aboutsummaryrefslogtreecommitdiff
path: root/lib/zstd/common/fse_decompress.c
diff options
context:
space:
mode:
authorLibravatar Linus Torvalds <torvalds@linux-foundation.org>2023-02-21 18:24:12 -0800
committerLibravatar Linus Torvalds <torvalds@linux-foundation.org>2023-02-21 18:24:12 -0800
commit5b7c4cabbb65f5c469464da6c5f614cbd7f730f2 (patch)
treecc5c2d0a898769fd59549594fedb3ee6f84e59a0 /lib/zstd/common/fse_decompress.c
downloadlinux-5b7c4cabbb65f5c469464da6c5f614cbd7f730f2.tar.gz
linux-5b7c4cabbb65f5c469464da6c5f614cbd7f730f2.zip
Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-nextgrafted
Pull networking updates from Jakub Kicinski: "Core: - Add dedicated kmem_cache for typical/small skb->head, avoid having to access struct page at kfree time, and improve memory use. - Introduce sysctl to set default RPS configuration for new netdevs. - Define Netlink protocol specification format which can be used to describe messages used by each family and auto-generate parsers. Add tools for generating kernel data structures and uAPI headers. - Expose all net/core sysctls inside netns. - Remove 4s sleep in netpoll if carrier is instantly detected on boot. - Add configurable limit of MDB entries per port, and port-vlan. - Continue populating drop reasons throughout the stack. - Retire a handful of legacy Qdiscs and classifiers. Protocols: - Support IPv4 big TCP (TSO frames larger than 64kB). - Add IP_LOCAL_PORT_RANGE socket option, to control local port range on socket by socket basis. - Track and report in procfs number of MPTCP sockets used. - Support mixing IPv4 and IPv6 flows in the in-kernel MPTCP path manager. - IPv6: don't check net.ipv6.route.max_size and rely on garbage collection to free memory (similarly to IPv4). - Support Penultimate Segment Pop (PSP) flavor in SRv6 (RFC8986). - ICMP: add per-rate limit counters. - Add support for user scanning requests in ieee802154. - Remove static WEP support. - Support minimal Wi-Fi 7 Extremely High Throughput (EHT) rate reporting. - WiFi 7 EHT channel puncturing support (client & AP). BPF: - Add a rbtree data structure following the "next-gen data structure" precedent set by recently added linked list, that is, by using kfunc + kptr instead of adding a new BPF map type. - Expose XDP hints via kfuncs with initial support for RX hash and timestamp metadata. - Add BPF_F_NO_TUNNEL_KEY extension to bpf_skb_set_tunnel_key to better support decap on GRE tunnel devices not operating in collect metadata. - Improve x86 JIT's codegen for PROBE_MEM runtime error checks. - Remove the need for trace_printk_lock for bpf_trace_printk and bpf_trace_vprintk helpers. - Extend libbpf's bpf_tracing.h support for tracing arguments of kprobes/uprobes and syscall as a special case. - Significantly reduce the search time for module symbols by livepatch and BPF. - Enable cpumasks to be used as kptrs, which is useful for tracing programs tracking which tasks end up running on which CPUs in different time intervals. - Add support for BPF trampoline on s390x and riscv64. - Add capability to export the XDP features supported by the NIC. - Add __bpf_kfunc tag for marking kernel functions as kfuncs. - Add cgroup.memory=nobpf kernel parameter option to disable BPF memory accounting for container environments. Netfilter: - Remove the CLUSTERIP target. It has been marked as obsolete for years, and we still have WARN splats wrt races of the out-of-band /proc interface installed by this target. - Add 'destroy' commands to nf_tables. They are identical to the existing 'delete' commands, but do not return an error if the referenced object (set, chain, rule...) did not exist. Driver API: - Improve cpumask_local_spread() locality to help NICs set the right IRQ affinity on AMD platforms. - Separate C22 and C45 MDIO bus transactions more clearly. - Introduce new DCB table to control DSCP rewrite on egress. - Support configuration of Physical Layer Collision Avoidance (PLCA) Reconciliation Sublayer (RS) (802.3cg-2019). Modern version of shared medium Ethernet. - Support for MAC Merge layer (IEEE 802.3-2018 clause 99). Allowing preemption of low priority frames by high priority frames. - Add support for controlling MACSec offload using netlink SET. - Rework devlink instance refcounts to allow registration and de-registration under the instance lock. Split the code into multiple files, drop some of the unnecessarily granular locks and factor out common parts of netlink operation handling. - Add TX frame aggregation parameters (for USB drivers). - Add a new attr TCA_EXT_WARN_MSG to report TC (offload) warning messages with notifications for debug. - Allow offloading of UDP NEW connections via act_ct. - Add support for per action HW stats in TC. - Support hardware miss to TC action (continue processing in SW from a specific point in the action chain). - Warn if old Wireless Extension user space interface is used with modern cfg80211/mac80211 drivers. Do not support Wireless Extensions for Wi-Fi 7 devices at all. Everyone should switch to using nl80211 interface instead. - Improve the CAN bit timing configuration. Use extack to return error messages directly to user space, update the SJW handling, including the definition of a new default value that will benefit CAN-FD controllers, by increasing their oscillator tolerance. New hardware / drivers: - Ethernet: - nVidia BlueField-3 support (control traffic driver) - Ethernet support for imx93 SoCs - Motorcomm yt8531 gigabit Ethernet PHY - onsemi NCN26000 10BASE-T1S PHY (with support for PLCA) - Microchip LAN8841 PHY (incl. cable diagnostics and PTP) - Amlogic gxl MDIO mux - WiFi: - RealTek RTL8188EU (rtl8xxxu) - Qualcomm Wi-Fi 7 devices (ath12k) - CAN: - Renesas R-Car V4H Drivers: - Bluetooth: - Set Per Platform Antenna Gain (PPAG) for Intel controllers. - Ethernet NICs: - Intel (1G, igc): - support TSN / Qbv / packet scheduling features of i226 model - Intel (100G, ice): - use GNSS subsystem instead of TTY - multi-buffer XDP support - extend support for GPIO pins to E823 devices - nVidia/Mellanox: - update the shared buffer configuration on PFC commands - implement PTP adjphase function for HW offset control - TC support for Geneve and GRE with VF tunnel offload - more efficient crypto key management method - multi-port eswitch support - Netronome/Corigine: - add DCB IEEE support - support IPsec offloading for NFP3800 - Freescale/NXP (enetc): - support XDP_REDIRECT for XDP non-linear buffers - improve reconfig, avoid link flap and waiting for idle - support MAC Merge layer - Other NICs: - sfc/ef100: add basic devlink support for ef100 - ionic: rx_push mode operation (writing descriptors via MMIO) - bnxt: use the auxiliary bus abstraction for RDMA - r8169: disable ASPM and reset bus in case of tx timeout - cpsw: support QSGMII mode for J721e CPSW9G - cpts: support pulse-per-second output - ngbe: add an mdio bus driver - usbnet: optimize usbnet_bh() by avoiding unnecessary queuing - r8152: handle devices with FW with NCM support - amd-xgbe: support 10Mbps, 2.5GbE speeds and rx-adaptation - virtio-net: support multi buffer XDP - virtio/vsock: replace virtio_vsock_pkt with sk_buff - tsnep: XDP support - Ethernet high-speed switches: - nVidia/Mellanox (mlxsw): - add support for latency TLV (in FW control messages) - Microchip (sparx5): - separate explicit and implicit traffic forwarding rules, make the implicit rules always active - add support for egress DSCP rewrite - IS0 VCAP support (Ingress Classification) - IS2 VCAP filters (protos, L3 addrs, L4 ports, flags, ToS etc.) - ES2 VCAP support (Egress Access Control) - support for Per-Stream Filtering and Policing (802.1Q, 8.6.5.1) - Ethernet embedded switches: - Marvell (mv88e6xxx): - add MAB (port auth) offload support - enable PTP receive for mv88e6390 - NXP (ocelot): - support MAC Merge layer - support for the the vsc7512 internal copper phys - Microchip: - lan9303: convert to PHYLINK - lan966x: support TC flower filter statistics - lan937x: PTP support for KSZ9563/KSZ8563 and LAN937x - lan937x: support Credit Based Shaper configuration - ksz9477: support Energy Efficient Ethernet - other: - qca8k: convert to regmap read/write API, use bulk operations - rswitch: Improve TX timestamp accuracy - Intel WiFi (iwlwifi): - EHT (Wi-Fi 7) rate reporting - STEP equalizer support: transfer some STEP (connection to radio on platforms with integrated wifi) related parameters from the BIOS to the firmware. - Qualcomm 802.11ax WiFi (ath11k): - IPQ5018 support - Fine Timing Measurement (FTM) responder role support - channel 177 support - MediaTek WiFi (mt76): - per-PHY LED support - mt7996: EHT (Wi-Fi 7) support - Wireless Ethernet Dispatch (WED) reset support - switch to using page pool allocator - RealTek WiFi (rtw89): - support new version of Bluetooth co-existance - Mobile: - rmnet: support TX aggregation" * tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1872 commits) page_pool: add a comment explaining the fragment counter usage net: ethtool: fix __ethtool_dev_mm_supported() implementation ethtool: pse-pd: Fix double word in comments xsk: add linux/vmalloc.h to xsk.c sefltests: netdevsim: wait for devlink instance after netns removal selftest: fib_tests: Always cleanup before exit net/mlx5e: Align IPsec ASO result memory to be as required by hardware net/mlx5e: TC, Set CT miss to the specific ct action instance net/mlx5e: Rename CHAIN_TO_REG to MAPPED_OBJ_TO_REG net/mlx5: Refactor tc miss handling to a single function net/mlx5: Kconfig: Make tc offload depend on tc skb extension net/sched: flower: Support hardware miss to tc action net/sched: flower: Move filter handle initialization earlier net/sched: cls_api: Support hardware miss to tc action net/sched: Rename user cookie and act cookie sfc: fix builds without CONFIG_RTC_LIB sfc: clean up some inconsistent indentings net/mlx4_en: Introduce flexible array to silence overflow warning net: lan966x: Fix possible deadlock inside PTP net/ulp: Remove redundant ->clone() test in inet_clone_ulp(). ...
Diffstat (limited to '')
-rw-r--r--lib/zstd/common/fse_decompress.c390
1 files changed, 390 insertions, 0 deletions
diff --git a/lib/zstd/common/fse_decompress.c b/lib/zstd/common/fse_decompress.c
new file mode 100644
index 000000000..a0d06095b
--- /dev/null
+++ b/lib/zstd/common/fse_decompress.c
@@ -0,0 +1,390 @@
+/* ******************************************************************
+ * FSE : Finite State Entropy decoder
+ * Copyright (c) Yann Collet, Facebook, Inc.
+ *
+ * You can contact the author at :
+ * - FSE source repository : https://github.com/Cyan4973/FiniteStateEntropy
+ * - Public forum : https://groups.google.com/forum/#!forum/lz4c
+ *
+ * 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.
+****************************************************************** */
+
+
+/* **************************************************************
+* Includes
+****************************************************************/
+#include "debug.h" /* assert */
+#include "bitstream.h"
+#include "compiler.h"
+#define FSE_STATIC_LINKING_ONLY
+#include "fse.h"
+#include "error_private.h"
+#define ZSTD_DEPS_NEED_MALLOC
+#include "zstd_deps.h"
+
+
+/* **************************************************************
+* Error Management
+****************************************************************/
+#define FSE_isError ERR_isError
+#define FSE_STATIC_ASSERT(c) DEBUG_STATIC_ASSERT(c) /* use only *after* variable declarations */
+
+
+/* **************************************************************
+* Templates
+****************************************************************/
+/*
+ designed to be included
+ for type-specific functions (template emulation in C)
+ Objective is to write these functions only once, for improved maintenance
+*/
+
+/* safety checks */
+#ifndef FSE_FUNCTION_EXTENSION
+# error "FSE_FUNCTION_EXTENSION must be defined"
+#endif
+#ifndef FSE_FUNCTION_TYPE
+# error "FSE_FUNCTION_TYPE must be defined"
+#endif
+
+/* Function names */
+#define FSE_CAT(X,Y) X##Y
+#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 */
+ FSE_DECODE_TYPE* const tableDecode = (FSE_DECODE_TYPE*) (tdPtr);
+ U16* symbolNext = (U16*)workSpace;
+ BYTE* spread = (BYTE*)(symbolNext + maxSymbolValue + 1);
+
+ U32 const maxSV1 = maxSymbolValue + 1;
+ U32 const tableSize = 1 << tableLog;
+ U32 highThreshold = tableSize-1;
+
+ /* Sanity Checks */
+ if (FSE_BUILD_DTABLE_WKSP_SIZE(tableLog, maxSymbolValue) > wkspSize) return ERROR(maxSymbolValue_tooLarge);
+ if (maxSymbolValue > FSE_MAX_SYMBOL_VALUE) return ERROR(maxSymbolValue_tooLarge);
+ if (tableLog > FSE_MAX_TABLELOG) return ERROR(tableLog_tooLarge);
+
+ /* Init, lay down lowprob symbols */
+ { FSE_DTableHeader DTableH;
+ DTableH.tableLog = (U16)tableLog;
+ DTableH.fastMode = 1;
+ { S16 const largeLimit= (S16)(1 << (tableLog-1));
+ U32 s;
+ for (s=0; s<maxSV1; s++) {
+ if (normalizedCounter[s]==-1) {
+ tableDecode[highThreshold--].symbol = (FSE_FUNCTION_TYPE)s;
+ symbolNext[s] = 1;
+ } else {
+ if (normalizedCounter[s] >= largeLimit) DTableH.fastMode=0;
+ symbolNext[s] = normalizedCounter[s];
+ } } }
+ ZSTD_memcpy(dt, &DTableH, sizeof(DTableH));
+ }
+
+ /* Spread symbols */
+ if (highThreshold == tableSize - 1) {
+ size_t const tableMask = tableSize-1;
+ size_t const step = FSE_TABLESTEP(tableSize);
+ /* First lay down the symbols in order.
+ * We use a uint64_t to lay down 8 bytes at a time. This reduces branch
+ * misses since small blocks generally have small table logs, so nearly
+ * 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;
+ size_t pos = 0;
+ U64 sv = 0;
+ U32 s;
+ for (s=0; s<maxSV1; ++s, sv += add) {
+ int i;
+ int const n = normalizedCounter[s];
+ MEM_write64(spread + pos, sv);
+ for (i = 8; i < n; i += 8) {
+ MEM_write64(spread + pos + i, sv);
+ }
+ pos += n;
+ }
+ }
+ /* Now we spread those positions across the table.
+ * The benefit of doing it in two stages is that we avoid the 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.
+ */
+ {
+ size_t position = 0;
+ size_t s;
+ size_t const unroll = 2;
+ assert(tableSize % unroll == 0); /* FSE_MIN_TABLELOG is 5 */
+ for (s = 0; s < (size_t)tableSize; s += unroll) {
+ size_t u;
+ for (u = 0; u < unroll; ++u) {
+ size_t const uPosition = (position + (u * step)) & tableMask;
+ tableDecode[uPosition].symbol = spread[s + u];
+ }
+ position = (position + (unroll * step)) & tableMask;
+ }
+ assert(position == 0);
+ }
+ } else {
+ U32 const tableMask = tableSize-1;
+ U32 const step = FSE_TABLESTEP(tableSize);
+ U32 s, position = 0;
+ for (s=0; s<maxSV1; s++) {
+ int i;
+ for (i=0; i<normalizedCounter[s]; i++) {
+ tableDecode[position].symbol = (FSE_FUNCTION_TYPE)s;
+ position = (position + step) & tableMask;
+ while (position > highThreshold) position = (position + step) & tableMask; /* lowprob area */
+ } }
+ if (position!=0) return ERROR(GENERIC); /* position must reach all cells once, otherwise normalizedCounter is incorrect */
+ }
+
+ /* Build Decoding table */
+ { U32 u;
+ 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].newState = (U16) ( (nextState << tableDecode[u].nbBits) - tableSize);
+ } }
+
+ return 0;
+}
+
+size_t FSE_buildDTable_wksp(FSE_DTable* dt, const short* normalizedCounter, unsigned maxSymbolValue, unsigned tableLog, void* workSpace, size_t wkspSize)
+{
+ return FSE_buildDTable_internal(dt, normalizedCounter, maxSymbolValue, tableLog, workSpace, wkspSize);
+}
+
+
+#ifndef FSE_COMMONDEFS_ONLY
+
+/*-*******************************************************
+* 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,
+ const void* cSrc, size_t cSrcSize,
+ const FSE_DTable* dt, const unsigned fast)
+{
+ BYTE* const ostart = (BYTE*) dst;
+ BYTE* op = ostart;
+ BYTE* const omax = op + maxDstSize;
+ BYTE* const olimit = omax-3;
+
+ BIT_DStream_t bitD;
+ FSE_DState_t state1;
+ FSE_DState_t state2;
+
+ /* Init */
+ CHECK_F(BIT_initDStream(&bitD, cSrc, cSrcSize));
+
+ FSE_initDState(&state1, &bitD, dt);
+ FSE_initDState(&state2, &bitD, dt);
+
+#define FSE_GETSYMBOL(statePtr) fast ? FSE_decodeSymbolFast(statePtr, &bitD) : FSE_decodeSymbol(statePtr, &bitD)
+
+ /* 4 symbols per loop */
+ for ( ; (BIT_reloadDStream(&bitD)==BIT_DStream_unfinished) & (op<olimit) ; op+=4) {
+ op[0] = FSE_GETSYMBOL(&state1);
+
+ if (FSE_MAX_TABLELOG*2+7 > sizeof(bitD.bitContainer)*8) /* This test must be static */
+ BIT_reloadDStream(&bitD);
+
+ op[1] = FSE_GETSYMBOL(&state2);
+
+ if (FSE_MAX_TABLELOG*4+7 > sizeof(bitD.bitContainer)*8) /* This test must be static */
+ { if (BIT_reloadDStream(&bitD) > BIT_DStream_unfinished) { op+=2; break; } }
+
+ op[2] = FSE_GETSYMBOL(&state1);
+
+ if (FSE_MAX_TABLELOG*2+7 > sizeof(bitD.bitContainer)*8) /* This test must be static */
+ BIT_reloadDStream(&bitD);
+
+ op[3] = FSE_GETSYMBOL(&state2);
+ }
+
+ /* tail */
+ /* note : BIT_reloadDStream(&bitD) >= FSE_DStream_partiallyFilled; Ends at exactly BIT_DStream_completed */
+ while (1) {
+ if (op>(omax-2)) return ERROR(dstSize_tooSmall);
+ *op++ = FSE_GETSYMBOL(&state1);
+ if (BIT_reloadDStream(&bitD)==BIT_DStream_overflow) {
+ *op++ = FSE_GETSYMBOL(&state2);
+ break;
+ }
+
+ if (op>(omax-2)) return ERROR(dstSize_tooSmall);
+ *op++ = FSE_GETSYMBOL(&state2);
+ if (BIT_reloadDStream(&bitD)==BIT_DStream_overflow) {
+ *op++ = FSE_GETSYMBOL(&state1);
+ 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);
+}
+
+typedef struct {
+ short ncount[FSE_MAX_SYMBOL_VALUE + 1];
+ FSE_DTable dtable[1]; /* Dynamically sized */
+} FSE_DecompressWksp;
+
+
+FORCE_INLINE_TEMPLATE size_t FSE_decompress_wksp_body(
+ void* dst, size_t dstCapacity,
+ const void* cSrc, size_t cSrcSize,
+ unsigned maxLog, void* workSpace, size_t wkspSize,
+ int bmi2)
+{
+ const BYTE* const istart = (const BYTE*)cSrc;
+ const BYTE* ip = istart;
+ unsigned tableLog;
+ unsigned maxSymbolValue = FSE_MAX_SYMBOL_VALUE;
+ FSE_DecompressWksp* const wksp = (FSE_DecompressWksp*)workSpace;
+
+ DEBUG_STATIC_ASSERT((FSE_MAX_SYMBOL_VALUE + 1) % 2 == 0);
+ if (wkspSize < sizeof(*wksp)) return ERROR(GENERIC);
+
+ /* normal FSE decoding mode */
+ {
+ 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);
+ ip += NCountLength;
+ cSrcSize -= NCountLength;
+ }
+
+ if (FSE_DECOMPRESS_WKSP_SIZE(tableLog, maxSymbolValue) > wkspSize) return ERROR(tableLog_tooLarge);
+ workSpace = wksp->dtable + FSE_DTABLE_SIZE_U32(tableLog);
+ wkspSize -= sizeof(*wksp) + FSE_DTABLE_SIZE(tableLog);
+
+ CHECK_F( FSE_buildDTable_internal(wksp->dtable, wksp->ncount, maxSymbolValue, tableLog, workSpace, wkspSize) );
+
+ {
+ const void* ptr = wksp->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);
+ }
+}
+
+/* Avoids the FORCE_INLINE of the _body() function. */
+static size_t FSE_decompress_wksp_body_default(void* dst, size_t dstCapacity, const void* cSrc, size_t cSrcSize, unsigned maxLog, void* workSpace, size_t wkspSize)
+{
+ return FSE_decompress_wksp_body(dst, dstCapacity, cSrc, cSrcSize, maxLog, workSpace, wkspSize, 0);
+}
+
+#if DYNAMIC_BMI2
+BMI2_TARGET_ATTRIBUTE static size_t FSE_decompress_wksp_body_bmi2(void* dst, size_t dstCapacity, const void* cSrc, size_t cSrcSize, unsigned maxLog, void* workSpace, size_t wkspSize)
+{
+ return FSE_decompress_wksp_body(dst, dstCapacity, cSrc, cSrcSize, maxLog, workSpace, wkspSize, 1);
+}
+#endif
+
+size_t FSE_decompress_wksp_bmi2(void* dst, size_t dstCapacity, const void* cSrc, size_t cSrcSize, unsigned maxLog, void* workSpace, size_t wkspSize, int bmi2)
+{
+#if DYNAMIC_BMI2
+ if (bmi2) {
+ return FSE_decompress_wksp_body_bmi2(dst, dstCapacity, cSrc, cSrcSize, maxLog, workSpace, wkspSize);
+ }
+#endif
+ (void)bmi2;
+ return FSE_decompress_wksp_body_default(dst, dstCapacity, cSrc, cSrcSize, maxLog, workSpace, wkspSize);
+}
+
+
+typedef FSE_DTable DTable_max_t[FSE_DTABLE_SIZE_U32(FSE_MAX_TABLELOG)];
+
+
+
+#endif /* FSE_COMMONDEFS_ONLY */