#include <asm/uaccess.h>
#include <asm/system.h>
+#include "delegation.h"
+#include "iostat.h"
+
#define NFSDBG_FACILITY NFSDBG_FILE
-static long nfs_file_fcntl(int fd, unsigned int cmd,
- unsigned long arg, struct file *filp);
static int nfs_file_open(struct inode *, struct file *);
static int nfs_file_release(struct inode *, struct file *);
+static loff_t nfs_file_llseek(struct file *file, loff_t offset, int origin);
static int nfs_file_mmap(struct file *, struct vm_area_struct *);
-static ssize_t nfs_file_sendfile(struct file *, loff_t *, size_t, read_actor_t, void __user *);
-static ssize_t nfs_file_read(struct kiocb *, char __user *, size_t, loff_t);
-static ssize_t nfs_file_write(struct kiocb *, const char __user *, size_t, loff_t);
-static int nfs_file_flush(struct file *);
+static ssize_t nfs_file_sendfile(struct file *, loff_t *, size_t, read_actor_t, void *);
+static ssize_t nfs_file_read(struct kiocb *, const struct iovec *iov,
+ unsigned long nr_segs, loff_t pos);
+static ssize_t nfs_file_write(struct kiocb *, const struct iovec *iov,
+ unsigned long nr_segs, loff_t pos);
+static int nfs_file_flush(struct file *, fl_owner_t id);
static int nfs_fsync(struct file *, struct dentry *dentry, int datasync);
+static int nfs_check_flags(int flags);
+static int nfs_lock(struct file *filp, int cmd, struct file_lock *fl);
+static int nfs_flock(struct file *filp, int cmd, struct file_lock *fl);
-struct file_operations nfs_file_operations = {
- .llseek = remote_llseek,
+const struct file_operations nfs_file_operations = {
+ .llseek = nfs_file_llseek,
.read = do_sync_read,
.write = do_sync_write,
- .aio_read = nfs_file_read,
- .aio_write = nfs_file_write,
+ .aio_read = nfs_file_read,
+ .aio_write = nfs_file_write,
.mmap = nfs_file_mmap,
.open = nfs_file_open,
.flush = nfs_file_flush,
.release = nfs_file_release,
.fsync = nfs_fsync,
.lock = nfs_lock,
+ .flock = nfs_flock,
.sendfile = nfs_file_sendfile,
- .fcntl = nfs_file_fcntl,
+ .check_flags = nfs_check_flags,
};
struct inode_operations nfs_file_inode_operations = {
.setattr = nfs_setattr,
};
+#ifdef CONFIG_NFS_V3
+struct inode_operations nfs3_file_inode_operations = {
+ .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 */
+
/* Hack for future NFS swap support */
#ifndef IS_SWAPFILE
# define IS_SWAPFILE(inode) (0)
#endif
-#define nfs_invalid_flags (O_APPEND | O_DIRECT)
-
-/*
- * Check for special cases that NFS doesn't support, and
- * pass the rest to the generic fcntl function.
- */
-static long
-nfs_file_fcntl(int fd, unsigned int cmd,
- unsigned long arg, struct file *filp)
+static int nfs_check_flags(int flags)
{
- switch (cmd) {
- case F_SETFL:
- if ((filp->f_flags & nfs_invalid_flags) == nfs_invalid_flags)
- return -EINVAL;
- break;
- default:
- break;
- }
+ if ((flags & (O_APPEND | O_DIRECT)) == (O_APPEND | O_DIRECT))
+ return -EINVAL;
- return generic_file_fcntl(fd, cmd, arg, filp);
+ return 0;
}
/*
static int
nfs_file_open(struct inode *inode, struct file *filp)
{
- struct nfs_server *server = NFS_SERVER(inode);
- int (*open)(struct inode *, struct file *);
- int res = 0;
+ int res;
- if ((filp->f_flags & nfs_invalid_flags) == nfs_invalid_flags)
- return -EINVAL;
+ res = nfs_check_flags(filp->f_flags);
+ if (res)
+ return res;
+ nfs_inc_stats(inode, NFSIOS_VFSOPEN);
lock_kernel();
- /* Do NFSv4 open() call */
- if ((open = server->rpc_ops->file_open) != NULL)
- res = open(inode, filp);
+ res = NFS_PROTO(inode)->file_open(inode, filp);
unlock_kernel();
return res;
}
static int
nfs_file_release(struct inode *inode, struct file *filp)
{
+ /* Ensure that dirty pages are flushed out with the right creds */
+ if (filp->f_mode & FMODE_WRITE)
+ filemap_fdatawrite(filp->f_mapping);
+ nfs_inc_stats(inode, NFSIOS_VFSRELEASE);
return NFS_PROTO(inode)->file_release(inode, filp);
}
+/**
+ * nfs_revalidate_size - Revalidate the file size
+ * @inode - pointer to inode struct
+ * @file - pointer to struct file
+ *
+ * Revalidates the file length. This is basically a wrapper around
+ * nfs_revalidate_inode() that takes into account the fact that we may
+ * have cached writes (in which case we don't care about the server's
+ * idea of what the file length is), or O_DIRECT (in which case we
+ * shouldn't trust the cache).
+ */
+static int nfs_revalidate_file_size(struct inode *inode, struct file *filp)
+{
+ struct nfs_server *server = NFS_SERVER(inode);
+ struct nfs_inode *nfsi = NFS_I(inode);
+
+ if (server->flags & NFS_MOUNT_NOAC)
+ goto force_reval;
+ if (filp->f_flags & O_DIRECT)
+ goto force_reval;
+ if (nfsi->npages != 0)
+ return 0;
+ if (!(nfsi->cache_validity & NFS_INO_REVAL_PAGECACHE) && !nfs_attribute_timeout(inode))
+ return 0;
+force_reval:
+ return __nfs_revalidate_inode(server, inode);
+}
+
+static loff_t nfs_file_llseek(struct file *filp, loff_t offset, int origin)
+{
+ /* origin == SEEK_END => we must revalidate the cached file length */
+ if (origin == SEEK_END) {
+ struct inode *inode = filp->f_mapping->host;
+ int retval = nfs_revalidate_file_size(inode, filp);
+ if (retval < 0)
+ return (loff_t)retval;
+ }
+ return remote_llseek(filp, offset, origin);
+}
+
/*
* Flush all dirty pages, and check for write errors.
*
*/
static int
-nfs_file_flush(struct file *file)
+nfs_file_flush(struct file *file, fl_owner_t id)
{
- struct inode *inode = file->f_dentry->d_inode;
+ struct nfs_open_context *ctx = (struct nfs_open_context *)file->private_data;
+ struct inode *inode = file->f_path.dentry->d_inode;
int status;
dfprintk(VFS, "nfs: flush(%s/%ld)\n", inode->i_sb->s_id, inode->i_ino);
if ((file->f_mode & FMODE_WRITE) == 0)
return 0;
+ nfs_inc_stats(inode, NFSIOS_VFSFLUSH);
lock_kernel();
/* Ensure that data+attribute caches are up to date after close() */
status = nfs_wb_all(inode);
if (!status) {
- status = file->f_error;
- file->f_error = 0;
+ status = ctx->error;
+ ctx->error = 0;
if (!status)
- __nfs_revalidate_inode(NFS_SERVER(inode), inode);
+ nfs_revalidate_inode(NFS_SERVER(inode), inode);
}
unlock_kernel();
return status;
}
static ssize_t
-nfs_file_read(struct kiocb *iocb, char __user * buf, size_t count, loff_t pos)
+nfs_file_read(struct kiocb *iocb, const struct iovec *iov,
+ unsigned long nr_segs, loff_t pos)
{
- struct dentry * dentry = iocb->ki_filp->f_dentry;
+ struct dentry * dentry = iocb->ki_filp->f_path.dentry;
struct inode * inode = dentry->d_inode;
ssize_t result;
+ size_t count = iov_length(iov, nr_segs);
#ifdef CONFIG_NFS_DIRECTIO
if (iocb->ki_filp->f_flags & O_DIRECT)
- return nfs_file_direct_read(iocb, buf, count, pos);
+ return nfs_file_direct_read(iocb, iov, nr_segs, pos);
#endif
dfprintk(VFS, "nfs: read(%s/%s, %lu@%lu)\n",
dentry->d_parent->d_name.name, dentry->d_name.name,
(unsigned long) count, (unsigned long) pos);
- result = nfs_revalidate_inode(NFS_SERVER(inode), inode);
+ result = nfs_revalidate_mapping(inode, iocb->ki_filp->f_mapping);
+ nfs_add_stats(inode, NFSIOS_NORMALREADBYTES, count);
if (!result)
- result = generic_file_aio_read(iocb, buf, count, pos);
+ result = generic_file_aio_read(iocb, iov, nr_segs, pos);
return result;
}
static ssize_t
nfs_file_sendfile(struct file *filp, loff_t *ppos, size_t count,
- read_actor_t actor, void __user *target)
+ read_actor_t actor, void *target)
{
- struct dentry *dentry = filp->f_dentry;
+ struct dentry *dentry = filp->f_path.dentry;
struct inode *inode = dentry->d_inode;
ssize_t res;
dentry->d_parent->d_name.name, dentry->d_name.name,
(unsigned long) count, (unsigned long long) *ppos);
- res = nfs_revalidate_inode(NFS_SERVER(inode), inode);
+ res = nfs_revalidate_mapping(inode, filp->f_mapping);
if (!res)
res = generic_file_sendfile(filp, ppos, count, actor, target);
return res;
static int
nfs_file_mmap(struct file * file, struct vm_area_struct * vma)
{
- struct dentry *dentry = file->f_dentry;
+ struct dentry *dentry = file->f_path.dentry;
struct inode *inode = dentry->d_inode;
int status;
dfprintk(VFS, "nfs: mmap(%s/%s)\n",
dentry->d_parent->d_name.name, dentry->d_name.name);
- status = nfs_revalidate_inode(NFS_SERVER(inode), inode);
+ status = nfs_revalidate_mapping(inode, file->f_mapping);
if (!status)
status = generic_file_mmap(file, vma);
return status;
static int
nfs_fsync(struct file *file, struct dentry *dentry, int datasync)
{
+ struct nfs_open_context *ctx = (struct nfs_open_context *)file->private_data;
struct inode *inode = dentry->d_inode;
int status;
dfprintk(VFS, "nfs: fsync(%s/%ld)\n", inode->i_sb->s_id, inode->i_ino);
+ nfs_inc_stats(inode, NFSIOS_VFSFSYNC);
lock_kernel();
status = nfs_wb_all(inode);
if (!status) {
- status = file->f_error;
- file->f_error = 0;
+ status = ctx->error;
+ ctx->error = 0;
}
unlock_kernel();
return status;
return status;
}
-struct address_space_operations nfs_file_aops = {
+static void nfs_invalidate_page(struct page *page, unsigned long offset)
+{
+ if (offset != 0)
+ return;
+ /* Cancel any unstarted writes on this page */
+ nfs_wb_page_priority(page->mapping->host, page, FLUSH_INVALIDATE);
+}
+
+static int nfs_release_page(struct page *page, gfp_t gfp)
+{
+ /* If PagePrivate() is set, then the page is not freeable */
+ return 0;
+}
+
+static int nfs_launder_page(struct page *page)
+{
+ return nfs_wb_page(page->mapping->host, page);
+}
+
+const struct address_space_operations nfs_file_aops = {
.readpage = nfs_readpage,
.readpages = nfs_readpages,
- .set_page_dirty = __set_page_dirty_nobuffers,
+ .set_page_dirty = nfs_set_page_dirty,
.writepage = nfs_writepage,
.writepages = nfs_writepages,
.prepare_write = nfs_prepare_write,
.commit_write = nfs_commit_write,
+ .invalidatepage = nfs_invalidate_page,
+ .releasepage = nfs_release_page,
#ifdef CONFIG_NFS_DIRECTIO
.direct_IO = nfs_direct_IO,
#endif
+ .launder_page = nfs_launder_page,
};
-/*
- * Write to a file (through the page cache).
- */
-static ssize_t
-nfs_file_write(struct kiocb *iocb, const char __user *buf, size_t count, loff_t pos)
+static ssize_t nfs_file_write(struct kiocb *iocb, const struct iovec *iov,
+ unsigned long nr_segs, loff_t pos)
{
- struct dentry * dentry = iocb->ki_filp->f_dentry;
+ struct dentry * dentry = iocb->ki_filp->f_path.dentry;
struct inode * inode = dentry->d_inode;
ssize_t result;
+ size_t count = iov_length(iov, nr_segs);
#ifdef CONFIG_NFS_DIRECTIO
if (iocb->ki_filp->f_flags & O_DIRECT)
- return nfs_file_direct_write(iocb, buf, count, pos);
+ return nfs_file_direct_write(iocb, iov, nr_segs, pos);
#endif
- dfprintk(VFS, "nfs: write(%s/%s(%ld), %lu@%lu)\n",
+ dfprintk(VFS, "nfs: write(%s/%s(%ld), %lu@%Ld)\n",
dentry->d_parent->d_name.name, dentry->d_name.name,
- inode->i_ino, (unsigned long) count, (unsigned long) pos);
+ inode->i_ino, (unsigned long) count, (long long) pos);
result = -EBUSY;
if (IS_SWAPFILE(inode))
goto out_swapfile;
- result = nfs_revalidate_inode(NFS_SERVER(inode), inode);
- if (result)
- goto out;
+ /*
+ * O_APPEND implies that we must revalidate the file length.
+ */
+ if (iocb->ki_filp->f_flags & O_APPEND) {
+ result = nfs_revalidate_file_size(inode, iocb->ki_filp);
+ if (result)
+ goto out;
+ }
result = count;
if (!count)
goto out;
- result = generic_file_aio_write(iocb, buf, count, pos);
+ nfs_add_stats(inode, NFSIOS_NORMALWRITTENBYTES, count);
+ result = generic_file_aio_write(iocb, iov, nr_segs, pos);
+ /* Return error values for O_SYNC and IS_SYNC() */
+ if (result >= 0 && (IS_SYNC(inode) || (iocb->ki_filp->f_flags & O_SYNC))) {
+ int err = nfs_fsync(iocb->ki_filp, dentry, 1);
+ if (err < 0)
+ result = err;
+ }
out:
return result;
goto out;
}
+static int do_getlk(struct file *filp, int cmd, struct file_lock *fl)
+{
+ struct file_lock cfl;
+ struct inode *inode = filp->f_mapping->host;
+ int status = 0;
+
+ lock_kernel();
+ /* Try local locking first */
+ if (posix_test_lock(filp, fl, &cfl)) {
+ fl->fl_start = cfl.fl_start;
+ fl->fl_end = cfl.fl_end;
+ fl->fl_type = cfl.fl_type;
+ fl->fl_pid = cfl.fl_pid;
+ goto out;
+ }
+
+ if (nfs_have_delegation(inode, FMODE_READ))
+ goto out_noconflict;
+
+ if (NFS_SERVER(inode)->flags & NFS_MOUNT_NONLM)
+ goto out_noconflict;
+
+ status = NFS_PROTO(inode)->lock(filp, cmd, fl);
+out:
+ unlock_kernel();
+ return status;
+out_noconflict:
+ fl->fl_type = F_UNLCK;
+ goto out;
+}
+
+static int do_vfs_lock(struct file *file, struct file_lock *fl)
+{
+ int res = 0;
+ switch (fl->fl_flags & (FL_POSIX|FL_FLOCK)) {
+ case FL_POSIX:
+ res = posix_lock_file_wait(file, fl);
+ break;
+ case FL_FLOCK:
+ res = flock_lock_file_wait(file, fl);
+ break;
+ default:
+ BUG();
+ }
+ if (res < 0)
+ dprintk(KERN_WARNING "%s: VFS is out of sync with lock manager"
+ " - error %d!\n",
+ __FUNCTION__, res);
+ return res;
+}
+
+static int do_unlk(struct file *filp, int cmd, struct file_lock *fl)
+{
+ struct inode *inode = filp->f_mapping->host;
+ int status;
+
+ /*
+ * Flush all pending writes before doing anything
+ * with locks..
+ */
+ nfs_sync_mapping(filp->f_mapping);
+
+ /* NOTE: special case
+ * If we're signalled while cleaning up locks on process exit, we
+ * still need to complete the unlock.
+ */
+ lock_kernel();
+ /* Use local locking if mounted with "-onolock" */
+ if (!(NFS_SERVER(inode)->flags & NFS_MOUNT_NONLM))
+ status = NFS_PROTO(inode)->lock(filp, cmd, fl);
+ else
+ status = do_vfs_lock(filp, fl);
+ unlock_kernel();
+ return status;
+}
+
+static int do_setlk(struct file *filp, int cmd, struct file_lock *fl)
+{
+ struct inode *inode = filp->f_mapping->host;
+ int status;
+
+ /*
+ * Flush all pending writes before doing anything
+ * with locks..
+ */
+ status = nfs_sync_mapping(filp->f_mapping);
+ if (status != 0)
+ goto out;
+
+ lock_kernel();
+ /* Use local locking if mounted with "-onolock" */
+ if (!(NFS_SERVER(inode)->flags & NFS_MOUNT_NONLM)) {
+ status = NFS_PROTO(inode)->lock(filp, cmd, fl);
+ /* If we were signalled we still need to ensure that
+ * we clean up any state on the server. We therefore
+ * record the lock call as having succeeded in order to
+ * ensure that locks_remove_posix() cleans it out when
+ * the process exits.
+ */
+ if (status == -EINTR || status == -ERESTARTSYS)
+ do_vfs_lock(filp, fl);
+ } else
+ status = do_vfs_lock(filp, fl);
+ unlock_kernel();
+ if (status < 0)
+ goto out;
+ /*
+ * Make sure we clear the cache whenever we try to get the lock.
+ * This makes locking act as a cache coherency point.
+ */
+ nfs_sync_mapping(filp->f_mapping);
+ nfs_zap_caches(inode);
+out:
+ return status;
+}
+
/*
* Lock a (portion of) a file
*/
-int
-nfs_lock(struct file *filp, int cmd, struct file_lock *fl)
+static int nfs_lock(struct file *filp, int cmd, struct file_lock *fl)
{
struct inode * inode = filp->f_mapping->host;
- int status = 0;
- int status2;
dprintk("NFS: nfs_lock(f=%s/%ld, t=%x, fl=%x, r=%Ld:%Ld)\n",
inode->i_sb->s_id, inode->i_ino,
fl->fl_type, fl->fl_flags,
(long long)fl->fl_start, (long long)fl->fl_end);
-
- if (!inode)
- return -EINVAL;
+ nfs_inc_stats(inode, NFSIOS_VFSLOCK);
/* No mandatory locks over NFS */
- if ((inode->i_mode & (S_ISGID | S_IXGRP)) == S_ISGID)
+ if ((inode->i_mode & (S_ISGID | S_IXGRP)) == S_ISGID &&
+ fl->fl_type != F_UNLCK)
return -ENOLCK;
- if (NFS_PROTO(inode)->version != 4) {
- /* Fake OK code if mounted without NLM support */
- if (NFS_SERVER(inode)->flags & NFS_MOUNT_NONLM) {
- if (IS_GETLK(cmd))
- status = LOCK_USE_CLNT;
- goto out_ok;
- }
- }
+ if (IS_GETLK(cmd))
+ return do_getlk(filp, cmd, fl);
+ if (fl->fl_type == F_UNLCK)
+ return do_unlk(filp, cmd, fl);
+ return do_setlk(filp, cmd, fl);
+}
+
+/*
+ * Lock a (portion of) a file
+ */
+static int nfs_flock(struct file *filp, int cmd, struct file_lock *fl)
+{
+ dprintk("NFS: nfs_flock(f=%s/%ld, t=%x, fl=%x)\n",
+ filp->f_path.dentry->d_inode->i_sb->s_id,
+ filp->f_path.dentry->d_inode->i_ino,
+ fl->fl_type, fl->fl_flags);
/*
* No BSD flocks over NFS allowed.
* Not sure whether that would be unique, though, or whether
* that would break in other places.
*/
- if (!fl->fl_owner || !(fl->fl_flags & FL_POSIX))
+ if (!(fl->fl_flags & FL_FLOCK))
return -ENOLCK;
- /*
- * Flush all pending writes before doing anything
- * with locks..
- */
- status = filemap_fdatawrite(filp->f_mapping);
- down(&inode->i_sem);
- status2 = nfs_wb_all(inode);
- if (!status)
- status = status2;
- up(&inode->i_sem);
- status2 = filemap_fdatawait(filp->f_mapping);
- if (!status)
- status = status2;
- if (status < 0)
- return status;
-
- lock_kernel();
- status = NFS_PROTO(inode)->lock(filp, cmd, fl);
- unlock_kernel();
- if (status < 0)
- return status;
-
- status = 0;
+ /* We're simulating flock() locks using posix locks on the server */
+ fl->fl_owner = (fl_owner_t)filp;
+ fl->fl_start = 0;
+ fl->fl_end = OFFSET_MAX;
- /*
- * Make sure we clear the cache whenever we try to get the lock.
- * This makes locking act as a cache coherency point.
- */
- out_ok:
- if ((IS_SETLK(cmd) || IS_SETLKW(cmd)) && fl->fl_type != F_UNLCK) {
- filemap_fdatawrite(filp->f_mapping);
- down(&inode->i_sem);
- nfs_wb_all(inode); /* we may have slept */
- up(&inode->i_sem);
- filemap_fdatawait(filp->f_mapping);
- nfs_zap_caches(inode);
- }
- return status;
+ if (fl->fl_type == F_UNLCK)
+ return do_unlk(filp, cmd, fl);
+ return do_setlk(filp, cmd, fl);
}
git://git.onelab.eu / linux-2.6.git / blobdiff