From 6d25a633ea68a103c7293d16eb69a7d4689075ad Mon Sep 17 00:00:00 2001 From: Nick Terrell Date: Thu, 30 Jul 2020 12:08:34 -0700 Subject: lib: Prepare zstd for preboot environment, improve performance These changes are necessary to get the build to work in the preboot environment, and to get reasonable performance: - Remove a double definition of the CHECK_F macro when the zstd library is amalgamated. - Switch ZSTD_copy8() to __builtin_memcpy(), because in the preboot environment on x86 gcc can't inline `memcpy()` otherwise. - Limit the gcc hack in ZSTD_wildcopy() to the broken gcc version. See https://gcc.gnu.org/bugzilla/show_bug.cgi?id=81388. ZSTD_copy8() and ZSTD_wildcopy() are in the core of the zstd hot loop. So outlining these calls to memcpy(), and having an extra branch are very detrimental to performance. Signed-off-by: Nick Terrell Signed-off-by: Ingo Molnar Tested-by: Sedat Dilek Reviewed-by: Kees Cook Link: https://lore.kernel.org/r/20200730190841.2071656-2-nickrterrell@gmail.com --- lib/zstd/fse_decompress.c | 9 +-------- lib/zstd/zstd_internal.h | 14 ++++++++++++-- 2 files changed, 13 insertions(+), 10 deletions(-) (limited to 'lib') diff --git a/lib/zstd/fse_decompress.c b/lib/zstd/fse_decompress.c index a84300e5a013..0b353530fb3f 100644 --- a/lib/zstd/fse_decompress.c +++ b/lib/zstd/fse_decompress.c @@ -47,6 +47,7 @@ ****************************************************************/ #include "bitstream.h" #include "fse.h" +#include "zstd_internal.h" #include #include #include /* memcpy, memset */ @@ -60,14 +61,6 @@ enum { FSE_static_assert = 1 / (int)(!!(c)) }; \ } /* use only *after* variable declarations */ -/* check and forward error code */ -#define CHECK_F(f) \ - { \ - size_t const e = f; \ - if (FSE_isError(e)) \ - return e; \ - } - /* ************************************************************** * Templates ****************************************************************/ diff --git a/lib/zstd/zstd_internal.h b/lib/zstd/zstd_internal.h index 1a79fab9e13a..dac753397f86 100644 --- a/lib/zstd/zstd_internal.h +++ b/lib/zstd/zstd_internal.h @@ -127,7 +127,14 @@ static const U32 OF_defaultNormLog = OF_DEFAULTNORMLOG; * Shared functions to include for inlining *********************************************/ ZSTD_STATIC void ZSTD_copy8(void *dst, const void *src) { - memcpy(dst, src, 8); + /* + * zstd relies heavily on gcc being able to analyze and inline this + * memcpy() call, since it is called in a tight loop. Preboot mode + * is compiled in freestanding mode, which stops gcc from analyzing + * memcpy(). Use __builtin_memcpy() to tell gcc to analyze this as a + * regular memcpy(). + */ + __builtin_memcpy(dst, src, 8); } /*! ZSTD_wildcopy() : * custom version of memcpy(), can copy up to 7 bytes too many (8 bytes if length==0) */ @@ -137,13 +144,16 @@ ZSTD_STATIC void ZSTD_wildcopy(void *dst, const void *src, ptrdiff_t length) const BYTE* ip = (const BYTE*)src; BYTE* op = (BYTE*)dst; BYTE* const oend = op + length; - /* Work around https://gcc.gnu.org/bugzilla/show_bug.cgi?id=81388. +#if defined(GCC_VERSION) && GCC_VERSION >= 70000 && GCC_VERSION < 70200 + /* + * Work around https://gcc.gnu.org/bugzilla/show_bug.cgi?id=81388. * Avoid the bad case where the loop only runs once by handling the * special case separately. This doesn't trigger the bug because it * doesn't involve pointer/integer overflow. */ if (length <= 8) return ZSTD_copy8(dst, src); +#endif do { ZSTD_copy8(op, ip); op += 8; -- cgit v1.2.3 From 4963bb2b89884bbdb7e33e6a09c159551e9627aa Mon Sep 17 00:00:00 2001 From: Nick Terrell Date: Thu, 30 Jul 2020 12:08:35 -0700 Subject: lib: Add zstd support to decompress - Add unzstd() and the zstd decompress interface. - Add zstd support to decompress_method(). The decompress_method() and unzstd() functions are used to decompress the initramfs and the initrd. The __decompress() function is used in the preboot environment to decompress a zstd compressed kernel. The zstd decompression function allows the input and output buffers to overlap because that is used by x86 kernel decompression. Signed-off-by: Nick Terrell Signed-off-by: Ingo Molnar Tested-by: Sedat Dilek Reviewed-by: Kees Cook Link: https://lore.kernel.org/r/20200730190841.2071656-3-nickrterrell@gmail.com --- include/linux/decompress/unzstd.h | 11 ++ lib/Kconfig | 4 + lib/Makefile | 1 + lib/decompress.c | 5 + lib/decompress_unzstd.c | 345 ++++++++++++++++++++++++++++++++++++++ 5 files changed, 366 insertions(+) create mode 100644 include/linux/decompress/unzstd.h create mode 100644 lib/decompress_unzstd.c (limited to 'lib') diff --git a/include/linux/decompress/unzstd.h b/include/linux/decompress/unzstd.h new file mode 100644 index 000000000000..56d539ae880f --- /dev/null +++ b/include/linux/decompress/unzstd.h @@ -0,0 +1,11 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef LINUX_DECOMPRESS_UNZSTD_H +#define LINUX_DECOMPRESS_UNZSTD_H + +int unzstd(unsigned char *inbuf, long len, + long (*fill)(void*, unsigned long), + long (*flush)(void*, unsigned long), + unsigned char *output, + long *pos, + void (*error_fn)(char *x)); +#endif diff --git a/lib/Kconfig b/lib/Kconfig index df3f3da95990..a5d6f23c4cab 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -342,6 +342,10 @@ config DECOMPRESS_LZ4 select LZ4_DECOMPRESS tristate +config DECOMPRESS_ZSTD + select ZSTD_DECOMPRESS + tristate + # # Generic allocator support is selected if needed # diff --git a/lib/Makefile b/lib/Makefile index b1c42c10073b..2ba9642a3a87 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -170,6 +170,7 @@ lib-$(CONFIG_DECOMPRESS_LZMA) += decompress_unlzma.o lib-$(CONFIG_DECOMPRESS_XZ) += decompress_unxz.o lib-$(CONFIG_DECOMPRESS_LZO) += decompress_unlzo.o lib-$(CONFIG_DECOMPRESS_LZ4) += decompress_unlz4.o +lib-$(CONFIG_DECOMPRESS_ZSTD) += decompress_unzstd.o obj-$(CONFIG_TEXTSEARCH) += textsearch.o obj-$(CONFIG_TEXTSEARCH_KMP) += ts_kmp.o diff --git a/lib/decompress.c b/lib/decompress.c index 857ab1af1ef3..ab3fc90ffc64 100644 --- a/lib/decompress.c +++ b/lib/decompress.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include @@ -37,6 +38,9 @@ #ifndef CONFIG_DECOMPRESS_LZ4 # define unlz4 NULL #endif +#ifndef CONFIG_DECOMPRESS_ZSTD +# define unzstd NULL +#endif struct compress_format { unsigned char magic[2]; @@ -52,6 +56,7 @@ static const struct compress_format compressed_formats[] __initconst = { { {0xfd, 0x37}, "xz", unxz }, { {0x89, 0x4c}, "lzo", unlzo }, { {0x02, 0x21}, "lz4", unlz4 }, + { {0x28, 0xb5}, "zstd", unzstd }, { {0, 0}, NULL, NULL } }; diff --git a/lib/decompress_unzstd.c b/lib/decompress_unzstd.c new file mode 100644 index 000000000000..0ad2c15479ed --- /dev/null +++ b/lib/decompress_unzstd.c @@ -0,0 +1,345 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* + * Important notes about in-place decompression + * + * At least on x86, the kernel is decompressed in place: the compressed data + * is placed to the end of the output buffer, and the decompressor overwrites + * most of the compressed data. There must be enough safety margin to + * guarantee that the write position is always behind the read position. + * + * The safety margin for ZSTD with a 128 KB block size is calculated below. + * Note that the margin with ZSTD is bigger than with GZIP or XZ! + * + * The worst case for in-place decompression is that the beginning of + * the file is compressed extremely well, and the rest of the file is + * uncompressible. Thus, we must look for worst-case expansion when the + * compressor is encoding uncompressible data. + * + * The structure of the .zst file in case of a compresed kernel is as follows. + * Maximum sizes (as bytes) of the fields are in parenthesis. + * + * Frame Header: (18) + * Blocks: (N) + * Checksum: (4) + * + * The frame header and checksum overhead is at most 22 bytes. + * + * ZSTD stores the data in blocks. Each block has a header whose size is + * a 3 bytes. After the block header, there is up to 128 KB of payload. + * The maximum uncompressed size of the payload is 128 KB. The minimum + * uncompressed size of the payload is never less than the payload size + * (excluding the block header). + * + * The assumption, that the uncompressed size of the payload is never + * smaller than the payload itself, is valid only when talking about + * the payload as a whole. It is possible that the payload has parts where + * the decompressor consumes more input than it produces output. Calculating + * the worst case for this would be tricky. Instead of trying to do that, + * let's simply make sure that the decompressor never overwrites any bytes + * of the payload which it is currently reading. + * + * Now we have enough information to calculate the safety margin. We need + * - 22 bytes for the .zst file format headers; + * - 3 bytes per every 128 KiB of uncompressed size (one block header per + * block); and + * - 128 KiB (biggest possible zstd block size) to make sure that the + * decompressor never overwrites anything from the block it is currently + * reading. + * + * We get the following formula: + * + * safety_margin = 22 + uncompressed_size * 3 / 131072 + 131072 + * <= 22 + (uncompressed_size >> 15) + 131072 + */ + +/* + * Preboot environments #include "path/to/decompress_unzstd.c". + * All of the source files we depend on must be #included. + * zstd's only source dependeny is xxhash, which has no source + * dependencies. + * + * When UNZSTD_PREBOOT is defined we declare __decompress(), which is + * used for kernel decompression, instead of unzstd(). + * + * Define __DISABLE_EXPORTS in preboot environments to prevent symbols + * from xxhash and zstd from being exported by the EXPORT_SYMBOL macro. + */ +#ifdef STATIC +# define UNZSTD_PREBOOT +# include "xxhash.c" +# include "zstd/entropy_common.c" +# include "zstd/fse_decompress.c" +# include "zstd/huf_decompress.c" +# include "zstd/zstd_common.c" +# include "zstd/decompress.c" +#endif + +#include +#include +#include + +/* 128MB is the maximum window size supported by zstd. */ +#define ZSTD_WINDOWSIZE_MAX (1 << ZSTD_WINDOWLOG_MAX) +/* + * Size of the input and output buffers in multi-call mode. + * Pick a larger size because it isn't used during kernel decompression, + * since that is single pass, and we have to allocate a large buffer for + * zstd's window anyway. The larger size speeds up initramfs decompression. + */ +#define ZSTD_IOBUF_SIZE (1 << 17) + +static int INIT handle_zstd_error(size_t ret, void (*error)(char *x)) +{ + const int err = ZSTD_getErrorCode(ret); + + if (!ZSTD_isError(ret)) + return 0; + + switch (err) { + case ZSTD_error_memory_allocation: + error("ZSTD decompressor ran out of memory"); + break; + case ZSTD_error_prefix_unknown: + error("Input is not in the ZSTD format (wrong magic bytes)"); + break; + case ZSTD_error_dstSize_tooSmall: + case ZSTD_error_corruption_detected: + case ZSTD_error_checksum_wrong: + error("ZSTD-compressed data is corrupt"); + break; + default: + error("ZSTD-compressed data is probably corrupt"); + break; + } + return -1; +} + +/* + * Handle the case where we have the entire input and output in one segment. + * We can allocate less memory (no circular buffer for the sliding window), + * and avoid some memcpy() calls. + */ +static int INIT decompress_single(const u8 *in_buf, long in_len, u8 *out_buf, + long out_len, long *in_pos, + void (*error)(char *x)) +{ + const size_t wksp_size = ZSTD_DCtxWorkspaceBound(); + void *wksp = large_malloc(wksp_size); + ZSTD_DCtx *dctx = ZSTD_initDCtx(wksp, wksp_size); + int err; + size_t ret; + + if (dctx == NULL) { + error("Out of memory while allocating ZSTD_DCtx"); + err = -1; + goto out; + } + /* + * Find out how large the frame actually is, there may be junk at + * the end of the frame that ZSTD_decompressDCtx() can't handle. + */ + ret = ZSTD_findFrameCompressedSize(in_buf, in_len); + err = handle_zstd_error(ret, error); + if (err) + goto out; + in_len = (long)ret; + + ret = ZSTD_decompressDCtx(dctx, out_buf, out_len, in_buf, in_len); + err = handle_zstd_error(ret, error); + if (err) + goto out; + + if (in_pos != NULL) + *in_pos = in_len; + + err = 0; +out: + if (wksp != NULL) + large_free(wksp); + return err; +} + +static int INIT __unzstd(unsigned char *in_buf, long in_len, + long (*fill)(void*, unsigned long), + long (*flush)(void*, unsigned long), + unsigned char *out_buf, long out_len, + long *in_pos, + void (*error)(char *x)) +{ + ZSTD_inBuffer in; + ZSTD_outBuffer out; + ZSTD_frameParams params; + void *in_allocated = NULL; + void *out_allocated = NULL; + void *wksp = NULL; + size_t wksp_size; + ZSTD_DStream *dstream; + int err; + size_t ret; + + if (out_len == 0) + out_len = LONG_MAX; /* no limit */ + + if (fill == NULL && flush == NULL) + /* + * We can decompress faster and with less memory when we have a + * single chunk. + */ + return decompress_single(in_buf, in_len, out_buf, out_len, + in_pos, error); + + /* + * If in_buf is not provided, we must be using fill(), so allocate + * a large enough buffer. If it is provided, it must be at least + * ZSTD_IOBUF_SIZE large. + */ + if (in_buf == NULL) { + in_allocated = large_malloc(ZSTD_IOBUF_SIZE); + if (in_allocated == NULL) { + error("Out of memory while allocating input buffer"); + err = -1; + goto out; + } + in_buf = in_allocated; + in_len = 0; + } + /* Read the first chunk, since we need to decode the frame header. */ + if (fill != NULL) + in_len = fill(in_buf, ZSTD_IOBUF_SIZE); + if (in_len < 0) { + error("ZSTD-compressed data is truncated"); + err = -1; + goto out; + } + /* Set the first non-empty input buffer. */ + in.src = in_buf; + in.pos = 0; + in.size = in_len; + /* Allocate the output buffer if we are using flush(). */ + if (flush != NULL) { + out_allocated = large_malloc(ZSTD_IOBUF_SIZE); + if (out_allocated == NULL) { + error("Out of memory while allocating output buffer"); + err = -1; + goto out; + } + out_buf = out_allocated; + out_len = ZSTD_IOBUF_SIZE; + } + /* Set the output buffer. */ + out.dst = out_buf; + out.pos = 0; + out.size = out_len; + + /* + * We need to know the window size to allocate the ZSTD_DStream. + * Since we are streaming, we need to allocate a buffer for the sliding + * window. The window size varies from 1 KB to ZSTD_WINDOWSIZE_MAX + * (8 MB), so it is important to use the actual value so as not to + * waste memory when it is smaller. + */ + ret = ZSTD_getFrameParams(¶ms, in.src, in.size); + err = handle_zstd_error(ret, error); + if (err) + goto out; + if (ret != 0) { + error("ZSTD-compressed data has an incomplete frame header"); + err = -1; + goto out; + } + if (params.windowSize > ZSTD_WINDOWSIZE_MAX) { + error("ZSTD-compressed data has too large a window size"); + err = -1; + goto out; + } + + /* + * Allocate the ZSTD_DStream now that we know how much memory is + * required. + */ + wksp_size = ZSTD_DStreamWorkspaceBound(params.windowSize); + wksp = large_malloc(wksp_size); + dstream = ZSTD_initDStream(params.windowSize, wksp, wksp_size); + if (dstream == NULL) { + error("Out of memory while allocating ZSTD_DStream"); + err = -1; + goto out; + } + + /* + * Decompression loop: + * Read more data if necessary (error if no more data can be read). + * Call the decompression function, which returns 0 when finished. + * Flush any data produced if using flush(). + */ + if (in_pos != NULL) + *in_pos = 0; + do { + /* + * If we need to reload data, either we have fill() and can + * try to get more data, or we don't and the input is truncated. + */ + if (in.pos == in.size) { + if (in_pos != NULL) + *in_pos += in.pos; + in_len = fill ? fill(in_buf, ZSTD_IOBUF_SIZE) : -1; + if (in_len < 0) { + error("ZSTD-compressed data is truncated"); + err = -1; + goto out; + } + in.pos = 0; + in.size = in_len; + } + /* Returns zero when the frame is complete. */ + ret = ZSTD_decompressStream(dstream, &out, &in); + err = handle_zstd_error(ret, error); + if (err) + goto out; + /* Flush all of the data produced if using flush(). */ + if (flush != NULL && out.pos > 0) { + if (out.pos != flush(out.dst, out.pos)) { + error("Failed to flush()"); + err = -1; + goto out; + } + out.pos = 0; + } + } while (ret != 0); + + if (in_pos != NULL) + *in_pos += in.pos; + + err = 0; +out: + if (in_allocated != NULL) + large_free(in_allocated); + if (out_allocated != NULL) + large_free(out_allocated); + if (wksp != NULL) + large_free(wksp); + return err; +} + +#ifndef UNZSTD_PREBOOT +STATIC int INIT unzstd(unsigned char *buf, long len, + long (*fill)(void*, unsigned long), + long (*flush)(void*, unsigned long), + unsigned char *out_buf, + long *pos, + void (*error)(char *x)) +{ + return __unzstd(buf, len, fill, flush, out_buf, 0, pos, error); +} +#else +STATIC int INIT __decompress(unsigned char *buf, long len, + long (*fill)(void*, unsigned long), + long (*flush)(void*, unsigned long), + unsigned char *out_buf, long out_len, + long *pos, + void (*error)(char *x)) +{ + return __unzstd(buf, len, fill, flush, out_buf, out_len, pos, error); +} +#endif -- cgit v1.2.3