X-Git-Url: http://pilppa.org/gitweb/gitweb.cgi?a=blobdiff_plain;f=mm%2Ffilemap.c;h=5dfc093ceb3d680322158f508bed3b0b47a8fbb7;hb=d56e03cd275486eb8141116a7af2df7457cb0115;hp=ec469235985d6e2cd89d39bf8bd40405f133e142;hpb=63c422afe3739b68bec0b5c42807d1450c951caf;p=linux-2.6-omap-h63xx.git

diff --git a/mm/filemap.c b/mm/filemap.c
index ec469235985..5dfc093ceb3 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -75,8 +75,8 @@ generic_file_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
  *  ->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)
@@ -327,7 +327,7 @@ EXPORT_SYMBOL(sync_page_range);
  * @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.
  */
@@ -467,25 +467,15 @@ int add_to_page_cache_lru(struct page *page, struct address_space *mapping,
 }
 
 #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)
@@ -615,26 +605,6 @@ struct page * find_get_page(struct address_space *mapping, unsigned long offset)
 }
 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
@@ -814,7 +784,7 @@ unsigned find_get_pages_tag(struct address_space *mapping, pgoff_t *index,
  * @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.
@@ -826,7 +796,6 @@ struct 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))
@@ -834,9 +803,8 @@ grab_cache_page_nowait(struct address_space *mapping, unsigned long index)
 		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;
 	}
@@ -1139,11 +1107,11 @@ success:
 }
 
 /**
- * __generic_file_aio_read - generic filesystem read routine
+ * 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
- * @ppos:	current file position
+ * @pos:	current file position
  *
  * This is the "read()" routine for all filesystems
  * that can use the page cache directly.
@@ -1193,13 +1161,13 @@ generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov,
 		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;
@@ -1455,7 +1423,6 @@ no_cached_page:
 	 * effect.
 	 */
 	error = page_cache_read(file, pgoff);
-	grab_swap_token();
 
 	/*
 	 * The page we want has now been added to the page cache.
@@ -1882,11 +1849,10 @@ repeat:
  *	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))
@@ -1899,13 +1865,29 @@ int remove_suid(struct dentry *dentry)
 	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);
 
@@ -2043,15 +2025,14 @@ generic_file_direct_write(struct kiocb *iocb, const struct iovec *iov,
 	 * 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);
@@ -2098,21 +2079,27 @@ generic_file_buffered_write(struct kiocb *iocb, const struct iovec *iov,
 		/* 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.
-		 */
-		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.
+		/* 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
 		 */
-		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;
@@ -2220,7 +2207,7 @@ __generic_file_aio_write_nolock(struct kiocb *iocb, const struct iovec *iov,
 				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;
@@ -2265,7 +2252,7 @@ __generic_file_aio_write_nolock(struct kiocb *iocb, const struct iovec *iov,
 	if (count == 0)
 		goto out;
 
-	err = remove_suid(file->f_dentry);
+	err = remove_suid(file->f_path.dentry);
 	if (err)
 		goto out;
 
@@ -2273,8 +2260,11 @@ __generic_file_aio_write_nolock(struct kiocb *iocb, const struct iovec *iov,
 
 	/* 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;
 		/*
@@ -2283,10 +2273,46 @@ __generic_file_aio_write_nolock(struct kiocb *iocb, const struct iovec *iov,
 		 */
 		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_file_range(file, 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;
@@ -2353,7 +2379,8 @@ generic_file_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
 	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
@@ -2362,23 +2389,46 @@ generic_file_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
 	 */
 	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;
 }