[PATCH v3 2/2] zstd: use cpu_feature_enabled() for in-kernel BMI2 dispatch

[Usama Arif]

Zstd's dynamic BMI2 implementation probes CPUID when a compression or
decompression context is initialized, stores the result in the context,
and tests that value at every dispatch site. In normal kernel builds this
bypasses the x86 feature policy and uses ordinary runtime branches instead
of allowing x86 alternatives to resolve the feature check at boot.

Add ZSTD_USE_BMI2() and use it at every runtime BMI2/default selector. For
normal x86 kernel objects, the predicate expands directly to
cpu_feature_enabled(X86_FEATURE_BMI2). When dynamic BMI2 dispatch is not
available it is false; other builds retain the caller-provided flag. Keep
the existing HUF conditional layout because DYNAMIC_BMI2 also controls
whether target-attributed variants are emitted.

Add the matching ZSTD_SET_BMI2() abstraction for context initialization.
Normal x86 kernel objects and builds without dynamic BMI2 do not cache CPU
state. Other builds with dynamic dispatch, including preboot, retain the
existing behavior. Keep the BMI2 members in the context structures so
their layouts do not change, and make the accessors return zero when
cached state is unused.

Select the normal-kernel policy in zstd_deps.h. Builds which define
__DISABLE_EXPORTS, including the x86 preboot decompressor, retain the existing
CPUID-backed dispatch because the normal alternatives infrastructure is not
available there.

A 4 KiB zstd-generic crypto_acomp benchmark in a one-vCPU KVM guest gave
these median results:

                        Before      After     Change
  Compression      16,634 ns/op  13,394 ns/op  -19.5%
  Decompression     3,480 ns/op     963 ns/op  -72.3%

Signed-off-by: Usama Arif <usama.arif@xxxxxxxxx>
---
 lib/zstd/common/compiler.h                    | 12 ++++++++++++
 lib/zstd/common/entropy_common.c              | 12 ++++++------
 lib/zstd/common/fse_decompress.c              |  7 ++++---
 lib/zstd/common/zstd_deps.h                   |  5 +++++
 lib/zstd/compress/huf_compress.c              |  6 +++++-
 lib/zstd/compress/zstd_compress.c             | 12 ++++++------
 lib/zstd/compress/zstd_compress_internal.h    |  9 +++++++++
 lib/zstd/compress/zstd_compress_sequences.c   |  8 +++++---
 lib/zstd/compress/zstd_compress_superblock.c  |  2 +-
 lib/zstd/decompress/huf_decompress.c          | 18 +++++++++---------
 lib/zstd/decompress/zstd_decompress.c         |  4 +---
 lib/zstd/decompress/zstd_decompress_block.c   | 19 +++++++------------
 .../decompress/zstd_decompress_internal.h     |  2 +-
 13 files changed, 71 insertions(+), 45 deletions(-)

diff --git a/lib/zstd/common/compiler.h b/lib/zstd/common/compiler.h
index dc9bd15e174e9..47f6c0372c58c 100644
--- a/lib/zstd/common/compiler.h
+++ b/lib/zstd/common/compiler.h
@@ -14,6 +14,7 @@
 
 #include <linux/types.h>
 
+#include "zstd_deps.h"
 #include "portability_macros.h"
 
 /*-*******************************************************
@@ -96,6 +97,17 @@
  */
 #define BMI2_TARGET_ATTRIBUTE TARGET_ATTRIBUTE("lzcnt,bmi,bmi2")
 
+#if !DYNAMIC_BMI2
+#  define ZSTD_USE_BMI2(bmi2) 0
+#  define ZSTD_SET_BMI2(state, value) do { } while (0)
+#elif defined(ZSTD_USE_KERNEL_CPU_FEATURES)
+#  define ZSTD_USE_BMI2(bmi2) cpu_feature_enabled(X86_FEATURE_BMI2)
+#  define ZSTD_SET_BMI2(state, value) do { } while (0)
+#else
+#  define ZSTD_USE_BMI2(bmi2) (bmi2)
+#  define ZSTD_SET_BMI2(state, value) do { (state) = (value); } while (0)
+#endif
+
 /* prefetch
  * can be disabled, by declaring NO_PREFETCH build macro */
 #if ( (__GNUC__ >= 4) || ( (__GNUC__ == 3) && (__GNUC_MINOR__ >= 1) ) )
diff --git a/lib/zstd/common/entropy_common.c b/lib/zstd/common/entropy_common.c
index 15a7c14ae8040..701bd495b13c8 100644
--- a/lib/zstd/common/entropy_common.c
+++ b/lib/zstd/common/entropy_common.c
@@ -16,6 +16,10 @@
 /* *************************************
 *  Dependencies
 ***************************************/
+#include "zstd_deps.h"
+#if defined(ZSTD_USE_KERNEL_CPU_FEATURES)
+#include <asm/cpufeature.h>
+#endif
 #include "mem.h"
 #include "error_private.h"       /* ERR_*, ERROR */
 #define FSE_STATIC_LINKING_ONLY  /* FSE_MIN_TABLELOG */
@@ -210,11 +214,9 @@ size_t FSE_readNCount_bmi2(
         short* normalizedCounter, unsigned* maxSVPtr, unsigned* tableLogPtr,
         const void* headerBuffer, size_t hbSize, int bmi2)
 {
-#if DYNAMIC_BMI2
-    if (bmi2) {
+    if (ZSTD_USE_BMI2(bmi2)) {
         return FSE_readNCount_body_bmi2(normalizedCounter, maxSVPtr, tableLogPtr, headerBuffer, hbSize);
     }
-#endif
     (void)bmi2;
     return FSE_readNCount_body_default(normalizedCounter, maxSVPtr, tableLogPtr, headerBuffer, hbSize);
 }
@@ -335,11 +337,9 @@ size_t HUF_readStats_wksp(BYTE* huffWeight, size_t hwSize, U32* rankStats,
                      void* workSpace, size_t wkspSize,
                      int flags)
 {
-#if DYNAMIC_BMI2
-    if (flags & HUF_flags_bmi2) {
+    if (ZSTD_USE_BMI2(flags & HUF_flags_bmi2)) {
         return HUF_readStats_body_bmi2(huffWeight, hwSize, rankStats, nbSymbolsPtr, tableLogPtr, src, srcSize, workSpace, wkspSize);
     }
-#endif
     (void)flags;
     return HUF_readStats_body_default(huffWeight, hwSize, rankStats, nbSymbolsPtr, tableLogPtr, src, srcSize, workSpace, wkspSize);
 }
diff --git a/lib/zstd/common/fse_decompress.c b/lib/zstd/common/fse_decompress.c
index 8d9c43b928833..008ce3401726a 100644
--- a/lib/zstd/common/fse_decompress.c
+++ b/lib/zstd/common/fse_decompress.c
@@ -24,6 +24,9 @@
 #include "fse.h"
 #include "error_private.h"
 #include "zstd_deps.h"  /* ZSTD_memcpy */
+#if defined(ZSTD_USE_KERNEL_CPU_FEATURES)
+#include <asm/cpufeature.h>
+#endif
 #include "bits.h"       /* ZSTD_highbit32 */
 
 
@@ -306,11 +309,9 @@ BMI2_TARGET_ATTRIBUTE static size_t FSE_decompress_wksp_body_bmi2(void* dst, siz
 
 size_t FSE_decompress_wksp_bmi2(void* dst, size_t dstCapacity, const void* cSrc, size_t cSrcSize, unsigned maxLog, void* workSpace, size_t wkspSize, int bmi2)
 {
-#if DYNAMIC_BMI2
-    if (bmi2) {
+    if (ZSTD_USE_BMI2(bmi2)) {
         return FSE_decompress_wksp_body_bmi2(dst, dstCapacity, cSrc, cSrcSize, maxLog, workSpace, wkspSize);
     }
-#endif
     (void)bmi2;
     return FSE_decompress_wksp_body_default(dst, dstCapacity, cSrc, cSrcSize, maxLog, workSpace, wkspSize);
 }
diff --git a/lib/zstd/common/zstd_deps.h b/lib/zstd/common/zstd_deps.h
index f931f7d0e2947..a312029df5660 100644
--- a/lib/zstd/common/zstd_deps.h
+++ b/lib/zstd/common/zstd_deps.h
@@ -26,6 +26,11 @@
 #ifndef ZSTD_DEPS_COMMON
 #define ZSTD_DEPS_COMMON
 
+#if defined(__KERNEL__) && defined(CONFIG_X86) && \
+    !defined(__DISABLE_EXPORTS)
+#define ZSTD_USE_KERNEL_CPU_FEATURES
+#endif
+
 #include <linux/limits.h>
 #include <linux/stddef.h>
 
diff --git a/lib/zstd/compress/huf_compress.c b/lib/zstd/compress/huf_compress.c
index 0b229f5d2ae22..f3f53240c981d 100644
--- a/lib/zstd/compress/huf_compress.c
+++ b/lib/zstd/compress/huf_compress.c
@@ -22,6 +22,9 @@
 *  Includes
 ****************************************************************/
 #include "../common/zstd_deps.h"     /* ZSTD_memcpy, ZSTD_memset */
+#if defined(ZSTD_USE_KERNEL_CPU_FEATURES)
+#include <asm/cpufeature.h>
+#endif
 #include "../common/compiler.h"
 #include "../common/bitstream.h"
 #include "hist.h"
@@ -1138,9 +1141,10 @@ HUF_compress1X_usingCTable_internal(void* dst, size_t dstSize,
                               const void* src, size_t srcSize,
                               const HUF_CElt* CTable, const int flags)
 {
-    if (flags & HUF_flags_bmi2) {
+    if (ZSTD_USE_BMI2(flags & HUF_flags_bmi2)) {
         return HUF_compress1X_usingCTable_internal_bmi2(dst, dstSize, src, srcSize, CTable);
     }
+    (void)flags;
     return HUF_compress1X_usingCTable_internal_default(dst, dstSize, src, srcSize, CTable);
 }
 
diff --git a/lib/zstd/compress/zstd_compress.c b/lib/zstd/compress/zstd_compress.c
index c41a747413e01..638bc0bf83127 100644
--- a/lib/zstd/compress/zstd_compress.c
+++ b/lib/zstd/compress/zstd_compress.c
@@ -102,7 +102,7 @@ static void ZSTD_initCCtx(ZSTD_CCtx* cctx, ZSTD_customMem memManager)
     assert(cctx != NULL);
     ZSTD_memset(cctx, 0, sizeof(*cctx));
     cctx->customMem = memManager;
-    cctx->bmi2 = ZSTD_cpuSupportsBmi2();
+    ZSTD_SET_BMI2(cctx->bmi2, ZSTD_cpuSupportsBmi2());
     {   size_t const err = ZSTD_CCtx_reset(cctx, ZSTD_reset_parameters);
         assert(!ZSTD_isError(err));
         (void)err;
@@ -142,7 +142,7 @@ ZSTD_CCtx* ZSTD_initStaticCCtx(void* workspace, size_t workspaceSize)
     cctx->blockState.nextCBlock = (ZSTD_compressedBlockState_t*)ZSTD_cwksp_reserve_object(&cctx->workspace, sizeof(ZSTD_compressedBlockState_t));
     cctx->tmpWorkspace = ZSTD_cwksp_reserve_object(&cctx->workspace, TMP_WORKSPACE_SIZE);
     cctx->tmpWkspSize = TMP_WORKSPACE_SIZE;
-    cctx->bmi2 = ZSTD_cpuid_bmi2(ZSTD_cpuid());
+    ZSTD_SET_BMI2(cctx->bmi2, ZSTD_cpuid_bmi2(ZSTD_cpuid()));
     return cctx;
 }
 
@@ -4042,7 +4042,7 @@ ZSTD_compressSeqStore_singleBlock(ZSTD_CCtx* zc,
                 op + ZSTD_blockHeaderSize, dstCapacity - ZSTD_blockHeaderSize,
                 srcSize,
                 zc->tmpWorkspace, zc->tmpWkspSize /* statically allocated in resetCCtx */,
-                zc->bmi2);
+                ZSTD_CCtx_get_bmi2(zc));
     FORWARD_IF_ERROR(cSeqsSize, "ZSTD_entropyCompressSeqStore failed!");
 
     if (!zc->isFirstBlock &&
@@ -4332,7 +4332,7 @@ ZSTD_compressBlock_internal(ZSTD_CCtx* zc,
             dst, dstCapacity,
             srcSize,
             zc->tmpWorkspace, zc->tmpWkspSize /* statically allocated in resetCCtx */,
-            zc->bmi2);
+            ZSTD_CCtx_get_bmi2(zc));
 
     if (frame &&
         /* We don't want to emit our first block as a RLE even if it qualifies because
@@ -6796,7 +6796,7 @@ ZSTD_compressSequences_internal(ZSTD_CCtx* cctx,
                                 op + ZSTD_blockHeaderSize /* Leave space for block header */, dstCapacity - ZSTD_blockHeaderSize,
                                 blockSize,
                                 cctx->tmpWorkspace, cctx->tmpWkspSize /* statically allocated in resetCCtx */,
-                                cctx->bmi2);
+                                ZSTD_CCtx_get_bmi2(cctx));
         FORWARD_IF_ERROR(compressedSeqsSize, "Compressing sequences of block failed");
         DEBUGLOG(5, "Compressed sequences size: %zu", compressedSeqsSize);
 
@@ -7321,7 +7321,7 @@ ZSTD_compressSequencesAndLiterals_internal(ZSTD_CCtx* cctx,
                                 &cctx->blockState.prevCBlock->entropy, &cctx->blockState.nextCBlock->entropy,
                                 &cctx->appliedParams,
                                 cctx->tmpWorkspace, cctx->tmpWkspSize /* statically allocated in resetCCtx */,
-                                cctx->bmi2);
+                                ZSTD_CCtx_get_bmi2(cctx));
         FORWARD_IF_ERROR(compressedSeqsSize, "Compressing sequences of block failed");
         /* note: the spec forbids for any compressed block to be larger than maximum block size */
         if (compressedSeqsSize > cctx->blockSizeMax) compressedSeqsSize = 0;
diff --git a/lib/zstd/compress/zstd_compress_internal.h b/lib/zstd/compress/zstd_compress_internal.h
index b109783858763..99ebe1e0c923f 100644
--- a/lib/zstd/compress/zstd_compress_internal.h
+++ b/lib/zstd/compress/zstd_compress_internal.h
@@ -537,6 +537,15 @@ struct ZSTD_CCtx_s {
     size_t extSeqBufCapacity;
 };
 
+MEM_STATIC int ZSTD_CCtx_get_bmi2(const struct ZSTD_CCtx_s *cctx) {
+#if DYNAMIC_BMI2 && !defined(ZSTD_USE_KERNEL_CPU_FEATURES)
+    return cctx->bmi2;
+#else
+    (void)cctx;
+    return 0;
+#endif
+}
+
 typedef enum { ZSTD_dtlm_fast, ZSTD_dtlm_full } ZSTD_dictTableLoadMethod_e;
 typedef enum { ZSTD_tfp_forCCtx, ZSTD_tfp_forCDict } ZSTD_tableFillPurpose_e;
 
diff --git a/lib/zstd/compress/zstd_compress_sequences.c b/lib/zstd/compress/zstd_compress_sequences.c
index 64abcdf2c5714..7a03a8fceea7d 100644
--- a/lib/zstd/compress/zstd_compress_sequences.c
+++ b/lib/zstd/compress/zstd_compress_sequences.c
@@ -12,6 +12,10 @@
  /*-*************************************
  *  Dependencies
  ***************************************/
+#include "../common/zstd_deps.h"
+#if defined(ZSTD_USE_KERNEL_CPU_FEATURES)
+#include <asm/cpufeature.h>
+#endif
 #include "zstd_compress_sequences.h"
 
 /*
@@ -429,15 +433,13 @@ size_t ZSTD_encodeSequences(
             SeqDef const* sequences, size_t nbSeq, int longOffsets, int bmi2)
 {
     DEBUGLOG(5, "ZSTD_encodeSequences: dstCapacity = %u", (unsigned)dstCapacity);
-#if DYNAMIC_BMI2
-    if (bmi2) {
+    if (ZSTD_USE_BMI2(bmi2)) {
         return ZSTD_encodeSequences_bmi2(dst, dstCapacity,
                                          CTable_MatchLength, mlCodeTable,
                                          CTable_OffsetBits, ofCodeTable,
                                          CTable_LitLength, llCodeTable,
                                          sequences, nbSeq, longOffsets);
     }
-#endif
     (void)bmi2;
     return ZSTD_encodeSequences_default(dst, dstCapacity,
                                         CTable_MatchLength, mlCodeTable,
diff --git a/lib/zstd/compress/zstd_compress_superblock.c b/lib/zstd/compress/zstd_compress_superblock.c
index dc12d64e935c4..fada5979c3b84 100644
--- a/lib/zstd/compress/zstd_compress_superblock.c
+++ b/lib/zstd/compress/zstd_compress_superblock.c
@@ -684,6 +684,6 @@ size_t ZSTD_compressSuperBlock(ZSTD_CCtx* zc,
             &zc->appliedParams,
             dst, dstCapacity,
             src, srcSize,
-            zc->bmi2, lastBlock,
+            ZSTD_CCtx_get_bmi2(zc), lastBlock,
             zc->tmpWorkspace, zc->tmpWkspSize /* statically allocated in resetCCtx */);
 }
diff --git a/lib/zstd/decompress/huf_decompress.c b/lib/zstd/decompress/huf_decompress.c
index 5663ae524cd83..8bf2279887e8f 100644
--- a/lib/zstd/decompress/huf_decompress.c
+++ b/lib/zstd/decompress/huf_decompress.c
@@ -17,6 +17,9 @@
 *  Dependencies
 ****************************************************************/
 #include "../common/zstd_deps.h"  /* ZSTD_memcpy, ZSTD_memset */
+#if defined(ZSTD_USE_KERNEL_CPU_FEATURES)
+#include <asm/cpufeature.h>
+#endif
 #include "../common/compiler.h"
 #include "../common/bitstream.h"  /* BIT_* */
 #include "../common/fse.h"        /* to compress headers */
@@ -113,9 +116,10 @@ typedef size_t (*HUF_DecompressUsingDTableFn)(void *dst, size_t dstSize,
     static size_t fn(void* dst, size_t dstSize, void const* cSrc,           \
                      size_t cSrcSize, HUF_DTable const* DTable, int flags)  \
     {                                                                       \
-        if (flags & HUF_flags_bmi2) {                                       \
+        if (ZSTD_USE_BMI2(flags & HUF_flags_bmi2)) {                        \
             return fn##_bmi2(dst, dstSize, cSrc, cSrcSize, DTable);         \
         }                                                                   \
+        (void)flags;                                                        \
         return fn##_default(dst, dstSize, cSrc, cSrcSize, DTable);          \
     }
 
@@ -899,18 +903,16 @@ static size_t HUF_decompress4X1_usingDTable_internal(void* dst, size_t dstSize,
     HUF_DecompressUsingDTableFn fallbackFn = HUF_decompress4X1_usingDTable_internal_default;
     HUF_DecompressFastLoopFn loopFn = HUF_decompress4X1_usingDTable_internal_fast_c_loop;
 
-#if DYNAMIC_BMI2
-    if (flags & HUF_flags_bmi2) {
+    if (ZSTD_USE_BMI2(flags & HUF_flags_bmi2)) {
         fallbackFn = HUF_decompress4X1_usingDTable_internal_bmi2;
 # if ZSTD_ENABLE_ASM_X86_64_BMI2
         if (!(flags & HUF_flags_disableAsm)) {
             loopFn = HUF_decompress4X1_usingDTable_internal_fast_asm_loop;
         }
 # endif
-    } else {
+    } else if (DYNAMIC_BMI2) {
         return fallbackFn(dst, dstSize, cSrc, cSrcSize, DTable);
     }
-#endif
 
 #if ZSTD_ENABLE_ASM_X86_64_BMI2 && defined(__BMI2__)
     if (!(flags & HUF_flags_disableAsm)) {
@@ -1723,18 +1725,16 @@ static size_t HUF_decompress4X2_usingDTable_internal(void* dst, size_t dstSize,
     HUF_DecompressUsingDTableFn fallbackFn = HUF_decompress4X2_usingDTable_internal_default;
     HUF_DecompressFastLoopFn loopFn = HUF_decompress4X2_usingDTable_internal_fast_c_loop;
 
-#if DYNAMIC_BMI2
-    if (flags & HUF_flags_bmi2) {
+    if (ZSTD_USE_BMI2(flags & HUF_flags_bmi2)) {
         fallbackFn = HUF_decompress4X2_usingDTable_internal_bmi2;
 # if ZSTD_ENABLE_ASM_X86_64_BMI2
         if (!(flags & HUF_flags_disableAsm)) {
             loopFn = HUF_decompress4X2_usingDTable_internal_fast_asm_loop;
         }
 # endif
-    } else {
+    } else if (DYNAMIC_BMI2) {
         return fallbackFn(dst, dstSize, cSrc, cSrcSize, DTable);
     }
-#endif
 
 #if ZSTD_ENABLE_ASM_X86_64_BMI2 && defined(__BMI2__)
     if (!(flags & HUF_flags_disableAsm)) {
diff --git a/lib/zstd/decompress/zstd_decompress.c b/lib/zstd/decompress/zstd_decompress.c
index bb009554e3a61..cc6ecd364970a 100644
--- a/lib/zstd/decompress/zstd_decompress.c
+++ b/lib/zstd/decompress/zstd_decompress.c
@@ -259,9 +259,7 @@ static void ZSTD_initDCtx_internal(ZSTD_DCtx* dctx)
     dctx->noForwardProgress = 0;
     dctx->oversizedDuration = 0;
     dctx->isFrameDecompression = 1;
-#if DYNAMIC_BMI2
-    dctx->bmi2 = ZSTD_cpuSupportsBmi2();
-#endif
+    ZSTD_SET_BMI2(dctx->bmi2, ZSTD_cpuSupportsBmi2());
     dctx->ddictSet = NULL;
     ZSTD_DCtx_resetParameters(dctx);
 #ifdef FUZZING_BUILD_MODE_UNSAFE_FOR_PRODUCTION
diff --git a/lib/zstd/decompress/zstd_decompress_block.c b/lib/zstd/decompress/zstd_decompress_block.c
index 9c4215e435014..31804cbf1f7ed 100644
--- a/lib/zstd/decompress/zstd_decompress_block.c
+++ b/lib/zstd/decompress/zstd_decompress_block.c
@@ -16,6 +16,9 @@
 *  Dependencies
 *********************************************************/
 #include "../common/zstd_deps.h"   /* ZSTD_memcpy, ZSTD_memmove, ZSTD_memset */
+#if defined(ZSTD_USE_KERNEL_CPU_FEATURES)
+#include <asm/cpufeature.h>
+#endif
 #include "../common/compiler.h"    /* prefetch */
 #include "../common/cpu.h"         /* bmi2 */
 #include "../common/mem.h"         /* low level memory routines */
@@ -631,13 +634,11 @@ void ZSTD_buildFSETable(ZSTD_seqSymbol* dt,
             const U32* baseValue, const U8* nbAdditionalBits,
             unsigned tableLog, void* wksp, size_t wkspSize, int bmi2)
 {
-#if DYNAMIC_BMI2
-    if (bmi2) {
+    if (ZSTD_USE_BMI2(bmi2)) {
         ZSTD_buildFSETable_body_bmi2(dt, normalizedCounter, maxSymbolValue,
                 baseValue, nbAdditionalBits, tableLog, wksp, wkspSize);
         return;
     }
-#endif
     (void)bmi2;
     ZSTD_buildFSETable_body_default(dt, normalizedCounter, maxSymbolValue,
             baseValue, nbAdditionalBits, tableLog, wksp, wkspSize);
@@ -1955,11 +1956,9 @@ ZSTD_decompressSequences(ZSTD_DCtx* dctx, void* dst, size_t maxDstSize,
                    const ZSTD_longOffset_e isLongOffset)
 {
     DEBUGLOG(5, "ZSTD_decompressSequences");
-#if DYNAMIC_BMI2
-    if (ZSTD_DCtx_get_bmi2(dctx)) {
+    if (ZSTD_USE_BMI2(ZSTD_DCtx_get_bmi2(dctx))) {
         return ZSTD_decompressSequences_bmi2(dctx, dst, maxDstSize, seqStart, seqSize, nbSeq, isLongOffset);
     }
-#endif
     return ZSTD_decompressSequences_default(dctx, dst, maxDstSize, seqStart, seqSize, nbSeq, isLongOffset);
 }
 static size_t
@@ -1968,11 +1967,9 @@ ZSTD_decompressSequencesSplitLitBuffer(ZSTD_DCtx* dctx, void* dst, size_t maxDst
                                  const ZSTD_longOffset_e isLongOffset)
 {
     DEBUGLOG(5, "ZSTD_decompressSequencesSplitLitBuffer");
-#if DYNAMIC_BMI2
-    if (ZSTD_DCtx_get_bmi2(dctx)) {
+    if (ZSTD_USE_BMI2(ZSTD_DCtx_get_bmi2(dctx))) {
         return ZSTD_decompressSequencesSplitLitBuffer_bmi2(dctx, dst, maxDstSize, seqStart, seqSize, nbSeq, isLongOffset);
     }
-#endif
     return ZSTD_decompressSequencesSplitLitBuffer_default(dctx, dst, maxDstSize, seqStart, seqSize, nbSeq, isLongOffset);
 }
 #endif /* ZSTD_FORCE_DECOMPRESS_SEQUENCES_LONG */
@@ -1991,11 +1988,9 @@ ZSTD_decompressSequencesLong(ZSTD_DCtx* dctx,
                              const ZSTD_longOffset_e isLongOffset)
 {
     DEBUGLOG(5, "ZSTD_decompressSequencesLong");
-#if DYNAMIC_BMI2
-    if (ZSTD_DCtx_get_bmi2(dctx)) {
+    if (ZSTD_USE_BMI2(ZSTD_DCtx_get_bmi2(dctx))) {
         return ZSTD_decompressSequencesLong_bmi2(dctx, dst, maxDstSize, seqStart, seqSize, nbSeq, isLongOffset);
     }
-#endif
   return ZSTD_decompressSequencesLong_default(dctx, dst, maxDstSize, seqStart, seqSize, nbSeq, isLongOffset);
 }
 #endif /* ZSTD_FORCE_DECOMPRESS_SEQUENCES_SHORT */
diff --git a/lib/zstd/decompress/zstd_decompress_internal.h b/lib/zstd/decompress/zstd_decompress_internal.h
index 2a225d1811c4f..401f2b526bbce 100644
--- a/lib/zstd/decompress/zstd_decompress_internal.h
+++ b/lib/zstd/decompress/zstd_decompress_internal.h
@@ -204,7 +204,7 @@ struct ZSTD_DCtx_s
 };  /* typedef'd to ZSTD_DCtx within "zstd.h" */
 
 MEM_STATIC int ZSTD_DCtx_get_bmi2(const struct ZSTD_DCtx_s *dctx) {
-#if DYNAMIC_BMI2
+#if DYNAMIC_BMI2 && !defined(ZSTD_USE_KERNEL_CPU_FEATURES)
     return dctx->bmi2;
 #else
     (void)dctx;
-- 
2.53.0-Meta