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, 444 insertions, 0 deletions

diff --git a/arch/x86/lib/checksum_32.S b/arch/x86/lib/checksum_32.S
new file mode 100644
index 000000000..23318c338
--- /dev/null
+++ b/arch/x86/lib/checksum_32.S
@@ -0,0 +1,444 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * INET		An implementation of the TCP/IP protocol suite for the LINUX
+ *		operating system.  INET is implemented using the  BSD Socket
+ *		interface as the means of communication with the user level.
+ *
+ *		IP/TCP/UDP checksumming routines
+ *
+ * Authors:	Jorge Cwik, <jorge@laser.satlink.net>
+ *		Arnt Gulbrandsen, <agulbra@nvg.unit.no>
+ *		Tom May, <ftom@netcom.com>
+ *              Pentium Pro/II routines:
+ *              Alexander Kjeldaas <astor@guardian.no>
+ *              Finn Arne Gangstad <finnag@guardian.no>
+ *		Lots of code moved from tcp.c and ip.c; see those files
+ *		for more names.
+ *
+ * Changes:     Ingo Molnar, converted csum_partial_copy() to 2.1 exception
+ *			     handling.
+ *		Andi Kleen,  add zeroing on error
+ *                   converted to pure assembler
+ */
+
+#include <linux/linkage.h>
+#include <asm/errno.h>
+#include <asm/asm.h>
+#include <asm/export.h>
+#include <asm/nospec-branch.h>
+
+/*
+ * computes a partial checksum, e.g. for TCP/UDP fragments
+ */
+
+/*	
+unsigned int csum_partial(const unsigned char * buff, int len, unsigned int sum)
+ */
+		
+.text
+		
+#ifndef CONFIG_X86_USE_PPRO_CHECKSUM
+
+	  /*		
+	   * Experiments with Ethernet and SLIP connections show that buff
+	   * is aligned on either a 2-byte or 4-byte boundary.  We get at
+	   * least a twofold speedup on 486 and Pentium if it is 4-byte aligned.
+	   * Fortunately, it is easy to convert 2-byte alignment to 4-byte
+	   * alignment for the unrolled loop.
+	   */		
+SYM_FUNC_START(csum_partial)
+	pushl %esi
+	pushl %ebx
+	movl 20(%esp),%eax	# Function arg: unsigned int sum
+	movl 16(%esp),%ecx	# Function arg: int len
+	movl 12(%esp),%esi	# Function arg: unsigned char *buff
+	testl $3, %esi		# Check alignment.
+	jz 2f			# Jump if alignment is ok.
+	testl $1, %esi		# Check alignment.
+	jz 10f			# Jump if alignment is boundary of 2 bytes.
+
+	# buf is odd
+	dec %ecx
+	jl 8f
+	movzbl (%esi), %ebx
+	adcl %ebx, %eax
+	roll $8, %eax
+	inc %esi
+	testl $2, %esi
+	jz 2f
+10:
+	subl $2, %ecx		# Alignment uses up two bytes.
+	jae 1f			# Jump if we had at least two bytes.
+	addl $2, %ecx		# ecx was < 2.  Deal with it.
+	jmp 4f
+1:	movw (%esi), %bx
+	addl $2, %esi
+	addw %bx, %ax
+	adcl $0, %eax
+2:
+	movl %ecx, %edx
+	shrl $5, %ecx
+	jz 2f
+	testl %esi, %esi
+1:	movl (%esi), %ebx
+	adcl %ebx, %eax
+	movl 4(%esi), %ebx
+	adcl %ebx, %eax
+	movl 8(%esi), %ebx
+	adcl %ebx, %eax
+	movl 12(%esi), %ebx
+	adcl %ebx, %eax
+	movl 16(%esi), %ebx
+	adcl %ebx, %eax
+	movl 20(%esi), %ebx
+	adcl %ebx, %eax
+	movl 24(%esi), %ebx
+	adcl %ebx, %eax
+	movl 28(%esi), %ebx
+	adcl %ebx, %eax
+	lea 32(%esi), %esi
+	dec %ecx
+	jne 1b
+	adcl $0, %eax
+2:	movl %edx, %ecx
+	andl $0x1c, %edx
+	je 4f
+	shrl $2, %edx		# This clears CF
+3:	adcl (%esi), %eax
+	lea 4(%esi), %esi
+	dec %edx
+	jne 3b
+	adcl $0, %eax
+4:	andl $3, %ecx
+	jz 7f
+	cmpl $2, %ecx
+	jb 5f
+	movw (%esi),%cx
+	leal 2(%esi),%esi
+	je 6f
+	shll $16,%ecx
+5:	movb (%esi),%cl
+6:	addl %ecx,%eax
+	adcl $0, %eax 
+7:	
+	testb $1, 12(%esp)
+	jz 8f
+	roll $8, %eax
+8:
+	popl %ebx
+	popl %esi
+	RET
+SYM_FUNC_END(csum_partial)
+
+#else
+
+/* Version for PentiumII/PPro */
+
+SYM_FUNC_START(csum_partial)
+	pushl %esi
+	pushl %ebx
+	movl 20(%esp),%eax	# Function arg: unsigned int sum
+	movl 16(%esp),%ecx	# Function arg: int len
+	movl 12(%esp),%esi	# Function arg:	const unsigned char *buf
+
+	testl $3, %esi         
+	jnz 25f                 
+10:
+	movl %ecx, %edx
+	movl %ecx, %ebx
+	andl $0x7c, %ebx
+	shrl $7, %ecx
+	addl %ebx,%esi
+	shrl $2, %ebx  
+	negl %ebx
+	lea 45f(%ebx,%ebx,2), %ebx
+	testl %esi, %esi
+	JMP_NOSPEC ebx
+
+	# Handle 2-byte-aligned regions
+20:	addw (%esi), %ax
+	lea 2(%esi), %esi
+	adcl $0, %eax
+	jmp 10b
+25:
+	testl $1, %esi         
+	jz 30f                 
+	# buf is odd
+	dec %ecx
+	jl 90f
+	movzbl (%esi), %ebx
+	addl %ebx, %eax
+	adcl $0, %eax
+	roll $8, %eax
+	inc %esi
+	testl $2, %esi
+	jz 10b
+
+30:	subl $2, %ecx          
+	ja 20b                 
+	je 32f
+	addl $2, %ecx
+	jz 80f
+	movzbl (%esi),%ebx	# csumming 1 byte, 2-aligned
+	addl %ebx, %eax
+	adcl $0, %eax
+	jmp 80f
+32:
+	addw (%esi), %ax	# csumming 2 bytes, 2-aligned
+	adcl $0, %eax
+	jmp 80f
+
+40: 
+	addl -128(%esi), %eax
+	adcl -124(%esi), %eax
+	adcl -120(%esi), %eax
+	adcl -116(%esi), %eax   
+	adcl -112(%esi), %eax   
+	adcl -108(%esi), %eax
+	adcl -104(%esi), %eax
+	adcl -100(%esi), %eax
+	adcl -96(%esi), %eax
+	adcl -92(%esi), %eax
+	adcl -88(%esi), %eax
+	adcl -84(%esi), %eax
+	adcl -80(%esi), %eax
+	adcl -76(%esi), %eax
+	adcl -72(%esi), %eax
+	adcl -68(%esi), %eax
+	adcl -64(%esi), %eax     
+	adcl -60(%esi), %eax     
+	adcl -56(%esi), %eax     
+	adcl -52(%esi), %eax   
+	adcl -48(%esi), %eax   
+	adcl -44(%esi), %eax
+	adcl -40(%esi), %eax
+	adcl -36(%esi), %eax
+	adcl -32(%esi), %eax
+	adcl -28(%esi), %eax
+	adcl -24(%esi), %eax
+	adcl -20(%esi), %eax
+	adcl -16(%esi), %eax
+	adcl -12(%esi), %eax
+	adcl -8(%esi), %eax
+	adcl -4(%esi), %eax
+45:
+	lea 128(%esi), %esi
+	adcl $0, %eax
+	dec %ecx
+	jge 40b
+	movl %edx, %ecx
+50:	andl $3, %ecx
+	jz 80f
+
+	# Handle the last 1-3 bytes without jumping
+	notl %ecx		# 1->2, 2->1, 3->0, higher bits are masked
+	movl $0xffffff,%ebx	# by the shll and shrl instructions
+	shll $3,%ecx
+	shrl %cl,%ebx
+	andl -128(%esi),%ebx	# esi is 4-aligned so should be ok
+	addl %ebx,%eax
+	adcl $0,%eax
+80: 
+	testb $1, 12(%esp)
+	jz 90f
+	roll $8, %eax
+90: 
+	popl %ebx
+	popl %esi
+	RET
+SYM_FUNC_END(csum_partial)
+				
+#endif
+EXPORT_SYMBOL(csum_partial)
+
+/*
+unsigned int csum_partial_copy_generic (const char *src, char *dst,
+				  int len)
+ */ 
+
+/*
+ * Copy from ds while checksumming, otherwise like csum_partial
+ */
+
+#define EXC(y...)						\
+	9999: y;						\
+	_ASM_EXTABLE_TYPE(9999b, 7f, EX_TYPE_UACCESS | EX_FLAG_CLEAR_AX)
+
+#ifndef CONFIG_X86_USE_PPRO_CHECKSUM
+
+#define ARGBASE 16		
+#define FP		12
+		
+SYM_FUNC_START(csum_partial_copy_generic)
+	subl  $4,%esp	
+	pushl %edi
+	pushl %esi
+	pushl %ebx
+	movl ARGBASE+12(%esp),%ecx	# len
+	movl ARGBASE+4(%esp),%esi	# src
+	movl ARGBASE+8(%esp),%edi	# dst
+
+	movl $-1, %eax			# sum
+	testl $2, %edi			# Check alignment. 
+	jz 2f				# Jump if alignment is ok.
+	subl $2, %ecx			# Alignment uses up two bytes.
+	jae 1f				# Jump if we had at least two bytes.
+	addl $2, %ecx			# ecx was < 2.  Deal with it.
+	jmp 4f
+EXC(1:	movw (%esi), %bx	)
+	addl $2, %esi
+EXC(	movw %bx, (%edi)	)
+	addl $2, %edi
+	addw %bx, %ax	
+	adcl $0, %eax
+2:
+	movl %ecx, FP(%esp)
+	shrl $5, %ecx
+	jz 2f
+	testl %esi, %esi		# what's wrong with clc?
+EXC(1:	movl (%esi), %ebx	)
+EXC(	movl 4(%esi), %edx	)
+	adcl %ebx, %eax
+EXC(	movl %ebx, (%edi)	)
+	adcl %edx, %eax
+EXC(	movl %edx, 4(%edi)	)
+
+EXC(	movl 8(%esi), %ebx	)
+EXC(	movl 12(%esi), %edx	)
+	adcl %ebx, %eax
+EXC(	movl %ebx, 8(%edi)	)
+	adcl %edx, %eax
+EXC(	movl %edx, 12(%edi)	)
+
+EXC(	movl 16(%esi), %ebx 	)
+EXC(	movl 20(%esi), %edx	)
+	adcl %ebx, %eax
+EXC(	movl %ebx, 16(%edi)	)
+	adcl %edx, %eax
+EXC(	movl %edx, 20(%edi)	)
+
+EXC(	movl 24(%esi), %ebx	)
+EXC(	movl 28(%esi), %edx	)
+	adcl %ebx, %eax
+EXC(	movl %ebx, 24(%edi)	)
+	adcl %edx, %eax
+EXC(	movl %edx, 28(%edi)	)
+
+	lea 32(%esi), %esi
+	lea 32(%edi), %edi
+	dec %ecx
+	jne 1b
+	adcl $0, %eax
+2:	movl FP(%esp), %edx
+	movl %edx, %ecx
+	andl $0x1c, %edx
+	je 4f
+	shrl $2, %edx			# This clears CF
+EXC(3:	movl (%esi), %ebx	)
+	adcl %ebx, %eax
+EXC(	movl %ebx, (%edi)	)
+	lea 4(%esi), %esi
+	lea 4(%edi), %edi
+	dec %edx
+	jne 3b
+	adcl $0, %eax
+4:	andl $3, %ecx
+	jz 7f
+	cmpl $2, %ecx
+	jb 5f
+EXC(	movw (%esi), %cx	)
+	leal 2(%esi), %esi
+EXC(	movw %cx, (%edi)	)
+	leal 2(%edi), %edi
+	je 6f
+	shll $16,%ecx
+EXC(5:	movb (%esi), %cl	)
+EXC(	movb %cl, (%edi)	)
+6:	addl %ecx, %eax
+	adcl $0, %eax
+7:
+
+	popl %ebx
+	popl %esi
+	popl %edi
+	popl %ecx			# equivalent to addl $4,%esp
+	RET
+SYM_FUNC_END(csum_partial_copy_generic)
+
+#else
+
+/* Version for PentiumII/PPro */
+
+#define ROUND1(x) \
+	EXC(movl x(%esi), %ebx	)	;	\
+	addl %ebx, %eax			;	\
+	EXC(movl %ebx, x(%edi)	)	;
+
+#define ROUND(x) \
+	EXC(movl x(%esi), %ebx	)	;	\
+	adcl %ebx, %eax			;	\
+	EXC(movl %ebx, x(%edi)	)	;
+
+#define ARGBASE 12
+		
+SYM_FUNC_START(csum_partial_copy_generic)
+	pushl %ebx
+	pushl %edi
+	pushl %esi
+	movl ARGBASE+4(%esp),%esi	#src
+	movl ARGBASE+8(%esp),%edi	#dst	
+	movl ARGBASE+12(%esp),%ecx	#len
+	movl $-1, %eax			#sum
+#	movl %ecx, %edx  
+	movl %ecx, %ebx  
+	movl %esi, %edx
+	shrl $6, %ecx     
+	andl $0x3c, %ebx  
+	negl %ebx
+	subl %ebx, %esi  
+	subl %ebx, %edi  
+	lea  -1(%esi),%edx
+	andl $-32,%edx
+	lea 3f(%ebx,%ebx), %ebx
+	testl %esi, %esi 
+	JMP_NOSPEC ebx
+1:	addl $64,%esi
+	addl $64,%edi 
+	EXC(movb -32(%edx),%bl)	; EXC(movb (%edx),%bl)
+	ROUND1(-64) ROUND(-60) ROUND(-56) ROUND(-52)	
+	ROUND (-48) ROUND(-44) ROUND(-40) ROUND(-36)	
+	ROUND (-32) ROUND(-28) ROUND(-24) ROUND(-20)	
+	ROUND (-16) ROUND(-12) ROUND(-8)  ROUND(-4)	
+3:	adcl $0,%eax
+	addl $64, %edx
+	dec %ecx
+	jge 1b
+4:	movl ARGBASE+12(%esp),%edx	#len
+	andl $3, %edx
+	jz 7f
+	cmpl $2, %edx
+	jb 5f
+EXC(	movw (%esi), %dx         )
+	leal 2(%esi), %esi
+EXC(	movw %dx, (%edi)         )
+	leal 2(%edi), %edi
+	je 6f
+	shll $16,%edx
+5:
+EXC(	movb (%esi), %dl         )
+EXC(	movb %dl, (%edi)         )
+6:	addl %edx, %eax
+	adcl $0, %eax
+7:
+
+	popl %esi
+	popl %edi
+	popl %ebx
+	RET
+SYM_FUNC_END(csum_partial_copy_generic)
+				
+#undef ROUND
+#undef ROUND1		
+		
+#endif
+EXPORT_SYMBOL(csum_partial_copy_generic)