[PATCH] random fixes

- I changed the sector_t thing in max_block to use davem's approach.
  I agree with Anton, but making it explicit doesn't hurt.

- Remove a dead comment in copy_strings.

Old stuff:

- Remove the IO error warning in end_buffer_io_sync().  Failed READA
  attempts trigger it.

- Emit a warning when an ext2 is mounting an ext3 filesystem.

  We have had quite a few problem reports related to this, mainly
  arising from initrd problems.  And mount(8) tends to report the
  fstype from /etc/fstab rather than reporting what has really
  happened.

Fixes some bogosity which I added to max_block():

- `size' doesn't need to be sector_t

- `retval' should not be initialised to "~0UL" because that is
  0x00000000ffffffff with 64-bit sector_t.

- Allocate task_structs with GFP_KERNEL, as discussed.

- Convert the EXPORT_SYMBOL for generic_file_direct_IO() to
  EXPORT_SYMBOL_GPL.  That was only exported as a practicality for the
  raw driver.

- Make the loop thread run balance_dirty_pages() after dirtying the
  backing file.  So it will perform writeback of the backing file when
  dirty memory levels are high.  Export balance_dirty_pages to GPL
  modules for this.

  This makes loop work a lot better - I suspect it broke when callers
  of balance_dirty_pages() started writing back only their own queue.

  There are many page allocation failures under heavy loop writeout.
  Coming from blk_queue_bounce()'s allocation from the page_pool
  mempool.  So...

- Disable page allocation warnings around the initial atomic
  allocation attempt in mempool_alloc() - the one where __GFP_WAIT and
  __GFP_IO were turned off.  That one can easily fail.

- Add some commentary in block_write_full_page()

drivers/block/loop.c

@@ -74,6 +74,7 @@
 #include <linux/slab.h>
 #include <linux/loop.h>
 #include <linux/suspend.h>
+#include <linux/writeback.h>
 #include <linux/buffer_head.h>		/* for invalidate_bdev() */
 
 #include <asm/uaccess.h>
@@ -235,6 +236,7 @@ do_lo_send(struct loop_device *lo, struct bio_vec *bvec, int bsize, loff_t pos)
 	up(&mapping->host->i_sem);
 out:
 	kunmap(bvec->bv_page);
+	balance_dirty_pages(mapping);
 	return ret;
 
 unlock:

fs/block_dev.c

@@ -26,12 +26,12 @@
 
 static sector_t max_block(struct block_device *bdev)
 {
-	sector_t retval = ~0U;
+	sector_t retval = ~((sector_t)0);
 	loff_t sz = bdev->bd_inode->i_size;
 
 	if (sz) {
-		sector_t size = block_size(bdev);
-		unsigned sizebits = blksize_bits(size);
+		unsigned int size = block_size(bdev);
+		unsigned int sizebits = blksize_bits(size);
 		retval = (sz >> sizebits);
 	}
 	return retval;

fs/buffer.c

@@ -180,7 +180,10 @@ void end_buffer_io_sync(struct buffer_head *bh, int uptodate)
 	if (uptodate) {
 		set_buffer_uptodate(bh);
 	} else {
-		buffer_io_error(bh);
+		/*
+		 * This happens, due to failed READA attempts.
+		 * buffer_io_error(bh);
+		 */
 		clear_buffer_uptodate(bh);
 	}
 	unlock_buffer(bh);
@@ -2307,7 +2310,13 @@ int block_write_full_page(struct page *page, get_block_t *get_block)
 		return -EIO;
 	}
 
-	/* The page straddles i_size */
+	/*
+	 * The page straddles i_size.  It must be zeroed out on each and every
+	 * writepage invokation because it may be mmapped.  "A file is mapped
+	 * in multiples of the page size.  For a file that is not a multiple of
+	 * the  page size, the remaining memory is zeroed when mapped, and
+	 * writes to that region are not written out to the file."
+	 */
 	kaddr = kmap(page);
 	memset(kaddr + offset, 0, PAGE_CACHE_SIZE - offset);
 	flush_dcache_page(page);

fs/exec.c

@@ -209,11 +209,6 @@ int copy_strings(int argc,char ** argv, struct linux_binprm *bprm)
 		/* XXX: add architecture specific overflow check here. */ 
 		pos = bprm->p;
 
-		/*
-		 * The only sleeping function which we are allowed to call in
-		 * this loop is copy_from_user().  Otherwise, copy_user_state
-		 * could get trashed.
-		 */
 		while (len > 0) {
 			int i, new, err;
 			int offset, bytes_to_copy;

fs/ext2/super.c

@@ -698,6 +698,9 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
 			printk(KERN_ERR "EXT2-fs: get root inode failed\n");
 		goto failed_mount2;
 	}
+	if (EXT2_HAS_COMPAT_FEATURE(sb, EXT3_FEATURE_COMPAT_HAS_JOURNAL))
+		ext2_warning(sb, __FUNCTION__,
+			"mounting ext3 filesystem as ext2\n");
 	ext2_setup_super (sb, es, sb->s_flags & MS_RDONLY);
 	return 0;
 failed_mount2:

kernel/fork.c

@@ -131,9 +131,10 @@ static struct task_struct *dup_task_struct(struct task_struct *orig)
 	struct thread_info *ti;
 
 	ti = alloc_thread_info();
-	if (!ti) return NULL;
+	if (!ti)
+		return NULL;
 
-	tsk = kmem_cache_alloc(task_struct_cachep,GFP_ATOMIC);
+	tsk = kmem_cache_alloc(task_struct_cachep, GFP_KERNEL);
 	if (!tsk) {
 		free_thread_info(ti);
 		return NULL;

kernel/ksyms.c

@@ -344,7 +344,7 @@ EXPORT_SYMBOL(register_disk);
 EXPORT_SYMBOL(read_dev_sector);
 EXPORT_SYMBOL(init_buffer);
 EXPORT_SYMBOL(wipe_partitions);
-EXPORT_SYMBOL(generic_file_direct_IO);
+EXPORT_SYMBOL_GPL(generic_file_direct_IO);
 
 /* tty routines */
 EXPORT_SYMBOL(tty_hangup);

mm/mempool.c

@@ -189,7 +189,9 @@ void * mempool_alloc(mempool_t *pool, int gfp_mask)
 	int gfp_nowait = gfp_mask & ~(__GFP_WAIT | __GFP_IO);
 
 repeat_alloc:
+	current->flags |= PF_NOWARN;
 	element = pool->alloc(gfp_nowait, pool->pool_data);
+	current->flags &= ~PF_NOWARN;
 	if (likely(element != NULL))
 		return element;
 

mm/page-writeback.c

@@ -136,6 +136,7 @@ void balance_dirty_pages(struct address_space *mapping)
 	if (!writeback_in_progress(bdi) && ps.nr_dirty > background_thresh)
 		pdflush_operation(background_writeout, 0);
 }
+EXPORT_SYMBOL_GPL(balance_dirty_pages);
 
 /**
  * balance_dirty_pages_ratelimited - balance dirty memory state