summaryrefslogtreecommitdiffstats
path: root/lib
diff options
context:
space:
mode:
authorNick Terrell <terrelln@fb.com>2021-11-15 20:33:08 -0800
committerNick Terrell <terrelln@fb.com>2021-11-18 13:15:33 -0800
commit1974990cca43a6ba708a70b15862113eb9c2f399 (patch)
tree02b6b97191b5b40989ab4e9165b21b33ddb1d6f8 /lib
parentae8d67b2117f1ec6c8170d6e1af8ded17392bd2c (diff)
downloadlinux-1974990cca43a6ba708a70b15862113eb9c2f399.tar.bz2
lib: zstd: Don't inline functions in zstd_opt.c
`zstd_opt.c` contains the match finder for the highest compression levels. These levels are already very slow, and are unlikely to be used in the kernel. If they are used, they shouldn't be used in latency sensitive workloads, so slowing them down shouldn't be a big deal. This saves 188 KB of the 288 KB regression reported by Geert Uytterhoeven [0]. I've also opened an issue upstream [1] so that we can properly tackle the code size issue in `zstd_opt.c` for all users, and can hopefully remove this hack in the next zstd version we import. Bloat-o-meter output on x86-64: ``` > ../scripts/bloat-o-meter vmlinux.old vmlinux add/remove: 6/5 grow/shrink: 1/9 up/down: 16673/-209939 (-193266) Function old new delta ZSTD_compressBlock_opt_generic.constprop - 7559 +7559 ZSTD_insertBtAndGetAllMatches - 6304 +6304 ZSTD_insertBt1 - 1731 +1731 ZSTD_storeSeq - 693 +693 ZSTD_BtGetAllMatches - 255 +255 ZSTD_updateRep - 128 +128 ZSTD_updateTree 96 99 +3 ZSTD_insertAndFindFirstIndexHash3 81 - -81 ZSTD_setBasePrices.constprop 98 - -98 ZSTD_litLengthPrice.constprop 138 - -138 ZSTD_count 362 181 -181 ZSTD_count_2segments 1407 938 -469 ZSTD_insertBt1.constprop 2689 - -2689 ZSTD_compressBlock_btultra2 19990 423 -19567 ZSTD_compressBlock_btultra 19633 15 -19618 ZSTD_initStats_ultra 19825 - -19825 ZSTD_compressBlock_btopt 20374 12 -20362 ZSTD_compressBlock_btopt_extDict 29984 12 -29972 ZSTD_compressBlock_btultra_extDict 30718 15 -30703 ZSTD_compressBlock_btopt_dictMatchState 32689 12 -32677 ZSTD_compressBlock_btultra_dictMatchState 33574 15 -33559 Total: Before=6611828, After=6418562, chg -2.92% ``` [0] https://lkml.org/lkml/2021/11/14/189 [1] https://github.com/facebook/zstd/issues/2862 Link: https://lore.kernel.org/r/20211117014949.1169186-3-nickrterrell@gmail.com/ Link: https://lore.kernel.org/r/20211117201459.1194876-3-nickrterrell@gmail.com/ Reported-by: Geert Uytterhoeven <geert@linux-m68k.org> Tested-by: Geert Uytterhoeven <geert@linux-m68k.org> Reviewed-by: Geert Uytterhoeven <geert@linux-m68k.org> Signed-off-by: Nick Terrell <terrelln@fb.com>
Diffstat (limited to 'lib')
-rw-r--r--lib/zstd/common/compiler.h7
-rw-r--r--lib/zstd/compress/zstd_opt.c12
2 files changed, 19 insertions, 0 deletions
diff --git a/lib/zstd/common/compiler.h b/lib/zstd/common/compiler.h
index a1a051e4bce6..f5a9c70a228a 100644
--- a/lib/zstd/common/compiler.h
+++ b/lib/zstd/common/compiler.h
@@ -16,6 +16,7 @@
*********************************************************/
/* force inlining */
+#if !defined(ZSTD_NO_INLINE)
#if (defined(__GNUC__) && !defined(__STRICT_ANSI__)) || defined(__cplusplus) || defined(__STDC_VERSION__) && __STDC_VERSION__ >= 199901L /* C99 */
# define INLINE_KEYWORD inline
#else
@@ -24,6 +25,12 @@
#define FORCE_INLINE_ATTR __attribute__((always_inline))
+#else
+
+#define INLINE_KEYWORD
+#define FORCE_INLINE_ATTR
+
+#endif
/*
On MSVC qsort requires that functions passed into it use the __cdecl calling conversion(CC).
diff --git a/lib/zstd/compress/zstd_opt.c b/lib/zstd/compress/zstd_opt.c
index 04337050fe9a..dfc55e3e8119 100644
--- a/lib/zstd/compress/zstd_opt.c
+++ b/lib/zstd/compress/zstd_opt.c
@@ -8,6 +8,18 @@
* You may select, at your option, one of the above-listed licenses.
*/
+/*
+ * Disable inlining for the optimal parser for the kernel build.
+ * It is unlikely to be used in the kernel, and where it is used
+ * latency shouldn't matter because it is very slow to begin with.
+ * We prefer a ~180KB binary size win over faster optimal parsing.
+ *
+ * TODO(https://github.com/facebook/zstd/issues/2862):
+ * Improve the code size of the optimal parser in general, so we
+ * don't need this hack for the kernel build.
+ */
+#define ZSTD_NO_INLINE 1
+
#include "zstd_compress_internal.h"
#include "hist.h"
#include "zstd_opt.h"