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().
  ...

1 files changed, 720 insertions, 0 deletions

diff --git a/lib/lz4/lz4_decompress.c b/lib/lz4/lz4_decompress.c
new file mode 100644
index 000000000..59fe69a63
--- /dev/null
+++ b/lib/lz4/lz4_decompress.c
@@ -0,0 +1,720 @@
+/*
+ * LZ4 - Fast LZ compression algorithm
+ * Copyright (C) 2011 - 2016, Yann Collet.
+ * BSD 2 - Clause License (http://www.opensource.org/licenses/bsd - license.php)
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are
+ * met:
+ *	* Redistributions of source code must retain the above copyright
+ *	  notice, this list of conditions and the following disclaimer.
+ *	* Redistributions in binary form must reproduce the above
+ * copyright notice, this list of conditions and the following disclaimer
+ * in the documentation and/or other materials provided with the
+ * distribution.
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ * You can contact the author at :
+ *	- LZ4 homepage : http://www.lz4.org
+ *	- LZ4 source repository : https://github.com/lz4/lz4
+ *
+ *	Changed for kernel usage by:
+ *	Sven Schmidt <4sschmid@informatik.uni-hamburg.de>
+ */
+
+/*-************************************
+ *	Dependencies
+ **************************************/
+#include <linux/lz4.h>
+#include "lz4defs.h"
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <asm/unaligned.h>
+
+/*-*****************************
+ *	Decompression functions
+ *******************************/
+
+#define DEBUGLOG(l, ...) {}	/* disabled */
+
+#ifndef assert
+#define assert(condition) ((void)0)
+#endif
+
+/*
+ * LZ4_decompress_generic() :
+ * This generic decompression function covers all use cases.
+ * It shall be instantiated several times, using different sets of directives.
+ * Note that it is important for performance that this function really get inlined,
+ * in order to remove useless branches during compilation optimization.
+ */
+static FORCE_INLINE int LZ4_decompress_generic(
+	 const char * const src,
+	 char * const dst,
+	 int srcSize,
+		/*
+		 * If endOnInput == endOnInputSize,
+		 * this value is `dstCapacity`
+		 */
+	 int outputSize,
+	 /* endOnOutputSize, endOnInputSize */
+	 endCondition_directive endOnInput,
+	 /* full, partial */
+	 earlyEnd_directive partialDecoding,
+	 /* noDict, withPrefix64k, usingExtDict */
+	 dict_directive dict,
+	 /* always <= dst, == dst when no prefix */
+	 const BYTE * const lowPrefix,
+	 /* only if dict == usingExtDict */
+	 const BYTE * const dictStart,
+	 /* note : = 0 if noDict */
+	 const size_t dictSize
+	 )
+{
+	const BYTE *ip = (const BYTE *) src;
+	const BYTE * const iend = ip + srcSize;
+
+	BYTE *op = (BYTE *) dst;
+	BYTE * const oend = op + outputSize;
+	BYTE *cpy;
+
+	const BYTE * const dictEnd = (const BYTE *)dictStart + dictSize;
+	static const unsigned int inc32table[8] = {0, 1, 2, 1, 0, 4, 4, 4};
+	static const int dec64table[8] = {0, 0, 0, -1, -4, 1, 2, 3};
+
+	const int safeDecode = (endOnInput == endOnInputSize);
+	const int checkOffset = ((safeDecode) && (dictSize < (int)(64 * KB)));
+
+	/* Set up the "end" pointers for the shortcut. */
+	const BYTE *const shortiend = iend -
+		(endOnInput ? 14 : 8) /*maxLL*/ - 2 /*offset*/;
+	const BYTE *const shortoend = oend -
+		(endOnInput ? 14 : 8) /*maxLL*/ - 18 /*maxML*/;
+
+	DEBUGLOG(5, "%s (srcSize:%i, dstSize:%i)", __func__,
+		 srcSize, outputSize);
+
+	/* Special cases */
+	assert(lowPrefix <= op);
+	assert(src != NULL);
+
+	/* Empty output buffer */
+	if ((endOnInput) && (unlikely(outputSize == 0)))
+		return ((srcSize == 1) && (*ip == 0)) ? 0 : -1;
+
+	if ((!endOnInput) && (unlikely(outputSize == 0)))
+		return (*ip == 0 ? 1 : -1);
+
+	if ((endOnInput) && unlikely(srcSize == 0))
+		return -1;
+
+	/* Main Loop : decode sequences */
+	while (1) {
+		size_t length;
+		const BYTE *match;
+		size_t offset;
+
+		/* get literal length */
+		unsigned int const token = *ip++;
+		length = token>>ML_BITS;
+
+		/* ip < iend before the increment */
+		assert(!endOnInput || ip <= iend);
+
+		/*
+		 * A two-stage shortcut for the most common case:
+		 * 1) If the literal length is 0..14, and there is enough
+		 * space, enter the shortcut and copy 16 bytes on behalf
+		 * of the literals (in the fast mode, only 8 bytes can be
+		 * safely copied this way).
+		 * 2) Further if the match length is 4..18, copy 18 bytes
+		 * in a similar manner; but we ensure that there's enough
+		 * space in the output for those 18 bytes earlier, upon
+		 * entering the shortcut (in other words, there is a
+		 * combined check for both stages).
+		 *
+		 * The & in the likely() below is intentionally not && so that
+		 * some compilers can produce better parallelized runtime code
+		 */
+		if ((endOnInput ? length != RUN_MASK : length <= 8)
+		   /*
+		    * strictly "less than" on input, to re-enter
+		    * the loop with at least one byte
+		    */
+		   && likely((endOnInput ? ip < shortiend : 1) &
+			     (op <= shortoend))) {
+			/* Copy the literals */
+			LZ4_memcpy(op, ip, endOnInput ? 16 : 8);
+			op += length; ip += length;
+
+			/*
+			 * The second stage:
+			 * prepare for match copying, decode full info.
+			 * If it doesn't work out, the info won't be wasted.
+			 */
+			length = token & ML_MASK; /* match length */
+			offset = LZ4_readLE16(ip);
+			ip += 2;
+			match = op - offset;
+			assert(match <= op); /* check overflow */
+
+			/* Do not deal with overlapping matches. */
+			if ((length != ML_MASK) &&
+			    (offset >= 8) &&
+			    (dict == withPrefix64k || match >= lowPrefix)) {
+				/* Copy the match. */
+				LZ4_memcpy(op + 0, match + 0, 8);
+				LZ4_memcpy(op + 8, match + 8, 8);
+				LZ4_memcpy(op + 16, match + 16, 2);
+				op += length + MINMATCH;
+				/* Both stages worked, load the next token. */
+				continue;
+			}
+
+			/*
+			 * The second stage didn't work out, but the info
+			 * is ready. Propel it right to the point of match
+			 * copying.
+			 */
+			goto _copy_match;
+		}
+
+		/* decode literal length */
+		if (length == RUN_MASK) {
+			unsigned int s;
+
+			if (unlikely(endOnInput ? ip >= iend - RUN_MASK : 0)) {
+				/* overflow detection */
+				goto _output_error;
+			}
+			do {
+				s = *ip++;
+				length += s;
+			} while (likely(endOnInput
+				? ip < iend - RUN_MASK
+				: 1) & (s == 255));
+
+			if ((safeDecode)
+			    && unlikely((uptrval)(op) +
+					length < (uptrval)(op))) {
+				/* overflow detection */
+				goto _output_error;
+			}
+			if ((safeDecode)
+			    && unlikely((uptrval)(ip) +
+					length < (uptrval)(ip))) {
+				/* overflow detection */
+				goto _output_error;
+			}
+		}
+
+		/* copy literals */
+		cpy = op + length;
+		LZ4_STATIC_ASSERT(MFLIMIT >= WILDCOPYLENGTH);
+
+		if (((endOnInput) && ((cpy > oend - MFLIMIT)
+			|| (ip + length > iend - (2 + 1 + LASTLITERALS))))
+			|| ((!endOnInput) && (cpy > oend - WILDCOPYLENGTH))) {
+			if (partialDecoding) {
+				if (cpy > oend) {
+					/*
+					 * Partial decoding :
+					 * stop in the middle of literal segment
+					 */
+					cpy = oend;
+					length = oend - op;
+				}
+				if ((endOnInput)
+					&& (ip + length > iend)) {
+					/*
+					 * Error :
+					 * read attempt beyond
+					 * end of input buffer
+					 */
+					goto _output_error;
+				}
+			} else {
+				if ((!endOnInput)
+					&& (cpy != oend)) {
+					/*
+					 * Error :
+					 * block decoding must
+					 * stop exactly there
+					 */
+					goto _output_error;
+				}
+				if ((endOnInput)
+					&& ((ip + length != iend)
+					|| (cpy > oend))) {
+					/*
+					 * Error :
+					 * input must be consumed
+					 */
+					goto _output_error;
+				}
+			}
+
+			/*
+			 * supports overlapping memory regions; only matters
+			 * for in-place decompression scenarios
+			 */
+			LZ4_memmove(op, ip, length);
+			ip += length;
+			op += length;
+
+			/* Necessarily EOF when !partialDecoding.
+			 * When partialDecoding, it is EOF if we've either
+			 * filled the output buffer or
+			 * can't proceed with reading an offset for following match.
+			 */
+			if (!partialDecoding || (cpy == oend) || (ip >= (iend - 2)))
+				break;
+		} else {
+			/* may overwrite up to WILDCOPYLENGTH beyond cpy */
+			LZ4_wildCopy(op, ip, cpy);
+			ip += length;
+			op = cpy;
+		}
+
+		/* get offset */
+		offset = LZ4_readLE16(ip);
+		ip += 2;
+		match = op - offset;
+
+		/* get matchlength */
+		length = token & ML_MASK;
+
+_copy_match:
+		if ((checkOffset) && (unlikely(match + dictSize < lowPrefix))) {
+			/* Error : offset outside buffers */
+			goto _output_error;
+		}
+
+		/* costs ~1%; silence an msan warning when offset == 0 */
+		/*
+		 * note : when partialDecoding, there is no guarantee that
+		 * at least 4 bytes remain available in output buffer
+		 */
+		if (!partialDecoding) {
+			assert(oend > op);
+			assert(oend - op >= 4);
+
+			LZ4_write32(op, (U32)offset);
+		}
+
+		if (length == ML_MASK) {
+			unsigned int s;
+
+			do {
+				s = *ip++;
+
+				if ((endOnInput) && (ip > iend - LASTLITERALS))
+					goto _output_error;
+
+				length += s;
+			} while (s == 255);
+
+			if ((safeDecode)
+				&& unlikely(
+					(uptrval)(op) + length < (uptrval)op)) {
+				/* overflow detection */
+				goto _output_error;
+			}
+		}
+
+		length += MINMATCH;
+
+		/* match starting within external dictionary */
+		if ((dict == usingExtDict) && (match < lowPrefix)) {
+			if (unlikely(op + length > oend - LASTLITERALS)) {
+				/* doesn't respect parsing restriction */
+				if (!partialDecoding)
+					goto _output_error;
+				length = min(length, (size_t)(oend - op));
+			}
+
+			if (length <= (size_t)(lowPrefix - match)) {
+				/*
+				 * match fits entirely within external
+				 * dictionary : just copy
+				 */
+				memmove(op, dictEnd - (lowPrefix - match),
+					length);
+				op += length;
+			} else {
+				/*
+				 * match stretches into both external
+				 * dictionary and current block
+				 */
+				size_t const copySize = (size_t)(lowPrefix - match);
+				size_t const restSize = length - copySize;
+
+				LZ4_memcpy(op, dictEnd - copySize, copySize);
+				op += copySize;
+				if (restSize > (size_t)(op - lowPrefix)) {
+					/* overlap copy */
+					BYTE * const endOfMatch = op + restSize;
+					const BYTE *copyFrom = lowPrefix;
+
+					while (op < endOfMatch)
+						*op++ = *copyFrom++;
+				} else {
+					LZ4_memcpy(op, lowPrefix, restSize);
+					op += restSize;
+				}
+			}
+			continue;
+		}
+
+		/* copy match within block */
+		cpy = op + length;
+
+		/*
+		 * partialDecoding :
+		 * may not respect endBlock parsing restrictions
+		 */
+		assert(op <= oend);
+		if (partialDecoding &&
+		    (cpy > oend - MATCH_SAFEGUARD_DISTANCE)) {
+			size_t const mlen = min(length, (size_t)(oend - op));
+			const BYTE * const matchEnd = match + mlen;
+			BYTE * const copyEnd = op + mlen;
+
+			if (matchEnd > op) {
+				/* overlap copy */
+				while (op < copyEnd)
+					*op++ = *match++;
+			} else {
+				LZ4_memcpy(op, match, mlen);
+			}
+			op = copyEnd;
+			if (op == oend)
+				break;
+			continue;
+		}
+
+		if (unlikely(offset < 8)) {
+			op[0] = match[0];
+			op[1] = match[1];
+			op[2] = match[2];
+			op[3] = match[3];
+			match += inc32table[offset];
+			LZ4_memcpy(op + 4, match, 4);
+			match -= dec64table[offset];
+		} else {
+			LZ4_copy8(op, match);
+			match += 8;
+		}
+
+		op += 8;
+
+		if (unlikely(cpy > oend - MATCH_SAFEGUARD_DISTANCE)) {
+			BYTE * const oCopyLimit = oend - (WILDCOPYLENGTH - 1);
+
+			if (cpy > oend - LASTLITERALS) {
+				/*
+				 * Error : last LASTLITERALS bytes
+				 * must be literals (uncompressed)
+				 */
+				goto _output_error;
+			}
+
+			if (op < oCopyLimit) {
+				LZ4_wildCopy(op, match, oCopyLimit);
+				match += oCopyLimit - op;
+				op = oCopyLimit;
+			}
+			while (op < cpy)
+				*op++ = *match++;
+		} else {
+			LZ4_copy8(op, match);
+			if (length > 16)
+				LZ4_wildCopy(op + 8, match + 8, cpy);
+		}
+		op = cpy; /* wildcopy correction */
+	}
+
+	/* end of decoding */
+	if (endOnInput) {
+		/* Nb of output bytes decoded */
+		return (int) (((char *)op) - dst);
+	} else {
+		/* Nb of input bytes read */
+		return (int) (((const char *)ip) - src);
+	}
+
+	/* Overflow error detected */
+_output_error:
+	return (int) (-(((const char *)ip) - src)) - 1;
+}
+
+int LZ4_decompress_safe(const char *source, char *dest,
+	int compressedSize, int maxDecompressedSize)
+{
+	return LZ4_decompress_generic(source, dest,
+				      compressedSize, maxDecompressedSize,
+				      endOnInputSize, decode_full_block,
+				      noDict, (BYTE *)dest, NULL, 0);
+}
+
+int LZ4_decompress_safe_partial(const char *src, char *dst,
+	int compressedSize, int targetOutputSize, int dstCapacity)
+{
+	dstCapacity = min(targetOutputSize, dstCapacity);
+	return LZ4_decompress_generic(src, dst, compressedSize, dstCapacity,
+				      endOnInputSize, partial_decode,
+				      noDict, (BYTE *)dst, NULL, 0);
+}
+
+int LZ4_decompress_fast(const char *source, char *dest, int originalSize)
+{
+	return LZ4_decompress_generic(source, dest, 0, originalSize,
+				      endOnOutputSize, decode_full_block,
+				      withPrefix64k,
+				      (BYTE *)dest - 64 * KB, NULL, 0);
+}
+
+/* ===== Instantiate a few more decoding cases, used more than once. ===== */
+
+static int LZ4_decompress_safe_withPrefix64k(const char *source, char *dest,
+				      int compressedSize, int maxOutputSize)
+{
+	return LZ4_decompress_generic(source, dest,
+				      compressedSize, maxOutputSize,
+				      endOnInputSize, decode_full_block,
+				      withPrefix64k,
+				      (BYTE *)dest - 64 * KB, NULL, 0);
+}
+
+static int LZ4_decompress_safe_withSmallPrefix(const char *source, char *dest,
+					       int compressedSize,
+					       int maxOutputSize,
+					       size_t prefixSize)
+{
+	return LZ4_decompress_generic(source, dest,
+				      compressedSize, maxOutputSize,
+				      endOnInputSize, decode_full_block,
+				      noDict,
+				      (BYTE *)dest - prefixSize, NULL, 0);
+}
+
+static int LZ4_decompress_safe_forceExtDict(const char *source, char *dest,
+					    int compressedSize, int maxOutputSize,
+					    const void *dictStart, size_t dictSize)
+{
+	return LZ4_decompress_generic(source, dest,
+				      compressedSize, maxOutputSize,
+				      endOnInputSize, decode_full_block,
+				      usingExtDict, (BYTE *)dest,
+				      (const BYTE *)dictStart, dictSize);
+}
+
+static int LZ4_decompress_fast_extDict(const char *source, char *dest,
+				       int originalSize,
+				       const void *dictStart, size_t dictSize)
+{
+	return LZ4_decompress_generic(source, dest,
+				      0, originalSize,
+				      endOnOutputSize, decode_full_block,
+				      usingExtDict, (BYTE *)dest,
+				      (const BYTE *)dictStart, dictSize);
+}
+
+/*
+ * The "double dictionary" mode, for use with e.g. ring buffers: the first part
+ * of the dictionary is passed as prefix, and the second via dictStart + dictSize.
+ * These routines are used only once, in LZ4_decompress_*_continue().
+ */
+static FORCE_INLINE
+int LZ4_decompress_safe_doubleDict(const char *source, char *dest,
+				   int compressedSize, int maxOutputSize,
+				   size_t prefixSize,
+				   const void *dictStart, size_t dictSize)
+{
+	return LZ4_decompress_generic(source, dest,
+				      compressedSize, maxOutputSize,
+				      endOnInputSize, decode_full_block,
+				      usingExtDict, (BYTE *)dest - prefixSize,
+				      (const BYTE *)dictStart, dictSize);
+}
+
+static FORCE_INLINE
+int LZ4_decompress_fast_doubleDict(const char *source, char *dest,
+				   int originalSize, size_t prefixSize,
+				   const void *dictStart, size_t dictSize)
+{
+	return LZ4_decompress_generic(source, dest,
+				      0, originalSize,
+				      endOnOutputSize, decode_full_block,
+				      usingExtDict, (BYTE *)dest - prefixSize,
+				      (const BYTE *)dictStart, dictSize);
+}
+
+/* ===== streaming decompression functions ===== */
+
+int LZ4_setStreamDecode(LZ4_streamDecode_t *LZ4_streamDecode,
+	const char *dictionary, int dictSize)
+{
+	LZ4_streamDecode_t_internal *lz4sd =
+		&LZ4_streamDecode->internal_donotuse;
+
+	lz4sd->prefixSize = (size_t) dictSize;
+	lz4sd->prefixEnd = (const BYTE *) dictionary + dictSize;
+	lz4sd->externalDict = NULL;
+	lz4sd->extDictSize	= 0;
+	return 1;
+}
+
+/*
+ * *_continue() :
+ * These decoding functions allow decompression of multiple blocks
+ * in "streaming" mode.
+ * Previously decoded blocks must still be available at the memory
+ * position where they were decoded.
+ * If it's not possible, save the relevant part of
+ * decoded data into a safe buffer,
+ * and indicate where it stands using LZ4_setStreamDecode()
+ */
+int LZ4_decompress_safe_continue(LZ4_streamDecode_t *LZ4_streamDecode,
+	const char *source, char *dest, int compressedSize, int maxOutputSize)
+{
+	LZ4_streamDecode_t_internal *lz4sd =
+		&LZ4_streamDecode->internal_donotuse;
+	int result;
+
+	if (lz4sd->prefixSize == 0) {
+		/* The first call, no dictionary yet. */
+		assert(lz4sd->extDictSize == 0);
+		result = LZ4_decompress_safe(source, dest,
+			compressedSize, maxOutputSize);
+		if (result <= 0)
+			return result;
+		lz4sd->prefixSize = result;
+		lz4sd->prefixEnd = (BYTE *)dest + result;
+	} else if (lz4sd->prefixEnd == (BYTE *)dest) {
+		/* They're rolling the current segment. */
+		if (lz4sd->prefixSize >= 64 * KB - 1)
+			result = LZ4_decompress_safe_withPrefix64k(source, dest,
+				compressedSize, maxOutputSize);
+		else if (lz4sd->extDictSize == 0)
+			result = LZ4_decompress_safe_withSmallPrefix(source,
+				dest, compressedSize, maxOutputSize,
+				lz4sd->prefixSize);
+		else
+			result = LZ4_decompress_safe_doubleDict(source, dest,
+				compressedSize, maxOutputSize,
+				lz4sd->prefixSize,
+				lz4sd->externalDict, lz4sd->extDictSize);
+		if (result <= 0)
+			return result;
+		lz4sd->prefixSize += result;
+		lz4sd->prefixEnd  += result;
+	} else {
+		/*
+		 * The buffer wraps around, or they're
+		 * switching to another buffer.
+		 */
+		lz4sd->extDictSize = lz4sd->prefixSize;
+		lz4sd->externalDict = lz4sd->prefixEnd - lz4sd->extDictSize;
+		result = LZ4_decompress_safe_forceExtDict(source, dest,
+			compressedSize, maxOutputSize,
+			lz4sd->externalDict, lz4sd->extDictSize);
+		if (result <= 0)
+			return result;
+		lz4sd->prefixSize = result;
+		lz4sd->prefixEnd  = (BYTE *)dest + result;
+	}
+
+	return result;
+}
+
+int LZ4_decompress_fast_continue(LZ4_streamDecode_t *LZ4_streamDecode,
+	const char *source, char *dest, int originalSize)
+{
+	LZ4_streamDecode_t_internal *lz4sd = &LZ4_streamDecode->internal_donotuse;
+	int result;
+
+	if (lz4sd->prefixSize == 0) {
+		assert(lz4sd->extDictSize == 0);
+		result = LZ4_decompress_fast(source, dest, originalSize);
+		if (result <= 0)
+			return result;
+		lz4sd->prefixSize = originalSize;
+		lz4sd->prefixEnd = (BYTE *)dest + originalSize;
+	} else if (lz4sd->prefixEnd == (BYTE *)dest) {
+		if (lz4sd->prefixSize >= 64 * KB - 1 ||
+		    lz4sd->extDictSize == 0)
+			result = LZ4_decompress_fast(source, dest,
+						     originalSize);
+		else
+			result = LZ4_decompress_fast_doubleDict(source, dest,
+				originalSize, lz4sd->prefixSize,
+				lz4sd->externalDict, lz4sd->extDictSize);
+		if (result <= 0)
+			return result;
+		lz4sd->prefixSize += originalSize;
+		lz4sd->prefixEnd  += originalSize;
+	} else {
+		lz4sd->extDictSize = lz4sd->prefixSize;
+		lz4sd->externalDict = lz4sd->prefixEnd - lz4sd->extDictSize;
+		result = LZ4_decompress_fast_extDict(source, dest,
+			originalSize, lz4sd->externalDict, lz4sd->extDictSize);
+		if (result <= 0)
+			return result;
+		lz4sd->prefixSize = originalSize;
+		lz4sd->prefixEnd = (BYTE *)dest + originalSize;
+	}
+	return result;
+}
+
+int LZ4_decompress_safe_usingDict(const char *source, char *dest,
+				  int compressedSize, int maxOutputSize,
+				  const char *dictStart, int dictSize)
+{
+	if (dictSize == 0)
+		return LZ4_decompress_safe(source, dest,
+					   compressedSize, maxOutputSize);
+	if (dictStart+dictSize == dest) {
+		if (dictSize >= 64 * KB - 1)
+			return LZ4_decompress_safe_withPrefix64k(source, dest,
+				compressedSize, maxOutputSize);
+		return LZ4_decompress_safe_withSmallPrefix(source, dest,
+			compressedSize, maxOutputSize, dictSize);
+	}
+	return LZ4_decompress_safe_forceExtDict(source, dest,
+		compressedSize, maxOutputSize, dictStart, dictSize);
+}
+
+int LZ4_decompress_fast_usingDict(const char *source, char *dest,
+				  int originalSize,
+				  const char *dictStart, int dictSize)
+{
+	if (dictSize == 0 || dictStart + dictSize == dest)
+		return LZ4_decompress_fast(source, dest, originalSize);
+
+	return LZ4_decompress_fast_extDict(source, dest, originalSize,
+		dictStart, dictSize);
+}
+
+#ifndef STATIC
+EXPORT_SYMBOL(LZ4_decompress_safe);
+EXPORT_SYMBOL(LZ4_decompress_safe_partial);
+EXPORT_SYMBOL(LZ4_decompress_fast);
+EXPORT_SYMBOL(LZ4_setStreamDecode);
+EXPORT_SYMBOL(LZ4_decompress_safe_continue);
+EXPORT_SYMBOL(LZ4_decompress_fast_continue);
+EXPORT_SYMBOL(LZ4_decompress_safe_usingDict);
+EXPORT_SYMBOL(LZ4_decompress_fast_usingDict);
+
+MODULE_LICENSE("Dual BSD/GPL");
+MODULE_DESCRIPTION("LZ4 decompressor");
+#endif