#include <linux/security.h>
#include <linux/syscalls.h>
#include <linux/cpuset.h>
-#include "filemap.h"
+#include <linux/hardirq.h> /* for BUG_ON(!in_atomic()) only */
#include "internal.h"
/*
* ->private_lock (__free_pte->__set_page_dirty_buffers)
* ->swap_lock (exclusive_swap_page, others)
* ->mapping->tree_lock
+ * ->zone.lock
*
* ->i_mutex
* ->i_mmap_lock (truncate->unmap_mapping_range)
}
EXPORT_SYMBOL(remove_suid);
-size_t
-__filemap_copy_from_user_iovec_inatomic(char *vaddr,
+static size_t __iovec_copy_from_user_inatomic(char *vaddr,
const struct iovec *iov, size_t base, size_t bytes)
{
size_t copied = 0, left = 0;
return copied - left;
}
+/*
+ * 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 return the number of
+ * bytes which were copied.
+ */
+size_t iov_iter_copy_from_user_atomic(struct page *page,
+ struct iov_iter *i, unsigned long offset, size_t bytes)
+{
+ char *kaddr;
+ size_t copied;
+
+ BUG_ON(!in_atomic());
+ kaddr = kmap_atomic(page, KM_USER0);
+ if (likely(i->nr_segs == 1)) {
+ int left;
+ char __user *buf = i->iov->iov_base + i->iov_offset;
+ left = __copy_from_user_inatomic_nocache(kaddr + offset,
+ buf, bytes);
+ copied = bytes - left;
+ } else {
+ copied = __iovec_copy_from_user_inatomic(kaddr + offset,
+ i->iov, i->iov_offset, bytes);
+ }
+ kunmap_atomic(kaddr, KM_USER0);
+
+ return copied;
+}
+EXPORT_SYMBOL(iov_iter_copy_from_user_atomic);
+
+/*
+ * This has the same sideeffects and return value as
+ * iov_iter_copy_from_user_atomic().
+ * The difference is that it attempts to resolve faults.
+ * Page must not be locked.
+ */
+size_t iov_iter_copy_from_user(struct page *page,
+ struct iov_iter *i, unsigned long offset, size_t bytes)
+{
+ char *kaddr;
+ size_t copied;
+
+ kaddr = kmap(page);
+ if (likely(i->nr_segs == 1)) {
+ int left;
+ char __user *buf = i->iov->iov_base + i->iov_offset;
+ left = __copy_from_user_nocache(kaddr + offset, buf, bytes);
+ copied = bytes - left;
+ } else {
+ copied = __iovec_copy_from_user_inatomic(kaddr + offset,
+ i->iov, i->iov_offset, bytes);
+ }
+ kunmap(page);
+ return copied;
+}
+EXPORT_SYMBOL(iov_iter_copy_from_user);
+
+static void __iov_iter_advance_iov(struct iov_iter *i, size_t bytes)
+{
+ if (likely(i->nr_segs == 1)) {
+ i->iov_offset += bytes;
+ } else {
+ const struct iovec *iov = i->iov;
+ size_t base = i->iov_offset;
+
+ while (bytes) {
+ int copy = min(bytes, iov->iov_len - base);
+
+ bytes -= copy;
+ base += copy;
+ if (iov->iov_len == base) {
+ iov++;
+ base = 0;
+ }
+ }
+ i->iov = iov;
+ i->iov_offset = base;
+ }
+}
+
+void iov_iter_advance(struct iov_iter *i, size_t bytes)
+{
+ BUG_ON(i->count < bytes);
+
+ __iov_iter_advance_iov(i, bytes);
+ i->count -= bytes;
+}
+EXPORT_SYMBOL(iov_iter_advance);
+
+/*
+ * Fault in the first iovec of the given iov_iter, to a maximum length
+ * of bytes. Returns 0 on success, or non-zero if the memory could not be
+ * accessed (ie. because it is an invalid address).
+ *
+ * writev-intensive code may want this to prefault several iovecs -- that
+ * would be possible (callers must not rely on the fact that _only_ the
+ * first iovec will be faulted with the current implementation).
+ */
+int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes)
+{
+ char __user *buf = i->iov->iov_base + i->iov_offset;
+ bytes = min(bytes, i->iov->iov_len - i->iov_offset);
+ return fault_in_pages_readable(buf, bytes);
+}
+EXPORT_SYMBOL(iov_iter_fault_in_readable);
+
+/*
+ * Return the count of just the current iov_iter segment.
+ */
+size_t iov_iter_single_seg_count(struct iov_iter *i)
+{
+ const struct iovec *iov = i->iov;
+ if (i->nr_segs == 1)
+ return i->count;
+ else
+ return min(i->count, iov->iov_len - i->iov_offset);
+}
+EXPORT_SYMBOL(iov_iter_single_seg_count);
+
/*
* Performs necessary checks before doing a write
*
}
EXPORT_SYMBOL(generic_write_checks);
+int pagecache_write_begin(struct file *file, struct address_space *mapping,
+ loff_t pos, unsigned len, unsigned flags,
+ struct page **pagep, void **fsdata)
+{
+ const struct address_space_operations *aops = mapping->a_ops;
+
+ if (aops->write_begin) {
+ return aops->write_begin(file, mapping, pos, len, flags,
+ pagep, fsdata);
+ } else {
+ int ret;
+ pgoff_t index = pos >> PAGE_CACHE_SHIFT;
+ unsigned offset = pos & (PAGE_CACHE_SIZE - 1);
+ struct inode *inode = mapping->host;
+ struct page *page;
+again:
+ page = __grab_cache_page(mapping, index);
+ *pagep = page;
+ if (!page)
+ return -ENOMEM;
+
+ if (flags & AOP_FLAG_UNINTERRUPTIBLE && !PageUptodate(page)) {
+ /*
+ * There is no way to resolve a short write situation
+ * for a !Uptodate page (except by double copying in
+ * the caller done by generic_perform_write_2copy).
+ *
+ * Instead, we have to bring it uptodate here.
+ */
+ ret = aops->readpage(file, page);
+ page_cache_release(page);
+ if (ret) {
+ if (ret == AOP_TRUNCATED_PAGE)
+ goto again;
+ return ret;
+ }
+ goto again;
+ }
+
+ ret = aops->prepare_write(file, page, offset, offset+len);
+ if (ret) {
+ unlock_page(page);
+ page_cache_release(page);
+ if (pos + len > inode->i_size)
+ vmtruncate(inode, inode->i_size);
+ }
+ return ret;
+ }
+}
+EXPORT_SYMBOL(pagecache_write_begin);
+
+int pagecache_write_end(struct file *file, struct address_space *mapping,
+ loff_t pos, unsigned len, unsigned copied,
+ struct page *page, void *fsdata)
+{
+ const struct address_space_operations *aops = mapping->a_ops;
+ int ret;
+
+ if (aops->write_end) {
+ mark_page_accessed(page);
+ ret = aops->write_end(file, mapping, pos, len, copied,
+ page, fsdata);
+ } else {
+ unsigned offset = pos & (PAGE_CACHE_SIZE - 1);
+ struct inode *inode = mapping->host;
+
+ flush_dcache_page(page);
+ ret = aops->commit_write(file, page, offset, offset+len);
+ unlock_page(page);
+ mark_page_accessed(page);
+ page_cache_release(page);
+
+ if (ret < 0) {
+ if (pos + len > inode->i_size)
+ vmtruncate(inode, inode->i_size);
+ } else if (ret > 0)
+ ret = min_t(size_t, copied, ret);
+ else
+ ret = copied;
+ }
+
+ return ret;
+}
+EXPORT_SYMBOL(pagecache_write_end);
+
ssize_t
generic_file_direct_write(struct kiocb *iocb, const struct iovec *iov,
unsigned long *nr_segs, loff_t pos, loff_t *ppos,
* Find or create a page at the given pagecache position. Return the locked
* page. This function is specifically for buffered writes.
*/
-static struct page *__grab_cache_page(struct address_space *mapping,
- pgoff_t index)
+struct page *__grab_cache_page(struct address_space *mapping, pgoff_t index)
{
int status;
struct page *page;
}
return page;
}
+EXPORT_SYMBOL(__grab_cache_page);
-ssize_t
-generic_file_buffered_write(struct kiocb *iocb, const struct iovec *iov,
- unsigned long nr_segs, loff_t pos, loff_t *ppos,
- size_t count, ssize_t written)
+static ssize_t generic_perform_write_2copy(struct file *file,
+ struct iov_iter *i, loff_t pos)
{
- struct file *file = iocb->ki_filp;
struct address_space *mapping = file->f_mapping;
const struct address_space_operations *a_ops = mapping->a_ops;
- struct inode *inode = mapping->host;
- long status = 0;
- const struct iovec *cur_iov = iov; /* current iovec */
- size_t iov_offset = 0; /* offset in the current iovec */
- char __user *buf;
-
- /*
- * handle partial DIO write. Adjust cur_iov if needed.
- */
- if (likely(nr_segs == 1))
- buf = iov->iov_base + written;
- else {
- filemap_set_next_iovec(&cur_iov, &iov_offset, written);
- buf = cur_iov->iov_base + iov_offset;
- }
+ struct inode *inode = mapping->host;
+ long status = 0;
+ ssize_t written = 0;
do {
+ struct page *src_page;
struct page *page;
pgoff_t index; /* Pagecache index for current page */
unsigned long offset; /* Offset into pagecache page */
- unsigned long maxlen; /* Bytes remaining in current iovec */
- size_t bytes; /* Bytes to write to page */
+ unsigned long bytes; /* Bytes to write to page */
size_t copied; /* Bytes copied from user */
offset = (pos & (PAGE_CACHE_SIZE - 1));
index = pos >> PAGE_CACHE_SHIFT;
- bytes = PAGE_CACHE_SIZE - offset;
- if (bytes > count)
- bytes = count;
+ bytes = min_t(unsigned long, PAGE_CACHE_SIZE - offset,
+ iov_iter_count(i));
- maxlen = cur_iov->iov_len - iov_offset;
- if (maxlen > bytes)
- maxlen = bytes;
+ /*
+ * a non-NULL src_page indicates that we're doing the
+ * copy via get_user_pages and kmap.
+ */
+ src_page = NULL;
-#ifndef CONFIG_DEBUG_VM
/*
* 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.
+ *
+ * Not only is this an optimisation, but it is also required
+ * to check that the address is actually valid, when atomic
+ * usercopies are used, below.
*/
- fault_in_pages_readable(buf, maxlen);
-#endif
-
+ if (unlikely(iov_iter_fault_in_readable(i, bytes))) {
+ status = -EFAULT;
+ break;
+ }
page = __grab_cache_page(mapping, index);
if (!page) {
break;
}
+ /*
+ * non-uptodate pages cannot cope with short copies, and we
+ * cannot take a pagefault with the destination page locked.
+ * So pin the source page to copy it.
+ */
+ if (!PageUptodate(page) && !segment_eq(get_fs(), KERNEL_DS)) {
+ unlock_page(page);
+
+ src_page = alloc_page(GFP_KERNEL);
+ if (!src_page) {
+ page_cache_release(page);
+ status = -ENOMEM;
+ break;
+ }
+
+ /*
+ * Cannot get_user_pages with a page locked for the
+ * same reason as we can't take a page fault with a
+ * page locked (as explained below).
+ */
+ copied = iov_iter_copy_from_user(src_page, i,
+ offset, bytes);
+ if (unlikely(copied == 0)) {
+ status = -EFAULT;
+ page_cache_release(page);
+ page_cache_release(src_page);
+ break;
+ }
+ bytes = copied;
+
+ lock_page(page);
+ /*
+ * Can't handle the page going uptodate here, because
+ * that means we would use non-atomic usercopies, which
+ * zero out the tail of the page, which can cause
+ * zeroes to become transiently visible. We could just
+ * use a non-zeroing copy, but the APIs aren't too
+ * consistent.
+ */
+ if (unlikely(!page->mapping || PageUptodate(page))) {
+ unlock_page(page);
+ page_cache_release(page);
+ page_cache_release(src_page);
+ continue;
+ }
+ }
+
status = a_ops->prepare_write(file, page, offset, offset+bytes);
if (unlikely(status))
goto fs_write_aop_error;
- if (likely(nr_segs == 1))
- copied = filemap_copy_from_user(page, offset,
- buf, bytes);
- else
- copied = filemap_copy_from_user_iovec(page, offset,
- cur_iov, iov_offset, bytes);
+ if (!src_page) {
+ /*
+ * Must not enter the pagefault handler here, because
+ * we hold the page lock, so we might recursively
+ * deadlock on the same lock, or get an ABBA deadlock
+ * against a different lock, or against the mmap_sem
+ * (which nests outside the page lock). So increment
+ * preempt count, and use _atomic usercopies.
+ *
+ * The page is uptodate so we are OK to encounter a
+ * short copy: if unmodified parts of the page are
+ * marked dirty and written out to disk, it doesn't
+ * really matter.
+ */
+ pagefault_disable();
+ copied = iov_iter_copy_from_user_atomic(page, i,
+ offset, bytes);
+ pagefault_enable();
+ } else {
+ void *src, *dst;
+ src = kmap_atomic(src_page, KM_USER0);
+ dst = kmap_atomic(page, KM_USER1);
+ memcpy(dst + offset, src + offset, bytes);
+ kunmap_atomic(dst, KM_USER1);
+ kunmap_atomic(src, KM_USER0);
+ copied = bytes;
+ }
flush_dcache_page(page);
+
status = a_ops->commit_write(file, page, offset, offset+bytes);
- if (unlikely(status < 0 || status == AOP_TRUNCATED_PAGE))
- goto fs_write_aop_error;
- if (unlikely(copied != bytes)) {
- status = -EFAULT;
+ if (unlikely(status < 0))
goto fs_write_aop_error;
- }
if (unlikely(status > 0)) /* filesystem did partial write */
- copied = status;
-
- if (likely(copied > 0)) {
- written += copied;
- count -= copied;
- pos += copied;
- buf += copied;
- if (unlikely(nr_segs > 1)) {
- filemap_set_next_iovec(&cur_iov,
- &iov_offset, copied);
- if (count)
- buf = cur_iov->iov_base + iov_offset;
- } else {
- iov_offset += copied;
- }
- }
+ copied = min_t(size_t, copied, status);
+
unlock_page(page);
mark_page_accessed(page);
page_cache_release(page);
+ if (src_page)
+ page_cache_release(src_page);
+
+ iov_iter_advance(i, copied);
+ pos += copied;
+ written += copied;
+
balance_dirty_pages_ratelimited(mapping);
cond_resched();
continue;
fs_write_aop_error:
- if (status != AOP_TRUNCATED_PAGE)
- unlock_page(page);
+ unlock_page(page);
page_cache_release(page);
+ if (src_page)
+ page_cache_release(src_page);
/*
* prepare_write() may have instantiated a few blocks
*/
if (pos + bytes > inode->i_size)
vmtruncate(inode, inode->i_size);
- if (status == AOP_TRUNCATED_PAGE)
- continue;
- else
- break;
+ break;
+ } while (iov_iter_count(i));
- } while (count);
- *ppos = pos;
+ return written ? written : status;
+}
+
+static ssize_t generic_perform_write(struct file *file,
+ struct iov_iter *i, loff_t pos)
+{
+ struct address_space *mapping = file->f_mapping;
+ const struct address_space_operations *a_ops = mapping->a_ops;
+ long status = 0;
+ ssize_t written = 0;
+ unsigned int flags = 0;
/*
- * For now, when the user asks for O_SYNC, we'll actually give O_DSYNC
+ * Copies from kernel address space cannot fail (NFSD is a big user).
*/
+ if (segment_eq(get_fs(), KERNEL_DS))
+ flags |= AOP_FLAG_UNINTERRUPTIBLE;
+
+ do {
+ struct page *page;
+ pgoff_t index; /* Pagecache index for current page */
+ unsigned long offset; /* Offset into pagecache page */
+ unsigned long bytes; /* Bytes to write to page */
+ size_t copied; /* Bytes copied from user */
+ void *fsdata;
+
+ offset = (pos & (PAGE_CACHE_SIZE - 1));
+ index = pos >> PAGE_CACHE_SHIFT;
+ bytes = min_t(unsigned long, PAGE_CACHE_SIZE - offset,
+ iov_iter_count(i));
+
+again:
+
+ /*
+ * 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.
+ *
+ * Not only is this an optimisation, but it is also required
+ * to check that the address is actually valid, when atomic
+ * usercopies are used, below.
+ */
+ if (unlikely(iov_iter_fault_in_readable(i, bytes))) {
+ status = -EFAULT;
+ break;
+ }
+
+ status = a_ops->write_begin(file, mapping, pos, bytes, flags,
+ &page, &fsdata);
+ if (unlikely(status))
+ break;
+
+ pagefault_disable();
+ copied = iov_iter_copy_from_user_atomic(page, i, offset, bytes);
+ pagefault_enable();
+ flush_dcache_page(page);
+
+ status = a_ops->write_end(file, mapping, pos, bytes, copied,
+ page, fsdata);
+ if (unlikely(status < 0))
+ break;
+ copied = status;
+
+ cond_resched();
+
+ if (unlikely(copied == 0)) {
+ /*
+ * If we were unable to copy any data at all, we must
+ * fall back to a single segment length write.
+ *
+ * If we didn't fallback here, we could livelock
+ * because not all segments in the iov can be copied at
+ * once without a pagefault.
+ */
+ bytes = min_t(unsigned long, PAGE_CACHE_SIZE - offset,
+ iov_iter_single_seg_count(i));
+ goto again;
+ }
+ iov_iter_advance(i, copied);
+ pos += copied;
+ written += copied;
+
+ balance_dirty_pages_ratelimited(mapping);
+
+ } while (iov_iter_count(i));
+
+ return written ? written : status;
+}
+
+ssize_t
+generic_file_buffered_write(struct kiocb *iocb, const struct iovec *iov,
+ unsigned long nr_segs, loff_t pos, loff_t *ppos,
+ size_t count, ssize_t written)
+{
+ struct file *file = iocb->ki_filp;
+ struct address_space *mapping = file->f_mapping;
+ const struct address_space_operations *a_ops = mapping->a_ops;
+ struct inode *inode = mapping->host;
+ ssize_t status;
+ struct iov_iter i;
+
+ iov_iter_init(&i, iov, nr_segs, count, written);
+ if (a_ops->write_begin)
+ status = generic_perform_write(file, &i, pos);
+ else
+ status = generic_perform_write_2copy(file, &i, pos);
+
if (likely(status >= 0)) {
+ written += status;
+ *ppos = pos + status;
+
+ /*
+ * For now, when the user asks for O_SYNC, we'll actually give
+ * O_DSYNC
+ */
if (unlikely((file->f_flags & O_SYNC) || IS_SYNC(inode))) {
if (!a_ops->writepage || !is_sync_kiocb(iocb))
status = generic_osync_inode(inode, mapping,
git.openpandora.org / pandora-kernel.git / blobdiff