Merge tag 'squashfs-updates' of git://git.kernel.org/pub/scm/linux/ke…

…rnel/git/pkl/squashfs-next

Pull squashfs updates from Phillip Lougher:
 "These patches optionally improve the multi-threading peformance of
  Squashfs by adding parallel decompression, and direct decompression
  into the page cache, eliminating an intermediate buffer (removing
  memcpy overhead and lock contention)"

* tag 'squashfs-updates' of git://git.kernel.org/pub/scm/linux/kernel/git/pkl/squashfs-next:
  Squashfs: Check stream is not NULL in decompressor_multi.c
  Squashfs: Directly decompress into the page cache for file data
  Squashfs: Restructure squashfs_readpage()
  Squashfs: Generalise paging handling in the decompressors
  Squashfs: add multi-threaded decompression using percpu variable
  squashfs: Enhance parallel I/O
  Squashfs: Refactor decompressor interface and code

fs/squashfs/Kconfig

@@ -25,6 +25,78 @@ config SQUASHFS
 
 	  If unsure, say N.
 
+choice
+	prompt "File decompression options"
+	depends on SQUASHFS
+	help
+	  Squashfs now supports two options for decompressing file
+	  data.  Traditionally Squashfs has decompressed into an
+	  intermediate buffer and then memcopied it into the page cache.
+	  Squashfs now supports the ability to decompress directly into
+	  the page cache.
+
+	  If unsure, select "Decompress file data into an intermediate buffer"
+
+config SQUASHFS_FILE_CACHE
+	bool "Decompress file data into an intermediate buffer"
+	help
+	  Decompress file data into an intermediate buffer and then
+	  memcopy it into the page cache.
+
+config SQUASHFS_FILE_DIRECT
+	bool "Decompress files directly into the page cache"
+	help
+	  Directly decompress file data into the page cache.
+	  Doing so can significantly improve performance because
+	  it eliminates a memcpy and it also removes the lock contention
+	  on the single buffer.
+
+endchoice
+
+choice
+	prompt "Decompressor parallelisation options"
+	depends on SQUASHFS
+	help
+	  Squashfs now supports three parallelisation options for
+	  decompression.  Each one exhibits various trade-offs between
+	  decompression performance and CPU and memory usage.
+
+	  If in doubt, select "Single threaded compression"
+
+config SQUASHFS_DECOMP_SINGLE
+	bool "Single threaded compression"
+	help
+	  Traditionally Squashfs has used single-threaded decompression.
+	  Only one block (data or metadata) can be decompressed at any
+	  one time.  This limits CPU and memory usage to a minimum.
+
+config SQUASHFS_DECOMP_MULTI
+	bool "Use multiple decompressors for parallel I/O"
+	help
+	  By default Squashfs uses a single decompressor but it gives
+	  poor performance on parallel I/O workloads when using multiple CPU
+	  machines due to waiting on decompressor availability.
+
+	  If you have a parallel I/O workload and your system has enough memory,
+	  using this option may improve overall I/O performance.
+
+	  This decompressor implementation uses up to two parallel
+	  decompressors per core.  It dynamically allocates decompressors
+	  on a demand basis.
+
+config SQUASHFS_DECOMP_MULTI_PERCPU
+	bool "Use percpu multiple decompressors for parallel I/O"
+	help
+	  By default Squashfs uses a single decompressor but it gives
+	  poor performance on parallel I/O workloads when using multiple CPU
+	  machines due to waiting on decompressor availability.
+
+	  This decompressor implementation uses a maximum of one
+	  decompressor per core.  It uses percpu variables to ensure
+	  decompression is load-balanced across the cores.
+
+endchoice
+
 config SQUASHFS_XATTR
 	bool "Squashfs XATTR support"
 	depends on SQUASHFS

fs/squashfs/Makefile

@@ -5,6 +5,11 @@
 obj-$(CONFIG_SQUASHFS) += squashfs.o
 squashfs-y += block.o cache.o dir.o export.o file.o fragment.o id.o inode.o
 squashfs-y += namei.o super.o symlink.o decompressor.o
+squashfs-$(CONFIG_SQUASHFS_FILE_CACHE) += file_cache.o
+squashfs-$(CONFIG_SQUASHFS_FILE_DIRECT) += file_direct.o page_actor.o
+squashfs-$(CONFIG_SQUASHFS_DECOMP_SINGLE) += decompressor_single.o
+squashfs-$(CONFIG_SQUASHFS_DECOMP_MULTI) += decompressor_multi.o
+squashfs-$(CONFIG_SQUASHFS_DECOMP_MULTI_PERCPU) += decompressor_multi_percpu.o
 squashfs-$(CONFIG_SQUASHFS_XATTR) += xattr.o xattr_id.o
 squashfs-$(CONFIG_SQUASHFS_LZO) += lzo_wrapper.o
 squashfs-$(CONFIG_SQUASHFS_XZ) += xz_wrapper.o

fs/squashfs/block.c

@@ -36,6 +36,7 @@
 #include "squashfs_fs_sb.h"
 #include "squashfs.h"
 #include "decompressor.h"
+#include "page_actor.h"
 
 /*
  * Read the metadata block length, this is stored in the first two
@@ -86,16 +87,16 @@ static struct buffer_head *get_block_length(struct super_block *sb,
  * generated a larger block - this does occasionally happen with compression
  * algorithms).
  */
-int squashfs_read_data(struct super_block *sb, void **buffer, u64 index,
-			int length, u64 *next_index, int srclength, int pages)
+int squashfs_read_data(struct super_block *sb, u64 index, int length,
+		u64 *next_index, struct squashfs_page_actor *output)
 {
 	struct squashfs_sb_info *msblk = sb->s_fs_info;
 	struct buffer_head **bh;
 	int offset = index & ((1 << msblk->devblksize_log2) - 1);
 	u64 cur_index = index >> msblk->devblksize_log2;
-	int bytes, compressed, b = 0, k = 0, page = 0, avail;
+	int bytes, compressed, b = 0, k = 0, avail, i;
 
-	bh = kcalloc(((srclength + msblk->devblksize - 1)
+	bh = kcalloc(((output->length + msblk->devblksize - 1)
 		>> msblk->devblksize_log2) + 1, sizeof(*bh), GFP_KERNEL);
 	if (bh == NULL)
 		return -ENOMEM;
@@ -111,9 +112,9 @@ int squashfs_read_data(struct super_block *sb, void **buffer, u64 index,
 			*next_index = index + length;
 
 		TRACE("Block @ 0x%llx, %scompressed size %d, src size %d\n",
-			index, compressed ? "" : "un", length, srclength);
+			index, compressed ? "" : "un", length, output->length);
 
-		if (length < 0 || length > srclength ||
+		if (length < 0 || length > output->length ||
 				(index + length) > msblk->bytes_used)
 			goto read_failure;
 
@@ -145,7 +146,7 @@ int squashfs_read_data(struct super_block *sb, void **buffer, u64 index,
 		TRACE("Block @ 0x%llx, %scompressed size %d\n", index,
 				compressed ? "" : "un", length);
 
-		if (length < 0 || length > srclength ||
+		if (length < 0 || length > output->length ||
 					(index + length) > msblk->bytes_used)
 			goto block_release;
 
@@ -158,39 +159,44 @@ int squashfs_read_data(struct super_block *sb, void **buffer, u64 index,
 		ll_rw_block(READ, b - 1, bh + 1);
 	}
 
+	for (i = 0; i < b; i++) {
+		wait_on_buffer(bh[i]);
+		if (!buffer_uptodate(bh[i]))
+			goto block_release;
+	}
+
 	if (compressed) {
-		length = squashfs_decompress(msblk, buffer, bh, b, offset,
-			 length, srclength, pages);
+		length = squashfs_decompress(msblk, bh, b, offset, length,
+			output);
 		if (length < 0)
 			goto read_failure;
 	} else {
 		/*
 		 * Block is uncompressed.
 		 */
 		int in, pg_offset = 0;
+		void *data = squashfs_first_page(output);
 
 		for (bytes = length; k < b; k++) {
 			in = min(bytes, msblk->devblksize - offset);
 			bytes -= in;
-			wait_on_buffer(bh[k]);
-			if (!buffer_uptodate(bh[k]))
-				goto block_release;
 			while (in) {
 				if (pg_offset == PAGE_CACHE_SIZE) {
-					page++;
+					data = squashfs_next_page(output);
 					pg_offset = 0;
 				}
 				avail = min_t(int, in, PAGE_CACHE_SIZE -
 						pg_offset);
-				memcpy(buffer[page] + pg_offset,
-						bh[k]->b_data + offset, avail);
+				memcpy(data + pg_offset, bh[k]->b_data + offset,
+						avail);
 				in -= avail;
 				pg_offset += avail;
 				offset += avail;
 			}
 			offset = 0;
 			put_bh(bh[k]);
 		}
+		squashfs_finish_page(output);
 	}
 
 	kfree(bh);

fs/squashfs/cache.c

@@ -56,6 +56,7 @@
 #include "squashfs_fs.h"
 #include "squashfs_fs_sb.h"
 #include "squashfs.h"
+#include "page_actor.h"
 
 /*
  * Look-up block in cache, and increment usage count.  If not in cache, read
@@ -119,9 +120,8 @@ struct squashfs_cache_entry *squashfs_cache_get(struct super_block *sb,
 			entry->error = 0;
 			spin_unlock(&cache->lock);
 
-			entry->length = squashfs_read_data(sb, entry->data,
-				block, length, &entry->next_index,
-				cache->block_size, cache->pages);
+			entry->length = squashfs_read_data(sb, block, length,
+				&entry->next_index, entry->actor);
 
 			spin_lock(&cache->lock);
 
@@ -220,6 +220,7 @@ void squashfs_cache_delete(struct squashfs_cache *cache)
 				kfree(cache->entry[i].data[j]);
 			kfree(cache->entry[i].data);
 		}
+		kfree(cache->entry[i].actor);
 	}
 
 	kfree(cache->entry);
@@ -280,6 +281,13 @@ struct squashfs_cache *squashfs_cache_init(char *name, int entries,
 				goto cleanup;
 			}
 		}
+
+		entry->actor = squashfs_page_actor_init(entry->data,
+						cache->pages, 0);
+		if (entry->actor == NULL) {
+			ERROR("Failed to allocate %s cache entry\n", name);
+			goto cleanup;
+		}
 	}
 
 	return cache;
@@ -410,6 +418,7 @@ void *squashfs_read_table(struct super_block *sb, u64 block, int length)
 	int pages = (length + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
 	int i, res;
 	void *table, *buffer, **data;
+	struct squashfs_page_actor *actor;
 
 	table = buffer = kmalloc(length, GFP_KERNEL);
 	if (table == NULL)
@@ -421,19 +430,28 @@ void *squashfs_read_table(struct super_block *sb, u64 block, int length)
 		goto failed;
 	}
 
+	actor = squashfs_page_actor_init(data, pages, length);
+	if (actor == NULL) {
+		res = -ENOMEM;
+		goto failed2;
+	}
+
 	for (i = 0; i < pages; i++, buffer += PAGE_CACHE_SIZE)
 		data[i] = buffer;
 
-	res = squashfs_read_data(sb, data, block, length |
-		SQUASHFS_COMPRESSED_BIT_BLOCK, NULL, length, pages);
+	res = squashfs_read_data(sb, block, length |
+		SQUASHFS_COMPRESSED_BIT_BLOCK, NULL, actor);
 
 	kfree(data);
+	kfree(actor);
 
 	if (res < 0)
 		goto failed;
 
 	return table;
 
+failed2:
+	kfree(data);
 failed:
 	kfree(table);
 	return ERR_PTR(res);

fs/squashfs/decompressor.c

@@ -30,36 +30,37 @@
 #include "squashfs_fs_sb.h"
 #include "decompressor.h"
 #include "squashfs.h"
+#include "page_actor.h"
 
 /*
  * This file (and decompressor.h) implements a decompressor framework for
  * Squashfs, allowing multiple decompressors to be easily supported
  */
 
 static const struct squashfs_decompressor squashfs_lzma_unsupported_comp_ops = {
-	NULL, NULL, NULL, LZMA_COMPRESSION, "lzma", 0
+	NULL, NULL, NULL, NULL, LZMA_COMPRESSION, "lzma", 0
 };
 
 #ifndef CONFIG_SQUASHFS_LZO
 static const struct squashfs_decompressor squashfs_lzo_comp_ops = {
-	NULL, NULL, NULL, LZO_COMPRESSION, "lzo", 0
+	NULL, NULL, NULL, NULL, LZO_COMPRESSION, "lzo", 0
 };
 #endif
 
 #ifndef CONFIG_SQUASHFS_XZ
 static const struct squashfs_decompressor squashfs_xz_comp_ops = {
-	NULL, NULL, NULL, XZ_COMPRESSION, "xz", 0
+	NULL, NULL, NULL, NULL, XZ_COMPRESSION, "xz", 0
 };
 #endif
 
 #ifndef CONFIG_SQUASHFS_ZLIB
 static const struct squashfs_decompressor squashfs_zlib_comp_ops = {
-	NULL, NULL, NULL, ZLIB_COMPRESSION, "zlib", 0
+	NULL, NULL, NULL, NULL, ZLIB_COMPRESSION, "zlib", 0
 };
 #endif
 
 static const struct squashfs_decompressor squashfs_unknown_comp_ops = {
-	NULL, NULL, NULL, 0, "unknown", 0
+	NULL, NULL, NULL, NULL, 0, "unknown", 0
 };
 
 static const struct squashfs_decompressor *decompressor[] = {
@@ -83,34 +84,58 @@ const struct squashfs_decompressor *squashfs_lookup_decompressor(int id)
 }
 
 
-void *squashfs_decompressor_init(struct super_block *sb, unsigned short flags)
+static void *get_comp_opts(struct super_block *sb, unsigned short flags)
 {
 	struct squashfs_sb_info *msblk = sb->s_fs_info;
-	void *strm, *buffer = NULL;
+	void *buffer = NULL, *comp_opts;
+	struct squashfs_page_actor *actor = NULL;
 	int length = 0;
 
 	/*
 	 * Read decompressor specific options from file system if present
 	 */
 	if (SQUASHFS_COMP_OPTS(flags)) {
 		buffer = kmalloc(PAGE_CACHE_SIZE, GFP_KERNEL);
-		if (buffer == NULL)
-			return ERR_PTR(-ENOMEM);
+		if (buffer == NULL) {
+			comp_opts = ERR_PTR(-ENOMEM);
+			goto out;
+		}
+
+		actor = squashfs_page_actor_init(&buffer, 1, 0);
+		if (actor == NULL) {
+			comp_opts = ERR_PTR(-ENOMEM);
+			goto out;
+		}
 
-		length = squashfs_read_data(sb, &buffer,
-			sizeof(struct squashfs_super_block), 0, NULL,
-			PAGE_CACHE_SIZE, 1);
+		length = squashfs_read_data(sb,
+			sizeof(struct squashfs_super_block), 0, NULL, actor);
 
 		if (length < 0) {
-			strm = ERR_PTR(length);
-			goto finished;
+			comp_opts = ERR_PTR(length);
+			goto out;
 		}
 	}
 
-	strm = msblk->decompressor->init(msblk, buffer, length);
+	comp_opts = squashfs_comp_opts(msblk, buffer, length);
 
-finished:
+out:
+	kfree(actor);
 	kfree(buffer);
+	return comp_opts;
+}
+
+
+void *squashfs_decompressor_setup(struct super_block *sb, unsigned short flags)
+{
+	struct squashfs_sb_info *msblk = sb->s_fs_info;
+	void *stream, *comp_opts = get_comp_opts(sb, flags);
+
+	if (IS_ERR(comp_opts))
+		return comp_opts;
+
+	stream = squashfs_decompressor_create(msblk, comp_opts);
+	if (IS_ERR(stream))
+		kfree(comp_opts);
 
-	return strm;
+	return stream;
 }