZE;
return actor(&subbuf, data);
}
/**
* pcl_process_nonpayloads - Process non-payload regions inside @xdr
* @pcl: Chunk list to process
* @xdr: xdr_buf to process
* @actor: Function to invoke on each non-payload region
* @data: Arguments for @actor
*
* This mechanism must ignore not only result payloads that were already
* sent via RDMA Write, but also XDR padding for those payloads that
* the upper layer has added.
*
* Assumptions:
* The xdr->len and ch_position fields are aligned to 4-byte multiples.
*
* Returns:
* On success, zero,
* %-EMSGSIZE on XDR buffer overflow, or
* The return value of @actor
*/
int pcl_process_nonpayloads(const struct svc_rdma_pcl *pcl,
const struct xdr_buf *xdr,
int (*actor)(const struct xdr_buf *, void *),
void *data)
{
struct svc_rdma_chunk *chunk, *next;
unsigned int start;
int ret;
chunk = pcl_first_chunk(pcl);
/* No result payloads were generated */
if (!chunk || !chunk->ch_payload_length)
return actor(xdr, data);
/* Process the region before the first result payload */
ret = pcl_process_region(xdr, 0, chunk->ch_position, actor, data);
if (ret < 0)
return ret;
/* Process the regions between each middle result payload */
while ((next = pcl_next_chunk(pcl, chunk))) {
if (!next->ch_payload_length)
break;
start = pcl_chunk_end_offset(chunk);
ret = pcl_process_region(xdr, start, next->ch_position - start,
actor, data);
if (ret < 0)
return ret;
chunk = next;
}
/* Process the region after the last result payload */
start = pcl_chunk_end_offset(chunk);
ret = pcl_process_region(xdr, start, xdr->len - start, actor, data);
if (ret < 0)
return ret;
return 0;
}

316
net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
View File

@ -93,6 +93,7 @@
* (see rdma_read_complete() below).
*/
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <asm/unaligned.h>
#include <rdma/ib_verbs.h>
@ -143,6 +144,10 @@ svc_rdma_recv_ctxt_alloc(struct svcxprt_rdma *rdma)
goto fail2;
svc_rdma_recv_cid_init(rdma, &ctxt->rc_cid);
pcl_init(&ctxt->rc_call_pcl);
pcl_init(&ctxt->rc_read_pcl);
pcl_init(&ctxt->rc_write_pcl);
pcl_init(&ctxt->rc_reply_pcl);
ctxt->rc_recv_wr.next = NULL;
ctxt->rc_recv_wr.wr_cqe = &ctxt->rc_cqe;
@ -189,8 +194,13 @@ void svc_rdma_recv_ctxts_destroy(struct svcxprt_rdma *rdma)
}
}
static struct svc_rdma_recv_ctxt *
svc_rdma_recv_ctxt_get(struct svcxprt_rdma *rdma)
/**
* svc_rdma_recv_ctxt_get - Allocate a recv_ctxt
* @rdma: controlling svcxprt_rdma
*
* Returns a recv_ctxt or (rarely) NULL if none are available.
*/
struct svc_rdma_recv_ctxt *svc_rdma_recv_ctxt_get(struct svcxprt_rdma *rdma)
{
struct svc_rdma_recv_ctxt *ctxt;
struct llist_node *node;
@ -202,7 +212,6 @@ svc_rdma_recv_ctxt_get(struct svcxprt_rdma *rdma)
out:
ctxt->rc_page_count = 0;
ctxt->rc_read_payload_length = 0;
return ctxt;
out_empty:
@ -226,6 +235,11 @@ void svc_rdma_recv_ctxt_put(struct svcxprt_rdma *rdma,
for (i = 0; i < ctxt->rc_page_count; i++)
put_page(ctxt->rc_pages[i]);
pcl_free(&ctxt->rc_call_pcl);
pcl_free(&ctxt->rc_read_pcl);
pcl_free(&ctxt->rc_write_pcl);
pcl_free(&ctxt->rc_reply_pcl);
if (!ctxt->rc_temp)
llist_add(&ctxt->rc_node, &rdma->sc_recv_ctxts);
else
@ -385,100 +399,123 @@ static void svc_rdma_build_arg_xdr(struct svc_rqst *rqstp,
arg->len = ctxt->rc_byte_len;
}
/* This accommodates the largest possible Write chunk.
*/
#define MAX_BYTES_WRITE_CHUNK ((u32)(RPCSVC_MAXPAGES << PAGE_SHIFT))
/* This accommodates the largest possible Position-Zero
* Read chunk or Reply chunk.
*/
#define MAX_BYTES_SPECIAL_CHUNK ((u32)((RPCSVC_MAXPAGES + 2) << PAGE_SHIFT))
/* Sanity check the Read list.
/**
* xdr_count_read_segments - Count number of Read segments in Read list
* @rctxt: Ingress receive context
* @p: Start of an un-decoded Read list
*
* Implementation limits:
* - This implementation supports only one Read chunk.
* Before allocating anything, ensure the ingress Read list is safe
* to use.
*
* Sanity checks:
* - Read list does not overflow Receive buffer.
* - Segment size limited by largest NFS data payload.
*
* The segment count is limited to how many segments can
* fit in the transport header without overflowing the
* buffer. That's about 40 Read segments for a 1KB inline
* threshold.
* The segment count is limited to how many segments can fit in the
* transport header without overflowing the buffer. That's about 40
* Read segments for a 1KB inline threshold.
*
* Return values:
* %true: Read list is valid. @rctxt's xdr_stream is updated
* to point to the first byte past the Read list.
* %false: Read list is corrupt. @rctxt's xdr_stream is left
* in an unknown state.
* %true: Read list is valid. @rctxt's xdr_stream is updated to point
* to the first byte past the Read list. rc_read_pcl and
* rc_call_pcl cl_count fields are set to the number of
* Read segments in the list.
* %false: Read list is corrupt. @rctxt's xdr_stream is left in an
* unknown state.
*/
static bool xdr_check_read_list(struct svc_rdma_recv_ctxt *rctxt)
static bool xdr_count_read_segments(struct svc_rdma_recv_ctxt *rctxt, __be32 *p)
{
u32 position, len;
bool first;
__be32 *p;
p = xdr_inline_decode(&rctxt->rc_stream, sizeof(*p));
if (!p)
return false;
len = 0;
first = true;
rctxt->rc_call_pcl.cl_count = 0;
rctxt->rc_read_pcl.cl_count = 0;
while (xdr_item_is_present(p)) {
u32 position, handle, length;
u64 offset;
p = xdr_inline_decode(&rctxt->rc_stream,
rpcrdma_readseg_maxsz * sizeof(*p));
if (!p)
return false;
if (first) {
position = be32_to_cpup(p);
first = false;
} else if (be32_to_cpup(p) != position) {
return false;
xdr_decode_read_segment(p, &position, &handle,
&length, &offset);
if (position) {
if (position & 3)
return false;
++rctxt->rc_read_pcl.cl_count;
} else {
++rctxt->rc_call_pcl.cl_count;
}
p += 2;
len += be32_to_cpup(p);
p = xdr_inline_decode(&rctxt->rc_stream, sizeof(*p));
if (!p)
return false;
}
return len <= MAX_BYTES_SPECIAL_CHUNK;
return true;
}
/* The segment count is limited to how many segments can
* fit in the transport header without overflowing the
* buffer. That's about 60 Write segments for a 1KB inline
* threshold.
/* Sanity check the Read list.
*
* Sanity checks:
* - Read list does not overflow Receive buffer.
* - Chunk size limited by largest NFS data payload.
*
* Return values:
* %true: Read list is valid. @rctxt's xdr_stream is updated
* to point to the first byte past the Read list.
* %false: Read list is corrupt. @rctxt's xdr_stream is left
* in an unknown state.
*/
static bool xdr_check_write_chunk(struct svc_rdma_recv_ctxt *rctxt, u32 maxlen)
static bool xdr_check_read_list(struct svc_rdma_recv_ctxt *rctxt)
{
u32 i, segcount, total;
__be32 *p;
p = xdr_inline_decode(&rctxt->rc_stream, sizeof(*p));
if (!p)
return false;
segcount = be32_to_cpup(p);
if (!xdr_count_read_segments(rctxt, p))
return false;
if (!pcl_alloc_call(rctxt, p))
return false;
return pcl_alloc_read(rctxt, p);
}
total = 0;
for (i = 0; i < segcount; i++) {
u32 handle, length;
u64 offset;
static bool xdr_check_write_chunk(struct svc_rdma_recv_ctxt *rctxt)
{
u32 segcount;
__be32 *p;
p = xdr_inline_decode(&rctxt->rc_stream,
rpcrdma_segment_maxsz * sizeof(*p));
if (xdr_stream_decode_u32(&rctxt->rc_stream, &segcount))
return false;
/* A bogus segcount causes this buffer overflow check to fail. */
p = xdr_inline_decode(&rctxt->rc_stream,
segcount * rpcrdma_segment_maxsz * sizeof(*p));
return p != NULL;
}
/**
* xdr_count_write_chunks - Count number of Write chunks in Write list
* @rctxt: Received header and decoding state
* @p: start of an un-decoded Write list
*
* Before allocating anything, ensure the ingress Write list is
* safe to use.
*
* Return values:
* %true: Write list is valid. @rctxt's xdr_stream is updated
* to point to the first byte past the Write list, and
* the number of Write chunks is in rc_write_pcl.cl_count.
* %false: Write list is corrupt. @rctxt's xdr_stream is left
* in an indeterminate state.
*/
static bool xdr_count_write_chunks(struct svc_rdma_recv_ctxt *rctxt, __be32 *p)
{
rctxt->rc_write_pcl.cl_count = 0;
while (xdr_item_is_present(p)) {
if (!xdr_check_write_chunk(rctxt))
return false;
++rctxt->rc_write_pcl.cl_count;
p = xdr_inline_decode(&rctxt->rc_stream, sizeof(*p));
if (!p)
return false;
xdr_decode_rdma_segment(p, &handle, &length, &offset);
trace_svcrdma_decode_wseg(handle, length, offset);
total += length;
}
return total <= maxlen;
return true;
}
/* Sanity check the Write list.
@ -498,24 +535,18 @@ static bool xdr_check_write_chunk(struct svc_rdma_recv_ctxt *rctxt, u32 maxlen)
*/
static bool xdr_check_write_list(struct svc_rdma_recv_ctxt *rctxt)
{
u32 chcount = 0;
__be32 *p;
p = xdr_inline_decode(&rctxt->rc_stream, sizeof(*p));
if (!p)
return false;
rctxt->rc_write_list = p;
while (xdr_item_is_present(p)) {
if (!xdr_check_write_chunk(rctxt, MAX_BYTES_WRITE_CHUNK))
return false;
++chcount;
p = xdr_inline_decode(&rctxt->rc_stream, sizeof(*p));
if (!p)
return false;
}
if (!chcount)
rctxt->rc_write_list = NULL;
return chcount < 2;
if (!xdr_count_write_chunks(rctxt, p))
return false;
if (!pcl_alloc_write(rctxt, &rctxt->rc_write_pcl, p))
return false;
rctxt->rc_cur_result_payload = pcl_first_chunk(&rctxt->rc_write_pcl);
return true;
}
/* Sanity check the Reply chunk.
@ -537,13 +568,14 @@ static bool xdr_check_reply_chunk(struct svc_rdma_recv_ctxt *rctxt)
p = xdr_inline_decode(&rctxt->rc_stream, sizeof(*p));
if (!p)
return false;
rctxt->rc_reply_chunk = NULL;
if (xdr_item_is_present(p)) {
if (!xdr_check_write_chunk(rctxt, MAX_BYTES_SPECIAL_CHUNK))
return false;
rctxt->rc_reply_chunk = p;
}
return true;
if (!xdr_item_is_present(p))
return true;
if (!xdr_check_write_chunk(rctxt))
return false;
rctxt->rc_reply_pcl.cl_count = 1;
return pcl_alloc_write(rctxt, &rctxt->rc_reply_pcl, p);
}
/* RPC-over-RDMA Version One private extension: Remote Invalidation.
@ -552,60 +584,53 @@ static bool xdr_check_reply_chunk(struct svc_rdma_recv_ctxt *rctxt)
*
* If there is exactly one distinct R_key in the received transport
* header, set rc_inv_rkey to that R_key. Otherwise, set it to zero.
*
* Perform this operation while the received transport header is
* still in the CPU cache.
*/
static void svc_rdma_get_inv_rkey(struct svcxprt_rdma *rdma,
struct svc_rdma_recv_ctxt *ctxt)
{
__be32 inv_rkey, *p;
u32 i, segcount;
struct svc_rdma_segment *segment;
struct svc_rdma_chunk *chunk;
u32 inv_rkey;
ctxt->rc_inv_rkey = 0;
if (!rdma->sc_snd_w_inv)
return;
inv_rkey = xdr_zero;
p = ctxt->rc_recv_buf;
p += rpcrdma_fixed_maxsz;
/* Read list */
while (xdr_item_is_present(p++)) {
p++; /* position */
if (inv_rkey == xdr_zero)
inv_rkey = *p;
else if (inv_rkey != *p)
return;
p += 4;
}
/* Write list */
while (xdr_item_is_present(p++)) {
segcount = be32_to_cpup(p++);
for (i = 0; i < segcount; i++) {
if (inv_rkey == xdr_zero)
inv_rkey = *p;
else if (inv_rkey != *p)
inv_rkey = 0;
pcl_for_each_chunk(chunk, &ctxt->rc_call_pcl) {
pcl_for_each_segment(segment, chunk) {
if (inv_rkey == 0)
inv_rkey = segment->rs_handle;
else if (inv_rkey != segment->rs_handle)
return;
p += 4;
}
}
/* Reply chunk */
if (xdr_item_is_present(p++)) {
segcount = be32_to_cpup(p++);
for (i = 0; i < segcount; i++) {
if (inv_rkey == xdr_zero)
inv_rkey = *p;
else if (inv_rkey != *p)
pcl_for_each_chunk(chunk, &ctxt->rc_read_pcl) {
pcl_for_each_segment(segment, chunk) {
if (inv_rkey == 0)
inv_rkey = segment->rs_handle;
else if (inv_rkey != segment->rs_handle)
return;
p += 4;
}
}
ctxt->rc_inv_rkey = be32_to_cpu(inv_rkey);
pcl_for_each_chunk(chunk, &ctxt->rc_write_pcl) {
pcl_for_each_segment(segment, chunk) {
if (inv_rkey == 0)
inv_rkey = segment->rs_handle;
else if (inv_rkey != segment->rs_handle)
return;
}
}
pcl_for_each_chunk(chunk, &ctxt->rc_reply_pcl) {
pcl_for_each_segment(segment, chunk) {
if (inv_rkey == 0)
inv_rkey = segment->rs_handle;
else if (inv_rkey != segment->rs_handle)
return;
}
}
ctxt->rc_inv_rkey = inv_rkey;
}
/**
@ -641,7 +666,8 @@ static int svc_rdma_xdr_decode_req(struct xdr_buf *rq_arg,
if (*p != rpcrdma_version)
goto out_version;
p += 2;
switch (*p) {
rctxt->rc_msgtype = *p;
switch (rctxt->rc_msgtype) {
case rdma_msg:
break;
case rdma_nomsg:
@ -735,30 +761,28 @@ static void svc_rdma_send_error(struct svcxprt_rdma *rdma,
* the RPC/RDMA header small and fixed in size, so it is
* straightforward to check the RPC header's direction field.
*/
static bool svc_rdma_is_backchannel_reply(struct svc_xprt *xprt,
__be32 *rdma_resp)
static bool svc_rdma_is_reverse_direction_reply(struct svc_xprt *xprt,
struct svc_rdma_recv_ctxt *rctxt)
{
__be32 *p;
__be32 *p = rctxt->rc_recv_buf;
if (!xprt->xpt_bc_xprt)
return false;
p = rdma_resp + 3;
if (*p++ != rdma_msg)
if (rctxt->rc_msgtype != rdma_msg)
return false;
if (*p++ != xdr_zero)
if (!pcl_is_empty(&rctxt->rc_call_pcl))
return false;
if (*p++ != xdr_zero)
if (!pcl_is_empty(&rctxt->rc_read_pcl))
return false;
if (*p++ != xdr_zero)
if (!pcl_is_empty(&rctxt->rc_write_pcl))
return false;
if (!pcl_is_empty(&rctxt->rc_reply_pcl))
return false;
/* XID sanity */
if (*p++ != *rdma_resp)
return false;
/* call direction */
if (*p == cpu_to_be32(RPC_CALL))
/* RPC call direction */
if (*(p + 8) == cpu_to_be32(RPC_CALL))
return false;
return true;
@ -800,7 +824,6 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp)
struct svcxprt_rdma *rdma_xprt =
container_of(xprt, struct svcxprt_rdma, sc_xprt);
struct svc_rdma_recv_ctxt *ctxt;
__be32 *p;
int ret;
rqstp->rq_xprt_ctxt = NULL;
@ -833,7 +856,6 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp)
rqstp->rq_respages = rqstp->rq_pages;
rqstp->rq_next_page = rqstp->rq_respages;
p = (__be32 *)rqstp->rq_arg.head[0].iov_base;
ret = svc_rdma_xdr_decode_req(&rqstp->rq_arg, ctxt);
if (ret < 0)
goto out_err;
@ -841,14 +863,14 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp)
goto out_drop;
rqstp->rq_xprt_hlen = ret;
if (svc_rdma_is_backchannel_reply(xprt, p))
if (svc_rdma_is_reverse_direction_reply(xprt, ctxt))
goto out_backchannel;
svc_rdma_get_inv_rkey(rdma_xprt, ctxt);
p += rpcrdma_fixed_maxsz;
if (*p != xdr_zero)
goto out_readchunk;
if (!pcl_is_empty(&ctxt->rc_read_pcl) ||
!pcl_is_empty(&ctxt->rc_call_pcl))
goto out_readlist;
complete:
rqstp->rq_xprt_ctxt = ctxt;
@ -856,10 +878,10 @@ complete:
svc_xprt_copy_addrs(rqstp, xprt);
return rqstp->rq_arg.len;
out_readchunk:
ret = svc_rdma_recv_read_chunk(rdma_xprt, rqstp, ctxt, p);
out_readlist:
ret = svc_rdma_process_read_list(rdma_xprt, rqstp, ctxt);
if (ret < 0)
goto out_postfail;
goto out_readfail;
return 0;
out_err:
@ -867,7 +889,7 @@ out_err:
svc_rdma_recv_ctxt_put(rdma_xprt, ctxt);
return 0;
out_postfail:
out_readfail:
if (ret == -EINVAL)
svc_rdma_send_error(rdma_xprt, ctxt, ret);
svc_rdma_recv_ctxt_put(rdma_xprt, ctxt);

608
net/sunrpc/xprtrdma/svc_rdma_rw.c
View File

@ -190,14 +190,14 @@ static void svc_rdma_cc_release(struct svc_rdma_chunk_ctxt *cc,
* - Stores arguments for the SGL constructor functions
*/
struct svc_rdma_write_info {
const struct svc_rdma_chunk *wi_chunk;
/* write state of this chunk */
unsigned int wi_seg_off;
unsigned int wi_seg_no;
unsigned int wi_nsegs;
__be32 *wi_segs;
/* SGL constructor arguments */
struct xdr_buf *wi_xdr;
const struct xdr_buf *wi_xdr;
unsigned char *wi_base;
unsigned int wi_next_off;
@ -205,7 +205,8 @@ struct svc_rdma_write_info {
};
static struct svc_rdma_write_info *
svc_rdma_write_info_alloc(struct svcxprt_rdma *rdma, __be32 *chunk)
svc_rdma_write_info_alloc(struct svcxprt_rdma *rdma,
const struct svc_rdma_chunk *chunk)
{
struct svc_rdma_write_info *info;
@ -213,10 +214,9 @@ svc_rdma_write_info_alloc(struct svcxprt_rdma *rdma, __be32 *chunk)
if (!info)
return info;
info->wi_chunk = chunk;
info->wi_seg_off = 0;
info->wi_seg_no = 0;
info->wi_nsegs = be32_to_cpup(++chunk);
info->wi_segs = ++chunk;
svc_rdma_cc_init(rdma, &info->wi_cc);
info->wi_cc.cc_cqe.done = svc_rdma_write_done;
return info;
@ -258,11 +258,11 @@ static void svc_rdma_write_done(struct ib_cq *cq, struct ib_wc *wc)
/* State for pulling a Read chunk.
*/
struct svc_rdma_read_info {
struct svc_rqst *ri_rqst;
struct svc_rdma_recv_ctxt *ri_readctxt;
unsigned int ri_position;
unsigned int ri_pageno;
unsigned int ri_pageoff;
unsigned int ri_chunklen;
unsigned int ri_totalbytes;
struct svc_rdma_chunk_ctxt ri_cc;
};
@ -358,7 +358,6 @@ static int svc_rdma_post_chunk_ctxt(struct svc_rdma_chunk_ctxt *cc)
do {
if (atomic_sub_return(cc->cc_sqecount,
&rdma->sc_sq_avail) > 0) {
trace_svcrdma_post_chunk(&cc->cc_cid, cc->cc_sqecount);
ret = ib_post_send(rdma->sc_qp, first_wr, &bad_wr);
if (ret)
break;
@ -405,7 +404,7 @@ static void svc_rdma_pagelist_to_sg(struct svc_rdma_write_info *info,
struct svc_rdma_rw_ctxt *ctxt)
{
unsigned int sge_no, sge_bytes, page_off, page_no;
struct xdr_buf *xdr = info->wi_xdr;
const struct xdr_buf *xdr = info->wi_xdr;
struct scatterlist *sg;
struct page **page;
@ -443,40 +442,36 @@ svc_rdma_build_writes(struct svc_rdma_write_info *info,
{
struct svc_rdma_chunk_ctxt *cc = &info->wi_cc;
struct svcxprt_rdma *rdma = cc->cc_rdma;
const struct svc_rdma_segment *seg;
struct svc_rdma_rw_ctxt *ctxt;
__be32 *seg;
int ret;
seg = info->wi_segs + info->wi_seg_no * rpcrdma_segment_maxsz;
do {
unsigned int write_len;
u32 handle, length;
u64 offset;
if (info->wi_seg_no >= info->wi_nsegs)
seg = &info->wi_chunk->ch_segments[info->wi_seg_no];
if (!seg)
goto out_overflow;
xdr_decode_rdma_segment(seg, &handle, &length, &offset);
offset += info->wi_seg_off;
write_len = min(remaining, length - info->wi_seg_off);
write_len = min(remaining, seg->rs_length - info->wi_seg_off);
if (!write_len)
goto out_overflow;
ctxt = svc_rdma_get_rw_ctxt(rdma,
(write_len >> PAGE_SHIFT) + 2);
if (!ctxt)
return -ENOMEM;
constructor(info, write_len, ctxt);
ret = svc_rdma_rw_ctx_init(rdma, ctxt, offset, handle,
offset = seg->rs_offset + info->wi_seg_off;
ret = svc_rdma_rw_ctx_init(rdma, ctxt, offset, seg->rs_handle,
DMA_TO_DEVICE);
if (ret < 0)
return -EIO;
trace_svcrdma_send_wseg(handle, write_len, offset);
list_add(&ctxt->rw_list, &cc->cc_rwctxts);
cc->cc_sqecount += ret;
if (write_len == length - info->wi_seg_off) {
seg += 4;
if (write_len == seg->rs_length - info->wi_seg_off) {
info->wi_seg_no++;
info->wi_seg_off = 0;
} else {
@ -489,31 +484,46 @@ svc_rdma_build_writes(struct svc_rdma_write_info *info,
out_overflow:
trace_svcrdma_small_wrch_err(rdma, remaining, info->wi_seg_no,
info->wi_nsegs);
info->wi_chunk->ch_segcount);
return -E2BIG;
}
/* Send one of an xdr_buf's kvecs by itself. To send a Reply
* chunk, the whole RPC Reply is written back to the client.
* This function writes either the head or tail of the xdr_buf
* containing the Reply.
/**
* svc_rdma_iov_write - Construct RDMA Writes from an iov
* @info: pointer to write arguments
* @iov: kvec to write
*
* Returns:
* On succes, returns zero
* %-E2BIG if the client-provided Write chunk is too small
* %-ENOMEM if a resource has been exhausted
* %-EIO if an rdma-rw error occurred
*/
static int svc_rdma_send_xdr_kvec(struct svc_rdma_write_info *info,
struct kvec *vec)
static int svc_rdma_iov_write(struct svc_rdma_write_info *info,
const struct kvec *iov)
{
info->wi_base = vec->iov_base;
info->wi_base = iov->iov_base;
return svc_rdma_build_writes(info, svc_rdma_vec_to_sg,
vec->iov_len);
iov->iov_len);
}
/* Send an xdr_buf's page list by itself. A Write chunk is just
* the page list. A Reply chunk is @xdr's head, page list, and
* tail. This function is shared between the two types of chunk.
/**
* svc_rdma_pages_write - Construct RDMA Writes from pages
* @info: pointer to write arguments
* @xdr: xdr_buf with pages to write
* @offset: offset into the content of @xdr
* @length: number of bytes to write
*
* Returns:
* On succes, returns zero
* %-E2BIG if the client-provided Write chunk is too small
* %-ENOMEM if a resource has been exhausted
* %-EIO if an rdma-rw error occurred
*/
static int svc_rdma_send_xdr_pagelist(struct svc_rdma_write_info *info,
struct xdr_buf *xdr,
unsigned int offset,
unsigned long length)
static int svc_rdma_pages_write(struct svc_rdma_write_info *info,
const struct xdr_buf *xdr,
unsigned int offset,
unsigned long length)
{
info->wi_xdr = xdr;
info->wi_next_off = offset - xdr->head[0].iov_len;
@ -521,13 +531,49 @@ static int svc_rdma_send_xdr_pagelist(struct svc_rdma_write_info *info,
length);
}
/**
* svc_rdma_xb_write - Construct RDMA Writes to write an xdr_buf
* @xdr: xdr_buf to write
* @data: pointer to write arguments
*
* Returns:
* On succes, returns zero
* %-E2BIG if the client-provided Write chunk is too small
* %-ENOMEM if a resource has been exhausted
* %-EIO if an rdma-rw error occurred
*/
static int svc_rdma_xb_write(const struct xdr_buf *xdr, void *data)
{
struct svc_rdma_write_info *info = data;
int ret;
if (xdr->head[0].iov_len) {
ret = svc_rdma_iov_write(info, &xdr->head[0]);
if (ret < 0)
return ret;
}
if (xdr->page_len) {
ret = svc_rdma_pages_write(info, xdr, xdr->head[0].iov_len,
xdr->page_len);
if (ret < 0)
return ret;
}
if (xdr->tail[0].iov_len) {
ret = svc_rdma_iov_write(info, &xdr->tail[0]);
if (ret < 0)
return ret;
}
return xdr->len;
}
/**
* svc_rdma_send_write_chunk - Write all segments in a Write chunk
* @rdma: controlling RDMA transport
* @wr_ch: Write chunk provided by client
* @chunk: Write chunk provided by the client
* @xdr: xdr_buf containing the data payload
* @offset: payload's byte offset in @xdr
* @length: size of payload, in bytes
*
* Returns a non-negative number of bytes the chunk consumed, or
* %-E2BIG if the payload was larger than the Write chunk,
@ -536,30 +582,28 @@ static int svc_rdma_send_xdr_pagelist(struct svc_rdma_write_info *info,
* %-ENOTCONN if posting failed (connection is lost),
* %-EIO if rdma_rw initialization failed (DMA mapping, etc).
*/
int svc_rdma_send_write_chunk(struct svcxprt_rdma *rdma, __be32 *wr_ch,
struct xdr_buf *xdr,
unsigned int offset, unsigned long length)
int svc_rdma_send_write_chunk(struct svcxprt_rdma *rdma,
const struct svc_rdma_chunk *chunk,
const struct xdr_buf *xdr)
{
struct svc_rdma_write_info *info;
struct svc_rdma_chunk_ctxt *cc;
int ret;
if (!length)
return 0;
info = svc_rdma_write_info_alloc(rdma, wr_ch);
info = svc_rdma_write_info_alloc(rdma, chunk);
if (!info)
return -ENOMEM;
cc = &info->wi_cc;
ret = svc_rdma_send_xdr_pagelist(info, xdr, offset, length);
if (ret < 0)
ret = svc_rdma_xb_write(xdr, info);
if (ret != xdr->len)
goto out_err;
ret = svc_rdma_post_chunk_ctxt(&info->wi_cc);
trace_svcrdma_post_write_chunk(&cc->cc_cid, cc->cc_sqecount);
ret = svc_rdma_post_chunk_ctxt(cc);
if (ret < 0)
goto out_err;
trace_svcrdma_send_write_chunk(xdr->page_len);
return length;
return xdr->len;
out_err:
svc_rdma_write_info_free(info);
@ -581,62 +625,62 @@ out_err:
*/
int svc_rdma_send_reply_chunk(struct svcxprt_rdma *rdma,
const struct svc_rdma_recv_ctxt *rctxt,
struct xdr_buf *xdr)
const struct xdr_buf *xdr)
{
struct svc_rdma_write_info *info;
int consumed, ret;
struct svc_rdma_chunk_ctxt *cc;
struct svc_rdma_chunk *chunk;
int ret;
info = svc_rdma_write_info_alloc(rdma, rctxt->rc_reply_chunk);
if (pcl_is_empty(&rctxt->rc_reply_pcl))
return 0;
chunk = pcl_first_chunk(&rctxt->rc_reply_pcl);
info = svc_rdma_write_info_alloc(rdma, chunk);
if (!info)
return -ENOMEM;
cc = &info->wi_cc;
ret = svc_rdma_send_xdr_kvec(info, &xdr->head[0]);
if (ret < 0)
goto out_err;
consumed = xdr->head[0].iov_len;
/* Send the page list in the Reply chunk only if the
* client did not provide Write chunks.
*/
if (!rctxt->rc_write_list && xdr->page_len) {
ret = svc_rdma_send_xdr_pagelist(info, xdr,
xdr->head[0].iov_len,
xdr->page_len);
if (ret < 0)
goto out_err;
consumed += xdr->page_len;
}
if (xdr->tail[0].iov_len) {
ret = svc_rdma_send_xdr_kvec(info, &xdr->tail[0]);
if (ret < 0)
goto out_err;
consumed += xdr->tail[0].iov_len;
}
ret = svc_rdma_post_chunk_ctxt(&info->wi_cc);
ret = pcl_process_nonpayloads(&rctxt->rc_write_pcl, xdr,
svc_rdma_xb_write, info);
if (ret < 0)
goto out_err;
trace_svcrdma_send_reply_chunk(consumed);
return consumed;
trace_svcrdma_post_reply_chunk(&cc->cc_cid, cc->cc_sqecount);
ret = svc_rdma_post_chunk_ctxt(cc);
if (ret < 0)
goto out_err;
return xdr->len;
out_err:
svc_rdma_write_info_free(info);
return ret;
}
/**
* svc_rdma_build_read_segment - Build RDMA Read WQEs to pull one RDMA segment
* @info: context for ongoing I/O
* @segment: co-ordinates of remote memory to be read
*
* Returns:
* %0: the Read WR chain was constructed successfully
* %-EINVAL: there were not enough rq_pages to finish
* %-ENOMEM: allocating a local resources failed
* %-EIO: a DMA mapping error occurred
*/
static int svc_rdma_build_read_segment(struct svc_rdma_read_info *info,
struct svc_rqst *rqstp,
u32 rkey, u32 len, u64 offset)
const struct svc_rdma_segment *segment)
{
struct svc_rdma_recv_ctxt *head = info->ri_readctxt;
struct svc_rdma_chunk_ctxt *cc = &info->ri_cc;
struct svc_rqst *rqstp = info->ri_rqst;
struct svc_rdma_rw_ctxt *ctxt;
unsigned int sge_no, seg_len;
unsigned int sge_no, seg_len, len;
struct scatterlist *sg;
int ret;
len = segment->rs_length;
sge_no = PAGE_ALIGN(info->ri_pageoff + len) >> PAGE_SHIFT;
ctxt = svc_rdma_get_rw_ctxt(cc->cc_rdma, sge_no);
if (!ctxt)
@ -670,8 +714,8 @@ static int svc_rdma_build_read_segment(struct svc_rdma_read_info *info,
goto out_overrun;
}
ret = svc_rdma_rw_ctx_init(cc->cc_rdma, ctxt, offset, rkey,
DMA_FROM_DEVICE);
ret = svc_rdma_rw_ctx_init(cc->cc_rdma, ctxt, segment->rs_offset,
segment->rs_handle, DMA_FROM_DEVICE);
if (ret < 0)
return -EIO;
@ -684,54 +728,177 @@ out_overrun:
return -EINVAL;
}
/* Walk the segments in the Read chunk starting at @p and construct
* RDMA Read operations to pull the chunk to the server.
/**
* svc_rdma_build_read_chunk - Build RDMA Read WQEs to pull one RDMA chunk
* @info: context for ongoing I/O
* @chunk: Read chunk to pull
*
* Return values:
* %0: the Read WR chain was constructed successfully
* %-EINVAL: there were not enough resources to finish
* %-ENOMEM: allocating a local resources failed
* %-EIO: a DMA mapping error occurred
*/
static int svc_rdma_build_read_chunk(struct svc_rqst *rqstp,
struct svc_rdma_read_info *info,
__be32 *p)
static int svc_rdma_build_read_chunk(struct svc_rdma_read_info *info,
const struct svc_rdma_chunk *chunk)
{
const struct svc_rdma_segment *segment;
int ret;
ret = -EINVAL;
info->ri_chunklen = 0;
while (*p++ != xdr_zero && be32_to_cpup(p++) == info->ri_position) {
u32 handle, length;
u64 offset;
p = xdr_decode_rdma_segment(p, &handle, &length, &offset);
ret = svc_rdma_build_read_segment(info, rqstp, handle, length,
offset);
pcl_for_each_segment(segment, chunk) {
ret = svc_rdma_build_read_segment(info, segment);
if (ret < 0)
break;
trace_svcrdma_send_rseg(handle, length, offset);
info->ri_chunklen += length;
info->ri_totalbytes += segment->rs_length;
}
return ret;
}
/* Construct RDMA Reads to pull over a normal Read chunk. The chunk
* data lands in the page list of head->rc_arg.pages.
/**
* svc_rdma_copy_inline_range - Copy part of the inline content into pages
* @info: context for RDMA Reads
* @offset: offset into the Receive buffer of region to copy
* @remaining: length of region to copy
*
* Take a page at a time from rqstp->rq_pages and copy the inline
* content from the Receive buffer into that page. Update
* info->ri_pageno and info->ri_pageoff so that the next RDMA Read
* result will land contiguously with the copied content.
*
* Return values:
* %0: Inline content was successfully copied
* %-EINVAL: offset or length was incorrect
*/
static int svc_rdma_copy_inline_range(struct svc_rdma_read_info *info,
unsigned int offset,
unsigned int remaining)
{
struct svc_rdma_recv_ctxt *head = info->ri_readctxt;
unsigned char *dst, *src = head->rc_recv_buf;
struct svc_rqst *rqstp = info->ri_rqst;
unsigned int page_no, numpages;
numpages = PAGE_ALIGN(info->ri_pageoff + remaining) >> PAGE_SHIFT;
for (page_no = 0; page_no < numpages; page_no++) {
unsigned int page_len;
page_len = min_t(unsigned int, remaining,
PAGE_SIZE - info->ri_pageoff);
head->rc_arg.pages[info->ri_pageno] =
rqstp->rq_pages[info->ri_pageno];
if (!info->ri_pageoff)
head->rc_page_count++;
dst = page_address(head->rc_arg.pages[info->ri_pageno]);
memcpy(dst + info->ri_pageno, src + offset, page_len);
info->ri_totalbytes += page_len;
info->ri_pageoff += page_len;
if (info->ri_pageoff == PAGE_SIZE) {
info->ri_pageno++;
info->ri_pageoff = 0;
}
remaining -= page_len;
offset += page_len;
}
return -EINVAL;
}
/**
* svc_rdma_read_multiple_chunks - Construct RDMA Reads to pull data item Read chunks
* @info: context for RDMA Reads
*
* The chunk data lands in head->rc_arg as a series of contiguous pages,
* like an incoming TCP call.
*
* Return values:
* %0: RDMA Read WQEs were successfully built
* %-EINVAL: client provided too many chunks or segments,
* %-ENOMEM: rdma_rw context pool was exhausted,
* %-ENOTCONN: posting failed (connection is lost),
* %-EIO: rdma_rw initialization failed (DMA mapping, etc).
*/
static noinline int svc_rdma_read_multiple_chunks(struct svc_rdma_read_info *info)
{
struct svc_rdma_recv_ctxt *head = info->ri_readctxt;
const struct svc_rdma_pcl *pcl = &head->rc_read_pcl;
struct svc_rdma_chunk *chunk, *next;
struct xdr_buf *buf = &head->rc_arg;
unsigned int start, length;
int ret;
start = 0;
chunk = pcl_first_chunk(pcl);
length = chunk->ch_position;
ret = svc_rdma_copy_inline_range(info, start, length);
if (ret < 0)
return ret;
pcl_for_each_chunk(chunk, pcl) {
ret = svc_rdma_build_read_chunk(info, chunk);
if (ret < 0)
return ret;
next = pcl_next_chunk(pcl, chunk);
if (!next)
break;
start += length;
length = next->ch_position - info->ri_totalbytes;
ret = svc_rdma_copy_inline_range(info, start, length);
if (ret < 0)
return ret;
}
start += length;
length = head->rc_byte_len - start;
ret = svc_rdma_copy_inline_range(info, start, length);
if (ret < 0)
return ret;
buf->len += info->ri_totalbytes;
buf->buflen += info->ri_totalbytes;
head->rc_hdr_count = 1;
buf->head[0].iov_base = page_address(head->rc_pages[0]);
buf->head[0].iov_len = min_t(size_t, PAGE_SIZE, info->ri_totalbytes);
buf->page_len = info->ri_totalbytes - buf->head[0].iov_len;
return 0;
}
/**
* svc_rdma_read_data_item - Construct RDMA Reads to pull data item Read chunks
* @info: context for RDMA Reads
*
* The chunk data lands in the page list of head->rc_arg.pages.
*
* Currently NFSD does not look at the head->rc_arg.tail[0] iovec.
* Therefore, XDR round-up of the Read chunk and trailing
* inline content must both be added at the end of the pagelist.
*
* Return values:
* %0: RDMA Read WQEs were successfully built
* %-EINVAL: client provided too many chunks or segments,
* %-ENOMEM: rdma_rw context pool was exhausted,
* %-ENOTCONN: posting failed (connection is lost),
* %-EIO: rdma_rw initialization failed (DMA mapping, etc).
*/
static int svc_rdma_build_normal_read_chunk(struct svc_rqst *rqstp,
struct svc_rdma_read_info *info,
__be32 *p)
static int svc_rdma_read_data_item(struct svc_rdma_read_info *info)
{
struct svc_rdma_recv_ctxt *head = info->ri_readctxt;
struct xdr_buf *buf = &head->rc_arg;
struct svc_rdma_chunk *chunk;
unsigned int length;
int ret;
ret = svc_rdma_build_read_chunk(rqstp, info, p);
chunk = pcl_first_chunk(&head->rc_read_pcl);
ret = svc_rdma_build_read_chunk(info, chunk);
if (ret < 0)
goto out;
trace_svcrdma_send_read_chunk(info->ri_chunklen, info->ri_position);
head->rc_hdr_count = 0;
/* Split the Receive buffer between the head and tail
@ -739,11 +906,9 @@ static int svc_rdma_build_normal_read_chunk(struct svc_rqst *rqstp,
* chunk is not included in either the pagelist or in
* the tail.
*/
head->rc_arg.tail[0].iov_base =
head->rc_arg.head[0].iov_base + info->ri_position;
head->rc_arg.tail[0].iov_len =
head->rc_arg.head[0].iov_len - info->ri_position;
head->rc_arg.head[0].iov_len = info->ri_position;
buf->tail[0].iov_base = buf->head[0].iov_base + chunk->ch_position;
buf->tail[0].iov_len = buf->head[0].iov_len - chunk->ch_position;
buf->head[0].iov_len = chunk->ch_position;
/* Read chunk may need XDR roundup (see RFC 8166, s. 3.4.5.2).
*
@ -754,50 +919,149 @@ static int svc_rdma_build_normal_read_chunk(struct svc_rqst *rqstp,
* Currently these chunks always start at page offset 0,
* thus the rounded-up length never crosses a page boundary.
*/
info->ri_chunklen = XDR_QUADLEN(info->ri_chunklen) << 2;
head->rc_arg.page_len = info->ri_chunklen;
head->rc_arg.len += info->ri_chunklen;
head->rc_arg.buflen += info->ri_chunklen;
length = XDR_QUADLEN(info->ri_totalbytes) << 2;
buf->page_len = length;
buf->len += length;
buf->buflen += length;
out:
return ret;
}
/* Construct RDMA Reads to pull over a Position Zero Read chunk.
* The start of the data lands in the first page just after
* the Transport header, and the rest lands in the page list of
/**
* svc_rdma_read_chunk_range - Build RDMA Read WQEs for portion of a chunk
* @info: context for RDMA Reads
* @chunk: parsed Call chunk to pull
* @offset: offset of region to pull
* @length: length of region to pull
*
* Return values:
* %0: RDMA Read WQEs were successfully built
* %-EINVAL: there were not enough resources to finish
* %-ENOMEM: rdma_rw context pool was exhausted,
* %-ENOTCONN: posting failed (connection is lost),
* %-EIO: rdma_rw initialization failed (DMA mapping, etc).
*/
static int svc_rdma_read_chunk_range(struct svc_rdma_read_info *info,
const struct svc_rdma_chunk *chunk,
unsigned int offset, unsigned int length)
{
const struct svc_rdma_segment *segment;
int ret;
ret = -EINVAL;
pcl_for_each_segment(segment, chunk) {
struct svc_rdma_segment dummy;
if (offset > segment->rs_length) {
offset -= segment->rs_length;
continue;
}
dummy.rs_handle = segment->rs_handle;
dummy.rs_length = min_t(u32, length, segment->rs_length) - offset;
dummy.rs_offset = segment->rs_offset + offset;
ret = svc_rdma_build_read_segment(info, &dummy);
if (ret < 0)
break;
info->ri_totalbytes += dummy.rs_length;
length -= dummy.rs_length;
offset = 0;
}
return ret;
}
/**
* svc_rdma_read_call_chunk - Build RDMA Read WQEs to pull a Long Message
* @info: context for RDMA Reads
*
* Return values:
* %0: RDMA Read WQEs were successfully built
* %-EINVAL: there were not enough resources to finish
* %-ENOMEM: rdma_rw context pool was exhausted,
* %-ENOTCONN: posting failed (connection is lost),
* %-EIO: rdma_rw initialization failed (DMA mapping, etc).
*/
static int svc_rdma_read_call_chunk(struct svc_rdma_read_info *info)
{
struct svc_rdma_recv_ctxt *head = info->ri_readctxt;
const struct svc_rdma_chunk *call_chunk =
pcl_first_chunk(&head->rc_call_pcl);
const struct svc_rdma_pcl *pcl = &head->rc_read_pcl;
struct svc_rdma_chunk *chunk, *next;
unsigned int start, length;
int ret;
if (pcl_is_empty(pcl))
return svc_rdma_build_read_chunk(info, call_chunk);
start = 0;
chunk = pcl_first_chunk(pcl);
length = chunk->ch_position;
ret = svc_rdma_read_chunk_range(info, call_chunk, start, length);
if (ret < 0)
return ret;
pcl_for_each_chunk(chunk, pcl) {
ret = svc_rdma_build_read_chunk(info, chunk);
if (ret < 0)
return ret;
next = pcl_next_chunk(pcl, chunk);
if (!next)
break;
start += length;
length = next->ch_position - info->ri_totalbytes;
ret = svc_rdma_read_chunk_range(info, call_chunk,
start, length);
if (ret < 0)
return ret;
}
start += length;
length = call_chunk->ch_length - start;
return svc_rdma_read_chunk_range(info, call_chunk, start, length);
}
/**
* svc_rdma_read_special - Build RDMA Read WQEs to pull a Long Message
* @info: context for RDMA Reads
*
* The start of the data lands in the first page just after the
* Transport header, and the rest lands in the page list of
* head->rc_arg.pages.
*
* Assumptions:
* - A PZRC has an XDR-aligned length (no implicit round-up).
* - There can be no trailing inline content (IOW, we assume
* a PZRC is never sent in an RDMA_MSG message, though it's
* allowed by spec).
* - A PZRC is never sent in an RDMA_MSG message, though it's
* allowed by spec.
*
* Return values:
* %0: RDMA Read WQEs were successfully built
* %-EINVAL: client provided too many chunks or segments,
* %-ENOMEM: rdma_rw context pool was exhausted,
* %-ENOTCONN: posting failed (connection is lost),
* %-EIO: rdma_rw initialization failed (DMA mapping, etc).
*/
static int svc_rdma_build_pz_read_chunk(struct svc_rqst *rqstp,
struct svc_rdma_read_info *info,
__be32 *p)
static noinline int svc_rdma_read_special(struct svc_rdma_read_info *info)
{
struct svc_rdma_recv_ctxt *head = info->ri_readctxt;
struct xdr_buf *buf = &head->rc_arg;
int ret;
ret = svc_rdma_build_read_chunk(rqstp, info, p);
ret = svc_rdma_read_call_chunk(info);
if (ret < 0)
goto out;
trace_svcrdma_send_pzr(info->ri_chunklen);
head->rc_arg.len += info->ri_chunklen;
head->rc_arg.buflen += info->ri_chunklen;
buf->len += info->ri_totalbytes;
buf->buflen += info->ri_totalbytes;
head->rc_hdr_count = 1;
head->rc_arg.head[0].iov_base = page_address(head->rc_pages[0]);
head->rc_arg.head[0].iov_len = min_t(size_t, PAGE_SIZE,
info->ri_chunklen);
head->rc_arg.page_len = info->ri_chunklen -
head->rc_arg.head[0].iov_len;
buf->head[0].iov_base = page_address(head->rc_pages[0]);
buf->head[0].iov_len = min_t(size_t, PAGE_SIZE, info->ri_totalbytes);
buf->page_len = info->ri_totalbytes - buf->head[0].iov_len;
out:
return ret;
@ -824,26 +1088,34 @@ static void svc_rdma_save_io_pages(struct svc_rqst *rqstp,
}
/**
* svc_rdma_recv_read_chunk - Pull a Read chunk from the client
* svc_rdma_process_read_list - Pull list of Read chunks from the client
* @rdma: controlling RDMA transport
* @rqstp: set of pages to use as Read sink buffers
* @head: pages under I/O collect here
* @p: pointer to start of Read chunk
*
* Returns:
* %0 if all needed RDMA Reads were posted successfully,
* %-EINVAL if client provided too many segments,
* %-ENOMEM if rdma_rw context pool was exhausted,
* %-ENOTCONN if posting failed (connection is lost),
* %-EIO if rdma_rw initialization failed (DMA mapping, etc).
* The RPC/RDMA protocol assumes that the upper layer's XDR decoders
* pull each Read chunk as they decode an incoming RPC message.
*
* Assumptions:
* - All Read segments in @p have the same Position value.
* On Linux, however, the server needs to have a fully-constructed RPC
* message in rqstp->rq_arg when there is a positive return code from
* ->xpo_recvfrom. So the Read list is safety-checked immediately when
* it is received, then here the whole Read list is pulled all at once.
* The ingress RPC message is fully reconstructed once all associated
* RDMA Reads have completed.
*
* Return values:
* %1: all needed RDMA Reads were posted successfully,
* %-EINVAL: client provided too many chunks or segments,
* %-ENOMEM: rdma_rw context pool was exhausted,
* %-ENOTCONN: posting failed (connection is lost),
* %-EIO: rdma_rw initialization failed (DMA mapping, etc).
*/
int svc_rdma_recv_read_chunk(struct svcxprt_rdma *rdma, struct svc_rqst *rqstp,
struct svc_rdma_recv_ctxt *head, __be32 *p)
int svc_rdma_process_read_list(struct svcxprt_rdma *rdma,
struct svc_rqst *rqstp,
struct svc_rdma_recv_ctxt *head)
{
struct svc_rdma_read_info *info;
struct svc_rdma_chunk_ctxt *cc;
int ret;
/* The request (with page list) is constructed in
@ -861,23 +1133,29 @@ int svc_rdma_recv_read_chunk(struct svcxprt_rdma *rdma, struct svc_rqst *rqstp,
info = svc_rdma_read_info_alloc(rdma);
if (!info)
return -ENOMEM;
cc = &info->ri_cc;
info->ri_rqst = rqstp;
info->ri_readctxt = head;
info->ri_pageno = 0;
info->ri_pageoff = 0;
info->ri_totalbytes = 0;
info->ri_position = be32_to_cpup(p + 1);
if (info->ri_position)
ret = svc_rdma_build_normal_read_chunk(rqstp, info, p);
else
ret = svc_rdma_build_pz_read_chunk(rqstp, info, p);
if (pcl_is_empty(&head->rc_call_pcl)) {
if (head->rc_read_pcl.cl_count == 1)
ret = svc_rdma_read_data_item(info);
else
ret = svc_rdma_read_multiple_chunks(info);
} else
ret = svc_rdma_read_special(info);
if (ret < 0)
goto out_err;
ret = svc_rdma_post_chunk_ctxt(&info->ri_cc);
trace_svcrdma_post_read_chunk(&cc->cc_cid, cc->cc_sqecount);
ret = svc_rdma_post_chunk_ctxt(cc);
if (ret < 0)
goto out_err;
svc_rdma_save_io_pages(rqstp, 0, head->rc_page_count);
return 0;
return 1;
out_err:
svc_rdma_read_info_free(info);

560
net/sunrpc/xprtrdma/svc_rdma_sendto.c
View File

@ -358,49 +358,42 @@ static ssize_t svc_rdma_encode_read_list(struct svc_rdma_send_ctxt *sctxt)
/**
* svc_rdma_encode_write_segment - Encode one Write segment
* @src: matching Write chunk in the RPC Call header
* @sctxt: Send context for the RPC Reply
* @chunk: Write chunk to push
* @remaining: remaining bytes of the payload left in the Write chunk
* @segno: which segment in the chunk
*
* Return values:
* On success, returns length in bytes of the Reply XDR buffer
* that was consumed by the Write segment
* that was consumed by the Write segment, and updates @remaining
* %-EMSGSIZE on XDR buffer overflow
*/
static ssize_t svc_rdma_encode_write_segment(__be32 *src,
struct svc_rdma_send_ctxt *sctxt,
unsigned int *remaining)
static ssize_t svc_rdma_encode_write_segment(struct svc_rdma_send_ctxt *sctxt,
const struct svc_rdma_chunk *chunk,
u32 *remaining, unsigned int segno)
{
const struct svc_rdma_segment *segment = &chunk->ch_segments[segno];
const size_t len = rpcrdma_segment_maxsz * sizeof(__be32);
u32 length;
__be32 *p;
const size_t len = rpcrdma_segment_maxsz * sizeof(*p);
u32 handle, length;
u64 offset;
p = xdr_reserve_space(&sctxt->sc_stream, len);
if (!p)
return -EMSGSIZE;
xdr_decode_rdma_segment(src, &handle, &length, &offset);
if (*remaining < length) {
/* segment only partly filled */
length = *remaining;
*remaining = 0;
} else {
/* entire segment was consumed */
*remaining -= length;
}
xdr_encode_rdma_segment(p, handle, length, offset);
trace_svcrdma_encode_wseg(handle, length, offset);
length = min_t(u32, *remaining, segment->rs_length);
*remaining -= length;
xdr_encode_rdma_segment(p, segment->rs_handle, length,
segment->rs_offset);
trace_svcrdma_encode_wseg(sctxt, segno, segment->rs_handle, length,
segment->rs_offset);
return len;
}
/**
* svc_rdma_encode_write_chunk - Encode one Write chunk
* @src: matching Write chunk in the RPC Call header
* @sctxt: Send context for the RPC Reply
* @remaining: size in bytes of the payload in the Write chunk
* @chunk: Write chunk to push
*
* Copy a Write chunk from the Call transport header to the
* Reply transport header. Update each segment's length field
@ -411,33 +404,28 @@ static ssize_t svc_rdma_encode_write_segment(__be32 *src,
* that was consumed by the Write chunk
* %-EMSGSIZE on XDR buffer overflow
*/
static ssize_t svc_rdma_encode_write_chunk(__be32 *src,
struct svc_rdma_send_ctxt *sctxt,
unsigned int remaining)
static ssize_t svc_rdma_encode_write_chunk(struct svc_rdma_send_ctxt *sctxt,
const struct svc_rdma_chunk *chunk)
{
unsigned int i, nsegs;
u32 remaining = chunk->ch_payload_length;
unsigned int segno;
ssize_t len, ret;
len = 0;
trace_svcrdma_encode_write_chunk(remaining);
src++;
ret = xdr_stream_encode_item_present(&sctxt->sc_stream);
if (ret < 0)
return -EMSGSIZE;
return ret;
len += ret;
nsegs = be32_to_cpup(src++);
ret = xdr_stream_encode_u32(&sctxt->sc_stream, nsegs);
ret = xdr_stream_encode_u32(&sctxt->sc_stream, chunk->ch_segcount);
if (ret < 0)
return -EMSGSIZE;
return ret;
len += ret;
for (i = nsegs; i; i--) {
ret = svc_rdma_encode_write_segment(src, sctxt, &remaining);
for (segno = 0; segno < chunk->ch_segcount; segno++) {
ret = svc_rdma_encode_write_segment(sctxt, chunk, &remaining, segno);
if (ret < 0)
return -EMSGSIZE;
src += rpcrdma_segment_maxsz;
return ret;
len += ret;
}
@ -448,32 +436,25 @@ static ssize_t svc_rdma_encode_write_chunk(__be32 *src,
* svc_rdma_encode_write_list - Encode RPC Reply's Write chunk list
* @rctxt: Reply context with information about the RPC Call
* @sctxt: Send context for the RPC Reply
* @length: size in bytes of the payload in the first Write chunk
*
* The client provides a Write chunk list in the Call message. Fill
* in the segments in the first Write chunk in the Reply's transport
* header with the number of bytes consumed in each segment.
* Remaining chunks are returned unused.
*
* Assumptions:
* - Client has provided only one Write chunk
*
* Return values:
* On success, returns length in bytes of the Reply XDR buffer
* that was consumed by the Reply's Write list
* %-EMSGSIZE on XDR buffer overflow
*/
static ssize_t
svc_rdma_encode_write_list(const struct svc_rdma_recv_ctxt *rctxt,
struct svc_rdma_send_ctxt *sctxt,
unsigned int length)
static ssize_t svc_rdma_encode_write_list(struct svc_rdma_recv_ctxt *rctxt,
struct svc_rdma_send_ctxt *sctxt)
{
struct svc_rdma_chunk *chunk;
ssize_t len, ret;
ret = svc_rdma_encode_write_chunk(rctxt->rc_write_list, sctxt, length);
if (ret < 0)
return ret;
len = ret;
len = 0;
pcl_for_each_chunk(chunk, &rctxt->rc_write_pcl) {
ret = svc_rdma_encode_write_chunk(sctxt, chunk);
if (ret < 0)
return ret;
len += ret;
}
/* Terminate the Write list */
ret = xdr_stream_encode_item_absent(&sctxt->sc_stream);
@ -489,56 +470,174 @@ svc_rdma_encode_write_list(const struct svc_rdma_recv_ctxt *rctxt,
* @sctxt: Send context for the RPC Reply
* @length: size in bytes of the payload in the Reply chunk
*
* Assumptions:
* - Reply can always fit in the client-provided Reply chunk
*
* Return values:
* On success, returns length in bytes of the Reply XDR buffer
* that was consumed by the Reply's Reply chunk
* %-EMSGSIZE on XDR buffer overflow
* %-E2BIG if the RPC message is larger than the Reply chunk
*/
static ssize_t
svc_rdma_encode_reply_chunk(const struct svc_rdma_recv_ctxt *rctxt,
svc_rdma_encode_reply_chunk(struct svc_rdma_recv_ctxt *rctxt,
struct svc_rdma_send_ctxt *sctxt,
unsigned int length)
{
return svc_rdma_encode_write_chunk(rctxt->rc_reply_chunk, sctxt,
length);
struct svc_rdma_chunk *chunk;
if (pcl_is_empty(&rctxt->rc_reply_pcl))
return xdr_stream_encode_item_absent(&sctxt->sc_stream);
chunk = pcl_first_chunk(&rctxt->rc_reply_pcl);
if (length > chunk->ch_length)
return -E2BIG;
chunk->ch_payload_length = length;
return svc_rdma_encode_write_chunk(sctxt, chunk);
}
static int svc_rdma_dma_map_page(struct svcxprt_rdma *rdma,
struct svc_rdma_send_ctxt *ctxt,
struct page *page,
unsigned long offset,
unsigned int len)
struct svc_rdma_map_data {
struct svcxprt_rdma *md_rdma;
struct svc_rdma_send_ctxt *md_ctxt;
};
/**
* svc_rdma_page_dma_map - DMA map one page
* @data: pointer to arguments
* @page: struct page to DMA map
* @offset: offset into the page
* @len: number of bytes to map
*
* Returns:
* %0 if DMA mapping was successful
* %-EIO if the page cannot be DMA mapped
*/
static int svc_rdma_page_dma_map(void *data, struct page *page,
unsigned long offset, unsigned int len)
{
struct svc_rdma_map_data *args = data;
struct svcxprt_rdma *rdma = args->md_rdma;
struct svc_rdma_send_ctxt *ctxt = args->md_ctxt;
struct ib_device *dev = rdma->sc_cm_id->device;
dma_addr_t dma_addr;
++ctxt->sc_cur_sge_no;
dma_addr = ib_dma_map_page(dev, page, offset, len, DMA_TO_DEVICE);
trace_svcrdma_dma_map_page(rdma, dma_addr, len);
if (ib_dma_mapping_error(dev, dma_addr))
goto out_maperr;
trace_svcrdma_dma_map_page(rdma, dma_addr, len);
ctxt->sc_sges[ctxt->sc_cur_sge_no].addr = dma_addr;
ctxt->sc_sges[ctxt->sc_cur_sge_no].length = len;
ctxt->sc_send_wr.num_sge++;
return 0;
out_maperr:
trace_svcrdma_dma_map_err(rdma, dma_addr, len);
return -EIO;
}
/* ib_dma_map_page() is used here because svc_rdma_dma_unmap()
/**
* svc_rdma_iov_dma_map - DMA map an iovec
* @data: pointer to arguments
* @iov: kvec to DMA map
*
* ib_dma_map_page() is used here because svc_rdma_dma_unmap()
* handles DMA-unmap and it uses ib_dma_unmap_page() exclusively.
*
* Returns:
* %0 if DMA mapping was successful
* %-EIO if the iovec cannot be DMA mapped
*/
static int svc_rdma_dma_map_buf(struct svcxprt_rdma *rdma,
struct svc_rdma_send_ctxt *ctxt,
unsigned char *base,
unsigned int len)
static int svc_rdma_iov_dma_map(void *data, const struct kvec *iov)
{
return svc_rdma_dma_map_page(rdma, ctxt, virt_to_page(base),
offset_in_page(base), len);
if (!iov->iov_len)
return 0;
return svc_rdma_page_dma_map(data, virt_to_page(iov->iov_base),
offset_in_page(iov->iov_base),
iov->iov_len);
}
/**
* svc_rdma_xb_dma_map - DMA map all segments of an xdr_buf
* @xdr: xdr_buf containing portion of an RPC message to transmit
* @data: pointer to arguments
*
* Returns:
* %0 if DMA mapping was successful
* %-EIO if DMA mapping failed
*
* On failure, any DMA mappings that have been already done must be
* unmapped by the caller.
*/
static int svc_rdma_xb_dma_map(const struct xdr_buf *xdr, void *data)
{
unsigned int len, remaining;
unsigned long pageoff;
struct page **ppages;
int ret;
ret = svc_rdma_iov_dma_map(data, &xdr->head[0]);
if (ret < 0)
return ret;
ppages = xdr->pages + (xdr->page_base >> PAGE_SHIFT);
pageoff = offset_in_page(xdr->page_base);
remaining = xdr->page_len;
while (remaining) {
len = min_t(u32, PAGE_SIZE - pageoff, remaining);
ret = svc_rdma_page_dma_map(data, *ppages++, pageoff, len);
if (ret < 0)
return ret;
remaining -= len;
pageoff = 0;
}
ret = svc_rdma_iov_dma_map(data, &xdr->tail[0]);
if (ret < 0)
return ret;
return xdr->len;
}
struct svc_rdma_pullup_data {
u8 *pd_dest;
unsigned int pd_length;
unsigned int pd_num_sges;
};
/**
* svc_rdma_xb_count_sges - Count how many SGEs will be needed
* @xdr: xdr_buf containing portion of an RPC message to transmit
* @data: pointer to arguments
*
* Returns:
* Number of SGEs needed to Send the contents of @xdr inline
*/
static int svc_rdma_xb_count_sges(const struct xdr_buf *xdr,
void *data)
{
struct svc_rdma_pullup_data *args = data;
unsigned int remaining;
unsigned long offset;
if (xdr->head[0].iov_len)
++args->pd_num_sges;
offset = offset_in_page(xdr->page_base);
remaining = xdr->page_len;
while (remaining) {
++args->pd_num_sges;
remaining -= min_t(u32, PAGE_SIZE - offset, remaining);
offset = 0;
}
if (xdr->tail[0].iov_len)
++args->pd_num_sges;
args->pd_length += xdr->len;
return 0;
}
/**
@ -549,48 +648,71 @@ static int svc_rdma_dma_map_buf(struct svcxprt_rdma *rdma,
* @xdr: xdr_buf containing RPC message to transmit
*
* Returns:
* %true if pull-up must be used
* %false otherwise
* %true if pull-up must be used
* %false otherwise
*/
static bool svc_rdma_pull_up_needed(struct svcxprt_rdma *rdma,
struct svc_rdma_send_ctxt *sctxt,
static bool svc_rdma_pull_up_needed(const struct svcxprt_rdma *rdma,
const struct svc_rdma_send_ctxt *sctxt,
const struct svc_rdma_recv_ctxt *rctxt,
struct xdr_buf *xdr)
const struct xdr_buf *xdr)
{
int elements;
/* Resources needed for the transport header */
struct svc_rdma_pullup_data args = {
.pd_length = sctxt->sc_hdrbuf.len,
.pd_num_sges = 1,
};
int ret;
/* For small messages, copying bytes is cheaper than DMA mapping.
*/
if (sctxt->sc_hdrbuf.len + xdr->len < RPCRDMA_PULLUP_THRESH)
ret = pcl_process_nonpayloads(&rctxt->rc_write_pcl, xdr,
svc_rdma_xb_count_sges, &args);
if (ret < 0)
return false;
if (args.pd_length < RPCRDMA_PULLUP_THRESH)
return true;
return args.pd_num_sges >= rdma->sc_max_send_sges;
}
/* Check whether the xdr_buf has more elements than can
* fit in a single RDMA Send.
*/
/* xdr->head */
elements = 1;
/**
* svc_rdma_xb_linearize - Copy region of xdr_buf to flat buffer
* @xdr: xdr_buf containing portion of an RPC message to copy
* @data: pointer to arguments
*
* Returns:
* Always zero.
*/
static int svc_rdma_xb_linearize(const struct xdr_buf *xdr,
void *data)
{
struct svc_rdma_pullup_data *args = data;
unsigned int len, remaining;
unsigned long pageoff;
struct page **ppages;
/* xdr->pages */
if (!rctxt || !rctxt->rc_write_list) {
unsigned int remaining;
unsigned long pageoff;
pageoff = xdr->page_base & ~PAGE_MASK;
remaining = xdr->page_len;
while (remaining) {
++elements;
remaining -= min_t(u32, PAGE_SIZE - pageoff,
remaining);
pageoff = 0;
}
if (xdr->head[0].iov_len) {
memcpy(args->pd_dest, xdr->head[0].iov_base, xdr->head[0].iov_len);
args->pd_dest += xdr->head[0].iov_len;
}
/* xdr->tail */
if (xdr->tail[0].iov_len)
++elements;
ppages = xdr->pages + (xdr->page_base >> PAGE_SHIFT);
pageoff = offset_in_page(xdr->page_base);
remaining = xdr->page_len;
while (remaining) {
len = min_t(u32, PAGE_SIZE - pageoff, remaining);
memcpy(args->pd_dest, page_address(*ppages) + pageoff, len);
remaining -= len;
args->pd_dest += len;
pageoff = 0;
ppages++;
}
/* assume 1 SGE is needed for the transport header */
return elements >= rdma->sc_max_send_sges;
if (xdr->tail[0].iov_len) {
memcpy(args->pd_dest, xdr->tail[0].iov_base, xdr->tail[0].iov_len);
args->pd_dest += xdr->tail[0].iov_len;
}
args->pd_length += xdr->len;
return 0;
}
/**
@ -603,54 +725,30 @@ static bool svc_rdma_pull_up_needed(struct svcxprt_rdma *rdma,
* The device is not capable of sending the reply directly.
* Assemble the elements of @xdr into the transport header buffer.
*
* Returns zero on success, or a negative errno on failure.
* Assumptions:
* pull_up_needed has determined that @xdr will fit in the buffer.
*
* Returns:
* %0 if pull-up was successful
* %-EMSGSIZE if a buffer manipulation problem occurred
*/
static int svc_rdma_pull_up_reply_msg(struct svcxprt_rdma *rdma,
static int svc_rdma_pull_up_reply_msg(const struct svcxprt_rdma *rdma,
struct svc_rdma_send_ctxt *sctxt,
const struct svc_rdma_recv_ctxt *rctxt,
const struct xdr_buf *xdr)
{
unsigned char *dst, *tailbase;
unsigned int taillen;
struct svc_rdma_pullup_data args = {
.pd_dest = sctxt->sc_xprt_buf + sctxt->sc_hdrbuf.len,
};
int ret;
dst = sctxt->sc_xprt_buf + sctxt->sc_hdrbuf.len;
memcpy(dst, xdr->head[0].iov_base, xdr->head[0].iov_len);
dst += xdr->head[0].iov_len;
ret = pcl_process_nonpayloads(&rctxt->rc_write_pcl, xdr,
svc_rdma_xb_linearize, &args);
if (ret < 0)
return ret;
tailbase = xdr->tail[0].iov_base;
taillen = xdr->tail[0].iov_len;
if (rctxt && rctxt->rc_write_list) {
u32 xdrpad;
xdrpad = xdr_pad_size(xdr->page_len);
if (taillen && xdrpad) {
tailbase += xdrpad;
taillen -= xdrpad;
}
} else {
unsigned int len, remaining;
unsigned long pageoff;
struct page **ppages;
ppages = xdr->pages + (xdr->page_base >> PAGE_SHIFT);
pageoff = xdr->page_base & ~PAGE_MASK;
remaining = xdr->page_len;
while (remaining) {
len = min_t(u32, PAGE_SIZE - pageoff, remaining);
memcpy(dst, page_address(*ppages) + pageoff, len);
remaining -= len;
dst += len;
pageoff = 0;
ppages++;
}
}
if (taillen)
memcpy(dst, tailbase, taillen);
sctxt->sc_sges[0].length += xdr->len;
trace_svcrdma_send_pullup(sctxt->sc_sges[0].length);
sctxt->sc_sges[0].length = sctxt->sc_hdrbuf.len + args.pd_length;
trace_svcrdma_send_pullup(sctxt, args.pd_length);
return 0;
}
@ -660,22 +758,22 @@ static int svc_rdma_pull_up_reply_msg(struct svcxprt_rdma *rdma,
* @rctxt: Write and Reply chunks provided by client
* @xdr: prepared xdr_buf containing RPC message
*
* Load the xdr_buf into the ctxt's sge array, and DMA map each
* element as it is added. The Send WR's num_sge field is set.
* Returns:
* %0 if DMA mapping was successful.
* %-EMSGSIZE if a buffer manipulation problem occurred
* %-EIO if DMA mapping failed
*
* Returns zero on success, or a negative errno on failure.
* The Send WR's num_sge field is set in all cases.
*/
int svc_rdma_map_reply_msg(struct svcxprt_rdma *rdma,
struct svc_rdma_send_ctxt *sctxt,
const struct svc_rdma_recv_ctxt *rctxt,
struct xdr_buf *xdr)
const struct xdr_buf *xdr)
{
unsigned int len, remaining;
unsigned long page_off;
struct page **ppages;
unsigned char *base;
u32 xdr_pad;
int ret;
struct svc_rdma_map_data args = {
.md_rdma = rdma,
.md_ctxt = sctxt,
};
/* Set up the (persistently-mapped) transport header SGE. */
sctxt->sc_send_wr.num_sge = 1;
@ -684,7 +782,7 @@ int svc_rdma_map_reply_msg(struct svcxprt_rdma *rdma,
/* If there is a Reply chunk, nothing follows the transport
* header, and we're done here.
*/
if (rctxt && rctxt->rc_reply_chunk)
if (!pcl_is_empty(&rctxt->rc_reply_pcl))
return 0;
/* For pull-up, svc_rdma_send() will sync the transport header.
@ -693,58 +791,8 @@ int svc_rdma_map_reply_msg(struct svcxprt_rdma *rdma,
if (svc_rdma_pull_up_needed(rdma, sctxt, rctxt, xdr))
return svc_rdma_pull_up_reply_msg(rdma, sctxt, rctxt, xdr);
++sctxt->sc_cur_sge_no;
ret = svc_rdma_dma_map_buf(rdma, sctxt,
xdr->head[0].iov_base,
xdr->head[0].iov_len);
if (ret < 0)
return ret;
/* If a Write chunk is present, the xdr_buf's page list
* is not included inline. However the Upper Layer may
* have added XDR padding in the tail buffer, and that
* should not be included inline.
*/
if (rctxt && rctxt->rc_write_list) {
base = xdr->tail[0].iov_base;
len = xdr->tail[0].iov_len;
xdr_pad = xdr_pad_size(xdr->page_len);
if (len && xdr_pad) {
base += xdr_pad;
len -= xdr_pad;
}
goto tail;
}
ppages = xdr->pages + (xdr->page_base >> PAGE_SHIFT);
page_off = xdr->page_base & ~PAGE_MASK;
remaining = xdr->page_len;
while (remaining) {
len = min_t(u32, PAGE_SIZE - page_off, remaining);
++sctxt->sc_cur_sge_no;
ret = svc_rdma_dma_map_page(rdma, sctxt, *ppages++,
page_off, len);
if (ret < 0)
return ret;
remaining -= len;
page_off = 0;
}
base = xdr->tail[0].iov_base;
len = xdr->tail[0].iov_len;
tail:
if (len) {
++sctxt->sc_cur_sge_no;
ret = svc_rdma_dma_map_buf(rdma, sctxt, base, len);
if (ret < 0)
return ret;
}
return 0;
return pcl_process_nonpayloads(&rctxt->rc_write_pcl, xdr,
svc_rdma_xb_dma_map, &args);
}
/* The svc_rqst and all resources it owns are released as soon as
@ -894,9 +942,6 @@ int svc_rdma_sendto(struct svc_rqst *rqstp)
container_of(xprt, struct svcxprt_rdma, sc_xprt);
struct svc_rdma_recv_ctxt *rctxt = rqstp->rq_xprt_ctxt;
__be32 *rdma_argp = rctxt->rc_recv_buf;
__be32 *wr_lst = rctxt->rc_write_list;
__be32 *rp_ch = rctxt->rc_reply_chunk;
struct xdr_buf *xdr = &rqstp->rq_res;
struct svc_rdma_send_ctxt *sctxt;
__be32 *p;
int ret;
@ -914,45 +959,22 @@ int svc_rdma_sendto(struct svc_rqst *rqstp)
rpcrdma_fixed_maxsz * sizeof(*p));
if (!p)
goto err0;
ret = svc_rdma_send_reply_chunk(rdma, rctxt, &rqstp->rq_res);
if (ret < 0)
goto err2;
*p++ = *rdma_argp;
*p++ = *(rdma_argp + 1);
*p++ = rdma->sc_fc_credits;
*p = rp_ch ? rdma_nomsg : rdma_msg;
*p = pcl_is_empty(&rctxt->rc_reply_pcl) ? rdma_msg : rdma_nomsg;
if (svc_rdma_encode_read_list(sctxt) < 0)
goto err0;
if (wr_lst) {
/* XXX: Presume the client sent only one Write chunk */
unsigned long offset;
unsigned int length;
if (rctxt->rc_read_payload_length) {
offset = rctxt->rc_read_payload_offset;
length = rctxt->rc_read_payload_length;
} else {
offset = xdr->head[0].iov_len;
length = xdr->page_len;
}
ret = svc_rdma_send_write_chunk(rdma, wr_lst, xdr, offset,
length);
if (ret < 0)
goto err2;
if (svc_rdma_encode_write_list(rctxt, sctxt, length) < 0)
goto err0;
} else {
if (xdr_stream_encode_item_absent(&sctxt->sc_stream) < 0)
goto err0;
}
if (rp_ch) {
ret = svc_rdma_send_reply_chunk(rdma, rctxt, &rqstp->rq_res);
if (ret < 0)
goto err2;
if (svc_rdma_encode_reply_chunk(rctxt, sctxt, ret) < 0)
goto err0;
} else {
if (xdr_stream_encode_item_absent(&sctxt->sc_stream) < 0)
goto err0;
}
if (svc_rdma_encode_write_list(rctxt, sctxt) < 0)
goto err0;
if (svc_rdma_encode_reply_chunk(rctxt, sctxt, ret) < 0)
goto err0;
ret = svc_rdma_send_reply_msg(rdma, sctxt, rctxt, rqstp);
if (ret < 0)
@ -979,28 +1001,46 @@ int svc_rdma_sendto(struct svc_rqst *rqstp)
}
/**
* svc_rdma_read_payload - special processing for a READ payload
* svc_rdma_result_payload - special processing for a result payload
* @rqstp: svc_rqst to operate on
* @offset: payload's byte offset in @xdr
* @length: size of payload, in bytes
*
* Returns zero on success.
*
* For the moment, just record the xdr_buf location of the READ
* payload. svc_rdma_sendto will use that location later when
* we actually send the payload.
* Return values:
* %0 if successful or nothing needed to be done
* %-EMSGSIZE on XDR buffer overflow
* %-E2BIG if the payload was larger than the Write chunk
* %-EINVAL if client provided too many segments
* %-ENOMEM if rdma_rw context pool was exhausted
* %-ENOTCONN if posting failed (connection is lost)
* %-EIO if rdma_rw initialization failed (DMA mapping, etc)
*/
int svc_rdma_read_payload(struct svc_rqst *rqstp, unsigned int offset,
unsigned int length)
int svc_rdma_result_payload(struct svc_rqst *rqstp, unsigned int offset,
unsigned int length)
{
struct svc_rdma_recv_ctxt *rctxt = rqstp->rq_xprt_ctxt;
struct svc_rdma_chunk *chunk;
struct svcxprt_rdma *rdma;
struct xdr_buf subbuf;
int ret;
/* XXX: Just one READ payload slot for now, since our
* transport implementation currently supports only one
* Write chunk.
*/
rctxt->rc_read_payload_offset = offset;
rctxt->rc_read_payload_length = length;
chunk = rctxt->rc_cur_result_payload;
if (!length || !chunk)
return 0;
rctxt->rc_cur_result_payload =
pcl_next_chunk(&rctxt->rc_write_pcl, chunk);
if (length > chunk->ch_length)
return -E2BIG;
chunk->ch_position = offset;
chunk->ch_payload_length = length;
if (xdr_buf_subsegment(&rqstp->rq_res, &subbuf, offset, length))
return -EMSGSIZE;
rdma = container_of(rqstp->rq_xprt, struct svcxprt_rdma, sc_xprt);
ret = svc_rdma_send_write_chunk(rdma, chunk, &subbuf);
if (ret < 0)
return ret;
return 0;
}

2
net/sunrpc/xprtrdma/svc_rdma_transport.c
View File

@ -80,7 +80,7 @@ static const struct svc_xprt_ops svc_rdma_ops = {
.xpo_create = svc_rdma_create,
.xpo_recvfrom = svc_rdma_recvfrom,
.xpo_sendto = svc_rdma_sendto,
.xpo_read_payload = svc_rdma_read_payload,
.xpo_result_payload = svc_rdma_result_payload,
.xpo_release_rqst = svc_rdma_release_rqst,
.xpo_detach = svc_rdma_detach,
.xpo_free = svc_rdma_free,