[PATCH] fadvise(): write commands

Add two new linux-specific fadvise extensions():

LINUX_FADV_ASYNC_WRITE: start async writeout of any dirty pages between file
offsets `offset' and `offset+len'.  Any pages which are currently under
writeout are skipped, whether or not they are dirty.

LINUX_FADV_WRITE_WAIT: wait upon writeout of any dirty pages between file
offsets `offset' and `offset+len'.

By combining these two operations the application may do several things:

LINUX_FADV_ASYNC_WRITE: push some or all of the dirty pages at the disk.

LINUX_FADV_WRITE_WAIT, LINUX_FADV_ASYNC_WRITE: push all of the currently dirty
pages at the disk.

LINUX_FADV_WRITE_WAIT, LINUX_FADV_ASYNC_WRITE, LINUX_FADV_WRITE_WAIT: push all
of the currently dirty pages at the disk, wait until they have been written.

It should be noted that none of these operations write out the file's
metadata.  So unless the application is strictly performing overwrites of
already-instantiated disk blocks, there are no guarantees here that the data
will be available after a crash.

To complete this suite of operations I guess we should have a "sync file
metadata only" operation.  This gives applications access to all the building
blocks needed for all sorts of sync operations.  But sync-metadata doesn't fit
well with the fadvise() interface.  Probably it should be a new syscall:
sys_fmetadatasync().

The patch also diddles with the meaning of `endbyte' in sys_fadvise64_64().
It is made to represent that last affected byte in the file (ie: it is
inclusive).  Generally, all these byterange and pagerange functions are
inclusive so we can easily represent EOF with -1.

As Ulrich notes, these two functions are somewhat abusive of the fadvise()
concept, which appears to be "set the future policy for this fd".

But these commands are a perfect fit with the fadvise() impementation, and
several of the existing fadvise() commands are synchronous and don't affect
future policy either.   I think we can live with the slight incongruity.

Cc: Michael Kerrisk <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>

include/linux/fadvise.h

@@ -18,4 +18,10 @@
 #define POSIX_FADV_NOREUSE	5 /* Data will be accessed once.  */
 #endif
 
+/*
+ * Linux-specific fadvise() extensions:
+ */
+#define LINUX_FADV_ASYNC_WRITE	32	/* Start writeout on range */
+#define LINUX_FADV_WRITE_WAIT	33	/* Wait upon writeout to range */
+
 #endif	/* FADVISE_H_INCLUDED */

include/linux/fs.h

@@ -1473,6 +1473,11 @@ extern int filemap_fdatawait(struct address_space *);
 extern int filemap_write_and_wait(struct address_space *mapping);
 extern int filemap_write_and_wait_range(struct address_space *mapping,
 				        loff_t lstart, loff_t lend);
+extern int wait_on_page_writeback_range(struct address_space *mapping,
+				pgoff_t start, pgoff_t end);
+extern int __filemap_fdatawrite_range(struct address_space *mapping,
+				loff_t start, loff_t end, int sync_mode);
+
 extern void sync_supers(void);
 extern void sync_filesystems(int wait);
 extern void emergency_sync(void);

mm/fadvise.c

@@ -15,20 +15,44 @@
 #include <linux/backing-dev.h>
 #include <linux/pagevec.h>
 #include <linux/fadvise.h>
+#include <linux/writeback.h>
 #include <linux/syscalls.h>
 
 #include <asm/unistd.h>
 
 /*
  * POSIX_FADV_WILLNEED could set PG_Referenced, and POSIX_FADV_NOREUSE could
  * deactivate the pages and clear PG_Referenced.
+ *
+ * LINUX_FADV_ASYNC_WRITE: start async writeout of any dirty pages between file
+ * offsets `offset' and `offset+len' inclusive.  Any pages which are currently
+ * under writeout are skipped, whether or not they are dirty.
+ *
+ * LINUX_FADV_WRITE_WAIT: wait upon writeout of any dirty pages between file
+ * offsets `offset' and `offset+len'.
+ *
+ * By combining these two operations the application may do several things:
+ *
+ * LINUX_FADV_ASYNC_WRITE: push some or all of the dirty pages at the disk.
+ *
+ * LINUX_FADV_WRITE_WAIT, LINUX_FADV_ASYNC_WRITE: push all of the currently
+ * dirty pages at the disk.
+ *
+ * LINUX_FADV_WRITE_WAIT, LINUX_FADV_ASYNC_WRITE, LINUX_FADV_WRITE_WAIT: push
+ * all of the currently dirty pages at the disk, wait until they have been
+ * written.
+ *
+ * It should be noted that none of these operations write out the file's
+ * metadata.  So unless the application is strictly performing overwrites of
+ * already-instantiated disk blocks, there are no guarantees here that the data
+ * will be available after a crash.
  */
 asmlinkage long sys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice)
 {
 	struct file *file = fget(fd);
 	struct address_space *mapping;
 	struct backing_dev_info *bdi;
-	loff_t endbyte;
+	loff_t endbyte;			/* inclusive */
 	pgoff_t start_index;
 	pgoff_t end_index;
 	unsigned long nrpages;
@@ -56,6 +80,8 @@ asmlinkage long sys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice)
 	endbyte = offset + len;
 	if (!len || endbyte < len)
 		endbyte = -1;
+	else
+		endbyte--;		/* inclusive */
 
 	bdi = mapping->backing_dev_info;
 
@@ -78,7 +104,7 @@ asmlinkage long sys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice)
 
 		/* First and last PARTIAL page! */
 		start_index = offset >> PAGE_CACHE_SHIFT;
-		end_index = (endbyte-1) >> PAGE_CACHE_SHIFT;
+		end_index = endbyte >> PAGE_CACHE_SHIFT;
 
 		/* Careful about overflow on the "+1" */
 		nrpages = end_index - start_index + 1;
@@ -96,11 +122,21 @@ asmlinkage long sys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice)
 			filemap_flush(mapping);
 
 		/* First and last FULL page! */
-		start_index = (offset + (PAGE_CACHE_SIZE-1)) >> PAGE_CACHE_SHIFT;
+		start_index = (offset+(PAGE_CACHE_SIZE-1)) >> PAGE_CACHE_SHIFT;
 		end_index = (endbyte >> PAGE_CACHE_SHIFT);
 
-		if (end_index > start_index)
-			invalidate_mapping_pages(mapping, start_index, end_index-1);
+		if (end_index >= start_index)
+			invalidate_mapping_pages(mapping, start_index,
+						end_index);
+		break;
+	case LINUX_FADV_ASYNC_WRITE:
+		ret = __filemap_fdatawrite_range(mapping, offset, endbyte,
+						WB_SYNC_NONE);
+		break;
+	case LINUX_FADV_WRITE_WAIT:
+		ret = wait_on_page_writeback_range(mapping,
+					offset >> PAGE_CACHE_SHIFT,
+					endbyte >> PAGE_CACHE_SHIFT);
 		break;
 	default:
 		ret = -EINVAL;

mm/filemap.c

@@ -183,8 +183,8 @@ static int sync_page(void *word)
  * these two operations is that if a dirty page/buffer is encountered, it must
  * be waited upon, and not just skipped over.
  */
-static int __filemap_fdatawrite_range(struct address_space *mapping,
-	loff_t start, loff_t end, int sync_mode)
+int __filemap_fdatawrite_range(struct address_space *mapping, loff_t start,
+				loff_t end, int sync_mode)
 {
 	int ret;
 	struct writeback_control wbc = {
@@ -213,8 +213,8 @@ int filemap_fdatawrite(struct address_space *mapping)
 }
 EXPORT_SYMBOL(filemap_fdatawrite);
 
-static int filemap_fdatawrite_range(struct address_space *mapping,
-	loff_t start, loff_t end)
+static int filemap_fdatawrite_range(struct address_space *mapping, loff_t start,
+				loff_t end)
 {
 	return __filemap_fdatawrite_range(mapping, start, end, WB_SYNC_ALL);
 }
@@ -233,7 +233,7 @@ EXPORT_SYMBOL(filemap_flush);
  * Wait for writeback to complete against pages indexed by start->end
  * inclusive
  */
-static int wait_on_page_writeback_range(struct address_space *mapping,
+int wait_on_page_writeback_range(struct address_space *mapping,
 				pgoff_t start, pgoff_t end)
 {
 	struct pagevec pvec;