From 69334ca530da80c1563ac6a3bd32afa40884ccd3 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Thu, 30 Jan 2020 22:11:01 -0800 Subject: lib/test_bitmap: correct test data offsets for 32-bit On 32-bit platform the size of long is only 32 bits which makes wrong offset in the array of 64 bit size. Calculate offset based on BITS_PER_LONG. Link: http://lkml.kernel.org/r/20200109103601.45929-1-andriy.shevchenko@linux.intel.com Fixes: 30544ed5de43 ("lib/bitmap: introduce bitmap_replace() helper") Signed-off-by: Andy Shevchenko Reported-by: Guenter Roeck Cc: Rasmus Villemoes Cc: Yury Norov Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/test_bitmap.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'lib') diff --git a/lib/test_bitmap.c b/lib/test_bitmap.c index e14a15ac250b..71ec3afe1681 100644 --- a/lib/test_bitmap.c +++ b/lib/test_bitmap.c @@ -275,22 +275,23 @@ static void __init test_copy(void) static void __init test_replace(void) { unsigned int nbits = 64; + unsigned int nlongs = DIV_ROUND_UP(nbits, BITS_PER_LONG); DECLARE_BITMAP(bmap, 1024); bitmap_zero(bmap, 1024); - bitmap_replace(bmap, &exp2[0], &exp2[1], exp2_to_exp3_mask, nbits); + bitmap_replace(bmap, &exp2[0 * nlongs], &exp2[1 * nlongs], exp2_to_exp3_mask, nbits); expect_eq_bitmap(bmap, exp3_0_1, nbits); bitmap_zero(bmap, 1024); - bitmap_replace(bmap, &exp2[1], &exp2[0], exp2_to_exp3_mask, nbits); + bitmap_replace(bmap, &exp2[1 * nlongs], &exp2[0 * nlongs], exp2_to_exp3_mask, nbits); expect_eq_bitmap(bmap, exp3_1_0, nbits); bitmap_fill(bmap, 1024); - bitmap_replace(bmap, &exp2[0], &exp2[1], exp2_to_exp3_mask, nbits); + bitmap_replace(bmap, &exp2[0 * nlongs], &exp2[1 * nlongs], exp2_to_exp3_mask, nbits); expect_eq_bitmap(bmap, exp3_0_1, nbits); bitmap_fill(bmap, 1024); - bitmap_replace(bmap, &exp2[1], &exp2[0], exp2_to_exp3_mask, nbits); + bitmap_replace(bmap, &exp2[1 * nlongs], &exp2[0 * nlongs], exp2_to_exp3_mask, nbits); expect_eq_bitmap(bmap, exp3_1_0, nbits); } -- cgit v1.2.3 From 3e21d9a501bf99aee2e5835d7f34d8c823f115b5 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Thu, 30 Jan 2020 22:13:51 -0800 Subject: lib/test_kasan.c: fix memory leak in kmalloc_oob_krealloc_more() In case memory resources for _ptr2_ were allocated, release them before return. Notice that in case _ptr1_ happens to be NULL, krealloc() behaves exactly like kmalloc(). Addresses-Coverity-ID: 1490594 ("Resource leak") Link: http://lkml.kernel.org/r/20200123160115.GA4202@embeddedor Fixes: 3f15801cdc23 ("lib: add kasan test module") Signed-off-by: Gustavo A. R. Silva Reviewed-by: Dmitry Vyukov Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/test_kasan.c | 1 + 1 file changed, 1 insertion(+) (limited to 'lib') diff --git a/lib/test_kasan.c b/lib/test_kasan.c index 328d33beae36..3872d250ed2c 100644 --- a/lib/test_kasan.c +++ b/lib/test_kasan.c @@ -158,6 +158,7 @@ static noinline void __init kmalloc_oob_krealloc_more(void) if (!ptr1 || !ptr2) { pr_err("Allocation failed\n"); kfree(ptr1); + kfree(ptr2); return; } -- cgit v1.2.3 From aa5b395b69b65450e008b95ec623b4fc4b175f9f Mon Sep 17 00:00:00 2001 From: Mikhail Zaslonko Date: Thu, 30 Jan 2020 22:16:17 -0800 Subject: lib/zlib: add s390 hardware support for kernel zlib_deflate Patch series "S390 hardware support for kernel zlib", v3. With IBM z15 mainframe the new DFLTCC instruction is available. It implements deflate algorithm in hardware (Nest Acceleration Unit - NXU) with estimated compression and decompression performance orders of magnitude faster than the current zlib. This patchset adds s390 hardware compression support to kernel zlib. The code is based on the userspace zlib implementation: https://github.com/madler/zlib/pull/410 The coding style is also preserved for future maintainability. There is only limited set of userspace zlib functions represented in kernel. Apart from that, all the memory allocation should be performed in advance. Thus, the workarea structures are extended with the parameter lists required for the DEFLATE CONVENTION CALL instruction. Since kernel zlib itself does not support gzip headers, only Adler-32 checksum is processed (also can be produced by DFLTCC facility). Like it was implemented for userspace, kernel zlib will compress in hardware on level 1, and in software on all other levels. Decompression will always happen in hardware (when enabled). Two DFLTCC compression calls produce the same results only when they both are made on machines of the same generation, and when the respective buffers have the same offset relative to the start of the page. Therefore care should be taken when using hardware compression when reproducible results are desired. However it does always produce the standard conform output which can be inflated anyway. The new kernel command line parameter 'dfltcc' is introduced to configure s390 zlib hardware support: Format: { on | off | def_only | inf_only | always } on: s390 zlib hardware support for compression on level 1 and decompression (default) off: No s390 zlib hardware support def_only: s390 zlib hardware support for deflate only (compression on level 1) inf_only: s390 zlib hardware support for inflate only (decompression) always: Same as 'on' but ignores the selected compression level always using hardware support (used for debugging) The main purpose of the integration of the NXU support into the kernel zlib is the use of hardware deflate in btrfs filesystem with on-the-fly compression enabled. Apart from that, hardware support can also be used during boot for decompressing the kernel or the ramdisk image With the patch for btrfs expanding zlib buffer from 1 to 4 pages (patch 6) the following performance results have been achieved using the ramdisk with btrfs. These are relative numbers based on throughput rate and compression ratio for zlib level 1: Input data Deflate rate Inflate rate Compression ratio NXU/Software NXU/Software NXU/Software stream of zeroes 1.46 1.02 1.00 random ASCII data 10.44 3.00 0.96 ASCII text (dickens) 6,21 3.33 0.94 binary data (vmlinux) 8,37 3.90 1.02 This means that s390 hardware deflate can provide up to 10 times faster compression (on level 1) and up to 4 times faster decompression (refers to all compression levels) for btrfs zlib. Disclaimer: Performance results are based on IBM internal tests using DD command-line utility on btrfs on a Fedora 30 based internal driver in native LPAR on a z15 system. Results may vary based on individual workload, configuration and software levels. This patch (of 9): Create zlib_dfltcc library with the s390 DEFLATE CONVERSION CALL implementation and related compression functions. Update zlib_deflate functions with the hooks for s390 hardware support and adjust workspace structures with extra parameter lists required for hardware deflate. Link: http://lkml.kernel.org/r/20200103223334.20669-2-zaslonko@linux.ibm.com Signed-off-by: Ilya Leoshkevich Signed-off-by: Mikhail Zaslonko Co-developed-by: Ilya Leoshkevich Cc: Chris Mason Cc: Christian Borntraeger Cc: David Sterba Cc: Eduard Shishkin Cc: Heiko Carstens Cc: Josef Bacik Cc: Richard Purdie Cc: Vasily Gorbik Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/Kconfig | 7 + lib/Makefile | 1 + lib/zlib_deflate/deflate.c | 79 +++++------ lib/zlib_deflate/deftree.c | 54 -------- lib/zlib_deflate/defutil.h | 134 +++++++++++++++++-- lib/zlib_dfltcc/Makefile | 11 ++ lib/zlib_dfltcc/dfltcc.c | 52 ++++++++ lib/zlib_dfltcc/dfltcc.h | 115 +++++++++++++++++ lib/zlib_dfltcc/dfltcc_deflate.c | 273 +++++++++++++++++++++++++++++++++++++++ lib/zlib_dfltcc/dfltcc_syms.c | 17 +++ lib/zlib_dfltcc/dfltcc_util.h | 110 ++++++++++++++++ 11 files changed, 751 insertions(+), 102 deletions(-) create mode 100644 lib/zlib_dfltcc/Makefile create mode 100644 lib/zlib_dfltcc/dfltcc.c create mode 100644 lib/zlib_dfltcc/dfltcc.h create mode 100644 lib/zlib_dfltcc/dfltcc_deflate.c create mode 100644 lib/zlib_dfltcc/dfltcc_syms.c create mode 100644 lib/zlib_dfltcc/dfltcc_util.h (limited to 'lib') diff --git a/lib/Kconfig b/lib/Kconfig index 6e790dc55c5b..bc7e56370129 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -278,6 +278,13 @@ config ZLIB_DEFLATE tristate select BITREVERSE +config ZLIB_DFLTCC + def_bool y + depends on S390 + prompt "Enable s390x DEFLATE CONVERSION CALL support for kernel zlib" + help + Enable s390x hardware support for zlib in the kernel. + config LZO_COMPRESS tristate diff --git a/lib/Makefile b/lib/Makefile index c20b1debe9b4..5fb02b93b1dc 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -140,6 +140,7 @@ obj-$(CONFIG_842_COMPRESS) += 842/ obj-$(CONFIG_842_DECOMPRESS) += 842/ obj-$(CONFIG_ZLIB_INFLATE) += zlib_inflate/ obj-$(CONFIG_ZLIB_DEFLATE) += zlib_deflate/ +obj-$(CONFIG_ZLIB_DFLTCC) += zlib_dfltcc/ obj-$(CONFIG_REED_SOLOMON) += reed_solomon/ obj-$(CONFIG_BCH) += bch.o obj-$(CONFIG_LZO_COMPRESS) += lzo/ diff --git a/lib/zlib_deflate/deflate.c b/lib/zlib_deflate/deflate.c index d20ef458f137..0d60d81a2637 100644 --- a/lib/zlib_deflate/deflate.c +++ b/lib/zlib_deflate/deflate.c @@ -52,16 +52,18 @@ #include #include "defutil.h" +/* architecture-specific bits */ +#ifdef CONFIG_ZLIB_DFLTCC +# include "../zlib_dfltcc/dfltcc.h" +#else +#define DEFLATE_RESET_HOOK(strm) do {} while (0) +#define DEFLATE_HOOK(strm, flush, bstate) 0 +#define DEFLATE_NEED_CHECKSUM(strm) 1 +#endif /* =========================================================================== * Function prototypes. */ -typedef enum { - need_more, /* block not completed, need more input or more output */ - block_done, /* block flush performed */ - finish_started, /* finish started, need only more output at next deflate */ - finish_done /* finish done, accept no more input or output */ -} block_state; typedef block_state (*compress_func) (deflate_state *s, int flush); /* Compression function. Returns the block state after the call. */ @@ -72,7 +74,6 @@ static block_state deflate_fast (deflate_state *s, int flush); static block_state deflate_slow (deflate_state *s, int flush); static void lm_init (deflate_state *s); static void putShortMSB (deflate_state *s, uInt b); -static void flush_pending (z_streamp strm); static int read_buf (z_streamp strm, Byte *buf, unsigned size); static uInt longest_match (deflate_state *s, IPos cur_match); @@ -98,6 +99,25 @@ static void check_match (deflate_state *s, IPos start, IPos match, * See deflate.c for comments about the MIN_MATCH+1. */ +/* Workspace to be allocated for deflate processing */ +typedef struct deflate_workspace { + /* State memory for the deflator */ + deflate_state deflate_memory; +#ifdef CONFIG_ZLIB_DFLTCC + /* State memory for s390 hardware deflate */ + struct dfltcc_state dfltcc_memory; +#endif + Byte *window_memory; + Pos *prev_memory; + Pos *head_memory; + char *overlay_memory; +} deflate_workspace; + +#ifdef CONFIG_ZLIB_DFLTCC +/* dfltcc_state must be doubleword aligned for DFLTCC call */ +static_assert(offsetof(struct deflate_workspace, dfltcc_memory) % 8 == 0); +#endif + /* Values for max_lazy_match, good_match and max_chain_length, depending on * the desired pack level (0..9). The values given below have been tuned to * exclude worst case performance for pathological files. Better values may be @@ -207,7 +227,15 @@ int zlib_deflateInit2( */ next = (char *) mem; next += sizeof(*mem); +#ifdef CONFIG_ZLIB_DFLTCC + /* + * DFLTCC requires the window to be page aligned. + * Thus, we overallocate and take the aligned portion of the buffer. + */ + mem->window_memory = (Byte *) PTR_ALIGN(next, PAGE_SIZE); +#else mem->window_memory = (Byte *) next; +#endif next += zlib_deflate_window_memsize(windowBits); mem->prev_memory = (Pos *) next; next += zlib_deflate_prev_memsize(windowBits); @@ -277,6 +305,8 @@ int zlib_deflateReset( zlib_tr_init(s); lm_init(s); + DEFLATE_RESET_HOOK(strm); + return Z_OK; } @@ -294,35 +324,6 @@ static void putShortMSB( put_byte(s, (Byte)(b & 0xff)); } -/* ========================================================================= - * Flush as much pending output as possible. All deflate() output goes - * through this function so some applications may wish to modify it - * to avoid allocating a large strm->next_out buffer and copying into it. - * (See also read_buf()). - */ -static void flush_pending( - z_streamp strm -) -{ - deflate_state *s = (deflate_state *) strm->state; - unsigned len = s->pending; - - if (len > strm->avail_out) len = strm->avail_out; - if (len == 0) return; - - if (strm->next_out != NULL) { - memcpy(strm->next_out, s->pending_out, len); - strm->next_out += len; - } - s->pending_out += len; - strm->total_out += len; - strm->avail_out -= len; - s->pending -= len; - if (s->pending == 0) { - s->pending_out = s->pending_buf; - } -} - /* ========================================================================= */ int zlib_deflate( z_streamp strm, @@ -404,7 +405,8 @@ int zlib_deflate( (flush != Z_NO_FLUSH && s->status != FINISH_STATE)) { block_state bstate; - bstate = (*(configuration_table[s->level].func))(s, flush); + bstate = DEFLATE_HOOK(strm, flush, &bstate) ? bstate : + (*(configuration_table[s->level].func))(s, flush); if (bstate == finish_started || bstate == finish_done) { s->status = FINISH_STATE; @@ -503,7 +505,8 @@ static int read_buf( strm->avail_in -= len; - if (!((deflate_state *)(strm->state))->noheader) { + if (!DEFLATE_NEED_CHECKSUM(strm)) {} + else if (!((deflate_state *)(strm->state))->noheader) { strm->adler = zlib_adler32(strm->adler, strm->next_in, len); } memcpy(buf, strm->next_in, len); diff --git a/lib/zlib_deflate/deftree.c b/lib/zlib_deflate/deftree.c index 9b1756b12743..a4a34da512fe 100644 --- a/lib/zlib_deflate/deftree.c +++ b/lib/zlib_deflate/deftree.c @@ -76,11 +76,6 @@ static const uch bl_order[BL_CODES] * probability, to avoid transmitting the lengths for unused bit length codes. */ -#define Buf_size (8 * 2*sizeof(char)) -/* Number of bits used within bi_buf. (bi_buf might be implemented on - * more than 16 bits on some systems.) - */ - /* =========================================================================== * Local data. These are initialized only once. */ @@ -147,7 +142,6 @@ static void send_all_trees (deflate_state *s, int lcodes, int dcodes, static void compress_block (deflate_state *s, ct_data *ltree, ct_data *dtree); static void set_data_type (deflate_state *s); -static void bi_windup (deflate_state *s); static void bi_flush (deflate_state *s); static void copy_block (deflate_state *s, char *buf, unsigned len, int header); @@ -169,54 +163,6 @@ static void copy_block (deflate_state *s, char *buf, unsigned len, * used. */ -/* =========================================================================== - * Send a value on a given number of bits. - * IN assertion: length <= 16 and value fits in length bits. - */ -#ifdef DEBUG_ZLIB -static void send_bits (deflate_state *s, int value, int length); - -static void send_bits( - deflate_state *s, - int value, /* value to send */ - int length /* number of bits */ -) -{ - Tracevv((stderr," l %2d v %4x ", length, value)); - Assert(length > 0 && length <= 15, "invalid length"); - s->bits_sent += (ulg)length; - - /* If not enough room in bi_buf, use (valid) bits from bi_buf and - * (16 - bi_valid) bits from value, leaving (width - (16-bi_valid)) - * unused bits in value. - */ - if (s->bi_valid > (int)Buf_size - length) { - s->bi_buf |= (value << s->bi_valid); - put_short(s, s->bi_buf); - s->bi_buf = (ush)value >> (Buf_size - s->bi_valid); - s->bi_valid += length - Buf_size; - } else { - s->bi_buf |= value << s->bi_valid; - s->bi_valid += length; - } -} -#else /* !DEBUG_ZLIB */ - -#define send_bits(s, value, length) \ -{ int len = length;\ - if (s->bi_valid > (int)Buf_size - len) {\ - int val = value;\ - s->bi_buf |= (val << s->bi_valid);\ - put_short(s, s->bi_buf);\ - s->bi_buf = (ush)val >> (Buf_size - s->bi_valid);\ - s->bi_valid += len - Buf_size;\ - } else {\ - s->bi_buf |= (value) << s->bi_valid;\ - s->bi_valid += len;\ - }\ -} -#endif /* DEBUG_ZLIB */ - /* =========================================================================== * Initialize the various 'constant' tables. In a multi-threaded environment, * this function may be called by two threads concurrently, but this is diff --git a/lib/zlib_deflate/defutil.h b/lib/zlib_deflate/defutil.h index a8c370897c9f..385333b22ec6 100644 --- a/lib/zlib_deflate/defutil.h +++ b/lib/zlib_deflate/defutil.h @@ -1,5 +1,7 @@ +#ifndef DEFUTIL_H +#define DEFUTIL_H - +#include #define Assert(err, str) #define Trace(dummy) @@ -238,17 +240,13 @@ typedef struct deflate_state { } deflate_state; -typedef struct deflate_workspace { - /* State memory for the deflator */ - deflate_state deflate_memory; - Byte *window_memory; - Pos *prev_memory; - Pos *head_memory; - char *overlay_memory; -} deflate_workspace; - +#ifdef CONFIG_ZLIB_DFLTCC +#define zlib_deflate_window_memsize(windowBits) \ + (2 * (1 << (windowBits)) * sizeof(Byte) + PAGE_SIZE) +#else #define zlib_deflate_window_memsize(windowBits) \ (2 * (1 << (windowBits)) * sizeof(Byte)) +#endif #define zlib_deflate_prev_memsize(windowBits) \ ((1 << (windowBits)) * sizeof(Pos)) #define zlib_deflate_head_memsize(memLevel) \ @@ -292,6 +290,24 @@ void zlib_tr_stored_type_only (deflate_state *); put_byte(s, (uch)((ush)(w) >> 8)); \ } +/* =========================================================================== + * Reverse the first len bits of a code, using straightforward code (a faster + * method would use a table) + * IN assertion: 1 <= len <= 15 + */ +static inline unsigned bi_reverse( + unsigned code, /* the value to invert */ + int len /* its bit length */ +) +{ + register unsigned res = 0; + do { + res |= code & 1; + code >>= 1, res <<= 1; + } while (--len > 0); + return res >> 1; +} + /* =========================================================================== * Flush the bit buffer, keeping at most 7 bits in it. */ @@ -325,3 +341,101 @@ static inline void bi_windup(deflate_state *s) #endif } +typedef enum { + need_more, /* block not completed, need more input or more output */ + block_done, /* block flush performed */ + finish_started, /* finish started, need only more output at next deflate */ + finish_done /* finish done, accept no more input or output */ +} block_state; + +#define Buf_size (8 * 2*sizeof(char)) +/* Number of bits used within bi_buf. (bi_buf might be implemented on + * more than 16 bits on some systems.) + */ + +/* =========================================================================== + * Send a value on a given number of bits. + * IN assertion: length <= 16 and value fits in length bits. + */ +#ifdef DEBUG_ZLIB +static void send_bits (deflate_state *s, int value, int length); + +static void send_bits( + deflate_state *s, + int value, /* value to send */ + int length /* number of bits */ +) +{ + Tracevv((stderr," l %2d v %4x ", length, value)); + Assert(length > 0 && length <= 15, "invalid length"); + s->bits_sent += (ulg)length; + + /* If not enough room in bi_buf, use (valid) bits from bi_buf and + * (16 - bi_valid) bits from value, leaving (width - (16-bi_valid)) + * unused bits in value. + */ + if (s->bi_valid > (int)Buf_size - length) { + s->bi_buf |= (value << s->bi_valid); + put_short(s, s->bi_buf); + s->bi_buf = (ush)value >> (Buf_size - s->bi_valid); + s->bi_valid += length - Buf_size; + } else { + s->bi_buf |= value << s->bi_valid; + s->bi_valid += length; + } +} +#else /* !DEBUG_ZLIB */ + +#define send_bits(s, value, length) \ +{ int len = length;\ + if (s->bi_valid > (int)Buf_size - len) {\ + int val = value;\ + s->bi_buf |= (val << s->bi_valid);\ + put_short(s, s->bi_buf);\ + s->bi_buf = (ush)val >> (Buf_size - s->bi_valid);\ + s->bi_valid += len - Buf_size;\ + } else {\ + s->bi_buf |= (value) << s->bi_valid;\ + s->bi_valid += len;\ + }\ +} +#endif /* DEBUG_ZLIB */ + +static inline void zlib_tr_send_bits( + deflate_state *s, + int value, + int length +) +{ + send_bits(s, value, length); +} + +/* ========================================================================= + * Flush as much pending output as possible. All deflate() output goes + * through this function so some applications may wish to modify it + * to avoid allocating a large strm->next_out buffer and copying into it. + * (See also read_buf()). + */ +static inline void flush_pending( + z_streamp strm +) +{ + deflate_state *s = (deflate_state *) strm->state; + unsigned len = s->pending; + + if (len > strm->avail_out) len = strm->avail_out; + if (len == 0) return; + + if (strm->next_out != NULL) { + memcpy(strm->next_out, s->pending_out, len); + strm->next_out += len; + } + s->pending_out += len; + strm->total_out += len; + strm->avail_out -= len; + s->pending -= len; + if (s->pending == 0) { + s->pending_out = s->pending_buf; + } +} +#endif /* DEFUTIL_H */ diff --git a/lib/zlib_dfltcc/Makefile b/lib/zlib_dfltcc/Makefile new file mode 100644 index 000000000000..863d3b37e09d --- /dev/null +++ b/lib/zlib_dfltcc/Makefile @@ -0,0 +1,11 @@ +# SPDX-License-Identifier: GPL-2.0-only +# +# This is a modified version of zlib, which does all memory +# allocation ahead of time. +# +# This is the code for s390 zlib hardware support. +# + +obj-$(CONFIG_ZLIB_DFLTCC) += zlib_dfltcc.o + +zlib_dfltcc-objs := dfltcc.o dfltcc_deflate.o dfltcc_syms.o diff --git a/lib/zlib_dfltcc/dfltcc.c b/lib/zlib_dfltcc/dfltcc.c new file mode 100644 index 000000000000..7f77e5bb01c6 --- /dev/null +++ b/lib/zlib_dfltcc/dfltcc.c @@ -0,0 +1,52 @@ +// SPDX-License-Identifier: Zlib +/* dfltcc.c - SystemZ DEFLATE CONVERSION CALL support. */ + +#include +#include "dfltcc_util.h" +#include "dfltcc.h" + +char *oesc_msg( + char *buf, + int oesc +) +{ + if (oesc == 0x00) + return NULL; /* Successful completion */ + else { +#ifdef STATIC + return NULL; /* Ignore for pre-boot decompressor */ +#else + sprintf(buf, "Operation-Ending-Supplemental Code is 0x%.2X", oesc); + return buf; +#endif + } +} + +void dfltcc_reset( + z_streamp strm, + uInt size +) +{ + struct dfltcc_state *dfltcc_state = + (struct dfltcc_state *)((char *)strm->state + size); + struct dfltcc_qaf_param *param = + (struct dfltcc_qaf_param *)&dfltcc_state->param; + + /* Initialize available functions */ + if (is_dfltcc_enabled()) { + dfltcc(DFLTCC_QAF, param, NULL, NULL, NULL, NULL, NULL); + memmove(&dfltcc_state->af, param, sizeof(dfltcc_state->af)); + } else + memset(&dfltcc_state->af, 0, sizeof(dfltcc_state->af)); + + /* Initialize parameter block */ + memset(&dfltcc_state->param, 0, sizeof(dfltcc_state->param)); + dfltcc_state->param.nt = 1; + + /* Initialize tuning parameters */ + dfltcc_state->level_mask = DFLTCC_LEVEL_MASK; + dfltcc_state->block_size = DFLTCC_BLOCK_SIZE; + dfltcc_state->block_threshold = DFLTCC_FIRST_FHT_BLOCK_SIZE; + dfltcc_state->dht_threshold = DFLTCC_DHT_MIN_SAMPLE_SIZE; + dfltcc_state->param.ribm = DFLTCC_RIBM; +} diff --git a/lib/zlib_dfltcc/dfltcc.h b/lib/zlib_dfltcc/dfltcc.h new file mode 100644 index 000000000000..18fed7a444bc --- /dev/null +++ b/lib/zlib_dfltcc/dfltcc.h @@ -0,0 +1,115 @@ +// SPDX-License-Identifier: Zlib +#ifndef DFLTCC_H +#define DFLTCC_H + +#include "../zlib_deflate/defutil.h" + +/* + * Tuning parameters. + */ +#define DFLTCC_LEVEL_MASK 0x2 /* DFLTCC compression for level 1 only */ +#define DFLTCC_BLOCK_SIZE 1048576 +#define DFLTCC_FIRST_FHT_BLOCK_SIZE 4096 +#define DFLTCC_DHT_MIN_SAMPLE_SIZE 4096 +#define DFLTCC_RIBM 0 + +/* + * Parameter Block for Query Available Functions. + */ +struct dfltcc_qaf_param { + char fns[16]; + char reserved1[8]; + char fmts[2]; + char reserved2[6]; +}; + +static_assert(sizeof(struct dfltcc_qaf_param) == 32); + +#define DFLTCC_FMT0 0 + +/* + * Parameter Block for Generate Dynamic-Huffman Table, Compress and Expand. + */ +struct dfltcc_param_v0 { + uint16_t pbvn; /* Parameter-Block-Version Number */ + uint8_t mvn; /* Model-Version Number */ + uint8_t ribm; /* Reserved for IBM use */ + unsigned reserved32 : 31; + unsigned cf : 1; /* Continuation Flag */ + uint8_t reserved64[8]; + unsigned nt : 1; /* New Task */ + unsigned reserved129 : 1; + unsigned cvt : 1; /* Check Value Type */ + unsigned reserved131 : 1; + unsigned htt : 1; /* Huffman-Table Type */ + unsigned bcf : 1; /* Block-Continuation Flag */ + unsigned bcc : 1; /* Block Closing Control */ + unsigned bhf : 1; /* Block Header Final */ + unsigned reserved136 : 1; + unsigned reserved137 : 1; + unsigned dhtgc : 1; /* DHT Generation Control */ + unsigned reserved139 : 5; + unsigned reserved144 : 5; + unsigned sbb : 3; /* Sub-Byte Boundary */ + uint8_t oesc; /* Operation-Ending-Supplemental Code */ + unsigned reserved160 : 12; + unsigned ifs : 4; /* Incomplete-Function Status */ + uint16_t ifl; /* Incomplete-Function Length */ + uint8_t reserved192[8]; + uint8_t reserved256[8]; + uint8_t reserved320[4]; + uint16_t hl; /* History Length */ + unsigned reserved368 : 1; + uint16_t ho : 15; /* History Offset */ + uint32_t cv; /* Check Value */ + unsigned eobs : 15; /* End-of-block Symbol */ + unsigned reserved431: 1; + uint8_t eobl : 4; /* End-of-block Length */ + unsigned reserved436 : 12; + unsigned reserved448 : 4; + uint16_t cdhtl : 12; /* Compressed-Dynamic-Huffman Table + Length */ + uint8_t reserved464[6]; + uint8_t cdht[288]; + uint8_t reserved[32]; + uint8_t csb[1152]; +}; + +static_assert(sizeof(struct dfltcc_param_v0) == 1536); + +#define CVT_CRC32 0 +#define CVT_ADLER32 1 +#define HTT_FIXED 0 +#define HTT_DYNAMIC 1 + +/* + * Extension of inflate_state and deflate_state for DFLTCC. + */ +struct dfltcc_state { + struct dfltcc_param_v0 param; /* Parameter block */ + struct dfltcc_qaf_param af; /* Available functions */ + uLong level_mask; /* Levels on which to use DFLTCC */ + uLong block_size; /* New block each X bytes */ + uLong block_threshold; /* New block after total_in > X */ + uLong dht_threshold; /* New block only if avail_in >= X */ + char msg[64]; /* Buffer for strm->msg */ +}; + +/* Resides right after inflate_state or deflate_state */ +#define GET_DFLTCC_STATE(state) ((struct dfltcc_state *)((state) + 1)) + +/* External functions */ +int dfltcc_can_deflate(z_streamp strm); +int dfltcc_deflate(z_streamp strm, + int flush, + block_state *result); +void dfltcc_reset(z_streamp strm, uInt size); + +#define DEFLATE_RESET_HOOK(strm) \ + dfltcc_reset((strm), sizeof(deflate_state)) + +#define DEFLATE_HOOK dfltcc_deflate + +#define DEFLATE_NEED_CHECKSUM(strm) (!dfltcc_can_deflate((strm))) + +#endif /* DFLTCC_H */ diff --git a/lib/zlib_dfltcc/dfltcc_deflate.c b/lib/zlib_dfltcc/dfltcc_deflate.c new file mode 100644 index 000000000000..9f0f1c90c4e0 --- /dev/null +++ b/lib/zlib_dfltcc/dfltcc_deflate.c @@ -0,0 +1,273 @@ +// SPDX-License-Identifier: Zlib + +#include "../zlib_deflate/defutil.h" +#include "dfltcc_util.h" +#include "dfltcc.h" +#include + +/* + * Compress. + */ +int dfltcc_can_deflate( + z_streamp strm +) +{ + deflate_state *state = (deflate_state *)strm->state; + struct dfltcc_state *dfltcc_state = GET_DFLTCC_STATE(state); + + /* Unsupported compression settings */ + if (!dfltcc_are_params_ok(state->level, state->w_bits, state->strategy, + dfltcc_state->level_mask)) + return 0; + + /* Unsupported hardware */ + if (!is_bit_set(dfltcc_state->af.fns, DFLTCC_GDHT) || + !is_bit_set(dfltcc_state->af.fns, DFLTCC_CMPR) || + !is_bit_set(dfltcc_state->af.fmts, DFLTCC_FMT0)) + return 0; + + return 1; +} + +static void dfltcc_gdht( + z_streamp strm +) +{ + deflate_state *state = (deflate_state *)strm->state; + struct dfltcc_param_v0 *param = &GET_DFLTCC_STATE(state)->param; + size_t avail_in = avail_in = strm->avail_in; + + dfltcc(DFLTCC_GDHT, + param, NULL, NULL, + &strm->next_in, &avail_in, NULL); +} + +static dfltcc_cc dfltcc_cmpr( + z_streamp strm +) +{ + deflate_state *state = (deflate_state *)strm->state; + struct dfltcc_param_v0 *param = &GET_DFLTCC_STATE(state)->param; + size_t avail_in = strm->avail_in; + size_t avail_out = strm->avail_out; + dfltcc_cc cc; + + cc = dfltcc(DFLTCC_CMPR | HBT_CIRCULAR, + param, &strm->next_out, &avail_out, + &strm->next_in, &avail_in, state->window); + strm->total_in += (strm->avail_in - avail_in); + strm->total_out += (strm->avail_out - avail_out); + strm->avail_in = avail_in; + strm->avail_out = avail_out; + return cc; +} + +static void send_eobs( + z_streamp strm, + const struct dfltcc_param_v0 *param +) +{ + deflate_state *state = (deflate_state *)strm->state; + + zlib_tr_send_bits( + state, + bi_reverse(param->eobs >> (15 - param->eobl), param->eobl), + param->eobl); + flush_pending(strm); + if (state->pending != 0) { + /* The remaining data is located in pending_out[0:pending]. If someone + * calls put_byte() - this might happen in deflate() - the byte will be + * placed into pending_buf[pending], which is incorrect. Move the + * remaining data to the beginning of pending_buf so that put_byte() is + * usable again. + */ + memmove(state->pending_buf, state->pending_out, state->pending); + state->pending_out = state->pending_buf; + } +#ifdef ZLIB_DEBUG + state->compressed_len += param->eobl; +#endif +} + +int dfltcc_deflate( + z_streamp strm, + int flush, + block_state *result +) +{ + deflate_state *state = (deflate_state *)strm->state; + struct dfltcc_state *dfltcc_state = GET_DFLTCC_STATE(state); + struct dfltcc_param_v0 *param = &dfltcc_state->param; + uInt masked_avail_in; + dfltcc_cc cc; + int need_empty_block; + int soft_bcc; + int no_flush; + + if (!dfltcc_can_deflate(strm)) + return 0; + +again: + masked_avail_in = 0; + soft_bcc = 0; + no_flush = flush == Z_NO_FLUSH; + + /* Trailing empty block. Switch to software, except when Continuation Flag + * is set, which means that DFLTCC has buffered some output in the + * parameter block and needs to be called again in order to flush it. + */ + if (flush == Z_FINISH && strm->avail_in == 0 && !param->cf) { + if (param->bcf) { + /* A block is still open, and the hardware does not support closing + * blocks without adding data. Thus, close it manually. + */ + send_eobs(strm, param); + param->bcf = 0; + } + return 0; + } + + if (strm->avail_in == 0 && !param->cf) { + *result = need_more; + return 1; + } + + /* There is an open non-BFINAL block, we are not going to close it just + * yet, we have compressed more than DFLTCC_BLOCK_SIZE bytes and we see + * more than DFLTCC_DHT_MIN_SAMPLE_SIZE bytes. Open a new block with a new + * DHT in order to adapt to a possibly changed input data distribution. + */ + if (param->bcf && no_flush && + strm->total_in > dfltcc_state->block_threshold && + strm->avail_in >= dfltcc_state->dht_threshold) { + if (param->cf) { + /* We need to flush the DFLTCC buffer before writing the + * End-of-block Symbol. Mask the input data and proceed as usual. + */ + masked_avail_in += strm->avail_in; + strm->avail_in = 0; + no_flush = 0; + } else { + /* DFLTCC buffer is empty, so we can manually write the + * End-of-block Symbol right away. + */ + send_eobs(strm, param); + param->bcf = 0; + dfltcc_state->block_threshold = + strm->total_in + dfltcc_state->block_size; + if (strm->avail_out == 0) { + *result = need_more; + return 1; + } + } + } + + /* The caller gave us too much data. Pass only one block worth of + * uncompressed data to DFLTCC and mask the rest, so that on the next + * iteration we start a new block. + */ + if (no_flush && strm->avail_in > dfltcc_state->block_size) { + masked_avail_in += (strm->avail_in - dfltcc_state->block_size); + strm->avail_in = dfltcc_state->block_size; + } + + /* When we have an open non-BFINAL deflate block and caller indicates that + * the stream is ending, we need to close an open deflate block and open a + * BFINAL one. + */ + need_empty_block = flush == Z_FINISH && param->bcf && !param->bhf; + + /* Translate stream to parameter block */ + param->cvt = CVT_ADLER32; + if (!no_flush) + /* We need to close a block. Always do this in software - when there is + * no input data, the hardware will not nohor BCC. */ + soft_bcc = 1; + if (flush == Z_FINISH && !param->bcf) + /* We are about to open a BFINAL block, set Block Header Final bit + * until the stream ends. + */ + param->bhf = 1; + /* DFLTCC-CMPR will write to next_out, so make sure that buffers with + * higher precedence are empty. + */ + Assert(state->pending == 0, "There must be no pending bytes"); + Assert(state->bi_valid < 8, "There must be less than 8 pending bits"); + param->sbb = (unsigned int)state->bi_valid; + if (param->sbb > 0) + *strm->next_out = (Byte)state->bi_buf; + if (param->hl) + param->nt = 0; /* Honor history */ + param->cv = strm->adler; + + /* When opening a block, choose a Huffman-Table Type */ + if (!param->bcf) { + if (strm->total_in == 0 && dfltcc_state->block_threshold > 0) { + param->htt = HTT_FIXED; + } + else { + param->htt = HTT_DYNAMIC; + dfltcc_gdht(strm); + } + } + + /* Deflate */ + do { + cc = dfltcc_cmpr(strm); + if (strm->avail_in < 4096 && masked_avail_in > 0) + /* We are about to call DFLTCC with a small input buffer, which is + * inefficient. Since there is masked data, there will be at least + * one more DFLTCC call, so skip the current one and make the next + * one handle more data. + */ + break; + } while (cc == DFLTCC_CC_AGAIN); + + /* Translate parameter block to stream */ + strm->msg = oesc_msg(dfltcc_state->msg, param->oesc); + state->bi_valid = param->sbb; + if (state->bi_valid == 0) + state->bi_buf = 0; /* Avoid accessing next_out */ + else + state->bi_buf = *strm->next_out & ((1 << state->bi_valid) - 1); + strm->adler = param->cv; + + /* Unmask the input data */ + strm->avail_in += masked_avail_in; + masked_avail_in = 0; + + /* If we encounter an error, it means there is a bug in DFLTCC call */ + Assert(cc != DFLTCC_CC_OP2_CORRUPT || param->oesc == 0, "BUG"); + + /* Update Block-Continuation Flag. It will be used to check whether to call + * GDHT the next time. + */ + if (cc == DFLTCC_CC_OK) { + if (soft_bcc) { + send_eobs(strm, param); + param->bcf = 0; + dfltcc_state->block_threshold = + strm->total_in + dfltcc_state->block_size; + } else + param->bcf = 1; + if (flush == Z_FINISH) { + if (need_empty_block) + /* Make the current deflate() call also close the stream */ + return 0; + else { + bi_windup(state); + *result = finish_done; + } + } else { + if (flush == Z_FULL_FLUSH) + param->hl = 0; /* Clear history */ + *result = flush == Z_NO_FLUSH ? need_more : block_done; + } + } else { + param->bcf = 1; + *result = need_more; + } + if (strm->avail_in != 0 && strm->avail_out != 0) + goto again; /* deflate() must use all input or all output */ + return 1; +} diff --git a/lib/zlib_dfltcc/dfltcc_syms.c b/lib/zlib_dfltcc/dfltcc_syms.c new file mode 100644 index 000000000000..6f23481804c1 --- /dev/null +++ b/lib/zlib_dfltcc/dfltcc_syms.c @@ -0,0 +1,17 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * linux/lib/zlib_dfltcc/dfltcc_syms.c + * + * Exported symbols for the s390 zlib dfltcc support. + * + */ + +#include +#include +#include +#include "dfltcc.h" + +EXPORT_SYMBOL(dfltcc_can_deflate); +EXPORT_SYMBOL(dfltcc_deflate); +EXPORT_SYMBOL(dfltcc_reset); +MODULE_LICENSE("GPL"); diff --git a/lib/zlib_dfltcc/dfltcc_util.h b/lib/zlib_dfltcc/dfltcc_util.h new file mode 100644 index 000000000000..82cd1950c416 --- /dev/null +++ b/lib/zlib_dfltcc/dfltcc_util.h @@ -0,0 +1,110 @@ +// SPDX-License-Identifier: Zlib +#ifndef DFLTCC_UTIL_H +#define DFLTCC_UTIL_H + +#include +#include + +/* + * C wrapper for the DEFLATE CONVERSION CALL instruction. + */ +typedef enum { + DFLTCC_CC_OK = 0, + DFLTCC_CC_OP1_TOO_SHORT = 1, + DFLTCC_CC_OP2_TOO_SHORT = 2, + DFLTCC_CC_OP2_CORRUPT = 2, + DFLTCC_CC_AGAIN = 3, +} dfltcc_cc; + +#define DFLTCC_QAF 0 +#define DFLTCC_GDHT 1 +#define DFLTCC_CMPR 2 +#define DFLTCC_XPND 4 +#define HBT_CIRCULAR (1 << 7) +#define HB_BITS 15 +#define HB_SIZE (1 << HB_BITS) +#define DFLTCC_FACILITY 151 + +static inline dfltcc_cc dfltcc( + int fn, + void *param, + Byte **op1, + size_t *len1, + const Byte **op2, + size_t *len2, + void *hist +) +{ + Byte *t2 = op1 ? *op1 : NULL; + size_t t3 = len1 ? *len1 : 0; + const Byte *t4 = op2 ? *op2 : NULL; + size_t t5 = len2 ? *len2 : 0; + register int r0 __asm__("r0") = fn; + register void *r1 __asm__("r1") = param; + register Byte *r2 __asm__("r2") = t2; + register size_t r3 __asm__("r3") = t3; + register const Byte *r4 __asm__("r4") = t4; + register size_t r5 __asm__("r5") = t5; + int cc; + + __asm__ volatile( + ".insn rrf,0xb9390000,%[r2],%[r4],%[hist],0\n" + "ipm %[cc]\n" + : [r2] "+r" (r2) + , [r3] "+r" (r3) + , [r4] "+r" (r4) + , [r5] "+r" (r5) + , [cc] "=r" (cc) + : [r0] "r" (r0) + , [r1] "r" (r1) + , [hist] "r" (hist) + : "cc", "memory"); + t2 = r2; t3 = r3; t4 = r4; t5 = r5; + + if (op1) + *op1 = t2; + if (len1) + *len1 = t3; + if (op2) + *op2 = t4; + if (len2) + *len2 = t5; + return (cc >> 28) & 3; +} + +static inline int is_bit_set( + const char *bits, + int n +) +{ + return bits[n / 8] & (1 << (7 - (n % 8))); +} + +static inline void turn_bit_off( + char *bits, + int n +) +{ + bits[n / 8] &= ~(1 << (7 - (n % 8))); +} + +static inline int dfltcc_are_params_ok( + int level, + uInt window_bits, + int strategy, + uLong level_mask +) +{ + return (level_mask & (1 << level)) != 0 && + (window_bits == HB_BITS) && + (strategy == Z_DEFAULT_STRATEGY); +} + +static inline int is_dfltcc_enabled(void) +{ + return test_facility(DFLTCC_FACILITY); +} + +char *oesc_msg(char *buf, int oesc); + +#endif /* DFLTCC_UTIL_H */ -- cgit v1.2.3 From 12619610006371bfc30159937d4546e731d7b297 Mon Sep 17 00:00:00 2001 From: Mikhail Zaslonko Date: Thu, 30 Jan 2020 22:16:23 -0800 Subject: lib/zlib: add s390 hardware support for kernel zlib_inflate Add decompression functions to zlib_dfltcc library. Update zlib_inflate functions with the hooks for s390 hardware support and adjust workspace structures with extra parameter lists required for hardware inflate decompression. Link: http://lkml.kernel.org/r/20200103223334.20669-4-zaslonko@linux.ibm.com Signed-off-by: Ilya Leoshkevich Signed-off-by: Mikhail Zaslonko Co-developed-by: Ilya Leoshkevich Cc: Chris Mason Cc: Christian Borntraeger Cc: David Sterba Cc: Eduard Shishkin Cc: Heiko Carstens Cc: Josef Bacik Cc: Richard Purdie Cc: Vasily Gorbik Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/decompress_inflate.c | 13 ++++ lib/zlib_dfltcc/Makefile | 2 +- lib/zlib_dfltcc/dfltcc.h | 28 ++++++++ lib/zlib_dfltcc/dfltcc_inflate.c | 143 +++++++++++++++++++++++++++++++++++++++ lib/zlib_inflate/inflate.c | 32 ++++++--- lib/zlib_inflate/inflate.h | 8 +++ lib/zlib_inflate/infutil.h | 18 ++++- 7 files changed, 233 insertions(+), 11 deletions(-) create mode 100644 lib/zlib_dfltcc/dfltcc_inflate.c (limited to 'lib') diff --git a/lib/decompress_inflate.c b/lib/decompress_inflate.c index 63b4b7eee138..6130c42b8e59 100644 --- a/lib/decompress_inflate.c +++ b/lib/decompress_inflate.c @@ -10,6 +10,10 @@ #include "zlib_inflate/inftrees.c" #include "zlib_inflate/inffast.c" #include "zlib_inflate/inflate.c" +#ifdef CONFIG_ZLIB_DFLTCC +#include "zlib_dfltcc/dfltcc.c" +#include "zlib_dfltcc/dfltcc_inflate.c" +#endif #else /* STATIC */ /* initramfs et al: linked */ @@ -76,7 +80,12 @@ STATIC int INIT __gunzip(unsigned char *buf, long len, } strm->workspace = malloc(flush ? zlib_inflate_workspacesize() : +#ifdef CONFIG_ZLIB_DFLTCC + /* Always allocate the full workspace for DFLTCC */ + zlib_inflate_workspacesize()); +#else sizeof(struct inflate_state)); +#endif if (strm->workspace == NULL) { error("Out of memory while allocating workspace"); goto gunzip_nomem4; @@ -123,10 +132,14 @@ STATIC int INIT __gunzip(unsigned char *buf, long len, rc = zlib_inflateInit2(strm, -MAX_WBITS); +#ifdef CONFIG_ZLIB_DFLTCC + /* Always keep the window for DFLTCC */ +#else if (!flush) { WS(strm)->inflate_state.wsize = 0; WS(strm)->inflate_state.window = NULL; } +#endif while (rc == Z_OK) { if (strm->avail_in == 0) { diff --git a/lib/zlib_dfltcc/Makefile b/lib/zlib_dfltcc/Makefile index 863d3b37e09d..8e4d5afbbb10 100644 --- a/lib/zlib_dfltcc/Makefile +++ b/lib/zlib_dfltcc/Makefile @@ -8,4 +8,4 @@ obj-$(CONFIG_ZLIB_DFLTCC) += zlib_dfltcc.o -zlib_dfltcc-objs := dfltcc.o dfltcc_deflate.o dfltcc_syms.o +zlib_dfltcc-objs := dfltcc.o dfltcc_deflate.o dfltcc_inflate.o dfltcc_syms.o diff --git a/lib/zlib_dfltcc/dfltcc.h b/lib/zlib_dfltcc/dfltcc.h index 18fed7a444bc..4782c92bb2ff 100644 --- a/lib/zlib_dfltcc/dfltcc.h +++ b/lib/zlib_dfltcc/dfltcc.h @@ -104,6 +104,14 @@ int dfltcc_deflate(z_streamp strm, int flush, block_state *result); void dfltcc_reset(z_streamp strm, uInt size); +int dfltcc_can_inflate(z_streamp strm); +typedef enum { + DFLTCC_INFLATE_CONTINUE, + DFLTCC_INFLATE_BREAK, + DFLTCC_INFLATE_SOFTWARE, +} dfltcc_inflate_action; +dfltcc_inflate_action dfltcc_inflate(z_streamp strm, + int flush, int *ret); #define DEFLATE_RESET_HOOK(strm) \ dfltcc_reset((strm), sizeof(deflate_state)) @@ -112,4 +120,24 @@ void dfltcc_reset(z_streamp strm, uInt size); #define DEFLATE_NEED_CHECKSUM(strm) (!dfltcc_can_deflate((strm))) +#define INFLATE_RESET_HOOK(strm) \ + dfltcc_reset((strm), sizeof(struct inflate_state)) + +#define INFLATE_TYPEDO_HOOK(strm, flush) \ + if (dfltcc_can_inflate((strm))) { \ + dfltcc_inflate_action action; \ +\ + RESTORE(); \ + action = dfltcc_inflate((strm), (flush), &ret); \ + LOAD(); \ + if (action == DFLTCC_INFLATE_CONTINUE) \ + break; \ + else if (action == DFLTCC_INFLATE_BREAK) \ + goto inf_leave; \ + } + +#define INFLATE_NEED_CHECKSUM(strm) (!dfltcc_can_inflate((strm))) + +#define INFLATE_NEED_UPDATEWINDOW(strm) (!dfltcc_can_inflate((strm))) + #endif /* DFLTCC_H */ diff --git a/lib/zlib_dfltcc/dfltcc_inflate.c b/lib/zlib_dfltcc/dfltcc_inflate.c new file mode 100644 index 000000000000..12a93a06bd61 --- /dev/null +++ b/lib/zlib_dfltcc/dfltcc_inflate.c @@ -0,0 +1,143 @@ +// SPDX-License-Identifier: Zlib + +#include "../zlib_inflate/inflate.h" +#include "dfltcc_util.h" +#include "dfltcc.h" +#include + +/* + * Expand. + */ +int dfltcc_can_inflate( + z_streamp strm +) +{ + struct inflate_state *state = (struct inflate_state *)strm->state; + struct dfltcc_state *dfltcc_state = GET_DFLTCC_STATE(state); + + /* Unsupported compression settings */ + if (state->wbits != HB_BITS) + return 0; + + /* Unsupported hardware */ + return is_bit_set(dfltcc_state->af.fns, DFLTCC_XPND) && + is_bit_set(dfltcc_state->af.fmts, DFLTCC_FMT0); +} + +static int dfltcc_was_inflate_used( + z_streamp strm +) +{ + struct inflate_state *state = (struct inflate_state *)strm->state; + struct dfltcc_param_v0 *param = &GET_DFLTCC_STATE(state)->param; + + return !param->nt; +} + +static int dfltcc_inflate_disable( + z_streamp strm +) +{ + struct inflate_state *state = (struct inflate_state *)strm->state; + struct dfltcc_state *dfltcc_state = GET_DFLTCC_STATE(state); + + if (!dfltcc_can_inflate(strm)) + return 0; + if (dfltcc_was_inflate_used(strm)) + /* DFLTCC has already decompressed some data. Since there is not + * enough information to resume decompression in software, the call + * must fail. + */ + return 1; + /* DFLTCC was not used yet - decompress in software */ + memset(&dfltcc_state->af, 0, sizeof(dfltcc_state->af)); + return 0; +} + +static dfltcc_cc dfltcc_xpnd( + z_streamp strm +) +{ + struct inflate_state *state = (struct inflate_state *)strm->state; + struct dfltcc_param_v0 *param = &GET_DFLTCC_STATE(state)->param; + size_t avail_in = strm->avail_in; + size_t avail_out = strm->avail_out; + dfltcc_cc cc; + + cc = dfltcc(DFLTCC_XPND | HBT_CIRCULAR, + param, &strm->next_out, &avail_out, + &strm->next_in, &avail_in, state->window); + strm->avail_in = avail_in; + strm->avail_out = avail_out; + return cc; +} + +dfltcc_inflate_action dfltcc_inflate( + z_streamp strm, + int flush, + int *ret +) +{ + struct inflate_state *state = (struct inflate_state *)strm->state; + struct dfltcc_state *dfltcc_state = GET_DFLTCC_STATE(state); + struct dfltcc_param_v0 *param = &dfltcc_state->param; + dfltcc_cc cc; + + if (flush == Z_BLOCK) { + /* DFLTCC does not support stopping on block boundaries */ + if (dfltcc_inflate_disable(strm)) { + *ret = Z_STREAM_ERROR; + return DFLTCC_INFLATE_BREAK; + } else + return DFLTCC_INFLATE_SOFTWARE; + } + + if (state->last) { + if (state->bits != 0) { + strm->next_in++; + strm->avail_in--; + state->bits = 0; + } + state->mode = CHECK; + return DFLTCC_INFLATE_CONTINUE; + } + + if (strm->avail_in == 0 && !param->cf) + return DFLTCC_INFLATE_BREAK; + + if (!state->window || state->wsize == 0) { + state->mode = MEM; + return DFLTCC_INFLATE_CONTINUE; + } + + /* Translate stream to parameter block */ + param->cvt = CVT_ADLER32; + param->sbb = state->bits; + param->hl = state->whave; /* Software and hardware history formats match */ + param->ho = (state->write - state->whave) & ((1 << HB_BITS) - 1); + if (param->hl) + param->nt = 0; /* Honor history for the first block */ + param->cv = state->flags ? REVERSE(state->check) : state->check; + + /* Inflate */ + do { + cc = dfltcc_xpnd(strm); + } while (cc == DFLTCC_CC_AGAIN); + + /* Translate parameter block to stream */ + strm->msg = oesc_msg(dfltcc_state->msg, param->oesc); + state->last = cc == DFLTCC_CC_OK; + state->bits = param->sbb; + state->whave = param->hl; + state->write = (param->ho + param->hl) & ((1 << HB_BITS) - 1); + state->check = state->flags ? REVERSE(param->cv) : param->cv; + if (cc == DFLTCC_CC_OP2_CORRUPT && param->oesc != 0) { + /* Report an error if stream is corrupted */ + state->mode = BAD; + return DFLTCC_INFLATE_CONTINUE; + } + state->mode = TYPEDO; + /* Break if operands are exhausted, otherwise continue looping */ + return (cc == DFLTCC_CC_OP1_TOO_SHORT || cc == DFLTCC_CC_OP2_TOO_SHORT) ? + DFLTCC_INFLATE_BREAK : DFLTCC_INFLATE_CONTINUE; +} diff --git a/lib/zlib_inflate/inflate.c b/lib/zlib_inflate/inflate.c index 48f14cd58c77..67cc9b08ae9d 100644 --- a/lib/zlib_inflate/inflate.c +++ b/lib/zlib_inflate/inflate.c @@ -15,6 +15,16 @@ #include "inffast.h" #include "infutil.h" +/* architecture-specific bits */ +#ifdef CONFIG_ZLIB_DFLTCC +# include "../zlib_dfltcc/dfltcc.h" +#else +#define INFLATE_RESET_HOOK(strm) do {} while (0) +#define INFLATE_TYPEDO_HOOK(strm, flush) do {} while (0) +#define INFLATE_NEED_UPDATEWINDOW(strm) 1 +#define INFLATE_NEED_CHECKSUM(strm) 1 +#endif + int zlib_inflate_workspacesize(void) { return sizeof(struct inflate_workspace); @@ -42,6 +52,7 @@ int zlib_inflateReset(z_streamp strm) state->write = 0; state->whave = 0; + INFLATE_RESET_HOOK(strm); return Z_OK; } @@ -66,7 +77,15 @@ int zlib_inflateInit2(z_streamp strm, int windowBits) return Z_STREAM_ERROR; } state->wbits = (unsigned)windowBits; +#ifdef CONFIG_ZLIB_DFLTCC + /* + * DFLTCC requires the window to be page aligned. + * Thus, we overallocate and take the aligned portion of the buffer. + */ + state->window = PTR_ALIGN(&WS(strm)->working_window[0], PAGE_SIZE); +#else state->window = &WS(strm)->working_window[0]; +#endif return zlib_inflateReset(strm); } @@ -227,11 +246,6 @@ static int zlib_inflateSyncPacket(z_streamp strm) bits -= bits & 7; \ } while (0) -/* Reverse the bytes in a 32-bit value */ -#define REVERSE(q) \ - ((((q) >> 24) & 0xff) + (((q) >> 8) & 0xff00) + \ - (((q) & 0xff00) << 8) + (((q) & 0xff) << 24)) - /* inflate() uses a state machine to process as much input data and generate as much output data as possible before returning. The state machine is @@ -395,6 +409,7 @@ int zlib_inflate(z_streamp strm, int flush) if (flush == Z_BLOCK) goto inf_leave; /* fall through */ case TYPEDO: + INFLATE_TYPEDO_HOOK(strm, flush); if (state->last) { BYTEBITS(); state->mode = CHECK; @@ -692,7 +707,7 @@ int zlib_inflate(z_streamp strm, int flush) out -= left; strm->total_out += out; state->total += out; - if (out) + if (INFLATE_NEED_CHECKSUM(strm) && out) strm->adler = state->check = UPDATE(state->check, put - out, out); out = left; @@ -726,7 +741,8 @@ int zlib_inflate(z_streamp strm, int flush) */ inf_leave: RESTORE(); - if (state->wsize || (state->mode < CHECK && out != strm->avail_out)) + if (INFLATE_NEED_UPDATEWINDOW(strm) && + (state->wsize || (state->mode < CHECK && out != strm->avail_out))) zlib_updatewindow(strm, out); in -= strm->avail_in; @@ -734,7 +750,7 @@ int zlib_inflate(z_streamp strm, int flush) strm->total_in += in; strm->total_out += out; state->total += out; - if (state->wrap && out) + if (INFLATE_NEED_CHECKSUM(strm) && state->wrap && out) strm->adler = state->check = UPDATE(state->check, strm->next_out - out, out); diff --git a/lib/zlib_inflate/inflate.h b/lib/zlib_inflate/inflate.h index 3d17b3d1b21f..f79337ddf98c 100644 --- a/lib/zlib_inflate/inflate.h +++ b/lib/zlib_inflate/inflate.h @@ -11,6 +11,8 @@ subject to change. Applications should only use zlib.h. */ +#include "inftrees.h" + /* Possible inflate modes between inflate() calls */ typedef enum { HEAD, /* i: waiting for magic header */ @@ -108,4 +110,10 @@ struct inflate_state { unsigned short work[288]; /* work area for code table building */ code codes[ENOUGH]; /* space for code tables */ }; + +/* Reverse the bytes in a 32-bit value */ +#define REVERSE(q) \ + ((((q) >> 24) & 0xff) + (((q) >> 8) & 0xff00) + \ + (((q) & 0xff00) << 8) + (((q) & 0xff) << 24)) + #endif diff --git a/lib/zlib_inflate/infutil.h b/lib/zlib_inflate/infutil.h index eb1a9007bd86..784ab33b7842 100644 --- a/lib/zlib_inflate/infutil.h +++ b/lib/zlib_inflate/infutil.h @@ -12,14 +12,28 @@ #define _INFUTIL_H #include +#ifdef CONFIG_ZLIB_DFLTCC +#include "../zlib_dfltcc/dfltcc.h" +#include +#endif /* memory allocation for inflation */ struct inflate_workspace { struct inflate_state inflate_state; - unsigned char working_window[1 << MAX_WBITS]; +#ifdef CONFIG_ZLIB_DFLTCC + struct dfltcc_state dfltcc_state; + unsigned char working_window[(1 << MAX_WBITS) + PAGE_SIZE]; +#else + unsigned char working_window[(1 << MAX_WBITS)]; +#endif }; -#define WS(z) ((struct inflate_workspace *)(z->workspace)) +#ifdef CONFIG_ZLIB_DFLTCC +/* dfltcc_state must be doubleword aligned for DFLTCC call */ +static_assert(offsetof(struct inflate_workspace, dfltcc_state) % 8 == 0); +#endif + +#define WS(strm) ((struct inflate_workspace *)(strm->workspace)) #endif -- cgit v1.2.3 From c65e6815db1c2e28d5554bd99d3a6e522ab599d1 Mon Sep 17 00:00:00 2001 From: Mikhail Zaslonko Date: Thu, 30 Jan 2020 22:16:27 -0800 Subject: s390/boot: add dfltcc= kernel command line parameter Add the new kernel command line parameter 'dfltcc=' to configure s390 zlib hardware support. Format: { on | off | def_only | inf_only | always } on: s390 zlib hardware support for compression on level 1 and decompression (default) off: No s390 zlib hardware support def_only: s390 zlib hardware support for deflate only (compression on level 1) inf_only: s390 zlib hardware support for inflate only (decompression) always: Same as 'on' but ignores the selected compression level always using hardware support (used for debugging) Link: http://lkml.kernel.org/r/20200103223334.20669-5-zaslonko@linux.ibm.com Signed-off-by: Mikhail Zaslonko Cc: Chris Mason Cc: Christian Borntraeger Cc: David Sterba Cc: Eduard Shishkin Cc: Heiko Carstens Cc: Ilya Leoshkevich Cc: Josef Bacik Cc: Richard Purdie Cc: Vasily Gorbik Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/zlib_dfltcc/dfltcc.c | 5 ++++- lib/zlib_dfltcc/dfltcc.h | 1 + lib/zlib_dfltcc/dfltcc_deflate.c | 6 ++++++ lib/zlib_dfltcc/dfltcc_inflate.c | 6 ++++++ lib/zlib_dfltcc/dfltcc_util.h | 4 +++- 5 files changed, 20 insertions(+), 2 deletions(-) (limited to 'lib') diff --git a/lib/zlib_dfltcc/dfltcc.c b/lib/zlib_dfltcc/dfltcc.c index 7f77e5bb01c6..c30de430b30c 100644 --- a/lib/zlib_dfltcc/dfltcc.c +++ b/lib/zlib_dfltcc/dfltcc.c @@ -44,7 +44,10 @@ void dfltcc_reset( dfltcc_state->param.nt = 1; /* Initialize tuning parameters */ - dfltcc_state->level_mask = DFLTCC_LEVEL_MASK; + if (zlib_dfltcc_support == ZLIB_DFLTCC_FULL_DEBUG) + dfltcc_state->level_mask = DFLTCC_LEVEL_MASK_DEBUG; + else + dfltcc_state->level_mask = DFLTCC_LEVEL_MASK; dfltcc_state->block_size = DFLTCC_BLOCK_SIZE; dfltcc_state->block_threshold = DFLTCC_FIRST_FHT_BLOCK_SIZE; dfltcc_state->dht_threshold = DFLTCC_DHT_MIN_SAMPLE_SIZE; diff --git a/lib/zlib_dfltcc/dfltcc.h b/lib/zlib_dfltcc/dfltcc.h index 4782c92bb2ff..be70c807b62f 100644 --- a/lib/zlib_dfltcc/dfltcc.h +++ b/lib/zlib_dfltcc/dfltcc.h @@ -8,6 +8,7 @@ * Tuning parameters. */ #define DFLTCC_LEVEL_MASK 0x2 /* DFLTCC compression for level 1 only */ +#define DFLTCC_LEVEL_MASK_DEBUG 0x3fe /* DFLTCC compression for all levels */ #define DFLTCC_BLOCK_SIZE 1048576 #define DFLTCC_FIRST_FHT_BLOCK_SIZE 4096 #define DFLTCC_DHT_MIN_SAMPLE_SIZE 4096 diff --git a/lib/zlib_dfltcc/dfltcc_deflate.c b/lib/zlib_dfltcc/dfltcc_deflate.c index 9f0f1c90c4e0..00c185101c6d 100644 --- a/lib/zlib_dfltcc/dfltcc_deflate.c +++ b/lib/zlib_dfltcc/dfltcc_deflate.c @@ -3,6 +3,7 @@ #include "../zlib_deflate/defutil.h" #include "dfltcc_util.h" #include "dfltcc.h" +#include #include /* @@ -15,6 +16,11 @@ int dfltcc_can_deflate( deflate_state *state = (deflate_state *)strm->state; struct dfltcc_state *dfltcc_state = GET_DFLTCC_STATE(state); + /* Check for kernel dfltcc command line parameter */ + if (zlib_dfltcc_support == ZLIB_DFLTCC_DISABLED || + zlib_dfltcc_support == ZLIB_DFLTCC_INFLATE_ONLY) + return 0; + /* Unsupported compression settings */ if (!dfltcc_are_params_ok(state->level, state->w_bits, state->strategy, dfltcc_state->level_mask)) diff --git a/lib/zlib_dfltcc/dfltcc_inflate.c b/lib/zlib_dfltcc/dfltcc_inflate.c index 12a93a06bd61..aa9ef23474df 100644 --- a/lib/zlib_dfltcc/dfltcc_inflate.c +++ b/lib/zlib_dfltcc/dfltcc_inflate.c @@ -3,6 +3,7 @@ #include "../zlib_inflate/inflate.h" #include "dfltcc_util.h" #include "dfltcc.h" +#include #include /* @@ -15,6 +16,11 @@ int dfltcc_can_inflate( struct inflate_state *state = (struct inflate_state *)strm->state; struct dfltcc_state *dfltcc_state = GET_DFLTCC_STATE(state); + /* Check for kernel dfltcc command line parameter */ + if (zlib_dfltcc_support == ZLIB_DFLTCC_DISABLED || + zlib_dfltcc_support == ZLIB_DFLTCC_DEFLATE_ONLY) + return 0; + /* Unsupported compression settings */ if (state->wbits != HB_BITS) return 0; diff --git a/lib/zlib_dfltcc/dfltcc_util.h b/lib/zlib_dfltcc/dfltcc_util.h index 82cd1950c416..7c0d3bdc50a9 100644 --- a/lib/zlib_dfltcc/dfltcc_util.h +++ b/lib/zlib_dfltcc/dfltcc_util.h @@ -4,6 +4,7 @@ #include #include +#include /* * C wrapper for the DEFLATE CONVERSION CALL instruction. @@ -102,7 +103,8 @@ static inline int dfltcc_are_params_ok( static inline int is_dfltcc_enabled(void) { - return test_facility(DFLTCC_FACILITY); + return (zlib_dfltcc_support != ZLIB_DFLTCC_DISABLED && + test_facility(DFLTCC_FACILITY)); } char *oesc_msg(char *buf, int oesc); -- cgit v1.2.3 From 803521b149c8c71a712445a32bd9316e074df76a Mon Sep 17 00:00:00 2001 From: Mikhail Zaslonko Date: Thu, 30 Jan 2020 22:16:30 -0800 Subject: lib/zlib: add zlib_deflate_dfltcc_enabled() function Add a new function to zlib.h checking if s390 Deflate-Conversion facility is installed and enabled. Link: http://lkml.kernel.org/r/20200103223334.20669-6-zaslonko@linux.ibm.com Signed-off-by: Mikhail Zaslonko Cc: Chris Mason Cc: Christian Borntraeger Cc: David Sterba Cc: Eduard Shishkin Cc: Heiko Carstens Cc: Ilya Leoshkevich Cc: Josef Bacik Cc: Richard Purdie Cc: Vasily Gorbik Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/zlib_deflate/deflate.c | 6 ++++++ lib/zlib_deflate/deflate_syms.c | 1 + lib/zlib_dfltcc/dfltcc.h | 11 +++++++++++ lib/zlib_dfltcc/dfltcc_util.h | 9 --------- 4 files changed, 18 insertions(+), 9 deletions(-) (limited to 'lib') diff --git a/lib/zlib_deflate/deflate.c b/lib/zlib_deflate/deflate.c index 0d60d81a2637..8a878d0d892c 100644 --- a/lib/zlib_deflate/deflate.c +++ b/lib/zlib_deflate/deflate.c @@ -59,6 +59,7 @@ #define DEFLATE_RESET_HOOK(strm) do {} while (0) #define DEFLATE_HOOK(strm, flush, bstate) 0 #define DEFLATE_NEED_CHECKSUM(strm) 1 +#define DEFLATE_DFLTCC_ENABLED() 0 #endif /* =========================================================================== @@ -1138,3 +1139,8 @@ int zlib_deflate_workspacesize(int windowBits, int memLevel) + zlib_deflate_head_memsize(memLevel) + zlib_deflate_overlay_memsize(memLevel); } + +int zlib_deflate_dfltcc_enabled(void) +{ + return DEFLATE_DFLTCC_ENABLED(); +} diff --git a/lib/zlib_deflate/deflate_syms.c b/lib/zlib_deflate/deflate_syms.c index 72fe4b73be53..24b740b99678 100644 --- a/lib/zlib_deflate/deflate_syms.c +++ b/lib/zlib_deflate/deflate_syms.c @@ -12,6 +12,7 @@ #include EXPORT_SYMBOL(zlib_deflate_workspacesize); +EXPORT_SYMBOL(zlib_deflate_dfltcc_enabled); EXPORT_SYMBOL(zlib_deflate); EXPORT_SYMBOL(zlib_deflateInit2); EXPORT_SYMBOL(zlib_deflateEnd); diff --git a/lib/zlib_dfltcc/dfltcc.h b/lib/zlib_dfltcc/dfltcc.h index be70c807b62f..2a2fac1d050a 100644 --- a/lib/zlib_dfltcc/dfltcc.h +++ b/lib/zlib_dfltcc/dfltcc.h @@ -3,6 +3,8 @@ #define DFLTCC_H #include "../zlib_deflate/defutil.h" +#include +#include /* * Tuning parameters. @@ -14,6 +16,8 @@ #define DFLTCC_DHT_MIN_SAMPLE_SIZE 4096 #define DFLTCC_RIBM 0 +#define DFLTCC_FACILITY 151 + /* * Parameter Block for Query Available Functions. */ @@ -113,6 +117,11 @@ typedef enum { } dfltcc_inflate_action; dfltcc_inflate_action dfltcc_inflate(z_streamp strm, int flush, int *ret); +static inline int is_dfltcc_enabled(void) +{ +return (zlib_dfltcc_support != ZLIB_DFLTCC_DISABLED && + test_facility(DFLTCC_FACILITY)); +} #define DEFLATE_RESET_HOOK(strm) \ dfltcc_reset((strm), sizeof(deflate_state)) @@ -121,6 +130,8 @@ dfltcc_inflate_action dfltcc_inflate(z_streamp strm, #define DEFLATE_NEED_CHECKSUM(strm) (!dfltcc_can_deflate((strm))) +#define DEFLATE_DFLTCC_ENABLED() is_dfltcc_enabled() + #define INFLATE_RESET_HOOK(strm) \ dfltcc_reset((strm), sizeof(struct inflate_state)) diff --git a/lib/zlib_dfltcc/dfltcc_util.h b/lib/zlib_dfltcc/dfltcc_util.h index 7c0d3bdc50a9..4a46b5009f0d 100644 --- a/lib/zlib_dfltcc/dfltcc_util.h +++ b/lib/zlib_dfltcc/dfltcc_util.h @@ -3,8 +3,6 @@ #define DFLTCC_UTIL_H #include -#include -#include /* * C wrapper for the DEFLATE CONVERSION CALL instruction. @@ -24,7 +22,6 @@ typedef enum { #define HBT_CIRCULAR (1 << 7) #define HB_BITS 15 #define HB_SIZE (1 << HB_BITS) -#define DFLTCC_FACILITY 151 static inline dfltcc_cc dfltcc( int fn, @@ -101,12 +98,6 @@ static inline int dfltcc_are_params_ok( (strategy == Z_DEFAULT_STRATEGY); } -static inline int is_dfltcc_enabled(void) -{ - return (zlib_dfltcc_support != ZLIB_DFLTCC_DISABLED && - test_facility(DFLTCC_FACILITY)); -} - char *oesc_msg(char *buf, int oesc); #endif /* DFLTCC_UTIL_H */ -- cgit v1.2.3 From 4e456fee215677584cafa7f67298a76917e89c64 Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Thu, 30 Jan 2020 22:16:37 -0800 Subject: lib/scatterlist.c: adjust indentation in __sg_alloc_table Clang warns: ../lib/scatterlist.c:314:5: warning: misleading indentation; statement is not part of the previous 'if' [-Wmisleading-indentation] return -ENOMEM; ^ ../lib/scatterlist.c:311:4: note: previous statement is here if (prv) ^ 1 warning generated. This warning occurs because there is a space before the tab on this line. Remove it so that the indentation is consistent with the Linux kernel coding style and clang no longer warns. Link: http://lkml.kernel.org/r/20191218033606.11942-1-natechancellor@gmail.com Link: https://github.com/ClangBuiltLinux/linux/issues/830 Fixes: edce6820a9fd ("scatterlist: prevent invalid free when alloc fails") Signed-off-by: Nathan Chancellor Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/scatterlist.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'lib') diff --git a/lib/scatterlist.c b/lib/scatterlist.c index c2cf2c311b7d..5813072bc589 100644 --- a/lib/scatterlist.c +++ b/lib/scatterlist.c @@ -311,7 +311,7 @@ int __sg_alloc_table(struct sg_table *table, unsigned int nents, if (prv) table->nents = ++table->orig_nents; - return -ENOMEM; + return -ENOMEM; } sg_init_table(sg, alloc_size); -- cgit v1.2.3 From d5767057c9a76a29f073dad66b7fa12a90e8c748 Mon Sep 17 00:00:00 2001 From: Yury Norov Date: Thu, 30 Jan 2020 22:16:40 -0800 Subject: uapi: rename ext2_swab() to swab() and share globally in swab.h ext2_swab() is defined locally in lib/find_bit.c However it is not specific to ext2, neither to bitmaps. There are many potential users of it, so rename it to just swab() and move to include/uapi/linux/swab.h ABI guarantees that size of unsigned long corresponds to BITS_PER_LONG, therefore drop unneeded cast. Link: http://lkml.kernel.org/r/20200103202846.21616-1-yury.norov@gmail.com Signed-off-by: Yury Norov Cc: Allison Randal Cc: Joe Perches Cc: Thomas Gleixner Cc: William Breathitt Gray Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/find_bit.c | 16 ++-------------- 1 file changed, 2 insertions(+), 14 deletions(-) (limited to 'lib') diff --git a/lib/find_bit.c b/lib/find_bit.c index e35a76b291e6..06e503c339f3 100644 --- a/lib/find_bit.c +++ b/lib/find_bit.c @@ -149,18 +149,6 @@ EXPORT_SYMBOL(find_last_bit); #ifdef __BIG_ENDIAN -/* include/linux/byteorder does not support "unsigned long" type */ -static inline unsigned long ext2_swab(const unsigned long y) -{ -#if BITS_PER_LONG == 64 - return (unsigned long) __swab64((u64) y); -#elif BITS_PER_LONG == 32 - return (unsigned long) __swab32((u32) y); -#else -#error BITS_PER_LONG not defined -#endif -} - #if !defined(find_next_bit_le) || !defined(find_next_zero_bit_le) static inline unsigned long _find_next_bit_le(const unsigned long *addr1, const unsigned long *addr2, unsigned long nbits, @@ -177,7 +165,7 @@ static inline unsigned long _find_next_bit_le(const unsigned long *addr1, tmp ^= invert; /* Handle 1st word. */ - tmp &= ext2_swab(BITMAP_FIRST_WORD_MASK(start)); + tmp &= swab(BITMAP_FIRST_WORD_MASK(start)); start = round_down(start, BITS_PER_LONG); while (!tmp) { @@ -191,7 +179,7 @@ static inline unsigned long _find_next_bit_le(const unsigned long *addr1, tmp ^= invert; } - return min(start + __ffs(ext2_swab(tmp)), nbits); + return min(start + __ffs(swab(tmp)), nbits); } #endif -- cgit v1.2.3 From b78c57135d470cfc5b461f2abde4eaeb07d100fb Mon Sep 17 00:00:00 2001 From: Yury Norov Date: Thu, 30 Jan 2020 22:16:43 -0800 Subject: lib/find_bit.c: join _find_next_bit{_le} _find_next_bit and _find_next_bit_le are very similar functions. It's possible to join them by adding 1 parameter and a couple of simple checks. It's simplify maintenance and make possible to shrink the size of .text by un-inlining the unified function (in the following patch). Link: http://lkml.kernel.org/r/20200103202846.21616-2-yury.norov@gmail.com Signed-off-by: Yury Norov Cc: Allison Randal Cc: Joe Perches Cc: Thomas Gleixner Cc: William Breathitt Gray Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/find_bit.c | 64 +++++++++++++++++----------------------------------------- 1 file changed, 19 insertions(+), 45 deletions(-) (limited to 'lib') diff --git a/lib/find_bit.c b/lib/find_bit.c index 06e503c339f3..c897c127316d 100644 --- a/lib/find_bit.c +++ b/lib/find_bit.c @@ -17,9 +17,9 @@ #include #include -#if !defined(find_next_bit) || !defined(find_next_zero_bit) || \ - !defined(find_next_and_bit) - +#if !defined(find_next_bit) || !defined(find_next_zero_bit) || \ + !defined(find_next_bit_le) || !defined(find_next_zero_bit_le) || \ + !defined(find_next_and_bit) /* * This is a common helper function for find_next_bit, find_next_zero_bit, and * find_next_and_bit. The differences are: @@ -29,9 +29,9 @@ */ static inline unsigned long _find_next_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long nbits, - unsigned long start, unsigned long invert) + unsigned long start, unsigned long invert, unsigned long le) { - unsigned long tmp; + unsigned long tmp, mask; if (unlikely(start >= nbits)) return nbits; @@ -42,7 +42,12 @@ static inline unsigned long _find_next_bit(const unsigned long *addr1, tmp ^= invert; /* Handle 1st word. */ - tmp &= BITMAP_FIRST_WORD_MASK(start); + mask = BITMAP_FIRST_WORD_MASK(start); + if (le) + mask = swab(mask); + + tmp &= mask; + start = round_down(start, BITS_PER_LONG); while (!tmp) { @@ -56,6 +61,9 @@ static inline unsigned long _find_next_bit(const unsigned long *addr1, tmp ^= invert; } + if (le) + tmp = swab(tmp); + return min(start + __ffs(tmp), nbits); } #endif @@ -67,7 +75,7 @@ static inline unsigned long _find_next_bit(const unsigned long *addr1, unsigned long find_next_bit(const unsigned long *addr, unsigned long size, unsigned long offset) { - return _find_next_bit(addr, NULL, size, offset, 0UL); + return _find_next_bit(addr, NULL, size, offset, 0UL, 0); } EXPORT_SYMBOL(find_next_bit); #endif @@ -76,7 +84,7 @@ EXPORT_SYMBOL(find_next_bit); unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size, unsigned long offset) { - return _find_next_bit(addr, NULL, size, offset, ~0UL); + return _find_next_bit(addr, NULL, size, offset, ~0UL, 0); } EXPORT_SYMBOL(find_next_zero_bit); #endif @@ -86,7 +94,7 @@ unsigned long find_next_and_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size, unsigned long offset) { - return _find_next_bit(addr1, addr2, size, offset, 0UL); + return _find_next_bit(addr1, addr2, size, offset, 0UL, 0); } EXPORT_SYMBOL(find_next_and_bit); #endif @@ -149,45 +157,11 @@ EXPORT_SYMBOL(find_last_bit); #ifdef __BIG_ENDIAN -#if !defined(find_next_bit_le) || !defined(find_next_zero_bit_le) -static inline unsigned long _find_next_bit_le(const unsigned long *addr1, - const unsigned long *addr2, unsigned long nbits, - unsigned long start, unsigned long invert) -{ - unsigned long tmp; - - if (unlikely(start >= nbits)) - return nbits; - - tmp = addr1[start / BITS_PER_LONG]; - if (addr2) - tmp &= addr2[start / BITS_PER_LONG]; - tmp ^= invert; - - /* Handle 1st word. */ - tmp &= swab(BITMAP_FIRST_WORD_MASK(start)); - start = round_down(start, BITS_PER_LONG); - - while (!tmp) { - start += BITS_PER_LONG; - if (start >= nbits) - return nbits; - - tmp = addr1[start / BITS_PER_LONG]; - if (addr2) - tmp &= addr2[start / BITS_PER_LONG]; - tmp ^= invert; - } - - return min(start + __ffs(swab(tmp)), nbits); -} -#endif - #ifndef find_next_zero_bit_le unsigned long find_next_zero_bit_le(const void *addr, unsigned long size, unsigned long offset) { - return _find_next_bit_le(addr, NULL, size, offset, ~0UL); + return _find_next_bit(addr, NULL, size, offset, ~0UL, 1); } EXPORT_SYMBOL(find_next_zero_bit_le); #endif @@ -196,7 +170,7 @@ EXPORT_SYMBOL(find_next_zero_bit_le); unsigned long find_next_bit_le(const void *addr, unsigned long size, unsigned long offset) { - return _find_next_bit_le(addr, NULL, size, offset, 0UL); + return _find_next_bit(addr, NULL, size, offset, 0UL, 1); } EXPORT_SYMBOL(find_next_bit_le); #endif -- cgit v1.2.3 From 7dfaa98f646bbc29c3575bc184f2b37aa2dd62c5 Mon Sep 17 00:00:00 2001 From: Yury Norov Date: Thu, 30 Jan 2020 22:16:47 -0800 Subject: lib/find_bit.c: uninline helper _find_next_bit() It saves 25% of .text for arm64, and more for BE architectures. Before: $ size lib/find_bit.o text data bss dec hex filename 1012 56 0 1068 42c lib/find_bit.o After: $ size lib/find_bit.o text data bss dec hex filename 776 56 0 832 340 lib/find_bit.o Link: http://lkml.kernel.org/r/20200103202846.21616-3-yury.norov@gmail.com Signed-off-by: Yury Norov Cc: Thomas Gleixner Cc: Allison Randal Cc: William Breathitt Gray Cc: Joe Perches Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/find_bit.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'lib') diff --git a/lib/find_bit.c b/lib/find_bit.c index c897c127316d..49f875f1baf7 100644 --- a/lib/find_bit.c +++ b/lib/find_bit.c @@ -27,7 +27,7 @@ * searching it for one bits. * - The optional "addr2", which is anded with "addr1" if present. */ -static inline unsigned long _find_next_bit(const unsigned long *addr1, +static unsigned long _find_next_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long nbits, unsigned long start, unsigned long invert, unsigned long le) { -- cgit v1.2.3 From 43e76af85fa7e75ac9b71fc2fcc250abb1889bff Mon Sep 17 00:00:00 2001 From: Dmitry Vyukov Date: Thu, 30 Jan 2020 22:17:35 -0800 Subject: kcov: ignore fault-inject and stacktrace Don't instrument 3 more files that contain debugging facilities and produce large amounts of uninteresting coverage for every syscall. The following snippets are sprinkled all over the place in kcov traces in a debugging kernel. We already try to disable instrumentation of stack unwinding code and of most debug facilities. I guess we did not use fault-inject.c at the time, and stacktrace.c was somehow missed (or something has changed in kernel/configs). This change both speeds up kcov (kernel doesn't need to store these PCs, user-space doesn't need to process them) and frees trace buffer capacity for more useful coverage. should_fail lib/fault-inject.c:149 fail_dump lib/fault-inject.c:45 stack_trace_save kernel/stacktrace.c:124 stack_trace_consume_entry kernel/stacktrace.c:86 stack_trace_consume_entry kernel/stacktrace.c:89 ... a hundred frames skipped ... stack_trace_consume_entry kernel/stacktrace.c:93 stack_trace_consume_entry kernel/stacktrace.c:86 Link: http://lkml.kernel.org/r/20200116111449.217744-1-dvyukov@gmail.com Signed-off-by: Dmitry Vyukov Reviewed-by: Andrey Konovalov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/Makefile | 1 + 1 file changed, 1 insertion(+) (limited to 'lib') diff --git a/lib/Makefile b/lib/Makefile index 5fb02b93b1dc..23ca78d43d24 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -16,6 +16,7 @@ KCOV_INSTRUMENT_rbtree.o := n KCOV_INSTRUMENT_list_debug.o := n KCOV_INSTRUMENT_debugobjects.o := n KCOV_INSTRUMENT_dynamic_debug.o := n +KCOV_INSTRUMENT_fault-inject.o := n # Early boot use of cmdline, don't instrument it ifdef CONFIG_AMD_MEM_ENCRYPT -- cgit v1.2.3