* ->mmap_sem
* ->lock_page (access_process_vm)
*
- * ->mmap_sem
- * ->i_mutex (msync)
+ * ->i_mutex (generic_file_buffered_write)
+ * ->mmap_sem (fault_in_pages_readable->do_page_fault)
*
* ->i_mutex
* ->i_alloc_sem (various)
page->mapping = NULL;
mapping->nrpages--;
__dec_zone_page_state(page, NR_FILE_PAGES);
+ BUG_ON(page_mapped(page));
}
void remove_from_page_cache(struct page *page)
* @pos: beginning offset in pages to write
* @count: number of bytes to write
*
- * Note: Holding i_mutex 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.
*/
}
#ifdef CONFIG_NUMA
-struct page *page_cache_alloc(struct address_space *x)
-{
- if (cpuset_do_page_mem_spread()) {
- int n = cpuset_mem_spread_node();
- return alloc_pages_node(n, mapping_gfp_mask(x), 0);
- }
- return alloc_pages(mapping_gfp_mask(x), 0);
-}
-EXPORT_SYMBOL(page_cache_alloc);
-
-struct page *page_cache_alloc_cold(struct address_space *x)
+struct page *__page_cache_alloc(gfp_t gfp)
{
if (cpuset_do_page_mem_spread()) {
int n = cpuset_mem_spread_node();
- return alloc_pages_node(n, mapping_gfp_mask(x)|__GFP_COLD, 0);
+ return alloc_pages_node(n, gfp, 0);
}
- return alloc_pages(mapping_gfp_mask(x)|__GFP_COLD, 0);
+ return alloc_pages(gfp, 0);
}
-EXPORT_SYMBOL(page_cache_alloc_cold);
+EXPORT_SYMBOL(__page_cache_alloc);
#endif
static int __sleep_on_page_lock(void *word)
EXPORT_SYMBOL(find_get_page);
/**
- * find_trylock_page - find and lock a page
- * @mapping: the address_space to search
- * @offset: the page index
- *
- * Same as find_get_page(), but trylock it instead of incrementing the count.
- */
-struct page *find_trylock_page(struct address_space *mapping, unsigned long offset)
-{
- struct page *page;
-
- read_lock_irq(&mapping->tree_lock);
- page = radix_tree_lookup(&mapping->page_tree, offset);
- if (page && TestSetPageLocked(page))
- page = NULL;
- read_unlock_irq(&mapping->tree_lock);
- return page;
-}
-EXPORT_SYMBOL(find_trylock_page);
-
-/**
* find_lock_page - locate, pin and lock a pagecache page
* @mapping: the address_space to search
* @offset: the page index
page = find_lock_page(mapping, index);
if (!page) {
if (!cached_page) {
- cached_page = alloc_page(gfp_mask);
+ cached_page =
+ __page_cache_alloc(gfp_mask);
if (!cached_page)
return NULL;
}
read_unlock_irq(&mapping->tree_lock);
return i;
}
+EXPORT_SYMBOL(find_get_pages_contig);
/**
* find_get_pages_tag - find and return pages that match @tag
read_unlock_irq(&mapping->tree_lock);
return ret;
}
+EXPORT_SYMBOL(find_get_pages_tag);
/**
* grab_cache_page_nowait - returns locked page at given index in given cache
* @mapping: target address_space
* @index: the page index
*
- * Same as grab_cache_page, but do not wait if the page is unavailable.
+ * Same as grab_cache_page(), but do not wait if the page is unavailable.
* This is intended for speculative data generators, where the data can
* be regenerated if the page couldn't be grabbed. This routine should
* be safe to call while holding the lock for another page.
grab_cache_page_nowait(struct address_space *mapping, unsigned long index)
{
struct page *page = find_get_page(mapping, index);
- gfp_t gfp_mask;
if (page) {
if (!TestSetPageLocked(page))
page_cache_release(page);
return NULL;
}
- gfp_mask = mapping_gfp_mask(mapping) & ~__GFP_FS;
- page = alloc_pages(gfp_mask, 0);
- if (page && add_to_page_cache_lru(page, mapping, index, gfp_mask)) {
+ page = __page_cache_alloc(mapping_gfp_mask(mapping) & ~__GFP_FS);
+ if (page && add_to_page_cache_lru(page, mapping, index, GFP_KERNEL)) {
page_cache_release(page);
page = NULL;
}
{
struct inode *inode = mapping->host;
unsigned long index;
- unsigned long end_index;
unsigned long offset;
unsigned long last_index;
unsigned long next_index;
unsigned long prev_index;
- loff_t isize;
+ unsigned int prev_offset;
struct page *cached_page;
int error;
struct file_ra_state ra = *_ra;
cached_page = NULL;
index = *ppos >> PAGE_CACHE_SHIFT;
next_index = index;
- prev_index = ra.prev_page;
+ prev_index = ra.prev_index;
+ prev_offset = ra.prev_offset;
last_index = (*ppos + desc->count + PAGE_CACHE_SIZE-1) >> PAGE_CACHE_SHIFT;
offset = *ppos & ~PAGE_CACHE_MASK;
- isize = i_size_read(inode);
- if (!isize)
- goto out;
-
- end_index = (isize - 1) >> PAGE_CACHE_SHIFT;
for (;;) {
struct page *page;
+ unsigned long end_index;
+ loff_t isize;
unsigned long nr, ret;
+ cond_resched();
+find_page:
+ page = find_get_page(mapping, index);
+ if (!page) {
+ page_cache_sync_readahead(mapping,
+ &ra, filp,
+ index, last_index - index);
+ page = find_get_page(mapping, index);
+ if (unlikely(page == NULL))
+ goto no_cached_page;
+ }
+ if (PageReadahead(page)) {
+ page_cache_async_readahead(mapping,
+ &ra, filp, page,
+ index, last_index - index);
+ }
+ if (!PageUptodate(page))
+ goto page_not_up_to_date;
+page_ok:
+ /*
+ * i_size must be checked after we know the page is Uptodate.
+ *
+ * Checking i_size after the check allows us to calculate
+ * the correct value for "nr", which means the zero-filled
+ * part of the page is not copied back to userspace (unless
+ * another truncate extends the file - this is desired though).
+ */
+
+ isize = i_size_read(inode);
+ end_index = (isize - 1) >> PAGE_CACHE_SHIFT;
+ if (unlikely(!isize || index > end_index)) {
+ page_cache_release(page);
+ goto out;
+ }
+
/* nr is the maximum number of bytes to copy from this page */
nr = PAGE_CACHE_SIZE;
- if (index >= end_index) {
- if (index > end_index)
- goto out;
+ if (index == end_index) {
nr = ((isize - 1) & ~PAGE_CACHE_MASK) + 1;
if (nr <= offset) {
+ page_cache_release(page);
goto out;
}
}
nr = nr - offset;
- cond_resched();
- if (index == next_index)
- next_index = page_cache_readahead(mapping, &ra, filp,
- index, last_index - index);
-
-find_page:
- page = find_get_page(mapping, index);
- if (unlikely(page == NULL)) {
- handle_ra_miss(mapping, &ra, index);
- goto no_cached_page;
- }
- if (!PageUptodate(page))
- goto page_not_up_to_date;
-page_ok:
-
/* If users can be writing to this page using arbitrary
* virtual addresses, take care about potential aliasing
* before reading the page on the kernel side.
flush_dcache_page(page);
/*
- * When (part of) the same page is read multiple times
- * in succession, only mark it as accessed the first time.
+ * When a sequential read accesses a page several times,
+ * only mark it as accessed the first time.
*/
- if (prev_index != index)
+ if (prev_index != index || offset != prev_offset)
mark_page_accessed(page);
prev_index = index;
offset += ret;
index += offset >> PAGE_CACHE_SHIFT;
offset &= ~PAGE_CACHE_MASK;
+ prev_offset = offset;
+ ra.prev_offset = offset;
page_cache_release(page);
if (ret == nr && desc->count)
unlock_page(page);
}
- /*
- * i_size must be checked after we have done ->readpage.
- *
- * Checking i_size after the readpage allows us to calculate
- * the correct value for "nr", which means the zero-filled
- * part of the page is not copied back to userspace (unless
- * another truncate extends the file - this is desired though).
- */
- isize = i_size_read(inode);
- end_index = (isize - 1) >> PAGE_CACHE_SHIFT;
- if (unlikely(!isize || index > end_index)) {
- page_cache_release(page);
- goto out;
- }
-
- /* nr is the maximum number of bytes to copy from this page */
- nr = PAGE_CACHE_SIZE;
- if (index == end_index) {
- nr = ((isize - 1) & ~PAGE_CACHE_MASK) + 1;
- if (nr <= offset) {
- page_cache_release(page);
- goto out;
- }
- }
- nr = nr - offset;
goto page_ok;
readpage_error:
out:
*_ra = ra;
+ _ra->prev_index = prev_index;
*ppos = ((loff_t) index << PAGE_CACHE_SHIFT) + offset;
if (cached_page)
return size;
}
-/**
- * __generic_file_aio_read - generic filesystem read routine
- * @iocb: kernel I/O control block
+/*
+ * Performs necessary checks before doing a write
* @iov: io vector request
* @nr_segs: number of segments in the iovec
- * @ppos: current file position
+ * @count: number of bytes to write
+ * @access_flags: type of access: %VERIFY_READ or %VERIFY_WRITE
*
- * This is the "read()" routine for all filesystems
- * that can use the page cache directly.
+ * Adjust number of segments and amount of bytes to write (nr_segs should be
+ * properly initialized first). Returns appropriate error code that caller
+ * should return or zero in case that write should be allowed.
*/
-ssize_t
-__generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov,
- unsigned long nr_segs, loff_t *ppos)
+int generic_segment_checks(const struct iovec *iov,
+ unsigned long *nr_segs, size_t *count, int access_flags)
{
- struct file *filp = iocb->ki_filp;
- ssize_t retval;
- unsigned long seg;
- size_t count;
-
- count = 0;
- for (seg = 0; seg < nr_segs; seg++) {
+ unsigned long seg;
+ size_t cnt = 0;
+ for (seg = 0; seg < *nr_segs; seg++) {
const struct iovec *iv = &iov[seg];
/*
* If any segment has a negative length, or the cumulative
* length ever wraps negative then return -EINVAL.
*/
- count += iv->iov_len;
- if (unlikely((ssize_t)(count|iv->iov_len) < 0))
+ cnt += iv->iov_len;
+ if (unlikely((ssize_t)(cnt|iv->iov_len) < 0))
return -EINVAL;
- if (access_ok(VERIFY_WRITE, iv->iov_base, iv->iov_len))
+ if (access_ok(access_flags, iv->iov_base, iv->iov_len))
continue;
if (seg == 0)
return -EFAULT;
- nr_segs = seg;
- count -= iv->iov_len; /* This segment is no good */
+ *nr_segs = seg;
+ cnt -= iv->iov_len; /* This segment is no good */
break;
}
+ *count = cnt;
+ return 0;
+}
+EXPORT_SYMBOL(generic_segment_checks);
+
+/**
+ * generic_file_aio_read - generic filesystem read routine
+ * @iocb: kernel I/O control block
+ * @iov: io vector request
+ * @nr_segs: number of segments in the iovec
+ * @pos: current file position
+ *
+ * This is the "read()" routine for all filesystems
+ * that can use the page cache directly.
+ */
+ssize_t
+generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov,
+ unsigned long nr_segs, loff_t pos)
+{
+ struct file *filp = iocb->ki_filp;
+ ssize_t retval;
+ unsigned long seg;
+ size_t count;
+ loff_t *ppos = &iocb->ki_pos;
+
+ count = 0;
+ retval = generic_segment_checks(iov, &nr_segs, &count, VERIFY_WRITE);
+ if (retval)
+ return retval;
/* coalesce the iovecs and go direct-to-BIO for O_DIRECT */
if (filp->f_flags & O_DIRECT) {
- loff_t pos = *ppos, size;
+ loff_t size;
struct address_space *mapping;
struct inode *inode;
if (pos < size) {
retval = generic_file_direct_IO(READ, iocb,
iov, pos, nr_segs);
- if (retval > 0 && !is_sync_kiocb(iocb))
- retval = -EIOCBQUEUED;
if (retval > 0)
*ppos = pos + retval;
}
- file_accessed(filp);
- goto out;
+ if (likely(retval != 0)) {
+ file_accessed(filp);
+ goto out;
+ }
}
retval = 0;
retval = retval ?: desc.error;
break;
}
+ if (desc.count > 0)
+ break;
}
}
out:
return retval;
}
-EXPORT_SYMBOL(__generic_file_aio_read);
-
-ssize_t
-generic_file_aio_read(struct kiocb *iocb, char __user *buf, size_t count, loff_t pos)
-{
- struct iovec local_iov = { .iov_base = buf, .iov_len = count };
-
- BUG_ON(iocb->ki_pos != pos);
- return __generic_file_aio_read(iocb, &local_iov, 1, &iocb->ki_pos);
-}
EXPORT_SYMBOL(generic_file_aio_read);
-ssize_t
-generic_file_read(struct file *filp, char __user *buf, size_t count, loff_t *ppos)
-{
- struct iovec local_iov = { .iov_base = buf, .iov_len = count };
- struct kiocb kiocb;
- ssize_t ret;
-
- init_sync_kiocb(&kiocb, filp);
- ret = __generic_file_aio_read(&kiocb, &local_iov, 1, ppos);
- if (-EIOCBQUEUED == ret)
- ret = wait_on_sync_kiocb(&kiocb);
- return ret;
-}
-EXPORT_SYMBOL(generic_file_read);
-
int file_send_actor(read_descriptor_t * desc, struct page *page, unsigned long offset, unsigned long size)
{
ssize_t written;
return written;
}
-ssize_t generic_file_sendfile(struct file *in_file, loff_t *ppos,
- size_t count, read_actor_t actor, void *target)
-{
- read_descriptor_t desc;
-
- if (!count)
- return 0;
-
- desc.written = 0;
- desc.count = count;
- desc.arg.data = target;
- desc.error = 0;
-
- do_generic_file_read(in_file, ppos, &desc, actor);
- if (desc.written)
- return desc.written;
- return desc.error;
-}
-EXPORT_SYMBOL(generic_file_sendfile);
-
static ssize_t
do_readahead(struct address_space *mapping, struct file *filp,
unsigned long index, unsigned long nr)
#define MMAP_LOTSAMISS (100)
/**
- * filemap_nopage - read in file data for page fault handling
- * @area: the applicable vm_area
- * @address: target address to read in
- * @type: returned with VM_FAULT_{MINOR,MAJOR} if not %NULL
+ * filemap_fault - read in file data for page fault handling
+ * @vma: vma in which the fault was taken
+ * @vmf: struct vm_fault containing details of the fault
*
- * filemap_nopage() is invoked via the vma operations vector for a
+ * filemap_fault() is invoked via the vma operations vector for a
* mapped memory region to read in file data during a page fault.
*
* The goto's are kind of ugly, but this streamlines the normal case of having
* it in the page cache, and handles the special cases reasonably without
* having a lot of duplicated code.
*/
-struct page *filemap_nopage(struct vm_area_struct *area,
- unsigned long address, int *type)
+int filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
{
int error;
- struct file *file = area->vm_file;
+ struct file *file = vma->vm_file;
struct address_space *mapping = file->f_mapping;
struct file_ra_state *ra = &file->f_ra;
struct inode *inode = mapping->host;
struct page *page;
- unsigned long size, pgoff;
- int did_readaround = 0, majmin = VM_FAULT_MINOR;
-
- pgoff = ((address-area->vm_start) >> PAGE_CACHE_SHIFT) + area->vm_pgoff;
+ unsigned long size;
+ int did_readaround = 0;
+ int ret = 0;
-retry_all:
size = (i_size_read(inode) + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
- if (pgoff >= size)
+ if (vmf->pgoff >= size)
goto outside_data_content;
/* If we don't want any read-ahead, don't bother */
- if (VM_RandomReadHint(area))
+ if (VM_RandomReadHint(vma))
goto no_cached_page;
/*
- * The readahead code wants to be told about each and every page
- * so it can build and shrink its windows appropriately
- *
- * For sequential accesses, we use the generic readahead logic.
- */
- if (VM_SequentialReadHint(area))
- page_cache_readahead(mapping, ra, file, pgoff, 1);
-
- /*
* Do we have something in the page cache already?
*/
retry_find:
- page = find_get_page(mapping, pgoff);
+ page = find_lock_page(mapping, vmf->pgoff);
+ /*
+ * For sequential accesses, we use the generic readahead logic.
+ */
+ if (VM_SequentialReadHint(vma)) {
+ if (!page) {
+ page_cache_sync_readahead(mapping, ra, file,
+ vmf->pgoff, 1);
+ page = find_lock_page(mapping, vmf->pgoff);
+ if (!page)
+ goto no_cached_page;
+ }
+ if (PageReadahead(page)) {
+ page_cache_async_readahead(mapping, ra, file, page,
+ vmf->pgoff, 1);
+ }
+ }
+
if (!page) {
unsigned long ra_pages;
- if (VM_SequentialReadHint(area)) {
- handle_ra_miss(mapping, ra, pgoff);
- goto no_cached_page;
- }
ra->mmap_miss++;
/*
* check did_readaround, as this is an inner loop.
*/
if (!did_readaround) {
- majmin = VM_FAULT_MAJOR;
+ ret = VM_FAULT_MAJOR;
count_vm_event(PGMAJFAULT);
}
did_readaround = 1;
if (ra_pages) {
pgoff_t start = 0;
- if (pgoff > ra_pages / 2)
- start = pgoff - ra_pages / 2;
+ if (vmf->pgoff > ra_pages / 2)
+ start = vmf->pgoff - ra_pages / 2;
do_page_cache_readahead(mapping, file, start, ra_pages);
}
- page = find_get_page(mapping, pgoff);
+ page = find_lock_page(mapping, vmf->pgoff);
if (!page)
goto no_cached_page;
}
ra->mmap_hit++;
/*
- * Ok, found a page in the page cache, now we need to check
- * that it's up-to-date.
+ * We have a locked page in the page cache, now we need to check
+ * that it's up-to-date. If not, it is going to be due to an error.
*/
- if (!PageUptodate(page))
+ if (unlikely(!PageUptodate(page)))
goto page_not_uptodate;
-success:
+ /* Must recheck i_size under page lock */
+ size = (i_size_read(inode) + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
+ if (unlikely(vmf->pgoff >= size)) {
+ unlock_page(page);
+ goto outside_data_content;
+ }
+
/*
* Found the page and have a reference on it.
*/
mark_page_accessed(page);
- if (type)
- *type = majmin;
- return page;
+ ra->prev_index = page->index;
+ vmf->page = page;
+ return ret | VM_FAULT_LOCKED;
outside_data_content:
/*
* An external ptracer can access pages that normally aren't
* accessible..
*/
- if (area->vm_mm == current->mm)
- return NOPAGE_SIGBUS;
+ if (vma->vm_mm == current->mm)
+ return VM_FAULT_SIGBUS;
+
/* Fall through to the non-read-ahead case */
no_cached_page:
/*
* We're only likely to ever get here if MADV_RANDOM is in
* effect.
*/
- error = page_cache_read(file, pgoff);
- grab_swap_token();
+ error = page_cache_read(file, vmf->pgoff);
/*
* The page we want has now been added to the page cache.
* to schedule I/O.
*/
if (error == -ENOMEM)
- return NOPAGE_OOM;
- return NOPAGE_SIGBUS;
+ return VM_FAULT_OOM;
+ return VM_FAULT_SIGBUS;
page_not_uptodate:
+ /* IO error path */
if (!did_readaround) {
- majmin = VM_FAULT_MAJOR;
+ ret = VM_FAULT_MAJOR;
count_vm_event(PGMAJFAULT);
}
- lock_page(page);
-
- /* Did it get unhashed while we waited for it? */
- if (!page->mapping) {
- unlock_page(page);
- page_cache_release(page);
- goto retry_all;
- }
-
- /* Did somebody else get it up-to-date? */
- if (PageUptodate(page)) {
- unlock_page(page);
- goto success;
- }
-
- 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;
- }
/*
* Umm, take care of errors if the page isn't up-to-date.
* because there really aren't any performance issues here
* and we need to check for errors.
*/
- lock_page(page);
-
- /* Somebody truncated the page on us? */
- if (!page->mapping) {
- unlock_page(page);
- page_cache_release(page);
- goto retry_all;
- }
-
- /* Somebody else successfully read it in? */
- if (PageUptodate(page)) {
- unlock_page(page);
- goto success;
- }
ClearPageError(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;
- }
-
- /*
- * Things didn't work out. Return zero to tell the
- * mm layer so, possibly freeing the page cache page first.
- */
- shrink_readahead_size_eio(file, ra);
page_cache_release(page);
- return NOPAGE_SIGBUS;
-}
-EXPORT_SYMBOL(filemap_nopage);
-
-static struct page * filemap_getpage(struct file *file, unsigned long pgoff,
- int nonblock)
-{
- struct address_space *mapping = file->f_mapping;
- struct page *page;
- int error;
-
- /*
- * Do we have something in the page cache already?
- */
-retry_find:
- page = find_get_page(mapping, pgoff);
- if (!page) {
- if (nonblock)
- return NULL;
- goto no_cached_page;
- }
-
- /*
- * Ok, found a page in the page cache, now we need to check
- * that it's up-to-date.
- */
- if (!PageUptodate(page)) {
- if (nonblock) {
- page_cache_release(page);
- return NULL;
- }
- goto page_not_uptodate;
- }
-success:
- /*
- * Found the page and have a reference on it.
- */
- mark_page_accessed(page);
- return page;
-
-no_cached_page:
- error = page_cache_read(file, pgoff);
-
- /*
- * The page we want has now been added to the page cache.
- * In the unlikely event that someone removed it in the
- * meantime, we'll just come back here and read it again.
- */
- if (error >= 0)
+ if (!error || error == AOP_TRUNCATED_PAGE)
goto retry_find;
- /*
- * An error return from page_cache_read can result if the
- * system is low on memory, or a problem occurs while trying
- * to schedule I/O.
- */
- return NULL;
-
-page_not_uptodate:
- lock_page(page);
-
- /* Did it get truncated while we waited for it? */
- if (!page->mapping) {
- unlock_page(page);
- goto err;
- }
-
- /* Did somebody else get it up-to-date? */
- if (PageUptodate(page)) {
- unlock_page(page);
- goto success;
- }
-
- 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;
- }
-
- /*
- * Umm, take care of errors if the page isn't up-to-date.
- * Try to re-read it _once_. We do this synchronously,
- * because there really aren't any performance issues here
- * and we need to check for errors.
- */
- lock_page(page);
-
- /* Somebody truncated the page on us? */
- if (!page->mapping) {
- unlock_page(page);
- goto err;
- }
- /* Somebody else successfully read it in? */
- if (PageUptodate(page)) {
- unlock_page(page);
- goto success;
- }
-
- ClearPageError(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;
- }
-
- /*
- * Things didn't work out. Return zero to tell the
- * mm layer so, possibly freeing the page cache page first.
- */
-err:
- page_cache_release(page);
-
- return NULL;
-}
-
-int filemap_populate(struct vm_area_struct *vma, unsigned long addr,
- unsigned long len, pgprot_t prot, unsigned long pgoff,
- int nonblock)
-{
- struct file *file = vma->vm_file;
- struct address_space *mapping = file->f_mapping;
- struct inode *inode = mapping->host;
- unsigned long size;
- struct mm_struct *mm = vma->vm_mm;
- struct page *page;
- int err;
-
- if (!nonblock)
- force_page_cache_readahead(mapping, vma->vm_file,
- pgoff, len >> PAGE_CACHE_SHIFT);
-
-repeat:
- size = (i_size_read(inode) + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
- if (pgoff + (len >> PAGE_CACHE_SHIFT) > size)
- 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 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;
- }
-
- len -= PAGE_SIZE;
- addr += PAGE_SIZE;
- pgoff++;
- if (len)
- goto repeat;
-
- return 0;
+ /* Things didn't work out. Return zero to tell the mm layer so. */
+ shrink_readahead_size_eio(file, ra);
+ return VM_FAULT_SIGBUS;
}
-EXPORT_SYMBOL(filemap_populate);
+EXPORT_SYMBOL(filemap_fault);
struct vm_operations_struct generic_file_vm_ops = {
- .nopage = filemap_nopage,
- .populate = filemap_populate,
+ .fault = filemap_fault,
};
/* This is used for a general mmap of a disk file */
return -ENOEXEC;
file_accessed(file);
vma->vm_ops = &generic_file_vm_ops;
+ vma->vm_flags |= VM_CAN_NONLINEAR;
return 0;
}
EXPORT_SYMBOL(generic_file_mmap);
EXPORT_SYMBOL(generic_file_readonly_mmap);
-static inline struct page *__read_cache_page(struct address_space *mapping,
+static struct page *__read_cache_page(struct address_space *mapping,
unsigned long index,
int (*filler)(void *,struct page*),
void *data)
return page;
}
-/**
- * read_cache_page - read into page cache, fill it if needed
- * @mapping: the page's address_space
- * @index: the page index
- * @filler: function to perform the read
- * @data: destination for read data
- *
- * Read into the page cache. If a page already exists,
- * and PageUptodate() is not set, try to fill the page.
+/*
+ * Same as read_cache_page, but don't wait for page to become unlocked
+ * after submitting it to the filler.
*/
-struct page *read_cache_page(struct address_space *mapping,
+struct page *read_cache_page_async(struct address_space *mapping,
unsigned long index,
int (*filler)(void *,struct page*),
void *data)
retry:
page = __read_cache_page(mapping, index, filler, data);
if (IS_ERR(page))
- goto out;
- mark_page_accessed(page);
+ return page;
if (PageUptodate(page))
goto out;
err = filler(data, page);
if (err < 0) {
page_cache_release(page);
- page = ERR_PTR(err);
+ return ERR_PTR(err);
+ }
+out:
+ mark_page_accessed(page);
+ return page;
+}
+EXPORT_SYMBOL(read_cache_page_async);
+
+/**
+ * read_cache_page - read into page cache, fill it if needed
+ * @mapping: the page's address_space
+ * @index: the page index
+ * @filler: function to perform the read
+ * @data: destination for read data
+ *
+ * Read into the page cache. If a page already exists, and PageUptodate() is
+ * not set, try to fill the page then wait for it to become unlocked.
+ *
+ * If the page does not get brought uptodate, return -EIO.
+ */
+struct page *read_cache_page(struct address_space *mapping,
+ unsigned long index,
+ int (*filler)(void *,struct page*),
+ void *data)
+{
+ struct page *page;
+
+ page = read_cache_page_async(mapping, index, filler, data);
+ if (IS_ERR(page))
+ goto out;
+ wait_on_page_locked(page);
+ if (!PageUptodate(page)) {
+ page_cache_release(page);
+ page = ERR_PTR(-EIO);
}
out:
return page;
* if suid or (sgid and xgrp)
* remove privs
*/
-int remove_suid(struct dentry *dentry)
+int should_remove_suid(struct dentry *dentry)
{
mode_t mode = dentry->d_inode->i_mode;
int kill = 0;
- int result = 0;
/* suid always must be killed */
if (unlikely(mode & S_ISUID))
if (unlikely((mode & S_ISGID) && (mode & S_IXGRP)))
kill |= ATTR_KILL_SGID;
- if (unlikely(kill && !capable(CAP_FSETID))) {
- struct iattr newattrs;
+ if (unlikely(kill && !capable(CAP_FSETID)))
+ return kill;
- newattrs.ia_valid = ATTR_FORCE | kill;
- result = notify_change(dentry, &newattrs);
- }
- return result;
+ return 0;
+}
+EXPORT_SYMBOL(should_remove_suid);
+
+int __remove_suid(struct dentry *dentry, int kill)
+{
+ struct iattr newattrs;
+
+ newattrs.ia_valid = ATTR_FORCE | kill;
+ return notify_change(dentry, &newattrs);
+}
+
+int remove_suid(struct dentry *dentry)
+{
+ int kill = should_remove_suid(dentry);
+
+ if (unlikely(kill))
+ return __remove_suid(dentry, kill);
+
+ return 0;
}
EXPORT_SYMBOL(remove_suid);
if (unlikely(*pos + *count > MAX_NON_LFS &&
!(file->f_flags & O_LARGEFILE))) {
if (*pos >= MAX_NON_LFS) {
- send_sig(SIGXFSZ, current, 0);
return -EFBIG;
}
if (*count > MAX_NON_LFS - (unsigned long)*pos) {
if (likely(!isblk)) {
if (unlikely(*pos >= inode->i_sb->s_maxbytes)) {
if (*count || *pos > inode->i_sb->s_maxbytes) {
- send_sig(SIGXFSZ, current, 0);
return -EFBIG;
}
/* zero-length writes at ->s_maxbytes are OK */
if (unlikely(*pos + *count > inode->i_sb->s_maxbytes))
*count = inode->i_sb->s_maxbytes - *pos;
} else {
+#ifdef CONFIG_BLOCK
loff_t isize;
if (bdev_read_only(I_BDEV(inode)))
return -EPERM;
if (*pos + *count > isize)
*count = isize - *pos;
+#else
+ return -EPERM;
+#endif
}
return 0;
}
* 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_mutex is held, which protects generic_osync_inode() from
- * livelocking.
+ * livelocking. AIO O_DIRECT ops attempt to sync metadata here.
*/
- if (written >= 0 && ((file->f_flags & O_SYNC) || IS_SYNC(inode))) {
+ if ((written >= 0 || written == -EIOCBQUEUED) &&
+ ((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;
}
EXPORT_SYMBOL(generic_file_direct_write);
/* Limit the size of the copy to the caller's write size */
bytes = min(bytes, count);
- /*
- * Limit the size of the copy to that of the current segment,
- * because fault_in_pages_readable() doesn't know how to walk
- * segments.
+ /* We only need to worry about prefaulting when writes are from
+ * user-space. NFSd uses vfs_writev with several non-aligned
+ * segments in the vector, and limiting to one segment a time is
+ * a noticeable performance for re-write
*/
- bytes = min(bytes, cur_iov->iov_len - iov_base);
-
- /*
- * Bring in the user page that we will copy from _first_.
- * Otherwise there's a nasty deadlock on copying from the
- * same page as we're writing to, without it being marked
- * up-to-date.
- */
- fault_in_pages_readable(buf, bytes);
+ if (!segment_eq(get_fs(), KERNEL_DS)) {
+ /*
+ * Limit the size of the copy to that of the current
+ * segment, because fault_in_pages_readable() doesn't
+ * know how to walk segments.
+ */
+ bytes = min(bytes, cur_iov->iov_len - iov_base);
+ /*
+ * Bring in the user page that we will copy from
+ * _first_. Otherwise there's a nasty deadlock on
+ * copying from the same page as we're writing to,
+ * without it being marked up-to-date.
+ */
+ fault_in_pages_readable(buf, bytes);
+ }
page = __grab_cache_page(mapping,index,&cached_page,&lru_pvec);
if (!page) {
status = -ENOMEM;
unsigned long nr_segs, loff_t *ppos)
{
struct file *file = iocb->ki_filp;
- const struct address_space * mapping = file->f_mapping;
+ struct address_space * mapping = file->f_mapping;
size_t ocount; /* original count */
size_t count; /* after file limit checks */
struct inode *inode = mapping->host;
- unsigned long seg;
loff_t pos;
ssize_t written;
ssize_t err;
ocount = 0;
- for (seg = 0; seg < nr_segs; seg++) {
- const struct iovec *iv = &iov[seg];
-
- /*
- * If any segment has a negative length, or the cumulative
- * length ever wraps negative then return -EINVAL.
- */
- ocount += iv->iov_len;
- if (unlikely((ssize_t)(ocount|iv->iov_len) < 0))
- return -EINVAL;
- if (access_ok(VERIFY_READ, iv->iov_base, iv->iov_len))
- continue;
- if (seg == 0)
- return -EFAULT;
- nr_segs = seg;
- ocount -= iv->iov_len; /* This segment is no good */
- break;
- }
+ err = generic_segment_checks(iov, &nr_segs, &ocount, VERIFY_READ);
+ if (err)
+ return err;
count = ocount;
pos = *ppos;
if (count == 0)
goto out;
- err = remove_suid(file->f_dentry);
+ err = remove_suid(file->f_path.dentry);
if (err)
goto out;
/* coalesce the iovecs and go direct-to-BIO for O_DIRECT */
if (unlikely(file->f_flags & O_DIRECT)) {
- written = generic_file_direct_write(iocb, iov,
- &nr_segs, pos, ppos, count, ocount);
+ loff_t endbyte;
+ ssize_t written_buffered;
+
+ written = generic_file_direct_write(iocb, iov, &nr_segs, pos,
+ ppos, count, ocount);
if (written < 0 || written == count)
goto out;
/*
*/
pos += written;
count -= written;
- }
+ written_buffered = generic_file_buffered_write(iocb, iov,
+ nr_segs, pos, ppos, count,
+ written);
+ /*
+ * If generic_file_buffered_write() retuned a synchronous error
+ * then we want to return the number of bytes which were
+ * direct-written, or the error code if that was zero. Note
+ * that this differs from normal direct-io semantics, which
+ * will return -EFOO even if some bytes were written.
+ */
+ if (written_buffered < 0) {
+ err = written_buffered;
+ goto out;
+ }
- written = generic_file_buffered_write(iocb, iov, nr_segs,
- pos, ppos, count, written);
+ /*
+ * We need to ensure that the page cache pages are written to
+ * disk and invalidated to preserve the expected O_DIRECT
+ * semantics.
+ */
+ endbyte = pos + written_buffered - written - 1;
+ err = do_sync_mapping_range(file->f_mapping, pos, endbyte,
+ SYNC_FILE_RANGE_WAIT_BEFORE|
+ SYNC_FILE_RANGE_WRITE|
+ SYNC_FILE_RANGE_WAIT_AFTER);
+ if (err == 0) {
+ written = written_buffered;
+ invalidate_mapping_pages(mapping,
+ pos >> PAGE_CACHE_SHIFT,
+ endbyte >> PAGE_CACHE_SHIFT);
+ } else {
+ /*
+ * We don't know how much we wrote, so just return
+ * the number of bytes which were direct-written
+ */
+ }
+ } else {
+ written = generic_file_buffered_write(iocb, iov, nr_segs,
+ pos, ppos, count, written);
+ }
out:
current->backing_dev_info = NULL;
return written ? written : err;
}
-EXPORT_SYMBOL(generic_file_aio_write_nolock);
-ssize_t
-generic_file_aio_write_nolock(struct kiocb *iocb, const struct iovec *iov,
- unsigned long nr_segs, loff_t *ppos)
+ssize_t generic_file_aio_write_nolock(struct kiocb *iocb,
+ const struct iovec *iov, unsigned long nr_segs, loff_t pos)
{
struct file *file = iocb->ki_filp;
struct address_space *mapping = file->f_mapping;
struct inode *inode = mapping->host;
ssize_t ret;
- loff_t pos = *ppos;
- ret = __generic_file_aio_write_nolock(iocb, iov, nr_segs, ppos);
+ BUG_ON(iocb->ki_pos != pos);
+
+ ret = __generic_file_aio_write_nolock(iocb, iov, nr_segs,
+ &iocb->ki_pos);
if (ret > 0 && ((file->f_flags & O_SYNC) || IS_SYNC(inode))) {
- int err;
+ ssize_t err;
err = sync_page_range_nolock(inode, mapping, pos, ret);
if (err < 0)
}
return ret;
}
+EXPORT_SYMBOL(generic_file_aio_write_nolock);
-static ssize_t
-__generic_file_write_nolock(struct file *file, const struct iovec *iov,
- unsigned long nr_segs, loff_t *ppos)
-{
- struct kiocb kiocb;
- ssize_t ret;
-
- init_sync_kiocb(&kiocb, file);
- ret = __generic_file_aio_write_nolock(&kiocb, iov, nr_segs, ppos);
- if (ret == -EIOCBQUEUED)
- ret = wait_on_sync_kiocb(&kiocb);
- return ret;
-}
-
-ssize_t
-generic_file_write_nolock(struct file *file, const struct iovec *iov,
- unsigned long nr_segs, loff_t *ppos)
-{
- struct kiocb kiocb;
- ssize_t ret;
-
- init_sync_kiocb(&kiocb, file);
- ret = generic_file_aio_write_nolock(&kiocb, iov, nr_segs, ppos);
- if (-EIOCBQUEUED == ret)
- ret = wait_on_sync_kiocb(&kiocb);
- return ret;
-}
-EXPORT_SYMBOL(generic_file_write_nolock);
-
-ssize_t generic_file_aio_write(struct kiocb *iocb, const char __user *buf,
- size_t count, loff_t pos)
+ssize_t generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
+ unsigned long nr_segs, loff_t pos)
{
struct file *file = iocb->ki_filp;
struct address_space *mapping = file->f_mapping;
struct inode *inode = mapping->host;
ssize_t ret;
- struct iovec local_iov = { .iov_base = (void __user *)buf,
- .iov_len = count };
BUG_ON(iocb->ki_pos != pos);
mutex_lock(&inode->i_mutex);
- ret = __generic_file_aio_write_nolock(iocb, &local_iov, 1,
- &iocb->ki_pos);
+ ret = __generic_file_aio_write_nolock(iocb, iov, nr_segs,
+ &iocb->ki_pos);
mutex_unlock(&inode->i_mutex);
if (ret > 0 && ((file->f_flags & O_SYNC) || IS_SYNC(inode))) {
}
EXPORT_SYMBOL(generic_file_aio_write);
-ssize_t generic_file_write(struct file *file, const char __user *buf,
- size_t count, loff_t *ppos)
-{
- struct address_space *mapping = file->f_mapping;
- struct inode *inode = mapping->host;
- ssize_t ret;
- struct iovec local_iov = { .iov_base = (void __user *)buf,
- .iov_len = count };
-
- mutex_lock(&inode->i_mutex);
- ret = __generic_file_write_nolock(file, &local_iov, 1, ppos);
- mutex_unlock(&inode->i_mutex);
-
- if (ret > 0 && ((file->f_flags & O_SYNC) || IS_SYNC(inode))) {
- ssize_t err;
-
- err = sync_page_range(inode, mapping, *ppos - ret, ret);
- if (err < 0)
- ret = err;
- }
- return ret;
-}
-EXPORT_SYMBOL(generic_file_write);
-
-ssize_t generic_file_readv(struct file *filp, const struct iovec *iov,
- unsigned long nr_segs, loff_t *ppos)
-{
- struct kiocb kiocb;
- ssize_t ret;
-
- init_sync_kiocb(&kiocb, filp);
- ret = __generic_file_aio_read(&kiocb, iov, nr_segs, ppos);
- if (-EIOCBQUEUED == ret)
- ret = wait_on_sync_kiocb(&kiocb);
- return ret;
-}
-EXPORT_SYMBOL(generic_file_readv);
-
-ssize_t generic_file_writev(struct file *file, const struct iovec *iov,
- unsigned long nr_segs, loff_t *ppos)
-{
- struct address_space *mapping = file->f_mapping;
- struct inode *inode = mapping->host;
- ssize_t ret;
-
- mutex_lock(&inode->i_mutex);
- ret = __generic_file_write_nolock(file, iov, nr_segs, ppos);
- mutex_unlock(&inode->i_mutex);
-
- if (ret > 0 && ((file->f_flags & O_SYNC) || IS_SYNC(inode))) {
- int err;
-
- err = sync_page_range(inode, mapping, *ppos - ret, ret);
- if (err < 0)
- ret = err;
- }
- return ret;
-}
-EXPORT_SYMBOL(generic_file_writev);
-
/*
* Called under i_mutex for writes to S_ISREG files. Returns -EIO if something
* went wrong during pagecache shootdown.
struct file *file = iocb->ki_filp;
struct address_space *mapping = file->f_mapping;
ssize_t retval;
- size_t write_len = 0;
+ size_t write_len;
+ pgoff_t end = 0; /* silence gcc */
/*
* If it's a write, unmap all mmappings of the file up-front. This
*/
if (rw == WRITE) {
write_len = iov_length(iov, nr_segs);
+ end = (offset + write_len - 1) >> PAGE_CACHE_SHIFT;
if (mapping_mapped(mapping))
unmap_mapping_range(mapping, offset, write_len, 0);
}
retval = filemap_write_and_wait(mapping);
- if (retval == 0) {
- retval = mapping->a_ops->direct_IO(rw, iocb, iov,
- offset, nr_segs);
- if (rw == WRITE && mapping->nrpages) {
- pgoff_t end = (offset + write_len - 1)
- >> PAGE_CACHE_SHIFT;
- int err = invalidate_inode_pages2_range(mapping,
+ if (retval)
+ goto out;
+
+ /*
+ * After a write we want buffered reads to be sure to go to disk to get
+ * the new data. We invalidate clean cached page from the region we're
+ * about to write. We do this *before* the write so that we can return
+ * -EIO without clobbering -EIOCBQUEUED from ->direct_IO().
+ */
+ if (rw == WRITE && mapping->nrpages) {
+ retval = invalidate_inode_pages2_range(mapping,
offset >> PAGE_CACHE_SHIFT, end);
- if (err)
- retval = err;
- }
+ if (retval)
+ goto out;
}
+
+ retval = mapping->a_ops->direct_IO(rw, iocb, iov, offset, nr_segs);
+ if (retval)
+ goto out;
+
+ /*
+ * Finally, try again to invalidate clean pages which might have been
+ * faulted in by get_user_pages() if the source of the write was an
+ * mmap()ed region of the file we're writing. That's a pretty crazy
+ * thing to do, so we don't support it 100%. If this invalidation
+ * fails and we have -EIOCBQUEUED we ignore the failure.
+ */
+ if (rw == WRITE && mapping->nrpages) {
+ int err = invalidate_inode_pages2_range(mapping,
+ offset >> PAGE_CACHE_SHIFT, end);
+ if (err && retval >= 0)
+ retval = err;
+ }
+out:
return retval;
}
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff