aboutsummaryrefslogtreecommitdiffstats
path: root/fs/nfs
diff options
context:
space:
mode:
Diffstat (limited to 'fs/nfs')
-rw-r--r--fs/nfs/Kconfig8
-rw-r--r--fs/nfs/Makefile1
-rw-r--r--fs/nfs/callback.c31
-rw-r--r--fs/nfs/callback.h1
-rw-r--r--fs/nfs/client.c132
-rw-r--r--fs/nfs/dir.c9
-rw-r--r--fs/nfs/file.c79
-rw-r--r--fs/nfs/fscache-index.c337
-rw-r--r--fs/nfs/fscache.c523
-rw-r--r--fs/nfs/fscache.h220
-rw-r--r--fs/nfs/getroot.c4
-rw-r--r--fs/nfs/inode.c323
-rw-r--r--fs/nfs/internal.h8
-rw-r--r--fs/nfs/iostat.h18
-rw-r--r--fs/nfs/nfs2xdr.c9
-rw-r--r--fs/nfs/nfs3proc.c7
-rw-r--r--fs/nfs/nfs3xdr.c40
-rw-r--r--fs/nfs/nfs4proc.c49
-rw-r--r--fs/nfs/nfs4state.c10
-rw-r--r--fs/nfs/nfs4xdr.c213
-rw-r--r--fs/nfs/pagelist.c11
-rw-r--r--fs/nfs/proc.c1
-rw-r--r--fs/nfs/read.c27
-rw-r--r--fs/nfs/super.c49
-rw-r--r--fs/nfs/write.c53
25 files changed, 1801 insertions, 362 deletions
diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig
index 36fe20d6eba2..e67f3ec07736 100644
--- a/fs/nfs/Kconfig
+++ b/fs/nfs/Kconfig
@@ -84,3 +84,11 @@ config ROOT_NFS
<file:Documentation/filesystems/nfsroot.txt>.
Most people say N here.
+
+config NFS_FSCACHE
+ bool "Provide NFS client caching support (EXPERIMENTAL)"
+ depends on EXPERIMENTAL
+ depends on NFS_FS=m && FSCACHE || NFS_FS=y && FSCACHE=y
+ help
+ Say Y here if you want NFS data to be cached locally on disc through
+ the general filesystem cache manager
diff --git a/fs/nfs/Makefile b/fs/nfs/Makefile
index ac6170c594a3..845159814de2 100644
--- a/fs/nfs/Makefile
+++ b/fs/nfs/Makefile
@@ -15,3 +15,4 @@ nfs-$(CONFIG_NFS_V4) += nfs4proc.o nfs4xdr.o nfs4state.o nfs4renewd.o \
callback.o callback_xdr.o callback_proc.o \
nfs4namespace.o
nfs-$(CONFIG_SYSCTL) += sysctl.o
+nfs-$(CONFIG_NFS_FSCACHE) += fscache.o fscache-index.o
diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c
index 3e634f2a1083..a886e692ddd0 100644
--- a/fs/nfs/callback.c
+++ b/fs/nfs/callback.c
@@ -38,19 +38,10 @@ static struct svc_program nfs4_callback_program;
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;
-/*
- * If the kernel has IPv6 support available, always listen for
- * both AF_INET and AF_INET6 requests.
- */
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
-static const sa_family_t nfs_callback_family = AF_INET6;
-#else
-static const sa_family_t nfs_callback_family = AF_INET;
-#endif
-
static int param_set_port(const char *val, struct kernel_param *kp)
{
char *endp;
@@ -116,19 +107,29 @@ int nfs_callback_up(void)
mutex_lock(&nfs_callback_mutex);
if (nfs_callback_info.users++ || nfs_callback_info.task != NULL)
goto out;
- serv = svc_create(&nfs4_callback_program, NFS4_CALLBACK_BUFSIZE,
- nfs_callback_family, NULL);
+ serv = svc_create(&nfs4_callback_program, NFS4_CALLBACK_BUFSIZE, NULL);
ret = -ENOMEM;
if (!serv)
goto out_err;
- ret = svc_create_xprt(serv, "tcp", nfs_callback_set_tcpport,
- SVC_SOCK_ANONYMOUS);
+ ret = svc_create_xprt(serv, "tcp", PF_INET,
+ nfs_callback_set_tcpport, SVC_SOCK_ANONYMOUS);
if (ret <= 0)
goto out_err;
nfs_callback_tcpport = ret;
dprintk("NFS: Callback listener port = %u (af %u)\n",
- nfs_callback_tcpport, nfs_callback_family);
+ nfs_callback_tcpport, PF_INET);
+
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+ ret = svc_create_xprt(serv, "tcp", PF_INET6,
+ nfs_callback_set_tcpport, SVC_SOCK_ANONYMOUS);
+ if (ret > 0) {
+ nfs_callback_tcpport6 = ret;
+ dprintk("NFS: Callback listener port = %u (af %u)\n",
+ nfs_callback_tcpport6, PF_INET6);
+ } else if (ret != -EAFNOSUPPORT)
+ goto out_err;
+#endif /* defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) */
nfs_callback_info.rqst = svc_prepare_thread(serv, &serv->sv_pools[0]);
if (IS_ERR(nfs_callback_info.rqst)) {
diff --git a/fs/nfs/callback.h b/fs/nfs/callback.h
index bb25d2135ff1..e110e286a262 100644
--- a/fs/nfs/callback.h
+++ b/fs/nfs/callback.h
@@ -72,5 +72,6 @@ extern void nfs_callback_down(void);
extern unsigned int nfs_callback_set_tcpport;
extern unsigned short nfs_callback_tcpport;
+extern unsigned short nfs_callback_tcpport6;
#endif /* __LINUX_FS_NFS_CALLBACK_H */
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index 574158ae2398..75c9cd2aa119 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -45,6 +45,7 @@
#include "delegation.h"
#include "iostat.h"
#include "internal.h"
+#include "fscache.h"
#define NFSDBG_FACILITY NFSDBG_CLIENT
@@ -154,6 +155,8 @@ static struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_
if (!IS_ERR(cred))
clp->cl_machine_cred = cred;
+ nfs_fscache_get_client_cookie(clp);
+
return clp;
error_3:
@@ -187,6 +190,8 @@ static void nfs_free_client(struct nfs_client *clp)
nfs4_shutdown_client(clp);
+ nfs_fscache_release_client_cookie(clp);
+
/* -EIO all pending I/O */
if (!IS_ERR(clp->cl_rpcclient))
rpc_shutdown_client(clp->cl_rpcclient);
@@ -224,38 +229,6 @@ void nfs_put_client(struct nfs_client *clp)
}
#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
-static const struct in6_addr *nfs_map_ipv4_addr(const struct sockaddr *sa, struct in6_addr *addr_mapped)
-{
- switch (sa->sa_family) {
- default:
- return NULL;
- case AF_INET6:
- return &((const struct sockaddr_in6 *)sa)->sin6_addr;
- break;
- case AF_INET:
- ipv6_addr_set_v4mapped(((const struct sockaddr_in *)sa)->sin_addr.s_addr,
- addr_mapped);
- return addr_mapped;
- }
-}
-
-static int nfs_sockaddr_match_ipaddr(const struct sockaddr *sa1,
- const struct sockaddr *sa2)
-{
- const struct in6_addr *addr1;
- const struct in6_addr *addr2;
- struct in6_addr addr1_mapped;
- struct in6_addr addr2_mapped;
-
- addr1 = nfs_map_ipv4_addr(sa1, &addr1_mapped);
- if (likely(addr1 != NULL)) {
- addr2 = nfs_map_ipv4_addr(sa2, &addr2_mapped);
- if (likely(addr2 != NULL))
- return ipv6_addr_equal(addr1, addr2);
- }
- return 0;
-}
-
/*
* Test if two ip6 socket addresses refer to the same socket by
* comparing relevant fields. The padding bytes specifically, are not
@@ -267,38 +240,21 @@ static int nfs_sockaddr_match_ipaddr(const struct sockaddr *sa1,
*
* The caller should ensure both socket addresses are AF_INET6.
*/
-static int nfs_sockaddr_cmp_ip6(const struct sockaddr *sa1,
- const struct sockaddr *sa2)
+static int nfs_sockaddr_match_ipaddr6(const struct sockaddr *sa1,
+ const struct sockaddr *sa2)
{
- const struct sockaddr_in6 *saddr1 = (const struct sockaddr_in6 *)sa1;
- const struct sockaddr_in6 *saddr2 = (const struct sockaddr_in6 *)sa2;
+ const struct sockaddr_in6 *sin1 = (const struct sockaddr_in6 *)sa1;
+ const struct sockaddr_in6 *sin2 = (const struct sockaddr_in6 *)sa2;
- if (!ipv6_addr_equal(&saddr1->sin6_addr,
- &saddr1->sin6_addr))
- return 0;
- if (ipv6_addr_scope(&saddr1->sin6_addr) == IPV6_ADDR_SCOPE_LINKLOCAL &&
- saddr1->sin6_scope_id != saddr2->sin6_scope_id)
+ if (ipv6_addr_scope(&sin1->sin6_addr) == IPV6_ADDR_SCOPE_LINKLOCAL &&
+ sin1->sin6_scope_id != sin2->sin6_scope_id)
return 0;
- return saddr1->sin6_port == saddr2->sin6_port;
-}
-#else
-static int nfs_sockaddr_match_ipaddr4(const struct sockaddr_in *sa1,
- const struct sockaddr_in *sa2)
-{
- return sa1->sin_addr.s_addr == sa2->sin_addr.s_addr;
-}
-static int nfs_sockaddr_match_ipaddr(const struct sockaddr *sa1,
- const struct sockaddr *sa2)
-{
- if (unlikely(sa1->sa_family != AF_INET || sa2->sa_family != AF_INET))
- return 0;
- return nfs_sockaddr_match_ipaddr4((const struct sockaddr_in *)sa1,
- (const struct sockaddr_in *)sa2);
+ return ipv6_addr_equal(&sin1->sin6_addr, &sin1->sin6_addr);
}
-
-static int nfs_sockaddr_cmp_ip6(const struct sockaddr * sa1,
- const struct sockaddr * sa2)
+#else /* !defined(CONFIG_IPV6) && !defined(CONFIG_IPV6_MODULE) */
+static int nfs_sockaddr_match_ipaddr6(const struct sockaddr *sa1,
+ const struct sockaddr *sa2)
{
return 0;
}
@@ -311,20 +267,57 @@ static int nfs_sockaddr_cmp_ip6(const struct sockaddr * sa1,
*
* The caller should ensure both socket addresses are AF_INET.
*/
+static int nfs_sockaddr_match_ipaddr4(const struct sockaddr *sa1,
+ const struct sockaddr *sa2)
+{
+ const struct sockaddr_in *sin1 = (const struct sockaddr_in *)sa1;
+ const struct sockaddr_in *sin2 = (const struct sockaddr_in *)sa2;
+
+ return sin1->sin_addr.s_addr == sin2->sin_addr.s_addr;
+}
+
+static int nfs_sockaddr_cmp_ip6(const struct sockaddr *sa1,
+ const struct sockaddr *sa2)
+{
+ const struct sockaddr_in6 *sin1 = (const struct sockaddr_in6 *)sa1;
+ const struct sockaddr_in6 *sin2 = (const struct sockaddr_in6 *)sa2;
+
+ return nfs_sockaddr_match_ipaddr6(sa1, sa2) &&
+ (sin1->sin6_port == sin2->sin6_port);
+}
+
static int nfs_sockaddr_cmp_ip4(const struct sockaddr *sa1,
const struct sockaddr *sa2)
{
- const struct sockaddr_in *saddr1 = (const struct sockaddr_in *)sa1;
- const struct sockaddr_in *saddr2 = (const struct sockaddr_in *)sa2;
+ const struct sockaddr_in *sin1 = (const struct sockaddr_in *)sa1;
+ const struct sockaddr_in *sin2 = (const struct sockaddr_in *)sa2;
- if (saddr1->sin_addr.s_addr != saddr2->sin_addr.s_addr)
+ return nfs_sockaddr_match_ipaddr4(sa1, sa2) &&
+ (sin1->sin_port == sin2->sin_port);
+}
+
+/*
+ * Test if two socket addresses represent the same actual socket,
+ * by comparing (only) relevant fields, excluding the port number.
+ */
+static int nfs_sockaddr_match_ipaddr(const struct sockaddr *sa1,
+ const struct sockaddr *sa2)
+{
+ if (sa1->sa_family != sa2->sa_family)
return 0;
- return saddr1->sin_port == saddr2->sin_port;
+
+ switch (sa1->sa_family) {
+ case AF_INET:
+ return nfs_sockaddr_match_ipaddr4(sa1, sa2);
+ case AF_INET6:
+ return nfs_sockaddr_match_ipaddr6(sa1, sa2);
+ }
+ return 0;
}
/*
* Test if two socket addresses represent the same actual socket,
- * by comparing (only) relevant fields.
+ * by comparing (only) relevant fields, including the port number.
*/
static int nfs_sockaddr_cmp(const struct sockaddr *sa1,
const struct sockaddr *sa2)
@@ -772,6 +765,7 @@ static int nfs_init_server(struct nfs_server *server,
/* Initialise the client representation from the mount data */
server->flags = data->flags;
+ server->options = data->options;
if (data->rsize)
server->rsize = nfs_block_size(data->rsize, NULL);
@@ -1160,6 +1154,7 @@ static int nfs4_init_server(struct nfs_server *server,
/* Initialise the client representation from the mount data */
server->flags = data->flags;
server->caps |= NFS_CAP_ATOMIC_OPEN;
+ server->options = data->options;
/* Get a client record */
error = nfs4_set_client(server,
@@ -1571,7 +1566,7 @@ static int nfs_volume_list_show(struct seq_file *m, void *v)
/* display header on line 1 */
if (v == &nfs_volume_list) {
- seq_puts(m, "NV SERVER PORT DEV FSID\n");
+ seq_puts(m, "NV SERVER PORT DEV FSID FSC\n");
return 0;
}
/* display one transport per line on subsequent lines */
@@ -1585,12 +1580,13 @@ static int nfs_volume_list_show(struct seq_file *m, void *v)
(unsigned long long) server->fsid.major,
(unsigned long long) server->fsid.minor);
- seq_printf(m, "v%u %s %s %-7s %-17s\n",
+ seq_printf(m, "v%u %s %s %-7s %-17s %s\n",
clp->rpc_ops->version,
rpc_peeraddr2str(clp->cl_rpcclient, RPC_DISPLAY_HEX_ADDR),
rpc_peeraddr2str(clp->cl_rpcclient, RPC_DISPLAY_HEX_PORT),
dev,
- fsid);
+ fsid,
+ nfs_server_fscache_state(server));
return 0;
}
@@ -1606,8 +1602,6 @@ int __init nfs_fs_proc_init(void)
if (!proc_fs_nfs)
goto error_0;
- proc_fs_nfs->owner = THIS_MODULE;
-
/* a file of servers with which we're dealing */
p = proc_create("servers", S_IFREG|S_IRUGO,
proc_fs_nfs, &nfs_server_list_fops);
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 78bf72fc1db3..370b190a09d1 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -1624,8 +1624,7 @@ static int nfs_rename(struct inode *old_dir, struct dentry *old_dentry,
} else if (atomic_read(&new_dentry->d_count) > 1)
/* dentry still busy? */
goto out;
- } else
- nfs_drop_nlink(new_inode);
+ }
go_ahead:
/*
@@ -1638,10 +1637,8 @@ go_ahead:
}
nfs_inode_return_delegation(old_inode);
- if (new_inode != NULL) {
+ if (new_inode != NULL)
nfs_inode_return_delegation(new_inode);
- d_delete(new_dentry);
- }
error = NFS_PROTO(old_dir)->rename(old_dir, &old_dentry->d_name,
new_dir, &new_dentry->d_name);
@@ -1650,6 +1647,8 @@ out:
if (rehash)
d_rehash(rehash);
if (!error) {
+ if (new_inode != NULL)
+ nfs_drop_nlink(new_inode);
d_move(old_dentry, new_dentry);
nfs_set_verifier(new_dentry,
nfs_save_change_attribute(new_dir));
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 90f292b520d2..ec7e27d00bc6 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -35,6 +35,7 @@
#include "delegation.h"
#include "internal.h"
#include "iostat.h"
+#include "fscache.h"
#define NFSDBG_FACILITY NFSDBG_FILE
@@ -64,11 +65,7 @@ const struct file_operations nfs_file_operations = {
.write = do_sync_write,
.aio_read = nfs_file_read,
.aio_write = nfs_file_write,
-#ifdef CONFIG_MMU
.mmap = nfs_file_mmap,
-#else
- .mmap = generic_file_mmap,
-#endif
.open = nfs_file_open,
.flush = nfs_file_flush,
.release = nfs_file_release,
@@ -141,9 +138,6 @@ nfs_file_release(struct inode *inode, struct file *filp)
dentry->d_parent->d_name.name,
dentry->d_name.name);
- /* Ensure that dirty pages are flushed out with the right creds */
- if (filp->f_mode & FMODE_WRITE)
- nfs_wb_all(dentry->d_inode);
nfs_inc_stats(inode, NFSIOS_VFSRELEASE);
return nfs_release(inode, filp);
}
@@ -235,7 +229,6 @@ nfs_file_flush(struct file *file, fl_owner_t id)
struct nfs_open_context *ctx = nfs_file_open_context(file);
struct dentry *dentry = file->f_path.dentry;
struct inode *inode = dentry->d_inode;
- int status;
dprintk("NFS: flush(%s/%s)\n",
dentry->d_parent->d_name.name,
@@ -245,11 +238,8 @@ nfs_file_flush(struct file *file, fl_owner_t id)
return 0;
nfs_inc_stats(inode, NFSIOS_VFSFLUSH);
- /* Ensure that data+attribute caches are up to date after close() */
- status = nfs_do_fsync(ctx, inode);
- if (!status)
- nfs_revalidate_inode(NFS_SERVER(inode), inode);
- return status;
+ /* Flush writes to the server and return any errors */
+ return nfs_do_fsync(ctx, inode);
}
static ssize_t
@@ -304,11 +294,13 @@ nfs_file_mmap(struct file * file, struct vm_area_struct * vma)
dprintk("NFS: mmap(%s/%s)\n",
dentry->d_parent->d_name.name, dentry->d_name.name);
- status = nfs_revalidate_mapping(inode, file->f_mapping);
+ /* Note: generic_file_mmap() returns ENOSYS on nommu systems
+ * so we call that before revalidating the mapping
+ */
+ status = generic_file_mmap(file, vma);
if (!status) {
vma->vm_ops = &nfs_file_vm_ops;
- vma->vm_flags |= VM_CAN_NONLINEAR;
- file_accessed(file);
+ status = nfs_revalidate_mapping(inode, file->f_mapping);
}
return status;
}
@@ -354,6 +346,15 @@ static int nfs_write_begin(struct file *file, struct address_space *mapping,
file->f_path.dentry->d_name.name,
mapping->host->i_ino, len, (long long) pos);
+ /*
+ * Prevent starvation issues if someone is doing a consistency
+ * sync-to-disk
+ */
+ ret = wait_on_bit(&NFS_I(mapping->host)->flags, NFS_INO_FLUSHING,
+ nfs_wait_bit_killable, TASK_KILLABLE);
+ if (ret)
+ return ret;
+
page = grab_cache_page_write_begin(mapping, index, flags);
if (!page)
return -ENOMEM;
@@ -409,6 +410,13 @@ static int nfs_write_end(struct file *file, struct address_space *mapping,
return copied;
}
+/*
+ * Partially or wholly invalidate a page
+ * - Release the private state associated with a page if undergoing complete
+ * page invalidation
+ * - Called if either PG_private or PG_fscache is set on the page
+ * - Caller holds page lock
+ */
static void nfs_invalidate_page(struct page *page, unsigned long offset)
{
dfprintk(PAGECACHE, "NFS: invalidate_page(%p, %lu)\n", page, offset);
@@ -417,23 +425,43 @@ static void nfs_invalidate_page(struct page *page, unsigned long offset)
return;
/* Cancel any unstarted writes on this page */
nfs_wb_page_cancel(page->mapping->host, page);
+
+ nfs_fscache_invalidate_page(page, page->mapping->host);
}
+/*
+ * Attempt to release the private state associated with a page
+ * - Called if either PG_private or PG_fscache is set on the page
+ * - Caller holds page lock
+ * - Return true (may release page) or false (may not)
+ */
static int nfs_release_page(struct page *page, gfp_t gfp)
{
dfprintk(PAGECACHE, "NFS: release_page(%p)\n", page);
/* If PagePrivate() is set, then the page is not freeable */
- return 0;
+ if (PagePrivate(page))
+ return 0;
+ return nfs_fscache_release_page(page, gfp);
}
+/*
+ * Attempt to clear the private state associated with a page when an error
+ * occurs that requires the cached contents of an inode to be written back or
+ * destroyed
+ * - Called if either PG_private or fscache is set on the page
+ * - Caller holds page lock
+ * - Return 0 if successful, -error otherwise
+ */
static int nfs_launder_page(struct page *page)
{
struct inode *inode = page->mapping->host;
+ struct nfs_inode *nfsi = NFS_I(inode);
dfprintk(PAGECACHE, "NFS: launder_page(%ld, %llu)\n",
inode->i_ino, (long long)page_offset(page));
+ nfs_fscache_wait_on_page_write(nfsi, page);
return nfs_wb_page(inode, page);
}
@@ -451,8 +479,14 @@ const struct address_space_operations nfs_file_aops = {
.launder_page = nfs_launder_page,
};
-static int nfs_vm_page_mkwrite(struct vm_area_struct *vma, struct page *page)
+/*
+ * Notification that a PTE pointing to an NFS page is about to be made
+ * writable, implying that someone is about to modify the page through a
+ * shared-writable mapping
+ */
+static int nfs_vm_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
{
+ struct page *page = vmf->page;
struct file *filp = vma->vm_file;
struct dentry *dentry = filp->f_path.dentry;
unsigned pagelen;
@@ -464,6 +498,9 @@ static int nfs_vm_page_mkwrite(struct vm_area_struct *vma, struct page *page)
filp->f_mapping->host->i_ino,
(long long)page_offset(page));
+ /* make sure the cache has finished storing the page */
+ nfs_fscache_wait_on_page_write(NFS_I(dentry->d_inode), page);
+
lock_page(page);
mapping = page->mapping;
if (mapping != dentry->d_inode->i_mapping)
@@ -479,11 +516,11 @@ static int nfs_vm_page_mkwrite(struct vm_area_struct *vma, struct page *page)
goto out_unlock;
ret = nfs_updatepage(filp, page, 0, pagelen);
- if (ret == 0)
- ret = pagelen;
out_unlock:
+ if (!ret)
+ return VM_FAULT_LOCKED;
unlock_page(page);
- return ret;
+ return VM_FAULT_SIGBUS;
}
static struct vm_operations_struct nfs_file_vm_ops = {
diff --git a/fs/nfs/fscache-index.c b/fs/nfs/fscache-index.c
new file mode 100644
index 000000000000..5b1006480bc2
--- /dev/null
+++ b/fs/nfs/fscache-index.c
@@ -0,0 +1,337 @@
+/* NFS FS-Cache index structure definition
+ *
+ * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/mm.h>
+#include <linux/nfs_fs.h>
+#include <linux/nfs_fs_sb.h>
+#include <linux/in6.h>
+
+#include "internal.h"
+#include "fscache.h"
+
+#define NFSDBG_FACILITY NFSDBG_FSCACHE
+
+/*
+ * Define the NFS filesystem for FS-Cache. Upon registration FS-Cache sticks
+ * the cookie for the top-level index object for NFS into here. The top-level
+ * index can than have other cache objects inserted into it.
+ */
+struct fscache_netfs nfs_fscache_netfs = {
+ .name = "nfs",
+ .version = 0,
+};
+
+/*
+ * Register NFS for caching
+ */
+int nfs_fscache_register(void)
+{
+ return fscache_register_netfs(&nfs_fscache_netfs);
+}
+
+/*
+ * Unregister NFS for caching
+ */
+void nfs_fscache_unregister(void)
+{
+ fscache_unregister_netfs(&nfs_fscache_netfs);
+}
+
+/*
+ * Layout of the key for an NFS server cache object.
+ */
+struct nfs_server_key {
+ uint16_t nfsversion; /* NFS protocol version */
+ uint16_t family; /* address family */
+ uint16_t port; /* IP port */
+ union {
+ struct in_addr ipv4_addr; /* IPv4 address */
+ struct in6_addr ipv6_addr; /* IPv6 address */
+ } addr[0];
+};
+
+/*
+ * Generate a key to describe a server in the main NFS index
+ * - We return the length of the key, or 0 if we can't generate one
+ */
+static uint16_t nfs_server_get_key(const void *cookie_netfs_data,
+ void *buffer, uint16_t bufmax)
+{
+ const struct nfs_client *clp = cookie_netfs_data;
+ const struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *) &clp->cl_addr;
+ const struct sockaddr_in *sin = (struct sockaddr_in *) &clp->cl_addr;
+ struct nfs_server_key *key = buffer;
+ uint16_t len = sizeof(struct nfs_server_key);
+
+ key->nfsversion = clp->rpc_ops->version;
+ key->family = clp->cl_addr.ss_family;
+
+ memset(key, 0, len);
+
+ switch (clp->cl_addr.ss_family) {
+ case AF_INET:
+ key->port = sin->sin_port;
+ key->addr[0].ipv4_addr = sin->sin_addr;
+ len += sizeof(key->addr[0].ipv4_addr);
+ break;
+
+ case AF_INET6:
+ key->port = sin6->sin6_port;
+ key->addr[0].ipv6_addr = sin6->sin6_addr;
+ len += sizeof(key->addr[0].ipv6_addr);
+ break;
+
+ default:
+ printk(KERN_WARNING "NFS: Unknown network family '%d'\n",
+ clp->cl_addr.ss_family);
+ len = 0;
+ break;
+ }
+
+ return len;
+}
+
+/*
+ * Define the server object for FS-Cache. This is used to describe a server
+ * object to fscache_acquire_cookie(). It is keyed by the NFS protocol and
+ * server address parameters.
+ */
+const struct fscache_cookie_def nfs_fscache_server_index_def = {
+ .name = "NFS.server",
+ .type = FSCACHE_COOKIE_TYPE_INDEX,
+ .get_key = nfs_server_get_key,
+};
+
+/*
+ * Generate a key to describe a superblock key in the main NFS index
+ */
+static uint16_t nfs_super_get_key(const void *cookie_netfs_data,
+ void *buffer, uint16_t bufmax)
+{
+ const struct nfs_fscache_key *key;
+ const struct nfs_server *nfss = cookie_netfs_data;
+ uint16_t len;
+
+ key = nfss->fscache_key;
+ len = sizeof(key->key) + key->key.uniq_len;
+ if (len > bufmax) {
+ len = 0;
+ } else {
+ memcpy(buffer, &key->key, sizeof(key->key));
+ memcpy(buffer + sizeof(key->key),
+ key->key.uniquifier, key->key.uniq_len);
+ }
+
+ return len;
+}
+
+/*
+ * Define the superblock object for FS-Cache. This is used to describe a
+ * superblock object to fscache_acquire_cookie(). It is keyed by all the NFS
+ * parameters that might cause a separate superblock.
+ */
+const struct fscache_cookie_def nfs_fscache_super_index_def = {
+ .name = "NFS.super",
+ .type = FSCACHE_COOKIE_TYPE_INDEX,
+ .get_key = nfs_super_get_key,
+};
+
+/*
+ * Definition of the auxiliary data attached to NFS inode storage objects
+ * within the cache.
+ *
+ * The contents of this struct are recorded in the on-disk local cache in the
+ * auxiliary data attached to the data storage object backing an inode. This
+ * permits coherency to be managed when a new inode binds to an already extant
+ * cache object.
+ */
+struct nfs_fscache_inode_auxdata {
+ struct timespec mtime;
+ struct timespec ctime;
+ loff_t size;
+ u64 change_attr;
+};
+
+/*
+ * Generate a key to describe an NFS inode in an NFS server's index
+ */
+static uint16_t nfs_fscache_inode_get_key(const void *cookie_netfs_data,
+ void *buffer, uint16_t bufmax)
+{
+ const struct nfs_inode *nfsi = cookie_netfs_data;
+ uint16_t nsize;
+
+ /* use the inode's NFS filehandle as the key */
+ nsize = nfsi->fh.size;
+ memcpy(buffer, nfsi->fh.data, nsize);
+ return nsize;
+}
+
+/*
+ * Get certain file attributes from the netfs data
+ * - This function can be absent for an index
+ * - Not permitted to return an error
+ * - The netfs data from the cookie being used as the source is presented
+ */
+static void nfs_fscache_inode_get_attr(const void *cookie_netfs_data,
+ uint64_t *size)
+{
+ const struct nfs_inode *nfsi = cookie_netfs_data;
+
+ *size = nfsi->vfs_inode.i_size;
+}
+
+/*
+ * Get the auxiliary data from netfs data
+ * - This function can be absent if the index carries no state data
+ * - Should store the auxiliary data in the buffer
+ * - Should return the amount of amount stored
+ * - Not permitted to return an error
+ * - The netfs data from the cookie being used as the source is presented
+ */
+static uint16_t nfs_fscache_inode_get_aux(const void *cookie_netfs_data,
+ void *buffer, uint16_t bufmax)
+{
+ struct nfs_fscache_inode_auxdata auxdata;
+ const struct nfs_inode *nfsi = cookie_netfs_data;
+
+ memset(&auxdata, 0, sizeof(auxdata));
+ auxdata.size = nfsi->vfs_inode.i_size;
+ auxdata.mtime = nfsi->vfs_inode.i_mtime;
+ auxdata.ctime = nfsi->vfs_inode.i_ctime;
+
+ if (NFS_SERVER(&nfsi->vfs_inode)->nfs_client->rpc_ops->version == 4)
+ auxdata.change_attr = nfsi->change_attr;
+
+ if (bufmax > sizeof(auxdata))
+ bufmax = sizeof(auxdata);
+
+ memcpy(buffer, &auxdata, bufmax);
+ return bufmax;
+}
+
+/*
+ * Consult the netfs about the state of an object
+ * - This function can be absent if the index carries no state data
+ * - The netfs data from the cookie being used as the target is
+ * presented, as is the auxiliary data
+ */
+static
+enum fscache_checkaux nfs_fscache_inode_check_aux(void *cookie_netfs_data,
+ const void *data,
+ uint16_t datalen)
+{
+ struct nfs_fscache_inode_auxdata auxdata;
+ struct nfs_inode *nfsi = cookie_netfs_data;
+
+ if (datalen != sizeof(auxdata))
+ return FSCACHE_CHECKAUX_OBSOLETE;
+
+ memset(&auxdata, 0, sizeof(auxdata));
+ auxdata.size = nfsi->vfs_inode.i_size;
+ auxdata.mtime = nfsi->vfs_inode.i_mtime;
+ auxdata.ctime = nfsi->vfs_inode.i_ctime;
+
+ if (NFS_SERVER(&nfsi->vfs_inode)->nfs_client->rpc_ops->version == 4)
+ auxdata.change_attr = nfsi->change_attr;
+
+ if (memcmp(data, &auxdata, datalen) != 0)
+ return FSCACHE_CHECKAUX_OBSOLETE;
+
+ return FSCACHE_CHECKAUX_OKAY;
+}
+
+/*
+ * Indication from FS-Cache that the cookie is no longer cached
+ * - This function is called when the backing store currently caching a cookie
+ * is removed
+ * - The netfs should use this to clean up any markers indicating cached pages
+ * - This is mandatory for any object that may have data
+ */
+static void nfs_fscache_inode_now_uncached(void *cookie_netfs_data)
+{
+ struct nfs_inode *nfsi = cookie_netfs_data;
+ struct pagevec pvec;
+ pgoff_t first;
+ int loop, nr_pages;
+
+ pagevec_init(&pvec, 0);
+ first = 0;
+
+ dprintk("NFS: nfs_inode_now_uncached: nfs_inode 0x%p\n", nfsi);
+
+ for (;;) {
+ /* grab a bunch of pages to unmark */
+ nr_pages = pagevec_lookup(&pvec,
+ nfsi->vfs_inode.i_mapping,
+ first,
+ PAGEVEC_SIZE - pagevec_count(&pvec));
+ if (!nr_pages)
+ break;
+
+ for (loop = 0; loop < nr_pages; loop++)
+ ClearPageFsCache(pvec.pages[loop]);
+
+ first = pvec.pages[nr_pages - 1]->index + 1;
+
+ pvec.nr = nr_pages;
+ pagevec_release(&pvec);
+ cond_resched();
+ }
+}
+
+/*
+ * Get an extra reference on a read context.
+ * - This function can be absent if the completion function doesn't require a
+ * context.
+ * - The read context is passed back to NFS in the event that a data read on the
+ * cache fails with EIO - in which case the server must be contacted to
+ * retrieve the data, which requires the read context for security.
+ */
+static void nfs_fh_get_context(void *cookie_netfs_data, void *context)
+{
+ get_nfs_open_context(context);
+}
+
+/*
+ * Release an extra reference on a read context.
+ * - This function can be absent if the completion function doesn't require a
+ * context.
+ */
+static void nfs_fh_put_context(void *cookie_netfs_data, void *context)
+{
+ if (context)
+ put_nfs_open_context(context);
+}
+
+/*
+ * Define the inode object for FS-Cache. This is used to describe an inode
+ * object to fscache_acquire_cookie(). It is keyed by the NFS file handle for
+ * an inode.
+ *
+ * Coherency is managed by comparing the copies of i_size, i_mtime and i_ctime
+ * held in the cache auxiliary data for the data storage object with those in
+ * the inode struct in memory.
+ */
+const struct fscache_cookie_def nfs_fscache_inode_object_def = {
+ .name = "NFS.fh",
+ .type = FSCACHE_COOKIE_TYPE_DATAFILE,
+ .get_key = nfs_fscache_inode_get_key,
+ .get_attr = nfs_fscache_inode_get_attr,
+ .get_aux = nfs_fscache_inode_get_aux,
+ .check_aux = nfs_fscache_inode_check_aux,
+ .now_uncached = nfs_fscache_inode_now_uncached,
+ .get_context = nfs_fh_get_context,
+ .put_context = nfs_fh_put_context,
+};
diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c
new file mode 100644
index 000000000000..379be678cb7e
--- /dev/null
+++ b/fs/nfs/fscache.c
@@ -0,0 +1,523 @@
+/* NFS filesystem cache interface
+ *
+ * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/mm.h>
+#include <linux/nfs_fs.h>
+#include <linux/nfs_fs_sb.h>
+#include <linux/in6.h>
+#include <linux/seq_file.h>
+
+#include "internal.h"
+#include "iostat.h"
+#include "fscache.h"
+
+#define NFSDBG_FACILITY NFSDBG_FSCACHE
+
+static struct rb_root nfs_fscache_keys = RB_ROOT;
+static DEFINE_SPINLOCK(nfs_fscache_keys_lock);
+
+/*
+ * Get the per-client index cookie for an NFS client if the appropriate mount
+ * flag was set
+ * - We always try and get an index cookie for the client, but get filehandle
+ * cookies on a per-superblock basis, depending on the mount flags
+ */
+void nfs_fscache_get_client_cookie(struct nfs_client *clp)
+{
+ /* create a cache index for looking up filehandles */
+ clp->fscache = fscache_acquire_cookie(nfs_fscache_netfs.primary_index,
+ &nfs_fscache_server_index_def,
+ clp);
+ dfprintk(FSCACHE, "NFS: get client cookie (0x%p/0x%p)\n",
+ clp, clp->fscache);
+}
+
+/*
+ * Dispose of a per-client cookie
+ */
+void nfs_fscache_release_client_cookie(struct nfs_client *clp)
+{
+ dfprintk(FSCACHE, "NFS: releasing client cookie (0x%p/0x%p)\n",
+ clp, clp->fscache);
+
+ fscache_relinquish_cookie(clp->fscache, 0);
+ clp->fscache = NULL;
+}
+
+/*
+ * Get the cache cookie for an NFS superblock. We have to handle
+ * uniquification here because the cache doesn't do it for us.
+ */
+void nfs_fscache_get_super_cookie(struct super_block *sb,
+ struct nfs_parsed_mount_data *data)
+{
+ struct nfs_fscache_key *key, *xkey;
+ struct nfs_server *nfss = NFS_SB(sb);
+ struct rb_node **p, *parent;
+ const char *uniq = data->fscache_uniq ?: "";
+ int diff, ulen;
+
+ ulen = strlen(uniq);
+ key = kzalloc(sizeof(*key) + ulen, GFP_KERNEL);
+ if (!key)
+ return;
+
+ key->nfs_client = nfss->nfs_client;
+ key->key.super.s_flags = sb->s_flags & NFS_MS_MASK;
+ key->key.nfs_server.flags = nfss->flags;
+ key->key.nfs_server.rsize = nfss->rsize;
+ key->key.nfs_server.wsize = nfss->wsize;
+ key->key.nfs_server.acregmin = nfss->acregmin;
+ key->key.nfs_server.acregmax = nfss->acregmax;
+ key->key.nfs_server.acdirmin = nfss->acdirmin;
+ key->key.nfs_server.acdirmax = nfss->acdirmax;
+ key->key.nfs_server.fsid = nfss->fsid;
+ key->key.rpc_auth.au_flavor = nfss->client->cl_auth->au_flavor;
+
+ key->key.uniq_len = ulen;
+ memcpy(key->key.uniquifier, uniq, ulen);
+
+ spin_lock(&nfs_fscache_keys_lock);
+ p = &nfs_fscache_keys.rb_node;
+ parent = NULL;
+ while (*p) {
+ parent = *p;
+ xkey = rb_entry(parent, struct nfs_fscache_key, node);
+
+ if (key->nfs_client < xkey->nfs_client)
+ goto go_left;
+ if (key->nfs_client > xkey->nfs_client)
+ goto go_right;
+
+ diff = memcmp(&key->key, &xkey->key, sizeof(key->key));
+ if (diff < 0)
+ goto go_left;
+ if (diff > 0)
+ goto go_right;
+
+ if (key->key.uniq_len == 0)
+ goto non_unique;
+ diff = memcmp(key->key.uniquifier,
+ xkey->key.uniquifier,
+ key->key.uniq_len);
+ if (diff < 0)
+ goto go_left;
+ if (diff > 0)
+ goto go_right;
+ goto non_unique;
+
+ go_left:
+ p = &(*p)->rb_left;
+ continue;
+ go_right:
+ p = &(*p)->rb_right;
+ }
+
+ rb_link_node(&key->node, parent, p);
+ rb_insert_color(&key->node, &nfs_fscache_keys);
+ spin_unlock(&nfs_fscache_keys_lock);
+ nfss->fscache_key = key;
+
+ /* create a cache index for looking up filehandles */
+ nfss->fscache = fscache_acquire_cookie(nfss->nfs_client->fscache,
+ &nfs_fscache_super_index_def,
+ nfss);
+ dfprintk(FSCACHE, "NFS: get superblock cookie (0x%p/0x%p)\n",
+ nfss, nfss->fscache);
+ return;
+
+non_unique:
+ spin_unlock(&nfs_fscache_keys_lock);
+ kfree(key);
+ nfss->fscache_key = NULL;
+ nfss->fscache = NULL;
+ printk(KERN_WARNING "NFS:"
+ " Cache request denied due to non-unique superblock keys\n");
+}
+
+/*
+ * release a per-superblock cookie
+ */
+void nfs_fscache_release_super_cookie(struct super_block *sb)
+{
+ struct nfs_server *nfss = NFS_SB(sb);
+
+ dfprintk(FSCACHE, "NFS: releasing superblock cookie (0x%p/0x%p)\n",
+ nfss, nfss->fscache);
+
+ fscache_relinquish_cookie(nfss->fscache, 0);
+ nfss->fscache = NULL;
+
+ if (nfss->fscache_key) {
+ spin_lock(&nfs_fscache_keys_lock);
+ rb_erase(&nfss->fscache_key->node, &nfs_fscache_keys);
+ spin_unlock(&nfs_fscache_keys_lock);
+ kfree(nfss->fscache_key);
+ nfss->fscache_key = NULL;
+ }
+}
+
+/*
+ * Initialise the per-inode cache cookie pointer for an NFS inode.
+ */
+void nfs_fscache_init_inode_cookie(struct inode *inode)
+{
+ NFS_I(inode)->fscache = NULL;
+ if (S_ISREG(inode->i_mode))
+ set_bit(NFS_INO_FSCACHE, &NFS_I(inode)->flags);
+}
+
+/*
+ * Get the per-inode cache cookie for an NFS inode.
+ */
+static void nfs_fscache_enable_inode_cookie(struct inode *inode)
+{
+ struct super_block *sb = inode->i_sb;
+ struct nfs_inode *nfsi = NFS_I(inode);
+
+ if (nfsi->fscache || !NFS_FSCACHE(inode))
+ return;
+
+ if ((NFS_SB(sb)->options & NFS_OPTION_FSCACHE)) {
+ nfsi->fscache = fscache_acquire_cookie(
+ NFS_SB(sb)->fscache,
+ &nfs_fscache_inode_object_def,
+ nfsi);
+
+ dfprintk(FSCACHE, "NFS: get FH cookie (0x%p/0x%p/0x%p)\n",
+ sb, nfsi, nfsi->fscache);
+ }
+}
+
+/*
+ * Release a per-inode cookie.
+ */
+void nfs_fscache_release_inode_cookie(struct inode *inode)
+{
+ struct nfs_inode *nfsi = NFS_I(inode);
+
+ dfprintk(FSCACHE, "NFS: clear cookie (0x%p/0x%p)\n",
+ nfsi, nfsi->fscache);
+
+ fscache_relinquish_cookie(nfsi->fscache, 0);
+ nfsi->fscache = NULL;
+}
+
+/*
+ * Retire a per-inode cookie, destroying the data attached to it.
+ */
+void nfs_fscache_zap_inode_cookie(struct inode *inode)
+{
+ struct nfs_inode *nfsi = NFS_I(inode);
+
+ dfprintk(FSCACHE, "NFS: zapping cookie (0x%p/0x%p)\n",
+ nfsi, nfsi->fscache);
+
+ fscache_relinquish_cookie(nfsi->fscache, 1);
+ nfsi->fscache = NULL;
+}
+
+/*
+ * Turn off the cache with regard to a per-inode cookie if opened for writing,
+ * invalidating all the pages in the page cache relating to the associated
+ * inode to clear the per-page caching.
+ */
+static void nfs_fscache_disable_inode_cookie(struct inode *inode)
+{
+ clear_bit(NFS_INO_FSCACHE, &NFS_I(inode)->flags);
+
+ if (NFS_I(inode)->fscache) {
+ dfprintk(FSCACHE,
+ "NFS: nfsi 0x%p turning cache off\n", NFS_I(inode));
+
+ /* Need to invalidate any mapped pages that were read in before
+ * turning off the cache.
+ */
+ if (inode->i_mapping && inode->i_mapping->nrpages)
+ invalidate_inode_pages2(inode->i_mapping);
+
+ nfs_fscache_zap_inode_cookie(inode);
+ }
+}
+
+/*
+ * wait_on_bit() sleep function for uninterruptible waiting
+ */
+static int nfs_fscache_wait_bit(void *flags)
+{
+ schedule();
+ return 0;
+}
+
+/*
+ * Lock against someone else trying to also acquire or relinquish a cookie
+ */
+static inline void nfs_fscache_inode_lock(struct inode *inode)
+{
+ struct nfs_inode *nfsi = NFS_I(inode);
+
+ while (test_and_set_bit(NFS_INO_FSCACHE_LOCK, &nfsi->flags))
+ wait_on_bit(&nfsi->flags, NFS_INO_FSCACHE_LOCK,
+ nfs_fscache_wait_bit, TASK_UNINTERRUPTIBLE);
+}
+
+/*
+ * Unlock cookie management lock
+ */
+static inline void nfs_fscache_inode_unlock(struct inode *inode)
+{
+ struct nfs_inode *nfsi = NFS_I(inode);
+
+ smp_mb__before_clear_bit();
+ clear_bit(NFS_INO_FSCACHE_LOCK, &nfsi->flags);
+ smp_mb__after_clear_bit();
+ wake_up_bit(&nfsi->flags, NFS_INO_FSCACHE_LOCK);
+}
+
+/*
+ * Decide if we should enable or disable local caching for this inode.
+ * - For now, with NFS, only regular files that are open read-only will be able
+ * to use the cache.
+ * - May be invoked multiple times in parallel by parallel nfs_open() functions.
+ */
+void nfs_fscache_set_inode_cookie(struct inode *inode, struct file *filp)
+{
+ if (NFS_FSCACHE(inode)) {
+ nfs_fscache_inode_lock(inode);
+ if ((filp->f_flags & O_ACCMODE) != O_RDONLY)
+ nfs_fscache_disable_inode_cookie(inode);
+ else
+ nfs_fscache_enable_inode_cookie(inode);
+ nfs_fscache_inode_unlock(inode);
+ }
+}
+
+/*
+ * Replace a per-inode cookie due to revalidation detecting a file having
+ * changed on the server.
+ */
+void nfs_fscache_reset_inode_cookie(struct inode *inode)
+{
+ struct nfs_inode *nfsi = NFS_I(inode);
+ struct nfs_server *nfss = NFS_SERVER(inode);
+ struct fscache_cookie *old = nfsi->fscache;
+
+ nfs_fscache_inode_lock(inode);
+ if (nfsi->fscache) {
+ /* retire the current fscache cache and get a new one */
+ fscache_relinquish_cookie(nfsi->fscache, 1);
+
+ nfsi->fscache = fscache_acquire_cookie(
+ nfss->nfs_client->fscache,
+ &nfs_fscache_inode_object_def,
+ nfsi);
+
+ dfprintk(FSCACHE,
+ "NFS: revalidation new cookie (0x%p/0x%p/0x%p/0x%p)\n",
+ nfss, nfsi, old, nfsi->fscache);
+ }
+ nfs_fscache_inode_unlock(inode);
+}
+
+/*
+ * Release the caching state associated with a page, if the page isn't busy
+ * interacting with the cache.
+ * - Returns true (can release page) or false (page busy).
+ */
+int nfs_fscache_release_page(struct page *page, gfp_t gfp)
+{
+ struct nfs_inode *nfsi = NFS_I(page->mapping->host);
+ struct fscache_cookie *cookie = nfsi->fscache;
+
+ BUG_ON(!cookie);
+
+ if (fscache_check_page_write(cookie, page)) {
+ if (!(gfp & __GFP_WAIT))
+ return 0;
+ fscache_wait_on_page_write(cookie, page);
+ }
+
+ if (PageFsCache(page)) {
+ dfprintk(FSCACHE, "NFS: fscache releasepage (0x%p/0x%p/0x%p)\n",
+ cookie, page, nfsi);
+
+ fscache_uncache_page(cookie, page);
+ nfs_add_fscache_stats(page->mapping->host,
+ NFSIOS_FSCACHE_PAGES_UNCACHED, 1);
+ }
+
+ return 1;
+}
+
+/*
+ * Release the caching state associated with a page if undergoing complete page
+ * invalidation.
+ */
+void __nfs_fscache_invalidate_page(struct page *page, struct inode *inode)
+{
+ struct nfs_inode *nfsi = NFS_I(inode);
+ struct fscache_cookie *cookie = nfsi->fscache;
+
+ BUG_ON(!cookie);
+
+ dfprintk(FSCACHE, "NFS: fscache invalidatepage (0x%p/0x%p/0x%p)\n",
+ cookie, page, nfsi);
+
+ fscache_wait_on_page_write(cookie, page);
+
+ BUG_ON(!PageLocked(page));
+ fscache_uncache_page(cookie, page);
+ nfs_add_fscache_stats(page->mapping->host,
+ NFSIOS_FSCACHE_PAGES_UNCACHED, 1);
+}
+
+/*
+ * Handle completion of a page being read from the cache.
+ * - Called in process (keventd) context.
+ */
+static void nfs_readpage_from_fscache_complete(struct page *page,
+ void *context,
+ int error)
+{
+ dfprintk(FSCACHE,
+ "NFS: readpage_from_fscache_complete (0x%p/0x%p/%d)\n",
+ page, context, error);
+
+ /* if the read completes with an error, we just unlock the page and let
+ * the VM reissue the readpage */
+ if (!error) {
+ SetPageUptodate(page);
+ unlock_page(page);
+ } else {
+ error = nfs_readpage_async(context, page->mapping->host, page);
+ if (error)
+ unlock_page(page);
+ }
+}
+
+/*
+ * Retrieve a page from fscache
+ */
+int __nfs_readpage_from_fscache(struct nfs_open_context *ctx,
+ struct inode *inode, struct page *page)
+{
+ int ret;
+
+ dfprintk(FSCACHE,
+ "NFS: readpage_from_fscache(fsc:%p/p:%p(i:%lx f:%lx)/0x%p)\n",
+ NFS_I(inode)->fscache, page, page->index, page->flags, inode);
+
+ ret = fscache_read_or_alloc_page(NFS_I(inode)->fscache,
+ page,
+ nfs_readpage_from_fscache_complete,
+ ctx,
+ GFP_KERNEL);
+
+ switch (ret) {
+ case 0: /* read BIO submitted (page in fscache) */
+ dfprintk(FSCACHE,
+ "NFS: readpage_from_fscache: BIO submitted\n");
+ nfs_add_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_OK, 1);
+ return ret;
+
+ case -ENOBUFS: /* inode not in cache */
+ case -ENODATA: /* page not in cache */
+ nfs_add_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_FAIL, 1);
+ dfprintk(FSCACHE,
+ "NFS: readpage_from_fscache %d\n", ret);
+ return 1;
+
+ default:
+ dfprintk(FSCACHE, "NFS: readpage_from_fscache %d\n", ret);
+ nfs_add_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_FAIL, 1);
+ }
+ return ret;
+}
+
+/*
+ * Retrieve a set of pages from fscache
+ */
+int __nfs_readpages_from_fscache(struct nfs_open_context *ctx,
+ struct inode *inode,
+ struct address_space *mapping,
+ struct list_head *pages,
+ unsigned *nr_pages)
+{
+ int ret, npages = *nr_pages;
+
+ dfprintk(FSCACHE, "NFS: nfs_getpages_from_fscache (0x%p/%u/0x%p)\n",
+ NFS_I(inode)->fscache, npages, inode);
+
+ ret = fscache_read_or_alloc_pages(NFS_I(inode)->fscache,
+ mapping, pages, nr_pages,
+ nfs_readpage_from_fscache_complete,
+ ctx,
+ mapping_gfp_mask(mapping));
+ if (*nr_pages < npages)
+ nfs_add_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_OK,
+ npages);
+ if (*nr_pages > 0)
+ nfs_add_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_FAIL,
+ *nr_pages);
+
+ switch (ret) {
+ case 0: /* read submitted to the cache for all pages */
+ BUG_ON(!list_empty(pages));
+ BUG_ON(*nr_pages != 0);
+ dfprintk(FSCACHE,
+ "NFS: nfs_getpages_from_fscache: submitted\n");
+
+ return ret;
+
+ case -ENOBUFS: /* some pages aren't cached and can't be */
+ case -ENODATA: /* some pages aren't cached */
+ dfprintk(FSCACHE,
+ "NFS: nfs_getpages_from_fscache: no page: %d\n", ret);
+ return 1;
+
+ default:
+ dfprintk(FSCACHE,
+ "NFS: nfs_getpages_from_fscache: ret %d\n", ret);
+ }
+
+ return ret;
+}
+
+/*
+ * Store a newly fetched page in fscache
+ * - PG_fscache must be set on the page
+ */
+void __nfs_readpage_to_fscache(struct inode *inode, struct page *page, int sync)
+{
+ int ret;
+
+ dfprintk(FSCACHE,
+ "NFS: readpage_to_fscache(fsc:%p/p:%p(i:%lx f:%lx)/%d)\n",
+ NFS_I(inode)->fscache, page, page->index, page->flags, sync);
+
+ ret = fscache_write_page(NFS_I(inode)->fscache, page, GFP_KERNEL);
+ dfprintk(FSCACHE,
+ "NFS: readpage_to_fscache: p:%p(i:%lu f:%lx) ret %d\n",
+ page, page->index, page->flags, ret);
+
+ if (ret != 0) {
+ fscache_uncache_page(NFS_I(inode)->fscache, page);
+ nfs_add_fscache_stats(inode,
+ NFSIOS_FSCACHE_PAGES_WRITTEN_FAIL, 1);
+ nfs_add_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_UNCACHED, 1);
+ } else {
+ nfs_add_fscache_stats(inode,
+ NFSIOS_FSCACHE_PAGES_WRITTEN_OK, 1);
+ }
+}
diff --git a/fs/nfs/fscache.h b/fs/nfs/fscache.h
new file mode 100644
index 000000000000..6e809bb0ff08
--- /dev/null
+++ b/fs/nfs/fscache.h
@@ -0,0 +1,220 @@
+/* NFS filesystem cache interface definitions
+ *
+ * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#ifndef _NFS_FSCACHE_H
+#define _NFS_FSCACHE_H
+
+#include <linux/nfs_fs.h>
+#include <linux/nfs_mount.h>
+#include <linux/nfs4_mount.h>
+#include <linux/fscache.h>
+
+#ifdef CONFIG_NFS_FSCACHE
+
+/*
+ * set of NFS FS-Cache objects that form a superblock key
+ */
+struct nfs_fscache_key {
+ struct rb_node node;
+ struct nfs_client *nfs_client; /* the server */
+
+ /* the elements of the unique key - as used by nfs_compare_super() and
+ * nfs_compare_mount_options() to distinguish superblocks */
+ struct {
+ struct {
+ unsigned long s_flags; /* various flags
+ * (& NFS_MS_MASK) */
+ } super;
+
+ struct {
+ struct nfs_fsid fsid;
+ int flags;
+ unsigned int rsize; /* read size */
+ unsigned int wsize; /* write size */
+ unsigned int acregmin; /* attr cache timeouts */
+ unsigned int acregmax;
+ unsigned int acdirmin;
+ unsigned int acdirmax;
+ } nfs_server;
+
+ struct {
+ rpc_authflavor_t au_flavor;
+ } rpc_auth;
+
+ /* uniquifier - can be used if nfs_server.flags includes
+ * NFS_MOUNT_UNSHARED */
+ u8 uniq_len;
+ char uniquifier[0];
+ } key;
+};
+
+/*
+ * fscache-index.c
+ */
+extern struct fscache_netfs nfs_fscache_netfs;
+extern const struct fscache_cookie_def nfs_fscache_server_index_def;
+extern const struct fscache_cookie_def nfs_fscache_super_index_def;
+extern const struct fscache_cookie_def nfs_fscache_inode_object_def;
+
+extern int nfs_fscache_register(void);
+extern void nfs_fscache_unregister(void);
+
+/*
+ * fscache.c
+ */
+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 *,
+ struct nfs_parsed_mount_data *);
+extern void nfs_fscache_release_super_cookie(struct super_block *);
+
+extern void nfs_fscache_init_inode_cookie(struct inode *);
+extern void nfs_fscache_release_inode_cookie(struct inode *);
+extern void nfs_fscache_zap_inode_cookie(struct inode *);
+extern void nfs_fscache_set_inode_cookie(struct inode *, struct file *);
+extern void nfs_fscache_reset_inode_cookie(struct inode *);
+
+extern void __nfs_fscache_invalidate_page(struct page *, struct inode *);
+extern int nfs_fscache_release_page(struct page *, gfp_t);
+
+extern int __nfs_readpage_from_fscache(struct nfs_open_context *,
+ struct inode *, struct page *);
+extern int __nfs_readpages_from_fscache(struct nfs_open_context *,
+ struct inode *, struct address_space *,
+ struct list_head *, unsigned *);
+extern void __nfs_readpage_to_fscache(struct inode *, struct page *, int);
+
+/*
+ * wait for a page to complete writing to the cache
+ */
+static inline void nfs_fscache_wait_on_page_write(struct nfs_inode *nfsi,
+ struct page *page)
+{
+ if (PageFsCache(page))
+ fscache_wait_on_page_write(nfsi->fscache, page);
+}
+
+/*
+ * release the caching state associated with a page if undergoing complete page
+ * invalidation
+ */
+static inline void nfs_fscache_invalidate_page(struct page *page,
+ struct inode *inode)
+{
+ if (PageFsCache(page))
+ __nfs_fscache_invalidate_page(page, inode);
+}
+
+/*
+ * Retrieve a page from an inode data storage object.
+ */
+static inline int nfs_readpage_from_fscache(struct nfs_open_context *ctx,
+ struct inode *inode,
+ struct page *page)
+{
+ if (NFS_I(inode)->fscache)
+ return __nfs_readpage_from_fscache(ctx, inode, page);
+ return -ENOBUFS;
+}
+
+/*
+ * Retrieve a set of pages from an inode data storage object.
+ */
+static inline int nfs_readpages_from_fscache(struct nfs_open_context *ctx,
+ struct inode *inode,
+ struct address_space *mapping,
+ struct list_head *pages,
+ unsigned *nr_pages)
+{
+ if (NFS_I(inode)->fscache)
+ return __nfs_readpages_from_fscache(ctx, inode, mapping, pages,
+ nr_pages);
+ return -ENOBUFS;
+}
+
+/*
+ * Store a page newly fetched from the server in an inode data storage object
+ * in the cache.
+ */
+static inline void nfs_readpage_to_fscache(struct inode *inode,
+ struct page *page,
+ int sync)
+{
+ if (PageFsCache(page))
+ __nfs_readpage_to_fscache(inode, page, sync);
+}
+
+/*
+ * indicate the client caching state as readable text
+ */
+static inline const char *nfs_server_fscache_state(struct nfs_server *server)
+{
+ if (server->fscache && (server->options & NFS_OPTION_FSCACHE))
+ return "yes";
+ return "no ";
+}
+
+
+#else /* CONFIG_NFS_FSCACHE */
+static inline int nfs_fscache_register(void) { return 0; }
+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,
+ struct nfs_parsed_mount_data *data)
+{
+}
+static inline void nfs_fscache_release_super_cookie(struct super_block *sb) {}
+
+static inline void nfs_fscache_init_inode_cookie(struct inode *inode) {}
+static inline void nfs_fscache_release_inode_cookie(struct inode *inode) {}
+static inline void nfs_fscache_zap_inode_cookie(struct inode *inode) {}
+static inline void nfs_fscache_set_inode_cookie(struct inode *inode,
+ struct file *filp) {}
+static inline void nfs_fscache_reset_inode_cookie(struct inode *inode) {}
+
+static inline int nfs_fscache_release_page(struct page *page, gfp_t gfp)
+{
+ return 1; /* True: may release page */
+}
+static inline void nfs_fscache_invalidate_page(struct page *page,
+ struct inode *inode) {}
+static inline void nfs_fscache_wait_on_page_write(struct nfs_inode *nfsi,
+ struct page *page) {}
+
+static inline int nfs_readpage_from_fscache(struct nfs_open_context *ctx,
+ struct inode *inode,
+ struct page *page)
+{
+ return -ENOBUFS;
+}
+static inline int nfs_readpages_from_fscache(struct nfs_open_context *ctx,
+ struct inode *inode,
+ struct address_space *mapping,
+ struct list_head *pages,
+ unsigned *nr_pages)
+{
+ return -ENOBUFS;
+}
+static inline void nfs_readpage_to_fscache(struct inode *inode,
+ struct page *page, int sync) {}
+
+static inline const char *nfs_server_fscache_state(struct nfs_server *server)
+{
+ return "no ";
+}
+
+#endif /* CONFIG_NFS_FSCACHE */
+#endif /* _NFS_FSCACHE_H */
diff --git a/fs/nfs/getroot.c b/fs/nfs/getroot.c
index b7c9b2df1f29..46177cb87064 100644
--- a/fs/nfs/getroot.c
+++ b/fs/nfs/getroot.c
@@ -156,7 +156,7 @@ int nfs4_path_walk(struct nfs_server *server,
return ret;
}
- if (fattr.type != NFDIR) {
+ if (!S_ISDIR(fattr.mode)) {
printk(KERN_ERR "nfs4_get_root:"
" getroot encountered non-directory\n");
return -ENOTDIR;
@@ -213,7 +213,7 @@ eat_dot_dir:
return ret;
}
- if (fattr.type != NFDIR) {
+ if (!S_ISDIR(fattr.mode)) {
printk(KERN_ERR "nfs4_get_root:"
" lookupfh encountered non-directory\n");
return -ENOTDIR;
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 0c381686171e..64f87194d390 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -46,6 +46,7 @@
#include "delegation.h"
#include "iostat.h"
#include "internal.h"
+#include "fscache.h"
#define NFSDBG_FACILITY NFSDBG_VFS
@@ -66,6 +67,18 @@ nfs_fattr_to_ino_t(struct nfs_fattr *fattr)
}
/**
+ * nfs_wait_bit_killable - helper for functions that are sleeping on bit locks
+ * @word: long word containing the bit lock
+ */
+int nfs_wait_bit_killable(void *word)
+{
+ if (fatal_signal_pending(current))
+ return -ERESTARTSYS;
+ schedule();
+ return 0;
+}
+
+/**
* nfs_compat_user_ino64 - returns the user-visible inode number
* @fileid: 64-bit fileid
*
@@ -109,6 +122,7 @@ void nfs_clear_inode(struct inode *inode)
BUG_ON(!list_empty(&NFS_I(inode)->open_files));
nfs_zap_acl_cache(inode);
nfs_access_zap_cache(inode);
+ nfs_fscache_release_inode_cookie(inode);
}
/**
@@ -249,13 +263,10 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr)
struct inode *inode = ERR_PTR(-ENOENT);
unsigned long hash;
- if ((fattr->valid & NFS_ATTR_FATTR) == 0)
+ if ((fattr->valid & NFS_ATTR_FATTR_FILEID) == 0)
goto out_no_inode;
-
- if (!fattr->nlink) {
- printk("NFS: Buggy server - nlink == 0!\n");
+ if ((fattr->valid & NFS_ATTR_FATTR_TYPE) == 0)
goto out_no_inode;
- }
hash = nfs_fattr_to_ino_t(fattr);
@@ -291,7 +302,8 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr)
&& fattr->size <= NFS_LIMIT_READDIRPLUS)
set_bit(NFS_INO_ADVISE_RDPLUS, &NFS_I(inode)->flags);
/* Deal with crossing mountpoints */
- if (!nfs_fsid_equal(&NFS_SB(sb)->fsid, &fattr->fsid)) {
+ if ((fattr->valid & NFS_ATTR_FATTR_FSID)
+ && !nfs_fsid_equal(&NFS_SB(sb)->fsid, &fattr->fsid)) {
if (fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL)
inode->i_op = &nfs_referral_inode_operations;
else
@@ -304,30 +316,49 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr)
else
init_special_inode(inode, inode->i_mode, fattr->rdev);
+ memset(&inode->i_atime, 0, sizeof(inode->i_atime));
+ memset(&inode->i_mtime, 0, sizeof(inode->i_mtime));
+ memset(&inode->i_ctime, 0, sizeof(inode->i_ctime));
+ nfsi->change_attr = 0;
+ inode->i_size = 0;
+ inode->i_nlink = 0;
+ inode->i_uid = -2;
+ inode->i_gid = -2;
+ inode->i_blocks = 0;
+ memset(nfsi->cookieverf, 0, sizeof(nfsi->cookieverf));
+
nfsi->read_cache_jiffies = fattr->time_start;
nfsi->attr_gencount = fattr->gencount;
- inode->i_atime = fattr->atime;
- inode->i_mtime = fattr->mtime;
- inode->i_ctime = fattr->ctime;
- if (fattr->valid & NFS_ATTR_FATTR_V4)
+ if (fattr->valid & NFS_ATTR_FATTR_ATIME)
+ inode->i_atime = fattr->atime;
+ if (fattr->valid & NFS_ATTR_FATTR_MTIME)
+ inode->i_mtime = fattr->mtime;
+ if (fattr->valid & NFS_ATTR_FATTR_CTIME)
+ inode->i_ctime = fattr->ctime;
+ if (fattr->valid & NFS_ATTR_FATTR_CHANGE)
nfsi->change_attr = fattr->change_attr;
- inode->i_size = nfs_size_to_loff_t(fattr->size);
- inode->i_nlink = fattr->nlink;
- inode->i_uid = fattr->uid;
- inode->i_gid = fattr->gid;
- if (fattr->valid & (NFS_ATTR_FATTR_V3 | NFS_ATTR_FATTR_V4)) {
+ if (fattr->valid & NFS_ATTR_FATTR_SIZE)
+ inode->i_size = nfs_size_to_loff_t(fattr->size);
+ if (fattr->valid & NFS_ATTR_FATTR_NLINK)
+ inode->i_nlink = fattr->nlink;
+ if (fattr->valid & NFS_ATTR_FATTR_OWNER)
+ inode->i_uid = fattr->uid;
+ if (fattr->valid & NFS_ATTR_FATTR_GROUP)
+ inode->i_gid = fattr->gid;
+ if (fattr->valid & NFS_ATTR_FATTR_BLOCKS_USED)
+ inode->i_blocks = fattr->du.nfs2.blocks;
+ if (fattr->valid & NFS_ATTR_FATTR_SPACE_USED) {
/*
* report the blocks in 512byte units
*/
inode->i_blocks = nfs_calc_block_size(fattr->du.nfs3.used);
- } else {
- inode->i_blocks = fattr->du.nfs2.blocks;
}
nfsi->attrtimeo = NFS_MINATTRTIMEO(inode);
nfsi->attrtimeo_timestamp = now;
- memset(nfsi->cookieverf, 0, sizeof(nfsi->cookieverf));
nfsi->access_cache = RB_ROOT;
+ nfs_fscache_init_inode_cookie(inode);
+
unlock_new_inode(inode);
} else
nfs_refresh_inode(inode, fattr);
@@ -514,6 +545,32 @@ int nfs_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
return err;
}
+/**
+ * nfs_close_context - Common close_context() routine NFSv2/v3
+ * @ctx: pointer to context
+ * @is_sync: is this a synchronous close
+ *
+ * always ensure that the attributes are up to date if we're mounted
+ * with close-to-open semantics
+ */
+void nfs_close_context(struct nfs_open_context *ctx, int is_sync)
+{
+ struct inode *inode;
+ struct nfs_server *server;
+
+ if (!(ctx->mode & FMODE_WRITE))
+ return;
+ if (!is_sync)
+ return;
+ inode = ctx->path.dentry->d_inode;
+ if (!list_empty(&NFS_I(inode)->open_files))
+ return;
+ server = NFS_SERVER(inode);
+ if (server->flags & NFS_MOUNT_NOCTO)
+ return;
+ nfs_revalidate_inode(server, inode);
+}
+
static struct nfs_open_context *alloc_nfs_open_context(struct vfsmount *mnt, struct dentry *dentry, struct rpc_cred *cred)
{
struct nfs_open_context *ctx;
@@ -540,24 +597,15 @@ struct nfs_open_context *get_nfs_open_context(struct nfs_open_context *ctx)
return ctx;
}
-static void __put_nfs_open_context(struct nfs_open_context *ctx, int wait)
+static void __put_nfs_open_context(struct nfs_open_context *ctx, int is_sync)
{
- struct inode *inode;
-
- if (ctx == NULL)
- return;
+ struct inode *inode = ctx->path.dentry->d_inode;
- inode = ctx->path.dentry->d_inode;
if (!atomic_dec_and_lock(&ctx->count, &inode->i_lock))
return;
list_del(&ctx->list);
spin_unlock(&inode->i_lock);
- if (ctx->state != NULL) {
- if (wait)
- nfs4_close_sync(&ctx->path, ctx->state, ctx->mode);
- else
- nfs4_close_state(&ctx->path, ctx->state, ctx->mode);
- }
+ NFS_PROTO(inode)->close_context(ctx, is_sync);
if (ctx->cred != NULL)
put_rpccred(ctx->cred);
path_put(&ctx->path);
@@ -642,6 +690,7 @@ int nfs_open(struct inode *inode, struct file *filp)
ctx->mode = filp->f_mode;
nfs_file_set_open_context(filp, ctx);
put_nfs_open_context(ctx);
+ nfs_fscache_set_inode_cookie(inode, filp);
return 0;
}
@@ -670,9 +719,6 @@ __nfs_revalidate_inode(struct nfs_server *server, struct inode *inode)
if (NFS_STALE(inode))
goto out;
- if (NFS_STALE(inode))
- goto out;
-
nfs_inc_stats(inode, NFSIOS_INODEREVALIDATE);
status = NFS_PROTO(inode)->getattr(server, NFS_FH(inode), &fattr);
if (status != 0) {
@@ -745,6 +791,7 @@ static int nfs_invalidate_mapping_nolock(struct inode *inode, struct address_spa
memset(nfsi->cookieverf, 0, sizeof(nfsi->cookieverf));
spin_unlock(&inode->i_lock);
nfs_inc_stats(inode, NFSIOS_DATAINVALIDATE);
+ nfs_fscache_reset_inode_cookie(inode);
dfprintk(PAGECACHE, "NFS: (%s/%Ld) data cache invalidated\n",
inode->i_sb->s_id, (long long)NFS_FILEID(inode));
return 0;
@@ -815,25 +862,31 @@ static void nfs_wcc_update_inode(struct inode *inode, struct nfs_fattr *fattr)
{
struct nfs_inode *nfsi = NFS_I(inode);
- if ((fattr->valid & NFS_ATTR_WCC_V4) != 0 &&
- nfsi->change_attr == fattr->pre_change_attr) {
+ if ((fattr->valid & NFS_ATTR_FATTR_PRECHANGE)
+ && (fattr->valid & NFS_ATTR_FATTR_CHANGE)
+ && nfsi->change_attr == fattr->pre_change_attr) {
nfsi->change_attr = fattr->change_attr;
if (S_ISDIR(inode->i_mode))
nfsi->cache_validity |= NFS_INO_INVALID_DATA;
}
/* If we have atomic WCC data, we may update some attributes */
- if ((fattr->valid & NFS_ATTR_WCC) != 0) {
- if (timespec_equal(&inode->i_ctime, &fattr->pre_ctime))
+ if ((fattr->valid & NFS_ATTR_FATTR_PRECTIME)
+ && (fattr->valid & NFS_ATTR_FATTR_CTIME)
+ && timespec_equal(&inode->i_ctime, &fattr->pre_ctime))
memcpy(&inode->i_ctime, &fattr->ctime, sizeof(inode->i_ctime));
- if (timespec_equal(&inode->i_mtime, &fattr->pre_mtime)) {
+
+ if ((fattr->valid & NFS_ATTR_FATTR_PREMTIME)
+ && (fattr->valid & NFS_ATTR_FATTR_MTIME)
+ && timespec_equal(&inode->i_mtime, &fattr->pre_mtime)) {
memcpy(&inode->i_mtime, &fattr->mtime, sizeof(inode->i_mtime));
if (S_ISDIR(inode->i_mode))
nfsi->cache_validity |= NFS_INO_INVALID_DATA;
- }
- if (i_size_read(inode) == nfs_size_to_loff_t(fattr->pre_size) &&
- nfsi->npages == 0)
- i_size_write(inode, nfs_size_to_loff_t(fattr->size));
}
+ if ((fattr->valid & NFS_ATTR_FATTR_PRESIZE)
+ && (fattr->valid & NFS_ATTR_FATTR_SIZE)
+ && i_size_read(inode) == nfs_size_to_loff_t(fattr->pre_size)
+ && nfsi->npages == 0)
+ i_size_write(inode, nfs_size_to_loff_t(fattr->size));
}
/**
@@ -853,35 +906,39 @@ static int nfs_check_inode_attributes(struct inode *inode, struct nfs_fattr *fat
/* Has the inode gone and changed behind our back? */
- if (nfsi->fileid != fattr->fileid
- || (inode->i_mode & S_IFMT) != (fattr->mode & S_IFMT)) {
+ if ((fattr->valid & NFS_ATTR_FATTR_FILEID) && nfsi->fileid != fattr->fileid)
+ return -EIO;
+ if ((fattr->valid & NFS_ATTR_FATTR_TYPE) && (inode->i_mode & S_IFMT) != (fattr->mode & S_IFMT))
return -EIO;
- }
- if ((fattr->valid & NFS_ATTR_FATTR_V4) != 0 &&
+ if ((fattr->valid & NFS_ATTR_FATTR_CHANGE) != 0 &&
nfsi->change_attr != fattr->change_attr)
invalid |= NFS_INO_INVALID_ATTR|NFS_INO_REVAL_PAGECACHE;
/* Verify a few of the more important attributes */
- if (!timespec_equal(&inode->i_mtime, &fattr->mtime))
+ if ((fattr->valid & NFS_ATTR_FATTR_MTIME) && !timespec_equal(&inode->i_mtime, &fattr->mtime))
invalid |= NFS_INO_INVALID_ATTR|NFS_INO_REVAL_PAGECACHE;
- cur_size = i_size_read(inode);
- new_isize = nfs_size_to_loff_t(fattr->size);
- if (cur_size != new_isize && nfsi->npages == 0)
- invalid |= NFS_INO_INVALID_ATTR|NFS_INO_REVAL_PAGECACHE;
+ if (fattr->valid & NFS_ATTR_FATTR_SIZE) {
+ cur_size = i_size_read(inode);
+ new_isize = nfs_size_to_loff_t(fattr->size);
+ if (cur_size != new_isize && nfsi->npages == 0)
+ invalid |= NFS_INO_INVALID_ATTR|NFS_INO_REVAL_PAGECACHE;
+ }
/* Have any file permissions changed? */
- if ((inode->i_mode & S_IALLUGO) != (fattr->mode & S_IALLUGO)
- || inode->i_uid != fattr->uid
- || inode->i_gid != fattr->gid)
+ if ((fattr->valid & NFS_ATTR_FATTR_MODE) && (inode->i_mode & S_IALLUGO) != (fattr->mode & S_IALLUGO))
+ invalid |= NFS_INO_INVALID_ATTR | NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL;
+ if ((fattr->valid & NFS_ATTR_FATTR_OWNER) && inode->i_uid != fattr->uid)
+ invalid |= NFS_INO_INVALID_ATTR | NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL;
+ if ((fattr->valid & NFS_ATTR_FATTR_GROUP) && inode->i_gid != fattr->gid)
invalid |= NFS_INO_INVALID_ATTR | NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL;
/* Has the link count changed? */
- if (inode->i_nlink != fattr->nlink)
+ if ((fattr->valid & NFS_ATTR_FATTR_NLINK) && inode->i_nlink != fattr->nlink)
invalid |= NFS_INO_INVALID_ATTR;
- if (!timespec_equal(&inode->i_atime, &fattr->atime))
+ if ((fattr->valid & NFS_ATTR_FATTR_ATIME) && !timespec_equal(&inode->i_atime, &fattr->atime))
invalid |= NFS_INO_INVALID_ATIME;
if (invalid != 0)
@@ -893,11 +950,15 @@ static int nfs_check_inode_attributes(struct inode *inode, struct nfs_fattr *fat
static int nfs_ctime_need_update(const struct inode *inode, const struct nfs_fattr *fattr)
{
+ if (!(fattr->valid & NFS_ATTR_FATTR_CTIME))
+ return 0;
return timespec_compare(&fattr->ctime, &inode->i_ctime) > 0;
}
static int nfs_size_need_update(const struct inode *inode, const struct nfs_fattr *fattr)
{
+ if (!(fattr->valid & NFS_ATTR_FATTR_SIZE))
+ return 0;
return nfs_size_to_loff_t(fattr->size) > i_size_read(inode);
}
@@ -975,6 +1036,7 @@ int nfs_refresh_inode(struct inode *inode, struct nfs_fattr *fattr)
spin_lock(&inode->i_lock);
status = nfs_refresh_inode_locked(inode, fattr);
spin_unlock(&inode->i_lock);
+
return status;
}
@@ -1033,20 +1095,31 @@ int nfs_post_op_update_inode_force_wcc(struct inode *inode, struct nfs_fattr *fa
/* Don't do a WCC update if these attributes are already stale */
if ((fattr->valid & NFS_ATTR_FATTR) == 0 ||
!nfs_inode_attrs_need_update(inode, fattr)) {
- fattr->valid &= ~(NFS_ATTR_WCC_V4|NFS_ATTR_WCC);
+ fattr->valid &= ~(NFS_ATTR_FATTR_PRECHANGE
+ | NFS_ATTR_FATTR_PRESIZE
+ | NFS_ATTR_FATTR_PREMTIME
+ | NFS_ATTR_FATTR_PRECTIME);
goto out_noforce;
}
- if ((fattr->valid & NFS_ATTR_FATTR_V4) != 0 &&
- (fattr->valid & NFS_ATTR_WCC_V4) == 0) {
+ if ((fattr->valid & NFS_ATTR_FATTR_CHANGE) != 0 &&
+ (fattr->valid & NFS_ATTR_FATTR_PRECHANGE) == 0) {
fattr->pre_change_attr = NFS_I(inode)->change_attr;
- fattr->valid |= NFS_ATTR_WCC_V4;
+ fattr->valid |= NFS_ATTR_FATTR_PRECHANGE;
}
- if ((fattr->valid & NFS_ATTR_FATTR) != 0 &&
- (fattr->valid & NFS_ATTR_WCC) == 0) {
+ if ((fattr->valid & NFS_ATTR_FATTR_CTIME) != 0 &&
+ (fattr->valid & NFS_ATTR_FATTR_PRECTIME) == 0) {
memcpy(&fattr->pre_ctime, &inode->i_ctime, sizeof(fattr->pre_ctime));
+ fattr->valid |= NFS_ATTR_FATTR_PRECTIME;
+ }
+ if ((fattr->valid & NFS_ATTR_FATTR_MTIME) != 0 &&
+ (fattr->valid & NFS_ATTR_FATTR_PREMTIME) == 0) {
memcpy(&fattr->pre_mtime, &inode->i_mtime, sizeof(fattr->pre_mtime));
+ fattr->valid |= NFS_ATTR_FATTR_PREMTIME;
+ }
+ if ((fattr->valid & NFS_ATTR_FATTR_SIZE) != 0 &&
+ (fattr->valid & NFS_ATTR_FATTR_PRESIZE) == 0) {
fattr->pre_size = i_size_read(inode);
- fattr->valid |= NFS_ATTR_WCC;
+ fattr->valid |= NFS_ATTR_FATTR_PRESIZE;
}
out_noforce:
status = nfs_post_op_update_inode_locked(inode, fattr);
@@ -1078,18 +1151,18 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
__func__, inode->i_sb->s_id, inode->i_ino,
atomic_read(&inode->i_count), fattr->valid);
- if (nfsi->fileid != fattr->fileid)
+ if ((fattr->valid & NFS_ATTR_FATTR_FILEID) && nfsi->fileid != fattr->fileid)
goto out_fileid;
/*
* Make sure the inode's type hasn't changed.
*/
- if ((inode->i_mode & S_IFMT) != (fattr->mode & S_IFMT))
+ if ((fattr->valid & NFS_ATTR_FATTR_TYPE) && (inode->i_mode & S_IFMT) != (fattr->mode & S_IFMT))
goto out_changed;
server = NFS_SERVER(inode);
/* Update the fsid? */
- if (S_ISDIR(inode->i_mode) &&
+ if (S_ISDIR(inode->i_mode) && (fattr->valid & NFS_ATTR_FATTR_FSID) &&
!nfs_fsid_equal(&server->fsid, &fattr->fsid) &&
!test_bit(NFS_INO_MOUNTPOINT, &nfsi->flags))
server->fsid = fattr->fsid;
@@ -1099,14 +1172,27 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
*/
nfsi->read_cache_jiffies = fattr->time_start;
- nfsi->cache_validity &= ~(NFS_INO_INVALID_ATTR | NFS_INO_INVALID_ATIME
- | NFS_INO_REVAL_PAGECACHE);
+ 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);
/* Do atomic weak cache consistency updates */
nfs_wcc_update_inode(inode, fattr);
/* More cache consistency checks */
- if (!(fattr->valid & NFS_ATTR_FATTR_V4)) {
+ if (fattr->valid & NFS_ATTR_FATTR_CHANGE) {
+ if (nfsi->change_attr != 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;
+ if (S_ISDIR(inode->i_mode))
+ nfs_force_lookup_revalidate(inode);
+ nfsi->change_attr = fattr->change_attr;
+ }
+ }
+
+ 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",
@@ -1114,59 +1200,80 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
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));
}
+ }
+ 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))
+ if (!timespec_equal(&inode->i_ctime, &fattr->ctime)) {
invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL;
- } else if (nfsi->change_attr != 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;
- if (S_ISDIR(inode->i_mode))
- nfs_force_lookup_revalidate(inode);
+ /* 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));
+ }
}
/* Check if our cached file size is stale */
- new_isize = nfs_size_to_loff_t(fattr->size);
- cur_isize = i_size_read(inode);
- if (new_isize != cur_isize) {
- /* Do we perhaps have any outstanding writes, or has
- * the file grown beyond our last write? */
- if (nfsi->npages == 0 || new_isize > cur_isize) {
- i_size_write(inode, new_isize);
- invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA;
+ if (fattr->valid & NFS_ATTR_FATTR_SIZE) {
+ new_isize = nfs_size_to_loff_t(fattr->size);
+ cur_isize = i_size_read(inode);
+ if (new_isize != cur_isize) {
+ /* Do we perhaps have any outstanding writes, or has
+ * the file grown beyond our last write? */
+ if (nfsi->npages == 0 || new_isize > cur_isize) {
+ i_size_write(inode, new_isize);
+ invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA;
+ }
+ dprintk("NFS: isize change on server for file %s/%ld\n",
+ inode->i_sb->s_id, inode->i_ino);
}
- dprintk("NFS: isize change on server for file %s/%ld\n",
- inode->i_sb->s_id, inode->i_ino);
}
- memcpy(&inode->i_mtime, &fattr->mtime, sizeof(inode->i_mtime));
- memcpy(&inode->i_ctime, &fattr->ctime, sizeof(inode->i_ctime));
- memcpy(&inode->i_atime, &fattr->atime, sizeof(inode->i_atime));
- nfsi->change_attr = fattr->change_attr;
-
- if ((inode->i_mode & S_IALLUGO) != (fattr->mode & S_IALLUGO) ||
- inode->i_uid != fattr->uid ||
- inode->i_gid != fattr->gid)
- invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL;
+ if (fattr->valid & NFS_ATTR_FATTR_ATIME)
+ memcpy(&inode->i_atime, &fattr->atime, sizeof(inode->i_atime));
- if (inode->i_nlink != fattr->nlink)
- invalid |= NFS_INO_INVALID_ATTR;
+ 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;
+ }
+ }
+ 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;
+ }
+ }
+ 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;
+ }
+ }
- inode->i_mode = fattr->mode;
- inode->i_nlink = fattr->nlink;
- inode->i_uid = fattr->uid;
- inode->i_gid = fattr->gid;
+ if (fattr->valid & NFS_ATTR_FATTR_NLINK) {
+ if (inode->i_nlink != fattr->nlink) {
+ invalid |= NFS_INO_INVALID_ATTR;
+ if (S_ISDIR(inode->i_mode))
+ invalid |= NFS_INO_INVALID_DATA;
+ inode->i_nlink = fattr->nlink;
+ }
+ }
- if (fattr->valid & (NFS_ATTR_FATTR_V3 | NFS_ATTR_FATTR_V4)) {
+ if (fattr->valid & NFS_ATTR_FATTR_SPACE_USED) {
/*
* report the blocks in 512byte units
*/
inode->i_blocks = nfs_calc_block_size(fattr->du.nfs3.used);
- } else {
- inode->i_blocks = fattr->du.nfs2.blocks;
}
+ if (fattr->valid & NFS_ATTR_FATTR_BLOCKS_USED)
+ inode->i_blocks = fattr->du.nfs2.blocks;
/* Update attrtimeo value if we're out of the unstable period */
if (invalid & NFS_INO_INVALID_ATTR) {
@@ -1274,7 +1381,6 @@ static void init_once(void *foo)
INIT_LIST_HEAD(&nfsi->access_cache_entry_lru);
INIT_LIST_HEAD(&nfsi->access_cache_inode_lru);
INIT_RADIX_TREE(&nfsi->nfs_page_tree, GFP_ATOMIC);
- nfsi->ncommit = 0;
nfsi->npages = 0;
atomic_set(&nfsi->silly_count, 1);
INIT_HLIST_HEAD(&nfsi->silly_list);
@@ -1337,6 +1443,10 @@ static int __init init_nfs_fs(void)
{
int err;
+ err = nfs_fscache_register();
+ if (err < 0)
+ goto out7;
+
err = nfsiod_start();
if (err)
goto out6;
@@ -1389,6 +1499,8 @@ out4:
out5:
nfsiod_stop();
out6:
+ nfs_fscache_unregister();
+out7:
return err;
}
@@ -1399,6 +1511,7 @@ static void __exit exit_nfs_fs(void)
nfs_destroy_readpagecache();
nfs_destroy_inodecache();
nfs_destroy_nfspagecache();
+ nfs_fscache_unregister();
#ifdef CONFIG_PROC_FS
rpc_proc_unregister("nfs");
#endif
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 340ede8f608f..e4d6a8348adf 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -5,6 +5,8 @@
#include <linux/mount.h>
#include <linux/security.h>
+#define NFS_MS_MASK (MS_RDONLY|MS_NOSUID|MS_NODEV|MS_NOEXEC|MS_SYNCHRONOUS)
+
struct nfs_string;
/* Maximum number of readahead requests
@@ -37,10 +39,12 @@ struct nfs_parsed_mount_data {
int acregmin, acregmax,
acdirmin, acdirmax;
int namlen;
+ unsigned int options;
unsigned int bsize;
unsigned int auth_flavor_len;
rpc_authflavor_t auth_flavors[1];
char *client_address;
+ char *fscache_uniq;
struct {
struct sockaddr_storage address;
@@ -152,6 +156,9 @@ extern __be32 *nfs4_decode_dirent(__be32 *p, struct nfs_entry *entry, int plus);
extern struct rpc_procinfo nfs4_procedures[];
#endif
+/* proc.c */
+void nfs_close_context(struct nfs_open_context *ctx, int is_sync);
+
/* dir.c */
extern int nfs_access_cache_shrinker(int nr_to_scan, gfp_t gfp_mask);
@@ -165,6 +172,7 @@ extern void nfs_clear_inode(struct inode *);
extern void nfs4_clear_inode(struct inode *);
#endif
void nfs_zap_acl_cache(struct inode *inode);
+extern int nfs_wait_bit_killable(void *word);
/* super.c */
void nfs_parse_ip_address(char *, size_t, struct sockaddr *, size_t *);
diff --git a/fs/nfs/iostat.h b/fs/nfs/iostat.h
index a36952810032..a2ab2529b5ca 100644
--- a/fs/nfs/iostat.h
+++ b/fs/nfs/iostat.h
@@ -16,6 +16,9 @@
struct nfs_iostats {
unsigned long long bytes[__NFSIOS_BYTESMAX];
+#ifdef CONFIG_NFS_FSCACHE
+ unsigned long long fscache[__NFSIOS_FSCACHEMAX];
+#endif
unsigned long events[__NFSIOS_COUNTSMAX];
} ____cacheline_aligned;
@@ -57,6 +60,21 @@ static inline void nfs_add_stats(const struct inode *inode,
nfs_add_server_stats(NFS_SERVER(inode), stat, addend);
}
+#ifdef CONFIG_NFS_FSCACHE
+static inline void nfs_add_fscache_stats(struct inode *inode,
+ enum nfs_stat_fscachecounters stat,
+ unsigned long addend)
+{
+ struct nfs_iostats *iostats;
+ int cpu;
+
+ cpu = get_cpu();
+ iostats = per_cpu_ptr(NFS_SERVER(inode)->io_stats, cpu);
+ iostats->fscache[stat] += addend;
+ put_cpu_no_resched();
+}
+#endif
+
static inline struct nfs_iostats *nfs_alloc_iostats(void)
{
return alloc_percpu(struct nfs_iostats);
diff --git a/fs/nfs/nfs2xdr.c b/fs/nfs/nfs2xdr.c
index 28bab67d1519..c862c9340f9a 100644
--- a/fs/nfs/nfs2xdr.c
+++ b/fs/nfs/nfs2xdr.c
@@ -120,8 +120,8 @@ xdr_decode_time(__be32 *p, struct timespec *timep)
static __be32 *
xdr_decode_fattr(__be32 *p, struct nfs_fattr *fattr)
{
- u32 rdev;
- fattr->type = (enum nfs_ftype) ntohl(*p++);
+ u32 rdev, type;
+ type = ntohl(*p++);
fattr->mode = ntohl(*p++);
fattr->nlink = ntohl(*p++);
fattr->uid = ntohl(*p++);
@@ -136,10 +136,9 @@ xdr_decode_fattr(__be32 *p, struct nfs_fattr *fattr)
p = xdr_decode_time(p, &fattr->atime);
p = xdr_decode_time(p, &fattr->mtime);
p = xdr_decode_time(p, &fattr->ctime);
- fattr->valid |= NFS_ATTR_FATTR;
+ fattr->valid |= NFS_ATTR_FATTR_V2;
fattr->rdev = new_decode_dev(rdev);
- if (fattr->type == NFCHR && rdev == NFS2_FIFO_DEV) {
- fattr->type = NFFIFO;
+ if (type == NFCHR && rdev == NFS2_FIFO_DEV) {
fattr->mode = (fattr->mode & ~S_IFMT) | S_IFIFO;
fattr->rdev = 0;
}
diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c
index c55be7a7679e..d0cc5ce0edfe 100644
--- a/fs/nfs/nfs3proc.c
+++ b/fs/nfs/nfs3proc.c
@@ -328,7 +328,7 @@ nfs3_proc_create(struct inode *dir, struct dentry *dentry, struct iattr *sattr,
data->arg.create.verifier[1] = current->pid;
}
- sattr->ia_mode &= ~current->fs->umask;
+ sattr->ia_mode &= ~current_umask();
for (;;) {
status = nfs3_do_create(dir, dentry, data);
@@ -528,7 +528,7 @@ nfs3_proc_mkdir(struct inode *dir, struct dentry *dentry, struct iattr *sattr)
dprintk("NFS call mkdir %s\n", dentry->d_name.name);
- sattr->ia_mode &= ~current->fs->umask;
+ sattr->ia_mode &= ~current_umask();
data = nfs3_alloc_createdata();
if (data == NULL)
@@ -639,7 +639,7 @@ nfs3_proc_mknod(struct inode *dir, struct dentry *dentry, struct iattr *sattr,
dprintk("NFS call mknod %s %u:%u\n", dentry->d_name.name,
MAJOR(rdev), MINOR(rdev));
- sattr->ia_mode &= ~current->fs->umask;
+ sattr->ia_mode &= ~current_umask();
data = nfs3_alloc_createdata();
if (data == NULL)
@@ -834,4 +834,5 @@ const struct nfs_rpc_ops nfs_v3_clientops = {
.commit_done = nfs3_commit_done,
.lock = nfs3_proc_lock,
.clear_acl_cache = nfs3_forget_cached_acls,
+ .close_context = nfs_close_context,
};
diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c
index 6cdeacffde46..35869a4921f1 100644
--- a/fs/nfs/nfs3xdr.c
+++ b/fs/nfs/nfs3xdr.c
@@ -91,19 +91,15 @@
/*
* Map file type to S_IFMT bits
*/
-static struct {
- unsigned int mode;
- unsigned int nfs2type;
-} nfs_type2fmt[] = {
- { 0, NFNON },
- { S_IFREG, NFREG },
- { S_IFDIR, NFDIR },
- { S_IFBLK, NFBLK },
- { S_IFCHR, NFCHR },
- { S_IFLNK, NFLNK },
- { S_IFSOCK, NFSOCK },
- { S_IFIFO, NFFIFO },
- { 0, NFBAD }
+static const umode_t nfs_type2fmt[] = {
+ [NF3BAD] = 0,
+ [NF3REG] = S_IFREG,
+ [NF3DIR] = S_IFDIR,
+ [NF3BLK] = S_IFBLK,
+ [NF3CHR] = S_IFCHR,
+ [NF3LNK] = S_IFLNK,
+ [NF3SOCK] = S_IFSOCK,
+ [NF3FIFO] = S_IFIFO,
};
/*
@@ -148,13 +144,12 @@ static __be32 *
xdr_decode_fattr(__be32 *p, struct nfs_fattr *fattr)
{
unsigned int type, major, minor;
- int fmode;
+ umode_t fmode;
type = ntohl(*p++);
- if (type >= NF3BAD)
- type = NF3BAD;
- fmode = nfs_type2fmt[type].mode;
- fattr->type = nfs_type2fmt[type].nfs2type;
+ if (type > NF3FIFO)
+ type = NF3NON;
+ fmode = nfs_type2fmt[type];
fattr->mode = (ntohl(*p++) & ~S_IFMT) | fmode;
fattr->nlink = ntohl(*p++);
fattr->uid = ntohl(*p++);
@@ -177,7 +172,7 @@ xdr_decode_fattr(__be32 *p, struct nfs_fattr *fattr)
p = xdr_decode_time3(p, &fattr->ctime);
/* Update the mode bits */
- fattr->valid |= (NFS_ATTR_FATTR | NFS_ATTR_FATTR_V3);
+ fattr->valid |= NFS_ATTR_FATTR_V3;
return p;
}
@@ -233,7 +228,9 @@ xdr_decode_wcc_attr(__be32 *p, struct nfs_fattr *fattr)
p = xdr_decode_hyper(p, &fattr->pre_size);
p = xdr_decode_time3(p, &fattr->pre_mtime);
p = xdr_decode_time3(p, &fattr->pre_ctime);
- fattr->valid |= NFS_ATTR_WCC;
+ fattr->valid |= NFS_ATTR_FATTR_PRESIZE
+ | NFS_ATTR_FATTR_PREMTIME
+ | NFS_ATTR_FATTR_PRECTIME;
return p;
}
@@ -716,7 +713,8 @@ nfs3_xdr_setaclargs(struct rpc_rqst *req, __be32 *p,
if (args->npages != 0)
xdr_encode_pages(buf, args->pages, 0, args->len);
else
- req->rq_slen += args->len;
+ req->rq_slen = xdr_adjust_iovec(req->rq_svec,
+ p + XDR_QUADLEN(args->len));
err = nfsacl_encode(buf, base, args->inode,
(args->mask & NFS_ACL) ?
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 8dde84b988d9..a4d242680299 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -193,14 +193,6 @@ static void nfs4_setup_readdir(u64 cookie, __be32 *verifier, struct dentry *dent
kunmap_atomic(start, KM_USER0);
}
-static int nfs4_wait_bit_killable(void *word)
-{
- if (fatal_signal_pending(current))
- return -ERESTARTSYS;
- schedule();
- return 0;
-}
-
static int nfs4_wait_clnt_recover(struct nfs_client *clp)
{
int res;
@@ -208,7 +200,7 @@ static int nfs4_wait_clnt_recover(struct nfs_client *clp)
might_sleep();
res = wait_on_bit(&clp->cl_state, NFS4CLNT_MANAGER_RUNNING,
- nfs4_wait_bit_killable, TASK_KILLABLE);
+ nfs_wait_bit_killable, TASK_KILLABLE);
return res;
}
@@ -1439,7 +1431,7 @@ int nfs4_do_close(struct path *path, struct nfs4_state *state, int wait)
if (calldata->arg.seqid == NULL)
goto out_free_calldata;
calldata->arg.fmode = 0;
- calldata->arg.bitmask = server->attr_bitmask;
+ calldata->arg.bitmask = server->cache_consistency_bitmask;
calldata->res.fattr = &calldata->fattr;
calldata->res.seqid = calldata->arg.seqid;
calldata->res.server = server;
@@ -1509,7 +1501,7 @@ nfs4_atomic_open(struct inode *dir, struct dentry *dentry, struct nameidata *nd)
attr.ia_mode = nd->intent.open.create_mode;
attr.ia_valid = ATTR_MODE;
if (!IS_POSIXACL(dir))
- attr.ia_mode &= ~current->fs->umask;
+ attr.ia_mode &= ~current_umask();
} else {
attr.ia_valid = 0;
BUG_ON(nd->intent.open.flags & O_CREAT);
@@ -1580,6 +1572,15 @@ out_drop:
return 0;
}
+void nfs4_close_context(struct nfs_open_context *ctx, int is_sync)
+{
+ if (ctx->state == NULL)
+ return;
+ if (is_sync)
+ nfs4_close_sync(&ctx->path, ctx->state, ctx->mode);
+ else
+ nfs4_close_state(&ctx->path, ctx->state, ctx->mode);
+}
static int _nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *fhandle)
{
@@ -1600,6 +1601,9 @@ static int _nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *f
server->caps |= NFS_CAP_HARDLINKS;
if (res.has_symlinks != 0)
server->caps |= NFS_CAP_SYMLINKS;
+ 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;
server->acl_bitmask = res.acl_bitmask;
}
return status;
@@ -2079,7 +2083,7 @@ static void nfs4_proc_unlink_setup(struct rpc_message *msg, struct inode *dir)
struct nfs_removeargs *args = msg->rpc_argp;
struct nfs_removeres *res = msg->rpc_resp;
- args->bitmask = server->attr_bitmask;
+ args->bitmask = server->cache_consistency_bitmask;
res->server = server;
msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_REMOVE];
}
@@ -2323,7 +2327,7 @@ static int _nfs4_proc_readdir(struct dentry *dentry, struct rpc_cred *cred,
.pages = &page,
.pgbase = 0,
.count = count,
- .bitmask = NFS_SERVER(dentry->d_inode)->attr_bitmask,
+ .bitmask = NFS_SERVER(dentry->d_inode)->cache_consistency_bitmask,
};
struct nfs4_readdir_res res;
struct rpc_message msg = {
@@ -2552,7 +2556,7 @@ static void nfs4_proc_write_setup(struct nfs_write_data *data, struct rpc_messag
{
struct nfs_server *server = NFS_SERVER(data->inode);
- data->args.bitmask = server->attr_bitmask;
+ data->args.bitmask = server->cache_consistency_bitmask;
data->res.server = server;
data->timestamp = jiffies;
@@ -2575,7 +2579,7 @@ static void nfs4_proc_commit_setup(struct nfs_write_data *data, struct rpc_messa
{
struct nfs_server *server = NFS_SERVER(data->inode);
- data->args.bitmask = server->attr_bitmask;
+ data->args.bitmask = server->cache_consistency_bitmask;
data->res.server = server;
msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_COMMIT];
}
@@ -3678,6 +3682,19 @@ ssize_t nfs4_listxattr(struct dentry *dentry, char *buf, size_t buflen)
return len;
}
+static void nfs_fixup_referral_attributes(struct nfs_fattr *fattr)
+{
+ if (!((fattr->valid & NFS_ATTR_FATTR_FILEID) &&
+ (fattr->valid & NFS_ATTR_FATTR_FSID) &&
+ (fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL)))
+ return;
+
+ fattr->valid |= NFS_ATTR_FATTR_TYPE | NFS_ATTR_FATTR_MODE |
+ NFS_ATTR_FATTR_NLINK;
+ fattr->mode = S_IFDIR | S_IRUGO | S_IXUGO;
+ fattr->nlink = 2;
+}
+
int nfs4_proc_fs_locations(struct inode *dir, const struct qstr *name,
struct nfs4_fs_locations *fs_locations, struct page *page)
{
@@ -3704,6 +3721,7 @@ int nfs4_proc_fs_locations(struct inode *dir, const struct qstr *name,
fs_locations->server = server;
fs_locations->nlocations = 0;
status = rpc_call_sync(server->client, &msg, 0);
+ nfs_fixup_referral_attributes(&fs_locations->fattr);
dprintk("%s: returned status = %d\n", __func__, status);
return status;
}
@@ -3767,6 +3785,7 @@ const struct nfs_rpc_ops nfs_v4_clientops = {
.commit_done = nfs4_commit_done,
.lock = nfs4_proc_lock,
.clear_acl_cache = nfs4_zap_acl_attr,
+ .close_context = nfs4_close_context,
};
/*
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 2022fe47966f..0298e909559f 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -62,8 +62,14 @@ static LIST_HEAD(nfs4_clientid_list);
static int nfs4_init_client(struct nfs_client *clp, struct rpc_cred *cred)
{
- int status = nfs4_proc_setclientid(clp, NFS4_CALLBACK,
- nfs_callback_tcpport, cred);
+ unsigned short port;
+ int status;
+
+ port = nfs_callback_tcpport;
+ if (clp->cl_addr.ss_family == AF_INET6)
+ port = nfs_callback_tcpport6;
+
+ status = nfs4_proc_setclientid(clp, NFS4_CALLBACK, port, cred);
if (status == 0)
status = nfs4_proc_setclientid_confirm(clp, cred);
if (status == 0)
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index d1e4c8f8a0a9..1690f0e44b91 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -522,20 +522,17 @@ static int nfs4_stat_to_errno(int);
decode_lookup_maxsz + \
decode_fs_locations_maxsz)
-static struct {
- unsigned int mode;
- unsigned int nfs2type;
-} nfs_type2fmt[] = {
- { 0, NFNON },
- { S_IFREG, NFREG },
- { S_IFDIR, NFDIR },
- { S_IFBLK, NFBLK },
- { S_IFCHR, NFCHR },
- { S_IFLNK, NFLNK },
- { S_IFSOCK, NFSOCK },
- { S_IFIFO, NFFIFO },
- { 0, NFNON },
- { 0, NFNON },
+static const umode_t nfs_type2fmt[] = {
+ [NF4BAD] = 0,
+ [NF4REG] = S_IFREG,
+ [NF4DIR] = S_IFDIR,
+ [NF4BLK] = S_IFBLK,
+ [NF4CHR] = S_IFCHR,
+ [NF4LNK] = S_IFLNK,
+ [NF4SOCK] = S_IFSOCK,
+ [NF4FIFO] = S_IFIFO,
+ [NF4ATTRDIR] = 0,
+ [NF4NAMEDATTR] = 0,
};
struct compound_hdr {
@@ -2160,6 +2157,7 @@ static int decode_attr_supported(struct xdr_stream *xdr, uint32_t *bitmap, uint3
static int decode_attr_type(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t *type)
{
__be32 *p;
+ int ret = 0;
*type = 0;
if (unlikely(bitmap[0] & (FATTR4_WORD0_TYPE - 1U)))
@@ -2172,14 +2170,16 @@ static int decode_attr_type(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t *
return -EIO;
}
bitmap[0] &= ~FATTR4_WORD0_TYPE;
+ ret = NFS_ATTR_FATTR_TYPE;
}
- dprintk("%s: type=0%o\n", __func__, nfs_type2fmt[*type].nfs2type);
- return 0;
+ dprintk("%s: type=0%o\n", __func__, nfs_type2fmt[*type]);
+ return ret;
}
static int decode_attr_change(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t *change)
{
__be32 *p;
+ int ret = 0;
*change = 0;
if (unlikely(bitmap[0] & (FATTR4_WORD0_CHANGE - 1U)))
@@ -2188,15 +2188,17 @@ static int decode_attr_change(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t
READ_BUF(8);
READ64(*change);
bitmap[0] &= ~FATTR4_WORD0_CHANGE;
+ ret = NFS_ATTR_FATTR_CHANGE;
}
dprintk("%s: change attribute=%Lu\n", __func__,
(unsigned long long)*change);
- return 0;
+ return ret;
}
static int decode_attr_size(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t *size)
{
__be32 *p;
+ int ret = 0;
*size = 0;
if (unlikely(bitmap[0] & (FATTR4_WORD0_SIZE - 1U)))
@@ -2205,9 +2207,10 @@ static int decode_attr_size(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t *
READ_BUF(8);
READ64(*size);
bitmap[0] &= ~FATTR4_WORD0_SIZE;
+ ret = NFS_ATTR_FATTR_SIZE;
}
dprintk("%s: file size=%Lu\n", __func__, (unsigned long long)*size);
- return 0;
+ return ret;
}
static int decode_attr_link_support(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t *res)
@@ -2245,6 +2248,7 @@ static int decode_attr_symlink_support(struct xdr_stream *xdr, uint32_t *bitmap,
static int decode_attr_fsid(struct xdr_stream *xdr, uint32_t *bitmap, struct nfs_fsid *fsid)
{
__be32 *p;
+ int ret = 0;
fsid->major = 0;
fsid->minor = 0;
@@ -2255,11 +2259,12 @@ static int decode_attr_fsid(struct xdr_stream *xdr, uint32_t *bitmap, struct nfs
READ64(fsid->major);
READ64(fsid->minor);
bitmap[0] &= ~FATTR4_WORD0_FSID;
+ ret = NFS_ATTR_FATTR_FSID;
}
dprintk("%s: fsid=(0x%Lx/0x%Lx)\n", __func__,
(unsigned long long)fsid->major,
(unsigned long long)fsid->minor);
- return 0;
+ return ret;
}
static int decode_attr_lease_time(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t *res)
@@ -2297,6 +2302,7 @@ static int decode_attr_aclsupport(struct xdr_stream *xdr, uint32_t *bitmap, uint
static int decode_attr_fileid(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t *fileid)
{
__be32 *p;
+ int ret = 0;
*fileid = 0;
if (unlikely(bitmap[0] & (FATTR4_WORD0_FILEID - 1U)))
@@ -2305,14 +2311,16 @@ static int decode_attr_fileid(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t
READ_BUF(8);
READ64(*fileid);
bitmap[0] &= ~FATTR4_WORD0_FILEID;
+ ret = NFS_ATTR_FATTR_FILEID;
}
dprintk("%s: fileid=%Lu\n", __func__, (unsigned long long)*fileid);
- return 0;
+ return ret;
}
static int decode_attr_mounted_on_fileid(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t *fileid)
{
__be32 *p;
+ int ret = 0;
*fileid = 0;
if (unlikely(bitmap[1] & (FATTR4_WORD1_MOUNTED_ON_FILEID - 1U)))
@@ -2321,9 +2329,10 @@ static int decode_attr_mounted_on_fileid(struct xdr_stream *xdr, uint32_t *bitma
READ_BUF(8);
READ64(*fileid);
bitmap[1] &= ~FATTR4_WORD1_MOUNTED_ON_FILEID;
+ ret = NFS_ATTR_FATTR_FILEID;
}
dprintk("%s: fileid=%Lu\n", __func__, (unsigned long long)*fileid);
- return 0;
+ return ret;
}
static int decode_attr_files_avail(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t *res)
@@ -2479,6 +2488,8 @@ static int decode_attr_fs_locations(struct xdr_stream *xdr, uint32_t *bitmap, st
if (res->nlocations < NFS4_FS_LOCATIONS_MAXENTRIES)
res->nlocations++;
}
+ if (res->nlocations != 0)
+ status = NFS_ATTR_FATTR_V4_REFERRAL;
out:
dprintk("%s: fs_locations done, error = %d\n", __func__, status);
return status;
@@ -2580,26 +2591,30 @@ static int decode_attr_maxwrite(struct xdr_stream *xdr, uint32_t *bitmap, uint32
return status;
}
-static int decode_attr_mode(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t *mode)
+static int decode_attr_mode(struct xdr_stream *xdr, uint32_t *bitmap, umode_t *mode)
{
+ uint32_t tmp;
__be32 *p;
+ int ret = 0;
*mode = 0;
if (unlikely(bitmap[1] & (FATTR4_WORD1_MODE - 1U)))
return -EIO;
if (likely(bitmap[1] & FATTR4_WORD1_MODE)) {
READ_BUF(4);
- READ32(*mode);
- *mode &= ~S_IFMT;
+ READ32(tmp);
+ *mode = tmp & ~S_IFMT;
bitmap[1] &= ~FATTR4_WORD1_MODE;
+ ret = NFS_ATTR_FATTR_MODE;
}
dprintk("%s: file mode=0%o\n", __func__, (unsigned int)*mode);
- return 0;
+ return ret;
}
static int decode_attr_nlink(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t *nlink)
{
__be32 *p;
+ int ret = 0;
*nlink = 1;
if (unlikely(bitmap[1] & (FATTR4_WORD1_NUMLINKS - 1U)))
@@ -2608,15 +2623,17 @@ static int decode_attr_nlink(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t
READ_BUF(4);
READ32(*nlink);
bitmap[1] &= ~FATTR4_WORD1_NUMLINKS;
+ ret = NFS_ATTR_FATTR_NLINK;
}
dprintk("%s: nlink=%u\n", __func__, (unsigned int)*nlink);
- return 0;
+ return ret;
}
static int decode_attr_owner(struct xdr_stream *xdr, uint32_t *bitmap, struct nfs_client *clp, uint32_t *uid)
{
uint32_t len;
__be32 *p;
+ int ret = 0;
*uid = -2;
if (unlikely(bitmap[1] & (FATTR4_WORD1_OWNER - 1U)))
@@ -2626,7 +2643,9 @@ static int decode_attr_owner(struct xdr_stream *xdr, uint32_t *bitmap, struct nf
READ32(len);
READ_BUF(len);
if (len < XDR_MAX_NETOBJ) {
- if (nfs_map_name_to_uid(clp, (char *)p, len, uid) != 0)
+ if (nfs_map_name_to_uid(clp, (char *)p, len, uid) == 0)
+ ret = NFS_ATTR_FATTR_OWNER;
+ else
dprintk("%s: nfs_map_name_to_uid failed!\n",
__func__);
} else
@@ -2635,13 +2654,14 @@ static int decode_attr_owner(struct xdr_stream *xdr, uint32_t *bitmap, struct nf
bitmap[1] &= ~FATTR4_WORD1_OWNER;
}
dprintk("%s: uid=%d\n", __func__, (int)*uid);
- return 0;
+ return ret;
}
static int decode_attr_group(struct xdr_stream *xdr, uint32_t *bitmap, struct nfs_client *clp, uint32_t *gid)
{
uint32_t len;
__be32 *p;
+ int ret = 0;
*gid = -2;
if (unlikely(bitmap[1] & (FATTR4_WORD1_OWNER_GROUP - 1U)))
@@ -2651,7 +2671,9 @@ static int decode_attr_group(struct xdr_stream *xdr, uint32_t *bitmap, struct nf
READ32(len);
READ_BUF(len);
if (len < XDR_MAX_NETOBJ) {
- if (nfs_map_group_to_gid(clp, (char *)p, len, gid) != 0)
+ if (nfs_map_group_to_gid(clp, (char *)p, len, gid) == 0)
+ ret = NFS_ATTR_FATTR_GROUP;
+ else
dprintk("%s: nfs_map_group_to_gid failed!\n",
__func__);
} else
@@ -2660,13 +2682,14 @@ static int decode_attr_group(struct xdr_stream *xdr, uint32_t *bitmap, struct nf
bitmap[1] &= ~FATTR4_WORD1_OWNER_GROUP;
}
dprintk("%s: gid=%d\n", __func__, (int)*gid);
- return 0;
+ return ret;
}
static int decode_attr_rdev(struct xdr_stream *xdr, uint32_t *bitmap, dev_t *rdev)
{
uint32_t major = 0, minor = 0;
__be32 *p;
+ int ret = 0;
*rdev = MKDEV(0,0);
if (unlikely(bitmap[1] & (FATTR4_WORD1_RAWDEV - 1U)))
@@ -2681,9 +2704,10 @@ static int decode_attr_rdev(struct xdr_stream *xdr, uint32_t *bitmap, dev_t *rde
if (MAJOR(tmp) == major && MINOR(tmp) == minor)
*rdev = tmp;
bitmap[1] &= ~ FATTR4_WORD1_RAWDEV;
+ ret = NFS_ATTR_FATTR_RDEV;
}
dprintk("%s: rdev=(0x%x:0x%x)\n", __func__, major, minor);
- return 0;
+ return ret;
}
static int decode_attr_space_avail(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t *res)
@@ -2740,6 +2764,7 @@ static int decode_attr_space_total(struct xdr_stream *xdr, uint32_t *bitmap, uin
static int decode_attr_space_used(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t *used)
{
__be32 *p;
+ int ret = 0;
*used = 0;
if (unlikely(bitmap[1] & (FATTR4_WORD1_SPACE_USED - 1U)))
@@ -2748,10 +2773,11 @@ static int decode_attr_space_used(struct xdr_stream *xdr, uint32_t *bitmap, uint
READ_BUF(8);
READ64(*used);
bitmap[1] &= ~FATTR4_WORD1_SPACE_USED;
+ ret = NFS_ATTR_FATTR_SPACE_USED;
}
dprintk("%s: space used=%Lu\n", __func__,
(unsigned long long)*used);
- return 0;
+ return ret;
}
static int decode_attr_time(struct xdr_stream *xdr, struct timespec *time)
@@ -2778,6 +2804,8 @@ static int decode_attr_time_access(struct xdr_stream *xdr, uint32_t *bitmap, str
return -EIO;
if (likely(bitmap[1] & FATTR4_WORD1_TIME_ACCESS)) {
status = decode_attr_time(xdr, time);
+ if (status == 0)
+ status = NFS_ATTR_FATTR_ATIME;
bitmap[1] &= ~FATTR4_WORD1_TIME_ACCESS;
}
dprintk("%s: atime=%ld\n", __func__, (long)time->tv_sec);
@@ -2794,6 +2822,8 @@ static int decode_attr_time_metadata(struct xdr_stream *xdr, uint32_t *bitmap, s
return -EIO;
if (likely(bitmap[1] & FATTR4_WORD1_TIME_METADATA)) {
status = decode_attr_time(xdr, time);
+ if (status == 0)
+ status = NFS_ATTR_FATTR_CTIME;
bitmap[1] &= ~FATTR4_WORD1_TIME_METADATA;
}
dprintk("%s: ctime=%ld\n", __func__, (long)time->tv_sec);
@@ -2810,6 +2840,8 @@ static int decode_attr_time_modify(struct xdr_stream *xdr, uint32_t *bitmap, str
return -EIO;
if (likely(bitmap[1] & FATTR4_WORD1_TIME_MODIFY)) {
status = decode_attr_time(xdr, time);
+ if (status == 0)
+ status = NFS_ATTR_FATTR_MTIME;
bitmap[1] &= ~FATTR4_WORD1_TIME_MODIFY;
}
dprintk("%s: mtime=%ld\n", __func__, (long)time->tv_sec);
@@ -2994,63 +3026,116 @@ static int decode_getfattr(struct xdr_stream *xdr, struct nfs_fattr *fattr, cons
uint32_t attrlen,
bitmap[2] = {0},
type;
- int status, fmode = 0;
+ int status;
+ umode_t fmode = 0;
uint64_t fileid;
- if ((status = decode_op_hdr(xdr, OP_GETATTR)) != 0)
- goto xdr_error;
- if ((status = decode_attr_bitmap(xdr, bitmap)) != 0)
+ status = decode_op_hdr(xdr, OP_GETATTR);
+ if (status < 0)
goto xdr_error;
- fattr->bitmap[0] = bitmap[0];
- fattr->bitmap[1] = bitmap[1];
+ status = decode_attr_bitmap(xdr, bitmap);
+ if (status < 0)
+ goto xdr_error;
- if ((status = decode_attr_length(xdr, &attrlen, &savep)) != 0)
+ status = decode_attr_length(xdr, &attrlen, &savep);
+ if (status < 0)
goto xdr_error;
- if ((status = decode_attr_type(xdr, bitmap, &type)) != 0)
+ status = decode_attr_type(xdr, bitmap, &type);
+ if (status < 0)
goto xdr_error;
- fattr->type = nfs_type2fmt[type].nfs2type;
- fmode = nfs_type2fmt[type].mode;
+ fattr->mode = 0;
+ if (status != 0) {
+ fattr->mode |= nfs_type2fmt[type];
+ fattr->valid |= status;
+ }
- if ((status = decode_attr_change(xdr, bitmap, &fattr->change_attr)) != 0)
+ status = decode_attr_change(xdr, bitmap, &fattr->change_attr);
+ if (status < 0)
goto xdr_error;
- if ((status = decode_attr_size(xdr, bitmap, &fattr->size)) != 0)
+ fattr->valid |= status;
+
+ status = decode_attr_size(xdr, bitmap, &fattr->size);
+ if (status < 0)
goto xdr_error;
- if ((status = decode_attr_fsid(xdr, bitmap, &fattr->fsid)) != 0)
+ fattr->valid |= status;
+
+ status = decode_attr_fsid(xdr, bitmap, &fattr->fsid);
+ if (status < 0)
goto xdr_error;
- if ((status = decode_attr_fileid(xdr, bitmap, &fattr->fileid)) != 0)
+ fattr->valid |= status;
+
+ status = decode_attr_fileid(xdr, bitmap, &fattr->fileid);
+ if (status < 0)
goto xdr_error;
- if ((status = decode_attr_fs_locations(xdr, bitmap, container_of(fattr,
+ fattr->valid |= status;
+
+ status = decode_attr_fs_locations(xdr, bitmap, container_of(fattr,
struct nfs4_fs_locations,
- fattr))) != 0)
+ fattr));
+ if (status < 0)
goto xdr_error;
- if ((status = decode_attr_mode(xdr, bitmap, &fattr->mode)) != 0)
+ fattr->valid |= status;
+
+ status = decode_attr_mode(xdr, bitmap, &fmode);
+ if (status < 0)
goto xdr_error;
- fattr->mode |= fmode;
- if ((status = decode_attr_nlink(xdr, bitmap, &fattr->nlink)) != 0)
+ if (status != 0) {
+ fattr->mode |= fmode;
+ fattr->valid |= status;
+ }
+
+ status = decode_attr_nlink(xdr, bitmap, &fattr->nlink);
+ if (status < 0)
goto xdr_error;
- if ((status = decode_attr_owner(xdr, bitmap, server->nfs_client, &fattr->uid)) != 0)
+ fattr->valid |= status;
+
+ status = decode_attr_owner(xdr, bitmap, server->nfs_client, &fattr->uid);
+ if (status < 0)
goto xdr_error;
- if ((status = decode_attr_group(xdr, bitmap, server->nfs_client, &fattr->gid)) != 0)
+ fattr->valid |= status;
+
+ status = decode_attr_group(xdr, bitmap, server->nfs_client, &fattr->gid);
+ if (status < 0)
goto xdr_error;
- if ((status = decode_attr_rdev(xdr, bitmap, &fattr->rdev)) != 0)
+ fattr->valid |= status;
+
+ status = decode_attr_rdev(xdr, bitmap, &fattr->rdev);
+ if (status < 0)
goto xdr_error;
- if ((status = decode_attr_space_used(xdr, bitmap, &fattr->du.nfs3.used)) != 0)
+ fattr->valid |= status;
+
+ status = decode_attr_space_used(xdr, bitmap, &fattr->du.nfs3.used);
+ if (status < 0)
goto xdr_error;
- if ((status = decode_attr_time_access(xdr, bitmap, &fattr->atime)) != 0)
+ fattr->valid |= status;
+
+ status = decode_attr_time_access(xdr, bitmap, &fattr->atime);
+ if (status < 0)
goto xdr_error;
- if ((status = decode_attr_time_metadata(xdr, bitmap, &fattr->ctime)) != 0)
+ fattr->valid |= status;
+
+ status = decode_attr_time_metadata(xdr, bitmap, &fattr->ctime);
+ if (status < 0)
goto xdr_error;
- if ((status = decode_attr_time_modify(xdr, bitmap, &fattr->mtime)) != 0)
+ fattr->valid |= status;
+
+ status = decode_attr_time_modify(xdr, bitmap, &fattr->mtime);
+ if (status < 0)
goto xdr_error;
- if ((status = decode_attr_mounted_on_fileid(xdr, bitmap, &fileid)) != 0)
+ fattr->valid |= status;
+
+ status = decode_attr_mounted_on_fileid(xdr, bitmap, &fileid);
+ if (status < 0)
goto xdr_error;
- if (fattr->fileid == 0 && fileid != 0)
+ if (status != 0 && !(fattr->valid & status)) {
fattr->fileid = fileid;
- if ((status = verify_attr_len(xdr, savep, attrlen)) == 0)
- fattr->valid = NFS_ATTR_FATTR | NFS_ATTR_FATTR_V3 | NFS_ATTR_FATTR_V4;
+ fattr->valid |= status;
+ }
+
+ status = verify_attr_len(xdr, savep, attrlen);
xdr_error:
dprintk("%s: xdr returned %d\n", __func__, -status);
return status;
@@ -4078,9 +4163,7 @@ static int nfs4_xdr_dec_setattr(struct rpc_rqst *rqstp, __be32 *p, struct nfs_se
status = decode_setattr(&xdr, res);
if (status)
goto out;
- status = decode_getfattr(&xdr, res->fattr, res->server);
- if (status == NFS4ERR_DELAY)
- status = 0;
+ decode_getfattr(&xdr, res->fattr, res->server);
out:
return status;
}
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index 7f079209d70a..e2975939126a 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -176,17 +176,6 @@ void nfs_release_request(struct nfs_page *req)
kref_put(&req->wb_kref, nfs_free_request);
}
-static int nfs_wait_bit_killable(void *word)
-{
- int ret = 0;
-
- if (fatal_signal_pending(current))
- ret = -ERESTARTSYS;
- else
- schedule();
- return ret;
-}
-
/**
* nfs_wait_on_request - Wait for a request to complete.
* @req: request to wait upon.
diff --git a/fs/nfs/proc.c b/fs/nfs/proc.c
index 193465210d7c..7be72d90d49d 100644
--- a/fs/nfs/proc.c
+++ b/fs/nfs/proc.c
@@ -663,4 +663,5 @@ const struct nfs_rpc_ops nfs_v2_clientops = {
.commit_setup = nfs_proc_commit_setup,
.lock = nfs_proc_lock,
.lock_check_bounds = nfs_lock_check_bounds,
+ .close_context = nfs_close_context,
};
diff --git a/fs/nfs/read.c b/fs/nfs/read.c
index f856004bb7fa..4ace3c50a8eb 100644
--- a/fs/nfs/read.c
+++ b/fs/nfs/read.c
@@ -24,6 +24,7 @@
#include "internal.h"
#include "iostat.h"
+#include "fscache.h"
#define NFSDBG_FACILITY NFSDBG_PAGECACHE
@@ -111,8 +112,8 @@ static void nfs_readpage_truncate_uninitialised_page(struct nfs_read_data *data)
}
}
-static int nfs_readpage_async(struct nfs_open_context *ctx, struct inode *inode,
- struct page *page)
+int nfs_readpage_async(struct nfs_open_context *ctx, struct inode *inode,
+ struct page *page)
{
LIST_HEAD(one_request);
struct nfs_page *new;
@@ -139,6 +140,11 @@ static int nfs_readpage_async(struct nfs_open_context *ctx, struct inode *inode,
static void nfs_readpage_release(struct nfs_page *req)
{
+ struct inode *d_inode = req->wb_context->path.dentry->d_inode;
+
+ if (PageUptodate(req->wb_page))
+ nfs_readpage_to_fscache(d_inode, req->wb_page, 0);
+
unlock_page(req->wb_page);
dprintk("NFS: read done (%s/%Ld %d@%Ld)\n",
@@ -510,8 +516,15 @@ int nfs_readpage(struct file *file, struct page *page)
} else
ctx = get_nfs_open_context(nfs_file_open_context(file));
+ if (!IS_SYNC(inode)) {
+ error = nfs_readpage_from_fscache(ctx, inode, page);
+ if (error == 0)
+ goto out;
+ }
+
error = nfs_readpage_async(ctx, inode, page);
+out:
put_nfs_open_context(ctx);
return error;
out_unlock:
@@ -584,6 +597,15 @@ int nfs_readpages(struct file *filp, struct address_space *mapping,
return -EBADF;
} else
desc.ctx = get_nfs_open_context(nfs_file_open_context(filp));
+
+ /* attempt to read as many of the pages as possible from the cache
+ * - this returns -ENOBUFS immediately if the cookie is negative
+ */
+ ret = nfs_readpages_from_fscache(desc.ctx, inode, mapping,
+ pages, &nr_pages);
+ if (ret == 0)
+ goto read_complete; /* all pages were read */
+
if (rsize < PAGE_CACHE_SIZE)
nfs_pageio_init(&pgio, inode, nfs_pagein_multi, rsize, 0);
else
@@ -594,6 +616,7 @@ int nfs_readpages(struct file *filp, struct address_space *mapping,
nfs_pageio_complete(&pgio);
npages = (pgio.pg_bytes_written + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
nfs_add_stats(inode, NFSIOS_READPAGES, npages);
+read_complete:
put_nfs_open_context(desc.ctx);
out:
return ret;
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index d6686f4786dc..6717200923fe 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -60,6 +60,7 @@
#include "delegation.h"
#include "iostat.h"
#include "internal.h"
+#include "fscache.h"
#define NFSDBG_FACILITY NFSDBG_VFS
@@ -76,6 +77,7 @@ enum {
Opt_rdirplus, Opt_nordirplus,
Opt_sharecache, Opt_nosharecache,
Opt_resvport, Opt_noresvport,
+ Opt_fscache, Opt_nofscache,
/* Mount options that take integer arguments */
Opt_port,
@@ -93,6 +95,7 @@ enum {
Opt_sec, Opt_proto, Opt_mountproto, Opt_mounthost,
Opt_addr, Opt_mountaddr, Opt_clientaddr,
Opt_lookupcache,
+ Opt_fscache_uniq,
/* Special mount options */
Opt_userspace, Opt_deprecated, Opt_sloppy,
@@ -132,6 +135,9 @@ static const match_table_t nfs_mount_option_tokens = {
{ Opt_nosharecache, "nosharecache" },
{ Opt_resvport, "resvport" },
{ Opt_noresvport, "noresvport" },
+ { Opt_fscache, "fsc" },
+ { Opt_fscache_uniq, "fsc=%s" },
+ { Opt_nofscache, "nofsc" },
{ Opt_port, "port=%u" },
{ Opt_rsize, "rsize=%u" },
@@ -563,6 +569,8 @@ static void nfs_show_mount_options(struct seq_file *m, struct nfs_server *nfss,
if (clp->rpc_ops->version == 4)
seq_printf(m, ",clientaddr=%s", clp->cl_ipaddr);
#endif
+ if (nfss->options & NFS_OPTION_FSCACHE)
+ seq_printf(m, ",fsc");
}
/*
@@ -641,6 +649,10 @@ static int nfs_show_stats(struct seq_file *m, struct vfsmount *mnt)
totals.events[i] += stats->events[i];
for (i = 0; i < __NFSIOS_BYTESMAX; i++)
totals.bytes[i] += stats->bytes[i];
+#ifdef CONFIG_NFS_FSCACHE
+ for (i = 0; i < __NFSIOS_FSCACHEMAX; i++)
+ totals.fscache[i] += stats->fscache[i];
+#endif
preempt_enable();
}
@@ -651,6 +663,13 @@ static int nfs_show_stats(struct seq_file *m, struct vfsmount *mnt)
seq_printf(m, "\n\tbytes:\t");
for (i = 0; i < __NFSIOS_BYTESMAX; i++)
seq_printf(m, "%Lu ", totals.bytes[i]);
+#ifdef CONFIG_NFS_FSCACHE
+ if (nfss->options & NFS_OPTION_FSCACHE) {
+ seq_printf(m, "\n\tfsc:\t");
+ for (i = 0; i < __NFSIOS_FSCACHEMAX; i++)
+ seq_printf(m, "%Lu ", totals.bytes[i]);
+ }
+#endif
seq_printf(m, "\n");
rpc_print_iostats(m, nfss->client);
@@ -1018,6 +1037,7 @@ static int nfs_parse_mount_options(char *raw,
case Opt_rdma:
mnt->flags |= NFS_MOUNT_TCP; /* for side protocols */
mnt->nfs_server.protocol = XPRT_TRANSPORT_RDMA;
+ xprt_load_transport(p);
break;
case Opt_acl:
mnt->flags &= ~NFS_MOUNT_NOACL;
@@ -1043,6 +1063,24 @@ static int nfs_parse_mount_options(char *raw,
case Opt_noresvport:
mnt->flags |= NFS_MOUNT_NORESVPORT;
break;
+ case Opt_fscache:
+ mnt->options |= NFS_OPTION_FSCACHE;
+ kfree(mnt->fscache_uniq);
+ mnt->fscache_uniq = NULL;
+ break;
+ case Opt_nofscache:
+ mnt->options &= ~NFS_OPTION_FSCACHE;
+ kfree(mnt->fscache_uniq);
+ mnt->fscache_uniq = NULL;
+ break;
+ case Opt_fscache_uniq:
+ string = match_strdup(args);
+ if (!string)
+ goto out_nomem;
+ kfree(mnt->fscache_uniq);
+ mnt->fscache_uniq = string;
+ mnt->options |= NFS_OPTION_FSCACHE;
+ break;
/*
* options that take numeric values
@@ -1190,7 +1228,6 @@ static int nfs_parse_mount_options(char *raw,
goto out_nomem;
token = match_token(string,
nfs_xprt_protocol_tokens, args);
- kfree(string);
switch (token) {
case Opt_xprt_udp:
@@ -1205,12 +1242,14 @@ static int nfs_parse_mount_options(char *raw,
/* vector side protocols to TCP */
mnt->flags |= NFS_MOUNT_TCP;
mnt->nfs_server.protocol = XPRT_TRANSPORT_RDMA;
+ xprt_load_transport(string);
break;
default:
errors++;
dfprintk(MOUNT, "NFS: unrecognized "
"transport protocol\n");
}
+ kfree(string);
break;
case Opt_mountproto:
string = match_strdup(args);
@@ -1868,8 +1907,6 @@ static void nfs_clone_super(struct super_block *sb,
nfs_initialise_sb(sb);
}
-#define NFS_MS_MASK (MS_RDONLY|MS_NOSUID|MS_NODEV|MS_NOEXEC|MS_SYNCHRONOUS)
-
static int nfs_compare_mount_options(const struct super_block *s, const struct nfs_server *b, int flags)
{
const struct nfs_server *a = s->s_fs_info;
@@ -2034,6 +2071,7 @@ static int nfs_get_sb(struct file_system_type *fs_type,
if (!s->s_root) {
/* initial superblock/root creation */
nfs_fill_super(s, data);
+ nfs_fscache_get_super_cookie(s, data);
}
mntroot = nfs_get_root(s, mntfh);
@@ -2054,6 +2092,7 @@ static int nfs_get_sb(struct file_system_type *fs_type,
out:
kfree(data->nfs_server.hostname);
kfree(data->mount_server.hostname);
+ kfree(data->fscache_uniq);
security_free_mnt_opts(&data->lsm_opts);
out_free_fh:
kfree(mntfh);
@@ -2081,6 +2120,7 @@ static void nfs_kill_super(struct super_block *s)
bdi_unregister(&server->backing_dev_info);
kill_anon_super(s);
+ nfs_fscache_release_super_cookie(s);
nfs_free_server(server);
}
@@ -2388,6 +2428,7 @@ static int nfs4_get_sb(struct file_system_type *fs_type,
if (!s->s_root) {
/* initial superblock/root creation */
nfs4_fill_super(s);
+ nfs_fscache_get_super_cookie(s, data);
}
mntroot = nfs4_get_root(s, mntfh);
@@ -2409,6 +2450,7 @@ out:
kfree(data->client_address);
kfree(data->nfs_server.export_path);
kfree(data->nfs_server.hostname);
+ kfree(data->fscache_uniq);
security_free_mnt_opts(&data->lsm_opts);
out_free_fh:
kfree(mntfh);
@@ -2435,6 +2477,7 @@ static void nfs4_kill_super(struct super_block *sb)
kill_anon_super(sb);
nfs4_renewd_prepare_shutdown(server);
+ nfs_fscache_release_super_cookie(sb);
nfs_free_server(server);
}
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 9f9845859fc1..e560a78995a3 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -313,19 +313,34 @@ static int nfs_writepages_callback(struct page *page, struct writeback_control *
int nfs_writepages(struct address_space *mapping, struct writeback_control *wbc)
{
struct inode *inode = mapping->host;
+ unsigned long *bitlock = &NFS_I(inode)->flags;
struct nfs_pageio_descriptor pgio;
int err;
+ /* Stop dirtying of new pages while we sync */
+ err = wait_on_bit_lock(bitlock, NFS_INO_FLUSHING,
+ nfs_wait_bit_killable, TASK_KILLABLE);
+ if (err)
+ goto out_err;
+
nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGES);
nfs_pageio_init_write(&pgio, inode, wb_priority(wbc));
err = write_cache_pages(mapping, wbc, nfs_writepages_callback, &pgio);
nfs_pageio_complete(&pgio);
+
+ clear_bit_unlock(NFS_INO_FLUSHING, bitlock);
+ smp_mb__after_clear_bit();
+ wake_up_bit(bitlock, NFS_INO_FLUSHING);
+
if (err < 0)
- return err;
- if (pgio.pg_error < 0)
- return pgio.pg_error;
+ goto out_err;
+ err = pgio.pg_error;
+ if (err < 0)
+ goto out_err;
return 0;
+out_err:
+ return err;
}
/*
@@ -404,7 +419,6 @@ nfs_mark_request_commit(struct nfs_page *req)
struct nfs_inode *nfsi = NFS_I(inode);
spin_lock(&inode->i_lock);
- nfsi->ncommit++;
set_bit(PG_CLEAN, &(req)->wb_flags);
radix_tree_tag_set(&nfsi->nfs_page_tree,
req->wb_index,
@@ -524,6 +538,12 @@ static void nfs_cancel_commit_list(struct list_head *head)
}
#if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4)
+static int
+nfs_need_commit(struct nfs_inode *nfsi)
+{
+ return radix_tree_tagged(&nfsi->nfs_page_tree, NFS_PAGE_TAG_COMMIT);
+}
+
/*
* nfs_scan_commit - Scan an inode for commit requests
* @inode: NFS inode to scan
@@ -538,16 +558,18 @@ static int
nfs_scan_commit(struct inode *inode, struct list_head *dst, pgoff_t idx_start, unsigned int npages)
{
struct nfs_inode *nfsi = NFS_I(inode);
- int res = 0;
- if (nfsi->ncommit != 0) {
- res = nfs_scan_list(nfsi, dst, idx_start, npages,
- NFS_PAGE_TAG_COMMIT);
- nfsi->ncommit -= res;
- }
- return res;
+ if (!nfs_need_commit(nfsi))
+ return 0;
+
+ return nfs_scan_list(nfsi, dst, idx_start, npages, NFS_PAGE_TAG_COMMIT);
}
#else
+static inline int nfs_need_commit(struct nfs_inode *nfsi)
+{
+ return 0;
+}
+
static inline int nfs_scan_commit(struct inode *inode, struct list_head *dst, pgoff_t idx_start, unsigned int npages)
{
return 0;
@@ -820,7 +842,7 @@ static int nfs_write_rpcsetup(struct nfs_page *req,
data->args.stable = NFS_UNSTABLE;
if (how & FLUSH_STABLE) {
data->args.stable = NFS_DATA_SYNC;
- if (!NFS_I(inode)->ncommit)
+ if (!nfs_need_commit(NFS_I(inode)))
data->args.stable = NFS_FILE_SYNC;
}
@@ -1425,18 +1447,13 @@ static int nfs_write_mapping(struct address_space *mapping, int how)
{
struct writeback_control wbc = {
.bdi = mapping->backing_dev_info,
- .sync_mode = WB_SYNC_NONE,
+ .sync_mode = WB_SYNC_ALL,
.nr_to_write = LONG_MAX,
.range_start = 0,
.range_end = LLONG_MAX,
.for_writepages = 1,
};
- int ret;
- ret = __nfs_write_mapping(mapping, &wbc, how);
- if (ret < 0)
- return ret;
- wbc.sync_mode = WB_SYNC_ALL;
return __nfs_write_mapping(mapping, &wbc, how);
}
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.