#include <linux/nfs_fs.h>
#include <linux/nfs_mount.h>
#include <linux/mm.h>
-#include <linux/slab.h>
#include <linux/pagemap.h>
-#include <linux/smp_lock.h>
#include <linux/aio.h>
+#include <linux/gfp.h>
#include <asm/uaccess.h>
#include <asm/system.h>
#include "delegation.h"
#include "internal.h"
#include "iostat.h"
+#include "fscache.h"
#define NFSDBG_FACILITY NFSDBG_FILE
size_t count, unsigned int flags);
static ssize_t nfs_file_read(struct kiocb *, const struct iovec *iov,
unsigned long nr_segs, loff_t pos);
+static ssize_t nfs_file_splice_write(struct pipe_inode_info *pipe,
+ struct file *filp, loff_t *ppos,
+ size_t count, unsigned int flags);
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_file_fsync(struct file *, struct dentry *dentry, int datasync);
+static int nfs_file_fsync(struct file *, 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);
static int nfs_setlease(struct file *file, long arg, struct file_lock **fl);
-static struct vm_operations_struct nfs_file_vm_ops;
+static const struct vm_operations_struct nfs_file_vm_ops;
const struct file_operations nfs_file_operations = {
.llseek = nfs_file_llseek,
.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,
.lock = nfs_lock,
.flock = nfs_flock,
.splice_read = nfs_file_splice_read,
+ .splice_write = nfs_file_splice_write,
.check_flags = nfs_check_flags,
.setlease = nfs_setlease,
};
filp->f_path.dentry->d_parent->d_name.name,
filp->f_path.dentry->d_name.name);
+ nfs_inc_stats(inode, NFSIOS_VFSOPEN);
res = nfs_check_flags(filp->f_flags);
if (res)
return res;
- nfs_inc_stats(inode, NFSIOS_VFSOPEN);
res = nfs_open(inode, filp);
return res;
}
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);
}
struct nfs_server *server = NFS_SERVER(inode);
struct nfs_inode *nfsi = NFS_I(inode);
- if (server->flags & NFS_MOUNT_NOAC)
- goto force_reval;
+ if (nfs_have_delegated_attributes(inode))
+ goto out_noreval;
+
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;
+ if (nfsi->cache_validity & NFS_INO_REVAL_PAGECACHE)
+ goto force_reval;
+ if (nfs_attribute_timeout(inode))
+ goto force_reval;
+out_noreval:
+ return 0;
force_reval:
return __nfs_revalidate_inode(server, inode);
}
/* 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;
- }
- lock_kernel(); /* BKL needed? */
- loff = generic_file_llseek_unlocked(filp, offset, origin);
- unlock_kernel();
+
+ spin_lock(&inode->i_lock);
+ loff = generic_file_llseek_unlocked(filp, offset, origin);
+ spin_unlock(&inode->i_lock);
+ } else
+ loff = generic_file_llseek_unlocked(filp, offset, origin);
return loff;
}
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,
dentry->d_name.name);
+ nfs_inc_stats(inode, NFSIOS_VFSFLUSH);
if ((file->f_mode & FMODE_WRITE) == 0)
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
(unsigned long) count, (unsigned long) pos);
result = nfs_revalidate_mapping(inode, iocb->ki_filp->f_mapping);
- nfs_add_stats(inode, NFSIOS_NORMALREADBYTES, count);
- if (!result)
+ if (!result) {
result = generic_file_aio_read(iocb, iov, nr_segs, pos);
+ if (result > 0)
+ nfs_add_stats(inode, NFSIOS_NORMALREADBYTES, result);
+ }
return result;
}
(unsigned long) count, (unsigned long long) *ppos);
res = nfs_revalidate_mapping(inode, filp->f_mapping);
- if (!res)
+ if (!res) {
res = generic_file_splice_read(filp, ppos, pipe, count, flags);
+ if (res > 0)
+ nfs_add_stats(inode, NFSIOS_NORMALREADBYTES, res);
+ }
return res;
}
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;
}
* whether any write errors occurred for this process.
*/
static int
-nfs_file_fsync(struct file *file, struct dentry *dentry, int datasync)
+nfs_file_fsync(struct file *file, int datasync)
{
+ struct dentry *dentry = file->f_path.dentry;
struct nfs_open_context *ctx = nfs_file_open_context(file);
struct inode *inode = dentry->d_inode;
}
/*
+ * Decide whether a read/modify/write cycle may be more efficient
+ * then a modify/write/read cycle when writing to a page in the
+ * page cache.
+ *
+ * The modify/write/read cycle may occur if a page is read before
+ * being completely filled by the writer. In this situation, the
+ * page must be completely written to stable storage on the server
+ * before it can be refilled by reading in the page from the server.
+ * This can lead to expensive, small, FILE_SYNC mode writes being
+ * done.
+ *
+ * It may be more efficient to read the page first if the file is
+ * open for reading in addition to writing, the page is not marked
+ * as Uptodate, it is not dirty or waiting to be committed,
+ * indicating that it was previously allocated and then modified,
+ * that there were valid bytes of data in that range of the file,
+ * and that the new data won't completely replace the old data in
+ * that range of the file.
+ */
+static int nfs_want_read_modify_write(struct file *file, struct page *page,
+ loff_t pos, unsigned len)
+{
+ unsigned int pglen = nfs_page_length(page);
+ unsigned int offset = pos & (PAGE_CACHE_SIZE - 1);
+ unsigned int end = offset + len;
+
+ if ((file->f_mode & FMODE_READ) && /* open for read? */
+ !PageUptodate(page) && /* Uptodate? */
+ !PagePrivate(page) && /* i/o request already? */
+ pglen && /* valid bytes of file? */
+ (end < pglen || offset)) /* replace all valid bytes? */
+ return 1;
+ return 0;
+}
+
+/*
* This does the "real" work of the write. We must allocate and lock the
* page to be sent back to the generic routine, which then copies the
* data from user space.
struct page **pagep, void **fsdata)
{
int ret;
- pgoff_t index;
+ pgoff_t index = pos >> PAGE_CACHE_SHIFT;
struct page *page;
- index = pos >> PAGE_CACHE_SHIFT;
+ int once_thru = 0;
dfprintk(PAGECACHE, "NFS: write_begin(%s/%s(%ld), %u@%lld)\n",
file->f_path.dentry->d_parent->d_name.name,
file->f_path.dentry->d_name.name,
mapping->host->i_ino, len, (long long) pos);
- page = __grab_cache_page(mapping, index);
+start:
+ /*
+ * 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;
*pagep = page;
if (ret) {
unlock_page(page);
page_cache_release(page);
+ } else if (!once_thru &&
+ nfs_want_read_modify_write(file, page, pos, len)) {
+ once_thru = 1;
+ ret = nfs_readpage(file, page);
+ page_cache_release(page);
+ if (!ret)
+ goto start;
}
return ret;
}
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);
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);
+ /* Only do I/O if gfp is a superset of GFP_KERNEL */
+ if ((gfp & GFP_KERNEL) == GFP_KERNEL)
+ nfs_wb_page(page->mapping->host, 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);
}
.invalidatepage = nfs_invalidate_page,
.releasepage = nfs_release_page,
.direct_IO = nfs_direct_IO,
+ .migratepage = nfs_migrate_page,
.launder_page = nfs_launder_page,
+ .error_remove_page = generic_error_remove_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;
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)
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 = {
+static const struct vm_operations_struct nfs_file_vm_ops = {
.fault = filemap_fault,
.page_mkwrite = nfs_vm_page_mkwrite,
};
{
struct nfs_open_context *ctx;
- if (IS_SYNC(inode) || (filp->f_flags & O_SYNC))
+ if (IS_SYNC(inode) || (filp->f_flags & O_DSYNC))
return 1;
ctx = nfs_file_open_context(filp);
if (test_bit(NFS_CONTEXT_ERROR_WRITE, &ctx->flags))
{
struct dentry * dentry = iocb->ki_filp->f_path.dentry;
struct inode * inode = dentry->d_inode;
+ unsigned long written = 0;
ssize_t result;
size_t count = iov_length(iov, nr_segs);
if (!count)
goto out;
- 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)
+ written = result;
+
+ /* Return error values for O_DSYNC and IS_SYNC() */
if (result >= 0 && nfs_need_sync_write(iocb->ki_filp, inode)) {
int err = nfs_do_fsync(nfs_file_open_context(iocb->ki_filp), inode);
if (err < 0)
result = err;
}
+ if (result > 0)
+ nfs_add_stats(inode, NFSIOS_NORMALWRITTENBYTES, written);
out:
return result;
goto out;
}
+static ssize_t nfs_file_splice_write(struct pipe_inode_info *pipe,
+ struct file *filp, loff_t *ppos,
+ size_t count, unsigned int flags)
+{
+ struct dentry *dentry = filp->f_path.dentry;
+ struct inode *inode = dentry->d_inode;
+ unsigned long written = 0;
+ ssize_t ret;
+
+ dprintk("NFS splice_write(%s/%s, %lu@%llu)\n",
+ dentry->d_parent->d_name.name, dentry->d_name.name,
+ (unsigned long) count, (unsigned long long) *ppos);
+
+ /*
+ * The combination of splice and an O_APPEND destination is disallowed.
+ */
+
+ ret = generic_file_splice_write(pipe, filp, ppos, count, flags);
+ if (ret > 0)
+ written = ret;
+
+ if (ret >= 0 && nfs_need_sync_write(filp, inode)) {
+ int err = nfs_do_fsync(nfs_file_open_context(filp), inode);
+ if (err < 0)
+ ret = err;
+ }
+ if (ret > 0)
+ nfs_add_stats(inode, NFSIOS_NORMALWRITTENBYTES, written);
+ return ret;
+}
+
static int do_getlk(struct file *filp, int cmd, struct file_lock *fl)
{
struct inode *inode = filp->f_mapping->host;
int status = 0;
- lock_kernel();
/* Try local locking first */
posix_test_lock(filp, fl);
if (fl->fl_type != F_UNLCK) {
status = NFS_PROTO(inode)->lock(filp, cmd, fl);
out:
- unlock_kernel();
return status;
out_noconflict:
fl->fl_type = F_UNLCK;
* 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;
}
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);
else
status = do_vfs_lock(filp, fl);
- unlock_kernel();
if (status < 0)
goto out;
/*
filp->f_path.dentry->d_name.name,
fl->fl_type, fl->fl_flags);
- /*
- * No BSD flocks over NFS allowed.
- * Note: we could try to fake a POSIX lock request here by
- * using ((u32) filp | 0x80000000) or some such as the pid.
- * Not sure whether that would be unique, though, or whether
- * that would break in other places.
- */
if (!(fl->fl_flags & FL_FLOCK))
return -ENOLCK;
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff