#include <linux/compiler.h>
#include <linux/fs.h>
#include <linux/aio.h>
+#include <linux/capability.h>
#include <linux/kernel_stat.h>
#include <linux/mm.h>
#include <linux/swap.h>
#include <linux/blkdev.h>
#include <linux/security.h>
#include <linux/syscalls.h>
+#include "filemap.h"
/*
- * This is needed for the following functions:
- * - try_to_release_page
- * - block_invalidatepage
- * - generic_osync_inode
- *
* FIXME: remove all knowledge of the buffer layer from the core VM
*/
#include <linux/buffer_head.h> /* for generic_osync_inode */
#include <asm/uaccess.h>
#include <asm/mman.h>
+static ssize_t
+generic_file_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
+ loff_t offset, unsigned long nr_segs);
+
/*
* Shared mappings implemented 30.11.1994. It's not fully working yet,
* though.
*
* ->i_mmap_lock (vmtruncate)
* ->private_lock (__free_pte->__set_page_dirty_buffers)
- * ->swap_list_lock
- * ->swap_device_lock (exclusive_swap_page, others)
- * ->mapping->tree_lock
+ * ->swap_lock (exclusive_swap_page, others)
+ * ->mapping->tree_lock
*
- * ->i_sem
+ * ->i_mutex
* ->i_mmap_lock (truncate->unmap_mapping_range)
*
* ->mmap_sem
* ->i_mmap_lock
- * ->page_table_lock (various places, mainly in mmap.c)
+ * ->page_table_lock or pte_lock (various, mainly in memory.c)
* ->mapping->tree_lock (arch-dependent flush_dcache_mmap_lock)
*
* ->mmap_sem
* ->lock_page (access_process_vm)
*
* ->mmap_sem
- * ->i_sem (msync)
+ * ->i_mutex (msync)
*
- * ->i_sem
+ * ->i_mutex
* ->i_alloc_sem (various)
*
* ->inode_lock
* ->anon_vma.lock (vma_adjust)
*
* ->anon_vma.lock
- * ->page_table_lock (anon_vma_prepare and various)
+ * ->page_table_lock or pte_lock (anon_vma_prepare and various)
*
- * ->page_table_lock
- * ->swap_device_lock (try_to_unmap_one)
+ * ->page_table_lock or pte_lock
+ * ->swap_lock (try_to_unmap_one)
* ->private_lock (try_to_unmap_one)
* ->tree_lock (try_to_unmap_one)
* ->zone.lru_lock (follow_page->mark_page_accessed)
{
struct address_space *mapping = page->mapping;
- if (unlikely(!PageLocked(page)))
- PAGE_BUG(page);
+ BUG_ON(!PageLocked(page));
write_lock_irq(&mapping->tree_lock);
__remove_from_page_cache(page);
struct address_space *mapping;
struct page *page;
- page = container_of((page_flags_t *)word, struct page, flags);
+ page = container_of((unsigned long *)word, struct page, flags);
/*
- * FIXME, fercrissake. What is this barrier here for?
+ * page_mapping() is being called without PG_locked held.
+ * Some knowledge of the state and use of the page is used to
+ * reduce the requirements down to a memory barrier.
+ * The danger here is of a stale page_mapping() return value
+ * indicating a struct address_space different from the one it's
+ * associated with when it is associated with one.
+ * After smp_mb(), it's either the correct page_mapping() for
+ * the page, or an old page_mapping() and the page's own
+ * page_mapping() has gone NULL.
+ * The ->sync_page() address_space operation must tolerate
+ * page_mapping() going NULL. By an amazing coincidence,
+ * this comes about because none of the users of the page
+ * in the ->sync_page() methods make essential use of the
+ * page_mapping(), merely passing the page down to the backing
+ * device's unplug functions when it's non-NULL, which in turn
+ * ignore it for all cases but swap, where only page_private(page) is
+ * of interest. When page_mapping() does go NULL, the entire
+ * call stack gracefully ignores the page and returns.
+ * -- wli
*/
smp_mb();
mapping = page_mapping(page);
/**
* filemap_fdatawrite_range - start writeback against all of a mapping's
* dirty pages that lie within the byte offsets <start, end>
- * @mapping: address space structure to write
- * @start: offset in bytes where the range starts
- * @end : offset in bytes where the range ends
+ * @mapping: address space structure to write
+ * @start: offset in bytes where the range starts
+ * @end: offset in bytes where the range ends
+ * @sync_mode: enable synchronous operation
*
* If sync_mode is WB_SYNC_ALL then this is a "data integrity" operation, as
* opposed to a regular memory * cleansing writeback. The difference between
* integrity" operation. It waits upon in-flight writeout before starting and
* waiting upon new writeout. If there was an IO error, return it.
*
- * We need to re-take i_sem during the generic_osync_inode list walk because
+ * We need to re-take i_mutex during the generic_osync_inode list walk because
* it is otherwise livelockable.
*/
int sync_page_range(struct inode *inode, struct address_space *mapping,
- loff_t pos, size_t count)
+ loff_t pos, loff_t count)
{
pgoff_t start = pos >> PAGE_CACHE_SHIFT;
pgoff_t end = (pos + count - 1) >> PAGE_CACHE_SHIFT;
return 0;
ret = filemap_fdatawrite_range(mapping, pos, pos + count - 1);
if (ret == 0) {
- down(&inode->i_sem);
+ mutex_lock(&inode->i_mutex);
ret = generic_osync_inode(inode, mapping, OSYNC_METADATA);
- up(&inode->i_sem);
+ mutex_unlock(&inode->i_mutex);
}
if (ret == 0)
ret = wait_on_page_writeback_range(mapping, start, end);
EXPORT_SYMBOL(sync_page_range);
/*
- * Note: Holding i_sem across sync_page_range_nolock is not a good idea
+ * Note: Holding i_mutex across sync_page_range_nolock is not a good idea
* as it forces O_SYNC writers to different parts of the same file
* to be serialised right until io completion.
*/
int sync_page_range_nolock(struct inode *inode, struct address_space *mapping,
- loff_t pos, size_t count)
+ loff_t pos, loff_t count)
{
pgoff_t start = pos >> PAGE_CACHE_SHIFT;
pgoff_t end = (pos + count - 1) >> PAGE_CACHE_SHIFT;
int filemap_write_and_wait(struct address_space *mapping)
{
- int retval = 0;
+ int err = 0;
if (mapping->nrpages) {
- retval = filemap_fdatawrite(mapping);
- if (retval == 0)
- retval = filemap_fdatawait(mapping);
+ err = filemap_fdatawrite(mapping);
+ /*
+ * Even if the above returned error, the pages may be
+ * written partially (e.g. -ENOSPC), so we wait for it.
+ * But the -EIO is special case, it may indicate the worst
+ * thing (e.g. bug) happened, so we avoid waiting for it.
+ */
+ if (err != -EIO) {
+ int err2 = filemap_fdatawait(mapping);
+ if (!err)
+ err = err2;
+ }
}
- return retval;
+ return err;
}
+EXPORT_SYMBOL(filemap_write_and_wait);
int filemap_write_and_wait_range(struct address_space *mapping,
loff_t lstart, loff_t lend)
{
- int retval = 0;
+ int err = 0;
if (mapping->nrpages) {
- retval = __filemap_fdatawrite_range(mapping, lstart, lend,
- WB_SYNC_ALL);
- if (retval == 0)
- retval = wait_on_page_writeback_range(mapping,
- lstart >> PAGE_CACHE_SHIFT,
- lend >> PAGE_CACHE_SHIFT);
+ err = __filemap_fdatawrite_range(mapping, lstart, lend,
+ WB_SYNC_ALL);
+ /* See comment of filemap_write_and_wait() */
+ if (err != -EIO) {
+ int err2 = wait_on_page_writeback_range(mapping,
+ lstart >> PAGE_CACHE_SHIFT,
+ lend >> PAGE_CACHE_SHIFT);
+ if (!err)
+ err = err2;
+ }
}
- return retval;
+ return err;
}
/*
* This function does not add the page to the LRU. The caller must do that.
*/
int add_to_page_cache(struct page *page, struct address_space *mapping,
- pgoff_t offset, int gfp_mask)
+ pgoff_t offset, gfp_t gfp_mask)
{
int error = radix_tree_preload(gfp_mask & ~__GFP_HIGHMEM);
EXPORT_SYMBOL(add_to_page_cache);
int add_to_page_cache_lru(struct page *page, struct address_space *mapping,
- pgoff_t offset, int gfp_mask)
+ pgoff_t offset, gfp_t gfp_mask)
{
int ret = add_to_page_cache(page, mapping, offset, gfp_mask);
if (ret == 0)
/**
* find_lock_page - locate, pin and lock a pagecache page
*
- * @mapping - the address_space to search
- * @offset - the page index
+ * @mapping: the address_space to search
+ * @offset: the page index
*
* Locates the desired pagecache page, locks it, increments its reference
* count and returns its address.
page_cache_get(page);
if (TestSetPageLocked(page)) {
read_unlock_irq(&mapping->tree_lock);
- lock_page(page);
+ __lock_page(page);
read_lock_irq(&mapping->tree_lock);
/* Has the page been truncated while we slept? */
- if (page->mapping != mapping || page->index != offset) {
+ if (unlikely(page->mapping != mapping ||
+ page->index != offset)) {
unlock_page(page);
page_cache_release(page);
goto repeat;
/**
* find_or_create_page - locate or add a pagecache page
*
- * @mapping - the page's address_space
- * @index - the page's index into the mapping
- * @gfp_mask - page allocation mode
+ * @mapping: the page's address_space
+ * @index: the page's index into the mapping
+ * @gfp_mask: page allocation mode
*
* Locates a page in the pagecache. If the page is not present, a new page
* is allocated using @gfp_mask and is added to the pagecache and to the VM's
* memory exhaustion.
*/
struct page *find_or_create_page(struct address_space *mapping,
- unsigned long index, unsigned int gfp_mask)
+ unsigned long index, gfp_t gfp_mask)
{
struct page *page, *cached_page = NULL;
int err;
grab_cache_page_nowait(struct address_space *mapping, unsigned long index)
{
struct page *page = find_get_page(mapping, index);
- unsigned int gfp_mask;
+ gfp_t gfp_mask;
if (page) {
if (!TestSetPageLocked(page))
/* Start the actual read. The read will unlock the page. */
error = mapping->a_ops->readpage(filp, page);
- if (unlikely(error))
+ if (unlikely(error)) {
+ if (error == AOP_TRUNCATED_PAGE) {
+ page_cache_release(page);
+ goto find_page;
+ }
goto readpage_error;
+ }
if (!PageUptodate(page)) {
lock_page(page);
if (pos < size) {
retval = generic_file_direct_IO(READ, iocb,
iov, pos, nr_segs);
- if (retval >= 0 && !is_sync_kiocb(iocb))
+ if (retval > 0 && !is_sync_kiocb(iocb))
retval = -EIOCBQUEUED;
if (retval > 0)
*ppos = pos + retval;
desc.error = 0;
do_generic_file_read(filp,ppos,&desc,file_read_actor);
retval += desc.written;
- if (!retval) {
- retval = desc.error;
+ if (desc.error) {
+ retval = retval ?: desc.error;
break;
}
}
{
struct address_space *mapping = file->f_mapping;
struct page *page;
- int error;
+ int ret;
- page = page_cache_alloc_cold(mapping);
- if (!page)
- return -ENOMEM;
+ do {
+ page = page_cache_alloc_cold(mapping);
+ if (!page)
+ return -ENOMEM;
+
+ ret = add_to_page_cache_lru(page, mapping, offset, GFP_KERNEL);
+ if (ret == 0)
+ ret = mapping->a_ops->readpage(file, page);
+ else if (ret == -EEXIST)
+ ret = 0; /* losing race to add is OK */
- error = add_to_page_cache_lru(page, mapping, offset, GFP_KERNEL);
- if (!error) {
- error = mapping->a_ops->readpage(file, page);
page_cache_release(page);
- return error;
- }
- /*
- * We arrive here in the unlikely event that someone
- * raced with us and added our page to the cache first
- * or we are out of memory for radix-tree nodes.
- */
- page_cache_release(page);
- return error == -EEXIST ? 0 : error;
+ } while (ret == AOP_TRUNCATED_PAGE);
+
+ return ret;
}
#define MMAP_LOTSAMISS (100)
goto success;
}
- if (!mapping->a_ops->readpage(file, page)) {
+ error = mapping->a_ops->readpage(file, page);
+ if (!error) {
wait_on_page_locked(page);
if (PageUptodate(page))
goto success;
+ } else if (error == AOP_TRUNCATED_PAGE) {
+ page_cache_release(page);
+ goto retry_find;
}
/*
goto success;
}
ClearPageError(page);
- if (!mapping->a_ops->readpage(file, page)) {
+ error = mapping->a_ops->readpage(file, page);
+ if (!error) {
wait_on_page_locked(page);
if (PageUptodate(page))
goto success;
+ } else if (error == AOP_TRUNCATED_PAGE) {
+ page_cache_release(page);
+ goto retry_find;
}
/*
* Ok, found a page in the page cache, now we need to check
* that it's up-to-date.
*/
- if (!PageUptodate(page))
+ if (!PageUptodate(page)) {
+ if (nonblock) {
+ page_cache_release(page);
+ return NULL;
+ }
goto page_not_uptodate;
+ }
success:
/*
goto success;
}
- if (!mapping->a_ops->readpage(file, page)) {
+ error = mapping->a_ops->readpage(file, page);
+ if (!error) {
wait_on_page_locked(page);
if (PageUptodate(page))
goto success;
+ } else if (error == AOP_TRUNCATED_PAGE) {
+ page_cache_release(page);
+ goto retry_find;
}
/*
}
ClearPageError(page);
- if (!mapping->a_ops->readpage(file, page)) {
+ error = mapping->a_ops->readpage(file, page);
+ if (!error) {
wait_on_page_locked(page);
if (PageUptodate(page))
goto success;
+ } else if (error == AOP_TRUNCATED_PAGE) {
+ page_cache_release(page);
+ goto retry_find;
}
/*
return -EINVAL;
page = filemap_getpage(file, pgoff, nonblock);
+
+ /* XXX: This is wrong, a filesystem I/O error may have happened. Fix that as
+ * done in shmem_populate calling shmem_getpage */
if (!page && !nonblock)
return -ENOMEM;
+
if (page) {
err = install_page(mm, vma, addr, page, prot);
if (err) {
page_cache_release(page);
return err;
}
- } else {
+ } else if (vma->vm_flags & VM_NONLINEAR) {
+ /* No page was found just because we can't read it in now (being
+ * here implies nonblock != 0), but the page may exist, so set
+ * the PTE to fault it in later. */
err = install_file_pte(mm, vma, addr, pgoff, prot);
if (err)
return err;
return 0;
}
+EXPORT_SYMBOL(filemap_populate);
struct vm_operations_struct generic_file_vm_ops = {
.nopage = filemap_nopage,
vma->vm_ops = &generic_file_vm_ops;
return 0;
}
-EXPORT_SYMBOL(filemap_populate);
/*
* This is for filesystems which do not implement ->writepage.
}
EXPORT_SYMBOL(remove_suid);
-/*
- * Copy as much as we can into the page and return the number of bytes which
- * were sucessfully copied. If a fault is encountered then clear the page
- * out to (offset+bytes) and return the number of bytes which were copied.
- */
-static inline size_t
-filemap_copy_from_user(struct page *page, unsigned long offset,
- const char __user *buf, unsigned bytes)
-{
- char *kaddr;
- int left;
-
- kaddr = kmap_atomic(page, KM_USER0);
- left = __copy_from_user_inatomic(kaddr + offset, buf, bytes);
- kunmap_atomic(kaddr, KM_USER0);
-
- if (left != 0) {
- /* Do it the slow way */
- kaddr = kmap(page);
- left = __copy_from_user(kaddr + offset, buf, bytes);
- kunmap(page);
- }
- return bytes - left;
-}
-
-static size_t
+size_t
__filemap_copy_from_user_iovec(char *vaddr,
const struct iovec *iov, size_t base, size_t bytes)
{
}
/*
- * This has the same sideeffects and return value as filemap_copy_from_user().
- * The difference is that on a fault we need to memset the remainder of the
- * page (out to offset+bytes), to emulate filemap_copy_from_user()'s
- * single-segment behaviour.
- */
-static inline size_t
-filemap_copy_from_user_iovec(struct page *page, unsigned long offset,
- const struct iovec *iov, size_t base, size_t bytes)
-{
- char *kaddr;
- size_t copied;
-
- kaddr = kmap_atomic(page, KM_USER0);
- copied = __filemap_copy_from_user_iovec(kaddr + offset, iov,
- base, bytes);
- kunmap_atomic(kaddr, KM_USER0);
- if (copied != bytes) {
- kaddr = kmap(page);
- copied = __filemap_copy_from_user_iovec(kaddr + offset, iov,
- base, bytes);
- kunmap(page);
- }
- return copied;
-}
-
-static inline void
-filemap_set_next_iovec(const struct iovec **iovp, size_t *basep, size_t bytes)
-{
- const struct iovec *iov = *iovp;
- size_t base = *basep;
-
- while (bytes) {
- int copy = min(bytes, iov->iov_len - base);
-
- bytes -= copy;
- base += copy;
- if (iov->iov_len == base) {
- iov++;
- base = 0;
- }
- }
- *iovp = iov;
- *basep = base;
-}
-
-/*
* Performs necessary checks before doing a write
*
* Can adjust writing position aor amount of bytes to write.
if (unlikely(*pos < 0))
return -EINVAL;
- if (unlikely(file->f_error)) {
- int err = file->f_error;
- file->f_error = 0;
- return err;
- }
-
if (!isblk) {
/* FIXME: this is for backwards compatibility with 2.4 */
if (file->f_flags & O_APPEND)
/*
* Sync the fs metadata but not the minor inode changes and
* of course not the data as we did direct DMA for the IO.
- * i_sem is held, which protects generic_osync_inode() from
+ * i_mutex is held, which protects generic_osync_inode() from
* livelocking.
*/
- if (written >= 0 && file->f_flags & O_SYNC)
- generic_osync_inode(inode, mapping, OSYNC_METADATA);
+ if (written >= 0 && ((file->f_flags & O_SYNC) || IS_SYNC(inode))) {
+ int err = generic_osync_inode(inode, mapping, OSYNC_METADATA);
+ if (err < 0)
+ written = err;
+ }
if (written == count && !is_sync_kiocb(iocb))
written = -EIOCBQUEUED;
return written;
buf = iov->iov_base + written;
else {
filemap_set_next_iovec(&cur_iov, &iov_base, written);
- buf = iov->iov_base + iov_base;
+ buf = cur_iov->iov_base + iov_base;
}
do {
unsigned long index;
unsigned long offset;
+ unsigned long maxlen;
size_t copied;
offset = (pos & (PAGE_CACHE_SIZE -1)); /* Within page */
* same page as we're writing to, without it being marked
* up-to-date.
*/
- fault_in_pages_readable(buf, bytes);
+ maxlen = cur_iov->iov_len - iov_base;
+ if (maxlen > bytes)
+ maxlen = bytes;
+ fault_in_pages_readable(buf, maxlen);
page = __grab_cache_page(mapping,index,&cached_page,&lru_pvec);
if (!page) {
status = a_ops->prepare_write(file, page, offset, offset+bytes);
if (unlikely(status)) {
loff_t isize = i_size_read(inode);
+
+ if (status != AOP_TRUNCATED_PAGE)
+ unlock_page(page);
+ page_cache_release(page);
+ if (status == AOP_TRUNCATED_PAGE)
+ continue;
/*
* prepare_write() may have instantiated a few blocks
* outside i_size. Trim these off again.
*/
- unlock_page(page);
- page_cache_release(page);
if (pos + bytes > isize)
vmtruncate(inode, isize);
break;
cur_iov, iov_base, bytes);
flush_dcache_page(page);
status = a_ops->commit_write(file, page, offset, offset+bytes);
+ if (status == AOP_TRUNCATED_PAGE) {
+ page_cache_release(page);
+ continue;
+ }
if (likely(copied > 0)) {
if (!status)
status = copied;
count -= status;
pos += status;
buf += status;
- if (unlikely(nr_segs > 1))
+ if (unlikely(nr_segs > 1)) {
filemap_set_next_iovec(&cur_iov,
&iov_base, status);
+ if (count)
+ buf = cur_iov->iov_base +
+ iov_base;
+ } else {
+ iov_base += status;
+ }
}
}
if (unlikely(copied != bytes))
}
EXPORT_SYMBOL(generic_file_buffered_write);
-ssize_t
+static ssize_t
__generic_file_aio_write_nolock(struct kiocb *iocb, const struct iovec *iov,
unsigned long nr_segs, loff_t *ppos)
{
if (err)
goto out;
- inode_update_time(inode, 1);
+ file_update_time(file);
/* coalesce the iovecs and go direct-to-BIO for O_DIRECT */
if (unlikely(file->f_flags & O_DIRECT)) {
return ret;
}
-ssize_t
+static ssize_t
__generic_file_write_nolock(struct file *file, const struct iovec *iov,
unsigned long nr_segs, loff_t *ppos)
{
BUG_ON(iocb->ki_pos != pos);
- down(&inode->i_sem);
+ mutex_lock(&inode->i_mutex);
ret = __generic_file_aio_write_nolock(iocb, &local_iov, 1,
&iocb->ki_pos);
- up(&inode->i_sem);
+ mutex_unlock(&inode->i_mutex);
if (ret > 0 && ((file->f_flags & O_SYNC) || IS_SYNC(inode))) {
ssize_t err;
struct iovec local_iov = { .iov_base = (void __user *)buf,
.iov_len = count };
- down(&inode->i_sem);
+ mutex_lock(&inode->i_mutex);
ret = __generic_file_write_nolock(file, &local_iov, 1, ppos);
- up(&inode->i_sem);
+ mutex_unlock(&inode->i_mutex);
if (ret > 0 && ((file->f_flags & O_SYNC) || IS_SYNC(inode))) {
ssize_t err;
struct inode *inode = mapping->host;
ssize_t ret;
- down(&inode->i_sem);
+ mutex_lock(&inode->i_mutex);
ret = __generic_file_write_nolock(file, iov, nr_segs, ppos);
- up(&inode->i_sem);
+ mutex_unlock(&inode->i_mutex);
if (ret > 0 && ((file->f_flags & O_SYNC) || IS_SYNC(inode))) {
int err;
EXPORT_SYMBOL(generic_file_writev);
/*
- * Called under i_sem for writes to S_ISREG files. Returns -EIO if something
+ * Called under i_mutex for writes to S_ISREG files. Returns -EIO if something
* went wrong during pagecache shootdown.
*/
-ssize_t
+static ssize_t
generic_file_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
loff_t offset, unsigned long nr_segs)
{
}
return retval;
}
-EXPORT_SYMBOL_GPL(generic_file_direct_IO);
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff