Merge branch 'master' of master.kernel.org:/pub/scm/linux/kernel/git/torvalds/linux-2.6 into common/serial-rework

Conflicts:
	arch/sh/kernel/cpu/sh2/setup-sh7619.c
	arch/sh/kernel/cpu/sh2a/setup-mxg.c
	arch/sh/kernel/cpu/sh2a/setup-sh7201.c
	arch/sh/kernel/cpu/sh2a/setup-sh7203.c
	arch/sh/kernel/cpu/sh2a/setup-sh7206.c
	arch/sh/kernel/cpu/sh3/setup-sh7705.c
	arch/sh/kernel/cpu/sh3/setup-sh770x.c
	arch/sh/kernel/cpu/sh3/setup-sh7710.c
	arch/sh/kernel/cpu/sh3/setup-sh7720.c
	arch/sh/kernel/cpu/sh4/setup-sh4-202.c
	arch/sh/kernel/cpu/sh4/setup-sh7750.c
	arch/sh/kernel/cpu/sh4/setup-sh7760.c
	arch/sh/kernel/cpu/sh4a/setup-sh7343.c
	arch/sh/kernel/cpu/sh4a/setup-sh7366.c
	arch/sh/kernel/cpu/sh4a/setup-sh7722.c
	arch/sh/kernel/cpu/sh4a/setup-sh7723.c
	arch/sh/kernel/cpu/sh4a/setup-sh7724.c
	arch/sh/kernel/cpu/sh4a/setup-sh7763.c
	arch/sh/kernel/cpu/sh4a/setup-sh7770.c
	arch/sh/kernel/cpu/sh4a/setup-sh7780.c
	arch/sh/kernel/cpu/sh4a/setup-sh7785.c
	arch/sh/kernel/cpu/sh4a/setup-sh7786.c
	arch/sh/kernel/cpu/sh4a/setup-shx3.c
	arch/sh/kernel/cpu/sh5/setup-sh5.c
	drivers/serial/sh-sci.c
	drivers/serial/sh-sci.h
	include/linux/serial_sci.h

7 files changed, 443 insertions, 353 deletions

diff --git a/fs/isofs/compress.c b/fs/isofs/compress.c
index defb932..0b3fa79 100644
--- a/fs/isofs/compress.c
+++ b/fs/isofs/compress.c
@@ -36,286 +36,323 @@ static void *zisofs_zlib_workspace;
 static DEFINE_MUTEX(zisofs_zlib_lock);
 
 /*
- * When decompressing, we typically obtain more than one page
- * per reference.  We inject the additional pages into the page
- * cache as a form of readahead.
+ * Read data of @inode from @block_start to @block_end and uncompress
+ * to one zisofs block. Store the data in the @pages array with @pcount
+ * entries. Start storing at offset @poffset of the first page.
  */
-static int zisofs_readpage(struct file *file, struct page *page)
+static loff_t zisofs_uncompress_block(struct inode *inode, loff_t block_start,
+				      loff_t block_end, int pcount,
+				      struct page **pages, unsigned poffset,
+				      int *errp)
 {
-	struct inode *inode = file->f_path.dentry->d_inode;
-	struct address_space *mapping = inode->i_mapping;
-	unsigned int maxpage, xpage, fpage, blockindex;
-	unsigned long offset;
-	unsigned long blockptr, blockendptr, cstart, cend, csize;
-	struct buffer_head *bh, *ptrbh[2];
-	unsigned long bufsize = ISOFS_BUFFER_SIZE(inode);
-	unsigned int bufshift = ISOFS_BUFFER_BITS(inode);
-	unsigned long bufmask  = bufsize - 1;
-	int err = -EIO;
-	int i;
-	unsigned int header_size = ISOFS_I(inode)->i_format_parm[0];
 	unsigned int zisofs_block_shift = ISOFS_I(inode)->i_format_parm[1];
-	/* unsigned long zisofs_block_size = 1UL << zisofs_block_shift; */
-	unsigned int zisofs_block_page_shift = zisofs_block_shift-PAGE_CACHE_SHIFT;
-	unsigned long zisofs_block_pages = 1UL << zisofs_block_page_shift;
-	unsigned long zisofs_block_page_mask = zisofs_block_pages-1;
-	struct page *pages[zisofs_block_pages];
-	unsigned long index = page->index;
-	int indexblocks;
-
-	/* We have already been given one page, this is the one
-	   we must do. */
-	xpage = index & zisofs_block_page_mask;
-	pages[xpage] = page;
- 
-	/* The remaining pages need to be allocated and inserted */
-	offset = index & ~zisofs_block_page_mask;
-	blockindex = offset >> zisofs_block_page_shift;
-	maxpage = (inode->i_size + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
-
-	/*
-	 * If this page is wholly outside i_size we just return zero;
-	 * do_generic_file_read() will handle this for us
-	 */
-	if (page->index >= maxpage) {
-		SetPageUptodate(page);
-		unlock_page(page);
+	unsigned int bufsize = ISOFS_BUFFER_SIZE(inode);
+	unsigned int bufshift = ISOFS_BUFFER_BITS(inode);
+	unsigned int bufmask = bufsize - 1;
+	int i, block_size = block_end - block_start;
+	z_stream stream = { .total_out = 0,
+			    .avail_in = 0,
+			    .avail_out = 0, };
+	int zerr;
+	int needblocks = (block_size + (block_start & bufmask) + bufmask)
+				>> bufshift;
+	int haveblocks;
+	blkcnt_t blocknum;
+	struct buffer_head *bhs[needblocks + 1];
+	int curbh, curpage;
+
+	if (block_size > deflateBound(1UL << zisofs_block_shift)) {
+		*errp = -EIO;
 		return 0;
 	}
-
-	maxpage = min(zisofs_block_pages, maxpage-offset);
-
-	for ( i = 0 ; i < maxpage ; i++, offset++ ) {
-		if ( i != xpage ) {
-			pages[i] = grab_cache_page_nowait(mapping, offset);
-		}
-		page = pages[i];
-		if ( page ) {
-			ClearPageError(page);
-			kmap(page);
+	/* Empty block? */
+	if (block_size == 0) {
+		for ( i = 0 ; i < pcount ; i++ ) {
+			if (!pages[i])
+				continue;
+			memset(page_address(pages[i]), 0, PAGE_CACHE_SIZE);
+			flush_dcache_page(pages[i]);
+			SetPageUptodate(pages[i]);
 		}
+		return ((loff_t)pcount) << PAGE_CACHE_SHIFT;
 	}
 
-	/* This is the last page filled, plus one; used in case of abort. */
-	fpage = 0;
+	/* Because zlib is not thread-safe, do all the I/O at the top. */
+	blocknum = block_start >> bufshift;
+	memset(bhs, 0, (needblocks + 1) * sizeof(struct buffer_head *));
+	haveblocks = isofs_get_blocks(inode, blocknum, bhs, needblocks);
+	ll_rw_block(READ, haveblocks, bhs);
 
-	/* Find the pointer to this specific chunk */
-	/* Note: we're not using isonum_731() here because the data is known aligned */
-	/* Note: header_size is in 32-bit words (4 bytes) */
-	blockptr = (header_size + blockindex) << 2;
-	blockendptr = blockptr + 4;
+	curbh = 0;
+	curpage = 0;
+	/*
+	 * First block is special since it may be fractional.  We also wait for
+	 * it before grabbing the zlib mutex; odds are that the subsequent
+	 * blocks are going to come in in short order so we don't hold the zlib
+	 * mutex longer than necessary.
+	 */
 
-	indexblocks = ((blockptr^blockendptr) >> bufshift) ? 2 : 1;
-	ptrbh[0] = ptrbh[1] = NULL;
+	if (!bhs[0])
+		goto b_eio;
 
-	if ( isofs_get_blocks(inode, blockptr >> bufshift, ptrbh, indexblocks) != indexblocks ) {
-		if ( ptrbh[0] ) brelse(ptrbh[0]);
-		printk(KERN_DEBUG "zisofs: Null buffer on reading block table, inode = %lu, block = %lu\n",
-		       inode->i_ino, blockptr >> bufshift);
-		goto eio;
-	}
-	ll_rw_block(READ, indexblocks, ptrbh);
-
-	bh = ptrbh[0];
-	if ( !bh || (wait_on_buffer(bh), !buffer_uptodate(bh)) ) {
-		printk(KERN_DEBUG "zisofs: Failed to read block table, inode = %lu, block = %lu\n",
-		       inode->i_ino, blockptr >> bufshift);
-		if ( ptrbh[1] )
-			brelse(ptrbh[1]);
-		goto eio;
-	}
-	cstart = le32_to_cpu(*(__le32 *)(bh->b_data + (blockptr & bufmask)));
-
-	if ( indexblocks == 2 ) {
-		/* We just crossed a block boundary.  Switch to the next block */
-		brelse(bh);
-		bh = ptrbh[1];
-		if ( !bh || (wait_on_buffer(bh), !buffer_uptodate(bh)) ) {
-			printk(KERN_DEBUG "zisofs: Failed to read block table, inode = %lu, block = %lu\n",
-			       inode->i_ino, blockendptr >> bufshift);
-			goto eio;
-		}
+	wait_on_buffer(bhs[0]);
+	if (!buffer_uptodate(bhs[0])) {
+		*errp = -EIO;
+		goto b_eio;
 	}
-	cend = le32_to_cpu(*(__le32 *)(bh->b_data + (blockendptr & bufmask)));
-	brelse(bh);
 
-	if (cstart > cend)
-		goto eio;
+	stream.workspace = zisofs_zlib_workspace;
+	mutex_lock(&zisofs_zlib_lock);
 		
-	csize = cend-cstart;
-
-	if (csize > deflateBound(1UL << zisofs_block_shift))
-		goto eio;
-
-	/* Now page[] contains an array of pages, any of which can be NULL,
-	   and the locks on which we hold.  We should now read the data and
-	   release the pages.  If the pages are NULL the decompressed data
-	   for that particular page should be discarded. */
-	
-	if ( csize == 0 ) {
-		/* This data block is empty. */
-
-		for ( fpage = 0 ; fpage < maxpage ; fpage++ ) {
-			if ( (page = pages[fpage]) != NULL ) {
-				memset(page_address(page), 0, PAGE_CACHE_SIZE);
-				
-				flush_dcache_page(page);
-				SetPageUptodate(page);
-				kunmap(page);
-				unlock_page(page);
-				if ( fpage == xpage )
-					err = 0; /* The critical page */
-				else
-					page_cache_release(page);
+	zerr = zlib_inflateInit(&stream);
+	if (zerr != Z_OK) {
+		if (zerr == Z_MEM_ERROR)
+			*errp = -ENOMEM;
+		else
+			*errp = -EIO;
+		printk(KERN_DEBUG "zisofs: zisofs_inflateInit returned %d\n",
+			       zerr);
+		goto z_eio;
+	}
+
+	while (curpage < pcount && curbh < haveblocks &&
+	       zerr != Z_STREAM_END) {
+		if (!stream.avail_out) {
+			if (pages[curpage]) {
+				stream.next_out = page_address(pages[curpage])
+						+ poffset;
+				stream.avail_out = PAGE_CACHE_SIZE - poffset;
+				poffset = 0;
+			} else {
+				stream.next_out = (void *)&zisofs_sink_page;
+				stream.avail_out = PAGE_CACHE_SIZE;
 			}
 		}
-	} else {
-		/* This data block is compressed. */
-		z_stream stream;
-		int bail = 0, left_out = -1;
-		int zerr;
-		int needblocks = (csize + (cstart & bufmask) + bufmask) >> bufshift;
-		int haveblocks;
-		struct buffer_head *bhs[needblocks+1];
-		struct buffer_head **bhptr;
-
-		/* Because zlib is not thread-safe, do all the I/O at the top. */
-
-		blockptr = cstart >> bufshift;
-		memset(bhs, 0, (needblocks+1)*sizeof(struct buffer_head *));
-		haveblocks = isofs_get_blocks(inode, blockptr, bhs, needblocks);
-		ll_rw_block(READ, haveblocks, bhs);
-
-		bhptr = &bhs[0];
-		bh = *bhptr++;
-
-		/* First block is special since it may be fractional.
-		   We also wait for it before grabbing the zlib
-		   mutex; odds are that the subsequent blocks are
-		   going to come in in short order so we don't hold
-		   the zlib mutex longer than necessary. */
-
-		if ( !bh || (wait_on_buffer(bh), !buffer_uptodate(bh)) ) {
-			printk(KERN_DEBUG "zisofs: Hit null buffer, fpage = %d, xpage = %d, csize = %ld\n",
-			       fpage, xpage, csize);
-			goto b_eio;
-		}
-		stream.next_in  = bh->b_data + (cstart & bufmask);
-		stream.avail_in = min(bufsize-(cstart & bufmask), csize);
-		csize -= stream.avail_in;
-
-		stream.workspace = zisofs_zlib_workspace;
-		mutex_lock(&zisofs_zlib_lock);
-		
-		zerr = zlib_inflateInit(&stream);
-		if ( zerr != Z_OK ) {
-			if ( err && zerr == Z_MEM_ERROR )
-				err = -ENOMEM;
-			printk(KERN_DEBUG "zisofs: zisofs_inflateInit returned %d\n",
-			       zerr);
-			goto z_eio;
+		if (!stream.avail_in) {
+			wait_on_buffer(bhs[curbh]);
+			if (!buffer_uptodate(bhs[curbh])) {
+				*errp = -EIO;
+				break;
+			}
+			stream.next_in  = bhs[curbh]->b_data +
+						(block_start & bufmask);
+			stream.avail_in = min_t(unsigned, bufsize -
+						(block_start & bufmask),
+						block_size);
+			block_size -= stream.avail_in;
+			block_start = 0;
 		}
 
-		while ( !bail && fpage < maxpage ) {
-			page = pages[fpage];
-			if ( page )
-				stream.next_out = page_address(page);
-			else
-				stream.next_out = (void *)&zisofs_sink_page;
-			stream.avail_out = PAGE_CACHE_SIZE;
-
-			while ( stream.avail_out ) {
-				int ao, ai;
-				if ( stream.avail_in == 0 && left_out ) {
-					if ( !csize ) {
-						printk(KERN_WARNING "zisofs: ZF read beyond end of input\n");
-						bail = 1;
-						break;
-					} else {
-						bh = *bhptr++;
-						if ( !bh ||
-						     (wait_on_buffer(bh), !buffer_uptodate(bh)) ) {
-							/* Reached an EIO */
- 							printk(KERN_DEBUG "zisofs: Hit null buffer, fpage = %d, xpage = %d, csize = %ld\n",
-							       fpage, xpage, csize);
-							       
-							bail = 1;
-							break;
-						}
-						stream.next_in = bh->b_data;
-						stream.avail_in = min(csize,bufsize);
-						csize -= stream.avail_in;
-					}
-				}
-				ao = stream.avail_out;  ai = stream.avail_in;
-				zerr = zlib_inflate(&stream, Z_SYNC_FLUSH);
-				left_out = stream.avail_out;
-				if ( zerr == Z_BUF_ERROR && stream.avail_in == 0 )
-					continue;
-				if ( zerr != Z_OK ) {
-					/* EOF, error, or trying to read beyond end of input */
-					if ( err && zerr == Z_MEM_ERROR )
-						err = -ENOMEM;
-					if ( zerr != Z_STREAM_END )
-						printk(KERN_DEBUG "zisofs: zisofs_inflate returned %d, inode = %lu, index = %lu, fpage = %d, xpage = %d, avail_in = %d, avail_out = %d, ai = %d, ao = %d\n",
-						       zerr, inode->i_ino, index,
-						       fpage, xpage,
-						       stream.avail_in, stream.avail_out,
-						       ai, ao);
-					bail = 1;
-					break;
+		while (stream.avail_out && stream.avail_in) {
+			zerr = zlib_inflate(&stream, Z_SYNC_FLUSH);
+			if (zerr == Z_BUF_ERROR && stream.avail_in == 0)
+				break;
+			if (zerr == Z_STREAM_END)
+				break;
+			if (zerr != Z_OK) {
+				/* EOF, error, or trying to read beyond end of input */
+				if (zerr == Z_MEM_ERROR)
+					*errp = -ENOMEM;
+				else {
+					printk(KERN_DEBUG
+					       "zisofs: zisofs_inflate returned"
+					       " %d, inode = %lu,"
+					       " page idx = %d, bh idx = %d,"
+					       " avail_in = %d,"
+					       " avail_out = %d\n",
+					       zerr, inode->i_ino, curpage,
+					       curbh, stream.avail_in,
+					       stream.avail_out);
+					*errp = -EIO;
 				}
+				goto inflate_out;
 			}
+		}
 
-			if ( stream.avail_out && zerr == Z_STREAM_END ) {
-				/* Fractional page written before EOF.  This may
-				   be the last page in the file. */
-				memset(stream.next_out, 0, stream.avail_out);
-				stream.avail_out = 0;
+		if (!stream.avail_out) {
+			/* This page completed */
+			if (pages[curpage]) {
+				flush_dcache_page(pages[curpage]);
+				SetPageUptodate(pages[curpage]);
 			}
+			curpage++;
+		}
+		if (!stream.avail_in)
+			curbh++;
+	}
+inflate_out:
+	zlib_inflateEnd(&stream);
 
-			if ( !stream.avail_out ) {
-				/* This page completed */
-				if ( page ) {
-					flush_dcache_page(page);
-					SetPageUptodate(page);
-					kunmap(page);
-					unlock_page(page);
-					if ( fpage == xpage )
-						err = 0; /* The critical page */
-					else
-						page_cache_release(page);
-				}
-				fpage++;
-			}
+z_eio:
+	mutex_unlock(&zisofs_zlib_lock);
+
+b_eio:
+	for (i = 0; i < haveblocks; i++)
+		brelse(bhs[i]);
+	return stream.total_out;
+}
+
+/*
+ * Uncompress data so that pages[full_page] is fully uptodate and possibly
+ * fills in other pages if we have data for them.
+ */
+static int zisofs_fill_pages(struct inode *inode, int full_page, int pcount,
+			     struct page **pages)
+{
+	loff_t start_off, end_off;
+	loff_t block_start, block_end;
+	unsigned int header_size = ISOFS_I(inode)->i_format_parm[0];
+	unsigned int zisofs_block_shift = ISOFS_I(inode)->i_format_parm[1];
+	unsigned int blockptr;
+	loff_t poffset = 0;
+	blkcnt_t cstart_block, cend_block;
+	struct buffer_head *bh;
+	unsigned int blkbits = ISOFS_BUFFER_BITS(inode);
+	unsigned int blksize = 1 << blkbits;
+	int err;
+	loff_t ret;
+
+	BUG_ON(!pages[full_page]);
+
+	/*
+	 * We want to read at least 'full_page' page. Because we have to
+	 * uncompress the whole compression block anyway, fill the surrounding
+	 * pages with the data we have anyway...
+	 */
+	start_off = page_offset(pages[full_page]);
+	end_off = min_t(loff_t, start_off + PAGE_CACHE_SIZE, inode->i_size);
+
+	cstart_block = start_off >> zisofs_block_shift;
+	cend_block = (end_off + (1 << zisofs_block_shift) - 1)
+			>> zisofs_block_shift;
+
+	WARN_ON(start_off - (full_page << PAGE_CACHE_SHIFT) !=
+		((cstart_block << zisofs_block_shift) & PAGE_CACHE_MASK));
+
+	/* Find the pointer to this specific chunk */
+	/* Note: we're not using isonum_731() here because the data is known aligned */
+	/* Note: header_size is in 32-bit words (4 bytes) */
+	blockptr = (header_size + cstart_block) << 2;
+	bh = isofs_bread(inode, blockptr >> blkbits);
+	if (!bh)
+		return -EIO;
+	block_start = le32_to_cpu(*(__le32 *)
+				(bh->b_data + (blockptr & (blksize - 1))));
+
+	while (cstart_block < cend_block && pcount > 0) {
+		/* Load end of the compressed block in the file */
+		blockptr += 4;
+		/* Traversed to next block? */
+		if (!(blockptr & (blksize - 1))) {
+			brelse(bh);
+
+			bh = isofs_bread(inode, blockptr >> blkbits);
+			if (!bh)
+				return -EIO;
+		}
+		block_end = le32_to_cpu(*(__le32 *)
+				(bh->b_data + (blockptr & (blksize - 1))));
+		if (block_start > block_end) {
+			brelse(bh);
+			return -EIO;
+		}
+		err = 0;
+		ret = zisofs_uncompress_block(inode, block_start, block_end,
+					      pcount, pages, poffset, &err);
+		poffset += ret;
+		pages += poffset >> PAGE_CACHE_SHIFT;
+		pcount -= poffset >> PAGE_CACHE_SHIFT;
+		full_page -= poffset >> PAGE_CACHE_SHIFT;
+		poffset &= ~PAGE_CACHE_MASK;
+
+		if (err) {
+			brelse(bh);
+			/*
+			 * Did we finish reading the page we really wanted
+			 * to read?
+			 */
+			if (full_page < 0)
+				return 0;
+			return err;
 		}
-		zlib_inflateEnd(&stream);
 
-	z_eio:
-		mutex_unlock(&zisofs_zlib_lock);
+		block_start = block_end;
+		cstart_block++;
+	}
+
+	if (poffset && *pages) {
+		memset(page_address(*pages) + poffset, 0,
+		       PAGE_CACHE_SIZE - poffset);
+		flush_dcache_page(*pages);
+		SetPageUptodate(*pages);
+	}
+	return 0;
+}
 
-	b_eio:
-		for ( i = 0 ; i < haveblocks ; i++ ) {
-			if ( bhs[i] )
-				brelse(bhs[i]);
+/*
+ * When decompressing, we typically obtain more than one page
+ * per reference.  We inject the additional pages into the page
+ * cache as a form of readahead.
+ */
+static int zisofs_readpage(struct file *file, struct page *page)
+{
+	struct inode *inode = file->f_path.dentry->d_inode;
+	struct address_space *mapping = inode->i_mapping;
+	int err;
+	int i, pcount, full_page;
+	unsigned int zisofs_block_shift = ISOFS_I(inode)->i_format_parm[1];
+	unsigned int zisofs_pages_per_cblock =
+		PAGE_CACHE_SHIFT <= zisofs_block_shift ?
+		(1 << (zisofs_block_shift - PAGE_CACHE_SHIFT)) : 0;
+	struct page *pages[max_t(unsigned, zisofs_pages_per_cblock, 1)];
+	pgoff_t index = page->index, end_index;
+
+	end_index = (inode->i_size + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
+	/*
+	 * If this page is wholly outside i_size we just return zero;
+	 * do_generic_file_read() will handle this for us
+	 */
+	if (index >= end_index) {
+		SetPageUptodate(page);
+		unlock_page(page);
+		return 0;
+	}
+
+	if (PAGE_CACHE_SHIFT <= zisofs_block_shift) {
+		/* We have already been given one page, this is the one
+		   we must do. */
+		full_page = index & (zisofs_pages_per_cblock - 1);
+		pcount = min_t(int, zisofs_pages_per_cblock,
+			end_index - (index & ~(zisofs_pages_per_cblock - 1)));
+		index -= full_page;
+	} else {
+		full_page = 0;
+		pcount = 1;
+	}
+	pages[full_page] = page;
+
+	for (i = 0; i < pcount; i++, index++) {
+		if (i != full_page)
+			pages[i] = grab_cache_page_nowait(mapping, index);
+		if (pages[i]) {
+			ClearPageError(pages[i]);
+			kmap(pages[i]);
 		}
 	}
 
-eio:
+	err = zisofs_fill_pages(inode, full_page, pcount, pages);
 
 	/* Release any residual pages, do not SetPageUptodate */
-	while ( fpage < maxpage ) {
-		page = pages[fpage];
-		if ( page ) {
-			flush_dcache_page(page);
-			if ( fpage == xpage )
-				SetPageError(page);
-			kunmap(page);
-			unlock_page(page);
-			if ( fpage != xpage )
-				page_cache_release(page);
+	for (i = 0; i < pcount; i++) {
+		if (pages[i]) {
+			flush_dcache_page(pages[i]);
+			if (i == full_page && err)
+				SetPageError(pages[i]);
+			kunmap(pages[i]);
+			unlock_page(pages[i]);
+			if (i != full_page)
+				page_cache_release(pages[i]);
 		}
-		fpage++;
 	}			
 
 	/* At this point, err contains 0 or -EIO depending on the "critical" page */
diff --git a/fs/isofs/dir.c b/fs/isofs/dir.c
index 8ba5441..0542b6e 100644
--- a/fs/isofs/dir.c
+++ b/fs/isofs/dir.c
@@ -10,7 +10,7 @@
  *
  *  isofs directory handling functions
  */
-#include <linux/smp_lock.h>
+#include <linux/gfp.h>
 #include "isofs.h"
 
 int isofs_name_translate(struct iso_directory_record *de, char *new, struct inode *inode)
@@ -254,23 +254,25 @@ static int isofs_readdir(struct file *filp,
 	char *tmpname;
 	struct iso_directory_record *tmpde;
 	struct inode *inode = filp->f_path.dentry->d_inode;
+	struct isofs_sb_info *sbi = ISOFS_SB(inode->i_sb);
 
 	tmpname = (char *)__get_free_page(GFP_KERNEL);
 	if (tmpname == NULL)
 		return -ENOMEM;
 
-	lock_kernel();
+	mutex_lock(&sbi->s_mutex);
 	tmpde = (struct iso_directory_record *) (tmpname+1024);
 
 	result = do_isofs_readdir(inode, filp, dirent, filldir, tmpname, tmpde);
 
 	free_page((unsigned long) tmpname);
-	unlock_kernel();
+	mutex_unlock(&sbi->s_mutex);
 	return result;
 }
 
 const struct file_operations isofs_dir_operations =
 {
+	.llseek = generic_file_llseek,
 	.read = generic_read_dir,
 	.readdir = isofs_readdir,
 };
diff --git a/fs/isofs/export.c b/fs/isofs/export.c
index e81a305..ed752cb 100644
--- a/fs/isofs/export.c
+++ b/fs/isofs/export.c
@@ -9,7 +9,7 @@
  *
  * The following files are helpful:
  *
- *     Documentation/filesystems/Exporting
+ *     Documentation/filesystems/nfs/Exporting
  *     fs/exportfs/expfs.c.
  */
 
diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c
index 58a7963..844a790 100644
--- a/fs/isofs/inode.c
+++ b/fs/isofs/inode.c
@@ -17,7 +17,6 @@
 #include <linux/slab.h>
 #include <linux/nls.h>
 #include <linux/ctype.h>
-#include <linux/smp_lock.h>
 #include <linux/statfs.h>
 #include <linux/cdrom.h>
 #include <linux/parser.h>
@@ -27,16 +26,32 @@
 
 #define BEQUIET
 
-static int isofs_hashi(struct dentry *parent, struct qstr *qstr);
-static int isofs_hash(struct dentry *parent, struct qstr *qstr);
-static int isofs_dentry_cmpi(struct dentry *dentry, struct qstr *a, struct qstr *b);
-static int isofs_dentry_cmp(struct dentry *dentry, struct qstr *a, struct qstr *b);
+static int isofs_hashi(const struct dentry *parent, const struct inode *inode,
+		struct qstr *qstr);
+static int isofs_hash(const struct dentry *parent, const struct inode *inode,
+		struct qstr *qstr);
+static int isofs_dentry_cmpi(const struct dentry *parent,
+		const struct inode *pinode,
+		const struct dentry *dentry, const struct inode *inode,
+		unsigned int len, const char *str, const struct qstr *name);
+static int isofs_dentry_cmp(const struct dentry *parent,
+		const struct inode *pinode,
+		const struct dentry *dentry, const struct inode *inode,
+		unsigned int len, const char *str, const struct qstr *name);
 
 #ifdef CONFIG_JOLIET
-static int isofs_hashi_ms(struct dentry *parent, struct qstr *qstr);
-static int isofs_hash_ms(struct dentry *parent, struct qstr *qstr);
-static int isofs_dentry_cmpi_ms(struct dentry *dentry, struct qstr *a, struct qstr *b);
-static int isofs_dentry_cmp_ms(struct dentry *dentry, struct qstr *a, struct qstr *b);
+static int isofs_hashi_ms(const struct dentry *parent, const struct inode *inode,
+		struct qstr *qstr);
+static int isofs_hash_ms(const struct dentry *parent, const struct inode *inode,
+		struct qstr *qstr);
+static int isofs_dentry_cmpi_ms(const struct dentry *parent,
+		const struct inode *pinode,
+		const struct dentry *dentry, const struct inode *inode,
+		unsigned int len, const char *str, const struct qstr *name);
+static int isofs_dentry_cmp_ms(const struct dentry *parent,
+		const struct inode *pinode,
+		const struct dentry *dentry, const struct inode *inode,
+		unsigned int len, const char *str, const struct qstr *name);
 #endif
 
 static void isofs_put_super(struct super_block *sb)
@@ -44,14 +59,7 @@ static void isofs_put_super(struct super_block *sb)
 	struct isofs_sb_info *sbi = ISOFS_SB(sb);
 
 #ifdef CONFIG_JOLIET
-	lock_kernel();
-
-	if (sbi->s_nls_iocharset) {
-		unload_nls(sbi->s_nls_iocharset);
-		sbi->s_nls_iocharset = NULL;
-	}
-
-	unlock_kernel();
+	unload_nls(sbi->s_nls_iocharset);
 #endif
 
 	kfree(sbi);
@@ -73,11 +81,18 @@ static struct inode *isofs_alloc_inode(struct super_block *sb)
 	return &ei->vfs_inode;
 }
 
-static void isofs_destroy_inode(struct inode *inode)
+static void isofs_i_callback(struct rcu_head *head)
 {
+	struct inode *inode = container_of(head, struct inode, i_rcu);
+	INIT_LIST_HEAD(&inode->i_dentry);
 	kmem_cache_free(isofs_inode_cachep, ISOFS_I(inode));
 }
 
+static void isofs_destroy_inode(struct inode *inode)
+{
+	call_rcu(&inode->i_rcu, isofs_i_callback);
+}
+
 static void init_once(void *foo)
 {
 	struct iso_inode_info *ei = foo;
@@ -142,6 +157,7 @@ static const struct dentry_operations isofs_dentry_ops[] = {
 
 struct iso9660_options{
 	unsigned int rock:1;
+	unsigned int joliet:1;
 	unsigned int cruft:1;
 	unsigned int hide:1;
 	unsigned int showassoc:1;
@@ -151,7 +167,6 @@ struct iso9660_options{
 	unsigned int gid_set:1;
 	unsigned int utf8:1;
 	unsigned char map;
-	char joliet;
 	unsigned char check;
 	unsigned int blocksize;
 	mode_t fmode;
@@ -168,7 +183,7 @@ struct iso9660_options{
  * Compute the hash for the isofs name corresponding to the dentry.
  */
 static int
-isofs_hash_common(struct dentry *dentry, struct qstr *qstr, int ms)
+isofs_hash_common(const struct dentry *dentry, struct qstr *qstr, int ms)
 {
 	const char *name;
 	int len;
@@ -189,7 +204,7 @@ isofs_hash_common(struct dentry *dentry, struct qstr *qstr, int ms)
  * Compute the hash for the isofs name corresponding to the dentry.
  */
 static int
-isofs_hashi_common(struct dentry *dentry, struct qstr *qstr, int ms)
+isofs_hashi_common(const struct dentry *dentry, struct qstr *qstr, int ms)
 {
 	const char *name;
 	int len;
@@ -214,100 +229,94 @@ isofs_hashi_common(struct dentry *dentry, struct qstr *qstr, int ms)
 }
 
 /*
- * Case insensitive compare of two isofs names.
+ * Compare of two isofs names.
  */
-static int isofs_dentry_cmpi_common(struct dentry *dentry, struct qstr *a,
-				struct qstr *b, int ms)
+static int isofs_dentry_cmp_common(
+		unsigned int len, const char *str,
+		const struct qstr *name, int ms, int ci)
 {
 	int alen, blen;
 
 	/* A filename cannot end in '.' or we treat it like it has none */
-	alen = a->len;
-	blen = b->len;
+	alen = name->len;
+	blen = len;
 	if (ms) {
-		while (alen && a->name[alen-1] == '.')
+		while (alen && name->name[alen-1] == '.')
 			alen--;
-		while (blen && b->name[blen-1] == '.')
+		while (blen && str[blen-1] == '.')
 			blen--;
 	}
 	if (alen == blen) {
-		if (strnicmp(a->name, b->name, alen) == 0)
-			return 0;
-	}
-	return 1;
-}
-
-/*
- * Case sensitive compare of two isofs names.
- */
-static int isofs_dentry_cmp_common(struct dentry *dentry, struct qstr *a,
-					struct qstr *b, int ms)
-{
-	int alen, blen;
-
-	/* A filename cannot end in '.' or we treat it like it has none */
-	alen = a->len;
-	blen = b->len;
-	if (ms) {
-		while (alen && a->name[alen-1] == '.')
-			alen--;
-		while (blen && b->name[blen-1] == '.')
-			blen--;
-	}
-	if (alen == blen) {
-		if (strncmp(a->name, b->name, alen) == 0)
-			return 0;
+		if (ci) {
+			if (strnicmp(name->name, str, alen) == 0)
+				return 0;
+		} else {
+			if (strncmp(name->name, str, alen) == 0)
+				return 0;
+		}
 	}
 	return 1;
 }
 
 static int
-isofs_hash(struct dentry *dentry, struct qstr *qstr)
+isofs_hash(const struct dentry *dentry, const struct inode *inode,
+		struct qstr *qstr)
 {
 	return isofs_hash_common(dentry, qstr, 0);
 }
 
 static int
-isofs_hashi(struct dentry *dentry, struct qstr *qstr)
+isofs_hashi(const struct dentry *dentry, const struct inode *inode,
+		struct qstr *qstr)
 {
 	return isofs_hashi_common(dentry, qstr, 0);
 }
 
 static int
-isofs_dentry_cmp(struct dentry *dentry,struct qstr *a,struct qstr *b)
+isofs_dentry_cmp(const struct dentry *parent, const struct inode *pinode,
+		const struct dentry *dentry, const struct inode *inode,
+		unsigned int len, const char *str, const struct qstr *name)
 {
-	return isofs_dentry_cmp_common(dentry, a, b, 0);
+	return isofs_dentry_cmp_common(len, str, name, 0, 0);
 }
 
 static int
-isofs_dentry_cmpi(struct dentry *dentry,struct qstr *a,struct qstr *b)
+isofs_dentry_cmpi(const struct dentry *parent, const struct inode *pinode,
+		const struct dentry *dentry, const struct inode *inode,
+		unsigned int len, const char *str, const struct qstr *name)
 {
-	return isofs_dentry_cmpi_common(dentry, a, b, 0);
+	return isofs_dentry_cmp_common(len, str, name, 0, 1);
 }
 
 #ifdef CONFIG_JOLIET
 static int
-isofs_hash_ms(struct dentry *dentry, struct qstr *qstr)
+isofs_hash_ms(const struct dentry *dentry, const struct inode *inode,
+		struct qstr *qstr)
 {
 	return isofs_hash_common(dentry, qstr, 1);
 }
 
 static int
-isofs_hashi_ms(struct dentry *dentry, struct qstr *qstr)
+isofs_hashi_ms(const struct dentry *dentry, const struct inode *inode,
+		struct qstr *qstr)
 {
 	return isofs_hashi_common(dentry, qstr, 1);
 }
 
 static int
-isofs_dentry_cmp_ms(struct dentry *dentry,struct qstr *a,struct qstr *b)
+isofs_dentry_cmp_ms(const struct dentry *parent, const struct inode *pinode,
+		const struct dentry *dentry, const struct inode *inode,
+		unsigned int len, const char *str, const struct qstr *name)
 {
-	return isofs_dentry_cmp_common(dentry, a, b, 1);
+	return isofs_dentry_cmp_common(len, str, name, 1, 0);
 }
 
 static int
-isofs_dentry_cmpi_ms(struct dentry *dentry,struct qstr *a,struct qstr *b)
+isofs_dentry_cmpi_ms(const struct dentry *parent, const struct inode *pinode,
+		const struct dentry *dentry, const struct inode *inode,
+		unsigned int len, const char *str, const struct qstr *name)
 {
-	return isofs_dentry_cmpi_common(dentry, a, b, 1);
+	return isofs_dentry_cmp_common(len, str, name, 1, 1);
 }
 #endif
 
@@ -552,6 +561,34 @@ static unsigned int isofs_get_last_session(struct super_block *sb, s32 session)
 }
 
 /*
+ * Check if root directory is empty (has less than 3 files).
+ *
+ * Used to detect broken CDs where ISO root directory is empty but Joliet root
+ * directory is OK. If such CD has Rock Ridge extensions, they will be disabled
+ * (and Joliet used instead) or else no files would be visible.
+ */
+static bool rootdir_empty(struct super_block *sb, unsigned long block)
+{
+	int offset = 0, files = 0, de_len;
+	struct iso_directory_record *de;
+	struct buffer_head *bh;
+
+	bh = sb_bread(sb, block);
+	if (!bh)
+		return true;
+	while (files < 3) {
+		de = (struct iso_directory_record *) (bh->b_data + offset);
+		de_len = *(unsigned char *) de;
+		if (de_len == 0)
+			break;
+		files++;
+		offset += de_len;
+	}
+	brelse(bh);
+	return files < 3;
+}
+
+/*
  * Initialize the superblock and read the root inode.
  *
  * Note: a check_disk_change() has been done immediately prior
@@ -632,7 +669,7 @@ static int isofs_fill_super(struct super_block *s, void *data, int silent)
 			else if (isonum_711(vdp->type) == ISO_VD_SUPPLEMENTARY) {
 				sec = (struct iso_supplementary_descriptor *)vdp;
 				if (sec->escape[0] == 0x25 && sec->escape[1] == 0x2f) {
-					if (opt.joliet == 'y') {
+					if (opt.joliet) {
 						if (sec->escape[2] == 0x40)
 							joliet_level = 1;
 						else if (sec->escape[2] == 0x43)
@@ -725,7 +762,12 @@ root_found:
 	}
 
 	s->s_magic = ISOFS_SUPER_MAGIC;
-	s->s_maxbytes = 0xffffffff; /* We can handle files up to 4 GB */
+
+	/*
+	 * With multi-extent files, file size is only limited by the maximum
+	 * size of a file system, which is 8 TB.
+	 */
+	s->s_maxbytes = 0x80000000000LL;
 
 	/*
 	 * The CDROM is read-only, has no nodes (devices) on it, and since
@@ -821,6 +863,7 @@ root_found:
 	sbi->s_utf8 = opt.utf8;
 	sbi->s_nocompress = opt.nocompress;
 	sbi->s_overriderockperm = opt.overriderockperm;
+	mutex_init(&sbi->s_mutex);
 	/*
 	 * It would be incredibly stupid to allow people to mark every file
 	 * on the disk as suid, so we merely allow them to set the default
@@ -845,6 +888,18 @@ root_found:
 		goto out_no_root;
 
 	/*
+	 * Fix for broken CDs with Rock Ridge and empty ISO root directory but
+	 * correct Joliet root directory.
+	 */
+	if (sbi->s_rock == 1 && joliet_level &&
+				rootdir_empty(s, sbi->s_firstdatazone)) {
+		printk(KERN_NOTICE
+			"ISOFS: primary root directory is empty. "
+			"Disabling Rock Ridge and switching to Joliet.");
+		sbi->s_rock = 0;
+	}
+
+	/*
 	 * If this disk has both Rock Ridge and Joliet on it, then we
 	 * want to use Rock Ridge by default.  This can be overridden
 	 * by using the norock mount option.  There is still one other
@@ -894,7 +949,7 @@ root_found:
 		table += 2;
 	if (opt.check == 'r')
 		table++;
-	s->s_root->d_op = &isofs_dentry_ops[table];
+	d_set_d_op(s->s_root, &isofs_dentry_ops[table]);
 
 	kfree(opt.iocharset);
 
@@ -912,8 +967,7 @@ out_no_root:
 		printk(KERN_WARNING "%s: get root inode failed\n", __func__);
 out_no_inode:
 #ifdef CONFIG_JOLIET
-	if (sbi->s_nls_iocharset)
-		unload_nls(sbi->s_nls_iocharset);
+	unload_nls(sbi->s_nls_iocharset);
 #endif
 	goto out_freesbi;
 out_no_read:
@@ -965,27 +1019,23 @@ static int isofs_statfs (struct dentry *dentry, struct kstatfs *buf)
  * or getblk() if they are not.  Returns the number of blocks inserted
  * (-ve == error.)
  */
-int isofs_get_blocks(struct inode *inode, sector_t iblock_s,
+int isofs_get_blocks(struct inode *inode, sector_t iblock,
 		     struct buffer_head **bh, unsigned long nblocks)
 {
-	unsigned long b_off;
+	unsigned long b_off = iblock;
 	unsigned offset, sect_size;
 	unsigned int firstext;
 	unsigned long nextblk, nextoff;
-	long iblock = (long)iblock_s;
 	int section, rv, error;
 	struct iso_inode_info *ei = ISOFS_I(inode);
 
-	lock_kernel();
-
 	error = -EIO;
 	rv = 0;
-	if (iblock < 0 || iblock != iblock_s) {
+	if (iblock != b_off) {
 		printk(KERN_DEBUG "%s: block number too large\n", __func__);
 		goto abort;
 	}
 
-	b_off = iblock;
 
 	offset = 0;
 	firstext = ei->i_first_extent;
@@ -1003,8 +1053,9 @@ int isofs_get_blocks(struct inode *inode, sector_t iblock_s,
 		 * I/O errors.
 		 */
 		if (b_off > ((inode->i_size + PAGE_CACHE_SIZE - 1) >> ISOFS_BUFFER_BITS(inode))) {
-			printk(KERN_DEBUG "%s: block >= EOF (%ld, %ld)\n",
-				__func__, iblock, (unsigned long) inode->i_size);
+			printk(KERN_DEBUG "%s: block >= EOF (%lu, %llu)\n",
+				__func__, b_off,
+				(unsigned long long)inode->i_size);
 			goto abort;
 		}
 
@@ -1030,9 +1081,9 @@ int isofs_get_blocks(struct inode *inode, sector_t iblock_s,
 			if (++section > 100) {
 				printk(KERN_DEBUG "%s: More than 100 file sections ?!?"
 					" aborting...\n", __func__);
-				printk(KERN_DEBUG "%s: block=%ld firstext=%u sect_size=%u "
+				printk(KERN_DEBUG "%s: block=%lu firstext=%u sect_size=%u "
 					"nextblk=%lu nextoff=%lu\n", __func__,
-					iblock, firstext, (unsigned) sect_size,
+					b_off, firstext, (unsigned) sect_size,
 					nextblk, nextoff);
 				goto abort;
 			}
@@ -1053,7 +1104,6 @@ int isofs_get_blocks(struct inode *inode, sector_t iblock_s,
 
 	error = 0;
 abort:
-	unlock_kernel();
 	return rv != 0 ? rv : error;
 }
 
@@ -1474,17 +1524,16 @@ struct inode *isofs_iget(struct super_block *sb,
 	return inode;
 }
 
-static int isofs_get_sb(struct file_system_type *fs_type,
-	int flags, const char *dev_name, void *data, struct vfsmount *mnt)
+static struct dentry *isofs_mount(struct file_system_type *fs_type,
+	int flags, const char *dev_name, void *data)
 {
-	return get_sb_bdev(fs_type, flags, dev_name, data, isofs_fill_super,
-				mnt);
+	return mount_bdev(fs_type, flags, dev_name, data, isofs_fill_super);
 }
 
 static struct file_system_type iso9660_fs_type = {
 	.owner		= THIS_MODULE,
 	.name		= "iso9660",
-	.get_sb		= isofs_get_sb,
+	.mount		= isofs_mount,
 	.kill_sb	= kill_block_super,
 	.fs_flags	= FS_REQUIRES_DEV,
 };
diff --git a/fs/isofs/isofs.h b/fs/isofs/isofs.h
index 7d33de8..2882dc0 100644
--- a/fs/isofs/isofs.h
+++ b/fs/isofs/isofs.h
@@ -55,6 +55,7 @@ struct isofs_sb_info {
 	gid_t s_gid;
 	uid_t s_uid;
 	struct nls_table *s_nls_iocharset; /* Native language support table */
+	struct mutex s_mutex; /* replaces BKL, please remove if possible */
 };
 
 #define ISOFS_INVALID_MODE ((mode_t) -1)
diff --git a/fs/isofs/namei.c b/fs/isofs/namei.c
index eaa8313..679a849 100644
--- a/fs/isofs/namei.c
+++ b/fs/isofs/namei.c
@@ -6,7 +6,7 @@
  *  (C) 1991  Linus Torvalds - minix filesystem
  */
 
-#include <linux/smp_lock.h>
+#include <linux/gfp.h>
 #include "isofs.h"
 
 /*
@@ -37,7 +37,8 @@ isofs_cmp(struct dentry *dentry, const char *compare, int dlen)
 
 	qstr.name = compare;
 	qstr.len = dlen;
-	return dentry->d_op->d_compare(dentry, &dentry->d_name, &qstr);
+	return dentry->d_op->d_compare(NULL, NULL, NULL, NULL,
+			dentry->d_name.len, dentry->d_name.name, &qstr);
 }
 
 /*
@@ -167,16 +168,17 @@ struct dentry *isofs_lookup(struct inode *dir, struct dentry *dentry, struct nam
 	int found;
 	unsigned long uninitialized_var(block);
 	unsigned long uninitialized_var(offset);
+	struct isofs_sb_info *sbi = ISOFS_SB(dir->i_sb);
 	struct inode *inode;
 	struct page *page;
 
-	dentry->d_op = dir->i_sb->s_root->d_op;
+	d_set_d_op(dentry, dir->i_sb->s_root->d_op);
 
 	page = alloc_page(GFP_USER);
 	if (!page)
 		return ERR_PTR(-ENOMEM);
 
-	lock_kernel();
+	mutex_lock(&sbi->s_mutex);
 	found = isofs_find_entry(dir, dentry,
 				&block, &offset,
 				page_address(page),
@@ -187,10 +189,10 @@ struct dentry *isofs_lookup(struct inode *dir, struct dentry *dentry, struct nam
 	if (found) {
 		inode = isofs_iget(dir->i_sb, block, offset);
 		if (IS_ERR(inode)) {
-			unlock_kernel();
+			mutex_unlock(&sbi->s_mutex);
 			return ERR_CAST(inode);
 		}
 	}
-	unlock_kernel();
+	mutex_unlock(&sbi->s_mutex);
 	return d_splice_alias(inode, dentry);
 }
diff --git a/fs/isofs/rock.c b/fs/isofs/rock.c
index c2fb2dd..f9cd04d 100644
--- a/fs/isofs/rock.c
+++ b/fs/isofs/rock.c
@@ -8,7 +8,6 @@
 
 #include <linux/slab.h>
 #include <linux/pagemap.h>
-#include <linux/smp_lock.h>
 
 #include "isofs.h"
 #include "rock.h"
@@ -518,8 +517,7 @@ repeat:
 			if (algo == SIG('p', 'z')) {
 				int block_shift =
 					isonum_711(&rr->u.ZF.parms[1]);
-				if (block_shift < PAGE_CACHE_SHIFT
-						|| block_shift > 17) {
+				if (block_shift > 17) {
 					printk(KERN_WARNING "isofs: "
 						"Can't handle ZF block "
 						"size of 2^%d\n",
@@ -662,6 +660,7 @@ static int rock_ridge_symlink_readpage(struct file *file, struct page *page)
 {
 	struct inode *inode = page->mapping->host;
 	struct iso_inode_info *ei = ISOFS_I(inode);
+	struct isofs_sb_info *sbi = ISOFS_SB(inode->i_sb);
 	char *link = kmap(page);
 	unsigned long bufsize = ISOFS_BUFFER_SIZE(inode);
 	struct buffer_head *bh;
@@ -674,12 +673,12 @@ static int rock_ridge_symlink_readpage(struct file *file, struct page *page)
 	struct rock_state rs;
 	int ret;
 
-	if (!ISOFS_SB(inode->i_sb)->s_rock)
+	if (!sbi->s_rock)
 		goto error;
 
 	init_rock_state(&rs, inode);
 	block = ei->i_iget5_block;
-	lock_kernel();
+	mutex_lock(&sbi->s_mutex);
 	bh = sb_bread(inode->i_sb, block);
 	if (!bh)
 		goto out_noread;
@@ -749,7 +748,7 @@ repeat:
 		goto fail;
 	brelse(bh);
 	*rpnt = '\0';
-	unlock_kernel();
+	mutex_unlock(&sbi->s_mutex);
 	SetPageUptodate(page);
 	kunmap(page);
 	unlock_page(page);
@@ -766,7 +765,7 @@ out_bad_span:
 	printk("symlink spans iso9660 blocks\n");
 fail:
 	brelse(bh);
-	unlock_kernel();
+	mutex_unlock(&sbi->s_mutex);
 error:
 	SetPageError(page);
 	kunmap(page);