aboutsummaryrefslogtreecommitdiff
path: root/fs/nfs/dir.c
diff options
context:
space:
mode:
Diffstat (limited to 'fs/nfs/dir.c')
-rw-r--r--fs/nfs/dir.c1413
1 files changed, 783 insertions, 630 deletions
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 07ac3847e56..4a3d4ef7612 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -17,6 +17,7 @@
* 6 Jun 1999 Cache readdir lookups in the page cache. -DaveM
*/
+#include <linux/module.h>
#include <linux/time.h>
#include <linux/errno.h>
#include <linux/stat.h>
@@ -32,104 +33,67 @@
#include <linux/pagevec.h>
#include <linux/namei.h>
#include <linux/mount.h>
+#include <linux/swap.h>
#include <linux/sched.h>
-#include <linux/vmalloc.h>
+#include <linux/kmemleak.h>
+#include <linux/xattr.h>
#include "delegation.h"
#include "iostat.h"
#include "internal.h"
#include "fscache.h"
+#include "nfstrace.h"
+
/* #define NFS_DEBUG_VERBOSE 1 */
static int nfs_opendir(struct inode *, struct file *);
-static int nfs_readdir(struct file *, void *, filldir_t);
-static struct dentry *nfs_lookup(struct inode *, struct dentry *, struct nameidata *);
-static int nfs_create(struct inode *, struct dentry *, int, struct nameidata *);
-static int nfs_mkdir(struct inode *, struct dentry *, int);
-static int nfs_rmdir(struct inode *, struct dentry *);
-static int nfs_unlink(struct inode *, struct dentry *);
-static int nfs_symlink(struct inode *, struct dentry *, const char *);
-static int nfs_link(struct dentry *, struct inode *, struct dentry *);
-static int nfs_mknod(struct inode *, struct dentry *, int, dev_t);
-static int nfs_rename(struct inode *, struct dentry *,
- struct inode *, struct dentry *);
-static int nfs_fsync_dir(struct file *, int);
+static int nfs_closedir(struct inode *, struct file *);
+static int nfs_readdir(struct file *, struct dir_context *);
+static int nfs_fsync_dir(struct file *, loff_t, loff_t, int);
static loff_t nfs_llseek_dir(struct file *, loff_t, int);
-static int nfs_readdir_clear_array(struct page*, gfp_t);
+static void nfs_readdir_clear_array(struct page*);
const struct file_operations nfs_dir_operations = {
.llseek = nfs_llseek_dir,
.read = generic_read_dir,
- .readdir = nfs_readdir,
+ .iterate = nfs_readdir,
.open = nfs_opendir,
- .release = nfs_release,
+ .release = nfs_closedir,
.fsync = nfs_fsync_dir,
};
-const struct inode_operations nfs_dir_inode_operations = {
- .create = nfs_create,
- .lookup = nfs_lookup,
- .link = nfs_link,
- .unlink = nfs_unlink,
- .symlink = nfs_symlink,
- .mkdir = nfs_mkdir,
- .rmdir = nfs_rmdir,
- .mknod = nfs_mknod,
- .rename = nfs_rename,
- .permission = nfs_permission,
- .getattr = nfs_getattr,
- .setattr = nfs_setattr,
-};
-
-const struct address_space_operations nfs_dir_addr_space_ops = {
- .releasepage = nfs_readdir_clear_array,
+const struct address_space_operations nfs_dir_aops = {
+ .freepage = nfs_readdir_clear_array,
};
-#ifdef CONFIG_NFS_V3
-const struct inode_operations nfs3_dir_inode_operations = {
- .create = nfs_create,
- .lookup = nfs_lookup,
- .link = nfs_link,
- .unlink = nfs_unlink,
- .symlink = nfs_symlink,
- .mkdir = nfs_mkdir,
- .rmdir = nfs_rmdir,
- .mknod = nfs_mknod,
- .rename = nfs_rename,
- .permission = nfs_permission,
- .getattr = nfs_getattr,
- .setattr = nfs_setattr,
- .listxattr = nfs3_listxattr,
- .getxattr = nfs3_getxattr,
- .setxattr = nfs3_setxattr,
- .removexattr = nfs3_removexattr,
-};
-#endif /* CONFIG_NFS_V3 */
-
-#ifdef CONFIG_NFS_V4
-
-static struct dentry *nfs_atomic_lookup(struct inode *, struct dentry *, struct nameidata *);
-static int nfs_open_create(struct inode *dir, struct dentry *dentry, int mode, struct nameidata *nd);
-const struct inode_operations nfs4_dir_inode_operations = {
- .create = nfs_open_create,
- .lookup = nfs_atomic_lookup,
- .link = nfs_link,
- .unlink = nfs_unlink,
- .symlink = nfs_symlink,
- .mkdir = nfs_mkdir,
- .rmdir = nfs_rmdir,
- .mknod = nfs_mknod,
- .rename = nfs_rename,
- .permission = nfs_permission,
- .getattr = nfs_getattr,
- .setattr = nfs_setattr,
- .getxattr = nfs4_getxattr,
- .setxattr = nfs4_setxattr,
- .listxattr = nfs4_listxattr,
-};
+static struct nfs_open_dir_context *alloc_nfs_open_dir_context(struct inode *dir, struct rpc_cred *cred)
+{
+ struct nfs_inode *nfsi = NFS_I(dir);
+ struct nfs_open_dir_context *ctx;
+ ctx = kmalloc(sizeof(*ctx), GFP_KERNEL);
+ if (ctx != NULL) {
+ ctx->duped = 0;
+ ctx->attr_gencount = nfsi->attr_gencount;
+ ctx->dir_cookie = 0;
+ ctx->dup_cookie = 0;
+ ctx->cred = get_rpccred(cred);
+ spin_lock(&dir->i_lock);
+ list_add(&ctx->list, &nfsi->open_files);
+ spin_unlock(&dir->i_lock);
+ return ctx;
+ }
+ return ERR_PTR(-ENOMEM);
+}
-#endif /* CONFIG_NFS_V4 */
+static void put_nfs_open_dir_context(struct inode *dir, struct nfs_open_dir_context *ctx)
+{
+ spin_lock(&dir->i_lock);
+ list_del(&ctx->list);
+ spin_unlock(&dir->i_lock);
+ put_rpccred(ctx->cred);
+ kfree(ctx);
+}
/*
* Open file
@@ -137,16 +101,23 @@ const struct inode_operations nfs4_dir_inode_operations = {
static int
nfs_opendir(struct inode *inode, struct file *filp)
{
- int res;
+ int res = 0;
+ struct nfs_open_dir_context *ctx;
+ struct rpc_cred *cred;
- dfprintk(FILE, "NFS: open dir(%s/%s)\n",
- filp->f_path.dentry->d_parent->d_name.name,
- filp->f_path.dentry->d_name.name);
+ dfprintk(FILE, "NFS: open dir(%pD2)\n", filp);
nfs_inc_stats(inode, NFSIOS_VFSOPEN);
- /* Call generic open code in order to cache credentials */
- res = nfs_open(inode, filp);
+ cred = rpc_lookup_cred();
+ if (IS_ERR(cred))
+ return PTR_ERR(cred);
+ ctx = alloc_nfs_open_dir_context(inode, cred);
+ if (IS_ERR(ctx)) {
+ res = PTR_ERR(ctx);
+ goto out;
+ }
+ filp->private_data = ctx;
if (filp->f_path.dentry == filp->f_path.mnt->mnt_root) {
/* This is a mountpoint, so d_revalidate will never
* have been called, so we need to refresh the
@@ -154,30 +125,40 @@ nfs_opendir(struct inode *inode, struct file *filp)
*/
__nfs_revalidate_inode(NFS_SERVER(inode), inode);
}
+out:
+ put_rpccred(cred);
return res;
}
+static int
+nfs_closedir(struct inode *inode, struct file *filp)
+{
+ put_nfs_open_dir_context(filp->f_path.dentry->d_inode, filp->private_data);
+ return 0;
+}
+
struct nfs_cache_array_entry {
u64 cookie;
u64 ino;
struct qstr string;
+ unsigned char d_type;
};
struct nfs_cache_array {
- unsigned int size;
+ int size;
int eof_index;
u64 last_cookie;
struct nfs_cache_array_entry array[0];
};
-#define MAX_READDIR_ARRAY ((PAGE_SIZE - sizeof(struct nfs_cache_array)) / sizeof(struct nfs_cache_array_entry))
-
-typedef __be32 * (*decode_dirent_t)(struct xdr_stream *, struct nfs_entry *, struct nfs_server *, int);
+typedef int (*decode_dirent_t)(struct xdr_stream *, struct nfs_entry *, int);
typedef struct {
struct file *file;
struct page *page;
+ struct dir_context *ctx;
unsigned long page_index;
u64 *dir_cookie;
+ u64 last_cookie;
loff_t current_index;
decode_dirent_t decode;
@@ -194,9 +175,13 @@ typedef struct {
static
struct nfs_cache_array *nfs_readdir_get_array(struct page *page)
{
+ void *ptr;
if (page == NULL)
return ERR_PTR(-EIO);
- return (struct nfs_cache_array *)kmap(page);
+ ptr = kmap(page);
+ if (ptr == NULL)
+ return ERR_PTR(-ENOMEM);
+ return ptr;
}
static
@@ -209,14 +194,15 @@ void nfs_readdir_release_array(struct page *page)
* we are freeing strings created by nfs_add_to_readdir_array()
*/
static
-int nfs_readdir_clear_array(struct page *page, gfp_t mask)
+void nfs_readdir_clear_array(struct page *page)
{
- struct nfs_cache_array *array = nfs_readdir_get_array(page);
+ struct nfs_cache_array *array;
int i;
+
+ array = kmap_atomic(page);
for (i = 0; i < array->size; i++)
kfree(array->array[i].string.name);
- nfs_readdir_release_array(page);
- return 0;
+ kunmap_atomic(array);
}
/*
@@ -231,6 +217,11 @@ int nfs_readdir_make_qstr(struct qstr *string, const char *name, unsigned int le
string->name = kmemdup(name, len, GFP_KERNEL);
if (string->name == NULL)
return -ENOMEM;
+ /*
+ * Avoid a kmemleak false positive. The pointer to the name is stored
+ * in a page cache page which kmemleak does not scan.
+ */
+ kmemleak_not_leak(string->name);
string->hash = full_name_hash(name, len);
return 0;
}
@@ -244,20 +235,24 @@ int nfs_readdir_add_to_array(struct nfs_entry *entry, struct page *page)
if (IS_ERR(array))
return PTR_ERR(array);
- ret = -EIO;
- if (array->size >= MAX_READDIR_ARRAY)
- goto out;
cache_entry = &array->array[array->size];
+
+ /* Check that this entry lies within the page bounds */
+ ret = -ENOSPC;
+ if ((char *)&cache_entry[1] - (char *)page_address(page) > PAGE_SIZE)
+ goto out;
+
cache_entry->cookie = entry->prev_cookie;
cache_entry->ino = entry->ino;
+ cache_entry->d_type = entry->d_type;
ret = nfs_readdir_make_qstr(&cache_entry->string, entry->name, entry->len);
if (ret)
goto out;
array->last_cookie = entry->cookie;
- if (entry->eof == 1)
- array->eof_index = array->size;
array->size++;
+ if (entry->eof != 0)
+ array->eof_index = array->size;
out:
nfs_readdir_release_array(page);
return ret;
@@ -266,47 +261,79 @@ out:
static
int nfs_readdir_search_for_pos(struct nfs_cache_array *array, nfs_readdir_descriptor_t *desc)
{
- loff_t diff = desc->file->f_pos - desc->current_index;
+ loff_t diff = desc->ctx->pos - desc->current_index;
unsigned int index;
if (diff < 0)
goto out_eof;
if (diff >= array->size) {
- if (array->eof_index > 0)
+ if (array->eof_index >= 0)
goto out_eof;
- desc->current_index += array->size;
return -EAGAIN;
}
index = (unsigned int)diff;
*desc->dir_cookie = array->array[index].cookie;
desc->cache_entry_index = index;
- if (index == array->eof_index)
- desc->eof = 1;
return 0;
out_eof:
desc->eof = 1;
return -EBADCOOKIE;
}
+static bool
+nfs_readdir_inode_mapping_valid(struct nfs_inode *nfsi)
+{
+ if (nfsi->cache_validity & (NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA))
+ return false;
+ smp_rmb();
+ return !test_bit(NFS_INO_INVALIDATING, &nfsi->flags);
+}
+
static
int nfs_readdir_search_for_cookie(struct nfs_cache_array *array, nfs_readdir_descriptor_t *desc)
{
int i;
+ loff_t new_pos;
int status = -EAGAIN;
for (i = 0; i < array->size; i++) {
- if (i == array->eof_index) {
- desc->eof = 1;
- status = -EBADCOOKIE;
- }
if (array->array[i].cookie == *desc->dir_cookie) {
+ struct nfs_inode *nfsi = NFS_I(file_inode(desc->file));
+ struct nfs_open_dir_context *ctx = desc->file->private_data;
+
+ new_pos = desc->current_index + i;
+ if (ctx->attr_gencount != nfsi->attr_gencount ||
+ !nfs_readdir_inode_mapping_valid(nfsi)) {
+ ctx->duped = 0;
+ ctx->attr_gencount = nfsi->attr_gencount;
+ } else if (new_pos < desc->ctx->pos) {
+ if (ctx->duped > 0
+ && ctx->dup_cookie == *desc->dir_cookie) {
+ if (printk_ratelimit()) {
+ pr_notice("NFS: directory %pD2 contains a readdir loop."
+ "Please contact your server vendor. "
+ "The file: %.*s has duplicate cookie %llu\n",
+ desc->file, array->array[i].string.len,
+ array->array[i].string.name, *desc->dir_cookie);
+ }
+ status = -ELOOP;
+ goto out;
+ }
+ ctx->dup_cookie = *desc->dir_cookie;
+ ctx->duped = -1;
+ }
+ desc->ctx->pos = new_pos;
desc->cache_entry_index = i;
- status = 0;
- break;
+ return 0;
}
}
-
+ if (array->eof_index >= 0) {
+ status = -EBADCOOKIE;
+ if (*desc->dir_cookie == array->last_cookie)
+ desc->eof = 1;
+ }
+out:
return status;
}
@@ -314,10 +341,7 @@ static
int nfs_readdir_search_array(nfs_readdir_descriptor_t *desc)
{
struct nfs_cache_array *array;
- int status = -EBADCOOKIE;
-
- if (desc->dir_cookie == NULL)
- goto out;
+ int status;
array = nfs_readdir_get_array(desc->page);
if (IS_ERR(array)) {
@@ -330,6 +354,11 @@ int nfs_readdir_search_array(nfs_readdir_descriptor_t *desc)
else
status = nfs_readdir_search_for_cookie(array, desc);
+ if (status == -EAGAIN) {
+ desc->last_cookie = array->last_cookie;
+ desc->current_index += array->size;
+ desc->page_index++;
+ }
nfs_readdir_release_array(desc->page);
out:
return status;
@@ -340,7 +369,8 @@ static
int nfs_readdir_xdr_filler(struct page **pages, nfs_readdir_descriptor_t *desc,
struct nfs_entry *entry, struct file *file, struct inode *inode)
{
- struct rpc_cred *cred = nfs_file_cred(file);
+ struct nfs_open_dir_context *ctx = file->private_data;
+ struct rpc_cred *cred = ctx->cred;
unsigned long timestamp, gencount;
int error;
@@ -365,14 +395,14 @@ error:
return error;
}
-/* Fill in an entry based on the xdr code stored in desc->page */
-static
-int xdr_decode(nfs_readdir_descriptor_t *desc, struct nfs_entry *entry, struct xdr_stream *stream)
+static int xdr_decode(nfs_readdir_descriptor_t *desc,
+ struct nfs_entry *entry, struct xdr_stream *xdr)
{
- __be32 *p = desc->decode(stream, entry, NFS_SERVER(desc->file->f_path.dentry->d_inode), desc->plus);
- if (IS_ERR(p))
- return PTR_ERR(p);
+ int error;
+ error = desc->decode(xdr, entry, desc->plus);
+ if (error)
+ return error;
entry->fattr->time_start = desc->timestamp;
entry->fattr->gencount = desc->gencount;
return 0;
@@ -381,13 +411,9 @@ int xdr_decode(nfs_readdir_descriptor_t *desc, struct nfs_entry *entry, struct x
static
int nfs_same_file(struct dentry *dentry, struct nfs_entry *entry)
{
- struct nfs_inode *node;
if (dentry->d_inode == NULL)
goto different;
- node = NFS_I(dentry->d_inode);
- if (node->fh.size != entry->fh->size)
- goto different;
- if (strncmp(node->fh.data, entry->fh->data, node->fh.size) != 0)
+ if (nfs_compare_fh(entry->fh, NFS_FH(dentry->d_inode)) != 0)
goto different;
return 1;
different:
@@ -395,16 +421,53 @@ different:
}
static
+bool nfs_use_readdirplus(struct inode *dir, struct dir_context *ctx)
+{
+ if (!nfs_server_capable(dir, NFS_CAP_READDIRPLUS))
+ return false;
+ if (test_and_clear_bit(NFS_INO_ADVISE_RDPLUS, &NFS_I(dir)->flags))
+ return true;
+ if (ctx->pos == 0)
+ return true;
+ return false;
+}
+
+/*
+ * This function is called by the lookup code to request the use of
+ * readdirplus to accelerate any future lookups in the same
+ * directory.
+ */
+static
+void nfs_advise_use_readdirplus(struct inode *dir)
+{
+ set_bit(NFS_INO_ADVISE_RDPLUS, &NFS_I(dir)->flags);
+}
+
+/*
+ * This function is mainly for use by nfs_getattr().
+ *
+ * If this is an 'ls -l', we want to force use of readdirplus.
+ * Do this by checking if there is an active file descriptor
+ * and calling nfs_advise_use_readdirplus, then forcing a
+ * cache flush.
+ */
+void nfs_force_use_readdirplus(struct inode *dir)
+{
+ if (!list_empty(&NFS_I(dir)->open_files)) {
+ nfs_advise_use_readdirplus(dir);
+ nfs_zap_mapping(dir, dir->i_mapping);
+ }
+}
+
+static
void nfs_prime_dcache(struct dentry *parent, struct nfs_entry *entry)
{
- struct qstr filename = {
- .len = entry->len,
- .name = entry->name,
- };
+ struct qstr filename = QSTR_INIT(entry->name, entry->len);
struct dentry *dentry;
struct dentry *alias;
struct inode *dir = parent->d_inode;
struct inode *inode;
+ int status;
if (filename.name[0] == '.') {
if (filename.len == 1)
@@ -417,10 +480,14 @@ void nfs_prime_dcache(struct dentry *parent, struct nfs_entry *entry)
dentry = d_lookup(parent, &filename);
if (dentry != NULL) {
if (nfs_same_file(dentry, entry)) {
- nfs_refresh_inode(dentry->d_inode, entry->fattr);
+ nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
+ status = nfs_refresh_inode(dentry->d_inode, entry->fattr);
+ if (!status)
+ nfs_setsecurity(dentry->d_inode, entry->fattr, entry->label);
goto out;
} else {
- d_drop(dentry);
+ if (d_invalidate(dentry) != 0)
+ goto out;
dput(dentry);
}
}
@@ -429,8 +496,7 @@ void nfs_prime_dcache(struct dentry *parent, struct nfs_entry *entry)
if (dentry == NULL)
return;
- dentry->d_op = NFS_PROTO(dir)->dentry_ops;
- inode = nfs_fhget(dentry->d_sb, entry->fh, entry->fattr);
+ inode = nfs_fhget(dentry->d_sb, entry->fh, entry->fattr, entry->label);
if (IS_ERR(inode))
goto out;
@@ -449,43 +515,53 @@ out:
/* Perform conversion from xdr to cache array */
static
-void nfs_readdir_page_filler(nfs_readdir_descriptor_t *desc, struct nfs_entry *entry,
- void *xdr_page, struct page *page, unsigned int buflen)
+int nfs_readdir_page_filler(nfs_readdir_descriptor_t *desc, struct nfs_entry *entry,
+ struct page **xdr_pages, struct page *page, unsigned int buflen)
{
struct xdr_stream stream;
struct xdr_buf buf;
- __be32 *ptr = xdr_page;
- int status;
+ struct page *scratch;
struct nfs_cache_array *array;
+ unsigned int count = 0;
+ int status;
- buf.head->iov_base = xdr_page;
- buf.head->iov_len = buflen;
- buf.tail->iov_len = 0;
- buf.page_base = 0;
- buf.page_len = 0;
- buf.buflen = buf.head->iov_len;
- buf.len = buf.head->iov_len;
-
- xdr_init_decode(&stream, &buf, ptr);
+ scratch = alloc_page(GFP_KERNEL);
+ if (scratch == NULL)
+ return -ENOMEM;
+ xdr_init_decode_pages(&stream, &buf, xdr_pages, buflen);
+ xdr_set_scratch_buffer(&stream, page_address(scratch), PAGE_SIZE);
do {
status = xdr_decode(desc, entry, &stream);
- if (status != 0)
+ if (status != 0) {
+ if (status == -EAGAIN)
+ status = 0;
break;
+ }
- if (nfs_readdir_add_to_array(entry, page) == -1)
- break;
- if (desc->plus == 1)
+ count++;
+
+ if (desc->plus != 0)
nfs_prime_dcache(desc->file->f_path.dentry, entry);
+
+ status = nfs_readdir_add_to_array(entry, page);
+ if (status != 0)
+ break;
} while (!entry->eof);
- if (status == -EBADCOOKIE && entry->eof) {
+ if (count == 0 || (status == -EBADCOOKIE && entry->eof != 0)) {
array = nfs_readdir_get_array(page);
- array->eof_index = array->size - 1;
- status = 0;
- nfs_readdir_release_array(page);
+ if (!IS_ERR(array)) {
+ array->eof_index = array->size;
+ status = 0;
+ nfs_readdir_release_array(page);
+ } else
+ status = PTR_ERR(array);
}
+
+ put_page(scratch);
+ return status;
}
static
@@ -500,7 +576,6 @@ static
void nfs_readdir_free_large_page(void *ptr, struct page **pages,
unsigned int npages)
{
- vm_unmap_ram(ptr, npages);
nfs_readdir_free_pagearray(pages, npages);
}
@@ -509,9 +584,8 @@ void nfs_readdir_free_large_page(void *ptr, struct page **pages,
* to nfs_readdir_free_large_page
*/
static
-void *nfs_readdir_large_page(struct page **pages, unsigned int npages)
+int nfs_readdir_large_page(struct page **pages, unsigned int npages)
{
- void *ptr;
unsigned int i;
for (i = 0; i < npages; i++) {
@@ -520,13 +594,11 @@ void *nfs_readdir_large_page(struct page **pages, unsigned int npages)
goto out_freepages;
pages[i] = page;
}
+ return 0;
- ptr = vm_map_ram(pages, npages, 0, PAGE_KERNEL);
- if (!IS_ERR_OR_NULL(ptr))
- return ptr;
out_freepages:
nfs_readdir_free_pagearray(pages, i);
- return NULL;
+ return -ENOMEM;
}
static
@@ -537,35 +609,55 @@ int nfs_readdir_xdr_to_array(nfs_readdir_descriptor_t *desc, struct page *page,
struct nfs_entry entry;
struct file *file = desc->file;
struct nfs_cache_array *array;
- int status = 0;
+ int status = -ENOMEM;
unsigned int array_size = ARRAY_SIZE(pages);
entry.prev_cookie = 0;
- entry.cookie = *desc->dir_cookie;
+ entry.cookie = desc->last_cookie;
entry.eof = 0;
entry.fh = nfs_alloc_fhandle();
entry.fattr = nfs_alloc_fattr();
+ entry.server = NFS_SERVER(inode);
if (entry.fh == NULL || entry.fattr == NULL)
goto out;
+ entry.label = nfs4_label_alloc(NFS_SERVER(inode), GFP_NOWAIT);
+ if (IS_ERR(entry.label)) {
+ status = PTR_ERR(entry.label);
+ goto out;
+ }
+
array = nfs_readdir_get_array(page);
+ if (IS_ERR(array)) {
+ status = PTR_ERR(array);
+ goto out_label_free;
+ }
memset(array, 0, sizeof(struct nfs_cache_array));
array->eof_index = -1;
- pages_ptr = nfs_readdir_large_page(pages, array_size);
- if (!pages_ptr)
+ status = nfs_readdir_large_page(pages, array_size);
+ if (status < 0)
goto out_release_array;
do {
+ unsigned int pglen;
status = nfs_readdir_xdr_filler(pages, desc, &entry, file, inode);
if (status < 0)
break;
- nfs_readdir_page_filler(desc, &entry, pages_ptr, page, array_size * PAGE_SIZE);
- } while (array->eof_index < 0 && array->size < MAX_READDIR_ARRAY);
+ pglen = status;
+ status = nfs_readdir_page_filler(desc, &entry, pages, page, pglen);
+ if (status < 0) {
+ if (status == -ENOSPC)
+ status = 0;
+ break;
+ }
+ } while (array->eof_index < 0);
nfs_readdir_free_large_page(pages_ptr, pages, array_size);
out_release_array:
nfs_readdir_release_array(page);
+out_label_free:
+ nfs4_label_free(entry.label);
out:
nfs_free_fattr(entry.fattr);
nfs_free_fhandle(entry.fh);
@@ -581,9 +673,11 @@ out:
static
int nfs_readdir_filler(nfs_readdir_descriptor_t *desc, struct page* page)
{
- struct inode *inode = desc->file->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(desc->file);
+ int ret;
- if (nfs_readdir_xdr_to_array(desc, page, inode) < 0)
+ ret = nfs_readdir_xdr_to_array(desc, page, inode);
+ if (ret < 0)
goto error;
SetPageUptodate(page);
@@ -595,12 +689,14 @@ int nfs_readdir_filler(nfs_readdir_descriptor_t *desc, struct page* page)
return 0;
error:
unlock_page(page);
- return -EIO;
+ return ret;
}
static
void cache_page_release(nfs_readdir_descriptor_t *desc)
{
+ if (!desc->page->mapping)
+ nfs_readdir_clear_array(desc->page);
page_cache_release(desc->page);
desc->page = NULL;
}
@@ -608,12 +704,8 @@ void cache_page_release(nfs_readdir_descriptor_t *desc)
static
struct page *get_cache_page(nfs_readdir_descriptor_t *desc)
{
- struct page *page;
- page = read_cache_page(desc->file->f_path.dentry->d_inode->i_mapping,
+ return read_cache_page(file_inode(desc->file)->i_mapping,
desc->page_index, (filler_t *)nfs_readdir_filler, desc);
- if (IS_ERR(page))
- desc->eof = 1;
- return page;
}
/*
@@ -629,9 +721,8 @@ int find_cache_page(nfs_readdir_descriptor_t *desc)
return PTR_ERR(desc->page);
res = nfs_readdir_search_array(desc);
- if (res == 0)
- return 0;
- cache_page_release(desc);
+ if (res != 0)
+ cache_page_release(desc);
return res;
}
@@ -639,62 +730,59 @@ int find_cache_page(nfs_readdir_descriptor_t *desc)
static inline
int readdir_search_pagecache(nfs_readdir_descriptor_t *desc)
{
- int res = -EAGAIN;
+ int res;
- while (1) {
- res = find_cache_page(desc);
- if (res != -EAGAIN)
- break;
- desc->page_index++;
+ if (desc->page_index == 0) {
+ desc->current_index = 0;
+ desc->last_cookie = 0;
}
+ do {
+ res = find_cache_page(desc);
+ } while (res == -EAGAIN);
return res;
}
-static inline unsigned int dt_type(struct inode *inode)
-{
- return (inode->i_mode >> 12) & 15;
-}
-
/*
* Once we've found the start of the dirent within a page: fill 'er up...
*/
static
-int nfs_do_filldir(nfs_readdir_descriptor_t *desc, void *dirent,
- filldir_t filldir)
+int nfs_do_filldir(nfs_readdir_descriptor_t *desc)
{
struct file *file = desc->file;
int i = 0;
int res = 0;
struct nfs_cache_array *array = NULL;
- unsigned int d_type = DT_UNKNOWN;
- struct dentry *dentry = NULL;
+ struct nfs_open_dir_context *ctx = file->private_data;
array = nfs_readdir_get_array(desc->page);
+ if (IS_ERR(array)) {
+ res = PTR_ERR(array);
+ goto out;
+ }
for (i = desc->cache_entry_index; i < array->size; i++) {
- d_type = DT_UNKNOWN;
+ struct nfs_cache_array_entry *ent;
- res = filldir(dirent, array->array[i].string.name,
- array->array[i].string.len, file->f_pos,
- nfs_compat_user_ino64(array->array[i].ino), d_type);
- if (res < 0)
+ ent = &array->array[i];
+ if (!dir_emit(desc->ctx, ent->string.name, ent->string.len,
+ nfs_compat_user_ino64(ent->ino), ent->d_type)) {
+ desc->eof = 1;
break;
- file->f_pos++;
- desc->cache_entry_index = i;
+ }
+ desc->ctx->pos++;
if (i < (array->size-1))
*desc->dir_cookie = array->array[i+1].cookie;
else
*desc->dir_cookie = array->last_cookie;
- if (i == array->eof_index) {
- desc->eof = 1;
- break;
- }
+ if (ctx->duped != 0)
+ ctx->duped = 1;
}
+ if (array->eof_index >= 0)
+ desc->eof = 1;
nfs_readdir_release_array(desc->page);
+out:
cache_page_release(desc);
- if (dentry != NULL)
- dput(dentry);
dfprintk(DIRCACHE, "NFS: nfs_do_filldir() filling ended @ cookie %Lu; returning = %d\n",
(unsigned long long)*desc->dir_cookie, res);
return res;
@@ -713,12 +801,12 @@ int nfs_do_filldir(nfs_readdir_descriptor_t *desc, void *dirent,
* directory in the page cache by the time we get here.
*/
static inline
-int uncached_readdir(nfs_readdir_descriptor_t *desc, void *dirent,
- filldir_t filldir)
+int uncached_readdir(nfs_readdir_descriptor_t *desc)
{
struct page *page = NULL;
int status;
- struct inode *inode = desc->file->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(desc->file);
+ struct nfs_open_dir_context *ctx = desc->file->private_data;
dfprintk(DIRCACHE, "NFS: uncached_readdir() searching for cookie %Lu\n",
(unsigned long long)*desc->dir_cookie);
@@ -729,14 +817,16 @@ int uncached_readdir(nfs_readdir_descriptor_t *desc, void *dirent,
goto out;
}
- if (nfs_readdir_xdr_to_array(desc, page, inode) == -1) {
- status = -EIO;
- goto out_release;
- }
-
desc->page_index = 0;
+ desc->last_cookie = *desc->dir_cookie;
desc->page = page;
- status = nfs_do_filldir(desc, dirent, filldir);
+ ctx->duped = 0;
+
+ status = nfs_readdir_xdr_to_array(desc, page, inode);
+ if (status < 0)
+ goto out_release;
+
+ status = nfs_do_filldir(desc);
out:
dfprintk(DIRCACHE, "NFS: %s: returns %d\n",
@@ -747,53 +837,66 @@ int uncached_readdir(nfs_readdir_descriptor_t *desc, void *dirent,
goto out;
}
+static bool nfs_dir_mapping_need_revalidate(struct inode *dir)
+{
+ struct nfs_inode *nfsi = NFS_I(dir);
+
+ if (nfs_attribute_cache_expired(dir))
+ return true;
+ if (nfsi->cache_validity & NFS_INO_INVALID_DATA)
+ return true;
+ return false;
+}
+
/* The file offset position represents the dirent entry number. A
last cookie cache takes care of the common case of reading the
whole directory.
*/
-static int nfs_readdir(struct file *filp, void *dirent, filldir_t filldir)
+static int nfs_readdir(struct file *file, struct dir_context *ctx)
{
- struct dentry *dentry = filp->f_path.dentry;
+ struct dentry *dentry = file->f_path.dentry;
struct inode *inode = dentry->d_inode;
nfs_readdir_descriptor_t my_desc,
*desc = &my_desc;
- int res = -ENOMEM;
+ struct nfs_open_dir_context *dir_ctx = file->private_data;
+ int res = 0;
- dfprintk(FILE, "NFS: readdir(%s/%s) starting at cookie %llu\n",
- dentry->d_parent->d_name.name, dentry->d_name.name,
- (long long)filp->f_pos);
+ dfprintk(FILE, "NFS: readdir(%pD2) starting at cookie %llu\n",
+ file, (long long)ctx->pos);
nfs_inc_stats(inode, NFSIOS_VFSGETDENTS);
/*
- * filp->f_pos points to the dirent entry number.
+ * ctx->pos points to the dirent entry number.
* *desc->dir_cookie has the cookie for the next entry. We have
* to either find the entry with the appropriate number or
* revalidate the cookie.
*/
memset(desc, 0, sizeof(*desc));
- desc->file = filp;
- desc->dir_cookie = &nfs_file_open_context(filp)->dir_cookie;
+ desc->file = file;
+ desc->ctx = ctx;
+ desc->dir_cookie = &dir_ctx->dir_cookie;
desc->decode = NFS_PROTO(inode)->decode_dirent;
- desc->plus = NFS_USE_READDIRPLUS(inode);
+ desc->plus = nfs_use_readdirplus(inode, ctx) ? 1 : 0;
nfs_block_sillyrename(dentry);
- res = nfs_revalidate_mapping(inode, filp->f_mapping);
+ if (ctx->pos == 0 || nfs_dir_mapping_need_revalidate(inode))
+ res = nfs_revalidate_mapping(inode, file->f_mapping);
if (res < 0)
goto out;
- while (desc->eof != 1) {
+ do {
res = readdir_search_pagecache(desc);
if (res == -EBADCOOKIE) {
+ res = 0;
/* This means either end of directory */
if (*desc->dir_cookie && desc->eof == 0) {
/* Or that the server has 'lost' a cookie */
- res = uncached_readdir(desc, dirent, filldir);
- if (res >= 0)
+ res = uncached_readdir(desc);
+ if (res == 0)
continue;
}
- res = 0;
break;
}
if (res == -ETOOSMALL && desc->plus) {
@@ -807,34 +910,28 @@ static int nfs_readdir(struct file *filp, void *dirent, filldir_t filldir)
if (res < 0)
break;
- res = nfs_do_filldir(desc, dirent, filldir);
- if (res < 0) {
- res = 0;
+ res = nfs_do_filldir(desc);
+ if (res < 0)
break;
- }
- }
+ } while (!desc->eof);
out:
nfs_unblock_sillyrename(dentry);
if (res > 0)
res = 0;
- dfprintk(FILE, "NFS: readdir(%s/%s) returns %d\n",
- dentry->d_parent->d_name.name, dentry->d_name.name,
- res);
+ dfprintk(FILE, "NFS: readdir(%pD2) returns %d\n", file, res);
return res;
}
-static loff_t nfs_llseek_dir(struct file *filp, loff_t offset, int origin)
+static loff_t nfs_llseek_dir(struct file *filp, loff_t offset, int whence)
{
- struct dentry *dentry = filp->f_path.dentry;
- struct inode *inode = dentry->d_inode;
+ struct inode *inode = file_inode(filp);
+ struct nfs_open_dir_context *dir_ctx = filp->private_data;
- dfprintk(FILE, "NFS: llseek dir(%s/%s, %lld, %d)\n",
- dentry->d_parent->d_name.name,
- dentry->d_name.name,
- offset, origin);
+ dfprintk(FILE, "NFS: llseek dir(%pD2, %lld, %d)\n",
+ filp, offset, whence);
mutex_lock(&inode->i_mutex);
- switch (origin) {
+ switch (whence) {
case 1:
offset += filp->f_pos;
case 0:
@@ -846,7 +943,8 @@ static loff_t nfs_llseek_dir(struct file *filp, loff_t offset, int origin)
}
if (offset != filp->f_pos) {
filp->f_pos = offset;
- nfs_file_open_context(filp)->dir_cookie = 0;
+ dir_ctx->dir_cookie = 0;
+ dir_ctx->duped = 0;
}
out:
mutex_unlock(&inode->i_mutex);
@@ -857,15 +955,16 @@ out:
* All directory operations under NFS are synchronous, so fsync()
* is a dummy operation.
*/
-static int nfs_fsync_dir(struct file *filp, int datasync)
+static int nfs_fsync_dir(struct file *filp, loff_t start, loff_t end,
+ int datasync)
{
- struct dentry *dentry = filp->f_path.dentry;
+ struct inode *inode = file_inode(filp);
- dfprintk(FILE, "NFS: fsync dir(%s/%s) datasync %d\n",
- dentry->d_parent->d_name.name, dentry->d_name.name,
- datasync);
+ dfprintk(FILE, "NFS: fsync dir(%pD2) datasync %d\n", filp, datasync);
- nfs_inc_stats(dentry->d_inode, NFSIOS_VFSFSYNC);
+ mutex_lock(&inode->i_mutex);
+ nfs_inc_stats(inode, NFSIOS_VFSFSYNC);
+ mutex_unlock(&inode->i_mutex);
return 0;
}
@@ -883,6 +982,7 @@ void nfs_force_lookup_revalidate(struct inode *dir)
{
NFS_I(dir)->cache_change_attribute++;
}
+EXPORT_SYMBOL_GPL(nfs_force_lookup_revalidate);
/*
* A check for whether or not the parent directory has changed.
@@ -906,28 +1006,14 @@ static int nfs_check_verifier(struct inode *dir, struct dentry *dentry)
}
/*
- * Return the intent data that applies to this particular path component
- *
- * Note that the current set of intents only apply to the very last
- * component of the path.
- * We check for this using LOOKUP_CONTINUE and LOOKUP_PARENT.
- */
-static inline unsigned int nfs_lookup_check_intent(struct nameidata *nd, unsigned int mask)
-{
- if (nd->flags & (LOOKUP_CONTINUE|LOOKUP_PARENT))
- return 0;
- return nd->flags & mask;
-}
-
-/*
* Use intent information to check whether or not we're going to do
* an O_EXCL create using this path component.
*/
-static int nfs_is_exclusive_create(struct inode *dir, struct nameidata *nd)
+static int nfs_is_exclusive_create(struct inode *dir, unsigned int flags)
{
if (NFS_PROTO(dir)->version == 2)
return 0;
- return nd && nfs_lookup_check_intent(nd, LOOKUP_EXCL);
+ return flags & LOOKUP_EXCL;
}
/*
@@ -938,28 +1024,28 @@ static int nfs_is_exclusive_create(struct inode *dir, struct nameidata *nd)
* particular file and the "nocto" mount flag is not set.
*
*/
-static inline
-int nfs_lookup_verify_inode(struct inode *inode, struct nameidata *nd)
+static
+int nfs_lookup_verify_inode(struct inode *inode, unsigned int flags)
{
struct nfs_server *server = NFS_SERVER(inode);
+ int ret;
- if (test_bit(NFS_INO_MOUNTPOINT, &NFS_I(inode)->flags))
- return 0;
- if (nd != NULL) {
- /* VFS wants an on-the-wire revalidation */
- if (nd->flags & LOOKUP_REVAL)
- goto out_force;
- /* This is an open(2) */
- if (nfs_lookup_check_intent(nd, LOOKUP_OPEN) != 0 &&
- !(server->flags & NFS_MOUNT_NOCTO) &&
- (S_ISREG(inode->i_mode) ||
- S_ISDIR(inode->i_mode)))
- goto out_force;
+ if (IS_AUTOMOUNT(inode))
return 0;
- }
- return nfs_revalidate_inode(server, inode);
+ /* VFS wants an on-the-wire revalidation */
+ if (flags & LOOKUP_REVAL)
+ goto out_force;
+ /* This is an open(2) */
+ if ((flags & LOOKUP_OPEN) && !(server->flags & NFS_MOUNT_NOCTO) &&
+ (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode)))
+ goto out_force;
+out:
+ return (inode->i_nlink == 0) ? -ENOENT : 0;
out_force:
- return __nfs_revalidate_inode(server, inode);
+ ret = __nfs_revalidate_inode(server, inode);
+ if (ret != 0)
+ return ret;
+ goto out;
}
/*
@@ -971,10 +1057,10 @@ out_force:
*/
static inline
int nfs_neg_need_reval(struct inode *dir, struct dentry *dentry,
- struct nameidata *nd)
+ unsigned int flags)
{
/* Don't revalidate a negative dentry if we're creating a new file */
- if (nd != NULL && nfs_lookup_check_intent(nd, LOOKUP_CREATE) != 0)
+ if (flags & LOOKUP_CREATE)
return 0;
if (NFS_SERVER(dir)->flags & NFS_MOUNT_LOOKUP_CACHE_NONEG)
return 1;
@@ -992,39 +1078,42 @@ int nfs_neg_need_reval(struct inode *dir, struct dentry *dentry,
* If the parent directory is seen to have changed, we throw out the
* cached dentry and do a new lookup.
*/
-static int nfs_lookup_revalidate(struct dentry * dentry, struct nameidata *nd)
+static int nfs_lookup_revalidate(struct dentry *dentry, unsigned int flags)
{
struct inode *dir;
struct inode *inode;
struct dentry *parent;
struct nfs_fh *fhandle = NULL;
struct nfs_fattr *fattr = NULL;
+ struct nfs4_label *label = NULL;
int error;
+ if (flags & LOOKUP_RCU)
+ return -ECHILD;
+
parent = dget_parent(dentry);
dir = parent->d_inode;
nfs_inc_stats(dir, NFSIOS_DENTRYREVALIDATE);
inode = dentry->d_inode;
if (!inode) {
- if (nfs_neg_need_reval(dir, dentry, nd))
+ if (nfs_neg_need_reval(dir, dentry, flags))
goto out_bad;
- goto out_valid;
+ goto out_valid_noent;
}
if (is_bad_inode(inode)) {
- dfprintk(LOOKUPCACHE, "%s: %s/%s has dud inode\n",
- __func__, dentry->d_parent->d_name.name,
- dentry->d_name.name);
+ dfprintk(LOOKUPCACHE, "%s: %pd2 has dud inode\n",
+ __func__, dentry);
goto out_bad;
}
- if (nfs_have_delegation(inode, FMODE_READ))
+ if (NFS_PROTO(dir)->have_delegation(inode, FMODE_READ))
goto out_set_verifier;
/* Force a full look up iff the parent directory has changed */
- if (!nfs_is_exclusive_create(dir, nd) && nfs_check_verifier(dir, dentry)) {
- if (nfs_lookup_verify_inode(inode, nd))
+ if (!nfs_is_exclusive_create(dir, flags) && nfs_check_verifier(dir, dentry)) {
+ if (nfs_lookup_verify_inode(inode, flags))
goto out_zap_parent;
goto out_valid;
}
@@ -1038,7 +1127,13 @@ static int nfs_lookup_revalidate(struct dentry * dentry, struct nameidata *nd)
if (fhandle == NULL || fattr == NULL)
goto out_error;
- error = NFS_PROTO(dir)->lookup(dir, &dentry->d_name, fhandle, fattr);
+ label = nfs4_label_alloc(NFS_SERVER(inode), GFP_NOWAIT);
+ if (IS_ERR(label))
+ goto out_error;
+
+ trace_nfs_lookup_revalidate_enter(dir, dentry, flags);
+ error = NFS_PROTO(dir)->lookup(dir, &dentry->d_name, fhandle, fattr, label);
+ trace_nfs_lookup_revalidate_exit(dir, dentry, flags, error);
if (error)
goto out_bad;
if (nfs_compare_fh(NFS_FH(inode), fhandle))
@@ -1046,56 +1141,103 @@ static int nfs_lookup_revalidate(struct dentry * dentry, struct nameidata *nd)
if ((error = nfs_refresh_inode(inode, fattr)) != 0)
goto out_bad;
+ nfs_setsecurity(inode, fattr, label);
+
nfs_free_fattr(fattr);
nfs_free_fhandle(fhandle);
+ nfs4_label_free(label);
+
out_set_verifier:
nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
out_valid:
+ /* Success: notify readdir to use READDIRPLUS */
+ nfs_advise_use_readdirplus(dir);
+ out_valid_noent:
dput(parent);
- dfprintk(LOOKUPCACHE, "NFS: %s(%s/%s) is valid\n",
- __func__, dentry->d_parent->d_name.name,
- dentry->d_name.name);
+ dfprintk(LOOKUPCACHE, "NFS: %s(%pd2) is valid\n",
+ __func__, dentry);
return 1;
out_zap_parent:
nfs_zap_caches(dir);
out_bad:
+ nfs_free_fattr(fattr);
+ nfs_free_fhandle(fhandle);
+ nfs4_label_free(label);
nfs_mark_for_revalidate(dir);
if (inode && S_ISDIR(inode->i_mode)) {
/* Purge readdir caches. */
nfs_zap_caches(inode);
- /* If we have submounts, don't unhash ! */
- if (have_submounts(dentry))
- goto out_valid;
- if (dentry->d_flags & DCACHE_DISCONNECTED)
+ /*
+ * We can't d_drop the root of a disconnected tree:
+ * its d_hash is on the s_anon list and d_drop() would hide
+ * it from shrink_dcache_for_unmount(), leading to busy
+ * inodes on unmount and further oopses.
+ */
+ if (IS_ROOT(dentry))
goto out_valid;
- shrink_dcache_parent(dentry);
}
- d_drop(dentry);
- nfs_free_fattr(fattr);
- nfs_free_fhandle(fhandle);
+ /* If we have submounts, don't unhash ! */
+ if (check_submounts_and_drop(dentry) != 0)
+ goto out_valid;
+
dput(parent);
- dfprintk(LOOKUPCACHE, "NFS: %s(%s/%s) is invalid\n",
- __func__, dentry->d_parent->d_name.name,
- dentry->d_name.name);
+ dfprintk(LOOKUPCACHE, "NFS: %s(%pd2) is invalid\n",
+ __func__, dentry);
return 0;
out_error:
nfs_free_fattr(fattr);
nfs_free_fhandle(fhandle);
+ nfs4_label_free(label);
dput(parent);
- dfprintk(LOOKUPCACHE, "NFS: %s(%s/%s) lookup returned error %d\n",
- __func__, dentry->d_parent->d_name.name,
- dentry->d_name.name, error);
+ dfprintk(LOOKUPCACHE, "NFS: %s(%pd2) lookup returned error %d\n",
+ __func__, dentry, error);
return error;
}
/*
+ * A weaker form of d_revalidate for revalidating just the dentry->d_inode
+ * when we don't really care about the dentry name. This is called when a
+ * pathwalk ends on a dentry that was not found via a normal lookup in the
+ * parent dir (e.g.: ".", "..", procfs symlinks or mountpoint traversals).
+ *
+ * In this situation, we just want to verify that the inode itself is OK
+ * since the dentry might have changed on the server.
+ */
+static int nfs_weak_revalidate(struct dentry *dentry, unsigned int flags)
+{
+ int error;
+ struct inode *inode = dentry->d_inode;
+
+ /*
+ * I believe we can only get a negative dentry here in the case of a
+ * procfs-style symlink. Just assume it's correct for now, but we may
+ * eventually need to do something more here.
+ */
+ if (!inode) {
+ dfprintk(LOOKUPCACHE, "%s: %pd2 has negative inode\n",
+ __func__, dentry);
+ return 1;
+ }
+
+ if (is_bad_inode(inode)) {
+ dfprintk(LOOKUPCACHE, "%s: %pd2 has dud inode\n",
+ __func__, dentry);
+ return 0;
+ }
+
+ error = nfs_revalidate_inode(NFS_SERVER(inode), inode);
+ dfprintk(LOOKUPCACHE, "NFS: %s: inode %lu is %s\n",
+ __func__, inode->i_ino, error ? "invalid" : "valid");
+ return !error;
+}
+
+/*
* This is called from dput() when d_count is going to 0.
*/
-static int nfs_dentry_delete(struct dentry *dentry)
+static int nfs_dentry_delete(const struct dentry *dentry)
{
- dfprintk(VFS, "NFS: dentry_delete(%s/%s, %x)\n",
- dentry->d_parent->d_name.name, dentry->d_name.name,
- dentry->d_flags);
+ dfprintk(VFS, "NFS: dentry_delete(%pd2, %x)\n",
+ dentry, dentry->d_flags);
/* Unhash any dentry with a stale inode */
if (dentry->d_inode != NULL && NFS_STALE(dentry->d_inode))
@@ -1114,11 +1256,14 @@ static int nfs_dentry_delete(struct dentry *dentry)
}
+/* Ensure that we revalidate inode->i_nlink */
static void nfs_drop_nlink(struct inode *inode)
{
spin_lock(&inode->i_lock);
- if (inode->i_nlink > 0)
- drop_nlink(inode);
+ /* drop the inode if we're reasonably sure this is the last link */
+ if (inode->i_nlink == 1)
+ clear_nlink(inode);
+ NFS_I(inode)->cache_validity |= NFS_INO_INVALID_ATTR;
spin_unlock(&inode->i_lock);
}
@@ -1133,42 +1278,55 @@ static void nfs_dentry_iput(struct dentry *dentry, struct inode *inode)
NFS_I(inode)->cache_validity |= NFS_INO_INVALID_DATA;
if (dentry->d_flags & DCACHE_NFSFS_RENAMED) {
- drop_nlink(inode);
nfs_complete_unlink(dentry, inode);
+ nfs_drop_nlink(inode);
}
iput(inode);
}
+static void nfs_d_release(struct dentry *dentry)
+{
+ /* free cached devname value, if it survived that far */
+ if (unlikely(dentry->d_fsdata)) {
+ if (dentry->d_flags & DCACHE_NFSFS_RENAMED)
+ WARN_ON(1);
+ else
+ kfree(dentry->d_fsdata);
+ }
+}
+
const struct dentry_operations nfs_dentry_operations = {
.d_revalidate = nfs_lookup_revalidate,
+ .d_weak_revalidate = nfs_weak_revalidate,
.d_delete = nfs_dentry_delete,
.d_iput = nfs_dentry_iput,
+ .d_automount = nfs_d_automount,
+ .d_release = nfs_d_release,
};
+EXPORT_SYMBOL_GPL(nfs_dentry_operations);
-static struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, struct nameidata *nd)
+struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, unsigned int flags)
{
struct dentry *res;
struct dentry *parent;
struct inode *inode = NULL;
struct nfs_fh *fhandle = NULL;
struct nfs_fattr *fattr = NULL;
+ struct nfs4_label *label = NULL;
int error;
- dfprintk(VFS, "NFS: lookup(%s/%s)\n",
- dentry->d_parent->d_name.name, dentry->d_name.name);
+ dfprintk(VFS, "NFS: lookup(%pd2)\n", dentry);
nfs_inc_stats(dir, NFSIOS_VFSLOOKUP);
res = ERR_PTR(-ENAMETOOLONG);
if (dentry->d_name.len > NFS_SERVER(dir)->namelen)
goto out;
- dentry->d_op = NFS_PROTO(dir)->dentry_ops;
-
/*
* If we're doing an exclusive create, optimize away the lookup
* but don't hash the dentry.
*/
- if (nfs_is_exclusive_create(dir, nd)) {
+ if (nfs_is_exclusive_create(dir, flags)) {
d_instantiate(dentry, NULL);
res = NULL;
goto out;
@@ -1180,21 +1338,29 @@ static struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, stru
if (fhandle == NULL || fattr == NULL)
goto out;
+ label = nfs4_label_alloc(NFS_SERVER(dir), GFP_NOWAIT);
+ if (IS_ERR(label))
+ goto out;
+
parent = dentry->d_parent;
/* Protect against concurrent sillydeletes */
+ trace_nfs_lookup_enter(dir, dentry, flags);
nfs_block_sillyrename(parent);
- error = NFS_PROTO(dir)->lookup(dir, &dentry->d_name, fhandle, fattr);
+ error = NFS_PROTO(dir)->lookup(dir, &dentry->d_name, fhandle, fattr, label);
if (error == -ENOENT)
goto no_entry;
if (error < 0) {
res = ERR_PTR(error);
goto out_unblock_sillyrename;
}
- inode = nfs_fhget(dentry->d_sb, fhandle, fattr);
- res = (struct dentry *)inode;
+ inode = nfs_fhget(dentry->d_sb, fhandle, fattr, label);
+ res = ERR_CAST(inode);
if (IS_ERR(res))
goto out_unblock_sillyrename;
+ /* Success: notify readdir to use READDIRPLUS */
+ nfs_advise_use_readdirplus(dir);
+
no_entry:
res = d_materialise_unique(dentry, inode);
if (res != NULL) {
@@ -1205,189 +1371,180 @@ no_entry:
nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
out_unblock_sillyrename:
nfs_unblock_sillyrename(parent);
+ trace_nfs_lookup_exit(dir, dentry, flags, error);
+ nfs4_label_free(label);
out:
nfs_free_fattr(fattr);
nfs_free_fhandle(fhandle);
return res;
}
+EXPORT_SYMBOL_GPL(nfs_lookup);
-#ifdef CONFIG_NFS_V4
-static int nfs_open_revalidate(struct dentry *, struct nameidata *);
+#if IS_ENABLED(CONFIG_NFS_V4)
+static int nfs4_lookup_revalidate(struct dentry *, unsigned int);
const struct dentry_operations nfs4_dentry_operations = {
- .d_revalidate = nfs_open_revalidate,
+ .d_revalidate = nfs4_lookup_revalidate,
.d_delete = nfs_dentry_delete,
.d_iput = nfs_dentry_iput,
+ .d_automount = nfs_d_automount,
+ .d_release = nfs_d_release,
};
+EXPORT_SYMBOL_GPL(nfs4_dentry_operations);
-/*
- * Use intent information to determine whether we need to substitute
- * the NFSv4-style stateful OPEN for the LOOKUP call
- */
-static int is_atomic_open(struct nameidata *nd)
+static fmode_t flags_to_mode(int flags)
{
- if (nd == NULL || nfs_lookup_check_intent(nd, LOOKUP_OPEN) == 0)
- return 0;
- /* NFS does not (yet) have a stateful open for directories */
- if (nd->flags & LOOKUP_DIRECTORY)
- return 0;
- /* Are we trying to write to a read only partition? */
- if (__mnt_is_readonly(nd->path.mnt) &&
- (nd->intent.open.flags & (O_CREAT|O_TRUNC|FMODE_WRITE)))
- return 0;
- return 1;
+ fmode_t res = (__force fmode_t)flags & FMODE_EXEC;
+ if ((flags & O_ACCMODE) != O_WRONLY)
+ res |= FMODE_READ;
+ if ((flags & O_ACCMODE) != O_RDONLY)
+ res |= FMODE_WRITE;
+ return res;
}
-static struct nfs_open_context *nameidata_to_nfs_open_context(struct dentry *dentry, struct nameidata *nd)
+static struct nfs_open_context *create_nfs_open_context(struct dentry *dentry, int open_flags)
{
- struct path path = {
- .mnt = nd->path.mnt,
- .dentry = dentry,
- };
- struct nfs_open_context *ctx;
- struct rpc_cred *cred;
- fmode_t fmode = nd->intent.open.flags & (FMODE_READ | FMODE_WRITE | FMODE_EXEC);
-
- cred = rpc_lookup_cred();
- if (IS_ERR(cred))
- return ERR_CAST(cred);
- ctx = alloc_nfs_open_context(&path, cred, fmode);
- put_rpccred(cred);
- if (ctx == NULL)
- return ERR_PTR(-ENOMEM);
- return ctx;
+ return alloc_nfs_open_context(dentry, flags_to_mode(open_flags));
}
static int do_open(struct inode *inode, struct file *filp)
{
- nfs_fscache_set_inode_cookie(inode, filp);
+ nfs_fscache_open_file(inode, filp);
return 0;
}
-static int nfs_intent_set_file(struct nameidata *nd, struct nfs_open_context *ctx)
+static int nfs_finish_open(struct nfs_open_context *ctx,
+ struct dentry *dentry,
+ struct file *file, unsigned open_flags,
+ int *opened)
{
- struct file *filp;
- int ret = 0;
+ int err;
+
+ if ((open_flags & (O_CREAT | O_EXCL)) == (O_CREAT | O_EXCL))
+ *opened |= FILE_CREATED;
+
+ err = finish_open(file, dentry, do_open, opened);
+ if (err)
+ goto out;
+ nfs_file_set_open_context(file, ctx);
- /* If the open_intent is for execute, we have an extra check to make */
- if (ctx->mode & FMODE_EXEC) {
- ret = nfs_may_open(ctx->path.dentry->d_inode,
- ctx->cred,
- nd->intent.open.flags);
- if (ret < 0)
- goto out;
- }
- filp = lookup_instantiate_filp(nd, ctx->path.dentry, do_open);
- if (IS_ERR(filp))
- ret = PTR_ERR(filp);
- else
- nfs_file_set_open_context(filp, ctx);
out:
- put_nfs_open_context(ctx);
- return ret;
+ return err;
}
-static struct dentry *nfs_atomic_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd)
+int nfs_atomic_open(struct inode *dir, struct dentry *dentry,
+ struct file *file, unsigned open_flags,
+ umode_t mode, int *opened)
{
struct nfs_open_context *ctx;
- struct iattr attr;
- struct dentry *res = NULL;
+ struct dentry *res;
+ struct iattr attr = { .ia_valid = ATTR_OPEN };
struct inode *inode;
- int open_flags;
+ unsigned int lookup_flags = 0;
int err;
- dfprintk(VFS, "NFS: atomic_lookup(%s/%ld), %s\n",
- dir->i_sb->s_id, dir->i_ino, dentry->d_name.name);
+ /* Expect a negative dentry */
+ BUG_ON(dentry->d_inode);
- /* Check that we are indeed trying to open this file */
- if (!is_atomic_open(nd))
- goto no_open;
+ dfprintk(VFS, "NFS: atomic_open(%s/%lu), %pd\n",
+ dir->i_sb->s_id, dir->i_ino, dentry);
- if (dentry->d_name.len > NFS_SERVER(dir)->namelen) {
- res = ERR_PTR(-ENAMETOOLONG);
- goto out;
+ err = nfs_check_flags(open_flags);
+ if (err)
+ return err;
+
+ /* NFS only supports OPEN on regular files */
+ if ((open_flags & O_DIRECTORY)) {
+ if (!d_unhashed(dentry)) {
+ /*
+ * Hashed negative dentry with O_DIRECTORY: dentry was
+ * revalidated and is fine, no need to perform lookup
+ * again
+ */
+ return -ENOENT;
+ }
+ lookup_flags = LOOKUP_OPEN|LOOKUP_DIRECTORY;
+ goto no_open;
}
- dentry->d_op = NFS_PROTO(dir)->dentry_ops;
- /* Let vfs_create() deal with O_EXCL. Instantiate, but don't hash
- * the dentry. */
- if (nd->flags & LOOKUP_EXCL) {
- d_instantiate(dentry, NULL);
- goto out;
+ if (dentry->d_name.len > NFS_SERVER(dir)->namelen)
+ return -ENAMETOOLONG;
+
+ if (open_flags & O_CREAT) {
+ attr.ia_valid |= ATTR_MODE;
+ attr.ia_mode = mode & ~current_umask();
+ }
+ if (open_flags & O_TRUNC) {
+ attr.ia_valid |= ATTR_SIZE;
+ attr.ia_size = 0;
}
- ctx = nameidata_to_nfs_open_context(dentry, nd);
- res = ERR_CAST(ctx);
+ ctx = create_nfs_open_context(dentry, open_flags);
+ err = PTR_ERR(ctx);
if (IS_ERR(ctx))
goto out;
- open_flags = nd->intent.open.flags;
- if (nd->flags & LOOKUP_CREATE) {
- attr.ia_mode = nd->intent.open.create_mode;
- attr.ia_valid = ATTR_MODE;
- if (!IS_POSIXACL(dir))
- attr.ia_mode &= ~current_umask();
- } else {
- open_flags &= ~(O_EXCL | O_CREAT);
- attr.ia_valid = 0;
- }
-
- /* Open the file on the server */
+ trace_nfs_atomic_open_enter(dir, ctx, open_flags);
nfs_block_sillyrename(dentry->d_parent);
- inode = NFS_PROTO(dir)->open_context(dir, ctx, open_flags, &attr);
+ inode = NFS_PROTO(dir)->open_context(dir, ctx, open_flags, &attr, opened);
+ nfs_unblock_sillyrename(dentry->d_parent);
if (IS_ERR(inode)) {
- nfs_unblock_sillyrename(dentry->d_parent);
+ err = PTR_ERR(inode);
+ trace_nfs_atomic_open_exit(dir, ctx, open_flags, err);
put_nfs_open_context(ctx);
- switch (PTR_ERR(inode)) {
- /* Make a negative dentry */
- case -ENOENT:
- d_add(dentry, NULL);
- res = NULL;
- goto out;
- /* This turned out not to be a regular file */
- case -EISDIR:
- case -ENOTDIR:
+ switch (err) {
+ case -ENOENT:
+ d_drop(dentry);
+ d_add(dentry, NULL);
+ break;
+ case -EISDIR:
+ case -ENOTDIR:
+ goto no_open;
+ case -ELOOP:
+ if (!(open_flags & O_NOFOLLOW))
goto no_open;
- case -ELOOP:
- if (!(nd->intent.open.flags & O_NOFOLLOW))
- goto no_open;
+ break;
/* case -EINVAL: */
- default:
- res = ERR_CAST(inode);
- goto out;
+ default:
+ break;
}
+ goto out;
}
- res = d_add_unique(dentry, inode);
- nfs_unblock_sillyrename(dentry->d_parent);
- if (res != NULL) {
- dput(ctx->path.dentry);
- ctx->path.dentry = dget(res);
- dentry = res;
- }
- err = nfs_intent_set_file(nd, ctx);
- if (err < 0) {
- if (res != NULL)
- dput(res);
- return ERR_PTR(err);
- }
+
+ err = nfs_finish_open(ctx, ctx->dentry, file, open_flags, opened);
+ trace_nfs_atomic_open_exit(dir, ctx, open_flags, err);
+ put_nfs_open_context(ctx);
out:
- nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
- return res;
+ return err;
+
no_open:
- return nfs_lookup(dir, dentry, nd);
+ res = nfs_lookup(dir, dentry, lookup_flags);
+ err = PTR_ERR(res);
+ if (IS_ERR(res))
+ goto out;
+
+ return finish_no_open(file, res);
}
+EXPORT_SYMBOL_GPL(nfs_atomic_open);
-static int nfs_open_revalidate(struct dentry *dentry, struct nameidata *nd)
+static int nfs4_lookup_revalidate(struct dentry *dentry, unsigned int flags)
{
struct dentry *parent = NULL;
- struct inode *inode = dentry->d_inode;
+ struct inode *inode;
struct inode *dir;
- struct nfs_open_context *ctx;
- int openflags, ret = 0;
+ int ret = 0;
+
+ if (flags & LOOKUP_RCU)
+ return -ECHILD;
- if (!is_atomic_open(nd) || d_mountpoint(dentry))
+ if (!(flags & LOOKUP_OPEN) || (flags & LOOKUP_DIRECTORY))
+ goto no_open;
+ if (d_mountpoint(dentry))
+ goto no_open;
+ if (NFS_SB(dentry->d_sb)->caps & NFS_CAP_ATOMIC_OPEN_V1)
goto no_open;
+ inode = dentry->d_inode;
parent = dget_parent(dentry);
dir = parent->d_inode;
@@ -1395,7 +1552,7 @@ static int nfs_open_revalidate(struct dentry *dentry, struct nameidata *nd)
* optimize away revalidation of negative dentries.
*/
if (inode == NULL) {
- if (!nfs_neg_need_reval(dir, dentry, nd))
+ if (!nfs_neg_need_reval(dir, dentry, flags))
ret = 1;
goto out;
}
@@ -1403,99 +1560,21 @@ static int nfs_open_revalidate(struct dentry *dentry, struct nameidata *nd)
/* NFS only supports OPEN on regular files */
if (!S_ISREG(inode->i_mode))
goto no_open_dput;
- openflags = nd->intent.open.flags;
/* We cannot do exclusive creation on a positive dentry */
- if ((openflags & (O_CREAT|O_EXCL)) == (O_CREAT|O_EXCL))
+ if (flags & LOOKUP_EXCL)
goto no_open_dput;
- /* We can't create new files, or truncate existing ones here */
- openflags &= ~(O_CREAT|O_EXCL|O_TRUNC);
- ctx = nameidata_to_nfs_open_context(dentry, nd);
- ret = PTR_ERR(ctx);
- if (IS_ERR(ctx))
- goto out;
- /*
- * Note: we're not holding inode->i_mutex and so may be racing with
- * operations that change the directory. We therefore save the
- * change attribute *before* we do the RPC call.
- */
- inode = NFS_PROTO(dir)->open_context(dir, ctx, openflags, NULL);
- if (IS_ERR(inode)) {
- ret = PTR_ERR(inode);
- switch (ret) {
- case -EPERM:
- case -EACCES:
- case -EDQUOT:
- case -ENOSPC:
- case -EROFS:
- goto out_put_ctx;
- default:
- goto out_drop;
- }
- }
- iput(inode);
- if (inode != dentry->d_inode)
- goto out_drop;
+ /* Let f_op->open() actually open (and revalidate) the file */
+ ret = 1;
- nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
- ret = nfs_intent_set_file(nd, ctx);
- if (ret >= 0)
- ret = 1;
out:
dput(parent);
return ret;
-out_drop:
- d_drop(dentry);
- ret = 0;
-out_put_ctx:
- put_nfs_open_context(ctx);
- goto out;
no_open_dput:
dput(parent);
no_open:
- return nfs_lookup_revalidate(dentry, nd);
-}
-
-static int nfs_open_create(struct inode *dir, struct dentry *dentry, int mode,
- struct nameidata *nd)
-{
- struct nfs_open_context *ctx = NULL;
- struct iattr attr;
- int error;
- int open_flags = 0;
-
- dfprintk(VFS, "NFS: create(%s/%ld), %s\n",
- dir->i_sb->s_id, dir->i_ino, dentry->d_name.name);
-
- attr.ia_mode = mode;
- attr.ia_valid = ATTR_MODE;
-
- if ((nd->flags & LOOKUP_CREATE) != 0) {
- open_flags = nd->intent.open.flags;
-
- ctx = nameidata_to_nfs_open_context(dentry, nd);
- error = PTR_ERR(ctx);
- if (IS_ERR(ctx))
- goto out_err_drop;
- }
-
- error = NFS_PROTO(dir)->create(dir, dentry, &attr, open_flags, ctx);
- if (error != 0)
- goto out_put_ctx;
- if (ctx != NULL) {
- error = nfs_intent_set_file(nd, ctx);
- if (error < 0)
- goto out_err;
- }
- return 0;
-out_put_ctx:
- if (ctx != NULL)
- put_nfs_open_context(ctx);
-out_err_drop:
- d_drop(dentry);
-out_err:
- return error;
+ return nfs_lookup_revalidate(dentry, flags);
}
#endif /* CONFIG_NFSV4 */
@@ -1504,7 +1583,8 @@ out_err:
* Code common to create, mkdir, and mknod.
*/
int nfs_instantiate(struct dentry *dentry, struct nfs_fh *fhandle,
- struct nfs_fattr *fattr)
+ struct nfs_fattr *fattr,
+ struct nfs4_label *label)
{
struct dentry *parent = dget_parent(dentry);
struct inode *dir = parent->d_inode;
@@ -1517,18 +1597,18 @@ int nfs_instantiate(struct dentry *dentry, struct nfs_fh *fhandle,
if (dentry->d_inode)
goto out;
if (fhandle->size == 0) {
- error = NFS_PROTO(dir)->lookup(dir, &dentry->d_name, fhandle, fattr);
+ error = NFS_PROTO(dir)->lookup(dir, &dentry->d_name, fhandle, fattr, NULL);
if (error)
goto out_error;
}
nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
if (!(fattr->valid & NFS_ATTR_FATTR)) {
struct nfs_server *server = NFS_SB(dentry->d_sb);
- error = server->nfs_client->rpc_ops->getattr(server, fhandle, fattr);
+ error = server->nfs_client->rpc_ops->getattr(server, fhandle, fattr, NULL);
if (error < 0)
goto out_error;
}
- inode = nfs_fhget(dentry->d_sb, fhandle, fattr);
+ inode = nfs_fhget(dentry->d_sb, fhandle, fattr, label);
error = PTR_ERR(inode);
if (IS_ERR(inode))
goto out_error;
@@ -1541,6 +1621,7 @@ out_error:
dput(parent);
return error;
}
+EXPORT_SYMBOL_GPL(nfs_instantiate);
/*
* Following a failed create operation, we drop the dentry rather
@@ -1548,19 +1629,22 @@ out_error:
* that the operation succeeded on the server, but an error in the
* reply path made it appear to have failed.
*/
-static int nfs_create(struct inode *dir, struct dentry *dentry, int mode,
- struct nameidata *nd)
+int nfs_create(struct inode *dir, struct dentry *dentry,
+ umode_t mode, bool excl)
{
struct iattr attr;
+ int open_flags = excl ? O_CREAT | O_EXCL : O_CREAT;
int error;
- dfprintk(VFS, "NFS: create(%s/%ld), %s\n",
- dir->i_sb->s_id, dir->i_ino, dentry->d_name.name);
+ dfprintk(VFS, "NFS: create(%s/%lu), %pd\n",
+ dir->i_sb->s_id, dir->i_ino, dentry);
attr.ia_mode = mode;
attr.ia_valid = ATTR_MODE;
- error = NFS_PROTO(dir)->create(dir, dentry, &attr, 0, NULL);
+ trace_nfs_create_enter(dir, dentry, open_flags);
+ error = NFS_PROTO(dir)->create(dir, dentry, &attr, open_flags);
+ trace_nfs_create_exit(dir, dentry, open_flags, error);
if (error != 0)
goto out_err;
return 0;
@@ -1568,18 +1652,19 @@ out_err:
d_drop(dentry);
return error;
}
+EXPORT_SYMBOL_GPL(nfs_create);
/*
* See comments for nfs_proc_create regarding failed operations.
*/
-static int
-nfs_mknod(struct inode *dir, struct dentry *dentry, int mode, dev_t rdev)
+int
+nfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t rdev)
{
struct iattr attr;
int status;
- dfprintk(VFS, "NFS: mknod(%s/%ld), %s\n",
- dir->i_sb->s_id, dir->i_ino, dentry->d_name.name);
+ dfprintk(VFS, "NFS: mknod(%s/%lu), %pd\n",
+ dir->i_sb->s_id, dir->i_ino, dentry);
if (!new_valid_dev(rdev))
return -EINVAL;
@@ -1587,7 +1672,9 @@ nfs_mknod(struct inode *dir, struct dentry *dentry, int mode, dev_t rdev)
attr.ia_mode = mode;
attr.ia_valid = ATTR_MODE;
+ trace_nfs_mknod_enter(dir, dentry);
status = NFS_PROTO(dir)->mknod(dir, dentry, &attr, rdev);
+ trace_nfs_mknod_exit(dir, dentry, status);
if (status != 0)
goto out_err;
return 0;
@@ -1595,22 +1682,25 @@ out_err:
d_drop(dentry);
return status;
}
+EXPORT_SYMBOL_GPL(nfs_mknod);
/*
* See comments for nfs_proc_create regarding failed operations.
*/
-static int nfs_mkdir(struct inode *dir, struct dentry *dentry, int mode)
+int nfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
{
struct iattr attr;
int error;
- dfprintk(VFS, "NFS: mkdir(%s/%ld), %s\n",
- dir->i_sb->s_id, dir->i_ino, dentry->d_name.name);
+ dfprintk(VFS, "NFS: mkdir(%s/%lu), %pd\n",
+ dir->i_sb->s_id, dir->i_ino, dentry);
attr.ia_valid = ATTR_MODE;
attr.ia_mode = mode | S_IFDIR;
+ trace_nfs_mkdir_enter(dir, dentry);
error = NFS_PROTO(dir)->mkdir(dir, dentry, &attr);
+ trace_nfs_mkdir_exit(dir, dentry, error);
if (error != 0)
goto out_err;
return 0;
@@ -1618,6 +1708,7 @@ out_err:
d_drop(dentry);
return error;
}
+EXPORT_SYMBOL_GPL(nfs_mkdir);
static void nfs_dentry_handle_enoent(struct dentry *dentry)
{
@@ -1625,22 +1716,32 @@ static void nfs_dentry_handle_enoent(struct dentry *dentry)
d_delete(dentry);
}
-static int nfs_rmdir(struct inode *dir, struct dentry *dentry)
+int nfs_rmdir(struct inode *dir, struct dentry *dentry)
{
int error;
- dfprintk(VFS, "NFS: rmdir(%s/%ld), %s\n",
- dir->i_sb->s_id, dir->i_ino, dentry->d_name.name);
+ dfprintk(VFS, "NFS: rmdir(%s/%lu), %pd\n",
+ dir->i_sb->s_id, dir->i_ino, dentry);
- error = NFS_PROTO(dir)->rmdir(dir, &dentry->d_name);
- /* Ensure the VFS deletes this inode */
- if (error == 0 && dentry->d_inode != NULL)
- clear_nlink(dentry->d_inode);
- else if (error == -ENOENT)
- nfs_dentry_handle_enoent(dentry);
+ trace_nfs_rmdir_enter(dir, dentry);
+ if (dentry->d_inode) {
+ nfs_wait_on_sillyrename(dentry);
+ error = NFS_PROTO(dir)->rmdir(dir, &dentry->d_name);
+ /* Ensure the VFS deletes this inode */
+ switch (error) {
+ case 0:
+ clear_nlink(dentry->d_inode);
+ break;
+ case -ENOENT:
+ nfs_dentry_handle_enoent(dentry);
+ }
+ } else
+ error = NFS_PROTO(dir)->rmdir(dir, &dentry->d_name);
+ trace_nfs_rmdir_exit(dir, dentry, error);
return error;
}
+EXPORT_SYMBOL_GPL(nfs_rmdir);
/*
* Remove a file after making sure there are no pending writes,
@@ -1655,8 +1756,7 @@ static int nfs_safe_remove(struct dentry *dentry)
struct inode *inode = dentry->d_inode;
int error = -EBUSY;
- dfprintk(VFS, "NFS: safe_remove(%s/%s)\n",
- dentry->d_parent->d_name.name, dentry->d_name.name);
+ dfprintk(VFS, "NFS: safe_remove(%pd2)\n", dentry);
/* If the dentry was sillyrenamed, we simply call d_delete() */
if (dentry->d_flags & DCACHE_NFSFS_RENAMED) {
@@ -1664,17 +1764,17 @@ static int nfs_safe_remove(struct dentry *dentry)
goto out;
}
+ trace_nfs_remove_enter(dir, dentry);
if (inode != NULL) {
- nfs_inode_return_delegation(inode);
+ NFS_PROTO(inode)->return_delegation(inode);
error = NFS_PROTO(dir)->remove(dir, &dentry->d_name);
- /* The VFS may want to delete this inode */
if (error == 0)
nfs_drop_nlink(inode);
- nfs_mark_for_revalidate(inode);
} else
error = NFS_PROTO(dir)->remove(dir, &dentry->d_name);
if (error == -ENOENT)
nfs_dentry_handle_enoent(dentry);
+ trace_nfs_remove_exit(dir, dentry, error);
out:
return error;
}
@@ -1684,37 +1784,38 @@ out:
*
* If sillyrename() returns 0, we do nothing, otherwise we unlink.
*/
-static int nfs_unlink(struct inode *dir, struct dentry *dentry)
+int nfs_unlink(struct inode *dir, struct dentry *dentry)
{
int error;
int need_rehash = 0;
- dfprintk(VFS, "NFS: unlink(%s/%ld, %s)\n", dir->i_sb->s_id,
- dir->i_ino, dentry->d_name.name);
+ dfprintk(VFS, "NFS: unlink(%s/%lu, %pd)\n", dir->i_sb->s_id,
+ dir->i_ino, dentry);
- spin_lock(&dcache_lock);
+ trace_nfs_unlink_enter(dir, dentry);
spin_lock(&dentry->d_lock);
- if (atomic_read(&dentry->d_count) > 1) {
+ if (d_count(dentry) > 1) {
spin_unlock(&dentry->d_lock);
- spin_unlock(&dcache_lock);
/* Start asynchronous writeout of the inode */
write_inode_now(dentry->d_inode, 0);
error = nfs_sillyrename(dir, dentry);
- return error;
+ goto out;
}
if (!d_unhashed(dentry)) {
__d_drop(dentry);
need_rehash = 1;
}
spin_unlock(&dentry->d_lock);
- spin_unlock(&dcache_lock);
error = nfs_safe_remove(dentry);
if (!error || error == -ENOENT) {
nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
} else if (need_rehash)
d_rehash(dentry);
+out:
+ trace_nfs_unlink_exit(dir, dentry, error);
return error;
}
+EXPORT_SYMBOL_GPL(nfs_unlink);
/*
* To create a symbolic link, most file systems instantiate a new inode,
@@ -1731,17 +1832,16 @@ static int nfs_unlink(struct inode *dir, struct dentry *dentry)
* now have a new file handle and can instantiate an in-core NFS inode
* and move the raw page into its mapping.
*/
-static int nfs_symlink(struct inode *dir, struct dentry *dentry, const char *symname)
+int nfs_symlink(struct inode *dir, struct dentry *dentry, const char *symname)
{
- struct pagevec lru_pvec;
struct page *page;
char *kaddr;
struct iattr attr;
unsigned int pathlen = strlen(symname);
int error;
- dfprintk(VFS, "NFS: symlink(%s/%ld, %s, %s)\n", dir->i_sb->s_id,
- dir->i_ino, dentry->d_name.name, symname);
+ dfprintk(VFS, "NFS: symlink(%s/%lu, %pd, %s)\n", dir->i_sb->s_id,
+ dir->i_ino, dentry, symname);
if (pathlen > PAGE_SIZE)
return -ENAMETOOLONG;
@@ -1753,17 +1853,19 @@ static int nfs_symlink(struct inode *dir, struct dentry *dentry, const char *sym
if (!page)
return -ENOMEM;
- kaddr = kmap_atomic(page, KM_USER0);
+ kaddr = kmap_atomic(page);
memcpy(kaddr, symname, pathlen);
if (pathlen < PAGE_SIZE)
memset(kaddr + pathlen, 0, PAGE_SIZE - pathlen);
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
+ trace_nfs_symlink_enter(dir, dentry);
error = NFS_PROTO(dir)->symlink(dir, dentry, page, pathlen, &attr);
+ trace_nfs_symlink_exit(dir, dentry, error);
if (error != 0) {
- dfprintk(VFS, "NFS: symlink(%s/%ld, %s, %s) error %d\n",
+ dfprintk(VFS, "NFS: symlink(%s/%lu, %pd, %s) error %d\n",
dir->i_sb->s_id, dir->i_ino,
- dentry->d_name.name, symname, error);
+ dentry, symname, error);
d_drop(dentry);
__free_page(page);
return error;
@@ -1773,30 +1875,33 @@ static int nfs_symlink(struct inode *dir, struct dentry *dentry, const char *sym
* No big deal if we can't add this page to the page cache here.
* READLINK will get the missing page from the server if needed.
*/
- pagevec_init(&lru_pvec, 0);
- if (!add_to_page_cache(page, dentry->d_inode->i_mapping, 0,
+ if (!add_to_page_cache_lru(page, dentry->d_inode->i_mapping, 0,
GFP_KERNEL)) {
- pagevec_add(&lru_pvec, page);
- pagevec_lru_add_file(&lru_pvec);
SetPageUptodate(page);
unlock_page(page);
+ /*
+ * add_to_page_cache_lru() grabs an extra page refcount.
+ * Drop it here to avoid leaking this page later.
+ */
+ page_cache_release(page);
} else
__free_page(page);
return 0;
}
+EXPORT_SYMBOL_GPL(nfs_symlink);
-static int
+int
nfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry)
{
struct inode *inode = old_dentry->d_inode;
int error;
- dfprintk(VFS, "NFS: link(%s/%s -> %s/%s)\n",
- old_dentry->d_parent->d_name.name, old_dentry->d_name.name,
- dentry->d_parent->d_name.name, dentry->d_name.name);
+ dfprintk(VFS, "NFS: link(%pd2 -> %pd2)\n",
+ old_dentry, dentry);
- nfs_inode_return_delegation(inode);
+ trace_nfs_link_enter(inode, dir, dentry);
+ NFS_PROTO(inode)->return_delegation(inode);
d_drop(dentry);
error = NFS_PROTO(dir)->link(inode, dir, &dentry->d_name);
@@ -1804,8 +1909,10 @@ nfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry)
ihold(inode);
d_add(dentry, inode);
}
+ trace_nfs_link_exit(inode, dir, dentry, error);
return error;
}
+EXPORT_SYMBOL_GPL(nfs_link);
/*
* RENAME
@@ -1831,19 +1938,20 @@ nfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry)
* If these conditions are met, we can drop the dentries before doing
* the rename.
*/
-static int nfs_rename(struct inode *old_dir, struct dentry *old_dentry,
+int nfs_rename(struct inode *old_dir, struct dentry *old_dentry,
struct inode *new_dir, struct dentry *new_dentry)
{
struct inode *old_inode = old_dentry->d_inode;
struct inode *new_inode = new_dentry->d_inode;
struct dentry *dentry = NULL, *rehash = NULL;
+ struct rpc_task *task;
int error = -EBUSY;
- dfprintk(VFS, "NFS: rename(%s/%s -> %s/%s, ct=%d)\n",
- old_dentry->d_parent->d_name.name, old_dentry->d_name.name,
- new_dentry->d_parent->d_name.name, new_dentry->d_name.name,
- atomic_read(&new_dentry->d_count));
+ dfprintk(VFS, "NFS: rename(%pd2 -> %pd2, ct=%d)\n",
+ old_dentry, new_dentry,
+ d_count(new_dentry));
+ trace_nfs_rename_enter(old_dir, old_dentry, new_dir, new_dentry);
/*
* For non-directories, check whether the target is busy and if so,
* make a copy of the dentry and then do a silly-rename. If the
@@ -1860,7 +1968,7 @@ static int nfs_rename(struct inode *old_dir, struct dentry *old_dentry,
rehash = new_dentry;
}
- if (atomic_read(&new_dentry->d_count) > 2) {
+ if (d_count(new_dentry) > 2) {
int err;
/* copy the target dentry's name */
@@ -1880,16 +1988,26 @@ static int nfs_rename(struct inode *old_dir, struct dentry *old_dentry,
}
}
- nfs_inode_return_delegation(old_inode);
+ NFS_PROTO(old_inode)->return_delegation(old_inode);
if (new_inode != NULL)
- nfs_inode_return_delegation(new_inode);
+ NFS_PROTO(new_inode)->return_delegation(new_inode);
+
+ task = nfs_async_rename(old_dir, new_dir, old_dentry, new_dentry, NULL);
+ if (IS_ERR(task)) {
+ error = PTR_ERR(task);
+ goto out;
+ }
- error = NFS_PROTO(old_dir)->rename(old_dir, &old_dentry->d_name,
- new_dir, &new_dentry->d_name);
+ error = rpc_wait_for_completion_task(task);
+ if (error == 0)
+ error = task->tk_status;
+ rpc_put_task(task);
nfs_mark_for_revalidate(old_inode);
out:
if (rehash)
d_rehash(rehash);
+ trace_nfs_rename_exit(old_dir, old_dentry,
+ new_dir, new_dentry, error);
if (!error) {
if (new_inode != NULL)
nfs_drop_nlink(new_inode);
@@ -1904,6 +2022,7 @@ out:
dput(dentry);
return error;
}
+EXPORT_SYMBOL_GPL(nfs_rename);
static DEFINE_SPINLOCK(nfs_access_lru_lock);
static LIST_HEAD(nfs_access_lru_list);
@@ -1913,9 +2032,9 @@ static void nfs_access_free_entry(struct nfs_access_entry *entry)
{
put_rpccred(entry->cred);
kfree(entry);
- smp_mb__before_atomic_dec();
+ smp_mb__before_atomic();
atomic_long_dec(&nfs_access_nr_entries);
- smp_mb__after_atomic_dec();
+ smp_mb__after_atomic();
}
static void nfs_access_free_list(struct list_head *head)
@@ -1929,14 +2048,18 @@ static void nfs_access_free_list(struct list_head *head)
}
}
-int nfs_access_cache_shrinker(struct shrinker *shrink, int nr_to_scan, gfp_t gfp_mask)
+unsigned long
+nfs_access_cache_scan(struct shrinker *shrink, struct shrink_control *sc)
{
LIST_HEAD(head);
struct nfs_inode *nfsi, *next;
struct nfs_access_entry *cache;
+ int nr_to_scan = sc->nr_to_scan;
+ gfp_t gfp_mask = sc->gfp_mask;
+ long freed = 0;
if ((gfp_mask & GFP_KERNEL) != GFP_KERNEL)
- return (nr_to_scan == 0) ? 0 : -1;
+ return SHRINK_STOP;
spin_lock(&nfs_access_lru_lock);
list_for_each_entry_safe(nfsi, next, &nfs_access_lru_list, access_cache_inode_lru) {
@@ -1952,21 +2075,28 @@ int nfs_access_cache_shrinker(struct shrinker *shrink, int nr_to_scan, gfp_t gfp
struct nfs_access_entry, lru);
list_move(&cache->lru, &head);
rb_erase(&cache->rb_node, &nfsi->access_cache);
+ freed++;
if (!list_empty(&nfsi->access_cache_entry_lru))
list_move_tail(&nfsi->access_cache_inode_lru,
&nfs_access_lru_list);
else {
remove_lru_entry:
list_del_init(&nfsi->access_cache_inode_lru);
- smp_mb__before_clear_bit();
+ smp_mb__before_atomic();
clear_bit(NFS_INO_ACL_LRU_SET, &nfsi->flags);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
}
spin_unlock(&inode->i_lock);
}
spin_unlock(&nfs_access_lru_lock);
nfs_access_free_list(&head);
- return (atomic_long_read(&nfs_access_nr_entries) / 100) * sysctl_vfs_cache_pressure;
+ return freed;
+}
+
+unsigned long
+nfs_access_cache_count(struct shrinker *shrink, struct shrink_control *sc)
+{
+ return vfs_pressure_ratio(atomic_long_read(&nfs_access_nr_entries));
}
static void __nfs_access_zap_cache(struct nfs_inode *nfsi, struct list_head *head)
@@ -2001,6 +2131,7 @@ void nfs_access_zap_cache(struct inode *inode)
spin_unlock(&nfs_access_lru_lock);
nfs_access_free_list(&head);
}
+EXPORT_SYMBOL_GPL(nfs_access_zap_cache);
static struct nfs_access_entry *nfs_access_search_rbtree(struct inode *inode, struct rpc_cred *cred)
{
@@ -2088,7 +2219,7 @@ found:
nfs_access_free_entry(entry);
}
-static void nfs_access_add_cache(struct inode *inode, struct nfs_access_entry *set)
+void nfs_access_add_cache(struct inode *inode, struct nfs_access_entry *set)
{
struct nfs_access_entry *cache = kmalloc(sizeof(*cache), GFP_KERNEL);
if (cache == NULL)
@@ -2101,9 +2232,9 @@ static void nfs_access_add_cache(struct inode *inode, struct nfs_access_entry *s
nfs_access_add_rbtree(inode, cache);
/* Update accounting */
- smp_mb__before_atomic_inc();
+ smp_mb__before_atomic();
atomic_long_inc(&nfs_access_nr_entries);
- smp_mb__after_atomic_inc();
+ smp_mb__after_atomic();
/* Add inode to global LRU list */
if (!test_bit(NFS_INO_ACL_LRU_SET, &NFS_I(inode)->flags)) {
@@ -2114,15 +2245,31 @@ static void nfs_access_add_cache(struct inode *inode, struct nfs_access_entry *s
spin_unlock(&nfs_access_lru_lock);
}
}
+EXPORT_SYMBOL_GPL(nfs_access_add_cache);
+
+void nfs_access_set_mask(struct nfs_access_entry *entry, u32 access_result)
+{
+ entry->mask = 0;
+ if (access_result & NFS4_ACCESS_READ)
+ entry->mask |= MAY_READ;
+ if (access_result &
+ (NFS4_ACCESS_MODIFY | NFS4_ACCESS_EXTEND | NFS4_ACCESS_DELETE))
+ entry->mask |= MAY_WRITE;
+ if (access_result & (NFS4_ACCESS_LOOKUP|NFS4_ACCESS_EXECUTE))
+ entry->mask |= MAY_EXEC;
+}
+EXPORT_SYMBOL_GPL(nfs_access_set_mask);
static int nfs_do_access(struct inode *inode, struct rpc_cred *cred, int mask)
{
struct nfs_access_entry cache;
int status;
+ trace_nfs_access_enter(inode);
+
status = nfs_access_get_cached(inode, cred, &cache);
if (status == 0)
- goto out;
+ goto out_cached;
/* Be clever: ask server to check for all possible rights */
cache.mask = MAY_EXEC | MAY_WRITE | MAY_READ;
@@ -2135,25 +2282,31 @@ static int nfs_do_access(struct inode *inode, struct rpc_cred *cred, int mask)
if (!S_ISDIR(inode->i_mode))
set_bit(NFS_INO_STALE, &NFS_I(inode)->flags);
}
- return status;
+ goto out;
}
nfs_access_add_cache(inode, &cache);
+out_cached:
+ if ((mask & ~cache.mask & (MAY_READ | MAY_WRITE | MAY_EXEC)) != 0)
+ status = -EACCES;
out:
- if ((mask & ~cache.mask & (MAY_READ | MAY_WRITE | MAY_EXEC)) == 0)
- return 0;
- return -EACCES;
+ trace_nfs_access_exit(inode, status);
+ return status;
}
static int nfs_open_permission_mask(int openflags)
{
int mask = 0;
- if (openflags & FMODE_READ)
- mask |= MAY_READ;
- if (openflags & FMODE_WRITE)
- mask |= MAY_WRITE;
- if (openflags & FMODE_EXEC)
- mask |= MAY_EXEC;
+ if (openflags & __FMODE_EXEC) {
+ /* ONLY check exec rights */
+ mask = MAY_EXEC;
+ } else {
+ if ((openflags & O_ACCMODE) != O_WRONLY)
+ mask |= MAY_READ;
+ if ((openflags & O_ACCMODE) != O_RDONLY)
+ mask |= MAY_WRITE;
+ }
+
return mask;
}
@@ -2161,12 +2314,16 @@ int nfs_may_open(struct inode *inode, struct rpc_cred *cred, int openflags)
{
return nfs_do_access(inode, cred, nfs_open_permission_mask(openflags));
}
+EXPORT_SYMBOL_GPL(nfs_may_open);
int nfs_permission(struct inode *inode, int mask)
{
struct rpc_cred *cred;
int res = 0;
+ if (mask & MAY_NOT_BLOCK)
+ return -ECHILD;
+
nfs_inc_stats(inode, NFSIOS_VFSACCESS);
if ((mask & (MAY_READ | MAY_WRITE | MAY_EXEC)) == 0)
@@ -2179,11 +2336,6 @@ int nfs_permission(struct inode *inode, int mask)
case S_IFLNK:
goto out;
case S_IFREG:
- /* NFSv4 has atomic_open... */
- if (nfs_server_capable(inode, NFS_CAP_ATOMIC_OPEN)
- && (mask & MAY_OPEN)
- && !(mask & MAY_EXEC))
- goto out;
break;
case S_IFDIR:
/*
@@ -2208,15 +2360,16 @@ out:
if (!res && (mask & MAY_EXEC) && !execute_ok(inode))
res = -EACCES;
- dfprintk(VFS, "NFS: permission(%s/%ld), mask=0x%x, res=%d\n",
+ dfprintk(VFS, "NFS: permission(%s/%lu), mask=0x%x, res=%d\n",
inode->i_sb->s_id, inode->i_ino, mask, res);
return res;
out_notsup:
res = nfs_revalidate_inode(NFS_SERVER(inode), inode);
if (res == 0)
- res = generic_permission(inode, mask, NULL);
+ res = generic_permission(inode, mask);
goto out;
}
+EXPORT_SYMBOL_GPL(nfs_permission);
/*
* Local variables:
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-11-03 18:26:21 +0000