Skip to contentSkip to conversation

szip: Add seekable zip format

PATCH New Dhaval Giani 1 participant 2 messages Jul 24, 2013 1 message not in the archive

Subsystems (3)
lore
Share & tools
lore

A message that is not in the archive (sent off-list or not yet received): [email protected]

#1 lore raw

PATCH 1/2 szip: Add seekable zip format

Add support for inflating seekable zip format. This uses zlib underneath. In order to create a seekable zip file, use the szip utility which can be obtained from

https://github.com/glandium/faulty.lib

We shall use this to implement transparent decompression on ext4. The use would be very similar to that used by the faulty.lib linker.

Cc Theodore Ts'o <[email protected]>
Cc Taras Glek <[email protected]>
Cc Vladan Djeric <[email protected]>
Cc linux-ext4 <[email protected]>
Cc linux-fsdevel <[email protected]>
Cc Mike Hommey <[email protected]>
---
 include/linux/szip.h |  32 ++++++++
 lib/Kconfig          |   8 ++
 lib/Makefile         |   1 +
 lib/szip.c           | 217 +++++++++++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 258 insertions(+)
 create mode 100644 include/linux/szip.h
 create mode 100644 lib/szip.c
include/linux/szip.h new file +32 -0
new file mode 100644
index 0000000..1d4421e
@@ -0,0 +1,32 @@
+#ifndef __SZIP_H
+#define __SZIP_H
+
+#include <linux/zlib.h>
+#include <linux/types.h>
+
+#define SZIP_HEADER_SIZE (20)
+
+struct szip_struct {
+	u32 magic;
+	u32 total_size;
+	u16 chunk_size;
+	u16 dict_size;
+	u32 nr_chunks;
+	u16 last_chunk_size;
+	signed char window_bits;
+	signed char filter;
+	unsigned *offset_table;
+	unsigned *dictionary;
+	char *buffer;
+	void *workspace;
+};
+
+extern int szip_decompress(struct szip_struct *, char *, size_t);
+extern int szip_seekable_decompress(struct szip_struct *, size_t,
+						size_t, char *, size_t);
+extern size_t szip_uncompressed_size(struct szip_struct *);
+extern int szip_init(struct szip_struct *, char *);
+extern void szip_init_offset_table(struct szip_struct *szip, char *buf);
+extern size_t szip_offset_table_size(struct szip_struct *szip);
+
+#endif
lib/Kconfig +8 -0
index fe01d41..0903693 100644
@@ -213,6 +213,14 @@ config DECOMPRESS_LZO
 	select LZO_DECOMPRESS
 	tristate
 
+config SZIP
+	select ZLIB_INFLATE
+	tristate
+	help
+	  Use this to provide szip decompression support. szip is a seekable
+	  zlib format. Check https://github.com/glandium/faulty.lib for the
+	  szip tool. This is required for transparent ext4 decompression.
+
 #
 # Generic allocator support is selected if needed
 #
lib/Makefile +1 -0
index c55a037..86a5d4b 100644
@@ -77,6 +77,7 @@ obj-$(CONFIG_LZO_COMPRESS) += lzo/
 obj-$(CONFIG_LZO_DECOMPRESS) += lzo/
 obj-$(CONFIG_XZ_DEC) += xz/
 obj-$(CONFIG_RAID6_PQ) += raid6/
+obj-${CONFIG_SZIP} += szip.o
 
 lib-$(CONFIG_DECOMPRESS_GZIP) += decompress_inflate.o
 lib-$(CONFIG_DECOMPRESS_BZIP2) += decompress_bunzip2.o
lib/szip.c new file +217 -0

217 lines not on this page · raw message

Signature · 1 line
1.8.1.4
#2 lore raw

PATCH 2/2 Add rudimentary transparent decompression support to ext4

In reply to a message not in the archive

Adds basic support for transparently reading compressed files in ext4.

Lots of issues in this patch
1. It requires a fully read file from disk, no seeking allowed
2. Compressed files give their compressed sizes and not uncompressed sizes. Therefore cat will return truncated data (since the buffer isn't big enough)
3. It adds a new file operation. That will be *removed*.
4. Doesn't mmap decompressed data

Cc Theodore Ts'o <[email protected]>
Cc Taras Glek <[email protected]>
Cc Vladan Djeric <[email protected]>
Cc linux-ext4 <[email protected]>
Cc linux-fsdevel <[email protected]>
Cc Mike Hommey <[email protected]>
---
 fs/ext4/file.c     | 66 ++++++++++++++++++++++++++++++++++++++++++++++++++++++
 fs/read_write.c    |  3 +++
 include/linux/fs.h |  1 +
 3 files changed, 70 insertions(+)
fs/ext4/file.c +66 -0
index b1b4d51..5c9db04 100644
@@ -31,6 +31,9 @@
 #include "xattr.h"
 #include "acl.h"
 
+#include <linux/zlib.h>
+#include <linux/szip.h>
+
 /*
  * Called when an inode is released. Note that this is different
  * from ext4_file_open: open gets called at every open, but release
@@ -623,6 +626,68 @@ loff_t ext4_llseek(struct file *file, loff_t offset, int whence)
 	return -EINVAL;
 }
 
+static int ext4_is_file_compressed(struct file *file)
+{
+	struct inode *inode = file->f_mapping->host;
+	return ext4_test_inode_flag(inode, EXT4_INODE_COMPR);
+}
+
+static int _ext4_decompress(char __user *buf, int sz)
+{
+	/*
+	 * We can really cheat here since we have the full buffer already read
+	 * and made available
+	 */
+	struct szip_struct szip;
+	char *temp;
+	size_t uncom_size;
+
+	int ret = szip_init(&szip, buf);
+	if (ret) {
+		ret = -1;
+		goto out;
+	}
+
+	uncom_size = szip_uncompressed_size(&szip);
+	temp = kmalloc(uncom_size, GFP_NOFS);
+	if (!temp) {
+		ret = -2;
+		goto out;
+	}
+
+	ret = szip_decompress(&szip, temp, 0);
+	if (ret) {
+		ret = -3;
+		goto out_free;
+	}
+
+	sz = min_t(int, sz, uncom_size);
+
+	memset(buf, 0, sz);
+	memcpy(buf, temp, sz);
+out_free:
+	kfree(temp);
+
+out:
+	return ret;
+
+}
+
+int ext4_decompress(struct file *file, char __user *buf, size_t len)
+{
+	int ret = 0;
+
+	if (!ext4_is_file_compressed(file))
+		return 0;
+
+	ret = _ext4_decompress(buf, len);
+	if (ret) {
+		goto out;
+	}
+out:
+	return ret;
+}
+
 const struct file_operations ext4_file_operations = {
 	.llseek		= ext4_llseek,
 	.read		= do_sync_read,
@@ -640,6 +705,7 @@ const struct file_operations ext4_file_operations = {
 	.splice_read	= generic_file_splice_read,
 	.splice_write	= generic_file_splice_write,
 	.fallocate	= ext4_fallocate,
+	.decompress	= ext4_decompress,
 };
 
 const struct inode_operations ext4_file_inode_operations = {
fs/read_write.c +3 -0
index 2cefa41..44d2523 100644
@@ -330,6 +330,7 @@ int rw_verify_area(int read_write, struct file *file, loff_t *ppos, size_t count
 	return count > MAX_RW_COUNT ? MAX_RW_COUNT : count;
 }
 
+
 ssize_t do_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos)
 {
 	struct iovec iov = { .iov_base = buf, .iov_len = len };
@@ -345,6 +346,8 @@ ssize_t do_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *pp
 	if (-EIOCBQUEUED == ret)
 		ret = wait_on_sync_kiocb(&kiocb);
 	*ppos = kiocb.ki_pos;
+	if (filp->f_op->decompress)
+		filp->f_op->decompress(filp, buf, len);
 	return ret;
 }
 
include/linux/fs.h +1 -0
index 65c2be2..ce43e82 100644
@@ -1543,6 +1543,7 @@ struct file_operations {
 	long (*fallocate)(struct file *file, int mode, loff_t offset,
 			  loff_t len);
 	int (*show_fdinfo)(struct seq_file *m, struct file *f);
+	int (*decompress)(struct file *, char *, size_t);
 };
 
 struct inode_operations {
Signature · 1 line
1.8.1.4