diff options
author | 2023-02-21 18:24:12 -0800 | |
---|---|---|
committer | 2023-02-21 18:24:12 -0800 | |
commit | 5b7c4cabbb65f5c469464da6c5f614cbd7f730f2 (patch) | |
tree | cc5c2d0a898769fd59549594fedb3ee6f84e59a0 /lib/zstd/compress/zstd_compress_superblock.c | |
download | linux-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/compress/zstd_compress_superblock.c | 573 |
1 files changed, 573 insertions, 0 deletions
diff --git a/lib/zstd/compress/zstd_compress_superblock.c b/lib/zstd/compress/zstd_compress_superblock.c new file mode 100644 index 000000000..17d836cc8 --- /dev/null +++ b/lib/zstd/compress/zstd_compress_superblock.c @@ -0,0 +1,573 @@ +/* + * Copyright (c) Yann Collet, Facebook, Inc. + * 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. + */ + + /*-************************************* + * Dependencies + ***************************************/ +#include "zstd_compress_superblock.h" + +#include "../common/zstd_internal.h" /* ZSTD_getSequenceLength */ +#include "hist.h" /* HIST_countFast_wksp */ +#include "zstd_compress_internal.h" /* ZSTD_[huf|fse|entropy]CTablesMetadata_t */ +#include "zstd_compress_sequences.h" +#include "zstd_compress_literals.h" + +/* ZSTD_compressSubBlock_literal() : + * Compresses literals section for a sub-block. + * When we have to write the Huffman table we will sometimes choose a header + * size larger than necessary. This is because we have to pick the header size + * before we know the table size + compressed size, so we have a bound on the + * table size. If we guessed incorrectly, we fall back to uncompressed literals. + * + * We write the header when writeEntropy=1 and set entropyWritten=1 when we succeeded + * in writing the header, otherwise it is set to 0. + * + * hufMetadata->hType has literals block type info. + * If it is set_basic, all sub-blocks literals section will be Raw_Literals_Block. + * If it is set_rle, all sub-blocks literals section will be RLE_Literals_Block. + * If it is set_compressed, first sub-block's literals section will be Compressed_Literals_Block + * If it is set_compressed, first sub-block's literals section will be Treeless_Literals_Block + * and the following sub-blocks' literals sections will be Treeless_Literals_Block. + * @return : compressed size of literals section of a sub-block + * Or 0 if it unable to compress. + * Or error code */ +static size_t ZSTD_compressSubBlock_literal(const HUF_CElt* hufTable, + const ZSTD_hufCTablesMetadata_t* hufMetadata, + const BYTE* literals, size_t litSize, + void* dst, size_t dstSize, + const int bmi2, int writeEntropy, int* entropyWritten) +{ + size_t const header = writeEntropy ? 200 : 0; + size_t const lhSize = 3 + (litSize >= (1 KB - header)) + (litSize >= (16 KB - header)); + BYTE* const ostart = (BYTE*)dst; + BYTE* const oend = ostart + dstSize; + BYTE* op = ostart + lhSize; + U32 const singleStream = lhSize == 3; + symbolEncodingType_e hType = writeEntropy ? hufMetadata->hType : set_repeat; + size_t cLitSize = 0; + + (void)bmi2; /* TODO bmi2... */ + + DEBUGLOG(5, "ZSTD_compressSubBlock_literal (litSize=%zu, lhSize=%zu, writeEntropy=%d)", litSize, lhSize, writeEntropy); + + *entropyWritten = 0; + if (litSize == 0 || hufMetadata->hType == set_basic) { + DEBUGLOG(5, "ZSTD_compressSubBlock_literal using raw literal"); + return ZSTD_noCompressLiterals(dst, dstSize, literals, litSize); + } else if (hufMetadata->hType == set_rle) { + DEBUGLOG(5, "ZSTD_compressSubBlock_literal using rle literal"); + return ZSTD_compressRleLiteralsBlock(dst, dstSize, literals, litSize); + } + + assert(litSize > 0); + assert(hufMetadata->hType == set_compressed || hufMetadata->hType == set_repeat); + + if (writeEntropy && hufMetadata->hType == set_compressed) { + ZSTD_memcpy(op, hufMetadata->hufDesBuffer, hufMetadata->hufDesSize); + op += hufMetadata->hufDesSize; + cLitSize += hufMetadata->hufDesSize; + DEBUGLOG(5, "ZSTD_compressSubBlock_literal (hSize=%zu)", hufMetadata->hufDesSize); + } + + /* TODO bmi2 */ + { const size_t cSize = singleStream ? HUF_compress1X_usingCTable(op, oend-op, literals, litSize, hufTable) + : HUF_compress4X_usingCTable(op, oend-op, literals, litSize, hufTable); + op += cSize; + cLitSize += cSize; + if (cSize == 0 || ERR_isError(cSize)) { + DEBUGLOG(5, "Failed to write entropy tables %s", ZSTD_getErrorName(cSize)); + return 0; + } + /* If we expand and we aren't writing a header then emit uncompressed */ + if (!writeEntropy && cLitSize >= litSize) { + DEBUGLOG(5, "ZSTD_compressSubBlock_literal using raw literal because uncompressible"); + return ZSTD_noCompressLiterals(dst, dstSize, literals, litSize); + } + /* If we are writing headers then allow expansion that doesn't change our header size. */ + if (lhSize < (size_t)(3 + (cLitSize >= 1 KB) + (cLitSize >= 16 KB))) { + assert(cLitSize > litSize); + DEBUGLOG(5, "Literals expanded beyond allowed header size"); + return ZSTD_noCompressLiterals(dst, dstSize, literals, litSize); + } + DEBUGLOG(5, "ZSTD_compressSubBlock_literal (cSize=%zu)", cSize); + } + + /* Build header */ + switch(lhSize) + { + case 3: /* 2 - 2 - 10 - 10 */ + { U32 const lhc = hType + ((!singleStream) << 2) + ((U32)litSize<<4) + ((U32)cLitSize<<14); + MEM_writeLE24(ostart, lhc); + break; + } + case 4: /* 2 - 2 - 14 - 14 */ + { U32 const lhc = hType + (2 << 2) + ((U32)litSize<<4) + ((U32)cLitSize<<18); + MEM_writeLE32(ostart, lhc); + break; + } + case 5: /* 2 - 2 - 18 - 18 */ + { U32 const lhc = hType + (3 << 2) + ((U32)litSize<<4) + ((U32)cLitSize<<22); + MEM_writeLE32(ostart, lhc); + ostart[4] = (BYTE)(cLitSize >> 10); + break; + } + default: /* not possible : lhSize is {3,4,5} */ + assert(0); + } + *entropyWritten = 1; + DEBUGLOG(5, "Compressed literals: %u -> %u", (U32)litSize, (U32)(op-ostart)); + return op-ostart; +} + +static size_t ZSTD_seqDecompressedSize(seqStore_t const* seqStore, const seqDef* sequences, size_t nbSeq, size_t litSize, int lastSequence) { + const seqDef* const sstart = sequences; + const seqDef* const send = sequences + nbSeq; + const seqDef* sp = sstart; + size_t matchLengthSum = 0; + size_t litLengthSum = 0; + (void)(litLengthSum); /* suppress unused variable warning on some environments */ + while (send-sp > 0) { + ZSTD_sequenceLength const seqLen = ZSTD_getSequenceLength(seqStore, sp); + litLengthSum += seqLen.litLength; + matchLengthSum += seqLen.matchLength; + sp++; + } + assert(litLengthSum <= litSize); + if (!lastSequence) { + assert(litLengthSum == litSize); + } + return matchLengthSum + litSize; +} + +/* ZSTD_compressSubBlock_sequences() : + * Compresses sequences section for a sub-block. + * fseMetadata->llType, fseMetadata->ofType, and fseMetadata->mlType have + * symbol compression modes for the super-block. + * The first successfully compressed block will have these in its header. + * We set entropyWritten=1 when we succeed in compressing the sequences. + * The following sub-blocks will always have repeat mode. + * @return : compressed size of sequences section of a sub-block + * Or 0 if it is unable to compress + * Or error code. */ +static size_t ZSTD_compressSubBlock_sequences(const ZSTD_fseCTables_t* fseTables, + const ZSTD_fseCTablesMetadata_t* fseMetadata, + const seqDef* sequences, size_t nbSeq, + const BYTE* llCode, const BYTE* mlCode, const BYTE* ofCode, + const ZSTD_CCtx_params* cctxParams, + void* dst, size_t dstCapacity, + const int bmi2, int writeEntropy, int* entropyWritten) +{ + const int longOffsets = cctxParams->cParams.windowLog > STREAM_ACCUMULATOR_MIN; + BYTE* const ostart = (BYTE*)dst; + BYTE* const oend = ostart + dstCapacity; + BYTE* op = ostart; + BYTE* seqHead; + + DEBUGLOG(5, "ZSTD_compressSubBlock_sequences (nbSeq=%zu, writeEntropy=%d, longOffsets=%d)", nbSeq, writeEntropy, longOffsets); + + *entropyWritten = 0; + /* Sequences Header */ + RETURN_ERROR_IF((oend-op) < 3 /*max nbSeq Size*/ + 1 /*seqHead*/, + dstSize_tooSmall, ""); + if (nbSeq < 0x7F) + *op++ = (BYTE)nbSeq; + else if (nbSeq < LONGNBSEQ) + op[0] = (BYTE)((nbSeq>>8) + 0x80), op[1] = (BYTE)nbSeq, op+=2; + else + op[0]=0xFF, MEM_writeLE16(op+1, (U16)(nbSeq - LONGNBSEQ)), op+=3; + if (nbSeq==0) { + return op - ostart; + } + + /* seqHead : flags for FSE encoding type */ + seqHead = op++; + + DEBUGLOG(5, "ZSTD_compressSubBlock_sequences (seqHeadSize=%u)", (unsigned)(op-ostart)); + + if (writeEntropy) { + const U32 LLtype = fseMetadata->llType; + const U32 Offtype = fseMetadata->ofType; + const U32 MLtype = fseMetadata->mlType; + DEBUGLOG(5, "ZSTD_compressSubBlock_sequences (fseTablesSize=%zu)", fseMetadata->fseTablesSize); + *seqHead = (BYTE)((LLtype<<6) + (Offtype<<4) + (MLtype<<2)); + ZSTD_memcpy(op, fseMetadata->fseTablesBuffer, fseMetadata->fseTablesSize); + op += fseMetadata->fseTablesSize; + } else { + const U32 repeat = set_repeat; + *seqHead = (BYTE)((repeat<<6) + (repeat<<4) + (repeat<<2)); + } + + { size_t const bitstreamSize = ZSTD_encodeSequences( + op, oend - op, + fseTables->matchlengthCTable, mlCode, + fseTables->offcodeCTable, ofCode, + fseTables->litlengthCTable, llCode, + sequences, nbSeq, + longOffsets, bmi2); + FORWARD_IF_ERROR(bitstreamSize, "ZSTD_encodeSequences failed"); + op += bitstreamSize; + /* zstd versions <= 1.3.4 mistakenly report corruption when + * FSE_readNCount() receives a buffer < 4 bytes. + * Fixed by https://github.com/facebook/zstd/pull/1146. + * This can happen when the last set_compressed table present is 2 + * bytes and the bitstream is only one byte. + * In this exceedingly rare case, we will simply emit an uncompressed + * block, since it isn't worth optimizing. + */ +#ifndef FUZZING_BUILD_MODE_UNSAFE_FOR_PRODUCTION + if (writeEntropy && fseMetadata->lastCountSize && fseMetadata->lastCountSize + bitstreamSize < 4) { + /* NCountSize >= 2 && bitstreamSize > 0 ==> lastCountSize == 3 */ + assert(fseMetadata->lastCountSize + bitstreamSize == 3); + DEBUGLOG(5, "Avoiding bug in zstd decoder in versions <= 1.3.4 by " + "emitting an uncompressed block."); + return 0; + } +#endif + DEBUGLOG(5, "ZSTD_compressSubBlock_sequences (bitstreamSize=%zu)", bitstreamSize); + } + + /* zstd versions <= 1.4.0 mistakenly report error when + * sequences section body size is less than 3 bytes. + * Fixed by https://github.com/facebook/zstd/pull/1664. + * This can happen when the previous sequences section block is compressed + * with rle mode and the current block's sequences section is compressed + * with repeat mode where sequences section body size can be 1 byte. + */ +#ifndef FUZZING_BUILD_MODE_UNSAFE_FOR_PRODUCTION + if (op-seqHead < 4) { + DEBUGLOG(5, "Avoiding bug in zstd decoder in versions <= 1.4.0 by emitting " + "an uncompressed block when sequences are < 4 bytes"); + return 0; + } +#endif + + *entropyWritten = 1; + return op - ostart; +} + +/* ZSTD_compressSubBlock() : + * Compresses a single sub-block. + * @return : compressed size of the sub-block + * Or 0 if it failed to compress. */ +static size_t ZSTD_compressSubBlock(const ZSTD_entropyCTables_t* entropy, + const ZSTD_entropyCTablesMetadata_t* entropyMetadata, + const seqDef* sequences, size_t nbSeq, + const BYTE* literals, size_t litSize, + const BYTE* llCode, const BYTE* mlCode, const BYTE* ofCode, + const ZSTD_CCtx_params* cctxParams, + void* dst, size_t dstCapacity, + const int bmi2, + int writeLitEntropy, int writeSeqEntropy, + int* litEntropyWritten, int* seqEntropyWritten, + U32 lastBlock) +{ + BYTE* const ostart = (BYTE*)dst; + BYTE* const oend = ostart + dstCapacity; + BYTE* op = ostart + ZSTD_blockHeaderSize; + DEBUGLOG(5, "ZSTD_compressSubBlock (litSize=%zu, nbSeq=%zu, writeLitEntropy=%d, writeSeqEntropy=%d, lastBlock=%d)", + litSize, nbSeq, writeLitEntropy, writeSeqEntropy, lastBlock); + { size_t cLitSize = ZSTD_compressSubBlock_literal((const HUF_CElt*)entropy->huf.CTable, + &entropyMetadata->hufMetadata, literals, litSize, + op, oend-op, bmi2, writeLitEntropy, litEntropyWritten); + FORWARD_IF_ERROR(cLitSize, "ZSTD_compressSubBlock_literal failed"); + if (cLitSize == 0) return 0; + op += cLitSize; + } + { size_t cSeqSize = ZSTD_compressSubBlock_sequences(&entropy->fse, + &entropyMetadata->fseMetadata, + sequences, nbSeq, + llCode, mlCode, ofCode, + cctxParams, + op, oend-op, + bmi2, writeSeqEntropy, seqEntropyWritten); + FORWARD_IF_ERROR(cSeqSize, "ZSTD_compressSubBlock_sequences failed"); + if (cSeqSize == 0) return 0; + op += cSeqSize; + } + /* Write block header */ + { size_t cSize = (op-ostart)-ZSTD_blockHeaderSize; + U32 const cBlockHeader24 = lastBlock + (((U32)bt_compressed)<<1) + (U32)(cSize << 3); + MEM_writeLE24(ostart, cBlockHeader24); + } + return op-ostart; +} + +static size_t ZSTD_estimateSubBlockSize_literal(const BYTE* literals, size_t litSize, + const ZSTD_hufCTables_t* huf, + const ZSTD_hufCTablesMetadata_t* hufMetadata, + void* workspace, size_t wkspSize, + int writeEntropy) +{ + unsigned* const countWksp = (unsigned*)workspace; + unsigned maxSymbolValue = 255; + size_t literalSectionHeaderSize = 3; /* Use hard coded size of 3 bytes */ + + if (hufMetadata->hType == set_basic) return litSize; + else if (hufMetadata->hType == set_rle) return 1; + else if (hufMetadata->hType == set_compressed || hufMetadata->hType == set_repeat) { + size_t const largest = HIST_count_wksp (countWksp, &maxSymbolValue, (const BYTE*)literals, litSize, workspace, wkspSize); + if (ZSTD_isError(largest)) return litSize; + { size_t cLitSizeEstimate = HUF_estimateCompressedSize((const HUF_CElt*)huf->CTable, countWksp, maxSymbolValue); + if (writeEntropy) cLitSizeEstimate += hufMetadata->hufDesSize; + return cLitSizeEstimate + literalSectionHeaderSize; + } } + assert(0); /* impossible */ + return 0; +} + +static size_t ZSTD_estimateSubBlockSize_symbolType(symbolEncodingType_e type, + const BYTE* codeTable, unsigned maxCode, + size_t nbSeq, const FSE_CTable* fseCTable, + const U8* additionalBits, + short const* defaultNorm, U32 defaultNormLog, U32 defaultMax, + void* workspace, size_t wkspSize) +{ + unsigned* const countWksp = (unsigned*)workspace; + const BYTE* ctp = codeTable; + const BYTE* const ctStart = ctp; + const BYTE* const ctEnd = ctStart + nbSeq; + size_t cSymbolTypeSizeEstimateInBits = 0; + unsigned max = maxCode; + + HIST_countFast_wksp(countWksp, &max, codeTable, nbSeq, workspace, wkspSize); /* can't fail */ + if (type == set_basic) { + /* We selected this encoding type, so it must be valid. */ + assert(max <= defaultMax); + cSymbolTypeSizeEstimateInBits = max <= defaultMax + ? ZSTD_crossEntropyCost(defaultNorm, defaultNormLog, countWksp, max) + : ERROR(GENERIC); + } else if (type == set_rle) { + cSymbolTypeSizeEstimateInBits = 0; + } else if (type == set_compressed || type == set_repeat) { + cSymbolTypeSizeEstimateInBits = ZSTD_fseBitCost(fseCTable, countWksp, max); + } + if (ZSTD_isError(cSymbolTypeSizeEstimateInBits)) return nbSeq * 10; + while (ctp < ctEnd) { + if (additionalBits) cSymbolTypeSizeEstimateInBits += additionalBits[*ctp]; + else cSymbolTypeSizeEstimateInBits += *ctp; /* for offset, offset code is also the number of additional bits */ + ctp++; + } + return cSymbolTypeSizeEstimateInBits / 8; +} + +static size_t ZSTD_estimateSubBlockSize_sequences(const BYTE* ofCodeTable, + const BYTE* llCodeTable, + const BYTE* mlCodeTable, + size_t nbSeq, + const ZSTD_fseCTables_t* fseTables, + const ZSTD_fseCTablesMetadata_t* fseMetadata, + void* workspace, size_t wkspSize, + int writeEntropy) +{ + size_t const sequencesSectionHeaderSize = 3; /* Use hard coded size of 3 bytes */ + size_t cSeqSizeEstimate = 0; + if (nbSeq == 0) return sequencesSectionHeaderSize; + cSeqSizeEstimate += ZSTD_estimateSubBlockSize_symbolType(fseMetadata->ofType, ofCodeTable, MaxOff, + nbSeq, fseTables->offcodeCTable, NULL, + OF_defaultNorm, OF_defaultNormLog, DefaultMaxOff, + workspace, wkspSize); + cSeqSizeEstimate += ZSTD_estimateSubBlockSize_symbolType(fseMetadata->llType, llCodeTable, MaxLL, + nbSeq, fseTables->litlengthCTable, LL_bits, + LL_defaultNorm, LL_defaultNormLog, MaxLL, + workspace, wkspSize); + cSeqSizeEstimate += ZSTD_estimateSubBlockSize_symbolType(fseMetadata->mlType, mlCodeTable, MaxML, + nbSeq, fseTables->matchlengthCTable, ML_bits, + ML_defaultNorm, ML_defaultNormLog, MaxML, + workspace, wkspSize); + if (writeEntropy) cSeqSizeEstimate += fseMetadata->fseTablesSize; + return cSeqSizeEstimate + sequencesSectionHeaderSize; +} + +static size_t ZSTD_estimateSubBlockSize(const BYTE* literals, size_t litSize, + const BYTE* ofCodeTable, + const BYTE* llCodeTable, + const BYTE* mlCodeTable, + size_t nbSeq, + const ZSTD_entropyCTables_t* entropy, + const ZSTD_entropyCTablesMetadata_t* entropyMetadata, + void* workspace, size_t wkspSize, + int writeLitEntropy, int writeSeqEntropy) { + size_t cSizeEstimate = 0; + cSizeEstimate += ZSTD_estimateSubBlockSize_literal(literals, litSize, + &entropy->huf, &entropyMetadata->hufMetadata, + workspace, wkspSize, writeLitEntropy); + cSizeEstimate += ZSTD_estimateSubBlockSize_sequences(ofCodeTable, llCodeTable, mlCodeTable, + nbSeq, &entropy->fse, &entropyMetadata->fseMetadata, + workspace, wkspSize, writeSeqEntropy); + return cSizeEstimate + ZSTD_blockHeaderSize; +} + +static int ZSTD_needSequenceEntropyTables(ZSTD_fseCTablesMetadata_t const* fseMetadata) +{ + if (fseMetadata->llType == set_compressed || fseMetadata->llType == set_rle) + return 1; + if (fseMetadata->mlType == set_compressed || fseMetadata->mlType == set_rle) + return 1; + if (fseMetadata->ofType == set_compressed || fseMetadata->ofType == set_rle) + return 1; + return 0; +} + +/* ZSTD_compressSubBlock_multi() : + * Breaks super-block into multiple sub-blocks and compresses them. + * Entropy will be written to the first block. + * The following blocks will use repeat mode to compress. + * All sub-blocks are compressed blocks (no raw or rle blocks). + * @return : compressed size of the super block (which is multiple ZSTD blocks) + * Or 0 if it failed to compress. */ +static size_t ZSTD_compressSubBlock_multi(const seqStore_t* seqStorePtr, + const ZSTD_compressedBlockState_t* prevCBlock, + ZSTD_compressedBlockState_t* nextCBlock, + const ZSTD_entropyCTablesMetadata_t* entropyMetadata, + const ZSTD_CCtx_params* cctxParams, + void* dst, size_t dstCapacity, + const void* src, size_t srcSize, + const int bmi2, U32 lastBlock, + void* workspace, size_t wkspSize) +{ + const seqDef* const sstart = seqStorePtr->sequencesStart; + const seqDef* const send = seqStorePtr->sequences; + const seqDef* sp = sstart; + const BYTE* const lstart = seqStorePtr->litStart; + const BYTE* const lend = seqStorePtr->lit; + const BYTE* lp = lstart; + BYTE const* ip = (BYTE const*)src; + BYTE const* const iend = ip + srcSize; + BYTE* const ostart = (BYTE*)dst; + BYTE* const oend = ostart + dstCapacity; + BYTE* op = ostart; + const BYTE* llCodePtr = seqStorePtr->llCode; + const BYTE* mlCodePtr = seqStorePtr->mlCode; + const BYTE* ofCodePtr = seqStorePtr->ofCode; + size_t targetCBlockSize = cctxParams->targetCBlockSize; + size_t litSize, seqCount; + int writeLitEntropy = entropyMetadata->hufMetadata.hType == set_compressed; + int writeSeqEntropy = 1; + int lastSequence = 0; + + DEBUGLOG(5, "ZSTD_compressSubBlock_multi (litSize=%u, nbSeq=%u)", + (unsigned)(lend-lp), (unsigned)(send-sstart)); + + litSize = 0; + seqCount = 0; + do { + size_t cBlockSizeEstimate = 0; + if (sstart == send) { + lastSequence = 1; + } else { + const seqDef* const sequence = sp + seqCount; + lastSequence = sequence == send - 1; + litSize += ZSTD_getSequenceLength(seqStorePtr, sequence).litLength; + seqCount++; + } + if (lastSequence) { + assert(lp <= lend); + assert(litSize <= (size_t)(lend - lp)); + litSize = (size_t)(lend - lp); + } + /* I think there is an optimization opportunity here. + * Calling ZSTD_estimateSubBlockSize for every sequence can be wasteful + * since it recalculates estimate from scratch. + * For example, it would recount literal distribution and symbol codes every time. + */ + cBlockSizeEstimate = ZSTD_estimateSubBlockSize(lp, litSize, ofCodePtr, llCodePtr, mlCodePtr, seqCount, + &nextCBlock->entropy, entropyMetadata, + workspace, wkspSize, writeLitEntropy, writeSeqEntropy); + if (cBlockSizeEstimate > targetCBlockSize || lastSequence) { + int litEntropyWritten = 0; + int seqEntropyWritten = 0; + const size_t decompressedSize = ZSTD_seqDecompressedSize(seqStorePtr, sp, seqCount, litSize, lastSequence); + const size_t cSize = ZSTD_compressSubBlock(&nextCBlock->entropy, entropyMetadata, + sp, seqCount, + lp, litSize, + llCodePtr, mlCodePtr, ofCodePtr, + cctxParams, + op, oend-op, + bmi2, writeLitEntropy, writeSeqEntropy, + &litEntropyWritten, &seqEntropyWritten, + lastBlock && lastSequence); + FORWARD_IF_ERROR(cSize, "ZSTD_compressSubBlock failed"); + if (cSize > 0 && cSize < decompressedSize) { + DEBUGLOG(5, "Committed the sub-block"); + assert(ip + decompressedSize <= iend); + ip += decompressedSize; + sp += seqCount; + lp += litSize; + op += cSize; + llCodePtr += seqCount; + mlCodePtr += seqCount; + ofCodePtr += seqCount; + litSize = 0; + seqCount = 0; + /* Entropy only needs to be written once */ + if (litEntropyWritten) { + writeLitEntropy = 0; + } + if (seqEntropyWritten) { + writeSeqEntropy = 0; + } + } + } + } while (!lastSequence); + if (writeLitEntropy) { + DEBUGLOG(5, "ZSTD_compressSubBlock_multi has literal entropy tables unwritten"); + ZSTD_memcpy(&nextCBlock->entropy.huf, &prevCBlock->entropy.huf, sizeof(prevCBlock->entropy.huf)); + } + if (writeSeqEntropy && ZSTD_needSequenceEntropyTables(&entropyMetadata->fseMetadata)) { + /* If we haven't written our entropy tables, then we've violated our contract and + * must emit an uncompressed block. + */ + DEBUGLOG(5, "ZSTD_compressSubBlock_multi has sequence entropy tables unwritten"); + return 0; + } + if (ip < iend) { + size_t const cSize = ZSTD_noCompressBlock(op, oend - op, ip, iend - ip, lastBlock); + DEBUGLOG(5, "ZSTD_compressSubBlock_multi last sub-block uncompressed, %zu bytes", (size_t)(iend - ip)); + FORWARD_IF_ERROR(cSize, "ZSTD_noCompressBlock failed"); + assert(cSize != 0); + op += cSize; + /* We have to regenerate the repcodes because we've skipped some sequences */ + if (sp < send) { + seqDef const* seq; + repcodes_t rep; + ZSTD_memcpy(&rep, prevCBlock->rep, sizeof(rep)); + for (seq = sstart; seq < sp; ++seq) { + ZSTD_updateRep(rep.rep, seq->offBase - 1, ZSTD_getSequenceLength(seqStorePtr, seq).litLength == 0); + } + ZSTD_memcpy(nextCBlock->rep, &rep, sizeof(rep)); + } + } + DEBUGLOG(5, "ZSTD_compressSubBlock_multi compressed"); + return op-ostart; +} + +size_t ZSTD_compressSuperBlock(ZSTD_CCtx* zc, + void* dst, size_t dstCapacity, + void const* src, size_t srcSize, + unsigned lastBlock) { + ZSTD_entropyCTablesMetadata_t entropyMetadata; + + FORWARD_IF_ERROR(ZSTD_buildBlockEntropyStats(&zc->seqStore, + &zc->blockState.prevCBlock->entropy, + &zc->blockState.nextCBlock->entropy, + &zc->appliedParams, + &entropyMetadata, + zc->entropyWorkspace, ENTROPY_WORKSPACE_SIZE /* statically allocated in resetCCtx */), ""); + + return ZSTD_compressSubBlock_multi(&zc->seqStore, + zc->blockState.prevCBlock, + zc->blockState.nextCBlock, + &entropyMetadata, + &zc->appliedParams, + dst, dstCapacity, + src, srcSize, + zc->bmi2, lastBlock, + zc->entropyWorkspace, ENTROPY_WORKSPACE_SIZE /* statically allocated in resetCCtx */); +} |