4 files changed, 57 insertions, 10 deletions

diff --git a/include/linux/fadvise.h b/include/linux/fadvise.h
index e8e747139b9a..b2913bba35d8 100644
--- a/include/linux/fadvise.h
+++ b/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 */
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 65e6df247ea5..0ad70c1e5e55 100644
--- a/include/linux/fs.h
+++ b/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);
diff --git a/mm/fadvise.c b/mm/fadvise.c
index d257c89e7704..907c39257ca0 100644
--- a/mm/fadvise.c
+++ b/mm/fadvise.c
@@ -15,6 +15,7 @@
 #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>
@@ -22,13 +23,36 @@
 /*
  * 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;
diff --git a/mm/filemap.c b/mm/filemap.c
index c1b1708cc95d..3ef20739e725 100644
--- a/mm/filemap.c
+++ b/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;