[PATCH 00/18] BLOCK: Permit block layer to be disabled [try #4]

[PATCH 00/18] BLOCK: Permit block layer to be disabled [try #4]

[David Howells]

This set of patches permits the block layer to be disabled and removed from
the compilation such that it doesn't take up any resources on systems that
don't need it.

This set of patches is against the block git tree.

David

[PATCH 01/18] [PATCH] BLOCK: Move functions out of buffer code [try #4]

[David Howells]

From: David Howells <dhowells@redhat.com>

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>
---

 fs/buffer.c                 |  174 -------------------------------------------
 fs/super.c                  |   31 ++++++++
 fs/sync.c                   |  113 ++++++++++++++++++++++++++++
 include/linux/buffer_head.h |    3 -
 include/linux/fs.h          |    1 
 include/linux/mm.h          |    4 +
 mm/filemap.c                |   30 +++++++
 mm/page-writeback.c         |    1 
 mm/truncate.c               |   24 ++++++
 9 files changed, 204 insertions(+), 177 deletions(-)

diff --git a/fs/buffer.c b/fs/buffer.c
index 71649ef..314b9c4 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -159,31 +159,6 @@ int sync_blockdev(struct block_device *b
 }
 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
 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
 }
 
 /**
- * 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 6d4e817..22c2fd1 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -219,6 +219,37 @@ static int grab_super(struct super_block
 	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/writeback.h>
 #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 bu
 		__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 0599da8..cd7fc6a 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1541,6 +1541,7 @@ extern int __filemap_fdatawrite_range(st
 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 990957e..72867ac 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -766,7 +766,9 @@ int get_user_pages(struct task_struct *t
 		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 b9a60c4..20a8a9b 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2474,3 +2474,33 @@ generic_file_direct_IO(int rw, struct ki
 	}
 	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 e630188..f75d033 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -29,6 +29,7 @@ #include <linux/smp.h>
 #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 cf1b015..4b742cf 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -16,6 +16,30 @@ #include <linux/buffer_head.h>	/* grr. t
 				   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);

[PATCH 02/18] [PATCH] BLOCK: Remove duplicate declaration of exit_io_context() [try #4]

[David Howells]

From: David Howells <dhowells@redhat.com>

Remove the duplicate declaration of exit_io_context() from linux/sched.h.

Signed-Off-By: David Howells <dhowells@redhat.com>
---

 include/linux/sched.h |    1 -
 kernel/exit.c         |    1 +
 2 files changed, 1 insertions(+), 1 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 6674fc1..c12c5f9 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -709,7 +709,6 @@ #endif	/* CONFIG_SMP */
 
 
 struct io_context;			/* See blkdev.h */
-void exit_io_context(void);
 struct cpuset;
 
 #define NGROUPS_SMALL		32
diff --git a/kernel/exit.c b/kernel/exit.c
index dba194a..e0abd78 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -38,6 +38,7 @@ #include <linux/compat.h>
 #include <linux/pipe_fs_i.h>
 #include <linux/audit.h> /* for audit_free() */
 #include <linux/resource.h>
+#include <linux/blkdev.h>
 
 #include <asm/uaccess.h>
 #include <asm/unistd.h>

[PATCH 03/18] [PATCH] BLOCK: Stop fallback_migrate_page() from using page_has_buffers() [try #4]

[David Howells]

From: David Howells <dhowells@redhat.com>

Stop fallback_migrate_page() from using page_has_buffers() since that might not
be available.  Use PagePrivate() instead since that's more general.

Signed-Off-By: David Howells <dhowells@redhat.com>
---

 mm/migrate.c |    2 +-
 1 files changed, 1 insertions(+), 1 deletions(-)

diff --git a/mm/migrate.c b/mm/migrate.c
index 3f1e0c2..0227163 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -525,7 +525,7 @@ static int fallback_migrate_page(struct 
 	 * Buffers may be managed in a filesystem specific way.
 	 * We must have no buffers or drop them.
 	 */
-	if (page_has_buffers(page) &&
+	if (PagePrivate(page) &&
 	    !try_to_release_page(page, GFP_KERNEL))
 		return -EAGAIN;
 

[PATCH 04/18] [PATCH] BLOCK: Separate the bounce buffering code from the highmem code [try #4]

[David Howells]

From: David Howells <dhowells@redhat.com>

Move the bounce buffer code from mm/highmem.c to mm/bounce.c so that it can be
more easily disabled when the block layer is disabled.

!!!NOTE!!! There may be a bug in this code: Should init_emergency_pool() be
	   contingent on CONFIG_HIGHMEM?

Signed-Off-By: David Howells <dhowells@redhat.com>
---

 mm/Makefile  |    4 +
 mm/bounce.c  |  302 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
 mm/highmem.c |  281 ------------------------------------------------------
 3 files changed, 305 insertions(+), 282 deletions(-)

diff --git a/mm/Makefile b/mm/Makefile
index 9dd824c..63637f0 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -12,6 +12,9 @@ obj-y			:= bootmem.o filemap.o mempool.o
 			   readahead.o swap.o truncate.o vmscan.o \
 			   prio_tree.o util.o mmzone.o vmstat.o $(mmu-y)
 
+ifeq ($(CONFIG_MMU),y)
+obj-y			+= bounce.o
+endif
 obj-$(CONFIG_SWAP)	+= page_io.o swap_state.o swapfile.o thrash.o
 obj-$(CONFIG_HUGETLBFS)	+= hugetlb.o
 obj-$(CONFIG_NUMA) 	+= mempolicy.o
@@ -23,4 +26,3 @@ obj-$(CONFIG_SLAB) += slab.o
 obj-$(CONFIG_MEMORY_HOTPLUG) += memory_hotplug.o
 obj-$(CONFIG_FS_XIP) += filemap_xip.o
 obj-$(CONFIG_MIGRATION) += migrate.o
-
diff --git a/mm/bounce.c b/mm/bounce.c
new file mode 100644
index 0000000..e4b62d2
--- /dev/null
+++ b/mm/bounce.c
@@ -0,0 +1,302 @@
+/* bounce buffer handling for block devices
+ *
+ * - Split from highmem.c
+ */
+
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/swap.h>
+#include <linux/bio.h>
+#include <linux/pagemap.h>
+#include <linux/mempool.h>
+#include <linux/blkdev.h>
+#include <linux/init.h>
+#include <linux/hash.h>
+#include <linux/highmem.h>
+#include <linux/blktrace_api.h>
+#include <asm/tlbflush.h>
+
+#define POOL_SIZE	64
+#define ISA_POOL_SIZE	16
+
+static mempool_t *page_pool, *isa_page_pool;
+
+#ifdef CONFIG_HIGHMEM
+static __init int init_emergency_pool(void)
+{
+	struct sysinfo i;
+	si_meminfo(&i);
+	si_swapinfo(&i);
+
+	if (!i.totalhigh)
+		return 0;
+
+	page_pool = mempool_create_page_pool(POOL_SIZE, 0);
+	BUG_ON(!page_pool);
+	printk("highmem bounce pool size: %d pages\n", POOL_SIZE);
+
+	return 0;
+}
+
+__initcall(init_emergency_pool);
+
+/*
+ * highmem version, map in to vec
+ */
+static void bounce_copy_vec(struct bio_vec *to, unsigned char *vfrom)
+{
+	unsigned long flags;
+	unsigned char *vto;
+
+	local_irq_save(flags);
+	vto = kmap_atomic(to->bv_page, KM_BOUNCE_READ);
+	memcpy(vto + to->bv_offset, vfrom, to->bv_len);
+	kunmap_atomic(vto, KM_BOUNCE_READ);
+	local_irq_restore(flags);
+}
+
+#else /* CONFIG_HIGHMEM */
+
+#define bounce_copy_vec(to, vfrom)	\
+	memcpy(page_address((to)->bv_page) + (to)->bv_offset, vfrom, (to)->bv_len)
+
+#endif /* CONFIG_HIGHMEM */
+
+/*
+ * allocate pages in the DMA region for the ISA pool
+ */
+static void *mempool_alloc_pages_isa(gfp_t gfp_mask, void *data)
+{
+	return mempool_alloc_pages(gfp_mask | GFP_DMA, data);
+}
+
+/*
+ * gets called "every" time someone init's a queue with BLK_BOUNCE_ISA
+ * as the max address, so check if the pool has already been created.
+ */
+int init_emergency_isa_pool(void)
+{
+	if (isa_page_pool)
+		return 0;
+
+	isa_page_pool = mempool_create(ISA_POOL_SIZE, mempool_alloc_pages_isa,
+				       mempool_free_pages, (void *) 0);
+	BUG_ON(!isa_page_pool);
+
+	printk("isa bounce pool size: %d pages\n", ISA_POOL_SIZE);
+	return 0;
+}
+
+/*
+ * Simple bounce buffer support for highmem pages. Depending on the
+ * queue gfp mask set, *to may or may not be a highmem page. kmap it
+ * always, it will do the Right Thing
+ */
+static void copy_to_high_bio_irq(struct bio *to, struct bio *from)
+{
+	unsigned char *vfrom;
+	struct bio_vec *tovec, *fromvec;
+	int i;
+
+	__bio_for_each_segment(tovec, to, i, 0) {
+		fromvec = from->bi_io_vec + i;
+
+		/*
+		 * not bounced
+		 */
+		if (tovec->bv_page == fromvec->bv_page)
+			continue;
+
+		/*
+		 * fromvec->bv_offset and fromvec->bv_len might have been
+		 * modified by the block layer, so use the original copy,
+		 * bounce_copy_vec already uses tovec->bv_len
+		 */
+		vfrom = page_address(fromvec->bv_page) + tovec->bv_offset;
+
+		flush_dcache_page(tovec->bv_page);
+		bounce_copy_vec(tovec, vfrom);
+	}
+}
+
+static void bounce_end_io(struct bio *bio, mempool_t *pool, int err)
+{
+	struct bio *bio_orig = bio->bi_private;
+	struct bio_vec *bvec, *org_vec;
+	int i;
+
+	if (test_bit(BIO_EOPNOTSUPP, &bio->bi_flags))
+		set_bit(BIO_EOPNOTSUPP, &bio_orig->bi_flags);
+
+	/*
+	 * free up bounce indirect pages used
+	 */
+	__bio_for_each_segment(bvec, bio, i, 0) {
+		org_vec = bio_orig->bi_io_vec + i;
+		if (bvec->bv_page == org_vec->bv_page)
+			continue;
+
+		dec_zone_page_state(bvec->bv_page, NR_BOUNCE);
+		mempool_free(bvec->bv_page, pool);
+	}
+
+	bio_endio(bio_orig, bio_orig->bi_size, err);
+	bio_put(bio);
+}
+
+static int bounce_end_io_write(struct bio *bio, unsigned int bytes_done, int err)
+{
+	if (bio->bi_size)
+		return 1;
+
+	bounce_end_io(bio, page_pool, err);
+	return 0;
+}
+
+static int bounce_end_io_write_isa(struct bio *bio, unsigned int bytes_done, int err)
+{
+	if (bio->bi_size)
+		return 1;
+
+	bounce_end_io(bio, isa_page_pool, err);
+	return 0;
+}
+
+static void __bounce_end_io_read(struct bio *bio, mempool_t *pool, int err)
+{
+	struct bio *bio_orig = bio->bi_private;
+
+	if (test_bit(BIO_UPTODATE, &bio->bi_flags))
+		copy_to_high_bio_irq(bio_orig, bio);
+
+	bounce_end_io(bio, pool, err);
+}
+
+static int bounce_end_io_read(struct bio *bio, unsigned int bytes_done, int err)
+{
+	if (bio->bi_size)
+		return 1;
+
+	__bounce_end_io_read(bio, page_pool, err);
+	return 0;
+}
+
+static int bounce_end_io_read_isa(struct bio *bio, unsigned int bytes_done, int err)
+{
+	if (bio->bi_size)
+		return 1;
+
+	__bounce_end_io_read(bio, isa_page_pool, err);
+	return 0;
+}
+
+static void __blk_queue_bounce(request_queue_t *q, struct bio **bio_orig,
+			       mempool_t *pool)
+{
+	struct page *page;
+	struct bio *bio = NULL;
+	int i, rw = bio_data_dir(*bio_orig);
+	struct bio_vec *to, *from;
+
+	bio_for_each_segment(from, *bio_orig, i) {
+		page = from->bv_page;
+
+		/*
+		 * is destination page below bounce pfn?
+		 */
+		if (page_to_pfn(page) < q->bounce_pfn)
+			continue;
+
+		/*
+		 * irk, bounce it
+		 */
+		if (!bio)
+			bio = bio_alloc(GFP_NOIO, (*bio_orig)->bi_vcnt);
+
+		to = bio->bi_io_vec + i;
+
+		to->bv_page = mempool_alloc(pool, q->bounce_gfp);
+		to->bv_len = from->bv_len;
+		to->bv_offset = from->bv_offset;
+		inc_zone_page_state(to->bv_page, NR_BOUNCE);
+
+		if (rw == WRITE) {
+			char *vto, *vfrom;
+
+			flush_dcache_page(from->bv_page);
+			vto = page_address(to->bv_page) + to->bv_offset;
+			vfrom = kmap(from->bv_page) + from->bv_offset;
+			memcpy(vto, vfrom, to->bv_len);
+			kunmap(from->bv_page);
+		}
+	}
+
+	/*
+	 * no pages bounced
+	 */
+	if (!bio)
+		return;
+
+	/*
+	 * at least one page was bounced, fill in possible non-highmem
+	 * pages
+	 */
+	__bio_for_each_segment(from, *bio_orig, i, 0) {
+		to = bio_iovec_idx(bio, i);
+		if (!to->bv_page) {
+			to->bv_page = from->bv_page;
+			to->bv_len = from->bv_len;
+			to->bv_offset = from->bv_offset;
+		}
+	}
+
+	bio->bi_bdev = (*bio_orig)->bi_bdev;
+	bio->bi_flags |= (1 << BIO_BOUNCED);
+	bio->bi_sector = (*bio_orig)->bi_sector;
+	bio->bi_rw = (*bio_orig)->bi_rw;
+
+	bio->bi_vcnt = (*bio_orig)->bi_vcnt;
+	bio->bi_idx = (*bio_orig)->bi_idx;
+	bio->bi_size = (*bio_orig)->bi_size;
+
+	if (pool == page_pool) {
+		bio->bi_end_io = bounce_end_io_write;
+		if (rw == READ)
+			bio->bi_end_io = bounce_end_io_read;
+	} else {
+		bio->bi_end_io = bounce_end_io_write_isa;
+		if (rw == READ)
+			bio->bi_end_io = bounce_end_io_read_isa;
+	}
+
+	bio->bi_private = *bio_orig;
+	*bio_orig = bio;
+}
+
+void blk_queue_bounce(request_queue_t *q, struct bio **bio_orig)
+{
+	mempool_t *pool;
+
+	/*
+	 * for non-isa bounce case, just check if the bounce pfn is equal
+	 * to or bigger than the highest pfn in the system -- in that case,
+	 * don't waste time iterating over bio segments
+	 */
+	if (!(q->bounce_gfp & GFP_DMA)) {
+		if (q->bounce_pfn >= blk_max_pfn)
+			return;
+		pool = page_pool;
+	} else {
+		BUG_ON(!isa_page_pool);
+		pool = isa_page_pool;
+	}
+
+	blk_add_trace_bio(q, *bio_orig, BLK_TA_BOUNCE);
+
+	/*
+	 * slow path
+	 */
+	__blk_queue_bounce(q, bio_orig, pool);
+}
+
+EXPORT_SYMBOL(blk_queue_bounce);
diff --git a/mm/highmem.c b/mm/highmem.c
index 9b2a540..1ac20d6 100644
--- a/mm/highmem.c
+++ b/mm/highmem.c
@@ -29,13 +29,6 @@ #include <linux/highmem.h>
 #include <linux/blktrace_api.h>
 #include <asm/tlbflush.h>
 
-static mempool_t *page_pool, *isa_page_pool;
-
-static void *mempool_alloc_pages_isa(gfp_t gfp_mask, void *data)
-{
-	return mempool_alloc_pages(gfp_mask | GFP_DMA, data);
-}
-
 /*
  * Virtual_count is not a pure "count".
  *  0 means that it is not mapped, and has not been mapped
@@ -204,282 +197,8 @@ void fastcall kunmap_high(struct page *p
 }
 
 EXPORT_SYMBOL(kunmap_high);
-
-#define POOL_SIZE	64
-
-static __init int init_emergency_pool(void)
-{
-	struct sysinfo i;
-	si_meminfo(&i);
-	si_swapinfo(&i);
-        
-	if (!i.totalhigh)
-		return 0;
-
-	page_pool = mempool_create_page_pool(POOL_SIZE, 0);
-	BUG_ON(!page_pool);
-	printk("highmem bounce pool size: %d pages\n", POOL_SIZE);
-
-	return 0;
-}
-
-__initcall(init_emergency_pool);
-
-/*
- * highmem version, map in to vec
- */
-static void bounce_copy_vec(struct bio_vec *to, unsigned char *vfrom)
-{
-	unsigned long flags;
-	unsigned char *vto;
-
-	local_irq_save(flags);
-	vto = kmap_atomic(to->bv_page, KM_BOUNCE_READ);
-	memcpy(vto + to->bv_offset, vfrom, to->bv_len);
-	kunmap_atomic(vto, KM_BOUNCE_READ);
-	local_irq_restore(flags);
-}
-
-#else /* CONFIG_HIGHMEM */
-
-#define bounce_copy_vec(to, vfrom)	\
-	memcpy(page_address((to)->bv_page) + (to)->bv_offset, vfrom, (to)->bv_len)
-
 #endif
 
-#define ISA_POOL_SIZE	16
-
-/*
- * gets called "every" time someone init's a queue with BLK_BOUNCE_ISA
- * as the max address, so check if the pool has already been created.
- */
-int init_emergency_isa_pool(void)
-{
-	if (isa_page_pool)
-		return 0;
-
-	isa_page_pool = mempool_create(ISA_POOL_SIZE, mempool_alloc_pages_isa,
-				       mempool_free_pages, (void *) 0);
-	BUG_ON(!isa_page_pool);
-
-	printk("isa bounce pool size: %d pages\n", ISA_POOL_SIZE);
-	return 0;
-}
-
-/*
- * Simple bounce buffer support for highmem pages. Depending on the
- * queue gfp mask set, *to may or may not be a highmem page. kmap it
- * always, it will do the Right Thing
- */
-static void copy_to_high_bio_irq(struct bio *to, struct bio *from)
-{
-	unsigned char *vfrom;
-	struct bio_vec *tovec, *fromvec;
-	int i;
-
-	__bio_for_each_segment(tovec, to, i, 0) {
-		fromvec = from->bi_io_vec + i;
-
-		/*
-		 * not bounced
-		 */
-		if (tovec->bv_page == fromvec->bv_page)
-			continue;
-
-		/*
-		 * fromvec->bv_offset and fromvec->bv_len might have been
-		 * modified by the block layer, so use the original copy,
-		 * bounce_copy_vec already uses tovec->bv_len
-		 */
-		vfrom = page_address(fromvec->bv_page) + tovec->bv_offset;
-
-		flush_dcache_page(tovec->bv_page);
-		bounce_copy_vec(tovec, vfrom);
-	}
-}
-
-static void bounce_end_io(struct bio *bio, mempool_t *pool, int err)
-{
-	struct bio *bio_orig = bio->bi_private;
-	struct bio_vec *bvec, *org_vec;
-	int i;
-
-	if (test_bit(BIO_EOPNOTSUPP, &bio->bi_flags))
-		set_bit(BIO_EOPNOTSUPP, &bio_orig->bi_flags);
-
-	/*
-	 * free up bounce indirect pages used
-	 */
-	__bio_for_each_segment(bvec, bio, i, 0) {
-		org_vec = bio_orig->bi_io_vec + i;
-		if (bvec->bv_page == org_vec->bv_page)
-			continue;
-
-		dec_zone_page_state(bvec->bv_page, NR_BOUNCE);
-		mempool_free(bvec->bv_page, pool);
-	}
-
-	bio_endio(bio_orig, bio_orig->bi_size, err);
-	bio_put(bio);
-}
-
-static int bounce_end_io_write(struct bio *bio, unsigned int bytes_done, int err)
-{
-	if (bio->bi_size)
-		return 1;
-
-	bounce_end_io(bio, page_pool, err);
-	return 0;
-}
-
-static int bounce_end_io_write_isa(struct bio *bio, unsigned int bytes_done, int err)
-{
-	if (bio->bi_size)
-		return 1;
-
-	bounce_end_io(bio, isa_page_pool, err);
-	return 0;
-}
-
-static void __bounce_end_io_read(struct bio *bio, mempool_t *pool, int err)
-{
-	struct bio *bio_orig = bio->bi_private;
-
-	if (test_bit(BIO_UPTODATE, &bio->bi_flags))
-		copy_to_high_bio_irq(bio_orig, bio);
-
-	bounce_end_io(bio, pool, err);
-}
-
-static int bounce_end_io_read(struct bio *bio, unsigned int bytes_done, int err)
-{
-	if (bio->bi_size)
-		return 1;
-
-	__bounce_end_io_read(bio, page_pool, err);
-	return 0;
-}
-
-static int bounce_end_io_read_isa(struct bio *bio, unsigned int bytes_done, int err)
-{
-	if (bio->bi_size)
-		return 1;
-
-	__bounce_end_io_read(bio, isa_page_pool, err);
-	return 0;
-}
-
-static void __blk_queue_bounce(request_queue_t *q, struct bio **bio_orig,
-			       mempool_t *pool)
-{
-	struct page *page;
-	struct bio *bio = NULL;
-	int i, rw = bio_data_dir(*bio_orig);
-	struct bio_vec *to, *from;
-
-	bio_for_each_segment(from, *bio_orig, i) {
-		page = from->bv_page;
-
-		/*
-		 * is destination page below bounce pfn?
-		 */
-		if (page_to_pfn(page) < q->bounce_pfn)
-			continue;
-
-		/*
-		 * irk, bounce it
-		 */
-		if (!bio)
-			bio = bio_alloc(GFP_NOIO, (*bio_orig)->bi_vcnt);
-
-		to = bio->bi_io_vec + i;
-
-		to->bv_page = mempool_alloc(pool, q->bounce_gfp);
-		to->bv_len = from->bv_len;
-		to->bv_offset = from->bv_offset;
-		inc_zone_page_state(to->bv_page, NR_BOUNCE);
-
-		if (rw == WRITE) {
-			char *vto, *vfrom;
-
-			flush_dcache_page(from->bv_page);
-			vto = page_address(to->bv_page) + to->bv_offset;
-			vfrom = kmap(from->bv_page) + from->bv_offset;
-			memcpy(vto, vfrom, to->bv_len);
-			kunmap(from->bv_page);
-		}
-	}
-
-	/*
-	 * no pages bounced
-	 */
-	if (!bio)
-		return;
-
-	/*
-	 * at least one page was bounced, fill in possible non-highmem
-	 * pages
-	 */
-	__bio_for_each_segment(from, *bio_orig, i, 0) {
-		to = bio_iovec_idx(bio, i);
-		if (!to->bv_page) {
-			to->bv_page = from->bv_page;
-			to->bv_len = from->bv_len;
-			to->bv_offset = from->bv_offset;
-		}
-	}
-
-	bio->bi_bdev = (*bio_orig)->bi_bdev;
-	bio->bi_flags |= (1 << BIO_BOUNCED);
-	bio->bi_sector = (*bio_orig)->bi_sector;
-	bio->bi_rw = (*bio_orig)->bi_rw;
-
-	bio->bi_vcnt = (*bio_orig)->bi_vcnt;
-	bio->bi_idx = (*bio_orig)->bi_idx;
-	bio->bi_size = (*bio_orig)->bi_size;
-
-	if (pool == page_pool) {
-		bio->bi_end_io = bounce_end_io_write;
-		if (rw == READ)
-			bio->bi_end_io = bounce_end_io_read;
-	} else {
-		bio->bi_end_io = bounce_end_io_write_isa;
-		if (rw == READ)
-			bio->bi_end_io = bounce_end_io_read_isa;
-	}
-
-	bio->bi_private = *bio_orig;
-	*bio_orig = bio;
-}
-
-void blk_queue_bounce(request_queue_t *q, struct bio **bio_orig)
-{
-	mempool_t *pool;
-
-	/*
-	 * for non-isa bounce case, just check if the bounce pfn is equal
-	 * to or bigger than the highest pfn in the system -- in that case,
-	 * don't waste time iterating over bio segments
-	 */
-	if (!(q->bounce_gfp & GFP_DMA)) {
-		if (q->bounce_pfn >= blk_max_pfn)
-			return;
-		pool = page_pool;
-	} else {
-		BUG_ON(!isa_page_pool);
-		pool = isa_page_pool;
-	}
-
-	blk_add_trace_bio(q, *bio_orig, BLK_TA_BOUNCE);
-
-	/*
-	 * slow path
-	 */
-	__blk_queue_bounce(q, bio_orig, pool);
-}
-
-EXPORT_SYMBOL(blk_queue_bounce);
-
 #if defined(HASHED_PAGE_VIRTUAL)
 
 #define PA_HASH_ORDER	7

Re: [PATCH 04/18] [PATCH] BLOCK: Separate the bounce buffering code from the highmem code [try #4]

[Sam Ravnborg]

On Fri, Aug 25, 2006 at 08:37:07PM +0100, David Howells wrote:
> From: David Howells <dhowells@redhat.com>
> 
> Move the bounce buffer code from mm/highmem.c to mm/bounce.c so that it can be
> more easily disabled when the block layer is disabled.
> 
> !!!NOTE!!! There may be a bug in this code: Should init_emergency_pool() be
> 	   contingent on CONFIG_HIGHMEM?
> 
> Signed-Off-By: David Howells <dhowells@redhat.com>
> ---
> 
>  mm/Makefile  |    4 +
>  mm/bounce.c  |  302 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
>  mm/highmem.c |  281 ------------------------------------------------------
>  3 files changed, 305 insertions(+), 282 deletions(-)
> 
> diff --git a/mm/Makefile b/mm/Makefile
> index 9dd824c..63637f0 100644
> --- a/mm/Makefile
> +++ b/mm/Makefile
> @@ -12,6 +12,9 @@ obj-y			:= bootmem.o filemap.o mempool.o
>  			   readahead.o swap.o truncate.o vmscan.o \
>  			   prio_tree.o util.o mmzone.o vmstat.o $(mmu-y)
>  
> +ifeq ($(CONFIG_MMU),y)
> +obj-y			+= bounce.o
> +endif

CONFIG_MMU is a bool so you can do this much more elegant:
obj-$(CONFIG_MMU) += bounce.o


	Sam

Re: [PATCH 04/18] [PATCH] BLOCK: Separate the bounce buffering code from the highmem code [try #4]

[David Howells]

Sam Ravnborg <sam@ravnborg.org> wrote:

> > +ifeq ($(CONFIG_MMU),y)
> > +obj-y			+= bounce.o
> > +endif
> 
> CONFIG_MMU is a bool so you can do this much more elegant:
> obj-$(CONFIG_MMU) += bounce.o

In patch 18/18, this changes to:

	ifeq ($(CONFIG_MMU)$(CONFIG_BLOCK),yy)

So the elegence in the end is irrelevant.

David

Re: [PATCH 04/18] [PATCH] BLOCK: Separate the bounce buffering code from the highmem code [try #4]

[Arnd Bergmann]

On Friday 25 August 2006 22:18, David Howells wrote:
> > > +ifeq ($(CONFIG_MMU),y)
> > > +obj-y                      += bounce.o
> > > +endif
> > 
> > CONFIG_MMU is a bool so you can do this much more elegant:
> > obj-$(CONFIG_MMU) += bounce.o
> 
> In patch 18/18, this changes to:
> 
>         ifeq ($(CONFIG_MMU)$(CONFIG_BLOCK),yy)
> 
> So the elegence in the end is irrelevant.

You could write it as

bounce-$(CONFIG_MMU) += bounce.o
obj-$(CONFIG_BLOCK)  += $(bounce-y)

	Arnd <><

Re: [PATCH 04/18] [PATCH] BLOCK: Separate the bounce buffering code from the highmem code [try #4]

[Arnd Bergmann]

On Friday 25 August 2006 22:18, David Howells wrote:
> > > +ifeq ($(CONFIG_MMU),y)
> > > +obj-y                      += bounce.o
> > > +endif
> > 
> > CONFIG_MMU is a bool so you can do this much more elegant:
> > obj-$(CONFIG_MMU) += bounce.o
> 
> In patch 18/18, this changes to:
> 
>         ifeq ($(CONFIG_MMU)$(CONFIG_BLOCK),yy)
> 
> So the elegence in the end is irrelevant.

You could write it as

bounce-$(CONFIG_MMU) += bounce.o
obj-$(CONFIG_BLOCK)  += $(bounce-y)

	Arnd <><
-
To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Re: [PATCH 04/18] [PATCH] BLOCK: Separate the bounce buffering code from the highmem code [try #4]

[David Howells]

Arnd Bergmann <arnd.bergmann@de.ibm.com> wrote:

> You could write it as
> 
> bounce-$(CONFIG_MMU) += bounce.o
> obj-$(CONFIG_BLOCK)  += $(bounce-y)

I could, yes, but why?  What does it buy?  I think this:

	ifeq ($(CONFIG_MMU)$(CONFIG_BLOCK),yy)
	obj-y += bounce.o
	endif

is clearer.

David

Re: [PATCH 04/18] [PATCH] BLOCK: Separate the bounce buffering code from the highmem code [try #4]

[Arnd Bergmann]

On Tuesday 29 August 2006 15:47, David Howells wrote:
> Arnd Bergmann <arnd.bergmann@de.ibm.com> wrote:
> 
> > You could write it as
> > 
> > bounce-$(CONFIG_MMU) += bounce.o
> > obj-$(CONFIG_BLOCK)  += $(bounce-y)
> 
> I could, yes, but why?  What does it buy?  I think this:
> 
>         ifeq ($(CONFIG_MMU)$(CONFIG_BLOCK),yy)
>         obj-y += bounce.o
>         endif
> 
> is clearer.

I remember having seen the first one in the kernel before
(e.g. in arch/powerpc/kernel/Makefile), but not the other one.

I agree that it doesn't make much difference at all, but it
would be nice to be consistant.

	Arnd <><

Re: [PATCH 04/18] [PATCH] BLOCK: Separate the bounce buffering code from the highmem code [try #4]

[Arnd Bergmann]

On Tuesday 29 August 2006 15:47, David Howells wrote:
> Arnd Bergmann <arnd.bergmann@de.ibm.com> wrote:
> 
> > You could write it as
> > 
> > bounce-$(CONFIG_MMU) += bounce.o
> > obj-$(CONFIG_BLOCK)  += $(bounce-y)
> 
> I could, yes, but why?  What does it buy?  I think this:
> 
>         ifeq ($(CONFIG_MMU)$(CONFIG_BLOCK),yy)
>         obj-y += bounce.o
>         endif
> 
> is clearer.

I remember having seen the first one in the kernel before
(e.g. in arch/powerpc/kernel/Makefile), but not the other one.

I agree that it doesn't make much difference at all, but it
would be nice to be consistant.

	Arnd <><
-
To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH 05/18] [PATCH] BLOCK: Don't call block_sync_page() from AFS [try #4]

[David Howells]

From: David Howells <dhowells@redhat.com>

The AFS filesystem specifies block_sync_page() as its sync_page address op,
which needs to be checked, and so is commented out for the moment.

Signed-Off-By: David Howells <dhowells@redhat.com>
---

 fs/afs/file.c |    2 ++
 1 files changed, 2 insertions(+), 0 deletions(-)

diff --git a/fs/afs/file.c b/fs/afs/file.c
index 67d6634..5ff8e3a 100644
--- a/fs/afs/file.c
+++ b/fs/afs/file.c
@@ -37,7 +37,9 @@ struct inode_operations afs_file_inode_o
 
 const struct address_space_operations afs_fs_aops = {
 	.readpage	= afs_file_readpage,
+#if 0 /* probably shouldn't do this - needs reconsideration */
 	.sync_page	= block_sync_page,
+#endif
 	.set_page_dirty	= __set_page_dirty_nobuffers,
 	.releasepage	= afs_file_releasepage,
 	.invalidatepage	= afs_file_invalidatepage,

Re: [PATCH 05/18] [PATCH] BLOCK: Don't call block_sync_page() from AFS [try #4]

[Chris Wedgwood]

On Fri, Aug 25, 2006 at 08:37:10PM +0100, David Howells wrote:

> The AFS filesystem specifies block_sync_page() as its sync_page
> address op, which needs to be checked, and so is commented out for
> the moment.

Wouldn't it be better to just let the link/build fail so someone who
groks AFS internals can look into this?

Re: [PATCH 05/18] [PATCH] BLOCK: Don't call block_sync_page() from AFS [try #4]

[Christoph Hellwig]

On Sun, Aug 27, 2006 at 02:21:36PM -0700, Chris Wedgwood wrote:
> On Fri, Aug 25, 2006 at 08:37:10PM +0100, David Howells wrote:
> 
> > The AFS filesystem specifies block_sync_page() as its sync_page
> > address op, which needs to be checked, and so is commented out for
> > the moment.
> 
> Wouldn't it be better to just let the link/build fail so someone who
> groks AFS internals can look into this?

David wrote most of this code.  But in fact one doesn't need AFS knowledge
to see that it's not needed.

Take a look at block_sync_page:

void block_sync_page(struct page *page)
{
	struct address_space *mapping;

	smp_mb();
	mapping = page_mapping(page);
	if (mapping)
		blk_run_backing_dev(mapping->backing_dev_info, page);
}

so it's a wrapper around blk_run_backing_dev:

static inline void blk_run_backing_dev(struct backing_dev_info *bdi,
				       struct page *page)
{
	if (bdi && bdi->unplug_io_fn)
		bdi->unplug_io_fn(bdi, page);
}

AFS never sets a backing_dev_info on it's own and thus uses
&default_backing_dev_info which sets the unplug_io_fn to
default_unplug_io_fn.  default_unplug_io_fn is a no-op, and thus
block_sync_page does nothing for AFS.

It thus can be safely removed, even without the #if 0

Re: [PATCH 05/18] [PATCH] BLOCK: Don't call block_sync_page() from AFS [try #4]

[David Howells]

Christoph Hellwig <hch@infradead.org> wrote:

> AFS never sets a backing_dev_info on it's own and thus uses
> &default_backing_dev_info which sets the unplug_io_fn to
> default_unplug_io_fn.  default_unplug_io_fn is a no-op, and thus
> block_sync_page does nothing for AFS.

I'm sure I used to require this for when there was a local cache on disk.
Maybe things have changed, or maybe I'm misremembering.

David

Re: [PATCH 05/18] [PATCH] BLOCK: Don't call block_sync_page() from AFS [try #4]

[David Howells]

Chris Wedgwood <cw@f00f.org> wrote:

> > The AFS filesystem specifies block_sync_page() as its sync_page
> > address op, which needs to be checked, and so is commented out for
> > the moment.
> 
> Wouldn't it be better to just let the link/build fail so someone who
> groks AFS internals can look into this?

That would be me...

I don't want the block patches getting rejected because make allyesconfig fails
due to AFS not linking.

David

[PATCH 06/18] [PATCH] BLOCK: Move extern declarations out of fs/*.c into header files [try #4]

[David Howells]

From: David Howells <dhowells@redhat.com>

Create a new header file, fs/internal.h, for common definitions local to the
sources in the fs/ directory.

Move extern definitions that should be in header files from fs/*.c to
fs/internal.h or other main header files where they span directories.

Signed-Off-By: David Howells <dhowells@redhat.com>
---

 fs/binfmt_elf.c        |    1 -
 fs/block_dev.c         |    1 +
 fs/char_dev.c          |    1 +
 fs/compat.c            |    8 +-------
 fs/compat_ioctl.c      |    2 --
 fs/dcache.c            |    4 +---
 fs/fs-writeback.c      |    3 +--
 fs/internal.h          |   36 ++++++++++++++++++++++++++++++++++++
 fs/namespace.c         |   12 +-----------
 include/linux/compat.h |    1 +
 include/linux/ramfs.h  |    1 +
 include/linux/sysfs.h  |    9 +++++++++
 include/linux/tty.h    |    3 +++
 13 files changed, 56 insertions(+), 26 deletions(-)

diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 672a3b9..deb4269 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -46,7 +46,6 @@ #include <asm/page.h>
 static int load_elf_binary(struct linux_binprm *bprm, struct pt_regs *regs);
 static int load_elf_library(struct file *);
 static unsigned long elf_map (struct file *, unsigned long, struct elf_phdr *, int, int);
-extern int dump_fpu (struct pt_regs *, elf_fpregset_t *);
 
 #ifndef elf_addr_t
 #define elf_addr_t unsigned long
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 3753457..b7ce764 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -22,6 +22,7 @@ #include <linux/mount.h>
 #include <linux/uio.h>
 #include <linux/namei.h>
 #include <asm/uaccess.h>
+#include "internal.h"
 
 struct bdev_inode {
 	struct block_device bdev;
diff --git a/fs/char_dev.c b/fs/char_dev.c
index 3483d3c..a35775b 100644
--- a/fs/char_dev.c
+++ b/fs/char_dev.c
@@ -23,6 +23,7 @@ #include <linux/mutex.h>
 #ifdef CONFIG_KMOD
 #include <linux/kmod.h>
 #endif
+#include "internal.h"
 
 static struct kobj_map *cdev_map;
 
diff --git a/fs/compat.c b/fs/compat.c
index e31e9cf..f7ce0f5 100644
--- a/fs/compat.c
+++ b/fs/compat.c
@@ -52,8 +52,7 @@ #include <net/sock.h>		/* siocdevprivate
 #include <asm/uaccess.h>
 #include <asm/mmu_context.h>
 #include <asm/ioctls.h>
-
-extern void sigset_from_compat(sigset_t *set, compat_sigset_t *compat);
+#include "internal.h"
 
 int compat_log = 1;
 
@@ -313,9 +312,6 @@ out:
 #define IOCTL_HASHSIZE 256
 static struct ioctl_trans *ioctl32_hash_table[IOCTL_HASHSIZE];
 
-extern struct ioctl_trans ioctl_start[];
-extern int ioctl_table_size;
-
 static inline unsigned long ioctl32_hash(unsigned long cmd)
 {
 	return (((cmd >> 6) ^ (cmd >> 4) ^ cmd)) % IOCTL_HASHSIZE;
@@ -838,8 +834,6 @@ static int do_nfs4_super_data_conv(void 
 	return 0;
 }
 
-extern int copy_mount_options (const void __user *, unsigned long *);
-
 #define SMBFS_NAME      "smbfs"
 #define NCPFS_NAME      "ncpfs"
 #define NFS4_NAME	"nfs4"
diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c
index 4063a93..ab74c9b 100644
--- a/fs/compat_ioctl.c
+++ b/fs/compat_ioctl.c
@@ -1279,8 +1279,6 @@ static int loop_status(unsigned int fd, 
 	return err;
 }
 
-extern int tty_ioctl(struct inode * inode, struct file * file, unsigned int cmd, unsigned long arg);
-
 #ifdef CONFIG_VT
 
 static int vt_check(struct file *file)
diff --git a/fs/dcache.c b/fs/dcache.c
index 1b4a3a3..ae6d053 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -32,6 +32,7 @@ #include <linux/security.h>
 #include <linux/seqlock.h>
 #include <linux/swap.h>
 #include <linux/bootmem.h>
+#include "internal.h"
 
 
 int sysctl_vfs_cache_pressure __read_mostly = 100;
@@ -1742,9 +1743,6 @@ kmem_cache_t *filp_cachep __read_mostly;
 
 EXPORT_SYMBOL(d_genocide);
 
-extern void bdev_cache_init(void);
-extern void chrdev_init(void);
-
 void __init vfs_caches_init_early(void)
 {
 	dcache_init_early();
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 892643d..0639024 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -22,8 +22,7 @@ #include <linux/writeback.h>
 #include <linux/blkdev.h>
 #include <linux/backing-dev.h>
 #include <linux/buffer_head.h>
-
-extern struct super_block *blockdev_superblock;
+#include "internal.h"
 
 /**
  *	__mark_inode_dirty -	internal function
diff --git a/fs/internal.h b/fs/internal.h
new file mode 100644
index 0000000..c21ecd3
--- /dev/null
+++ b/fs/internal.h
@@ -0,0 +1,36 @@
+/* fs/ internal definitions
+ *
+ * Copyright (C) 2006 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/ioctl32.h>
+
+/*
+ * block_dev.c
+ */
+extern struct super_block *blockdev_superblock;
+extern void __init bdev_cache_init(void);
+
+/*
+ * char_dev.c
+ */
+extern void __init chrdev_init(void);
+
+/*
+ * compat_ioctl.c
+ */
+#ifdef CONFIG_COMPAT
+extern struct ioctl_trans ioctl_start[];
+extern int ioctl_table_size;
+#endif
+
+/*
+ * namespace.c
+ */
+extern int copy_mount_options(const void __user *, unsigned long *);
diff --git a/fs/namespace.c b/fs/namespace.c
index fa7ed6a..6100d84 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -22,21 +22,11 @@ #include <linux/namespace.h>
 #include <linux/namei.h>
 #include <linux/security.h>
 #include <linux/mount.h>
+#include <linux/ramfs.h>
 #include <asm/uaccess.h>
 #include <asm/unistd.h>
 #include "pnode.h"
 
-extern int __init init_rootfs(void);
-
-#ifdef CONFIG_SYSFS
-extern int __init sysfs_init(void);
-#else
-static inline int sysfs_init(void)
-{
-	return 0;
-}
-#endif
-
 /* spinlock for vfsmount related operations, inplace of dcache_lock */
 __cacheline_aligned_in_smp DEFINE_SPINLOCK(vfsmount_lock);
 
diff --git a/include/linux/compat.h b/include/linux/compat.h
index 9760753..967e748 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -227,6 +227,7 @@ static inline int compat_timespec_compar
 asmlinkage long compat_sys_adjtimex(struct compat_timex __user *utp);
 
 extern int compat_printk(const char *fmt, ...);
+extern void sigset_from_compat(sigset_t *set, compat_sigset_t *compat);
 
 #endif /* CONFIG_COMPAT */
 #endif /* _LINUX_COMPAT_H */
diff --git a/include/linux/ramfs.h b/include/linux/ramfs.h
index 00b340b..b160fb1 100644
--- a/include/linux/ramfs.h
+++ b/include/linux/ramfs.h
@@ -17,5 +17,6 @@ #endif
 
 extern const struct file_operations ramfs_file_operations;
 extern struct vm_operations_struct generic_file_vm_ops;
+extern int __init init_rootfs(void);
 
 #endif
diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h
index 1ea5d3c..73d10f3 100644
--- a/include/linux/sysfs.h
+++ b/include/linux/sysfs.h
@@ -10,6 +10,7 @@
 #ifndef _SYSFS_H_
 #define _SYSFS_H_
 
+#include <linux/init.h>
 #include <asm/atomic.h>
 
 struct kobject;
@@ -86,6 +87,9 @@ #define SYSFS_NOT_PINNED	(SYSFS_KOBJ_ATT
 
 #ifdef CONFIG_SYSFS
 
+extern int __init
+sysfs_init(void);
+
 extern int
 sysfs_create_dir(struct kobject *);
 
@@ -122,6 +126,11 @@ void sysfs_notify(struct kobject * k, ch
 
 #else /* CONFIG_SYSFS */
 
+static inline int sysfs_init(void)
+{
+	return 0;
+}
+
 static inline int sysfs_create_dir(struct kobject * k)
 {
 	return 0;
diff --git a/include/linux/tty.h b/include/linux/tty.h
index e421d5e..184028d 100644
--- a/include/linux/tty.h
+++ b/include/linux/tty.h
@@ -307,6 +307,9 @@ extern void tty_ldisc_put(int);
 extern void tty_wakeup(struct tty_struct *tty);
 extern void tty_ldisc_flush(struct tty_struct *tty);
 
+extern int tty_ioctl(struct inode *inode, struct file *file, unsigned int cmd,
+		     unsigned long arg);
+
 extern struct mutex tty_mutex;
 
 /* n_tty.c */

Re: [PATCH 06/18] [PATCH] BLOCK: Move extern declarations out of fs/*.c into header files [try #4]

[Sam Ravnborg]

On Fri, Aug 25, 2006 at 08:37:12PM +0100, David Howells wrote:
> From: David Howells <dhowells@redhat.com>
> 
> Create a new header file, fs/internal.h, for common definitions local to the
> sources in the fs/ directory.
> 
> Move extern definitions that should be in header files from fs/*.c to
> fs/internal.h or other main header files where they span directories.

Why not fsinternal.h to make it explicit this is fs internal stuff.
This makes it a bit more obvious when lookign at the filename isolated.

	Sam

Re: [PATCH 06/18] [PATCH] BLOCK: Move extern declarations out of fs/*.c into header files [try #4]

[David Howells]

Sam Ravnborg <sam@ravnborg.org> wrote:

> Why not fsinternal.h to make it explicit this is fs internal stuff.
> This makes it a bit more obvious when lookign at the filename isolated.

Consistency:

	warthog>echo */internal.h
	crypto/internal.h fs/internal.h mm/internal.h
	warthog>echo */*/internal.h
	fs/afs/internal.h fs/nfs/internal.h fs/proc/internal.h fs/ramfs/internal.h net/rxrpc/internal.h security/keys/internal.h

David

[PATCH 07/18] [PATCH] BLOCK: Remove dependence on existence of blockdev_superblock [try #4]

[David Howells]

From: David Howells <dhowells@redhat.com>

Move blockdev_superblock extern declaration from fs/fs-writeback.c to a
headerfile and remove the dependence on it by wrapping it in a macro.

Signed-Off-By: David Howells <dhowells@redhat.com>
---

 fs/fs-writeback.c |    6 +++---
 fs/internal.h     |    2 ++
 2 files changed, 5 insertions(+), 3 deletions(-)

diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 0639024..c403b66 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -319,7 +319,7 @@ sync_sb_inodes(struct super_block *sb, s
 
 		if (!bdi_cap_writeback_dirty(bdi)) {
 			list_move(&inode->i_list, &sb->s_dirty);
-			if (sb == blockdev_superblock) {
+			if (sb_is_blkdev_sb(sb)) {
 				/*
 				 * Dirty memory-backed blockdev: the ramdisk
 				 * driver does this.  Skip just this inode
@@ -336,14 +336,14 @@ sync_sb_inodes(struct super_block *sb, s
 
 		if (wbc->nonblocking && bdi_write_congested(bdi)) {
 			wbc->encountered_congestion = 1;
-			if (sb != blockdev_superblock)
+			if (!sb_is_blkdev_sb(sb))
 				break;		/* Skip a congested fs */
 			list_move(&inode->i_list, &sb->s_dirty);
 			continue;		/* Skip a congested blockdev */
 		}
 
 		if (wbc->bdi && bdi != wbc->bdi) {
-			if (sb != blockdev_superblock)
+			if (!sb_is_blkdev_sb(sb))
 				break;		/* fs has the wrong queue */
 			list_move(&inode->i_list, &sb->s_dirty);
 			continue;		/* blockdev has wrong queue */
diff --git a/fs/internal.h b/fs/internal.h
index c21ecd3..f662b70 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -17,6 +17,8 @@ #include <linux/ioctl32.h>
 extern struct super_block *blockdev_superblock;
 extern void __init bdev_cache_init(void);
 
+#define sb_is_blkdev_sb(sb) ((sb) == blockdev_superblock)
+
 /*
  * char_dev.c
  */

[PATCH 08/18] [PATCH] BLOCK: Dissociate generic_writepages() from mpage stuff [try #4]

[David Howells]

From: David Howells <dhowells@redhat.com>

Dissociate the generic_writepages() function from the mpage stuff, moving its
declaration to linux/mm.h and actually emitting a full implementation into
mm/page-writeback.c.

The implementation is a partial duplicate of mpage_writepages() with all BIO
references removed.

It is used by NFS to do writeback.

Signed-Off-By: David Howells <dhowells@redhat.com>
---

 fs/block_dev.c            |    1 
 fs/mpage.c                |    2 +
 include/linux/mpage.h     |    6 --
 include/linux/writeback.h |    2 +
 mm/page-writeback.c       |  134 +++++++++++++++++++++++++++++++++++++++++++++
 5 files changed, 139 insertions(+), 6 deletions(-)

diff --git a/fs/block_dev.c b/fs/block_dev.c
index b7ce764..6e24cd4 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -17,6 +17,7 @@ #include <linux/blkdev.h>
 #include <linux/module.h>
 #include <linux/blkpg.h>
 #include <linux/buffer_head.h>
+#include <linux/writeback.h>
 #include <linux/mpage.h>
 #include <linux/mount.h>
 #include <linux/uio.h>
diff --git a/fs/mpage.c b/fs/mpage.c
index 1e45982..692a3e5 100644
--- a/fs/mpage.c
+++ b/fs/mpage.c
@@ -693,6 +693,8 @@ out:
  * the call was made get new I/O started against them.  If wbc->sync_mode is
  * WB_SYNC_ALL then we were called for data integrity and we must wait for
  * existing IO to complete.
+ *
+ * If you fix this you should check generic_writepages() also!
  */
 int
 mpage_writepages(struct address_space *mapping,
diff --git a/include/linux/mpage.h b/include/linux/mpage.h
index 3ca8804..517c098 100644
--- a/include/linux/mpage.h
+++ b/include/linux/mpage.h
@@ -20,9 +20,3 @@ int mpage_writepages(struct address_spac
 		struct writeback_control *wbc, get_block_t get_block);
 int mpage_writepage(struct page *page, get_block_t *get_block,
 		struct writeback_control *wbc);
-
-static inline int
-generic_writepages(struct address_space *mapping, struct writeback_control *wbc)
-{
-	return mpage_writepages(mapping, wbc, NULL);
-}
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index 9e38b56..671c43b 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -110,6 +110,8 @@ balance_dirty_pages_ratelimited(struct a
 }
 
 int pdflush_operation(void (*fn)(unsigned long), unsigned long arg0);
+extern int generic_writepages(struct address_space *mapping,
+			      struct writeback_control *wbc);
 int do_writepages(struct address_space *mapping, struct writeback_control *wbc);
 int sync_page_range(struct inode *inode, struct address_space *mapping,
 			loff_t pos, loff_t count);
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index f75d033..eeeaf43 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>
+#include <linux/pagevec.h>
 
 /*
  * The maximum number of pages to writeout in a single bdflush/kupdate
@@ -543,6 +544,139 @@ void __init page_writeback_init(void)
 	register_cpu_notifier(&ratelimit_nb);
 }
 
+/**
+ * generic_writepages - walk the list of dirty pages of the given
+ *                      address space and writepage() all of them.
+ *
+ * @mapping: address space structure to write
+ * @wbc: subtract the number of written pages from *@wbc->nr_to_write
+ *
+ * This is a library function, which implements the writepages()
+ * address_space_operation.
+ *
+ * If a page is already under I/O, generic_writepages() skips it, even
+ * if it's dirty.  This is desirable behaviour for memory-cleaning writeback,
+ * but it is INCORRECT for data-integrity system calls such as fsync().  fsync()
+ * and msync() need to guarantee that all the data which was dirty at the time
+ * the call was made get new I/O started against them.  If wbc->sync_mode is
+ * WB_SYNC_ALL then we were called for data integrity and we must wait for
+ * existing IO to complete.
+ *
+ * Derived from mpage_writepages() - if you fix this you should check that
+ * also!
+ */
+int generic_writepages(struct address_space *mapping,
+		       struct writeback_control *wbc)
+{
+	struct backing_dev_info *bdi = mapping->backing_dev_info;
+	int ret = 0;
+	int done = 0;
+	int (*writepage)(struct page *page, struct writeback_control *wbc);
+	struct pagevec pvec;
+	int nr_pages;
+	pgoff_t index;
+	pgoff_t end;		/* Inclusive */
+	int scanned = 0;
+	int range_whole = 0;
+
+	if (wbc->nonblocking && bdi_write_congested(bdi)) {
+		wbc->encountered_congestion = 1;
+		return 0;
+	}
+
+	writepage = mapping->a_ops->writepage;
+
+	/* deal with chardevs and other special file */
+	if (!writepage)
+		return 0;
+
+	pagevec_init(&pvec, 0);
+	if (wbc->range_cyclic) {
+		index = mapping->writeback_index; /* Start from prev offset */
+		end = -1;
+	} else {
+		index = wbc->range_start >> PAGE_CACHE_SHIFT;
+		end = wbc->range_end >> PAGE_CACHE_SHIFT;
+		if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
+			range_whole = 1;
+		scanned = 1;
+	}
+retry:
+	while (!done && (index <= end) &&
+	       (nr_pages = pagevec_lookup_tag(&pvec, mapping, &index,
+					      PAGECACHE_TAG_DIRTY,
+					      min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1))) {
+		unsigned i;
+
+		scanned = 1;
+		for (i = 0; i < nr_pages; i++) {
+			struct page *page = pvec.pages[i];
+
+			/*
+			 * At this point we hold neither mapping->tree_lock nor
+			 * lock on the page itself: the page may be truncated or
+			 * invalidated (changing page->mapping to NULL), or even
+			 * swizzled back from swapper_space to tmpfs file
+			 * mapping
+			 */
+			lock_page(page);
+
+			if (unlikely(page->mapping != mapping)) {
+				unlock_page(page);
+				continue;
+			}
+
+			if (!wbc->range_cyclic && page->index > end) {
+				done = 1;
+				unlock_page(page);
+				continue;
+			}
+
+			if (wbc->sync_mode != WB_SYNC_NONE)
+				wait_on_page_writeback(page);
+
+			if (PageWriteback(page) ||
+			    !clear_page_dirty_for_io(page)) {
+				unlock_page(page);
+				continue;
+			}
+
+			ret = (*writepage)(page, wbc);
+			if (ret) {
+				if (ret == -ENOSPC)
+					set_bit(AS_ENOSPC, &mapping->flags);
+				else
+					set_bit(AS_EIO, &mapping->flags);
+			}
+
+			if (unlikely(ret == AOP_WRITEPAGE_ACTIVATE))
+				unlock_page(page);
+			if (ret || (--(wbc->nr_to_write) <= 0))
+				done = 1;
+			if (wbc->nonblocking && bdi_write_congested(bdi)) {
+				wbc->encountered_congestion = 1;
+				done = 1;
+			}
+		}
+		pagevec_release(&pvec);
+		cond_resched();
+	}
+	if (!scanned && !done) {
+		/*
+		 * We hit the last page and there is more work to be done: wrap
+		 * back to the start of the file
+		 */
+		scanned = 1;
+		index = 0;
+		goto retry;
+	}
+	if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0))
+		mapping->writeback_index = index;
+	return ret;
+}
+
+EXPORT_SYMBOL(generic_writepages);
+
 int do_writepages(struct address_space *mapping, struct writeback_control *wbc)
 {
 	int ret;

[PATCH 09/18] [PATCH] BLOCK: Move __invalidate_device() to block_dev.c [try #4]

[David Howells]

From: David Howells <dhowells@redhat.com>

Move __invalidate_device() from fs/inode.c to fs/block_dev.c so that it can
more easily be disabled when the block layer is disabled.

Signed-Off-By: David Howells <dhowells@redhat.com>
---

 fs/block_dev.c |   21 +++++++++++++++++++++
 fs/inode.c     |   21 ---------------------
 2 files changed, 21 insertions(+), 21 deletions(-)

diff --git a/fs/block_dev.c b/fs/block_dev.c
index 6e24cd4..f2c3637 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1307,3 +1307,24 @@ void close_bdev_excl(struct block_device
 }
 
 EXPORT_SYMBOL(close_bdev_excl);
+
+int __invalidate_device(struct block_device *bdev)
+{
+	struct super_block *sb = get_super(bdev);
+	int res = 0;
+
+	if (sb) {
+		/*
+		 * no need to lock the super, get_super holds the
+		 * read mutex so the filesystem cannot go away
+		 * under us (->put_super runs with the write lock
+		 * hold).
+		 */
+		shrink_dcache_sb(sb);
+		res = invalidate_inodes(sb);
+		drop_super(sb);
+	}
+	invalidate_bdev(bdev, 0);
+	return res;
+}
+EXPORT_SYMBOL(__invalidate_device);
diff --git a/fs/inode.c b/fs/inode.c
index 0bf9f04..6426bb0 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -363,27 +363,6 @@ int invalidate_inodes(struct super_block
 }
 
 EXPORT_SYMBOL(invalidate_inodes);
- 
-int __invalidate_device(struct block_device *bdev)
-{
-	struct super_block *sb = get_super(bdev);
-	int res = 0;
-
-	if (sb) {
-		/*
-		 * no need to lock the super, get_super holds the
-		 * read mutex so the filesystem cannot go away
-		 * under us (->put_super runs with the write lock
-		 * hold).
-		 */
-		shrink_dcache_sb(sb);
-		res = invalidate_inodes(sb);
-		drop_super(sb);
-	}
-	invalidate_bdev(bdev, 0);
-	return res;
-}
-EXPORT_SYMBOL(__invalidate_device);
 
 static int can_unuse(struct inode *inode)
 {

[PATCH 10/18] [PATCH] BLOCK: Move the loop device ioctl compat stuff to the loop driver [try #4]

[David Howells]

From: David Howells <dhowells@redhat.com>

Move the loop device ioctl compat stuff from fs/compat_ioctl.c to the loop
driver so that the loop header file doesn't need to be included.

Signed-Off-By: David Howells <dhowells@redhat.com>
---

 drivers/block/loop.c         |  160 ++++++++++++++++++++++++++++++++++++++++++
 fs/compat_ioctl.c            |   68 ------------------
 include/linux/compat_ioctl.h |    6 --
 3 files changed, 160 insertions(+), 74 deletions(-)

diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 7b3b94d..23d3381 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -66,6 +66,7 @@ #include <linux/smp_lock.h>
 #include <linux/swap.h>
 #include <linux/slab.h>
 #include <linux/loop.h>
+#include <linux/compat.h>
 #include <linux/suspend.h>
 #include <linux/writeback.h>
 #include <linux/buffer_head.h>		/* for invalidate_bdev() */
@@ -1174,6 +1175,162 @@ static int lo_ioctl(struct inode * inode
 	return err;
 }
 
+#ifdef CONFIG_COMPAT
+struct compat_loop_info {
+	compat_int_t	lo_number;      /* ioctl r/o */
+	compat_dev_t	lo_device;      /* ioctl r/o */
+	compat_ulong_t	lo_inode;       /* ioctl r/o */
+	compat_dev_t	lo_rdevice;     /* ioctl r/o */
+	compat_int_t	lo_offset;
+	compat_int_t	lo_encrypt_type;
+	compat_int_t	lo_encrypt_key_size;    /* ioctl w/o */
+	compat_int_t	lo_flags;       /* ioctl r/o */
+	char		lo_name[LO_NAME_SIZE];
+	unsigned char	lo_encrypt_key[LO_KEY_SIZE]; /* ioctl w/o */
+	compat_ulong_t	lo_init[2];
+	char		reserved[4];
+};
+
+/*
+ * Transfer 32-bit compatibility structure in userspace to 64-bit loop info
+ * - noinlined to reduce stack space usage in main part of driver
+ */
+static noinline int
+loop_info64_from_compat(const struct compat_loop_info *arg,
+			struct loop_info64 *info64)
+{
+	struct compat_loop_info info;
+
+	if (copy_from_user(&info, arg, sizeof(info)))
+		return -EFAULT;
+
+	memset(info64, 0, sizeof(*info64));
+	info64->lo_number = info.lo_number;
+	info64->lo_device = info.lo_device;
+	info64->lo_inode = info.lo_inode;
+	info64->lo_rdevice = info.lo_rdevice;
+	info64->lo_offset = info.lo_offset;
+	info64->lo_sizelimit = 0;
+	info64->lo_encrypt_type = info.lo_encrypt_type;
+	info64->lo_encrypt_key_size = info.lo_encrypt_key_size;
+	info64->lo_flags = info.lo_flags;
+	info64->lo_init[0] = info.lo_init[0];
+	info64->lo_init[1] = info.lo_init[1];
+	if (info.lo_encrypt_type == LO_CRYPT_CRYPTOAPI)
+		memcpy(info64->lo_crypt_name, info.lo_name, LO_NAME_SIZE);
+	else
+		memcpy(info64->lo_file_name, info.lo_name, LO_NAME_SIZE);
+	memcpy(info64->lo_encrypt_key, info.lo_encrypt_key, LO_KEY_SIZE);
+	return 0;
+}
+
+/*
+ * Transfer 64-bit loop info to 32-bit compatibility structure in userspace
+ * - noinlined to reduce stack space usage in main part of driver
+ */
+static noinline int
+loop_info64_to_compat(const struct loop_info64 *info64,
+		      struct compat_loop_info __user *arg)
+{
+	struct compat_loop_info info;
+
+	memset(&info, 0, sizeof(info));
+	info.lo_number = info64->lo_number;
+	info.lo_device = info64->lo_device;
+	info.lo_inode = info64->lo_inode;
+	info.lo_rdevice = info64->lo_rdevice;
+	info.lo_offset = info64->lo_offset;
+	info.lo_encrypt_type = info64->lo_encrypt_type;
+	info.lo_encrypt_key_size = info64->lo_encrypt_key_size;
+	info.lo_flags = info64->lo_flags;
+	info.lo_init[0] = info64->lo_init[0];
+	info.lo_init[1] = info64->lo_init[1];
+	if (info.lo_encrypt_type == LO_CRYPT_CRYPTOAPI)
+		memcpy(info.lo_name, info64->lo_crypt_name, LO_NAME_SIZE);
+	else
+		memcpy(info.lo_name, info64->lo_file_name, LO_NAME_SIZE);
+	memcpy(info.lo_encrypt_key, info64->lo_encrypt_key, LO_KEY_SIZE);
+
+	/* error in case values were truncated */
+	if (info.lo_device != info64->lo_device ||
+	    info.lo_rdevice != info64->lo_rdevice ||
+	    info.lo_inode != info64->lo_inode ||
+	    info.lo_offset != info64->lo_offset ||
+	    info.lo_init[0] != info64->lo_init[0] ||
+	    info.lo_init[1] != info64->lo_init[1])
+		return -EOVERFLOW;
+
+	if (copy_to_user(arg, &info, sizeof(info)))
+		return -EFAULT;
+	return 0;
+}
+
+static int
+loop_set_status_compat(struct loop_device *lo,
+		       const struct compat_loop_info __user *arg)
+{
+	struct loop_info64 info64;
+	int ret;
+
+	ret = loop_info64_from_compat(arg, &info64);
+	if (ret < 0)
+		return ret;
+	return loop_set_status(lo, &info64);
+}
+
+static int
+loop_get_status_compat(struct loop_device *lo,
+		       struct compat_loop_info __user *arg)
+{
+	struct loop_info64 info64;
+	int err = 0;
+
+	if (!arg)
+		err = -EINVAL;
+	if (!err)
+		err = loop_get_status(lo, &info64);
+	if (!err)
+		err = loop_info64_to_compat(&info64, arg);
+	return err;
+}
+
+static long lo_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+	struct inode *inode = file->f_dentry->d_inode;
+	struct loop_device *lo = inode->i_bdev->bd_disk->private_data;
+	int err;
+
+	lock_kernel();
+	switch(cmd) {
+	case LOOP_SET_STATUS:
+		mutex_lock(&lo->lo_ctl_mutex);
+		err = loop_set_status_compat(
+			lo, (const struct compat_loop_info __user *) arg);
+		mutex_unlock(&lo->lo_ctl_mutex);
+		break;
+	case LOOP_GET_STATUS:
+		mutex_lock(&lo->lo_ctl_mutex);
+		err = loop_get_status_compat(
+			lo, (struct compat_loop_info __user *) arg);
+		mutex_unlock(&lo->lo_ctl_mutex);
+		break;
+	case LOOP_CLR_FD:
+	case LOOP_GET_STATUS64:
+	case LOOP_SET_STATUS64:
+		arg = (unsigned long) compat_ptr(arg);
+	case LOOP_SET_FD:
+	case LOOP_CHANGE_FD:
+		err = lo_ioctl(inode, file, cmd, arg);
+		break;
+	default:
+		err = -ENOIOCTLCMD;
+		break;
+	}
+	unlock_kernel();
+	return err;
+}
+#endif
+
 static int lo_open(struct inode *inode, struct file *file)
 {
 	struct loop_device *lo = inode->i_bdev->bd_disk->private_data;
@@ -1201,6 +1358,9 @@ static struct block_device_operations lo
 	.open =		lo_open,
 	.release =	lo_release,
 	.ioctl =	lo_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl =	lo_compat_ioctl,
+#endif
 };
 
 /*
diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c
index ab74c9b..3b0cf7f 100644
--- a/fs/compat_ioctl.c
+++ b/fs/compat_ioctl.c
@@ -40,7 +40,6 @@ #include <linux/if_ppp.h>
 #include <linux/if_pppox.h>
 #include <linux/mtio.h>
 #include <linux/cdrom.h>
-#include <linux/loop.h>
 #include <linux/auto_fs.h>
 #include <linux/auto_fs4.h>
 #include <linux/tty.h>
@@ -1214,71 +1213,6 @@ static int cdrom_ioctl_trans(unsigned in
 	return err;
 }
 
-struct loop_info32 {
-	compat_int_t	lo_number;      /* ioctl r/o */
-	compat_dev_t	lo_device;      /* ioctl r/o */
-	compat_ulong_t	lo_inode;       /* ioctl r/o */
-	compat_dev_t	lo_rdevice;     /* ioctl r/o */
-	compat_int_t	lo_offset;
-	compat_int_t	lo_encrypt_type;
-	compat_int_t	lo_encrypt_key_size;    /* ioctl w/o */
-	compat_int_t	lo_flags;       /* ioctl r/o */
-	char		lo_name[LO_NAME_SIZE];
-	unsigned char	lo_encrypt_key[LO_KEY_SIZE]; /* ioctl w/o */
-	compat_ulong_t	lo_init[2];
-	char		reserved[4];
-};
-
-static int loop_status(unsigned int fd, unsigned int cmd, unsigned long arg)
-{
-	mm_segment_t old_fs = get_fs();
-	struct loop_info l;
-	struct loop_info32 __user *ul;
-	int err = -EINVAL;
-
-	ul = compat_ptr(arg);
-	switch(cmd) {
-	case LOOP_SET_STATUS:
-		err = get_user(l.lo_number, &ul->lo_number);
-		err |= __get_user(l.lo_device, &ul->lo_device);
-		err |= __get_user(l.lo_inode, &ul->lo_inode);
-		err |= __get_user(l.lo_rdevice, &ul->lo_rdevice);
-		err |= __copy_from_user(&l.lo_offset, &ul->lo_offset,
-		        8 + (unsigned long)l.lo_init - (unsigned long)&l.lo_offset);
-		if (err) {
-			err = -EFAULT;
-		} else {
-			set_fs (KERNEL_DS);
-			err = sys_ioctl (fd, cmd, (unsigned long)&l);
-			set_fs (old_fs);
-		}
-		break;
-	case LOOP_GET_STATUS:
-		set_fs (KERNEL_DS);
-		err = sys_ioctl (fd, cmd, (unsigned long)&l);
-		set_fs (old_fs);
-		if (!err) {
-			err = put_user(l.lo_number, &ul->lo_number);
-			err |= __put_user(l.lo_device, &ul->lo_device);
-			err |= __put_user(l.lo_inode, &ul->lo_inode);
-			err |= __put_user(l.lo_rdevice, &ul->lo_rdevice);
-			err |= __copy_to_user(&ul->lo_offset, &l.lo_offset,
-				(unsigned long)l.lo_init - (unsigned long)&l.lo_offset);
-			if (err)
-				err = -EFAULT;
-		}
-		break;
-	default: {
-		static int count;
-		if (++count <= 20)
-			printk("%s: Unknown loop ioctl cmd, fd(%d) "
-			       "cmd(%08x) arg(%08lx)\n",
-			       __FUNCTION__, fd, cmd, arg);
-	}
-	}
-	return err;
-}
-
 #ifdef CONFIG_VT
 
 static int vt_check(struct file *file)
@@ -2808,8 +2742,6 @@ HANDLE_IOCTL(MTIOCGET32, mt_ioctl_trans)
 HANDLE_IOCTL(MTIOCPOS32, mt_ioctl_trans)
 HANDLE_IOCTL(CDROMREADAUDIO, cdrom_ioctl_trans)
 HANDLE_IOCTL(CDROM_SEND_PACKET, cdrom_ioctl_trans)
-HANDLE_IOCTL(LOOP_SET_STATUS, loop_status)
-HANDLE_IOCTL(LOOP_GET_STATUS, loop_status)
 #define AUTOFS_IOC_SETTIMEOUT32 _IOWR(0x93,0x64,unsigned int)
 HANDLE_IOCTL(AUTOFS_IOC_SETTIMEOUT32, ioc_settimeout)
 #ifdef CONFIG_VT
diff --git a/include/linux/compat_ioctl.h b/include/linux/compat_ioctl.h
index 269d000..13cea44 100644
--- a/include/linux/compat_ioctl.h
+++ b/include/linux/compat_ioctl.h
@@ -394,12 +394,6 @@ COMPATIBLE_IOCTL(DVD_WRITE_STRUCT)
 COMPATIBLE_IOCTL(DVD_AUTH)
 /* pktcdvd */
 COMPATIBLE_IOCTL(PACKET_CTRL_CMD)
-/* Big L */
-ULONG_IOCTL(LOOP_SET_FD)
-ULONG_IOCTL(LOOP_CHANGE_FD)
-COMPATIBLE_IOCTL(LOOP_CLR_FD)
-COMPATIBLE_IOCTL(LOOP_GET_STATUS64)
-COMPATIBLE_IOCTL(LOOP_SET_STATUS64)
 /* Big A */
 /* sparc only */
 /* Big Q for sound/OSS */

[PATCH 11/18] [PATCH] BLOCK: Move common FS-specific ioctls to linux/fs.h [try #4]

[David Howells]

From: David Howells <dhowells@redhat.com>

Move common FS-specific ioctls from linux/ext2_fs.h to linux/fs.h as FS_IOC_*
and FS_IOC32_* and have the users of them use those as a base.

Also move the GETFLAGS/SETFLAGS flags to linux/fs.h as FS_*_FL macros, and then
have the other users use them as a base.

Signed-Off-By: David Howells <dhowells@redhat.com>
---

 fs/cifs/ioctl.c             |    7 ++---
 fs/compat_ioctl.c           |   15 ----------
 fs/hfsplus/hfsplus_fs.h     |    8 +----
 fs/hfsplus/ioctl.c          |   17 +++++------
 fs/jfs/ioctl.c              |   15 +++++-----
 include/linux/ext2_fs.h     |   66 ++++++++++++++++++++++++-------------------
 include/linux/ext3_fs.h     |   20 ++++++++++---
 include/linux/fs.h          |   39 +++++++++++++++++++++++++
 include/linux/reiserfs_fs.h |   28 ++++++++----------
 9 files changed, 125 insertions(+), 90 deletions(-)

diff --git a/fs/cifs/ioctl.c b/fs/cifs/ioctl.c
index b0ea668..e34c7db 100644
--- a/fs/cifs/ioctl.c
+++ b/fs/cifs/ioctl.c
@@ -22,7 +22,6 @@
  */
 
 #include <linux/fs.h>
-#include <linux/ext2_fs.h>
 #include "cifspdu.h"
 #include "cifsglob.h"
 #include "cifsproto.h"
@@ -74,7 +73,7 @@ #endif /* CONFIG_CIFS_POSIX */
 			}
 			break;
 #ifdef CONFIG_CIFS_POSIX
-		case EXT2_IOC_GETFLAGS:
+		case FS_IOC_GETFLAGS:
 			if(CIFS_UNIX_EXTATTR_CAP & caps) {
 				if (pSMBFile == NULL)
 					break;
@@ -82,12 +81,12 @@ #ifdef CONFIG_CIFS_POSIX
 					&ExtAttrBits, &ExtAttrMask);
 				if(rc == 0)
 					rc = put_user(ExtAttrBits &
-						EXT2_FL_USER_VISIBLE,
+						FS_FL_USER_VISIBLE,
 						(int __user *)arg);
 			}
 			break;
 
-		case EXT2_IOC_SETFLAGS:
+		case FS_IOC_SETFLAGS:
 			if(CIFS_UNIX_EXTATTR_CAP & caps) {
 				if(get_user(ExtAttrBits,(int __user *)arg)) {
 					rc = -EFAULT;
diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c
index 3b0cf7f..bd9c4f4 100644
--- a/fs/compat_ioctl.c
+++ b/fs/compat_ioctl.c
@@ -123,21 +123,6 @@ #include <linux/dvb/frontend.h>
 #include <linux/dvb/video.h>
 #include <linux/lp.h>
 
-/* Aiee. Someone does not find a difference between int and long */
-#define EXT2_IOC32_GETFLAGS               _IOR('f', 1, int)
-#define EXT2_IOC32_SETFLAGS               _IOW('f', 2, int)
-#define EXT3_IOC32_GETVERSION             _IOR('f', 3, int)
-#define EXT3_IOC32_SETVERSION             _IOW('f', 4, int)
-#define EXT3_IOC32_GETRSVSZ               _IOR('f', 5, int)
-#define EXT3_IOC32_SETRSVSZ               _IOW('f', 6, int)
-#define EXT3_IOC32_GROUP_EXTEND           _IOW('f', 7, unsigned int)
-#ifdef CONFIG_JBD_DEBUG
-#define EXT3_IOC32_WAIT_FOR_READONLY      _IOR('f', 99, int)
-#endif
-
-#define EXT2_IOC32_GETVERSION             _IOR('v', 1, int)
-#define EXT2_IOC32_SETVERSION             _IOW('v', 2, int)
-
 static int do_ioctl32_pointer(unsigned int fd, unsigned int cmd,
 			      unsigned long arg, struct file *f)
 {
diff --git a/fs/hfsplus/hfsplus_fs.h b/fs/hfsplus/hfsplus_fs.h
index 8a1ca5e..3915635 100644
--- a/fs/hfsplus/hfsplus_fs.h
+++ b/fs/hfsplus/hfsplus_fs.h
@@ -246,12 +246,8 @@ #define hfs_part_find hfsplus_part_find
 
 /* ext2 ioctls (EXT2_IOC_GETFLAGS and EXT2_IOC_SETFLAGS) to support
  * chattr/lsattr */
-#define HFSPLUS_IOC_EXT2_GETFLAGS	_IOR('f', 1, long)
-#define HFSPLUS_IOC_EXT2_SETFLAGS	_IOW('f', 2, long)
-
-#define EXT2_FLAG_IMMUTABLE		0x00000010 /* Immutable file */
-#define EXT2_FLAG_APPEND		0x00000020 /* writes to file may only append */
-#define EXT2_FLAG_NODUMP		0x00000040 /* do not dump file */
+#define HFSPLUS_IOC_EXT2_GETFLAGS	FS_IOC_GETFLAGS
+#define HFSPLUS_IOC_EXT2_SETFLAGS	FS_IOC_SETFLAGS
 
 
 /*
diff --git a/fs/hfsplus/ioctl.c b/fs/hfsplus/ioctl.c
index 13cf848..79fd104 100644
--- a/fs/hfsplus/ioctl.c
+++ b/fs/hfsplus/ioctl.c
@@ -28,11 +28,11 @@ int hfsplus_ioctl(struct inode *inode, s
 	case HFSPLUS_IOC_EXT2_GETFLAGS:
 		flags = 0;
 		if (HFSPLUS_I(inode).rootflags & HFSPLUS_FLG_IMMUTABLE)
-			flags |= EXT2_FLAG_IMMUTABLE; /* EXT2_IMMUTABLE_FL */
+			flags |= FS_IMMUTABLE_FL; /* EXT2_IMMUTABLE_FL */
 		if (HFSPLUS_I(inode).rootflags & HFSPLUS_FLG_APPEND)
-			flags |= EXT2_FLAG_APPEND; /* EXT2_APPEND_FL */
+			flags |= FS_APPEND_FL; /* EXT2_APPEND_FL */
 		if (HFSPLUS_I(inode).userflags & HFSPLUS_FLG_NODUMP)
-			flags |= EXT2_FLAG_NODUMP; /* EXT2_NODUMP_FL */
+			flags |= FS_NODUMP_FL; /* EXT2_NODUMP_FL */
 		return put_user(flags, (int __user *)arg);
 	case HFSPLUS_IOC_EXT2_SETFLAGS: {
 		if (IS_RDONLY(inode))
@@ -44,32 +44,31 @@ int hfsplus_ioctl(struct inode *inode, s
 		if (get_user(flags, (int __user *)arg))
 			return -EFAULT;
 
-		if (flags & (EXT2_FLAG_IMMUTABLE|EXT2_FLAG_APPEND) ||
+		if (flags & (FS_IMMUTABLE_FL|FS_APPEND_FL) ||
 		    HFSPLUS_I(inode).rootflags & (HFSPLUS_FLG_IMMUTABLE|HFSPLUS_FLG_APPEND)) {
 			if (!capable(CAP_LINUX_IMMUTABLE))
 				return -EPERM;
 		}
 
 		/* don't silently ignore unsupported ext2 flags */
-		if (flags & ~(EXT2_FLAG_IMMUTABLE|EXT2_FLAG_APPEND|
-			      EXT2_FLAG_NODUMP))
+		if (flags & ~(FS_IMMUTABLE_FL|FS_APPEND_FL|FS_NODUMP_FL))
 			return -EOPNOTSUPP;
 
-		if (flags & EXT2_FLAG_IMMUTABLE) { /* EXT2_IMMUTABLE_FL */
+		if (flags & FS_IMMUTABLE_FL) { /* EXT2_IMMUTABLE_FL */
 			inode->i_flags |= S_IMMUTABLE;
 			HFSPLUS_I(inode).rootflags |= HFSPLUS_FLG_IMMUTABLE;
 		} else {
 			inode->i_flags &= ~S_IMMUTABLE;
 			HFSPLUS_I(inode).rootflags &= ~HFSPLUS_FLG_IMMUTABLE;
 		}
-		if (flags & EXT2_FLAG_APPEND) { /* EXT2_APPEND_FL */
+		if (flags & FS_APPEND_FL) { /* EXT2_APPEND_FL */
 			inode->i_flags |= S_APPEND;
 			HFSPLUS_I(inode).rootflags |= HFSPLUS_FLG_APPEND;
 		} else {
 			inode->i_flags &= ~S_APPEND;
 			HFSPLUS_I(inode).rootflags &= ~HFSPLUS_FLG_APPEND;
 		}
-		if (flags & EXT2_FLAG_NODUMP) /* EXT2_NODUMP_FL */
+		if (flags & FS_NODUMP_FL) /* EXT2_NODUMP_FL */
 			HFSPLUS_I(inode).userflags |= HFSPLUS_FLG_NODUMP;
 		else
 			HFSPLUS_I(inode).userflags &= ~HFSPLUS_FLG_NODUMP;
diff --git a/fs/jfs/ioctl.c b/fs/jfs/ioctl.c
index 67b3774..37db524 100644
--- a/fs/jfs/ioctl.c
+++ b/fs/jfs/ioctl.c
@@ -6,7 +6,6 @@
  */
 
 #include <linux/fs.h>
-#include <linux/ext2_fs.h>
 #include <linux/ctype.h>
 #include <linux/capability.h>
 #include <linux/time.h>
@@ -22,13 +21,13 @@ static struct {
 	long jfs_flag;
 	long ext2_flag;
 } jfs_map[] = {
-	{JFS_NOATIME_FL, EXT2_NOATIME_FL},
-	{JFS_DIRSYNC_FL, EXT2_DIRSYNC_FL},
-	{JFS_SYNC_FL, EXT2_SYNC_FL},
-	{JFS_SECRM_FL, EXT2_SECRM_FL},
-	{JFS_UNRM_FL, EXT2_UNRM_FL},
-	{JFS_APPEND_FL, EXT2_APPEND_FL},
-	{JFS_IMMUTABLE_FL, EXT2_IMMUTABLE_FL},
+	{JFS_NOATIME_FL,	FS_NOATIME_FL},
+	{JFS_DIRSYNC_FL,	FS_DIRSYNC_FL},
+	{JFS_SYNC_FL,		FS_SYNC_FL},
+	{JFS_SECRM_FL,		FS_SECRM_FL},
+	{JFS_UNRM_FL,		FS_UNRM_FL},
+	{JFS_APPEND_FL,		FS_APPEND_FL},
+	{JFS_IMMUTABLE_FL,	FS_IMMUTABLE_FL},
 	{0, 0},
 };
 
diff --git a/include/linux/ext2_fs.h b/include/linux/ext2_fs.h
index facf34e..9996d2e 100644
--- a/include/linux/ext2_fs.h
+++ b/include/linux/ext2_fs.h
@@ -169,41 +169,49 @@ #define	EXT2_TIND_BLOCK			(EXT2_DIND_BLO
 #define	EXT2_N_BLOCKS			(EXT2_TIND_BLOCK + 1)
 
 /*
- * Inode flags
- */
-#define	EXT2_SECRM_FL			0x00000001 /* Secure deletion */
-#define	EXT2_UNRM_FL			0x00000002 /* Undelete */
-#define	EXT2_COMPR_FL			0x00000004 /* Compress file */
-#define EXT2_SYNC_FL			0x00000008 /* Synchronous updates */
-#define EXT2_IMMUTABLE_FL		0x00000010 /* Immutable file */
-#define EXT2_APPEND_FL			0x00000020 /* writes to file may only append */
-#define EXT2_NODUMP_FL			0x00000040 /* do not dump file */
-#define EXT2_NOATIME_FL			0x00000080 /* do not update atime */
+ * Inode flags (GETFLAGS/SETFLAGS)
+ */
+#define	EXT2_SECRM_FL			FS_SECRM_FL	/* Secure deletion */
+#define	EXT2_UNRM_FL			FS_UNRM_FL	/* Undelete */
+#define	EXT2_COMPR_FL			FS_COMPR_FL	/* Compress file */
+#define EXT2_SYNC_FL			FS_SYNC_FL	/* Synchronous updates */
+#define EXT2_IMMUTABLE_FL		FS_IMMUTABLE_FL	/* Immutable file */
+#define EXT2_APPEND_FL			FS_APPEND_FL	/* writes to file may only append */
+#define EXT2_NODUMP_FL			FS_NODUMP_FL	/* do not dump file */
+#define EXT2_NOATIME_FL			FS_NOATIME_FL	/* do not update atime */
 /* Reserved for compression usage... */
-#define EXT2_DIRTY_FL			0x00000100
-#define EXT2_COMPRBLK_FL		0x00000200 /* One or more compressed clusters */
-#define EXT2_NOCOMP_FL			0x00000400 /* Don't compress */
-#define EXT2_ECOMPR_FL			0x00000800 /* Compression error */
+#define EXT2_DIRTY_FL			FS_DIRTY_FL
+#define EXT2_COMPRBLK_FL		FS_COMPRBLK_FL	/* One or more compressed clusters */
+#define EXT2_NOCOMP_FL			FS_NOCOMP_FL	/* Don't compress */
+#define EXT2_ECOMPR_FL			FS_ECOMPR_FL	/* Compression error */
 /* End compression flags --- maybe not all used */	
-#define EXT2_BTREE_FL			0x00001000 /* btree format dir */
-#define EXT2_INDEX_FL			0x00001000 /* hash-indexed directory */
-#define EXT2_IMAGIC_FL			0x00002000 /* AFS directory */
-#define EXT2_JOURNAL_DATA_FL		0x00004000 /* Reserved for ext3 */
-#define EXT2_NOTAIL_FL			0x00008000 /* file tail should not be merged */
-#define EXT2_DIRSYNC_FL			0x00010000 /* dirsync behaviour (directories only) */
-#define EXT2_TOPDIR_FL			0x00020000 /* Top of directory hierarchies*/
-#define EXT2_RESERVED_FL		0x80000000 /* reserved for ext2 lib */
-
-#define EXT2_FL_USER_VISIBLE		0x0003DFFF /* User visible flags */
-#define EXT2_FL_USER_MODIFIABLE		0x000380FF /* User modifiable flags */
+#define EXT2_BTREE_FL			FS_BTREE_FL	/* btree format dir */
+#define EXT2_INDEX_FL			FS_INDEX_FL	/* hash-indexed directory */
+#define EXT2_IMAGIC_FL			FS_IMAGIC_FL	/* AFS directory */
+#define EXT2_JOURNAL_DATA_FL		FS_JOURNAL_DATA_FL /* Reserved for ext3 */
+#define EXT2_NOTAIL_FL			FS_NOTAIL_FL	/* file tail should not be merged */
+#define EXT2_DIRSYNC_FL			FS_DIRSYNC_FL	/* dirsync behaviour (directories only) */
+#define EXT2_TOPDIR_FL			FS_TOPDIR_FL	/* Top of directory hierarchies*/
+#define EXT2_RESERVED_FL		FS_RESERVED_FL	/* reserved for ext2 lib */
+
+#define EXT2_FL_USER_VISIBLE		FS_FL_USER_VISIBLE	/* User visible flags */
+#define EXT2_FL_USER_MODIFIABLE		FS_FL_USER_MODIFIABLE	/* User modifiable flags */
 
 /*
  * ioctl commands
  */
-#define	EXT2_IOC_GETFLAGS		_IOR('f', 1, long)
-#define	EXT2_IOC_SETFLAGS		_IOW('f', 2, long)
-#define	EXT2_IOC_GETVERSION		_IOR('v', 1, long)
-#define	EXT2_IOC_SETVERSION		_IOW('v', 2, long)
+#define	EXT2_IOC_GETFLAGS		FS_IOC_GETFLAGS
+#define	EXT2_IOC_SETFLAGS		FS_IOC_SETFLAGS
+#define	EXT2_IOC_GETVERSION		FS_IOC_GETVERSION
+#define	EXT2_IOC_SETVERSION		FS_IOC_SETVERSION
+
+/*
+ * ioctl commands in 32 bit emulation
+ */
+#define EXT2_IOC32_GETFLAGS		FS_IOC32_GETFLAGS
+#define EXT2_IOC32_SETFLAGS		FS_IOC32_SETFLAGS
+#define EXT2_IOC32_GETVERSION		FS_IOC32_GETVERSION
+#define EXT2_IOC32_SETVERSION		FS_IOC32_SETVERSION
 
 /*
  * Structure of an inode on the disk
diff --git a/include/linux/ext3_fs.h b/include/linux/ext3_fs.h
index 9f9cce7..90cfba2 100644
--- a/include/linux/ext3_fs.h
+++ b/include/linux/ext3_fs.h
@@ -220,14 +220,14 @@ struct ext3_new_group_data {
 /*
  * ioctl commands
  */
-#define	EXT3_IOC_GETFLAGS		_IOR('f', 1, long)
-#define	EXT3_IOC_SETFLAGS		_IOW('f', 2, long)
+#define	EXT3_IOC_GETFLAGS		FS_IOC_GETFLAGS
+#define	EXT3_IOC_SETFLAGS		FS_IOC_SETFLAGS
 #define	EXT3_IOC_GETVERSION		_IOR('f', 3, long)
 #define	EXT3_IOC_SETVERSION		_IOW('f', 4, long)
 #define EXT3_IOC_GROUP_EXTEND		_IOW('f', 7, unsigned long)
 #define EXT3_IOC_GROUP_ADD		_IOW('f', 8,struct ext3_new_group_input)
-#define	EXT3_IOC_GETVERSION_OLD		_IOR('v', 1, long)
-#define	EXT3_IOC_SETVERSION_OLD		_IOW('v', 2, long)
+#define	EXT3_IOC_GETVERSION_OLD		FS_IOC_GETVERSION
+#define	EXT3_IOC_SETVERSION_OLD		FS_IOC_SETVERSION
 #ifdef CONFIG_JBD_DEBUG
 #define EXT3_IOC_WAIT_FOR_READONLY	_IOR('f', 99, long)
 #endif
@@ -235,6 +235,18 @@ #define EXT3_IOC_GETRSVSZ		_IOR('f', 5, 
 #define EXT3_IOC_SETRSVSZ		_IOW('f', 6, long)
 
 /*
+ * ioctl commands in 32 bit emulation
+ */
+#define EXT3_IOC32_GETVERSION		_IOR('f', 3, int)
+#define EXT3_IOC32_SETVERSION		_IOW('f', 4, int)
+#define EXT3_IOC32_GETRSVSZ		_IOR('f', 5, int)
+#define EXT3_IOC32_SETRSVSZ		_IOW('f', 6, int)
+#define EXT3_IOC32_GROUP_EXTEND		_IOW('f', 7, unsigned int)
+#ifdef CONFIG_JBD_DEBUG
+#define EXT3_IOC32_WAIT_FOR_READONLY	_IOR('f', 99, int)
+#endif
+
+/*
  *  Mount options
  */
 struct ext3_mount_options {
diff --git a/include/linux/fs.h b/include/linux/fs.h
index cd7fc6a..63d3126 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -216,6 +216,45 @@ #define BMAP_IOCTL 1		/* obsolete - kept
 #define FIBMAP	   _IO(0x00,1)	/* bmap access */
 #define FIGETBSZ   _IO(0x00,2)	/* get the block size used for bmap */
 
+#define	FS_IOC_GETFLAGS			_IOR('f', 1, long)
+#define	FS_IOC_SETFLAGS			_IOW('f', 2, long)
+#define	FS_IOC_GETVERSION		_IOR('v', 1, long)
+#define	FS_IOC_SETVERSION		_IOW('v', 2, long)
+#define FS_IOC32_GETFLAGS		_IOR('f', 1, int)
+#define FS_IOC32_SETFLAGS		_IOW('f', 2, int)
+#define FS_IOC32_GETVERSION		_IOR('v', 1, int)
+#define FS_IOC32_SETVERSION		_IOW('v', 2, int)
+
+/*
+ * Inode flags (FS_IOC_GETFLAGS / FS_IOC_SETFLAGS)
+ */
+#define	FS_SECRM_FL			0x00000001 /* Secure deletion */
+#define	FS_UNRM_FL			0x00000002 /* Undelete */
+#define	FS_COMPR_FL			0x00000004 /* Compress file */
+#define FS_SYNC_FL			0x00000008 /* Synchronous updates */
+#define FS_IMMUTABLE_FL			0x00000010 /* Immutable file */
+#define FS_APPEND_FL			0x00000020 /* writes to file may only append */
+#define FS_NODUMP_FL			0x00000040 /* do not dump file */
+#define FS_NOATIME_FL			0x00000080 /* do not update atime */
+/* Reserved for compression usage... */
+#define FS_DIRTY_FL			0x00000100
+#define FS_COMPRBLK_FL			0x00000200 /* One or more compressed clusters */
+#define FS_NOCOMP_FL			0x00000400 /* Don't compress */
+#define FS_ECOMPR_FL			0x00000800 /* Compression error */
+/* End compression flags --- maybe not all used */
+#define FS_BTREE_FL			0x00001000 /* btree format dir */
+#define FS_INDEX_FL			0x00001000 /* hash-indexed directory */
+#define FS_IMAGIC_FL			0x00002000 /* AFS directory */
+#define FS_JOURNAL_DATA_FL		0x00004000 /* Reserved for ext3 */
+#define FS_NOTAIL_FL			0x00008000 /* file tail should not be merged */
+#define FS_DIRSYNC_FL			0x00010000 /* dirsync behaviour (directories only) */
+#define FS_TOPDIR_FL			0x00020000 /* Top of directory hierarchies*/
+#define FS_RESERVED_FL			0x80000000 /* reserved for ext2 lib */
+
+#define FS_FL_USER_VISIBLE		0x0003DFFF /* User visible flags */
+#define FS_FL_USER_MODIFIABLE		0x000380FF /* User modifiable flags */
+
+
 #define SYNC_FILE_RANGE_WAIT_BEFORE	1
 #define SYNC_FILE_RANGE_WRITE		2
 #define SYNC_FILE_RANGE_WAIT_AFTER	4
diff --git a/include/linux/reiserfs_fs.h b/include/linux/reiserfs_fs.h
index daa2d83..54c3054 100644
--- a/include/linux/reiserfs_fs.h
+++ b/include/linux/reiserfs_fs.h
@@ -813,21 +813,19 @@ #define sd_v1_first_direct_byte(sdp) \
 #define set_sd_v1_first_direct_byte(sdp,v) \
                                 ((sdp)->sd_first_direct_byte = cpu_to_le32(v))
 
-#include <linux/ext2_fs.h>
-
 /* inode flags stored in sd_attrs (nee sd_reserved) */
 
 /* we want common flags to have the same values as in ext2,
    so chattr(1) will work without problems */
-#define REISERFS_IMMUTABLE_FL EXT2_IMMUTABLE_FL
-#define REISERFS_APPEND_FL    EXT2_APPEND_FL
-#define REISERFS_SYNC_FL      EXT2_SYNC_FL
-#define REISERFS_NOATIME_FL   EXT2_NOATIME_FL
-#define REISERFS_NODUMP_FL    EXT2_NODUMP_FL
-#define REISERFS_SECRM_FL     EXT2_SECRM_FL
-#define REISERFS_UNRM_FL      EXT2_UNRM_FL
-#define REISERFS_COMPR_FL     EXT2_COMPR_FL
-#define REISERFS_NOTAIL_FL    EXT2_NOTAIL_FL
+#define REISERFS_IMMUTABLE_FL FS_IMMUTABLE_FL
+#define REISERFS_APPEND_FL    FS_APPEND_FL
+#define REISERFS_SYNC_FL      FS_SYNC_FL
+#define REISERFS_NOATIME_FL   FS_NOATIME_FL
+#define REISERFS_NODUMP_FL    FS_NODUMP_FL
+#define REISERFS_SECRM_FL     FS_SECRM_FL
+#define REISERFS_UNRM_FL      FS_UNRM_FL
+#define REISERFS_COMPR_FL     FS_COMPR_FL
+#define REISERFS_NOTAIL_FL    FS_NOTAIL_FL
 
 /* persistent flags that file inherits from the parent directory */
 #define REISERFS_INHERIT_MASK ( REISERFS_IMMUTABLE_FL |	\
@@ -2174,10 +2172,10 @@ int reiserfs_ioctl(struct inode *inode, 
 #define REISERFS_IOC_UNPACK		_IOW(0xCD,1,long)
 /* define following flags to be the same as in ext2, so that chattr(1),
    lsattr(1) will work with us. */
-#define REISERFS_IOC_GETFLAGS		EXT2_IOC_GETFLAGS
-#define REISERFS_IOC_SETFLAGS		EXT2_IOC_SETFLAGS
-#define REISERFS_IOC_GETVERSION		EXT2_IOC_GETVERSION
-#define REISERFS_IOC_SETVERSION		EXT2_IOC_SETVERSION
+#define REISERFS_IOC_GETFLAGS		FS_IOC_GETFLAGS
+#define REISERFS_IOC_SETFLAGS		FS_IOC_SETFLAGS
+#define REISERFS_IOC_GETVERSION		FS_IOC_GETVERSION
+#define REISERFS_IOC_SETVERSION		FS_IOC_SETVERSION
 
 /* Locking primitives */
 /* Right now we are still falling back to (un)lock_kernel, but eventually that

[PATCH 12/18] [PATCH] BLOCK: Move the ReiserFS device ioctl compat stuff to the ReiserFS driver [try #4]

[David Howells]

From: David Howells <dhowells@redhat.com>

Move the ReiserFS device ioctl compat stuff from fs/compat_ioctl.c to the
ReiserFS driver so that the ReiserFS header file doesn't need to be included.

Signed-Off-By: David Howells <dhowells@redhat.com>
---

 fs/compat_ioctl.c           |   12 ------------
 fs/reiserfs/dir.c           |    3 +++
 fs/reiserfs/file.c          |    4 ++++
 fs/reiserfs/ioctl.c         |   35 +++++++++++++++++++++++++++++++++++
 include/linux/reiserfs_fs.h |    9 +++++++++
 5 files changed, 51 insertions(+), 12 deletions(-)

diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c
index bd9c4f4..0346f2a 100644
--- a/fs/compat_ioctl.c
+++ b/fs/compat_ioctl.c
@@ -59,7 +59,6 @@ #include <linux/rtc.h>
 #include <linux/pci.h>
 #include <linux/module.h>
 #include <linux/serial.h>
-#include <linux/reiserfs_fs.h>
 #include <linux/if_tun.h>
 #include <linux/ctype.h>
 #include <linux/ioctl32.h>
@@ -2014,16 +2013,6 @@ static int vfat_ioctl32(unsigned fd, uns
 	return ret;
 }
 
-#define REISERFS_IOC_UNPACK32               _IOW(0xCD,1,int)
-
-static int reiserfs_ioctl32(unsigned fd, unsigned cmd, unsigned long ptr)
-{
-        if (cmd == REISERFS_IOC_UNPACK32)
-                cmd = REISERFS_IOC_UNPACK;
-
-        return sys_ioctl(fd,cmd,ptr);
-}
-
 struct raw32_config_request
 {
         compat_int_t    raw_minor;
@@ -2784,7 +2773,6 @@ HANDLE_IOCTL(BLKGETSIZE64_32, do_blkgets
 /* vfat */
 HANDLE_IOCTL(VFAT_IOCTL_READDIR_BOTH32, vfat_ioctl32)
 HANDLE_IOCTL(VFAT_IOCTL_READDIR_SHORT32, vfat_ioctl32)
-HANDLE_IOCTL(REISERFS_IOC_UNPACK32, reiserfs_ioctl32)
 /* Raw devices */
 HANDLE_IOCTL(RAW_SETBIND, raw_ioctl)
 HANDLE_IOCTL(RAW_GETBIND, raw_ioctl)
diff --git a/fs/reiserfs/dir.c b/fs/reiserfs/dir.c
index 9aabcc0..657050a 100644
--- a/fs/reiserfs/dir.c
+++ b/fs/reiserfs/dir.c
@@ -22,6 +22,9 @@ const struct file_operations reiserfs_di
 	.readdir = reiserfs_readdir,
 	.fsync = reiserfs_dir_fsync,
 	.ioctl = reiserfs_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl = reiserfs_compat_ioctl,
+#endif
 };
 
 static int reiserfs_dir_fsync(struct file *filp, struct dentry *dentry,
diff --git a/fs/reiserfs/file.c b/fs/reiserfs/file.c
index 1627edd..719b367 100644
--- a/fs/reiserfs/file.c
+++ b/fs/reiserfs/file.c
@@ -2,6 +2,7 @@
  * Copyright 2000 by Hans Reiser, licensing governed by reiserfs/README
  */
 
+#include <linux/config.h>
 #include <linux/time.h>
 #include <linux/reiserfs_fs.h>
 #include <linux/reiserfs_acl.h>
@@ -1568,6 +1569,9 @@ const struct file_operations reiserfs_fi
 	.read = generic_file_read,
 	.write = reiserfs_file_write,
 	.ioctl = reiserfs_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl = reiserfs_compat_ioctl,
+#endif
 	.mmap = generic_file_mmap,
 	.release = reiserfs_file_release,
 	.fsync = reiserfs_sync_file,
diff --git a/fs/reiserfs/ioctl.c b/fs/reiserfs/ioctl.c
index a986b5e..9c57578 100644
--- a/fs/reiserfs/ioctl.c
+++ b/fs/reiserfs/ioctl.c
@@ -9,6 +9,7 @@ #include <linux/time.h>
 #include <asm/uaccess.h>
 #include <linux/pagemap.h>
 #include <linux/smp_lock.h>
+#include <linux/compat.h>
 
 static int reiserfs_unpack(struct inode *inode, struct file *filp);
 
@@ -94,6 +95,40 @@ int reiserfs_ioctl(struct inode *inode, 
 	}
 }
 
+#ifdef CONFIG_COMPAT
+long reiserfs_compat_ioctl(struct file *file, unsigned int cmd,
+				unsigned long arg)
+{
+	struct inode *inode = file->f_dentry->d_inode;
+	int ret;
+
+	/* These are just misnamed, they actually get/put from/to user an int */
+	switch (cmd) {
+	case REISERFS_IOC32_UNPACK:
+		cmd = REISERFS_IOC_UNPACK;
+		break;
+	case REISERFS_IOC32_GETFLAGS:
+		cmd = REISERFS_IOC_GETFLAGS;
+		break;
+	case REISERFS_IOC32_SETFLAGS:
+		cmd = REISERFS_IOC_SETFLAGS;
+		break;
+	case REISERFS_IOC32_GETVERSION:
+		cmd = REISERFS_IOC_GETVERSION;
+		break;
+	case REISERFS_IOC32_SETVERSION:
+		cmd = REISERFS_IOC_SETVERSION;
+		break;
+	default:
+		return -ENOIOCTLCMD;
+	}
+	lock_kernel();
+	ret = reiserfs_ioctl(inode, file, cmd, (unsigned long) compat_ptr(arg));
+	unlock_kernel();
+	return ret;
+}
+#endif
+
 /*
 ** reiserfs_unpack
 ** Function try to convert tail from direct item into indirect.
diff --git a/include/linux/reiserfs_fs.h b/include/linux/reiserfs_fs.h
index 54c3054..6ab7be9 100644
--- a/include/linux/reiserfs_fs.h
+++ b/include/linux/reiserfs_fs.h
@@ -2167,6 +2167,8 @@ #define SPARE_SPACE 500
 /* prototypes from ioctl.c */
 int reiserfs_ioctl(struct inode *inode, struct file *filp,
 		   unsigned int cmd, unsigned long arg);
+long reiserfs_compat_ioctl(struct file *filp,
+		   unsigned int cmd, unsigned long arg);
 
 /* ioctl's command */
 #define REISERFS_IOC_UNPACK		_IOW(0xCD,1,long)
@@ -2177,6 +2179,13 @@ #define REISERFS_IOC_SETFLAGS		FS_IOC_SE
 #define REISERFS_IOC_GETVERSION		FS_IOC_GETVERSION
 #define REISERFS_IOC_SETVERSION		FS_IOC_SETVERSION
 
+/* the 32 bit compat definitions with int argument */
+#define REISERFS_IOC32_UNPACK		_IOW(0xCD, 1, int)
+#define REISERFS_IOC32_GETFLAGS		FS_IOC32_GETFLAGS
+#define REISERFS_IOC32_SETFLAGS		FS_IOC32_SETFLAGS
+#define REISERFS_IOC32_GETVERSION	FS_IOC32_GETVERSION
+#define REISERFS_IOC32_SETVERSION	FS_IOC32_SETVERSION
+
 /* Locking primitives */
 /* Right now we are still falling back to (un)lock_kernel, but eventually that
    would evolve into real per-fs locks */

[PATCH 13/18] [PATCH] BLOCK: Move the Ext2 device ioctl compat stuff to the Ext2 driver [try #4]

[David Howells]

From: David Howells <dhowells@redhat.com>

Move the Ext2 device ioctl compat stuff from fs/compat_ioctl.c to the Ext2
driver so that the Ext2 header file doesn't need to be included.

Signed-Off-By: David Howells <dhowells@redhat.com>
---

 fs/compat_ioctl.c |   17 -----------------
 fs/ext2/dir.c     |    3 +++
 fs/ext2/ext2.h    |    1 +
 fs/ext2/file.c    |    6 ++++++
 fs/ext2/ioctl.c   |   32 ++++++++++++++++++++++++++++++++
 5 files changed, 42 insertions(+), 17 deletions(-)

diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c
index 0346f2a..3594668 100644
--- a/fs/compat_ioctl.c
+++ b/fs/compat_ioctl.c
@@ -45,7 +45,6 @@ #include <linux/auto_fs4.h>
 #include <linux/tty.h>
 #include <linux/vt_kern.h>
 #include <linux/fb.h>
-#include <linux/ext2_fs.h>
 #include <linux/ext3_jbd.h>
 #include <linux/ext3_fs.h>
 #include <linux/videodev.h>
@@ -159,18 +158,6 @@ static int rw_long(unsigned int fd, unsi
 	return err;
 }
 
-static int do_ext2_ioctl(unsigned int fd, unsigned int cmd, unsigned long arg)
-{
-	/* These are just misnamed, they actually get/put from/to user an int */
-	switch (cmd) {
-	case EXT2_IOC32_GETFLAGS: cmd = EXT2_IOC_GETFLAGS; break;
-	case EXT2_IOC32_SETFLAGS: cmd = EXT2_IOC_SETFLAGS; break;
-	case EXT2_IOC32_GETVERSION: cmd = EXT2_IOC_GETVERSION; break;
-	case EXT2_IOC32_SETVERSION: cmd = EXT2_IOC_SETVERSION; break;
-	}
-	return sys_ioctl(fd, cmd, (unsigned long)compat_ptr(arg));
-}
-
 static int do_ext3_ioctl(unsigned int fd, unsigned int cmd, unsigned long arg)
 {
 	/* These are just misnamed, they actually get/put from/to user an int */
@@ -2725,10 +2712,6 @@ HANDLE_IOCTL(PIO_UNIMAP, do_unimap_ioctl
 HANDLE_IOCTL(GIO_UNIMAP, do_unimap_ioctl)
 HANDLE_IOCTL(KDFONTOP, do_kdfontop_ioctl)
 #endif
-HANDLE_IOCTL(EXT2_IOC32_GETFLAGS, do_ext2_ioctl)
-HANDLE_IOCTL(EXT2_IOC32_SETFLAGS, do_ext2_ioctl)
-HANDLE_IOCTL(EXT2_IOC32_GETVERSION, do_ext2_ioctl)
-HANDLE_IOCTL(EXT2_IOC32_SETVERSION, do_ext2_ioctl)
 HANDLE_IOCTL(EXT3_IOC32_GETVERSION, do_ext3_ioctl)
 HANDLE_IOCTL(EXT3_IOC32_SETVERSION, do_ext3_ioctl)
 HANDLE_IOCTL(EXT3_IOC32_GETRSVSZ, do_ext3_ioctl)
diff --git a/fs/ext2/dir.c b/fs/ext2/dir.c
index 92ea826..3e7a84a 100644
--- a/fs/ext2/dir.c
+++ b/fs/ext2/dir.c
@@ -661,5 +661,8 @@ const struct file_operations ext2_dir_op
 	.read		= generic_read_dir,
 	.readdir	= ext2_readdir,
 	.ioctl		= ext2_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl	= ext2_compat_ioctl,
+#endif
 	.fsync		= ext2_sync_file,
 };
diff --git a/fs/ext2/ext2.h b/fs/ext2/ext2.h
index e65a019..c19ac15 100644
--- a/fs/ext2/ext2.h
+++ b/fs/ext2/ext2.h
@@ -137,6 +137,7 @@ extern void ext2_set_inode_flags(struct 
 /* ioctl.c */
 extern int ext2_ioctl (struct inode *, struct file *, unsigned int,
 		       unsigned long);
+extern long ext2_compat_ioctl(struct file *, unsigned int, unsigned long);
 
 /* namei.c */
 struct dentry *ext2_get_parent(struct dentry *child);
diff --git a/fs/ext2/file.c b/fs/ext2/file.c
index 23e2c7c..e8bbed9 100644
--- a/fs/ext2/file.c
+++ b/fs/ext2/file.c
@@ -46,6 +46,9 @@ const struct file_operations ext2_file_o
 	.aio_read	= generic_file_aio_read,
 	.aio_write	= generic_file_aio_write,
 	.ioctl		= ext2_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl	= ext2_compat_ioctl,
+#endif
 	.mmap		= generic_file_mmap,
 	.open		= generic_file_open,
 	.release	= ext2_release_file,
@@ -63,6 +66,9 @@ const struct file_operations ext2_xip_fi
 	.read		= xip_file_read,
 	.write		= xip_file_write,
 	.ioctl		= ext2_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl	= ext2_compat_ioctl,
+#endif
 	.mmap		= xip_file_mmap,
 	.open		= generic_file_open,
 	.release	= ext2_release_file,
diff --git a/fs/ext2/ioctl.c b/fs/ext2/ioctl.c
index 3ca9afd..1dfba77 100644
--- a/fs/ext2/ioctl.c
+++ b/fs/ext2/ioctl.c
@@ -11,6 +11,8 @@ #include "ext2.h"
 #include <linux/capability.h>
 #include <linux/time.h>
 #include <linux/sched.h>
+#include <linux/compat.h>
+#include <linux/smp_lock.h>
 #include <asm/current.h>
 #include <asm/uaccess.h>
 
@@ -80,3 +82,33 @@ int ext2_ioctl (struct inode * inode, st
 		return -ENOTTY;
 	}
 }
+
+#ifdef CONFIG_COMPAT
+long ext2_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+	struct inode *inode = file->f_dentry->d_inode;
+	int ret;
+
+	/* These are just misnamed, they actually get/put from/to user an int */
+	switch (cmd) {
+	case EXT2_IOC32_GETFLAGS:
+		cmd = EXT2_IOC_GETFLAGS;
+		break;
+	case EXT2_IOC32_SETFLAGS:
+		cmd = EXT2_IOC_SETFLAGS;
+		break;
+	case EXT2_IOC32_GETVERSION:
+		cmd = EXT2_IOC_GETVERSION;
+		break;
+	case EXT2_IOC32_SETVERSION:
+		cmd = EXT2_IOC_SETVERSION;
+		break;
+	default:
+		return -ENOIOCTLCMD;
+	}
+	lock_kernel();
+	ret = ext2_ioctl(inode, file, cmd, (unsigned long) compat_ptr(arg));
+	unlock_kernel();
+	return ret;
+}
+#endif

[PATCH 14/18] [PATCH] BLOCK: Move the Ext3 device ioctl compat stuff to the Ext3 driver [try #4]

[David Howells]

From: David Howells <dhowells@redhat.com>

Move the Ext3 device ioctl compat stuff from fs/compat_ioctl.c to the Ext3
driver so that the Ext3 header file doesn't need to be included.

Signed-Off-By: David Howells <dhowells@redhat.com>
---

 fs/compat_ioctl.c       |   27 -----------------------
 fs/ext3/dir.c           |    3 +++
 fs/ext3/file.c          |    3 +++
 fs/ext3/ioctl.c         |   55 ++++++++++++++++++++++++++++++++++++++++++++++-
 include/linux/ext3_fs.h |    6 +++++
 5 files changed, 66 insertions(+), 28 deletions(-)

diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c
index 3594668..e5eb0f1 100644
--- a/fs/compat_ioctl.c
+++ b/fs/compat_ioctl.c
@@ -45,8 +45,6 @@ #include <linux/auto_fs4.h>
 #include <linux/tty.h>
 #include <linux/vt_kern.h>
 #include <linux/fb.h>
-#include <linux/ext3_jbd.h>
-#include <linux/ext3_fs.h>
 #include <linux/videodev.h>
 #include <linux/netdevice.h>
 #include <linux/raw.h>
@@ -158,22 +156,6 @@ static int rw_long(unsigned int fd, unsi
 	return err;
 }
 
-static int do_ext3_ioctl(unsigned int fd, unsigned int cmd, unsigned long arg)
-{
-	/* These are just misnamed, they actually get/put from/to user an int */
-	switch (cmd) {
-	case EXT3_IOC32_GETVERSION: cmd = EXT3_IOC_GETVERSION; break;
-	case EXT3_IOC32_SETVERSION: cmd = EXT3_IOC_SETVERSION; break;
-	case EXT3_IOC32_GETRSVSZ: cmd = EXT3_IOC_GETRSVSZ; break;
-	case EXT3_IOC32_SETRSVSZ: cmd = EXT3_IOC_SETRSVSZ; break;
-	case EXT3_IOC32_GROUP_EXTEND: cmd = EXT3_IOC_GROUP_EXTEND; break;
-#ifdef CONFIG_JBD_DEBUG
-	case EXT3_IOC32_WAIT_FOR_READONLY: cmd = EXT3_IOC_WAIT_FOR_READONLY; break;
-#endif
-	}
-	return sys_ioctl(fd, cmd, (unsigned long)compat_ptr(arg));
-}
-
 struct compat_video_event {
 	int32_t		type;
 	compat_time_t	timestamp;
@@ -2712,15 +2694,6 @@ HANDLE_IOCTL(PIO_UNIMAP, do_unimap_ioctl
 HANDLE_IOCTL(GIO_UNIMAP, do_unimap_ioctl)
 HANDLE_IOCTL(KDFONTOP, do_kdfontop_ioctl)
 #endif
-HANDLE_IOCTL(EXT3_IOC32_GETVERSION, do_ext3_ioctl)
-HANDLE_IOCTL(EXT3_IOC32_SETVERSION, do_ext3_ioctl)
-HANDLE_IOCTL(EXT3_IOC32_GETRSVSZ, do_ext3_ioctl)
-HANDLE_IOCTL(EXT3_IOC32_SETRSVSZ, do_ext3_ioctl)
-HANDLE_IOCTL(EXT3_IOC32_GROUP_EXTEND, do_ext3_ioctl)
-COMPATIBLE_IOCTL(EXT3_IOC_GROUP_ADD)
-#ifdef CONFIG_JBD_DEBUG
-HANDLE_IOCTL(EXT3_IOC32_WAIT_FOR_READONLY, do_ext3_ioctl)
-#endif
 /* One SMB ioctl needs translations. */
 #define SMB_IOC_GETMOUNTUID_32 _IOR('u', 1, compat_uid_t)
 HANDLE_IOCTL(SMB_IOC_GETMOUNTUID_32, do_smb_getmountuid)
diff --git a/fs/ext3/dir.c b/fs/ext3/dir.c
index fbb0d4e..7ba8917 100644
--- a/fs/ext3/dir.c
+++ b/fs/ext3/dir.c
@@ -44,6 +44,9 @@ const struct file_operations ext3_dir_op
 	.read		= generic_read_dir,
 	.readdir	= ext3_readdir,		/* we take BKL. needed?*/
 	.ioctl		= ext3_ioctl,		/* BKL held */
+#ifdef CONFIG_COMPAT
+	.compat_ioctl	= ext3_compat_ioctl,
+#endif
 	.fsync		= ext3_sync_file,	/* BKL held */
 #ifdef CONFIG_EXT3_INDEX
 	.release	= ext3_release_dir,
diff --git a/fs/ext3/file.c b/fs/ext3/file.c
index 1efefb6..40320da 100644
--- a/fs/ext3/file.c
+++ b/fs/ext3/file.c
@@ -114,6 +114,9 @@ const struct file_operations ext3_file_o
 	.readv		= generic_file_readv,
 	.writev		= generic_file_writev,
 	.ioctl		= ext3_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl	= ext3_compat_ioctl,
+#endif
 	.mmap		= generic_file_mmap,
 	.open		= generic_file_open,
 	.release	= ext3_release_file,
diff --git a/fs/ext3/ioctl.c b/fs/ext3/ioctl.c
index 3a6b012..12daa68 100644
--- a/fs/ext3/ioctl.c
+++ b/fs/ext3/ioctl.c
@@ -13,9 +13,10 @@ #include <linux/capability.h>
 #include <linux/ext3_fs.h>
 #include <linux/ext3_jbd.h>
 #include <linux/time.h>
+#include <linux/compat.h>
+#include <linux/smp_lock.h>
 #include <asm/uaccess.h>
 
-
 int ext3_ioctl (struct inode * inode, struct file * filp, unsigned int cmd,
 		unsigned long arg)
 {
@@ -252,3 +253,55 @@ #endif
 		return -ENOTTY;
 	}
 }
+
+#ifdef CONFIG_COMPAT
+long ext3_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+	struct inode *inode = file->f_dentry->d_inode;
+	int ret;
+
+	/* These are just misnamed, they actually get/put from/to user an int */
+	switch (cmd) {
+	case EXT3_IOC32_GETFLAGS:
+		cmd = EXT3_IOC_GETFLAGS;
+		break;
+	case EXT3_IOC32_SETFLAGS:
+		cmd = EXT3_IOC_SETFLAGS;
+		break;
+	case EXT3_IOC32_GETVERSION:
+		cmd = EXT3_IOC_GETVERSION;
+		break;
+	case EXT3_IOC32_SETVERSION:
+		cmd = EXT3_IOC_SETVERSION;
+		break;
+	case EXT3_IOC32_GROUP_EXTEND:
+		cmd = EXT3_IOC_GROUP_EXTEND;
+		break;
+	case EXT3_IOC32_GETVERSION_OLD:
+		cmd = EXT3_IOC_GETVERSION_OLD;
+		break;
+	case EXT3_IOC32_SETVERSION_OLD:
+		cmd = EXT3_IOC_SETVERSION_OLD;
+		break;
+#ifdef CONFIG_JBD_DEBUG
+	case EXT3_IOC32_WAIT_FOR_READONLY:
+		cmd = EXT3_IOC_WAIT_FOR_READONLY;
+		break;
+#endif
+	case EXT3_IOC32_GETRSVSZ:
+		cmd = EXT3_IOC_GETRSVSZ;
+		break;
+	case EXT3_IOC32_SETRSVSZ:
+		cmd = EXT3_IOC_SETRSVSZ;
+		break;
+	case EXT3_IOC_GROUP_ADD:
+		break;
+	default:
+		return -ENOIOCTLCMD;
+	}
+	lock_kernel();
+	ret = ext3_ioctl(inode, file, cmd, (unsigned long) compat_ptr(arg));
+	unlock_kernel();
+	return ret;
+}
+#endif
diff --git a/include/linux/ext3_fs.h b/include/linux/ext3_fs.h
index 90cfba2..690c730 100644
--- a/include/linux/ext3_fs.h
+++ b/include/linux/ext3_fs.h
@@ -237,6 +237,8 @@ #define EXT3_IOC_SETRSVSZ		_IOW('f', 6, 
 /*
  * ioctl commands in 32 bit emulation
  */
+#define EXT3_IOC32_GETFLAGS		FS_IOC32_GETFLAGS
+#define EXT3_IOC32_SETFLAGS		FS_IOC32_SETFLAGS
 #define EXT3_IOC32_GETVERSION		_IOR('f', 3, int)
 #define EXT3_IOC32_SETVERSION		_IOW('f', 4, int)
 #define EXT3_IOC32_GETRSVSZ		_IOR('f', 5, int)
@@ -245,6 +247,9 @@ #define EXT3_IOC32_GROUP_EXTEND		_IOW('f
 #ifdef CONFIG_JBD_DEBUG
 #define EXT3_IOC32_WAIT_FOR_READONLY	_IOR('f', 99, int)
 #endif
+#define EXT3_IOC32_GETVERSION_OLD	FS_IOC32_GETVERSION
+#define EXT3_IOC32_SETVERSION_OLD	FS_IOC32_SETVERSION
+
 
 /*
  *  Mount options
@@ -828,6 +833,7 @@ extern void ext3_set_aops(struct inode *
 /* ioctl.c */
 extern int ext3_ioctl (struct inode *, struct file *, unsigned int,
 		       unsigned long);
+extern long ext3_compat_ioctl (struct file *, unsigned int, unsigned long);
 
 /* namei.c */
 extern int ext3_orphan_add(handle_t *, struct inode *);

[PATCH 15/18] [PATCH] BLOCK: Move the msdos device ioctl compat stuff to the msdos driver [try #4]

[David Howells]

From: David Howells <dhowells@redhat.com>

Move the msdos device ioctl compat stuff from fs/compat_ioctl.c to the msdos
driver so that the msdos header file doesn't need to be included.

Signed-Off-By: David Howells <dhowells@redhat.com>
---

 fs/compat_ioctl.c |   49 ------------------------------------------------
 fs/fat/dir.c      |   54 +++++++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 54 insertions(+), 49 deletions(-)

diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c
index e5eb0f1..e1a5643 100644
--- a/fs/compat_ioctl.c
+++ b/fs/compat_ioctl.c
@@ -108,7 +108,6 @@ #include <linux/usbdevice_fs.h>
 #include <linux/nbd.h>
 #include <linux/random.h>
 #include <linux/filter.h>
-#include <linux/msdos_fs.h>
 #include <linux/pktcdvd.h>
 
 #include <linux/hiddev.h>
@@ -1937,51 +1936,6 @@ static int mtd_rw_oob(unsigned int fd, u
 	return err;
 }	
 
-#define	VFAT_IOCTL_READDIR_BOTH32	_IOR('r', 1, struct compat_dirent[2])
-#define	VFAT_IOCTL_READDIR_SHORT32	_IOR('r', 2, struct compat_dirent[2])
-
-static long
-put_dirent32 (struct dirent *d, struct compat_dirent __user *d32)
-{
-        if (!access_ok(VERIFY_WRITE, d32, sizeof(struct compat_dirent)))
-                return -EFAULT;
-
-        __put_user(d->d_ino, &d32->d_ino);
-        __put_user(d->d_off, &d32->d_off);
-        __put_user(d->d_reclen, &d32->d_reclen);
-        if (__copy_to_user(d32->d_name, d->d_name, d->d_reclen))
-		return -EFAULT;
-
-        return 0;
-}
-
-static int vfat_ioctl32(unsigned fd, unsigned cmd, unsigned long arg)
-{
-	struct compat_dirent __user *p = compat_ptr(arg);
-	int ret;
-	mm_segment_t oldfs = get_fs();
-	struct dirent d[2];
-
-	switch(cmd)
-	{
-        	case VFAT_IOCTL_READDIR_BOTH32:
-                	cmd = VFAT_IOCTL_READDIR_BOTH;
-                	break;
-        	case VFAT_IOCTL_READDIR_SHORT32:
-                	cmd = VFAT_IOCTL_READDIR_SHORT;
-                	break;
-	}
-
-	set_fs(KERNEL_DS);
-	ret = sys_ioctl(fd,cmd,(unsigned long)&d);
-	set_fs(oldfs);
-	if (ret >= 0) {
-		ret |= put_dirent32(&d[0], p);
-		ret |= put_dirent32(&d[1], p + 1);
-	}
-	return ret;
-}
-
 struct raw32_config_request
 {
         compat_int_t    raw_minor;
@@ -2726,9 +2680,6 @@ HANDLE_IOCTL(SONET_GETFRSENSE, do_atm_io
 HANDLE_IOCTL(BLKBSZGET_32, do_blkbszget)
 HANDLE_IOCTL(BLKBSZSET_32, do_blkbszset)
 HANDLE_IOCTL(BLKGETSIZE64_32, do_blkgetsize64)
-/* vfat */
-HANDLE_IOCTL(VFAT_IOCTL_READDIR_BOTH32, vfat_ioctl32)
-HANDLE_IOCTL(VFAT_IOCTL_READDIR_SHORT32, vfat_ioctl32)
 /* Raw devices */
 HANDLE_IOCTL(RAW_SETBIND, raw_ioctl)
 HANDLE_IOCTL(RAW_GETBIND, raw_ioctl)
diff --git a/fs/fat/dir.c b/fs/fat/dir.c
index 698b85b..8e99330 100644
--- a/fs/fat/dir.c
+++ b/fs/fat/dir.c
@@ -20,6 +20,7 @@ #include <linux/msdos_fs.h>
 #include <linux/dirent.h>
 #include <linux/smp_lock.h>
 #include <linux/buffer_head.h>
+#include <linux/compat.h>
 #include <asm/uaccess.h>
 
 static inline loff_t fat_make_i_pos(struct super_block *sb,
@@ -740,11 +741,64 @@ static int fat_dir_ioctl(struct inode * 
 		ret = buf.result;
 	return ret;
 }
+#define	VFAT_IOCTL_READDIR_BOTH32	_IOR('r', 1, struct compat_dirent[2])
+#define	VFAT_IOCTL_READDIR_SHORT32	_IOR('r', 2, struct compat_dirent[2])
+
+static long fat_compat_put_dirent32(struct dirent *d,
+				    struct compat_dirent __user *d32)
+{
+        if (!access_ok(VERIFY_WRITE, d32, sizeof(struct compat_dirent)))
+                return -EFAULT;
+
+        __put_user(d->d_ino, &d32->d_ino);
+        __put_user(d->d_off, &d32->d_off);
+        __put_user(d->d_reclen, &d32->d_reclen);
+        if (__copy_to_user(d32->d_name, d->d_name, d->d_reclen))
+		return -EFAULT;
+
+        return 0;
+}
+
+static long fat_compat_dir_ioctl(struct file *file, unsigned cmd,
+				 unsigned long arg)
+{
+	struct compat_dirent __user *p = compat_ptr(arg);
+	int ret;
+	mm_segment_t oldfs = get_fs();
+	struct dirent d[2];
+
+	switch (cmd) {
+	case VFAT_IOCTL_READDIR_BOTH32:
+		cmd = VFAT_IOCTL_READDIR_BOTH;
+		break;
+	case VFAT_IOCTL_READDIR_SHORT32:
+		cmd = VFAT_IOCTL_READDIR_SHORT;
+		break;
+	default:
+		return -ENOIOCTLCMD;
+	}
+
+	set_fs(KERNEL_DS);
+	lock_kernel();
+	ret = fat_dir_ioctl(file->f_dentry->d_inode, file,
+			    cmd, (unsigned long) &d);
+	unlock_kernel();
+	set_fs(oldfs);
+	if (ret >= 0) {
+		ret |= fat_compat_put_dirent32(&d[0], p);
+		ret |= fat_compat_put_dirent32(&d[1], p + 1);
+	}
+	return ret;
+}
+
 
 const struct file_operations fat_dir_operations = {
 	.read		= generic_read_dir,
 	.readdir	= fat_readdir,
 	.ioctl		= fat_dir_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl	= fat_compat_dir_ioctl,
+#endif
 	.fsync		= file_fsync,
 };
 

[PATCH 16/18] [PATCH] BLOCK: Remove no-longer necessary linux/mpage.h inclusions [try #4]

[David Howells]

From: David Howells <dhowells@redhat.com>

Remove inclusions of linux/mpage.h that are no longer necessary due to the
transfer of generic_writepages().

Signed-Off-By: David Howells <dhowells@redhat.com>
---

 fs/cifs/file.c |    1 -
 fs/nfs/write.c |    1 -
 2 files changed, 0 insertions(+), 2 deletions(-)

diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 944d2b9..8488f27 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -24,7 +24,6 @@ #include <linux/fs.h>
 #include <linux/backing-dev.h>
 #include <linux/stat.h>
 #include <linux/fcntl.h>
-#include <linux/mpage.h>
 #include <linux/pagemap.h>
 #include <linux/pagevec.h>
 #include <linux/smp_lock.h>
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 5077499..18b248e 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -51,7 +51,6 @@ #include <linux/slab.h>
 #include <linux/mm.h>
 #include <linux/pagemap.h>
 #include <linux/file.h>
-#include <linux/mpage.h>
 #include <linux/writeback.h>
 
 #include <linux/sunrpc/clnt.h>

[PATCH 17/18] [PATCH] BLOCK: Remove no-longer necessary linux/buffer_head.h inclusions [try #4]

[David Howells]

From: David Howells <dhowells@redhat.com>

Remove inclusions of linux/buffer_head.h that are no longer necessary due to the
transfer of a number of things out of there.

Signed-Off-By: David Howells <dhowells@redhat.com>
---

 fs/afs/file.c   |    1 -
 fs/cifs/inode.c |    1 -
 2 files changed, 0 insertions(+), 2 deletions(-)

diff --git a/fs/afs/file.c b/fs/afs/file.c
index 5ff8e3a..82e8d83 100644
--- a/fs/afs/file.c
+++ b/fs/afs/file.c
@@ -16,7 +16,6 @@ #include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/fs.h>
 #include <linux/pagemap.h>
-#include <linux/buffer_head.h>
 #include "volume.h"
 #include "vnode.h"
 #include <rxrpc/call.h>
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index b88147c..05f874c 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -19,7 +19,6 @@
  *   Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
  */
 #include <linux/fs.h>
-#include <linux/buffer_head.h>
 #include <linux/stat.h>
 #include <linux/pagemap.h>
 #include <asm/div64.h>

[PATCH 18/18] [PATCH] BLOCK: Make it possible to disable the block layer [try #4]

[David Howells]

From: David Howells <dhowells@redhat.com>

Make it possible to disable the block layer.  Not all embedded devices require
it, some can make do with just JFFS2, NFS, ramfs, etc - none of which require
the block layer to be present.

This patch does the following:

 (*) Introduces CONFIG_BLOCK to disable the block layer, buffering and blockdev
     support.

 (*) Adds dependencies on CONFIG_BLOCK to any configuration item that controls
     an item that uses the block layer.  This includes:

     (*) Block I/O tracing.

     (*) Disk partition code.

     (*) All filesystems that are block based, eg: Ext3, ReiserFS, ISOFS.

     (*) The SCSI layer.  As far as I can tell, even SCSI chardevs use the
     	 block layer to do scheduling.

     (*) Various block-based device drivers, such as IDE, the old CDROM
     	 drivers and USB storage.

     (*) MTD blockdev handling and FTL.

     (*) JFFS - which uses set_bdev_super(), something it could avoid doing by
     	 taking a leaf out of JFFS2's book.

 (*) Makes most of the contents of linux/blkdev.h, linux/buffer_head.h and
     linux/elevator.h contingent on CONFIG_BLOCK being set.  sector_div() is,
     however, still used in places, and so is still available.

 (*) Also made contingent are the contents of linux/mpage.h, linux/genhd.h and
     parts of linux/fs.h.

 (*) Makes a number of files in fs/ contingent on CONFIG_BLOCK.

 (*) Makes mm/bounce.c (bounce buffering) contingent on CONFIG_BLOCK.

 (*) set_page_dirty() doesn't call __set_page_dirty_buffers() if CONFIG_BLOCK
     is not enabled.

 (*) fs/no-block.c is created to hold out-of-line stubs and things that are
     required when CONFIG_BLOCK is not set:

     (*) Default blockdev file operations (to give error ENODEV on opening).

 (*) Makes some /proc changes:

     (*) /proc/devices does not list any blockdevs.

     (*) /proc/diskstats and /proc/partitions are contingent on CONFIG_BLOCK.

 (*) Makes some compat ioctl handling contingent on CONFIG_BLOCK.

 (*) If CONFIG_BLOCK is not defined, makes sys_quotactl() return -ENODEV if
     given command other than Q_SYNC or if a special device is specified.

 (*) In init/do_mounts.c, no reference is made to the blockdev routines if
     CONFIG_BLOCK is not defined.  This does not prohibit NFS roots or JFFS2.

 (*) The bdflush, ioprio_set and ioprio_get syscalls can now be absent (return
     error ENOSYS by way of cond_syscall if so).

 (*) The seclvl_bd_claim() and seclvl_bd_release() security calls do nothing if
     CONFIG_BLOCK is not set, since they can't then happen.

Signed-Off-By: David Howells <dhowells@redhat.com>
---

 block/Kconfig                       |   20 ++++++++++++++
 block/Kconfig.iosched               |    3 ++
 block/Makefile                      |    5 ++--
 drivers/block/Kconfig               |    4 +++
 drivers/cdrom/Kconfig               |    2 +
 drivers/char/Kconfig                |    1 +
 drivers/char/random.c               |    4 +++
 drivers/ide/Kconfig                 |    4 +++
 drivers/ieee1394/Kconfig            |    2 +
 drivers/infiniband/ulp/iser/Kconfig |    2 +
 drivers/infiniband/ulp/srp/Kconfig  |    2 +
 drivers/md/Kconfig                  |    3 ++
 drivers/message/i2o/Kconfig         |    2 +
 drivers/mmc/Kconfig                 |    2 +
 drivers/mmc/Makefile                |    3 +-
 drivers/mtd/Kconfig                 |   12 ++++----
 drivers/mtd/devices/Kconfig         |    2 +
 drivers/s390/block/Kconfig          |    2 +
 drivers/scsi/Kconfig                |    8 ++++--
 drivers/usb/storage/Kconfig         |    2 +
 fs/Kconfig                          |   32 ++++++++++++++++++----
 fs/Makefile                         |   14 +++++++---
 fs/compat_ioctl.c                   |   18 +++++++++++++
 fs/internal.h                       |    6 ++++
 fs/no-block.c                       |   22 +++++++++++++++
 fs/partitions/Makefile              |    2 +
 fs/proc/proc_misc.c                 |   11 +++++++-
 fs/quota.c                          |   44 ++++++++++++++++++++++---------
 fs/super.c                          |    4 +++
 fs/xfs/Kconfig                      |    1 +
 include/linux/blkdev.h              |   50 +++++++++++++++++++++++++----------
 include/linux/buffer_head.h         |   16 +++++++++++
 include/linux/compat_ioctl.h        |    2 +
 include/linux/elevator.h            |    3 ++
 include/linux/fs.h                  |   25 +++++++++++++++---
 include/linux/genhd.h               |    4 +++
 include/linux/mpage.h               |    3 ++
 include/linux/raid/md.h             |    3 ++
 include/linux/raid/md_k.h           |    3 ++
 include/scsi/scsi_tcq.h             |    3 +-
 init/Kconfig                        |    2 +
 init/do_mounts.c                    |   13 ++++++++-
 kernel/sys_ni.c                     |    5 ++++
 mm/Makefile                         |    2 +
 mm/filemap.c                        |    4 +++
 mm/migrate.c                        |    2 +
 mm/page-writeback.c                 |    8 ++++--
 mm/truncate.c                       |    2 +
 security/seclvl.c                   |    4 +++
 49 files changed, 322 insertions(+), 71 deletions(-)

diff --git a/block/Kconfig b/block/Kconfig
index b6f5f0a..9af6c61 100644
--- a/block/Kconfig
+++ b/block/Kconfig
@@ -1,6 +1,24 @@
 #
 # Block layer core configuration
 #
+config BLOCK
+       bool "Enable the block layer"
+       default y
+       help
+	 This permits the block layer to be removed from the kernel if it's not
+	 needed (on some embedded devices for example).  If this option is
+	 disabled, then blockdev files will become unusable and some
+	 filesystems (such as ext3) will become unavailable.
+
+	 This option will also disable SCSI character devices and USB storage
+	 since they make use of various block layer definitions and
+	 facilities.
+
+	 Say Y here unless you know you really don't want to mount disks and
+	 suchlike.
+
+if BLOCK
+
 #XXX - it makes sense to enable this only for 32-bit subarch's, not for x86_64
 #for instance.
 config LBD
@@ -33,4 +51,6 @@ config LSF
 
 	  If unsure, say Y.
 
+endif
+
 source block/Kconfig.iosched
diff --git a/block/Kconfig.iosched b/block/Kconfig.iosched
index 48d090e..903f0d3 100644
--- a/block/Kconfig.iosched
+++ b/block/Kconfig.iosched
@@ -1,3 +1,4 @@
+if BLOCK
 
 menu "IO Schedulers"
 
@@ -67,3 +68,5 @@ config DEFAULT_IOSCHED
 	default "noop" if DEFAULT_NOOP
 
 endmenu
+
+endif
diff --git a/block/Makefile b/block/Makefile
index bedb3b2..901aed3 100644
--- a/block/Makefile
+++ b/block/Makefile
@@ -2,8 +2,9 @@ #
 # Makefile for the kernel block layer
 #
 
-obj-y	:= elevator.o genhd.o bio-core.o bio-queuesetup.o bio-sysfs.o \
-	   bio-tag.o bio-barrier.o bio-helpers.o ioctl.o scsi_ioctl.o
+obj-$(CONFIG_BLOCK) := \
+	elevator.o genhd.o bio-core.o bio-queuesetup.o bio-sysfs.o \
+	bio-tag.o bio-barrier.o bio-helpers.o ioctl.o scsi_ioctl.o
 
 obj-$(CONFIG_IOSCHED_NOOP)	+= noop-iosched.o
 obj-$(CONFIG_IOSCHED_AS)	+= as-iosched.o
diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig
index b5382ce..422e31d 100644
--- a/drivers/block/Kconfig
+++ b/drivers/block/Kconfig
@@ -2,6 +2,8 @@ #
 # Block device driver configuration
 #
 
+if BLOCK
+
 menu "Block devices"
 
 config BLK_DEV_FD
@@ -468,3 +470,5 @@ config ATA_OVER_ETH
 	devices like the Coraid EtherDrive (R) Storage Blade.
 
 endmenu
+
+endif
diff --git a/drivers/cdrom/Kconfig b/drivers/cdrom/Kconfig
index ff5652d..4b12e90 100644
--- a/drivers/cdrom/Kconfig
+++ b/drivers/cdrom/Kconfig
@@ -3,7 +3,7 @@ # CDROM driver configuration
 #
 
 menu "Old CD-ROM drivers (not SCSI, not IDE)"
-	depends on ISA
+	depends on ISA && BLOCK
 
 config CD_NO_IDESCSI
 	bool "Support non-SCSI/IDE/ATAPI CDROM drives"
diff --git a/drivers/char/Kconfig b/drivers/char/Kconfig
index c40e487..b9c6777 100644
--- a/drivers/char/Kconfig
+++ b/drivers/char/Kconfig
@@ -984,6 +984,7 @@ config GPIO_VR41XX
 
 config RAW_DRIVER
 	tristate "RAW driver (/dev/raw/rawN) (OBSOLETE)"
+	depends on BLOCK
 	help
 	  The raw driver permits block devices to be bound to /dev/raw/rawN. 
 	  Once bound, I/O against /dev/raw/rawN uses efficient zero-copy I/O. 
diff --git a/drivers/char/random.c b/drivers/char/random.c
index 4c3a5ca..b430a12 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -655,6 +655,7 @@ void add_interrupt_randomness(int irq)
 	add_timer_randomness(irq_timer_state[irq], 0x100 + irq);
 }
 
+#ifdef CONFIG_BLOCK
 void add_disk_randomness(struct gendisk *disk)
 {
 	if (!disk || !disk->random)
@@ -667,6 +668,7 @@ void add_disk_randomness(struct gendisk 
 }
 
 EXPORT_SYMBOL(add_disk_randomness);
+#endif
 
 #define EXTRACT_SIZE 10
 
@@ -918,6 +920,7 @@ void rand_initialize_irq(int irq)
 	}
 }
 
+#ifdef CONFIG_BLOCK
 void rand_initialize_disk(struct gendisk *disk)
 {
 	struct timer_rand_state *state;
@@ -932,6 +935,7 @@ void rand_initialize_disk(struct gendisk
 		disk->random = state;
 	}
 }
+#endif
 
 static ssize_t
 random_read(struct file * file, char __user * buf, size_t nbytes, loff_t *ppos)
diff --git a/drivers/ide/Kconfig b/drivers/ide/Kconfig
index b6fb167..69d627b 100644
--- a/drivers/ide/Kconfig
+++ b/drivers/ide/Kconfig
@@ -4,6 +4,8 @@ #
 # Andre Hedrick <andre@linux-ide.org>
 #
 
+if BLOCK
+
 menu "ATA/ATAPI/MFM/RLL support"
 
 config IDE
@@ -1082,3 +1084,5 @@ config BLK_DEV_HD
 endif
 
 endmenu
+
+endif
diff --git a/drivers/ieee1394/Kconfig b/drivers/ieee1394/Kconfig
index 1867375..c9d84b9 100644
--- a/drivers/ieee1394/Kconfig
+++ b/drivers/ieee1394/Kconfig
@@ -122,7 +122,7 @@ config IEEE1394_VIDEO1394
 
 config IEEE1394_SBP2
 	tristate "SBP-2 support (Harddisks etc.)"
-	depends on IEEE1394 && SCSI && (PCI || BROKEN)
+	depends on IEEE1394 && BLOCK && SCSI && (PCI || BROKEN)
 	help
 	  This option enables you to use SBP-2 devices connected to your IEEE
 	  1394 bus.  SBP-2 devices include harddrives and DVD devices.
diff --git a/drivers/infiniband/ulp/iser/Kconfig b/drivers/infiniband/ulp/iser/Kconfig
index fead87d..f945953 100644
--- a/drivers/infiniband/ulp/iser/Kconfig
+++ b/drivers/infiniband/ulp/iser/Kconfig
@@ -1,6 +1,6 @@
 config INFINIBAND_ISER
 	tristate "ISCSI RDMA Protocol"
-	depends on INFINIBAND && SCSI
+	depends on INFINIBAND && BLOCK && SCSI
 	select SCSI_ISCSI_ATTRS
 	---help---
 	  Support for the ISCSI RDMA Protocol over InfiniBand.  This
diff --git a/drivers/infiniband/ulp/srp/Kconfig b/drivers/infiniband/ulp/srp/Kconfig
index 8fe3be4..63d7d5a 100644
--- a/drivers/infiniband/ulp/srp/Kconfig
+++ b/drivers/infiniband/ulp/srp/Kconfig
@@ -1,6 +1,6 @@
 config INFINIBAND_SRP
 	tristate "InfiniBand SCSI RDMA Protocol"
-	depends on INFINIBAND && SCSI
+	depends on INFINIBAND && BLOCK && SCSI
 	---help---
 	  Support for the SCSI RDMA Protocol over InfiniBand.  This
 	  allows you to access storage devices that speak SRP over
diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig
index bf869ed..1e91f90 100644
--- a/drivers/md/Kconfig
+++ b/drivers/md/Kconfig
@@ -2,6 +2,8 @@ #
 # Block device driver configuration
 #
 
+if CONFIG_BLOCK
+
 menu "Multi-device support (RAID and LVM)"
 
 config MD
@@ -251,3 +253,4 @@ config DM_MULTIPATH_EMC
 
 endmenu
 
+endif
diff --git a/drivers/message/i2o/Kconfig b/drivers/message/i2o/Kconfig
index fef6771..6443392 100644
--- a/drivers/message/i2o/Kconfig
+++ b/drivers/message/i2o/Kconfig
@@ -88,7 +88,7 @@ config I2O_BUS
 
 config I2O_BLOCK
 	tristate "I2O Block OSM"
-	depends on I2O
+	depends on I2O && BLOCK
 	---help---
 	  Include support for the I2O Block OSM. The Block OSM presents disk
 	  and other structured block devices to the operating system. If you
diff --git a/drivers/mmc/Kconfig b/drivers/mmc/Kconfig
index 45bcf09..f540bd8 100644
--- a/drivers/mmc/Kconfig
+++ b/drivers/mmc/Kconfig
@@ -21,7 +21,7 @@ config MMC_DEBUG
 
 config MMC_BLOCK
 	tristate "MMC block device driver"
-	depends on MMC
+	depends on MMC && BLOCK
 	default y
 	help
 	  Say Y here to enable the MMC block device driver support.
diff --git a/drivers/mmc/Makefile b/drivers/mmc/Makefile
index d2957e3..b1f6e03 100644
--- a/drivers/mmc/Makefile
+++ b/drivers/mmc/Makefile
@@ -24,7 +24,8 @@ obj-$(CONFIG_MMC_AU1X)		+= au1xmmc.o
 obj-$(CONFIG_MMC_OMAP)		+= omap.o
 obj-$(CONFIG_MMC_AT91RM9200)	+= at91_mci.o
 
-mmc_core-y := mmc.o mmc_queue.o mmc_sysfs.o
+mmc_core-y := mmc.o mmc_sysfs.o
+mmc_core-$(CONFIG_BLOCK) += mmc_queue.o
 
 ifeq ($(CONFIG_MMC_DEBUG),y)
 EXTRA_CFLAGS += -DDEBUG
diff --git a/drivers/mtd/Kconfig b/drivers/mtd/Kconfig
index 1344ad7..188cd37 100644
--- a/drivers/mtd/Kconfig
+++ b/drivers/mtd/Kconfig
@@ -166,7 +166,7 @@ config MTD_CHAR
 
 config MTD_BLOCK
 	tristate "Caching block device access to MTD devices"
-	depends on MTD
+	depends on MTD && BLOCK
 	---help---
 	  Although most flash chips have an erase size too large to be useful
 	  as block devices, it is possible to use MTD devices which are based
@@ -188,7 +188,7 @@ config MTD_BLOCK
 
 config MTD_BLOCK_RO
 	tristate "Readonly block device access to MTD devices"
-	depends on MTD_BLOCK!=y && MTD
+	depends on MTD_BLOCK!=y && MTD && BLOCK
 	help
 	  This allows you to mount read-only file systems (such as cramfs)
 	  from an MTD device, without the overhead (and danger) of the caching
@@ -199,7 +199,7 @@ config MTD_BLOCK_RO
 
 config FTL
 	tristate "FTL (Flash Translation Layer) support"
-	depends on MTD
+	depends on MTD && BLOCK
 	---help---
 	  This provides support for the original Flash Translation Layer which
 	  is part of the PCMCIA specification. It uses a kind of pseudo-
@@ -215,7 +215,7 @@ config FTL
 
 config NFTL
 	tristate "NFTL (NAND Flash Translation Layer) support"
-	depends on MTD
+	depends on MTD && BLOCK
 	---help---
 	  This provides support for the NAND Flash Translation Layer which is
 	  used on M-Systems' DiskOnChip devices. It uses a kind of pseudo-
@@ -238,7 +238,7 @@ config NFTL_RW
 
 config INFTL
 	tristate "INFTL (Inverse NAND Flash Translation Layer) support"
-	depends on MTD
+	depends on MTD && BLOCK
 	---help---
 	  This provides support for the Inverse NAND Flash Translation
 	  Layer which is used on M-Systems' newer DiskOnChip devices. It
@@ -255,7 +255,7 @@ config INFTL
 
 config RFD_FTL
         tristate "Resident Flash Disk (Flash Translation Layer) support"
-	depends on MTD
+	depends on MTD && BLOCK
 	---help---
 	  This provides support for the flash translation layer known
 	  as the Resident Flash Disk (RFD), as used by the Embedded BIOS
diff --git a/drivers/mtd/devices/Kconfig b/drivers/mtd/devices/Kconfig
index 16c02b5..440f685 100644
--- a/drivers/mtd/devices/Kconfig
+++ b/drivers/mtd/devices/Kconfig
@@ -136,7 +136,7 @@ config MTDRAM_ABS_POS
 
 config MTD_BLOCK2MTD
 	tristate "MTD using block device"
-	depends on MTD
+	depends on MTD && BLOCK
 	help
 	  This driver allows a block device to appear as an MTD. It would
 	  generally be used in the following cases:
diff --git a/drivers/s390/block/Kconfig b/drivers/s390/block/Kconfig
index 929d6ff..b250c53 100644
--- a/drivers/s390/block/Kconfig
+++ b/drivers/s390/block/Kconfig
@@ -1,4 +1,4 @@
-if S390
+if S390 && BLOCK
 
 comment "S/390 block device drivers"
 	depends on S390
diff --git a/drivers/scsi/Kconfig b/drivers/scsi/Kconfig
index 96a81cd..afcbe19 100644
--- a/drivers/scsi/Kconfig
+++ b/drivers/scsi/Kconfig
@@ -3,11 +3,13 @@ menu "SCSI device support"
 config RAID_ATTRS
 	tristate "RAID Transport Class"
 	default n
+	depends on BLOCK
 	---help---
 	  Provides RAID
 
 config SCSI
 	tristate "SCSI device support"
+	depends on BLOCK
 	---help---
 	  If you want to use a SCSI hard disk, SCSI tape drive, SCSI CD-ROM or
 	  any other SCSI device under Linux, say Y and make sure that you know
@@ -43,7 +45,7 @@ comment "SCSI support type (disk, tape, 
 
 config BLK_DEV_SD
 	tristate "SCSI disk support"
-	depends on SCSI
+	depends on SCSI && BLOCK
 	---help---
 	  If you want to use SCSI hard disks, Fibre Channel disks,
 	  USB storage or the SCSI or parallel port version of
@@ -98,7 +100,7 @@ config CHR_DEV_OSST
 
 config BLK_DEV_SR
 	tristate "SCSI CDROM support"
-	depends on SCSI
+	depends on SCSI && BLOCK
 	---help---
 	  If you want to use a SCSI or FireWire CD-ROM under Linux,
 	  say Y and read the SCSI-HOWTO and the CDROM-HOWTO at
@@ -473,7 +475,7 @@ source "drivers/scsi/megaraid/Kconfig.me
 
 config SCSI_SATA
 	tristate "Serial ATA (SATA) support"
-	depends on SCSI
+	depends on SCSI && BLOCK
 	help
 	  This driver family supports Serial ATA host controllers
 	  and devices.
diff --git a/drivers/usb/storage/Kconfig b/drivers/usb/storage/Kconfig
index be9eec2..578aa13 100644
--- a/drivers/usb/storage/Kconfig
+++ b/drivers/usb/storage/Kconfig
@@ -8,7 +8,7 @@ comment "may also be needed; see USB_STO
 
 config USB_STORAGE
 	tristate "USB Mass Storage support"
-	depends on USB
+	depends on USB && BLOCK
 	select SCSI
 	---help---
 	  Say Y here if you want to connect USB mass storage devices to your
diff --git a/fs/Kconfig b/fs/Kconfig
index 3f00a9f..dc5e69b 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -4,6 +4,8 @@ #
 
 menu "File systems"
 
+if BLOCK
+
 config EXT2_FS
 	tristate "Second extended fs support"
 	help
@@ -383,8 +385,11 @@ config MINIX_FS
 	  partition (the one containing the directory /) cannot be compiled as
 	  a module.
 
+endif
+
 config ROMFS_FS
 	tristate "ROM file system support"
+	depends on BLOCK
 	---help---
 	  This is a very small read-only file system mainly intended for
 	  initial ram disks of installation disks, but it could be used for
@@ -530,6 +535,7 @@ config FUSE_FS
 	  If you want to develop a userspace FS, or if you want to use
 	  a filesystem based on FUSE, answer Y or M.
 
+if BLOCK
 menu "CD-ROM/DVD Filesystems"
 
 config ISO9660_FS
@@ -597,7 +603,9 @@ config UDF_NLS
 	depends on (UDF_FS=m && NLS) || (UDF_FS=y && NLS=y)
 
 endmenu
+endif
 
+if BLOCK
 menu "DOS/FAT/NT Filesystems"
 
 config FAT_FS
@@ -782,6 +790,7 @@ config NTFS_RW
 	  It is perfectly safe to say N here.
 
 endmenu
+endif
 
 menu "Pseudo filesystems"
 
@@ -907,7 +916,7 @@ menu "Miscellaneous filesystems"
 
 config ADFS_FS
 	tristate "ADFS file system support (EXPERIMENTAL)"
-	depends on EXPERIMENTAL
+	depends on BLOCK && EXPERIMENTAL
 	help
 	  The Acorn Disc Filing System is the standard file system of the
 	  RiscOS operating system which runs on Acorn's ARM-based Risc PC
@@ -935,7 +944,7 @@ config ADFS_FS_RW
 
 config AFFS_FS
 	tristate "Amiga FFS file system support (EXPERIMENTAL)"
-	depends on EXPERIMENTAL
+	depends on BLOCK && EXPERIMENTAL
 	help
 	  The Fast File System (FFS) is the common file system used on hard
 	  disks by Amiga(tm) systems since AmigaOS Version 1.3 (34.20).  Say Y
@@ -957,7 +966,7 @@ config AFFS_FS
 
 config HFS_FS
 	tristate "Apple Macintosh file system support (EXPERIMENTAL)"
-	depends on EXPERIMENTAL
+	depends on BLOCK && EXPERIMENTAL
 	select NLS
 	help
 	  If you say Y here, you will be able to mount Macintosh-formatted
@@ -970,6 +979,7 @@ config HFS_FS
 
 config HFSPLUS_FS
 	tristate "Apple Extended HFS file system support"
+	depends on BLOCK
 	select NLS
 	select NLS_UTF8
 	help
@@ -983,7 +993,7 @@ config HFSPLUS_FS
 
 config BEFS_FS
 	tristate "BeOS file system (BeFS) support (read only) (EXPERIMENTAL)"
-	depends on EXPERIMENTAL
+	depends on BLOCK && EXPERIMENTAL
 	select NLS
 	help
 	  The BeOS File System (BeFS) is the native file system of Be, Inc's
@@ -1010,7 +1020,7 @@ config BEFS_DEBUG
 
 config BFS_FS
 	tristate "BFS file system support (EXPERIMENTAL)"
-	depends on EXPERIMENTAL
+	depends on BLOCK && EXPERIMENTAL
 	help
 	  Boot File System (BFS) is a file system used under SCO UnixWare to
 	  allow the bootloader access to the kernel image and other important
@@ -1032,7 +1042,7 @@ config BFS_FS
 
 config EFS_FS
 	tristate "EFS file system support (read only) (EXPERIMENTAL)"
-	depends on EXPERIMENTAL
+	depends on BLOCK && EXPERIMENTAL
 	help
 	  EFS is an older file system used for non-ISO9660 CD-ROMs and hard
 	  disk partitions by SGI's IRIX operating system (IRIX 6.0 and newer
@@ -1047,7 +1057,7 @@ config EFS_FS
 
 config JFFS_FS
 	tristate "Journalling Flash File System (JFFS) support"
-	depends on MTD
+	depends on MTD && BLOCK
 	help
 	  JFFS is the Journaling Flash File System developed by Axis
 	  Communications in Sweden, aimed at providing a crash/powerdown-safe
@@ -1232,6 +1242,7 @@ endchoice
 
 config CRAMFS
 	tristate "Compressed ROM file system support (cramfs)"
+	depends on BLOCK
 	select ZLIB_INFLATE
 	help
 	  Saying Y here includes support for CramFs (Compressed ROM File
@@ -1251,6 +1262,7 @@ config CRAMFS
 
 config VXFS_FS
 	tristate "FreeVxFS file system support (VERITAS VxFS(TM) compatible)"
+	depends on BLOCK
 	help
 	  FreeVxFS is a file system driver that support the VERITAS VxFS(TM)
 	  file system format.  VERITAS VxFS(TM) is the standard file system
@@ -1268,6 +1280,7 @@ config VXFS_FS
 
 config HPFS_FS
 	tristate "OS/2 HPFS file system support"
+	depends on BLOCK
 	help
 	  OS/2 is IBM's operating system for PC's, the same as Warp, and HPFS
 	  is the file system used for organizing files on OS/2 hard disk
@@ -1284,6 +1297,7 @@ config HPFS_FS
 
 config QNX4FS_FS
 	tristate "QNX4 file system support (read only)"
+	depends on BLOCK
 	help
 	  This is the file system used by the real-time operating systems
 	  QNX 4 and QNX 6 (the latter is also called QNX RTP).
@@ -1311,6 +1325,7 @@ config QNX4FS_RW
 
 config SYSV_FS
 	tristate "System V/Xenix/V7/Coherent file system support"
+	depends on BLOCK
 	help
 	  SCO, Xenix and Coherent are commercial Unix systems for Intel
 	  machines, and Version 7 was used on the DEC PDP-11. Saying Y
@@ -1349,6 +1364,7 @@ config SYSV_FS
 
 config UFS_FS
 	tristate "UFS file system support (read only)"
+	depends on BLOCK
 	help
 	  BSD and derivate versions of Unix (such as SunOS, FreeBSD, NetBSD,
 	  OpenBSD and NeXTstep) use a file system called UFS. Some System V
@@ -1923,11 +1939,13 @@ config 9P_FS
 
 endmenu
 
+if BLOCK
 menu "Partition Types"
 
 source "fs/partitions/Kconfig"
 
 endmenu
+endif
 
 source "fs/nls/Kconfig"
 
diff --git a/fs/Makefile b/fs/Makefile
index 8913542..8071c64 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -5,12 +5,18 @@ # 14 Sep 2000, Christoph Hellwig <hch@in
 # Rewritten to use lists instead of if-statements.
 # 
 
-obj-y :=	open.o read_write.o file_table.o buffer.o  bio.o super.o \
-		block_dev.o char_dev.o stat.o exec.o pipe.o namei.o fcntl.o \
+obj-y :=	open.o read_write.o file_table.o super.o \
+		char_dev.o stat.o exec.o pipe.o namei.o fcntl.o \
 		ioctl.o readdir.o select.o fifo.o locks.o dcache.o inode.o \
 		attr.o bad_inode.o file.o filesystems.o namespace.o aio.o \
-		seq_file.o xattr.o libfs.o fs-writeback.o mpage.o direct-io.o \
-		ioprio.o pnode.o drop_caches.o splice.o sync.o
+		seq_file.o xattr.o libfs.o fs-writeback.o \
+		pnode.o drop_caches.o splice.o sync.o
+
+ifeq ($(CONFIG_BLOCK),y)
+obj-y +=	buffer.o bio.o block_dev.o direct-io.o mpage.o ioprio.o
+else
+obj-y +=	no-block.o
+endif
 
 obj-$(CONFIG_INOTIFY)		+= inotify.o
 obj-$(CONFIG_INOTIFY_USER)	+= inotify_user.o
diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c
index e1a5643..64b3453 100644
--- a/fs/compat_ioctl.c
+++ b/fs/compat_ioctl.c
@@ -645,6 +645,7 @@ out:
 }
 #endif
 
+#ifdef CONFIG_BLOCK
 struct hd_geometry32 {
 	unsigned char heads;
 	unsigned char sectors;
@@ -869,6 +870,7 @@ static int sg_grt_trans(unsigned int fd,
 	}
 	return err;
 }
+#endif /* CONFIG_BLOCK */
 
 struct sock_fprog32 {
 	unsigned short	len;
@@ -992,6 +994,7 @@ static int ppp_ioctl_trans(unsigned int 
 }
 
 
+#ifdef CONFIG_BLOCK
 struct mtget32 {
 	compat_long_t	mt_type;
 	compat_long_t	mt_resid;
@@ -1164,6 +1167,7 @@ static int cdrom_ioctl_trans(unsigned in
 
 	return err;
 }
+#endif /* CONFIG_BLOCK */
 
 #ifdef CONFIG_VT
 
@@ -1491,6 +1495,7 @@ ret_einval(unsigned int fd, unsigned int
 	return -EINVAL;
 }
 
+#ifdef CONFIG_BLOCK
 static int broken_blkgetsize(unsigned int fd, unsigned int cmd, unsigned long arg)
 {
 	/* The mkswap binary hard codes it to Intel value :-((( */
@@ -1525,12 +1530,14 @@ static int blkpg_ioctl_trans(unsigned in
 
 	return sys_ioctl(fd, cmd, (unsigned long)a);
 }
+#endif
 
 static int ioc_settimeout(unsigned int fd, unsigned int cmd, unsigned long arg)
 {
 	return rw_long(fd, AUTOFS_IOC_SETTIMEOUT, arg);
 }
 
+#ifdef CONFIG_BLOCK
 /* Fix sizeof(sizeof()) breakage */
 #define BLKBSZGET_32   _IOR(0x12,112,int)
 #define BLKBSZSET_32   _IOW(0x12,113,int)
@@ -1551,6 +1558,7 @@ static int do_blkgetsize64(unsigned int 
 {
        return sys_ioctl(fd, BLKGETSIZE64, (unsigned long)compat_ptr(arg));
 }
+#endif
 
 /* Bluetooth ioctls */
 #define HCIUARTSETPROTO	_IOW('U', 200, int)
@@ -1571,6 +1579,7 @@ #define HIDPCONNDEL	_IOW('H', 201, int)
 #define HIDPGETCONNLIST	_IOR('H', 210, int)
 #define HIDPGETCONNINFO	_IOR('H', 211, int)
 
+#ifdef CONFIG_BLOCK
 struct floppy_struct32 {
 	compat_uint_t	size;
 	compat_uint_t	sect;
@@ -1895,6 +1904,7 @@ out:
 	kfree(karg);
 	return err;
 }
+#endif
 
 struct mtd_oob_buf32 {
 	u_int32_t start;
@@ -1936,6 +1946,7 @@ static int mtd_rw_oob(unsigned int fd, u
 	return err;
 }	
 
+#ifdef CONFIG_BLOCK
 struct raw32_config_request
 {
         compat_int_t    raw_minor;
@@ -2000,6 +2011,7 @@ static int raw_ioctl(unsigned fd, unsign
         }
         return ret;
 }
+#endif /* CONFIG_BLOCK */
 
 struct serial_struct32 {
         compat_int_t    type;
@@ -2606,6 +2618,7 @@ HANDLE_IOCTL(SIOCBRDELIF, dev_ifsioc)
 HANDLE_IOCTL(SIOCRTMSG, ret_einval)
 HANDLE_IOCTL(SIOCGSTAMP, do_siocgstamp)
 #endif
+#ifdef CONFIG_BLOCK
 HANDLE_IOCTL(HDIO_GETGEO, hdio_getgeo)
 HANDLE_IOCTL(BLKRAGET, w_long)
 HANDLE_IOCTL(BLKGETSIZE, w_long)
@@ -2631,14 +2644,17 @@ HANDLE_IOCTL(FDGETFDCSTAT32, fd_ioctl_tr
 HANDLE_IOCTL(FDWERRORGET32, fd_ioctl_trans)
 HANDLE_IOCTL(SG_IO,sg_ioctl_trans)
 HANDLE_IOCTL(SG_GET_REQUEST_TABLE, sg_grt_trans)
+#endif
 HANDLE_IOCTL(PPPIOCGIDLE32, ppp_ioctl_trans)
 HANDLE_IOCTL(PPPIOCSCOMPRESS32, ppp_ioctl_trans)
 HANDLE_IOCTL(PPPIOCSPASS32, ppp_sock_fprog_ioctl_trans)
 HANDLE_IOCTL(PPPIOCSACTIVE32, ppp_sock_fprog_ioctl_trans)
+#ifdef CONFIG_BLOCK
 HANDLE_IOCTL(MTIOCGET32, mt_ioctl_trans)
 HANDLE_IOCTL(MTIOCPOS32, mt_ioctl_trans)
 HANDLE_IOCTL(CDROMREADAUDIO, cdrom_ioctl_trans)
 HANDLE_IOCTL(CDROM_SEND_PACKET, cdrom_ioctl_trans)
+#endif
 #define AUTOFS_IOC_SETTIMEOUT32 _IOWR(0x93,0x64,unsigned int)
 HANDLE_IOCTL(AUTOFS_IOC_SETTIMEOUT32, ioc_settimeout)
 #ifdef CONFIG_VT
@@ -2677,12 +2693,14 @@ HANDLE_IOCTL(SONET_SETFRAMING, do_atm_io
 HANDLE_IOCTL(SONET_GETFRAMING, do_atm_ioctl)
 HANDLE_IOCTL(SONET_GETFRSENSE, do_atm_ioctl)
 /* block stuff */
+#ifdef CONFIG_BLOCK
 HANDLE_IOCTL(BLKBSZGET_32, do_blkbszget)
 HANDLE_IOCTL(BLKBSZSET_32, do_blkbszset)
 HANDLE_IOCTL(BLKGETSIZE64_32, do_blkgetsize64)
 /* Raw devices */
 HANDLE_IOCTL(RAW_SETBIND, raw_ioctl)
 HANDLE_IOCTL(RAW_GETBIND, raw_ioctl)
+#endif
 /* Serial */
 HANDLE_IOCTL(TIOCGSERIAL, serial_struct_ioctl)
 HANDLE_IOCTL(TIOCSSERIAL, serial_struct_ioctl)
diff --git a/fs/internal.h b/fs/internal.h
index f662b70..f07147d 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -14,10 +14,16 @@ #include <linux/ioctl32.h>
 /*
  * block_dev.c
  */
+#ifdef CONFIG_BLOCK
 extern struct super_block *blockdev_superblock;
 extern void __init bdev_cache_init(void);
 
 #define sb_is_blkdev_sb(sb) ((sb) == blockdev_superblock)
+#else
+static inline void bdev_cache_init(void) {}
+
+#define sb_is_blkdev_sb(sb) 0
+#endif
 
 /*
  * char_dev.c
diff --git a/fs/no-block.c b/fs/no-block.c
new file mode 100644
index 0000000..d269a93
--- /dev/null
+++ b/fs/no-block.c
@@ -0,0 +1,22 @@
+/* no-block.c: implementation of routines required for non-BLOCK configuration
+ *
+ * Copyright (C) 2006 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/fs.h>
+
+static int no_blkdev_open(struct inode * inode, struct file * filp)
+{
+	return -ENODEV;
+}
+
+const struct file_operations def_blk_fops = {
+	.open		= no_blkdev_open,
+};
diff --git a/fs/partitions/Makefile b/fs/partitions/Makefile
index d713ce6..67e665f 100644
--- a/fs/partitions/Makefile
+++ b/fs/partitions/Makefile
@@ -2,7 +2,7 @@ #
 # Makefile for the linux kernel.
 #
 
-obj-y := check.o
+obj-$(CONFIG_BLOCK) := check.o
 
 obj-$(CONFIG_ACORN_PARTITION) += acorn.o
 obj-$(CONFIG_AMIGA_PARTITION) += amiga.o
diff --git a/fs/proc/proc_misc.c b/fs/proc/proc_misc.c
index 9f2cfc3..ed8646e 100644
--- a/fs/proc/proc_misc.c
+++ b/fs/proc/proc_misc.c
@@ -268,12 +268,15 @@ static int devinfo_show(struct seq_file 
 		if (i == 0)
 			seq_printf(f, "Character devices:\n");
 		chrdev_show(f, i);
-	} else {
+	}
+#ifdef CONFIG_BLOCK
+	else {
 		i -= CHRDEV_MAJOR_HASH_SIZE;
 		if (i == 0)
 			seq_printf(f, "\nBlock devices:\n");
 		blkdev_show(f, i);
 	}
+#endif
 	return 0;
 }
 
@@ -346,6 +349,7 @@ static int stram_read_proc(char *page, c
 }
 #endif
 
+#ifdef CONFIG_BLOCK
 extern struct seq_operations partitions_op;
 static int partitions_open(struct inode *inode, struct file *file)
 {
@@ -369,6 +373,7 @@ static struct file_operations proc_disks
 	.llseek		= seq_lseek,
 	.release	= seq_release,
 };
+#endif
 
 #ifdef CONFIG_MODULES
 extern struct seq_operations modules_op;
@@ -686,7 +691,9 @@ #endif
 		entry->proc_fops = &proc_kmsg_operations;
 	create_seq_entry("devices", 0, &proc_devinfo_operations);
 	create_seq_entry("cpuinfo", 0, &proc_cpuinfo_operations);
+#ifdef CONFIG_BLOCK
 	create_seq_entry("partitions", 0, &proc_partitions_operations);
+#endif
 	create_seq_entry("stat", 0, &proc_stat_operations);
 	create_seq_entry("interrupts", 0, &proc_interrupts_operations);
 #ifdef CONFIG_SLAB
@@ -698,7 +705,9 @@ #endif
 	create_seq_entry("buddyinfo",S_IRUGO, &fragmentation_file_operations);
 	create_seq_entry("vmstat",S_IRUGO, &proc_vmstat_file_operations);
 	create_seq_entry("zoneinfo",S_IRUGO, &proc_zoneinfo_file_operations);
+#ifdef CONFIG_BLOCK
 	create_seq_entry("diskstats", 0, &proc_diskstats_operations);
+#endif
 #ifdef CONFIG_MODULES
 	create_seq_entry("modules", 0, &proc_modules_operations);
 #endif
diff --git a/fs/quota.c b/fs/quota.c
index d6a2be8..b9dae76 100644
--- a/fs/quota.c
+++ b/fs/quota.c
@@ -338,6 +338,34 @@ static int do_quotactl(struct super_bloc
 }
 
 /*
+ * look up a superblock on which quota ops will be performed
+ * - use the name of a block device to find the superblock thereon
+ */
+static inline struct super_block *quotactl_block(const char __user *special)
+{
+#ifdef CONFIG_BLOCK
+	struct block_device *bdev;
+	struct super_block *sb;
+	char *tmp = getname(special);
+
+	if (IS_ERR(tmp))
+		return ERR_PTR(PTR_ERR(tmp));
+	bdev = lookup_bdev(tmp);
+	putname(tmp);
+	if (IS_ERR(bdev))
+		return ERR_PTR(PTR_ERR(bdev));
+	sb = get_super(bdev);
+	bdput(bdev);
+	if (!sb)
+		return ERR_PTR(-ENODEV);
+
+	return sb;
+#else
+	return ERR_PTR(-ENODEV);
+#endif
+}
+
+/*
  * This is the system call interface. This communicates with
  * the user-level programs. Currently this only supports diskquota
  * calls. Maybe we need to add the process quotas etc. in the future,
@@ -347,25 +375,15 @@ asmlinkage long sys_quotactl(unsigned in
 {
 	uint cmds, type;
 	struct super_block *sb = NULL;
-	struct block_device *bdev;
-	char *tmp;
 	int ret;
 
 	cmds = cmd >> SUBCMDSHIFT;
 	type = cmd & SUBCMDMASK;
 
 	if (cmds != Q_SYNC || special) {
-		tmp = getname(special);
-		if (IS_ERR(tmp))
-			return PTR_ERR(tmp);
-		bdev = lookup_bdev(tmp);
-		putname(tmp);
-		if (IS_ERR(bdev))
-			return PTR_ERR(bdev);
-		sb = get_super(bdev);
-		bdput(bdev);
-		if (!sb)
-			return -ENODEV;
+		sb = quotactl_block(special);
+		if (IS_ERR(sb))
+			return PTR_ERR(sb);
 	}
 
 	ret = check_quotactl_valid(sb, type, cmds, id);
diff --git a/fs/super.c b/fs/super.c
index 22c2fd1..33ce475 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -570,8 +570,10 @@ int do_remount_sb(struct super_block *sb
 {
 	int retval;
 	
+#ifdef CONFIG_BLOCK
 	if (!(flags & MS_RDONLY) && bdev_read_only(sb->s_bdev))
 		return -EACCES;
+#endif
 	if (flags & MS_RDONLY)
 		acct_auto_close(sb);
 	shrink_dcache_sb(sb);
@@ -691,6 +693,7 @@ void kill_litter_super(struct super_bloc
 
 EXPORT_SYMBOL(kill_litter_super);
 
+#ifdef CONFIG_BLOCK
 static int set_bdev_super(struct super_block *s, void *data)
 {
 	s->s_bdev = data;
@@ -786,6 +789,7 @@ void kill_block_super(struct super_block
 }
 
 EXPORT_SYMBOL(kill_block_super);
+#endif
 
 int get_sb_nodev(struct file_system_type *fs_type,
 	int flags, void *data,
diff --git a/fs/xfs/Kconfig b/fs/xfs/Kconfig
index 26b364c..35115bc 100644
--- a/fs/xfs/Kconfig
+++ b/fs/xfs/Kconfig
@@ -1,5 +1,6 @@
 config XFS_FS
 	tristate "XFS filesystem support"
+	depends on BLOCK
 	help
 	  XFS is a high performance journaling filesystem which originated
 	  on the SGI IRIX platform.  It is completely multi-threaded, can
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index c0c60d3..32e2c7c 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -16,6 +16,22 @@ #include <linux/stringify.h>
 
 #include <asm/scatterlist.h>
 
+#ifdef CONFIG_LBD
+# include <asm/div64.h>
+# define sector_div(a, b) do_div(a, b)
+#else
+# define sector_div(n, b)( \
+{ \
+	int _res; \
+	_res = (n) % (b); \
+	(n) /= (b); \
+	_res; \
+} \
+)
+#endif
+
+#ifdef CONFIG_BLOCK
+
 struct scsi_ioctl_command;
 
 struct request_queue;
@@ -815,24 +831,30 @@ struct work_struct;
 int kblockd_schedule_work(struct work_struct *work);
 void kblockd_flush(void);
 
-#ifdef CONFIG_LBD
-# include <asm/div64.h>
-# define sector_div(a, b) do_div(a, b)
-#else
-# define sector_div(n, b)( \
-{ \
-	int _res; \
-	_res = (n) % (b); \
-	(n) /= (b); \
-	_res; \
-} \
-)
-#endif 
-
 #define MODULE_ALIAS_BLOCKDEV(major,minor) \
 	MODULE_ALIAS("block-major-" __stringify(major) "-" __stringify(minor))
 #define MODULE_ALIAS_BLOCKDEV_MAJOR(major) \
 	MODULE_ALIAS("block-major-" __stringify(major) "-*")
 
 
+#else /* CONFIG_BLOCK */
+/*
+ * stubs for when the block layer is configured out
+ */
+#define buffer_heads_over_limit 0
+
+static inline long blk_congestion_wait(int rw, long timeout)
+{
+	return timeout;
+}
+
+static inline long nr_blockdev_pages(void)
+{
+	return 0;
+}
+
+static inline void exit_io_context(void) {}
+
+#endif /* CONFIG_BLOCK */
+
 #endif
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index 64b508e..131ffd3 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -14,6 +14,8 @@ #include <linux/pagemap.h>
 #include <linux/wait.h>
 #include <asm/atomic.h>
 
+#ifdef CONFIG_BLOCK
+
 enum bh_state_bits {
 	BH_Uptodate,	/* Contains valid data */
 	BH_Dirty,	/* Is dirty */
@@ -301,4 +303,18 @@ static inline void lock_buffer(struct bu
 }
 
 extern int __set_page_dirty_buffers(struct page *page);
+
+#else /* CONFIG_BLOCK */
+
+static inline void buffer_init(void) {}
+static inline int try_to_free_buffers(struct page *page) { return 1; }
+static inline int sync_blockdev(struct block_device *bdev) { return 0; }
+static inline int inode_has_buffers(struct inode *inode) { return 0; }
+static inline void invalidate_inode_buffers(struct inode *inode) {}
+static inline int remove_inode_buffers(struct inode *inode) { return 1; }
+static inline int sync_mapping_buffers(struct address_space *mapping) { return 0; }
+static inline void invalidate_bdev(struct block_device *bdev, int destroy_dirty_buffers) {}
+
+
+#endif /* CONFIG_BLOCK */
 #endif /* _LINUX_BUFFER_HEAD_H */
diff --git a/include/linux/compat_ioctl.h b/include/linux/compat_ioctl.h
index 13cea44..307f2db 100644
--- a/include/linux/compat_ioctl.h
+++ b/include/linux/compat_ioctl.h
@@ -90,6 +90,7 @@ COMPATIBLE_IOCTL(FDTWADDLE)
 COMPATIBLE_IOCTL(FDFMTTRK)
 COMPATIBLE_IOCTL(FDRAWCMD)
 /* 0x12 */
+#ifdef CONFIG_BLOCK
 COMPATIBLE_IOCTL(BLKRASET)
 COMPATIBLE_IOCTL(BLKROSET)
 COMPATIBLE_IOCTL(BLKROGET)
@@ -103,6 +104,7 @@ COMPATIBLE_IOCTL(BLKTRACESETUP)
 COMPATIBLE_IOCTL(BLKTRACETEARDOWN)
 ULONG_IOCTL(BLKRASET)
 ULONG_IOCTL(BLKFRASET)
+#endif
 /* RAID */
 COMPATIBLE_IOCTL(RAID_VERSION)
 COMPATIBLE_IOCTL(GET_ARRAY_INFO)
diff --git a/include/linux/elevator.h b/include/linux/elevator.h
index 9c5a04f..b3370ef 100644
--- a/include/linux/elevator.h
+++ b/include/linux/elevator.h
@@ -3,6 +3,8 @@ #define _LINUX_ELEVATOR_H
 
 #include <linux/percpu.h>
 
+#ifdef CONFIG_BLOCK
+
 typedef int (elevator_merge_fn) (request_queue_t *, struct request **,
 				 struct bio *);
 
@@ -203,4 +205,5 @@ ({								\
 	__val;							\
 })
 
+#endif /* CONFIG_BLOCK */
 #endif
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 63d3126..5ad7d8b 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1477,6 +1477,7 @@ #else
 extern void putname(const char *name);
 #endif
 
+#ifdef CONFIG_BLOCK
 extern int register_blkdev(unsigned int, const char *);
 extern int unregister_blkdev(unsigned int, const char *);
 extern struct block_device *bdget(dev_t);
@@ -1485,11 +1486,15 @@ extern void bd_forget(struct inode *inod
 extern void bdput(struct block_device *);
 extern struct block_device *open_by_devnum(dev_t, unsigned);
 extern struct block_device *open_partition_by_devnum(dev_t, unsigned);
-extern const struct file_operations def_blk_fops;
 extern const struct address_space_operations def_blk_aops;
+#else
+static inline void bd_forget(struct inode *inode) {}
+#endif
+extern const struct file_operations def_blk_fops;
 extern const struct file_operations def_chr_fops;
 extern const struct file_operations bad_sock_fops;
 extern const struct file_operations def_fifo_fops;
+#ifdef CONFIG_BLOCK
 extern int ioctl_by_bdev(struct block_device *, unsigned, unsigned long);
 extern int blkdev_ioctl(struct inode *, struct file *, unsigned, unsigned long);
 extern long compat_blkdev_ioctl(struct file *, unsigned, unsigned long);
@@ -1505,6 +1510,7 @@ #else
 #define bd_claim_by_disk(bdev, holder, disk)	bd_claim(bdev, holder)
 #define bd_release_from_disk(bdev, disk)	bd_release(bdev)
 #endif
+#endif
 
 /* fs/char_dev.c */
 #define CHRDEV_MAJOR_HASH_SIZE	255
@@ -1518,14 +1524,19 @@ extern int chrdev_open(struct inode *, s
 extern void chrdev_show(struct seq_file *,off_t);
 
 /* fs/block_dev.c */
-#define BLKDEV_MAJOR_HASH_SIZE	255
 #define BDEVNAME_SIZE	32	/* Largest string for a blockdev identifier */
+
+#ifdef CONFIG_BLOCK
+#define BLKDEV_MAJOR_HASH_SIZE	255
 extern const char *__bdevname(dev_t, char *buffer);
 extern const char *bdevname(struct block_device *bdev, char *buffer);
 extern struct block_device *lookup_bdev(const char *);
 extern struct block_device *open_bdev_excl(const char *, int, void *);
 extern void close_bdev_excl(struct block_device *);
 extern void blkdev_show(struct seq_file *,off_t);
+#else
+#define BLKDEV_MAJOR_HASH_SIZE	0
+#endif
 
 extern void init_special_inode(struct inode *, umode_t, dev_t);
 
@@ -1539,6 +1550,7 @@ extern const struct file_operations rdwr
 
 extern int fs_may_remount_ro(struct super_block *);
 
+#ifdef CONFIG_BLOCK
 /*
  * return READ, READA, or WRITE
  */
@@ -1550,9 +1562,10 @@ #define bio_rw(bio)		((bio)->bi_rw & (RW
 #define bio_data_dir(bio)	((bio)->bi_rw & 1)
 
 extern int check_disk_change(struct block_device *);
-extern int invalidate_inodes(struct super_block *);
 extern int __invalidate_device(struct block_device *);
 extern int invalidate_partition(struct gendisk *, int);
+#endif
+extern int invalidate_inodes(struct super_block *);
 unsigned long invalidate_mapping_pages(struct address_space *mapping,
 					pgoff_t start, pgoff_t end);
 unsigned long invalidate_inode_pages(struct address_space *mapping);
@@ -1585,7 +1598,9 @@ extern void emergency_sync(void);
 extern void emergency_remount(void);
 extern int do_remount_sb(struct super_block *sb, int flags,
 			 void *data, int force);
+#ifdef CONFIG_BLOCK
 extern sector_t bmap(struct inode *, sector_t);
+#endif
 extern int notify_change(struct dentry *, struct iattr *);
 extern int permission(struct inode *, int, struct nameidata *);
 extern int generic_permission(struct inode *, int,
@@ -1668,9 +1683,11 @@ static inline void insert_inode_hash(str
 extern struct file * get_empty_filp(void);
 extern void file_move(struct file *f, struct list_head *list);
 extern void file_kill(struct file *f);
+#ifdef CONFIG_BLOCK
 struct bio;
 extern void submit_bio(int, struct bio *);
 extern int bdev_read_only(struct block_device *);
+#endif
 extern int set_blocksize(struct block_device *, int);
 extern int sb_set_blocksize(struct super_block *, int);
 extern int sb_min_blocksize(struct super_block *, int);
@@ -1751,6 +1768,7 @@ static inline void do_generic_file_read(
 				actor);
 }
 
+#ifdef CONFIG_BLOCK
 ssize_t __blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
 	struct block_device *bdev, const struct iovec *iov, loff_t offset,
 	unsigned long nr_segs, get_block_t get_block, dio_iodone_t end_io,
@@ -1788,6 +1806,7 @@ static inline ssize_t blockdev_direct_IO
 	return __blockdev_direct_IO(rw, iocb, inode, bdev, iov, offset,
 				nr_segs, get_block, end_io, DIO_OWN_LOCKING);
 }
+#endif
 
 extern const struct file_operations generic_ro_fops;
 
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index e4af57e..41f276f 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -11,6 +11,8 @@ #define _LINUX_GENHD_H
 
 #include <linux/types.h>
 
+#ifdef CONFIG_BLOCK
+
 enum {
 /* These three have identical behaviour; use the second one if DOS FDISK gets
    confused about extended/logical partitions starting past cylinder 1023. */
@@ -420,3 +422,5 @@ static inline struct block_device *bdget
 #endif
 
 #endif
+
+#endif
diff --git a/include/linux/mpage.h b/include/linux/mpage.h
index 517c098..cc5fb75 100644
--- a/include/linux/mpage.h
+++ b/include/linux/mpage.h
@@ -9,6 +9,7 @@
  * (And no, it doesn't do the #ifdef __MPAGE_H thing, and it doesn't do
  * nested includes.  Get it right in the .c file).
  */
+#ifdef CONFIG_BLOCK
 
 struct writeback_control;
 typedef int (writepage_t)(struct page *page, struct writeback_control *wbc);
@@ -20,3 +21,5 @@ int mpage_writepages(struct address_spac
 		struct writeback_control *wbc, get_block_t get_block);
 int mpage_writepage(struct page *page, get_block_t *get_block,
 		struct writeback_control *wbc);
+
+#endif
diff --git a/include/linux/raid/md.h b/include/linux/raid/md.h
index eb3e547..c588709 100644
--- a/include/linux/raid/md.h
+++ b/include/linux/raid/md.h
@@ -53,6 +53,8 @@ #include <linux/raid/md_p.h>
 #include <linux/raid/md_u.h>
 #include <linux/raid/md_k.h>
 
+#ifdef CONFIG_MD
+
 /*
  * Different major versions are not compatible.
  * Different minor versions are only downward compatible.
@@ -95,5 +97,6 @@ extern void md_new_event(mddev_t *mddev)
 
 extern void md_update_sb(mddev_t * mddev);
 
+#endif /* CONFIG_MD */
 #endif 
 
diff --git a/include/linux/raid/md_k.h b/include/linux/raid/md_k.h
index d288902..920b94f 100644
--- a/include/linux/raid/md_k.h
+++ b/include/linux/raid/md_k.h
@@ -18,6 +18,8 @@ #define _MD_K_H
 /* and dm-bio-list.h is not under include/linux because.... ??? */
 #include "../../../drivers/md/dm-bio-list.h"
 
+#ifdef CONFIG_BLOCK
+
 #define	LEVEL_MULTIPATH		(-4)
 #define	LEVEL_LINEAR		(-1)
 #define	LEVEL_FAULTY		(-5)
@@ -362,5 +364,6 @@ static inline void safe_put_page(struct 
 	if (p) put_page(p);
 }
 
+#endif /* CONFIG_BLOCK */
 #endif
 
diff --git a/include/scsi/scsi_tcq.h b/include/scsi/scsi_tcq.h
index 1d0b23d..d1d9b10 100644
--- a/include/scsi/scsi_tcq.h
+++ b/include/scsi/scsi_tcq.h
@@ -5,7 +5,6 @@ #include <linux/blkdev.h>
 #include <scsi/scsi_cmnd.h>
 #include <scsi/scsi_device.h>
 
-
 #define MSG_SIMPLE_TAG	0x20
 #define MSG_HEAD_TAG	0x21
 #define MSG_ORDERED_TAG	0x22
@@ -13,6 +12,7 @@ #define MSG_ORDERED_TAG	0x22
 #define SCSI_NO_TAG	(-1)    /* identify no tag in use */
 
 
+#ifdef CONFIG_BLOCK
 
 /**
  * scsi_get_tag_type - get the type of tag the device supports
@@ -131,4 +131,5 @@ static inline struct scsi_cmnd *scsi_fin
 	return sdev->current_cmnd;
 }
 
+#endif /* CONFIG_BLOCK */
 #endif /* _SCSI_SCSI_TCQ_H */
diff --git a/init/Kconfig b/init/Kconfig
index a099fc6..814bacc 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -92,7 +92,7 @@ config LOCALVERSION_AUTO
 
 config SWAP
 	bool "Support for paging of anonymous memory (swap)"
-	depends on MMU
+	depends on MMU && BLOCK
 	default y
 	help
 	  This option allows you to choose whether you want to have support
diff --git a/init/do_mounts.c b/init/do_mounts.c
index 94aeec7..dbb2604 100644
--- a/init/do_mounts.c
+++ b/init/do_mounts.c
@@ -284,7 +284,11 @@ void __init mount_block_root(char *name,
 {
 	char *fs_names = __getname();
 	char *p;
+#ifdef CONFIG_BLOCK
 	char b[BDEVNAME_SIZE];
+#else
+	const char *b = name;
+#endif
 
 	get_fs_names(fs_names);
 retry:
@@ -303,7 +307,9 @@ retry:
 		 * Allow the user to distinguish between failed sys_open
 		 * and bad superblock on root device.
 		 */
+#ifdef CONFIG_BLOCK
 		__bdevname(ROOT_DEV, b);
+#endif
 		printk("VFS: Cannot open root device \"%s\" or %s\n",
 				root_device_name, b);
 		printk("Please append a correct \"root=\" boot option\n");
@@ -315,7 +321,10 @@ retry:
 	for (p = fs_names; *p; p += strlen(p)+1)
 		printk(" %s", p);
 	printk("\n");
-	panic("VFS: Unable to mount root fs on %s", __bdevname(ROOT_DEV, b));
+#ifdef CONFIG_BLOCK
+	__bdevname(ROOT_DEV, b);
+#endif
+	panic("VFS: Unable to mount root fs on %s", b);
 out:
 	putname(fs_names);
 }
@@ -386,8 +395,10 @@ #ifdef CONFIG_BLK_DEV_FD
 			change_floppy("root floppy");
 	}
 #endif
+#ifdef CONFIG_BLOCK
 	create_dev("/dev/root", ROOT_DEV);
 	mount_block_root("/dev/root", root_mountflags);
+#endif
 }
 
 /*
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index 6991bec..7a3b2e7 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -134,3 +134,8 @@ cond_syscall(sys_madvise);
 cond_syscall(sys_mremap);
 cond_syscall(sys_remap_file_pages);
 cond_syscall(compat_sys_move_pages);
+
+/* block-layer dependent */
+cond_syscall(sys_bdflush);
+cond_syscall(sys_ioprio_set);
+cond_syscall(sys_ioprio_get);
diff --git a/mm/Makefile b/mm/Makefile
index 63637f0..761b08b 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -12,7 +12,7 @@ obj-y			:= bootmem.o filemap.o mempool.o
 			   readahead.o swap.o truncate.o vmscan.o \
 			   prio_tree.o util.o mmzone.o vmstat.o $(mmu-y)
 
-ifeq ($(CONFIG_MMU),y)
+ifeq ($(CONFIG_MMU)$(CONFIG_BLOCK),yy)
 obj-y			+= bounce.o
 endif
 obj-$(CONFIG_SWAP)	+= page_io.o swap_state.o swapfile.o thrash.o
diff --git a/mm/filemap.c b/mm/filemap.c
index 20a8a9b..6da05fc 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2003,6 +2003,7 @@ inline int generic_write_checks(struct f
 		if (unlikely(*pos + *count > inode->i_sb->s_maxbytes))
 			*count = inode->i_sb->s_maxbytes - *pos;
 	} else {
+#ifdef CONFIG_BLOCK
 		loff_t isize;
 		if (bdev_read_only(I_BDEV(inode)))
 			return -EPERM;
@@ -2014,6 +2015,9 @@ inline int generic_write_checks(struct f
 
 		if (*pos + *count > isize)
 			*count = isize - *pos;
+#else
+		return -EPERM;
+#endif
 	}
 	return 0;
 }
diff --git a/mm/migrate.c b/mm/migrate.c
index 0227163..bedc0ed 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -409,6 +409,7 @@ int migrate_page(struct address_space *m
 }
 EXPORT_SYMBOL(migrate_page);
 
+#ifdef CONFIG_BLOCK
 /*
  * Migration function for pages with buffers. This function can only be used
  * if the underlying filesystem guarantees that no other references to "page"
@@ -466,6 +467,7 @@ int buffer_migrate_page(struct address_s
 	return 0;
 }
 EXPORT_SYMBOL(buffer_migrate_page);
+#endif
 
 /*
  * Writeback a page to clean the dirty state
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index eeeaf43..64f4690 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -799,9 +799,11 @@ int fastcall set_page_dirty(struct page 
 
 	if (likely(mapping)) {
 		int (*spd)(struct page *) = mapping->a_ops->set_page_dirty;
-		if (spd)
-			return (*spd)(page);
-		return __set_page_dirty_buffers(page);
+#ifdef CONFIG_BLOCK
+		if (!spd)
+			spd = __set_page_dirty_buffers;
+#endif
+		return (*spd)(page);
 	}
 	if (!PageDirty(page)) {
 		if (!TestSetPageDirty(page))
diff --git a/mm/truncate.c b/mm/truncate.c
index 4b742cf..081437d 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -34,8 +34,10 @@ void do_invalidatepage(struct page *page
 {
 	void (*invalidatepage)(struct page *, unsigned long);
 	invalidatepage = page->mapping->a_ops->invalidatepage;
+#ifdef CONFIG_BLOCK
 	if (!invalidatepage)
 		invalidatepage = block_invalidatepage;
+#endif
 	if (invalidatepage)
 		(*invalidatepage)(page, offset);
 }
diff --git a/security/seclvl.c b/security/seclvl.c
index c26dd7d..fc00df2 100644
--- a/security/seclvl.c
+++ b/security/seclvl.c
@@ -377,6 +377,7 @@ static int seclvl_settime(struct timespe
 /* claim the blockdev to exclude mounters, release on file close */
 static int seclvl_bd_claim(struct inode *inode)
 {
+#ifdef CONFIG_BLOCK
 	int holder;
 	struct block_device *bdev = NULL;
 	dev_t dev = inode->i_rdev;
@@ -389,12 +390,14 @@ static int seclvl_bd_claim(struct inode 
 		/* claimed, mark it to release on close */
 		inode->i_security = current;
 	}
+#endif
 	return 0;
 }
 
 /* release the blockdev if you claimed it */
 static void seclvl_bd_release(struct inode *inode)
 {
+#ifdef CONFIG_BLOCK
 	if (inode && S_ISBLK(inode->i_mode) && inode->i_security == current) {
 		struct block_device *bdev = inode->i_bdev;
 		if (bdev) {
@@ -403,6 +406,7 @@ static void seclvl_bd_release(struct ino
 			inode->i_security = NULL;
 		}
 	}
+#endif
 }
 
 /**