[PATCH] BLOCK: Make it possible to disable the block layer [try #6]

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.  Some drivers that use SCSI facilities -
     	 such as USB storage - end up disabled indirectly from this.

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

     (*) 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>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

5 files changed, 14 insertions, 4 deletions

diff --git a/mm/Makefile b/mm/Makefile
index 4f2166a833b9..12b3a4eee88d 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -12,7 +12,7 @@ obj-y			:= bootmem.o filemap.o mempool.o oom_kill.o fadvise.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 d6846de08887..c4fe97f5ace0 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2020,6 +2020,7 @@ inline int generic_write_checks(struct file *file, loff_t *pos, size_t *count, i
                 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;
@@ -2031,6 +2032,9 @@ inline int generic_write_checks(struct file *file, loff_t *pos, size_t *count, i
 
                 if (*pos + *count > isize)
                         *count = isize - *pos;
+#else
+                return -EPERM;
+#endif
         }
         return 0;
 }
diff --git a/mm/migrate.c b/mm/migrate.c
index 7f50e3ff54cd..ba2453f9483d 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -409,6 +409,7 @@ int migrate_page(struct address_space *mapping,
 }
 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_space *mapping,
         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 ecf27839c203..c0d4ce144dec 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -807,9 +807,11 @@ int fastcall set_page_dirty(struct page *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 cd3e34b816db..8fde6580657e 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -35,8 +35,10 @@ void do_invalidatepage(struct page *page, unsigned long offset)
 {
         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);
 }