Commit 9cf514cc authored by Christoph Hellwig's avatar Christoph Hellwig

nfsd: implement pNFS operations

Add support for the GETDEVICEINFO, LAYOUTGET, LAYOUTCOMMIT and
LAYOUTRETURN NFSv4.1 operations, as well as backing code to manage
outstanding layouts and devices.

Layout management is very straight forward, with a nfs4_layout_stateid
structure that extends nfs4_stid to manage layout stateids as the
top-level structure.  It is linked into the nfs4_file and nfs4_client
structures like the other stateids, and contains a linked list of
layouts that hang of the stateid.  The actual layout operations are
implemented in layout drivers that are not part of this commit, but
will be added later.

The worst part of this commit is the management of the pNFS device IDs,
which suffers from a specification that is not sanely implementable due
to the fact that the device-IDs are global and not bound to an export,
and have a small enough size so that we can't store the fsid portion of
a file handle, and must never be reused.  As we still do need perform all
export authentication and validation checks on a device ID passed to
GETDEVICEINFO we are caught between a rock and a hard place.  To work
around this issue we add a new hash that maps from a 64-bit integer to a
fsid so that we can look up the export to authenticate against it,
a 32-bit integer as a generation that we can bump when changing the device,
and a currently unused 32-bit integer that could be used in the future
to handle more than a single device per export.  Entries in this hash
table are never deleted as we can't reuse the ids anyway, and would have
a severe lifetime problem anyway as Linux export structures are temporary
structures that can go away under load.

Parts of the XDR data, structures and marshaling/unmarshaling code, as
well as many concepts are derived from the old pNFS server implementation
from Andy Adamson, Benny Halevy, Dean Hildebrand, Marc Eshel, Fred Isaman,
Mike Sager, Ricardo Labiaga and many others.
Signed-off-by: default avatarChristoph Hellwig <hch@lst.de>
parent 4d227fca
...@@ -82,6 +82,16 @@ config NFSD_V4 ...@@ -82,6 +82,16 @@ config NFSD_V4
If unsure, say N. If unsure, say N.
config NFSD_PNFS
bool "NFSv4.1 server support for Parallel NFS (pNFS)"
depends on NFSD_V4
help
This option enables support for the parallel NFS features of the
minor version 1 of the NFSv4 protocol (RFC5661) in the kernel's NFS
server.
If unsure, say N.
config NFSD_V4_SECURITY_LABEL config NFSD_V4_SECURITY_LABEL
bool "Provide Security Label support for NFSv4 server" bool "Provide Security Label support for NFSv4 server"
depends on NFSD_V4 && SECURITY depends on NFSD_V4 && SECURITY
......
...@@ -12,3 +12,4 @@ nfsd-$(CONFIG_NFSD_V3) += nfs3proc.o nfs3xdr.o ...@@ -12,3 +12,4 @@ nfsd-$(CONFIG_NFSD_V3) += nfs3proc.o nfs3xdr.o
nfsd-$(CONFIG_NFSD_V3_ACL) += nfs3acl.o nfsd-$(CONFIG_NFSD_V3_ACL) += nfs3acl.o
nfsd-$(CONFIG_NFSD_V4) += nfs4proc.o nfs4xdr.o nfs4state.o nfs4idmap.o \ nfsd-$(CONFIG_NFSD_V4) += nfs4proc.o nfs4xdr.o nfs4state.o nfs4idmap.o \
nfs4acl.o nfs4callback.o nfs4recover.o nfs4acl.o nfs4callback.o nfs4recover.o
nfsd-$(CONFIG_NFSD_PNFS) += nfs4layouts.o
...@@ -20,6 +20,7 @@ ...@@ -20,6 +20,7 @@
#include "nfsd.h" #include "nfsd.h"
#include "nfsfh.h" #include "nfsfh.h"
#include "netns.h" #include "netns.h"
#include "pnfs.h"
#define NFSDDBG_FACILITY NFSDDBG_EXPORT #define NFSDDBG_FACILITY NFSDDBG_EXPORT
...@@ -545,6 +546,7 @@ static int svc_export_parse(struct cache_detail *cd, char *mesg, int mlen) ...@@ -545,6 +546,7 @@ static int svc_export_parse(struct cache_detail *cd, char *mesg, int mlen)
exp.ex_client = dom; exp.ex_client = dom;
exp.cd = cd; exp.cd = cd;
exp.ex_devid_map = NULL;
/* expiry */ /* expiry */
err = -EINVAL; err = -EINVAL;
...@@ -621,6 +623,8 @@ static int svc_export_parse(struct cache_detail *cd, char *mesg, int mlen) ...@@ -621,6 +623,8 @@ static int svc_export_parse(struct cache_detail *cd, char *mesg, int mlen)
if (!gid_valid(exp.ex_anon_gid)) if (!gid_valid(exp.ex_anon_gid))
goto out4; goto out4;
err = 0; err = 0;
nfsd4_setup_layout_type(&exp);
} }
expp = svc_export_lookup(&exp); expp = svc_export_lookup(&exp);
...@@ -703,6 +707,7 @@ static void svc_export_init(struct cache_head *cnew, struct cache_head *citem) ...@@ -703,6 +707,7 @@ static void svc_export_init(struct cache_head *cnew, struct cache_head *citem)
new->ex_fslocs.locations = NULL; new->ex_fslocs.locations = NULL;
new->ex_fslocs.locations_count = 0; new->ex_fslocs.locations_count = 0;
new->ex_fslocs.migrated = 0; new->ex_fslocs.migrated = 0;
new->ex_layout_type = 0;
new->ex_uuid = NULL; new->ex_uuid = NULL;
new->cd = item->cd; new->cd = item->cd;
} }
...@@ -717,6 +722,8 @@ static void export_update(struct cache_head *cnew, struct cache_head *citem) ...@@ -717,6 +722,8 @@ static void export_update(struct cache_head *cnew, struct cache_head *citem)
new->ex_anon_uid = item->ex_anon_uid; new->ex_anon_uid = item->ex_anon_uid;
new->ex_anon_gid = item->ex_anon_gid; new->ex_anon_gid = item->ex_anon_gid;
new->ex_fsid = item->ex_fsid; new->ex_fsid = item->ex_fsid;
new->ex_devid_map = item->ex_devid_map;
item->ex_devid_map = NULL;
new->ex_uuid = item->ex_uuid; new->ex_uuid = item->ex_uuid;
item->ex_uuid = NULL; item->ex_uuid = NULL;
new->ex_fslocs.locations = item->ex_fslocs.locations; new->ex_fslocs.locations = item->ex_fslocs.locations;
...@@ -725,6 +732,7 @@ static void export_update(struct cache_head *cnew, struct cache_head *citem) ...@@ -725,6 +732,7 @@ static void export_update(struct cache_head *cnew, struct cache_head *citem)
item->ex_fslocs.locations_count = 0; item->ex_fslocs.locations_count = 0;
new->ex_fslocs.migrated = item->ex_fslocs.migrated; new->ex_fslocs.migrated = item->ex_fslocs.migrated;
item->ex_fslocs.migrated = 0; item->ex_fslocs.migrated = 0;
new->ex_layout_type = item->ex_layout_type;
new->ex_nflavors = item->ex_nflavors; new->ex_nflavors = item->ex_nflavors;
for (i = 0; i < MAX_SECINFO_LIST; i++) { for (i = 0; i < MAX_SECINFO_LIST; i++) {
new->ex_flavors[i] = item->ex_flavors[i]; new->ex_flavors[i] = item->ex_flavors[i];
......
...@@ -56,6 +56,8 @@ struct svc_export { ...@@ -56,6 +56,8 @@ struct svc_export {
struct nfsd4_fs_locations ex_fslocs; struct nfsd4_fs_locations ex_fslocs;
uint32_t ex_nflavors; uint32_t ex_nflavors;
struct exp_flavor_info ex_flavors[MAX_SECINFO_LIST]; struct exp_flavor_info ex_flavors[MAX_SECINFO_LIST];
enum pnfs_layouttype ex_layout_type;
struct nfsd4_deviceid_map *ex_devid_map;
struct cache_detail *cd; struct cache_detail *cd;
}; };
......
This diff is collapsed.
...@@ -43,6 +43,7 @@ ...@@ -43,6 +43,7 @@
#include "current_stateid.h" #include "current_stateid.h"
#include "netns.h" #include "netns.h"
#include "acl.h" #include "acl.h"
#include "pnfs.h"
#ifdef CONFIG_NFSD_V4_SECURITY_LABEL #ifdef CONFIG_NFSD_V4_SECURITY_LABEL
#include <linux/security.h> #include <linux/security.h>
...@@ -1178,6 +1179,252 @@ nfsd4_verify(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, ...@@ -1178,6 +1179,252 @@ nfsd4_verify(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
return status == nfserr_same ? nfs_ok : status; return status == nfserr_same ? nfs_ok : status;
} }
#ifdef CONFIG_NFSD_PNFS
static const struct nfsd4_layout_ops *
nfsd4_layout_verify(struct svc_export *exp, unsigned int layout_type)
{
if (!exp->ex_layout_type) {
dprintk("%s: export does not support pNFS\n", __func__);
return NULL;
}
if (exp->ex_layout_type != layout_type) {
dprintk("%s: layout type %d not supported\n",
__func__, layout_type);
return NULL;
}
return nfsd4_layout_ops[layout_type];
}
static __be32
nfsd4_getdeviceinfo(struct svc_rqst *rqstp,
struct nfsd4_compound_state *cstate,
struct nfsd4_getdeviceinfo *gdp)
{
const struct nfsd4_layout_ops *ops;
struct nfsd4_deviceid_map *map;
struct svc_export *exp;
__be32 nfserr;
dprintk("%s: layout_type %u dev_id [0x%llx:0x%x] maxcnt %u\n",
__func__,
gdp->gd_layout_type,
gdp->gd_devid.fsid_idx, gdp->gd_devid.generation,
gdp->gd_maxcount);
map = nfsd4_find_devid_map(gdp->gd_devid.fsid_idx);
if (!map) {
dprintk("%s: couldn't find device ID to export mapping!\n",
__func__);
return nfserr_noent;
}
exp = rqst_exp_find(rqstp, map->fsid_type, map->fsid);
if (IS_ERR(exp)) {
dprintk("%s: could not find device id\n", __func__);
return nfserr_noent;
}
nfserr = nfserr_layoutunavailable;
ops = nfsd4_layout_verify(exp, gdp->gd_layout_type);
if (!ops)
goto out;
nfserr = nfs_ok;
if (gdp->gd_maxcount != 0)
nfserr = ops->proc_getdeviceinfo(exp->ex_path.mnt->mnt_sb, gdp);
gdp->gd_notify_types &= ops->notify_types;
exp_put(exp);
out:
return nfserr;
}
static __be32
nfsd4_layoutget(struct svc_rqst *rqstp,
struct nfsd4_compound_state *cstate,
struct nfsd4_layoutget *lgp)
{
struct svc_fh *current_fh = &cstate->current_fh;
const struct nfsd4_layout_ops *ops;
struct nfs4_layout_stateid *ls;
__be32 nfserr;
int accmode;
switch (lgp->lg_seg.iomode) {
case IOMODE_READ:
accmode = NFSD_MAY_READ;
break;
case IOMODE_RW:
accmode = NFSD_MAY_READ | NFSD_MAY_WRITE;
break;
default:
dprintk("%s: invalid iomode %d\n",
__func__, lgp->lg_seg.iomode);
nfserr = nfserr_badiomode;
goto out;
}
nfserr = fh_verify(rqstp, current_fh, 0, accmode);
if (nfserr)
goto out;
nfserr = nfserr_layoutunavailable;
ops = nfsd4_layout_verify(current_fh->fh_export, lgp->lg_layout_type);
if (!ops)
goto out;
/*
* Verify minlength and range as per RFC5661:
* o If loga_length is less than loga_minlength,
* the metadata server MUST return NFS4ERR_INVAL.
* o If the sum of loga_offset and loga_minlength exceeds
* NFS4_UINT64_MAX, and loga_minlength is not
* NFS4_UINT64_MAX, the error NFS4ERR_INVAL MUST result.
* o If the sum of loga_offset and loga_length exceeds
* NFS4_UINT64_MAX, and loga_length is not NFS4_UINT64_MAX,
* the error NFS4ERR_INVAL MUST result.
*/
nfserr = nfserr_inval;
if (lgp->lg_seg.length < lgp->lg_minlength ||
(lgp->lg_minlength != NFS4_MAX_UINT64 &&
lgp->lg_minlength > NFS4_MAX_UINT64 - lgp->lg_seg.offset) ||
(lgp->lg_seg.length != NFS4_MAX_UINT64 &&
lgp->lg_seg.length > NFS4_MAX_UINT64 - lgp->lg_seg.offset))
goto out;
if (lgp->lg_seg.length == 0)
goto out;
nfserr = nfsd4_preprocess_layout_stateid(rqstp, cstate, &lgp->lg_sid,
true, lgp->lg_layout_type, &ls);
if (nfserr)
goto out;
nfserr = ops->proc_layoutget(current_fh->fh_dentry->d_inode,
current_fh, lgp);
if (nfserr)
goto out_put_stid;
nfserr = nfsd4_insert_layout(lgp, ls);
out_put_stid:
nfs4_put_stid(&ls->ls_stid);
out:
return nfserr;
}
static __be32
nfsd4_layoutcommit(struct svc_rqst *rqstp,
struct nfsd4_compound_state *cstate,
struct nfsd4_layoutcommit *lcp)
{
const struct nfsd4_layout_seg *seg = &lcp->lc_seg;
struct svc_fh *current_fh = &cstate->current_fh;
const struct nfsd4_layout_ops *ops;
loff_t new_size = lcp->lc_last_wr + 1;
struct inode *inode;
struct nfs4_layout_stateid *ls;
__be32 nfserr;
nfserr = fh_verify(rqstp, current_fh, 0, NFSD_MAY_WRITE);
if (nfserr)
goto out;
nfserr = nfserr_layoutunavailable;
ops = nfsd4_layout_verify(current_fh->fh_export, lcp->lc_layout_type);
if (!ops)
goto out;
inode = current_fh->fh_dentry->d_inode;
nfserr = nfserr_inval;
if (new_size <= seg->offset) {
dprintk("pnfsd: last write before layout segment\n");
goto out;
}
if (new_size > seg->offset + seg->length) {
dprintk("pnfsd: last write beyond layout segment\n");
goto out;
}
if (!lcp->lc_newoffset && new_size > i_size_read(inode)) {
dprintk("pnfsd: layoutcommit beyond EOF\n");
goto out;
}
nfserr = nfsd4_preprocess_layout_stateid(rqstp, cstate, &lcp->lc_sid,
false, lcp->lc_layout_type,
&ls);
if (nfserr) {
/* fixup error code as per RFC5661 */
if (nfserr == nfserr_bad_stateid)
nfserr = nfserr_badlayout;
goto out;
}
nfserr = ops->proc_layoutcommit(inode, lcp);
if (nfserr)
goto out_put_stid;
if (new_size > i_size_read(inode)) {
lcp->lc_size_chg = 1;
lcp->lc_newsize = new_size;
} else {
lcp->lc_size_chg = 0;
}
out_put_stid:
nfs4_put_stid(&ls->ls_stid);
out:
return nfserr;
}
static __be32
nfsd4_layoutreturn(struct svc_rqst *rqstp,
struct nfsd4_compound_state *cstate,
struct nfsd4_layoutreturn *lrp)
{
struct svc_fh *current_fh = &cstate->current_fh;
__be32 nfserr;
nfserr = fh_verify(rqstp, current_fh, 0, NFSD_MAY_NOP);
if (nfserr)
goto out;
nfserr = nfserr_layoutunavailable;
if (!nfsd4_layout_verify(current_fh->fh_export, lrp->lr_layout_type))
goto out;
switch (lrp->lr_seg.iomode) {
case IOMODE_READ:
case IOMODE_RW:
case IOMODE_ANY:
break;
default:
dprintk("%s: invalid iomode %d\n", __func__,
lrp->lr_seg.iomode);
nfserr = nfserr_inval;
goto out;
}
switch (lrp->lr_return_type) {
case RETURN_FILE:
nfserr = nfsd4_return_file_layouts(rqstp, cstate, lrp);
break;
case RETURN_FSID:
case RETURN_ALL:
nfserr = nfsd4_return_client_layouts(rqstp, cstate, lrp);
break;
default:
dprintk("%s: invalid return_type %d\n", __func__,
lrp->lr_return_type);
nfserr = nfserr_inval;
break;
}
out:
return nfserr;
}
#endif /* CONFIG_NFSD_PNFS */
/* /*
* NULL call. * NULL call.
*/ */
...@@ -1679,6 +1926,36 @@ static inline u32 nfsd4_create_session_rsize(struct svc_rqst *rqstp, struct nfsd ...@@ -1679,6 +1926,36 @@ static inline u32 nfsd4_create_session_rsize(struct svc_rqst *rqstp, struct nfsd
op_encode_channel_attrs_maxsz) * sizeof(__be32); op_encode_channel_attrs_maxsz) * sizeof(__be32);
} }
#ifdef CONFIG_NFSD_PNFS
/*
* At this stage we don't really know what layout driver will handle the request,
* so we need to define an arbitrary upper bound here.
*/
#define MAX_LAYOUT_SIZE 128
static inline u32 nfsd4_layoutget_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
{
return (op_encode_hdr_size +
1 /* logr_return_on_close */ +
op_encode_stateid_maxsz +
1 /* nr of layouts */ +
MAX_LAYOUT_SIZE) * sizeof(__be32);
}
static inline u32 nfsd4_layoutcommit_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
{
return (op_encode_hdr_size +
1 /* locr_newsize */ +
2 /* ns_size */) * sizeof(__be32);
}
static inline u32 nfsd4_layoutreturn_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
{
return (op_encode_hdr_size +
1 /* lrs_stateid */ +
op_encode_stateid_maxsz) * sizeof(__be32);
}
#endif /* CONFIG_NFSD_PNFS */
static struct nfsd4_operation nfsd4_ops[] = { static struct nfsd4_operation nfsd4_ops[] = {
[OP_ACCESS] = { [OP_ACCESS] = {
.op_func = (nfsd4op_func)nfsd4_access, .op_func = (nfsd4op_func)nfsd4_access,
...@@ -1966,6 +2243,31 @@ static struct nfsd4_operation nfsd4_ops[] = { ...@@ -1966,6 +2243,31 @@ static struct nfsd4_operation nfsd4_ops[] = {
.op_get_currentstateid = (stateid_getter)nfsd4_get_freestateid, .op_get_currentstateid = (stateid_getter)nfsd4_get_freestateid,
.op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize, .op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize,
}, },
#ifdef CONFIG_NFSD_PNFS
[OP_GETDEVICEINFO] = {
.op_func = (nfsd4op_func)nfsd4_getdeviceinfo,
.op_flags = ALLOWED_WITHOUT_FH,
.op_name = "OP_GETDEVICEINFO",
},
[OP_LAYOUTGET] = {
.op_func = (nfsd4op_func)nfsd4_layoutget,
.op_flags = OP_MODIFIES_SOMETHING,
.op_name = "OP_LAYOUTGET",
.op_rsize_bop = (nfsd4op_rsize)nfsd4_layoutget_rsize,
},
[OP_LAYOUTCOMMIT] = {
.op_func = (nfsd4op_func)nfsd4_layoutcommit,
.op_flags = OP_MODIFIES_SOMETHING,
.op_name = "OP_LAYOUTCOMMIT",
.op_rsize_bop = (nfsd4op_rsize)nfsd4_layoutcommit_rsize,
},
[OP_LAYOUTRETURN] = {
.op_func = (nfsd4op_func)nfsd4_layoutreturn,
.op_flags = OP_MODIFIES_SOMETHING,
.op_name = "OP_LAYOUTRETURN",
.op_rsize_bop = (nfsd4op_rsize)nfsd4_layoutreturn_rsize,
},
#endif /* CONFIG_NFSD_PNFS */
/* NFSv4.2 operations */ /* NFSv4.2 operations */
[OP_ALLOCATE] = { [OP_ALLOCATE] = {
......
...@@ -48,6 +48,7 @@ ...@@ -48,6 +48,7 @@
#include "current_stateid.h" #include "current_stateid.h"
#include "netns.h" #include "netns.h"
#include "pnfs.h"
#define NFSDDBG_FACILITY NFSDDBG_PROC #define NFSDDBG_FACILITY NFSDDBG_PROC
...@@ -1539,6 +1540,9 @@ static struct nfs4_client *alloc_client(struct xdr_netobj name) ...@@ -1539,6 +1540,9 @@ static struct nfs4_client *alloc_client(struct xdr_netobj name)
INIT_LIST_HEAD(&clp->cl_lru); INIT_LIST_HEAD(&clp->cl_lru);
INIT_LIST_HEAD(&clp->cl_callbacks); INIT_LIST_HEAD(&clp->cl_callbacks);
INIT_LIST_HEAD(&clp->cl_revoked); INIT_LIST_HEAD(&clp->cl_revoked);
#ifdef CONFIG_NFSD_PNFS
INIT_LIST_HEAD(&clp->cl_lo_states);
#endif
spin_lock_init(&clp->cl_lock); spin_lock_init(&clp->cl_lock);
rpc_init_wait_queue(&clp->cl_cb_waitq, "Backchannel slot table"); rpc_init_wait_queue(&clp->cl_cb_waitq, "Backchannel slot table");
return clp; return clp;
...@@ -1643,6 +1647,7 @@ __destroy_client(struct nfs4_client *clp) ...@@ -1643,6 +1647,7 @@ __destroy_client(struct nfs4_client *clp)
nfs4_get_stateowner(&oo->oo_owner); nfs4_get_stateowner(&oo->oo_owner);
release_openowner(oo); release_openowner(oo);
} }
nfsd4_return_all_client_layouts(clp);
nfsd4_shutdown_callback(clp); nfsd4_shutdown_callback(clp);
if (clp->cl_cb_conn.cb_xprt) if (clp->cl_cb_conn.cb_xprt)
svc_xprt_put(clp->cl_cb_conn.cb_xprt); svc_xprt_put(clp->cl_cb_conn.cb_xprt);
...@@ -2126,8 +2131,11 @@ nfsd4_replay_cache_entry(struct nfsd4_compoundres *resp, ...@@ -2126,8 +2131,11 @@ nfsd4_replay_cache_entry(struct nfsd4_compoundres *resp,
static void static void
nfsd4_set_ex_flags(struct nfs4_client *new, struct nfsd4_exchange_id *clid) nfsd4_set_ex_flags(struct nfs4_client *new, struct nfsd4_exchange_id *clid)
{ {
/* pNFS is not supported */ #ifdef CONFIG_NFSD_PNFS
new->cl_exchange_flags |= EXCHGID4_FLAG_USE_PNFS_MDS;
#else
new->cl_exchange_flags |= EXCHGID4_FLAG_USE_NON_PNFS; new->cl_exchange_flags |= EXCHGID4_FLAG_USE_NON_PNFS;
#endif
/* Referrals are supported, Migration is not. */ /* Referrals are supported, Migration is not. */
new->cl_exchange_flags |= EXCHGID4_FLAG_SUPP_MOVED_REFER; new->cl_exchange_flags |= EXCHGID4_FLAG_SUPP_MOVED_REFER;
...@@ -3055,6 +3063,9 @@ static void nfsd4_init_file(struct knfsd_fh *fh, unsigned int hashval, ...@@ -3055,6 +3063,9 @@ static void nfsd4_init_file(struct knfsd_fh *fh, unsigned int hashval,
fp->fi_share_deny = 0; fp->fi_share_deny = 0;
memset(fp->fi_fds, 0, sizeof(fp->fi_fds)); memset(fp->fi_fds, 0, sizeof(fp->fi_fds));
memset(fp->fi_access, 0, sizeof(fp->fi_access)); memset(fp->fi_access, 0, sizeof(fp->fi_access));
#ifdef CONFIG_NFSD_PNFS
INIT_LIST_HEAD(&fp->fi_lo_states);
#endif
hlist_add_head_rcu(&fp->fi_hash, &file_hashtbl[hashval]); hlist_add_head_rcu(&fp->fi_hash, &file_hashtbl[hashval]);
} }
...@@ -4841,6 +4852,9 @@ nfsd4_close(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, ...@@ -4841,6 +4852,9 @@ nfsd4_close(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
update_stateid(&stp->st_stid.sc_stateid); update_stateid(&stp->st_stid.sc_stateid);
memcpy(&close->cl_stateid, &stp->st_stid.sc_stateid, sizeof(stateid_t)); memcpy(&close->cl_stateid, &stp->st_stid.sc_stateid, sizeof(stateid_t));
nfsd4_return_all_file_layouts(stp->st_stateowner->so_client,
stp->st_stid.sc_file);
nfsd4_close_open_stateid(stp); nfsd4_close_open_stateid(stp);
/* put reference from nfs4_preprocess_seqid_op */ /* put reference from nfs4_preprocess_seqid_op */
......
This diff is collapsed.
...@@ -21,6 +21,7 @@ ...@@ -21,6 +21,7 @@
#include "cache.h" #include "cache.h"
#include "state.h" #include "state.h"
#include "netns.h" #include "netns.h"
#include "pnfs.h"
/* /*
* We have a single directory with several nodes in it. * We have a single directory with several nodes in it.
...@@ -1258,9 +1259,12 @@ static int __init init_nfsd(void) ...@@ -1258,9 +1259,12 @@ static int __init init_nfsd(void)
retval = nfsd4_init_slabs(); retval = nfsd4_init_slabs();
if (retval) if (retval)
goto out_unregister_pernet; goto out_unregister_pernet;
retval = nfsd_fault_inject_init(); /* nfsd fault injection controls */ retval = nfsd4_init_pnfs();
if (retval) if (retval)
goto out_free_slabs; goto out_free_slabs;
retval = nfsd_fault_inject_init(); /* nfsd fault injection controls */
if (retval)
goto out_exit_pnfs;
nfsd_stat_init(); /* Statistics */ nfsd_stat_init(); /* Statistics */
retval = nfsd_reply_cache_init(); retval = nfsd_reply_cache_init();
if (retval) if (retval)
...@@ -1282,6 +1286,8 @@ static int __init init_nfsd(void) ...@@ -1282,6 +1286,8 @@ static int __init init_nfsd(void)
out_free_stat: out_free_stat:
nfsd_stat_shutdown(); nfsd_stat_shutdown();
nfsd_fault_inject_cleanup(); nfsd_fault_inject_cleanup();
out_exit_pnfs:
nfsd4_exit_pnfs();
out_free_slabs: out_free_slabs:
nfsd4_free_slabs(); nfsd4_free_slabs();
out_unregister_pernet: out_unregister_pernet:
...@@ -1299,6 +1305,7 @@ static void __exit exit_nfsd(void) ...@@ -1299,6 +1305,7 @@ static void __exit exit_nfsd(void)
nfsd_stat_shutdown(); nfsd_stat_shutdown();
nfsd_lockd_shutdown(); nfsd_lockd_shutdown();
nfsd4_free_slabs(); nfsd4_free_slabs();
nfsd4_exit_pnfs();
nfsd_fault_inject_cleanup(); nfsd_fault_inject_cleanup();
unregister_filesystem(&nfsd_fs_type); unregister_filesystem(&nfsd_fs_type);
unregister_pernet_subsys(&nfsd_net_ops); unregister_pernet_subsys(&nfsd_net_ops);
......
...@@ -325,15 +325,27 @@ void nfsd_lockd_shutdown(void); ...@@ -325,15 +325,27 @@ void nfsd_lockd_shutdown(void);
#define NFSD4_SUPPORTED_ATTRS_WORD2 0 #define NFSD4_SUPPORTED_ATTRS_WORD2 0
/* 4.1 */
#ifdef CONFIG_NFSD_PNFS
#define PNFSD_SUPPORTED_ATTRS_WORD1 FATTR4_WORD1_FS_LAYOUT_TYPES
#define PNFSD_SUPPORTED_ATTRS_WORD2 \
(FATTR4_WORD2_LAYOUT_BLKSIZE | FATTR4_WORD2_LAYOUT_TYPES)
#else
#define PNFSD_SUPPORTED_ATTRS_WORD1 0
#define PNFSD_SUPPORTED_ATTRS_WORD2 0
#endif /* CONFIG_NFSD_PNFS */
#define NFSD4_1_SUPPORTED_ATTRS_WORD0 \ #define NFSD4_1_SUPPORTED_ATTRS_WORD0 \
NFSD4_SUPPORTED_ATTRS_WORD0 NFSD4_SUPPORTED_ATTRS_WORD0
#define NFSD4_1_SUPPORTED_ATTRS_WORD1 \ #define NFSD4_1_SUPPORTED_ATTRS_WORD1 \
NFSD4_SUPPORTED_ATTRS_WORD1 (NFSD4_SUPPORTED_ATTRS_WORD1 | PNFSD_SUPPORTED_ATTRS_WORD1)
#define NFSD4_1_SUPPORTED_ATTRS_WORD2 \ #define NFSD4_1_SUPPORTED_ATTRS_WORD2 \
(NFSD4_SUPPORTED_ATTRS_WORD2 | FATTR4_WORD2_SUPPATTR_EXCLCREAT) (NFSD4_SUPPORTED_ATTRS_WORD2 | PNFSD_SUPPORTED_ATTRS_WORD2 | \
FATTR4_WORD2_SUPPATTR_EXCLCREAT)
/* 4.2 */
#ifdef CONFIG_NFSD_V4_SECURITY_LABEL #ifdef CONFIG_NFSD_V4_SECURITY_LABEL
#define NFSD4_2_SECURITY_ATTRS FATTR4_WORD2_SECURITY_LABEL #define NFSD4_2_SECURITY_ATTRS FATTR4_WORD2_SECURITY_LABEL
#else #else
......
#ifndef _FS_NFSD_PNFS_H
#define _FS_NFSD_PNFS_H 1
#include <linux/exportfs.h>
#include <linux/nfsd/export.h>
#include "state.h"
#include "xdr4.h"
struct xdr_stream;
struct nfsd4_deviceid_map {
struct list_head hash;
u64 idx;
int fsid_type;
u32 fsid[];
};
struct nfsd4_layout_ops {
u32 notify_types;
__be32 (*proc_getdeviceinfo)(struct super_block *sb,
struct nfsd4_getdeviceinfo *gdevp);
__be32 (*encode_getdeviceinfo)(struct xdr_stream *xdr,
struct nfsd4_getdeviceinfo *gdevp);
__be32 (*proc_layoutget)(struct inode *, const struct svc_fh *fhp,
struct nfsd4_layoutget *lgp);
__be32 (*encode_layoutget)(struct xdr_stream *,
struct nfsd4_layoutget *lgp);
__be32 (*proc_layoutcommit)(struct inode *inode,
struct nfsd4_layoutcommit *lcp);
};
extern const struct nfsd4_layout_ops *nfsd4_layout_ops[];
__be32 nfsd4_preprocess_layout_stateid(struct svc_rqst *rqstp,
struct nfsd4_compound_state *cstate, stateid_t *stateid,
bool create, u32 layout_type, struct nfs4_layout_stateid **lsp);
__be32 nfsd4_insert_layout(struct nfsd4_layoutget *lgp,
struct nfs4_layout_stateid *ls);
__be32 nfsd4_return_file_layouts(struct svc_rqst *rqstp,
struct nfsd4_compound_state *cstate,
struct nfsd4_layoutreturn *lrp);
__be32 nfsd4_return_client_layouts(struct svc_rqst *rqstp,
struct nfsd4_compound_state *cstate,
struct nfsd4_layoutreturn *lrp);
int nfsd4_set_deviceid(struct nfsd4_deviceid *id, const struct svc_fh *fhp,
u32 device_generation);
struct nfsd4_deviceid_map *nfsd4_find_devid_map(int idx);
#ifdef CONFIG_NFSD_PNFS
void nfsd4_setup_layout_type(struct svc_export *exp);
void nfsd4_return_all_client_layouts(struct nfs4_client *);
void nfsd4_return_all_file_layouts(struct nfs4_client *clp,
struct nfs4_file *fp);
int nfsd4_init_pnfs(void);
void nfsd4_exit_pnfs(void);
#else
static inline void nfsd4_setup_layout_type(struct svc_export *exp)
{
}
static inline void nfsd4_return_all_client_layouts(struct nfs4_client *clp)
{
}
static inline void nfsd4_return_all_file_layouts(struct nfs4_client *clp,
struct nfs4_file *fp)
{
}
static inline void nfsd4_exit_pnfs(void)
{
}
static inline int nfsd4_init_pnfs(void)
{
return 0;
}
#endif /* CONFIG_NFSD_PNFS */
#endif /* _FS_NFSD_PNFS_H */
...@@ -92,6 +92,7 @@ struct nfs4_stid { ...@@ -92,6 +92,7 @@ struct nfs4_stid {
/* For a deleg stateid kept around only to process free_stateid's: */ /* For a deleg stateid kept around only to process free_stateid's: */
#define NFS4_REVOKED_DELEG_STID 16 #define NFS4_REVOKED_DELEG_STID 16
#define NFS4_CLOSED_DELEG_STID 32 #define NFS4_CLOSED_DELEG_STID 32
#define NFS4_LAYOUT_STID 64
unsigned char sc_type; unsigned char sc_type;
stateid_t sc_stateid; stateid_t sc_stateid;
struct nfs4_client *sc_client; struct nfs4_client *sc_client;
...@@ -297,6 +298,9 @@ struct nfs4_client { ...@@ -297,6 +298,9 @@ struct nfs4_client {
struct list_head cl_delegations; struct list_head cl_delegations;
struct list_head cl_revoked; /* unacknowledged, revoked 4.1 state */ struct list_head cl_revoked; /* unacknowledged, revoked 4.1 state */
struct list_head cl_lru; /* tail queue */ struct list_head cl_lru; /* tail queue */
#ifdef CONFIG_NFSD_PNFS
struct list_head cl_lo_states; /* outstanding layout states */
#endif
struct xdr_netobj cl_name; /* id generated by client */ struct xdr_netobj cl_name; /* id generated by client */
nfs4_verifier cl_verifier; /* generated by client */ nfs4_verifier cl_verifier; /* generated by client */
time_t cl_time; /* time of last lease renewal */ time_t cl_time; /* time of last lease renewal */
...@@ -496,6 +500,9 @@ struct nfs4_file { ...@@ -496,6 +500,9 @@ struct nfs4_file {
int fi_delegees; int fi_delegees;
struct knfsd_fh fi_fhandle; struct knfsd_fh fi_fhandle;
bool fi_had_conflict; bool fi_had_conflict;
#ifdef CONFIG_NFSD_PNFS
struct list_head fi_lo_states;
#endif
}; };
/* /*
...@@ -528,6 +535,20 @@ static inline struct nfs4_ol_stateid *openlockstateid(struct nfs4_stid *s) ...@@ -528,6 +535,20 @@ static inline struct nfs4_ol_stateid *openlockstateid(struct nfs4_stid *s)
return container_of(s, struct nfs4_ol_stateid, st_stid); return container_of(s, struct nfs4_ol_stateid, st_stid);
} }
struct nfs4_layout_stateid {
struct nfs4_stid ls_stid;
struct list_head ls_perclnt;
struct list_head ls_perfile;
spinlock_t ls_lock;
struct list_head ls_layouts;
u32 ls_layout_type;
};
static inline struct nfs4_layout_stateid *layoutstateid(struct nfs4_stid *s)
{
return container_of(s, struct nfs4_layout_stateid, ls_stid);
}
/* flags for preprocess_seqid_op() */ /* flags for preprocess_seqid_op() */
#define RD_STATE 0x00000010 #define RD_STATE 0x00000010
#define WR_STATE 0x00000020 #define WR_STATE 0x00000020
......
...@@ -428,6 +428,61 @@ struct nfsd4_reclaim_complete { ...@@ -428,6 +428,61 @@ struct nfsd4_reclaim_complete {
u32 rca_one_fs; u32 rca_one_fs;
}; };
struct nfsd4_deviceid {
u64 fsid_idx;
u32 generation;
u32 pad;
};
struct nfsd4_layout_seg {
u32 iomode;
u64 offset;
u64 length;
};
struct nfsd4_getdeviceinfo {
struct nfsd4_deviceid gd_devid; /* request */
u32 gd_layout_type; /* request */
u32 gd_maxcount; /* request */
u32 gd_notify_types;/* request - response */
void *gd_device; /* response */
};
struct nfsd4_layoutget {
u64 lg_minlength; /* request */
u32 lg_signal; /* request */
u32 lg_layout_type; /* request */
u32 lg_maxcount; /* request */
stateid_t lg_sid; /* request/response */
struct nfsd4_layout_seg lg_seg; /* request/response */
void *lg_content; /* response */
};
struct nfsd4_layoutcommit {
stateid_t lc_sid; /* request */
struct nfsd4_layout_seg lc_seg; /* request */
u32 lc_reclaim; /* request */
u32 lc_newoffset; /* request */
u64 lc_last_wr; /* request */
struct timespec lc_mtime; /* request */
u32 lc_layout_type; /* request */
u32 lc_up_len; /* layout length */
void *lc_up_layout; /* decoded by callback */
u32 lc_size_chg; /* boolean for response */
u64 lc_newsize; /* response */
};
struct nfsd4_layoutreturn {
u32 lr_return_type; /* request */
u32 lr_layout_type; /* request */
struct nfsd4_layout_seg lr_seg; /* request */
u32 lr_reclaim; /* request */
u32 lrf_body_len; /* request */
void *lrf_body; /* request */
stateid_t lr_sid; /* request/response */
u32 lrs_present; /* response */
};
struct nfsd4_fallocate { struct nfsd4_fallocate {
/* request */ /* request */
stateid_t falloc_stateid; stateid_t falloc_stateid;
...@@ -491,6 +546,10 @@ struct nfsd4_op { ...@@ -491,6 +546,10 @@ struct nfsd4_op {
struct nfsd4_reclaim_complete reclaim_complete; struct nfsd4_reclaim_complete reclaim_complete;
struct nfsd4_test_stateid test_stateid; struct nfsd4_test_stateid test_stateid;
struct nfsd4_free_stateid free_stateid; struct nfsd4_free_stateid free_stateid;
struct nfsd4_getdeviceinfo getdeviceinfo;
struct nfsd4_layoutget layoutget;
struct nfsd4_layoutcommit layoutcommit;
struct nfsd4_layoutreturn layoutreturn;
/* NFSv4.2 */ /* NFSv4.2 */
struct nfsd4_fallocate allocate; struct nfsd4_fallocate allocate;
......
...@@ -411,6 +411,7 @@ enum lock_type4 { ...@@ -411,6 +411,7 @@ enum lock_type4 {
#define FATTR4_WORD1_TIME_MODIFY_SET (1UL << 22) #define FATTR4_WORD1_TIME_MODIFY_SET (1UL << 22)
#define FATTR4_WORD1_MOUNTED_ON_FILEID (1UL << 23) #define FATTR4_WORD1_MOUNTED_ON_FILEID (1UL << 23)
#define FATTR4_WORD1_FS_LAYOUT_TYPES (1UL << 30) #define FATTR4_WORD1_FS_LAYOUT_TYPES (1UL << 30)
#define FATTR4_WORD2_LAYOUT_TYPES (1UL << 0)
#define FATTR4_WORD2_LAYOUT_BLKSIZE (1UL << 1) #define FATTR4_WORD2_LAYOUT_BLKSIZE (1UL << 1)
#define FATTR4_WORD2_MDSTHRESHOLD (1UL << 4) #define FATTR4_WORD2_MDSTHRESHOLD (1UL << 4)
#define FATTR4_WORD2_SECURITY_LABEL (1UL << 16) #define FATTR4_WORD2_SECURITY_LABEL (1UL << 16)
......
...@@ -32,6 +32,7 @@ ...@@ -32,6 +32,7 @@
#define NFSDDBG_REPCACHE 0x0080 #define NFSDDBG_REPCACHE 0x0080
#define NFSDDBG_XDR 0x0100 #define NFSDDBG_XDR 0x0100
#define NFSDDBG_LOCKD 0x0200 #define NFSDDBG_LOCKD 0x0200
#define NFSDDBG_PNFS 0x0400
#define NFSDDBG_ALL 0x7FFF #define NFSDDBG_ALL 0x7FFF
#define NFSDDBG_NOCHANGE 0xFFFF #define NFSDDBG_NOCHANGE 0xFFFF
......
...@@ -47,8 +47,10 @@ ...@@ -47,8 +47,10 @@
* exported filesystem. * exported filesystem.
*/ */
#define NFSEXP_V4ROOT 0x10000 #define NFSEXP_V4ROOT 0x10000
#define NFSEXP_NOPNFS 0x20000
/* All flags that we claim to support. (Note we don't support NOACL.) */ /* All flags that we claim to support. (Note we don't support NOACL.) */
#define NFSEXP_ALLFLAGS 0x1FE7F #define NFSEXP_ALLFLAGS 0x3FE7F
/* The flags that may vary depending on security flavor: */ /* The flags that may vary depending on security flavor: */
#define NFSEXP_SECINFO_FLAGS (NFSEXP_READONLY | NFSEXP_ROOTSQUASH \ #define NFSEXP_SECINFO_FLAGS (NFSEXP_READONLY | NFSEXP_ROOTSQUASH \
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment