Merge branch 'patches_cel-for-2.6.32' into nfs-for-2.6.32
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index dd1a6d4..2f18206 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -2391,6 +2391,18 @@
stifb= [HW]
Format: bpp:<bpp1>[:<bpp2>[:<bpp3>...]]
+ sunrpc.min_resvport=
+ sunrpc.max_resvport=
+ [NFS,SUNRPC]
+ SunRPC servers often require that client requests
+ originate from a privileged port (i.e. a port in the
+ range 0 < portnr < 1024).
+ An administrator who wishes to reserve some of these
+ ports for other uses may adjust the range that the
+ kernel's sunrpc client considers to be privileged
+ using these two parameters to set the minimum and
+ maximum port values.
+
sunrpc.pool_mode=
[NFS]
Control how the NFS server code allocates CPUs to
@@ -2407,6 +2419,15 @@
pernode one pool for each NUMA node (equivalent
to global on non-NUMA machines)
+ sunrpc.tcp_slot_table_entries=
+ sunrpc.udp_slot_table_entries=
+ [NFS,SUNRPC]
+ Sets the upper limit on the number of simultaneous
+ RPC calls that can be sent from the client to a
+ server. Increasing these values may allow you to
+ improve throughput, but will also increase the
+ amount of memory reserved for use by the client.
+
swiotlb= [IA-64] Number of I/O TLB slabs
switches= [HW,M68k]
diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c
index 7f604c7..293fa05 100644
--- a/fs/nfs/callback.c
+++ b/fs/nfs/callback.c
@@ -43,21 +43,29 @@
unsigned int nfs_callback_set_tcpport;
unsigned short nfs_callback_tcpport;
unsigned short nfs_callback_tcpport6;
-static const int nfs_set_port_min = 0;
-static const int nfs_set_port_max = 65535;
+#define NFS_CALLBACK_MAXPORTNR (65535U)
-static int param_set_port(const char *val, struct kernel_param *kp)
+static int param_set_portnr(const char *val, struct kernel_param *kp)
{
- char *endp;
- int num = simple_strtol(val, &endp, 0);
- if (endp == val || *endp || num < nfs_set_port_min || num > nfs_set_port_max)
+ unsigned long num;
+ int ret;
+
+ if (!val)
return -EINVAL;
- *((int *)kp->arg) = num;
+ ret = strict_strtoul(val, 0, &num);
+ if (ret == -EINVAL || num > NFS_CALLBACK_MAXPORTNR)
+ return -EINVAL;
+ *((unsigned int *)kp->arg) = num;
return 0;
}
-module_param_call(callback_tcpport, param_set_port, param_get_int,
- &nfs_callback_set_tcpport, 0644);
+static int param_get_portnr(char *buffer, struct kernel_param *kp)
+{
+ return param_get_uint(buffer, kp);
+}
+#define param_check_portnr(name, p) __param_check(name, p, unsigned int);
+
+module_param_named(callback_tcpport, nfs_callback_set_tcpport, portnr, 0644);
/*
* This is the NFSv4 callback kernel thread.
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index 8d25ccb..d36925f 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -809,6 +809,9 @@
/* Initialise the client representation from the mount data */
server->flags = data->flags;
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;
if (data->rsize)
server->rsize = nfs_block_size(data->rsize, NULL);
@@ -1074,10 +1077,6 @@
(unsigned long long) server->fsid.major,
(unsigned long long) server->fsid.minor);
- BUG_ON(!server->nfs_client);
- BUG_ON(!server->nfs_client->rpc_ops);
- BUG_ON(!server->nfs_client->rpc_ops->file_inode_ops);
-
spin_lock(&nfs_client_lock);
list_add_tail(&server->client_link, &server->nfs_client->cl_superblocks);
list_add_tail(&server->master_link, &nfs_volume_list);
@@ -1274,7 +1273,7 @@
/* Initialise the client representation from the mount data */
server->flags = data->flags;
- server->caps |= NFS_CAP_ATOMIC_OPEN;
+ server->caps |= NFS_CAP_ATOMIC_OPEN|NFS_CAP_CHANGE_ATTR;
server->options = data->options;
/* Get a client record */
@@ -1359,10 +1358,6 @@
if (server->namelen == 0 || server->namelen > NFS4_MAXNAMLEN)
server->namelen = NFS4_MAXNAMLEN;
- BUG_ON(!server->nfs_client);
- BUG_ON(!server->nfs_client->rpc_ops);
- BUG_ON(!server->nfs_client->rpc_ops->file_inode_ops);
-
spin_lock(&nfs_client_lock);
list_add_tail(&server->client_link, &server->nfs_client->cl_superblocks);
list_add_tail(&server->master_link, &nfs_volume_list);
@@ -1400,7 +1395,7 @@
/* Initialise the client representation from the parent server */
nfs_server_copy_userdata(server, parent_server);
- server->caps |= NFS_CAP_ATOMIC_OPEN;
+ server->caps |= NFS_CAP_ATOMIC_OPEN|NFS_CAP_CHANGE_ATTR;
/* Get a client representation.
* Note: NFSv4 always uses TCP, */
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 0506232..5021b75 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -328,6 +328,42 @@
}
/*
+ * Decide whether a read/modify/write cycle may be more efficient
+ * then a modify/write/read cycle when writing to a page in the
+ * page cache.
+ *
+ * The modify/write/read cycle may occur if a page is read before
+ * being completely filled by the writer. In this situation, the
+ * page must be completely written to stable storage on the server
+ * before it can be refilled by reading in the page from the server.
+ * This can lead to expensive, small, FILE_SYNC mode writes being
+ * done.
+ *
+ * It may be more efficient to read the page first if the file is
+ * open for reading in addition to writing, the page is not marked
+ * as Uptodate, it is not dirty or waiting to be committed,
+ * indicating that it was previously allocated and then modified,
+ * that there were valid bytes of data in that range of the file,
+ * and that the new data won't completely replace the old data in
+ * that range of the file.
+ */
+static int nfs_want_read_modify_write(struct file *file, struct page *page,
+ loff_t pos, unsigned len)
+{
+ unsigned int pglen = nfs_page_length(page);
+ unsigned int offset = pos & (PAGE_CACHE_SIZE - 1);
+ unsigned int end = offset + len;
+
+ if ((file->f_mode & FMODE_READ) && /* open for read? */
+ !PageUptodate(page) && /* Uptodate? */
+ !PagePrivate(page) && /* i/o request already? */
+ pglen && /* valid bytes of file? */
+ (end < pglen || offset)) /* replace all valid bytes? */
+ return 1;
+ return 0;
+}
+
+/*
* This does the "real" work of the write. We must allocate and lock the
* page to be sent back to the generic routine, which then copies the
* data from user space.
@@ -340,15 +376,16 @@
struct page **pagep, void **fsdata)
{
int ret;
- pgoff_t index;
+ pgoff_t index = pos >> PAGE_CACHE_SHIFT;
struct page *page;
- index = pos >> PAGE_CACHE_SHIFT;
+ int once_thru = 0;
dfprintk(PAGECACHE, "NFS: write_begin(%s/%s(%ld), %u@%lld)\n",
file->f_path.dentry->d_parent->d_name.name,
file->f_path.dentry->d_name.name,
mapping->host->i_ino, len, (long long) pos);
+start:
/*
* Prevent starvation issues if someone is doing a consistency
* sync-to-disk
@@ -367,6 +404,13 @@
if (ret) {
unlock_page(page);
page_cache_release(page);
+ } else if (!once_thru &&
+ nfs_want_read_modify_write(file, page, pos, len)) {
+ once_thru = 1;
+ ret = nfs_readpage(file, page);
+ page_cache_release(page);
+ if (!ret)
+ goto start;
}
return ret;
}
@@ -479,6 +523,7 @@
.invalidatepage = nfs_invalidate_page,
.releasepage = nfs_release_page,
.direct_IO = nfs_direct_IO,
+ .migratepage = nfs_migrate_page,
.launder_page = nfs_launder_page,
};
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index bd7938e..fe5a8b4 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -286,6 +286,11 @@
/* We can't support update_atime(), since the server will reset it */
inode->i_flags |= S_NOATIME|S_NOCMTIME;
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;
/* Why so? Because we want revalidate for devices/FIFOs, and
* that's precisely what we have in nfs_file_inode_operations.
*/
@@ -330,20 +335,46 @@
nfsi->attr_gencount = fattr->gencount;
if (fattr->valid & NFS_ATTR_FATTR_ATIME)
inode->i_atime = fattr->atime;
+ else if (nfs_server_capable(inode, NFS_CAP_ATIME))
+ nfsi->cache_validity |= NFS_INO_INVALID_ATTR;
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;
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;
if (fattr->valid & NFS_ATTR_FATTR_CHANGE)
nfsi->change_attr = fattr->change_attr;
+ else if (nfs_server_capable(inode, NFS_CAP_CHANGE_ATTR))
+ nfsi->cache_validity |= NFS_INO_INVALID_ATTR
+ | NFS_INO_INVALID_DATA;
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)
inode->i_nlink = fattr->nlink;
+ else if (nfs_server_capable(inode, NFS_CAP_NLINK))
+ nfsi->cache_validity |= NFS_INO_INVALID_ATTR;
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;
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;
if (fattr->valid & NFS_ATTR_FATTR_BLOCKS_USED)
inode->i_blocks = fattr->du.nfs2.blocks;
if (fattr->valid & NFS_ATTR_FATTR_SPACE_USED) {
@@ -1145,6 +1176,7 @@
loff_t cur_isize, new_isize;
unsigned long invalid = 0;
unsigned long now = jiffies;
+ unsigned long save_cache_validity;
dfprintk(VFS, "NFS: %s(%s/%ld ct=%d info=0x%x)\n",
__func__, inode->i_sb->s_id, inode->i_ino,
@@ -1171,10 +1203,11 @@
*/
nfsi->read_cache_jiffies = fattr->time_start;
- if ((fattr->valid & NFS_ATTR_FATTR_CHANGE) || (fattr->valid & (NFS_ATTR_FATTR_MTIME|NFS_ATTR_FATTR_CTIME)))
- nfsi->cache_validity &= ~(NFS_INO_INVALID_ATTR
- | NFS_INO_INVALID_ATIME
- | NFS_INO_REVAL_PAGECACHE);
+ save_cache_validity = nfsi->cache_validity;
+ nfsi->cache_validity &= ~(NFS_INO_INVALID_ATTR
+ | NFS_INO_INVALID_ATIME
+ | NFS_INO_REVAL_FORCED
+ | NFS_INO_REVAL_PAGECACHE);
/* Do atomic weak cache consistency updates */
nfs_wcc_update_inode(inode, fattr);
@@ -1189,7 +1222,8 @@
nfs_force_lookup_revalidate(inode);
nfsi->change_attr = fattr->change_attr;
}
- }
+ } else if (server->caps & NFS_CAP_CHANGE_ATTR)
+ invalid |= save_cache_validity;
if (fattr->valid & NFS_ATTR_FATTR_MTIME) {
/* NFSv2/v3: Check if the mtime agrees */
@@ -1201,7 +1235,12 @@
nfs_force_lookup_revalidate(inode);
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)) {
@@ -1215,7 +1254,11 @@
}
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 */
if (fattr->valid & NFS_ATTR_FATTR_SIZE) {
@@ -1231,30 +1274,50 @@
dprintk("NFS: isize change on server for file %s/%ld\n",
inode->i_sb->s_id, inode->i_ino);
}
- }
+ } else
+ invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR
+ | NFS_INO_REVAL_PAGECACHE
+ | NFS_INO_REVAL_FORCED);
if (fattr->valid & NFS_ATTR_FATTR_ATIME)
memcpy(&inode->i_atime, &fattr->atime, sizeof(inode->i_atime));
+ else if (server->caps & NFS_CAP_ATIME)
+ invalid |= save_cache_validity & (NFS_INO_INVALID_ATIME
+ | NFS_INO_REVAL_FORCED);
if (fattr->valid & NFS_ATTR_FATTR_MODE) {
if ((inode->i_mode & S_IALLUGO) != (fattr->mode & S_IALLUGO)) {
invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL;
inode->i_mode = fattr->mode;
}
- }
+ } else if (server->caps & NFS_CAP_MODE)
+ invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR
+ | NFS_INO_INVALID_ACCESS
+ | NFS_INO_INVALID_ACL
+ | NFS_INO_REVAL_FORCED);
+
if (fattr->valid & NFS_ATTR_FATTR_OWNER) {
if (inode->i_uid != fattr->uid) {
invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL;
inode->i_uid = fattr->uid;
}
- }
+ } else if (server->caps & NFS_CAP_OWNER)
+ invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR
+ | NFS_INO_INVALID_ACCESS
+ | NFS_INO_INVALID_ACL
+ | NFS_INO_REVAL_FORCED);
+
if (fattr->valid & NFS_ATTR_FATTR_GROUP) {
if (inode->i_gid != fattr->gid) {
invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL;
inode->i_gid = fattr->gid;
}
- }
+ } else if (server->caps & NFS_CAP_OWNER_GROUP)
+ invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR
+ | NFS_INO_INVALID_ACCESS
+ | NFS_INO_INVALID_ACL
+ | NFS_INO_REVAL_FORCED);
if (fattr->valid & NFS_ATTR_FATTR_NLINK) {
if (inode->i_nlink != fattr->nlink) {
@@ -1263,7 +1326,9 @@
invalid |= NFS_INO_INVALID_DATA;
inode->i_nlink = fattr->nlink;
}
- }
+ } else if (server->caps & NFS_CAP_NLINK)
+ invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR
+ | NFS_INO_REVAL_FORCED);
if (fattr->valid & NFS_ATTR_FATTR_SPACE_USED) {
/*
@@ -1293,9 +1358,8 @@
|| S_ISLNK(inode->i_mode)))
invalid &= ~NFS_INO_INVALID_DATA;
if (!nfs_have_delegation(inode, FMODE_READ) ||
- (nfsi->cache_validity & NFS_INO_REVAL_FORCED))
+ (save_cache_validity & NFS_INO_REVAL_FORCED))
nfsi->cache_validity |= invalid;
- nfsi->cache_validity &= ~NFS_INO_REVAL_FORCED;
return 0;
out_changed:
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index c2f171a..2e48567 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -248,6 +248,12 @@
/* write.c */
extern void nfs_write_prepare(struct rpc_task *task, void *calldata);
+#ifdef CONFIG_MIGRATION
+extern int nfs_migrate_page(struct address_space *,
+ struct page *, struct page *);
+#else
+#define nfs_migrate_page NULL
+#endif
/* nfs4proc.c */
extern int _nfs4_call_sync(struct nfs_server *server,
diff --git a/fs/nfs/mount_clnt.c b/fs/nfs/mount_clnt.c
index 72dd8b6..0adefc4 100644
--- a/fs/nfs/mount_clnt.c
+++ b/fs/nfs/mount_clnt.c
@@ -323,7 +323,7 @@
return -EIO;
status = ntohl(*p);
- for (i = 0; i <= ARRAY_SIZE(mnt_errtbl); i++) {
+ for (i = 0; i < ARRAY_SIZE(mnt_errtbl); i++) {
if (mnt_errtbl[i].status == status) {
res->errno = mnt_errtbl[i].errno;
return 0;
@@ -374,7 +374,7 @@
return -EIO;
status = ntohl(*p);
- for (i = 0; i <= ARRAY_SIZE(mnt3_errtbl); i++) {
+ for (i = 0; i < ARRAY_SIZE(mnt3_errtbl); i++) {
if (mnt3_errtbl[i].status == status) {
res->errno = mnt3_errtbl[i].errno;
return 0;
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 6917311..be6544a 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -61,6 +61,8 @@
#define NFS4_POLL_RETRY_MIN (HZ/10)
#define NFS4_POLL_RETRY_MAX (15*HZ)
+#define NFS4_MAX_LOOP_ON_RECOVER (10)
+
struct nfs4_opendata;
static int _nfs4_proc_open(struct nfs4_opendata *data);
static int nfs4_do_fsinfo(struct nfs_server *, struct nfs_fh *, struct nfs_fsinfo *);
@@ -426,17 +428,19 @@
static int nfs4_recover_session(struct nfs4_session *session)
{
struct nfs_client *clp = session->clp;
+ unsigned int loop;
int ret;
- for (;;) {
+ for (loop = NFS4_MAX_LOOP_ON_RECOVER; loop != 0; loop--) {
ret = nfs4_wait_clnt_recover(clp);
if (ret != 0)
- return ret;
+ break;
if (!test_bit(NFS4CLNT_SESSION_SETUP, &clp->cl_state))
break;
nfs4_schedule_state_manager(clp);
+ ret = -EIO;
}
- return 0;
+ return ret;
}
static int nfs41_setup_sequence(struct nfs4_session *session,
@@ -1444,18 +1448,20 @@
static int nfs4_recover_expired_lease(struct nfs_server *server)
{
struct nfs_client *clp = server->nfs_client;
+ unsigned int loop;
int ret;
- for (;;) {
+ for (loop = NFS4_MAX_LOOP_ON_RECOVER; loop != 0; loop--) {
ret = nfs4_wait_clnt_recover(clp);
if (ret != 0)
- return ret;
+ break;
if (!test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state) &&
!test_bit(NFS4CLNT_CHECK_LEASE,&clp->cl_state))
break;
nfs4_schedule_state_recovery(clp);
+ ret = -EIO;
}
- return 0;
+ return ret;
}
/*
@@ -1997,12 +2003,34 @@
status = nfs4_call_sync(server, &msg, &args, &res, 0);
if (status == 0) {
memcpy(server->attr_bitmask, res.attr_bitmask, sizeof(server->attr_bitmask));
+ server->caps &= ~(NFS_CAP_ACLS|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);
if (res.attr_bitmask[0] & FATTR4_WORD0_ACL)
server->caps |= NFS_CAP_ACLS;
if (res.has_links != 0)
server->caps |= NFS_CAP_HARDLINKS;
if (res.has_symlinks != 0)
server->caps |= NFS_CAP_SYMLINKS;
+ if (res.attr_bitmask[0] & FATTR4_WORD0_FILEID)
+ server->caps |= NFS_CAP_FILEID;
+ if (res.attr_bitmask[1] & FATTR4_WORD1_MODE)
+ server->caps |= NFS_CAP_MODE;
+ if (res.attr_bitmask[1] & FATTR4_WORD1_NUMLINKS)
+ server->caps |= NFS_CAP_NLINK;
+ if (res.attr_bitmask[1] & FATTR4_WORD1_OWNER)
+ server->caps |= NFS_CAP_OWNER;
+ if (res.attr_bitmask[1] & FATTR4_WORD1_OWNER_GROUP)
+ server->caps |= NFS_CAP_OWNER_GROUP;
+ if (res.attr_bitmask[1] & FATTR4_WORD1_TIME_ACCESS)
+ server->caps |= NFS_CAP_ATIME;
+ if (res.attr_bitmask[1] & FATTR4_WORD1_TIME_METADATA)
+ server->caps |= NFS_CAP_CTIME;
+ if (res.attr_bitmask[1] & FATTR4_WORD1_TIME_MODIFY)
+ server->caps |= NFS_CAP_MTIME;
+
memcpy(server->cache_consistency_bitmask, res.attr_bitmask, sizeof(server->cache_consistency_bitmask));
server->cache_consistency_bitmask[0] &= FATTR4_WORD0_CHANGE|FATTR4_WORD0_SIZE;
server->cache_consistency_bitmask[1] &= FATTR4_WORD1_TIME_METADATA|FATTR4_WORD1_TIME_MODIFY;
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 617273e..e65cc2e 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -3075,7 +3075,8 @@
return ret;
}
-static int decode_attr_owner(struct xdr_stream *xdr, uint32_t *bitmap, struct nfs_client *clp, uint32_t *uid)
+static int decode_attr_owner(struct xdr_stream *xdr, uint32_t *bitmap,
+ struct nfs_client *clp, uint32_t *uid, int may_sleep)
{
uint32_t len;
__be32 *p;
@@ -3088,7 +3089,9 @@
READ_BUF(4);
READ32(len);
READ_BUF(len);
- if (len < XDR_MAX_NETOBJ) {
+ if (!may_sleep) {
+ /* do nothing */
+ } else if (len < XDR_MAX_NETOBJ) {
if (nfs_map_name_to_uid(clp, (char *)p, len, uid) == 0)
ret = NFS_ATTR_FATTR_OWNER;
else
@@ -3103,7 +3106,8 @@
return ret;
}
-static int decode_attr_group(struct xdr_stream *xdr, uint32_t *bitmap, struct nfs_client *clp, uint32_t *gid)
+static int decode_attr_group(struct xdr_stream *xdr, uint32_t *bitmap,
+ struct nfs_client *clp, uint32_t *gid, int may_sleep)
{
uint32_t len;
__be32 *p;
@@ -3116,7 +3120,9 @@
READ_BUF(4);
READ32(len);
READ_BUF(len);
- if (len < XDR_MAX_NETOBJ) {
+ if (!may_sleep) {
+ /* do nothing */
+ } else if (len < XDR_MAX_NETOBJ) {
if (nfs_map_group_to_gid(clp, (char *)p, len, gid) == 0)
ret = NFS_ATTR_FATTR_GROUP;
else
@@ -3466,7 +3472,8 @@
return status;
}
-static int decode_getfattr(struct xdr_stream *xdr, struct nfs_fattr *fattr, const struct nfs_server *server)
+static int decode_getfattr(struct xdr_stream *xdr, struct nfs_fattr *fattr,
+ const struct nfs_server *server, int may_sleep)
{
__be32 *savep;
uint32_t attrlen,
@@ -3538,12 +3545,14 @@
goto xdr_error;
fattr->valid |= status;
- status = decode_attr_owner(xdr, bitmap, server->nfs_client, &fattr->uid);
+ status = decode_attr_owner(xdr, bitmap, server->nfs_client,
+ &fattr->uid, may_sleep);
if (status < 0)
goto xdr_error;
fattr->valid |= status;
- status = decode_attr_group(xdr, bitmap, server->nfs_client, &fattr->gid);
+ status = decode_attr_group(xdr, bitmap, server->nfs_client,
+ &fattr->gid, may_sleep);
if (status < 0)
goto xdr_error;
fattr->valid |= status;
@@ -4370,7 +4379,8 @@
status = decode_open_downgrade(&xdr, res);
if (status != 0)
goto out;
- decode_getfattr(&xdr, res->fattr, res->server);
+ decode_getfattr(&xdr, res->fattr, res->server,
+ !RPC_IS_ASYNC(rqstp->rq_task));
out:
return status;
}
@@ -4397,7 +4407,8 @@
status = decode_access(&xdr, res);
if (status != 0)
goto out;
- decode_getfattr(&xdr, res->fattr, res->server);
+ decode_getfattr(&xdr, res->fattr, res->server,
+ !RPC_IS_ASYNC(rqstp->rq_task));
out:
return status;
}
@@ -4424,7 +4435,8 @@
goto out;
if ((status = decode_getfh(&xdr, res->fh)) != 0)
goto out;
- status = decode_getfattr(&xdr, res->fattr, res->server);
+ status = decode_getfattr(&xdr, res->fattr, res->server
+ ,!RPC_IS_ASYNC(rqstp->rq_task));
out:
return status;
}
@@ -4448,7 +4460,8 @@
if ((status = decode_putrootfh(&xdr)) != 0)
goto out;
if ((status = decode_getfh(&xdr, res->fh)) == 0)
- status = decode_getfattr(&xdr, res->fattr, res->server);
+ status = decode_getfattr(&xdr, res->fattr, res->server,
+ !RPC_IS_ASYNC(rqstp->rq_task));
out:
return status;
}
@@ -4473,7 +4486,8 @@
goto out;
if ((status = decode_remove(&xdr, &res->cinfo)) != 0)
goto out;
- decode_getfattr(&xdr, &res->dir_attr, res->server);
+ decode_getfattr(&xdr, &res->dir_attr, res->server,
+ !RPC_IS_ASYNC(rqstp->rq_task));
out:
return status;
}
@@ -4503,11 +4517,13 @@
if ((status = decode_rename(&xdr, &res->old_cinfo, &res->new_cinfo)) != 0)
goto out;
/* Current FH is target directory */
- if (decode_getfattr(&xdr, res->new_fattr, res->server) != 0)
+ if (decode_getfattr(&xdr, res->new_fattr, res->server,
+ !RPC_IS_ASYNC(rqstp->rq_task)) != 0)
goto out;
if ((status = decode_restorefh(&xdr)) != 0)
goto out;
- decode_getfattr(&xdr, res->old_fattr, res->server);
+ decode_getfattr(&xdr, res->old_fattr, res->server,
+ !RPC_IS_ASYNC(rqstp->rq_task));
out:
return status;
}
@@ -4540,11 +4556,13 @@
* Note order: OP_LINK leaves the directory as the current
* filehandle.
*/
- if (decode_getfattr(&xdr, res->dir_attr, res->server) != 0)
+ if (decode_getfattr(&xdr, res->dir_attr, res->server,
+ !RPC_IS_ASYNC(rqstp->rq_task)) != 0)
goto out;
if ((status = decode_restorefh(&xdr)) != 0)
goto out;
- decode_getfattr(&xdr, res->fattr, res->server);
+ decode_getfattr(&xdr, res->fattr, res->server,
+ !RPC_IS_ASYNC(rqstp->rq_task));
out:
return status;
}
@@ -4573,11 +4591,13 @@
goto out;
if ((status = decode_getfh(&xdr, res->fh)) != 0)
goto out;
- if (decode_getfattr(&xdr, res->fattr, res->server) != 0)
+ if (decode_getfattr(&xdr, res->fattr, res->server,
+ !RPC_IS_ASYNC(rqstp->rq_task)) != 0)
goto out;
if ((status = decode_restorefh(&xdr)) != 0)
goto out;
- decode_getfattr(&xdr, res->dir_fattr, res->server);
+ decode_getfattr(&xdr, res->dir_fattr, res->server,
+ !RPC_IS_ASYNC(rqstp->rq_task));
out:
return status;
}
@@ -4609,7 +4629,8 @@
status = decode_putfh(&xdr);
if (status)
goto out;
- status = decode_getfattr(&xdr, res->fattr, res->server);
+ status = decode_getfattr(&xdr, res->fattr, res->server,
+ !RPC_IS_ASYNC(rqstp->rq_task));
out:
return status;
}
@@ -4716,7 +4737,8 @@
* an ESTALE error. Shouldn't be a problem,
* though, since fattr->valid will remain unset.
*/
- decode_getfattr(&xdr, res->fattr, res->server);
+ decode_getfattr(&xdr, res->fattr, res->server,
+ !RPC_IS_ASYNC(rqstp->rq_task));
out:
return status;
}
@@ -4748,11 +4770,13 @@
goto out;
if (decode_getfh(&xdr, &res->fh) != 0)
goto out;
- if (decode_getfattr(&xdr, res->f_attr, res->server) != 0)
+ if (decode_getfattr(&xdr, res->f_attr, res->server,
+ !RPC_IS_ASYNC(rqstp->rq_task)) != 0)
goto out;
if (decode_restorefh(&xdr) != 0)
goto out;
- decode_getfattr(&xdr, res->dir_attr, res->server);
+ decode_getfattr(&xdr, res->dir_attr, res->server,
+ !RPC_IS_ASYNC(rqstp->rq_task));
out:
return status;
}
@@ -4800,7 +4824,8 @@
status = decode_open(&xdr, res);
if (status)
goto out;
- decode_getfattr(&xdr, res->f_attr, res->server);
+ decode_getfattr(&xdr, res->f_attr, res->server,
+ !RPC_IS_ASYNC(rqstp->rq_task));
out:
return status;
}
@@ -4827,7 +4852,8 @@
status = decode_setattr(&xdr);
if (status)
goto out;
- decode_getfattr(&xdr, res->fattr, res->server);
+ decode_getfattr(&xdr, res->fattr, res->server,
+ !RPC_IS_ASYNC(rqstp->rq_task));
out:
return status;
}
@@ -5001,7 +5027,8 @@
status = decode_write(&xdr, res);
if (status)
goto out;
- decode_getfattr(&xdr, res->fattr, res->server);
+ decode_getfattr(&xdr, res->fattr, res->server,
+ !RPC_IS_ASYNC(rqstp->rq_task));
if (!status)
status = res->count;
out:
@@ -5030,7 +5057,8 @@
status = decode_commit(&xdr, res);
if (status)
goto out;
- decode_getfattr(&xdr, res->fattr, res->server);
+ decode_getfattr(&xdr, res->fattr, res->server,
+ !RPC_IS_ASYNC(rqstp->rq_task));
out:
return status;
}
@@ -5194,7 +5222,8 @@
if (status != 0)
goto out;
status = decode_delegreturn(&xdr);
- decode_getfattr(&xdr, res->fattr, res->server);
+ decode_getfattr(&xdr, res->fattr, res->server,
+ !RPC_IS_ASYNC(rqstp->rq_task));
out:
return status;
}
@@ -5222,7 +5251,8 @@
goto out;
xdr_enter_page(&xdr, PAGE_SIZE);
status = decode_getfattr(&xdr, &res->fs_locations->fattr,
- res->fs_locations->server);
+ res->fs_locations->server,
+ !RPC_IS_ASYNC(req->rq_task));
out:
return status;
}
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 0a0a2ff..6240e64 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -13,6 +13,7 @@
#include <linux/file.h>
#include <linux/writeback.h>
#include <linux/swap.h>
+#include <linux/migrate.h>
#include <linux/sunrpc/clnt.h>
#include <linux/nfs_fs.h>
@@ -26,6 +27,7 @@
#include "internal.h"
#include "iostat.h"
#include "nfs4_fs.h"
+#include "fscache.h"
#define NFSDBG_FACILITY NFSDBG_PAGECACHE
@@ -220,24 +222,17 @@
clear_bdi_congested(&nfss->backing_dev_info, BLK_RW_ASYNC);
}
-/*
- * Find an associated nfs write request, and prepare to flush it out
- * May return an error if the user signalled nfs_wait_on_request().
- */
-static int nfs_page_async_flush(struct nfs_pageio_descriptor *pgio,
- struct page *page)
+static struct nfs_page *nfs_find_and_lock_request(struct page *page)
{
struct inode *inode = page->mapping->host;
struct nfs_page *req;
int ret;
spin_lock(&inode->i_lock);
- for(;;) {
+ for (;;) {
req = nfs_page_find_request_locked(page);
- if (req == NULL) {
- spin_unlock(&inode->i_lock);
- return 0;
- }
+ if (req == NULL)
+ break;
if (nfs_set_page_tag_locked(req))
break;
/* Note: If we hold the page lock, as is the case in nfs_writepage,
@@ -249,23 +244,40 @@
ret = nfs_wait_on_request(req);
nfs_release_request(req);
if (ret != 0)
- return ret;
+ return ERR_PTR(ret);
spin_lock(&inode->i_lock);
}
- if (test_bit(PG_CLEAN, &req->wb_flags)) {
- spin_unlock(&inode->i_lock);
- BUG();
- }
- if (nfs_set_page_writeback(page) != 0) {
- spin_unlock(&inode->i_lock);
- BUG();
- }
spin_unlock(&inode->i_lock);
+ return req;
+}
+
+/*
+ * Find an associated nfs write request, and prepare to flush it out
+ * May return an error if the user signalled nfs_wait_on_request().
+ */
+static int nfs_page_async_flush(struct nfs_pageio_descriptor *pgio,
+ struct page *page)
+{
+ struct nfs_page *req;
+ int ret = 0;
+
+ req = nfs_find_and_lock_request(page);
+ if (!req)
+ goto out;
+ ret = PTR_ERR(req);
+ if (IS_ERR(req))
+ goto out;
+
+ ret = nfs_set_page_writeback(page);
+ BUG_ON(ret != 0);
+ BUG_ON(test_bit(PG_CLEAN, &req->wb_flags));
+
if (!nfs_pageio_add_request(pgio, req)) {
nfs_redirty_request(req);
- return pgio->pg_error;
+ ret = pgio->pg_error;
}
- return 0;
+out:
+ return ret;
}
static int nfs_do_writepage(struct page *page, struct writeback_control *wbc, struct nfs_pageio_descriptor *pgio)
@@ -1582,6 +1594,41 @@
return nfs_wb_page_priority(inode, page, FLUSH_STABLE);
}
+#ifdef CONFIG_MIGRATION
+int nfs_migrate_page(struct address_space *mapping, struct page *newpage,
+ struct page *page)
+{
+ struct nfs_page *req;
+ int ret;
+
+ if (PageFsCache(page))
+ nfs_fscache_release_page(page, GFP_KERNEL);
+
+ req = nfs_find_and_lock_request(page);
+ ret = PTR_ERR(req);
+ if (IS_ERR(req))
+ goto out;
+
+ ret = migrate_page(mapping, newpage, page);
+ if (!req)
+ goto out;
+ if (ret)
+ goto out_unlock;
+ page_cache_get(newpage);
+ req->wb_page = newpage;
+ SetPagePrivate(newpage);
+ set_page_private(newpage, page_private(page));
+ ClearPagePrivate(page);
+ set_page_private(page, 0);
+ page_cache_release(page);
+out_unlock:
+ nfs_clear_page_tag_locked(req);
+ nfs_release_request(req);
+out:
+ return ret;
+}
+#endif
+
int __init nfs_init_writepagecache(void)
{
nfs_wdata_cachep = kmem_cache_create("nfs_write_data",
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index 19fe15d..320569e 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -167,6 +167,15 @@
#define NFS_CAP_SYMLINKS (1U << 2)
#define NFS_CAP_ACLS (1U << 3)
#define NFS_CAP_ATOMIC_OPEN (1U << 4)
+#define NFS_CAP_CHANGE_ATTR (1U << 5)
+#define NFS_CAP_FILEID (1U << 6)
+#define NFS_CAP_MODE (1U << 7)
+#define NFS_CAP_NLINK (1U << 8)
+#define NFS_CAP_OWNER (1U << 9)
+#define NFS_CAP_OWNER_GROUP (1U << 10)
+#define NFS_CAP_ATIME (1U << 11)
+#define NFS_CAP_CTIME (1U << 12)
+#define NFS_CAP_MTIME (1U << 13)
/* maximum number of slots to use */
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 8aaf900..62438f3 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -2371,3 +2371,55 @@
xprt_unregister_transport(&xs_udp_transport);
xprt_unregister_transport(&xs_tcp_transport);
}
+
+static int param_set_uint_minmax(const char *val, struct kernel_param *kp,
+ unsigned int min, unsigned int max)
+{
+ unsigned long num;
+ int ret;
+
+ if (!val)
+ return -EINVAL;
+ ret = strict_strtoul(val, 0, &num);
+ if (ret == -EINVAL || num < min || num > max)
+ return -EINVAL;
+ *((unsigned int *)kp->arg) = num;
+ return 0;
+}
+
+static int param_set_portnr(const char *val, struct kernel_param *kp)
+{
+ return param_set_uint_minmax(val, kp,
+ RPC_MIN_RESVPORT,
+ RPC_MAX_RESVPORT);
+}
+
+static int param_get_portnr(char *buffer, struct kernel_param *kp)
+{
+ return param_get_uint(buffer, kp);
+}
+#define param_check_portnr(name, p) \
+ __param_check(name, p, unsigned int);
+
+module_param_named(min_resvport, xprt_min_resvport, portnr, 0644);
+module_param_named(max_resvport, xprt_max_resvport, portnr, 0644);
+
+static int param_set_slot_table_size(const char *val, struct kernel_param *kp)
+{
+ return param_set_uint_minmax(val, kp,
+ RPC_MIN_SLOT_TABLE,
+ RPC_MAX_SLOT_TABLE);
+}
+
+static int param_get_slot_table_size(char *buffer, struct kernel_param *kp)
+{
+ return param_get_uint(buffer, kp);
+}
+#define param_check_slot_table_size(name, p) \
+ __param_check(name, p, unsigned int);
+
+module_param_named(tcp_slot_table_entries, xprt_tcp_slot_table_entries,
+ slot_table_size, 0644);
+module_param_named(udp_slot_table_entries, xprt_udp_slot_table_entries,
+ slot_table_size, 0644);
+