summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorDavid Howells <dhowells@redhat.com>2006-08-29 18:05:54 (GMT)
committerJens Axboe <axboe@nelson.home.kernel.dk>2006-09-30 18:31:19 (GMT)
commitcf9a2ae8d49948f861b56e5333530e491a9da190 (patch)
tree21f0b0d781b3e60cc60464d39b6d95681201b37e
parent4090959aee403817ff386415f9bc602c1a0882ef (diff)
downloadlinux-cf9a2ae8d49948f861b56e5333530e491a9da190.tar.xz
[PATCH] BLOCK: Move functions out of buffer code [try #6]
Move some functions out of the buffering code that aren't strictly buffering specific. This is a precursor to being able to disable the block layer. (*) Moved some stuff out of fs/buffer.c: (*) The file sync and general sync stuff moved to fs/sync.c. (*) The superblock sync stuff moved to fs/super.c. (*) do_invalidatepage() moved to mm/truncate.c. (*) try_to_release_page() moved to mm/filemap.c. (*) Moved some related declarations between header files: (*) declarations for do_invalidatepage() and try_to_release_page() moved to linux/mm.h. (*) __set_page_dirty_buffers() moved to linux/buffer_head.h. Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
-rw-r--r--fs/buffer.c174
-rw-r--r--fs/super.c31
-rw-r--r--fs/sync.c113
-rw-r--r--include/linux/buffer_head.h3
-rw-r--r--include/linux/fs.h1
-rw-r--r--include/linux/mm.h4
-rw-r--r--mm/filemap.c30
-rw-r--r--mm/page-writeback.c1
-rw-r--r--mm/truncate.c24
9 files changed, 204 insertions, 177 deletions
diff --git a/fs/buffer.c b/fs/buffer.c
index 3b6d701..16cfbcd 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -159,31 +159,6 @@ int sync_blockdev(struct block_device *bdev)
}
EXPORT_SYMBOL(sync_blockdev);
-static void __fsync_super(struct super_block *sb)
-{
- sync_inodes_sb(sb, 0);
- DQUOT_SYNC(sb);
- lock_super(sb);
- if (sb->s_dirt && sb->s_op->write_super)
- sb->s_op->write_super(sb);
- unlock_super(sb);
- if (sb->s_op->sync_fs)
- sb->s_op->sync_fs(sb, 1);
- sync_blockdev(sb->s_bdev);
- sync_inodes_sb(sb, 1);
-}
-
-/*
- * Write out and wait upon all dirty data associated with this
- * superblock. Filesystem data as well as the underlying block
- * device. Takes the superblock lock.
- */
-int fsync_super(struct super_block *sb)
-{
- __fsync_super(sb);
- return sync_blockdev(sb->s_bdev);
-}
-
/*
* Write out and wait upon all dirty data associated with this
* device. Filesystem data as well as the underlying block
@@ -260,118 +235,6 @@ void thaw_bdev(struct block_device *bdev, struct super_block *sb)
EXPORT_SYMBOL(thaw_bdev);
/*
- * sync everything. Start out by waking pdflush, because that writes back
- * all queues in parallel.
- */
-static void do_sync(unsigned long wait)
-{
- wakeup_pdflush(0);
- sync_inodes(0); /* All mappings, inodes and their blockdevs */
- DQUOT_SYNC(NULL);
- sync_supers(); /* Write the superblocks */
- sync_filesystems(0); /* Start syncing the filesystems */
- sync_filesystems(wait); /* Waitingly sync the filesystems */
- sync_inodes(wait); /* Mappings, inodes and blockdevs, again. */
- if (!wait)
- printk("Emergency Sync complete\n");
- if (unlikely(laptop_mode))
- laptop_sync_completion();
-}
-
-asmlinkage long sys_sync(void)
-{
- do_sync(1);
- return 0;
-}
-
-void emergency_sync(void)
-{
- pdflush_operation(do_sync, 0);
-}
-
-/*
- * Generic function to fsync a file.
- *
- * filp may be NULL if called via the msync of a vma.
- */
-
-int file_fsync(struct file *filp, struct dentry *dentry, int datasync)
-{
- struct inode * inode = dentry->d_inode;
- struct super_block * sb;
- int ret, err;
-
- /* sync the inode to buffers */
- ret = write_inode_now(inode, 0);
-
- /* sync the superblock to buffers */
- sb = inode->i_sb;
- lock_super(sb);
- if (sb->s_op->write_super)
- sb->s_op->write_super(sb);
- unlock_super(sb);
-
- /* .. finally sync the buffers to disk */
- err = sync_blockdev(sb->s_bdev);
- if (!ret)
- ret = err;
- return ret;
-}
-
-long do_fsync(struct file *file, int datasync)
-{
- int ret;
- int err;
- struct address_space *mapping = file->f_mapping;
-
- if (!file->f_op || !file->f_op->fsync) {
- /* Why? We can still call filemap_fdatawrite */
- ret = -EINVAL;
- goto out;
- }
-
- ret = filemap_fdatawrite(mapping);
-
- /*
- * We need to protect against concurrent writers, which could cause
- * livelocks in fsync_buffers_list().
- */
- mutex_lock(&mapping->host->i_mutex);
- err = file->f_op->fsync(file, file->f_dentry, datasync);
- if (!ret)
- ret = err;
- mutex_unlock(&mapping->host->i_mutex);
- err = filemap_fdatawait(mapping);
- if (!ret)
- ret = err;
-out:
- return ret;
-}
-
-static long __do_fsync(unsigned int fd, int datasync)
-{
- struct file *file;
- int ret = -EBADF;
-
- file = fget(fd);
- if (file) {
- ret = do_fsync(file, datasync);
- fput(file);
- }
- return ret;
-}
-
-asmlinkage long sys_fsync(unsigned int fd)
-{
- return __do_fsync(fd, 0);
-}
-
-asmlinkage long sys_fdatasync(unsigned int fd)
-{
- return __do_fsync(fd, 1);
-}
-
-/*
* Various filesystems appear to want __find_get_block to be non-blocking.
* But it's the page lock which protects the buffers. To get around this,
* we get exclusion from try_to_free_buffers with the blockdev mapping's
@@ -1551,35 +1414,6 @@ static void discard_buffer(struct buffer_head * bh)
}
/**
- * try_to_release_page() - release old fs-specific metadata on a page
- *
- * @page: the page which the kernel is trying to free
- * @gfp_mask: memory allocation flags (and I/O mode)
- *
- * The address_space is to try to release any data against the page
- * (presumably at page->private). If the release was successful, return `1'.
- * Otherwise return zero.
- *
- * The @gfp_mask argument specifies whether I/O may be performed to release
- * this page (__GFP_IO), and whether the call may block (__GFP_WAIT).
- *
- * NOTE: @gfp_mask may go away, and this function may become non-blocking.
- */
-int try_to_release_page(struct page *page, gfp_t gfp_mask)
-{
- struct address_space * const mapping = page->mapping;
-
- BUG_ON(!PageLocked(page));
- if (PageWriteback(page))
- return 0;
-
- if (mapping && mapping->a_ops->releasepage)
- return mapping->a_ops->releasepage(page, gfp_mask);
- return try_to_free_buffers(page);
-}
-EXPORT_SYMBOL(try_to_release_page);
-
-/**
* block_invalidatepage - invalidate part of all of a buffer-backed page
*
* @page: the page which is affected
@@ -1630,14 +1464,6 @@ out:
}
EXPORT_SYMBOL(block_invalidatepage);
-void do_invalidatepage(struct page *page, unsigned long offset)
-{
- void (*invalidatepage)(struct page *, unsigned long);
- invalidatepage = page->mapping->a_ops->invalidatepage ? :
- block_invalidatepage;
- (*invalidatepage)(page, offset);
-}
-
/*
* We attach and possibly dirty the buffers atomically wrt
* __set_page_dirty_buffers() via private_lock. try_to_free_buffers
diff --git a/fs/super.c b/fs/super.c
index 6987824..15671cd 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -220,6 +220,37 @@ static int grab_super(struct super_block *s) __releases(sb_lock)
return 0;
}
+/*
+ * Write out and wait upon all dirty data associated with this
+ * superblock. Filesystem data as well as the underlying block
+ * device. Takes the superblock lock. Requires a second blkdev
+ * flush by the caller to complete the operation.
+ */
+void __fsync_super(struct super_block *sb)
+{
+ sync_inodes_sb(sb, 0);
+ DQUOT_SYNC(sb);
+ lock_super(sb);
+ if (sb->s_dirt && sb->s_op->write_super)
+ sb->s_op->write_super(sb);
+ unlock_super(sb);
+ if (sb->s_op->sync_fs)
+ sb->s_op->sync_fs(sb, 1);
+ sync_blockdev(sb->s_bdev);
+ sync_inodes_sb(sb, 1);
+}
+
+/*
+ * Write out and wait upon all dirty data associated with this
+ * superblock. Filesystem data as well as the underlying block
+ * device. Takes the superblock lock.
+ */
+int fsync_super(struct super_block *sb)
+{
+ __fsync_super(sb);
+ return sync_blockdev(sb->s_bdev);
+}
+
/**
* generic_shutdown_super - common helper for ->kill_sb()
* @sb: superblock to kill
diff --git a/fs/sync.c b/fs/sync.c
index 955aef0..1de747b 100644
--- a/fs/sync.c
+++ b/fs/sync.c
@@ -10,11 +10,124 @@
#include <linux/syscalls.h>
#include <linux/linkage.h>
#include <linux/pagemap.h>
+#include <linux/quotaops.h>
+#include <linux/buffer_head.h>
#define VALID_FLAGS (SYNC_FILE_RANGE_WAIT_BEFORE|SYNC_FILE_RANGE_WRITE| \
SYNC_FILE_RANGE_WAIT_AFTER)
/*
+ * sync everything. Start out by waking pdflush, because that writes back
+ * all queues in parallel.
+ */
+static void do_sync(unsigned long wait)
+{
+ wakeup_pdflush(0);
+ sync_inodes(0); /* All mappings, inodes and their blockdevs */
+ DQUOT_SYNC(NULL);
+ sync_supers(); /* Write the superblocks */
+ sync_filesystems(0); /* Start syncing the filesystems */
+ sync_filesystems(wait); /* Waitingly sync the filesystems */
+ sync_inodes(wait); /* Mappings, inodes and blockdevs, again. */
+ if (!wait)
+ printk("Emergency Sync complete\n");
+ if (unlikely(laptop_mode))
+ laptop_sync_completion();
+}
+
+asmlinkage long sys_sync(void)
+{
+ do_sync(1);
+ return 0;
+}
+
+void emergency_sync(void)
+{
+ pdflush_operation(do_sync, 0);
+}
+
+/*
+ * Generic function to fsync a file.
+ *
+ * filp may be NULL if called via the msync of a vma.
+ */
+int file_fsync(struct file *filp, struct dentry *dentry, int datasync)
+{
+ struct inode * inode = dentry->d_inode;
+ struct super_block * sb;
+ int ret, err;
+
+ /* sync the inode to buffers */
+ ret = write_inode_now(inode, 0);
+
+ /* sync the superblock to buffers */
+ sb = inode->i_sb;
+ lock_super(sb);
+ if (sb->s_op->write_super)
+ sb->s_op->write_super(sb);
+ unlock_super(sb);
+
+ /* .. finally sync the buffers to disk */
+ err = sync_blockdev(sb->s_bdev);
+ if (!ret)
+ ret = err;
+ return ret;
+}
+
+long do_fsync(struct file *file, int datasync)
+{
+ int ret;
+ int err;
+ struct address_space *mapping = file->f_mapping;
+
+ if (!file->f_op || !file->f_op->fsync) {
+ /* Why? We can still call filemap_fdatawrite */
+ ret = -EINVAL;
+ goto out;
+ }
+
+ ret = filemap_fdatawrite(mapping);
+
+ /*
+ * We need to protect against concurrent writers, which could cause
+ * livelocks in fsync_buffers_list().
+ */
+ mutex_lock(&mapping->host->i_mutex);
+ err = file->f_op->fsync(file, file->f_dentry, datasync);
+ if (!ret)
+ ret = err;
+ mutex_unlock(&mapping->host->i_mutex);
+ err = filemap_fdatawait(mapping);
+ if (!ret)
+ ret = err;
+out:
+ return ret;
+}
+
+static long __do_fsync(unsigned int fd, int datasync)
+{
+ struct file *file;
+ int ret = -EBADF;
+
+ file = fget(fd);
+ if (file) {
+ ret = do_fsync(file, datasync);
+ fput(file);
+ }
+ return ret;
+}
+
+asmlinkage long sys_fsync(unsigned int fd)
+{
+ return __do_fsync(fd, 0);
+}
+
+asmlinkage long sys_fdatasync(unsigned int fd)
+{
+ return __do_fsync(fd, 1);
+}
+
+/*
* sys_sync_file_range() permits finely controlled syncing over a segment of
* a file in the range offset .. (offset+nbytes-1) inclusive. If nbytes is
* zero then sys_sync_file_range() will operate from offset out to EOF.
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index 737e407..64b508e 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -190,9 +190,7 @@ extern int buffer_heads_over_limit;
* Generic address_space_operations implementations for buffer_head-backed
* address_spaces.
*/
-int try_to_release_page(struct page * page, gfp_t gfp_mask);
void block_invalidatepage(struct page *page, unsigned long offset);
-void do_invalidatepage(struct page *page, unsigned long offset);
int block_write_full_page(struct page *page, get_block_t *get_block,
struct writeback_control *wbc);
int block_read_full_page(struct page*, get_block_t*);
@@ -302,4 +300,5 @@ static inline void lock_buffer(struct buffer_head *bh)
__lock_buffer(bh);
}
+extern int __set_page_dirty_buffers(struct page *page);
#endif /* _LINUX_BUFFER_HEAD_H */
diff --git a/include/linux/fs.h b/include/linux/fs.h
index d68c37a..1728142 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1546,6 +1546,7 @@ extern int __filemap_fdatawrite_range(struct address_space *mapping,
extern long do_fsync(struct file *file, int datasync);
extern void sync_supers(void);
extern void sync_filesystems(int wait);
+extern void __fsync_super(struct super_block *sb);
extern void emergency_sync(void);
extern void emergency_remount(void);
extern int do_remount_sb(struct super_block *sb, int flags,
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 7b703b6..4edf193 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -743,7 +743,9 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm, unsigned long
int len, int write, int force, struct page **pages, struct vm_area_struct **vmas);
void print_bad_pte(struct vm_area_struct *, pte_t, unsigned long);
-int __set_page_dirty_buffers(struct page *page);
+extern int try_to_release_page(struct page * page, gfp_t gfp_mask);
+extern void do_invalidatepage(struct page *page, unsigned long offset);
+
int __set_page_dirty_nobuffers(struct page *page);
int redirty_page_for_writepage(struct writeback_control *wbc,
struct page *page);
diff --git a/mm/filemap.c b/mm/filemap.c
index 3277f3b..d6846de 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2491,3 +2491,33 @@ generic_file_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
}
return retval;
}
+
+/**
+ * try_to_release_page() - release old fs-specific metadata on a page
+ *
+ * @page: the page which the kernel is trying to free
+ * @gfp_mask: memory allocation flags (and I/O mode)
+ *
+ * The address_space is to try to release any data against the page
+ * (presumably at page->private). If the release was successful, return `1'.
+ * Otherwise return zero.
+ *
+ * The @gfp_mask argument specifies whether I/O may be performed to release
+ * this page (__GFP_IO), and whether the call may block (__GFP_WAIT).
+ *
+ * NOTE: @gfp_mask may go away, and this function may become non-blocking.
+ */
+int try_to_release_page(struct page *page, gfp_t gfp_mask)
+{
+ struct address_space * const mapping = page->mapping;
+
+ BUG_ON(!PageLocked(page));
+ if (PageWriteback(page))
+ return 0;
+
+ if (mapping && mapping->a_ops->releasepage)
+ return mapping->a_ops->releasepage(page, gfp_mask);
+ return try_to_free_buffers(page);
+}
+
+EXPORT_SYMBOL(try_to_release_page);
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 488b708..9fdcc79 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -30,6 +30,7 @@
#include <linux/sysctl.h>
#include <linux/cpu.h>
#include <linux/syscalls.h>
+#include <linux/buffer_head.h>
/*
* The maximum number of pages to writeout in a single bdflush/kupdate
diff --git a/mm/truncate.c b/mm/truncate.c
index a654928..cd3e34b 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -17,6 +17,30 @@
do_invalidatepage */
+/**
+ * do_invalidatepage - invalidate part of all of a page
+ * @page: the page which is affected
+ * @offset: the index of the truncation point
+ *
+ * do_invalidatepage() is called when all or part of the page has become
+ * invalidated by a truncate operation.
+ *
+ * do_invalidatepage() does not have to release all buffers, but it must
+ * ensure that no dirty buffer is left outside @offset and that no I/O
+ * is underway against any of the blocks which are outside the truncation
+ * point. Because the caller is about to free (and possibly reuse) those
+ * blocks on-disk.
+ */
+void do_invalidatepage(struct page *page, unsigned long offset)
+{
+ void (*invalidatepage)(struct page *, unsigned long);
+ invalidatepage = page->mapping->a_ops->invalidatepage;
+ if (!invalidatepage)
+ invalidatepage = block_invalidatepage;
+ if (invalidatepage)
+ (*invalidatepage)(page, offset);
+}
+
static inline void truncate_partial_page(struct page *page, unsigned partial)
{
memclear_highpage_flush(page, partial, PAGE_CACHE_SIZE-partial);