* [PATCH 3/4] crypto: Change LZ4 modules to work with new LZ4 module version
From: Sven Schmidt @ 2017-01-21 15:09 UTC (permalink / raw)
To: akpm
Cc: bongkyu.kim, rsalvaterra, sergey.senozhatsky, gregkh,
linux-kernel, herbert, davem, linux-crypto, anton, ccross,
keescook, tony.luck, phillip, Sven Schmidt
In-Reply-To: <1485011351-7463-1-git-send-email-4sschmid@informatik.uni-hamburg.de>
This patch updates the crypto modules using LZ4 compression
to work with the new LZ4 module version.
Signed-off-by: Sven Schmidt <4sschmid@informatik.uni-hamburg.de>
---
crypto/lz4.c | 21 ++++++++-------------
crypto/lz4hc.c | 21 ++++++++-------------
2 files changed, 16 insertions(+), 26 deletions(-)
diff --git a/crypto/lz4.c b/crypto/lz4.c
index 99c1b2c..40fd2c2 100644
--- a/crypto/lz4.c
+++ b/crypto/lz4.c
@@ -66,15 +66,13 @@ static void lz4_exit(struct crypto_tfm *tfm)
static int __lz4_compress_crypto(const u8 *src, unsigned int slen,
u8 *dst, unsigned int *dlen, void *ctx)
{
- size_t tmp_len = *dlen;
- int err;
+ int out_len = LZ4_compress_default(src, dst,
+ slen, (int)((size_t)dlen), ctx);
- err = lz4_compress(src, slen, dst, &tmp_len, ctx);
-
- if (err < 0)
+ if (!out_len)
return -EINVAL;
- *dlen = tmp_len;
+ *dlen = out_len;
return 0;
}
@@ -96,16 +94,13 @@ static int lz4_compress_crypto(struct crypto_tfm *tfm, const u8 *src,
static int __lz4_decompress_crypto(const u8 *src, unsigned int slen,
u8 *dst, unsigned int *dlen, void *ctx)
{
- int err;
- size_t tmp_len = *dlen;
- size_t __slen = slen;
+ int out_len = LZ4_decompress_safe(src, dst, slen, (int)((size_t)dlen));
- err = lz4_decompress_unknownoutputsize(src, __slen, dst, &tmp_len);
- if (err < 0)
+ if (out_len < 0)
return -EINVAL;
- *dlen = tmp_len;
- return err;
+ *dlen = out_len;
+ return out_len;
}
static int lz4_sdecompress(struct crypto_scomp *tfm, const u8 *src,
diff --git a/crypto/lz4hc.c b/crypto/lz4hc.c
index 75ffc4a..6f16f96 100644
--- a/crypto/lz4hc.c
+++ b/crypto/lz4hc.c
@@ -65,15 +65,13 @@ static void lz4hc_exit(struct crypto_tfm *tfm)
static int __lz4hc_compress_crypto(const u8 *src, unsigned int slen,
u8 *dst, unsigned int *dlen, void *ctx)
{
- size_t tmp_len = *dlen;
- int err;
+ int out_len = LZ4_compress_HC(src, dst, slen,
+ (int)((size_t)dlen), LZ4HC_DEFAULT_CLEVEL, ctx);
- err = lz4hc_compress(src, slen, dst, &tmp_len, ctx);
-
- if (err < 0)
+ if (out_len == 0)
return -EINVAL;
- *dlen = tmp_len;
+ *dlen = out_len;
return 0;
}
@@ -97,16 +95,13 @@ static int lz4hc_compress_crypto(struct crypto_tfm *tfm, const u8 *src,
static int __lz4hc_decompress_crypto(const u8 *src, unsigned int slen,
u8 *dst, unsigned int *dlen, void *ctx)
{
- int err;
- size_t tmp_len = *dlen;
- size_t __slen = slen;
+ int out_len = LZ4_decompress_safe(src, dst, slen, (int)((size_t)dlen));
- err = lz4_decompress_unknownoutputsize(src, __slen, dst, &tmp_len);
- if (err < 0)
+ if (out_len < 0)
return -EINVAL;
- *dlen = tmp_len;
- return err;
+ *dlen = out_len;
+ return out_len;
}
static int lz4hc_sdecompress(struct crypto_scomp *tfm, const u8 *src,
--
2.1.4
^ permalink raw reply related
* [PATCH 4/4] fs/pstore: fs/squashfs: Change usage of LZ4 to work with new LZ4 version
From: Sven Schmidt @ 2017-01-21 15:09 UTC (permalink / raw)
To: akpm
Cc: bongkyu.kim, rsalvaterra, sergey.senozhatsky, gregkh,
linux-kernel, herbert, davem, linux-crypto, anton, ccross,
keescook, tony.luck, phillip, Sven Schmidt
In-Reply-To: <1485011351-7463-1-git-send-email-4sschmid@informatik.uni-hamburg.de>
This patch updates fs/pstore and fs/squashfs to use the updated
functions from the new LZ4 module.
Signed-off-by: Sven Schmidt <4sschmid@informatik.uni-hamburg.de>
---
fs/pstore/platform.c | 14 +++++++-------
fs/squashfs/lz4_wrapper.c | 12 ++++++------
2 files changed, 13 insertions(+), 13 deletions(-)
diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c
index 729677e..85c4c58 100644
--- a/fs/pstore/platform.c
+++ b/fs/pstore/platform.c
@@ -342,31 +342,31 @@ static int compress_lz4(const void *in, void *out, size_t inlen, size_t outlen)
{
int ret;
- ret = lz4_compress(in, inlen, out, &outlen, workspace);
- if (ret) {
+ ret = LZ4_compress_default(in, out, inlen, outlen, workspace);
+ if (!ret) {
pr_err("lz4_compress error, ret = %d!\n", ret);
return -EIO;
}
- return outlen;
+ return ret;
}
static int decompress_lz4(void *in, void *out, size_t inlen, size_t outlen)
{
int ret;
- ret = lz4_decompress_unknownoutputsize(in, inlen, out, &outlen);
- if (ret) {
+ ret = LZ4_decompress_safe(in, out, inlen, outlen);
+ if (ret < 0) {
pr_err("lz4_decompress error, ret = %d!\n", ret);
return -EIO;
}
- return outlen;
+ return ret;
}
static void allocate_lz4(void)
{
- big_oops_buf_sz = lz4_compressbound(psinfo->bufsize);
+ big_oops_buf_sz = LZ4_compressBound(psinfo->bufsize);
big_oops_buf = kmalloc(big_oops_buf_sz, GFP_KERNEL);
if (big_oops_buf) {
workspace = kmalloc(LZ4_MEM_COMPRESS, GFP_KERNEL);
diff --git a/fs/squashfs/lz4_wrapper.c b/fs/squashfs/lz4_wrapper.c
index ff4468b..95da653 100644
--- a/fs/squashfs/lz4_wrapper.c
+++ b/fs/squashfs/lz4_wrapper.c
@@ -97,7 +97,6 @@ static int lz4_uncompress(struct squashfs_sb_info *msblk, void *strm,
struct squashfs_lz4 *stream = strm;
void *buff = stream->input, *data;
int avail, i, bytes = length, res;
- size_t dest_len = output->length;
for (i = 0; i < b; i++) {
avail = min(bytes, msblk->devblksize - offset);
@@ -108,12 +107,13 @@ static int lz4_uncompress(struct squashfs_sb_info *msblk, void *strm,
put_bh(bh[i]);
}
- res = lz4_decompress_unknownoutputsize(stream->input, length,
- stream->output, &dest_len);
- if (res)
+ res = LZ4_decompress_safe(stream->input, stream->output,
+ length, output->length);
+
+ if (res < 0)
return -EIO;
- bytes = dest_len;
+ bytes = res;
data = squashfs_first_page(output);
buff = stream->output;
while (data) {
@@ -128,7 +128,7 @@ static int lz4_uncompress(struct squashfs_sb_info *msblk, void *strm,
}
squashfs_finish_page(output);
- return dest_len;
+ return res;
}
const struct squashfs_decompressor squashfs_lz4_comp_ops = {
--
2.1.4
^ permalink raw reply related
* Re: [PATCH 1/4] lib: Update LZ4 compressor module
From: kbuild test robot @ 2017-01-21 15:56 UTC (permalink / raw)
To: Sven Schmidt
Cc: kbuild-all, akpm, bongkyu.kim, rsalvaterra, sergey.senozhatsky,
gregkh, linux-kernel, herbert, davem, linux-crypto, anton, ccross,
keescook, tony.luck, phillip, Sven Schmidt
In-Reply-To: <1485011351-7463-2-git-send-email-4sschmid@informatik.uni-hamburg.de>
[-- Attachment #1: Type: text/plain, Size: 2113 bytes --]
Hi Sven,
[auto build test ERROR on linus/master]
[also build test ERROR on v4.10-rc4 next-20170120]
[if your patch is applied to the wrong git tree, please drop us a note to help improve the system]
url: https://github.com/0day-ci/linux/commits/Sven-Schmidt/Update-LZ4-compressor-module/20170121-231418
config: i386-randconfig-r0-201703 (attached as .config)
compiler: gcc-5 (Debian 5.4.1-2) 5.4.1 20160904
reproduce:
# save the attached .config to linux build tree
make ARCH=i386
Note: the linux-review/Sven-Schmidt/Update-LZ4-compressor-module/20170121-231418 HEAD 0472409e2a1c442b51502961aa6d83b866218953 builds fine.
It only hurts bisectibility.
All errors (new ones prefixed by >>):
fs/pstore/platform.c: In function 'allocate_lz4':
>> fs/pstore/platform.c:369:20: error: implicit declaration of function 'lz4_compressbound' [-Werror=implicit-function-declaration]
big_oops_buf_sz = lz4_compressbound(psinfo->bufsize);
^
cc1: some warnings being treated as errors
vim +/lz4_compressbound +369 fs/pstore/platform.c
8cfc8ddc Geliang Tang 2016-02-18 363
8cfc8ddc Geliang Tang 2016-02-18 364 return outlen;
8cfc8ddc Geliang Tang 2016-02-18 365 }
8cfc8ddc Geliang Tang 2016-02-18 366
8cfc8ddc Geliang Tang 2016-02-18 367 static void allocate_lz4(void)
8cfc8ddc Geliang Tang 2016-02-18 368 {
8cfc8ddc Geliang Tang 2016-02-18 @369 big_oops_buf_sz = lz4_compressbound(psinfo->bufsize);
8cfc8ddc Geliang Tang 2016-02-18 370 big_oops_buf = kmalloc(big_oops_buf_sz, GFP_KERNEL);
8cfc8ddc Geliang Tang 2016-02-18 371 if (big_oops_buf) {
8cfc8ddc Geliang Tang 2016-02-18 372 workspace = kmalloc(LZ4_MEM_COMPRESS, GFP_KERNEL);
:::::: The code at line 369 was first introduced by commit
:::::: 8cfc8ddc99df9509a46043b14af81f5c6a223eab pstore: add lzo/lz4 compression support
:::::: TO: Geliang Tang <geliangtang@163.com>
:::::: CC: Kees Cook <keescook@chromium.org>
---
0-DAY kernel test infrastructure Open Source Technology Center
https://lists.01.org/pipermail/kbuild-all Intel Corporation
[-- Attachment #2: .config.gz --]
[-- Type: application/gzip, Size: 24765 bytes --]
^ permalink raw reply
* Re: [PATCH 1/4] lib: Update LZ4 compressor module
From: kbuild test robot @ 2017-01-21 16:16 UTC (permalink / raw)
To: Sven Schmidt
Cc: kbuild-all, akpm, bongkyu.kim, rsalvaterra, sergey.senozhatsky,
gregkh, linux-kernel, herbert, davem, linux-crypto, anton, ccross,
keescook, tony.luck, phillip, Sven Schmidt
In-Reply-To: <1485011351-7463-2-git-send-email-4sschmid@informatik.uni-hamburg.de>
[-- Attachment #1: Type: text/plain, Size: 5885 bytes --]
Hi Sven,
[auto build test ERROR on linus/master]
[also build test ERROR on v4.10-rc4 next-20170120]
[if your patch is applied to the wrong git tree, please drop us a note to help improve the system]
url: https://github.com/0day-ci/linux/commits/Sven-Schmidt/Update-LZ4-compressor-module/20170121-231418
config: x86_64-lkp (attached as .config)
compiler: gcc-6 (Debian 6.2.0-3) 6.2.0 20160901
reproduce:
# save the attached .config to linux build tree
make ARCH=x86_64
Note: the linux-review/Sven-Schmidt/Update-LZ4-compressor-module/20170121-231418 HEAD 0472409e2a1c442b51502961aa6d83b866218953 builds fine.
It only hurts bisectibility.
All errors (new ones prefixed by >>):
In file included from lib/decompress_unlz4.c:19:0:
lib/decompress_unlz4.c: In function 'unlz4':
>> lib/decompress_unlz4.c:75:22: error: implicit declaration of function 'lz4_compressbound' [-Werror=implicit-function-declaration]
inp = large_malloc(lz4_compressbound(uncomp_chunksize));
^
include/linux/decompress/mm.h:83:33: note: in definition of macro 'large_malloc'
#define large_malloc(a) vmalloc(a)
^
cc1: some warnings being treated as errors
vim +/lz4_compressbound +75 lib/decompress_unlz4.c
e76e1fdf Kyungsik Lee 2013-07-08 13 #include "lz4/lz4_decompress.c"
e76e1fdf Kyungsik Lee 2013-07-08 14 #else
e76e1fdf Kyungsik Lee 2013-07-08 15 #include <linux/decompress/unlz4.h>
e76e1fdf Kyungsik Lee 2013-07-08 16 #endif
e76e1fdf Kyungsik Lee 2013-07-08 17 #include <linux/types.h>
e76e1fdf Kyungsik Lee 2013-07-08 18 #include <linux/lz4.h>
e76e1fdf Kyungsik Lee 2013-07-08 @19 #include <linux/decompress/mm.h>
e76e1fdf Kyungsik Lee 2013-07-08 20 #include <linux/compiler.h>
e76e1fdf Kyungsik Lee 2013-07-08 21
e76e1fdf Kyungsik Lee 2013-07-08 22 #include <asm/unaligned.h>
e76e1fdf Kyungsik Lee 2013-07-08 23
e76e1fdf Kyungsik Lee 2013-07-08 24 /*
e76e1fdf Kyungsik Lee 2013-07-08 25 * Note: Uncompressed chunk size is used in the compressor side
e76e1fdf Kyungsik Lee 2013-07-08 26 * (userspace side for compression).
e76e1fdf Kyungsik Lee 2013-07-08 27 * It is hardcoded because there is not proper way to extract it
e76e1fdf Kyungsik Lee 2013-07-08 28 * from the binary stream which is generated by the preliminary
e76e1fdf Kyungsik Lee 2013-07-08 29 * version of LZ4 tool so far.
e76e1fdf Kyungsik Lee 2013-07-08 30 */
e76e1fdf Kyungsik Lee 2013-07-08 31 #define LZ4_DEFAULT_UNCOMPRESSED_CHUNK_SIZE (8 << 20)
e76e1fdf Kyungsik Lee 2013-07-08 32 #define ARCHIVE_MAGICNUMBER 0x184C2102
e76e1fdf Kyungsik Lee 2013-07-08 33
d97b07c5 Yinghai Lu 2014-08-08 34 STATIC inline int INIT unlz4(u8 *input, long in_len,
d97b07c5 Yinghai Lu 2014-08-08 35 long (*fill)(void *, unsigned long),
d97b07c5 Yinghai Lu 2014-08-08 36 long (*flush)(void *, unsigned long),
d97b07c5 Yinghai Lu 2014-08-08 37 u8 *output, long *posp,
e76e1fdf Kyungsik Lee 2013-07-08 38 void (*error) (char *x))
e76e1fdf Kyungsik Lee 2013-07-08 39 {
e76e1fdf Kyungsik Lee 2013-07-08 40 int ret = -1;
e76e1fdf Kyungsik Lee 2013-07-08 41 size_t chunksize = 0;
e76e1fdf Kyungsik Lee 2013-07-08 42 size_t uncomp_chunksize = LZ4_DEFAULT_UNCOMPRESSED_CHUNK_SIZE;
e76e1fdf Kyungsik Lee 2013-07-08 43 u8 *inp;
e76e1fdf Kyungsik Lee 2013-07-08 44 u8 *inp_start;
e76e1fdf Kyungsik Lee 2013-07-08 45 u8 *outp;
d97b07c5 Yinghai Lu 2014-08-08 46 long size = in_len;
e76e1fdf Kyungsik Lee 2013-07-08 47 #ifdef PREBOOT
e76e1fdf Kyungsik Lee 2013-07-08 48 size_t out_len = get_unaligned_le32(input + in_len);
e76e1fdf Kyungsik Lee 2013-07-08 49 #endif
e76e1fdf Kyungsik Lee 2013-07-08 50 size_t dest_len;
e76e1fdf Kyungsik Lee 2013-07-08 51
e76e1fdf Kyungsik Lee 2013-07-08 52
e76e1fdf Kyungsik Lee 2013-07-08 53 if (output) {
e76e1fdf Kyungsik Lee 2013-07-08 54 outp = output;
e76e1fdf Kyungsik Lee 2013-07-08 55 } else if (!flush) {
e76e1fdf Kyungsik Lee 2013-07-08 56 error("NULL output pointer and no flush function provided");
e76e1fdf Kyungsik Lee 2013-07-08 57 goto exit_0;
e76e1fdf Kyungsik Lee 2013-07-08 58 } else {
e76e1fdf Kyungsik Lee 2013-07-08 59 outp = large_malloc(uncomp_chunksize);
e76e1fdf Kyungsik Lee 2013-07-08 60 if (!outp) {
e76e1fdf Kyungsik Lee 2013-07-08 61 error("Could not allocate output buffer");
e76e1fdf Kyungsik Lee 2013-07-08 62 goto exit_0;
e76e1fdf Kyungsik Lee 2013-07-08 63 }
e76e1fdf Kyungsik Lee 2013-07-08 64 }
e76e1fdf Kyungsik Lee 2013-07-08 65
e76e1fdf Kyungsik Lee 2013-07-08 66 if (input && fill) {
e76e1fdf Kyungsik Lee 2013-07-08 67 error("Both input pointer and fill function provided,");
e76e1fdf Kyungsik Lee 2013-07-08 68 goto exit_1;
e76e1fdf Kyungsik Lee 2013-07-08 69 } else if (input) {
e76e1fdf Kyungsik Lee 2013-07-08 70 inp = input;
e76e1fdf Kyungsik Lee 2013-07-08 71 } else if (!fill) {
e76e1fdf Kyungsik Lee 2013-07-08 72 error("NULL input pointer and missing fill function");
e76e1fdf Kyungsik Lee 2013-07-08 73 goto exit_1;
e76e1fdf Kyungsik Lee 2013-07-08 74 } else {
e76e1fdf Kyungsik Lee 2013-07-08 @75 inp = large_malloc(lz4_compressbound(uncomp_chunksize));
e76e1fdf Kyungsik Lee 2013-07-08 76 if (!inp) {
e76e1fdf Kyungsik Lee 2013-07-08 77 error("Could not allocate input buffer");
e76e1fdf Kyungsik Lee 2013-07-08 78 goto exit_1;
:::::: The code at line 75 was first introduced by commit
:::::: e76e1fdfa8f8dc1ea6699923cf5d92b5bee9c936 lib: add support for LZ4-compressed kernel
:::::: TO: Kyungsik Lee <kyungsik.lee@lge.com>
:::::: CC: Linus Torvalds <torvalds@linux-foundation.org>
---
0-DAY kernel test infrastructure Open Source Technology Center
https://lists.01.org/pipermail/kbuild-all Intel Corporation
[-- Attachment #2: .config.gz --]
[-- Type: application/gzip, Size: 24663 bytes --]
^ permalink raw reply
* Re: [PATCH 1/4] lib: Update LZ4 compressor module
From: kbuild test robot @ 2017-01-21 17:38 UTC (permalink / raw)
To: Sven Schmidt
Cc: kbuild-all, akpm, bongkyu.kim, rsalvaterra, sergey.senozhatsky,
gregkh, linux-kernel, herbert, davem, linux-crypto, anton, ccross,
keescook, tony.luck, phillip, Sven Schmidt
In-Reply-To: <1485011351-7463-2-git-send-email-4sschmid@informatik.uni-hamburg.de>
Hi Sven,
[auto build test WARNING on linus/master]
[also build test WARNING on v4.10-rc4 next-20170120]
[if your patch is applied to the wrong git tree, please drop us a note to help improve the system]
url: https://github.com/0day-ci/linux/commits/Sven-Schmidt/Update-LZ4-compressor-module/20170121-231418
reproduce:
# apt-get install sparse
make ARCH=x86_64 allmodconfig
make C=1 CF=-D__CHECK_ENDIAN__
sparse warnings: (new ones prefixed by >>)
include/linux/compiler.h:253:8: sparse: attribute 'no_sanitize_address': unknown attribute
>> lib/lz4/lz4_decompress.c:521:21: sparse: incompatible types for operation (>)
lib/lz4/lz4_decompress.c:521:21: left side has type unsigned long [usertype] *src_len
lib/lz4/lz4_decompress.c:521:21: right side has type int
vim +521 lib/lz4/lz4_decompress.c
505 return -1;
506 }
507 EXPORT_SYMBOL(lz4_decompress_unknownoutputsize);
508
509 int lz4_decompress(const unsigned char *src, size_t *src_len,
510 unsigned char *dest, size_t actual_dest_len) {
511 *src_len = LZ4_decompress_fast(src, dest, (int)actual_dest_len);
512
513 /*
514 * Prior lz4_decompress will return
515 * 0 for success and a negative result for error
516 * new LZ4_decompress_fast returns
517 * - the length of data read on success
518 * - and also a negative result on error
519 * meaning when result > 0, we just return 0 here
520 */
> 521 if (src_len > 0)
522 return 0;
523 else
524 return -1;
525 }
526 EXPORT_SYMBOL(lz4_decompress);
527
528 MODULE_LICENSE("Dual BSD/GPL");
529 MODULE_DESCRIPTION("LZ4 decompressor");
---
0-DAY kernel test infrastructure Open Source Technology Center
https://lists.01.org/pipermail/kbuild-all Intel Corporation
^ permalink raw reply
* Re: [PATCH 1/4] lib: Update LZ4 compressor module
From: Greg KH @ 2017-01-22 11:05 UTC (permalink / raw)
To: Sven Schmidt
Cc: akpm, bongkyu.kim, rsalvaterra, sergey.senozhatsky, linux-kernel,
herbert, davem, linux-crypto, anton, ccross, keescook, tony.luck,
phillip
In-Reply-To: <1485011351-7463-2-git-send-email-4sschmid@informatik.uni-hamburg.de>
On Sat, Jan 21, 2017 at 04:09:08PM +0100, Sven Schmidt wrote:
> This patch updates LZ4 kernel module to LZ4 v1.7.3 by Yann Collet.
> The kernel module is inspired by the previous work by Chanho Min.
> The updated LZ4 module will not break existing code since there were alias
> methods added to ensure backwards compatibility.
>
> API changes:
>
> New method LZ4_compress_fast which differs from the variant available
> in kernel by the new acceleration parameter,
> allowing to trade compression ratio for more compression speed
> and vice versa.
>
> LZ4_decompress_fast is the respective decompression method, featuring a very
> fast decoder (multiple GB/s per core), able to reach RAM speed in multi-core
> systems. The decompressor allows to decompress data compressed with
> LZ4 fast as well as the LZ4 HC (high compression) algorithm.
>
> Also the useful functions LZ4_decompress_safe_partial
> LZ4_compress_destsize were added. The latter reverses the logic by trying to
> compress as much data as possible from source to dest while the former aims
> to decompress partial blocks of data.
>
> A bunch of streaming functions were also added
> which allow compressig/decompressing data in multiple steps
> (so called "streaming mode").
>
> The methods lz4_compress and lz4_decompress_unknownoutputsize
> are now known as LZ4_compress_default respectivley LZ4_decompress_safe.
> The old methods are still available for providing backwards compatibility.
>
> Signed-off-by: Sven Schmidt <4sschmid@informatik.uni-hamburg.de>
Please fix up so that it doesn't break the build as reported by the
kbuild tool...
thanks,
greg k-h
^ permalink raw reply
* [PATCH v4 1/4] lib: Update LZ4 compressor module
From: Sven Schmidt @ 2017-01-22 19:35 UTC (permalink / raw)
To: akpm
Cc: bongkyu.kim, rsalvaterra, sergey.senozhatsky, gregkh,
linux-kernel, herbert, davem, linux-crypto, anton, ccross,
keescook, tony.luck, phillip, Sven Schmidt
In-Reply-To: <1485113717-29261-1-git-send-email-4sschmid@informatik.uni-hamburg.de>
This patch updates LZ4 kernel module to LZ4 v1.7.3 by Yann Collet.
The kernel module is inspired by the previous work by Chanho Min.
The updated LZ4 module will not break existing code since there were alias
methods added to ensure backwards compatibility.
API changes:
New method LZ4_compress_fast which differs from the variant available
in kernel by the new acceleration parameter,
allowing to trade compression ratio for more compression speed
and vice versa.
LZ4_decompress_fast is the respective decompression method, featuring a very
fast decoder (multiple GB/s per core), able to reach RAM speed in multi-core
systems. The decompressor allows to decompress data compressed with
LZ4 fast as well as the LZ4 HC (high compression) algorithm.
Also the useful functions LZ4_decompress_safe_partial
LZ4_compress_destsize were added. The latter reverses the logic by trying to
compress as much data as possible from source to dest while the former aims
to decompress partial blocks of data.
A bunch of streaming functions were also added
which allow compressig/decompressing data in multiple steps
(so called "streaming mode").
The methods lz4_compress and lz4_decompress_unknownoutputsize
are now known as LZ4_compress_default respectivley LZ4_decompress_safe.
The old methods are still available for providing backwards compatibility.
Signed-off-by: Sven Schmidt <4sschmid@informatik.uni-hamburg.de>
---
include/linux/lz4.h | 589 ++++++++++++++++++++++---
lib/lz4/lz4_compress.c | 1103 ++++++++++++++++++++++++++++++++--------------
lib/lz4/lz4_decompress.c | 694 ++++++++++++++++++-----------
lib/lz4/lz4defs.h | 320 ++++++++------
lib/lz4/lz4hc_compress.c | 855 ++++++++++++++++++++++-------------
5 files changed, 2486 insertions(+), 1075 deletions(-)
diff --git a/include/linux/lz4.h b/include/linux/lz4.h
index 6b784c5..2072255 100644
--- a/include/linux/lz4.h
+++ b/include/linux/lz4.h
@@ -1,87 +1,554 @@
-#ifndef __LZ4_H__
-#define __LZ4_H__
-/*
- * LZ4 Kernel Interface
+/* LZ4 Kernel Interface
*
* Copyright (C) 2013, LG Electronics, Kyungsik Lee <kyungsik.lee@lge.com>
+ * Copyright (C) 2016, Sven Schmidt <4sschmid@informatik.uni-hamburg.de>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
+ *
+ * This file is based on the original header file
+ * for LZ4 - Fast LZ compression algorithm.
+ *
+ * LZ4 - Fast LZ compression algorithm
+ * Copyright (C) 2011-2016, Yann Collet.
+ * BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are
+ * met:
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above
+ * copyright notice, this list of conditions and the following disclaimer
+ * in the documentation and/or other materials provided with the
+ * distribution.
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ * You can contact the author at :
+ * - LZ4 homepage : http://www.lz4.org
+ * - LZ4 source repository : https://github.com/lz4/lz4
+ */
+
+#ifndef __LZ4_H__
+#define __LZ4_H__
+
+#include <linux/types.h>
+#include <linux/string.h> /* memset, memcpy */
+
+/*-************************************************************************
+ * CONSTANTS
+ **************************************************************************/
+/*
+ * LZ4_MEMORY_USAGE :
+ * Memory usage formula : N->2^N Bytes
+ * (examples : 10 -> 1KB; 12 -> 4KB ; 16 -> 64KB; 20 -> 1MB; etc.)
+ * Increasing memory usage improves compression ratio
+ * Reduced memory usage can improve speed, due to cache effect
+ * Default value is 14, for 16KB, which nicely fits into Intel x86 L1 cache
+ */
+#define LZ4_MEMORY_USAGE 10
+
+#define LZ4_MAX_INPUT_SIZE 0x7E000000 /* 2 113 929 216 bytes */
+#define LZ4_COMPRESSBOUND(isize) (\
+ (unsigned int)(isize) > (unsigned int)LZ4_MAX_INPUT_SIZE \
+ ? 0 \
+ : (isize) + ((isize)/255) + 16)
+
+#define LZ4_ACCELERATION_DEFAULT 1
+#define LZ4_HASHLOG (LZ4_MEMORY_USAGE-2)
+#define LZ4_HASHTABLESIZE (1 << LZ4_MEMORY_USAGE)
+#define LZ4_HASH_SIZE_U32 (1 << LZ4_HASHLOG)
+
+#define LZ4HC_MIN_CLEVEL 3
+#define LZ4HC_DEFAULT_CLEVEL 9
+#define LZ4HC_MAX_CLEVEL 16
+
+#define LZ4HC_DICTIONARY_LOGSIZE 16
+#define LZ4HC_MAXD (1<<LZ4HC_DICTIONARY_LOGSIZE)
+#define LZ4HC_MAXD_MASK (LZ4HC_MAXD - 1)
+#define LZ4HC_HASH_LOG (LZ4HC_DICTIONARY_LOGSIZE-1)
+#define LZ4HC_HASHTABLESIZE (1 << LZ4HC_HASH_LOG)
+#define LZ4HC_HASH_MASK (LZ4HC_HASHTABLESIZE - 1)
+
+/*-************************************************************************
+ * STREAMING CONSTANTS AND STRUCTURES
+ **************************************************************************/
+#define LZ4_STREAMSIZE_U64 ((1 << (LZ4_MEMORY_USAGE-3)) + 4)
+#define LZ4_STREAMSIZE (LZ4_STREAMSIZE_U64 * sizeof(unsigned long long))
+
+#define LZ4_STREAMHCSIZE 262192
+#define LZ4_STREAMHCSIZE_SIZET (262192 / sizeof(size_t))
+
+#define LZ4_STREAMDECODESIZE_U64 4
+#define LZ4_STREAMDECODESIZE (LZ4_STREAMDECODESIZE_U64 * \
+ sizeof(unsigned long long))
+
+/*
+ * LZ4_stream_t :
+ * information structure to track an LZ4 stream.
+ */
+typedef struct {
+ uint32_t hashTable[LZ4_HASH_SIZE_U32];
+ uint32_t currentOffset;
+ uint32_t initCheck;
+ const uint8_t *dictionary;
+ uint8_t *bufferStart;
+ uint32_t dictSize;
+} LZ4_stream_t_internal;
+typedef union {
+ unsigned long long table[LZ4_STREAMSIZE_U64];
+ LZ4_stream_t_internal internal_donotuse;
+} LZ4_stream_t;
+
+/*
+ * LZ4_streamHC_t :
+ * information structure to track an LZ4HC stream.
*/
-#define LZ4_MEM_COMPRESS (16384)
-#define LZ4HC_MEM_COMPRESS (262144 + (2 * sizeof(unsigned char *)))
+typedef struct {
+ unsigned int hashTable[LZ4HC_HASHTABLESIZE];
+ unsigned short chainTable[LZ4HC_MAXD];
+ /* next block to continue on current prefix */
+ const unsigned char *end;
+ /* All index relative to this position */
+ const unsigned char *base;
+ /* alternate base for extDict */
+ const unsigned char *dictBase;
+ /* below that point, need extDict */
+ unsigned int dictLimit;
+ /* below that point, no more dict */
+ unsigned int lowLimit;
+ /* index from which to continue dict update */
+ unsigned int nextToUpdate;
+ unsigned int compressionLevel;
+} LZ4HC_CCtx_internal;
+typedef union {
+ size_t table[LZ4_STREAMHCSIZE_SIZET];
+ LZ4HC_CCtx_internal internal_donotuse;
+} LZ4_streamHC_t;
/*
- * lz4_compressbound()
- * Provides the maximum size that LZ4 may output in a "worst case" scenario
- * (input data not compressible)
+ * LZ4_streamDecode_t :
+ * information structure to track an LZ4 stream during decompression.
+ * init this structure using LZ4_setStreamDecode
+ * (or memset()) before first use
*/
-static inline size_t lz4_compressbound(size_t isize)
+typedef struct {
+ const uint8_t *externalDict;
+ size_t extDictSize;
+ const uint8_t *prefixEnd;
+ size_t prefixSize;
+} LZ4_streamDecode_t_internal;
+typedef union {
+ unsigned long long table[LZ4_STREAMDECODESIZE_U64];
+ LZ4_streamDecode_t_internal internal_donotuse;
+} LZ4_streamDecode_t;
+
+/*-************************************************************************
+ * SIZE OF STATE
+ **************************************************************************/
+#define LZ4_MEM_COMPRESS LZ4_STREAMSIZE
+#define LZ4HC_MEM_COMPRESS LZ4_STREAMHCSIZE
+
+/*-************************************************************************
+ * Compression Functions
+ **************************************************************************/
+
+/*
+ * LZ4_compressBound() :
+ * Provides the maximum size that LZ4 may output in a "worst case" scenario
+ * (input data not compressible)
+ */
+static inline int LZ4_compressBound(size_t isize)
+{
+ return LZ4_COMPRESSBOUND(isize);
+}
+
+/*
+ * For backward compatibility
+ */
+static inline int lz4_compressbound(size_t isize)
{
- return isize + (isize / 255) + 16;
+ return LZ4_COMPRESSBOUND(isize);
}
/*
+ * LZ4_compress_default()
+ * Compresses 'sourceSize' bytes from buffer 'source'
+ * into already allocated 'dest' buffer of size 'maxOutputSize'.
+ * Compression is guaranteed to succeed if
+ * 'maxOutputSize' >= LZ4_compressBound(inputSize).
+ * It also runs faster, so it's a recommended setting.
+ * If the function cannot compress 'source'
+ * into a more limited 'dest' budget,
+ * compression stops *immediately*,
+ * and the function result is zero.
+ * As a consequence, 'dest' content is not valid.
+ *
+ * source : source address of the original data
+ * dest : output buffer address
+ * of the compressed data
+ * inputSize : Max supported value is
+ * LZ4_MAX_INPUT_SIZE
+ * maxOutputSize: full or partial size of buffer 'dest'
+ * (which must be already allocated)
+ * workmem : address of the working memory.
+ * This requires 'workmem' of size LZ4_MEM_COMPRESS.
+ * return : the number of bytes written into buffer 'dest'
+ * (necessarily <= maxOutputSize) or 0 if compression fails
+ */
+int LZ4_compress_default(const char *source, char *dest, int inputSize,
+ int maxOutputSize, void *wrkmem);
+
+/*
+ * LZ4_compress_fast() :
+ * Same as LZ4_compress_default(),
+ * but allows to select an "acceleration" factor.
+ * The larger the acceleration value,
+ * the faster the algorithm,
+ * but also the lesser the compression.
+ * It's a trade-off. It can be fine tuned,
+ * with each successive value
+ * providing roughly +~3% to speed.
+ * An acceleration value of "1"
+ * is the same as regular LZ4_compress_default()
+ * Values <= 0 will be replaced by
+ * LZ4_ACCELERATION_DEFAULT, which is 1.
+ */
+int LZ4_compress_fast(const char *source, char *dest, int inputSize,
+ int maxOutputSize, void *wrkmem, int acceleration);
+
+/*
+ * LZ4_compress_destSize()
+ * Reverse the logic, by compressing as much data as possible
+ * from 'source' buffer into already allocated buffer 'dest'
+ * of size 'targetDestSize'.
+ * This function either compresses the entire 'source' content into 'dest'
+ * if it's large enough, or fill 'dest' buffer completely with as much data as
+ * ossible from 'source'.
+ *
+ * source : source address of the original data
+ * dest : output buffer address of the compressed data
+ * inputSize : Max supported value is LZ4_MAX_INPUT_SIZE
+ * *sourceSizePtr: will be modified to indicate how many bytes where read
+ * from 'source' to fill 'dest'.
+ * New value is necessarily <= old value.
+ * workmem : address of the working memory.
+ * This requires 'workmem' of size LZ4_MEM_COMPRESS.
+ * return : Nb bytes written into 'dest' (necessarily <= targetDestSize)
+ or 0 if compression fails
+ */
+int LZ4_compress_destSize(const char *source, char *dest, int *sourceSizePtr,
+ int targetDestSize, void *wrkmem);
+
+/*
* lz4_compress()
- * src : source address of the original data
- * src_len : size of the original data
- * dst : output buffer address of the compressed data
- * This requires 'dst' of size LZ4_COMPRESSBOUND.
- * dst_len : is the output size, which is returned after compress done
- * workmem : address of the working memory.
- * This requires 'workmem' of size LZ4_MEM_COMPRESS.
- * return : Success if return 0
- * Error if return (< 0)
- * note : Destination buffer and workmem must be already allocated with
+ * src : source address of the original data
+ * src_len: size of the original data
+ * dst : output buffer address of the compressed data
+ * This requires 'dst' of size LZ4_COMPRESSBOUND.
+ * dst_len: is the output size, which is returned after compress done
+ * workmem: address of the working memory.
+ * This requires 'workmem' of size LZ4_MEM_COMPRESS.
+ * return : Success if return 0
+ * Error if return (< 0)
+ * note : Destination buffer and workmem must be already allocated with
* the defined size.
*/
-int lz4_compress(const unsigned char *src, size_t src_len,
- unsigned char *dst, size_t *dst_len, void *wrkmem);
-
- /*
- * lz4hc_compress()
- * src : source address of the original data
- * src_len : size of the original data
- * dst : output buffer address of the compressed data
- * This requires 'dst' of size LZ4_COMPRESSBOUND.
- * dst_len : is the output size, which is returned after compress done
- * workmem : address of the working memory.
- * This requires 'workmem' of size LZ4HC_MEM_COMPRESS.
- * return : Success if return 0
- * Error if return (< 0)
- * note : Destination buffer and workmem must be already allocated with
- * the defined size.
- */
-int lz4hc_compress(const unsigned char *src, size_t src_len,
- unsigned char *dst, size_t *dst_len, void *wrkmem);
-
-/*
- * lz4_decompress()
- * src : source address of the compressed data
- * src_len : is the input size, whcih is returned after decompress done
- * dest : output buffer address of the decompressed data
- * actual_dest_len: is the size of uncompressed data, supposing it's known
- * return : Success if return 0
- * Error if return (< 0)
- * note : Destination buffer must be already allocated.
- * slightly faster than lz4_decompress_unknownoutputsize()
+int lz4_compress(const unsigned char *src, size_t src_len, unsigned char *dst,
+ size_t *dst_len, void *wrkmem);
+
+/*-************************************************************************
+ * Decompression Functions
+ **************************************************************************/
+
+/*
+ * LZ4_decompress_fast()
+ * source : source address of the compressed data
+ * dst : output buffer address of the decompressed data
+ * originalSize: is the original and therefore uncompressed size
+ * return : the number of bytes read from the source buffer
+ * (in other words, the compressed size)
+ * If the source stream is detected malformed, the function will
+ * stop decoding and return a negative result.
+ * Destination buffer must be already allocated.
+ * Its size must be a minimum of 'originalSize' bytes.
+ * note : This function fully respect memory boundaries
+ * for properly formed compressed data.
+ * It is a bit faster than LZ4_decompress_safe().
+ * However, it does not provide any protection against intentionally
+ * modified data stream (malicious input).
+ * Use this function in trusted environment only
+ * (data to decode comes from a trusted source).
*/
-int lz4_decompress(const unsigned char *src, size_t *src_len,
- unsigned char *dest, size_t actual_dest_len);
+int LZ4_decompress_fast(const char *source, char *dest, int originalSize);
+
+/*
+ * LZ4_decompress_safe()
+ * source : source address of the compressed data
+ * dest : output buffer address of the decompressed data
+ * compressedSize : is the precise full size of the compressed block.
+ * maxDecompressedSize: is the size of destination buffer,
+ * which must be already allocated.
+ * return : the number of bytes decompressed into destination buffer
+ * (necessarily <= maxDecompressedSize)
+ * If destination buffer is not large enough, decoding will stop
+ * and output an error code (<0).
+ * If the source stream is detected malformed, the function will
+ * stop decoding and return a negative result.
+ * This function is protected against buffer overflow exploits,
+ * including malicious data packets. It never writes outside
+ * output buffer, nor reads outside input buffer.
+ */
+int LZ4_decompress_safe(const char *source, char *dest, int compressedSize,
+ int maxDecompressedSize);
/*
- * lz4_decompress_unknownoutputsize()
+ * LZ4_decompress_safe_partial() :
+ * This function decompress a compressed block of size 'compressedSize'
+ * at position 'source' into destination buffer 'dest'
+ * of size 'maxDecompressedSize'.
+ * The function tries to stop decompressing operation as soon as
+ * 'targetOutputSize' has been reached, reducing decompression time.
+ *
+ * source : source address of the compressed data
+ * dest : output buffer address of the decompressed data
+ * compressedSize : is the precise full size of the compressed block.
+ * targetOutputSize : the decompression operation will try
+ * to stop as soon as 'targetOutputSize'
+ * has been reached
+ * maxDecompressedSize: is the size of destination buffer,
+ * which must be already allocated.
+ * return : the number of bytes decoded in the destination buffer
+ * (necessarily <= maxDecompressedSize)
+ * Note : this number can be < 'targetOutputSize' should the compressed
+ * block to decode be smaller. Always control how many bytes
+ * were decoded. If the source stream is detected malformed,
+ * the function will stop decoding and return a negative result.
+ * This function never writes outside of output buffer,
+ * and never reads outside of input buffer.
+ * It is therefore protected against malicious data packets
+ */
+int LZ4_decompress_safe_partial(const char *source, char *dest,
+ int compressedSize, int targetOutputSize, int maxDecompressedSize);
+
+
+/*
+ * lz4_decompress_unknownoutputsize() :
* src : source address of the compressed data
* src_len : is the input size, therefore the compressed size
- * dest : output buffer address of the decompressed data
+ * dest : output buffer address of the decompressed data
* dest_len: is the max size of the destination buffer, which is
- * returned with actual size of decompressed data after
- * decompress done
- * return : Success if return 0
- * Error if return (< 0)
- * note : Destination buffer must be already allocated.
+ * returned with actual size of decompressed data after
+ * decompress done
+ * return: Success if return 0
+ * Error if return (< 0)
+ * note: Destination buffer must be already allocated.
*/
int lz4_decompress_unknownoutputsize(const unsigned char *src, size_t src_len,
- unsigned char *dest, size_t *dest_len);
+ unsigned char *dest, size_t *dest_len);
+
+/*
+ * lz4_decompress() :
+ * src : source address of the compressed data
+ * src_len : is the input size,
+ * which is returned after decompress done
+ * dest : output buffer address of the decompressed data
+ * actual_dest_len: is the size of uncompressed data, supposing it's known
+ * return: Success if return 0
+ * Error if return (< 0)
+ * note : Destination buffer must be already allocated.
+ * slightly faster than lz4_decompress_unknownoutputsize()
+ */
+int lz4_decompress(const unsigned char *src, size_t *src_len,
+ unsigned char *dest, size_t actual_dest_len);
+
+/*-************************************************************************
+ * LZ4 HC Compression
+ **************************************************************************/
+
+/*! LZ4_compress_HC() :
+ * Compress data from `src` into `dst`, using the more powerful
+ * but slower "HC" algorithm. dst` must be already allocated.
+ * Compression is guaranteed to succeed if
+ * `dstCapacity >= LZ4_compressBound(srcSize)
+ * Max supported `srcSize` value is LZ4_MAX_INPUT_SIZE
+ *
+ * src : source address of the original data
+ * dst : output buffer address of the compressed data
+ * srcSize : Max supported value is LZ4_MAX_INPUT_SIZE
+ * dstCapacity : full or partial size of buffer 'dst'
+ * (which must be already allocated)
+ * compressionLevel: Recommended values are between 4 and 9, although any
+ * value between 1 and LZ4HC_MAX_CLEVEL will work.
+ * Values >LZ4HC_MAX_CLEVEL behave the same as 16.
+ * wrkmem : address of the working memory.
+ * This requires 'wrkmem' of size LZ4HC_MEM_COMPRESS.
+ * return : the number of bytes written into 'dst'
+ * or 0 if compression fails.
+ */
+int LZ4_compress_HC(const char *src, char *dst, int srcSize, int dstCapacity,
+ int compressionLevel, void *wrkmem);
+
+/*
+ * lz4hc_compress()
+ * src : source address of the original data
+ * src_len: size of the original data
+ * dst : output buffer address of the compressed data
+ * This requires 'dst' of size LZ4_COMPRESSBOUND.
+ * dst_len: is the output size, which is returned after compress done
+ * workmem: address of the working memory.
+ * This requires 'workmem' of size LZ4HC_MEM_COMPRESS.
+ * return : Success if return 0
+ * Error if return (< 0)
+ * note : Destination buffer and workmem must be already allocated with
+ * the defined size.
+ */
+int lz4hc_compress(const unsigned char *src, size_t src_len, unsigned char *dst,
+ size_t *dst_len, void *wrkmem);
+
+/*
+ * These functions compress data in successive blocks of any size,
+ * using previous blocks as dictionary. One key assumption is that previous
+ * blocks (up to 64 KB) remain read-accessible while
+ * compressing next blocks.
+ * There is an exception for ring buffers, which can be smaller than 64 KB.
+ * Ring buffers scenario is automatically detected and handled by
+ * LZ4_compress_HC_continue().
+ * Before starting compression, state must be properly initialized,
+ * using LZ4_resetStreamHC().
+ * A first "fictional block" can then be designated as initial dictionary,
+ * using LZ4_loadDictHC() (Optional).
+ * Then, use LZ4_compress_HC_continue() to compress each successive block.
+ * Previous memory blocks (including initial dictionary when present) must
+ * remain accessible and unmodified during compression.
+ * 'dst' buffer should be sized to handle worst case scenarios, using
+ * LZ4_compressBound(), to ensure operation success.
+ * If, for any reason, previous data blocks can't be preserved unmodified
+ * in memory during next compression block,
+ * you must save it to a safer memory space, using LZ4_saveDictHC().
+ * Return value of LZ4_saveDictHC() is the size of dictionary
+ * effectively saved into 'safeBuffer'.
+ */
+void LZ4_resetStreamHC(LZ4_streamHC_t *streamHCPtr, int compressionLevel);
+int LZ4_loadDictHC(LZ4_streamHC_t *streamHCPtr, const char *dictionary,
+ int dictSize);
+int LZ4_compress_HC_continue(LZ4_streamHC_t *streamHCPtr, const char *src,
+ char *dst, int srcSize, int maxDstSize);
+int LZ4_saveDictHC(LZ4_streamHC_t *streamHCPtr, char *safeBuffer,
+ int maxDictSize);
+
+/*-*********************************************
+ * Streaming Compression Functions
+ ***********************************************/
+/*
+ * LZ4_resetStream() :
+ * An LZ4_stream_t structure can be allocated once
+ * and re-used multiple times.
+ * Use this function to init an allocated `LZ4_stream_t` structure
+ * and start a new compression.
+ */
+void LZ4_resetStream(LZ4_stream_t *LZ4_stream);
+
+/*
+ * LZ4_loadDict() :
+ * Use this function to load a static dictionary into LZ4_stream.
+ * Any previous data will be forgotten, only 'dictionary'
+ * will remain in memory.
+ * Loading a size of 0 is allowed.
+ * Return : dictionary size, in bytes (necessarily <= 64 KB)
+ */
+int LZ4_loadDict(LZ4_stream_t *streamPtr, const char *dictionary,
+ int dictSize);
+
+/*
+ * LZ4_compress_fast_continue() :
+ * Compress buffer content 'src',
+ * using data from previously compressed blocks
+ * as dictionary to improve compression ratio.
+ * Important : Previous data blocks are assumed to still
+ * be present and unmodified !
+ * 'dst' buffer must be already allocated.
+ * If maxDstSize >= LZ4_compressBound(srcSize),
+ * compression is guaranteed to succeed, and runs faster.
+ * If not, and if compressed data cannot fit into 'dst' buffer size,
+ * compression stops, and function returns a zero.
+ */
+int LZ4_compress_fast_continue(LZ4_stream_t *streamPtr, const char *src,
+ char *dst, int srcSize, int maxDstSize, int acceleration);
+
+/*
+ * LZ4_saveDict() :
+ * If previously compressed data block is not guaranteed
+ * to remain available at its memory location,
+ * save it into a safer place (char *safeBuffer).
+ * Note : you don't need to call LZ4_loadDict() afterwards,
+ * dictionary is immediately usable, you can therefore call
+ * LZ4_compress_fast_continue().
+ * Return : saved dictionary size in bytes (necessarily <= dictSize),
+ * or 0 if error.
+ */
+int LZ4_saveDict(LZ4_stream_t *streamPtr, char *safeBuffer, int dictSize);
+
+/*
+ * LZ4_setStreamDecode() :
+ * Use this function to instruct where to find the dictionary.
+ * Setting a size of 0 is allowed (same effect as reset).
+ * @return : 1 if OK, 0 if error
+ */
+int LZ4_setStreamDecode(LZ4_streamDecode_t *LZ4_streamDecode,
+ const char *dictionary, int dictSize);
+
+/*
+ * LZ4_decompress_*_continue() :
+ * These decoding functions allow decompression of multiple blocks
+ * in "streaming" mode.
+ * Previously decoded blocks *must* remain available at the memory position
+ * where they were decoded (up to 64 KB)
+ * In the case of a ring buffers, decoding buffer must be either :
+ * - Exactly same size as encoding buffer, with same update rule
+ * (block boundaries at same positions) In which case,
+ * the decoding & encoding ring buffer can have any size,
+ * including very small ones ( < 64 KB).
+ * - Larger than encoding buffer, by a minimum of maxBlockSize more bytes.
+ * maxBlockSize is implementation dependent.
+ * It's the maximum size you intend to compress into a single block.
+ * In which case, encoding and decoding buffers do not need
+ * to be synchronized, and encoding ring buffer can have any size,
+ * including small ones ( < 64 KB).
+ * - _At least_ 64 KB + 8 bytes + maxBlockSize.
+ * In which case, encoding and decoding buffers do not need to be
+ * synchronized, and encoding ring buffer can have any size,
+ * including larger than decoding buffer. W
+ * Whenever these conditions are not possible, save the last 64KB of decoded
+ * data into a safe buffer, and indicate where it is saved
+ * using LZ4_setStreamDecode()
+ */
+int LZ4_decompress_safe_continue(LZ4_streamDecode_t *LZ4_streamDecode,
+ const char *source, char *dest, int compressedSize,
+ int maxDecompressedSize);
+int LZ4_decompress_fast_continue(LZ4_streamDecode_t *LZ4_streamDecode,
+ const char *source, char *dest, int originalSize);
+
+/*
+ * LZ4_decompress_*_usingDict() :
+ * These decoding functions work the same as
+ * a combination of LZ4_setStreamDecode() followed by
+ * LZ4_decompress_*_continue()
+ * They are stand-alone, and don't need an LZ4_streamDecode_t structure.
+ */
+int LZ4_decompress_safe_usingDict(const char *source, char *dest,
+ int compressedSize, int maxDecompressedSize, const char *dictStart,
+ int dictSize);
+int LZ4_decompress_fast_usingDict(const char *source, char *dest,
+ int originalSize, const char *dictStart, int dictSize);
+
#endif
diff --git a/lib/lz4/lz4_compress.c b/lib/lz4/lz4_compress.c
index 28321d8..e595896 100644
--- a/lib/lz4/lz4_compress.c
+++ b/lib/lz4/lz4_compress.c
@@ -1,19 +1,16 @@
/*
* LZ4 - Fast LZ compression algorithm
- * Copyright (C) 2011-2012, Yann Collet.
- * BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
-
+ * Copyright (C) 2011 - 2016, Yann Collet.
+ * BSD 2 - Clause License (http://www.opensource.org/licenses/bsd - license.php)
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions are
* met:
- *
- * * Redistributions of source code must retain the above copyright
+ * * Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
- * * Redistributions in binary form must reproduce the above
+ * * Redistributions in binary form must reproduce the above
* copyright notice, this list of conditions and the following disclaimer
* in the documentation and/or other materials provided with the
* distribution.
- *
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
@@ -25,417 +22,875 @@
* THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
* OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
* You can contact the author at :
- * - LZ4 homepage : http://fastcompression.blogspot.com/p/lz4.html
- * - LZ4 source repository : http://code.google.com/p/lz4/
+ * - LZ4 homepage : http://www.lz4.org
+ * - LZ4 source repository : https://github.com/lz4/lz4
*
- * Changed for kernel use by:
- * Chanho Min <chanho.min@lge.com>
+ * Changed for kernel usage by:
+ * Sven Schmidt <4sschmid@informatik.uni-hamburg.de>
*/
+/*-************************************
+ * Dependencies
+ **************************************/
+#include <linux/lz4.h>
+#include "lz4defs.h"
#include <linux/module.h>
#include <linux/kernel.h>
-#include <linux/lz4.h>
#include <asm/unaligned.h>
-#include "lz4defs.h"
-/*
- * LZ4_compressCtx :
- * -----------------
- * Compress 'isize' bytes from 'source' into an output buffer 'dest' of
- * maximum size 'maxOutputSize'. * If it cannot achieve it, compression
- * will stop, and result of the function will be zero.
- * return : the number of bytes written in buffer 'dest', or 0 if the
- * compression fails
- */
-static inline int lz4_compressctx(void *ctx,
- const char *source,
- char *dest,
- int isize,
- int maxoutputsize)
+/*-******************************
+ * Compression functions
+ ********************************/
+static U32 LZ4_hash4(U32 sequence, tableType_t const tableType)
{
- HTYPE *hashtable = (HTYPE *)ctx;
- const u8 *ip = (u8 *)source;
+ if (tableType == byU16)
+ return ((sequence * 2654435761U)
+ >> ((MINMATCH*8) - (LZ4_HASHLOG + 1)));
+ else
+ return ((sequence * 2654435761U)
+ >> ((MINMATCH*8) - LZ4_HASHLOG));
+}
+
#if LZ4_ARCH64
- const BYTE * const base = ip;
+static U32 LZ4_hash5(U64 sequence, tableType_t const tableType)
+{
+ const U32 hashLog = (tableType == byU16)
+ ? LZ4_HASHLOG + 1
+ : LZ4_HASHLOG;
+
+#ifdef __LITTLE_ENDIAN__
+ static const U64 prime5bytes = 889523592379ULL;
+
+ return (U32)(((sequence << 24) * prime5bytes) >> (64 - hashLog));
#else
- const int base = 0;
+ static const U64 prime8bytes = 11400714785074694791ULL;
+
+ return (U32)(((sequence >> 24) * prime8bytes) >> (64 - hashLog));
#endif
- const u8 *anchor = ip;
- const u8 *const iend = ip + isize;
- const u8 *const mflimit = iend - MFLIMIT;
- #define MATCHLIMIT (iend - LASTLITERALS)
-
- u8 *op = (u8 *) dest;
- u8 *const oend = op + maxoutputsize;
- int length;
- const int skipstrength = SKIPSTRENGTH;
- u32 forwardh;
- int lastrun;
-
- /* Init */
- if (isize < MINLENGTH)
- goto _last_literals;
+}
+#endif
+
+static U32 LZ4_hashPosition(const void *p, tableType_t tableType)
+{
+#if LZ4_ARCH64
+ if (tableType == byU32)
+ return LZ4_hash5(LZ4_read_ARCH(p), tableType);
+#endif
+
+ return LZ4_hash4(LZ4_read32(p), tableType);
+}
+
+static void LZ4_putPositionOnHash(const BYTE *p, U32 h, void *tableBase,
+ tableType_t const tableType, const BYTE *srcBase)
+{
+ switch (tableType) {
+ case byPtr:
+ {
+ const BYTE **hashTable = (const BYTE **)tableBase;
+
+ hashTable[h] = p;
+ return;
+ }
+ case byU32:
+ {
+ U32 *hashTable = (U32 *) tableBase;
+
+ hashTable[h] = (U32)(p - srcBase);
+ return;
+ }
+ case byU16:
+ {
+ U16 *hashTable = (U16 *) tableBase;
+
+ hashTable[h] = (U16)(p - srcBase);
+ return;
+ }
+ }
+}
+
+static inline void LZ4_putPosition(const BYTE *p, void *tableBase,
+ tableType_t tableType, const BYTE *srcBase)
+{
+ U32 const h = LZ4_hashPosition(p, tableType);
+
+ LZ4_putPositionOnHash(p, h, tableBase, tableType, srcBase);
+}
+
+static const BYTE *LZ4_getPositionOnHash(U32 h, void *tableBase,
+ tableType_t tableType, const BYTE *srcBase)
+{
+ if (tableType == byPtr) {
+ const BYTE **hashTable = (const BYTE **) tableBase;
+
+ return hashTable[h];
+ }
+
+ if (tableType == byU32) {
+ const U32 * const hashTable = (U32 *) tableBase;
+
+ return hashTable[h] + srcBase;
+ }
+
+ {
+ /* default, to ensure a return */
+ const U16 * const hashTable = (U16 *) tableBase;
+ return hashTable[h] + srcBase;
+ }
+}
+
+static inline const BYTE *LZ4_getPosition(const BYTE *p, void *tableBase,
+ tableType_t tableType, const BYTE *srcBase)
+{
+ U32 const h = LZ4_hashPosition(p, tableType);
+
+ return LZ4_getPositionOnHash(h, tableBase, tableType, srcBase);
+}
+
+
+/*
+ * LZ4_compress_generic() :
+ * inlined, to ensure branches are decided at compilation time
+ */
+static inline int LZ4_compress_generic(
+ LZ4_stream_t_internal * const dictPtr,
+ const char * const source,
+ char * const dest,
+ const int inputSize,
+ const int maxOutputSize,
+ const limitedOutput_directive outputLimited,
+ const tableType_t tableType,
+ const dict_directive dict,
+ const dictIssue_directive dictIssue,
+ const U32 acceleration)
+{
+ const BYTE *ip = (const BYTE *) source;
+ const BYTE *base;
+ const BYTE *lowLimit;
+ const BYTE * const lowRefLimit = ip - dictPtr->dictSize;
+ const BYTE * const dictionary = dictPtr->dictionary;
+ const BYTE * const dictEnd = dictionary + dictPtr->dictSize;
+ const size_t dictDelta = dictEnd - (const BYTE *)source;
+ const BYTE *anchor = (const BYTE *) source;
+ const BYTE * const iend = ip + inputSize;
+ const BYTE * const mflimit = iend - MFLIMIT;
+ const BYTE * const matchlimit = iend - LASTLITERALS;
+
+ BYTE *op = (BYTE *) dest;
+ BYTE * const olimit = op + maxOutputSize;
+
+ U32 forwardH;
+ size_t refDelta = 0;
+
+ /* Init conditions */
+ if ((U32)inputSize > (U32)LZ4_MAX_INPUT_SIZE) {
+ /* Unsupported inputSize, too large (or negative) */
+ return 0;
+ }
+ switch (dict) {
+ case noDict:
+ default:
+ base = (const BYTE *)source;
+ lowLimit = (const BYTE *)source;
+ break;
+ case withPrefix64k:
+ base = (const BYTE *)source - dictPtr->currentOffset;
+ lowLimit = (const BYTE *)source - dictPtr->dictSize;
+ break;
+ case usingExtDict:
+ base = (const BYTE *)source - dictPtr->currentOffset;
+ lowLimit = (const BYTE *)source;
+ break;
+ }
+
+ if ((tableType == byU16)
+ && (inputSize >= LZ4_64Klimit)) {
+ /* Size too large (not within 64K limit) */
+ return 0;
+ }
- memset((void *)hashtable, 0, LZ4_MEM_COMPRESS);
+ if (inputSize < LZ4_minLength) {
+ /* Input too small, no compression (all literals) */
+ goto _last_literals;
+ }
/* First Byte */
- hashtable[LZ4_HASH_VALUE(ip)] = ip - base;
- ip++;
- forwardh = LZ4_HASH_VALUE(ip);
+ LZ4_putPosition(ip, dictPtr->hashTable, tableType, base);
+ ip++; forwardH = LZ4_hashPosition(ip, tableType);
/* Main Loop */
- for (;;) {
- int findmatchattempts = (1U << skipstrength) + 3;
- const u8 *forwardip = ip;
- const u8 *ref;
- u8 *token;
+ for ( ; ; ) {
+ const BYTE *match;
+ BYTE *token;
/* Find a match */
- do {
- u32 h = forwardh;
- int step = findmatchattempts++ >> skipstrength;
- ip = forwardip;
- forwardip = ip + step;
-
- if (unlikely(forwardip > mflimit))
- goto _last_literals;
-
- forwardh = LZ4_HASH_VALUE(forwardip);
- ref = base + hashtable[h];
- hashtable[h] = ip - base;
- } while ((ref < ip - MAX_DISTANCE) || (A32(ref) != A32(ip)));
+ { const BYTE *forwardIp = ip;
+ unsigned int step = 1;
+ unsigned int searchMatchNb = acceleration
+ << LZ4_skipTrigger;
+
+ do {
+ U32 const h = forwardH;
+
+ ip = forwardIp;
+ forwardIp += step;
+ step = (searchMatchNb++ >> LZ4_skipTrigger);
+
+ if (unlikely(forwardIp > mflimit))
+ goto _last_literals;
+
+ match = LZ4_getPositionOnHash(h,
+ dictPtr->hashTable,
+ tableType, base);
+ if (dict == usingExtDict) {
+ if (match < (const BYTE *)source) {
+ refDelta = dictDelta;
+ lowLimit = dictionary;
+ } else {
+ refDelta = 0;
+ lowLimit = (const BYTE *)source;
+ } }
+ forwardH = LZ4_hashPosition(forwardIp,
+ tableType);
+ LZ4_putPositionOnHash(ip, h, dictPtr->hashTable,
+ tableType, base);
+
+ } while (((dictIssue == dictSmall)
+ ? (match < lowRefLimit)
+ : 0)
+ || ((tableType == byU16)
+ ? 0
+ : (match + MAX_DISTANCE < ip))
+ || (LZ4_read32(match + refDelta)
+ != LZ4_read32(ip)));
+ }
/* Catch up */
- while ((ip > anchor) && (ref > (u8 *)source) &&
- unlikely(ip[-1] == ref[-1])) {
+ while (((ip > anchor) & (match + refDelta > lowLimit))
+ && (unlikely(ip[-1] == match[refDelta - 1]))) {
ip--;
- ref--;
- }
+ match--;
+ }
- /* Encode Literal length */
- length = (int)(ip - anchor);
- token = op++;
- /* check output limit */
- if (unlikely(op + length + (2 + 1 + LASTLITERALS) +
- (length >> 8) > oend))
- return 0;
+ /* Encode Literals */
+ { unsigned const int litLength = (unsigned int)(ip - anchor);
- if (length >= (int)RUN_MASK) {
- int len;
- *token = (RUN_MASK << ML_BITS);
- len = length - RUN_MASK;
- for (; len > 254 ; len -= 255)
- *op++ = 255;
- *op++ = (u8)len;
- } else
- *token = (length << ML_BITS);
+ token = op++;
+ if ((outputLimited) &&
+ /* Check output buffer overflow */
+ (unlikely(op + litLength +
+ (2 + 1 + LASTLITERALS) +
+ (litLength/255) > olimit)))
+ return 0;
+ if (litLength >= RUN_MASK) {
+ int len = (int)litLength - RUN_MASK;
+
+ *token = (RUN_MASK<<ML_BITS);
+ for (; len >= 255 ; len -= 255)
+ *op++ = 255;
+ *op++ = (BYTE)len;
+ } else
+ *token = (BYTE)(litLength<<ML_BITS);
+
+ /* Copy Literals */
+ LZ4_wildCopy(op, anchor, op + litLength);
+ op += litLength;
+ }
- /* Copy Literals */
- LZ4_BLINDCOPY(anchor, op, length);
_next_match:
/* Encode Offset */
- LZ4_WRITE_LITTLEENDIAN_16(op, (u16)(ip - ref));
+ LZ4_writeLE16(op, (U16)(ip - match)); op += 2;
- /* Start Counting */
- ip += MINMATCH;
- /* MinMatch verified */
- ref += MINMATCH;
- anchor = ip;
- while (likely(ip < MATCHLIMIT - (STEPSIZE - 1))) {
- #if LZ4_ARCH64
- u64 diff = A64(ref) ^ A64(ip);
- #else
- u32 diff = A32(ref) ^ A32(ip);
- #endif
- if (!diff) {
- ip += STEPSIZE;
- ref += STEPSIZE;
- continue;
- }
- ip += LZ4_NBCOMMONBYTES(diff);
- goto _endcount;
- }
- #if LZ4_ARCH64
- if ((ip < (MATCHLIMIT - 3)) && (A32(ref) == A32(ip))) {
- ip += 4;
- ref += 4;
- }
- #endif
- if ((ip < (MATCHLIMIT - 1)) && (A16(ref) == A16(ip))) {
- ip += 2;
- ref += 2;
- }
- if ((ip < MATCHLIMIT) && (*ref == *ip))
- ip++;
-_endcount:
/* Encode MatchLength */
- length = (int)(ip - anchor);
- /* Check output limit */
- if (unlikely(op + (1 + LASTLITERALS) + (length >> 8) > oend))
- return 0;
- if (length >= (int)ML_MASK) {
- *token += ML_MASK;
- length -= ML_MASK;
- for (; length > 509 ; length -= 510) {
- *op++ = 255;
- *op++ = 255;
- }
- if (length > 254) {
- length -= 255;
- *op++ = 255;
+ { unsigned int matchCode;
+
+ if ((dict == usingExtDict)
+ && (lowLimit == dictionary)) {
+ const BYTE *limit;
+
+ match += refDelta;
+ limit = ip + (dictEnd - match);
+ if (limit > matchlimit)
+ limit = matchlimit;
+ matchCode = LZ4_count(ip + MINMATCH,
+ match + MINMATCH, limit);
+ ip += MINMATCH + matchCode;
+ if (ip == limit) {
+ unsigned const int more = LZ4_count(ip,
+ (const BYTE *)source,
+ matchlimit);
+
+ matchCode += more;
+ ip += more;
+ }
+ } else {
+ matchCode = LZ4_count(ip + MINMATCH,
+ match + MINMATCH, matchlimit);
+ ip += MINMATCH + matchCode;
}
- *op++ = (u8)length;
- } else
- *token += length;
+
+ if (outputLimited &&
+ /* Check output buffer overflow */
+ (unlikely(op +
+ (1 + LASTLITERALS) +
+ (matchCode>>8) > olimit)))
+ return 0;
+ if (matchCode >= ML_MASK) {
+ *token += ML_MASK;
+ matchCode -= ML_MASK;
+ LZ4_write32(op, 0xFFFFFFFF);
+ while (matchCode >= 4*255) {
+ op += 4;
+ LZ4_write32(op, 0xFFFFFFFF);
+ matchCode -= 4*255;
+ }
+ op += matchCode / 255;
+ *op++ = (BYTE)(matchCode % 255);
+ } else
+ *token += (BYTE)(matchCode);
+ }
+
+ anchor = ip;
/* Test end of chunk */
- if (ip > mflimit) {
- anchor = ip;
+ if (ip > mflimit)
break;
- }
/* Fill table */
- hashtable[LZ4_HASH_VALUE(ip-2)] = ip - 2 - base;
+ LZ4_putPosition(ip - 2, dictPtr->hashTable, tableType, base);
/* Test next position */
- ref = base + hashtable[LZ4_HASH_VALUE(ip)];
- hashtable[LZ4_HASH_VALUE(ip)] = ip - base;
- if ((ref > ip - (MAX_DISTANCE + 1)) && (A32(ref) == A32(ip))) {
+ match = LZ4_getPosition(ip, dictPtr->hashTable,
+ tableType, base);
+ if (dict == usingExtDict) {
+ if (match < (const BYTE *)source) {
+ refDelta = dictDelta;
+ lowLimit = dictionary;
+ } else {
+ refDelta = 0;
+ lowLimit = (const BYTE *)source;
+ }
+ }
+ LZ4_putPosition(ip, dictPtr->hashTable, tableType, base);
+ if (((dictIssue == dictSmall) ? (match >= lowRefLimit) : 1)
+ && (match + MAX_DISTANCE >= ip)
+ && (LZ4_read32(match + refDelta) == LZ4_read32(ip))) {
token = op++;
*token = 0;
goto _next_match;
}
/* Prepare next loop */
- anchor = ip++;
- forwardh = LZ4_HASH_VALUE(ip);
+ forwardH = LZ4_hashPosition(++ip, tableType);
}
_last_literals:
/* Encode Last Literals */
- lastrun = (int)(iend - anchor);
- if (((char *)op - dest) + lastrun + 1
- + ((lastrun + 255 - RUN_MASK) / 255) > (u32)maxoutputsize)
- return 0;
-
- if (lastrun >= (int)RUN_MASK) {
- *op++ = (RUN_MASK << ML_BITS);
- lastrun -= RUN_MASK;
- for (; lastrun > 254 ; lastrun -= 255)
- *op++ = 255;
- *op++ = (u8)lastrun;
- } else
- *op++ = (lastrun << ML_BITS);
- memcpy(op, anchor, iend - anchor);
- op += iend - anchor;
+ { size_t const lastRun = (size_t)(iend - anchor);
+ if ((outputLimited) &&
+ /* Check output buffer overflow */
+ ((op - (BYTE *)dest) + lastRun + 1 +
+ ((lastRun + 255 - RUN_MASK)/255) > (U32)maxOutputSize))
+ return 0;
+ if (lastRun >= RUN_MASK) {
+ size_t accumulator = lastRun - RUN_MASK;
+ *op++ = RUN_MASK << ML_BITS;
+ for (; accumulator >= 255 ; accumulator -= 255)
+ *op++ = 255;
+ *op++ = (BYTE) accumulator;
+ } else {
+ *op++ = (BYTE)(lastRun<<ML_BITS);
+ }
+ memcpy(op, anchor, lastRun);
+ op += lastRun;
+ }
/* End */
- return (int)(((char *)op) - dest);
+ return (int) (((char *)op) - dest);
}
-static inline int lz4_compress64kctx(void *ctx,
- const char *source,
- char *dest,
- int isize,
- int maxoutputsize)
+int LZ4_compress_fast_extState(void *state, const char *source, char *dest,
+ int inputSize, int maxOutputSize, int acceleration)
{
- u16 *hashtable = (u16 *)ctx;
- const u8 *ip = (u8 *) source;
- const u8 *anchor = ip;
- const u8 *const base = ip;
- const u8 *const iend = ip + isize;
- const u8 *const mflimit = iend - MFLIMIT;
- #define MATCHLIMIT (iend - LASTLITERALS)
-
- u8 *op = (u8 *) dest;
- u8 *const oend = op + maxoutputsize;
- int len, length;
- const int skipstrength = SKIPSTRENGTH;
- u32 forwardh;
- int lastrun;
-
- /* Init */
- if (isize < MINLENGTH)
- goto _last_literals;
+ #if LZ4_ARCH64
+ tableType_t tableType = byU32;
+ #else
+ tableType_t tableType = byPtr;
+ #endif
+
+ LZ4_stream_t_internal *ctx = &((LZ4_stream_t *)state)->internal_donotuse;
+
+ LZ4_resetStream((LZ4_stream_t *)state);
+
+ if (acceleration < 1)
+ acceleration = LZ4_ACCELERATION_DEFAULT;
+
+ if (maxOutputSize >= LZ4_compressBound(inputSize)) {
+ if (inputSize < LZ4_64Klimit)
+ return LZ4_compress_generic(ctx, source,
+ dest, inputSize, 0,
+ noLimit, byU16, noDict,
+ noDictIssue, acceleration);
+ else
+ return LZ4_compress_generic(ctx, source,
+ dest, inputSize, 0,
+ noLimit, tableType, noDict,
+ noDictIssue, acceleration);
+ } else {
+ if (inputSize < LZ4_64Klimit)
+ return LZ4_compress_generic(ctx, source,
+ dest, inputSize,
+ maxOutputSize, limitedOutput, byU16, noDict,
+ noDictIssue, acceleration);
+ else
+ return LZ4_compress_generic(ctx, source,
+ dest, inputSize,
+ maxOutputSize, limitedOutput, tableType, noDict,
+ noDictIssue, acceleration);
+ }
+}
- memset((void *)hashtable, 0, LZ4_MEM_COMPRESS);
+int LZ4_compress_fast(const char *source, char *dest, int inputSize,
+ int maxOutputSize, void *wrkmem, int acceleration)
+{
+ return LZ4_compress_fast_extState(wrkmem, source, dest, inputSize,
+ maxOutputSize, acceleration);
+}
+EXPORT_SYMBOL(LZ4_compress_fast);
+
+int LZ4_compress_default(const char *source, char *dest, int inputSize,
+ int maxOutputSize, void *wrkmem)
+{
+ return LZ4_compress_fast(source, dest, inputSize,
+ maxOutputSize, wrkmem, 1);
+}
+EXPORT_SYMBOL(LZ4_compress_default);
+
+/*-******************************
+ * *_destSize() variant
+ ********************************/
+
+static int LZ4_compress_destSize_generic(
+ LZ4_stream_t_internal * const ctx,
+ const char * const src,
+ char * const dst,
+ int * const srcSizePtr,
+ const int targetDstSize,
+ const tableType_t tableType)
+{
+ const BYTE *ip = (const BYTE *) src;
+ const BYTE *base = (const BYTE *) src;
+ const BYTE *lowLimit = (const BYTE *) src;
+ const BYTE *anchor = ip;
+ const BYTE * const iend = ip + *srcSizePtr;
+ const BYTE * const mflimit = iend - MFLIMIT;
+ const BYTE * const matchlimit = iend - LASTLITERALS;
+
+ BYTE *op = (BYTE *) dst;
+ BYTE * const oend = op + targetDstSize;
+ BYTE * const oMaxLit = op + targetDstSize - 2 /* offset */
+ - 8 /* because 8 + MINMATCH == MFLIMIT */ - 1 /* token */;
+ BYTE * const oMaxMatch = op + targetDstSize
+ - (LASTLITERALS + 1 /* token */);
+ BYTE * const oMaxSeq = oMaxLit - 1 /* token */;
+
+ U32 forwardH;
+
+ /* Init conditions */
+ /* Impossible to store anything */
+ if (targetDstSize < 1)
+ return 0;
+ /* Unsupported input size, too large (or negative) */
+ if ((U32)*srcSizePtr > (U32)LZ4_MAX_INPUT_SIZE)
+ return 0;
+ /* Size too large (not within 64K limit) */
+ if ((tableType == byU16) && (*srcSizePtr >= LZ4_64Klimit))
+ return 0;
+ /* Input too small, no compression (all literals) */
+ if (*srcSizePtr < LZ4_minLength)
+ goto _last_literals;
/* First Byte */
- ip++;
- forwardh = LZ4_HASH64K_VALUE(ip);
+ *srcSizePtr = 0;
+ LZ4_putPosition(ip, ctx->hashTable, tableType, base);
+ ip++; forwardH = LZ4_hashPosition(ip, tableType);
/* Main Loop */
- for (;;) {
- int findmatchattempts = (1U << skipstrength) + 3;
- const u8 *forwardip = ip;
- const u8 *ref;
- u8 *token;
+ for ( ; ; ) {
+ const BYTE *match;
+ BYTE *token;
/* Find a match */
- do {
- u32 h = forwardh;
- int step = findmatchattempts++ >> skipstrength;
- ip = forwardip;
- forwardip = ip + step;
-
- if (forwardip > mflimit)
- goto _last_literals;
-
- forwardh = LZ4_HASH64K_VALUE(forwardip);
- ref = base + hashtable[h];
- hashtable[h] = (u16)(ip - base);
- } while (A32(ref) != A32(ip));
+ { const BYTE *forwardIp = ip;
+ unsigned int step = 1;
+ unsigned int searchMatchNb = 1 << LZ4_skipTrigger;
+
+ do {
+ U32 h = forwardH;
+
+ ip = forwardIp;
+ forwardIp += step;
+ step = (searchMatchNb++ >> LZ4_skipTrigger);
+
+ if (unlikely(forwardIp > mflimit))
+ goto _last_literals;
+
+ match = LZ4_getPositionOnHash(h, ctx->hashTable,
+ tableType, base);
+ forwardH = LZ4_hashPosition(forwardIp,
+ tableType);
+ LZ4_putPositionOnHash(ip, h,
+ ctx->hashTable, tableType,
+ base);
+
+ } while (((tableType == byU16)
+ ? 0
+ : (match + MAX_DISTANCE < ip))
+ || (LZ4_read32(match) != LZ4_read32(ip)));
+ }
/* Catch up */
- while ((ip > anchor) && (ref > (u8 *)source)
- && (ip[-1] == ref[-1])) {
- ip--;
- ref--;
- }
+ while ((ip > anchor)
+ && (match > lowLimit)
+ && (unlikely(ip[-1] == match[-1]))) {
+ ip--; match--;
+ }
/* Encode Literal length */
- length = (int)(ip - anchor);
- token = op++;
- /* Check output limit */
- if (unlikely(op + length + (2 + 1 + LASTLITERALS)
- + (length >> 8) > oend))
- return 0;
- if (length >= (int)RUN_MASK) {
- *token = (RUN_MASK << ML_BITS);
- len = length - RUN_MASK;
- for (; len > 254 ; len -= 255)
- *op++ = 255;
- *op++ = (u8)len;
- } else
- *token = (length << ML_BITS);
+ { unsigned int litLength = (unsigned int)(ip - anchor);
- /* Copy Literals */
- LZ4_BLINDCOPY(anchor, op, length);
+ token = op++;
+ if (op + ((litLength + 240)/255)
+ + litLength > oMaxLit) {
+ /* Not enough space for a last match */
+ op--;
+ goto _last_literals;
+ }
+ if (litLength >= RUN_MASK) {
+ unsigned int len = litLength - RUN_MASK;
+ *token = (RUN_MASK<<ML_BITS);
+ for (; len >= 255 ; len -= 255)
+ *op++ = 255;
+ *op++ = (BYTE)len;
+ } else
+ *token = (BYTE)(litLength<<ML_BITS);
+
+ /* Copy Literals */
+ LZ4_wildCopy(op, anchor, op + litLength);
+ op += litLength;
+ }
_next_match:
/* Encode Offset */
- LZ4_WRITE_LITTLEENDIAN_16(op, (u16)(ip - ref));
+ LZ4_writeLE16(op, (U16)(ip - match)); op += 2;
- /* Start Counting */
- ip += MINMATCH;
- /* MinMatch verified */
- ref += MINMATCH;
- anchor = ip;
+ /* Encode MatchLength */
+ { size_t matchLength = LZ4_count(ip + MINMATCH,
+ match + MINMATCH, matchlimit);
- while (ip < MATCHLIMIT - (STEPSIZE - 1)) {
- #if LZ4_ARCH64
- u64 diff = A64(ref) ^ A64(ip);
- #else
- u32 diff = A32(ref) ^ A32(ip);
- #endif
-
- if (!diff) {
- ip += STEPSIZE;
- ref += STEPSIZE;
- continue;
+ if (op + ((matchLength + 240)/255) > oMaxMatch) {
+ /* Match description too long : reduce it */
+ matchLength = (15 - 1) + (oMaxMatch - op) * 255;
}
- ip += LZ4_NBCOMMONBYTES(diff);
- goto _endcount;
- }
- #if LZ4_ARCH64
- if ((ip < (MATCHLIMIT - 3)) && (A32(ref) == A32(ip))) {
- ip += 4;
- ref += 4;
+ ip += MINMATCH + matchLength;
+
+ if (matchLength >= ML_MASK) {
+ *token += ML_MASK;
+ matchLength -= ML_MASK;
+ while (matchLength >= 255) {
+ matchLength -= 255; *op++ = 255;
+ }
+ *op++ = (BYTE)matchLength;
+ } else
+ *token += (BYTE)(matchLength);
}
- #endif
- if ((ip < (MATCHLIMIT - 1)) && (A16(ref) == A16(ip))) {
- ip += 2;
- ref += 2;
- }
- if ((ip < MATCHLIMIT) && (*ref == *ip))
- ip++;
-_endcount:
- /* Encode MatchLength */
- len = (int)(ip - anchor);
- /* Check output limit */
- if (unlikely(op + (1 + LASTLITERALS) + (len >> 8) > oend))
- return 0;
- if (len >= (int)ML_MASK) {
- *token += ML_MASK;
- len -= ML_MASK;
- for (; len > 509 ; len -= 510) {
- *op++ = 255;
- *op++ = 255;
- }
- if (len > 254) {
- len -= 255;
- *op++ = 255;
- }
- *op++ = (u8)len;
- } else
- *token += len;
+ anchor = ip;
- /* Test end of chunk */
- if (ip > mflimit) {
- anchor = ip;
+ /* Test end of block */
+ if (ip > mflimit)
+ break;
+ if (op > oMaxSeq)
break;
- }
/* Fill table */
- hashtable[LZ4_HASH64K_VALUE(ip-2)] = (u16)(ip - 2 - base);
+ LZ4_putPosition(ip - 2, ctx->hashTable, tableType, base);
/* Test next position */
- ref = base + hashtable[LZ4_HASH64K_VALUE(ip)];
- hashtable[LZ4_HASH64K_VALUE(ip)] = (u16)(ip - base);
- if (A32(ref) == A32(ip)) {
- token = op++;
- *token = 0;
+ match = LZ4_getPosition(ip, ctx->hashTable, tableType, base);
+ LZ4_putPosition(ip, ctx->hashTable, tableType, base);
+
+ if ((match + MAX_DISTANCE >= ip)
+ && (LZ4_read32(match) == LZ4_read32(ip))) {
+ token = op++; *token = 0;
goto _next_match;
}
/* Prepare next loop */
- anchor = ip++;
- forwardh = LZ4_HASH64K_VALUE(ip);
+ forwardH = LZ4_hashPosition(++ip, tableType);
}
_last_literals:
/* Encode Last Literals */
- lastrun = (int)(iend - anchor);
- if (op + lastrun + 1 + (lastrun - RUN_MASK + 255) / 255 > oend)
- return 0;
- if (lastrun >= (int)RUN_MASK) {
- *op++ = (RUN_MASK << ML_BITS);
- lastrun -= RUN_MASK;
- for (; lastrun > 254 ; lastrun -= 255)
- *op++ = 255;
- *op++ = (u8)lastrun;
- } else
- *op++ = (lastrun << ML_BITS);
- memcpy(op, anchor, iend - anchor);
- op += iend - anchor;
+ { size_t lastRunSize = (size_t)(iend - anchor);
+
+ if (op + 1 /* token */
+ + ((lastRunSize + 240)/255) /* litLength */
+ + lastRunSize /* literals */ > oend) {
+ /* adapt lastRunSize to fill 'dst' */
+ lastRunSize = (oend - op) - 1;
+ lastRunSize -= (lastRunSize + 240)/255;
+ }
+ ip = anchor + lastRunSize;
+
+ if (lastRunSize >= RUN_MASK) {
+ size_t accumulator = lastRunSize - RUN_MASK;
+
+ *op++ = RUN_MASK << ML_BITS;
+ for (; accumulator >= 255 ; accumulator -= 255)
+ *op++ = 255;
+ *op++ = (BYTE) accumulator;
+ } else {
+ *op++ = (BYTE)(lastRunSize<<ML_BITS);
+ }
+ memcpy(op, anchor, lastRunSize);
+ op += lastRunSize;
+ }
+
/* End */
- return (int)(((char *)op) - dest);
+ *srcSizePtr = (int) (((const char *)ip) - src);
+ return (int) (((char *)op) - dst);
}
-int lz4_compress(const unsigned char *src, size_t src_len,
- unsigned char *dst, size_t *dst_len, void *wrkmem)
+static int LZ4_compress_destSize_extState(LZ4_stream_t *state, const char *src,
+ char *dst, int *srcSizePtr, int targetDstSize)
{
- int ret = -1;
- int out_len = 0;
+ #if LZ4_ARCH64
+ tableType_t tableType = byU32;
+ #else
+ tableType_t tableType = byPtr;
+ #endif
+
+ LZ4_resetStream(state);
+
+ if (targetDstSize >= LZ4_compressBound(*srcSizePtr)) {
+ /* compression success is guaranteed */
+ return LZ4_compress_fast_extState(
+ state, src, dst, *srcSizePtr,
+ targetDstSize, 1);
+ } else {
+ if (*srcSizePtr < LZ4_64Klimit)
+ return LZ4_compress_destSize_generic(
+ &state->internal_donotuse,
+ src, dst, srcSizePtr,
+ targetDstSize, byU16);
+ else
+ return LZ4_compress_destSize_generic(
+ &state->internal_donotuse,
+ src, dst, srcSizePtr,
+ targetDstSize, tableType);
+ }
+}
- if (src_len < LZ4_64KLIMIT)
- out_len = lz4_compress64kctx(wrkmem, src, dst, src_len,
- lz4_compressbound(src_len));
- else
- out_len = lz4_compressctx(wrkmem, src, dst, src_len,
- lz4_compressbound(src_len));
- if (out_len < 0)
- goto exit;
+int LZ4_compress_destSize(const char *src, char *dst, int *srcSizePtr,
+ int targetDstSize, void *wrkmem)
+{
+ return LZ4_compress_destSize_extState(wrkmem, src, dst, srcSizePtr,
+ targetDstSize);
+}
+EXPORT_SYMBOL(LZ4_compress_destSize);
+
+/*-******************************
+ * Streaming functions
+ ********************************/
+void LZ4_resetStream(LZ4_stream_t *LZ4_stream)
+{
+ memset(LZ4_stream, 0, sizeof(LZ4_stream_t));
+}
+
+#define HASH_UNIT sizeof(reg_t)
+int LZ4_loadDict(LZ4_stream_t *LZ4_dict,
+ const char *dictionary, int dictSize)
+{
+ LZ4_stream_t_internal *dict = &LZ4_dict->internal_donotuse;
+ const BYTE *p = (const BYTE *)dictionary;
+ const BYTE * const dictEnd = p + dictSize;
+ const BYTE *base;
+
+ if ((dict->initCheck)
+ || (dict->currentOffset > 1 * GB)) {
+ /* Uninitialized structure, or reuse overflow */
+ LZ4_resetStream(LZ4_dict);
+ }
+
+ if (dictSize < (int)HASH_UNIT) {
+ dict->dictionary = NULL;
+ dict->dictSize = 0;
+ return 0;
+ }
+
+ if ((dictEnd - p) > 64 * KB)
+ p = dictEnd - 64 * KB;
+ dict->currentOffset += 64 * KB;
+ base = p - dict->currentOffset;
+ dict->dictionary = p;
+ dict->dictSize = (U32)(dictEnd - p);
+ dict->currentOffset += dict->dictSize;
+
+ while (p <= dictEnd - HASH_UNIT) {
+ LZ4_putPosition(p, dict->hashTable, byU32, base);
+ p += 3;
+ }
- *dst_len = out_len;
+ return dict->dictSize;
+}
+EXPORT_SYMBOL(LZ4_loadDict);
+
+static void LZ4_renormDictT(LZ4_stream_t_internal *LZ4_dict,
+ const BYTE *src)
+{
+ if ((LZ4_dict->currentOffset > 0x80000000) ||
+ ((uptrval)LZ4_dict->currentOffset > (uptrval)src)) {
+ /* address space overflow */
+ /* rescale hash table */
+ U32 const delta = LZ4_dict->currentOffset - 64 * KB;
+ const BYTE *dictEnd = LZ4_dict->dictionary + LZ4_dict->dictSize;
+ int i;
+
+ for (i = 0; i < LZ4_HASH_SIZE_U32; i++) {
+ if (LZ4_dict->hashTable[i] < delta)
+ LZ4_dict->hashTable[i] = 0;
+ else
+ LZ4_dict->hashTable[i] -= delta;
+ }
+ LZ4_dict->currentOffset = 64 * KB;
+ if (LZ4_dict->dictSize > 64 * KB)
+ LZ4_dict->dictSize = 64 * KB;
+ LZ4_dict->dictionary = dictEnd - LZ4_dict->dictSize;
+ }
+}
+
+int LZ4_saveDict(LZ4_stream_t *LZ4_dict, char *safeBuffer, int dictSize)
+{
+ LZ4_stream_t_internal * const dict = &LZ4_dict->internal_donotuse;
+ const BYTE * const previousDictEnd = dict->dictionary + dict->dictSize;
+
+ if ((U32)dictSize > 64 * KB) {
+ /* useless to define a dictionary > 64 * KB */
+ dictSize = 64 * KB;
+ }
+ if ((U32)dictSize > dict->dictSize)
+ dictSize = dict->dictSize;
- return 0;
-exit:
- return ret;
+ memmove(safeBuffer, previousDictEnd - dictSize, dictSize);
+
+ dict->dictionary = (const BYTE *)safeBuffer;
+ dict->dictSize = (U32)dictSize;
+
+ return dictSize;
+}
+EXPORT_SYMBOL(LZ4_saveDict);
+
+int LZ4_compress_fast_continue(LZ4_stream_t *LZ4_stream, const char *source,
+ char *dest, int inputSize, int maxOutputSize, int acceleration)
+{
+ LZ4_stream_t_internal *streamPtr = &LZ4_stream->internal_donotuse;
+ const BYTE * const dictEnd = streamPtr->dictionary
+ + streamPtr->dictSize;
+
+ const BYTE *smallest = (const BYTE *) source;
+
+ if (streamPtr->initCheck) {
+ /* Uninitialized structure detected */
+ return 0;
+ }
+
+ if ((streamPtr->dictSize > 0) && (smallest > dictEnd))
+ smallest = dictEnd;
+
+ LZ4_renormDictT(streamPtr, smallest);
+
+ if (acceleration < 1)
+ acceleration = LZ4_ACCELERATION_DEFAULT;
+
+ /* Check overlapping input/dictionary space */
+ { const BYTE *sourceEnd = (const BYTE *) source + inputSize;
+
+ if ((sourceEnd > streamPtr->dictionary)
+ && (sourceEnd < dictEnd)) {
+ streamPtr->dictSize = (U32)(dictEnd - sourceEnd);
+ if (streamPtr->dictSize > 64 * KB)
+ streamPtr->dictSize = 64 * KB;
+ if (streamPtr->dictSize < 4)
+ streamPtr->dictSize = 0;
+ streamPtr->dictionary = dictEnd - streamPtr->dictSize;
+ }
+ }
+
+ /* prefix mode : source data follows dictionary */
+ if (dictEnd == (const BYTE *)source) {
+ int result;
+
+ if ((streamPtr->dictSize < 64 * KB) &&
+ (streamPtr->dictSize < streamPtr->currentOffset)) {
+ result = LZ4_compress_generic(
+ streamPtr, source, dest, inputSize,
+ maxOutputSize, limitedOutput, byU32,
+ withPrefix64k, dictSmall, acceleration);
+ } else {
+ result = LZ4_compress_generic(
+ streamPtr, source, dest, inputSize,
+ maxOutputSize, limitedOutput, byU32,
+ withPrefix64k, noDictIssue, acceleration);
+ }
+ streamPtr->dictSize += (U32)inputSize;
+ streamPtr->currentOffset += (U32)inputSize;
+ return result;
+ }
+
+ /* external dictionary mode */
+ { int result;
+
+ if ((streamPtr->dictSize < 64 * KB) &&
+ (streamPtr->dictSize < streamPtr->currentOffset)) {
+ result = LZ4_compress_generic(
+ streamPtr, source, dest, inputSize,
+ maxOutputSize, limitedOutput, byU32,
+ usingExtDict, dictSmall, acceleration);
+ } else {
+ result = LZ4_compress_generic(
+ streamPtr, source, dest, inputSize,
+ maxOutputSize, limitedOutput, byU32,
+ usingExtDict, noDictIssue, acceleration);
+ }
+ streamPtr->dictionary = (const BYTE *)source;
+ streamPtr->dictSize = (U32)inputSize;
+ streamPtr->currentOffset += (U32)inputSize;
+ return result;
+ }
+}
+EXPORT_SYMBOL(LZ4_compress_fast_continue);
+
+/*-******************************
+ * For backwards compatibility
+ ********************************/
+int lz4_compress(const unsigned char *src, size_t src_len, unsigned char *dst,
+ size_t *dst_len, void *wrkmem) {
+ *dst_len = LZ4_compress_default(src, dst, (int)src_len,
+ (int)((size_t)dst_len), wrkmem);
+
+ /*
+ * Prior lz4_compress will return -1 in case of error
+ * and 0 on success
+ * while new LZ4_compress_fast/default
+ * returns 0 in case of error
+ * and the output length on success
+ */
+ if (!dst_len)
+ return -1;
+ else
+ return 0;
}
EXPORT_SYMBOL(lz4_compress);
diff --git a/lib/lz4/lz4_decompress.c b/lib/lz4/lz4_decompress.c
index 6d940c7..ca71375 100644
--- a/lib/lz4/lz4_decompress.c
+++ b/lib/lz4/lz4_decompress.c
@@ -1,25 +1,16 @@
/*
- * LZ4 Decompressor for Linux kernel
- *
- * Copyright (C) 2013, LG Electronics, Kyungsik Lee <kyungsik.lee@lge.com>
- *
- * Based on LZ4 implementation by Yann Collet.
- *
* LZ4 - Fast LZ compression algorithm
- * Copyright (C) 2011-2012, Yann Collet.
- * BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
- *
+ * Copyright (C) 2011 - 2016, Yann Collet.
+ * BSD 2 - Clause License (http://www.opensource.org/licenses/bsd - license.php)
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions are
* met:
- *
- * * Redistributions of source code must retain the above copyright
+ * * Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
- * * Redistributions in binary form must reproduce the above
+ * * Redistributions in binary form must reproduce the above
* copyright notice, this list of conditions and the following disclaimer
* in the documentation and/or other materials provided with the
* distribution.
- *
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
@@ -31,313 +22,508 @@
* THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
* OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ * You can contact the author at :
+ * - LZ4 homepage : http://www.lz4.org
+ * - LZ4 source repository : https://github.com/lz4/lz4
*
- * You can contact the author at :
- * - LZ4 homepage : http://fastcompression.blogspot.com/p/lz4.html
- * - LZ4 source repository : http://code.google.com/p/lz4/
+ * Changed for kernel usage by:
+ * Sven Schmidt <4sschmid@informatik.uni-hamburg.de>
*/
-#ifndef STATIC
+/*-************************************
+ * Dependencies
+ **************************************/
+#include <linux/lz4.h>
+#include "lz4defs.h"
+#include <linux/init.h>
#include <linux/module.h>
#include <linux/kernel.h>
-#endif
-#include <linux/lz4.h>
-
#include <asm/unaligned.h>
-#include "lz4defs.h"
-
-static const int dec32table[] = {0, 3, 2, 3, 0, 0, 0, 0};
-#if LZ4_ARCH64
-static const int dec64table[] = {0, 0, 0, -1, 0, 1, 2, 3};
-#endif
-
-static int lz4_uncompress(const char *source, char *dest, int osize)
+/*-*****************************
+ * Decompression functions
+ *******************************/
+/* LZ4_decompress_generic() :
+ * This generic decompression function cover all use cases.
+ * It shall be instantiated several times, using different sets of directives
+ * Note that it is important this generic function is really inlined,
+ * in order to remove useless branches during compilation optimization.
+ */
+static inline int LZ4_decompress_generic(
+ const char *const source,
+ char * const dest,
+ int inputSize,
+ /*
+ * If endOnInput == endOnInputSize,
+ * this value is the max size of Output Buffer.
+ */
+ int outputSize,
+ /* endOnOutputSize, endOnInputSize */
+ int endOnInput,
+ /* full, partial */
+ int partialDecoding,
+ /* only used if partialDecoding == partial */
+ int targetOutputSize,
+ /* noDict, withPrefix64k, usingExtDict */
+ int dict,
+ /* == dest when no prefix */
+ const BYTE * const lowPrefix,
+ /* only if dict == usingExtDict */
+ const BYTE * const dictStart,
+ /* note : = 0 if noDict */
+ const size_t dictSize
+ )
{
+ /* Local Variables */
const BYTE *ip = (const BYTE *) source;
- const BYTE *ref;
+ const BYTE * const iend = ip + inputSize;
+
BYTE *op = (BYTE *) dest;
- BYTE * const oend = op + osize;
+ BYTE * const oend = op + outputSize;
BYTE *cpy;
- unsigned token;
- size_t length;
+ BYTE *oexit = op + targetOutputSize;
+ const BYTE * const lowLimit = lowPrefix - dictSize;
+
+ const BYTE * const dictEnd = (const BYTE *)dictStart + dictSize;
+ const unsigned int dec32table[] = {0, 1, 2, 1, 4, 4, 4, 4};
+ const int dec64table[] = {0, 0, 0, -1, 0, 1, 2, 3};
+
+ const int safeDecode = (endOnInput == endOnInputSize);
+ const int checkOffset = ((safeDecode) && (dictSize < (int)(64 * KB)));
+ /* Special cases */
+ /* targetOutputSize too high => decode everything */
+ if ((partialDecoding) && (oexit > oend - MFLIMIT))
+ oexit = oend - MFLIMIT;
+
+ /* Empty output buffer */
+ if ((endOnInput) && (unlikely(outputSize == 0)))
+ return ((inputSize == 1) && (*ip == 0)) ? 0 : -1;
+
+ if ((!endOnInput) && (unlikely(outputSize == 0)))
+ return (*ip == 0 ? 1 : -1);
+
+ /* Main Loop : decode sequences */
while (1) {
+ size_t length;
+ const BYTE *match;
+ size_t offset;
+
+ /* get literal length */
+ unsigned int const token = *ip++;
+
+ length = token>>ML_BITS;
- /* get runlength */
- token = *ip++;
- length = (token >> ML_BITS);
if (length == RUN_MASK) {
- size_t len;
+ unsigned int s;
- len = *ip++;
- for (; len == 255; length += 255)
- len = *ip++;
- if (unlikely(length > (size_t)(length + len)))
+ do {
+ s = *ip++;
+ length += s;
+ } while (likely(endOnInput
+ ? ip < iend - RUN_MASK
+ : 1) & (s == 255));
+
+ if ((safeDecode)
+ && unlikely(
+ (size_t)(op + length) < (size_t)(op))) {
+ /* overflow detection */
goto _output_error;
- length += len;
+ }
+ if ((safeDecode)
+ && unlikely(
+ (size_t)(ip + length) < (size_t)(ip))) {
+ /* overflow detection */
+ goto _output_error;
+ }
}
/* copy literals */
cpy = op + length;
- if (unlikely(cpy > oend - COPYLENGTH)) {
- /*
- * Error: not enough place for another match
- * (min 4) + 5 literals
- */
- if (cpy != oend)
- goto _output_error;
-
+ if (((endOnInput) && ((cpy > (partialDecoding ? oexit : oend - MFLIMIT))
+ || (ip + length > iend - (2 + 1 + LASTLITERALS))))
+ || ((!endOnInput) && (cpy > oend - WILDCOPYLENGTH))) {
+ if (partialDecoding) {
+ if (cpy > oend) {
+ /*
+ * Error :
+ * write attempt beyond end of output buffer
+ */
+ goto _output_error;
+ }
+ if ((endOnInput)
+ && (ip + length > iend)) {
+ /*
+ * Error :
+ * read attempt beyond
+ * end of input buffer
+ */
+ goto _output_error;
+ }
+ } else {
+ if ((!endOnInput)
+ && (cpy != oend)) {
+ /*
+ * Error :
+ * block decoding must
+ * stop exactly there
+ */
+ goto _output_error;
+ }
+ if ((endOnInput)
+ && ((ip + length != iend)
+ || (cpy > oend))) {
+ /*
+ * Error :
+ * input must be consumed
+ */
+ goto _output_error;
+ }
+ }
memcpy(op, ip, length);
ip += length;
- break; /* EOF */
+ op += length;
+ /* Necessarily EOF, due to parsing restrictions */
+ break;
}
- LZ4_WILDCOPY(ip, op, cpy);
- ip -= (op - cpy);
- op = cpy;
+ LZ4_wildCopy(op, ip, cpy);
+ ip += length; op = cpy;
/* get offset */
- LZ4_READ_LITTLEENDIAN_16(ref, cpy, ip);
- ip += 2;
-
- /* Error: offset create reference outside destination buffer */
- if (unlikely(ref < (BYTE *const) dest))
+ offset = LZ4_readLE16(ip); ip += 2;
+ match = op - offset;
+ if ((checkOffset) && (unlikely(match < lowLimit))) {
+ /* Error : offset outside buffers */
goto _output_error;
+ }
+ /* costs ~1%; silence an msan warning when offset == 0 */
+ LZ4_write32(op, (U32)offset);
/* get matchlength */
length = token & ML_MASK;
if (length == ML_MASK) {
- for (; *ip == 255; length += 255)
- ip++;
- if (unlikely(length > (size_t)(length + *ip)))
+ unsigned int s;
+
+ do {
+ s = *ip++;
+ if ((endOnInput) && (ip > iend - LASTLITERALS))
+ goto _output_error;
+ length += s;
+ } while (s == 255);
+ if ((safeDecode)
+ && unlikely(
+ (size_t)(op + length) < (size_t)op)) {
+ /* overflow detection */
goto _output_error;
- length += *ip++;
+ }
}
+ length += MINMATCH;
+
+ /* check external dictionary */
+ if ((dict == usingExtDict) && (match < lowPrefix)) {
+ if (unlikely(op + length > oend - LASTLITERALS)) {
+ /* doesn't respect parsing restriction */
+ goto _output_error;
+ }
- /* copy repeated sequence */
- if (unlikely((op - ref) < STEPSIZE)) {
-#if LZ4_ARCH64
- int dec64 = dec64table[op - ref];
-#else
- const int dec64 = 0;
-#endif
- op[0] = ref[0];
- op[1] = ref[1];
- op[2] = ref[2];
- op[3] = ref[3];
- op += 4;
- ref += 4;
- ref -= dec32table[op-ref];
- PUT4(ref, op);
- op += STEPSIZE - 4;
- ref -= dec64;
+ if (length <= (size_t)(lowPrefix - match)) {
+ /*
+ * match can be copied as a single segment
+ * from external dictionary
+ */
+ memmove(op, dictEnd - (lowPrefix - match), length);
+ op += length;
+ } else {
+ /*
+ * match encompass external
+ * dictionary and current block
+ */
+ size_t const copySize = (size_t)(lowPrefix - match);
+ size_t const restSize = length - copySize;
+
+ memcpy(op, dictEnd - copySize, copySize);
+ op += copySize;
+
+ if (restSize > (size_t)(op - lowPrefix)) {
+ /* overlap copy */
+ BYTE * const endOfMatch = op + restSize;
+ const BYTE *copyFrom = lowPrefix;
+
+ while (op < endOfMatch)
+ *op++ = *copyFrom++;
+ } else {
+ memcpy(op, lowPrefix, restSize);
+ op += restSize;
+ }
+ }
+ continue;
+ }
+
+ /* copy match within block */
+ cpy = op + length;
+ if (unlikely(offset < 8)) {
+ const int dec64 = dec64table[offset];
+
+ op[0] = match[0];
+ op[1] = match[1];
+ op[2] = match[2];
+ op[3] = match[3];
+ match += dec32table[offset];
+ memcpy(op + 4, match, 4);
+ match -= dec64;
} else {
- LZ4_COPYSTEP(ref, op);
+ LZ4_copy8(op, match); match += 8;
}
- cpy = op + length - (STEPSIZE - 4);
- if (cpy > (oend - COPYLENGTH)) {
- /* Error: request to write beyond destination buffer */
- if (cpy > oend)
- goto _output_error;
-#if LZ4_ARCH64
- if ((ref + COPYLENGTH) > oend)
-#else
- if ((ref + COPYLENGTH) > oend ||
- (op + COPYLENGTH) > oend)
-#endif
+ op += 8;
+
+ if (unlikely(cpy > oend - 12)) {
+ BYTE * const oCopyLimit = oend - (WILDCOPYLENGTH - 1);
+
+ if (cpy > oend - LASTLITERALS) {
+ /*
+ * Error : last LASTLITERALS bytes
+ * must be literals (uncompressed)
+ */
goto _output_error;
- LZ4_SECURECOPY(ref, op, (oend - COPYLENGTH));
+ }
+ if (op < oCopyLimit) {
+ LZ4_wildCopy(op, match, oCopyLimit);
+ match += oCopyLimit - op;
+ op = oCopyLimit;
+ }
while (op < cpy)
- *op++ = *ref++;
- op = cpy;
- /*
- * Check EOF (should never happen, since last 5 bytes
- * are supposed to be literals)
- */
- if (op == oend)
- goto _output_error;
- continue;
+ *op++ = *match++;
+ } else {
+ LZ4_copy8(op, match);
+ if (length > 16)
+ LZ4_wildCopy(op + 8, match + 8, cpy);
}
- LZ4_SECURECOPY(ref, op, cpy);
op = cpy; /* correction */
}
+
/* end of decoding */
- return (int) (((char *)ip) - source);
+ if (endOnInput) {
+ /* Nb of output bytes decoded */
+ return (int) (((char *)op) - dest);
+ } else {
+ /* Nb of input bytes read */
+ return (int) (((const char *)ip) - source);
+ }
- /* write overflow error detected */
+ /* Overflow error detected */
_output_error:
return -1;
}
-static int lz4_uncompress_unknownoutputsize(const char *source, char *dest,
- int isize, size_t maxoutputsize)
+int LZ4_decompress_safe(const char *source, char *dest,
+ int compressedSize, int maxDecompressedSize)
{
- const BYTE *ip = (const BYTE *) source;
- const BYTE *const iend = ip + isize;
- const BYTE *ref;
-
+ return LZ4_decompress_generic(source, dest, compressedSize,
+ maxDecompressedSize, endOnInputSize, full, 0,
+ noDict, (BYTE *)dest, NULL, 0);
+}
+EXPORT_SYMBOL(LZ4_decompress_safe);
- BYTE *op = (BYTE *) dest;
- BYTE * const oend = op + maxoutputsize;
- BYTE *cpy;
+int LZ4_decompress_safe_partial(const char *source, char *dest,
+ int compressedSize, int targetOutputSize, int maxDecompressedSize)
+{
+ return LZ4_decompress_generic(source, dest, compressedSize,
+ maxDecompressedSize, endOnInputSize, partial,
+ targetOutputSize, noDict, (BYTE *)dest, NULL, 0);
+}
+EXPORT_SYMBOL(LZ4_decompress_safe_partial);
- /* Main Loop */
- while (ip < iend) {
+int LZ4_decompress_fast(const char *source, char *dest, int originalSize)
+{
+ return LZ4_decompress_generic(source, dest, 0, originalSize,
+ endOnOutputSize, full, 0, withPrefix64k,
+ (BYTE *)(dest - 64 * KB), NULL, 64 * KB);
+}
+EXPORT_SYMBOL(LZ4_decompress_fast);
- unsigned token;
- size_t length;
+int LZ4_setStreamDecode(LZ4_streamDecode_t *LZ4_streamDecode,
+ const char *dictionary, int dictSize)
+{
+ LZ4_streamDecode_t_internal *lz4sd = (LZ4_streamDecode_t_internal *) LZ4_streamDecode;
- /* get runlength */
- token = *ip++;
- length = (token >> ML_BITS);
- if (length == RUN_MASK) {
- int s = 255;
- while ((ip < iend) && (s == 255)) {
- s = *ip++;
- if (unlikely(length > (size_t)(length + s)))
- goto _output_error;
- length += s;
- }
- }
- /* copy literals */
- cpy = op + length;
- if ((cpy > oend - COPYLENGTH) ||
- (ip + length > iend - COPYLENGTH)) {
-
- if (cpy > oend)
- goto _output_error;/* writes beyond buffer */
-
- if (ip + length != iend)
- goto _output_error;/*
- * Error: LZ4 format requires
- * to consume all input
- * at this stage
- */
- memcpy(op, ip, length);
- op += length;
- break;/* Necessarily EOF, due to parsing restrictions */
- }
- LZ4_WILDCOPY(ip, op, cpy);
- ip -= (op - cpy);
- op = cpy;
+ lz4sd->prefixSize = (size_t) dictSize;
+ lz4sd->prefixEnd = (const BYTE *) dictionary + dictSize;
+ lz4sd->externalDict = NULL;
+ lz4sd->extDictSize = 0;
+ return 1;
+}
+EXPORT_SYMBOL(LZ4_setStreamDecode);
- /* get offset */
- LZ4_READ_LITTLEENDIAN_16(ref, cpy, ip);
- ip += 2;
- if (ref < (BYTE * const) dest)
- goto _output_error;
- /*
- * Error : offset creates reference
- * outside of destination buffer
- */
+/*
+ * *_continue() :
+ * These decoding functions allow decompression of multiple blocks
+ * in "streaming" mode.
+ * Previously decoded blocks must still be available at the memory
+ * position where they were decoded.
+ * If it's not possible, save the relevant part of
+ * decoded data into a safe buffer,
+ * and indicate where it stands using LZ4_setStreamDecode()
+ */
+int LZ4_decompress_safe_continue(LZ4_streamDecode_t *LZ4_streamDecode,
+ const char *source, char *dest, int compressedSize, int maxOutputSize)
+{
+ LZ4_streamDecode_t_internal *lz4sd = &LZ4_streamDecode->internal_donotuse;
+ int result;
+
+ if (lz4sd->prefixEnd == (BYTE *)dest) {
+ result = LZ4_decompress_generic(source, dest,
+ compressedSize,
+ maxOutputSize,
+ endOnInputSize, full, 0,
+ usingExtDict, lz4sd->prefixEnd - lz4sd->prefixSize,
+ lz4sd->externalDict,
+ lz4sd->extDictSize);
+
+ if (result <= 0)
+ return result;
+
+ lz4sd->prefixSize += result;
+ lz4sd->prefixEnd += result;
+ } else {
+ lz4sd->extDictSize = lz4sd->prefixSize;
+ lz4sd->externalDict = lz4sd->prefixEnd - lz4sd->extDictSize;
+ result = LZ4_decompress_generic(source, dest,
+ compressedSize, maxOutputSize,
+ endOnInputSize, full, 0,
+ usingExtDict, (BYTE *)dest,
+ lz4sd->externalDict, lz4sd->extDictSize);
+ if (result <= 0)
+ return result;
+ lz4sd->prefixSize = result;
+ lz4sd->prefixEnd = (BYTE *)dest + result;
+ }
- /* get matchlength */
- length = (token & ML_MASK);
- if (length == ML_MASK) {
- while (ip < iend) {
- int s = *ip++;
- if (unlikely(length > (size_t)(length + s)))
- goto _output_error;
- length += s;
- if (s == 255)
- continue;
- break;
- }
- }
+ return result;
+}
+EXPORT_SYMBOL(LZ4_decompress_safe_continue);
- /* copy repeated sequence */
- if (unlikely((op - ref) < STEPSIZE)) {
-#if LZ4_ARCH64
- int dec64 = dec64table[op - ref];
-#else
- const int dec64 = 0;
-#endif
- op[0] = ref[0];
- op[1] = ref[1];
- op[2] = ref[2];
- op[3] = ref[3];
- op += 4;
- ref += 4;
- ref -= dec32table[op - ref];
- PUT4(ref, op);
- op += STEPSIZE - 4;
- ref -= dec64;
- } else {
- LZ4_COPYSTEP(ref, op);
- }
- cpy = op + length - (STEPSIZE-4);
- if (cpy > oend - COPYLENGTH) {
- if (cpy > oend)
- goto _output_error; /* write outside of buf */
-#if LZ4_ARCH64
- if ((ref + COPYLENGTH) > oend)
-#else
- if ((ref + COPYLENGTH) > oend ||
- (op + COPYLENGTH) > oend)
-#endif
- goto _output_error;
- LZ4_SECURECOPY(ref, op, (oend - COPYLENGTH));
- while (op < cpy)
- *op++ = *ref++;
- op = cpy;
- /*
- * Check EOF (should never happen, since last 5 bytes
- * are supposed to be literals)
- */
- if (op == oend)
- goto _output_error;
- continue;
- }
- LZ4_SECURECOPY(ref, op, cpy);
- op = cpy; /* correction */
+int LZ4_decompress_fast_continue(LZ4_streamDecode_t *LZ4_streamDecode,
+ const char *source, char *dest, int originalSize)
+{
+ LZ4_streamDecode_t_internal *lz4sd = &LZ4_streamDecode->internal_donotuse;
+ int result;
+
+ if (lz4sd->prefixEnd == (BYTE *)dest) {
+ result = LZ4_decompress_generic(source, dest, 0, originalSize,
+ endOnOutputSize, full, 0,
+ usingExtDict,
+ lz4sd->prefixEnd - lz4sd->prefixSize,
+ lz4sd->externalDict, lz4sd->extDictSize);
+
+ if (result <= 0)
+ return result;
+
+ lz4sd->prefixSize += originalSize;
+ lz4sd->prefixEnd += originalSize;
+ } else {
+ lz4sd->extDictSize = lz4sd->prefixSize;
+ lz4sd->externalDict = lz4sd->prefixEnd - lz4sd->extDictSize;
+ result = LZ4_decompress_generic(source, dest, 0, originalSize,
+ endOnOutputSize, full, 0,
+ usingExtDict, (BYTE *)dest,
+ lz4sd->externalDict, lz4sd->extDictSize);
+ if (result <= 0)
+ return result;
+ lz4sd->prefixSize = originalSize;
+ lz4sd->prefixEnd = (BYTE *)dest + originalSize;
}
- /* end of decoding */
- return (int) (((char *) op) - dest);
- /* write overflow error detected */
-_output_error:
- return -1;
+ return result;
}
+EXPORT_SYMBOL(LZ4_decompress_fast_continue);
-int lz4_decompress(const unsigned char *src, size_t *src_len,
- unsigned char *dest, size_t actual_dest_len)
+/*
+ * Advanced decoding functions :
+ * *_usingDict() :
+ * These decoding functions work the same as "_continue" ones,
+ * the dictionary must be explicitly provided within parameters
+ */
+static inline int LZ4_decompress_usingDict_generic(const char *source,
+ char *dest, int compressedSize, int maxOutputSize, int safe,
+ const char *dictStart, int dictSize)
{
- int ret = -1;
- int input_len = 0;
-
- input_len = lz4_uncompress(src, dest, actual_dest_len);
- if (input_len < 0)
- goto exit_0;
- *src_len = input_len;
+ if (dictSize == 0)
+ return LZ4_decompress_generic(source, dest,
+ compressedSize, maxOutputSize, safe, full, 0,
+ noDict, (BYTE *)dest, NULL, 0);
+ if (dictStart + dictSize == dest) {
+ if (dictSize >= (int)(64 * KB - 1))
+ return LZ4_decompress_generic(source, dest,
+ compressedSize, maxOutputSize, safe, full, 0,
+ withPrefix64k, (BYTE *)dest - 64 * KB, NULL, 0);
+ return LZ4_decompress_generic(source, dest, compressedSize,
+ maxOutputSize, safe, full, 0, noDict,
+ (BYTE *)dest - dictSize, NULL, 0);
+ }
+ return LZ4_decompress_generic(source, dest, compressedSize,
+ maxOutputSize, safe, full, 0, usingExtDict,
+ (BYTE *)dest, (const BYTE *)dictStart, dictSize);
+}
- return 0;
-exit_0:
- return ret;
+int LZ4_decompress_safe_usingDict(const char *source, char *dest,
+ int compressedSize, int maxOutputSize,
+ const char *dictStart, int dictSize)
+{
+ return LZ4_decompress_usingDict_generic(source, dest,
+ compressedSize, maxOutputSize, 1, dictStart, dictSize);
}
-#ifndef STATIC
-EXPORT_SYMBOL(lz4_decompress);
-#endif
+EXPORT_SYMBOL(LZ4_decompress_safe_usingDict);
-int lz4_decompress_unknownoutputsize(const unsigned char *src, size_t src_len,
- unsigned char *dest, size_t *dest_len)
+int LZ4_decompress_fast_usingDict(const char *source, char *dest,
+ int originalSize, const char *dictStart, int dictSize)
{
- int ret = -1;
- int out_len = 0;
-
- out_len = lz4_uncompress_unknownoutputsize(src, dest, src_len,
- *dest_len);
- if (out_len < 0)
- goto exit_0;
- *dest_len = out_len;
-
- return 0;
-exit_0:
- return ret;
+ return LZ4_decompress_usingDict_generic(source, dest, 0,
+ originalSize, 0, dictStart, dictSize);
+}
+EXPORT_SYMBOL(LZ4_decompress_fast_usingDict);
+
+/*-******************************
+ * For backwards compatibility
+ ********************************/
+int lz4_decompress_unknownoutputsize(const unsigned char *src,
+ size_t src_len, unsigned char *dest, size_t *dest_len) {
+ *dest_len = LZ4_decompress_safe(src, dest,
+ (int)src_len, (int)((size_t)dest_len));
+
+ /*
+ * Prior lz4_decompress_unknownoutputsize will return
+ * 0 for success and a negative result for error
+ * new LZ4_decompress_safe returns
+ * - the length of data read on success
+ * - and also a negative result on error
+ * meaning when result > 0, we just return 0 here
+ */
+ if (src_len > 0) {
+ return 0;
+ } else
+ return -1;
}
-#ifndef STATIC
EXPORT_SYMBOL(lz4_decompress_unknownoutputsize);
+int lz4_decompress(const unsigned char *src, size_t *src_len,
+ unsigned char *dest, size_t actual_dest_len) {
+ *src_len = LZ4_decompress_fast(src, dest, (int)actual_dest_len);
+
+ /*
+ * Prior lz4_decompress will return
+ * 0 for success and a negative result for error
+ * new LZ4_decompress_fast returns
+ * - the length of data read on success
+ * - and also a negative result on error
+ * meaning when result > 0, we just return 0 here
+ */
+ if ((int)((size_t)src_len) > 0)
+ return 0;
+ else
+ return -1;
+}
+EXPORT_SYMBOL(lz4_decompress);
+
MODULE_LICENSE("Dual BSD/GPL");
-MODULE_DESCRIPTION("LZ4 Decompressor");
-#endif
+MODULE_DESCRIPTION("LZ4 decompressor");
diff --git a/lib/lz4/lz4defs.h b/lib/lz4/lz4defs.h
index c79d7ea..b0d21b5 100644
--- a/lib/lz4/lz4defs.h
+++ b/lib/lz4/lz4defs.h
@@ -1,157 +1,219 @@
+#ifndef __LZ4DEFS_H__
+#define __LZ4DEFS_H__
+
/*
- * lz4defs.h -- architecture specific defines
- *
- * Copyright (C) 2013, LG Electronics, Kyungsik Lee <kyungsik.lee@lge.com>
+ * lz4defs.h -- common and architecture specific defines for the kernel usage
+
+ * LZ4 - Fast LZ compression algorithm
+ * Copyright (C) 2011-2016, Yann Collet.
+ * BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are
+ * met:
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above
+ * copyright notice, this list of conditions and the following disclaimer
+ * in the documentation and/or other materials provided with the
+ * distribution.
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ * You can contact the author at :
+ * - LZ4 homepage : http://www.lz4.org
+ * - LZ4 source repository : https://github.com/lz4/lz4
*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
+ * Changed for kernel usage by:
+ * Sven Schmidt <4sschmid@informatik.uni-hamburg.de>
*/
+#include <asm/unaligned.h>
+#include <linux/string.h> /* memset, memcpy */
+
/*
* Detects 64 bits mode
- */
+*/
#if defined(CONFIG_64BIT)
#define LZ4_ARCH64 1
#else
#define LZ4_ARCH64 0
#endif
-/*
- * Architecture-specific macros
- */
-#define BYTE u8
-typedef struct _U16_S { u16 v; } U16_S;
-typedef struct _U32_S { u32 v; } U32_S;
-typedef struct _U64_S { u64 v; } U64_S;
-#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)
-
-#define A16(x) (((U16_S *)(x))->v)
-#define A32(x) (((U32_S *)(x))->v)
-#define A64(x) (((U64_S *)(x))->v)
-
-#define PUT4(s, d) (A32(d) = A32(s))
-#define PUT8(s, d) (A64(d) = A64(s))
-
-#define LZ4_READ_LITTLEENDIAN_16(d, s, p) \
- (d = s - A16(p))
-
-#define LZ4_WRITE_LITTLEENDIAN_16(p, v) \
- do { \
- A16(p) = v; \
- p += 2; \
- } while (0)
-#else /* CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS */
-
-#define A64(x) get_unaligned((u64 *)&(((U16_S *)(x))->v))
-#define A32(x) get_unaligned((u32 *)&(((U16_S *)(x))->v))
-#define A16(x) get_unaligned((u16 *)&(((U16_S *)(x))->v))
-
-#define PUT4(s, d) \
- put_unaligned(get_unaligned((const u32 *) s), (u32 *) d)
-#define PUT8(s, d) \
- put_unaligned(get_unaligned((const u64 *) s), (u64 *) d)
-
-#define LZ4_READ_LITTLEENDIAN_16(d, s, p) \
- (d = s - get_unaligned_le16(p))
-
-#define LZ4_WRITE_LITTLEENDIAN_16(p, v) \
- do { \
- put_unaligned_le16(v, (u16 *)(p)); \
- p += 2; \
- } while (0)
+/*-************************************
+ * Basic Types
+ **************************************/
+#include <linux/types.h>
+
+typedef uint8_t BYTE;
+typedef uint16_t U16;
+typedef uint32_t U32;
+typedef int32_t S32;
+typedef uint64_t U64;
+typedef uintptr_t uptrval;
+
+#if defined(__x86_64__)
+ typedef U64 reg_t; /* 64-bits in x32 mode */
+#else
+ typedef size_t reg_t; /* 32-bits in x32 mode */
#endif
-#define COPYLENGTH 8
-#define ML_BITS 4
-#define ML_MASK ((1U << ML_BITS) - 1)
-#define RUN_BITS (8 - ML_BITS)
-#define RUN_MASK ((1U << RUN_BITS) - 1)
-#define MEMORY_USAGE 14
-#define MINMATCH 4
-#define SKIPSTRENGTH 6
-#define LASTLITERALS 5
-#define MFLIMIT (COPYLENGTH + MINMATCH)
-#define MINLENGTH (MFLIMIT + 1)
-#define MAXD_LOG 16
-#define MAXD (1 << MAXD_LOG)
-#define MAXD_MASK (u32)(MAXD - 1)
-#define MAX_DISTANCE (MAXD - 1)
-#define HASH_LOG (MAXD_LOG - 1)
-#define HASHTABLESIZE (1 << HASH_LOG)
-#define MAX_NB_ATTEMPTS 256
-#define OPTIMAL_ML (int)((ML_MASK-1)+MINMATCH)
-#define LZ4_64KLIMIT ((1<<16) + (MFLIMIT - 1))
-#define HASHLOG64K ((MEMORY_USAGE - 2) + 1)
-#define HASH64KTABLESIZE (1U << HASHLOG64K)
-#define LZ4_HASH_VALUE(p) (((A32(p)) * 2654435761U) >> \
- ((MINMATCH * 8) - (MEMORY_USAGE-2)))
-#define LZ4_HASH64K_VALUE(p) (((A32(p)) * 2654435761U) >> \
- ((MINMATCH * 8) - HASHLOG64K))
-#define HASH_VALUE(p) (((A32(p)) * 2654435761U) >> \
- ((MINMATCH * 8) - HASH_LOG))
-
-#if LZ4_ARCH64/* 64-bit */
-#define STEPSIZE 8
-
-#define LZ4_COPYSTEP(s, d) \
- do { \
- PUT8(s, d); \
- d += 8; \
- s += 8; \
- } while (0)
-
-#define LZ4_COPYPACKET(s, d) LZ4_COPYSTEP(s, d)
-
-#define LZ4_SECURECOPY(s, d, e) \
- do { \
- if (d < e) { \
- LZ4_WILDCOPY(s, d, e); \
- } \
- } while (0)
-#define HTYPE u32
-
-#ifdef __BIG_ENDIAN
-#define LZ4_NBCOMMONBYTES(val) (__builtin_clzll(val) >> 3)
+/*-************************************
+ * Constants
+ **************************************/
+#define MINMATCH 4
+
+#define WILDCOPYLENGTH 8
+#define LASTLITERALS 5
+#define MFLIMIT (WILDCOPYLENGTH+MINMATCH)
+static const int LZ4_minLength = (MFLIMIT+1);
+
+#define KB (1<<10)
+#define MB (1<<20)
+#define GB (1U<<30)
+
+#define MAXD_LOG 16
+#define MAX_DISTANCE ((1<<MAXD_LOG) - 1)
+#define STEPSIZE sizeof(size_t)
+
+#define ML_BITS 4
+#define ML_MASK ((1U<<ML_BITS)-1)
+#define RUN_BITS (8-ML_BITS)
+#define RUN_MASK ((1U<<RUN_BITS)-1)
+
+static const int LZ4_64Klimit = ((64 * KB) + (MFLIMIT-1));
+static const U32 LZ4_skipTrigger = 6;
+
+/*-************************************
+ * Reading and writing into memory
+ **************************************/
+
+static inline U16 LZ4_read16(const void *memPtr)
+{
+ U16 val; memcpy(&val, memPtr, sizeof(val)); return val;
+}
+
+static inline U32 LZ4_read32(const void *memPtr)
+{
+ U32 val; memcpy(&val, memPtr, sizeof(val)); return val;
+}
+
+static inline size_t LZ4_read_ARCH(const void *memPtr)
+{
+ size_t val; memcpy(&val, memPtr, sizeof(val)); return val;
+}
+
+static inline void LZ4_write16(void *memPtr, U16 value)
+{
+ memcpy(memPtr, &value, sizeof(value));
+}
+
+static inline void LZ4_write32(void *memPtr, U32 value)
+{
+ memcpy(memPtr, &value, sizeof(value));
+}
+
+static inline U16 LZ4_readLE16(const void *memPtr)
+{
+#ifdef __LITTLE_ENDIAN__
+ return LZ4_read16(memPtr);
#else
-#define LZ4_NBCOMMONBYTES(val) (__builtin_ctzll(val) >> 3)
+ const BYTE *p = (const BYTE *)memPtr;
+
+ return (U16)((U16)p[0] + (p[1] << 8));
#endif
+}
+
+static inline void LZ4_writeLE16(void *memPtr, U16 value)
+{
+#ifdef __LITTLE_ENDIAN__
+ LZ4_write16(memPtr, value);
+#else
+ BYTE *p = (BYTE *)memPtr;
-#else /* 32-bit */
-#define STEPSIZE 4
+ p[0] = (BYTE) value;
+ p[1] = (BYTE)(value>>8);
+#endif
+}
-#define LZ4_COPYSTEP(s, d) \
- do { \
- PUT4(s, d); \
- d += 4; \
- s += 4; \
- } while (0)
+static inline void LZ4_copy8(void *dst, const void *src)
+{
+ memcpy(dst, src, 8);
+}
-#define LZ4_COPYPACKET(s, d) \
- do { \
- LZ4_COPYSTEP(s, d); \
- LZ4_COPYSTEP(s, d); \
- } while (0)
+/*
+ * customized variant of memcpy,
+ * which can overwrite up to 7 bytes beyond dstEnd
+ */
+static inline void LZ4_wildCopy(void *dstPtr, const void *srcPtr, void *dstEnd)
+{
+ BYTE *d = (BYTE *)dstPtr;
+ const BYTE *s = (const BYTE *)srcPtr;
+ BYTE *const e = (BYTE *)dstEnd;
-#define LZ4_SECURECOPY LZ4_WILDCOPY
-#define HTYPE const u8*
+ do { LZ4_copy8(d, s); d += 8; s += 8; } while (d < e);
+}
-#ifdef __BIG_ENDIAN
+#if LZ4_ARCH64
+#ifdef __BIG_ENDIAN__
+#define LZ4_NBCOMMONBYTES(val) (__builtin_clzll(val) >> 3)
+#else
+#define LZ4_NBCOMMONBYTES(val) (__builtin_clzll(val) >> 3)
+#endif
+#else
+#ifdef __BIG_ENDIAN__
#define LZ4_NBCOMMONBYTES(val) (__builtin_clz(val) >> 3)
#else
#define LZ4_NBCOMMONBYTES(val) (__builtin_ctz(val) >> 3)
#endif
+#endif
+static inline unsigned int LZ4_count(const BYTE *pIn, const BYTE *pMatch,
+ const BYTE *pInLimit)
+{
+ const BYTE *const pStart = pIn;
+
+ while (likely(pIn < pInLimit-(STEPSIZE-1))) {
+ size_t diff = LZ4_read_ARCH(pMatch) ^ LZ4_read_ARCH(pIn);
+
+ if (!diff) {
+ pIn += STEPSIZE;
+ pMatch += STEPSIZE;
+ continue;
+ }
+ pIn += LZ4_NBCOMMONBYTES(diff);
+ return (unsigned int)(pIn - pStart);
+ }
+
+#ifdef LZ4_ARCH64
+ if ((pIn < (pInLimit-3))
+ && (LZ4_read32(pMatch) == LZ4_read32(pIn))) {
+ pIn += 4; pMatch += 4;
+ }
#endif
+ if ((pIn < (pInLimit-1))
+ && (LZ4_read16(pMatch) == LZ4_read16(pIn))) {
+ pIn += 2; pMatch += 2;
+ }
+ if ((pIn < pInLimit) && (*pMatch == *pIn))
+ pIn++;
+ return (unsigned int)(pIn - pStart);
+}
+
+typedef enum { noLimit = 0, limitedOutput = 1 } limitedOutput_directive;
+typedef enum { byPtr, byU32, byU16 } tableType_t;
-#define LZ4_WILDCOPY(s, d, e) \
- do { \
- LZ4_COPYPACKET(s, d); \
- } while (d < e)
-
-#define LZ4_BLINDCOPY(s, d, l) \
- do { \
- u8 *e = (d) + l; \
- LZ4_WILDCOPY(s, d, e); \
- d = e; \
- } while (0)
+typedef enum { noDict = 0, withPrefix64k, usingExtDict } dict_directive;
+typedef enum { noDictIssue = 0, dictSmall } dictIssue_directive;
+
+typedef enum { endOnOutputSize = 0, endOnInputSize = 1 } endCondition_directive;
+typedef enum { full = 0, partial = 1 } earlyEnd_directive;
+
+#endif
diff --git a/lib/lz4/lz4hc_compress.c b/lib/lz4/lz4hc_compress.c
index f344f76..880c778 100644
--- a/lib/lz4/lz4hc_compress.c
+++ b/lib/lz4/lz4hc_compress.c
@@ -1,19 +1,17 @@
/*
* LZ4 HC - High Compression Mode of LZ4
- * Copyright (C) 2011-2012, Yann Collet.
- * BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
+ * Copyright (C) 2011-2015, Yann Collet.
*
+ * BSD 2 - Clause License (http://www.opensource.org/licenses/bsd - license.php)
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions are
* met:
- *
- * * Redistributions of source code must retain the above copyright
+ * * Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
- * * Redistributions in binary form must reproduce the above
+ * * Redistributions in binary form must reproduce the above
* copyright notice, this list of conditions and the following disclaimer
* in the documentation and/or other materials provided with the
* distribution.
- *
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
@@ -25,323 +23,353 @@
* THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
* OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
* You can contact the author at :
- * - LZ4 homepage : http://fastcompression.blogspot.com/p/lz4.html
- * - LZ4 source repository : http://code.google.com/p/lz4/
+ * - LZ4 homepage : http://www.lz4.org
+ * - LZ4 source repository : https://github.com/lz4/lz4
*
- * Changed for kernel use by:
- * Chanho Min <chanho.min@lge.com>
+ * Changed for kernel usage by:
+ * Sven Schmidt <4sschmid@informatik.uni-hamburg.de>
*/
-#include <linux/module.h>
-#include <linux/kernel.h>
+/*-************************************
+ * Dependencies
+ **************************************/
#include <linux/lz4.h>
-#include <asm/unaligned.h>
#include "lz4defs.h"
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/string.h> /* memset */
-struct lz4hc_data {
- const u8 *base;
- HTYPE hashtable[HASHTABLESIZE];
- u16 chaintable[MAXD];
- const u8 *nexttoupdate;
-} __attribute__((__packed__));
+/* *************************************
+ * Local Constants and types
+ ***************************************/
-static inline int lz4hc_init(struct lz4hc_data *hc4, const u8 *base)
+#define OPTIMAL_ML (int)((ML_MASK - 1) + MINMATCH)
+
+#define HASH_FUNCTION(i) (((i) * 2654435761U) \
+ >> ((MINMATCH*8) - LZ4HC_HASH_LOG))
+#define DELTANEXTU16(p) chainTable[(U16)(p)] /* faster */
+
+static U32 LZ4HC_hashPtr(const void *ptr)
{
- memset((void *)hc4->hashtable, 0, sizeof(hc4->hashtable));
- memset(hc4->chaintable, 0xFF, sizeof(hc4->chaintable));
-
-#if LZ4_ARCH64
- hc4->nexttoupdate = base + 1;
-#else
- hc4->nexttoupdate = base;
-#endif
- hc4->base = base;
- return 1;
+ return HASH_FUNCTION(LZ4_read32(ptr));
+}
+
+/**************************************
+ * HC Compression
+ **************************************/
+static void LZ4HC_init(LZ4HC_CCtx_internal *hc4, const BYTE *start)
+{
+ memset((void *)hc4->hashTable, 0, sizeof(hc4->hashTable));
+ memset(hc4->chainTable, 0xFF, sizeof(hc4->chainTable));
+ hc4->nextToUpdate = 64 * KB;
+ hc4->base = start - 64 * KB;
+ hc4->end = start;
+ hc4->dictBase = start - 64 * KB;
+ hc4->dictLimit = 64 * KB;
+ hc4->lowLimit = 64 * KB;
}
/* Update chains up to ip (excluded) */
-static inline void lz4hc_insert(struct lz4hc_data *hc4, const u8 *ip)
+static inline void LZ4HC_Insert(LZ4HC_CCtx_internal *hc4,
+ const BYTE *ip)
{
- u16 *chaintable = hc4->chaintable;
- HTYPE *hashtable = hc4->hashtable;
-#if LZ4_ARCH64
+ U16 * const chainTable = hc4->chainTable;
+ U32 * const hashTable = hc4->hashTable;
const BYTE * const base = hc4->base;
-#else
- const int base = 0;
-#endif
+ U32 const target = (U32)(ip - base);
+ U32 idx = hc4->nextToUpdate;
+
+ while (idx < target) {
+ U32 const h = LZ4HC_hashPtr(base + idx);
+ size_t delta = idx - hashTable[h];
- while (hc4->nexttoupdate < ip) {
- const u8 *p = hc4->nexttoupdate;
- size_t delta = p - (hashtable[HASH_VALUE(p)] + base);
if (delta > MAX_DISTANCE)
delta = MAX_DISTANCE;
- chaintable[(size_t)(p) & MAXD_MASK] = (u16)delta;
- hashtable[HASH_VALUE(p)] = (p) - base;
- hc4->nexttoupdate++;
- }
-}
-static inline size_t lz4hc_commonlength(const u8 *p1, const u8 *p2,
- const u8 *const matchlimit)
-{
- const u8 *p1t = p1;
-
- while (p1t < matchlimit - (STEPSIZE - 1)) {
-#if LZ4_ARCH64
- u64 diff = A64(p2) ^ A64(p1t);
-#else
- u32 diff = A32(p2) ^ A32(p1t);
-#endif
- if (!diff) {
- p1t += STEPSIZE;
- p2 += STEPSIZE;
- continue;
- }
- p1t += LZ4_NBCOMMONBYTES(diff);
- return p1t - p1;
- }
-#if LZ4_ARCH64
- if ((p1t < (matchlimit-3)) && (A32(p2) == A32(p1t))) {
- p1t += 4;
- p2 += 4;
- }
-#endif
+ DELTANEXTU16(idx) = (U16)delta;
- if ((p1t < (matchlimit - 1)) && (A16(p2) == A16(p1t))) {
- p1t += 2;
- p2 += 2;
+ hashTable[h] = idx;
+ idx++;
}
- if ((p1t < matchlimit) && (*p2 == *p1t))
- p1t++;
- return p1t - p1;
+
+ hc4->nextToUpdate = target;
}
-static inline int lz4hc_insertandfindbestmatch(struct lz4hc_data *hc4,
- const u8 *ip, const u8 *const matchlimit, const u8 **matchpos)
+static inline int LZ4HC_InsertAndFindBestMatch(
+ LZ4HC_CCtx_internal *hc4, /* Index table will be updated */
+ const BYTE *ip,
+ const BYTE * const iLimit,
+ const BYTE **matchpos,
+ const int maxNbAttempts)
{
- u16 *const chaintable = hc4->chaintable;
- HTYPE *const hashtable = hc4->hashtable;
- const u8 *ref;
-#if LZ4_ARCH64
+ U16 * const chainTable = hc4->chainTable;
+ U32 * const HashTable = hc4->hashTable;
const BYTE * const base = hc4->base;
-#else
- const int base = 0;
-#endif
- int nbattempts = MAX_NB_ATTEMPTS;
- size_t repl = 0, ml = 0;
- u16 delta;
+ const BYTE * const dictBase = hc4->dictBase;
+ const U32 dictLimit = hc4->dictLimit;
+ const U32 lowLimit = (hc4->lowLimit + 64 * KB > (U32)(ip - base))
+ ? hc4->lowLimit
+ : (U32)(ip - base) - (64 * KB - 1);
+ U32 matchIndex;
+ int nbAttempts = maxNbAttempts;
+ size_t ml = 0;
/* HC4 match finder */
- lz4hc_insert(hc4, ip);
- ref = hashtable[HASH_VALUE(ip)] + base;
-
- /* potential repetition */
- if (ref >= ip-4) {
- /* confirmed */
- if (A32(ref) == A32(ip)) {
- delta = (u16)(ip-ref);
- repl = ml = lz4hc_commonlength(ip + MINMATCH,
- ref + MINMATCH, matchlimit) + MINMATCH;
- *matchpos = ref;
- }
- ref -= (size_t)chaintable[(size_t)(ref) & MAXD_MASK];
- }
+ LZ4HC_Insert(hc4, ip);
+ matchIndex = HashTable[LZ4HC_hashPtr(ip)];
+
+ while ((matchIndex >= lowLimit)
+ && (nbAttempts)) {
+ nbAttempts--;
+ if (matchIndex >= dictLimit) {
+ const BYTE * const match = base + matchIndex;
+
+ if (*(match + ml) == *(ip + ml)
+ && (LZ4_read32(match) == LZ4_read32(ip))) {
+ size_t const mlt = LZ4_count(ip + MINMATCH,
+ match + MINMATCH, iLimit) + MINMATCH;
- while ((ref >= ip - MAX_DISTANCE) && nbattempts) {
- nbattempts--;
- if (*(ref + ml) == *(ip + ml)) {
- if (A32(ref) == A32(ip)) {
- size_t mlt =
- lz4hc_commonlength(ip + MINMATCH,
- ref + MINMATCH, matchlimit) + MINMATCH;
if (mlt > ml) {
ml = mlt;
- *matchpos = ref;
+ *matchpos = match;
+ }
+ }
+ } else {
+ const BYTE * const match = dictBase + matchIndex;
+
+ if (LZ4_read32(match) == LZ4_read32(ip)) {
+ size_t mlt;
+ const BYTE *vLimit = ip
+ + (dictLimit - matchIndex);
+
+ if (vLimit > iLimit)
+ vLimit = iLimit;
+ mlt = LZ4_count(ip + MINMATCH,
+ match + MINMATCH, vLimit) + MINMATCH;
+ if ((ip + mlt == vLimit)
+ && (vLimit < iLimit))
+ mlt += LZ4_count(ip + mlt,
+ base + dictLimit,
+ iLimit);
+ if (mlt > ml) {
+ /* virtual matchpos */
+ ml = mlt;
+ *matchpos = base + matchIndex;
}
}
}
- ref -= (size_t)chaintable[(size_t)(ref) & MAXD_MASK];
- }
-
- /* Complete table */
- if (repl) {
- const BYTE *ptr = ip;
- const BYTE *end;
- end = ip + repl - (MINMATCH-1);
- /* Pre-Load */
- while (ptr < end - delta) {
- chaintable[(size_t)(ptr) & MAXD_MASK] = delta;
- ptr++;
- }
- do {
- chaintable[(size_t)(ptr) & MAXD_MASK] = delta;
- /* Head of chain */
- hashtable[HASH_VALUE(ptr)] = (ptr) - base;
- ptr++;
- } while (ptr < end);
- hc4->nexttoupdate = end;
+ matchIndex -= DELTANEXTU16(matchIndex);
}
return (int)ml;
}
-static inline int lz4hc_insertandgetwidermatch(struct lz4hc_data *hc4,
- const u8 *ip, const u8 *startlimit, const u8 *matchlimit, int longest,
- const u8 **matchpos, const u8 **startpos)
+static inline int LZ4HC_InsertAndGetWiderMatch(
+ LZ4HC_CCtx_internal *hc4,
+ const BYTE * const ip,
+ const BYTE * const iLowLimit,
+ const BYTE * const iHighLimit,
+ int longest,
+ const BYTE **matchpos,
+ const BYTE **startpos,
+ const int maxNbAttempts)
{
- u16 *const chaintable = hc4->chaintable;
- HTYPE *const hashtable = hc4->hashtable;
-#if LZ4_ARCH64
+ U16 * const chainTable = hc4->chainTable;
+ U32 * const HashTable = hc4->hashTable;
const BYTE * const base = hc4->base;
-#else
- const int base = 0;
-#endif
- const u8 *ref;
- int nbattempts = MAX_NB_ATTEMPTS;
- int delta = (int)(ip - startlimit);
+ const U32 dictLimit = hc4->dictLimit;
+ const BYTE * const lowPrefixPtr = base + dictLimit;
+ const U32 lowLimit = (hc4->lowLimit + 64 * KB > (U32)(ip - base))
+ ? hc4->lowLimit
+ : (U32)(ip - base) - (64 * KB - 1);
+ const BYTE * const dictBase = hc4->dictBase;
+ U32 matchIndex;
+ int nbAttempts = maxNbAttempts;
+ int delta = (int)(ip - iLowLimit);
/* First Match */
- lz4hc_insert(hc4, ip);
- ref = hashtable[HASH_VALUE(ip)] + base;
-
- while ((ref >= ip - MAX_DISTANCE) && (ref >= hc4->base)
- && (nbattempts)) {
- nbattempts--;
- if (*(startlimit + longest) == *(ref - delta + longest)) {
- if (A32(ref) == A32(ip)) {
- const u8 *reft = ref + MINMATCH;
- const u8 *ipt = ip + MINMATCH;
- const u8 *startt = ip;
-
- while (ipt < matchlimit-(STEPSIZE - 1)) {
- #if LZ4_ARCH64
- u64 diff = A64(reft) ^ A64(ipt);
- #else
- u32 diff = A32(reft) ^ A32(ipt);
- #endif
-
- if (!diff) {
- ipt += STEPSIZE;
- reft += STEPSIZE;
- continue;
+ LZ4HC_Insert(hc4, ip);
+ matchIndex = HashTable[LZ4HC_hashPtr(ip)];
+
+ while ((matchIndex >= lowLimit)
+ && (nbAttempts)) {
+ nbAttempts--;
+ if (matchIndex >= dictLimit) {
+ const BYTE *matchPtr = base + matchIndex;
+
+ if (*(iLowLimit + longest)
+ == *(matchPtr - delta + longest)) {
+ if (LZ4_read32(matchPtr) == LZ4_read32(ip)) {
+ int mlt = MINMATCH +
+ LZ4_count(ip + MINMATCH,
+ matchPtr + MINMATCH,
+ iHighLimit);
+ int back = 0;
+
+ while ((ip + back > iLowLimit)
+ && (matchPtr + back > lowPrefixPtr)
+ && (ip[back - 1] == matchPtr[back - 1]))
+ back--;
+
+ mlt -= back;
+
+ if (mlt > longest) {
+ longest = (int)mlt;
+ *matchpos = matchPtr + back;
+ *startpos = ip + back;
}
- ipt += LZ4_NBCOMMONBYTES(diff);
- goto _endcount;
- }
- #if LZ4_ARCH64
- if ((ipt < (matchlimit - 3))
- && (A32(reft) == A32(ipt))) {
- ipt += 4;
- reft += 4;
- }
- ipt += 2;
- #endif
- if ((ipt < (matchlimit - 1))
- && (A16(reft) == A16(ipt))) {
- reft += 2;
}
- if ((ipt < matchlimit) && (*reft == *ipt))
- ipt++;
-_endcount:
- reft = ref;
-
- while ((startt > startlimit)
- && (reft > hc4->base)
- && (startt[-1] == reft[-1])) {
- startt--;
- reft--;
- }
-
- if ((ipt - startt) > longest) {
- longest = (int)(ipt - startt);
- *matchpos = reft;
- *startpos = startt;
+ }
+ } else {
+ const BYTE * const matchPtr = dictBase + matchIndex;
+
+ if (LZ4_read32(matchPtr) == LZ4_read32(ip)) {
+ size_t mlt;
+ int back = 0;
+ const BYTE *vLimit = ip + (dictLimit - matchIndex);
+
+ if (vLimit > iHighLimit)
+ vLimit = iHighLimit;
+
+ mlt = LZ4_count(ip + MINMATCH,
+ matchPtr + MINMATCH, vLimit) + MINMATCH;
+
+ if ((ip + mlt == vLimit) && (vLimit < iHighLimit))
+ mlt += LZ4_count(ip + mlt, base + dictLimit,
+ iHighLimit);
+ while ((ip + back > iLowLimit)
+ && (matchIndex + back > lowLimit)
+ && (ip[back - 1] == matchPtr[back - 1]))
+ back--;
+ mlt -= back;
+ if ((int)mlt > longest) {
+ longest = (int)mlt;
+ *matchpos = base + matchIndex + back;
+ *startpos = ip + back;
}
}
}
- ref -= (size_t)chaintable[(size_t)(ref) & MAXD_MASK];
+ matchIndex -= DELTANEXTU16(matchIndex);
}
+
return longest;
}
-static inline int lz4_encodesequence(const u8 **ip, u8 **op, const u8 **anchor,
- int ml, const u8 *ref)
+static inline int LZ4HC_encodeSequence(
+ const BYTE **ip,
+ BYTE **op,
+ const BYTE **anchor,
+ int matchLength,
+ const BYTE * const match,
+ limitedOutput_directive limitedOutputBuffer,
+ BYTE *oend)
{
- int length, len;
- u8 *token;
+ int length;
+ BYTE *token;
/* Encode Literal length */
length = (int)(*ip - *anchor);
token = (*op)++;
+
+ if ((limitedOutputBuffer)
+ && ((*op + (length>>8)
+ + length + (2 + 1 + LASTLITERALS)) > oend)) {
+ /* Check output limit */
+ return 1;
+ }
if (length >= (int)RUN_MASK) {
- *token = (RUN_MASK << ML_BITS);
+ int len;
+
+ *token = (RUN_MASK<<ML_BITS);
len = length - RUN_MASK;
- for (; len > 254 ; len -= 255)
+ for (; len > 254 ; len -= 255) {
*(*op)++ = 255;
- *(*op)++ = (u8)len;
+ *(*op)++ = (BYTE)len;
+ }
} else
- *token = (length << ML_BITS);
+ *token = (BYTE)(length<<ML_BITS);
/* Copy Literals */
- LZ4_BLINDCOPY(*anchor, *op, length);
+ LZ4_wildCopy(*op, *anchor, (*op) + length);
+ *op += length;
/* Encode Offset */
- LZ4_WRITE_LITTLEENDIAN_16(*op, (u16)(*ip - ref));
+ LZ4_writeLE16(*op, (U16)(*ip - match)); *op += 2;
/* Encode MatchLength */
- len = (int)(ml - MINMATCH);
- if (len >= (int)ML_MASK) {
+ length = (int)(matchLength - MINMATCH);
+ if ((limitedOutputBuffer)
+ && (*op + (length>>8)
+ + (1 + LASTLITERALS) > oend)) {
+ /* Check output limit */
+ return 1;
+ }
+ if (length >= (int)ML_MASK) {
*token += ML_MASK;
- len -= ML_MASK;
- for (; len > 509 ; len -= 510) {
+ length -= ML_MASK;
+ for (; length > 509 ; length -= 510) {
*(*op)++ = 255;
*(*op)++ = 255;
}
- if (len > 254) {
- len -= 255;
+ if (length > 254) {
+ length -= 255;
*(*op)++ = 255;
}
- *(*op)++ = (u8)len;
+ *(*op)++ = (BYTE)length;
} else
- *token += len;
+ *token += (BYTE)(length);
/* Prepare next loop */
- *ip += ml;
+ *ip += matchLength;
*anchor = *ip;
return 0;
}
-static int lz4_compresshcctx(struct lz4hc_data *ctx,
- const char *source,
- char *dest,
- int isize)
+static int LZ4HC_compress_generic(
+ LZ4HC_CCtx_internal *const ctx,
+ const char * const source,
+ char * const dest,
+ int const inputSize,
+ int const maxOutputSize,
+ int compressionLevel,
+ limitedOutput_directive limit
+ )
{
- const u8 *ip = (const u8 *)source;
- const u8 *anchor = ip;
- const u8 *const iend = ip + isize;
- const u8 *const mflimit = iend - MFLIMIT;
- const u8 *const matchlimit = (iend - LASTLITERALS);
+ const BYTE *ip = (const BYTE *) source;
+ const BYTE *anchor = ip;
+ const BYTE * const iend = ip + inputSize;
+ const BYTE * const mflimit = iend - MFLIMIT;
+ const BYTE * const matchlimit = (iend - LASTLITERALS);
- u8 *op = (u8 *)dest;
+ BYTE *op = (BYTE *) dest;
+ BYTE * const oend = op + maxOutputSize;
+ unsigned int maxNbAttempts;
int ml, ml2, ml3, ml0;
- const u8 *ref = NULL;
- const u8 *start2 = NULL;
- const u8 *ref2 = NULL;
- const u8 *start3 = NULL;
- const u8 *ref3 = NULL;
- const u8 *start0;
- const u8 *ref0;
- int lastrun;
+ const BYTE *ref = NULL;
+ const BYTE *start2 = NULL;
+ const BYTE *ref2 = NULL;
+ const BYTE *start3 = NULL;
+ const BYTE *ref3 = NULL;
+ const BYTE *start0;
+ const BYTE *ref0;
+
+ /* init */
+ if (compressionLevel > LZ4HC_MAX_CLEVEL)
+ compressionLevel = LZ4HC_MAX_CLEVEL;
+ if (compressionLevel < 1)
+ compressionLevel = LZ4HC_DEFAULT_CLEVEL;
+ maxNbAttempts = 1 << (compressionLevel - 1);
+ ctx->end += inputSize;
ip++;
/* Main Loop */
while (ip < mflimit) {
- ml = lz4hc_insertandfindbestmatch(ctx, ip, matchlimit, (&ref));
+ ml = LZ4HC_InsertAndFindBestMatch(ctx, ip,
+ matchlimit, (&ref), maxNbAttempts);
if (!ml) {
ip++;
continue;
@@ -351,46 +379,52 @@ static int lz4_compresshcctx(struct lz4hc_data *ctx,
start0 = ip;
ref0 = ref;
ml0 = ml;
-_search2:
- if (ip+ml < mflimit)
- ml2 = lz4hc_insertandgetwidermatch(ctx, ip + ml - 2,
- ip + 1, matchlimit, ml, &ref2, &start2);
+
+_Search2:
+ if (ip + ml < mflimit)
+ ml2 = LZ4HC_InsertAndGetWiderMatch(ctx,
+ ip + ml - 2, ip + 0,
+ matchlimit, ml, &ref2,
+ &start2, maxNbAttempts);
else
ml2 = ml;
- /* No better match */
+
if (ml2 == ml) {
- lz4_encodesequence(&ip, &op, &anchor, ml, ref);
+ /* No better match */
+ if (LZ4HC_encodeSequence(&ip, &op,
+ &anchor, ml, ref, limit, oend))
+ return 0;
continue;
}
if (start0 < ip) {
- /* empirical */
if (start2 < ip + ml0) {
+ /* empirical */
ip = start0;
ref = ref0;
ml = ml0;
}
}
- /*
- * Here, start0==ip
- * First Match too small : removed
- */
+
+ /* Here, start0 == ip */
if ((start2 - ip) < 3) {
+ /* First Match too small : removed */
ml = ml2;
ip = start2;
ref = ref2;
- goto _search2;
+ goto _Search2;
}
-_search3:
+_Search3:
/*
- * Currently we have :
- * ml2 > ml1, and
- * ip1+3 <= ip2 (usually < ip1+ml1)
- */
+ * Currently we have :
+ * ml2 > ml1, and
+ * ip1 + 3 <= ip2 (usually < ip1 + ml1)
+ */
if ((start2 - ip) < OPTIMAL_ML) {
int correction;
int new_ml = ml;
+
if (new_ml > OPTIMAL_ML)
new_ml = OPTIMAL_ML;
if (ip + new_ml > start2 + ml2 - MINMATCH)
@@ -403,39 +437,44 @@ static int lz4_compresshcctx(struct lz4hc_data *ctx,
}
}
/*
- * Now, we have start2 = ip+new_ml,
- * with new_ml=min(ml, OPTIMAL_ML=18)
+ * Now, we have start2 = ip + new_ml,
+ * with new_ml = min(ml, OPTIMAL_ML = 18)
*/
+
if (start2 + ml2 < mflimit)
- ml3 = lz4hc_insertandgetwidermatch(ctx,
- start2 + ml2 - 3, start2, matchlimit,
- ml2, &ref3, &start3);
+ ml3 = LZ4HC_InsertAndGetWiderMatch(ctx,
+ start2 + ml2 - 3, start2,
+ matchlimit, ml2, &ref3, &start3,
+ maxNbAttempts);
else
ml3 = ml2;
- /* No better match : 2 sequences to encode */
if (ml3 == ml2) {
+ /* No better match : 2 sequences to encode */
/* ip & ref are known; Now for ml */
- if (start2 < ip+ml)
+ if (start2 < ip + ml)
ml = (int)(start2 - ip);
-
/* Now, encode 2 sequences */
- lz4_encodesequence(&ip, &op, &anchor, ml, ref);
+ if (LZ4HC_encodeSequence(&ip, &op, &anchor,
+ ml, ref, limit, oend))
+ return 0;
ip = start2;
- lz4_encodesequence(&ip, &op, &anchor, ml2, ref2);
+ if (LZ4HC_encodeSequence(&ip, &op, &anchor,
+ ml2, ref2, limit, oend))
+ return 0;
continue;
}
- /* Not enough space for match 2 : remove it */
if (start3 < ip + ml + 3) {
- /*
- * can write Seq1 immediately ==> Seq2 is removed,
- * so Seq3 becomes Seq1
- */
+ /* Not enough space for match 2 : remove it */
if (start3 >= (ip + ml)) {
+ /* can write Seq1 immediately
+ * ==> Seq2 is removed,
+ * so Seq3 becomes Seq1
+ */
if (start2 < ip + ml) {
- int correction =
- (int)(ip + ml - start2);
+ int correction = (int)(ip + ml - start2);
+
start2 += correction;
ref2 += correction;
ml2 -= correction;
@@ -446,35 +485,38 @@ static int lz4_compresshcctx(struct lz4hc_data *ctx,
}
}
- lz4_encodesequence(&ip, &op, &anchor, ml, ref);
- ip = start3;
+ if (LZ4HC_encodeSequence(&ip, &op, &anchor,
+ ml, ref, limit, oend))
+ return 0;
+ ip = start3;
ref = ref3;
- ml = ml3;
+ ml = ml3;
start0 = start2;
ref0 = ref2;
ml0 = ml2;
- goto _search2;
+ goto _Search2;
}
start2 = start3;
ref2 = ref3;
ml2 = ml3;
- goto _search3;
+ goto _Search3;
}
/*
- * OK, now we have 3 ascending matches; let's write at least
- * the first one ip & ref are known; Now for ml
- */
+ * OK, now we have 3 ascending matches;
+ * let's write at least the first one
+ * ip & ref are known; Now for ml
+ */
if (start2 < ip + ml) {
if ((start2 - ip) < (int)ML_MASK) {
int correction;
+
if (ml > OPTIMAL_ML)
ml = OPTIMAL_ML;
if (ip + ml > start2 + ml2 - MINMATCH)
- ml = (int)(start2 - ip) + ml2
- - MINMATCH;
+ ml = (int)(start2 - ip) + ml2 - MINMATCH;
correction = ml - (int)(start2 - ip);
if (correction > 0) {
start2 += correction;
@@ -484,7 +526,9 @@ static int lz4_compresshcctx(struct lz4hc_data *ctx,
} else
ml = (int)(start2 - ip);
}
- lz4_encodesequence(&ip, &op, &anchor, ml, ref);
+ if (LZ4HC_encodeSequence(&ip, &op, &anchor, ml,
+ ref, limit, oend))
+ return 0;
ip = start2;
ref = ref2;
@@ -494,46 +538,243 @@ static int lz4_compresshcctx(struct lz4hc_data *ctx,
ref2 = ref3;
ml2 = ml3;
- goto _search3;
+ goto _Search3;
}
/* Encode Last Literals */
- lastrun = (int)(iend - anchor);
- if (lastrun >= (int)RUN_MASK) {
- *op++ = (RUN_MASK << ML_BITS);
- lastrun -= RUN_MASK;
- for (; lastrun > 254 ; lastrun -= 255)
- *op++ = 255;
- *op++ = (u8) lastrun;
- } else
- *op++ = (lastrun << ML_BITS);
- memcpy(op, anchor, iend - anchor);
- op += iend - anchor;
+ { int lastRun = (int)(iend - anchor);
+
+ if ((limit)
+ && (((char *)op - dest) + lastRun + 1
+ + ((lastRun + 255 - RUN_MASK)/255)
+ > (U32)maxOutputSize)) {
+ /* Check output limit */
+ return 0;
+ }
+ if (lastRun >= (int)RUN_MASK) {
+ *op++ = (RUN_MASK<<ML_BITS);
+ lastRun -= RUN_MASK;
+ for (; lastRun > 254 ; lastRun -= 255) {
+ *op++ = 255;
+ *op++ = (BYTE) lastRun;
+ }
+ } else
+ *op++ = (BYTE)(lastRun<<ML_BITS);
+ memcpy(op, anchor, iend - anchor);
+ op += iend - anchor;
+ }
+
/* End */
return (int) (((char *)op) - dest);
}
-int lz4hc_compress(const unsigned char *src, size_t src_len,
- unsigned char *dst, size_t *dst_len, void *wrkmem)
+static int LZ4_compress_HC_extStateHC(
+ void *state,
+ const char *src,
+ char *dst,
+ int srcSize,
+ int maxDstSize,
+ int compressionLevel)
{
- int ret = -1;
- int out_len = 0;
+ LZ4HC_CCtx_internal *ctx = &((LZ4_streamHC_t *)state)->internal_donotuse;
- struct lz4hc_data *hc4 = (struct lz4hc_data *)wrkmem;
- lz4hc_init(hc4, (const u8 *)src);
- out_len = lz4_compresshcctx((struct lz4hc_data *)hc4, (const u8 *)src,
- (char *)dst, (int)src_len);
+ if (((size_t)(state)&(sizeof(void *) - 1)) != 0) {
+ /* Error : state is not aligned
+ * for pointers (32 or 64 bits)
+ */
+ return 0;
+ }
- if (out_len < 0)
- goto exit;
+ LZ4HC_init(ctx, (const BYTE *)src);
- *dst_len = out_len;
- return 0;
+ if (maxDstSize < LZ4_compressBound(srcSize))
+ return LZ4HC_compress_generic(ctx, src, dst,
+ srcSize, maxDstSize, compressionLevel, limitedOutput);
+ else
+ return LZ4HC_compress_generic(ctx, src, dst,
+ srcSize, maxDstSize, compressionLevel, noLimit);
+}
-exit:
- return ret;
+int LZ4_compress_HC(const char *src, char *dst, int srcSize,
+ int maxDstSize, int compressionLevel, void *wrkmem)
+{
+ return LZ4_compress_HC_extStateHC(wrkmem, src, dst,
+ srcSize, maxDstSize, compressionLevel);
+}
+EXPORT_SYMBOL(LZ4_compress_HC);
+
+/*-******************************
+ * For backwards compatibility
+ ********************************/
+int lz4hc_compress(const unsigned char *src, size_t src_len,
+ unsigned char *dst, size_t *dst_len, void *wrkmem)
+{
+ *dst_len = LZ4_compress_HC(src, dst, (int)src_len,
+ (int)((size_t)dst_len), LZ4HC_DEFAULT_CLEVEL, wrkmem);
+
+ /*
+ * Prior lz4hc_compress will return -1 in case of error
+ * and 0 on success
+ * while new LZ4_compress_HC
+ * returns 0 in case of error
+ * and the output length on success
+ */
+ if (!dst_len)
+ return -1;
+ else
+ return 0;
}
EXPORT_SYMBOL(lz4hc_compress);
+/**************************************
+ * Streaming Functions
+ **************************************/
+void LZ4_resetStreamHC(LZ4_streamHC_t *LZ4_streamHCPtr, int compressionLevel)
+{
+ LZ4_streamHCPtr->internal_donotuse.base = NULL;
+ LZ4_streamHCPtr->internal_donotuse.compressionLevel = (unsigned int)compressionLevel;
+}
+
+int LZ4_loadDictHC(LZ4_streamHC_t *LZ4_streamHCPtr,
+ const char *dictionary,
+ int dictSize)
+{
+ LZ4HC_CCtx_internal *ctxPtr = &LZ4_streamHCPtr->internal_donotuse;
+
+ if (dictSize > 64 * KB) {
+ dictionary += dictSize - 64 * KB;
+ dictSize = 64 * KB;
+ }
+ LZ4HC_init(ctxPtr, (const BYTE *)dictionary);
+ if (dictSize >= 4)
+ LZ4HC_Insert(ctxPtr, (const BYTE *)dictionary + (dictSize - 3));
+ ctxPtr->end = (const BYTE *)dictionary + dictSize;
+ return dictSize;
+}
+EXPORT_SYMBOL(LZ4_loadDictHC);
+
+/* compression */
+
+static void LZ4HC_setExternalDict(
+ LZ4HC_CCtx_internal *ctxPtr,
+ const BYTE *newBlock)
+{
+ if (ctxPtr->end >= ctxPtr->base + 4) {
+ /* Referencing remaining dictionary content */
+ LZ4HC_Insert(ctxPtr, ctxPtr->end - 3);
+ }
+
+ /*
+ * Only one memory segment for extDict,
+ * so any previous extDict is lost at this stage
+ */
+ ctxPtr->lowLimit = ctxPtr->dictLimit;
+ ctxPtr->dictLimit = (U32)(ctxPtr->end - ctxPtr->base);
+ ctxPtr->dictBase = ctxPtr->base;
+ ctxPtr->base = newBlock - ctxPtr->dictLimit;
+ ctxPtr->end = newBlock;
+ /* match referencing will resume from there */
+ ctxPtr->nextToUpdate = ctxPtr->dictLimit;
+}
+EXPORT_SYMBOL(LZ4HC_setExternalDict);
+
+static int LZ4_compressHC_continue_generic(
+ LZ4_streamHC_t *LZ4_streamHCPtr,
+ const char *source,
+ char *dest,
+ int inputSize,
+ int maxOutputSize,
+ limitedOutput_directive limit)
+{
+ LZ4HC_CCtx_internal *ctxPtr = &LZ4_streamHCPtr->internal_donotuse;
+
+ /* auto - init if forgotten */
+ if (ctxPtr->base == NULL)
+ LZ4HC_init(ctxPtr, (const BYTE *) source);
+
+ /* Check overflow */
+ if ((size_t)(ctxPtr->end - ctxPtr->base) > 2 * GB) {
+ size_t dictSize = (size_t)(ctxPtr->end - ctxPtr->base)
+ - ctxPtr->dictLimit;
+ if (dictSize > 64 * KB)
+ dictSize = 64 * KB;
+ LZ4_loadDictHC(LZ4_streamHCPtr,
+ (const char *)(ctxPtr->end) - dictSize, (int)dictSize);
+ }
+
+ /* Check if blocks follow each other */
+ if ((const BYTE *)source != ctxPtr->end)
+ LZ4HC_setExternalDict(ctxPtr, (const BYTE *)source);
+
+ /* Check overlapping input/dictionary space */
+ { const BYTE *sourceEnd = (const BYTE *) source + inputSize;
+ const BYTE * const dictBegin = ctxPtr->dictBase + ctxPtr->lowLimit;
+ const BYTE * const dictEnd = ctxPtr->dictBase + ctxPtr->dictLimit;
+
+ if ((sourceEnd > dictBegin)
+ && ((const BYTE *)source < dictEnd)) {
+ if (sourceEnd > dictEnd)
+ sourceEnd = dictEnd;
+ ctxPtr->lowLimit = (U32)(sourceEnd - ctxPtr->dictBase);
+
+ if (ctxPtr->dictLimit - ctxPtr->lowLimit < 4)
+ ctxPtr->lowLimit = ctxPtr->dictLimit;
+ }
+ }
+
+ return LZ4HC_compress_generic(ctxPtr, source, dest,
+ inputSize, maxOutputSize, ctxPtr->compressionLevel, limit);
+}
+
+int LZ4_compress_HC_continue(
+ LZ4_streamHC_t *LZ4_streamHCPtr,
+ const char *source,
+ char *dest,
+ int inputSize,
+ int maxOutputSize)
+{
+ if (maxOutputSize < LZ4_compressBound(inputSize))
+ return LZ4_compressHC_continue_generic(LZ4_streamHCPtr,
+ source, dest, inputSize, maxOutputSize, limitedOutput);
+ else
+ return LZ4_compressHC_continue_generic(LZ4_streamHCPtr,
+ source, dest, inputSize, maxOutputSize, noLimit);
+}
+EXPORT_SYMBOL(LZ4_compress_HC_continue);
+
+/* dictionary saving */
+
+int LZ4_saveDictHC(
+ LZ4_streamHC_t *LZ4_streamHCPtr,
+ char *safeBuffer,
+ int dictSize)
+{
+ LZ4HC_CCtx_internal *const streamPtr = &LZ4_streamHCPtr->internal_donotuse;
+ int const prefixSize = (int)(streamPtr->end
+ - (streamPtr->base + streamPtr->dictLimit));
+
+ if (dictSize > 64 * KB)
+ dictSize = 64 * KB;
+ if (dictSize < 4)
+ dictSize = 0;
+ if (dictSize > prefixSize)
+ dictSize = prefixSize;
+
+ memmove(safeBuffer, streamPtr->end - dictSize, dictSize);
+
+ { U32 const endIndex = (U32)(streamPtr->end - streamPtr->base);
+
+ streamPtr->end = (const BYTE *)safeBuffer + dictSize;
+ streamPtr->base = streamPtr->end - endIndex;
+ streamPtr->dictLimit = endIndex - dictSize;
+ streamPtr->lowLimit = endIndex - dictSize;
+
+ if (streamPtr->nextToUpdate < streamPtr->dictLimit)
+ streamPtr->nextToUpdate = streamPtr->dictLimit;
+ }
+ return dictSize;
+}
+EXPORT_SYMBOL(LZ4_saveDictHC);
+
MODULE_LICENSE("Dual BSD/GPL");
-MODULE_DESCRIPTION("LZ4HC compressor");
+MODULE_DESCRIPTION("LZ4 HC compressor");
--
2.1.4
^ permalink raw reply related
* [PATCH v4 4/4] fs/pstore: fs/squashfs: Change usage of LZ4 to work with new LZ4 version
From: Sven Schmidt @ 2017-01-22 19:35 UTC (permalink / raw)
To: akpm
Cc: bongkyu.kim, rsalvaterra, sergey.senozhatsky, gregkh,
linux-kernel, herbert, davem, linux-crypto, anton, ccross,
keescook, tony.luck, phillip, Sven Schmidt
In-Reply-To: <1485113717-29261-1-git-send-email-4sschmid@informatik.uni-hamburg.de>
This patch updates fs/pstore and fs/squashfs to use the updated
functions from the new LZ4 module.
Signed-off-by: Sven Schmidt <4sschmid@informatik.uni-hamburg.de>
---
fs/pstore/platform.c | 14 +++++++-------
fs/squashfs/lz4_wrapper.c | 12 ++++++------
2 files changed, 13 insertions(+), 13 deletions(-)
diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c
index 729677e..85c4c58 100644
--- a/fs/pstore/platform.c
+++ b/fs/pstore/platform.c
@@ -342,31 +342,31 @@ static int compress_lz4(const void *in, void *out, size_t inlen, size_t outlen)
{
int ret;
- ret = lz4_compress(in, inlen, out, &outlen, workspace);
- if (ret) {
+ ret = LZ4_compress_default(in, out, inlen, outlen, workspace);
+ if (!ret) {
pr_err("lz4_compress error, ret = %d!\n", ret);
return -EIO;
}
- return outlen;
+ return ret;
}
static int decompress_lz4(void *in, void *out, size_t inlen, size_t outlen)
{
int ret;
- ret = lz4_decompress_unknownoutputsize(in, inlen, out, &outlen);
- if (ret) {
+ ret = LZ4_decompress_safe(in, out, inlen, outlen);
+ if (ret < 0) {
pr_err("lz4_decompress error, ret = %d!\n", ret);
return -EIO;
}
- return outlen;
+ return ret;
}
static void allocate_lz4(void)
{
- big_oops_buf_sz = lz4_compressbound(psinfo->bufsize);
+ big_oops_buf_sz = LZ4_compressBound(psinfo->bufsize);
big_oops_buf = kmalloc(big_oops_buf_sz, GFP_KERNEL);
if (big_oops_buf) {
workspace = kmalloc(LZ4_MEM_COMPRESS, GFP_KERNEL);
diff --git a/fs/squashfs/lz4_wrapper.c b/fs/squashfs/lz4_wrapper.c
index ff4468b..95da653 100644
--- a/fs/squashfs/lz4_wrapper.c
+++ b/fs/squashfs/lz4_wrapper.c
@@ -97,7 +97,6 @@ static int lz4_uncompress(struct squashfs_sb_info *msblk, void *strm,
struct squashfs_lz4 *stream = strm;
void *buff = stream->input, *data;
int avail, i, bytes = length, res;
- size_t dest_len = output->length;
for (i = 0; i < b; i++) {
avail = min(bytes, msblk->devblksize - offset);
@@ -108,12 +107,13 @@ static int lz4_uncompress(struct squashfs_sb_info *msblk, void *strm,
put_bh(bh[i]);
}
- res = lz4_decompress_unknownoutputsize(stream->input, length,
- stream->output, &dest_len);
- if (res)
+ res = LZ4_decompress_safe(stream->input, stream->output,
+ length, output->length);
+
+ if (res < 0)
return -EIO;
- bytes = dest_len;
+ bytes = res;
data = squashfs_first_page(output);
buff = stream->output;
while (data) {
@@ -128,7 +128,7 @@ static int lz4_uncompress(struct squashfs_sb_info *msblk, void *strm,
}
squashfs_finish_page(output);
- return dest_len;
+ return res;
}
const struct squashfs_decompressor squashfs_lz4_comp_ops = {
--
2.1.4
^ permalink raw reply related
* [PATCH v4 0/4] Update LZ4 compressor module
From: Sven Schmidt @ 2017-01-22 19:35 UTC (permalink / raw)
To: akpm
Cc: bongkyu.kim, rsalvaterra, sergey.senozhatsky, gregkh,
linux-kernel, herbert, davem, linux-crypto, anton, ccross,
keescook, tony.luck, phillip
In-Reply-To: <1482259992-16680-1-git-send-email-4sschmid@informatik.uni-hamburg.de>
This patchset is for updating the LZ4 compression module to a version based
on LZ4 v1.7.3 allowing to use the fast compression algorithm aka LZ4 fast
which provides an "acceleration" parameter as a tradeoff between
high compression ratio and high compression speed.
We want to use LZ4 fast in order to support compression in lustre
and (mostly, based on that) investigate data reduction techniques in behalf of
storage systems.
Also, it will be useful for other users of LZ4 compression, as with LZ4 fast
it is possible to enable applications to use fast and/or high compression
depending on the usecase.
For instance, ZRAM is offering a LZ4 backend and could benefit from an updated
LZ4 in the kernel.
LZ4 homepage: http://www.lz4.org/
LZ4 source repository: https://github.com/lz4/lz4
Source version: 1.7.3
Benchmark (taken from [1], Core i5-4300U @1.9GHz):
----------------|--------------|----------------|----------
Compressor | Compression | Decompression | Ratio
----------------|--------------|----------------|----------
memcpy | 4200 MB/s | 4200 MB/s | 1.000
LZ4 fast 50 | 1080 MB/s | 2650 MB/s | 1.375
LZ4 fast 17 | 680 MB/s | 2220 MB/s | 1.607
LZ4 fast 5 | 475 MB/s | 1920 MB/s | 1.886
LZ4 default | 385 MB/s | 1850 MB/s | 2.101
[1] http://fastcompression.blogspot.de/2015/04/sampling-or-faster-lz4.html
fs/pstore: fs/squashfs: Change usage of LZ4 to work with new LZ4 version
[PATCH 1/4] lib: Update LZ4 compressor module
[PATCH 2/4] lib/decompress_unlz4: Change module to work with new LZ4 module version
[PATCH 3/4] crypto: Change LZ4 modules to work with new LZ4 module version
[PATCH 4/4] fs/pstore: fs/squashfs: Change usage of LZ4 to work with new LZ4 version
v2:
- Changed order of the patches since in the initial patchset the lz4.h was in the
last patch but was referenced by the other ones
- Split lib/decompress_unlz4.c in an own patch
- Fixed errors reported by the buildbot
- Further refactorings
- Added more appropriate copyright note to include/linux/lz4.h
v3:
- Adjusted the code to satisfy kernel coding style (checkpatch.pl)
- Made sure the changes to LZ4 in Kernel (overflow checks etc.)
are included in the new module (they are)
- Removed the second LZ4_compressBound function with related name but
different return type
- Corrected version number (was LZ4 1.7.3)
- Added missing LZ4 streaming functions
v4:
- Fixed kbuild errors
- Re-added lz4_compressbound as alias for LZ4_compressBound
to ensure backwards compatibility
- Wrapped LZ4_hash5 with check for LZ4_ARCH64 since it is only used there
and triggers an unused function warning when false
^ permalink raw reply
* [PATCH v4 2/4] lib/decompress_unlz4: Change module to work with new LZ4 module version
From: Sven Schmidt @ 2017-01-22 19:35 UTC (permalink / raw)
To: akpm
Cc: bongkyu.kim, rsalvaterra, sergey.senozhatsky, gregkh,
linux-kernel, herbert, davem, linux-crypto, anton, ccross,
keescook, tony.luck, phillip, Sven Schmidt
In-Reply-To: <1485113717-29261-1-git-send-email-4sschmid@informatik.uni-hamburg.de>
This patch updates the unlz4 wrapper to work with the
updated LZ4 kernel module version.
Signed-off-by: Sven Schmidt <4sschmid@informatik.uni-hamburg.de>
---
lib/decompress_unlz4.c | 13 ++++++++-----
1 file changed, 8 insertions(+), 5 deletions(-)
diff --git a/lib/decompress_unlz4.c b/lib/decompress_unlz4.c
index 036fc88..1b0baf3 100644
--- a/lib/decompress_unlz4.c
+++ b/lib/decompress_unlz4.c
@@ -72,7 +72,7 @@ STATIC inline int INIT unlz4(u8 *input, long in_len,
error("NULL input pointer and missing fill function");
goto exit_1;
} else {
- inp = large_malloc(lz4_compressbound(uncomp_chunksize));
+ inp = large_malloc(LZ4_compressBound(uncomp_chunksize));
if (!inp) {
error("Could not allocate input buffer");
goto exit_1;
@@ -136,7 +136,7 @@ STATIC inline int INIT unlz4(u8 *input, long in_len,
inp += 4;
size -= 4;
} else {
- if (chunksize > lz4_compressbound(uncomp_chunksize)) {
+ if (chunksize > LZ4_compressBound(uncomp_chunksize)) {
error("chunk length is longer than allocated");
goto exit_2;
}
@@ -152,11 +152,14 @@ STATIC inline int INIT unlz4(u8 *input, long in_len,
out_len -= dest_len;
} else
dest_len = out_len;
- ret = lz4_decompress(inp, &chunksize, outp, dest_len);
+
+ ret = LZ4_decompress_fast(inp, outp, dest_len);
+ chunksize = ret;
#else
dest_len = uncomp_chunksize;
- ret = lz4_decompress_unknownoutputsize(inp, chunksize, outp,
- &dest_len);
+
+ ret = LZ4_decompress_safe(inp, outp, chunksize, dest_len);
+ dest_len = ret;
#endif
if (ret < 0) {
error("Decoding failed");
--
2.1.4
^ permalink raw reply related
* [PATCH v4 3/4] crypto: Change LZ4 modules to work with new LZ4 module version
From: Sven Schmidt @ 2017-01-22 19:35 UTC (permalink / raw)
To: akpm
Cc: bongkyu.kim, rsalvaterra, sergey.senozhatsky, gregkh,
linux-kernel, herbert, davem, linux-crypto, anton, ccross,
keescook, tony.luck, phillip, Sven Schmidt
In-Reply-To: <1485113717-29261-1-git-send-email-4sschmid@informatik.uni-hamburg.de>
This patch updates the crypto modules using LZ4 compression
to work with the new LZ4 module version.
Signed-off-by: Sven Schmidt <4sschmid@informatik.uni-hamburg.de>
---
crypto/lz4.c | 21 ++++++++-------------
crypto/lz4hc.c | 21 ++++++++-------------
2 files changed, 16 insertions(+), 26 deletions(-)
diff --git a/crypto/lz4.c b/crypto/lz4.c
index 99c1b2c..40fd2c2 100644
--- a/crypto/lz4.c
+++ b/crypto/lz4.c
@@ -66,15 +66,13 @@ static void lz4_exit(struct crypto_tfm *tfm)
static int __lz4_compress_crypto(const u8 *src, unsigned int slen,
u8 *dst, unsigned int *dlen, void *ctx)
{
- size_t tmp_len = *dlen;
- int err;
+ int out_len = LZ4_compress_default(src, dst,
+ slen, (int)((size_t)dlen), ctx);
- err = lz4_compress(src, slen, dst, &tmp_len, ctx);
-
- if (err < 0)
+ if (!out_len)
return -EINVAL;
- *dlen = tmp_len;
+ *dlen = out_len;
return 0;
}
@@ -96,16 +94,13 @@ static int lz4_compress_crypto(struct crypto_tfm *tfm, const u8 *src,
static int __lz4_decompress_crypto(const u8 *src, unsigned int slen,
u8 *dst, unsigned int *dlen, void *ctx)
{
- int err;
- size_t tmp_len = *dlen;
- size_t __slen = slen;
+ int out_len = LZ4_decompress_safe(src, dst, slen, (int)((size_t)dlen));
- err = lz4_decompress_unknownoutputsize(src, __slen, dst, &tmp_len);
- if (err < 0)
+ if (out_len < 0)
return -EINVAL;
- *dlen = tmp_len;
- return err;
+ *dlen = out_len;
+ return out_len;
}
static int lz4_sdecompress(struct crypto_scomp *tfm, const u8 *src,
diff --git a/crypto/lz4hc.c b/crypto/lz4hc.c
index 75ffc4a..6f16f96 100644
--- a/crypto/lz4hc.c
+++ b/crypto/lz4hc.c
@@ -65,15 +65,13 @@ static void lz4hc_exit(struct crypto_tfm *tfm)
static int __lz4hc_compress_crypto(const u8 *src, unsigned int slen,
u8 *dst, unsigned int *dlen, void *ctx)
{
- size_t tmp_len = *dlen;
- int err;
+ int out_len = LZ4_compress_HC(src, dst, slen,
+ (int)((size_t)dlen), LZ4HC_DEFAULT_CLEVEL, ctx);
- err = lz4hc_compress(src, slen, dst, &tmp_len, ctx);
-
- if (err < 0)
+ if (out_len == 0)
return -EINVAL;
- *dlen = tmp_len;
+ *dlen = out_len;
return 0;
}
@@ -97,16 +95,13 @@ static int lz4hc_compress_crypto(struct crypto_tfm *tfm, const u8 *src,
static int __lz4hc_decompress_crypto(const u8 *src, unsigned int slen,
u8 *dst, unsigned int *dlen, void *ctx)
{
- int err;
- size_t tmp_len = *dlen;
- size_t __slen = slen;
+ int out_len = LZ4_decompress_safe(src, dst, slen, (int)((size_t)dlen));
- err = lz4_decompress_unknownoutputsize(src, __slen, dst, &tmp_len);
- if (err < 0)
+ if (out_len < 0)
return -EINVAL;
- *dlen = tmp_len;
- return err;
+ *dlen = out_len;
+ return out_len;
}
static int lz4hc_sdecompress(struct crypto_scomp *tfm, const u8 *src,
--
2.1.4
^ permalink raw reply related
* Re: [RFC PATCH 0/6] Add bulk skcipher requests to crypto API and dm-crypt
From: Herbert Xu @ 2017-01-23 13:04 UTC (permalink / raw)
To: Ondrej Mosnáček
Cc: linux-crypto, dm-devel, Mike Snitzer, Milan Broz, Mikulas Patocka,
Binoy Jayan
In-Reply-To: <CAAUqJDtZNGLW-PcPKJD5vdKMZqd6+sAKrbjqVbaVTQqWwZ4cGQ@mail.gmail.com>
On Thu, Jan 19, 2017 at 03:21:37PM +0100, Ondrej Mosnáček wrote:
>
> Hm, I just looked at what the IPsec IV generation is actually doing
> and it seems to me that it's basically a crypto template that just
> somehow transforms the IV before it is passed to the child cipher... I
> thought for a while that you were implying that there already is some
> facility in the crypto API that allows submitting multiple messages +
> some initial sequence number that is auto-incremented and IVs are
> generated from the numbers. However, I could not find anything like
> that in the code, so now I think what you meant was just that I should
> somehow pull the actual IV generators into the crypto layer so that
> the IVs can be generated inside the hardware.
IPsec currently only deals with one packet at a time, but the
point is that the IV generator handles everything transparently
and the IV is actually part of the cipher text for the AEAD op.
IOW it would be trivial to extend our current IPsec IV generators
to handle multiple packets as the IVs are embedded with the cipher
text.
Cheers,
--
Email: Herbert Xu <herbert@gondor.apana.org.au>
Home Page: http://gondor.apana.org.au/~herbert/
PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt
^ permalink raw reply
* Re: [PATCH 00/13] crypto: copy AAD during encrypt for AEAD ciphers
From: Herbert Xu @ 2017-01-23 13:10 UTC (permalink / raw)
To: Cyrille Pitchen; +Cc: Stephan Müller, linux-crypto
In-Reply-To: <2a4fab23-3ea7-a0f7-7c30-55d301f51ec9@atmel.com>
On Fri, Jan 20, 2017 at 06:07:04PM +0100, Cyrille Pitchen wrote:
> Hi all,
>
> Le 13/01/2017 à 12:39, Herbert Xu a écrit :
> > On Fri, Jan 13, 2017 at 12:36:56PM +0100, Stephan Müller wrote:
> >>
> >> I thought I understood that you would not want to see it in any
> >> implementation. But, ok, if you want to leave it.
> >
> > If you remove it from authenc then authenc will be broken.
> >
>
> Hence if the copy of the associated data is needed in the crypto/authenc.c
> driver, then I should also keep this copy in the drivers/crypto/atmel-aes.c
> for authenc(hmac(shaX),cbc-aes) algorithms [1], shouldn't I?
>
> If so, should I keep the current not optimized implementation of
> atmel_aes_authenc_copy_assoc() or try to use the code extracted by Stephan
> from crypto/authenc.c using the null cipher as proposed in this thread?
>
> As said earlier in this thread, copying the associated data is not a so big
> deal when compared to the main crypto processing.
Please just ignore this for now. We have not decided to require
the copying of the AAD in the kernel API.
Thanks,
--
Email: Herbert Xu <herbert@gondor.apana.org.au>
Home Page: http://gondor.apana.org.au/~herbert/
PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt
^ permalink raw reply
* Re: [PATCH v1 0/4]crypto:chcr- Bug Fixes for 4.10
From: Herbert Xu @ 2017-01-23 13:39 UTC (permalink / raw)
To: Harsh Jain; +Cc: hariprasad, netdev, linux-crypto
In-Reply-To: <cover.1484309965.git.harsh@chelsio.com>
On Fri, Jan 13, 2017 at 05:59:19PM +0530, Harsh Jain wrote:
> This patch series is based on Herbert's cryptodev-2.6 tree.
> It includes several critical bug fixes.
>
> Atul Gupta (3):
> crypto:chcr-Change flow IDs
> crypto:chcr- Fix panic on dma_unmap_sg
> crypto:chcr- Check device is allocated before use
> Julia Lawall (1):
> crypto:chcr-fix itnull.cocci warnings
Patches 2 and 3 look critical, but the other ones do not. Please
don't mix fixes targeted for this cycle with other patches.
Please resubmit them as two separate series.
Thanks,
--
Email: Herbert Xu <herbert@gondor.apana.org.au>
Home Page: http://gondor.apana.org.au/~herbert/
PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt
^ permalink raw reply
* Re: [PATCH] crypto: camellia: add missing declarations
From: Herbert Xu @ 2017-01-23 14:02 UTC (permalink / raw)
To: Nicholas Mc Guire
Cc: David S. Miller, Thomas Gleixner, Ingo Molnar, H. Peter Anvin,
x86, linux-crypto, linux-kernel
In-Reply-To: <1484582811-3505-1-git-send-email-hofrat@osadl.org>
On Mon, Jan 16, 2017 at 05:06:51PM +0100, Nicholas Mc Guire wrote:
> Add declarations for the camellia substitution box to allow a clean build.
>
> Signed-off-by: Nicholas Mc Guire <hofrat@osadl.org>
> ---
> Problem reported by sparse
> arch/x86/crypto/camellia_glue.c:65:21: warning: symbol 'camellia_sp10011110' was not declared. Should it be static?
> arch/x86/crypto/camellia_glue.c:154:21: warning: symbol 'camellia_sp22000222' was not declared. Should it be static?
> arch/x86/crypto/camellia_glue.c:243:21: warning: symbol 'camellia_sp03303033' was not declared. Should it be static?
> arch/x86/crypto/camellia_glue.c:332:21: warning: symbol 'camellia_sp00444404' was not declared. Should it be static?
> arch/x86/crypto/camellia_glue.c:421:21: warning: symbol 'camellia_sp02220222' was not declared. Should it be static?
> arch/x86/crypto/camellia_glue.c:510:21: warning: symbol 'camellia_sp30333033' was not declared. Should it be static?
> arch/x86/crypto/camellia_glue.c:599:21: warning: symbol 'camellia_sp44044404' was not declared. Should it be static?
> arch/x86/crypto/camellia_glue.c:688:21: warning: symbol 'camellia_sp11101110' was not declared. Should it be static?
>
> Patch was compile tested with: x86_64_defconfig +
> CONFIG_CRYPTO_CAMELLIA_X86_64=m
>
> Patch is against 4.10-rc3 (localversion-next is next-20170116)
This is arguably a sparse bug. These variables are only referenced
by assembly code and already carries the __visible tag. So sparse
should learn to suppress this warning when __visible is present.
Thanks,
--
Email: Herbert Xu <herbert@gondor.apana.org.au>
Home Page: http://gondor.apana.org.au/~herbert/
PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt
^ permalink raw reply
* [PATCH v2 00/10] crypto - AES for ARM/arm64 updates for v4.11 (round #2)
From: Ard Biesheuvel @ 2017-01-23 14:05 UTC (permalink / raw)
To: linux-crypto, herbert; +Cc: Ard Biesheuvel
Patch #1 is a fix for the CBC chaining issue that was discussed on the
mailing list. The driver itself is queued for v4.11, so this fix can go
right on top.
Patches #2 - #6 clear the cra_alignmasks of various drivers: all NEON
capable CPUs can perform unaligned accesses, and the advantage of using
the slightly faster aligned accessors (which only exist on ARM not arm64)
is certainly outweighed by the cost of copying data to suitably aligned
buffers.
NOTE: patch #5 won't apply unless 'crypto: arm64/aes-blk - honour iv_out
requirement in CBC and CTR modes' is applied first, which was sent out
separately as a bugfix for v3.16 - v4.9. If this is a problem, this patch
can wait.
Patch #7 and #8 are minor tweaks to the new scalar AES code.
Patch #9 improves the performance of the plain NEON AES code, to make it
more suitable as a fallback for the new bitsliced NEON code, which can
only operate on 8 blocks in parallel, and needs another driver to perform
CBC encryption or XTS tweak generation.
Patch #10 updates the new bitsliced AES NEON code to switch to the plain
NEON driver as a fallback.
Patches #9 and #10 improve the performance of CBC encryption by ~35% on
low end cores such as the Cortex-A53 that can be found in the Raspberry Pi3
Changes since v1:
- shave off another few cycles from the sequential AES NEON code (patch #9)
Ard Biesheuvel (10):
crypto: arm64/aes-neon-bs - honour iv_out requirement in CTR mode
crypto: arm/aes-ce - remove cra_alignmask
crypto: arm/chacha20 - remove cra_alignmask
crypto: arm64/aes-ce-ccm - remove cra_alignmask
crypto: arm64/aes-blk - remove cra_alignmask
crypto: arm64/chacha20 - remove cra_alignmask
crypto: arm64/aes - avoid literals for cross-module symbol references
crypto: arm64/aes - performance tweak
crypto: arm64/aes-neon-blk - tweak performance for low end cores
crypto: arm64/aes - replace scalar fallback with plain NEON fallback
arch/arm/crypto/aes-ce-core.S | 84 ++++----
arch/arm/crypto/aes-ce-glue.c | 15 +-
arch/arm/crypto/chacha20-neon-glue.c | 1 -
arch/arm64/crypto/Kconfig | 2 +-
arch/arm64/crypto/aes-ce-ccm-glue.c | 1 -
arch/arm64/crypto/aes-cipher-core.S | 59 ++----
arch/arm64/crypto/aes-glue.c | 18 +-
arch/arm64/crypto/aes-modes.S | 8 +-
arch/arm64/crypto/aes-neon.S | 210 ++++++++------------
arch/arm64/crypto/aes-neonbs-core.S | 25 ++-
arch/arm64/crypto/aes-neonbs-glue.c | 38 +++-
arch/arm64/crypto/chacha20-neon-glue.c | 1 -
12 files changed, 203 insertions(+), 259 deletions(-)
--
2.7.4
^ permalink raw reply
* [PATCH v2 01/10] crypto: arm64/aes-neon-bs - honour iv_out requirement in CTR mode
From: Ard Biesheuvel @ 2017-01-23 14:05 UTC (permalink / raw)
To: linux-crypto, herbert; +Cc: Ard Biesheuvel
In-Reply-To: <1485180326-25612-1-git-send-email-ard.biesheuvel@linaro.org>
Update the new bitsliced NEON AES implementation in CTR mode to return
the next IV back to the skcipher API client. This is necessary for
chaining to work correctly.
Note that this is only done if the request is a round multiple of the
block size, since otherwise, chaining is impossible anyway.
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
---
arch/arm64/crypto/aes-neonbs-core.S | 25 +++++++++++++-------
1 file changed, 16 insertions(+), 9 deletions(-)
diff --git a/arch/arm64/crypto/aes-neonbs-core.S b/arch/arm64/crypto/aes-neonbs-core.S
index 8d0cdaa2768d..2ada12dd768e 100644
--- a/arch/arm64/crypto/aes-neonbs-core.S
+++ b/arch/arm64/crypto/aes-neonbs-core.S
@@ -874,12 +874,19 @@ CPU_LE( rev x8, x8 )
csel x4, x4, xzr, pl
csel x9, x9, xzr, le
+ tbnz x9, #1, 0f
next_ctr v1
+ tbnz x9, #2, 0f
next_ctr v2
+ tbnz x9, #3, 0f
next_ctr v3
+ tbnz x9, #4, 0f
next_ctr v4
+ tbnz x9, #5, 0f
next_ctr v5
+ tbnz x9, #6, 0f
next_ctr v6
+ tbnz x9, #7, 0f
next_ctr v7
0: mov bskey, x2
@@ -928,11 +935,11 @@ CPU_LE( rev x8, x8 )
eor v5.16b, v5.16b, v15.16b
st1 {v5.16b}, [x0], #16
- next_ctr v0
+8: next_ctr v0
cbnz x4, 99b
0: st1 {v0.16b}, [x5]
-8: ldp x29, x30, [sp], #16
+9: ldp x29, x30, [sp], #16
ret
/*
@@ -941,23 +948,23 @@ CPU_LE( rev x8, x8 )
*/
1: cbz x6, 8b
st1 {v1.16b}, [x5]
- b 8b
+ b 9b
2: cbz x6, 8b
st1 {v4.16b}, [x5]
- b 8b
+ b 9b
3: cbz x6, 8b
st1 {v6.16b}, [x5]
- b 8b
+ b 9b
4: cbz x6, 8b
st1 {v3.16b}, [x5]
- b 8b
+ b 9b
5: cbz x6, 8b
st1 {v7.16b}, [x5]
- b 8b
+ b 9b
6: cbz x6, 8b
st1 {v2.16b}, [x5]
- b 8b
+ b 9b
7: cbz x6, 8b
st1 {v5.16b}, [x5]
- b 8b
+ b 9b
ENDPROC(aesbs_ctr_encrypt)
--
2.7.4
^ permalink raw reply related
* [PATCH v2 02/10] crypto: arm/aes-ce - remove cra_alignmask
From: Ard Biesheuvel @ 2017-01-23 14:05 UTC (permalink / raw)
To: linux-crypto, herbert; +Cc: Ard Biesheuvel
In-Reply-To: <1485180326-25612-1-git-send-email-ard.biesheuvel@linaro.org>
Remove the unnecessary alignmask: it is much more efficient to deal with
the misalignment in the core algorithm than relying on the crypto API to
copy the data to a suitably aligned buffer.
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
---
arch/arm/crypto/aes-ce-core.S | 84 ++++++++++----------
arch/arm/crypto/aes-ce-glue.c | 15 ++--
2 files changed, 47 insertions(+), 52 deletions(-)
diff --git a/arch/arm/crypto/aes-ce-core.S b/arch/arm/crypto/aes-ce-core.S
index 987aa632c9f0..ba8e6a32fdc9 100644
--- a/arch/arm/crypto/aes-ce-core.S
+++ b/arch/arm/crypto/aes-ce-core.S
@@ -169,19 +169,19 @@ ENTRY(ce_aes_ecb_encrypt)
.Lecbencloop3x:
subs r4, r4, #3
bmi .Lecbenc1x
- vld1.8 {q0-q1}, [r1, :64]!
- vld1.8 {q2}, [r1, :64]!
+ vld1.8 {q0-q1}, [r1]!
+ vld1.8 {q2}, [r1]!
bl aes_encrypt_3x
- vst1.8 {q0-q1}, [r0, :64]!
- vst1.8 {q2}, [r0, :64]!
+ vst1.8 {q0-q1}, [r0]!
+ vst1.8 {q2}, [r0]!
b .Lecbencloop3x
.Lecbenc1x:
adds r4, r4, #3
beq .Lecbencout
.Lecbencloop:
- vld1.8 {q0}, [r1, :64]!
+ vld1.8 {q0}, [r1]!
bl aes_encrypt
- vst1.8 {q0}, [r0, :64]!
+ vst1.8 {q0}, [r0]!
subs r4, r4, #1
bne .Lecbencloop
.Lecbencout:
@@ -195,19 +195,19 @@ ENTRY(ce_aes_ecb_decrypt)
.Lecbdecloop3x:
subs r4, r4, #3
bmi .Lecbdec1x
- vld1.8 {q0-q1}, [r1, :64]!
- vld1.8 {q2}, [r1, :64]!
+ vld1.8 {q0-q1}, [r1]!
+ vld1.8 {q2}, [r1]!
bl aes_decrypt_3x
- vst1.8 {q0-q1}, [r0, :64]!
- vst1.8 {q2}, [r0, :64]!
+ vst1.8 {q0-q1}, [r0]!
+ vst1.8 {q2}, [r0]!
b .Lecbdecloop3x
.Lecbdec1x:
adds r4, r4, #3
beq .Lecbdecout
.Lecbdecloop:
- vld1.8 {q0}, [r1, :64]!
+ vld1.8 {q0}, [r1]!
bl aes_decrypt
- vst1.8 {q0}, [r0, :64]!
+ vst1.8 {q0}, [r0]!
subs r4, r4, #1
bne .Lecbdecloop
.Lecbdecout:
@@ -226,10 +226,10 @@ ENTRY(ce_aes_cbc_encrypt)
vld1.8 {q0}, [r5]
prepare_key r2, r3
.Lcbcencloop:
- vld1.8 {q1}, [r1, :64]! @ get next pt block
+ vld1.8 {q1}, [r1]! @ get next pt block
veor q0, q0, q1 @ ..and xor with iv
bl aes_encrypt
- vst1.8 {q0}, [r0, :64]!
+ vst1.8 {q0}, [r0]!
subs r4, r4, #1
bne .Lcbcencloop
vst1.8 {q0}, [r5]
@@ -244,8 +244,8 @@ ENTRY(ce_aes_cbc_decrypt)
.Lcbcdecloop3x:
subs r4, r4, #3
bmi .Lcbcdec1x
- vld1.8 {q0-q1}, [r1, :64]!
- vld1.8 {q2}, [r1, :64]!
+ vld1.8 {q0-q1}, [r1]!
+ vld1.8 {q2}, [r1]!
vmov q3, q0
vmov q4, q1
vmov q5, q2
@@ -254,19 +254,19 @@ ENTRY(ce_aes_cbc_decrypt)
veor q1, q1, q3
veor q2, q2, q4
vmov q6, q5
- vst1.8 {q0-q1}, [r0, :64]!
- vst1.8 {q2}, [r0, :64]!
+ vst1.8 {q0-q1}, [r0]!
+ vst1.8 {q2}, [r0]!
b .Lcbcdecloop3x
.Lcbcdec1x:
adds r4, r4, #3
beq .Lcbcdecout
vmov q15, q14 @ preserve last round key
.Lcbcdecloop:
- vld1.8 {q0}, [r1, :64]! @ get next ct block
+ vld1.8 {q0}, [r1]! @ get next ct block
veor q14, q15, q6 @ combine prev ct with last key
vmov q6, q0
bl aes_decrypt
- vst1.8 {q0}, [r0, :64]!
+ vst1.8 {q0}, [r0]!
subs r4, r4, #1
bne .Lcbcdecloop
.Lcbcdecout:
@@ -300,15 +300,15 @@ ENTRY(ce_aes_ctr_encrypt)
rev ip, r6
add r6, r6, #1
vmov s11, ip
- vld1.8 {q3-q4}, [r1, :64]!
- vld1.8 {q5}, [r1, :64]!
+ vld1.8 {q3-q4}, [r1]!
+ vld1.8 {q5}, [r1]!
bl aes_encrypt_3x
veor q0, q0, q3
veor q1, q1, q4
veor q2, q2, q5
rev ip, r6
- vst1.8 {q0-q1}, [r0, :64]!
- vst1.8 {q2}, [r0, :64]!
+ vst1.8 {q0-q1}, [r0]!
+ vst1.8 {q2}, [r0]!
vmov s27, ip
b .Lctrloop3x
.Lctr1x:
@@ -318,10 +318,10 @@ ENTRY(ce_aes_ctr_encrypt)
vmov q0, q6
bl aes_encrypt
subs r4, r4, #1
- bmi .Lctrhalfblock @ blocks < 0 means 1/2 block
- vld1.8 {q3}, [r1, :64]!
+ bmi .Lctrtailblock @ blocks < 0 means tail block
+ vld1.8 {q3}, [r1]!
veor q3, q0, q3
- vst1.8 {q3}, [r0, :64]!
+ vst1.8 {q3}, [r0]!
adds r6, r6, #1 @ increment BE ctr
rev ip, r6
@@ -333,10 +333,8 @@ ENTRY(ce_aes_ctr_encrypt)
vst1.8 {q6}, [r5]
pop {r4-r6, pc}
-.Lctrhalfblock:
- vld1.8 {d1}, [r1, :64]
- veor d0, d0, d1
- vst1.8 {d0}, [r0, :64]
+.Lctrtailblock:
+ vst1.8 {q0}, [r0, :64] @ return just the key stream
pop {r4-r6, pc}
.Lctrcarry:
@@ -405,8 +403,8 @@ ENTRY(ce_aes_xts_encrypt)
.Lxtsenc3x:
subs r4, r4, #3
bmi .Lxtsenc1x
- vld1.8 {q0-q1}, [r1, :64]! @ get 3 pt blocks
- vld1.8 {q2}, [r1, :64]!
+ vld1.8 {q0-q1}, [r1]! @ get 3 pt blocks
+ vld1.8 {q2}, [r1]!
next_tweak q4, q3, q7, q6
veor q0, q0, q3
next_tweak q5, q4, q7, q6
@@ -416,8 +414,8 @@ ENTRY(ce_aes_xts_encrypt)
veor q0, q0, q3
veor q1, q1, q4
veor q2, q2, q5
- vst1.8 {q0-q1}, [r0, :64]! @ write 3 ct blocks
- vst1.8 {q2}, [r0, :64]!
+ vst1.8 {q0-q1}, [r0]! @ write 3 ct blocks
+ vst1.8 {q2}, [r0]!
vmov q3, q5
teq r4, #0
beq .Lxtsencout
@@ -426,11 +424,11 @@ ENTRY(ce_aes_xts_encrypt)
adds r4, r4, #3
beq .Lxtsencout
.Lxtsencloop:
- vld1.8 {q0}, [r1, :64]!
+ vld1.8 {q0}, [r1]!
veor q0, q0, q3
bl aes_encrypt
veor q0, q0, q3
- vst1.8 {q0}, [r0, :64]!
+ vst1.8 {q0}, [r0]!
subs r4, r4, #1
beq .Lxtsencout
next_tweak q3, q3, q7, q6
@@ -456,8 +454,8 @@ ENTRY(ce_aes_xts_decrypt)
.Lxtsdec3x:
subs r4, r4, #3
bmi .Lxtsdec1x
- vld1.8 {q0-q1}, [r1, :64]! @ get 3 ct blocks
- vld1.8 {q2}, [r1, :64]!
+ vld1.8 {q0-q1}, [r1]! @ get 3 ct blocks
+ vld1.8 {q2}, [r1]!
next_tweak q4, q3, q7, q6
veor q0, q0, q3
next_tweak q5, q4, q7, q6
@@ -467,8 +465,8 @@ ENTRY(ce_aes_xts_decrypt)
veor q0, q0, q3
veor q1, q1, q4
veor q2, q2, q5
- vst1.8 {q0-q1}, [r0, :64]! @ write 3 pt blocks
- vst1.8 {q2}, [r0, :64]!
+ vst1.8 {q0-q1}, [r0]! @ write 3 pt blocks
+ vst1.8 {q2}, [r0]!
vmov q3, q5
teq r4, #0
beq .Lxtsdecout
@@ -477,12 +475,12 @@ ENTRY(ce_aes_xts_decrypt)
adds r4, r4, #3
beq .Lxtsdecout
.Lxtsdecloop:
- vld1.8 {q0}, [r1, :64]!
+ vld1.8 {q0}, [r1]!
veor q0, q0, q3
add ip, r2, #32 @ 3rd round key
bl aes_decrypt
veor q0, q0, q3
- vst1.8 {q0}, [r0, :64]!
+ vst1.8 {q0}, [r0]!
subs r4, r4, #1
beq .Lxtsdecout
next_tweak q3, q3, q7, q6
diff --git a/arch/arm/crypto/aes-ce-glue.c b/arch/arm/crypto/aes-ce-glue.c
index 8857531915bf..883b84d828c5 100644
--- a/arch/arm/crypto/aes-ce-glue.c
+++ b/arch/arm/crypto/aes-ce-glue.c
@@ -278,14 +278,15 @@ static int ctr_encrypt(struct skcipher_request *req)
u8 *tsrc = walk.src.virt.addr;
/*
- * Minimum alignment is 8 bytes, so if nbytes is <= 8, we need
- * to tell aes_ctr_encrypt() to only read half a block.
+ * Tell aes_ctr_encrypt() to process a tail block.
*/
- blocks = (nbytes <= 8) ? -1 : 1;
+ blocks = -1;
- ce_aes_ctr_encrypt(tail, tsrc, (u8 *)ctx->key_enc,
+ ce_aes_ctr_encrypt(tail, NULL, (u8 *)ctx->key_enc,
num_rounds(ctx), blocks, walk.iv);
- memcpy(tdst, tail, nbytes);
+ if (tdst != tsrc)
+ memcpy(tdst, tsrc, nbytes);
+ crypto_xor(tdst, tail, nbytes);
err = skcipher_walk_done(&walk, 0);
}
kernel_neon_end();
@@ -345,7 +346,6 @@ static struct skcipher_alg aes_algs[] = { {
.cra_flags = CRYPTO_ALG_INTERNAL,
.cra_blocksize = AES_BLOCK_SIZE,
.cra_ctxsize = sizeof(struct crypto_aes_ctx),
- .cra_alignmask = 7,
.cra_module = THIS_MODULE,
},
.min_keysize = AES_MIN_KEY_SIZE,
@@ -361,7 +361,6 @@ static struct skcipher_alg aes_algs[] = { {
.cra_flags = CRYPTO_ALG_INTERNAL,
.cra_blocksize = AES_BLOCK_SIZE,
.cra_ctxsize = sizeof(struct crypto_aes_ctx),
- .cra_alignmask = 7,
.cra_module = THIS_MODULE,
},
.min_keysize = AES_MIN_KEY_SIZE,
@@ -378,7 +377,6 @@ static struct skcipher_alg aes_algs[] = { {
.cra_flags = CRYPTO_ALG_INTERNAL,
.cra_blocksize = 1,
.cra_ctxsize = sizeof(struct crypto_aes_ctx),
- .cra_alignmask = 7,
.cra_module = THIS_MODULE,
},
.min_keysize = AES_MIN_KEY_SIZE,
@@ -396,7 +394,6 @@ static struct skcipher_alg aes_algs[] = { {
.cra_flags = CRYPTO_ALG_INTERNAL,
.cra_blocksize = AES_BLOCK_SIZE,
.cra_ctxsize = sizeof(struct crypto_aes_xts_ctx),
- .cra_alignmask = 7,
.cra_module = THIS_MODULE,
},
.min_keysize = 2 * AES_MIN_KEY_SIZE,
--
2.7.4
^ permalink raw reply related
* [PATCH v2 03/10] crypto: arm/chacha20 - remove cra_alignmask
From: Ard Biesheuvel @ 2017-01-23 14:05 UTC (permalink / raw)
To: linux-crypto, herbert; +Cc: Ard Biesheuvel
In-Reply-To: <1485180326-25612-1-git-send-email-ard.biesheuvel@linaro.org>
Remove the unnecessary alignmask: it is much more efficient to deal with
the misalignment in the core algorithm than relying on the crypto API to
copy the data to a suitably aligned buffer.
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
---
arch/arm/crypto/chacha20-neon-glue.c | 1 -
1 file changed, 1 deletion(-)
diff --git a/arch/arm/crypto/chacha20-neon-glue.c b/arch/arm/crypto/chacha20-neon-glue.c
index 592f75ae4fa1..59a7be08e80c 100644
--- a/arch/arm/crypto/chacha20-neon-glue.c
+++ b/arch/arm/crypto/chacha20-neon-glue.c
@@ -94,7 +94,6 @@ static struct skcipher_alg alg = {
.base.cra_priority = 300,
.base.cra_blocksize = 1,
.base.cra_ctxsize = sizeof(struct chacha20_ctx),
- .base.cra_alignmask = 1,
.base.cra_module = THIS_MODULE,
.min_keysize = CHACHA20_KEY_SIZE,
--
2.7.4
^ permalink raw reply related
* [PATCH v2 04/10] crypto: arm64/aes-ce-ccm - remove cra_alignmask
From: Ard Biesheuvel @ 2017-01-23 14:05 UTC (permalink / raw)
To: linux-crypto, herbert; +Cc: Ard Biesheuvel
In-Reply-To: <1485180326-25612-1-git-send-email-ard.biesheuvel@linaro.org>
Remove the unnecessary alignmask: it is much more efficient to deal with
the misalignment in the core algorithm than relying on the crypto API to
copy the data to a suitably aligned buffer.
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
---
arch/arm64/crypto/aes-ce-ccm-glue.c | 1 -
1 file changed, 1 deletion(-)
diff --git a/arch/arm64/crypto/aes-ce-ccm-glue.c b/arch/arm64/crypto/aes-ce-ccm-glue.c
index cc5515dac74a..6a7dbc7c83a6 100644
--- a/arch/arm64/crypto/aes-ce-ccm-glue.c
+++ b/arch/arm64/crypto/aes-ce-ccm-glue.c
@@ -258,7 +258,6 @@ static struct aead_alg ccm_aes_alg = {
.cra_priority = 300,
.cra_blocksize = 1,
.cra_ctxsize = sizeof(struct crypto_aes_ctx),
- .cra_alignmask = 7,
.cra_module = THIS_MODULE,
},
.ivsize = AES_BLOCK_SIZE,
--
2.7.4
^ permalink raw reply related
* [PATCH v2 05/10] crypto: arm64/aes-blk - remove cra_alignmask
From: Ard Biesheuvel @ 2017-01-23 14:05 UTC (permalink / raw)
To: linux-crypto, herbert; +Cc: Ard Biesheuvel
In-Reply-To: <1485180326-25612-1-git-send-email-ard.biesheuvel@linaro.org>
Remove the unnecessary alignmask: it is much more efficient to deal with
the misalignment in the core algorithm than relying on the crypto API to
copy the data to a suitably aligned buffer.
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
---
arch/arm64/crypto/aes-glue.c | 16 ++++++----------
arch/arm64/crypto/aes-modes.S | 8 +++-----
2 files changed, 9 insertions(+), 15 deletions(-)
diff --git a/arch/arm64/crypto/aes-glue.c b/arch/arm64/crypto/aes-glue.c
index 5164aaf82c6a..8ee1fb7aaa4f 100644
--- a/arch/arm64/crypto/aes-glue.c
+++ b/arch/arm64/crypto/aes-glue.c
@@ -215,14 +215,15 @@ static int ctr_encrypt(struct skcipher_request *req)
u8 *tsrc = walk.src.virt.addr;
/*
- * Minimum alignment is 8 bytes, so if nbytes is <= 8, we need
- * to tell aes_ctr_encrypt() to only read half a block.
+ * Tell aes_ctr_encrypt() to process a tail block.
*/
- blocks = (nbytes <= 8) ? -1 : 1;
+ blocks = -1;
- aes_ctr_encrypt(tail, tsrc, (u8 *)ctx->key_enc, rounds,
+ aes_ctr_encrypt(tail, NULL, (u8 *)ctx->key_enc, rounds,
blocks, walk.iv, first);
- memcpy(tdst, tail, nbytes);
+ if (tdst != tsrc)
+ memcpy(tdst, tsrc, nbytes);
+ crypto_xor(tdst, tail, nbytes);
err = skcipher_walk_done(&walk, 0);
}
kernel_neon_end();
@@ -282,7 +283,6 @@ static struct skcipher_alg aes_algs[] = { {
.cra_flags = CRYPTO_ALG_INTERNAL,
.cra_blocksize = AES_BLOCK_SIZE,
.cra_ctxsize = sizeof(struct crypto_aes_ctx),
- .cra_alignmask = 7,
.cra_module = THIS_MODULE,
},
.min_keysize = AES_MIN_KEY_SIZE,
@@ -298,7 +298,6 @@ static struct skcipher_alg aes_algs[] = { {
.cra_flags = CRYPTO_ALG_INTERNAL,
.cra_blocksize = AES_BLOCK_SIZE,
.cra_ctxsize = sizeof(struct crypto_aes_ctx),
- .cra_alignmask = 7,
.cra_module = THIS_MODULE,
},
.min_keysize = AES_MIN_KEY_SIZE,
@@ -315,7 +314,6 @@ static struct skcipher_alg aes_algs[] = { {
.cra_flags = CRYPTO_ALG_INTERNAL,
.cra_blocksize = 1,
.cra_ctxsize = sizeof(struct crypto_aes_ctx),
- .cra_alignmask = 7,
.cra_module = THIS_MODULE,
},
.min_keysize = AES_MIN_KEY_SIZE,
@@ -332,7 +330,6 @@ static struct skcipher_alg aes_algs[] = { {
.cra_priority = PRIO - 1,
.cra_blocksize = 1,
.cra_ctxsize = sizeof(struct crypto_aes_ctx),
- .cra_alignmask = 7,
.cra_module = THIS_MODULE,
},
.min_keysize = AES_MIN_KEY_SIZE,
@@ -350,7 +347,6 @@ static struct skcipher_alg aes_algs[] = { {
.cra_flags = CRYPTO_ALG_INTERNAL,
.cra_blocksize = AES_BLOCK_SIZE,
.cra_ctxsize = sizeof(struct crypto_aes_xts_ctx),
- .cra_alignmask = 7,
.cra_module = THIS_MODULE,
},
.min_keysize = 2 * AES_MIN_KEY_SIZE,
diff --git a/arch/arm64/crypto/aes-modes.S b/arch/arm64/crypto/aes-modes.S
index 838dad5c209f..92b982a8b112 100644
--- a/arch/arm64/crypto/aes-modes.S
+++ b/arch/arm64/crypto/aes-modes.S
@@ -337,7 +337,7 @@ AES_ENTRY(aes_ctr_encrypt)
.Lctrcarrydone:
subs w4, w4, #1
- bmi .Lctrhalfblock /* blocks < 0 means 1/2 block */
+ bmi .Lctrtailblock /* blocks <0 means tail block */
ld1 {v3.16b}, [x1], #16
eor v3.16b, v0.16b, v3.16b
st1 {v3.16b}, [x0], #16
@@ -348,10 +348,8 @@ AES_ENTRY(aes_ctr_encrypt)
FRAME_POP
ret
-.Lctrhalfblock:
- ld1 {v3.8b}, [x1]
- eor v3.8b, v0.8b, v3.8b
- st1 {v3.8b}, [x0]
+.Lctrtailblock:
+ st1 {v0.16b}, [x0]
FRAME_POP
ret
--
2.7.4
^ permalink raw reply related
* [PATCH v2 06/10] crypto: arm64/chacha20 - remove cra_alignmask
From: Ard Biesheuvel @ 2017-01-23 14:05 UTC (permalink / raw)
To: linux-crypto, herbert; +Cc: Ard Biesheuvel
In-Reply-To: <1485180326-25612-1-git-send-email-ard.biesheuvel@linaro.org>
Remove the unnecessary alignmask: it is much more efficient to deal with
the misalignment in the core algorithm than relying on the crypto API to
copy the data to a suitably aligned buffer.
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
---
arch/arm64/crypto/chacha20-neon-glue.c | 1 -
1 file changed, 1 deletion(-)
diff --git a/arch/arm64/crypto/chacha20-neon-glue.c b/arch/arm64/crypto/chacha20-neon-glue.c
index a7f2337d46cf..a7cd575ea223 100644
--- a/arch/arm64/crypto/chacha20-neon-glue.c
+++ b/arch/arm64/crypto/chacha20-neon-glue.c
@@ -93,7 +93,6 @@ static struct skcipher_alg alg = {
.base.cra_priority = 300,
.base.cra_blocksize = 1,
.base.cra_ctxsize = sizeof(struct chacha20_ctx),
- .base.cra_alignmask = 1,
.base.cra_module = THIS_MODULE,
.min_keysize = CHACHA20_KEY_SIZE,
--
2.7.4
^ permalink raw reply related
* [PATCH v2 07/10] crypto: arm64/aes - avoid literals for cross-module symbol references
From: Ard Biesheuvel @ 2017-01-23 14:05 UTC (permalink / raw)
To: linux-crypto, herbert; +Cc: Ard Biesheuvel
In-Reply-To: <1485180326-25612-1-git-send-email-ard.biesheuvel@linaro.org>
Using simple adrp/add pairs to refer to the AES lookup tables exposed by
the generic AES driver (which could be loaded far away from this driver
when KASLR is in effect) was unreliable at module load time before commit
41c066f2c4d4 ("arm64: assembler: make adr_l work in modules under KASLR"),
which is why the AES code used literals instead.
So now we can get rid of the literals, and switch to the adr_l macro.
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
---
arch/arm64/crypto/aes-cipher-core.S | 7 ++-----
1 file changed, 2 insertions(+), 5 deletions(-)
diff --git a/arch/arm64/crypto/aes-cipher-core.S b/arch/arm64/crypto/aes-cipher-core.S
index 37590ab8121a..cd58c61e6677 100644
--- a/arch/arm64/crypto/aes-cipher-core.S
+++ b/arch/arm64/crypto/aes-cipher-core.S
@@ -89,8 +89,8 @@ CPU_BE( rev w8, w8 )
eor w7, w7, w11
eor w8, w8, w12
- ldr tt, =\ttab
- ldr lt, =\ltab
+ adr_l tt, \ttab
+ adr_l lt, \ltab
tbnz rounds, #1, 1f
@@ -111,9 +111,6 @@ CPU_BE( rev w8, w8 )
stp w5, w6, [out]
stp w7, w8, [out, #8]
ret
-
- .align 4
- .ltorg
.endm
.align 5
--
2.7.4
^ permalink raw reply related
* [PATCH v2 08/10] crypto: arm64/aes - performance tweak
From: Ard Biesheuvel @ 2017-01-23 14:05 UTC (permalink / raw)
To: linux-crypto, herbert; +Cc: Ard Biesheuvel
In-Reply-To: <1485180326-25612-1-git-send-email-ard.biesheuvel@linaro.org>
Shuffle some instructions around in the __hround macro to shave off
0.1 cycles per byte on Cortex-A57.
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
---
arch/arm64/crypto/aes-cipher-core.S | 52 +++++++-------------
1 file changed, 19 insertions(+), 33 deletions(-)
diff --git a/arch/arm64/crypto/aes-cipher-core.S b/arch/arm64/crypto/aes-cipher-core.S
index cd58c61e6677..f2f9cc519309 100644
--- a/arch/arm64/crypto/aes-cipher-core.S
+++ b/arch/arm64/crypto/aes-cipher-core.S
@@ -20,46 +20,32 @@
tt .req x4
lt .req x2
- .macro __hround, out0, out1, in0, in1, in2, in3, t0, t1, enc
- ldp \out0, \out1, [rk], #8
-
- ubfx w13, \in0, #0, #8
- ubfx w14, \in1, #8, #8
- ldr w13, [tt, w13, uxtw #2]
- ldr w14, [tt, w14, uxtw #2]
-
+ .macro __pair, enc, reg0, reg1, in0, in1e, in1d, shift
+ ubfx \reg0, \in0, #\shift, #8
.if \enc
- ubfx w17, \in1, #0, #8
- ubfx w18, \in2, #8, #8
+ ubfx \reg1, \in1e, #\shift, #8
.else
- ubfx w17, \in3, #0, #8
- ubfx w18, \in0, #8, #8
+ ubfx \reg1, \in1d, #\shift, #8
.endif
- ldr w17, [tt, w17, uxtw #2]
- ldr w18, [tt, w18, uxtw #2]
+ ldr \reg0, [tt, \reg0, uxtw #2]
+ ldr \reg1, [tt, \reg1, uxtw #2]
+ .endm
- ubfx w15, \in2, #16, #8
- ubfx w16, \in3, #24, #8
- ldr w15, [tt, w15, uxtw #2]
- ldr w16, [tt, w16, uxtw #2]
+ .macro __hround, out0, out1, in0, in1, in2, in3, t0, t1, enc
+ ldp \out0, \out1, [rk], #8
- .if \enc
- ubfx \t0, \in3, #16, #8
- ubfx \t1, \in0, #24, #8
- .else
- ubfx \t0, \in1, #16, #8
- ubfx \t1, \in2, #24, #8
- .endif
- ldr \t0, [tt, \t0, uxtw #2]
- ldr \t1, [tt, \t1, uxtw #2]
+ __pair \enc, w13, w14, \in0, \in1, \in3, 0
+ __pair \enc, w15, w16, \in1, \in2, \in0, 8
+ __pair \enc, w17, w18, \in2, \in3, \in1, 16
+ __pair \enc, \t0, \t1, \in3, \in0, \in2, 24
eor \out0, \out0, w13
- eor \out1, \out1, w17
- eor \out0, \out0, w14, ror #24
- eor \out1, \out1, w18, ror #24
- eor \out0, \out0, w15, ror #16
- eor \out1, \out1, \t0, ror #16
- eor \out0, \out0, w16, ror #8
+ eor \out1, \out1, w14
+ eor \out0, \out0, w15, ror #24
+ eor \out1, \out1, w16, ror #24
+ eor \out0, \out0, w17, ror #16
+ eor \out1, \out1, w18, ror #16
+ eor \out0, \out0, \t0, ror #8
eor \out1, \out1, \t1, ror #8
.endm
--
2.7.4
^ permalink raw reply related
* [PATCH v2 09/10] crypto: arm64/aes-neon-blk - tweak performance for low end cores
From: Ard Biesheuvel @ 2017-01-23 14:05 UTC (permalink / raw)
To: linux-crypto, herbert; +Cc: Ard Biesheuvel
In-Reply-To: <1485180326-25612-1-git-send-email-ard.biesheuvel@linaro.org>
The non-bitsliced AES implementation using the NEON is highly sensitive
to micro-architectural details, and, as it turns out, the Cortex-A53 on
the Raspberry Pi 3 is a core that can benefit from this code, given that
its scalar AES performance is abysmal (32.9 cycles per byte).
The new bitsliced AES code manages 19.8 cycles per byte on this core,
but can only operate on 8 blocks at a time, which is not supported by
all chaining modes. With a bit of tweaking, we can get the plain NEON
code to run at 22.0 cycles per byte, making it useful for sequential
modes like CBC encryption. (Like bitsliced NEON, the plain NEON
implementation does not use any lookup tables, which makes it easy on
the D-cache, and invulnerable to cache timing attacks)
So tweak the plain NEON AES code to use tbl instructions rather than
shl/sri pairs, and to avoid the need to reload permutation vectors or
other constants from memory in every round.
To allow the ECB and CBC encrypt routines to be reused by the bitsliced
NEON code in a subsequent patch, export them from the module.
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
---
arch/arm64/crypto/aes-glue.c | 2 +
arch/arm64/crypto/aes-neon.S | 210 ++++++++------------
2 files changed, 81 insertions(+), 131 deletions(-)
diff --git a/arch/arm64/crypto/aes-glue.c b/arch/arm64/crypto/aes-glue.c
index 8ee1fb7aaa4f..055bc3f61138 100644
--- a/arch/arm64/crypto/aes-glue.c
+++ b/arch/arm64/crypto/aes-glue.c
@@ -409,5 +409,7 @@ static int __init aes_init(void)
module_cpu_feature_match(AES, aes_init);
#else
module_init(aes_init);
+EXPORT_SYMBOL(neon_aes_ecb_encrypt);
+EXPORT_SYMBOL(neon_aes_cbc_encrypt);
#endif
module_exit(aes_exit);
diff --git a/arch/arm64/crypto/aes-neon.S b/arch/arm64/crypto/aes-neon.S
index 85f07ead7c5c..0d111a6fc229 100644
--- a/arch/arm64/crypto/aes-neon.S
+++ b/arch/arm64/crypto/aes-neon.S
@@ -1,7 +1,7 @@
/*
* linux/arch/arm64/crypto/aes-neon.S - AES cipher for ARMv8 NEON
*
- * Copyright (C) 2013 Linaro Ltd <ard.biesheuvel@linaro.org>
+ * Copyright (C) 2013 - 2017 Linaro Ltd. <ard.biesheuvel@linaro.org>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
@@ -25,9 +25,9 @@
/* preload the entire Sbox */
.macro prepare, sbox, shiftrows, temp
adr \temp, \sbox
- movi v12.16b, #0x40
+ movi v12.16b, #0x1b
ldr q13, \shiftrows
- movi v14.16b, #0x1b
+ ldr q14, .Lror32by8
ld1 {v16.16b-v19.16b}, [\temp], #64
ld1 {v20.16b-v23.16b}, [\temp], #64
ld1 {v24.16b-v27.16b}, [\temp], #64
@@ -50,37 +50,32 @@
/* apply SubBytes transformation using the the preloaded Sbox */
.macro sub_bytes, in
- sub v9.16b, \in\().16b, v12.16b
+ sub v9.16b, \in\().16b, v15.16b
tbl \in\().16b, {v16.16b-v19.16b}, \in\().16b
- sub v10.16b, v9.16b, v12.16b
+ sub v10.16b, v9.16b, v15.16b
tbx \in\().16b, {v20.16b-v23.16b}, v9.16b
- sub v11.16b, v10.16b, v12.16b
+ sub v11.16b, v10.16b, v15.16b
tbx \in\().16b, {v24.16b-v27.16b}, v10.16b
tbx \in\().16b, {v28.16b-v31.16b}, v11.16b
.endm
/* apply MixColumns transformation */
- .macro mix_columns, in
- mul_by_x v10.16b, \in\().16b, v9.16b, v14.16b
- rev32 v8.8h, \in\().8h
- eor \in\().16b, v10.16b, \in\().16b
- shl v9.4s, v8.4s, #24
- shl v11.4s, \in\().4s, #24
- sri v9.4s, v8.4s, #8
- sri v11.4s, \in\().4s, #8
- eor v9.16b, v9.16b, v8.16b
- eor v10.16b, v10.16b, v9.16b
- eor \in\().16b, v10.16b, v11.16b
- .endm
-
+ .macro mix_columns, in, enc
+ .if \enc == 0
/* Inverse MixColumns: pre-multiply by { 5, 0, 4, 0 } */
- .macro inv_mix_columns, in
- mul_by_x v11.16b, \in\().16b, v10.16b, v14.16b
- mul_by_x v11.16b, v11.16b, v10.16b, v14.16b
- eor \in\().16b, \in\().16b, v11.16b
- rev32 v11.8h, v11.8h
- eor \in\().16b, \in\().16b, v11.16b
- mix_columns \in
+ mul_by_x v8.16b, \in\().16b, v9.16b, v12.16b
+ mul_by_x v8.16b, v8.16b, v9.16b, v12.16b
+ eor \in\().16b, \in\().16b, v8.16b
+ rev32 v8.8h, v8.8h
+ eor \in\().16b, \in\().16b, v8.16b
+ .endif
+
+ mul_by_x v9.16b, \in\().16b, v8.16b, v12.16b
+ rev32 v8.8h, \in\().8h
+ eor v8.16b, v8.16b, v9.16b
+ eor \in\().16b, \in\().16b, v8.16b
+ tbl \in\().16b, {\in\().16b}, v14.16b
+ eor \in\().16b, \in\().16b, v8.16b
.endm
.macro do_block, enc, in, rounds, rk, rkp, i
@@ -88,16 +83,13 @@
add \rkp, \rk, #16
mov \i, \rounds
1111: eor \in\().16b, \in\().16b, v15.16b /* ^round key */
+ movi v15.16b, #0x40
tbl \in\().16b, {\in\().16b}, v13.16b /* ShiftRows */
sub_bytes \in
- ld1 {v15.4s}, [\rkp], #16
subs \i, \i, #1
+ ld1 {v15.4s}, [\rkp], #16
beq 2222f
- .if \enc == 1
- mix_columns \in
- .else
- inv_mix_columns \in
- .endif
+ mix_columns \in, \enc
b 1111b
2222: eor \in\().16b, \in\().16b, v15.16b /* ^round key */
.endm
@@ -116,48 +108,48 @@
*/
.macro sub_bytes_2x, in0, in1
- sub v8.16b, \in0\().16b, v12.16b
- sub v9.16b, \in1\().16b, v12.16b
+ sub v8.16b, \in0\().16b, v15.16b
tbl \in0\().16b, {v16.16b-v19.16b}, \in0\().16b
+ sub v9.16b, \in1\().16b, v15.16b
tbl \in1\().16b, {v16.16b-v19.16b}, \in1\().16b
- sub v10.16b, v8.16b, v12.16b
- sub v11.16b, v9.16b, v12.16b
+ sub v10.16b, v8.16b, v15.16b
tbx \in0\().16b, {v20.16b-v23.16b}, v8.16b
+ sub v11.16b, v9.16b, v15.16b
tbx \in1\().16b, {v20.16b-v23.16b}, v9.16b
- sub v8.16b, v10.16b, v12.16b
- sub v9.16b, v11.16b, v12.16b
+ sub v8.16b, v10.16b, v15.16b
tbx \in0\().16b, {v24.16b-v27.16b}, v10.16b
+ sub v9.16b, v11.16b, v15.16b
tbx \in1\().16b, {v24.16b-v27.16b}, v11.16b
tbx \in0\().16b, {v28.16b-v31.16b}, v8.16b
tbx \in1\().16b, {v28.16b-v31.16b}, v9.16b
.endm
.macro sub_bytes_4x, in0, in1, in2, in3
- sub v8.16b, \in0\().16b, v12.16b
+ sub v8.16b, \in0\().16b, v15.16b
tbl \in0\().16b, {v16.16b-v19.16b}, \in0\().16b
- sub v9.16b, \in1\().16b, v12.16b
+ sub v9.16b, \in1\().16b, v15.16b
tbl \in1\().16b, {v16.16b-v19.16b}, \in1\().16b
- sub v10.16b, \in2\().16b, v12.16b
+ sub v10.16b, \in2\().16b, v15.16b
tbl \in2\().16b, {v16.16b-v19.16b}, \in2\().16b
- sub v11.16b, \in3\().16b, v12.16b
+ sub v11.16b, \in3\().16b, v15.16b
tbl \in3\().16b, {v16.16b-v19.16b}, \in3\().16b
tbx \in0\().16b, {v20.16b-v23.16b}, v8.16b
tbx \in1\().16b, {v20.16b-v23.16b}, v9.16b
- sub v8.16b, v8.16b, v12.16b
+ sub v8.16b, v8.16b, v15.16b
tbx \in2\().16b, {v20.16b-v23.16b}, v10.16b
- sub v9.16b, v9.16b, v12.16b
+ sub v9.16b, v9.16b, v15.16b
tbx \in3\().16b, {v20.16b-v23.16b}, v11.16b
- sub v10.16b, v10.16b, v12.16b
+ sub v10.16b, v10.16b, v15.16b
tbx \in0\().16b, {v24.16b-v27.16b}, v8.16b
- sub v11.16b, v11.16b, v12.16b
+ sub v11.16b, v11.16b, v15.16b
tbx \in1\().16b, {v24.16b-v27.16b}, v9.16b
- sub v8.16b, v8.16b, v12.16b
+ sub v8.16b, v8.16b, v15.16b
tbx \in2\().16b, {v24.16b-v27.16b}, v10.16b
- sub v9.16b, v9.16b, v12.16b
+ sub v9.16b, v9.16b, v15.16b
tbx \in3\().16b, {v24.16b-v27.16b}, v11.16b
- sub v10.16b, v10.16b, v12.16b
+ sub v10.16b, v10.16b, v15.16b
tbx \in0\().16b, {v28.16b-v31.16b}, v8.16b
- sub v11.16b, v11.16b, v12.16b
+ sub v11.16b, v11.16b, v15.16b
tbx \in1\().16b, {v28.16b-v31.16b}, v9.16b
tbx \in2\().16b, {v28.16b-v31.16b}, v10.16b
tbx \in3\().16b, {v28.16b-v31.16b}, v11.16b
@@ -174,59 +166,30 @@
eor \out1\().16b, \out1\().16b, \tmp1\().16b
.endm
- .macro mix_columns_2x, in0, in1
- mul_by_x_2x v8, v9, \in0, \in1, v10, v11, v14
- rev32 v10.8h, \in0\().8h
- rev32 v11.8h, \in1\().8h
- eor \in0\().16b, v8.16b, \in0\().16b
- eor \in1\().16b, v9.16b, \in1\().16b
- shl v12.4s, v10.4s, #24
- shl v13.4s, v11.4s, #24
- eor v8.16b, v8.16b, v10.16b
- sri v12.4s, v10.4s, #8
- shl v10.4s, \in0\().4s, #24
- eor v9.16b, v9.16b, v11.16b
- sri v13.4s, v11.4s, #8
- shl v11.4s, \in1\().4s, #24
- sri v10.4s, \in0\().4s, #8
- eor \in0\().16b, v8.16b, v12.16b
- sri v11.4s, \in1\().4s, #8
- eor \in1\().16b, v9.16b, v13.16b
- eor \in0\().16b, v10.16b, \in0\().16b
- eor \in1\().16b, v11.16b, \in1\().16b
- .endm
-
- .macro inv_mix_cols_2x, in0, in1
- mul_by_x_2x v8, v9, \in0, \in1, v10, v11, v14
- mul_by_x_2x v8, v9, v8, v9, v10, v11, v14
+ .macro mix_columns_2x, in0, in1, enc
+ .if \enc == 0
+ /* Inverse MixColumns: pre-multiply by { 5, 0, 4, 0 } */
+ mul_by_x_2x v8, v9, \in0, \in1, v10, v11, v12
+ mul_by_x_2x v8, v9, v8, v9, v10, v11, v12
eor \in0\().16b, \in0\().16b, v8.16b
- eor \in1\().16b, \in1\().16b, v9.16b
rev32 v8.8h, v8.8h
- rev32 v9.8h, v9.8h
- eor \in0\().16b, \in0\().16b, v8.16b
eor \in1\().16b, \in1\().16b, v9.16b
- mix_columns_2x \in0, \in1
- .endm
-
- .macro inv_mix_cols_4x, in0, in1, in2, in3
- mul_by_x_2x v8, v9, \in0, \in1, v10, v11, v14
- mul_by_x_2x v10, v11, \in2, \in3, v12, v13, v14
- mul_by_x_2x v8, v9, v8, v9, v12, v13, v14
- mul_by_x_2x v10, v11, v10, v11, v12, v13, v14
- eor \in0\().16b, \in0\().16b, v8.16b
- eor \in1\().16b, \in1\().16b, v9.16b
- eor \in2\().16b, \in2\().16b, v10.16b
- eor \in3\().16b, \in3\().16b, v11.16b
- rev32 v8.8h, v8.8h
rev32 v9.8h, v9.8h
- rev32 v10.8h, v10.8h
- rev32 v11.8h, v11.8h
eor \in0\().16b, \in0\().16b, v8.16b
eor \in1\().16b, \in1\().16b, v9.16b
- eor \in2\().16b, \in2\().16b, v10.16b
- eor \in3\().16b, \in3\().16b, v11.16b
- mix_columns_2x \in0, \in1
- mix_columns_2x \in2, \in3
+ .endif
+
+ mul_by_x_2x v8, v9, \in0, \in1, v10, v11, v12
+ rev32 v10.8h, \in0\().8h
+ rev32 v11.8h, \in1\().8h
+ eor v10.16b, v10.16b, v8.16b
+ eor v11.16b, v11.16b, v9.16b
+ eor \in0\().16b, \in0\().16b, v10.16b
+ eor \in1\().16b, \in1\().16b, v11.16b
+ tbl \in0\().16b, {\in0\().16b}, v14.16b
+ tbl \in1\().16b, {\in1\().16b}, v14.16b
+ eor \in0\().16b, \in0\().16b, v10.16b
+ eor \in1\().16b, \in1\().16b, v11.16b
.endm
.macro do_block_2x, enc, in0, in1 rounds, rk, rkp, i
@@ -235,20 +198,14 @@
mov \i, \rounds
1111: eor \in0\().16b, \in0\().16b, v15.16b /* ^round key */
eor \in1\().16b, \in1\().16b, v15.16b /* ^round key */
- sub_bytes_2x \in0, \in1
+ movi v15.16b, #0x40
tbl \in0\().16b, {\in0\().16b}, v13.16b /* ShiftRows */
tbl \in1\().16b, {\in1\().16b}, v13.16b /* ShiftRows */
- ld1 {v15.4s}, [\rkp], #16
+ sub_bytes_2x \in0, \in1
subs \i, \i, #1
+ ld1 {v15.4s}, [\rkp], #16
beq 2222f
- .if \enc == 1
- mix_columns_2x \in0, \in1
- ldr q13, .LForward_ShiftRows
- .else
- inv_mix_cols_2x \in0, \in1
- ldr q13, .LReverse_ShiftRows
- .endif
- movi v12.16b, #0x40
+ mix_columns_2x \in0, \in1, \enc
b 1111b
2222: eor \in0\().16b, \in0\().16b, v15.16b /* ^round key */
eor \in1\().16b, \in1\().16b, v15.16b /* ^round key */
@@ -262,23 +219,17 @@
eor \in1\().16b, \in1\().16b, v15.16b /* ^round key */
eor \in2\().16b, \in2\().16b, v15.16b /* ^round key */
eor \in3\().16b, \in3\().16b, v15.16b /* ^round key */
- sub_bytes_4x \in0, \in1, \in2, \in3
+ movi v15.16b, #0x40
tbl \in0\().16b, {\in0\().16b}, v13.16b /* ShiftRows */
tbl \in1\().16b, {\in1\().16b}, v13.16b /* ShiftRows */
tbl \in2\().16b, {\in2\().16b}, v13.16b /* ShiftRows */
tbl \in3\().16b, {\in3\().16b}, v13.16b /* ShiftRows */
- ld1 {v15.4s}, [\rkp], #16
+ sub_bytes_4x \in0, \in1, \in2, \in3
subs \i, \i, #1
+ ld1 {v15.4s}, [\rkp], #16
beq 2222f
- .if \enc == 1
- mix_columns_2x \in0, \in1
- mix_columns_2x \in2, \in3
- ldr q13, .LForward_ShiftRows
- .else
- inv_mix_cols_4x \in0, \in1, \in2, \in3
- ldr q13, .LReverse_ShiftRows
- .endif
- movi v12.16b, #0x40
+ mix_columns_2x \in0, \in1, \enc
+ mix_columns_2x \in2, \in3, \enc
b 1111b
2222: eor \in0\().16b, \in0\().16b, v15.16b /* ^round key */
eor \in1\().16b, \in1\().16b, v15.16b /* ^round key */
@@ -305,19 +256,7 @@
#include "aes-modes.S"
.text
- .align 4
-.LForward_ShiftRows:
-CPU_LE( .byte 0x0, 0x5, 0xa, 0xf, 0x4, 0x9, 0xe, 0x3 )
-CPU_LE( .byte 0x8, 0xd, 0x2, 0x7, 0xc, 0x1, 0x6, 0xb )
-CPU_BE( .byte 0xb, 0x6, 0x1, 0xc, 0x7, 0x2, 0xd, 0x8 )
-CPU_BE( .byte 0x3, 0xe, 0x9, 0x4, 0xf, 0xa, 0x5, 0x0 )
-
-.LReverse_ShiftRows:
-CPU_LE( .byte 0x0, 0xd, 0xa, 0x7, 0x4, 0x1, 0xe, 0xb )
-CPU_LE( .byte 0x8, 0x5, 0x2, 0xf, 0xc, 0x9, 0x6, 0x3 )
-CPU_BE( .byte 0x3, 0x6, 0x9, 0xc, 0xf, 0x2, 0x5, 0x8 )
-CPU_BE( .byte 0xb, 0xe, 0x1, 0x4, 0x7, 0xa, 0xd, 0x0 )
-
+ .align 6
.LForward_Sbox:
.byte 0x63, 0x7c, 0x77, 0x7b, 0xf2, 0x6b, 0x6f, 0xc5
.byte 0x30, 0x01, 0x67, 0x2b, 0xfe, 0xd7, 0xab, 0x76
@@ -385,3 +324,12 @@ CPU_BE( .byte 0xb, 0xe, 0x1, 0x4, 0x7, 0xa, 0xd, 0x0 )
.byte 0xc8, 0xeb, 0xbb, 0x3c, 0x83, 0x53, 0x99, 0x61
.byte 0x17, 0x2b, 0x04, 0x7e, 0xba, 0x77, 0xd6, 0x26
.byte 0xe1, 0x69, 0x14, 0x63, 0x55, 0x21, 0x0c, 0x7d
+
+.LForward_ShiftRows:
+ .octa 0x0b06010c07020d08030e09040f0a0500
+
+.LReverse_ShiftRows:
+ .octa 0x0306090c0f0205080b0e0104070a0d00
+
+.Lror32by8:
+ .octa 0x0c0f0e0d080b0a090407060500030201
--
2.7.4
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox