leandrof/linux
1
0
Fork 0
forked from Minki/linux
Code Issues Pull Requests Packages Projects Releases Wiki Activity

NFS client updates for Linux 3.5

Browse Source 
New features include:
 - Rewrite the O_DIRECT code so that it can share the same coalescing and
   pNFS functionality as the page cache code.
 - Allow the server to provide hints as to when we should use pNFS, and
   when it is more efficient to read and write through the metadata
   server.
 - NFS cache consistency updates:
   - Use the ctime to emulate a change attribute for NFSv2/v3 so that
     all NFS versions can share the same cache management code.
   - New cache management code will only look at the change attribute
     and size attribute when deciding whether or not our cached data
     is still valid or not.
   - Don't request NFSv4 post-op attributes on writes in cases such as
     O_DIRECT, where we don't care about data cache consistency, or
     when we have a write delegation, and know that our cache is
     still consistent.
   - Don't request NFSv4 post-op attributes on operations such as
     COMMIT, where there are no expected metadata updates.
   - Don't request NFSv4 directory post-op attributes in cases where
     the operations themselves already return change attribute updates:
     i.e.  operations such as OPEN, CREATE, REMOVE, LINK and RENAME.
 - Speed up 'ls' and friends by using READDIR rather than READDIRPLUS
   if we detect no attempts to lookup filenames.
 - Improve the code sharing between NFSv2/v3 and v4 mounts
 - NFSv4.1 state management efficiency improvements
 - More patches in preparation for NFSv4/v4.1 migration functionality.
 -----BEGIN PGP SIGNATURE-----
 Version: GnuPG v1.4.12 (GNU/Linux)
 
 iQIcBAABAgAGBQJPw/MNAAoJEGcL54qWCgDyxU8P/2kKqhAlhoLEArBqo9FT3/OK
 YrNs5uO/erTgnCG8L0XQvTKjHB9F7TAeFXqTmBZuPlb1afRpHHt2vzPqzIvUCeOC
 ZXm8vzZf4nxWZgEFoTDdUBvqQi9lLdIzCRhSaVCKcRnNwiuaKDd/iwykbWGcHqmv
 jtR4lzXPllJdKCUL3yb3juVrpq6Vvn254ID2pqdnYcEtIJIHgaRZpwdp4Iz9+8b5
 Moishiw2rgCBJIhf+VCYd8B2oYfMgSDPxG1o3etkwY46qo+4s+CIls9Vu/6YzGXK
 3+NdLatRDqKhQpLm0/R+dI3rntnTZ8x6LgWnTGxUsiqb6pAaHZPK284rf2eh/s7M
 Q4G4203r0uw539kIt6eKOGqC9c8kZAPCHlQSPCaImZyCJsz+6OMShNlGB5bZpFPr
 tbdxaxudrhCF7UVKXicJCWgv2nIHtek6fNwey1jqFoYgZP5ipiBKymvXQC5WAMBw
 7RHJor/JEC+UJkVg/7Mkpg0UNw3E36CTYLeRJKlNCS6YO9NJQseCDxhhMNAy/ab7
 RGO8DVMkUsOUH20S+a19LyeFQtveWFIE0DiDqRn0KnNGhGwHrv2t4xFukjlrf4Sw
 8FQUBRdtFxfmspfA1IdoTY49XZQda5eagvTy1MyaWEh+jPSJ4G5j3sSjFiaKAJqw
 79iQKFGkxPOSHx2yCdAF
 =suVW
 -----END PGP SIGNATURE-----

Merge tag 'nfs-for-3.5-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs

Pull NFS client updates from Trond Myklebust:
 "New features include:
   - Rewrite the O_DIRECT code so that it can share the same coalescing
     and pNFS functionality as the page cache code.
   - Allow the server to provide hints as to when we should use pNFS,
     and when it is more efficient to read and write through the
     metadata server.
   - NFS cache consistency updates:
     * Use the ctime to emulate a change attribute for NFSv2/v3 so that
       all NFS versions can share the same cache management code.
     * New cache management code will only look at the change attribute
       and size attribute when deciding whether or not our cached data
       is still valid or not.
     * Don't request NFSv4 post-op attributes on writes in cases such as
       O_DIRECT, where we don't care about data cache consistency, or
       when we have a write delegation, and know that our cache is still
       consistent.
     * Don't request NFSv4 post-op attributes on operations such as
       COMMIT, where there are no expected metadata updates.
     * Don't request NFSv4 directory post-op attributes in cases where
       the operations themselves already return change attribute
       updates: i.e. operations such as OPEN, CREATE, REMOVE, LINK and
       RENAME.
   - Speed up 'ls' and friends by using READDIR rather than READDIRPLUS
     if we detect no attempts to lookup filenames.
   - Improve the code sharing between NFSv2/v3 and v4 mounts
   - NFSv4.1 state management efficiency improvements
   - More patches in preparation for NFSv4/v4.1 migration functionality."

Fix trivial conflict in fs/nfs/nfs4proc.c that was due to the dcache
qstr name initialization changes (that made the length/hash a 64-bit
union)

* tag 'nfs-for-3.5-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs: (146 commits)
  NFSv4: Add debugging printks to state manager
  NFSv4: Map NFS4ERR_SHARE_DENIED into an EACCES error instead of EIO
  NFSv4: update_changeattr does not need to set NFS_INO_REVAL_PAGECACHE
  NFSv4.1: nfs4_reset_session should use nfs4_handle_reclaim_lease_error
  NFSv4.1: Handle other occurrences of NFS4ERR_CONN_NOT_BOUND_TO_SESSION
  NFSv4.1: Handle NFS4ERR_CONN_NOT_BOUND_TO_SESSION in the state manager
  NFSv4.1: Handle errors in nfs4_bind_conn_to_session
  NFSv4.1: nfs4_bind_conn_to_session should drain the session
  NFSv4.1: Don't clobber the seqid if exchange_id returns a confirmed clientid
  NFSv4.1: Add DESTROY_CLIENTID
  NFSv4.1: Ensure we use the correct credentials for bind_conn_to_session
  NFSv4.1: Ensure we use the correct credentials for session create/destroy
  NFSv4.1: Move NFSPROC4_CLNT_BIND_CONN_TO_SESSION to the end of the operations
  NFSv4.1: Handle NFS4ERR_SEQ_MISORDERED when confirming the lease
  NFSv4: When purging the lease, we must clear NFS4CLNT_LEASE_CONFIRM
  NFSv4: Clean up the error handling for nfs4_reclaim_lease
  NFSv4.1: Exchange ID must use GFP_NOFS allocation mode
  nfs41: Use BIND_CONN_TO_SESSION for CB_PATH_DOWN*
  nfs4.1: add BIND_CONN_TO_SESSION operation
  NFSv4.1 test the mdsthreshold hint parameters
  ...
This commit is contained in:
Linus Torvalds 2012-05-29 10:43:51 -07:00
commit 53f2c4a8fd
48 changed files with 3996 additions and 2917 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
fs/nfs/Kconfig
View File

@ -29,9 +29,20 @@ config NFS_FS
If unsure, say N.
config NFS_V2
bool "NFS client support for NFS version 2"
depends on NFS_FS
default y
help
This option enables support for version 2 of the NFS protocol
(RFC 1094) in the kernel's NFS client.
If unsure, say Y.
config NFS_V3
bool "NFS client support for NFS version 3"
depends on NFS_FS
default y
help
This option enables support for version 3 of the NFS protocol
(RFC 1813) in the kernel's NFS client.

5
fs/nfs/Makefile
View File

@ -4,11 +4,12 @@
obj-$(CONFIG_NFS_FS) += nfs.o
nfs-y := client.o dir.o file.o getroot.o inode.o super.o nfs2xdr.o \
direct.o pagelist.o proc.o read.o symlink.o unlink.o \
nfs-y := client.o dir.o file.o getroot.o inode.o super.o \
direct.o pagelist.o read.o symlink.o unlink.o \
write.o namespace.o mount_clnt.o \
dns_resolve.o cache_lib.o
nfs-$(CONFIG_ROOT_NFS) += nfsroot.o
nfs-$(CONFIG_NFS_V2) += proc.o nfs2xdr.o
nfs-$(CONFIG_NFS_V3) += nfs3proc.o nfs3xdr.o
nfs-$(CONFIG_NFS_V3_ACL) += nfs3acl.o
nfs-$(CONFIG_NFS_V4) += nfs4proc.o nfs4xdr.o nfs4state.o nfs4renewd.o \

90
fs/nfs/blocklayout/blocklayout.c
View File

@ -187,7 +187,6 @@ static void bl_end_io_read(struct bio *bio, int err)
struct parallel_io *par = bio->bi_private;
const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
struct bio_vec *bvec = bio->bi_io_vec + bio->bi_vcnt - 1;
struct nfs_read_data *rdata = (struct nfs_read_data *)par->data;
do {
struct page *page = bvec->bv_page;
@ -198,9 +197,12 @@ static void bl_end_io_read(struct bio *bio, int err)
SetPageUptodate(page);
} while (bvec >= bio->bi_io_vec);
if (!uptodate) {
if (!rdata->pnfs_error)
rdata->pnfs_error = -EIO;
pnfs_set_lo_fail(rdata->lseg);
struct nfs_read_data *rdata = par->data;
struct nfs_pgio_header *header = rdata->header;
if (!header->pnfs_error)
header->pnfs_error = -EIO;
pnfs_set_lo_fail(header->lseg);
}
bio_put(bio);
put_parallel(par);
@ -221,7 +223,7 @@ bl_end_par_io_read(void *data, int unused)
{
struct nfs_read_data *rdata = data;
rdata->task.tk_status = rdata->pnfs_error;
rdata->task.tk_status = rdata->header->pnfs_error;
INIT_WORK(&rdata->task.u.tk_work, bl_read_cleanup);
schedule_work(&rdata->task.u.tk_work);
}
@ -229,6 +231,7 @@ bl_end_par_io_read(void *data, int unused)
static enum pnfs_try_status
bl_read_pagelist(struct nfs_read_data *rdata)
{
struct nfs_pgio_header *header = rdata->header;
int i, hole;
struct bio *bio = NULL;
struct pnfs_block_extent *be = NULL, *cow_read = NULL;
@ -239,7 +242,7 @@ bl_read_pagelist(struct nfs_read_data *rdata)
int pg_index = rdata->args.pgbase >> PAGE_CACHE_SHIFT;
dprintk("%s enter nr_pages %u offset %lld count %u\n", __func__,
rdata->npages, f_offset, (unsigned int)rdata->args.count);
rdata->pages.npages, f_offset, (unsigned int)rdata->args.count);
par = alloc_parallel(rdata);
if (!par)
@ -249,17 +252,17 @@ bl_read_pagelist(struct nfs_read_data *rdata)
isect = (sector_t) (f_offset >> SECTOR_SHIFT);
/* Code assumes extents are page-aligned */
for (i = pg_index; i < rdata->npages; i++) {
for (i = pg_index; i < rdata->pages.npages; i++) {
if (!extent_length) {
/* We've used up the previous extent */
bl_put_extent(be);
bl_put_extent(cow_read);
bio = bl_submit_bio(READ, bio);
/* Get the next one */
be = bl_find_get_extent(BLK_LSEG2EXT(rdata->lseg),
be = bl_find_get_extent(BLK_LSEG2EXT(header->lseg),
isect, &cow_read);
if (!be) {
rdata->pnfs_error = -EIO;
header->pnfs_error = -EIO;
goto out;
}
extent_length = be->be_length -
@ -282,11 +285,12 @@ bl_read_pagelist(struct nfs_read_data *rdata)
struct pnfs_block_extent *be_read;
be_read = (hole && cow_read) ? cow_read : be;
bio = bl_add_page_to_bio(bio, rdata->npages - i, READ,
bio = bl_add_page_to_bio(bio, rdata->pages.npages - i,
READ,
isect, pages[i], be_read,
bl_end_io_read, par);
if (IS_ERR(bio)) {
rdata->pnfs_error = PTR_ERR(bio);
header->pnfs_error = PTR_ERR(bio);
bio = NULL;
goto out;
}
@ -294,9 +298,9 @@ bl_read_pagelist(struct nfs_read_data *rdata)
isect += PAGE_CACHE_SECTORS;
extent_length -= PAGE_CACHE_SECTORS;
}
if ((isect << SECTOR_SHIFT) >= rdata->inode->i_size) {
if ((isect << SECTOR_SHIFT) >= header->inode->i_size) {
rdata->res.eof = 1;
rdata->res.count = rdata->inode->i_size - f_offset;
rdata->res.count = header->inode->i_size - f_offset;
} else {
rdata->res.count = (isect << SECTOR_SHIFT) - f_offset;
}
@ -345,7 +349,6 @@ static void bl_end_io_write_zero(struct bio *bio, int err)
struct parallel_io *par = bio->bi_private;
const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
struct bio_vec *bvec = bio->bi_io_vec + bio->bi_vcnt - 1;
struct nfs_write_data *wdata = (struct nfs_write_data *)par->data;
do {
struct page *page = bvec->bv_page;
@ -358,9 +361,12 @@ static void bl_end_io_write_zero(struct bio *bio, int err)
} while (bvec >= bio->bi_io_vec);
if (unlikely(!uptodate)) {
if (!wdata->pnfs_error)
wdata->pnfs_error = -EIO;
pnfs_set_lo_fail(wdata->lseg);
struct nfs_write_data *data = par->data;
struct nfs_pgio_header *header = data->header;
if (!header->pnfs_error)
header->pnfs_error = -EIO;
pnfs_set_lo_fail(header->lseg);
}
bio_put(bio);
put_parallel(par);
@ -370,12 +376,13 @@ static void bl_end_io_write(struct bio *bio, int err)
{
struct parallel_io *par = bio->bi_private;
const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
struct nfs_write_data *wdata = (struct nfs_write_data *)par->data;
struct nfs_write_data *data = par->data;
struct nfs_pgio_header *header = data->header;
if (!uptodate) {
if (!wdata->pnfs_error)
wdata->pnfs_error = -EIO;
pnfs_set_lo_fail(wdata->lseg);
if (!header->pnfs_error)
header->pnfs_error = -EIO;
pnfs_set_lo_fail(header->lseg);
}
bio_put(bio);
put_parallel(par);
@ -391,9 +398,9 @@ static void bl_write_cleanup(struct work_struct *work)
dprintk("%s enter\n", __func__);
task = container_of(work, struct rpc_task, u.tk_work);
wdata = container_of(task, struct nfs_write_data, task);
if (likely(!wdata->pnfs_error)) {
if (likely(!wdata->header->pnfs_error)) {
/* Marks for LAYOUTCOMMIT */
mark_extents_written(BLK_LSEG2EXT(wdata->lseg),
mark_extents_written(BLK_LSEG2EXT(wdata->header->lseg),
wdata->args.offset, wdata->args.count);
}
pnfs_ld_write_done(wdata);
@ -404,12 +411,12 @@ static void bl_end_par_io_write(void *data, int num_se)
{
struct nfs_write_data *wdata = data;
if (unlikely(wdata->pnfs_error)) {
bl_free_short_extents(&BLK_LSEG2EXT(wdata->lseg)->bl_inval,
if (unlikely(wdata->header->pnfs_error)) {
bl_free_short_extents(&BLK_LSEG2EXT(wdata->header->lseg)->bl_inval,
num_se);
}
wdata->task.tk_status = wdata->pnfs_error;
wdata->task.tk_status = wdata->header->pnfs_error;
wdata->verf.committed = NFS_FILE_SYNC;
INIT_WORK(&wdata->task.u.tk_work, bl_write_cleanup);
schedule_work(&wdata->task.u.tk_work);
@ -540,6 +547,7 @@ check_page:
static enum pnfs_try_status
bl_write_pagelist(struct nfs_write_data *wdata, int sync)
{
struct nfs_pgio_header *header = wdata->header;
int i, ret, npg_zero, pg_index, last = 0;
struct bio *bio = NULL;
struct pnfs_block_extent *be = NULL, *cow_read = NULL;
@ -552,7 +560,7 @@ bl_write_pagelist(struct nfs_write_data *wdata, int sync)
pgoff_t index;
u64 temp;
int npg_per_block =
NFS_SERVER(wdata->inode)->pnfs_blksize >> PAGE_CACHE_SHIFT;
NFS_SERVER(header->inode)->pnfs_blksize >> PAGE_CACHE_SHIFT;
dprintk("%s enter, %Zu@%lld\n", __func__, count, offset);
/* At this point, wdata->pages is a (sequential) list of nfs_pages.
@ -566,7 +574,7 @@ bl_write_pagelist(struct nfs_write_data *wdata, int sync)
/* At this point, have to be more careful with error handling */
isect = (sector_t) ((offset & (long)PAGE_CACHE_MASK) >> SECTOR_SHIFT);
be = bl_find_get_extent(BLK_LSEG2EXT(wdata->lseg), isect, &cow_read);
be = bl_find_get_extent(BLK_LSEG2EXT(header->lseg), isect, &cow_read);
if (!be || !is_writable(be, isect)) {
dprintk("%s no matching extents!\n", __func__);
goto out_mds;
@ -597,10 +605,10 @@ fill_invalid_ext:
dprintk("%s zero %dth page: index %lu isect %llu\n",
__func__, npg_zero, index,
(unsigned long long)isect);
page = bl_find_get_zeroing_page(wdata->inode, index,
page = bl_find_get_zeroing_page(header->inode, index,
cow_read);
if (unlikely(IS_ERR(page))) {
wdata->pnfs_error = PTR_ERR(page);
header->pnfs_error = PTR_ERR(page);
goto out;
} else if (page == NULL)
goto next_page;
@ -612,7 +620,7 @@ fill_invalid_ext:
__func__, ret);
end_page_writeback(page);
page_cache_release(page);
wdata->pnfs_error = ret;
header->pnfs_error = ret;
goto out;
}
if (likely(!bl_push_one_short_extent(be->be_inval)))
@ -620,11 +628,11 @@ fill_invalid_ext:
else {
end_page_writeback(page);
page_cache_release(page);
wdata->pnfs_error = -ENOMEM;
header->pnfs_error = -ENOMEM;
goto out;
}
/* FIXME: This should be done in bi_end_io */
mark_extents_written(BLK_LSEG2EXT(wdata->lseg),
mark_extents_written(BLK_LSEG2EXT(header->lseg),
page->index << PAGE_CACHE_SHIFT,
PAGE_CACHE_SIZE);
@ -632,7 +640,7 @@ fill_invalid_ext:
isect, page, be,
bl_end_io_write_zero, par);
if (IS_ERR(bio)) {
wdata->pnfs_error = PTR_ERR(bio);
header->pnfs_error = PTR_ERR(bio);
bio = NULL;
goto out;
}
@ -647,16 +655,16 @@ next_page:
/* Middle pages */
pg_index = wdata->args.pgbase >> PAGE_CACHE_SHIFT;
for (i = pg_index; i < wdata->npages; i++) {
for (i = pg_index; i < wdata->pages.npages; i++) {
if (!extent_length) {
/* We've used up the previous extent */
bl_put_extent(be);
bio = bl_submit_bio(WRITE, bio);
/* Get the next one */
be = bl_find_get_extent(BLK_LSEG2EXT(wdata->lseg),
be = bl_find_get_extent(BLK_LSEG2EXT(header->lseg),
isect, NULL);
if (!be || !is_writable(be, isect)) {
wdata->pnfs_error = -EINVAL;
header->pnfs_error = -EINVAL;
goto out;
}
if (be->be_state == PNFS_BLOCK_INVALID_DATA) {
@ -664,7 +672,7 @@ next_page:
be->be_inval)))
par->bse_count++;
else {
wdata->pnfs_error = -ENOMEM;
header->pnfs_error = -ENOMEM;
goto out;
}
}
@ -677,15 +685,15 @@ next_page:
if (unlikely(ret)) {
dprintk("%s bl_mark_sectors_init fail %d\n",
__func__, ret);
wdata->pnfs_error = ret;
header->pnfs_error = ret;
goto out;
}
}
bio = bl_add_page_to_bio(bio, wdata->npages - i, WRITE,
bio = bl_add_page_to_bio(bio, wdata->pages.npages - i, WRITE,
isect, pages[i], be,
bl_end_io_write, par);
if (IS_ERR(bio)) {
wdata->pnfs_error = PTR_ERR(bio);
header->pnfs_error = PTR_ERR(bio);
bio = NULL;
goto out;
}

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

@ -123,7 +123,7 @@ nfs4_blk_decode_device(struct nfs_server *server,
uint8_t *dataptr;
DECLARE_WAITQUEUE(wq, current);
int offset, len, i, rc;
struct net *net = server->nfs_client->net;
struct net *net = server->nfs_client->cl_net;
struct nfs_net *nn = net_generic(net, nfs_net_id);
struct bl_dev_msg *reply = &nn->bl_mount_reply;

286
fs/nfs/client.c
View File

@ -65,7 +65,7 @@ static DECLARE_WAIT_QUEUE_HEAD(nfs_client_active_wq);
static int nfs_get_cb_ident_idr(struct nfs_client *clp, int minorversion)
{
int ret = 0;
struct nfs_net *nn = net_generic(clp->net, nfs_net_id);
struct nfs_net *nn = net_generic(clp->cl_net, nfs_net_id);
if (clp->rpc_ops->version != 4 || minorversion != 0)
return ret;
@ -90,7 +90,9 @@ static bool nfs4_disable_idmapping = true;
* RPC cruft for NFS
*/
static const struct rpc_version *nfs_version[5] = {
#ifdef CONFIG_NFS_V2
[2] = &nfs_version2,
#endif
#ifdef CONFIG_NFS_V3
[3] = &nfs_version3,
#endif
@ -129,6 +131,7 @@ const struct rpc_program nfsacl_program = {
#endif /* CONFIG_NFS_V3_ACL */
struct nfs_client_initdata {
unsigned long init_flags;
const char *hostname;
const struct sockaddr *addr;
size_t addrlen;
@ -172,7 +175,7 @@ static struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_
clp->cl_rpcclient = ERR_PTR(-EINVAL);
clp->cl_proto = cl_init->proto;
clp->net = get_net(cl_init->net);
clp->cl_net = get_net(cl_init->net);
#ifdef CONFIG_NFS_V4
err = nfs_get_cb_ident_idr(clp, cl_init->minorversion);
@ -182,7 +185,6 @@ static struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_
spin_lock_init(&clp->cl_lock);
INIT_DELAYED_WORK(&clp->cl_renewd, nfs4_renew_state);
rpc_init_wait_queue(&clp->cl_rpcwaitq, "NFS client");
clp->cl_boot_time = CURRENT_TIME;
clp->cl_state = 1 << NFS4CLNT_LEASE_EXPIRED;
clp->cl_minorversion = cl_init->minorversion;
clp->cl_mvops = nfs_v4_minor_ops[cl_init->minorversion];
@ -207,6 +209,7 @@ static void nfs4_shutdown_session(struct nfs_client *clp)
if (nfs4_has_session(clp)) {
nfs4_deviceid_purge_client(clp);
nfs4_destroy_session(clp->cl_session);
nfs4_destroy_clientid(clp);
}
}
@ -235,6 +238,9 @@ static void nfs4_shutdown_client(struct nfs_client *clp)
nfs_idmap_delete(clp);
rpc_destroy_wait_queue(&clp->cl_rpcwaitq);
kfree(clp->cl_serverowner);
kfree(clp->cl_serverscope);
kfree(clp->cl_implid);
}
/* idr_remove_all is not needed as all id's are removed by nfs_put_client */
@ -248,7 +254,7 @@ void nfs_cleanup_cb_ident_idr(struct net *net)
/* nfs_client_lock held */
static void nfs_cb_idr_remove_locked(struct nfs_client *clp)
{
struct nfs_net *nn = net_generic(clp->net, nfs_net_id);
struct nfs_net *nn = net_generic(clp->cl_net, nfs_net_id);
if (clp->cl_cb_ident)
idr_remove(&nn->cb_ident_idr, clp->cl_cb_ident);
@ -301,10 +307,8 @@ static void nfs_free_client(struct nfs_client *clp)
if (clp->cl_machine_cred != NULL)
put_rpccred(clp->cl_machine_cred);
put_net(clp->net);
put_net(clp->cl_net);
kfree(clp->cl_hostname);
kfree(clp->server_scope);
kfree(clp->impl_id);
kfree(clp);
dprintk("<-- nfs_free_client()\n");
@ -321,7 +325,7 @@ void nfs_put_client(struct nfs_client *clp)
return;
dprintk("--> nfs_put_client({%d})\n", atomic_read(&clp->cl_count));
nn = net_generic(clp->net, nfs_net_id);
nn = net_generic(clp->cl_net, nfs_net_id);
if (atomic_dec_and_lock(&clp->cl_count, &nn->nfs_client_lock)) {
list_del(&clp->cl_share_link);
@ -456,6 +460,8 @@ static bool nfs4_cb_match_client(const struct sockaddr *addr,
clp->cl_cons_state == NFS_CS_SESSION_INITING))
return false;
smp_rmb();
/* Match the version and minorversion */
if (clp->rpc_ops->version != 4 ||
clp->cl_minorversion != minorversion)
@ -504,68 +510,27 @@ static struct nfs_client *nfs_match_client(const struct nfs_client_initdata *dat
return NULL;
}
static bool nfs_client_init_is_complete(const struct nfs_client *clp)
{
return clp->cl_cons_state != NFS_CS_INITING;
}
int nfs_wait_client_init_complete(const struct nfs_client *clp)
{
return wait_event_killable(nfs_client_active_wq,
nfs_client_init_is_complete(clp));
}
/*
* Look up a client by IP address and protocol version
* - creates a new record if one doesn't yet exist
* Found an existing client. Make sure it's ready before returning.
*/
static struct nfs_client *
nfs_get_client(const struct nfs_client_initdata *cl_init,
const struct rpc_timeout *timeparms,
const char *ip_addr,
rpc_authflavor_t authflavour,
int noresvport)
nfs_found_client(const struct nfs_client_initdata *cl_init,
struct nfs_client *clp)
{
struct nfs_client *clp, *new = NULL;
int error;
struct nfs_net *nn = net_generic(cl_init->net, nfs_net_id);
dprintk("--> nfs_get_client(%s,v%u)\n",
cl_init->hostname ?: "", cl_init->rpc_ops->version);
/* see if the client already exists */
do {
spin_lock(&nn->nfs_client_lock);
clp = nfs_match_client(cl_init);
if (clp)
goto found_client;
if (new)
goto install_client;
spin_unlock(&nn->nfs_client_lock);
new = nfs_alloc_client(cl_init);
} while (!IS_ERR(new));
dprintk("--> nfs_get_client() = %ld [failed]\n", PTR_ERR(new));
return new;
/* install a new client and return with it unready */
install_client:
clp = new;
list_add(&clp->cl_share_link, &nn->nfs_client_list);
spin_unlock(&nn->nfs_client_lock);
error = cl_init->rpc_ops->init_client(clp, timeparms, ip_addr,
authflavour, noresvport);
if (error < 0) {
nfs_put_client(clp);
return ERR_PTR(error);
}
dprintk("--> nfs_get_client() = %p [new]\n", clp);
return clp;
/* found an existing client
* - make sure it's ready before returning
*/
found_client:
spin_unlock(&nn->nfs_client_lock);
if (new)
nfs_free_client(new);
error = wait_event_killable(nfs_client_active_wq,
clp->cl_cons_state < NFS_CS_INITING);
error = nfs_wait_client_init_complete(clp);
if (error < 0) {
nfs_put_client(clp);
return ERR_PTR(-ERESTARTSYS);
@ -577,37 +542,71 @@ found_client:
return ERR_PTR(error);
}
smp_rmb();
BUG_ON(clp->cl_cons_state != NFS_CS_READY);
dprintk("--> nfs_get_client() = %p [share]\n", clp);
dprintk("<-- %s found nfs_client %p for %s\n",
__func__, clp, cl_init->hostname ?: "");
return clp;
}
/*
* Look up a client by IP address and protocol version
* - creates a new record if one doesn't yet exist
*/
static struct nfs_client *
nfs_get_client(const struct nfs_client_initdata *cl_init,
const struct rpc_timeout *timeparms,
const char *ip_addr,
rpc_authflavor_t authflavour)
{
struct nfs_client *clp, *new = NULL;
struct nfs_net *nn = net_generic(cl_init->net, nfs_net_id);
dprintk("--> nfs_get_client(%s,v%u)\n",
cl_init->hostname ?: "", cl_init->rpc_ops->version);
/* see if the client already exists */
do {
spin_lock(&nn->nfs_client_lock);
clp = nfs_match_client(cl_init);
if (clp) {
spin_unlock(&nn->nfs_client_lock);
if (new)
nfs_free_client(new);
return nfs_found_client(cl_init, clp);
}
if (new) {
list_add(&new->cl_share_link, &nn->nfs_client_list);
spin_unlock(&nn->nfs_client_lock);
new->cl_flags = cl_init->init_flags;
return cl_init->rpc_ops->init_client(new,
timeparms, ip_addr,
authflavour);
}
spin_unlock(&nn->nfs_client_lock);
new = nfs_alloc_client(cl_init);
} while (!IS_ERR(new));
dprintk("<-- nfs_get_client() Failed to find %s (%ld)\n",
cl_init->hostname ?: "", PTR_ERR(new));
return new;
}
/*
* Mark a server as ready or failed
*/
void nfs_mark_client_ready(struct nfs_client *clp, int state)
{
smp_wmb();
clp->cl_cons_state = state;
wake_up_all(&nfs_client_active_wq);
}
/*
* With sessions, the client is not marked ready until after a
* successful EXCHANGE_ID and CREATE_SESSION.
*
* Map errors cl_cons_state errors to EPROTONOSUPPORT to indicate
* other versions of NFS can be tried.
*/
int nfs4_check_client_ready(struct nfs_client *clp)
{
if (!nfs4_has_session(clp))
return 0;
if (clp->cl_cons_state < NFS_CS_READY)
return -EPROTONOSUPPORT;
return 0;
}
/*
* Initialise the timeout values for a connection
*/
@ -654,12 +653,11 @@ static void nfs_init_timeout_values(struct rpc_timeout *to, int proto,
*/
static int nfs_create_rpc_client(struct nfs_client *clp,
const struct rpc_timeout *timeparms,
rpc_authflavor_t flavor,
int discrtry, int noresvport)
rpc_authflavor_t flavor)
{
struct rpc_clnt *clnt = NULL;
struct rpc_create_args args = {
.net = clp->net,
.net = clp->cl_net,
.protocol = clp->cl_proto,
.address = (struct sockaddr *)&clp->cl_addr,
.addrsize = clp->cl_addrlen,
@ -670,9 +668,9 @@ static int nfs_create_rpc_client(struct nfs_client *clp,
.authflavor = flavor,
};
if (discrtry)
if (test_bit(NFS_CS_DISCRTRY, &clp->cl_flags))
args.flags |= RPC_CLNT_CREATE_DISCRTRY;
if (noresvport)
if (test_bit(NFS_CS_NORESVPORT, &clp->cl_flags))
args.flags |= RPC_CLNT_CREATE_NONPRIVPORT;
if (!IS_ERR(clp->cl_rpcclient))
@ -713,7 +711,7 @@ static int nfs_start_lockd(struct nfs_server *server)
.nfs_version = clp->rpc_ops->version,
.noresvport = server->flags & NFS_MOUNT_NORESVPORT ?
1 : 0,
.net = clp->net,
.net = clp->cl_net,
};
if (nlm_init.nfs_version > 3)
@ -805,36 +803,43 @@ static int nfs_init_server_rpcclient(struct nfs_server *server,
return 0;
}
/*
* Initialise an NFS2 or NFS3 client
/**
* nfs_init_client - Initialise an NFS2 or NFS3 client
*
* @clp: nfs_client to initialise
* @timeparms: timeout parameters for underlying RPC transport
* @ip_addr: IP presentation address (not used)
* @authflavor: authentication flavor for underlying RPC transport
*
* Returns pointer to an NFS client, or an ERR_PTR value.
*/
int nfs_init_client(struct nfs_client *clp, const struct rpc_timeout *timeparms,
const char *ip_addr, rpc_authflavor_t authflavour,
int noresvport)
struct nfs_client *nfs_init_client(struct nfs_client *clp,
const struct rpc_timeout *timeparms,
const char *ip_addr, rpc_authflavor_t authflavour)
{
int error;
if (clp->cl_cons_state == NFS_CS_READY) {
/* the client is already initialised */
dprintk("<-- nfs_init_client() = 0 [already %p]\n", clp);
return 0;
return clp;
}
/*
* Create a client RPC handle for doing FSSTAT with UNIX auth only
* - RFC 2623, sec 2.3.2
*/
error = nfs_create_rpc_client(clp, timeparms, RPC_AUTH_UNIX,
0, noresvport);
error = nfs_create_rpc_client(clp, timeparms, RPC_AUTH_UNIX);
if (error < 0)
goto error;
nfs_mark_client_ready(clp, NFS_CS_READY);
return 0;
return clp;
error:
nfs_mark_client_ready(clp, error);
nfs_put_client(clp);
dprintk("<-- nfs_init_client() = xerror %d\n", error);
return error;
return ERR_PTR(error);
}
/*
@ -847,7 +852,7 @@ static int nfs_init_server(struct nfs_server *server,
.hostname = data->nfs_server.hostname,
.addr = (const struct sockaddr *)&data->nfs_server.address,
.addrlen = data->nfs_server.addrlen,
.rpc_ops = &nfs_v2_clientops,
.rpc_ops = NULL,
.proto = data->nfs_server.protocol,
.net = data->net,
};
@ -857,17 +862,28 @@ static int nfs_init_server(struct nfs_server *server,
dprintk("--> nfs_init_server()\n");
#ifdef CONFIG_NFS_V3
if (data->version == 3)
cl_init.rpc_ops = &nfs_v3_clientops;
switch (data->version) {
#ifdef CONFIG_NFS_V2
case 2:
cl_init.rpc_ops = &nfs_v2_clientops;
break;
#endif
#ifdef CONFIG_NFS_V3
case 3:
cl_init.rpc_ops = &nfs_v3_clientops;
break;
#endif
default:
return -EPROTONOSUPPORT;
}
nfs_init_timeout_values(&timeparms, data->nfs_server.protocol,
data->timeo, data->retrans);
if (data->flags & NFS_MOUNT_NORESVPORT)
set_bit(NFS_CS_NORESVPORT, &cl_init.init_flags);
/* Allocate or find a client reference we can use */
clp = nfs_get_client(&cl_init, &timeparms, NULL, RPC_AUTH_UNIX,
data->flags & NFS_MOUNT_NORESVPORT);
clp = nfs_get_client(&cl_init, &timeparms, NULL, RPC_AUTH_UNIX);
if (IS_ERR(clp)) {
dprintk("<-- nfs_init_server() = error %ld\n", PTR_ERR(clp));
return PTR_ERR(clp);
@ -880,7 +896,7 @@ static int nfs_init_server(struct nfs_server *server,
server->options = data->options;
server->caps |= NFS_CAP_HARDLINKS|NFS_CAP_SYMLINKS|NFS_CAP_FILEID|
NFS_CAP_MODE|NFS_CAP_NLINK|NFS_CAP_OWNER|NFS_CAP_OWNER_GROUP|
NFS_CAP_ATIME|NFS_CAP_CTIME|NFS_CAP_MTIME;
NFS_CAP_ATIME|NFS_CAP_CTIME|NFS_CAP_MTIME|NFS_CAP_CHANGE_ATTR;
if (data->rsize)
server->rsize = nfs_block_size(data->rsize, NULL);
@ -1048,7 +1064,7 @@ static void nfs_server_copy_userdata(struct nfs_server *target, struct nfs_serve
static void nfs_server_insert_lists(struct nfs_server *server)
{
struct nfs_client *clp = server->nfs_client;
struct nfs_net *nn = net_generic(clp->net, nfs_net_id);
struct nfs_net *nn = net_generic(clp->cl_net, nfs_net_id);
spin_lock(&nn->nfs_client_lock);
list_add_tail_rcu(&server->client_link, &clp->cl_superblocks);
@ -1065,7 +1081,7 @@ static void nfs_server_remove_lists(struct nfs_server *server)
if (clp == NULL)
return;
nn = net_generic(clp->net, nfs_net_id);
nn = net_generic(clp->cl_net, nfs_net_id);
spin_lock(&nn->nfs_client_lock);
list_del_rcu(&server->client_link);
if (list_empty(&clp->cl_superblocks))
@ -1333,21 +1349,27 @@ static int nfs4_init_client_minor_version(struct nfs_client *clp)
* so that the client back channel can find the
* nfs_client struct
*/
clp->cl_cons_state = NFS_CS_SESSION_INITING;
nfs_mark_client_ready(clp, NFS_CS_SESSION_INITING);
}
#endif /* CONFIG_NFS_V4_1 */
return nfs4_init_callback(clp);
}
/*
* Initialise an NFS4 client record
/**
* nfs4_init_client - Initialise an NFS4 client record
*
* @clp: nfs_client to initialise
* @timeparms: timeout parameters for underlying RPC transport
* @ip_addr: callback IP address in presentation format
* @authflavor: authentication flavor for underlying RPC transport
*
* Returns pointer to an NFS client, or an ERR_PTR value.
*/
int nfs4_init_client(struct nfs_client *clp,
const struct rpc_timeout *timeparms,
const char *ip_addr,
rpc_authflavor_t authflavour,
int noresvport)
struct nfs_client *nfs4_init_client(struct nfs_client *clp,
const struct rpc_timeout *timeparms,
const char *ip_addr,
rpc_authflavor_t authflavour)
{
char buf[INET6_ADDRSTRLEN + 1];
int error;
@ -1355,14 +1377,14 @@ int nfs4_init_client(struct nfs_client *clp,
if (clp->cl_cons_state == NFS_CS_READY) {
/* the client is initialised already */
dprintk("<-- nfs4_init_client() = 0 [already %p]\n", clp);
return 0;
return clp;
}
/* Check NFS protocol revision and initialize RPC op vector */
clp->rpc_ops = &nfs_v4_clientops;
error = nfs_create_rpc_client(clp, timeparms, authflavour,
1, noresvport);
__set_bit(NFS_CS_DISCRTRY, &clp->cl_flags);
error = nfs_create_rpc_client(clp, timeparms, authflavour);
if (error < 0)
goto error;
@ -1395,12 +1417,13 @@ int nfs4_init_client(struct nfs_client *clp,
if (!nfs4_has_session(clp))
nfs_mark_client_ready(clp, NFS_CS_READY);
return 0;
return clp;
error:
nfs_mark_client_ready(clp, error);
nfs_put_client(clp);
dprintk("<-- nfs4_init_client() = xerror %d\n", error);
return error;
return ERR_PTR(error);
}
/*
@ -1429,9 +1452,11 @@ static int nfs4_set_client(struct nfs_server *server,
dprintk("--> nfs4_set_client()\n");
if (server->flags & NFS_MOUNT_NORESVPORT)
set_bit(NFS_CS_NORESVPORT, &cl_init.init_flags);
/* Allocate or find a client reference we can use */
clp = nfs_get_client(&cl_init, timeparms, ip_addr, authflavour,
server->flags & NFS_MOUNT_NORESVPORT);
clp = nfs_get_client(&cl_init, timeparms, ip_addr, authflavour);
if (IS_ERR(clp)) {
error = PTR_ERR(clp);
goto error;
@ -1465,8 +1490,8 @@ error:
* the MDS.
*/
struct nfs_client *nfs4_set_ds_client(struct nfs_client* mds_clp,
const struct sockaddr *ds_addr,
int ds_addrlen, int ds_proto)
const struct sockaddr *ds_addr, int ds_addrlen,
int ds_proto, unsigned int ds_timeo, unsigned int ds_retrans)
{
struct nfs_client_initdata cl_init = {
.addr = ds_addr,
@ -1474,14 +1499,9 @@ struct nfs_client *nfs4_set_ds_client(struct nfs_client* mds_clp,
.rpc_ops = &nfs_v4_clientops,
.proto = ds_proto,
.minorversion = mds_clp->cl_minorversion,
.net = mds_clp->net,
};
struct rpc_timeout ds_timeout = {
.to_initval = 15 * HZ,
.to_maxval = 15 * HZ,
.to_retries = 1,
.to_exponential = 1,
.net = mds_clp->cl_net,
};
struct rpc_timeout ds_timeout;
struct nfs_client *clp;
/*
@ -1489,8 +1509,9 @@ struct nfs_client *nfs4_set_ds_client(struct nfs_client* mds_clp,
* cl_ipaddr so as to use the same EXCHANGE_ID co_ownerid as the MDS
* (section 13.1 RFC 5661).
*/
nfs_init_timeout_values(&ds_timeout, ds_proto, ds_timeo, ds_retrans);
clp = nfs_get_client(&cl_init, &ds_timeout, mds_clp->cl_ipaddr,
mds_clp->cl_rpcclient->cl_auth->au_flavor, 0);
mds_clp->cl_rpcclient->cl_auth->au_flavor);
dprintk("<-- %s %p\n", __func__, clp);
return clp;
@ -1701,7 +1722,7 @@ struct nfs_server *nfs4_create_referral_server(struct nfs_clone_mount *data,
rpc_protocol(parent_server->client),
parent_server->client->cl_timeout,
parent_client->cl_mvops->minor_version,
parent_client->net);
parent_client->cl_net);
if (error < 0)
goto error;
@ -1805,6 +1826,7 @@ void nfs_clients_init(struct net *net)
idr_init(&nn->cb_ident_idr);
#endif
spin_lock_init(&nn->nfs_client_lock);
nn->boot_time = CURRENT_TIME;
}
#ifdef CONFIG_PROC_FS

16
fs/nfs/delegation.c
View File

@ -316,6 +316,10 @@ out:
* nfs_client_return_marked_delegations - return previously marked delegations
* @clp: nfs_client to process
*
* Note that this function is designed to be called by the state
* manager thread. For this reason, it cannot flush the dirty data,
* since that could deadlock in case of a state recovery error.
*
* Returns zero on success, or a negative errno value.
*/
int nfs_client_return_marked_delegations(struct nfs_client *clp)
@ -340,11 +344,9 @@ restart:
server);
rcu_read_unlock();
if (delegation != NULL) {
filemap_flush(inode->i_mapping);
if (delegation != NULL)
err = __nfs_inode_return_delegation(inode,
delegation, 0);
}
iput(inode);
if (!err)
goto restart;
@ -380,6 +382,10 @@ void nfs_inode_return_delegation_noreclaim(struct inode *inode)
* nfs_inode_return_delegation - synchronously return a delegation
* @inode: inode to process
*
* This routine will always flush any dirty data to disk on the
* assumption that if we need to return the delegation, then
* we should stop caching.
*
* Returns zero on success, or a negative errno value.
*/
int nfs_inode_return_delegation(struct inode *inode)
@ -389,10 +395,10 @@ int nfs_inode_return_delegation(struct inode *inode)
struct nfs_delegation *delegation;
int err = 0;
nfs_wb_all(inode);
if (rcu_access_pointer(nfsi->delegation) != NULL) {
delegation = nfs_detach_delegation(nfsi, server);
if (delegation != NULL) {
nfs_wb_all(inode);
err = __nfs_inode_return_delegation(inode, delegation, 1);
}
}
@ -538,6 +544,8 @@ int nfs_async_inode_return_delegation(struct inode *inode,
struct nfs_client *clp = server->nfs_client;
struct nfs_delegation *delegation;
filemap_flush(inode->i_mapping);
rcu_read_lock();
delegation = rcu_dereference(NFS_I(inode)->delegation);

1
fs/nfs/delegation.h
View File

@ -66,6 +66,7 @@ static inline int nfs_have_delegation(struct inode *inode, fmode_t flags)
static inline int nfs_inode_return_delegation(struct inode *inode)
{
nfs_wb_all(inode);
return 0;
}
#endif

39
fs/nfs/dir.c
View File

@ -474,6 +474,29 @@ different:
return 0;
}
static
bool nfs_use_readdirplus(struct inode *dir, struct file *filp)
{
if (!nfs_server_capable(dir, NFS_CAP_READDIRPLUS))
return false;
if (test_and_clear_bit(NFS_INO_ADVISE_RDPLUS, &NFS_I(dir)->flags))
return true;
if (filp->f_pos == 0)
return true;
return false;
}
/*
* This function is called by the lookup code to request the use of
* readdirplus to accelerate any future lookups in the same
* directory.
*/
static
void nfs_advise_use_readdirplus(struct inode *dir)
{
set_bit(NFS_INO_ADVISE_RDPLUS, &NFS_I(dir)->flags);
}
static
void nfs_prime_dcache(struct dentry *parent, struct nfs_entry *entry)
{
@ -871,7 +894,7 @@ static int nfs_readdir(struct file *filp, void *dirent, filldir_t filldir)
desc->file = filp;
desc->dir_cookie = &dir_ctx->dir_cookie;
desc->decode = NFS_PROTO(inode)->decode_dirent;
desc->plus = NFS_USE_READDIRPLUS(inode);
desc->plus = nfs_use_readdirplus(inode, filp) ? 1 : 0;
nfs_block_sillyrename(dentry);
res = nfs_revalidate_mapping(inode, filp->f_mapping);
@ -1111,7 +1134,7 @@ static int nfs_lookup_revalidate(struct dentry *dentry, struct nameidata *nd)
if (!inode) {
if (nfs_neg_need_reval(dir, dentry, nd))
goto out_bad;
goto out_valid;
goto out_valid_noent;
}
if (is_bad_inode(inode)) {
@ -1140,7 +1163,7 @@ static int nfs_lookup_revalidate(struct dentry *dentry, struct nameidata *nd)
if (fhandle == NULL || fattr == NULL)
goto out_error;
error = NFS_PROTO(dir)->lookup(NFS_SERVER(dir)->client, dir, &dentry->d_name, fhandle, fattr);
error = NFS_PROTO(dir)->lookup(dir, &dentry->d_name, fhandle, fattr);
if (error)
goto out_bad;
if (nfs_compare_fh(NFS_FH(inode), fhandle))
@ -1153,6 +1176,9 @@ static int nfs_lookup_revalidate(struct dentry *dentry, struct nameidata *nd)
out_set_verifier:
nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
out_valid:
/* Success: notify readdir to use READDIRPLUS */
nfs_advise_use_readdirplus(dir);
out_valid_noent:
dput(parent);
dfprintk(LOOKUPCACHE, "NFS: %s(%s/%s) is valid\n",
__func__, dentry->d_parent->d_name.name,
@ -1296,7 +1322,7 @@ static struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, stru
parent = dentry->d_parent;
/* Protect against concurrent sillydeletes */
nfs_block_sillyrename(parent);
error = NFS_PROTO(dir)->lookup(NFS_SERVER(dir)->client, dir, &dentry->d_name, fhandle, fattr);
error = NFS_PROTO(dir)->lookup(dir, &dentry->d_name, fhandle, fattr);
if (error == -ENOENT)
goto no_entry;
if (error < 0) {
@ -1308,6 +1334,9 @@ static struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, stru
if (IS_ERR(res))
goto out_unblock_sillyrename;
/* Success: notify readdir to use READDIRPLUS */
nfs_advise_use_readdirplus(dir);
no_entry:
res = d_materialise_unique(dentry, inode);
if (res != NULL) {
@ -1643,7 +1672,7 @@ int nfs_instantiate(struct dentry *dentry, struct nfs_fh *fhandle,
if (dentry->d_inode)
goto out;
if (fhandle->size == 0) {
error = NFS_PROTO(dir)->lookup(NFS_SERVER(dir)->client, dir, &dentry->d_name, fhandle, fattr);
error = NFS_PROTO(dir)->lookup(dir, &dentry->d_name, fhandle, fattr);
if (error)
goto out_error;
}

740
fs/nfs/direct.c
View File

File diff suppressed because it is too large Load Diff

8
fs/nfs/file.c
View File

@ -174,6 +174,13 @@ nfs_file_flush(struct file *file, fl_owner_t id)
if ((file->f_mode & FMODE_WRITE) == 0)
return 0;
/*
* If we're holding a write delegation, then just start the i/o
* but don't wait for completion (or send a commit).
*/
if (nfs_have_delegation(inode, FMODE_WRITE))
return filemap_fdatawrite(file->f_mapping);
/* Flush writes to the server and return any errors */
return vfs_fsync(file, 0);
}
@ -417,6 +424,7 @@ static int nfs_write_end(struct file *file, struct address_space *mapping,
if (status < 0)
return status;
NFS_I(mapping->host)->write_io += copied;
return copied;
}

15
fs/nfs/fscache.c
View File

@ -64,23 +64,12 @@ void nfs_fscache_release_client_cookie(struct nfs_client *clp)
* either by the 'fsc=xxx' option to mount, or by inheriting it from the parent
* superblock across an automount point of some nature.
*/
void nfs_fscache_get_super_cookie(struct super_block *sb, const char *uniq,
struct nfs_clone_mount *mntdata)
void nfs_fscache_get_super_cookie(struct super_block *sb, const char *uniq, int ulen)
{
struct nfs_fscache_key *key, *xkey;
struct nfs_server *nfss = NFS_SB(sb);
struct rb_node **p, *parent;
int diff, ulen;
if (uniq) {
ulen = strlen(uniq);
} else if (mntdata) {
struct nfs_server *mnt_s = NFS_SB(mntdata->sb);
if (mnt_s->fscache_key) {
uniq = mnt_s->fscache_key->key.uniquifier;
ulen = mnt_s->fscache_key->key.uniq_len;
}
}
int diff;
if (!uniq) {
uniq = "";

10
fs/nfs/fscache.h
View File

@ -73,9 +73,7 @@ extern void nfs_fscache_unregister(void);
extern void nfs_fscache_get_client_cookie(struct nfs_client *);
extern void nfs_fscache_release_client_cookie(struct nfs_client *);
extern void nfs_fscache_get_super_cookie(struct super_block *,
const char *,
struct nfs_clone_mount *);
extern void nfs_fscache_get_super_cookie(struct super_block *, const char *, int);
extern void nfs_fscache_release_super_cookie(struct super_block *);
extern void nfs_fscache_init_inode_cookie(struct inode *);
@ -172,12 +170,6 @@ static inline void nfs_fscache_unregister(void) {}
static inline void nfs_fscache_get_client_cookie(struct nfs_client *clp) {}
static inline void nfs_fscache_release_client_cookie(struct nfs_client *clp) {}
static inline void nfs_fscache_get_super_cookie(
struct super_block *sb,
const char *uniq,
struct nfs_clone_mount *mntdata)
{
}
static inline void nfs_fscache_release_super_cookie(struct super_block *sb) {}
static inline void nfs_fscache_init_inode_cookie(struct inode *inode) {}

85
fs/nfs/getroot.c
View File

@ -150,7 +150,7 @@ int nfs4_get_rootfh(struct nfs_server *server, struct nfs_fh *mntfh)
goto out;
/* Start by getting the root filehandle from the server */
ret = server->nfs_client->rpc_ops->getroot(server, mntfh, &fsinfo);
ret = nfs4_proc_get_rootfh(server, mntfh, &fsinfo);
if (ret < 0) {
dprintk("nfs4_get_rootfh: getroot error = %d\n", -ret);
goto out;
@ -178,87 +178,4 @@ out:
return ret;
}
/*
* get an NFS4 root dentry from the root filehandle
*/
struct dentry *nfs4_get_root(struct super_block *sb, struct nfs_fh *mntfh,
const char *devname)
{
struct nfs_server *server = NFS_SB(sb);
struct nfs_fattr *fattr = NULL;
struct dentry *ret;
struct inode *inode;
void *name = kstrdup(devname, GFP_KERNEL);
int error;
dprintk("--> nfs4_get_root()\n");
if (!name)
return ERR_PTR(-ENOMEM);
/* get the info about the server and filesystem */
error = nfs4_server_capabilities(server, mntfh);
if (error < 0) {
dprintk("nfs_get_root: getcaps error = %d\n",
-error);
kfree(name);
return ERR_PTR(error);
}
fattr = nfs_alloc_fattr();
if (fattr == NULL) {
kfree(name);
return ERR_PTR(-ENOMEM);
}
/* get the actual root for this mount */
error = server->nfs_client->rpc_ops->getattr(server, mntfh, fattr);
if (error < 0) {
dprintk("nfs_get_root: getattr error = %d\n", -error);
ret = ERR_PTR(error);
goto out;
}
if (fattr->valid & NFS_ATTR_FATTR_FSID &&
!nfs_fsid_equal(&server->fsid, &fattr->fsid))
memcpy(&server->fsid, &fattr->fsid, sizeof(server->fsid));
inode = nfs_fhget(sb, mntfh, fattr);
if (IS_ERR(inode)) {
dprintk("nfs_get_root: get root inode failed\n");
ret = ERR_CAST(inode);
goto out;
}
error = nfs_superblock_set_dummy_root(sb, inode);
if (error != 0) {
ret = ERR_PTR(error);
goto out;
}
/* root dentries normally start off anonymous and get spliced in later
* if the dentry tree reaches them; however if the dentry already
* exists, we'll pick it up at this point and use it as the root
*/
ret = d_obtain_alias(inode);
if (IS_ERR(ret)) {
dprintk("nfs_get_root: get root dentry failed\n");
goto out;
}
security_d_instantiate(ret, inode);
spin_lock(&ret->d_lock);
if (IS_ROOT(ret) && !(ret->d_flags & DCACHE_NFSFS_RENAMED)) {
ret->d_fsdata = name;
name = NULL;
}
spin_unlock(&ret->d_lock);
out:
if (name)
kfree(name);
nfs_free_fattr(fattr);
dprintk("<-- nfs4_get_root()\n");
return ret;
}
#endif /* CONFIG_NFS_V4 */

30
fs/nfs/idmap.c
View File

@ -415,7 +415,7 @@ static int __nfs_idmap_register(struct dentry *dir,
static void nfs_idmap_unregister(struct nfs_client *clp,
struct rpc_pipe *pipe)
{
struct net *net = clp->net;
struct net *net = clp->cl_net;
struct super_block *pipefs_sb;
pipefs_sb = rpc_get_sb_net(net);
@ -429,7 +429,7 @@ static int nfs_idmap_register(struct nfs_client *clp,
struct idmap *idmap,
struct rpc_pipe *pipe)
{
struct net *net = clp->net;
struct net *net = clp->cl_net;
struct super_block *pipefs_sb;
int err = 0;
@ -530,9 +530,25 @@ static struct nfs_client *nfs_get_client_for_event(struct net *net, int event)
struct nfs_net *nn = net_generic(net, nfs_net_id);
struct dentry *cl_dentry;
struct nfs_client *clp;
int err;
restart:
spin_lock(&nn->nfs_client_lock);
list_for_each_entry(clp, &nn->nfs_client_list, cl_share_link) {
/* Wait for initialisation to finish */
if (clp->cl_cons_state == NFS_CS_INITING) {
atomic_inc(&clp->cl_count);
spin_unlock(&nn->nfs_client_lock);
err = nfs_wait_client_init_complete(clp);
nfs_put_client(clp);
if (err)
return NULL;
goto restart;
}
/* Skip nfs_clients that failed to initialise */
if (clp->cl_cons_state < 0)
continue;
smp_rmb();
if (clp->rpc_ops != &nfs_v4_clientops)
continue;
cl_dentry = clp->cl_idmap->idmap_pipe->dentry;
@ -640,20 +656,16 @@ static int nfs_idmap_legacy_upcall(struct key_construction *cons,
struct idmap_msg *im;
struct idmap *idmap = (struct idmap *)aux;
struct key *key = cons->key;
int ret;
int ret = -ENOMEM;
/* msg and im are freed in idmap_pipe_destroy_msg */
msg = kmalloc(sizeof(*msg), GFP_KERNEL);
if (IS_ERR(msg)) {
ret = PTR_ERR(msg);
if (!msg)
goto out0;
}
im = kmalloc(sizeof(*im), GFP_KERNEL);
if (IS_ERR(im)) {
ret = PTR_ERR(im);
if (!im)
goto out1;
}
ret = nfs_idmap_prepare_message(key->description, im, msg);
if (ret < 0)

118
fs/nfs/inode.c
View File

@ -285,9 +285,7 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr)
inode->i_mode = fattr->mode;
if ((fattr->valid & NFS_ATTR_FATTR_MODE) == 0
&& nfs_server_capable(inode, NFS_CAP_MODE))
nfsi->cache_validity |= NFS_INO_INVALID_ATTR
| NFS_INO_INVALID_ACCESS
| NFS_INO_INVALID_ACL;
nfsi->cache_validity |= NFS_INO_INVALID_ATTR;
/* Why so? Because we want revalidate for devices/FIFOs, and
* that's precisely what we have in nfs_file_inode_operations.
*/
@ -300,8 +298,6 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr)
inode->i_op = NFS_SB(sb)->nfs_client->rpc_ops->dir_inode_ops;
inode->i_fop = &nfs_dir_operations;
inode->i_data.a_ops = &nfs_dir_aops;
if (nfs_server_capable(inode, NFS_CAP_READDIRPLUS))
set_bit(NFS_INO_ADVISE_RDPLUS, &NFS_I(inode)->flags);
/* Deal with crossing mountpoints */
if (fattr->valid & NFS_ATTR_FATTR_MOUNTPOINT ||
fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL) {
@ -327,6 +323,8 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr)
inode->i_gid = -2;
inode->i_blocks = 0;
memset(nfsi->cookieverf, 0, sizeof(nfsi->cookieverf));
nfsi->write_io = 0;
nfsi->read_io = 0;
nfsi->read_cache_jiffies = fattr->time_start;
nfsi->attr_gencount = fattr->gencount;
@ -337,24 +335,19 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr)
if (fattr->valid & NFS_ATTR_FATTR_MTIME)
inode->i_mtime = fattr->mtime;
else if (nfs_server_capable(inode, NFS_CAP_MTIME))
nfsi->cache_validity |= NFS_INO_INVALID_ATTR
| NFS_INO_INVALID_DATA;
nfsi->cache_validity |= NFS_INO_INVALID_ATTR;
if (fattr->valid & NFS_ATTR_FATTR_CTIME)
inode->i_ctime = fattr->ctime;
else if (nfs_server_capable(inode, NFS_CAP_CTIME))
nfsi->cache_validity |= NFS_INO_INVALID_ATTR
| NFS_INO_INVALID_ACCESS
| NFS_INO_INVALID_ACL;
nfsi->cache_validity |= NFS_INO_INVALID_ATTR;
if (fattr->valid & NFS_ATTR_FATTR_CHANGE)
inode->i_version = fattr->change_attr;
else if (nfs_server_capable(inode, NFS_CAP_CHANGE_ATTR))
nfsi->cache_validity |= NFS_INO_INVALID_ATTR
| NFS_INO_INVALID_DATA;
nfsi->cache_validity |= NFS_INO_INVALID_ATTR;
if (fattr->valid & NFS_ATTR_FATTR_SIZE)
inode->i_size = nfs_size_to_loff_t(fattr->size);
else
nfsi->cache_validity |= NFS_INO_INVALID_ATTR
| NFS_INO_INVALID_DATA
| NFS_INO_REVAL_PAGECACHE;
if (fattr->valid & NFS_ATTR_FATTR_NLINK)
set_nlink(inode, fattr->nlink);
@ -363,15 +356,11 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr)
if (fattr->valid & NFS_ATTR_FATTR_OWNER)
inode->i_uid = fattr->uid;
else if (nfs_server_capable(inode, NFS_CAP_OWNER))
nfsi->cache_validity |= NFS_INO_INVALID_ATTR
| NFS_INO_INVALID_ACCESS
| NFS_INO_INVALID_ACL;
nfsi->cache_validity |= NFS_INO_INVALID_ATTR;
if (fattr->valid & NFS_ATTR_FATTR_GROUP)
inode->i_gid = fattr->gid;
else if (nfs_server_capable(inode, NFS_CAP_OWNER_GROUP))
nfsi->cache_validity |= NFS_INO_INVALID_ATTR
| NFS_INO_INVALID_ACCESS
| NFS_INO_INVALID_ACL;
nfsi->cache_validity |= NFS_INO_INVALID_ATTR;
if (fattr->valid & NFS_ATTR_FATTR_BLOCKS_USED)
inode->i_blocks = fattr->du.nfs2.blocks;
if (fattr->valid & NFS_ATTR_FATTR_SPACE_USED) {
@ -654,6 +643,7 @@ struct nfs_open_context *alloc_nfs_open_context(struct dentry *dentry, fmode_t f
nfs_init_lock_context(&ctx->lock_context);
ctx->lock_context.open_context = ctx;
INIT_LIST_HEAD(&ctx->list);
ctx->mdsthreshold = NULL;
return ctx;
}
@ -682,6 +672,7 @@ static void __put_nfs_open_context(struct nfs_open_context *ctx, int is_sync)
put_rpccred(ctx->cred);
dput(ctx->dentry);
nfs_sb_deactive(sb);
kfree(ctx->mdsthreshold);
kfree(ctx);
}
@ -870,6 +861,15 @@ static int nfs_invalidate_mapping(struct inode *inode, struct address_space *map
return 0;
}
static bool nfs_mapping_need_revalidate_inode(struct inode *inode)
{
if (nfs_have_delegated_attributes(inode))
return false;
return (NFS_I(inode)->cache_validity & NFS_INO_REVAL_PAGECACHE)
|| nfs_attribute_timeout(inode)
|| NFS_STALE(inode);
}
/**
* nfs_revalidate_mapping - Revalidate the pagecache
* @inode - pointer to host inode
@ -880,9 +880,7 @@ int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping)
struct nfs_inode *nfsi = NFS_I(inode);
int ret = 0;
if ((nfsi->cache_validity & NFS_INO_REVAL_PAGECACHE)
|| nfs_attribute_cache_expired(inode)
|| NFS_STALE(inode)) {
if (nfs_mapping_need_revalidate_inode(inode)) {
ret = __nfs_revalidate_inode(NFS_SERVER(inode), inode);
if (ret < 0)
goto out;
@ -948,6 +946,8 @@ static int nfs_check_inode_attributes(struct inode *inode, struct nfs_fattr *fat
unsigned long invalid = 0;
if (nfs_have_delegated_attributes(inode))
return 0;
/* Has the inode gone and changed behind our back? */
if ((fattr->valid & NFS_ATTR_FATTR_FILEID) && nfsi->fileid != fattr->fileid)
return -EIO;
@ -960,7 +960,7 @@ static int nfs_check_inode_attributes(struct inode *inode, struct nfs_fattr *fat
/* Verify a few of the more important attributes */
if ((fattr->valid & NFS_ATTR_FATTR_MTIME) && !timespec_equal(&inode->i_mtime, &fattr->mtime))
invalid |= NFS_INO_INVALID_ATTR|NFS_INO_REVAL_PAGECACHE;
invalid |= NFS_INO_INVALID_ATTR;
if (fattr->valid & NFS_ATTR_FATTR_SIZE) {
cur_size = i_size_read(inode);
@ -1279,14 +1279,26 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
nfs_display_fhandle_hash(NFS_FH(inode)),
atomic_read(&inode->i_count), fattr->valid);
if ((fattr->valid & NFS_ATTR_FATTR_FILEID) && nfsi->fileid != fattr->fileid)
goto out_fileid;
if ((fattr->valid & NFS_ATTR_FATTR_FILEID) && nfsi->fileid != fattr->fileid) {
printk(KERN_ERR "NFS: server %s error: fileid changed\n"
"fsid %s: expected fileid 0x%Lx, got 0x%Lx\n",
NFS_SERVER(inode)->nfs_client->cl_hostname,
inode->i_sb->s_id, (long long)nfsi->fileid,
(long long)fattr->fileid);
goto out_err;
}
/*
* Make sure the inode's type hasn't changed.
*/
if ((fattr->valid & NFS_ATTR_FATTR_TYPE) && (inode->i_mode & S_IFMT) != (fattr->mode & S_IFMT))
goto out_changed;
if ((fattr->valid & NFS_ATTR_FATTR_TYPE) && (inode->i_mode & S_IFMT) != (fattr->mode & S_IFMT)) {
/*
* Big trouble! The inode has become a different object.
*/
printk(KERN_DEBUG "NFS: %s: inode %ld mode changed, %07o to %07o\n",
__func__, inode->i_ino, inode->i_mode, fattr->mode);
goto out_err;
}
server = NFS_SERVER(inode);
/* Update the fsid? */
@ -1314,7 +1326,11 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
if (inode->i_version != fattr->change_attr) {
dprintk("NFS: change_attr change on server for file %s/%ld\n",
inode->i_sb->s_id, inode->i_ino);
invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL;
invalid |= NFS_INO_INVALID_ATTR
| NFS_INO_INVALID_DATA
| NFS_INO_INVALID_ACCESS
| NFS_INO_INVALID_ACL
| NFS_INO_REVAL_PAGECACHE;
if (S_ISDIR(inode->i_mode))
nfs_force_lookup_revalidate(inode);
inode->i_version = fattr->change_attr;
@ -1323,38 +1339,15 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
invalid |= save_cache_validity;
if (fattr->valid & NFS_ATTR_FATTR_MTIME) {
/* NFSv2/v3: Check if the mtime agrees */
if (!timespec_equal(&inode->i_mtime, &fattr->mtime)) {
dprintk("NFS: mtime change on server for file %s/%ld\n",
inode->i_sb->s_id, inode->i_ino);
invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA;
if (S_ISDIR(inode->i_mode))
nfs_force_lookup_revalidate(inode);
memcpy(&inode->i_mtime, &fattr->mtime, sizeof(inode->i_mtime));
}
memcpy(&inode->i_mtime, &fattr->mtime, sizeof(inode->i_mtime));
} else if (server->caps & NFS_CAP_MTIME)
invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR
| NFS_INO_INVALID_DATA
| NFS_INO_REVAL_PAGECACHE
| NFS_INO_REVAL_FORCED);
if (fattr->valid & NFS_ATTR_FATTR_CTIME) {
/* If ctime has changed we should definitely clear access+acl caches */
if (!timespec_equal(&inode->i_ctime, &fattr->ctime)) {
invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL;
/* and probably clear data for a directory too as utimes can cause
* havoc with our cache.
*/
if (S_ISDIR(inode->i_mode)) {
invalid |= NFS_INO_INVALID_DATA;
nfs_force_lookup_revalidate(inode);
}
memcpy(&inode->i_ctime, &fattr->ctime, sizeof(inode->i_ctime));
}
memcpy(&inode->i_ctime, &fattr->ctime, sizeof(inode->i_ctime));
} else if (server->caps & NFS_CAP_CTIME)
invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR
| NFS_INO_INVALID_ACCESS
| NFS_INO_INVALID_ACL
| NFS_INO_REVAL_FORCED);
/* Check if our cached file size is stale */
@ -1466,12 +1459,6 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
nfsi->cache_validity |= invalid;
return 0;
out_changed:
/*
* Big trouble! The inode has become a different object.
*/
printk(KERN_DEBUG "NFS: %s: inode %ld mode changed, %07o to %07o\n",
__func__, inode->i_ino, inode->i_mode, fattr->mode);
out_err:
/*
* No need to worry about unhashing the dentry, as the
@ -1480,13 +1467,6 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
*/
nfs_invalidate_inode(inode);
return -ESTALE;
out_fileid:
printk(KERN_ERR "NFS: server %s error: fileid changed\n"
"fsid %s: expected fileid 0x%Lx, got 0x%Lx\n",
NFS_SERVER(inode)->nfs_client->cl_hostname, inode->i_sb->s_id,
(long long)nfsi->fileid, (long long)fattr->fileid);
goto out_err;
}
@ -1547,7 +1527,7 @@ static inline void nfs4_init_once(struct nfs_inode *nfsi)
nfsi->delegation_state = 0;
init_rwsem(&nfsi->rwsem);
nfsi->layout = NULL;
atomic_set(&nfsi->commits_outstanding, 0);
atomic_set(&nfsi->commit_info.rpcs_out, 0);
#endif
}
@ -1559,9 +1539,9 @@ static void init_once(void *foo)
INIT_LIST_HEAD(&nfsi->open_files);
INIT_LIST_HEAD(&nfsi->access_cache_entry_lru);
INIT_LIST_HEAD(&nfsi->access_cache_inode_lru);
INIT_LIST_HEAD(&nfsi->commit_list);
INIT_LIST_HEAD(&nfsi->commit_info.list);
nfsi->npages = 0;
nfsi->ncommit = 0;
nfsi->commit_info.ncommit = 0;
atomic_set(&nfsi->silly_count, 1);
INIT_HLIST_HEAD(&nfsi->silly_list);
init_waitqueue_head(&nfsi->waitqueue);

135
fs/nfs/internal.h
View File

@ -103,6 +103,7 @@ struct nfs_parsed_mount_data {
unsigned int version;
unsigned int minorversion;
char *fscache_uniq;
bool need_mount;
struct {
struct sockaddr_storage address;
@ -167,11 +168,13 @@ extern struct nfs_server *nfs_clone_server(struct nfs_server *,
struct nfs_fh *,
struct nfs_fattr *,
rpc_authflavor_t);
extern int nfs_wait_client_init_complete(const struct nfs_client *clp);
extern void nfs_mark_client_ready(struct nfs_client *clp, int state);
extern int nfs4_check_client_ready(struct nfs_client *clp);
extern struct nfs_client *nfs4_set_ds_client(struct nfs_client* mds_clp,
const struct sockaddr *ds_addr,
int ds_addrlen, int ds_proto);
int ds_addrlen, int ds_proto,
unsigned int ds_timeo,
unsigned int ds_retrans);
#ifdef CONFIG_PROC_FS
extern int __init nfs_fs_proc_init(void);
extern void nfs_fs_proc_exit(void);
@ -185,21 +188,11 @@ static inline void nfs_fs_proc_exit(void)
}
#endif
/* nfs4namespace.c */
#ifdef CONFIG_NFS_V4
extern struct vfsmount *nfs_do_refmount(struct rpc_clnt *client, struct dentry *dentry);
#else
static inline
struct vfsmount *nfs_do_refmount(struct rpc_clnt *client, struct dentry *dentry)
{
return ERR_PTR(-ENOENT);
}
#endif
/* callback_xdr.c */
extern struct svc_version nfs4_callback_version1;
extern struct svc_version nfs4_callback_version4;
struct nfs_pageio_descriptor;
/* pagelist.c */
extern int __init nfs_init_nfspagecache(void);
extern void nfs_destroy_nfspagecache(void);
@ -210,9 +203,13 @@ extern void nfs_destroy_writepagecache(void);
extern int __init nfs_init_directcache(void);
extern void nfs_destroy_directcache(void);
extern bool nfs_pgarray_set(struct nfs_page_array *p, unsigned int pagecount);
extern void nfs_pgheader_init(struct nfs_pageio_descriptor *desc,
struct nfs_pgio_header *hdr,
void (*release)(struct nfs_pgio_header *hdr));
void nfs_set_pgio_error(struct nfs_pgio_header *hdr, int error, loff_t pos);
/* nfs2xdr.c */
extern int nfs_stat_to_errno(enum nfs_stat);
extern struct rpc_procinfo nfs_procedures[];
extern int nfs2_decode_dirent(struct xdr_stream *,
struct nfs_entry *, int);
@ -237,14 +234,13 @@ extern const u32 nfs41_maxwrite_overhead;
extern struct rpc_procinfo nfs4_procedures[];
#endif
extern int nfs4_init_ds_session(struct nfs_client *clp);
extern int nfs4_init_ds_session(struct nfs_client *, unsigned long);
/* proc.c */
void nfs_close_context(struct nfs_open_context *ctx, int is_sync);
extern int nfs_init_client(struct nfs_client *clp,
extern struct nfs_client *nfs_init_client(struct nfs_client *clp,
const struct rpc_timeout *timeparms,
const char *ip_addr, rpc_authflavor_t authflavour,
int noresvport);
const char *ip_addr, rpc_authflavor_t authflavour);
/* dir.c */
extern int nfs_access_cache_shrinker(struct shrinker *shrink,
@ -280,9 +276,10 @@ extern void nfs_sb_deactive(struct super_block *sb);
extern char *nfs_path(char **p, struct dentry *dentry,
char *buffer, ssize_t buflen);
extern struct vfsmount *nfs_d_automount(struct path *path);
#ifdef CONFIG_NFS_V4
rpc_authflavor_t nfs_find_best_sec(struct nfs4_secinfo_flavors *);
#endif
struct vfsmount *nfs_submount(struct nfs_server *, struct dentry *,
struct nfs_fh *, struct nfs_fattr *);
struct vfsmount *nfs_do_submount(struct dentry *, struct nfs_fh *,
struct nfs_fattr *, rpc_authflavor_t);
/* getroot.c */
extern struct dentry *nfs_get_root(struct super_block *, struct nfs_fh *,
@ -294,46 +291,73 @@ extern struct dentry *nfs4_get_root(struct super_block *, struct nfs_fh *,
extern int nfs4_get_rootfh(struct nfs_server *server, struct nfs_fh *mntfh);
#endif
struct nfs_pageio_descriptor;
struct nfs_pgio_completion_ops;
/* read.c */
extern int nfs_initiate_read(struct nfs_read_data *data, struct rpc_clnt *clnt,
const struct rpc_call_ops *call_ops);
extern struct nfs_read_header *nfs_readhdr_alloc(void);
extern void nfs_readhdr_free(struct nfs_pgio_header *hdr);
extern void nfs_pageio_init_read(struct nfs_pageio_descriptor *pgio,
struct inode *inode,
const struct nfs_pgio_completion_ops *compl_ops);
extern int nfs_initiate_read(struct rpc_clnt *clnt,
struct nfs_read_data *data,
const struct rpc_call_ops *call_ops, int flags);
extern void nfs_read_prepare(struct rpc_task *task, void *calldata);
extern int nfs_generic_pagein(struct nfs_pageio_descriptor *desc,
struct list_head *head);
struct nfs_pgio_header *hdr);
extern void nfs_pageio_init_read_mds(struct nfs_pageio_descriptor *pgio,
struct inode *inode);
struct inode *inode,
const struct nfs_pgio_completion_ops *compl_ops);
extern void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio);
extern void nfs_readdata_release(struct nfs_read_data *rdata);
/* write.c */
extern void nfs_pageio_init_write(struct nfs_pageio_descriptor *pgio,
struct inode *inode, int ioflags,
const struct nfs_pgio_completion_ops *compl_ops);
extern struct nfs_write_header *nfs_writehdr_alloc(void);
extern void nfs_writehdr_free(struct nfs_pgio_header *hdr);
extern int nfs_generic_flush(struct nfs_pageio_descriptor *desc,
struct list_head *head);
struct nfs_pgio_header *hdr);
extern void nfs_pageio_init_write_mds(struct nfs_pageio_descriptor *pgio,
struct inode *inode, int ioflags);
struct inode *inode, int ioflags,
const struct nfs_pgio_completion_ops *compl_ops);
extern void nfs_pageio_reset_write_mds(struct nfs_pageio_descriptor *pgio);
extern void nfs_writedata_release(struct nfs_write_data *wdata);
extern void nfs_commit_free(struct nfs_write_data *p);
extern int nfs_initiate_write(struct nfs_write_data *data,
struct rpc_clnt *clnt,
extern void nfs_commit_free(struct nfs_commit_data *p);
extern int nfs_initiate_write(struct rpc_clnt *clnt,
struct nfs_write_data *data,
const struct rpc_call_ops *call_ops,
int how);
int how, int flags);
extern void nfs_write_prepare(struct rpc_task *task, void *calldata);
extern int nfs_initiate_commit(struct nfs_write_data *data,
struct rpc_clnt *clnt,
extern void nfs_commit_prepare(struct rpc_task *task, void *calldata);
extern int nfs_initiate_commit(struct rpc_clnt *clnt,
struct nfs_commit_data *data,
const struct rpc_call_ops *call_ops,
int how);
extern void nfs_init_commit(struct nfs_write_data *data,
int how, int flags);
extern void nfs_init_commit(struct nfs_commit_data *data,
struct list_head *head,
struct pnfs_layout_segment *lseg);
struct pnfs_layout_segment *lseg,
struct nfs_commit_info *cinfo);
int nfs_scan_commit_list(struct list_head *src, struct list_head *dst,
struct nfs_commit_info *cinfo, int max);
int nfs_scan_commit(struct inode *inode, struct list_head *dst,
struct nfs_commit_info *cinfo);
void nfs_mark_request_commit(struct nfs_page *req,
struct pnfs_layout_segment *lseg,
struct nfs_commit_info *cinfo);
int nfs_generic_commit_list(struct inode *inode, struct list_head *head,
int how, struct nfs_commit_info *cinfo);
void nfs_retry_commit(struct list_head *page_list,
struct pnfs_layout_segment *lseg);
void nfs_commit_clear_lock(struct nfs_inode *nfsi);
void nfs_commitdata_release(void *data);
void nfs_commit_release_pages(struct nfs_write_data *data);
void nfs_request_add_commit_list(struct nfs_page *req, struct list_head *head);
void nfs_request_remove_commit_list(struct nfs_page *req);
struct pnfs_layout_segment *lseg,
struct nfs_commit_info *cinfo);
void nfs_commitdata_release(struct nfs_commit_data *data);
void nfs_request_add_commit_list(struct nfs_page *req, struct list_head *dst,
struct nfs_commit_info *cinfo);
void nfs_request_remove_commit_list(struct nfs_page *req,
struct nfs_commit_info *cinfo);
void nfs_init_cinfo(struct nfs_commit_info *cinfo,
struct inode *inode,
struct nfs_direct_req *dreq);
#ifdef CONFIG_MIGRATION
extern int nfs_migrate_page(struct address_space *,
@ -342,15 +366,16 @@ extern int nfs_migrate_page(struct address_space *,
#define nfs_migrate_page NULL
#endif
/* direct.c */
void nfs_init_cinfo_from_dreq(struct nfs_commit_info *cinfo,
struct nfs_direct_req *dreq);
/* nfs4proc.c */
extern void __nfs4_read_done_cb(struct nfs_read_data *);
extern void nfs4_reset_read(struct rpc_task *task, struct nfs_read_data *data);
extern int nfs4_init_client(struct nfs_client *clp,
extern struct nfs_client *nfs4_init_client(struct nfs_client *clp,
const struct rpc_timeout *timeparms,
const char *ip_addr,
rpc_authflavor_t authflavour,
int noresvport);
extern void nfs4_reset_write(struct rpc_task *task, struct nfs_write_data *data);
rpc_authflavor_t authflavour);
extern int _nfs4_call_sync(struct rpc_clnt *clnt,
struct nfs_server *server,
struct rpc_message *msg,
@ -466,3 +491,15 @@ unsigned int nfs_page_array_len(unsigned int base, size_t len)
PAGE_SIZE - 1) >> PAGE_SHIFT;
}
/*
* Convert a struct timespec into a 64-bit change attribute
*
* This does approximately the same thing as timespec_to_ns(),
* but for calculation efficiency, we multiply the seconds by
* 1024*1024*1024.
*/
static inline
u64 nfs_timespec_to_change_attr(const struct timespec *ts)
{
return ((u64)ts->tv_sec << 30) + ts->tv_nsec;
}

103
fs/nfs/namespace.c
View File

@ -26,11 +26,6 @@ static LIST_HEAD(nfs_automount_list);
static DECLARE_DELAYED_WORK(nfs_automount_task, nfs_expire_automounts);
int nfs_mountpoint_expiry_timeout = 500 * HZ;
static struct vfsmount *nfs_do_submount(struct dentry *dentry,
struct nfs_fh *fh,
struct nfs_fattr *fattr,
rpc_authflavor_t authflavor);
/*
* nfs_path - reconstruct the path given an arbitrary dentry
* @base - used to return pointer to the end of devname part of path
@ -118,64 +113,6 @@ Elong:
return ERR_PTR(-ENAMETOOLONG);
}
#ifdef CONFIG_NFS_V4
rpc_authflavor_t nfs_find_best_sec(struct nfs4_secinfo_flavors *flavors)
{
struct gss_api_mech *mech;
struct xdr_netobj oid;
int i;
rpc_authflavor_t pseudoflavor = RPC_AUTH_UNIX;
for (i = 0; i < flavors->num_flavors; i++) {
struct nfs4_secinfo_flavor *flavor;
flavor = &flavors->flavors[i];
if (flavor->flavor == RPC_AUTH_NULL || flavor->flavor == RPC_AUTH_UNIX) {
pseudoflavor = flavor->flavor;
break;
} else if (flavor->flavor == RPC_AUTH_GSS) {
oid.len = flavor->gss.sec_oid4.len;
oid.data = flavor->gss.sec_oid4.data;
mech = gss_mech_get_by_OID(&oid);
if (!mech)
continue;
pseudoflavor = gss_svc_to_pseudoflavor(mech, flavor->gss.service);
gss_mech_put(mech);
break;
}
}
return pseudoflavor;
}
static struct rpc_clnt *nfs_lookup_mountpoint(struct inode *dir,
struct qstr *name,
struct nfs_fh *fh,
struct nfs_fattr *fattr)
{
int err;
if (NFS_PROTO(dir)->version == 4)
return nfs4_proc_lookup_mountpoint(dir, name, fh, fattr);
err = NFS_PROTO(dir)->lookup(NFS_SERVER(dir)->client, dir, name, fh, fattr);
if (err)
return ERR_PTR(err);
return rpc_clone_client(NFS_SERVER(dir)->client);
}
#else /* CONFIG_NFS_V4 */
static inline struct rpc_clnt *nfs_lookup_mountpoint(struct inode *dir,
struct qstr *name,
struct nfs_fh *fh,
struct nfs_fattr *fattr)
{
int err = NFS_PROTO(dir)->lookup(NFS_SERVER(dir)->client, dir, name, fh, fattr);
if (err)
return ERR_PTR(err);
return rpc_clone_client(NFS_SERVER(dir)->client);
}
#endif /* CONFIG_NFS_V4 */
/*
* nfs_d_automount - Handle crossing a mountpoint on the server
* @path - The mountpoint
@ -191,10 +128,9 @@ static inline struct rpc_clnt *nfs_lookup_mountpoint(struct inode *dir,
struct vfsmount *nfs_d_automount(struct path *path)
{
struct vfsmount *mnt;
struct dentry *parent;
struct nfs_server *server = NFS_SERVER(path->dentry->d_inode);
struct nfs_fh *fh = NULL;
struct nfs_fattr *fattr = NULL;
struct rpc_clnt *client;
dprintk("--> nfs_d_automount()\n");
@ -210,21 +146,7 @@ struct vfsmount *nfs_d_automount(struct path *path)
dprintk("%s: enter\n", __func__);
/* Look it up again to get its attributes */
parent = dget_parent(path->dentry);
client = nfs_lookup_mountpoint(parent->d_inode, &path->dentry->d_name, fh, fattr);
dput(parent);
if (IS_ERR(client)) {
mnt = ERR_CAST(client);
goto out;
}
if (fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL)
mnt = nfs_do_refmount(client, path->dentry);
else
mnt = nfs_do_submount(path->dentry, fh, fattr, client->cl_auth->au_flavor);
rpc_shutdown_client(client);
mnt = server->nfs_client->rpc_ops->submount(server, path->dentry, fh, fattr);
if (IS_ERR(mnt))
goto out;
@ -297,10 +219,8 @@ static struct vfsmount *nfs_do_clone_mount(struct nfs_server *server,
* @authflavor - security flavor to use when performing the mount
*
*/
static struct vfsmount *nfs_do_submount(struct dentry *dentry,
struct nfs_fh *fh,
struct nfs_fattr *fattr,
rpc_authflavor_t authflavor)
struct vfsmount *nfs_do_submount(struct dentry *dentry, struct nfs_fh *fh,
struct nfs_fattr *fattr, rpc_authflavor_t authflavor)
{
struct nfs_clone_mount mountdata = {
.sb = dentry->d_sb,
@ -333,3 +253,18 @@ out:
dprintk("<-- nfs_do_submount() = %p\n", mnt);
return mnt;
}
struct vfsmount *nfs_submount(struct nfs_server *server, struct dentry *dentry,
struct nfs_fh *fh, struct nfs_fattr *fattr)
{
int err;
struct dentry *parent = dget_parent(dentry);
/* Look it up again to get its attributes */
err = server->nfs_client->rpc_ops->lookup(parent->d_inode, &dentry->d_name, fh, fattr);
dput(parent);
if (err != 0)
return ERR_PTR(err);
return nfs_do_submount(dentry, fh, fattr, server->client->cl_auth->au_flavor);
}

5
fs/nfs/netns.h
View File

@ -1,3 +1,7 @@
/*
* NFS-private data for each "struct net". Accessed with net_generic().
*/
#ifndef __NFS_NETNS_H__
#define __NFS_NETNS_H__
@ -20,6 +24,7 @@ struct nfs_net {
struct idr cb_ident_idr; /* Protected by nfs_client_lock */
#endif
spinlock_t nfs_client_lock;
struct timespec boot_time;
};
extern int nfs_net_id;

5
fs/nfs/nfs2xdr.c
View File

@ -61,6 +61,7 @@
#define NFS_readdirres_sz (1)
#define NFS_statfsres_sz (1+NFS_info_sz)
static int nfs_stat_to_errno(enum nfs_stat);
/*
* While encoding arguments, set up the reply buffer in advance to
@ -313,6 +314,8 @@ static int decode_fattr(struct xdr_stream *xdr, struct nfs_fattr *fattr)
p = xdr_decode_time(p, &fattr->atime);
p = xdr_decode_time(p, &fattr->mtime);
xdr_decode_time(p, &fattr->ctime);
fattr->change_attr = nfs_timespec_to_change_attr(&fattr->ctime);
return 0;
out_overflow:
print_overflow_msg(__func__, xdr);
@ -1109,7 +1112,7 @@ static const struct {
* Returns a local errno value, or -EIO if the NFS status code is
* not recognized. This function is used jointly by NFSv2 and NFSv3.
*/
int nfs_stat_to_errno(enum nfs_stat status)
static int nfs_stat_to_errno(enum nfs_stat status)
{
int i;

27
fs/nfs/nfs3proc.c
View File

@ -142,7 +142,7 @@ nfs3_proc_setattr(struct dentry *dentry, struct nfs_fattr *fattr,
}
static int
nfs3_proc_lookup(struct rpc_clnt *clnt, struct inode *dir, struct qstr *name,
nfs3_proc_lookup(struct inode *dir, struct qstr *name,
struct nfs_fh *fhandle, struct nfs_fattr *fattr)
{
struct nfs3_diropargs arg = {
@ -810,11 +810,13 @@ nfs3_proc_pathconf(struct nfs_server *server, struct nfs_fh *fhandle,
static int nfs3_read_done(struct rpc_task *task, struct nfs_read_data *data)
{
if (nfs3_async_handle_jukebox(task, data->inode))
struct inode *inode = data->header->inode;
if (nfs3_async_handle_jukebox(task, inode))
return -EAGAIN;
nfs_invalidate_atime(data->inode);
nfs_refresh_inode(data->inode, &data->fattr);
nfs_invalidate_atime(inode);
nfs_refresh_inode(inode, &data->fattr);
return 0;
}
@ -830,10 +832,12 @@ static void nfs3_proc_read_rpc_prepare(struct rpc_task *task, struct nfs_read_da
static int nfs3_write_done(struct rpc_task *task, struct nfs_write_data *data)
{
if (nfs3_async_handle_jukebox(task, data->inode))
struct inode *inode = data->header->inode;
if (nfs3_async_handle_jukebox(task, inode))
return -EAGAIN;
if (task->tk_status >= 0)
nfs_post_op_update_inode_force_wcc(data->inode, data->res.fattr);
nfs_post_op_update_inode_force_wcc(inode, data->res.fattr);
return 0;
}
@ -847,7 +851,12 @@ static void nfs3_proc_write_rpc_prepare(struct rpc_task *task, struct nfs_write_
rpc_call_start(task);
}
static int nfs3_commit_done(struct rpc_task *task, struct nfs_write_data *data)
static void nfs3_proc_commit_rpc_prepare(struct rpc_task *task, struct nfs_commit_data *data)
{
rpc_call_start(task);
}
static int nfs3_commit_done(struct rpc_task *task, struct nfs_commit_data *data)
{
if (nfs3_async_handle_jukebox(task, data->inode))
return -EAGAIN;
@ -855,7 +864,7 @@ static int nfs3_commit_done(struct rpc_task *task, struct nfs_write_data *data)
return 0;
}
static void nfs3_proc_commit_setup(struct nfs_write_data *data, struct rpc_message *msg)
static void nfs3_proc_commit_setup(struct nfs_commit_data *data, struct rpc_message *msg)
{
msg->rpc_proc = &nfs3_procedures[NFS3PROC_COMMIT];
}
@ -875,6 +884,7 @@ const struct nfs_rpc_ops nfs_v3_clientops = {
.file_inode_ops = &nfs3_file_inode_operations,
.file_ops = &nfs_file_operations,
.getroot = nfs3_proc_get_root,
.submount = nfs_submount,
.getattr = nfs3_proc_getattr,
.setattr = nfs3_proc_setattr,
.lookup = nfs3_proc_lookup,
@ -906,6 +916,7 @@ const struct nfs_rpc_ops nfs_v3_clientops = {
.write_rpc_prepare = nfs3_proc_write_rpc_prepare,
.write_done = nfs3_write_done,
.commit_setup = nfs3_proc_commit_setup,
.commit_rpc_prepare = nfs3_proc_commit_rpc_prepare,
.commit_done = nfs3_commit_done,
.lock = nfs3_proc_lock,
.clear_acl_cache = nfs3_forget_cached_acls,

112
fs/nfs/nfs3xdr.c
View File

@ -86,6 +86,8 @@
XDR_QUADLEN(NFS_ACL_INLINE_BUFSIZE))
#define ACL3_setaclres_sz (1+NFS3_post_op_attr_sz)
static int nfs3_stat_to_errno(enum nfs_stat);
/*
* Map file type to S_IFMT bits
*/
@ -675,6 +677,7 @@ static int decode_fattr3(struct xdr_stream *xdr, struct nfs_fattr *fattr)
p = xdr_decode_nfstime3(p, &fattr->atime);
p = xdr_decode_nfstime3(p, &fattr->mtime);
xdr_decode_nfstime3(p, &fattr->ctime);
fattr->change_attr = nfs_timespec_to_change_attr(&fattr->ctime);
fattr->valid |= NFS_ATTR_FATTR_V3;
return 0;
@ -725,12 +728,14 @@ static int decode_wcc_attr(struct xdr_stream *xdr, struct nfs_fattr *fattr)
goto out_overflow;
fattr->valid |= NFS_ATTR_FATTR_PRESIZE
| NFS_ATTR_FATTR_PRECHANGE
| NFS_ATTR_FATTR_PREMTIME
| NFS_ATTR_FATTR_PRECTIME;
p = xdr_decode_size3(p, &fattr->pre_size);
p = xdr_decode_nfstime3(p, &fattr->pre_mtime);
xdr_decode_nfstime3(p, &fattr->pre_ctime);
fattr->pre_change_attr = nfs_timespec_to_change_attr(&fattr->pre_ctime);
return 0;
out_overflow:
@ -1287,7 +1292,7 @@ static void nfs3_xdr_enc_readdirplus3args(struct rpc_rqst *req,
* };
*/
static void encode_commit3args(struct xdr_stream *xdr,
const struct nfs_writeargs *args)
const struct nfs_commitargs *args)
{
__be32 *p;
@ -1300,7 +1305,7 @@ static void encode_commit3args(struct xdr_stream *xdr,
static void nfs3_xdr_enc_commit3args(struct rpc_rqst *req,
struct xdr_stream *xdr,
const struct nfs_writeargs *args)
const struct nfs_commitargs *args)
{
encode_commit3args(xdr, args);
}
@ -1385,7 +1390,7 @@ static int nfs3_xdr_dec_getattr3res(struct rpc_rqst *req,
out:
return error;
out_default:
return nfs_stat_to_errno(status);
return nfs3_stat_to_errno(status);
}
/*
@ -1424,7 +1429,7 @@ static int nfs3_xdr_dec_setattr3res(struct rpc_rqst *req,
out:
return error;
out_status:
return nfs_stat_to_errno(status);
return nfs3_stat_to_errno(status);
}
/*
@ -1472,7 +1477,7 @@ out_default:
error = decode_post_op_attr(xdr, result->dir_attr);
if (unlikely(error))
goto out;
return nfs_stat_to_errno(status);
return nfs3_stat_to_errno(status);
}
/*
@ -1513,7 +1518,7 @@ static int nfs3_xdr_dec_access3res(struct rpc_rqst *req,
out:
return error;
out_default:
return nfs_stat_to_errno(status);
return nfs3_stat_to_errno(status);
}
/*
@ -1554,7 +1559,7 @@ static int nfs3_xdr_dec_readlink3res(struct rpc_rqst *req,
out:
return error;
out_default:
return nfs_stat_to_errno(status);
return nfs3_stat_to_errno(status);
}
/*
@ -1636,7 +1641,7 @@ static int nfs3_xdr_dec_read3res(struct rpc_rqst *req, struct xdr_stream *xdr,
out:
return error;
out_status:
return nfs_stat_to_errno(status);
return nfs3_stat_to_errno(status);
}
/*
@ -1706,7 +1711,7 @@ static int nfs3_xdr_dec_write3res(struct rpc_rqst *req, struct xdr_stream *xdr,
out:
return error;
out_status:
return nfs_stat_to_errno(status);
return nfs3_stat_to_errno(status);
}
/*
@ -1770,7 +1775,7 @@ out_default:
error = decode_wcc_data(xdr, result->dir_attr);
if (unlikely(error))
goto out;
return nfs_stat_to_errno(status);
return nfs3_stat_to_errno(status);
}
/*
@ -1809,7 +1814,7 @@ static int nfs3_xdr_dec_remove3res(struct rpc_rqst *req,
out:
return error;
out_status:
return nfs_stat_to_errno(status);
return nfs3_stat_to_errno(status);
}
/*
@ -1853,7 +1858,7 @@ static int nfs3_xdr_dec_rename3res(struct rpc_rqst *req,
out:
return error;
out_status:
return nfs_stat_to_errno(status);
return nfs3_stat_to_errno(status);
}
/*
@ -1896,7 +1901,7 @@ static int nfs3_xdr_dec_link3res(struct rpc_rqst *req, struct xdr_stream *xdr,
out:
return error;
out_status:
return nfs_stat_to_errno(status);
return nfs3_stat_to_errno(status);
}
/**
@ -2088,7 +2093,7 @@ out_default:
error = decode_post_op_attr(xdr, result->dir_attr);
if (unlikely(error))
goto out;
return nfs_stat_to_errno(status);
return nfs3_stat_to_errno(status);
}
/*
@ -2156,7 +2161,7 @@ static int nfs3_xdr_dec_fsstat3res(struct rpc_rqst *req,
out:
return error;
out_status:
return nfs_stat_to_errno(status);
return nfs3_stat_to_errno(status);
}
/*
@ -2232,7 +2237,7 @@ static int nfs3_xdr_dec_fsinfo3res(struct rpc_rqst *req,
out:
return error;
out_status:
return nfs_stat_to_errno(status);
return nfs3_stat_to_errno(status);
}
/*
@ -2295,7 +2300,7 @@ static int nfs3_xdr_dec_pathconf3res(struct rpc_rqst *req,
out:
return error;
out_status:
return nfs_stat_to_errno(status);
return nfs3_stat_to_errno(status);
}
/*
@ -2319,7 +2324,7 @@ out_status:
*/
static int nfs3_xdr_dec_commit3res(struct rpc_rqst *req,
struct xdr_stream *xdr,
struct nfs_writeres *result)
struct nfs_commitres *result)
{
enum nfs_stat status;
int error;
@ -2336,7 +2341,7 @@ static int nfs3_xdr_dec_commit3res(struct rpc_rqst *req,
out:
return error;
out_status:
return nfs_stat_to_errno(status);
return nfs3_stat_to_errno(status);
}
#ifdef CONFIG_NFS_V3_ACL
@ -2401,7 +2406,7 @@ static int nfs3_xdr_dec_getacl3res(struct rpc_rqst *req,
out:
return error;
out_default:
return nfs_stat_to_errno(status);
return nfs3_stat_to_errno(status);
}
static int nfs3_xdr_dec_setacl3res(struct rpc_rqst *req,
@ -2420,11 +2425,76 @@ static int nfs3_xdr_dec_setacl3res(struct rpc_rqst *req,
out:
return error;
out_default:
return nfs_stat_to_errno(status);
return nfs3_stat_to_errno(status);
}
#endif /* CONFIG_NFS_V3_ACL */
/*
* We need to translate between nfs status return values and
* the local errno values which may not be the same.
*/
static const struct {
int stat;
int errno;
} nfs_errtbl[] = {
{ NFS_OK, 0 },
{ NFSERR_PERM, -EPERM },
{ NFSERR_NOENT, -ENOENT },
{ NFSERR_IO, -errno_NFSERR_IO},
{ NFSERR_NXIO, -ENXIO },
/* { NFSERR_EAGAIN, -EAGAIN }, */
{ NFSERR_ACCES, -EACCES },
{ NFSERR_EXIST, -EEXIST },
{ NFSERR_XDEV, -EXDEV },
{ NFSERR_NODEV, -ENODEV },
{ NFSERR_NOTDIR, -ENOTDIR },
{ NFSERR_ISDIR, -EISDIR },
{ NFSERR_INVAL, -EINVAL },
{ NFSERR_FBIG, -EFBIG },
{ NFSERR_NOSPC, -ENOSPC },
{ NFSERR_ROFS, -EROFS },
{ NFSERR_MLINK, -EMLINK },
{ NFSERR_NAMETOOLONG, -ENAMETOOLONG },
{ NFSERR_NOTEMPTY, -ENOTEMPTY },
{ NFSERR_DQUOT, -EDQUOT },
{ NFSERR_STALE, -ESTALE },
{ NFSERR_REMOTE, -EREMOTE },
#ifdef EWFLUSH
{ NFSERR_WFLUSH, -EWFLUSH },
#endif
{ NFSERR_BADHANDLE, -EBADHANDLE },
{ NFSERR_NOT_SYNC, -ENOTSYNC },
{ NFSERR_BAD_COOKIE, -EBADCOOKIE },
{ NFSERR_NOTSUPP, -ENOTSUPP },
{ NFSERR_TOOSMALL, -ETOOSMALL },
{ NFSERR_SERVERFAULT, -EREMOTEIO },
{ NFSERR_BADTYPE, -EBADTYPE },
{ NFSERR_JUKEBOX, -EJUKEBOX },
{ -1, -EIO }
};
/**
* nfs3_stat_to_errno - convert an NFS status code to a local errno
* @status: NFS status code to convert
*
* Returns a local errno value, or -EIO if the NFS status code is
* not recognized. This function is used jointly by NFSv2 and NFSv3.
*/
static int nfs3_stat_to_errno(enum nfs_stat status)
{
int i;
for (i = 0; nfs_errtbl[i].stat != -1; i++) {
if (nfs_errtbl[i].stat == (int)status)
return nfs_errtbl[i].errno;
}
dprintk("NFS: Unrecognized nfs status value: %u\n", status);
return nfs_errtbl[i].errno;
}
#define PROC(proc, argtype, restype, timer) \
[NFS3PROC_##proc] = { \
.p_proc = NFS3PROC_##proc, \

23
fs/nfs/nfs4_fs.h
View File

@ -24,6 +24,8 @@ enum nfs4_client_state {
NFS4CLNT_RECALL_SLOT,
NFS4CLNT_LEASE_CONFIRM,
NFS4CLNT_SERVER_SCOPE_MISMATCH,
NFS4CLNT_PURGE_STATE,
NFS4CLNT_BIND_CONN_TO_SESSION,
};
enum nfs4_session_state {
@ -52,11 +54,6 @@ struct nfs4_minor_version_ops {
const struct nfs4_state_maintenance_ops *state_renewal_ops;
};
struct nfs_unique_id {
struct rb_node rb_node;
__u64 id;
};
#define NFS_SEQID_CONFIRMED 1
struct nfs_seqid_counter {
ktime_t create_time;
@ -206,12 +203,18 @@ extern const struct dentry_operations nfs4_dentry_operations;
extern const struct inode_operations nfs4_dir_inode_operations;
/* nfs4namespace.c */
rpc_authflavor_t nfs_find_best_sec(struct nfs4_secinfo_flavors *);
struct rpc_clnt *nfs4_create_sec_client(struct rpc_clnt *, struct inode *, struct qstr *);
struct vfsmount *nfs4_submount(struct nfs_server *, struct dentry *,
struct nfs_fh *, struct nfs_fattr *);
/* nfs4proc.c */
extern int nfs4_proc_setclientid(struct nfs_client *, u32, unsigned short, struct rpc_cred *, struct nfs4_setclientid_res *);
extern int nfs4_proc_setclientid_confirm(struct nfs_client *, struct nfs4_setclientid_res *arg, struct rpc_cred *);
extern int nfs4_proc_get_rootfh(struct nfs_server *, struct nfs_fh *, struct nfs_fsinfo *);
extern int nfs4_proc_bind_conn_to_session(struct nfs_client *, struct rpc_cred *cred);
extern int nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred);
extern int nfs4_destroy_clientid(struct nfs_client *clp);
extern int nfs4_init_clientid(struct nfs_client *, struct rpc_cred *);
extern int nfs41_init_clientid(struct nfs_client *, struct rpc_cred *);
extern int nfs4_do_close(struct nfs4_state *state, gfp_t gfp_mask, int wait, bool roc);
@ -239,8 +242,8 @@ extern int nfs41_setup_sequence(struct nfs4_session *session,
struct rpc_task *task);
extern void nfs4_destroy_session(struct nfs4_session *session);
extern struct nfs4_session *nfs4_alloc_session(struct nfs_client *clp);
extern int nfs4_proc_create_session(struct nfs_client *);
extern int nfs4_proc_destroy_session(struct nfs4_session *);
extern int nfs4_proc_create_session(struct nfs_client *, struct rpc_cred *);
extern int nfs4_proc_destroy_session(struct nfs4_session *, struct rpc_cred *);
extern int nfs4_init_session(struct nfs_server *server);
extern int nfs4_proc_get_lease_time(struct nfs_client *clp,
struct nfs_fsinfo *fsinfo);
@ -310,9 +313,9 @@ struct rpc_cred *nfs4_get_renew_cred_locked(struct nfs_client *clp);
#if defined(CONFIG_NFS_V4_1)
struct rpc_cred *nfs4_get_machine_cred_locked(struct nfs_client *clp);
struct rpc_cred *nfs4_get_exchange_id_cred(struct nfs_client *clp);
extern void nfs4_schedule_session_recovery(struct nfs4_session *);
extern void nfs4_schedule_session_recovery(struct nfs4_session *, int);
#else
static inline void nfs4_schedule_session_recovery(struct nfs4_session *session)
static inline void nfs4_schedule_session_recovery(struct nfs4_session *session, int err)
{
}
#endif /* CONFIG_NFS_V4_1 */
@ -334,7 +337,7 @@ extern void nfs4_schedule_stateid_recovery(const struct nfs_server *, struct nfs
extern void nfs41_handle_sequence_flag_errors(struct nfs_client *clp, u32 flags);
extern void nfs41_handle_recall_slot(struct nfs_client *clp);
extern void nfs41_handle_server_scope(struct nfs_client *,
struct server_scope **);
struct nfs41_server_scope **);
extern void nfs4_put_lock_state(struct nfs4_lock_state *lsp);
extern int nfs4_set_lock_state(struct nfs4_state *state, struct file_lock *fl);
extern void nfs4_select_rw_stateid(nfs4_stateid *, struct nfs4_state *,

702
fs/nfs/nfs4filelayout.c
View File

File diff suppressed because it is too large Load Diff

63
fs/nfs/nfs4filelayout.h
View File

@ -32,6 +32,13 @@
#include "pnfs.h"
/*
* Default data server connection timeout and retrans vaules.
* Set by module paramters dataserver_timeo and dataserver_retrans.
*/
#define NFS4_DEF_DS_TIMEO 60
#define NFS4_DEF_DS_RETRANS 5
/*
* Field testing shows we need to support up to 4096 stripe indices.
* We store each index as a u8 (u32 on the wire) to keep the memory footprint
@ -41,6 +48,9 @@
#define NFS4_PNFS_MAX_STRIPE_CNT 4096
#define NFS4_PNFS_MAX_MULTI_CNT 256 /* 256 fit into a u8 stripe_index */
/* error codes for internal use */
#define NFS4ERR_RESET_TO_MDS 12001
enum stripetype4 {
STRIPE_SPARSE = 1,
STRIPE_DENSE = 2
@ -62,23 +72,14 @@ struct nfs4_pnfs_ds {
atomic_t ds_count;
};
/* nfs4_file_layout_dsaddr flags */
#define NFS4_DEVICE_ID_NEG_ENTRY 0x00000001
struct nfs4_file_layout_dsaddr {
struct nfs4_deviceid_node id_node;
unsigned long flags;
u32 stripe_count;
u8 *stripe_indices;
u32 ds_num;
struct nfs4_pnfs_ds *ds_list[1];
};
struct nfs4_fl_commit_bucket {
struct list_head written;
struct list_head committing;
};
struct nfs4_filelayout_segment {
struct pnfs_layout_segment generic_hdr;
u32 stripe_type;
@ -89,10 +90,19 @@ struct nfs4_filelayout_segment {
struct nfs4_file_layout_dsaddr *dsaddr; /* Point to GETDEVINFO data */
unsigned int num_fh;
struct nfs_fh **fh_array;
struct nfs4_fl_commit_bucket *commit_buckets; /* Sort commits to ds */
int number_of_buckets;
};
struct nfs4_filelayout {
struct pnfs_layout_hdr generic_hdr;
struct pnfs_ds_commit_info commit_info;
};
static inline struct nfs4_filelayout *
FILELAYOUT_FROM_HDR(struct pnfs_layout_hdr *lo)
{
return container_of(lo, struct nfs4_filelayout, generic_hdr);
}
static inline struct nfs4_filelayout_segment *
FILELAYOUT_LSEG(struct pnfs_layout_segment *lseg)
{
@ -107,6 +117,36 @@ FILELAYOUT_DEVID_NODE(struct pnfs_layout_segment *lseg)
return &FILELAYOUT_LSEG(lseg)->dsaddr->id_node;
}
static inline void
filelayout_mark_devid_invalid(struct nfs4_deviceid_node *node)
{
u32 *p = (u32 *)&node->deviceid;
printk(KERN_WARNING "NFS: Deviceid [%x%x%x%x] marked out of use.\n",
p[0], p[1], p[2], p[3]);
set_bit(NFS_DEVICEID_INVALID, &node->flags);
}
static inline bool
filelayout_test_layout_invalid(struct pnfs_layout_hdr *lo)
{
return test_bit(NFS_LAYOUT_INVALID, &lo->plh_flags);
}
static inline bool
filelayout_test_devid_invalid(struct nfs4_deviceid_node *node)
{
return test_bit(NFS_DEVICEID_INVALID, &node->flags);
}
static inline bool
filelayout_reset_to_mds(struct pnfs_layout_segment *lseg)
{
return filelayout_test_devid_invalid(FILELAYOUT_DEVID_NODE(lseg)) ||
filelayout_test_layout_invalid(lseg->pls_layout);
}
extern struct nfs_fh *
nfs4_fl_select_ds_fh(struct pnfs_layout_segment *lseg, u32 j);
@ -119,5 +159,6 @@ extern void nfs4_fl_put_deviceid(struct nfs4_file_layout_dsaddr *dsaddr);
extern void nfs4_fl_free_deviceid(struct nfs4_file_layout_dsaddr *dsaddr);
struct nfs4_file_layout_dsaddr *
get_device_info(struct inode *inode, struct nfs4_deviceid *dev_id, gfp_t gfp_flags);
void nfs4_ds_disconnect(struct nfs_client *clp);
#endif /* FS_NFS_NFS4FILELAYOUT_H */

102
fs/nfs/nfs4filelayoutdev.c
View File

@ -30,12 +30,16 @@
#include <linux/nfs_fs.h>
#include <linux/vmalloc.h>
#include <linux/module.h>
#include "internal.h"
#include "nfs4filelayout.h"
#define NFSDBG_FACILITY NFSDBG_PNFS_LD
static unsigned int dataserver_timeo = NFS4_DEF_DS_TIMEO;
static unsigned int dataserver_retrans = NFS4_DEF_DS_RETRANS;
/*
* Data server cache
*
@ -144,6 +148,28 @@ _data_server_lookup_locked(const struct list_head *dsaddrs)
return NULL;
}
/*
* Lookup DS by nfs_client pointer. Zero data server client pointer
*/
void nfs4_ds_disconnect(struct nfs_client *clp)
{
struct nfs4_pnfs_ds *ds;
struct nfs_client *found = NULL;
dprintk("%s clp %p\n", __func__, clp);
spin_lock(&nfs4_ds_cache_lock);
list_for_each_entry(ds, &nfs4_data_server_cache, ds_node)
if (ds->ds_clp && ds->ds_clp == clp) {
found = ds->ds_clp;
ds->ds_clp = NULL;
}
spin_unlock(&nfs4_ds_cache_lock);
if (found) {
set_bit(NFS_CS_STOP_RENEW, &clp->cl_res_state);
nfs_put_client(clp);
}
}
/*
* Create an rpc connection to the nfs4_pnfs_ds data server
* Currently only supports IPv4 and IPv6 addresses
@ -165,8 +191,9 @@ nfs4_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds)
__func__, ds->ds_remotestr, da->da_remotestr);
clp = nfs4_set_ds_client(mds_srv->nfs_client,
(struct sockaddr *)&da->da_addr,
da->da_addrlen, IPPROTO_TCP);
(struct sockaddr *)&da->da_addr,
da->da_addrlen, IPPROTO_TCP,
dataserver_timeo, dataserver_retrans);
if (!IS_ERR(clp))
break;
}
@ -176,28 +203,7 @@ nfs4_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds)
goto out;
}
if ((clp->cl_exchange_flags & EXCHGID4_FLAG_MASK_PNFS) != 0) {
if (!is_ds_client(clp)) {
status = -ENODEV;
goto out_put;
}
ds->ds_clp = clp;
dprintk("%s [existing] server=%s\n", __func__,
ds->ds_remotestr);
goto out;
}
/*
* Do not set NFS_CS_CHECK_LEASE_TIME instead set the DS lease to
* be equal to the MDS lease. Renewal is scheduled in create_session.
*/
spin_lock(&mds_srv->nfs_client->cl_lock);
clp->cl_lease_time = mds_srv->nfs_client->cl_lease_time;
spin_unlock(&mds_srv->nfs_client->cl_lock);
clp->cl_last_renewal = jiffies;
/* New nfs_client */
status = nfs4_init_ds_session(clp);
status = nfs4_init_ds_session(clp, mds_srv->nfs_client->cl_lease_time);
if (status)
goto out_put;
@ -602,7 +608,7 @@ decode_device(struct inode *ino, struct pnfs_device *pdev, gfp_t gfp_flags)
mp_count = be32_to_cpup(p); /* multipath count */
for (j = 0; j < mp_count; j++) {
da = decode_ds_addr(NFS_SERVER(ino)->nfs_client->net,
da = decode_ds_addr(NFS_SERVER(ino)->nfs_client->cl_net,
&stream, gfp_flags);
if (da)
list_add_tail(&da->da_node, &dsaddrs);
@ -791,48 +797,42 @@ nfs4_fl_select_ds_fh(struct pnfs_layout_segment *lseg, u32 j)
return flseg->fh_array[i];
}
static void
filelayout_mark_devid_negative(struct nfs4_file_layout_dsaddr *dsaddr,
int err, const char *ds_remotestr)
{
u32 *p = (u32 *)&dsaddr->id_node.deviceid;
printk(KERN_ERR "NFS: data server %s connection error %d."
" Deviceid [%x%x%x%x] marked out of use.\n",
ds_remotestr, err, p[0], p[1], p[2], p[3]);
spin_lock(&nfs4_ds_cache_lock);
dsaddr->flags |= NFS4_DEVICE_ID_NEG_ENTRY;
spin_unlock(&nfs4_ds_cache_lock);
}
struct nfs4_pnfs_ds *
nfs4_fl_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx)
{
struct nfs4_file_layout_dsaddr *dsaddr = FILELAYOUT_LSEG(lseg)->dsaddr;
struct nfs4_pnfs_ds *ds = dsaddr->ds_list[ds_idx];
struct nfs4_deviceid_node *devid = FILELAYOUT_DEVID_NODE(lseg);
if (filelayout_test_devid_invalid(devid))
return NULL;
if (ds == NULL) {
printk(KERN_ERR "NFS: %s: No data server for offset index %d\n",
__func__, ds_idx);
return NULL;
goto mark_dev_invalid;
}
if (!ds->ds_clp) {
struct nfs_server *s = NFS_SERVER(lseg->pls_layout->plh_inode);
int err;
if (dsaddr->flags & NFS4_DEVICE_ID_NEG_ENTRY) {
/* Already tried to connect, don't try again */
dprintk("%s Deviceid marked out of use\n", __func__);
return NULL;
}
err = nfs4_ds_connect(s, ds);
if (err) {
filelayout_mark_devid_negative(dsaddr, err,
ds->ds_remotestr);
return NULL;
}
if (err)
goto mark_dev_invalid;
}
return ds;
mark_dev_invalid:
filelayout_mark_devid_invalid(devid);
return NULL;
}
module_param(dataserver_retrans, uint, 0644);
MODULE_PARM_DESC(dataserver_retrans, "The number of times the NFSv4.1 client "
"retries a request before it attempts further "
" recovery action.");
module_param(dataserver_timeo, uint, 0644);
MODULE_PARM_DESC(dataserver_timeo, "The time (in tenths of a second) the "
"NFSv4.1 client waits for a response from a "
" data server before it retries an NFS request.");

55
fs/nfs/nfs4namespace.c
View File

@ -132,6 +132,35 @@ static size_t nfs_parse_server_name(char *string, size_t len,
return ret;
}
rpc_authflavor_t nfs_find_best_sec(struct nfs4_secinfo_flavors *flavors)
{
struct gss_api_mech *mech;
struct xdr_netobj oid;
int i;
rpc_authflavor_t pseudoflavor = RPC_AUTH_UNIX;
for (i = 0; i < flavors->num_flavors; i++) {
struct nfs4_secinfo_flavor *flavor;
flavor = &flavors->flavors[i];
if (flavor->flavor == RPC_AUTH_NULL || flavor->flavor == RPC_AUTH_UNIX) {
pseudoflavor = flavor->flavor;
break;
} else if (flavor->flavor == RPC_AUTH_GSS) {
oid.len = flavor->gss.sec_oid4.len;
oid.data = flavor->gss.sec_oid4.data;
mech = gss_mech_get_by_OID(&oid);
if (!mech)
continue;
pseudoflavor = gss_svc_to_pseudoflavor(mech, flavor->gss.service);
gss_mech_put(mech);
break;
}
}
return pseudoflavor;
}
static rpc_authflavor_t nfs4_negotiate_security(struct inode *inode, struct qstr *name)
{
struct page *page;
@ -168,7 +197,7 @@ struct rpc_clnt *nfs4_create_sec_client(struct rpc_clnt *clnt, struct inode *ino
rpc_authflavor_t flavor;
flavor = nfs4_negotiate_security(inode, name);
if (flavor < 0)
if ((int)flavor < 0)
return ERR_PTR(flavor);
clone = rpc_clone_client(clnt);
@ -300,7 +329,7 @@ out:
* @dentry - dentry of referral
*
*/
struct vfsmount *nfs_do_refmount(struct rpc_clnt *client, struct dentry *dentry)
static struct vfsmount *nfs_do_refmount(struct rpc_clnt *client, struct dentry *dentry)
{
struct vfsmount *mnt = ERR_PTR(-ENOMEM);
struct dentry *parent;
@ -341,3 +370,25 @@ out:
dprintk("%s: done\n", __func__);
return mnt;
}
struct vfsmount *nfs4_submount(struct nfs_server *server, struct dentry *dentry,
struct nfs_fh *fh, struct nfs_fattr *fattr)
{
struct dentry *parent = dget_parent(dentry);
struct rpc_clnt *client;
struct vfsmount *mnt;
/* Look it up again to get its attributes and sec flavor */
client = nfs4_proc_lookup_mountpoint(parent->d_inode, &dentry->d_name, fh, fattr);
dput(parent);
if (IS_ERR(client))
return ERR_CAST(client);
if (fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL)
mnt = nfs_do_refmount(client, dentry);
else
mnt = nfs_do_submount(dentry, fh, fattr, client->cl_auth->au_flavor);
rpc_shutdown_client(client);
return mnt;
}

537
fs/nfs/nfs4proc.c
View File

File diff suppressed because it is too large Load Diff

2
fs/nfs/nfs4renewd.c
View File

@ -49,7 +49,7 @@
#include "nfs4_fs.h"
#include "delegation.h"
#define NFSDBG_FACILITY NFSDBG_PROC
#define NFSDBG_FACILITY NFSDBG_STATE
void
nfs4_renew_state(struct work_struct *work)

229
fs/nfs/nfs4state.c
View File

@ -57,6 +57,8 @@
#include "internal.h"
#include "pnfs.h"
#define NFSDBG_FACILITY NFSDBG_STATE
#define OPENOWNER_POOL_SIZE 8
const nfs4_stateid zero_stateid;
@ -254,7 +256,7 @@ int nfs41_init_clientid(struct nfs_client *clp, struct rpc_cred *cred)
goto out;
set_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state);
do_confirm:
status = nfs4_proc_create_session(clp);
status = nfs4_proc_create_session(clp, cred);
if (status != 0)
goto out;
clear_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state);
@ -1106,6 +1108,8 @@ void nfs4_schedule_lease_recovery(struct nfs_client *clp)
return;
if (!test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state))
set_bit(NFS4CLNT_CHECK_LEASE, &clp->cl_state);
dprintk("%s: scheduling lease recovery for server %s\n", __func__,
clp->cl_hostname);
nfs4_schedule_state_manager(clp);
}
EXPORT_SYMBOL_GPL(nfs4_schedule_lease_recovery);
@ -1122,6 +1126,8 @@ static void nfs40_handle_cb_pathdown(struct nfs_client *clp)
{
set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state);
nfs_expire_all_delegations(clp);
dprintk("%s: handling CB_PATHDOWN recovery for server %s\n", __func__,
clp->cl_hostname);
}
void nfs4_schedule_path_down_recovery(struct nfs_client *clp)
@ -1158,6 +1164,8 @@ void nfs4_schedule_stateid_recovery(const struct nfs_server *server, struct nfs4
struct nfs_client *clp = server->nfs_client;
nfs4_state_mark_reclaim_nograce(clp, state);
dprintk("%s: scheduling stateid recovery for server %s\n", __func__,
clp->cl_hostname);
nfs4_schedule_state_manager(clp);
}
EXPORT_SYMBOL_GPL(nfs4_schedule_stateid_recovery);
@ -1491,19 +1499,25 @@ static int nfs4_recovery_handle_error(struct nfs_client *clp, int error)
case -NFS4ERR_BADSLOT:
case -NFS4ERR_BAD_HIGH_SLOT:
case -NFS4ERR_DEADSESSION:
case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION:
case -NFS4ERR_SEQ_FALSE_RETRY:
case -NFS4ERR_SEQ_MISORDERED:
set_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state);
/* Zero session reset errors */
break;
case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION:
set_bit(NFS4CLNT_BIND_CONN_TO_SESSION, &clp->cl_state);
break;
case -EKEYEXPIRED:
/* Nothing we can do */
nfs4_warn_keyexpired(clp->cl_hostname);
break;
default:
dprintk("%s: failed to handle error %d for server %s\n",
__func__, error, clp->cl_hostname);
return error;
}
dprintk("%s: handled error %d for server %s\n", __func__, error,
clp->cl_hostname);
return 0;
}
@ -1572,34 +1586,82 @@ out:
return nfs4_recovery_handle_error(clp, status);
}
/* Set NFS4CLNT_LEASE_EXPIRED for all v4.0 errors and for recoverable errors
* on EXCHANGE_ID for v4.1
*/
static int nfs4_handle_reclaim_lease_error(struct nfs_client *clp, int status)
{
switch (status) {
case -NFS4ERR_SEQ_MISORDERED:
if (test_and_set_bit(NFS4CLNT_PURGE_STATE, &clp->cl_state))
return -ESERVERFAULT;
/* Lease confirmation error: retry after purging the lease */
ssleep(1);
case -NFS4ERR_CLID_INUSE:
case -NFS4ERR_STALE_CLIENTID:
clear_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state);
break;
case -EACCES:
if (clp->cl_machine_cred == NULL)
return -EACCES;
/* Handle case where the user hasn't set up machine creds */
nfs4_clear_machine_cred(clp);
case -NFS4ERR_DELAY:
case -ETIMEDOUT:
case -EAGAIN:
ssleep(1);
break;
case -NFS4ERR_MINOR_VERS_MISMATCH:
if (clp->cl_cons_state == NFS_CS_SESSION_INITING)
nfs_mark_client_ready(clp, -EPROTONOSUPPORT);
dprintk("%s: exit with error %d for server %s\n",
__func__, -EPROTONOSUPPORT, clp->cl_hostname);
return -EPROTONOSUPPORT;
case -EKEYEXPIRED:
nfs4_warn_keyexpired(clp->cl_hostname);
case -NFS4ERR_NOT_SAME: /* FixMe: implement recovery
* in nfs4_exchange_id */
default:
dprintk("%s: exit with error %d for server %s\n", __func__,
status, clp->cl_hostname);
return status;
}
set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state);
dprintk("%s: handled error %d for server %s\n", __func__, status,
clp->cl_hostname);
return 0;
}
static int nfs4_reclaim_lease(struct nfs_client *clp)
{
struct rpc_cred *cred;
const struct nfs4_state_recovery_ops *ops =
clp->cl_mvops->reboot_recovery_ops;
int status = -ENOENT;
int status;
cred = ops->get_clid_cred(clp);
if (cred != NULL) {
status = ops->establish_clid(clp, cred);
put_rpccred(cred);
/* Handle case where the user hasn't set up machine creds */
if (status == -EACCES && cred == clp->cl_machine_cred) {
nfs4_clear_machine_cred(clp);
status = -EAGAIN;
}
if (status == -NFS4ERR_MINOR_VERS_MISMATCH)
status = -EPROTONOSUPPORT;
}
return status;
if (cred == NULL)
return -ENOENT;
status = ops->establish_clid(clp, cred);
put_rpccred(cred);
if (status != 0)
return nfs4_handle_reclaim_lease_error(clp, status);
return 0;
}
#ifdef CONFIG_NFS_V4_1
void nfs4_schedule_session_recovery(struct nfs4_session *session)
void nfs4_schedule_session_recovery(struct nfs4_session *session, int err)
{
struct nfs_client *clp = session->clp;
set_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state);
switch (err) {
default:
set_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state);
break;
case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION:
set_bit(NFS4CLNT_BIND_CONN_TO_SESSION, &clp->cl_state);
}
nfs4_schedule_lease_recovery(clp);
}
EXPORT_SYMBOL_GPL(nfs4_schedule_session_recovery);
@ -1607,14 +1669,19 @@ EXPORT_SYMBOL_GPL(nfs4_schedule_session_recovery);
void nfs41_handle_recall_slot(struct nfs_client *clp)
{
set_bit(NFS4CLNT_RECALL_SLOT, &clp->cl_state);
dprintk("%s: scheduling slot recall for server %s\n", __func__,
clp->cl_hostname);
nfs4_schedule_state_manager(clp);
}
static void nfs4_reset_all_state(struct nfs_client *clp)
{
if (test_and_set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state) == 0) {
clp->cl_boot_time = CURRENT_TIME;
set_bit(NFS4CLNT_PURGE_STATE, &clp->cl_state);
clear_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state);
nfs4_state_start_reclaim_nograce(clp);
dprintk("%s: scheduling reset of all state for server %s!\n",
__func__, clp->cl_hostname);
nfs4_schedule_state_manager(clp);
}
}
@ -1623,26 +1690,39 @@ static void nfs41_handle_server_reboot(struct nfs_client *clp)
{
if (test_and_set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state) == 0) {
nfs4_state_start_reclaim_reboot(clp);
dprintk("%s: server %s rebooted!\n", __func__,
clp->cl_hostname);
nfs4_schedule_state_manager(clp);
}
}
static void nfs41_handle_state_revoked(struct nfs_client *clp)
{
/* Temporary */
nfs4_reset_all_state(clp);
dprintk("%s: state revoked on server %s\n", __func__, clp->cl_hostname);
}
static void nfs41_handle_recallable_state_revoked(struct nfs_client *clp)
{
/* This will need to handle layouts too */
nfs_expire_all_delegations(clp);
dprintk("%s: Recallable state revoked on server %s!\n", __func__,
clp->cl_hostname);
}
static void nfs41_handle_backchannel_fault(struct nfs_client *clp)
{
nfs_expire_all_delegations(clp);
if (test_and_set_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state) == 0)
nfs4_schedule_state_manager(clp);
dprintk("%s: server %s declared a backchannel fault\n", __func__,
clp->cl_hostname);
}
static void nfs41_handle_cb_path_down(struct nfs_client *clp)
{
nfs_expire_all_delegations(clp);
if (test_and_set_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state) == 0)
if (test_and_set_bit(NFS4CLNT_BIND_CONN_TO_SESSION,
&clp->cl_state) == 0)
nfs4_schedule_state_manager(clp);
}
@ -1650,6 +1730,10 @@ void nfs41_handle_sequence_flag_errors(struct nfs_client *clp, u32 flags)
{
if (!flags)
return;
dprintk("%s: \"%s\" (client ID %llx) flags=0x%08x\n",
__func__, clp->cl_hostname, clp->cl_clientid, flags);
if (flags & SEQ4_STATUS_RESTART_RECLAIM_NEEDED)
nfs41_handle_server_reboot(clp);
if (flags & (SEQ4_STATUS_EXPIRED_ALL_STATE_REVOKED |
@ -1659,18 +1743,21 @@ void nfs41_handle_sequence_flag_errors(struct nfs_client *clp, u32 flags)
nfs41_handle_state_revoked(clp);
if (flags & SEQ4_STATUS_RECALLABLE_STATE_REVOKED)
nfs41_handle_recallable_state_revoked(clp);
if (flags & (SEQ4_STATUS_CB_PATH_DOWN |
SEQ4_STATUS_BACKCHANNEL_FAULT |
SEQ4_STATUS_CB_PATH_DOWN_SESSION))
if (flags & SEQ4_STATUS_BACKCHANNEL_FAULT)
nfs41_handle_backchannel_fault(clp);
else if (flags & (SEQ4_STATUS_CB_PATH_DOWN |
SEQ4_STATUS_CB_PATH_DOWN_SESSION))
nfs41_handle_cb_path_down(clp);
}
static int nfs4_reset_session(struct nfs_client *clp)
{
struct rpc_cred *cred;
int status;
nfs4_begin_drain_session(clp);
status = nfs4_proc_destroy_session(clp->cl_session);
cred = nfs4_get_exchange_id_cred(clp);
status = nfs4_proc_destroy_session(clp->cl_session, cred);
if (status && status != -NFS4ERR_BADSESSION &&
status != -NFS4ERR_DEADSESSION) {
status = nfs4_recovery_handle_error(clp, status);
@ -1678,19 +1765,26 @@ static int nfs4_reset_session(struct nfs_client *clp)
}
memset(clp->cl_session->sess_id.data, 0, NFS4_MAX_SESSIONID_LEN);
status = nfs4_proc_create_session(clp);
status = nfs4_proc_create_session(clp, cred);
if (status) {
status = nfs4_recovery_handle_error(clp, status);
dprintk("%s: session reset failed with status %d for server %s!\n",
__func__, status, clp->cl_hostname);
status = nfs4_handle_reclaim_lease_error(clp, status);
goto out;
}
clear_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state);
/* create_session negotiated new slot table */
clear_bit(NFS4CLNT_RECALL_SLOT, &clp->cl_state);
clear_bit(NFS4CLNT_BIND_CONN_TO_SESSION, &clp->cl_state);
dprintk("%s: session reset was successful for server %s!\n",
__func__, clp->cl_hostname);
/* Let the state manager reestablish state */
if (!test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state))
nfs41_setup_state_renewal(clp);
out:
if (cred)
put_rpccred(cred);
return status;
}
@ -1722,37 +1816,41 @@ static int nfs4_recall_slot(struct nfs_client *clp)
return 0;
}
static int nfs4_bind_conn_to_session(struct nfs_client *clp)
{
struct rpc_cred *cred;
int ret;
nfs4_begin_drain_session(clp);
cred = nfs4_get_exchange_id_cred(clp);
ret = nfs4_proc_bind_conn_to_session(clp, cred);
if (cred)
put_rpccred(cred);
clear_bit(NFS4CLNT_BIND_CONN_TO_SESSION, &clp->cl_state);
switch (ret) {
case 0:
dprintk("%s: bind_conn_to_session was successful for server %s!\n",
__func__, clp->cl_hostname);
break;
case -NFS4ERR_DELAY:
ssleep(1);
set_bit(NFS4CLNT_BIND_CONN_TO_SESSION, &clp->cl_state);
break;
default:
return nfs4_recovery_handle_error(clp, ret);
}
return 0;
}
#else /* CONFIG_NFS_V4_1 */
static int nfs4_reset_session(struct nfs_client *clp) { return 0; }
static int nfs4_end_drain_session(struct nfs_client *clp) { return 0; }
static int nfs4_recall_slot(struct nfs_client *clp) { return 0; }
#endif /* CONFIG_NFS_V4_1 */
/* Set NFS4CLNT_LEASE_EXPIRED for all v4.0 errors and for recoverable errors
* on EXCHANGE_ID for v4.1
*/
static void nfs4_set_lease_expired(struct nfs_client *clp, int status)
static int nfs4_bind_conn_to_session(struct nfs_client *clp)
{
switch (status) {
case -NFS4ERR_CLID_INUSE:
case -NFS4ERR_STALE_CLIENTID:
clear_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state);
break;
case -NFS4ERR_DELAY:
case -ETIMEDOUT:
case -EAGAIN:
ssleep(1);
break;
case -EKEYEXPIRED:
nfs4_warn_keyexpired(clp->cl_hostname);
case -NFS4ERR_NOT_SAME: /* FixMe: implement recovery
* in nfs4_exchange_id */
default:
return;
}
set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state);
return 0;
}
#endif /* CONFIG_NFS_V4_1 */
static void nfs4_state_manager(struct nfs_client *clp)
{
@ -1760,19 +1858,21 @@ static void nfs4_state_manager(struct nfs_client *clp)
/* Ensure exclusive access to NFSv4 state */
do {
if (test_bit(NFS4CLNT_PURGE_STATE, &clp->cl_state)) {
status = nfs4_reclaim_lease(clp);
if (status < 0)
goto out_error;
clear_bit(NFS4CLNT_PURGE_STATE, &clp->cl_state);
set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state);
}
if (test_and_clear_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state)) {
/* We're going to have to re-establish a clientid */
status = nfs4_reclaim_lease(clp);
if (status) {
nfs4_set_lease_expired(clp, status);
if (test_bit(NFS4CLNT_LEASE_EXPIRED,
&clp->cl_state))
continue;
if (clp->cl_cons_state ==
NFS_CS_SESSION_INITING)
nfs_mark_client_ready(clp, status);
if (status < 0)
goto out_error;
}
if (test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state))
continue;
clear_bit(NFS4CLNT_CHECK_LEASE, &clp->cl_state);
if (test_and_clear_bit(NFS4CLNT_SERVER_SCOPE_MISMATCH,
@ -1803,6 +1903,15 @@ static void nfs4_state_manager(struct nfs_client *clp)
goto out_error;
}
/* Send BIND_CONN_TO_SESSION */
if (test_and_clear_bit(NFS4CLNT_BIND_CONN_TO_SESSION,
&clp->cl_state) && nfs4_has_session(clp)) {
status = nfs4_bind_conn_to_session(clp);
if (status < 0)
goto out_error;
continue;
}
/* First recover reboot state... */
if (test_bit(NFS4CLNT_RECLAIM_REBOOT, &clp->cl_state)) {
status = nfs4_do_reclaim(clp,

405
fs/nfs/nfs4xdr.c
View File

@ -53,9 +53,11 @@
#include <linux/nfs4.h>
#include <linux/nfs_fs.h>
#include <linux/nfs_idmap.h>
#include "nfs4_fs.h"
#include "internal.h"
#include "pnfs.h"
#include "netns.h"
#define NFSDBG_FACILITY NFSDBG_XDR
@ -99,9 +101,12 @@ static int nfs4_stat_to_errno(int);
#define nfs4_path_maxsz (1 + ((3 + NFS4_MAXPATHLEN) >> 2))
#define nfs4_owner_maxsz (1 + XDR_QUADLEN(IDMAP_NAMESZ))
#define nfs4_group_maxsz (1 + XDR_QUADLEN(IDMAP_NAMESZ))
/* We support only one layout type per file system */
#define decode_mdsthreshold_maxsz (1 + 1 + nfs4_fattr_bitmap_maxsz + 1 + 8)
/* This is based on getfattr, which uses the most attributes: */
#define nfs4_fattr_value_maxsz (1 + (1 + 2 + 2 + 4 + 2 + 1 + 1 + 2 + 2 + \
3 + 3 + 3 + nfs4_owner_maxsz + nfs4_group_maxsz))
3 + 3 + 3 + nfs4_owner_maxsz + \
nfs4_group_maxsz + decode_mdsthreshold_maxsz))
#define nfs4_fattr_maxsz (nfs4_fattr_bitmap_maxsz + \
nfs4_fattr_value_maxsz)
#define decode_getattr_maxsz (op_decode_hdr_maxsz + nfs4_fattr_maxsz)
@ -321,8 +326,20 @@ static int nfs4_stat_to_errno(int);
1 /* csr_flags */ + \
decode_channel_attrs_maxsz + \
decode_channel_attrs_maxsz)
#define encode_bind_conn_to_session_maxsz (op_encode_hdr_maxsz + \
/* bctsa_sessid */ \
XDR_QUADLEN(NFS4_MAX_SESSIONID_LEN) + \
1 /* bctsa_dir */ + \
1 /* bctsa_use_conn_in_rdma_mode */)
#define decode_bind_conn_to_session_maxsz (op_decode_hdr_maxsz + \
/* bctsr_sessid */ \
XDR_QUADLEN(NFS4_MAX_SESSIONID_LEN) + \
1 /* bctsr_dir */ + \
1 /* bctsr_use_conn_in_rdma_mode */)
#define encode_destroy_session_maxsz (op_encode_hdr_maxsz + 4)
#define decode_destroy_session_maxsz (op_decode_hdr_maxsz)
#define encode_destroy_clientid_maxsz (op_encode_hdr_maxsz + 2)
#define decode_destroy_clientid_maxsz (op_decode_hdr_maxsz)
#define encode_sequence_maxsz (op_encode_hdr_maxsz + \
XDR_QUADLEN(NFS4_MAX_SESSIONID_LEN) + 4)
#define decode_sequence_maxsz (op_decode_hdr_maxsz + \
@ -421,30 +438,22 @@ static int nfs4_stat_to_errno(int);
#define NFS4_enc_commit_sz (compound_encode_hdr_maxsz + \
encode_sequence_maxsz + \
encode_putfh_maxsz + \
encode_commit_maxsz + \
encode_getattr_maxsz)
encode_commit_maxsz)
#define NFS4_dec_commit_sz (compound_decode_hdr_maxsz + \
decode_sequence_maxsz + \
decode_putfh_maxsz + \
decode_commit_maxsz + \
decode_getattr_maxsz)
decode_commit_maxsz)
#define NFS4_enc_open_sz (compound_encode_hdr_maxsz + \
encode_sequence_maxsz + \
encode_putfh_maxsz + \
encode_savefh_maxsz + \
encode_open_maxsz + \
encode_getfh_maxsz + \
encode_getattr_maxsz + \
encode_restorefh_maxsz + \
encode_getattr_maxsz)
#define NFS4_dec_open_sz (compound_decode_hdr_maxsz + \
decode_sequence_maxsz + \
decode_putfh_maxsz + \
decode_savefh_maxsz + \
decode_open_maxsz + \
decode_getfh_maxsz + \
decode_getattr_maxsz + \
decode_restorefh_maxsz + \
decode_getattr_maxsz)
#define NFS4_enc_open_confirm_sz \
(compound_encode_hdr_maxsz + \
@ -595,47 +604,37 @@ static int nfs4_stat_to_errno(int);
#define NFS4_enc_remove_sz (compound_encode_hdr_maxsz + \
encode_sequence_maxsz + \
encode_putfh_maxsz + \
encode_remove_maxsz + \
encode_getattr_maxsz)
encode_remove_maxsz)
#define NFS4_dec_remove_sz (compound_decode_hdr_maxsz + \
decode_sequence_maxsz + \
decode_putfh_maxsz + \
decode_remove_maxsz + \
decode_getattr_maxsz)
decode_remove_maxsz)
#define NFS4_enc_rename_sz (compound_encode_hdr_maxsz + \
encode_sequence_maxsz + \
encode_putfh_maxsz + \
encode_savefh_maxsz + \
encode_putfh_maxsz + \
encode_rename_maxsz + \
encode_getattr_maxsz + \
encode_restorefh_maxsz + \
encode_getattr_maxsz)
encode_rename_maxsz)
#define NFS4_dec_rename_sz (compound_decode_hdr_maxsz + \
decode_sequence_maxsz + \
decode_putfh_maxsz + \
decode_savefh_maxsz + \
decode_putfh_maxsz + \
decode_rename_maxsz + \
decode_getattr_maxsz + \
decode_restorefh_maxsz + \
decode_getattr_maxsz)
decode_rename_maxsz)
#define NFS4_enc_link_sz (compound_encode_hdr_maxsz + \
encode_sequence_maxsz + \
encode_putfh_maxsz + \
encode_savefh_maxsz + \
encode_putfh_maxsz + \
encode_link_maxsz + \
decode_getattr_maxsz + \
encode_restorefh_maxsz + \
decode_getattr_maxsz)
encode_getattr_maxsz)
#define NFS4_dec_link_sz (compound_decode_hdr_maxsz + \
decode_sequence_maxsz + \
decode_putfh_maxsz + \
decode_savefh_maxsz + \
decode_putfh_maxsz + \
decode_link_maxsz + \
decode_getattr_maxsz + \
decode_restorefh_maxsz + \
decode_getattr_maxsz)
#define NFS4_enc_symlink_sz (compound_encode_hdr_maxsz + \
@ -653,20 +652,14 @@ static int nfs4_stat_to_errno(int);
#define NFS4_enc_create_sz (compound_encode_hdr_maxsz + \
encode_sequence_maxsz + \
encode_putfh_maxsz + \
encode_savefh_maxsz + \
encode_create_maxsz + \
encode_getfh_maxsz + \
encode_getattr_maxsz + \
encode_restorefh_maxsz + \
encode_getattr_maxsz)
#define NFS4_dec_create_sz (compound_decode_hdr_maxsz + \
decode_sequence_maxsz + \
decode_putfh_maxsz + \
decode_savefh_maxsz + \
decode_create_maxsz + \
decode_getfh_maxsz + \
decode_getattr_maxsz + \
decode_restorefh_maxsz + \
decode_getattr_maxsz)
#define NFS4_enc_pathconf_sz (compound_encode_hdr_maxsz + \
encode_sequence_maxsz + \
@ -738,6 +731,12 @@ static int nfs4_stat_to_errno(int);
decode_putfh_maxsz + \
decode_secinfo_maxsz)
#if defined(CONFIG_NFS_V4_1)
#define NFS4_enc_bind_conn_to_session_sz \
(compound_encode_hdr_maxsz + \
encode_bind_conn_to_session_maxsz)
#define NFS4_dec_bind_conn_to_session_sz \
(compound_decode_hdr_maxsz + \
decode_bind_conn_to_session_maxsz)
#define NFS4_enc_exchange_id_sz \
(compound_encode_hdr_maxsz + \
encode_exchange_id_maxsz)
@ -754,6 +753,10 @@ static int nfs4_stat_to_errno(int);
encode_destroy_session_maxsz)
#define NFS4_dec_destroy_session_sz (compound_decode_hdr_maxsz + \
decode_destroy_session_maxsz)
#define NFS4_enc_destroy_clientid_sz (compound_encode_hdr_maxsz + \
encode_destroy_clientid_maxsz)
#define NFS4_dec_destroy_clientid_sz (compound_decode_hdr_maxsz + \
decode_destroy_clientid_maxsz)
#define NFS4_enc_sequence_sz \
(compound_decode_hdr_maxsz + \
encode_sequence_maxsz)
@ -1103,7 +1106,7 @@ static void encode_close(struct xdr_stream *xdr, const struct nfs_closeargs *arg
encode_nfs4_stateid(xdr, arg->stateid);
}
static void encode_commit(struct xdr_stream *xdr, const struct nfs_writeargs *args, struct compound_hdr *hdr)
static void encode_commit(struct xdr_stream *xdr, const struct nfs_commitargs *args, struct compound_hdr *hdr)
{
__be32 *p;
@ -1194,6 +1197,16 @@ static void encode_getfattr(struct xdr_stream *xdr, const u32* bitmask, struct c
bitmask[1] & nfs4_fattr_bitmap[1], hdr);
}
static void encode_getfattr_open(struct xdr_stream *xdr, const u32 *bitmask,
struct compound_hdr *hdr)
{
encode_getattr_three(xdr,
bitmask[0] & nfs4_fattr_bitmap[0],
bitmask[1] & nfs4_fattr_bitmap[1],
bitmask[2] & FATTR4_WORD2_MDSTHRESHOLD,
hdr);
}
static void encode_fsinfo(struct xdr_stream *xdr, const u32* bitmask, struct compound_hdr *hdr)
{
encode_getattr_three(xdr,
@ -1678,6 +1691,20 @@ static void encode_secinfo(struct xdr_stream *xdr, const struct qstr *name, stru
#if defined(CONFIG_NFS_V4_1)
/* NFSv4.1 operations */
static void encode_bind_conn_to_session(struct xdr_stream *xdr,
struct nfs4_session *session,
struct compound_hdr *hdr)
{
__be32 *p;
encode_op_hdr(xdr, OP_BIND_CONN_TO_SESSION,
decode_bind_conn_to_session_maxsz, hdr);
encode_opaque_fixed(xdr, session->sess_id.data, NFS4_MAX_SESSIONID_LEN);
p = xdr_reserve_space(xdr, 8);
*p++ = cpu_to_be32(NFS4_CDFC4_BACK_OR_BOTH);
*p = 0; /* use_conn_in_rdma_mode = False */
}
static void encode_exchange_id(struct xdr_stream *xdr,
struct nfs41_exchange_id_args *args,
struct compound_hdr *hdr)
@ -1726,6 +1753,7 @@ static void encode_create_session(struct xdr_stream *xdr,
char machine_name[NFS4_MAX_MACHINE_NAME_LEN];
uint32_t len;
struct nfs_client *clp = args->client;
struct nfs_net *nn = net_generic(clp->cl_net, nfs_net_id);
u32 max_resp_sz_cached;
/*
@ -1767,7 +1795,7 @@ static void encode_create_session(struct xdr_stream *xdr,
*p++ = cpu_to_be32(RPC_AUTH_UNIX); /* auth_sys */
/* authsys_parms rfc1831 */
*p++ = cpu_to_be32((u32)clp->cl_boot_time.tv_nsec); /* stamp */
*p++ = (__be32)nn->boot_time.tv_nsec; /* stamp */
p = xdr_encode_opaque(p, machine_name, len);
*p++ = cpu_to_be32(0); /* UID */
*p++ = cpu_to_be32(0); /* GID */
@ -1782,6 +1810,14 @@ static void encode_destroy_session(struct xdr_stream *xdr,
encode_opaque_fixed(xdr, session->sess_id.data, NFS4_MAX_SESSIONID_LEN);
}
static void encode_destroy_clientid(struct xdr_stream *xdr,
uint64_t clientid,
struct compound_hdr *hdr)
{
encode_op_hdr(xdr, OP_DESTROY_CLIENTID, decode_destroy_clientid_maxsz, hdr);
encode_uint64(xdr, clientid);
}
static void encode_reclaim_complete(struct xdr_stream *xdr,
struct nfs41_reclaim_complete_args *args,
struct compound_hdr *hdr)
@ -2064,7 +2100,6 @@ static void nfs4_xdr_enc_remove(struct rpc_rqst *req, struct xdr_stream *xdr,
encode_sequence(xdr, &args->seq_args, &hdr);
encode_putfh(xdr, args->fh, &hdr);
encode_remove(xdr, &args->name, &hdr);
encode_getfattr(xdr, args->bitmask, &hdr);
encode_nops(&hdr);
}
@ -2084,9 +2119,6 @@ static void nfs4_xdr_enc_rename(struct rpc_rqst *req, struct xdr_stream *xdr,
encode_savefh(xdr, &hdr);
encode_putfh(xdr, args->new_dir, &hdr);
encode_rename(xdr, args->old_name, args->new_name, &hdr);
encode_getfattr(xdr, args->bitmask, &hdr);
encode_restorefh(xdr, &hdr);
encode_getfattr(xdr, args->bitmask, &hdr);
encode_nops(&hdr);
}
@ -2106,7 +2138,6 @@ static void nfs4_xdr_enc_link(struct rpc_rqst *req, struct xdr_stream *xdr,
encode_savefh(xdr, &hdr);
encode_putfh(xdr, args->dir_fh, &hdr);
encode_link(xdr, args->name, &hdr);
encode_getfattr(xdr, args->bitmask, &hdr);
encode_restorefh(xdr, &hdr);
encode_getfattr(xdr, args->bitmask, &hdr);
encode_nops(&hdr);
@ -2125,12 +2156,9 @@ static void nfs4_xdr_enc_create(struct rpc_rqst *req, struct xdr_stream *xdr,
encode_compound_hdr(xdr, req, &hdr);
encode_sequence(xdr, &args->seq_args, &hdr);
encode_putfh(xdr, args->dir_fh, &hdr);
encode_savefh(xdr, &hdr);
encode_create(xdr, args, &hdr);
encode_getfh(xdr, &hdr);
encode_getfattr(xdr, args->bitmask, &hdr);
encode_restorefh(xdr, &hdr);
encode_getfattr(xdr, args->bitmask, &hdr);
encode_nops(&hdr);
}
@ -2191,12 +2219,9 @@ static void nfs4_xdr_enc_open(struct rpc_rqst *req, struct xdr_stream *xdr,
encode_compound_hdr(xdr, req, &hdr);
encode_sequence(xdr, &args->seq_args, &hdr);
encode_putfh(xdr, args->fh, &hdr);
encode_savefh(xdr, &hdr);
encode_open(xdr, args, &hdr);
encode_getfh(xdr, &hdr);
encode_getfattr(xdr, args->bitmask, &hdr);
encode_restorefh(xdr, &hdr);
encode_getfattr(xdr, args->dir_bitmask, &hdr);
encode_getfattr_open(xdr, args->bitmask, &hdr);
encode_nops(&hdr);
}
@ -2448,7 +2473,7 @@ static void nfs4_xdr_enc_write(struct rpc_rqst *req, struct xdr_stream *xdr,
* a COMMIT request
*/
static void nfs4_xdr_enc_commit(struct rpc_rqst *req, struct xdr_stream *xdr,
struct nfs_writeargs *args)
struct nfs_commitargs *args)
{
struct compound_hdr hdr = {
.minorversion = nfs4_xdr_minorversion(&args->seq_args),
@ -2458,8 +2483,6 @@ static void nfs4_xdr_enc_commit(struct rpc_rqst *req, struct xdr_stream *xdr,
encode_sequence(xdr, &args->seq_args, &hdr);
encode_putfh(xdr, args->fh, &hdr);
encode_commit(xdr, args, &hdr);
if (args->bitmask)
encode_getfattr(xdr, args->bitmask, &hdr);
encode_nops(&hdr);
}
@ -2602,8 +2625,8 @@ static void nfs4_xdr_enc_delegreturn(struct rpc_rqst *req,
encode_compound_hdr(xdr, req, &hdr);
encode_sequence(xdr, &args->seq_args, &hdr);
encode_putfh(xdr, args->fhandle, &hdr);
encode_delegreturn(xdr, args->stateid, &hdr);
encode_getfattr(xdr, args->bitmask, &hdr);
encode_delegreturn(xdr, args->stateid, &hdr);
encode_nops(&hdr);
}
@ -2650,6 +2673,22 @@ static void nfs4_xdr_enc_secinfo(struct rpc_rqst *req,
}
#if defined(CONFIG_NFS_V4_1)
/*
* BIND_CONN_TO_SESSION request
*/
static void nfs4_xdr_enc_bind_conn_to_session(struct rpc_rqst *req,
struct xdr_stream *xdr,
struct nfs_client *clp)
{
struct compound_hdr hdr = {
.minorversion = clp->cl_mvops->minor_version,
};
encode_compound_hdr(xdr, req, &hdr);
encode_bind_conn_to_session(xdr, clp->cl_session, &hdr);
encode_nops(&hdr);
}
/*
* EXCHANGE_ID request
*/
@ -2698,6 +2737,22 @@ static void nfs4_xdr_enc_destroy_session(struct rpc_rqst *req,
encode_nops(&hdr);
}
/*
* a DESTROY_CLIENTID request
*/
static void nfs4_xdr_enc_destroy_clientid(struct rpc_rqst *req,
struct xdr_stream *xdr,
struct nfs_client *clp)
{
struct compound_hdr hdr = {
.minorversion = clp->cl_mvops->minor_version,
};
encode_compound_hdr(xdr, req, &hdr);
encode_destroy_clientid(xdr, clp->cl_clientid, &hdr);
encode_nops(&hdr);
}
/*
* a SEQUENCE request
*/
@ -4102,7 +4157,7 @@ static int decode_verifier(struct xdr_stream *xdr, void *verifier)
return decode_opaque_fixed(xdr, verifier, NFS4_VERIFIER_SIZE);
}
static int decode_commit(struct xdr_stream *xdr, struct nfs_writeres *res)
static int decode_commit(struct xdr_stream *xdr, struct nfs_commitres *res)
{
int status;
@ -4220,6 +4275,110 @@ xdr_error:
return status;
}
static int decode_threshold_hint(struct xdr_stream *xdr,
uint32_t *bitmap,
uint64_t *res,
uint32_t hint_bit)
{
__be32 *p;
*res = 0;
if (likely(bitmap[0] & hint_bit)) {
p = xdr_inline_decode(xdr, 8);
if (unlikely(!p))
goto out_overflow;
xdr_decode_hyper(p, res);
}
return 0;
out_overflow:
print_overflow_msg(__func__, xdr);
return -EIO;
}
static int decode_first_threshold_item4(struct xdr_stream *xdr,
struct nfs4_threshold *res)
{
__be32 *p, *savep;
uint32_t bitmap[3] = {0,}, attrlen;
int status;
/* layout type */
p = xdr_inline_decode(xdr, 4);
if (unlikely(!p)) {
print_overflow_msg(__func__, xdr);
return -EIO;
}
res->l_type = be32_to_cpup(p);
/* thi_hintset bitmap */
status = decode_attr_bitmap(xdr, bitmap);
if (status < 0)
goto xdr_error;
/* thi_hintlist length */
status = decode_attr_length(xdr, &attrlen, &savep);
if (status < 0)
goto xdr_error;
/* thi_hintlist */
status = decode_threshold_hint(xdr, bitmap, &res->rd_sz, THRESHOLD_RD);
if (status < 0)
goto xdr_error;
status = decode_threshold_hint(xdr, bitmap, &res->wr_sz, THRESHOLD_WR);
if (status < 0)
goto xdr_error;
status = decode_threshold_hint(xdr, bitmap, &res->rd_io_sz,
THRESHOLD_RD_IO);
if (status < 0)
goto xdr_error;
status = decode_threshold_hint(xdr, bitmap, &res->wr_io_sz,
THRESHOLD_WR_IO);
if (status < 0)
goto xdr_error;
status = verify_attr_len(xdr, savep, attrlen);
res->bm = bitmap[0];
dprintk("%s bm=0x%x rd_sz=%llu wr_sz=%llu rd_io=%llu wr_io=%llu\n",
__func__, res->bm, res->rd_sz, res->wr_sz, res->rd_io_sz,
res->wr_io_sz);
xdr_error:
dprintk("%s ret=%d!\n", __func__, status);
return status;
}
/*
* Thresholds on pNFS direct I/O vrs MDS I/O
*/
static int decode_attr_mdsthreshold(struct xdr_stream *xdr,
uint32_t *bitmap,
struct nfs4_threshold *res)
{
__be32 *p;
int status = 0;
uint32_t num;
if (unlikely(bitmap[2] & (FATTR4_WORD2_MDSTHRESHOLD - 1U)))
return -EIO;
if (likely(bitmap[2] & FATTR4_WORD2_MDSTHRESHOLD)) {
p = xdr_inline_decode(xdr, 4);
if (unlikely(!p))
goto out_overflow;
num = be32_to_cpup(p);
if (num == 0)
return 0;
if (num > 1)
printk(KERN_INFO "%s: Warning: Multiple pNFS layout "
"drivers per filesystem not supported\n",
__func__);
status = decode_first_threshold_item4(xdr, res);
}
return status;
out_overflow:
print_overflow_msg(__func__, xdr);
return -EIO;
}
static int decode_getfattr_attrs(struct xdr_stream *xdr, uint32_t *bitmap,
struct nfs_fattr *fattr, struct nfs_fh *fh,
struct nfs4_fs_locations *fs_loc,
@ -4326,6 +4485,10 @@ static int decode_getfattr_attrs(struct xdr_stream *xdr, uint32_t *bitmap,
goto xdr_error;
fattr->valid |= status;
status = decode_attr_mdsthreshold(xdr, bitmap, fattr->mdsthreshold);
if (status < 0)
goto xdr_error;
xdr_error:
dprintk("%s: xdr returned %d\n", __func__, -status);
return status;
@ -5156,7 +5319,6 @@ static int decode_exchange_id(struct xdr_stream *xdr,
uint32_t dummy;
char *dummy_str;
int status;
struct nfs_client *clp = res->client;
uint32_t impl_id_count;
status = decode_op_hdr(xdr, OP_EXCHANGE_ID);
@ -5166,36 +5328,39 @@ static int decode_exchange_id(struct xdr_stream *xdr,
p = xdr_inline_decode(xdr, 8);
if (unlikely(!p))
goto out_overflow;
xdr_decode_hyper(p, &clp->cl_clientid);
xdr_decode_hyper(p, &res->clientid);
p = xdr_inline_decode(xdr, 12);
if (unlikely(!p))
goto out_overflow;
clp->cl_seqid = be32_to_cpup(p++);
clp->cl_exchange_flags = be32_to_cpup(p++);
res->seqid = be32_to_cpup(p++);
res->flags = be32_to_cpup(p++);
/* We ask for SP4_NONE */
dummy = be32_to_cpup(p);
if (dummy != SP4_NONE)
return -EIO;
/* Throw away minor_id */
/* server_owner4.so_minor_id */
p = xdr_inline_decode(xdr, 8);
if (unlikely(!p))
goto out_overflow;
p = xdr_decode_hyper(p, &res->server_owner->minor_id);
/* Throw away Major id */
/* server_owner4.so_major_id */
status = decode_opaque_inline(xdr, &dummy, &dummy_str);
if (unlikely(status))
return status;
/* Save server_scope */
status = decode_opaque_inline(xdr, &dummy, &dummy_str);
if (unlikely(status))
return status;
if (unlikely(dummy > NFS4_OPAQUE_LIMIT))
return -EIO;
memcpy(res->server_owner->major_id, dummy_str, dummy);
res->server_owner->major_id_sz = dummy;
/* server_scope4 */
status = decode_opaque_inline(xdr, &dummy, &dummy_str);
if (unlikely(status))
return status;
if (unlikely(dummy > NFS4_OPAQUE_LIMIT))
return -EIO;
memcpy(res->server_scope->server_scope, dummy_str, dummy);
res->server_scope->server_scope_sz = dummy;
@ -5276,6 +5441,37 @@ static int decode_sessionid(struct xdr_stream *xdr, struct nfs4_sessionid *sid)
return decode_opaque_fixed(xdr, sid->data, NFS4_MAX_SESSIONID_LEN);
}
static int decode_bind_conn_to_session(struct xdr_stream *xdr,
struct nfs41_bind_conn_to_session_res *res)
{
__be32 *p;
int status;
status = decode_op_hdr(xdr, OP_BIND_CONN_TO_SESSION);
if (!status)
status = decode_sessionid(xdr, &res->session->sess_id);
if (unlikely(status))
return status;
/* dir flags, rdma mode bool */
p = xdr_inline_decode(xdr, 8);
if (unlikely(!p))
goto out_overflow;
res->dir = be32_to_cpup(p++);
if (res->dir == 0 || res->dir > NFS4_CDFS4_BOTH)
return -EIO;
if (be32_to_cpup(p) == 0)
res->use_conn_in_rdma_mode = false;
else
res->use_conn_in_rdma_mode = true;
return 0;
out_overflow:
print_overflow_msg(__func__, xdr);
return -EIO;
}
static int decode_create_session(struct xdr_stream *xdr,
struct nfs41_create_session_res *res)
{
@ -5312,6 +5508,11 @@ static int decode_destroy_session(struct xdr_stream *xdr, void *dummy)
return decode_op_hdr(xdr, OP_DESTROY_SESSION);
}
static int decode_destroy_clientid(struct xdr_stream *xdr, void *dummy)
{
return decode_op_hdr(xdr, OP_DESTROY_CLIENTID);
}
static int decode_reclaim_complete(struct xdr_stream *xdr, void *dummy)
{
return decode_op_hdr(xdr, OP_RECLAIM_COMPLETE);
@ -5800,9 +6001,6 @@ static int nfs4_xdr_dec_remove(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
if (status)
goto out;
status = decode_remove(xdr, &res->cinfo);
if (status)
goto out;
decode_getfattr(xdr, res->dir_attr, res->server);
out:
return status;
}
@ -5832,15 +6030,6 @@ static int nfs4_xdr_dec_rename(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
if (status)
goto out;
status = decode_rename(xdr, &res->old_cinfo, &res->new_cinfo);
if (status)
goto out;
/* Current FH is target directory */
if (decode_getfattr(xdr, res->new_fattr, res->server))
goto out;
status = decode_restorefh(xdr);
if (status)
goto out;
decode_getfattr(xdr, res->old_fattr, res->server);
out:
return status;
}
@ -5876,8 +6065,6 @@ static int nfs4_xdr_dec_link(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
* Note order: OP_LINK leaves the directory as the current
* filehandle.
*/
if (decode_getfattr(xdr, res->dir_attr, res->server))
goto out;
status = decode_restorefh(xdr);
if (status)
goto out;
@ -5902,9 +6089,6 @@ static int nfs4_xdr_dec_create(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
if (status)
goto out;
status = decode_putfh(xdr);
if (status)
goto out;
status = decode_savefh(xdr);
if (status)
goto out;
status = decode_create(xdr, &res->dir_cinfo);
@ -5913,12 +6097,7 @@ static int nfs4_xdr_dec_create(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
status = decode_getfh(xdr, res->fh);
if (status)
goto out;
if (decode_getfattr(xdr, res->fattr, res->server))
goto out;
status = decode_restorefh(xdr);
if (status)
goto out;
decode_getfattr(xdr, res->dir_fattr, res->server);
decode_getfattr(xdr, res->fattr, res->server);
out:
return status;
}
@ -6073,9 +6252,6 @@ static int nfs4_xdr_dec_open(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
if (status)
goto out;
status = decode_putfh(xdr);
if (status)
goto out;
status = decode_savefh(xdr);
if (status)
goto out;
status = decode_open(xdr, res);
@ -6083,11 +6259,7 @@ static int nfs4_xdr_dec_open(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
goto out;
if (decode_getfh(xdr, &res->fh) != 0)
goto out;
if (decode_getfattr(xdr, res->f_attr, res->server) != 0)
goto out;
if (decode_restorefh(xdr) != 0)
goto out;
decode_getfattr(xdr, res->dir_attr, res->server);
decode_getfattr(xdr, res->f_attr, res->server);
out:
return status;
}
@ -6353,7 +6525,7 @@ out:
* Decode COMMIT response
*/
static int nfs4_xdr_dec_commit(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
struct nfs_writeres *res)
struct nfs_commitres *res)
{
struct compound_hdr hdr;
int status;
@ -6368,10 +6540,6 @@ static int nfs4_xdr_dec_commit(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
if (status)
goto out;
status = decode_commit(xdr, res);
if (status)
goto out;
if (res->fattr)
decode_getfattr(xdr, res->fattr, res->server);
out:
return status;
}
@ -6527,10 +6695,10 @@ static int nfs4_xdr_dec_delegreturn(struct rpc_rqst *rqstp,
status = decode_putfh(xdr);
if (status != 0)
goto out;
status = decode_delegreturn(xdr);
status = decode_getfattr(xdr, res->fattr, res->server);
if (status != 0)
goto out;
decode_getfattr(xdr, res->fattr, res->server);
status = decode_delegreturn(xdr);
out:
return status;
}
@ -6590,6 +6758,22 @@ out:
}
#if defined(CONFIG_NFS_V4_1)
/*
* Decode BIND_CONN_TO_SESSION response
*/
static int nfs4_xdr_dec_bind_conn_to_session(struct rpc_rqst *rqstp,
struct xdr_stream *xdr,
void *res)
{
struct compound_hdr hdr;
int status;
status = decode_compound_hdr(xdr, &hdr);
if (!status)
status = decode_bind_conn_to_session(xdr, res);
return status;
}
/*
* Decode EXCHANGE_ID response
*/
@ -6638,6 +6822,22 @@ static int nfs4_xdr_dec_destroy_session(struct rpc_rqst *rqstp,
return status;
}
/*
* Decode DESTROY_CLIENTID response
*/
static int nfs4_xdr_dec_destroy_clientid(struct rpc_rqst *rqstp,
struct xdr_stream *xdr,
void *res)
{
struct compound_hdr hdr;
int status;
status = decode_compound_hdr(xdr, &hdr);
if (!status)
status = decode_destroy_clientid(xdr, res);
return status;
}
/*
* Decode SEQUENCE response
*/
@ -7085,6 +7285,9 @@ struct rpc_procinfo nfs4_procedures[] = {
PROC(TEST_STATEID, enc_test_stateid, dec_test_stateid),
PROC(FREE_STATEID, enc_free_stateid, dec_free_stateid),
PROC(GETDEVICELIST, enc_getdevicelist, dec_getdevicelist),
PROC(BIND_CONN_TO_SESSION,
enc_bind_conn_to_session, dec_bind_conn_to_session),
PROC(DESTROY_CLIENTID, enc_destroy_clientid, dec_destroy_clientid),
#endif /* CONFIG_NFS_V4_1 */
};

18
fs/nfs/objlayout/objio_osd.c
View File

@ -211,7 +211,7 @@ static void copy_single_comp(struct ore_components *oc, unsigned c,
memcpy(ocomp->cred, src_comp->oc_cap.cred, sizeof(ocomp->cred));
}
int __alloc_objio_seg(unsigned numdevs, gfp_t gfp_flags,
static int __alloc_objio_seg(unsigned numdevs, gfp_t gfp_flags,
struct objio_segment **pseg)
{
/* This is the in memory structure of the objio_segment
@ -440,11 +440,12 @@ static void _read_done(struct ore_io_state *ios, void *private)
int objio_read_pagelist(struct nfs_read_data *rdata)
{
struct nfs_pgio_header *hdr = rdata->header;
struct objio_state *objios;
int ret;
ret = objio_alloc_io_state(NFS_I(rdata->inode)->layout, true,
rdata->lseg, rdata->args.pages, rdata->args.pgbase,
ret = objio_alloc_io_state(NFS_I(hdr->inode)->layout, true,
hdr->lseg, rdata->args.pages, rdata->args.pgbase,
rdata->args.offset, rdata->args.count, rdata,
GFP_KERNEL, &objios);
if (unlikely(ret))
@ -483,12 +484,12 @@ static struct page *__r4w_get_page(void *priv, u64 offset, bool *uptodate)
{
struct objio_state *objios = priv;
struct nfs_write_data *wdata = objios->oir.rpcdata;
struct address_space *mapping = wdata->header->inode->i_mapping;
pgoff_t index = offset / PAGE_SIZE;
struct page *page = find_get_page(wdata->inode->i_mapping, index);
struct page *page = find_get_page(mapping, index);
if (!page) {
page = find_or_create_page(wdata->inode->i_mapping,
index, GFP_NOFS);
page = find_or_create_page(mapping, index, GFP_NOFS);
if (unlikely(!page)) {
dprintk("%s: grab_cache_page Failed index=0x%lx\n",
__func__, index);
@ -518,11 +519,12 @@ static const struct _ore_r4w_op _r4w_op = {
int objio_write_pagelist(struct nfs_write_data *wdata, int how)
{
struct nfs_pgio_header *hdr = wdata->header;
struct objio_state *objios;
int ret;
ret = objio_alloc_io_state(NFS_I(wdata->inode)->layout, false,
wdata->lseg, wdata->args.pages, wdata->args.pgbase,
ret = objio_alloc_io_state(NFS_I(hdr->inode)->layout, false,
hdr->lseg, wdata->args.pages, wdata->args.pgbase,
wdata->args.offset, wdata->args.count, wdata, GFP_NOFS,
&objios);
if (unlikely(ret))

19
fs/nfs/objlayout/objlayout.c
View File

@ -258,7 +258,7 @@ objlayout_read_done(struct objlayout_io_res *oir, ssize_t status, bool sync)
if (status >= 0)
rdata->res.count = status;
else
rdata->pnfs_error = status;
rdata->header->pnfs_error = status;
objlayout_iodone(oir);
/* must not use oir after this point */
@ -279,12 +279,14 @@ objlayout_read_done(struct objlayout_io_res *oir, ssize_t status, bool sync)
enum pnfs_try_status
objlayout_read_pagelist(struct nfs_read_data *rdata)
{
struct nfs_pgio_header *hdr = rdata->header;
struct inode *inode = hdr->inode;
loff_t offset = rdata->args.offset;
size_t count = rdata->args.count;
int err;
loff_t eof;
eof = i_size_read(rdata->inode);
eof = i_size_read(inode);
if (unlikely(offset + count > eof)) {
if (offset >= eof) {
err = 0;
@ -297,17 +299,17 @@ objlayout_read_pagelist(struct nfs_read_data *rdata)
}
rdata->res.eof = (offset + count) >= eof;
_fix_verify_io_params(rdata->lseg, &rdata->args.pages,
_fix_verify_io_params(hdr->lseg, &rdata->args.pages,
&rdata->args.pgbase,
rdata->args.offset, rdata->args.count);
dprintk("%s: inode(%lx) offset 0x%llx count 0x%Zx eof=%d\n",
__func__, rdata->inode->i_ino, offset, count, rdata->res.eof);
__func__, inode->i_ino, offset, count, rdata->res.eof);
err = objio_read_pagelist(rdata);
out:
if (unlikely(err)) {
rdata->pnfs_error = err;
hdr->pnfs_error = err;
dprintk("%s: Returned Error %d\n", __func__, err);
return PNFS_NOT_ATTEMPTED;
}
@ -340,7 +342,7 @@ objlayout_write_done(struct objlayout_io_res *oir, ssize_t status, bool sync)
wdata->res.count = status;
wdata->verf.committed = oir->committed;
} else {
wdata->pnfs_error = status;
wdata->header->pnfs_error = status;
}
objlayout_iodone(oir);
/* must not use oir after this point */
@ -363,15 +365,16 @@ enum pnfs_try_status
objlayout_write_pagelist(struct nfs_write_data *wdata,
int how)
{
struct nfs_pgio_header *hdr = wdata->header;
int err;
_fix_verify_io_params(wdata->lseg, &wdata->args.pages,
_fix_verify_io_params(hdr->lseg, &wdata->args.pages,
&wdata->args.pgbase,
wdata->args.offset, wdata->args.count);
err = objio_write_pagelist(wdata, how);
if (unlikely(err)) {
wdata->pnfs_error = err;
hdr->pnfs_error = err;
dprintk("%s: Returned Error %d\n", __func__, err);
return PNFS_NOT_ATTEMPTED;
}

61
fs/nfs/pagelist.c
View File

@ -26,6 +26,47 @@
static struct kmem_cache *nfs_page_cachep;
bool nfs_pgarray_set(struct nfs_page_array *p, unsigned int pagecount)
{
p->npages = pagecount;
if (pagecount <= ARRAY_SIZE(p->page_array))
p->pagevec = p->page_array;
else {
p->pagevec = kcalloc(pagecount, sizeof(struct page *), GFP_KERNEL);
if (!p->pagevec)
p->npages = 0;
}
return p->pagevec != NULL;
}
void nfs_pgheader_init(struct nfs_pageio_descriptor *desc,
struct nfs_pgio_header *hdr,
void (*release)(struct nfs_pgio_header *hdr))
{
hdr->req = nfs_list_entry(desc->pg_list.next);
hdr->inode = desc->pg_inode;
hdr->cred = hdr->req->wb_context->cred;
hdr->io_start = req_offset(hdr->req);
hdr->good_bytes = desc->pg_count;
hdr->dreq = desc->pg_dreq;
hdr->release = release;
hdr->completion_ops = desc->pg_completion_ops;
if (hdr->completion_ops->init_hdr)
hdr->completion_ops->init_hdr(hdr);
}
void nfs_set_pgio_error(struct nfs_pgio_header *hdr, int error, loff_t pos)
{
spin_lock(&hdr->lock);
if (pos < hdr->io_start + hdr->good_bytes) {
set_bit(NFS_IOHDR_ERROR, &hdr->flags);
clear_bit(NFS_IOHDR_EOF, &hdr->flags);
hdr->good_bytes = pos - hdr->io_start;
hdr->error = error;
}
spin_unlock(&hdr->lock);
}
static inline struct nfs_page *
nfs_page_alloc(void)
{
@ -76,12 +117,8 @@ nfs_create_request(struct nfs_open_context *ctx, struct inode *inode,
* long write-back delay. This will be adjusted in
* update_nfs_request below if the region is not locked. */
req->wb_page = page;
atomic_set(&req->wb_complete, 0);
req->wb_index = page->index;
page_cache_get(page);
BUG_ON(PagePrivate(page));
BUG_ON(!PageLocked(page));
BUG_ON(page->mapping->host != inode);
req->wb_offset = offset;
req->wb_pgbase = offset;
req->wb_bytes = count;
@ -104,6 +141,15 @@ void nfs_unlock_request(struct nfs_page *req)
clear_bit(PG_BUSY, &req->wb_flags);
smp_mb__after_clear_bit();
wake_up_bit(&req->wb_flags, PG_BUSY);
}
/**
* nfs_unlock_and_release_request - Unlock request and release the nfs_page
* @req:
*/
void nfs_unlock_and_release_request(struct nfs_page *req)
{
nfs_unlock_request(req);
nfs_release_request(req);
}
@ -203,6 +249,7 @@ EXPORT_SYMBOL_GPL(nfs_generic_pg_test);
void nfs_pageio_init(struct nfs_pageio_descriptor *desc,
struct inode *inode,
const struct nfs_pageio_ops *pg_ops,
const struct nfs_pgio_completion_ops *compl_ops,
size_t bsize,
int io_flags)
{
@ -215,9 +262,11 @@ void nfs_pageio_init(struct nfs_pageio_descriptor *desc,
desc->pg_recoalesce = 0;
desc->pg_inode = inode;
desc->pg_ops = pg_ops;
desc->pg_completion_ops = compl_ops;
desc->pg_ioflags = io_flags;
desc->pg_error = 0;
desc->pg_lseg = NULL;
desc->pg_dreq = NULL;
}
/**
@ -241,12 +290,12 @@ static bool nfs_can_coalesce_requests(struct nfs_page *prev,
return false;
if (req->wb_context->state != prev->wb_context->state)
return false;
if (req->wb_index != (prev->wb_index + 1))
return false;
if (req->wb_pgbase != 0)
return false;
if (prev->wb_pgbase + prev->wb_bytes != PAGE_CACHE_SIZE)
return false;
if (req_offset(req) != req_offset(prev) + prev->wb_bytes)
return false;
return pgio->pg_ops->pg_test(pgio, prev, req);
}

352
fs/nfs/pnfs.c
View File

@ -395,6 +395,9 @@ mark_matching_lsegs_invalid(struct pnfs_layout_hdr *lo,
dprintk("%s:Begin lo %p\n", __func__, lo);
if (list_empty(&lo->plh_segs)) {
/* Reset MDS Threshold I/O counters */
NFS_I(lo->plh_inode)->write_io = 0;
NFS_I(lo->plh_inode)->read_io = 0;
if (!test_and_set_bit(NFS_LAYOUT_DESTROYED, &lo->plh_flags))
put_layout_hdr_locked(lo);
return 0;
@ -455,6 +458,7 @@ pnfs_destroy_layout(struct nfs_inode *nfsi)
spin_unlock(&nfsi->vfs_inode.i_lock);
pnfs_free_lseg_list(&tmp_list);
}
EXPORT_SYMBOL_GPL(pnfs_destroy_layout);
/*
* Called by the state manger to remove all layouts established under an
@ -692,6 +696,7 @@ out:
dprintk("<-- %s status: %d\n", __func__, status);
return status;
}
EXPORT_SYMBOL_GPL(_pnfs_return_layout);
bool pnfs_roc(struct inode *ino)
{
@ -930,6 +935,81 @@ pnfs_find_lseg(struct pnfs_layout_hdr *lo,
return ret;
}
/*
* Use mdsthreshold hints set at each OPEN to determine if I/O should go
* to the MDS or over pNFS
*
* The nfs_inode read_io and write_io fields are cumulative counters reset
* when there are no layout segments. Note that in pnfs_update_layout iomode
* is set to IOMODE_READ for a READ request, and set to IOMODE_RW for a
* WRITE request.
*
* A return of true means use MDS I/O.
*
* From rfc 5661:
* If a file's size is smaller than the file size threshold, data accesses
* SHOULD be sent to the metadata server. If an I/O request has a length that
* is below the I/O size threshold, the I/O SHOULD be sent to the metadata
* server. If both file size and I/O size are provided, the client SHOULD
* reach or exceed both thresholds before sending its read or write
* requests to the data server.
*/
static bool pnfs_within_mdsthreshold(struct nfs_open_context *ctx,
struct inode *ino, int iomode)
{
struct nfs4_threshold *t = ctx->mdsthreshold;
struct nfs_inode *nfsi = NFS_I(ino);
loff_t fsize = i_size_read(ino);
bool size = false, size_set = false, io = false, io_set = false, ret = false;
if (t == NULL)
return ret;
dprintk("%s bm=0x%x rd_sz=%llu wr_sz=%llu rd_io=%llu wr_io=%llu\n",
__func__, t->bm, t->rd_sz, t->wr_sz, t->rd_io_sz, t->wr_io_sz);
switch (iomode) {
case IOMODE_READ:
if (t->bm & THRESHOLD_RD) {
dprintk("%s fsize %llu\n", __func__, fsize);
size_set = true;
if (fsize < t->rd_sz)
size = true;
}
if (t->bm & THRESHOLD_RD_IO) {
dprintk("%s nfsi->read_io %llu\n", __func__,
nfsi->read_io);
io_set = true;
if (nfsi->read_io < t->rd_io_sz)
io = true;
}
break;
case IOMODE_RW:
if (t->bm & THRESHOLD_WR) {
dprintk("%s fsize %llu\n", __func__, fsize);
size_set = true;
if (fsize < t->wr_sz)
size = true;
}
if (t->bm & THRESHOLD_WR_IO) {
dprintk("%s nfsi->write_io %llu\n", __func__,
nfsi->write_io);
io_set = true;
if (nfsi->write_io < t->wr_io_sz)
io = true;
}
break;
}
if (size_set && io_set) {
if (size && io)
ret = true;
} else if (size || io)
ret = true;
dprintk("<-- %s size %d io %d ret %d\n", __func__, size, io, ret);
return ret;
}
/*
* Layout segment is retreived from the server if not cached.
* The appropriate layout segment is referenced and returned to the caller.
@ -957,6 +1037,10 @@ pnfs_update_layout(struct inode *ino,
if (!pnfs_enabled_sb(NFS_SERVER(ino)))
return NULL;
if (pnfs_within_mdsthreshold(ctx, ino, iomode))
return NULL;
spin_lock(&ino->i_lock);
lo = pnfs_find_alloc_layout(ino, ctx, gfp_flags);
if (lo == NULL) {
@ -1082,6 +1166,10 @@ pnfs_generic_pg_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *r
{
BUG_ON(pgio->pg_lseg != NULL);
if (req->wb_offset != req->wb_pgbase) {
nfs_pageio_reset_read_mds(pgio);
return;
}
pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
req->wb_context,
req_offset(req),
@ -1100,6 +1188,10 @@ pnfs_generic_pg_init_write(struct nfs_pageio_descriptor *pgio, struct nfs_page *
{
BUG_ON(pgio->pg_lseg != NULL);
if (req->wb_offset != req->wb_pgbase) {
nfs_pageio_reset_write_mds(pgio);
return;
}
pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
req->wb_context,
req_offset(req),
@ -1113,26 +1205,31 @@ pnfs_generic_pg_init_write(struct nfs_pageio_descriptor *pgio, struct nfs_page *
EXPORT_SYMBOL_GPL(pnfs_generic_pg_init_write);
bool
pnfs_pageio_init_read(struct nfs_pageio_descriptor *pgio, struct inode *inode)
pnfs_pageio_init_read(struct nfs_pageio_descriptor *pgio, struct inode *inode,
const struct nfs_pgio_completion_ops *compl_ops)
{
struct nfs_server *server = NFS_SERVER(inode);
struct pnfs_layoutdriver_type *ld = server->pnfs_curr_ld;
if (ld == NULL)
return false;
nfs_pageio_init(pgio, inode, ld->pg_read_ops, server->rsize, 0);
nfs_pageio_init(pgio, inode, ld->pg_read_ops, compl_ops,
server->rsize, 0);
return true;
}
bool
pnfs_pageio_init_write(struct nfs_pageio_descriptor *pgio, struct inode *inode, int ioflags)
pnfs_pageio_init_write(struct nfs_pageio_descriptor *pgio, struct inode *inode,
int ioflags,
const struct nfs_pgio_completion_ops *compl_ops)
{
struct nfs_server *server = NFS_SERVER(inode);
struct pnfs_layoutdriver_type *ld = server->pnfs_curr_ld;
if (ld == NULL)
return false;
nfs_pageio_init(pgio, inode, ld->pg_write_ops, server->wsize, ioflags);
nfs_pageio_init(pgio, inode, ld->pg_write_ops, compl_ops,
server->wsize, ioflags);
return true;
}
@ -1162,13 +1259,15 @@ pnfs_generic_pg_test(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev,
}
EXPORT_SYMBOL_GPL(pnfs_generic_pg_test);
static int pnfs_write_done_resend_to_mds(struct inode *inode, struct list_head *head)
int pnfs_write_done_resend_to_mds(struct inode *inode,
struct list_head *head,
const struct nfs_pgio_completion_ops *compl_ops)
{
struct nfs_pageio_descriptor pgio;
LIST_HEAD(failed);
/* Resend all requests through the MDS */
nfs_pageio_init_write_mds(&pgio, inode, FLUSH_STABLE);
nfs_pageio_init_write_mds(&pgio, inode, FLUSH_STABLE, compl_ops);
while (!list_empty(head)) {
struct nfs_page *req = nfs_list_entry(head->next);
@ -1188,30 +1287,37 @@ static int pnfs_write_done_resend_to_mds(struct inode *inode, struct list_head *
}
return 0;
}
EXPORT_SYMBOL_GPL(pnfs_write_done_resend_to_mds);
static void pnfs_ld_handle_write_error(struct nfs_write_data *data)
{
struct nfs_pgio_header *hdr = data->header;
dprintk("pnfs write error = %d\n", hdr->pnfs_error);
if (NFS_SERVER(hdr->inode)->pnfs_curr_ld->flags &
PNFS_LAYOUTRET_ON_ERROR) {
clear_bit(NFS_INO_LAYOUTCOMMIT, &NFS_I(hdr->inode)->flags);
pnfs_return_layout(hdr->inode);
}
if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags))
data->task.tk_status = pnfs_write_done_resend_to_mds(hdr->inode,
&hdr->pages,
hdr->completion_ops);
}
/*
* Called by non rpc-based layout drivers
*/
void pnfs_ld_write_done(struct nfs_write_data *data)
{
if (likely(!data->pnfs_error)) {
struct nfs_pgio_header *hdr = data->header;
if (!hdr->pnfs_error) {
pnfs_set_layoutcommit(data);
data->mds_ops->rpc_call_done(&data->task, data);
} else {
dprintk("pnfs write error = %d\n", data->pnfs_error);
if (NFS_SERVER(data->inode)->pnfs_curr_ld->flags &
PNFS_LAYOUTRET_ON_ERROR) {
/* Don't lo_commit on error, Server will needs to
* preform a file recovery.
*/
clear_bit(NFS_INO_LAYOUTCOMMIT,
&NFS_I(data->inode)->flags);
pnfs_return_layout(data->inode);
}
data->task.tk_status = pnfs_write_done_resend_to_mds(data->inode, &data->pages);
}
put_lseg(data->lseg);
data->mds_ops->rpc_release(data);
hdr->mds_ops->rpc_call_done(&data->task, data);
} else
pnfs_ld_handle_write_error(data);
hdr->mds_ops->rpc_release(data);
}
EXPORT_SYMBOL_GPL(pnfs_ld_write_done);
@ -1219,12 +1325,13 @@ static void
pnfs_write_through_mds(struct nfs_pageio_descriptor *desc,
struct nfs_write_data *data)
{
list_splice_tail_init(&data->pages, &desc->pg_list);
if (data->req && list_empty(&data->req->wb_list))
nfs_list_add_request(data->req, &desc->pg_list);
nfs_pageio_reset_write_mds(desc);
desc->pg_recoalesce = 1;
put_lseg(data->lseg);
struct nfs_pgio_header *hdr = data->header;
if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags)) {
list_splice_tail_init(&hdr->pages, &desc->pg_list);
nfs_pageio_reset_write_mds(desc);
desc->pg_recoalesce = 1;
}
nfs_writedata_release(data);
}
@ -1234,23 +1341,18 @@ pnfs_try_to_write_data(struct nfs_write_data *wdata,
struct pnfs_layout_segment *lseg,
int how)
{
struct inode *inode = wdata->inode;
struct nfs_pgio_header *hdr = wdata->header;
struct inode *inode = hdr->inode;
enum pnfs_try_status trypnfs;
struct nfs_server *nfss = NFS_SERVER(inode);
wdata->mds_ops = call_ops;
wdata->lseg = get_lseg(lseg);
hdr->mds_ops = call_ops;
dprintk("%s: Writing ino:%lu %u@%llu (how %d)\n", __func__,
inode->i_ino, wdata->args.count, wdata->args.offset, how);
trypnfs = nfss->pnfs_curr_ld->write_pagelist(wdata, how);
if (trypnfs == PNFS_NOT_ATTEMPTED) {
put_lseg(wdata->lseg);
wdata->lseg = NULL;
} else
if (trypnfs != PNFS_NOT_ATTEMPTED)
nfs_inc_stats(inode, NFSIOS_PNFS_WRITE);
dprintk("%s End (trypnfs:%d)\n", __func__, trypnfs);
return trypnfs;
}
@ -1266,7 +1368,7 @@ pnfs_do_multiple_writes(struct nfs_pageio_descriptor *desc, struct list_head *he
while (!list_empty(head)) {
enum pnfs_try_status trypnfs;
data = list_entry(head->next, struct nfs_write_data, list);
data = list_first_entry(head, struct nfs_write_data, list);
list_del_init(&data->list);
trypnfs = pnfs_try_to_write_data(data, call_ops, lseg, how);
@ -1276,43 +1378,82 @@ pnfs_do_multiple_writes(struct nfs_pageio_descriptor *desc, struct list_head *he
put_lseg(lseg);
}
static void pnfs_writehdr_free(struct nfs_pgio_header *hdr)
{
put_lseg(hdr->lseg);
nfs_writehdr_free(hdr);
}
int
pnfs_generic_pg_writepages(struct nfs_pageio_descriptor *desc)
{
LIST_HEAD(head);
struct nfs_write_header *whdr;
struct nfs_pgio_header *hdr;
int ret;
ret = nfs_generic_flush(desc, &head);
whdr = nfs_writehdr_alloc();
if (!whdr) {
desc->pg_completion_ops->error_cleanup(&desc->pg_list);
put_lseg(desc->pg_lseg);
desc->pg_lseg = NULL;
return -ENOMEM;
}
hdr = &whdr->header;
nfs_pgheader_init(desc, hdr, pnfs_writehdr_free);
hdr->lseg = get_lseg(desc->pg_lseg);
atomic_inc(&hdr->refcnt);
ret = nfs_generic_flush(desc, hdr);
if (ret != 0) {
put_lseg(desc->pg_lseg);
desc->pg_lseg = NULL;
return ret;
}
pnfs_do_multiple_writes(desc, &head, desc->pg_ioflags);
return 0;
} else
pnfs_do_multiple_writes(desc, &hdr->rpc_list, desc->pg_ioflags);
if (atomic_dec_and_test(&hdr->refcnt))
hdr->completion_ops->completion(hdr);
return ret;
}
EXPORT_SYMBOL_GPL(pnfs_generic_pg_writepages);
static void pnfs_ld_handle_read_error(struct nfs_read_data *data)
int pnfs_read_done_resend_to_mds(struct inode *inode,
struct list_head *head,
const struct nfs_pgio_completion_ops *compl_ops)
{
struct nfs_pageio_descriptor pgio;
LIST_HEAD(failed);
put_lseg(data->lseg);
data->lseg = NULL;
dprintk("pnfs write error = %d\n", data->pnfs_error);
if (NFS_SERVER(data->inode)->pnfs_curr_ld->flags &
PNFS_LAYOUTRET_ON_ERROR)
pnfs_return_layout(data->inode);
nfs_pageio_init_read_mds(&pgio, data->inode);
while (!list_empty(&data->pages)) {
struct nfs_page *req = nfs_list_entry(data->pages.next);
/* Resend all requests through the MDS */
nfs_pageio_init_read_mds(&pgio, inode, compl_ops);
while (!list_empty(head)) {
struct nfs_page *req = nfs_list_entry(head->next);
nfs_list_remove_request(req);
nfs_pageio_add_request(&pgio, req);
if (!nfs_pageio_add_request(&pgio, req))
nfs_list_add_request(req, &failed);
}
nfs_pageio_complete(&pgio);
if (!list_empty(&failed)) {
list_move(&failed, head);
return -EIO;
}
return 0;
}
EXPORT_SYMBOL_GPL(pnfs_read_done_resend_to_mds);
static void pnfs_ld_handle_read_error(struct nfs_read_data *data)
{
struct nfs_pgio_header *hdr = data->header;
dprintk("pnfs read error = %d\n", hdr->pnfs_error);
if (NFS_SERVER(hdr->inode)->pnfs_curr_ld->flags &
PNFS_LAYOUTRET_ON_ERROR) {
clear_bit(NFS_INO_LAYOUTCOMMIT, &NFS_I(hdr->inode)->flags);
pnfs_return_layout(hdr->inode);
}
if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags))
data->task.tk_status = pnfs_read_done_resend_to_mds(hdr->inode,
&hdr->pages,
hdr->completion_ops);
}
/*
@ -1320,13 +1461,14 @@ static void pnfs_ld_handle_read_error(struct nfs_read_data *data)
*/
void pnfs_ld_read_done(struct nfs_read_data *data)
{
if (likely(!data->pnfs_error)) {
struct nfs_pgio_header *hdr = data->header;
if (likely(!hdr->pnfs_error)) {
__nfs4_read_done_cb(data);
data->mds_ops->rpc_call_done(&data->task, data);
hdr->mds_ops->rpc_call_done(&data->task, data);
} else
pnfs_ld_handle_read_error(data);
put_lseg(data->lseg);
data->mds_ops->rpc_release(data);
hdr->mds_ops->rpc_release(data);
}
EXPORT_SYMBOL_GPL(pnfs_ld_read_done);
@ -1334,11 +1476,13 @@ static void
pnfs_read_through_mds(struct nfs_pageio_descriptor *desc,
struct nfs_read_data *data)
{
list_splice_tail_init(&data->pages, &desc->pg_list);
if (data->req && list_empty(&data->req->wb_list))
nfs_list_add_request(data->req, &desc->pg_list);
nfs_pageio_reset_read_mds(desc);
desc->pg_recoalesce = 1;
struct nfs_pgio_header *hdr = data->header;
if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags)) {
list_splice_tail_init(&hdr->pages, &desc->pg_list);
nfs_pageio_reset_read_mds(desc);
desc->pg_recoalesce = 1;
}
nfs_readdata_release(data);
}
@ -1350,23 +1494,19 @@ pnfs_try_to_read_data(struct nfs_read_data *rdata,
const struct rpc_call_ops *call_ops,
struct pnfs_layout_segment *lseg)
{
struct inode *inode = rdata->inode;
struct nfs_pgio_header *hdr = rdata->header;
struct inode *inode = hdr->inode;
struct nfs_server *nfss = NFS_SERVER(inode);
enum pnfs_try_status trypnfs;
rdata->mds_ops = call_ops;
rdata->lseg = get_lseg(lseg);
hdr->mds_ops = call_ops;
dprintk("%s: Reading ino:%lu %u@%llu\n",
__func__, inode->i_ino, rdata->args.count, rdata->args.offset);
trypnfs = nfss->pnfs_curr_ld->read_pagelist(rdata);
if (trypnfs == PNFS_NOT_ATTEMPTED) {
put_lseg(rdata->lseg);
rdata->lseg = NULL;
} else {
if (trypnfs != PNFS_NOT_ATTEMPTED)
nfs_inc_stats(inode, NFSIOS_PNFS_READ);
}
dprintk("%s End (trypnfs:%d)\n", __func__, trypnfs);
return trypnfs;
}
@ -1382,7 +1522,7 @@ pnfs_do_multiple_reads(struct nfs_pageio_descriptor *desc, struct list_head *hea
while (!list_empty(head)) {
enum pnfs_try_status trypnfs;
data = list_entry(head->next, struct nfs_read_data, list);
data = list_first_entry(head, struct nfs_read_data, list);
list_del_init(&data->list);
trypnfs = pnfs_try_to_read_data(data, call_ops, lseg);
@ -1392,20 +1532,40 @@ pnfs_do_multiple_reads(struct nfs_pageio_descriptor *desc, struct list_head *hea
put_lseg(lseg);
}
static void pnfs_readhdr_free(struct nfs_pgio_header *hdr)
{
put_lseg(hdr->lseg);
nfs_readhdr_free(hdr);
}
int
pnfs_generic_pg_readpages(struct nfs_pageio_descriptor *desc)
{
LIST_HEAD(head);
struct nfs_read_header *rhdr;
struct nfs_pgio_header *hdr;
int ret;
ret = nfs_generic_pagein(desc, &head);
if (ret != 0) {
rhdr = nfs_readhdr_alloc();
if (!rhdr) {
desc->pg_completion_ops->error_cleanup(&desc->pg_list);
ret = -ENOMEM;
put_lseg(desc->pg_lseg);
desc->pg_lseg = NULL;
return ret;
}
pnfs_do_multiple_reads(desc, &head);
return 0;
hdr = &rhdr->header;
nfs_pgheader_init(desc, hdr, pnfs_readhdr_free);
hdr->lseg = get_lseg(desc->pg_lseg);
atomic_inc(&hdr->refcnt);
ret = nfs_generic_pagein(desc, hdr);
if (ret != 0) {
put_lseg(desc->pg_lseg);
desc->pg_lseg = NULL;
} else
pnfs_do_multiple_reads(desc, &hdr->rpc_list);
if (atomic_dec_and_test(&hdr->refcnt))
hdr->completion_ops->completion(hdr);
return ret;
}
EXPORT_SYMBOL_GPL(pnfs_generic_pg_readpages);
@ -1438,30 +1598,32 @@ EXPORT_SYMBOL_GPL(pnfs_set_lo_fail);
void
pnfs_set_layoutcommit(struct nfs_write_data *wdata)
{
struct nfs_inode *nfsi = NFS_I(wdata->inode);
struct nfs_pgio_header *hdr = wdata->header;
struct inode *inode = hdr->inode;
struct nfs_inode *nfsi = NFS_I(inode);
loff_t end_pos = wdata->mds_offset + wdata->res.count;
bool mark_as_dirty = false;
spin_lock(&nfsi->vfs_inode.i_lock);
spin_lock(&inode->i_lock);
if (!test_and_set_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags)) {
mark_as_dirty = true;
dprintk("%s: Set layoutcommit for inode %lu ",
__func__, wdata->inode->i_ino);
__func__, inode->i_ino);
}
if (!test_and_set_bit(NFS_LSEG_LAYOUTCOMMIT, &wdata->lseg->pls_flags)) {
if (!test_and_set_bit(NFS_LSEG_LAYOUTCOMMIT, &hdr->lseg->pls_flags)) {
/* references matched in nfs4_layoutcommit_release */
get_lseg(wdata->lseg);
get_lseg(hdr->lseg);
}
if (end_pos > nfsi->layout->plh_lwb)
nfsi->layout->plh_lwb = end_pos;
spin_unlock(&nfsi->vfs_inode.i_lock);
spin_unlock(&inode->i_lock);
dprintk("%s: lseg %p end_pos %llu\n",
__func__, wdata->lseg, nfsi->layout->plh_lwb);
__func__, hdr->lseg, nfsi->layout->plh_lwb);
/* if pnfs_layoutcommit_inode() runs between inode locks, the next one
* will be a noop because NFS_INO_LAYOUTCOMMIT will not be set */
if (mark_as_dirty)
mark_inode_dirty_sync(wdata->inode);
mark_inode_dirty_sync(inode);
}
EXPORT_SYMBOL_GPL(pnfs_set_layoutcommit);
@ -1550,3 +1712,15 @@ out_free:
kfree(data);
goto out;
}
struct nfs4_threshold *pnfs_mdsthreshold_alloc(void)
{
struct nfs4_threshold *thp;
thp = kzalloc(sizeof(*thp), GFP_NOFS);
if (!thp) {
dprintk("%s mdsthreshold allocation failed\n", __func__);
return NULL;
}
return thp;
}

127
fs/nfs/pnfs.h
View File

@ -63,6 +63,7 @@ enum {
NFS_LAYOUT_BULK_RECALL, /* bulk recall affecting layout */
NFS_LAYOUT_ROC, /* some lseg had roc bit set */
NFS_LAYOUT_DESTROYED, /* no new use of layout allowed */
NFS_LAYOUT_INVALID, /* layout is being destroyed */
};
enum layoutdriver_policy_flags {
@ -94,11 +95,20 @@ struct pnfs_layoutdriver_type {
const struct nfs_pageio_ops *pg_read_ops;
const struct nfs_pageio_ops *pg_write_ops;
struct pnfs_ds_commit_info *(*get_ds_info) (struct inode *inode);
void (*mark_request_commit) (struct nfs_page *req,
struct pnfs_layout_segment *lseg);
void (*clear_request_commit) (struct nfs_page *req);
int (*scan_commit_lists) (struct inode *inode, int max, spinlock_t *lock);
int (*commit_pagelist)(struct inode *inode, struct list_head *mds_pages, int how);
struct pnfs_layout_segment *lseg,
struct nfs_commit_info *cinfo);
void (*clear_request_commit) (struct nfs_page *req,
struct nfs_commit_info *cinfo);
int (*scan_commit_lists) (struct nfs_commit_info *cinfo,
int max);
void (*recover_commit_reqs) (struct list_head *list,
struct nfs_commit_info *cinfo);
int (*commit_pagelist)(struct inode *inode,
struct list_head *mds_pages,
int how,
struct nfs_commit_info *cinfo);
/*
* Return PNFS_ATTEMPTED to indicate the layout code has attempted
@ -168,8 +178,10 @@ extern int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp);
void get_layout_hdr(struct pnfs_layout_hdr *lo);
void put_lseg(struct pnfs_layout_segment *lseg);
bool pnfs_pageio_init_read(struct nfs_pageio_descriptor *, struct inode *);
bool pnfs_pageio_init_write(struct nfs_pageio_descriptor *, struct inode *, int);
bool pnfs_pageio_init_read(struct nfs_pageio_descriptor *, struct inode *,
const struct nfs_pgio_completion_ops *);
bool pnfs_pageio_init_write(struct nfs_pageio_descriptor *, struct inode *,
int, const struct nfs_pgio_completion_ops *);
void set_pnfs_layoutdriver(struct nfs_server *, const struct nfs_fh *, u32);
void unset_pnfs_layoutdriver(struct nfs_server *);
@ -211,6 +223,11 @@ struct pnfs_layout_segment *pnfs_update_layout(struct inode *ino,
gfp_t gfp_flags);
void nfs4_deviceid_mark_client_invalid(struct nfs_client *clp);
int pnfs_read_done_resend_to_mds(struct inode *inode, struct list_head *head,
const struct nfs_pgio_completion_ops *compl_ops);
int pnfs_write_done_resend_to_mds(struct inode *inode, struct list_head *head,
const struct nfs_pgio_completion_ops *compl_ops);
struct nfs4_threshold *pnfs_mdsthreshold_alloc(void);
/* nfs4_deviceid_flags */
enum {
@ -261,49 +278,66 @@ static inline int pnfs_enabled_sb(struct nfs_server *nfss)
}
static inline int
pnfs_commit_list(struct inode *inode, struct list_head *mds_pages, int how)
pnfs_commit_list(struct inode *inode, struct list_head *mds_pages, int how,
struct nfs_commit_info *cinfo)
{
if (!test_and_clear_bit(NFS_INO_PNFS_COMMIT, &NFS_I(inode)->flags))
if (cinfo->ds == NULL || cinfo->ds->ncommitting == 0)
return PNFS_NOT_ATTEMPTED;
return NFS_SERVER(inode)->pnfs_curr_ld->commit_pagelist(inode, mds_pages, how);
return NFS_SERVER(inode)->pnfs_curr_ld->commit_pagelist(inode, mds_pages, how, cinfo);
}
static inline struct pnfs_ds_commit_info *
pnfs_get_ds_info(struct inode *inode)
{
struct pnfs_layoutdriver_type *ld = NFS_SERVER(inode)->pnfs_curr_ld;
if (ld == NULL || ld->get_ds_info == NULL)
return NULL;
return ld->get_ds_info(inode);
}
static inline bool
pnfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg)
pnfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg,
struct nfs_commit_info *cinfo)
{
struct inode *inode = req->wb_context->dentry->d_inode;
struct pnfs_layoutdriver_type *ld = NFS_SERVER(inode)->pnfs_curr_ld;
if (lseg == NULL || ld->mark_request_commit == NULL)
return false;
ld->mark_request_commit(req, lseg);
ld->mark_request_commit(req, lseg, cinfo);
return true;
}
static inline bool
pnfs_clear_request_commit(struct nfs_page *req)
pnfs_clear_request_commit(struct nfs_page *req, struct nfs_commit_info *cinfo)
{
struct inode *inode = req->wb_context->dentry->d_inode;
struct pnfs_layoutdriver_type *ld = NFS_SERVER(inode)->pnfs_curr_ld;
if (ld == NULL || ld->clear_request_commit == NULL)
return false;
ld->clear_request_commit(req);
ld->clear_request_commit(req, cinfo);
return true;
}
static inline int
pnfs_scan_commit_lists(struct inode *inode, int max, spinlock_t *lock)
pnfs_scan_commit_lists(struct inode *inode, struct nfs_commit_info *cinfo,
int max)
{
struct pnfs_layoutdriver_type *ld = NFS_SERVER(inode)->pnfs_curr_ld;
int ret;
if (ld == NULL || ld->scan_commit_lists == NULL)
if (cinfo->ds == NULL || cinfo->ds->nwritten == 0)
return 0;
ret = ld->scan_commit_lists(inode, max, lock);
if (ret != 0)
set_bit(NFS_INO_PNFS_COMMIT, &NFS_I(inode)->flags);
return ret;
else
return NFS_SERVER(inode)->pnfs_curr_ld->scan_commit_lists(cinfo, max);
}
static inline void
pnfs_recover_commit_reqs(struct inode *inode, struct list_head *list,
struct nfs_commit_info *cinfo)
{
if (cinfo->ds == NULL || cinfo->ds->nwritten == 0)
return;
NFS_SERVER(inode)->pnfs_curr_ld->recover_commit_reqs(list, cinfo);
}
/* Should the pNFS client commit and return the layout upon a setattr */
@ -327,6 +361,14 @@ static inline int pnfs_return_layout(struct inode *ino)
return 0;
}
static inline bool
pnfs_use_threshold(struct nfs4_threshold **dst, struct nfs4_threshold *src,
struct nfs_server *nfss)
{
return (dst && src && src->bm != 0 &&
nfss->pnfs_curr_ld->id == src->l_type);
}
#ifdef NFS_DEBUG
void nfs4_print_deviceid(const struct nfs4_deviceid *dev_id);
#else
@ -396,45 +438,74 @@ static inline void unset_pnfs_layoutdriver(struct nfs_server *s)
{
}
static inline bool pnfs_pageio_init_read(struct nfs_pageio_descriptor *pgio, struct inode *inode)
static inline bool pnfs_pageio_init_read(struct nfs_pageio_descriptor *pgio, struct inode *inode,
const struct nfs_pgio_completion_ops *compl_ops)
{
return false;
}
static inline bool pnfs_pageio_init_write(struct nfs_pageio_descriptor *pgio, struct inode *inode, int ioflags)
static inline bool pnfs_pageio_init_write(struct nfs_pageio_descriptor *pgio, struct inode *inode, int ioflags,
const struct nfs_pgio_completion_ops *compl_ops)
{
return false;
}
static inline int
pnfs_commit_list(struct inode *inode, struct list_head *mds_pages, int how)
pnfs_commit_list(struct inode *inode, struct list_head *mds_pages, int how,
struct nfs_commit_info *cinfo)
{
return PNFS_NOT_ATTEMPTED;
}
static inline struct pnfs_ds_commit_info *
pnfs_get_ds_info(struct inode *inode)
{
return NULL;
}
static inline bool
pnfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg)
pnfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg,
struct nfs_commit_info *cinfo)
{
return false;
}
static inline bool
pnfs_clear_request_commit(struct nfs_page *req)
pnfs_clear_request_commit(struct nfs_page *req, struct nfs_commit_info *cinfo)
{
return false;
}
static inline int
pnfs_scan_commit_lists(struct inode *inode, int max, spinlock_t *lock)
pnfs_scan_commit_lists(struct inode *inode, struct nfs_commit_info *cinfo,
int max)
{
return 0;
}
static inline void
pnfs_recover_commit_reqs(struct inode *inode, struct list_head *list,
struct nfs_commit_info *cinfo)
{
}
static inline int pnfs_layoutcommit_inode(struct inode *inode, bool sync)
{
return 0;
}
static inline bool
pnfs_use_threshold(struct nfs4_threshold **dst, struct nfs4_threshold *src,
struct nfs_server *nfss)
{
return false;
}
static inline struct nfs4_threshold *pnfs_mdsthreshold_alloc(void)
{
return NULL;
}
#endif /* CONFIG_NFS_V4_1 */
#endif /* FS_NFS_PNFS_H */

21
fs/nfs/proc.c
View File

@ -178,7 +178,7 @@ nfs_proc_setattr(struct dentry *dentry, struct nfs_fattr *fattr,
}
static int
nfs_proc_lookup(struct rpc_clnt *clnt, struct inode *dir, struct qstr *name,
nfs_proc_lookup(struct inode *dir, struct qstr *name,
struct nfs_fh *fhandle, struct nfs_fattr *fattr)
{
struct nfs_diropargs arg = {
@ -640,12 +640,14 @@ nfs_proc_pathconf(struct nfs_server *server, struct nfs_fh *fhandle,
static int nfs_read_done(struct rpc_task *task, struct nfs_read_data *data)
{
struct inode *inode = data->header->inode;
if (nfs_async_handle_expired_key(task))
return -EAGAIN;
nfs_invalidate_atime(data->inode);
nfs_invalidate_atime(inode);
if (task->tk_status >= 0) {
nfs_refresh_inode(data->inode, data->res.fattr);
nfs_refresh_inode(inode, data->res.fattr);
/* Emulate the eof flag, which isn't normally needed in NFSv2
* as it is guaranteed to always return the file attributes
*/
@ -667,11 +669,13 @@ static void nfs_proc_read_rpc_prepare(struct rpc_task *task, struct nfs_read_dat
static int nfs_write_done(struct rpc_task *task, struct nfs_write_data *data)
{
struct inode *inode = data->header->inode;
if (nfs_async_handle_expired_key(task))
return -EAGAIN;
if (task->tk_status >= 0)
nfs_post_op_update_inode_force_wcc(data->inode, data->res.fattr);
nfs_post_op_update_inode_force_wcc(inode, data->res.fattr);
return 0;
}
@ -687,8 +691,13 @@ static void nfs_proc_write_rpc_prepare(struct rpc_task *task, struct nfs_write_d
rpc_call_start(task);
}
static void nfs_proc_commit_rpc_prepare(struct rpc_task *task, struct nfs_commit_data *data)
{
BUG();
}
static void
nfs_proc_commit_setup(struct nfs_write_data *data, struct rpc_message *msg)
nfs_proc_commit_setup(struct nfs_commit_data *data, struct rpc_message *msg)
{
BUG();
}
@ -732,6 +741,7 @@ const struct nfs_rpc_ops nfs_v2_clientops = {
.file_inode_ops = &nfs_file_inode_operations,
.file_ops = &nfs_file_operations,
.getroot = nfs_proc_get_root,
.submount = nfs_submount,
.getattr = nfs_proc_getattr,
.setattr = nfs_proc_setattr,
.lookup = nfs_proc_lookup,
@ -763,6 +773,7 @@ const struct nfs_rpc_ops nfs_v2_clientops = {
.write_rpc_prepare = nfs_proc_write_rpc_prepare,
.write_done = nfs_write_done,
.commit_setup = nfs_proc_commit_setup,
.commit_rpc_prepare = nfs_proc_commit_rpc_prepare,
.lock = nfs_proc_lock,
.lock_check_bounds = nfs_lock_check_bounds,
.close_context = nfs_close_context,

433
fs/nfs/read.c
View File

@ -30,43 +30,73 @@
#define NFSDBG_FACILITY NFSDBG_PAGECACHE
static const struct nfs_pageio_ops nfs_pageio_read_ops;
static const struct rpc_call_ops nfs_read_partial_ops;
static const struct rpc_call_ops nfs_read_full_ops;
static const struct rpc_call_ops nfs_read_common_ops;
static const struct nfs_pgio_completion_ops nfs_async_read_completion_ops;
static struct kmem_cache *nfs_rdata_cachep;
struct nfs_read_data *nfs_readdata_alloc(unsigned int pagecount)
struct nfs_read_header *nfs_readhdr_alloc(void)
{
struct nfs_read_data *p;
struct nfs_read_header *rhdr;
p = kmem_cache_zalloc(nfs_rdata_cachep, GFP_KERNEL);
if (p) {
INIT_LIST_HEAD(&p->pages);
p->npages = pagecount;
if (pagecount <= ARRAY_SIZE(p->page_array))
p->pagevec = p->page_array;
else {
p->pagevec = kcalloc(pagecount, sizeof(struct page *), GFP_KERNEL);
if (!p->pagevec) {
kmem_cache_free(nfs_rdata_cachep, p);
p = NULL;
}
}
rhdr = kmem_cache_zalloc(nfs_rdata_cachep, GFP_KERNEL);
if (rhdr) {
struct nfs_pgio_header *hdr = &rhdr->header;
INIT_LIST_HEAD(&hdr->pages);
INIT_LIST_HEAD(&hdr->rpc_list);
spin_lock_init(&hdr->lock);
atomic_set(&hdr->refcnt, 0);
}
return p;
return rhdr;
}
void nfs_readdata_free(struct nfs_read_data *p)
static struct nfs_read_data *nfs_readdata_alloc(struct nfs_pgio_header *hdr,
unsigned int pagecount)
{
if (p && (p->pagevec != &p->page_array[0]))
kfree(p->pagevec);
kmem_cache_free(nfs_rdata_cachep, p);
struct nfs_read_data *data, *prealloc;
prealloc = &container_of(hdr, struct nfs_read_header, header)->rpc_data;
if (prealloc->header == NULL)
data = prealloc;
else
data = kzalloc(sizeof(*data), GFP_KERNEL);
if (!data)
goto out;
if (nfs_pgarray_set(&data->pages, pagecount)) {
data->header = hdr;
atomic_inc(&hdr->refcnt);
} else {
if (data != prealloc)
kfree(data);
data = NULL;
}
out:
return data;
}
void nfs_readhdr_free(struct nfs_pgio_header *hdr)
{
struct nfs_read_header *rhdr = container_of(hdr, struct nfs_read_header, header);
kmem_cache_free(nfs_rdata_cachep, rhdr);
}
void nfs_readdata_release(struct nfs_read_data *rdata)
{
struct nfs_pgio_header *hdr = rdata->header;
struct nfs_read_header *read_header = container_of(hdr, struct nfs_read_header, header);
put_nfs_open_context(rdata->args.context);
nfs_readdata_free(rdata);
if (rdata->pages.pagevec != rdata->pages.page_array)
kfree(rdata->pages.pagevec);
if (rdata != &read_header->rpc_data)
kfree(rdata);
else
rdata->header = NULL;
if (atomic_dec_and_test(&hdr->refcnt))
hdr->completion_ops->completion(hdr);
}
static
@ -78,39 +108,11 @@ int nfs_return_empty_page(struct page *page)
return 0;
}
static void nfs_readpage_truncate_uninitialised_page(struct nfs_read_data *data)
{
unsigned int remainder = data->args.count - data->res.count;
unsigned int base = data->args.pgbase + data->res.count;
unsigned int pglen;
struct page **pages;
if (data->res.eof == 0 || remainder == 0)
return;
/*
* Note: "remainder" can never be negative, since we check for
* this in the XDR code.
*/
pages = &data->args.pages[base >> PAGE_CACHE_SHIFT];
base &= ~PAGE_CACHE_MASK;
pglen = PAGE_CACHE_SIZE - base;
for (;;) {
if (remainder <= pglen) {
zero_user(*pages, base, remainder);
break;
}
zero_user(*pages, base, pglen);
pages++;
remainder -= pglen;
pglen = PAGE_CACHE_SIZE;
base = 0;
}
}
void nfs_pageio_init_read_mds(struct nfs_pageio_descriptor *pgio,
struct inode *inode)
struct inode *inode,
const struct nfs_pgio_completion_ops *compl_ops)
{
nfs_pageio_init(pgio, inode, &nfs_pageio_read_ops,
nfs_pageio_init(pgio, inode, &nfs_pageio_read_ops, compl_ops,
NFS_SERVER(inode)->rsize, 0);
}
@ -121,11 +123,12 @@ void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio)
}
EXPORT_SYMBOL_GPL(nfs_pageio_reset_read_mds);
static void nfs_pageio_init_read(struct nfs_pageio_descriptor *pgio,
struct inode *inode)
void nfs_pageio_init_read(struct nfs_pageio_descriptor *pgio,
struct inode *inode,
const struct nfs_pgio_completion_ops *compl_ops)
{
if (!pnfs_pageio_init_read(pgio, inode))
nfs_pageio_init_read_mds(pgio, inode);
if (!pnfs_pageio_init_read(pgio, inode, compl_ops))
nfs_pageio_init_read_mds(pgio, inode, compl_ops);
}
int nfs_readpage_async(struct nfs_open_context *ctx, struct inode *inode,
@ -146,9 +149,10 @@ int nfs_readpage_async(struct nfs_open_context *ctx, struct inode *inode,
if (len < PAGE_CACHE_SIZE)
zero_user_segment(page, len, PAGE_CACHE_SIZE);
nfs_pageio_init_read(&pgio, inode);
nfs_pageio_init_read(&pgio, inode, &nfs_async_read_completion_ops);
nfs_pageio_add_request(&pgio, new);
nfs_pageio_complete(&pgio);
NFS_I(inode)->read_io += pgio.pg_bytes_written;
return 0;
}
@ -169,16 +173,49 @@ static void nfs_readpage_release(struct nfs_page *req)
nfs_release_request(req);
}
int nfs_initiate_read(struct nfs_read_data *data, struct rpc_clnt *clnt,
const struct rpc_call_ops *call_ops)
/* Note io was page aligned */
static void nfs_read_completion(struct nfs_pgio_header *hdr)
{
struct inode *inode = data->inode;
unsigned long bytes = 0;
if (test_bit(NFS_IOHDR_REDO, &hdr->flags))
goto out;
while (!list_empty(&hdr->pages)) {
struct nfs_page *req = nfs_list_entry(hdr->pages.next);
struct page *page = req->wb_page;
if (test_bit(NFS_IOHDR_EOF, &hdr->flags)) {
if (bytes > hdr->good_bytes)
zero_user(page, 0, PAGE_SIZE);
else if (hdr->good_bytes - bytes < PAGE_SIZE)
zero_user_segment(page,
hdr->good_bytes & ~PAGE_MASK,
PAGE_SIZE);
}
bytes += req->wb_bytes;
if (test_bit(NFS_IOHDR_ERROR, &hdr->flags)) {
if (bytes <= hdr->good_bytes)
SetPageUptodate(page);
} else
SetPageUptodate(page);
nfs_list_remove_request(req);
nfs_readpage_release(req);
}
out:
hdr->release(hdr);
}
int nfs_initiate_read(struct rpc_clnt *clnt,
struct nfs_read_data *data,
const struct rpc_call_ops *call_ops, int flags)
{
struct inode *inode = data->header->inode;
int swap_flags = IS_SWAPFILE(inode) ? NFS_RPC_SWAPFLAGS : 0;
struct rpc_task *task;
struct rpc_message msg = {
.rpc_argp = &data->args,
.rpc_resp = &data->res,
.rpc_cred = data->cred,
.rpc_cred = data->header->cred,
};
struct rpc_task_setup task_setup_data = {
.task = &data->task,
@ -187,7 +224,7 @@ int nfs_initiate_read(struct nfs_read_data *data, struct rpc_clnt *clnt,
.callback_ops = call_ops,
.callback_data = data,
.workqueue = nfsiod_workqueue,
.flags = RPC_TASK_ASYNC | swap_flags,
.flags = RPC_TASK_ASYNC | swap_flags | flags,
};
/* Set up the initial task struct. */
@ -212,19 +249,15 @@ EXPORT_SYMBOL_GPL(nfs_initiate_read);
/*
* Set up the NFS read request struct
*/
static void nfs_read_rpcsetup(struct nfs_page *req, struct nfs_read_data *data,
static void nfs_read_rpcsetup(struct nfs_read_data *data,
unsigned int count, unsigned int offset)
{
struct inode *inode = req->wb_context->dentry->d_inode;
struct nfs_page *req = data->header->req;
data->req = req;
data->inode = inode;
data->cred = req->wb_context->cred;
data->args.fh = NFS_FH(inode);
data->args.fh = NFS_FH(data->header->inode);
data->args.offset = req_offset(req) + offset;
data->args.pgbase = req->wb_pgbase + offset;
data->args.pages = data->pagevec;
data->args.pages = data->pages.pagevec;
data->args.count = count;
data->args.context = get_nfs_open_context(req->wb_context);
data->args.lock_context = req->wb_lock_context;
@ -238,9 +271,9 @@ static void nfs_read_rpcsetup(struct nfs_page *req, struct nfs_read_data *data,
static int nfs_do_read(struct nfs_read_data *data,
const struct rpc_call_ops *call_ops)
{
struct inode *inode = data->args.context->dentry->d_inode;
struct inode *inode = data->header->inode;
return nfs_initiate_read(data, NFS_CLIENT(inode), call_ops);
return nfs_initiate_read(NFS_CLIENT(inode), data, call_ops, 0);
}
static int
@ -253,7 +286,7 @@ nfs_do_multiple_reads(struct list_head *head,
while (!list_empty(head)) {
int ret2;
data = list_entry(head->next, struct nfs_read_data, list);
data = list_first_entry(head, struct nfs_read_data, list);
list_del_init(&data->list);
ret2 = nfs_do_read(data, call_ops);
@ -275,6 +308,24 @@ nfs_async_read_error(struct list_head *head)
}
}
static const struct nfs_pgio_completion_ops nfs_async_read_completion_ops = {
.error_cleanup = nfs_async_read_error,
.completion = nfs_read_completion,
};
static void nfs_pagein_error(struct nfs_pageio_descriptor *desc,
struct nfs_pgio_header *hdr)
{
set_bit(NFS_IOHDR_REDO, &hdr->flags);
while (!list_empty(&hdr->rpc_list)) {
struct nfs_read_data *data = list_first_entry(&hdr->rpc_list,
struct nfs_read_data, list);
list_del(&data->list);
nfs_readdata_release(data);
}
desc->pg_completion_ops->error_cleanup(&desc->pg_list);
}
/*
* Generate multiple requests to fill a single page.
*
@ -288,93 +339,95 @@ nfs_async_read_error(struct list_head *head)
* won't see the new data until our attribute cache is updated. This is more
* or less conventional NFS client behavior.
*/
static int nfs_pagein_multi(struct nfs_pageio_descriptor *desc, struct list_head *res)
static int nfs_pagein_multi(struct nfs_pageio_descriptor *desc,
struct nfs_pgio_header *hdr)
{
struct nfs_page *req = nfs_list_entry(desc->pg_list.next);
struct nfs_page *req = hdr->req;
struct page *page = req->wb_page;
struct nfs_read_data *data;
size_t rsize = desc->pg_bsize, nbytes;
unsigned int offset;
int requests = 0;
int ret = 0;
nfs_list_remove_request(req);
offset = 0;
nbytes = desc->pg_count;
do {
size_t len = min(nbytes,rsize);
data = nfs_readdata_alloc(1);
if (!data)
goto out_bad;
data->pagevec[0] = page;
nfs_read_rpcsetup(req, data, len, offset);
list_add(&data->list, res);
requests++;
data = nfs_readdata_alloc(hdr, 1);
if (!data) {
nfs_pagein_error(desc, hdr);
return -ENOMEM;
}
data->pages.pagevec[0] = page;
nfs_read_rpcsetup(data, len, offset);
list_add(&data->list, &hdr->rpc_list);
nbytes -= len;
offset += len;
} while(nbytes != 0);
atomic_set(&req->wb_complete, requests);
desc->pg_rpc_callops = &nfs_read_partial_ops;
return ret;
out_bad:
while (!list_empty(res)) {
data = list_entry(res->next, struct nfs_read_data, list);
list_del(&data->list);
nfs_readdata_release(data);
}
nfs_readpage_release(req);
return -ENOMEM;
} while (nbytes != 0);
nfs_list_remove_request(req);
nfs_list_add_request(req, &hdr->pages);
desc->pg_rpc_callops = &nfs_read_common_ops;
return 0;
}
static int nfs_pagein_one(struct nfs_pageio_descriptor *desc, struct list_head *res)
static int nfs_pagein_one(struct nfs_pageio_descriptor *desc,
struct nfs_pgio_header *hdr)
{
struct nfs_page *req;
struct page **pages;
struct nfs_read_data *data;
struct nfs_read_data *data;
struct list_head *head = &desc->pg_list;
int ret = 0;
data = nfs_readdata_alloc(nfs_page_array_len(desc->pg_base,
desc->pg_count));
data = nfs_readdata_alloc(hdr, nfs_page_array_len(desc->pg_base,
desc->pg_count));
if (!data) {
nfs_async_read_error(head);
ret = -ENOMEM;
goto out;
nfs_pagein_error(desc, hdr);
return -ENOMEM;
}
pages = data->pagevec;
pages = data->pages.pagevec;
while (!list_empty(head)) {
req = nfs_list_entry(head->next);
nfs_list_remove_request(req);
nfs_list_add_request(req, &data->pages);
nfs_list_add_request(req, &hdr->pages);
*pages++ = req->wb_page;
}
req = nfs_list_entry(data->pages.next);
nfs_read_rpcsetup(req, data, desc->pg_count, 0);
list_add(&data->list, res);
desc->pg_rpc_callops = &nfs_read_full_ops;
out:
return ret;
nfs_read_rpcsetup(data, desc->pg_count, 0);
list_add(&data->list, &hdr->rpc_list);
desc->pg_rpc_callops = &nfs_read_common_ops;
return 0;
}
int nfs_generic_pagein(struct nfs_pageio_descriptor *desc, struct list_head *head)
int nfs_generic_pagein(struct nfs_pageio_descriptor *desc,
struct nfs_pgio_header *hdr)
{
if (desc->pg_bsize < PAGE_CACHE_SIZE)
return nfs_pagein_multi(desc, head);
return nfs_pagein_one(desc, head);
return nfs_pagein_multi(desc, hdr);
return nfs_pagein_one(desc, hdr);
}
static int nfs_generic_pg_readpages(struct nfs_pageio_descriptor *desc)
{
LIST_HEAD(head);
struct nfs_read_header *rhdr;
struct nfs_pgio_header *hdr;
int ret;
ret = nfs_generic_pagein(desc, &head);
rhdr = nfs_readhdr_alloc();
if (!rhdr) {
desc->pg_completion_ops->error_cleanup(&desc->pg_list);
return -ENOMEM;
}
hdr = &rhdr->header;
nfs_pgheader_init(desc, hdr, nfs_readhdr_free);
atomic_inc(&hdr->refcnt);
ret = nfs_generic_pagein(desc, hdr);
if (ret == 0)
ret = nfs_do_multiple_reads(&head, desc->pg_rpc_callops);
ret = nfs_do_multiple_reads(&hdr->rpc_list,
desc->pg_rpc_callops);
if (atomic_dec_and_test(&hdr->refcnt))
hdr->completion_ops->completion(hdr);
return ret;
}
@ -389,20 +442,21 @@ static const struct nfs_pageio_ops nfs_pageio_read_ops = {
*/
int nfs_readpage_result(struct rpc_task *task, struct nfs_read_data *data)
{
struct inode *inode = data->header->inode;
int status;
dprintk("NFS: %s: %5u, (status %d)\n", __func__, task->tk_pid,
task->tk_status);
status = NFS_PROTO(data->inode)->read_done(task, data);
status = NFS_PROTO(inode)->read_done(task, data);
if (status != 0)
return status;
nfs_add_stats(data->inode, NFSIOS_SERVERREADBYTES, data->res.count);
nfs_add_stats(inode, NFSIOS_SERVERREADBYTES, data->res.count);
if (task->tk_status == -ESTALE) {
set_bit(NFS_INO_STALE, &NFS_I(data->inode)->flags);
nfs_mark_for_revalidate(data->inode);
set_bit(NFS_INO_STALE, &NFS_I(inode)->flags);
nfs_mark_for_revalidate(inode);
}
return 0;
}
@ -412,15 +466,13 @@ static void nfs_readpage_retry(struct rpc_task *task, struct nfs_read_data *data
struct nfs_readargs *argp = &data->args;
struct nfs_readres *resp = &data->res;
if (resp->eof || resp->count == argp->count)
return;
/* This is a short read! */
nfs_inc_stats(data->inode, NFSIOS_SHORTREAD);
nfs_inc_stats(data->header->inode, NFSIOS_SHORTREAD);
/* Has the server at least made some progress? */
if (resp->count == 0)
if (resp->count == 0) {
nfs_set_pgio_error(data->header, -EIO, argp->offset);
return;
}
/* Yes, so retry the read at the end of the data */
data->mds_offset += resp->count;
argp->offset += resp->count;
@ -429,114 +481,46 @@ static void nfs_readpage_retry(struct rpc_task *task, struct nfs_read_data *data
rpc_restart_call_prepare(task);
}
/*
* Handle a read reply that fills part of a page.
*/
static void nfs_readpage_result_partial(struct rpc_task *task, void *calldata)
static void nfs_readpage_result_common(struct rpc_task *task, void *calldata)
{
struct nfs_read_data *data = calldata;
struct nfs_pgio_header *hdr = data->header;
/* Note the only returns of nfs_readpage_result are 0 and -EAGAIN */
if (nfs_readpage_result(task, data) != 0)
return;
if (task->tk_status < 0)
return;
nfs_set_pgio_error(hdr, task->tk_status, data->args.offset);
else if (data->res.eof) {
loff_t bound;
nfs_readpage_truncate_uninitialised_page(data);
nfs_readpage_retry(task, data);
bound = data->args.offset + data->res.count;
spin_lock(&hdr->lock);
if (bound < hdr->io_start + hdr->good_bytes) {
set_bit(NFS_IOHDR_EOF, &hdr->flags);
clear_bit(NFS_IOHDR_ERROR, &hdr->flags);
hdr->good_bytes = bound - hdr->io_start;
}
spin_unlock(&hdr->lock);
} else if (data->res.count != data->args.count)
nfs_readpage_retry(task, data);
}
static void nfs_readpage_release_partial(void *calldata)
static void nfs_readpage_release_common(void *calldata)
{
struct nfs_read_data *data = calldata;
struct nfs_page *req = data->req;
struct page *page = req->wb_page;
int status = data->task.tk_status;
if (status < 0)
set_bit(PG_PARTIAL_READ_FAILED, &req->wb_flags);
if (atomic_dec_and_test(&req->wb_complete)) {
if (!test_bit(PG_PARTIAL_READ_FAILED, &req->wb_flags))
SetPageUptodate(page);
nfs_readpage_release(req);
}
nfs_readdata_release(calldata);
}
void nfs_read_prepare(struct rpc_task *task, void *calldata)
{
struct nfs_read_data *data = calldata;
NFS_PROTO(data->inode)->read_rpc_prepare(task, data);
NFS_PROTO(data->header->inode)->read_rpc_prepare(task, data);
}
static const struct rpc_call_ops nfs_read_partial_ops = {
static const struct rpc_call_ops nfs_read_common_ops = {
.rpc_call_prepare = nfs_read_prepare,
.rpc_call_done = nfs_readpage_result_partial,
.rpc_release = nfs_readpage_release_partial,
};
static void nfs_readpage_set_pages_uptodate(struct nfs_read_data *data)
{
unsigned int count = data->res.count;
unsigned int base = data->args.pgbase;
struct page **pages;
if (data->res.eof)
count = data->args.count;
if (unlikely(count == 0))
return;
pages = &data->args.pages[base >> PAGE_CACHE_SHIFT];
base &= ~PAGE_CACHE_MASK;
count += base;
for (;count >= PAGE_CACHE_SIZE; count -= PAGE_CACHE_SIZE, pages++)
SetPageUptodate(*pages);
if (count == 0)
return;
/* Was this a short read? */
if (data->res.eof || data->res.count == data->args.count)
SetPageUptodate(*pages);
}
/*
* This is the callback from RPC telling us whether a reply was
* received or some error occurred (timeout or socket shutdown).
*/
static void nfs_readpage_result_full(struct rpc_task *task, void *calldata)
{
struct nfs_read_data *data = calldata;
if (nfs_readpage_result(task, data) != 0)
return;
if (task->tk_status < 0)
return;
/*
* Note: nfs_readpage_retry may change the values of
* data->args. In the multi-page case, we therefore need
* to ensure that we call nfs_readpage_set_pages_uptodate()
* first.
*/
nfs_readpage_truncate_uninitialised_page(data);
nfs_readpage_set_pages_uptodate(data);
nfs_readpage_retry(task, data);
}
static void nfs_readpage_release_full(void *calldata)
{
struct nfs_read_data *data = calldata;
while (!list_empty(&data->pages)) {
struct nfs_page *req = nfs_list_entry(data->pages.next);
nfs_list_remove_request(req);
nfs_readpage_release(req);
}
nfs_readdata_release(calldata);
}
static const struct rpc_call_ops nfs_read_full_ops = {
.rpc_call_prepare = nfs_read_prepare,
.rpc_call_done = nfs_readpage_result_full,
.rpc_release = nfs_readpage_release_full,
.rpc_call_done = nfs_readpage_result_common,
.rpc_release = nfs_readpage_release_common,
};
/*
@ -668,11 +652,12 @@ int nfs_readpages(struct file *filp, struct address_space *mapping,
if (ret == 0)
goto read_complete; /* all pages were read */
nfs_pageio_init_read(&pgio, inode);
nfs_pageio_init_read(&pgio, inode, &nfs_async_read_completion_ops);
ret = read_cache_pages(mapping, pages, readpage_async_filler, &desc);
nfs_pageio_complete(&pgio);
NFS_I(inode)->read_io += pgio.pg_bytes_written;
npages = (pgio.pg_bytes_written + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
nfs_add_stats(inode, NFSIOS_READPAGES, npages);
read_complete:
@ -684,7 +669,7 @@ out:
int __init nfs_init_readpagecache(void)
{
nfs_rdata_cachep = kmem_cache_create("nfs_read_data",
sizeof(struct nfs_read_data),
sizeof(struct nfs_read_header),
0, SLAB_HWCACHE_ALIGN,
NULL);
if (nfs_rdata_cachep == NULL)

778
fs/nfs/super.c
View File

File diff suppressed because it is too large Load Diff

817
fs/nfs/write.c
View File

File diff suppressed because it is too large Load Diff

13
include/linux/nfs4.h
View File

@ -69,6 +69,10 @@
#define NFS4_CDFC4_FORE_OR_BOTH 0x3
#define NFS4_CDFC4_BACK_OR_BOTH 0x7
#define NFS4_CDFS4_FORE 0x1
#define NFS4_CDFS4_BACK 0x2
#define NFS4_CDFS4_BOTH 0x3
#define NFS4_SET_TO_SERVER_TIME 0
#define NFS4_SET_TO_CLIENT_TIME 1
@ -526,6 +530,13 @@ enum lock_type4 {
#define FATTR4_WORD1_MOUNTED_ON_FILEID (1UL << 23)
#define FATTR4_WORD1_FS_LAYOUT_TYPES (1UL << 30)
#define FATTR4_WORD2_LAYOUT_BLKSIZE (1UL << 1)
#define FATTR4_WORD2_MDSTHRESHOLD (1UL << 4)
/* MDS threshold bitmap bits */
#define THRESHOLD_RD (1UL << 0)
#define THRESHOLD_WR (1UL << 1)
#define THRESHOLD_RD_IO (1UL << 2)
#define THRESHOLD_WR_IO (1UL << 3)
#define NFSPROC4_NULL 0
#define NFSPROC4_COMPOUND 1
@ -596,6 +607,8 @@ enum {
NFSPROC4_CLNT_TEST_STATEID,
NFSPROC4_CLNT_FREE_STATEID,
NFSPROC4_CLNT_GETDEVICELIST,
NFSPROC4_CLNT_BIND_CONN_TO_SESSION,
NFSPROC4_CLNT_DESTROY_CLIENTID,
};
/* nfs41 types */

31
include/linux/nfs_fs.h
View File

@ -102,6 +102,7 @@ struct nfs_open_context {
int error;
struct list_head list;
struct nfs4_threshold *mdsthreshold;
};
struct nfs_open_dir_context {
@ -179,8 +180,7 @@ struct nfs_inode {
__be32 cookieverf[2];
unsigned long npages;
unsigned long ncommit;
struct list_head commit_list;
struct nfs_mds_commit_info commit_info;
/* Open contexts for shared mmap writes */
struct list_head open_files;
@ -201,8 +201,10 @@ struct nfs_inode {
/* pNFS layout information */
struct pnfs_layout_hdr *layout;
atomic_t commits_outstanding;
#endif /* CONFIG_NFS_V4*/
/* how many bytes have been written/read and how many bytes queued up */
__u64 write_io;
__u64 read_io;
#ifdef CONFIG_NFS_FSCACHE
struct fscache_cookie *fscache;
#endif
@ -230,7 +232,6 @@ struct nfs_inode {
#define NFS_INO_FSCACHE (5) /* inode can be cached by FS-Cache */
#define NFS_INO_FSCACHE_LOCK (6) /* FS-Cache cookie management lock */
#define NFS_INO_COMMIT (7) /* inode is committing unstable writes */
#define NFS_INO_PNFS_COMMIT (8) /* use pnfs code for commit */
#define NFS_INO_LAYOUTCOMMIT (9) /* layoutcommit required */
#define NFS_INO_LAYOUTCOMMITTING (10) /* layoutcommit inflight */
@ -317,11 +318,6 @@ static inline int nfs_server_capable(struct inode *inode, int cap)
return NFS_SERVER(inode)->caps & cap;
}
static inline int NFS_USE_READDIRPLUS(struct inode *inode)
{
return test_bit(NFS_INO_ADVISE_RDPLUS, &NFS_I(inode)->flags);
}
static inline void nfs_set_verifier(struct dentry * dentry, unsigned long verf)
{
dentry->d_time = verf;
@ -552,8 +548,8 @@ extern int nfs_wb_page(struct inode *inode, struct page* page);
extern int nfs_wb_page_cancel(struct inode *inode, struct page* page);
#if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4)
extern int nfs_commit_inode(struct inode *, int);
extern struct nfs_write_data *nfs_commitdata_alloc(void);
extern void nfs_commit_free(struct nfs_write_data *wdata);
extern struct nfs_commit_data *nfs_commitdata_alloc(void);
extern void nfs_commit_free(struct nfs_commit_data *data);
#else
static inline int
nfs_commit_inode(struct inode *inode, int how)
@ -568,12 +564,6 @@ nfs_have_writebacks(struct inode *inode)
return NFS_I(inode)->npages != 0;
}
/*
* Allocate nfs_write_data structures
*/
extern struct nfs_write_data *nfs_writedata_alloc(unsigned int npages);
extern void nfs_writedata_free(struct nfs_write_data *);
/*
* linux/fs/nfs/read.c
*/
@ -584,12 +574,6 @@ extern int nfs_readpage_result(struct rpc_task *, struct nfs_read_data *);
extern int nfs_readpage_async(struct nfs_open_context *, struct inode *,
struct page *);
/*
* Allocate nfs_read_data structures
*/
extern struct nfs_read_data *nfs_readdata_alloc(unsigned int npages);
extern void nfs_readdata_free(struct nfs_read_data *);
/*
* linux/fs/nfs3proc.c
*/
@ -654,6 +638,7 @@ nfs_fileid_to_ino_t(u64 fileid)
#define NFSDBG_FSCACHE 0x0800
#define NFSDBG_PNFS 0x1000
#define NFSDBG_PNFS_LD 0x2000
#define NFSDBG_STATE 0x4000
#define NFSDBG_ALL 0xFFFF
#ifdef __KERNEL__

17
include/linux/nfs_fs_sb.h
View File

@ -17,7 +17,7 @@ struct nfs4_sequence_args;
struct nfs4_sequence_res;
struct nfs_server;
struct nfs4_minor_version_ops;
struct server_scope;
struct nfs41_server_scope;
struct nfs41_impl_id;
/*
@ -35,6 +35,9 @@ struct nfs_client {
#define NFS_CS_RENEWD 3 /* - renewd started */
#define NFS_CS_STOP_RENEW 4 /* no more state to renew */
#define NFS_CS_CHECK_LEASE_TIME 5 /* need to check lease time */
unsigned long cl_flags; /* behavior switches */
#define NFS_CS_NORESVPORT 0 /* - use ephemeral src port */
#define NFS_CS_DISCRTRY 1 /* - disconnect on RPC retry */
struct sockaddr_storage cl_addr; /* server identifier */
size_t cl_addrlen;
char * cl_hostname; /* hostname of server */
@ -61,9 +64,6 @@ struct nfs_client {
struct rpc_wait_queue cl_rpcwaitq;
/* used for the setclientid verifier */
struct timespec cl_boot_time;
/* idmapper */
struct idmap * cl_idmap;
@ -79,16 +79,17 @@ struct nfs_client {
u32 cl_seqid;
/* The flags used for obtaining the clientid during EXCHANGE_ID */
u32 cl_exchange_flags;
struct nfs4_session *cl_session; /* sharred session */
struct nfs4_session *cl_session; /* shared session */
struct nfs41_server_owner *cl_serverowner;
struct nfs41_server_scope *cl_serverscope;
struct nfs41_impl_id *cl_implid;
#endif /* CONFIG_NFS_V4 */
#ifdef CONFIG_NFS_FSCACHE
struct fscache_cookie *fscache; /* client index cache cookie */
#endif
struct server_scope *server_scope; /* from exchange_id */
struct nfs41_impl_id *impl_id; /* from exchange_id */
struct net *net;
struct net *cl_net;
};
/*

20
include/linux/nfs_page.h
View File

@ -27,7 +27,6 @@ enum {
PG_CLEAN,
PG_NEED_COMMIT,
PG_NEED_RESCHED,
PG_PARTIAL_READ_FAILED,
PG_COMMIT_TO_DS,
};
@ -37,7 +36,6 @@ struct nfs_page {
struct page *wb_page; /* page to read in/write out */
struct nfs_open_context *wb_context; /* File state context info */
struct nfs_lock_context *wb_lock_context; /* lock context info */
atomic_t wb_complete; /* i/os we're waiting for */
pgoff_t wb_index; /* Offset >> PAGE_CACHE_SHIFT */
unsigned int wb_offset, /* Offset & ~PAGE_CACHE_MASK */
wb_pgbase, /* Start of page data */
@ -68,7 +66,9 @@ struct nfs_pageio_descriptor {
int pg_ioflags;
int pg_error;
const struct rpc_call_ops *pg_rpc_callops;
const struct nfs_pgio_completion_ops *pg_completion_ops;
struct pnfs_layout_segment *pg_lseg;
struct nfs_direct_req *pg_dreq;
};
#define NFS_WBACK_BUSY(req) (test_bit(PG_BUSY,&(req)->wb_flags))
@ -84,6 +84,7 @@ extern void nfs_release_request(struct nfs_page *req);
extern void nfs_pageio_init(struct nfs_pageio_descriptor *desc,
struct inode *inode,
const struct nfs_pageio_ops *pg_ops,
const struct nfs_pgio_completion_ops *compl_ops,
size_t bsize,
int how);
extern int nfs_pageio_add_request(struct nfs_pageio_descriptor *,
@ -95,26 +96,17 @@ extern bool nfs_generic_pg_test(struct nfs_pageio_descriptor *desc,
struct nfs_page *req);
extern int nfs_wait_on_request(struct nfs_page *);
extern void nfs_unlock_request(struct nfs_page *req);
extern void nfs_unlock_and_release_request(struct nfs_page *req);
/*
* Lock the page of an asynchronous request without getting a new reference
* Lock the page of an asynchronous request
*/
static inline int
nfs_lock_request_dontget(struct nfs_page *req)
{
return !test_and_set_bit(PG_BUSY, &req->wb_flags);
}
static inline int
nfs_lock_request(struct nfs_page *req)
{
if (test_and_set_bit(PG_BUSY, &req->wb_flags))
return 0;
kref_get(&req->wb_kref);
return 1;
return !test_and_set_bit(PG_BUSY, &req->wb_flags);
}
/**
* nfs_list_add_request - Insert a request into a list
* @req: request

224
include/linux/nfs_xdr.h
View File

@ -35,6 +35,15 @@ static inline int nfs_fsid_equal(const struct nfs_fsid *a, const struct nfs_fsid
return a->major == b->major && a->minor == b->minor;
}
struct nfs4_threshold {
__u32 bm;
__u32 l_type;
__u64 rd_sz;
__u64 wr_sz;
__u64 rd_io_sz;
__u64 wr_io_sz;
};
struct nfs_fattr {
unsigned int valid; /* which fields are valid */
umode_t mode;
@ -67,6 +76,7 @@ struct nfs_fattr {
unsigned long gencount;
struct nfs4_string *owner_name;
struct nfs4_string *group_name;
struct nfs4_threshold *mdsthreshold; /* pNFS threshold hints */
};
#define NFS_ATTR_FATTR_TYPE (1U << 0)
@ -106,14 +116,14 @@ struct nfs_fattr {
| NFS_ATTR_FATTR_FILEID \
| NFS_ATTR_FATTR_ATIME \
| NFS_ATTR_FATTR_MTIME \
| NFS_ATTR_FATTR_CTIME)
| NFS_ATTR_FATTR_CTIME \
| NFS_ATTR_FATTR_CHANGE)
#define NFS_ATTR_FATTR_V2 (NFS_ATTR_FATTR \
| NFS_ATTR_FATTR_BLOCKS_USED)
#define NFS_ATTR_FATTR_V3 (NFS_ATTR_FATTR \
| NFS_ATTR_FATTR_SPACE_USED)
#define NFS_ATTR_FATTR_V4 (NFS_ATTR_FATTR \
| NFS_ATTR_FATTR_SPACE_USED \
| NFS_ATTR_FATTR_CHANGE)
| NFS_ATTR_FATTR_SPACE_USED)
/*
* Info on the file system
@ -338,7 +348,6 @@ struct nfs_openargs {
const struct qstr * name;
const struct nfs_server *server; /* Needed for ID mapping */
const u32 * bitmask;
const u32 * dir_bitmask;
__u32 claim;
struct nfs4_sequence_args seq_args;
};
@ -349,7 +358,6 @@ struct nfs_openres {
struct nfs4_change_info cinfo;
__u32 rflags;
struct nfs_fattr * f_attr;
struct nfs_fattr * dir_attr;
struct nfs_seqid * seqid;
const struct nfs_server *server;
fmode_t delegation_type;
@ -518,13 +526,30 @@ struct nfs_writeres {
struct nfs4_sequence_res seq_res;
};
/*
* Arguments to the commit call.
*/
struct nfs_commitargs {
struct nfs_fh *fh;
__u64 offset;
__u32 count;
const u32 *bitmask;
struct nfs4_sequence_args seq_args;
};
struct nfs_commitres {
struct nfs_fattr *fattr;
struct nfs_writeverf *verf;
const struct nfs_server *server;
struct nfs4_sequence_res seq_res;
};
/*
* Common arguments to the unlink call
*/
struct nfs_removeargs {
const struct nfs_fh *fh;
struct qstr name;
const u32 * bitmask;
struct nfs4_sequence_args seq_args;
};
@ -543,7 +568,6 @@ struct nfs_renameargs {
const struct nfs_fh *new_dir;
const struct qstr *old_name;
const struct qstr *new_name;
const u32 *bitmask;
struct nfs4_sequence_args seq_args;
};
@ -839,7 +863,6 @@ struct nfs4_create_res {
struct nfs_fh * fh;
struct nfs_fattr * fattr;
struct nfs4_change_info dir_cinfo;
struct nfs_fattr * dir_fattr;
struct nfs4_sequence_res seq_res;
};
@ -1061,6 +1084,21 @@ struct nfstime4 {
};
#ifdef CONFIG_NFS_V4_1
struct pnfs_commit_bucket {
struct list_head written;
struct list_head committing;
struct pnfs_layout_segment *wlseg;
struct pnfs_layout_segment *clseg;
};
struct pnfs_ds_commit_info {
int nwritten;
int ncommitting;
int nbuckets;
struct pnfs_commit_bucket *buckets;
};
#define NFS4_EXCHANGE_ID_LEN (48)
struct nfs41_exchange_id_args {
struct nfs_client *client;
@ -1070,13 +1108,13 @@ struct nfs41_exchange_id_args {
u32 flags;
};
struct server_owner {
struct nfs41_server_owner {
uint64_t minor_id;
uint32_t major_id_sz;
char major_id[NFS4_OPAQUE_LIMIT];
};
struct server_scope {
struct nfs41_server_scope {
uint32_t server_scope_sz;
char server_scope[NFS4_OPAQUE_LIMIT];
};
@ -1087,10 +1125,18 @@ struct nfs41_impl_id {
struct nfstime4 date;
};
struct nfs41_bind_conn_to_session_res {
struct nfs4_session *session;
u32 dir;
bool use_conn_in_rdma_mode;
};
struct nfs41_exchange_id_res {
struct nfs_client *client;
u64 clientid;
u32 seqid;
u32 flags;
struct server_scope *server_scope;
struct nfs41_server_owner *server_owner;
struct nfs41_server_scope *server_scope;
struct nfs41_impl_id *impl_id;
};
@ -1143,35 +1189,114 @@ struct nfs41_free_stateid_res {
struct nfs4_sequence_res seq_res;
};
#else
struct pnfs_ds_commit_info {
};
#endif /* CONFIG_NFS_V4_1 */
struct nfs_page;
#define NFS_PAGEVEC_SIZE (8U)
struct nfs_read_data {
struct rpc_task task;
struct inode *inode;
struct rpc_cred *cred;
struct nfs_fattr fattr; /* fattr storage */
struct list_head pages; /* Coalesced read requests */
struct list_head list; /* lists of struct nfs_read_data */
struct nfs_page *req; /* multi ops per nfs_page */
struct nfs_page_array {
struct page **pagevec;
unsigned int npages; /* Max length of pagevec */
struct nfs_readargs args;
struct nfs_readres res;
unsigned long timestamp; /* For lease renewal */
struct pnfs_layout_segment *lseg;
struct nfs_client *ds_clp; /* pNFS data server */
const struct rpc_call_ops *mds_ops;
int (*read_done_cb) (struct rpc_task *task, struct nfs_read_data *data);
__u64 mds_offset;
int pnfs_error;
unsigned int npages; /* Max length of pagevec */
struct page *page_array[NFS_PAGEVEC_SIZE];
};
struct nfs_read_data {
struct nfs_pgio_header *header;
struct list_head list;
struct rpc_task task;
struct nfs_fattr fattr; /* fattr storage */
struct nfs_readargs args;
struct nfs_readres res;
unsigned long timestamp; /* For lease renewal */
int (*read_done_cb) (struct rpc_task *task, struct nfs_read_data *data);
__u64 mds_offset;
struct nfs_page_array pages;
struct nfs_client *ds_clp; /* pNFS data server */
};
/* used as flag bits in nfs_pgio_header */
enum {
NFS_IOHDR_ERROR = 0,
NFS_IOHDR_EOF,
NFS_IOHDR_REDO,
NFS_IOHDR_NEED_COMMIT,
NFS_IOHDR_NEED_RESCHED,
};
struct nfs_pgio_header {
struct inode *inode;
struct rpc_cred *cred;
struct list_head pages;
struct list_head rpc_list;
atomic_t refcnt;
struct nfs_page *req;
struct pnfs_layout_segment *lseg;
loff_t io_start;
const struct rpc_call_ops *mds_ops;
void (*release) (struct nfs_pgio_header *hdr);
const struct nfs_pgio_completion_ops *completion_ops;
struct nfs_direct_req *dreq;
spinlock_t lock;
/* fields protected by lock */
int pnfs_error;
int error; /* merge with pnfs_error */
unsigned long good_bytes; /* boundary of good data */
unsigned long flags;
};
struct nfs_read_header {
struct nfs_pgio_header header;
struct nfs_read_data rpc_data;
};
struct nfs_write_data {
struct nfs_pgio_header *header;
struct list_head list;
struct rpc_task task;
struct nfs_fattr fattr;
struct nfs_writeverf verf;
struct nfs_writeargs args; /* argument struct */
struct nfs_writeres res; /* result struct */
unsigned long timestamp; /* For lease renewal */
int (*write_done_cb) (struct rpc_task *task, struct nfs_write_data *data);
__u64 mds_offset; /* Filelayout dense stripe */
struct nfs_page_array pages;
struct nfs_client *ds_clp; /* pNFS data server */
};
struct nfs_write_header {
struct nfs_pgio_header header;
struct nfs_write_data rpc_data;
};
struct nfs_mds_commit_info {
atomic_t rpcs_out;
unsigned long ncommit;
struct list_head list;
};
struct nfs_commit_data;
struct nfs_inode;
struct nfs_commit_completion_ops {
void (*error_cleanup) (struct nfs_inode *nfsi);
void (*completion) (struct nfs_commit_data *data);
};
struct nfs_commit_info {
spinlock_t *lock;
struct nfs_mds_commit_info *mds;
struct pnfs_ds_commit_info *ds;
struct nfs_direct_req *dreq; /* O_DIRECT request */
const struct nfs_commit_completion_ops *completion_ops;
};
struct nfs_commit_data {
struct rpc_task task;
struct inode *inode;
struct rpc_cred *cred;
@ -1179,22 +1304,22 @@ struct nfs_write_data {
struct nfs_writeverf verf;
struct list_head pages; /* Coalesced requests we wish to flush */
struct list_head list; /* lists of struct nfs_write_data */
struct nfs_page *req; /* multi ops per nfs_page */
struct page **pagevec;
unsigned int npages; /* Max length of pagevec */
struct nfs_writeargs args; /* argument struct */
struct nfs_writeres res; /* result struct */
struct nfs_direct_req *dreq; /* O_DIRECT request */
struct nfs_commitargs args; /* argument struct */
struct nfs_commitres res; /* result struct */
struct nfs_open_context *context;
struct pnfs_layout_segment *lseg;
struct nfs_client *ds_clp; /* pNFS data server */
int ds_commit_index;
const struct rpc_call_ops *mds_ops;
int (*write_done_cb) (struct rpc_task *task, struct nfs_write_data *data);
#ifdef CONFIG_NFS_V4
unsigned long timestamp; /* For lease renewal */
#endif
__u64 mds_offset; /* Filelayout dense stripe */
int pnfs_error;
struct page *page_array[NFS_PAGEVEC_SIZE];
const struct nfs_commit_completion_ops *completion_ops;
int (*commit_done_cb) (struct rpc_task *task, struct nfs_commit_data *data);
};
struct nfs_pgio_completion_ops {
void (*error_cleanup)(struct list_head *head);
void (*init_hdr)(struct nfs_pgio_header *hdr);
void (*completion)(struct nfs_pgio_header *hdr);
};
struct nfs_unlinkdata {
@ -1234,11 +1359,13 @@ struct nfs_rpc_ops {
int (*getroot) (struct nfs_server *, struct nfs_fh *,
struct nfs_fsinfo *);
struct vfsmount *(*submount) (struct nfs_server *, struct dentry *,
struct nfs_fh *, struct nfs_fattr *);
int (*getattr) (struct nfs_server *, struct nfs_fh *,
struct nfs_fattr *);
int (*setattr) (struct dentry *, struct nfs_fattr *,
struct iattr *);
int (*lookup) (struct rpc_clnt *clnt, struct inode *, struct qstr *,
int (*lookup) (struct inode *, struct qstr *,
struct nfs_fh *, struct nfs_fattr *);
int (*access) (struct inode *, struct nfs_access_entry *);
int (*readlink)(struct inode *, struct page *, unsigned int,
@ -1277,8 +1404,9 @@ struct nfs_rpc_ops {
void (*write_setup) (struct nfs_write_data *, struct rpc_message *);
void (*write_rpc_prepare)(struct rpc_task *, struct nfs_write_data *);
int (*write_done) (struct rpc_task *, struct nfs_write_data *);
void (*commit_setup) (struct nfs_write_data *, struct rpc_message *);
int (*commit_done) (struct rpc_task *, struct nfs_write_data *);
void (*commit_setup) (struct nfs_commit_data *, struct rpc_message *);
void (*commit_rpc_prepare)(struct rpc_task *, struct nfs_commit_data *);
int (*commit_done) (struct rpc_task *, struct nfs_commit_data *);
int (*lock)(struct file *, int, struct file_lock *);
int (*lock_check_bounds)(const struct file_lock *);
void (*clear_acl_cache)(struct inode *);
@ -1287,9 +1415,9 @@ struct nfs_rpc_ops {
struct nfs_open_context *ctx,
int open_flags,
struct iattr *iattr);
int (*init_client) (struct nfs_client *, const struct rpc_timeout *,
const char *, rpc_authflavor_t, int);
int (*secinfo)(struct inode *, const struct qstr *, struct nfs4_secinfo_flavors *);
struct nfs_client *
(*init_client) (struct nfs_client *, const struct rpc_timeout *,
const char *, rpc_authflavor_t);
};
/*

2
net/sunrpc/clnt.c
View File

@ -1286,6 +1286,8 @@ call_reserveresult(struct rpc_task *task)
}
switch (status) {
case -ENOMEM:
rpc_delay(task, HZ >> 2);
case -EAGAIN: /* woken up; retry */
task->tk_action = call_reserve;
return;

10
net/sunrpc/rpc_pipe.c
View File

@ -120,7 +120,7 @@ EXPORT_SYMBOL_GPL(rpc_pipe_generic_upcall);
/**
* rpc_queue_upcall - queue an upcall message to userspace
* @inode: inode of upcall pipe on which to queue given message
* @pipe: upcall pipe on which to queue given message
* @msg: message to queue
*
* Call with an @inode created by rpc_mkpipe() to queue an upcall.
@ -819,9 +819,7 @@ static int rpc_rmdir_depopulate(struct dentry *dentry,
* @parent: dentry of directory to create new "pipe" in
* @name: name of pipe
* @private: private data to associate with the pipe, for the caller's use
* @ops: operations defining the behavior of the pipe: upcall, downcall,
* release_pipe, open_pipe, and destroy_msg.
* @flags: rpc_pipe flags
* @pipe: &rpc_pipe containing input parameters
*
* Data is made available for userspace to read by calls to
* rpc_queue_upcall(). The actual reads will result in calls to
@ -943,7 +941,7 @@ struct dentry *rpc_create_client_dir(struct dentry *dentry,
/**
* rpc_remove_client_dir - Remove a directory created with rpc_create_client_dir()
* @clnt: rpc client
* @dentry: dentry for the pipe
*/
int rpc_remove_client_dir(struct dentry *dentry)
{
@ -1115,7 +1113,7 @@ rpc_fill_super(struct super_block *sb, void *data, int silent)
sb->s_op = &s_ops;
sb->s_time_gran = 1;
inode = rpc_get_inode(sb, S_IFDIR | 0755);
inode = rpc_get_inode(sb, S_IFDIR | S_IRUGO | S_IXUGO);
sb->s_root = root = d_make_root(inode);
if (!root)
return -ENOMEM;

2
net/sunrpc/rpcb_clnt.c
View File

@ -394,6 +394,7 @@ static int rpcb_register_call(struct rpc_clnt *clnt, struct rpc_message *msg)
/**
* rpcb_register - set or unset a port registration with the local rpcbind svc
* @net: target network namespace
* @prog: RPC program number to bind
* @vers: RPC version number to bind
* @prot: transport protocol to register
@ -521,6 +522,7 @@ static int rpcb_unregister_all_protofamilies(struct sunrpc_net *sn,
/**
* rpcb_v4_register - set or unset a port registration with the local rpcbind
* @net: target network namespace
* @program: RPC program number of service to (un)register
* @version: RPC version number of service to (un)register
* @address: address family, IP address, and port to (un)register

7
net/sunrpc/xprt.c
View File

@ -979,20 +979,21 @@ static void xprt_alloc_slot(struct rpc_task *task)
list_del(&req->rq_list);
goto out_init_req;
}
req = xprt_dynamic_alloc_slot(xprt, GFP_NOWAIT);
req = xprt_dynamic_alloc_slot(xprt, GFP_NOWAIT|__GFP_NOWARN);
if (!IS_ERR(req))
goto out_init_req;
switch (PTR_ERR(req)) {
case -ENOMEM:
rpc_delay(task, HZ >> 2);
dprintk("RPC: dynamic allocation of request slot "
"failed! Retrying\n");
task->tk_status = -ENOMEM;
break;
case -EAGAIN:
rpc_sleep_on(&xprt->backlog, task, NULL);
dprintk("RPC: waiting for request slot\n");
default:
task->tk_status = -EAGAIN;
}
task->tk_status = -EAGAIN;
return;
out_init_req:
task->tk_status = 0;