zstd: Import upstream v1.5.7

In addition to keeping the kernel's copy of zstd up to date, this update
was requested by Intel to expose upstream's APIs that allow QAT to accelerate
the LZ match finding stage of Zstd.

This patch is imported from the upstream tag v1.5.7-kernel [0], which is signed
with upstream's signing key EF8FE99528B52FFD [1]. It was imported from upstream
using this command:

  export ZSTD=/path/to/repo/zstd/
  export LINUX=/path/to/repo/linux/
  cd "$ZSTD/contrib/linux-kernel"
  git checkout v1.5.7-kernel
  make import LINUX="$LINUX"

This patch has been tested on x86-64, and has been boot tested with
a zstd compressed kernel & initramfs on i386 and aarch64. I benchmarked
the patch on x86-64 with gcc-14.2.1 on an Intel i9-9900K by measruing the
performance of compressed filesystem reads and writes.

Component,  Level,  Size delta, C. time delta,  D. time delta
Btrfs    ,      1,      +0.00%,         -6.1%,          +1.4%
Btrfs    ,      3,      +0.00%,         -9.8%,          +3.0%
Btrfs    ,      5,      +0.00%,         +1.7%,          +1.4%
Btrfs    ,      7,      +0.00%,         -1.9%,          +2.7%
Btrfs    ,      9,      +0.00%,         -3.4%,          +3.7%
Btrfs    ,     15,      +0.00%,         -0.3%,          +3.6%
SquashFS ,      1,      +0.00%,           N/A,          +1.9%

The major changes that impact the kernel use cases for each version are:

v1.5.7: https://github.com/facebook/zstd/releases/tag/v1.5.7
* Add zstd_compress_sequences_and_literals() for use by Intel's QAT driver
  to implement Zstd compression acceleration in the kernel.
* Fix an underflow bug in 32-bit builds that can cause data corruption when
  processing more than 4GB of data with a single `ZSTD_CCtx` object, when an
  input crosses the 4GB boundry. I don't believe this impacts any current kernel
  use cases, because the `ZSTD_CCtx` is typically reconstructed between
  compressions.
* Levels 1-4 see 5-10% compression speed improvements for inputs smaller than
  128KB.

v1.5.6: https://github.com/facebook/zstd/releases/tag/v1.5.6
* Improved compression ratio for the highest compression levels. I don't expect
  these see much use however, due to their slow speeds.

v1.5.5: https://github.com/facebook/zstd/releases/tag/v1.5.5
* Fix a rare corruption bug that can trigger on levels 13 and above.
* Improve compression speed of levels 5-11 on incompressible data.

v1.5.4: https://github.com/facebook/zstd/releases/tag/v1.5.4
* Improve copmression speed of levels 5-11 on ARM.
* Improve dictionary compression speed.

Signed-off-by: Nick Terrell <terrelln@fb.com>

18 files changed, 697 insertions, 737 deletions

diff --git a/lib/zstd/common/allocations.h b/lib/zstd/common/allocations.h
new file mode 100644
index 000000000000..16c3d08e8d1a
--- /dev/null
+++ b/lib/zstd/common/allocations.h
@@ -0,0 +1,56 @@
+/* SPDX-License-Identifier: GPL-2.0+ OR BSD-3-Clause */
+/*
+ * Copyright (c) Meta Platforms, Inc. and affiliates.
+ * All rights reserved.
+ *
+ * This source code is licensed under both the BSD-style license (found in the
+ * LICENSE file in the root directory of this source tree) and the GPLv2 (found
+ * in the COPYING file in the root directory of this source tree).
+ * You may select, at your option, one of the above-listed licenses.
+ */
+
+/* This file provides custom allocation primitives
+ */
+
+#define ZSTD_DEPS_NEED_MALLOC
+#include "zstd_deps.h"   /* ZSTD_malloc, ZSTD_calloc, ZSTD_free, ZSTD_memset */
+
+#include "compiler.h" /* MEM_STATIC */
+#define ZSTD_STATIC_LINKING_ONLY
+#include <linux/zstd.h> /* ZSTD_customMem */
+
+#ifndef ZSTD_ALLOCATIONS_H
+#define ZSTD_ALLOCATIONS_H
+
+/* custom memory allocation functions */
+
+MEM_STATIC void* ZSTD_customMalloc(size_t size, ZSTD_customMem customMem)
+{
+    if (customMem.customAlloc)
+        return customMem.customAlloc(customMem.opaque, size);
+    return ZSTD_malloc(size);
+}
+
+MEM_STATIC void* ZSTD_customCalloc(size_t size, ZSTD_customMem customMem)
+{
+    if (customMem.customAlloc) {
+        /* calloc implemented as malloc+memset;
+         * not as efficient as calloc, but next best guess for custom malloc */
+        void* const ptr = customMem.customAlloc(customMem.opaque, size);
+        ZSTD_memset(ptr, 0, size);
+        return ptr;
+    }
+    return ZSTD_calloc(1, size);
+}
+
+MEM_STATIC void ZSTD_customFree(void* ptr, ZSTD_customMem customMem)
+{
+    if (ptr!=NULL) {
+        if (customMem.customFree)
+            customMem.customFree(customMem.opaque, ptr);
+        else
+            ZSTD_free(ptr);
+    }
+}
+
+#endif /* ZSTD_ALLOCATIONS_H */
diff --git a/lib/zstd/common/bits.h b/lib/zstd/common/bits.h
new file mode 100644
index 000000000000..c5faaa3d7b08
--- /dev/null
+++ b/lib/zstd/common/bits.h
@@ -0,0 +1,150 @@
+/* SPDX-License-Identifier: GPL-2.0+ OR BSD-3-Clause */
+/*
+ * Copyright (c) Meta Platforms, Inc. and affiliates.
+ * All rights reserved.
+ *
+ * This source code is licensed under both the BSD-style license (found in the
+ * LICENSE file in the root directory of this source tree) and the GPLv2 (found
+ * in the COPYING file in the root directory of this source tree).
+ * You may select, at your option, one of the above-listed licenses.
+ */
+
+#ifndef ZSTD_BITS_H
+#define ZSTD_BITS_H
+
+#include "mem.h"
+
+MEM_STATIC unsigned ZSTD_countTrailingZeros32_fallback(U32 val)
+{
+    assert(val != 0);
+    {
+        static const U32 DeBruijnBytePos[32] = {0, 1, 28, 2, 29, 14, 24, 3,
+                                                30, 22, 20, 15, 25, 17, 4, 8,
+                                                31, 27, 13, 23, 21, 19, 16, 7,
+                                                26, 12, 18, 6, 11, 5, 10, 9};
+        return DeBruijnBytePos[((U32) ((val & -(S32) val) * 0x077CB531U)) >> 27];
+    }
+}
+
+MEM_STATIC unsigned ZSTD_countTrailingZeros32(U32 val)
+{
+    assert(val != 0);
+#if (__GNUC__ >= 4)
+    return (unsigned)__builtin_ctz(val);
+#else
+    return ZSTD_countTrailingZeros32_fallback(val);
+#endif
+}
+
+MEM_STATIC unsigned ZSTD_countLeadingZeros32_fallback(U32 val)
+{
+    assert(val != 0);
+    {
+        static const U32 DeBruijnClz[32] = {0, 9, 1, 10, 13, 21, 2, 29,
+                                            11, 14, 16, 18, 22, 25, 3, 30,
+                                            8, 12, 20, 28, 15, 17, 24, 7,
+                                            19, 27, 23, 6, 26, 5, 4, 31};
+        val |= val >> 1;
+        val |= val >> 2;
+        val |= val >> 4;
+        val |= val >> 8;
+        val |= val >> 16;
+        return 31 - DeBruijnClz[(val * 0x07C4ACDDU) >> 27];
+    }
+}
+
+MEM_STATIC unsigned ZSTD_countLeadingZeros32(U32 val)
+{
+    assert(val != 0);
+#if (__GNUC__ >= 4)
+    return (unsigned)__builtin_clz(val);
+#else
+    return ZSTD_countLeadingZeros32_fallback(val);
+#endif
+}
+
+MEM_STATIC unsigned ZSTD_countTrailingZeros64(U64 val)
+{
+    assert(val != 0);
+#if (__GNUC__ >= 4) && defined(__LP64__)
+    return (unsigned)__builtin_ctzll(val);
+#else
+    {
+        U32 mostSignificantWord = (U32)(val >> 32);
+        U32 leastSignificantWord = (U32)val;
+        if (leastSignificantWord == 0) {
+            return 32 + ZSTD_countTrailingZeros32(mostSignificantWord);
+        } else {
+            return ZSTD_countTrailingZeros32(leastSignificantWord);
+        }
+    }
+#endif
+}
+
+MEM_STATIC unsigned ZSTD_countLeadingZeros64(U64 val)
+{
+    assert(val != 0);
+#if (__GNUC__ >= 4)
+    return (unsigned)(__builtin_clzll(val));
+#else
+    {
+        U32 mostSignificantWord = (U32)(val >> 32);
+        U32 leastSignificantWord = (U32)val;
+        if (mostSignificantWord == 0) {
+            return 32 + ZSTD_countLeadingZeros32(leastSignificantWord);
+        } else {
+            return ZSTD_countLeadingZeros32(mostSignificantWord);
+        }
+    }
+#endif
+}
+
+MEM_STATIC unsigned ZSTD_NbCommonBytes(size_t val)
+{
+    if (MEM_isLittleEndian()) {
+        if (MEM_64bits()) {
+            return ZSTD_countTrailingZeros64((U64)val) >> 3;
+        } else {
+            return ZSTD_countTrailingZeros32((U32)val) >> 3;
+        }
+    } else {  /* Big Endian CPU */
+        if (MEM_64bits()) {
+            return ZSTD_countLeadingZeros64((U64)val) >> 3;
+        } else {
+            return ZSTD_countLeadingZeros32((U32)val) >> 3;
+        }
+    }
+}
+
+MEM_STATIC unsigned ZSTD_highbit32(U32 val)   /* compress, dictBuilder, decodeCorpus */
+{
+    assert(val != 0);
+    return 31 - ZSTD_countLeadingZeros32(val);
+}
+
+/* ZSTD_rotateRight_*():
+ * Rotates a bitfield to the right by "count" bits.
+ * https://en.wikipedia.org/w/index.php?title=Circular_shift&oldid=991635599#Implementing_circular_shifts
+ */
+MEM_STATIC
+U64 ZSTD_rotateRight_U64(U64 const value, U32 count) {
+    assert(count < 64);
+    count &= 0x3F; /* for fickle pattern recognition */
+    return (value >> count) | (U64)(value << ((0U - count) & 0x3F));
+}
+
+MEM_STATIC
+U32 ZSTD_rotateRight_U32(U32 const value, U32 count) {
+    assert(count < 32);
+    count &= 0x1F; /* for fickle pattern recognition */
+    return (value >> count) | (U32)(value << ((0U - count) & 0x1F));
+}
+
+MEM_STATIC
+U16 ZSTD_rotateRight_U16(U16 const value, U32 count) {
+    assert(count < 16);
+    count &= 0x0F; /* for fickle pattern recognition */
+    return (value >> count) | (U16)(value << ((0U - count) & 0x0F));
+}
+
+#endif /* ZSTD_BITS_H */
diff --git a/lib/zstd/common/bitstream.h b/lib/zstd/common/bitstream.h
index feef3a1b1d60..86439da0eea7 100644
--- a/lib/zstd/common/bitstream.h
+++ b/lib/zstd/common/bitstream.h
@@ -1,7 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0+ OR BSD-3-Clause */
 /* ******************************************************************
  * bitstream
  * Part of FSE library
- * Copyright (c) Yann Collet, Facebook, Inc.
+ * Copyright (c) Meta Platforms, Inc. and affiliates.
  *
  * You can contact the author at :
  * - Source repository : https://github.com/Cyan4973/FiniteStateEntropy
@@ -27,7 +28,7 @@
 #include "compiler.h"       /* UNLIKELY() */
 #include "debug.h"          /* assert(), DEBUGLOG(), RAWLOG() */
 #include "error_private.h"  /* error codes and messages */
-
+#include "bits.h"           /* ZSTD_highbit32 */
 
 /*=========================================
 *  Target specific
@@ -41,12 +42,13 @@
 /*-******************************************
 *  bitStream encoding API (write forward)
 ********************************************/
+typedef size_t BitContainerType;
 /* bitStream can mix input from multiple sources.
  * A critical property of these streams is that they encode and decode in **reverse** direction.
  * So the first bit sequence you add will be the last to be read, like a LIFO stack.
  */
 typedef struct {
-    size_t bitContainer;
+    BitContainerType bitContainer;
     unsigned bitPos;
     char*  startPtr;
     char*  ptr;
@@ -54,7 +56,7 @@ typedef struct {
 } BIT_CStream_t;
 
 MEM_STATIC size_t BIT_initCStream(BIT_CStream_t* bitC, void* dstBuffer, size_t dstCapacity);
-MEM_STATIC void   BIT_addBits(BIT_CStream_t* bitC, size_t value, unsigned nbBits);
+MEM_STATIC void   BIT_addBits(BIT_CStream_t* bitC, BitContainerType value, unsigned nbBits);
 MEM_STATIC void   BIT_flushBits(BIT_CStream_t* bitC);
 MEM_STATIC size_t BIT_closeCStream(BIT_CStream_t* bitC);
 
@@ -63,7 +65,7 @@ MEM_STATIC size_t BIT_closeCStream(BIT_CStream_t* bitC);
 *  `dstCapacity` must be >= sizeof(bitD->bitContainer), otherwise @return will be an error code.
 *
 *  bits are first added to a local register.
-*  Local register is size_t, hence 64-bits on 64-bits systems, or 32-bits on 32-bits systems.
+*  Local register is BitContainerType, 64-bits on 64-bits systems, or 32-bits on 32-bits systems.
 *  Writing data into memory is an explicit operation, performed by the flushBits function.
 *  Hence keep track how many bits are potentially stored into local register to avoid register overflow.
 *  After a flushBits, a maximum of 7 bits might still be stored into local register.
@@ -80,28 +82,28 @@ MEM_STATIC size_t BIT_closeCStream(BIT_CStream_t* bitC);
 *  bitStream decoding API (read backward)
 **********************************************/
 typedef struct {
-    size_t   bitContainer;
+    BitContainerType bitContainer;
     unsigned bitsConsumed;
     const char* ptr;
     const char* start;
     const char* limitPtr;
 } BIT_DStream_t;
 
-typedef enum { BIT_DStream_unfinished = 0,
-               BIT_DStream_endOfBuffer = 1,
-               BIT_DStream_completed = 2,
-               BIT_DStream_overflow = 3 } BIT_DStream_status;  /* result of BIT_reloadDStream() */
-               /* 1,2,4,8 would be better for bitmap combinations, but slows down performance a bit ... :( */
+typedef enum { BIT_DStream_unfinished = 0,  /* fully refilled */
+               BIT_DStream_endOfBuffer = 1, /* still some bits left in bitstream */
+               BIT_DStream_completed = 2,   /* bitstream entirely consumed, bit-exact */
+               BIT_DStream_overflow = 3     /* user requested more bits than present in bitstream */
+    } BIT_DStream_status;  /* result of BIT_reloadDStream() */
 
 MEM_STATIC size_t   BIT_initDStream(BIT_DStream_t* bitD, const void* srcBuffer, size_t srcSize);
-MEM_STATIC size_t   BIT_readBits(BIT_DStream_t* bitD, unsigned nbBits);
+MEM_STATIC BitContainerType BIT_readBits(BIT_DStream_t* bitD, unsigned nbBits);
 MEM_STATIC BIT_DStream_status BIT_reloadDStream(BIT_DStream_t* bitD);
 MEM_STATIC unsigned BIT_endOfDStream(const BIT_DStream_t* bitD);
 
 
 /* Start by invoking BIT_initDStream().
 *  A chunk of the bitStream is then stored into a local register.
-*  Local register size is 64-bits on 64-bits systems, 32-bits on 32-bits systems (size_t).
+*  Local register size is 64-bits on 64-bits systems, 32-bits on 32-bits systems (BitContainerType).
 *  You can then retrieve bitFields stored into the local register, **in reverse order**.
 *  Local register is explicitly reloaded from memory by the BIT_reloadDStream() method.
 *  A reload guarantee a minimum of ((8*sizeof(bitD->bitContainer))-7) bits when its result is BIT_DStream_unfinished.
@@ -113,7 +115,7 @@ MEM_STATIC unsigned BIT_endOfDStream(const BIT_DStream_t* bitD);
 /*-****************************************
 *  unsafe API
 ******************************************/
-MEM_STATIC void BIT_addBitsFast(BIT_CStream_t* bitC, size_t value, unsigned nbBits);
+MEM_STATIC void BIT_addBitsFast(BIT_CStream_t* bitC, BitContainerType value, unsigned nbBits);
 /* faster, but works only if value is "clean", meaning all high bits above nbBits are 0 */
 
 MEM_STATIC void BIT_flushBitsFast(BIT_CStream_t* bitC);
@@ -122,33 +124,6 @@ MEM_STATIC void BIT_flushBitsFast(BIT_CStream_t* bitC);
 MEM_STATIC size_t BIT_readBitsFast(BIT_DStream_t* bitD, unsigned nbBits);
 /* faster, but works only if nbBits >= 1 */
 
-
-
-/*-**************************************************************
-*  Internal functions
-****************************************************************/
-MEM_STATIC unsigned BIT_highbit32 (U32 val)
-{
-    assert(val != 0);
-    {
-#   if (__GNUC__ >= 3)   /* Use GCC Intrinsic */
-        return __builtin_clz (val) ^ 31;
-#   else   /* Software version */
-        static const unsigned DeBruijnClz[32] = { 0,  9,  1, 10, 13, 21,  2, 29,
-                                                 11, 14, 16, 18, 22, 25,  3, 30,
-                                                  8, 12, 20, 28, 15, 17, 24,  7,
-                                                 19, 27, 23,  6, 26,  5,  4, 31 };
-        U32 v = val;
-        v |= v >> 1;
-        v |= v >> 2;
-        v |= v >> 4;
-        v |= v >> 8;
-        v |= v >> 16;
-        return DeBruijnClz[ (U32) (v * 0x07C4ACDDU) >> 27];
-#   endif
-    }
-}
-
 /*=====    Local Constants   =====*/
 static const unsigned BIT_mask[] = {
     0,          1,         3,         7,         0xF,       0x1F,
@@ -178,16 +153,22 @@ MEM_STATIC size_t BIT_initCStream(BIT_CStream_t* bitC,
     return 0;
 }
 
+FORCE_INLINE_TEMPLATE BitContainerType BIT_getLowerBits(BitContainerType bitContainer, U32 const nbBits)
+{
+    assert(nbBits < BIT_MASK_SIZE);
+    return bitContainer & BIT_mask[nbBits];
+}
+
 /*! BIT_addBits() :
  *  can add up to 31 bits into `bitC`.
  *  Note : does not check for register overflow ! */
 MEM_STATIC void BIT_addBits(BIT_CStream_t* bitC,
-                            size_t value, unsigned nbBits)
+                            BitContainerType value, unsigned nbBits)
 {
     DEBUG_STATIC_ASSERT(BIT_MASK_SIZE == 32);
     assert(nbBits < BIT_MASK_SIZE);
     assert(nbBits + bitC->bitPos < sizeof(bitC->bitContainer) * 8);
-    bitC->bitContainer |= (value & BIT_mask[nbBits]) << bitC->bitPos;
+    bitC->bitContainer |= BIT_getLowerBits(value, nbBits) << bitC->bitPos;
     bitC->bitPos += nbBits;
 }
 
@@ -195,7 +176,7 @@ MEM_STATIC void BIT_addBits(BIT_CStream_t* bitC,
  *  works only if `value` is _clean_,
  *  meaning all high bits above nbBits are 0 */
 MEM_STATIC void BIT_addBitsFast(BIT_CStream_t* bitC,
-                                size_t value, unsigned nbBits)
+                                BitContainerType value, unsigned nbBits)
 {
     assert((value>>nbBits) == 0);
     assert(nbBits + bitC->bitPos < sizeof(bitC->bitContainer) * 8);
@@ -242,7 +223,7 @@ MEM_STATIC size_t BIT_closeCStream(BIT_CStream_t* bitC)
     BIT_addBitsFast(bitC, 1, 1);   /* endMark */
     BIT_flushBits(bitC);
     if (bitC->ptr >= bitC->endPtr) return 0; /* overflow detected */
-    return (bitC->ptr - bitC->startPtr) + (bitC->bitPos > 0);
+    return (size_t)(bitC->ptr - bitC->startPtr) + (bitC->bitPos > 0);
 }
 
 
@@ -266,35 +247,35 @@ MEM_STATIC size_t BIT_initDStream(BIT_DStream_t* bitD, const void* srcBuffer, si
         bitD->ptr   = (const char*)srcBuffer + srcSize - sizeof(bitD->bitContainer);
         bitD->bitContainer = MEM_readLEST(bitD->ptr);
         { BYTE const lastByte = ((const BYTE*)srcBuffer)[srcSize-1];
-          bitD->bitsConsumed = lastByte ? 8 - BIT_highbit32(lastByte) : 0;  /* ensures bitsConsumed is always set */
+          bitD->bitsConsumed = lastByte ? 8 - ZSTD_highbit32(lastByte) : 0;  /* ensures bitsConsumed is always set */
           if (lastByte == 0) return ERROR(GENERIC); /* endMark not present */ }
     } else {
         bitD->ptr   = bitD->start;
         bitD->bitContainer = *(const BYTE*)(bitD->start);
         switch(srcSize)
         {
-        case 7: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[6]) << (sizeof(bitD->bitContainer)*8 - 16);
+        case 7: bitD->bitContainer += (BitContainerType)(((const BYTE*)(srcBuffer))[6]) << (sizeof(bitD->bitContainer)*8 - 16);
                 ZSTD_FALLTHROUGH;
 
-        case 6: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[5]) << (sizeof(bitD->bitContainer)*8 - 24);
+        case 6: bitD->bitContainer += (BitContainerType)(((const BYTE*)(srcBuffer))[5]) << (sizeof(bitD->bitContainer)*8 - 24);
                 ZSTD_FALLTHROUGH;
 
-        case 5: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[4]) << (sizeof(bitD->bitContainer)*8 - 32);
+        case 5: bitD->bitContainer += (BitContainerType)(((const BYTE*)(srcBuffer))[4]) << (sizeof(bitD->bitContainer)*8 - 32);
                 ZSTD_FALLTHROUGH;
 
-        case 4: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[3]) << 24;
+        case 4: bitD->bitContainer += (BitContainerType)(((const BYTE*)(srcBuffer))[3]) << 24;
                 ZSTD_FALLTHROUGH;
 
-        case 3: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[2]) << 16;
+        case 3: bitD->bitContainer += (BitContainerType)(((const BYTE*)(srcBuffer))[2]) << 16;
                 ZSTD_FALLTHROUGH;
 
-        case 2: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[1]) <<  8;
+        case 2: bitD->bitContainer += (BitContainerType)(((const BYTE*)(srcBuffer))[1]) <<  8;
                 ZSTD_FALLTHROUGH;
 
         default: break;
         }
         {   BYTE const lastByte = ((const BYTE*)srcBuffer)[srcSize-1];
-            bitD->bitsConsumed = lastByte ? 8 - BIT_highbit32(lastByte) : 0;
+            bitD->bitsConsumed = lastByte ? 8 - ZSTD_highbit32(lastByte) : 0;
             if (lastByte == 0) return ERROR(corruption_detected);  /* endMark not present */
         }
         bitD->bitsConsumed += (U32)(sizeof(bitD->bitContainer) - srcSize)*8;
@@ -303,12 +284,12 @@ MEM_STATIC size_t BIT_initDStream(BIT_DStream_t* bitD, const void* srcBuffer, si
     return srcSize;
 }
 
-MEM_STATIC FORCE_INLINE_ATTR size_t BIT_getUpperBits(size_t bitContainer, U32 const start)
+FORCE_INLINE_TEMPLATE BitContainerType BIT_getUpperBits(BitContainerType bitContainer, U32 const start)
 {
     return bitContainer >> start;
 }
 
-MEM_STATIC FORCE_INLINE_ATTR size_t BIT_getMiddleBits(size_t bitContainer, U32 const start, U32 const nbBits)
+FORCE_INLINE_TEMPLATE BitContainerType BIT_getMiddleBits(BitContainerType bitContainer, U32 const start, U32 const nbBits)
 {
     U32 const regMask = sizeof(bitContainer)*8 - 1;
     /* if start > regMask, bitstream is corrupted, and result is undefined */
@@ -318,26 +299,20 @@ MEM_STATIC FORCE_INLINE_ATTR size_t BIT_getMiddleBits(size_t bitContainer, U32 c
      * such cpus old (pre-Haswell, 2013) and their performance is not of that
      * importance.
      */
-#if defined(__x86_64__) || defined(_M_X86)
+#if defined(__x86_64__) || defined(_M_X64)
     return (bitContainer >> (start & regMask)) & ((((U64)1) << nbBits) - 1);
 #else
     return (bitContainer >> (start & regMask)) & BIT_mask[nbBits];
 #endif
 }
 
-MEM_STATIC FORCE_INLINE_ATTR size_t BIT_getLowerBits(size_t bitContainer, U32 const nbBits)
-{
-    assert(nbBits < BIT_MASK_SIZE);
-    return bitContainer & BIT_mask[nbBits];
-}
-
 /*! BIT_lookBits() :
  *  Provides next n bits from local register.
  *  local register is not modified.
  *  On 32-bits, maxNbBits==24.
  *  On 64-bits, maxNbBits==56.
  * @return : value extracted */
-MEM_STATIC  FORCE_INLINE_ATTR size_t BIT_lookBits(const BIT_DStream_t*  bitD, U32 nbBits)
+FORCE_INLINE_TEMPLATE BitContainerType BIT_lookBits(const BIT_DStream_t*  bitD, U32 nbBits)
 {
     /* arbitrate between double-shift and shift+mask */
 #if 1
@@ -353,14 +328,14 @@ MEM_STATIC  FORCE_INLINE_ATTR size_t BIT_lookBits(const BIT_DStream_t*  bitD, U3
 
 /*! BIT_lookBitsFast() :
  *  unsafe version; only works if nbBits >= 1 */
-MEM_STATIC size_t BIT_lookBitsFast(const BIT_DStream_t* bitD, U32 nbBits)
+MEM_STATIC BitContainerType BIT_lookBitsFast(const BIT_DStream_t* bitD, U32 nbBits)
 {
     U32 const regMask = sizeof(bitD->bitContainer)*8 - 1;
     assert(nbBits >= 1);
     return (bitD->bitContainer << (bitD->bitsConsumed & regMask)) >> (((regMask+1)-nbBits) & regMask);
 }
 
-MEM_STATIC FORCE_INLINE_ATTR void BIT_skipBits(BIT_DStream_t* bitD, U32 nbBits)
+FORCE_INLINE_TEMPLATE void BIT_skipBits(BIT_DStream_t* bitD, U32 nbBits)
 {
     bitD->bitsConsumed += nbBits;
 }
@@ -369,23 +344,38 @@ MEM_STATIC FORCE_INLINE_ATTR void BIT_skipBits(BIT_DStream_t* bitD, U32 nbBits)
  *  Read (consume) next n bits from local register and update.
  *  Pay attention to not read more than nbBits contained into local register.
  * @return : extracted value. */
-MEM_STATIC FORCE_INLINE_ATTR size_t BIT_readBits(BIT_DStream_t* bitD, unsigned nbBits)
+FORCE_INLINE_TEMPLATE BitContainerType BIT_readBits(BIT_DStream_t* bitD, unsigned nbBits)
 {
-    size_t const value = BIT_lookBits(bitD, nbBits);
+    BitContainerType const value = BIT_lookBits(bitD, nbBits);
     BIT_skipBits(bitD, nbBits);
     return value;
 }
 
 /*! BIT_readBitsFast() :
- *  unsafe version; only works only if nbBits >= 1 */
-MEM_STATIC size_t BIT_readBitsFast(BIT_DStream_t* bitD, unsigned nbBits)
+ *  unsafe version; only works if nbBits >= 1 */
+MEM_STATIC BitContainerType BIT_readBitsFast(BIT_DStream_t* bitD, unsigned nbBits)
 {
-    size_t const value = BIT_lookBitsFast(bitD, nbBits);
+    BitContainerType const value = BIT_lookBitsFast(bitD, nbBits);
     assert(nbBits >= 1);
     BIT_skipBits(bitD, nbBits);
     return value;
 }
 
+/*! BIT_reloadDStream_internal() :
+ *  Simple variant of BIT_reloadDStream(), with two conditions:
+ *  1. bitstream is valid : bitsConsumed <= sizeof(bitD->bitContainer)*8
+ *  2. look window is valid after shifted down : bitD->ptr >= bitD->start
+ */
+MEM_STATIC BIT_DStream_status BIT_reloadDStream_internal(BIT_DStream_t* bitD)
+{
+    assert(bitD->bitsConsumed <= sizeof(bitD->bitContainer)*8);
+    bitD->ptr -= bitD->bitsConsumed >> 3;
+    assert(bitD->ptr >= bitD->start);
+    bitD->bitsConsumed &= 7;
+    bitD->bitContainer = MEM_readLEST(bitD->ptr);
+    return BIT_DStream_unfinished;
+}
+
 /*! BIT_reloadDStreamFast() :
  *  Similar to BIT_reloadDStream(), but with two differences:
  *  1. bitsConsumed <= sizeof(bitD->bitContainer)*8 must hold!
@@ -396,31 +386,35 @@ MEM_STATIC BIT_DStream_status BIT_reloadDStreamFast(BIT_DStream_t* bitD)
 {
     if (UNLIKELY(bitD->ptr < bitD->limitPtr))
         return BIT_DStream_overflow;
-    assert(bitD->bitsConsumed <= sizeof(bitD->bitContainer)*8);
-    bitD->ptr -= bitD->bitsConsumed >> 3;
-    bitD->bitsConsumed &= 7;
-    bitD->bitContainer = MEM_readLEST(bitD->ptr);
-    return BIT_DStream_unfinished;
+    return BIT_reloadDStream_internal(bitD);
 }
 
 /*! BIT_reloadDStream() :
  *  Refill `bitD` from buffer previously set in BIT_initDStream() .
- *  This function is safe, it guarantees it will not read beyond src buffer.
+ *  This function is safe, it guarantees it will not never beyond src buffer.
  * @return : status of `BIT_DStream_t` internal register.
  *           when status == BIT_DStream_unfinished, internal register is filled with at least 25 or 57 bits */
-MEM_STATIC BIT_DStream_status BIT_reloadDStream(BIT_DStream_t* bitD)
+FORCE_INLINE_TEMPLATE BIT_DStream_status BIT_reloadDStream(BIT_DStream_t* bitD)
 {
-    if (bitD->bitsConsumed > (sizeof(bitD->bitContainer)*8))  /* overflow detected, like end of stream */
+    /* note : once in overflow mode, a bitstream remains in this mode until it's reset */
+    if (UNLIKELY(bitD->bitsConsumed > (sizeof(bitD->bitContainer)*8))) {
+        static const BitContainerType zeroFilled = 0;
+        bitD->ptr = (const char*)&zeroFilled; /* aliasing is allowed for char */
+        /* overflow detected, erroneous scenario or end of stream: no update */
         return BIT_DStream_overflow;
+    }
+
+    assert(bitD->ptr >= bitD->start);
 
     if (bitD->ptr >= bitD->limitPtr) {
-        return BIT_reloadDStreamFast(bitD);
+        return BIT_reloadDStream_internal(bitD);
     }
     if (bitD->ptr == bitD->start) {
+        /* reached end of bitStream => no update */
         if (bitD->bitsConsumed < sizeof(bitD->bitContainer)*8) return BIT_DStream_endOfBuffer;
         return BIT_DStream_completed;
     }
-    /* start < ptr < limitPtr */
+    /* start < ptr < limitPtr => cautious update */
     {   U32 nbBytes = bitD->bitsConsumed >> 3;
         BIT_DStream_status result = BIT_DStream_unfinished;
         if (bitD->ptr - nbBytes < bitD->start) {
@@ -442,5 +436,4 @@ MEM_STATIC unsigned BIT_endOfDStream(const BIT_DStream_t* DStream)
     return ((DStream->ptr == DStream->start) && (DStream->bitsConsumed == sizeof(DStream->bitContainer)*8));
 }
 
-
 #endif /* BITSTREAM_H_MODULE */
diff --git a/lib/zstd/common/compiler.h b/lib/zstd/common/compiler.h
index c42d39faf9bd..dc9bd15e174e 100644
--- a/lib/zstd/common/compiler.h
+++ b/lib/zstd/common/compiler.h
@@ -1,5 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0+ OR BSD-3-Clause */
 /*
- * Copyright (c) Yann Collet, Facebook, Inc.
+ * Copyright (c) Meta Platforms, Inc. and affiliates.
  * All rights reserved.
  *
  * This source code is licensed under both the BSD-style license (found in the
@@ -11,6 +12,8 @@
 #ifndef ZSTD_COMPILER_H
 #define ZSTD_COMPILER_H
 
+#include <linux/types.h>
+
 #include "portability_macros.h"
 
 /*-*******************************************************
@@ -41,12 +44,15 @@
 */
 #define WIN_CDECL
 
+/* UNUSED_ATTR tells the compiler it is okay if the function is unused. */
+#define UNUSED_ATTR __attribute__((unused))
+
 /*
  * FORCE_INLINE_TEMPLATE is used to define C "templates", which take constant
  * parameters. They must be inlined for the compiler to eliminate the constant
  * branches.
  */
-#define FORCE_INLINE_TEMPLATE static INLINE_KEYWORD FORCE_INLINE_ATTR
+#define FORCE_INLINE_TEMPLATE static INLINE_KEYWORD FORCE_INLINE_ATTR UNUSED_ATTR
 /*
  * HINT_INLINE is used to help the compiler generate better code. It is *not*
  * used for "templates", so it can be tweaked based on the compilers
@@ -61,11 +67,21 @@
 #if !defined(__clang__) && defined(__GNUC__) && __GNUC__ >= 4 && __GNUC_MINOR__ >= 8 && __GNUC__ < 5
 #  define HINT_INLINE static INLINE_KEYWORD
 #else
-#  define HINT_INLINE static INLINE_KEYWORD FORCE_INLINE_ATTR
+#  define HINT_INLINE FORCE_INLINE_TEMPLATE
 #endif
 
-/* UNUSED_ATTR tells the compiler it is okay if the function is unused. */
-#define UNUSED_ATTR __attribute__((unused))
+/* "soft" inline :
+ * The compiler is free to select if it's a good idea to inline or not.
+ * The main objective is to silence compiler warnings
+ * when a defined function in included but not used.
+ *
+ * Note : this macro is prefixed `MEM_` because it used to be provided by `mem.h` unit.
+ * Updating the prefix is probably preferable, but requires a fairly large codemod,
+ * since this name is used everywhere.
+ */
+#ifndef MEM_STATIC  /* already defined in Linux Kernel mem.h */
+#define MEM_STATIC static __inline UNUSED_ATTR
+#endif
 
 /* force no inlining */
 #define FORCE_NOINLINE static __attribute__((__noinline__))
@@ -86,23 +102,24 @@
 #  define PREFETCH_L1(ptr)  __builtin_prefetch((ptr), 0 /* rw==read */, 3 /* locality */)
 #  define PREFETCH_L2(ptr)  __builtin_prefetch((ptr), 0 /* rw==read */, 2 /* locality */)
 #elif defined(__aarch64__)
-#  define PREFETCH_L1(ptr)  __asm__ __volatile__("prfm pldl1keep, %0" ::"Q"(*(ptr)))
-#  define PREFETCH_L2(ptr)  __asm__ __volatile__("prfm pldl2keep, %0" ::"Q"(*(ptr)))
+#  define PREFETCH_L1(ptr)  do { __asm__ __volatile__("prfm pldl1keep, %0" ::"Q"(*(ptr))); } while (0)
+#  define PREFETCH_L2(ptr)  do { __asm__ __volatile__("prfm pldl2keep, %0" ::"Q"(*(ptr))); } while (0)
 #else
-#  define PREFETCH_L1(ptr) (void)(ptr)  /* disabled */
-#  define PREFETCH_L2(ptr) (void)(ptr)  /* disabled */
+#  define PREFETCH_L1(ptr) do { (void)(ptr); } while (0)  /* disabled */
+#  define PREFETCH_L2(ptr) do { (void)(ptr); } while (0)  /* disabled */
 #endif  /* NO_PREFETCH */
 
 #define CACHELINE_SIZE 64
 
-#define PREFETCH_AREA(p, s)  {            \
-    const char* const _ptr = (const char*)(p);  \
-    size_t const _size = (size_t)(s);     \
-    size_t _pos;                          \
-    for (_pos=0; _pos<_size; _pos+=CACHELINE_SIZE) {  \
-        PREFETCH_L2(_ptr + _pos);         \
-    }                                     \
-}
+#define PREFETCH_AREA(p, s)                              \
+    do {                                                 \
+        const char* const _ptr = (const char*)(p);       \
+        size_t const _size = (size_t)(s);                \
+        size_t _pos;                                     \
+        for (_pos=0; _pos<_size; _pos+=CACHELINE_SIZE) { \
+            PREFETCH_L2(_ptr + _pos);                    \
+        }                                                \
+    } while (0)
 
 /* vectorization
  * older GCC (pre gcc-4.3 picked as the cutoff) uses a different syntax,
@@ -126,16 +143,13 @@
 #define UNLIKELY(x) (__builtin_expect((x), 0))
 
 #if __has_builtin(__builtin_unreachable) || (defined(__GNUC__) && (__GNUC__ > 4 || (__GNUC__ == 4 && __GNUC_MINOR__ >= 5)))
-#  define ZSTD_UNREACHABLE { assert(0), __builtin_unreachable(); }
+#  define ZSTD_UNREACHABLE do { assert(0), __builtin_unreachable(); } while (0)
 #else
-#  define ZSTD_UNREACHABLE { assert(0); }
+#  define ZSTD_UNREACHABLE do { assert(0); } while (0)
 #endif
 
 /* disable warnings */
 
-/*Like DYNAMIC_BMI2 but for compile time determination of BMI2 support*/
-
-
 /* compile time determination of SIMD support */
 
 /* C-language Attributes are added in C23. */
@@ -158,9 +172,15 @@
 #define ZSTD_FALLTHROUGH fallthrough
 
 /*-**************************************************************
-*  Alignment check
+*  Alignment
 *****************************************************************/
 
+/* @return 1 if @u is a 2^n value, 0 otherwise
+ * useful to check a value is valid for alignment restrictions */
+MEM_STATIC int ZSTD_isPower2(size_t u) {
+    return (u & (u-1)) == 0;
+}
+
 /* this test was initially positioned in mem.h,
  * but this file is removed (or replaced) for linux kernel
  * so it's now hosted in compiler.h,
@@ -175,10 +195,95 @@
 
 #endif /* ZSTD_ALIGNOF */
 
+#ifndef ZSTD_ALIGNED
+/* C90-compatible alignment macro (GCC/Clang). Adjust for other compilers if needed. */
+#define ZSTD_ALIGNED(a) __attribute__((aligned(a)))
+#endif /* ZSTD_ALIGNED */
+
+
 /*-**************************************************************
 *  Sanitizer
 *****************************************************************/
 
+/*
+ * Zstd relies on pointer overflow in its decompressor.
+ * We add this attribute to functions that rely on pointer overflow.
+ */
+#ifndef ZSTD_ALLOW_POINTER_OVERFLOW_ATTR
+#  if __has_attribute(no_sanitize)
+#    if !defined(__clang__) && defined(__GNUC__) && __GNUC__ < 8
+       /* gcc < 8 only has signed-integer-overlow which triggers on pointer overflow */
+#      define ZSTD_ALLOW_POINTER_OVERFLOW_ATTR __attribute__((no_sanitize("signed-integer-overflow")))
+#    else
+       /* older versions of clang [3.7, 5.0) will warn that pointer-overflow is ignored. */
+#      define ZSTD_ALLOW_POINTER_OVERFLOW_ATTR __attribute__((no_sanitize("pointer-overflow")))
+#    endif
+#  else
+#    define ZSTD_ALLOW_POINTER_OVERFLOW_ATTR
+#  endif
+#endif
+
+/*
+ * Helper function to perform a wrapped pointer difference without triggering
+ * UBSAN.
+ *
+ * @returns lhs - rhs with wrapping
+ */
+MEM_STATIC
+ZSTD_ALLOW_POINTER_OVERFLOW_ATTR
+ptrdiff_t ZSTD_wrappedPtrDiff(unsigned char const* lhs, unsigned char const* rhs)
+{
+    return lhs - rhs;
+}
+
+/*
+ * Helper function to perform a wrapped pointer add without triggering UBSAN.
+ *
+ * @return ptr + add with wrapping
+ */
+MEM_STATIC
+ZSTD_ALLOW_POINTER_OVERFLOW_ATTR
+unsigned char const* ZSTD_wrappedPtrAdd(unsigned char const* ptr, ptrdiff_t add)
+{
+    return ptr + add;
+}
+
+/*
+ * Helper function to perform a wrapped pointer subtraction without triggering
+ * UBSAN.
+ *
+ * @return ptr - sub with wrapping
+ */
+MEM_STATIC
+ZSTD_ALLOW_POINTER_OVERFLOW_ATTR
+unsigned char const* ZSTD_wrappedPtrSub(unsigned char const* ptr, ptrdiff_t sub)
+{
+    return ptr - sub;
+}
+
+/*
+ * Helper function to add to a pointer that works around C's undefined behavior
+ * of adding 0 to NULL.
+ *
+ * @returns `ptr + add` except it defines `NULL + 0 == NULL`.
+ */
+MEM_STATIC
+unsigned char* ZSTD_maybeNullPtrAdd(unsigned char* ptr, ptrdiff_t add)
+{
+    return add > 0 ? ptr + add : ptr;
+}
+
+/* Issue #3240 reports an ASAN failure on an llvm-mingw build. Out of an
+ * abundance of caution, disable our custom poisoning on mingw. */
+#ifdef __MINGW32__
+#ifndef ZSTD_ASAN_DONT_POISON_WORKSPACE
+#define ZSTD_ASAN_DONT_POISON_WORKSPACE 1
+#endif
+#ifndef ZSTD_MSAN_DONT_POISON_WORKSPACE
+#define ZSTD_MSAN_DONT_POISON_WORKSPACE 1
+#endif
+#endif
+
 
 
 #endif /* ZSTD_COMPILER_H */
diff --git a/lib/zstd/common/cpu.h b/lib/zstd/common/cpu.h
index 0db7b42407ee..d8319a2bef4c 100644
--- a/lib/zstd/common/cpu.h
+++ b/lib/zstd/common/cpu.h
@@ -1,5 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0+ OR BSD-3-Clause */
 /*
- * Copyright (c) Facebook, Inc.
+ * Copyright (c) Meta Platforms, Inc. and affiliates.
  * All rights reserved.
  *
  * This source code is licensed under both the BSD-style license (found in the
diff --git a/lib/zstd/common/debug.c b/lib/zstd/common/debug.c
index bb863c9ea616..8eb6aa9a3b20 100644
--- a/lib/zstd/common/debug.c
+++ b/lib/zstd/common/debug.c
@@ -1,7 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0+ OR BSD-3-Clause
 /* ******************************************************************
  * debug
  * Part of FSE library
- * Copyright (c) Yann Collet, Facebook, Inc.
+ * Copyright (c) Meta Platforms, Inc. and affiliates.
  *
  * You can contact the author at :
  * - Source repository : https://github.com/Cyan4973/FiniteStateEntropy
@@ -21,4 +22,10 @@
 
 #include "debug.h"
 
+#if (DEBUGLEVEL>=2)
+/* We only use this when DEBUGLEVEL>=2, but we get -Werror=pedantic errors if a
+ * translation unit is empty. So remove this from Linux kernel builds, but
+ * otherwise just leave it in.
+ */
 int g_debuglevel = DEBUGLEVEL;
+#endif
diff --git a/lib/zstd/common/debug.h b/lib/zstd/common/debug.h
index 6dd88d1fbd02..c8a10281f112 100644
--- a/lib/zstd/common/debug.h
+++ b/lib/zstd/common/debug.h
@@ -1,7 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0+ OR BSD-3-Clause */
 /* ******************************************************************
  * debug
  * Part of FSE library
- * Copyright (c) Yann Collet, Facebook, Inc.
+ * Copyright (c) Meta Platforms, Inc. and affiliates.
  *
  * You can contact the author at :
  * - Source repository : https://github.com/Cyan4973/FiniteStateEntropy
@@ -33,7 +34,6 @@
 #define DEBUG_H_12987983217
 
 
-
 /* static assert is triggered at compile time, leaving no runtime artefact.
  * static assert only works with compile-time constants.
  * Also, this variant can only be used inside a function. */
@@ -82,20 +82,27 @@ extern int g_debuglevel; /* the variable is only declared,
                             It's useful when enabling very verbose levels
                             on selective conditions (such as position in src) */
 
-#  define RAWLOG(l, ...) {                                       \
-                if (l<=g_debuglevel) {                           \
-                    ZSTD_DEBUG_PRINT(__VA_ARGS__);               \
-            }   }
-#  define DEBUGLOG(l, ...) {                                     \
-                if (l<=g_debuglevel) {                           \
-                    ZSTD_DEBUG_PRINT(__FILE__ ": " __VA_ARGS__); \
-                    ZSTD_DEBUG_PRINT(" \n");                     \
-            }   }
+#  define RAWLOG(l, ...)                   \
+    do {                                   \
+        if (l<=g_debuglevel) {             \
+            ZSTD_DEBUG_PRINT(__VA_ARGS__); \
+        }                                  \
+    } while (0)
+
+#define STRINGIFY(x) #x
+#define TOSTRING(x) STRINGIFY(x)
+#define LINE_AS_STRING TOSTRING(__LINE__)
+
+#  define DEBUGLOG(l, ...)                               \
+    do {                                                 \
+        if (l<=g_debuglevel) {                           \
+            ZSTD_DEBUG_PRINT(__FILE__ ":" LINE_AS_STRING ": " __VA_ARGS__); \
+            ZSTD_DEBUG_PRINT(" \n");                     \
+        }                                                \
+    } while (0)
 #else
-#  define RAWLOG(l, ...)      {}    /* disabled */
-#  define DEBUGLOG(l, ...)    {}    /* disabled */
+#  define RAWLOG(l, ...)   do { } while (0)    /* disabled */
+#  define DEBUGLOG(l, ...) do { } while (0)    /* disabled */
 #endif
 
-
-
 #endif /* DEBUG_H_12987983217 */
diff --git a/lib/zstd/common/entropy_common.c b/lib/zstd/common/entropy_common.c
index fef67056f052..6cdd82233fb5 100644
--- a/lib/zstd/common/entropy_common.c
+++ b/lib/zstd/common/entropy_common.c
@@ -1,6 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0+ OR BSD-3-Clause
 /* ******************************************************************
  * Common functions of New Generation Entropy library
- * Copyright (c) Yann Collet, Facebook, Inc.
+ * Copyright (c) Meta Platforms, Inc. and affiliates.
  *
  *  You can contact the author at :
  *  - FSE+HUF source repository : https://github.com/Cyan4973/FiniteStateEntropy
@@ -19,8 +20,8 @@
 #include "error_private.h"       /* ERR_*, ERROR */
 #define FSE_STATIC_LINKING_ONLY  /* FSE_MIN_TABLELOG */
 #include "fse.h"
-#define HUF_STATIC_LINKING_ONLY  /* HUF_TABLELOG_ABSOLUTEMAX */
 #include "huf.h"
+#include "bits.h"                /* ZSDT_highbit32, ZSTD_countTrailingZeros32 */
 
 
 /*===   Version   ===*/
@@ -38,23 +39,6 @@ const char* HUF_getErrorName(size_t code) { return ERR_getErrorName(code); }
 /*-**************************************************************
 *  FSE NCount encoding-decoding
 ****************************************************************/
-static U32 FSE_ctz(U32 val)
-{
-    assert(val != 0);
-    {
-#   if (__GNUC__ >= 3)   /* GCC Intrinsic */
-        return __builtin_ctz(val);
-#   else   /* Software version */
-        U32 count = 0;
-        while ((val & 1) == 0) {
-            val >>= 1;
-            ++count;
-        }
-        return count;
-#   endif
-    }
-}
-
 FORCE_INLINE_TEMPLATE
 size_t FSE_readNCount_body(short* normalizedCounter, unsigned* maxSVPtr, unsigned* tableLogPtr,
                            const void* headerBuffer, size_t hbSize)
@@ -102,7 +86,7 @@ size_t FSE_readNCount_body(short* normalizedCounter, unsigned* maxSVPtr, unsigne
              * repeat.
              * Avoid UB by setting the high bit to 1.
              */
-            int repeats = FSE_ctz(~bitStream | 0x80000000) >> 1;
+            int repeats = ZSTD_countTrailingZeros32(~bitStream | 0x80000000) >> 1;
             while (repeats >= 12) {
                 charnum += 3 * 12;
                 if (LIKELY(ip <= iend-7)) {
@@ -113,7 +97,7 @@ size_t FSE_readNCount_body(short* normalizedCounter, unsigned* maxSVPtr, unsigne
                     ip = iend - 4;
                 }
                 bitStream = MEM_readLE32(ip) >> bitCount;
-                repeats = FSE_ctz(~bitStream | 0x80000000) >> 1;
+                repeats = ZSTD_countTrailingZeros32(~bitStream | 0x80000000) >> 1;
             }
             charnum += 3 * repeats;
             bitStream >>= 2 * repeats;
@@ -178,7 +162,7 @@ size_t FSE_readNCount_body(short* normalizedCounter, unsigned* maxSVPtr, unsigne
                  * know that threshold > 1.
                  */
                 if (remaining <= 1) break;
-                nbBits = BIT_highbit32(remaining) + 1;
+                nbBits = ZSTD_highbit32(remaining) + 1;
                 threshold = 1 << (nbBits - 1);
             }
             if (charnum >= maxSV1) break;
@@ -253,7 +237,7 @@ size_t HUF_readStats(BYTE* huffWeight, size_t hwSize, U32* rankStats,
                      const void* src, size_t srcSize)
 {
     U32 wksp[HUF_READ_STATS_WORKSPACE_SIZE_U32];
-    return HUF_readStats_wksp(huffWeight, hwSize, rankStats, nbSymbolsPtr, tableLogPtr, src, srcSize, wksp, sizeof(wksp), /* bmi2 */ 0);
+    return HUF_readStats_wksp(huffWeight, hwSize, rankStats, nbSymbolsPtr, tableLogPtr, src, srcSize, wksp, sizeof(wksp), /* flags */ 0);
 }
 
 FORCE_INLINE_TEMPLATE size_t
@@ -301,14 +285,14 @@ HUF_readStats_body(BYTE* huffWeight, size_t hwSize, U32* rankStats,
     if (weightTotal == 0) return ERROR(corruption_detected);
 
     /* get last non-null symbol weight (implied, total must be 2^n) */
-    {   U32 const tableLog = BIT_highbit32(weightTotal) + 1;
+    {   U32 const tableLog = ZSTD_highbit32(weightTotal) + 1;
         if (tableLog > HUF_TABLELOG_MAX) return ERROR(corruption_detected);
         *tableLogPtr = tableLog;
         /* determine last weight */
         {   U32 const total = 1 << tableLog;
             U32 const rest = total - weightTotal;
-            U32 const verif = 1 << BIT_highbit32(rest);
-            U32 const lastWeight = BIT_highbit32(rest) + 1;
+            U32 const verif = 1 << ZSTD_highbit32(rest);
+            U32 const lastWeight = ZSTD_highbit32(rest) + 1;
             if (verif != rest) return ERROR(corruption_detected);    /* last value must be a clean power of 2 */
             huffWeight[oSize] = (BYTE)lastWeight;
             rankStats[lastWeight]++;
@@ -345,13 +329,13 @@ size_t HUF_readStats_wksp(BYTE* huffWeight, size_t hwSize, U32* rankStats,
                      U32* nbSymbolsPtr, U32* tableLogPtr,
                      const void* src, size_t srcSize,
                      void* workSpace, size_t wkspSize,
-                     int bmi2)
+                     int flags)
 {
 #if DYNAMIC_BMI2
-    if (bmi2) {
+    if (flags & HUF_flags_bmi2) {
         return HUF_readStats_body_bmi2(huffWeight, hwSize, rankStats, nbSymbolsPtr, tableLogPtr, src, srcSize, workSpace, wkspSize);
     }
 #endif
-    (void)bmi2;
+    (void)flags;
     return HUF_readStats_body_default(huffWeight, hwSize, rankStats, nbSymbolsPtr, tableLogPtr, src, srcSize, workSpace, wkspSize);
 }
diff --git a/lib/zstd/common/error_private.c b/lib/zstd/common/error_private.c
index 6d1135f8c373..6c3dbad838b6 100644
--- a/lib/zstd/common/error_private.c
+++ b/lib/zstd/common/error_private.c
@@ -1,5 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0+ OR BSD-3-Clause
 /*
- * Copyright (c) Yann Collet, Facebook, Inc.
+ * Copyright (c) Meta Platforms, Inc. and affiliates.
  * All rights reserved.
  *
  * This source code is licensed under both the BSD-style license (found in the
@@ -27,9 +28,11 @@ const char* ERR_getErrorString(ERR_enum code)
     case PREFIX(version_unsupported): return "Version not supported";
     case PREFIX(frameParameter_unsupported): return "Unsupported frame parameter";
     case PREFIX(frameParameter_windowTooLarge): return "Frame requires too much memory for decoding";
-    case PREFIX(corruption_detected): return "Corrupted block detected";
+    case PREFIX(corruption_detected): return "Data corruption detected";
     case PREFIX(checksum_wrong): return "Restored data doesn't match checksum";
+    case PREFIX(literals_headerWrong): return "Header of Literals' block doesn't respect format specification";
     case PREFIX(parameter_unsupported): return "Unsupported parameter";
+    case PREFIX(parameter_combination_unsupported): return "Unsupported combination of parameters";
     case PREFIX(parameter_outOfBound): return "Parameter is out of bound";
     case PREFIX(init_missing): return "Context should be init first";
     case PREFIX(memory_allocation): return "Allocation error : not enough memory";
@@ -38,17 +41,23 @@ const char* ERR_getErrorString(ERR_enum code)
     case PREFIX(tableLog_tooLarge): return "tableLog requires too much memory : unsupported";
     case PREFIX(maxSymbolValue_tooLarge): return "Unsupported max Symbol Value : too large";
     case PREFIX(maxSymbolValue_tooSmall): return "Specified maxSymbolValue is too small";
+    case PREFIX(cannotProduce_uncompressedBlock): return "This mode cannot generate an uncompressed block";
+    case PREFIX(stabilityCondition_notRespected): return "pledged buffer stability condition is not respected";
     case PREFIX(dictionary_corrupted): return "Dictionary is corrupted";
     case PREFIX(dictionary_wrong): return "Dictionary mismatch";
     case PREFIX(dictionaryCreation_failed): return "Cannot create Dictionary from provided samples";
     case PREFIX(dstSize_tooSmall): return "Destination buffer is too small";
     case PREFIX(srcSize_wrong): return "Src size is incorrect";
     case PREFIX(dstBuffer_null): return "Operation on NULL destination buffer";
+    case PREFIX(noForwardProgress_destFull): return "Operation made no progress over multiple calls, due to output buffer being full";
+    case PREFIX(noForwardProgress_inputEmpty): return "Operation made no progress over multiple calls, due to input being empty";
         /* following error codes are not stable and may be removed or changed in a future version */
     case PREFIX(frameIndex_tooLarge): return "Frame index is too large";
     case PREFIX(seekableIO): return "An I/O error occurred when reading/seeking";
     case PREFIX(dstBuffer_wrong): return "Destination buffer is wrong";
     case PREFIX(srcBuffer_wrong): return "Source buffer is wrong";
+    case PREFIX(sequenceProducer_failed): return "Block-level external sequence producer returned an error code";
+    case PREFIX(externalSequences_invalid): return "External sequences are not valid";
     case PREFIX(maxCode):
     default: return notErrorCode;
     }
diff --git a/lib/zstd/common/error_private.h b/lib/zstd/common/error_private.h
index ca5101e542fa..08ee87b68cca 100644
--- a/lib/zstd/common/error_private.h
+++ b/lib/zstd/common/error_private.h
@@ -1,5 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0+ OR BSD-3-Clause */
 /*
- * Copyright (c) Yann Collet, Facebook, Inc.
+ * Copyright (c) Meta Platforms, Inc. and affiliates.
  * All rights reserved.
  *
  * This source code is licensed under both the BSD-style license (found in the
@@ -13,8 +14,6 @@
 #ifndef ERROR_H_MODULE
 #define ERROR_H_MODULE
 
-
-
 /* ****************************************
 *  Dependencies
 ******************************************/
@@ -23,7 +22,6 @@
 #include "debug.h"
 #include "zstd_deps.h"       /* size_t */
 
-
 /* ****************************************
 *  Compiler-specific
 ******************************************/
@@ -49,8 +47,13 @@ ERR_STATIC unsigned ERR_isError(size_t code) { return (code > ERROR(maxCode)); }
 ERR_STATIC ERR_enum ERR_getErrorCode(size_t code) { if (!ERR_isError(code)) return (ERR_enum)0; return (ERR_enum) (0-code); }
 
 /* check and forward error code */
-#define CHECK_V_F(e, f) size_t const e = f; if (ERR_isError(e)) return e
-#define CHECK_F(f)   { CHECK_V_F(_var_err__, f); }
+#define CHECK_V_F(e, f)     \
+    size_t const e = f;     \
+    do {                    \
+        if (ERR_isError(e)) \
+            return e;       \
+    } while (0)
+#define CHECK_F(f)   do { CHECK_V_F(_var_err__, f); } while (0)
 
 
 /*-****************************************
@@ -84,10 +87,12 @@ void _force_has_format_string(const char *format, ...) {
  * We want to force this function invocation to be syntactically correct, but
  * we don't want to force runtime evaluation of its arguments.
  */
-#define _FORCE_HAS_FORMAT_STRING(...) \
-  if (0) { \
-    _force_has_format_string(__VA_ARGS__); \
-  }
+#define _FORCE_HAS_FORMAT_STRING(...)              \
+    do {                                           \
+        if (0) {                                   \
+            _force_has_format_string(__VA_ARGS__); \
+        }                                          \
+    } while (0)
 
 #define ERR_QUOTE(str) #str
 
@@ -98,48 +103,49 @@ void _force_has_format_string(const char *format, ...) {
  * In order to do that (particularly, printing the conditional that failed),
  * this can't just wrap RETURN_ERROR().
  */
-#define RETURN_ERROR_IF(cond, err, ...) \
-  if (cond) { \
-    RAWLOG(3, "%s:%d: ERROR!: check %s failed, returning %s", \
-           __FILE__, __LINE__, ERR_QUOTE(cond), ERR_QUOTE(ERROR(err))); \
-    _FORCE_HAS_FORMAT_STRING(__VA_ARGS__); \
-    RAWLOG(3, ": " __VA_ARGS__); \
-    RAWLOG(3, "\n"); \
-    return ERROR(err); \
-  }
+#define RETURN_ERROR_IF(cond, err, ...)                                        \
+    do {                                                                       \
+        if (cond) {                                                            \
+            RAWLOG(3, "%s:%d: ERROR!: check %s failed, returning %s",          \
+                  __FILE__, __LINE__, ERR_QUOTE(cond), ERR_QUOTE(ERROR(err))); \
+            _FORCE_HAS_FORMAT_STRING(__VA_ARGS__);                             \
+            RAWLOG(3, ": " __VA_ARGS__);                                       \
+            RAWLOG(3, "\n");                                                   \
+            return ERROR(err);                                                 \
+        }                                                                      \
+    } while (0)
 
 /*
  * Unconditionally return the specified error.
  *
  * In debug modes, prints additional information.
  */
-#define RETURN_ERROR(err, ...) \
-  do { \
-    RAWLOG(3, "%s:%d: ERROR!: unconditional check failed, returning %s", \
-           __FILE__, __LINE__, ERR_QUOTE(ERROR(err))); \
-    _FORCE_HAS_FORMAT_STRING(__VA_ARGS__); \
-    RAWLOG(3, ": " __VA_ARGS__); \
-    RAWLOG(3, "\n"); \
-    return ERROR(err); \
-  } while(0);
+#define RETURN_ERROR(err, ...)                                               \
+    do {                                                                     \
+        RAWLOG(3, "%s:%d: ERROR!: unconditional check failed, returning %s", \
+              __FILE__, __LINE__, ERR_QUOTE(ERROR(err)));                    \
+        _FORCE_HAS_FORMAT_STRING(__VA_ARGS__);                               \
+        RAWLOG(3, ": " __VA_ARGS__);                                         \
+        RAWLOG(3, "\n");                                                     \
+        return ERROR(err);                                                   \
+    } while(0)
 
 /*
  * If the provided expression evaluates to an error code, returns that error code.
  *
  * In debug modes, prints additional information.
  */
-#define FORWARD_IF_ERROR(err, ...) \
-  do { \
-    size_t const err_code = (err); \
-    if (ERR_isError(err_code)) { \
-      RAWLOG(3, "%s:%d: ERROR!: forwarding error in %s: %s", \
-             __FILE__, __LINE__, ERR_QUOTE(err), ERR_getErrorName(err_code)); \
-      _FORCE_HAS_FORMAT_STRING(__VA_ARGS__); \
-      RAWLOG(3, ": " __VA_ARGS__); \
-      RAWLOG(3, "\n"); \
-      return err_code; \
-    } \
-  } while(0);
-
+#define FORWARD_IF_ERROR(err, ...)                                                 \
+    do {                                                                           \
+        size_t const err_code = (err);                                             \
+        if (ERR_isError(err_code)) {                                               \
+            RAWLOG(3, "%s:%d: ERROR!: forwarding error in %s: %s",                 \
+                  __FILE__, __LINE__, ERR_QUOTE(err), ERR_getErrorName(err_code)); \
+            _FORCE_HAS_FORMAT_STRING(__VA_ARGS__);                                 \
+            RAWLOG(3, ": " __VA_ARGS__);                                           \
+            RAWLOG(3, "\n");                                                       \
+            return err_code;                                                       \
+        }                                                                          \
+    } while(0)
 
 #endif /* ERROR_H_MODULE */
diff --git a/lib/zstd/common/fse.h b/lib/zstd/common/fse.h
index 4507043b2287..b36ce7a2a8c3 100644
--- a/lib/zstd/common/fse.h
+++ b/lib/zstd/common/fse.h
@@ -1,7 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0+ OR BSD-3-Clause */
 /* ******************************************************************
  * FSE : Finite State Entropy codec
  * Public Prototypes declaration
- * Copyright (c) Yann Collet, Facebook, Inc.
+ * Copyright (c) Meta Platforms, Inc. and affiliates.
  *
  * You can contact the author at :
  * - Source repository : https://github.com/Cyan4973/FiniteStateEntropy
@@ -11,8 +12,6 @@
  * in the COPYING file in the root directory of this source tree).
  * You may select, at your option, one of the above-listed licenses.
 ****************************************************************** */
-
-
 #ifndef FSE_H
 #define FSE_H
 
@@ -22,7 +21,6 @@
 ******************************************/
 #include "zstd_deps.h"    /* size_t, ptrdiff_t */
 
-
 /*-*****************************************
 *  FSE_PUBLIC_API : control library symbols visibility
 ******************************************/
@@ -50,34 +48,6 @@
 FSE_PUBLIC_API unsigned FSE_versionNumber(void);   /*< library version number; to be used when checking dll version */
 
 
-/*-****************************************
-*  FSE simple functions
-******************************************/
-/*! FSE_compress() :
-    Compress content of buffer 'src', of size 'srcSize', into destination buffer 'dst'.
-    'dst' buffer must be already allocated. Compression runs faster is dstCapacity >= FSE_compressBound(srcSize).
-    @return : size of compressed data (<= dstCapacity).
-    Special values : if return == 0, srcData is not compressible => Nothing is stored within dst !!!
-                     if return == 1, srcData is a single byte symbol * srcSize times. Use RLE compression instead.
-                     if FSE_isError(return), compression failed (more details using FSE_getErrorName())
-*/
-FSE_PUBLIC_API size_t FSE_compress(void* dst, size_t dstCapacity,
-                             const void* src, size_t srcSize);
-
-/*! FSE_decompress():
-    Decompress FSE data from buffer 'cSrc', of size 'cSrcSize',
-    into already allocated destination buffer 'dst', of size 'dstCapacity'.
-    @return : size of regenerated data (<= maxDstSize),
-              or an error code, which can be tested using FSE_isError() .
-
-    ** Important ** : FSE_decompress() does not decompress non-compressible nor RLE data !!!
-    Why ? : making this distinction requires a header.
-    Header management is intentionally delegated to the user layer, which can better manage special cases.
-*/
-FSE_PUBLIC_API size_t FSE_decompress(void* dst,  size_t dstCapacity,
-                               const void* cSrc, size_t cSrcSize);
-
-
 /*-*****************************************
 *  Tool functions
 ******************************************/
@@ -89,20 +59,6 @@ FSE_PUBLIC_API const char* FSE_getErrorName(size_t code);   /* provides error co
 
 
 /*-*****************************************
-*  FSE advanced functions
-******************************************/
-/*! FSE_compress2() :
-    Same as FSE_compress(), but allows the selection of 'maxSymbolValue' and 'tableLog'
-    Both parameters can be defined as '0' to mean : use default value
-    @return : size of compressed data
-    Special values : if return == 0, srcData is not compressible => Nothing is stored within cSrc !!!
-                     if return == 1, srcData is a single byte symbol * srcSize times. Use RLE compression.
-                     if FSE_isError(return), it's an error code.
-*/
-FSE_PUBLIC_API size_t FSE_compress2 (void* dst, size_t dstSize, const void* src, size_t srcSize, unsigned maxSymbolValue, unsigned tableLog);
-
-
-/*-*****************************************
 *  FSE detailed API
 ******************************************/
 /*!
@@ -161,8 +117,6 @@ FSE_PUBLIC_API size_t FSE_writeNCount (void* buffer, size_t bufferSize,
 /*! Constructor and Destructor of FSE_CTable.
     Note that FSE_CTable size depends on 'tableLog' and 'maxSymbolValue' */
 typedef unsigned FSE_CTable;   /* don't allocate that. It's only meant to be more restrictive than void* */
-FSE_PUBLIC_API FSE_CTable* FSE_createCTable (unsigned maxSymbolValue, unsigned tableLog);
-FSE_PUBLIC_API void        FSE_freeCTable (FSE_CTable* ct);
 
 /*! FSE_buildCTable():
     Builds `ct`, which must be already allocated, using FSE_createCTable().
@@ -238,23 +192,7 @@ FSE_PUBLIC_API size_t FSE_readNCount_bmi2(short* normalizedCounter,
                            unsigned* maxSymbolValuePtr, unsigned* tableLogPtr,
                            const void* rBuffer, size_t rBuffSize, int bmi2);
 
-/*! Constructor and Destructor of FSE_DTable.
-    Note that its size depends on 'tableLog' */
 typedef unsigned FSE_DTable;   /* don't allocate that. It's just a way to be more restrictive than void* */
-FSE_PUBLIC_API FSE_DTable* FSE_createDTable(unsigned tableLog);
-FSE_PUBLIC_API void        FSE_freeDTable(FSE_DTable* dt);
-
-/*! FSE_buildDTable():
-    Builds 'dt', which must be already allocated, using FSE_createDTable().
-    return : 0, or an errorCode, which can be tested using FSE_isError() */
-FSE_PUBLIC_API size_t FSE_buildDTable (FSE_DTable* dt, const short* normalizedCounter, unsigned maxSymbolValue, unsigned tableLog);
-
-/*! FSE_decompress_usingDTable():
-    Decompress compressed source `cSrc` of size `cSrcSize` using `dt`
-    into `dst` which must be already allocated.
-    @return : size of regenerated data (necessarily <= `dstCapacity`),
-              or an errorCode, which can be tested using FSE_isError() */
-FSE_PUBLIC_API size_t FSE_decompress_usingDTable(void* dst, size_t dstCapacity, const void* cSrc, size_t cSrcSize, const FSE_DTable* dt);
 
 /*!
 Tutorial :
@@ -286,13 +224,11 @@ If there is an error, the function will return an error code, which can be teste
 
 #endif  /* FSE_H */
 
+
 #if !defined(FSE_H_FSE_STATIC_LINKING_ONLY)
 #define FSE_H_FSE_STATIC_LINKING_ONLY
-
-/* *** Dependency *** */
 #include "bitstream.h"
 
-
 /* *****************************************
 *  Static allocation
 *******************************************/
@@ -317,16 +253,6 @@ If there is an error, the function will return an error code, which can be teste
 unsigned FSE_optimalTableLog_internal(unsigned maxTableLog, size_t srcSize, unsigned maxSymbolValue, unsigned minus);
 /*< same as FSE_optimalTableLog(), which used `minus==2` */
 
-/* FSE_compress_wksp() :
- * Same as FSE_compress2(), but using an externally allocated scratch buffer (`workSpace`).
- * FSE_COMPRESS_WKSP_SIZE_U32() provides the minimum size required for `workSpace` as a table of FSE_CTable.
- */
-#define FSE_COMPRESS_WKSP_SIZE_U32(maxTableLog, maxSymbolValue)   ( FSE_CTABLE_SIZE_U32(maxTableLog, maxSymbolValue) + ((maxTableLog > 12) ? (1 << (maxTableLog - 2)) : 1024) )
-size_t FSE_compress_wksp (void* dst, size_t dstSize, const void* src, size_t srcSize, unsigned maxSymbolValue, unsigned tableLog, void* workSpace, size_t wkspSize);
-
-size_t FSE_buildCTable_raw (FSE_CTable* ct, unsigned nbBits);
-/*< build a fake FSE_CTable, designed for a flat distribution, where each symbol uses nbBits */
-
 size_t FSE_buildCTable_rle (FSE_CTable* ct, unsigned char symbolValue);
 /*< build a fake FSE_CTable, designed to compress always the same symbolValue */
 
@@ -344,19 +270,11 @@ size_t FSE_buildCTable_wksp(FSE_CTable* ct, const short* normalizedCounter, unsi
 FSE_PUBLIC_API size_t FSE_buildDTable_wksp(FSE_DTable* dt, const short* normalizedCounter, unsigned maxSymbolValue, unsigned tableLog, void* workSpace, size_t wkspSize);
 /*< Same as FSE_buildDTable(), using an externally allocated `workspace` produced with `FSE_BUILD_DTABLE_WKSP_SIZE_U32(maxSymbolValue)` */
 
-size_t FSE_buildDTable_raw (FSE_DTable* dt, unsigned nbBits);
-/*< build a fake FSE_DTable, designed to read a flat distribution where each symbol uses nbBits */
-
-size_t FSE_buildDTable_rle (FSE_DTable* dt, unsigned char symbolValue);
-/*< build a fake FSE_DTable, designed to always generate the same symbolValue */
-
-#define FSE_DECOMPRESS_WKSP_SIZE_U32(maxTableLog, maxSymbolValue) (FSE_DTABLE_SIZE_U32(maxTableLog) + FSE_BUILD_DTABLE_WKSP_SIZE_U32(maxTableLog, maxSymbolValue) + (FSE_MAX_SYMBOL_VALUE + 1) / 2 + 1)
+#define FSE_DECOMPRESS_WKSP_SIZE_U32(maxTableLog, maxSymbolValue) (FSE_DTABLE_SIZE_U32(maxTableLog) + 1 + FSE_BUILD_DTABLE_WKSP_SIZE_U32(maxTableLog, maxSymbolValue) + (FSE_MAX_SYMBOL_VALUE + 1) / 2 + 1)
 #define FSE_DECOMPRESS_WKSP_SIZE(maxTableLog, maxSymbolValue) (FSE_DECOMPRESS_WKSP_SIZE_U32(maxTableLog, maxSymbolValue) * sizeof(unsigned))
-size_t FSE_decompress_wksp(void* dst, size_t dstCapacity, const void* cSrc, size_t cSrcSize, unsigned maxLog, void* workSpace, size_t wkspSize);
-/*< same as FSE_decompress(), using an externally allocated `workSpace` produced with `FSE_DECOMPRESS_WKSP_SIZE_U32(maxLog, maxSymbolValue)` */
-
 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);
-/*< Same as FSE_decompress_wksp() but with dynamic BMI2 support. Pass 1 if your CPU supports BMI2 or 0 if it doesn't. */
+/*< same as FSE_decompress(), using an externally allocated `workSpace` produced with `FSE_DECOMPRESS_WKSP_SIZE_U32(maxLog, maxSymbolValue)`.
+ * Set bmi2 to 1 if your CPU supports BMI2 or 0 if it doesn't */
 
 typedef enum {
    FSE_repeat_none,  /*< Cannot use the previous table */
@@ -539,20 +457,20 @@ MEM_STATIC void FSE_encodeSymbol(BIT_CStream_t* bitC, FSE_CState_t* statePtr, un
     FSE_symbolCompressionTransform const symbolTT = ((const FSE_symbolCompressionTransform*)(statePtr->symbolTT))[symbol];
     const U16* const stateTable = (const U16*)(statePtr->stateTable);
     U32 const nbBitsOut  = (U32)((statePtr->value + symbolTT.deltaNbBits) >> 16);
-    BIT_addBits(bitC, statePtr->value, nbBitsOut);
+    BIT_addBits(bitC, (BitContainerType)statePtr->value, nbBitsOut);
     statePtr->value = stateTable[ (statePtr->value >> nbBitsOut) + symbolTT.deltaFindState];
 }
 
 MEM_STATIC void FSE_flushCState(BIT_CStream_t* bitC, const FSE_CState_t* statePtr)
 {
-    BIT_addBits(bitC, statePtr->value, statePtr->stateLog);
+    BIT_addBits(bitC, (BitContainerType)statePtr->value, statePtr->stateLog);
     BIT_flushBits(bitC);
 }
 
 
 /* FSE_getMaxNbBits() :
  * Approximate maximum cost of a symbol, in bits.
- * Fractional get rounded up (i.e : a symbol with a normalized frequency of 3 gives the same result as a frequency of 2)
+ * Fractional get rounded up (i.e. a symbol with a normalized frequency of 3 gives the same result as a frequency of 2)
  * note 1 : assume symbolValue is valid (<= maxSymbolValue)
  * note 2 : if freq[symbolValue]==0, @return a fake cost of tableLog+1 bits */
 MEM_STATIC U32 FSE_getMaxNbBits(const void* symbolTTPtr, U32 symbolValue)
@@ -705,7 +623,4 @@ MEM_STATIC unsigned FSE_endOfDState(const FSE_DState_t* DStatePtr)
 
 #define FSE_TABLESTEP(tableSize) (((tableSize)>>1) + ((tableSize)>>3) + 3)
 
-
 #endif /* FSE_STATIC_LINKING_ONLY */
-
-
diff --git a/lib/zstd/common/fse_decompress.c b/lib/zstd/common/fse_decompress.c
index 8dcb8ca39767..15081d8dc607 100644
--- a/lib/zstd/common/fse_decompress.c
+++ b/lib/zstd/common/fse_decompress.c
@@ -1,6 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0+ OR BSD-3-Clause
 /* ******************************************************************
  * FSE : Finite State Entropy decoder
- * Copyright (c) Yann Collet, Facebook, Inc.
+ * Copyright (c) Meta Platforms, Inc. and affiliates.
  *
  *  You can contact the author at :
  *  - FSE source repository : https://github.com/Cyan4973/FiniteStateEntropy
@@ -22,8 +23,8 @@
 #define FSE_STATIC_LINKING_ONLY
 #include "fse.h"
 #include "error_private.h"
-#define ZSTD_DEPS_NEED_MALLOC
-#include "zstd_deps.h"
+#include "zstd_deps.h"  /* ZSTD_memcpy */
+#include "bits.h"       /* ZSTD_highbit32 */
 
 
 /* **************************************************************
@@ -55,19 +56,6 @@
 #define FSE_FUNCTION_NAME(X,Y) FSE_CAT(X,Y)
 #define FSE_TYPE_NAME(X,Y) FSE_CAT(X,Y)
 
-
-/* Function templates */
-FSE_DTable* FSE_createDTable (unsigned tableLog)
-{
-    if (tableLog > FSE_TABLELOG_ABSOLUTE_MAX) tableLog = FSE_TABLELOG_ABSOLUTE_MAX;
-    return (FSE_DTable*)ZSTD_malloc( FSE_DTABLE_SIZE_U32(tableLog) * sizeof (U32) );
-}
-
-void FSE_freeDTable (FSE_DTable* dt)
-{
-    ZSTD_free(dt);
-}
-
 static size_t FSE_buildDTable_internal(FSE_DTable* dt, const short* normalizedCounter, unsigned maxSymbolValue, unsigned tableLog, void* workSpace, size_t wkspSize)
 {
     void* const tdPtr = dt+1;   /* because *dt is unsigned, 32-bits aligned on 32-bits */
@@ -96,7 +84,7 @@ static size_t FSE_buildDTable_internal(FSE_DTable* dt, const short* normalizedCo
                     symbolNext[s] = 1;
                 } else {
                     if (normalizedCounter[s] >= largeLimit) DTableH.fastMode=0;
-                    symbolNext[s] = normalizedCounter[s];
+                    symbolNext[s] = (U16)normalizedCounter[s];
         }   }   }
         ZSTD_memcpy(dt, &DTableH, sizeof(DTableH));
     }
@@ -111,8 +99,7 @@ static size_t FSE_buildDTable_internal(FSE_DTable* dt, const short* normalizedCo
          * all symbols have counts <= 8. We ensure we have 8 bytes at the end of
          * our buffer to handle the over-write.
          */
-        {
-            U64 const add = 0x0101010101010101ull;
+        {   U64 const add = 0x0101010101010101ull;
             size_t pos = 0;
             U64 sv = 0;
             U32 s;
@@ -123,14 +110,13 @@ static size_t FSE_buildDTable_internal(FSE_DTable* dt, const short* normalizedCo
                 for (i = 8; i < n; i += 8) {
                     MEM_write64(spread + pos + i, sv);
                 }
-                pos += n;
-            }
-        }
+                pos += (size_t)n;
+        }   }
         /* Now we spread those positions across the table.
-         * The benefit of doing it in two stages is that we avoid the the
+         * The benefit of doing it in two stages is that we avoid the
          * variable size inner loop, which caused lots of branch misses.
          * Now we can run through all the positions without any branch misses.
-         * We unroll the loop twice, since that is what emperically worked best.
+         * We unroll the loop twice, since that is what empirically worked best.
          */
         {
             size_t position = 0;
@@ -166,7 +152,7 @@ static size_t FSE_buildDTable_internal(FSE_DTable* dt, const short* normalizedCo
         for (u=0; u<tableSize; u++) {
             FSE_FUNCTION_TYPE const symbol = (FSE_FUNCTION_TYPE)(tableDecode[u].symbol);
             U32 const nextState = symbolNext[symbol]++;
-            tableDecode[u].nbBits = (BYTE) (tableLog - BIT_highbit32(nextState) );
+            tableDecode[u].nbBits = (BYTE) (tableLog - ZSTD_highbit32(nextState) );
             tableDecode[u].newState = (U16) ( (nextState << tableDecode[u].nbBits) - tableSize);
     }   }
 
@@ -184,49 +170,6 @@ size_t FSE_buildDTable_wksp(FSE_DTable* dt, const short* normalizedCounter, unsi
 /*-*******************************************************
 *  Decompression (Byte symbols)
 *********************************************************/
-size_t FSE_buildDTable_rle (FSE_DTable* dt, BYTE symbolValue)
-{
-    void* ptr = dt;
-    FSE_DTableHeader* const DTableH = (FSE_DTableHeader*)ptr;
-    void* dPtr = dt + 1;
-    FSE_decode_t* const cell = (FSE_decode_t*)dPtr;
-
-    DTableH->tableLog = 0;
-    DTableH->fastMode = 0;
-
-    cell->newState = 0;
-    cell->symbol = symbolValue;
-    cell->nbBits = 0;
-
-    return 0;
-}
-
-
-size_t FSE_buildDTable_raw (FSE_DTable* dt, unsigned nbBits)
-{
-    void* ptr = dt;
-    FSE_DTableHeader* const DTableH = (FSE_DTableHeader*)ptr;
-    void* dPtr = dt + 1;
-    FSE_decode_t* const dinfo = (FSE_decode_t*)dPtr;
-    const unsigned tableSize = 1 << nbBits;
-    const unsigned tableMask = tableSize - 1;
-    const unsigned maxSV1 = tableMask+1;
-    unsigned s;
-
-    /* Sanity checks */
-    if (nbBits < 1) return ERROR(GENERIC);         /* min size */
-
-    /* Build Decoding Table */
-    DTableH->tableLog = (U16)nbBits;
-    DTableH->fastMode = 1;
-    for (s=0; s<maxSV1; s++) {
-        dinfo[s].newState = 0;
-        dinfo[s].symbol = (BYTE)s;
-        dinfo[s].nbBits = (BYTE)nbBits;
-    }
-
-    return 0;
-}
 
 FORCE_INLINE_TEMPLATE size_t FSE_decompress_usingDTable_generic(
           void* dst, size_t maxDstSize,
@@ -248,6 +191,8 @@ FORCE_INLINE_TEMPLATE size_t FSE_decompress_usingDTable_generic(
     FSE_initDState(&state1, &bitD, dt);
     FSE_initDState(&state2, &bitD, dt);
 
+    RETURN_ERROR_IF(BIT_reloadDStream(&bitD)==BIT_DStream_overflow, corruption_detected, "");
+
 #define FSE_GETSYMBOL(statePtr) fast ? FSE_decodeSymbolFast(statePtr, &bitD) : FSE_decodeSymbol(statePtr, &bitD)
 
     /* 4 symbols per loop */
@@ -287,32 +232,12 @@ FORCE_INLINE_TEMPLATE size_t FSE_decompress_usingDTable_generic(
             break;
     }   }
 
-    return op-ostart;
-}
-
-
-size_t FSE_decompress_usingDTable(void* dst, size_t originalSize,
-                            const void* cSrc, size_t cSrcSize,
-                            const FSE_DTable* dt)
-{
-    const void* ptr = dt;
-    const FSE_DTableHeader* DTableH = (const FSE_DTableHeader*)ptr;
-    const U32 fastMode = DTableH->fastMode;
-
-    /* select fast mode (static) */
-    if (fastMode) return FSE_decompress_usingDTable_generic(dst, originalSize, cSrc, cSrcSize, dt, 1);
-    return FSE_decompress_usingDTable_generic(dst, originalSize, cSrc, cSrcSize, dt, 0);
-}
-
-
-size_t FSE_decompress_wksp(void* dst, size_t dstCapacity, const void* cSrc, size_t cSrcSize, unsigned maxLog, void* workSpace, size_t wkspSize)
-{
-    return FSE_decompress_wksp_bmi2(dst, dstCapacity, cSrc, cSrcSize, maxLog, workSpace, wkspSize, /* bmi2 */ 0);
+    assert(op >= ostart);
+    return (size_t)(op-ostart);
 }
 
 typedef struct {
     short ncount[FSE_MAX_SYMBOL_VALUE + 1];
-    FSE_DTable dtable[]; /* Dynamically sized */
 } FSE_DecompressWksp;
 
 
@@ -327,13 +252,18 @@ FORCE_INLINE_TEMPLATE size_t FSE_decompress_wksp_body(
     unsigned tableLog;
     unsigned maxSymbolValue = FSE_MAX_SYMBOL_VALUE;
     FSE_DecompressWksp* const wksp = (FSE_DecompressWksp*)workSpace;
+    size_t const dtablePos = sizeof(FSE_DecompressWksp) / sizeof(FSE_DTable);
+    FSE_DTable* const dtable = (FSE_DTable*)workSpace + dtablePos;
 
-    DEBUG_STATIC_ASSERT((FSE_MAX_SYMBOL_VALUE + 1) % 2 == 0);
+    FSE_STATIC_ASSERT((FSE_MAX_SYMBOL_VALUE + 1) % 2 == 0);
     if (wkspSize < sizeof(*wksp)) return ERROR(GENERIC);
 
+    /* correct offset to dtable depends on this property */
+    FSE_STATIC_ASSERT(sizeof(FSE_DecompressWksp) % sizeof(FSE_DTable) == 0);
+
     /* normal FSE decoding mode */
-    {
-        size_t const NCountLength = FSE_readNCount_bmi2(wksp->ncount, &maxSymbolValue, &tableLog, istart, cSrcSize, bmi2);
+    {   size_t const NCountLength =
+            FSE_readNCount_bmi2(wksp->ncount, &maxSymbolValue, &tableLog, istart, cSrcSize, bmi2);
         if (FSE_isError(NCountLength)) return NCountLength;
         if (tableLog > maxLog) return ERROR(tableLog_tooLarge);
         assert(NCountLength <= cSrcSize);
@@ -342,19 +272,20 @@ FORCE_INLINE_TEMPLATE size_t FSE_decompress_wksp_body(
     }
 
     if (FSE_DECOMPRESS_WKSP_SIZE(tableLog, maxSymbolValue) > wkspSize) return ERROR(tableLog_tooLarge);
-    workSpace = wksp->dtable + FSE_DTABLE_SIZE_U32(tableLog);
+    assert(sizeof(*wksp) + FSE_DTABLE_SIZE(tableLog) <= wkspSize);
+    workSpace = (BYTE*)workSpace + sizeof(*wksp) + FSE_DTABLE_SIZE(tableLog);
     wkspSize -= sizeof(*wksp) + FSE_DTABLE_SIZE(tableLog);
 
-    CHECK_F( FSE_buildDTable_internal(wksp->dtable, wksp->ncount, maxSymbolValue, tableLog, workSpace, wkspSize) );
+    CHECK_F( FSE_buildDTable_internal(dtable, wksp->ncount, maxSymbolValue, tableLog, workSpace, wkspSize) );
 
     {
-        const void* ptr = wksp->dtable;
+        const void* ptr = dtable;
         const FSE_DTableHeader* DTableH = (const FSE_DTableHeader*)ptr;
         const U32 fastMode = DTableH->fastMode;
 
         /* select fast mode (static) */
-        if (fastMode) return FSE_decompress_usingDTable_generic(dst, dstCapacity, ip, cSrcSize, wksp->dtable, 1);
-        return FSE_decompress_usingDTable_generic(dst, dstCapacity, ip, cSrcSize, wksp->dtable, 0);
+        if (fastMode) return FSE_decompress_usingDTable_generic(dst, dstCapacity, ip, cSrcSize, dtable, 1);
+        return FSE_decompress_usingDTable_generic(dst, dstCapacity, ip, cSrcSize, dtable, 0);
     }
 }
 
@@ -382,9 +313,4 @@ size_t FSE_decompress_wksp_bmi2(void* dst, size_t dstCapacity, const void* cSrc,
     return FSE_decompress_wksp_body_default(dst, dstCapacity, cSrc, cSrcSize, maxLog, workSpace, wkspSize);
 }
 
-
-typedef FSE_DTable DTable_max_t[FSE_DTABLE_SIZE_U32(FSE_MAX_TABLELOG)];
-
-
-
 #endif   /* FSE_COMMONDEFS_ONLY */
diff --git a/lib/zstd/common/huf.h b/lib/zstd/common/huf.h
index 5042ff870308..49736dcd8f49 100644
--- a/lib/zstd/common/huf.h
+++ b/lib/zstd/common/huf.h
@@ -1,7 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0+ OR BSD-3-Clause */
 /* ******************************************************************
  * huff0 huffman codec,
  * part of Finite State Entropy library
- * Copyright (c) Yann Collet, Facebook, Inc.
+ * Copyright (c) Meta Platforms, Inc. and affiliates.
  *
  * You can contact the author at :
  * - Source repository : https://github.com/Cyan4973/FiniteStateEntropy
@@ -12,105 +13,26 @@
  * You may select, at your option, one of the above-listed licenses.
 ****************************************************************** */
 
-
 #ifndef HUF_H_298734234
 #define HUF_H_298734234
 
 /* *** Dependencies *** */
 #include "zstd_deps.h"    /* size_t */
-
-
-/* *** library symbols visibility *** */
-/* Note : when linking with -fvisibility=hidden on gcc, or by default on Visual,
- *        HUF symbols remain "private" (internal symbols for library only).
- *        Set macro FSE_DLL_EXPORT to 1 if you want HUF symbols visible on DLL interface */
-#if defined(FSE_DLL_EXPORT) && (FSE_DLL_EXPORT==1) && defined(__GNUC__) && (__GNUC__ >= 4)
-#  define HUF_PUBLIC_API __attribute__ ((visibility ("default")))
-#elif defined(FSE_DLL_EXPORT) && (FSE_DLL_EXPORT==1)   /* Visual expected */
-#  define HUF_PUBLIC_API __declspec(dllexport)
-#elif defined(FSE_DLL_IMPORT) && (FSE_DLL_IMPORT==1)
-#  define HUF_PUBLIC_API __declspec(dllimport)  /* not required, just to generate faster code (saves a function pointer load from IAT and an indirect jump) */
-#else
-#  define HUF_PUBLIC_API
-#endif
-
-
-/* ========================== */
-/* ***  simple functions  *** */
-/* ========================== */
-
-/* HUF_compress() :
- *  Compress content from buffer 'src', of size 'srcSize', into buffer 'dst'.
- * 'dst' buffer must be already allocated.
- *  Compression runs faster if `dstCapacity` >= HUF_compressBound(srcSize).
- * `srcSize` must be <= `HUF_BLOCKSIZE_MAX` == 128 KB.
- * @return : size of compressed data (<= `dstCapacity`).
- *  Special values : if return == 0, srcData is not compressible => Nothing is stored within dst !!!
- *                   if HUF_isError(return), compression failed (more details using HUF_getErrorName())
- */
-HUF_PUBLIC_API size_t HUF_compress(void* dst, size_t dstCapacity,
-                             const void* src, size_t srcSize);
-
-/* HUF_decompress() :
- *  Decompress HUF data from buffer 'cSrc', of size 'cSrcSize',
- *  into already allocated buffer 'dst', of minimum size 'dstSize'.
- * `originalSize` : **must** be the ***exact*** size of original (uncompressed) data.
- *  Note : in contrast with FSE, HUF_decompress can regenerate
- *         RLE (cSrcSize==1) and uncompressed (cSrcSize==dstSize) data,
- *         because it knows size to regenerate (originalSize).
- * @return : size of regenerated data (== originalSize),
- *           or an error code, which can be tested using HUF_isError()
- */
-HUF_PUBLIC_API size_t HUF_decompress(void* dst,  size_t originalSize,
-                               const void* cSrc, size_t cSrcSize);
-
+#include "mem.h"          /* U32 */
+#define FSE_STATIC_LINKING_ONLY
+#include "fse.h"
 
 /* ***   Tool functions *** */
-#define HUF_BLOCKSIZE_MAX (128 * 1024)                  /*< maximum input size for a single block compressed with HUF_compress */
-HUF_PUBLIC_API size_t HUF_compressBound(size_t size);   /*< maximum compressed size (worst case) */
+#define HUF_BLOCKSIZE_MAX (128 * 1024)   /*< maximum input size for a single block compressed with HUF_compress */
+size_t HUF_compressBound(size_t size);   /*< maximum compressed size (worst case) */
 
 /* Error Management */
-HUF_PUBLIC_API unsigned    HUF_isError(size_t code);       /*< tells if a return value is an error code */
-HUF_PUBLIC_API const char* HUF_getErrorName(size_t code);  /*< provides error code string (useful for debugging) */
+unsigned    HUF_isError(size_t code);       /*< tells if a return value is an error code */
+const char* HUF_getErrorName(size_t code);  /*< provides error code string (useful for debugging) */
 
 
-/* ***   Advanced function   *** */
-
-/* HUF_compress2() :
- *  Same as HUF_compress(), but offers control over `maxSymbolValue` and `tableLog`.
- * `maxSymbolValue` must be <= HUF_SYMBOLVALUE_MAX .
- * `tableLog` must be `<= HUF_TABLELOG_MAX` . */
-HUF_PUBLIC_API size_t HUF_compress2 (void* dst, size_t dstCapacity,
-                               const void* src, size_t srcSize,
-                               unsigned maxSymbolValue, unsigned tableLog);
-
-/* HUF_compress4X_wksp() :
- *  Same as HUF_compress2(), but uses externally allocated `workSpace`.
- * `workspace` must be at least as large as HUF_WORKSPACE_SIZE */
 #define HUF_WORKSPACE_SIZE ((8 << 10) + 512 /* sorting scratch space */)
 #define HUF_WORKSPACE_SIZE_U64 (HUF_WORKSPACE_SIZE / sizeof(U64))
-HUF_PUBLIC_API size_t HUF_compress4X_wksp (void* dst, size_t dstCapacity,
-                                     const void* src, size_t srcSize,
-                                     unsigned maxSymbolValue, unsigned tableLog,
-                                     void* workSpace, size_t wkspSize);
-
-#endif   /* HUF_H_298734234 */
-
-/* ******************************************************************
- *  WARNING !!
- *  The following section contains advanced and experimental definitions
- *  which shall never be used in the context of a dynamic library,
- *  because they are not guaranteed to remain stable in the future.
- *  Only consider them in association with static linking.
- * *****************************************************************/
-#if !defined(HUF_H_HUF_STATIC_LINKING_ONLY)
-#define HUF_H_HUF_STATIC_LINKING_ONLY
-
-/* *** Dependencies *** */
-#include "mem.h"   /* U32 */
-#define FSE_STATIC_LINKING_ONLY
-#include "fse.h"
-
 
 /* *** Constants *** */
 #define HUF_TABLELOG_MAX      12      /* max runtime value of tableLog (due to static allocation); can be modified up to HUF_TABLELOG_ABSOLUTEMAX */
@@ -151,25 +73,49 @@ typedef U32 HUF_DTable;
 /* ****************************************
 *  Advanced decompression functions
 ******************************************/
-size_t HUF_decompress4X1 (void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize);   /*< single-symbol decoder */
-#ifndef HUF_FORCE_DECOMPRESS_X1
-size_t HUF_decompress4X2 (void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize);   /*< double-symbols decoder */
-#endif
 
-size_t HUF_decompress4X_DCtx (HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize);   /*< decodes RLE and uncompressed */
-size_t HUF_decompress4X_hufOnly(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize); /*< considers RLE and uncompressed as errors */
-size_t HUF_decompress4X_hufOnly_wksp(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize); /*< considers RLE and uncompressed as errors */
-size_t HUF_decompress4X1_DCtx(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize);   /*< single-symbol decoder */
-size_t HUF_decompress4X1_DCtx_wksp(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize);   /*< single-symbol decoder */
-#ifndef HUF_FORCE_DECOMPRESS_X1
-size_t HUF_decompress4X2_DCtx(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize);   /*< double-symbols decoder */
-size_t HUF_decompress4X2_DCtx_wksp(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize);   /*< double-symbols decoder */
-#endif
+/*
+ * Huffman flags bitset.
+ * For all flags, 0 is the default value.
+ */
+typedef enum {
+    /*
+     * If compiled with DYNAMIC_BMI2: Set flag only if the CPU supports BMI2 at runtime.
+     * Otherwise: Ignored.
+     */
+    HUF_flags_bmi2 = (1 << 0),
+    /*
+     * If set: Test possible table depths to find the one that produces the smallest header + encoded size.
+     * If unset: Use heuristic to find the table depth.
+     */
+    HUF_flags_optimalDepth = (1 << 1),
+    /*
+     * If set: If the previous table can encode the input, always reuse the previous table.
+     * If unset: If the previous table can encode the input, reuse the previous table if it results in a smaller output.
+     */
+    HUF_flags_preferRepeat = (1 << 2),
+    /*
+     * If set: Sample the input and check if the sample is uncompressible, if it is then don't attempt to compress.
+     * If unset: Always histogram the entire input.
+     */
+    HUF_flags_suspectUncompressible = (1 << 3),
+    /*
+     * If set: Don't use assembly implementations
+     * If unset: Allow using assembly implementations
+     */
+    HUF_flags_disableAsm = (1 << 4),
+    /*
+     * If set: Don't use the fast decoding loop, always use the fallback decoding loop.
+     * If unset: Use the fast decoding loop when possible.
+     */
+    HUF_flags_disableFast = (1 << 5)
+} HUF_flags_e;
 
 
 /* ****************************************
  *  HUF detailed API
  * ****************************************/
+#define HUF_OPTIMAL_DEPTH_THRESHOLD ZSTD_btultra
 
 /*! HUF_compress() does the following:
  *  1. count symbol occurrence from source[] into table count[] using FSE_count() (exposed within "fse.h")
@@ -182,12 +128,12 @@ size_t HUF_decompress4X2_DCtx_wksp(HUF_DTable* dctx, void* dst, size_t dstSize,
  *  For example, it's possible to compress several blocks using the same 'CTable',
  *  or to save and regenerate 'CTable' using external methods.
  */
-unsigned HUF_optimalTableLog(unsigned maxTableLog, size_t srcSize, unsigned maxSymbolValue);
-size_t HUF_buildCTable (HUF_CElt* CTable, const unsigned* count, unsigned maxSymbolValue, unsigned maxNbBits);   /* @return : maxNbBits; CTable and count can overlap. In which case, CTable will overwrite count content */
-size_t HUF_writeCTable (void* dst, size_t maxDstSize, const HUF_CElt* CTable, unsigned maxSymbolValue, unsigned huffLog);
+unsigned HUF_minTableLog(unsigned symbolCardinality);
+unsigned HUF_cardinality(const unsigned* count, unsigned maxSymbolValue);
+unsigned HUF_optimalTableLog(unsigned maxTableLog, size_t srcSize, unsigned maxSymbolValue, void* workSpace,
+ size_t wkspSize, HUF_CElt* table, const unsigned* count, int flags); /* table is used as scratch space for building and testing tables, not a return value */
 size_t HUF_writeCTable_wksp(void* dst, size_t maxDstSize, const HUF_CElt* CTable, unsigned maxSymbolValue, unsigned huffLog, void* workspace, size_t workspaceSize);
-size_t HUF_compress4X_usingCTable(void* dst, size_t dstSize, const void* src, size_t srcSize, const HUF_CElt* CTable);
-size_t HUF_compress4X_usingCTable_bmi2(void* dst, size_t dstSize, const void* src, size_t srcSize, const HUF_CElt* CTable, int bmi2);
+size_t HUF_compress4X_usingCTable(void* dst, size_t dstSize, const void* src, size_t srcSize, const HUF_CElt* CTable, int flags);
 size_t HUF_estimateCompressedSize(const HUF_CElt* CTable, const unsigned* count, unsigned maxSymbolValue);
 int HUF_validateCTable(const HUF_CElt* CTable, const unsigned* count, unsigned maxSymbolValue);
 
@@ -196,6 +142,7 @@ typedef enum {
    HUF_repeat_check, /*< Can use the previous table but it must be checked. Note : The previous table must have been constructed by HUF_compress{1, 4}X_repeat */
    HUF_repeat_valid  /*< Can use the previous table and it is assumed to be valid */
  } HUF_repeat;
+
 /* HUF_compress4X_repeat() :
  *  Same as HUF_compress4X_wksp(), but considers using hufTable if *repeat != HUF_repeat_none.
  *  If it uses hufTable it does not modify hufTable or repeat.
@@ -206,13 +153,13 @@ size_t HUF_compress4X_repeat(void* dst, size_t dstSize,
                        const void* src, size_t srcSize,
                        unsigned maxSymbolValue, unsigned tableLog,
                        void* workSpace, size_t wkspSize,    /*< `workSpace` must be aligned on 4-bytes boundaries, `wkspSize` must be >= HUF_WORKSPACE_SIZE */
-                       HUF_CElt* hufTable, HUF_repeat* repeat, int preferRepeat, int bmi2, unsigned suspectUncompressible);
+                       HUF_CElt* hufTable, HUF_repeat* repeat, int flags);
 
 /* HUF_buildCTable_wksp() :
  *  Same as HUF_buildCTable(), but using externally allocated scratch buffer.
  * `workSpace` must be aligned on 4-bytes boundaries, and its size must be >= HUF_CTABLE_WORKSPACE_SIZE.
  */
-#define HUF_CTABLE_WORKSPACE_SIZE_U32 (2*HUF_SYMBOLVALUE_MAX +1 +1)
+#define HUF_CTABLE_WORKSPACE_SIZE_U32 ((4 * (HUF_SYMBOLVALUE_MAX + 1)) + 192)
 #define HUF_CTABLE_WORKSPACE_SIZE (HUF_CTABLE_WORKSPACE_SIZE_U32 * sizeof(unsigned))
 size_t HUF_buildCTable_wksp (HUF_CElt* tree,
                        const unsigned* count, U32 maxSymbolValue, U32 maxNbBits,
@@ -238,7 +185,7 @@ size_t HUF_readStats_wksp(BYTE* huffWeight, size_t hwSize,
                           U32* rankStats, U32* nbSymbolsPtr, U32* tableLogPtr,
                           const void* src, size_t srcSize,
                           void* workspace, size_t wkspSize,
-                          int bmi2);
+                          int flags);
 
 /* HUF_readCTable() :
  *  Loading a CTable saved with HUF_writeCTable() */
@@ -246,9 +193,22 @@ size_t HUF_readCTable (HUF_CElt* CTable, unsigned* maxSymbolValuePtr, const void
 
 /* HUF_getNbBitsFromCTable() :
  *  Read nbBits from CTable symbolTable, for symbol `symbolValue` presumed <= HUF_SYMBOLVALUE_MAX
- *  Note 1 : is not inlined, as HUF_CElt definition is private */
+ *  Note 1 : If symbolValue > HUF_readCTableHeader(symbolTable).maxSymbolValue, returns 0
+ *  Note 2 : is not inlined, as HUF_CElt definition is private
+ */
 U32 HUF_getNbBitsFromCTable(const HUF_CElt* symbolTable, U32 symbolValue);
 
+typedef struct {
+    BYTE tableLog;
+    BYTE maxSymbolValue;
+    BYTE unused[sizeof(size_t) - 2];
+} HUF_CTableHeader;
+
+/* HUF_readCTableHeader() :
+ *  @returns The header from the CTable specifying the tableLog and the maxSymbolValue.
+ */
+HUF_CTableHeader HUF_readCTableHeader(HUF_CElt const* ctable);
+
 /*
  * HUF_decompress() does the following:
  * 1. select the decompression algorithm (X1, X2) based on pre-computed heuristics
@@ -276,32 +236,12 @@ U32 HUF_selectDecoder (size_t dstSize, size_t cSrcSize);
 #define HUF_DECOMPRESS_WORKSPACE_SIZE ((2 << 10) + (1 << 9))
 #define HUF_DECOMPRESS_WORKSPACE_SIZE_U32 (HUF_DECOMPRESS_WORKSPACE_SIZE / sizeof(U32))
 
-#ifndef HUF_FORCE_DECOMPRESS_X2
-size_t HUF_readDTableX1 (HUF_DTable* DTable, const void* src, size_t srcSize);
-size_t HUF_readDTableX1_wksp (HUF_DTable* DTable, const void* src, size_t srcSize, void* workSpace, size_t wkspSize);
-#endif
-#ifndef HUF_FORCE_DECOMPRESS_X1
-size_t HUF_readDTableX2 (HUF_DTable* DTable, const void* src, size_t srcSize);
-size_t HUF_readDTableX2_wksp (HUF_DTable* DTable, const void* src, size_t srcSize, void* workSpace, size_t wkspSize);
-#endif
-
-size_t HUF_decompress4X_usingDTable(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable);
-#ifndef HUF_FORCE_DECOMPRESS_X2
-size_t HUF_decompress4X1_usingDTable(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable);
-#endif
-#ifndef HUF_FORCE_DECOMPRESS_X1
-size_t HUF_decompress4X2_usingDTable(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable);
-#endif
-
 
 /* ====================== */
 /* single stream variants */
 /* ====================== */
 
-size_t HUF_compress1X (void* dst, size_t dstSize, const void* src, size_t srcSize, unsigned maxSymbolValue, unsigned tableLog);
-size_t HUF_compress1X_wksp (void* dst, size_t dstSize, const void* src, size_t srcSize, unsigned maxSymbolValue, unsigned tableLog, void* workSpace, size_t wkspSize);  /*< `workSpace` must be a table of at least HUF_WORKSPACE_SIZE_U64 U64 */
-size_t HUF_compress1X_usingCTable(void* dst, size_t dstSize, const void* src, size_t srcSize, const HUF_CElt* CTable);
-size_t HUF_compress1X_usingCTable_bmi2(void* dst, size_t dstSize, const void* src, size_t srcSize, const HUF_CElt* CTable, int bmi2);
+size_t HUF_compress1X_usingCTable(void* dst, size_t dstSize, const void* src, size_t srcSize, const HUF_CElt* CTable, int flags);
 /* HUF_compress1X_repeat() :
  *  Same as HUF_compress1X_wksp(), but considers using hufTable if *repeat != HUF_repeat_none.
  *  If it uses hufTable it does not modify hufTable or repeat.
@@ -312,47 +252,27 @@ size_t HUF_compress1X_repeat(void* dst, size_t dstSize,
                        const void* src, size_t srcSize,
                        unsigned maxSymbolValue, unsigned tableLog,
                        void* workSpace, size_t wkspSize,   /*< `workSpace` must be aligned on 4-bytes boundaries, `wkspSize` must be >= HUF_WORKSPACE_SIZE */
-                       HUF_CElt* hufTable, HUF_repeat* repeat, int preferRepeat, int bmi2, unsigned suspectUncompressible);
-
-size_t HUF_decompress1X1 (void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize);   /* single-symbol decoder */
-#ifndef HUF_FORCE_DECOMPRESS_X1
-size_t HUF_decompress1X2 (void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize);   /* double-symbol decoder */
-#endif
-
-size_t HUF_decompress1X_DCtx (HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize);
-size_t HUF_decompress1X_DCtx_wksp (HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize);
-#ifndef HUF_FORCE_DECOMPRESS_X2
-size_t HUF_decompress1X1_DCtx(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize);   /*< single-symbol decoder */
-size_t HUF_decompress1X1_DCtx_wksp(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize);   /*< single-symbol decoder */
-#endif
-#ifndef HUF_FORCE_DECOMPRESS_X1
-size_t HUF_decompress1X2_DCtx(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize);   /*< double-symbols decoder */
-size_t HUF_decompress1X2_DCtx_wksp(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize);   /*< double-symbols decoder */
-#endif
+                       HUF_CElt* hufTable, HUF_repeat* repeat, int flags);
 
-size_t HUF_decompress1X_usingDTable(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable);   /*< automatic selection of sing or double symbol decoder, based on DTable */
-#ifndef HUF_FORCE_DECOMPRESS_X2
-size_t HUF_decompress1X1_usingDTable(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable);
-#endif
+size_t HUF_decompress1X_DCtx_wksp(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize, int flags);
 #ifndef HUF_FORCE_DECOMPRESS_X1
-size_t HUF_decompress1X2_usingDTable(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable);
+size_t HUF_decompress1X2_DCtx_wksp(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize, int flags);   /*< double-symbols decoder */
 #endif
 
 /* BMI2 variants.
  * If the CPU has BMI2 support, pass bmi2=1, otherwise pass bmi2=0.
  */
-size_t HUF_decompress1X_usingDTable_bmi2(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable, int bmi2);
+size_t HUF_decompress1X_usingDTable(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable, int flags);
 #ifndef HUF_FORCE_DECOMPRESS_X2
-size_t HUF_decompress1X1_DCtx_wksp_bmi2(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize, int bmi2);
+size_t HUF_decompress1X1_DCtx_wksp(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize, int flags);
 #endif
-size_t HUF_decompress4X_usingDTable_bmi2(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable, int bmi2);
-size_t HUF_decompress4X_hufOnly_wksp_bmi2(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize, int bmi2);
+size_t HUF_decompress4X_usingDTable(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable, int flags);
+size_t HUF_decompress4X_hufOnly_wksp(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize, int flags);
 #ifndef HUF_FORCE_DECOMPRESS_X2
-size_t HUF_readDTableX1_wksp_bmi2(HUF_DTable* DTable, const void* src, size_t srcSize, void* workSpace, size_t wkspSize, int bmi2);
+size_t HUF_readDTableX1_wksp(HUF_DTable* DTable, const void* src, size_t srcSize, void* workSpace, size_t wkspSize, int flags);
 #endif
 #ifndef HUF_FORCE_DECOMPRESS_X1
-size_t HUF_readDTableX2_wksp_bmi2(HUF_DTable* DTable, const void* src, size_t srcSize, void* workSpace, size_t wkspSize, int bmi2);
+size_t HUF_readDTableX2_wksp(HUF_DTable* DTable, const void* src, size_t srcSize, void* workSpace, size_t wkspSize, int flags);
 #endif
 
-#endif /* HUF_STATIC_LINKING_ONLY */
-
+#endif   /* HUF_H_298734234 */
diff --git a/lib/zstd/common/mem.h b/lib/zstd/common/mem.h
index c22a2e69bf46..d9bd752fe17b 100644
--- a/lib/zstd/common/mem.h
+++ b/lib/zstd/common/mem.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0+ OR BSD-3-Clause */
 /*
- * Copyright (c) Yann Collet, Facebook, Inc.
+ * Copyright (c) Meta Platforms, Inc. and affiliates.
  * All rights reserved.
  *
  * This source code is licensed under both the BSD-style license (found in the
@@ -24,6 +24,7 @@
 /*-****************************************
 *  Compiler specifics
 ******************************************/
+#undef MEM_STATIC /* may be already defined from common/compiler.h */
 #define MEM_STATIC static inline
 
 /*-**************************************************************
diff --git a/lib/zstd/common/portability_macros.h b/lib/zstd/common/portability_macros.h
index 0e3b2c0a527d..05286af72683 100644
--- a/lib/zstd/common/portability_macros.h
+++ b/lib/zstd/common/portability_macros.h
@@ -1,5 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0+ OR BSD-3-Clause */
 /*
- * Copyright (c) Facebook, Inc.
+ * Copyright (c) Meta Platforms, Inc. and affiliates.
  * All rights reserved.
  *
  * This source code is licensed under both the BSD-style license (found in the
@@ -12,7 +13,7 @@
 #define ZSTD_PORTABILITY_MACROS_H
 
 /*
- * This header file contains macro defintions to support portability.
+ * This header file contains macro definitions to support portability.
  * This header is shared between C and ASM code, so it MUST only
  * contain macro definitions. It MUST not contain any C code.
  *
@@ -45,30 +46,35 @@
 /* Mark the internal assembly functions as hidden  */
 #ifdef __ELF__
 # define ZSTD_HIDE_ASM_FUNCTION(func) .hidden func
+#elif defined(__APPLE__)
+# define ZSTD_HIDE_ASM_FUNCTION(func) .private_extern func
 #else
 # define ZSTD_HIDE_ASM_FUNCTION(func)
 #endif
 
+/* Compile time determination of BMI2 support */
+
+
 /* Enable runtime BMI2 dispatch based on the CPU.
  * Enabled for clang & gcc >=4.8 on x86 when BMI2 isn't enabled by default.
  */
 #ifndef DYNAMIC_BMI2
-  #if ((defined(__clang__) && __has_attribute(__target__)) \
+#  if ((defined(__clang__) && __has_attribute(__target__)) \
       || (defined(__GNUC__) \
           && (__GNUC__ >= 5 || (__GNUC__ == 4 && __GNUC_MINOR__ >= 8)))) \
-      && (defined(__x86_64__) || defined(_M_X64)) \
+      && (defined(__i386__) || defined(__x86_64__) || defined(_M_IX86) || defined(_M_X64)) \
       && !defined(__BMI2__)
-  #  define DYNAMIC_BMI2 1
-  #else
-  #  define DYNAMIC_BMI2 0
-  #endif
+#    define DYNAMIC_BMI2 1
+#  else
+#    define DYNAMIC_BMI2 0
+#  endif
 #endif
 
 /*
- * Only enable assembly for GNUC comptabile compilers,
+ * Only enable assembly for GNU C compatible compilers,
  * because other platforms may not support GAS assembly syntax.
  *
- * Only enable assembly for Linux / MacOS, other platforms may
+ * Only enable assembly for Linux / MacOS / Win32, other platforms may
  * work, but they haven't been tested. This could likely be
  * extended to BSD systems.
  *
@@ -90,4 +96,23 @@
  */
 #define ZSTD_ENABLE_ASM_X86_64_BMI2 0
 
+/*
+ * For x86 ELF targets, add .note.gnu.property section for Intel CET in
+ * assembly sources when CET is enabled.
+ *
+ * Additionally, any function that may be called indirectly must begin
+ * with ZSTD_CET_ENDBRANCH.
+ */
+#if defined(__ELF__) && (defined(__x86_64__) || defined(__i386__)) \
+    && defined(__has_include)
+# if __has_include(<cet.h>)
+#  include <cet.h>
+#  define ZSTD_CET_ENDBRANCH _CET_ENDBR
+# endif
+#endif
+
+#ifndef ZSTD_CET_ENDBRANCH
+# define ZSTD_CET_ENDBRANCH
+#endif
+
 #endif /* ZSTD_PORTABILITY_MACROS_H */
diff --git a/lib/zstd/common/zstd_common.c b/lib/zstd/common/zstd_common.c
index 3d7e35b309b5..44b95b25344a 100644
--- a/lib/zstd/common/zstd_common.c
+++ b/lib/zstd/common/zstd_common.c
@@ -1,5 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0+ OR BSD-3-Clause
 /*
- * Copyright (c) Yann Collet, Facebook, Inc.
+ * Copyright (c) Meta Platforms, Inc. and affiliates.
  * All rights reserved.
  *
  * This source code is licensed under both the BSD-style license (found in the
@@ -14,7 +15,6 @@
 *  Dependencies
 ***************************************/
 #define ZSTD_DEPS_NEED_MALLOC
-#include "zstd_deps.h"   /* ZSTD_malloc, ZSTD_calloc, ZSTD_free, ZSTD_memset */
 #include "error_private.h"
 #include "zstd_internal.h"
 
@@ -47,37 +47,3 @@ ZSTD_ErrorCode ZSTD_getErrorCode(size_t code) { return ERR_getErrorCode(code); }
 /*! ZSTD_getErrorString() :
  *  provides error code string from enum */
 const char* ZSTD_getErrorString(ZSTD_ErrorCode code) { return ERR_getErrorString(code); }
-
-
-
-/*=**************************************************************
-*  Custom allocator
-****************************************************************/
-void* ZSTD_customMalloc(size_t size, ZSTD_customMem customMem)
-{
-    if (customMem.customAlloc)
-        return customMem.customAlloc(customMem.opaque, size);
-    return ZSTD_malloc(size);
-}
-
-void* ZSTD_customCalloc(size_t size, ZSTD_customMem customMem)
-{
-    if (customMem.customAlloc) {
-        /* calloc implemented as malloc+memset;
-         * not as efficient as calloc, but next best guess for custom malloc */
-        void* const ptr = customMem.customAlloc(customMem.opaque, size);
-        ZSTD_memset(ptr, 0, size);
-        return ptr;
-    }
-    return ZSTD_calloc(1, size);
-}
-
-void ZSTD_customFree(void* ptr, ZSTD_customMem customMem)
-{
-    if (ptr!=NULL) {
-        if (customMem.customFree)
-            customMem.customFree(customMem.opaque, ptr);
-        else
-            ZSTD_free(ptr);
-    }
-}
diff --git a/lib/zstd/common/zstd_deps.h b/lib/zstd/common/zstd_deps.h
index 2c34e8a33a1c..f931f7d0e294 100644
--- a/lib/zstd/common/zstd_deps.h
+++ b/lib/zstd/common/zstd_deps.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0+ OR BSD-3-Clause */
 /*
- * Copyright (c) Facebook, Inc.
+ * Copyright (c) Meta Platforms, Inc. and affiliates.
  * All rights reserved.
  *
  * This source code is licensed under both the BSD-style license (found in the
@@ -105,3 +105,17 @@ static uint64_t ZSTD_div64(uint64_t dividend, uint32_t divisor) {
 
 #endif /* ZSTD_DEPS_IO */
 #endif /* ZSTD_DEPS_NEED_IO */
+
+/*
+ * Only requested when MSAN is enabled.
+ * Need:
+ * intptr_t
+ */
+#ifdef ZSTD_DEPS_NEED_STDINT
+#ifndef ZSTD_DEPS_STDINT
+#define ZSTD_DEPS_STDINT
+
+/* intptr_t already provided by ZSTD_DEPS_COMMON */
+
+#endif /* ZSTD_DEPS_STDINT */
+#endif /* ZSTD_DEPS_NEED_STDINT */
diff --git a/lib/zstd/common/zstd_internal.h b/lib/zstd/common/zstd_internal.h
index 93305d9b41bb..52a79435caf6 100644
--- a/lib/zstd/common/zstd_internal.h
+++ b/lib/zstd/common/zstd_internal.h
@@ -1,5 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0+ OR BSD-3-Clause */
 /*
- * Copyright (c) Yann Collet, Facebook, Inc.
+ * Copyright (c) Meta Platforms, Inc. and affiliates.
  * All rights reserved.
  *
  * This source code is licensed under both the BSD-style license (found in the
@@ -28,12 +29,10 @@
 #include <linux/zstd.h>
 #define FSE_STATIC_LINKING_ONLY
 #include "fse.h"
-#define HUF_STATIC_LINKING_ONLY
 #include "huf.h"
 #include <linux/xxhash.h>                /* XXH_reset, update, digest */
 #define ZSTD_TRACE 0
 
-
 /* ---- static assert (debug) --- */
 #define ZSTD_STATIC_ASSERT(c) DEBUG_STATIC_ASSERT(c)
 #define ZSTD_isError ERR_isError   /* for inlining */
@@ -83,16 +82,17 @@ typedef enum { bt_raw, bt_rle, bt_compressed, bt_reserved } blockType_e;
 #define ZSTD_FRAMECHECKSUMSIZE 4
 
 #define MIN_SEQUENCES_SIZE 1 /* nbSeq==0 */
-#define MIN_CBLOCK_SIZE (1 /*litCSize*/ + 1 /* RLE or RAW */ + MIN_SEQUENCES_SIZE /* nbSeq==0 */)   /* for a non-null block */
+#define MIN_CBLOCK_SIZE (1 /*litCSize*/ + 1 /* RLE or RAW */)   /* for a non-null block */
+#define MIN_LITERALS_FOR_4_STREAMS 6
 
-#define HufLog 12
-typedef enum { set_basic, set_rle, set_compressed, set_repeat } symbolEncodingType_e;
+typedef enum { set_basic, set_rle, set_compressed, set_repeat } SymbolEncodingType_e;
 
 #define LONGNBSEQ 0x7F00
 
 #define MINMATCH 3
 
 #define Litbits  8
+#define LitHufLog 11
 #define MaxLit ((1<<Litbits) - 1)
 #define MaxML   52
 #define MaxLL   35
@@ -103,6 +103,8 @@ typedef enum { set_basic, set_rle, set_compressed, set_repeat } symbolEncodingTy
 #define LLFSELog    9
 #define OffFSELog   8
 #define MaxFSELog  MAX(MAX(MLFSELog, LLFSELog), OffFSELog)
+#define MaxMLBits 16
+#define MaxLLBits 16
 
 #define ZSTD_MAX_HUF_HEADER_SIZE 128 /* header + <= 127 byte tree description */
 /* Each table cannot take more than #symbols * FSELog bits */
@@ -166,7 +168,7 @@ static void ZSTD_copy8(void* dst, const void* src) {
     ZSTD_memcpy(dst, src, 8);
 #endif
 }
-#define COPY8(d,s) { ZSTD_copy8(d,s); d+=8; s+=8; }
+#define COPY8(d,s) do { ZSTD_copy8(d,s); d+=8; s+=8; } while (0)
 
 /* Need to use memmove here since the literal buffer can now be located within
    the dst buffer. In circumstances where the op "catches up" to where the
@@ -186,7 +188,7 @@ static void ZSTD_copy16(void* dst, const void* src) {
     ZSTD_memcpy(dst, copy16_buf, 16);
 #endif
 }
-#define COPY16(d,s) { ZSTD_copy16(d,s); d+=16; s+=16; }
+#define COPY16(d,s) do { ZSTD_copy16(d,s); d+=16; s+=16; } while (0)
 
 #define WILDCOPY_OVERLENGTH 32
 #define WILDCOPY_VECLEN 16
@@ -215,7 +217,7 @@ void ZSTD_wildcopy(void* dst, const void* src, ptrdiff_t length, ZSTD_overlap_e
     if (ovtype == ZSTD_overlap_src_before_dst && diff < WILDCOPY_VECLEN) {
         /* Handle short offset copies. */
         do {
-            COPY8(op, ip)
+            COPY8(op, ip);
         } while (op < oend);
     } else {
         assert(diff >= WILDCOPY_VECLEN || diff <= -WILDCOPY_VECLEN);
@@ -225,12 +227,6 @@ void ZSTD_wildcopy(void* dst, const void* src, ptrdiff_t length, ZSTD_overlap_e
          * one COPY16() in the first call. Then, do two calls per loop since
          * at that point it is more likely to have a high trip count.
          */
-#ifdef __aarch64__
-        do {
-            COPY16(op, ip);
-        }
-        while (op < oend);
-#else
         ZSTD_copy16(op, ip);
         if (16 >= length) return;
         op += 16;
@@ -240,7 +236,6 @@ void ZSTD_wildcopy(void* dst, const void* src, ptrdiff_t length, ZSTD_overlap_e
             COPY16(op, ip);
         }
         while (op < oend);
-#endif
     }
 }
 
@@ -273,62 +268,6 @@ typedef enum {
 /*-*******************************************
 *  Private declarations
 *********************************************/
-typedef struct seqDef_s {
-    U32 offBase;   /* offBase == Offset + ZSTD_REP_NUM, or repcode 1,2,3 */
-    U16 litLength;
-    U16 mlBase;    /* mlBase == matchLength - MINMATCH */
-} seqDef;
-
-/* Controls whether seqStore has a single "long" litLength or matchLength. See seqStore_t. */
-typedef enum {
-    ZSTD_llt_none = 0,             /* no longLengthType */
-    ZSTD_llt_literalLength = 1,    /* represents a long literal */
-    ZSTD_llt_matchLength = 2       /* represents a long match */
-} ZSTD_longLengthType_e;
-
-typedef struct {
-    seqDef* sequencesStart;
-    seqDef* sequences;      /* ptr to end of sequences */
-    BYTE* litStart;
-    BYTE* lit;              /* ptr to end of literals */
-    BYTE* llCode;
-    BYTE* mlCode;
-    BYTE* ofCode;
-    size_t maxNbSeq;
-    size_t maxNbLit;
-
-    /* longLengthPos and longLengthType to allow us to represent either a single litLength or matchLength
-     * in the seqStore that has a value larger than U16 (if it exists). To do so, we increment
-     * the existing value of the litLength or matchLength by 0x10000.
-     */
-    ZSTD_longLengthType_e   longLengthType;
-    U32                     longLengthPos;  /* Index of the sequence to apply long length modification to */
-} seqStore_t;
-
-typedef struct {
-    U32 litLength;
-    U32 matchLength;
-} ZSTD_sequenceLength;
-
-/*
- * Returns the ZSTD_sequenceLength for the given sequences. It handles the decoding of long sequences
- * indicated by longLengthPos and longLengthType, and adds MINMATCH back to matchLength.
- */
-MEM_STATIC ZSTD_sequenceLength ZSTD_getSequenceLength(seqStore_t const* seqStore, seqDef const* seq)
-{
-    ZSTD_sequenceLength seqLen;
-    seqLen.litLength = seq->litLength;
-    seqLen.matchLength = seq->mlBase + MINMATCH;
-    if (seqStore->longLengthPos == (U32)(seq - seqStore->sequencesStart)) {
-        if (seqStore->longLengthType == ZSTD_llt_literalLength) {
-            seqLen.litLength += 0xFFFF;
-        }
-        if (seqStore->longLengthType == ZSTD_llt_matchLength) {
-            seqLen.matchLength += 0xFFFF;
-        }
-    }
-    return seqLen;
-}
 
 /*
  * Contains the compressed frame size and an upper-bound for the decompressed frame size.
@@ -337,74 +276,11 @@ MEM_STATIC ZSTD_sequenceLength ZSTD_getSequenceLength(seqStore_t const* seqStore
  *          `decompressedBound != ZSTD_CONTENTSIZE_ERROR`
  */
 typedef struct {
+    size_t nbBlocks;
     size_t compressedSize;
     unsigned long long decompressedBound;
 } ZSTD_frameSizeInfo;   /* decompress & legacy */
 
-const seqStore_t* ZSTD_getSeqStore(const ZSTD_CCtx* ctx);   /* compress & dictBuilder */
-void ZSTD_seqToCodes(const seqStore_t* seqStorePtr);   /* compress, dictBuilder, decodeCorpus (shouldn't get its definition from here) */
-
-/* custom memory allocation functions */
-void* ZSTD_customMalloc(size_t size, ZSTD_customMem customMem);
-void* ZSTD_customCalloc(size_t size, ZSTD_customMem customMem);
-void ZSTD_customFree(void* ptr, ZSTD_customMem customMem);
-
-
-MEM_STATIC U32 ZSTD_highbit32(U32 val)   /* compress, dictBuilder, decodeCorpus */
-{
-    assert(val != 0);
-    {
-#   if (__GNUC__ >= 3)   /* GCC Intrinsic */
-        return __builtin_clz (val) ^ 31;
-#   else   /* Software version */
-        static const U32 DeBruijnClz[32] = { 0, 9, 1, 10, 13, 21, 2, 29, 11, 14, 16, 18, 22, 25, 3, 30, 8, 12, 20, 28, 15, 17, 24, 7, 19, 27, 23, 6, 26, 5, 4, 31 };
-        U32 v = val;
-        v |= v >> 1;
-        v |= v >> 2;
-        v |= v >> 4;
-        v |= v >> 8;
-        v |= v >> 16;
-        return DeBruijnClz[(v * 0x07C4ACDDU) >> 27];
-#   endif
-    }
-}
-
-/*
- * Counts the number of trailing zeros of a `size_t`.
- * Most compilers should support CTZ as a builtin. A backup
- * implementation is provided if the builtin isn't supported, but
- * it may not be terribly efficient.
- */
-MEM_STATIC unsigned ZSTD_countTrailingZeros(size_t val)
-{
-    if (MEM_64bits()) {
-#       if (__GNUC__ >= 4)
-            return __builtin_ctzll((U64)val);
-#       else
-            static const int DeBruijnBytePos[64] = {  0,  1,  2,  7,  3, 13,  8, 19,
-                                                      4, 25, 14, 28,  9, 34, 20, 56,
-                                                      5, 17, 26, 54, 15, 41, 29, 43,
-                                                      10, 31, 38, 35, 21, 45, 49, 57,
-                                                      63,  6, 12, 18, 24, 27, 33, 55,
-                                                      16, 53, 40, 42, 30, 37, 44, 48,
-                                                      62, 11, 23, 32, 52, 39, 36, 47,
-                                                      61, 22, 51, 46, 60, 50, 59, 58 };
-            return DeBruijnBytePos[((U64)((val & -(long long)val) * 0x0218A392CDABBD3FULL)) >> 58];
-#       endif
-    } else { /* 32 bits */
-#       if (__GNUC__ >= 3)
-            return __builtin_ctz((U32)val);
-#       else
-            static const int DeBruijnBytePos[32] = {  0,  1, 28,  2, 29, 14, 24,  3,
-                                                     30, 22, 20, 15, 25, 17,  4,  8,
-                                                     31, 27, 13, 23, 21, 19, 16,  7,
-                                                     26, 12, 18,  6, 11,  5, 10,  9 };
-            return DeBruijnBytePos[((U32)((val & -(S32)val) * 0x077CB531U)) >> 27];
-#       endif
-    }
-}
-
-
 /* ZSTD_invalidateRepCodes() :
  * ensures next compression will not use repcodes from previous block.
  * Note : only works with regular variant;
@@ -420,13 +296,13 @@ typedef struct {
 
 /*! ZSTD_getcBlockSize() :
  *  Provides the size of compressed block from block header `src` */
-/* Used by: decompress, fullbench (does not get its definition from here) */
+/*  Used by: decompress, fullbench */
 size_t ZSTD_getcBlockSize(const void* src, size_t srcSize,
                           blockProperties_t* bpPtr);
 
 /*! ZSTD_decodeSeqHeaders() :
  *  decode sequence header from src */
-/* Used by: decompress, fullbench (does not get its definition from here) */
+/*  Used by: zstd_decompress_block, fullbench */
 size_t ZSTD_decodeSeqHeaders(ZSTD_DCtx* dctx, int* nbSeqPtr,
                        const void* src, size_t srcSize);
 
@@ -439,5 +315,4 @@ MEM_STATIC int ZSTD_cpuSupportsBmi2(void)
     return ZSTD_cpuid_bmi1(cpuid) && ZSTD_cpuid_bmi2(cpuid);
 }
 
-
 #endif   /* ZSTD_CCOMMON_H_MODULE */