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, 1679 insertions, 0 deletions

diff --git a/arch/parisc/kernel/perf_asm.S b/arch/parisc/kernel/perf_asm.S
new file mode 100644
index 000000000..8fceabb1a
--- /dev/null
+++ b/arch/parisc/kernel/perf_asm.S
@@ -0,0 +1,1679 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+
+/*    low-level asm for "intrigue" (PA8500-8700 CPU perf counters)
+ * 
+ *    Copyright (C) 2001 Randolph Chung <tausq at parisc-linux.org>
+ *    Copyright (C) 2001 Hewlett-Packard (Grant Grundler)
+ */
+
+#include <asm/assembly.h>
+
+#include <linux/init.h>
+#include <linux/linkage.h>
+
+#ifdef CONFIG_64BIT
+	.level		2.0w
+#endif /* CONFIG_64BIT */
+
+#define MTDIAG_1(gr)    .word 0x14201840 + gr*0x10000
+#define MTDIAG_2(gr)    .word 0x14401840 + gr*0x10000
+#define MFDIAG_1(gr)    .word 0x142008A0 + gr
+#define MFDIAG_2(gr)    .word 0x144008A0 + gr
+#define STDIAG(dr)      .word 0x14000AA0 + dr*0x200000
+#define SFDIAG(dr)      .word 0x14000BA0 + dr*0x200000
+#define DR2_SLOW_RET    53
+
+
+;
+; Enable the performance counters
+;
+; The coprocessor only needs to be enabled when
+; starting/stopping the coprocessor with the pmenb/pmdis.
+;
+	.text
+
+ENTRY(perf_intrigue_enable_perf_counters)
+	.proc
+	.callinfo  frame=0,NO_CALLS
+	.entry
+
+	ldi     0x20,%r25                ; load up perfmon bit
+	mfctl   ccr,%r26                 ; get coprocessor register
+	or      %r25,%r26,%r26             ; set bit
+	mtctl   %r26,ccr                 ; turn on performance coprocessor
+	pmenb                           ; enable performance monitor
+	ssm     0,0                     ; dummy op to ensure completion
+	sync                            ; follow ERS
+	andcm   %r26,%r25,%r26             ; clear bit now 
+	mtctl   %r26,ccr                 ; turn off performance coprocessor
+	nop                             ; NOPs as specified in ERS
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	bve    (%r2)
+	nop
+	.exit
+	.procend
+ENDPROC(perf_intrigue_enable_perf_counters)
+
+ENTRY(perf_intrigue_disable_perf_counters)
+	.proc
+	.callinfo  frame=0,NO_CALLS
+	.entry
+	ldi     0x20,%r25                ; load up perfmon bit
+	mfctl   ccr,%r26                 ; get coprocessor register
+	or      %r25,%r26,%r26             ; set bit
+	mtctl   %r26,ccr                 ; turn on performance coprocessor
+	pmdis                           ; disable performance monitor
+	ssm     0,0                     ; dummy op to ensure completion
+	andcm   %r26,%r25,%r26             ; clear bit now 
+	bve    (%r2)
+	mtctl   %r26,ccr                 ; turn off performance coprocessor
+	.exit
+	.procend
+ENDPROC(perf_intrigue_disable_perf_counters)
+
+;***********************************************************************
+;*
+;* Name: perf_rdr_shift_in_W
+;*
+;* Description:
+;*	This routine shifts data in from the RDR in arg0 and returns
+;*	the result in ret0.  If the RDR is <= 64 bits in length, it
+;*	is shifted shifted backup immediately.  This is to compensate
+;*	for RDR10 which has bits that preclude PDC stack operations
+;*	when they are in the wrong state.
+;*
+;* Arguments:
+;*	arg0 : rdr to be read
+;*	arg1 : bit length of rdr
+;*
+;* Returns:
+;*	ret0 = next 64 bits of rdr data from staging register
+;*
+;* Register usage:
+;*	arg0 : rdr to be read
+;*	arg1 : bit length of rdr
+;*	%r24  - original DR2 value
+;*	%r1   - scratch
+;*  %r29  - scratch
+;*
+;* Returns:
+;*	ret0 = RDR data (right justified)
+;*
+;***********************************************************************
+
+ENTRY(perf_rdr_shift_in_W)
+	.proc
+	.callinfo frame=0,NO_CALLS
+	.entry
+;
+; read(shift in) the RDR.
+;
+
+; NOTE: The PCX-W ERS states that DR2_SLOW_RET must be set before any
+; shifting is done, from or to, remote diagnose registers.
+;
+
+	depdi,z		1,DR2_SLOW_RET,1,%r29
+	MFDIAG_2	(24)
+	or		    %r24,%r29,%r29
+	MTDIAG_2	(29)			; set DR2_SLOW_RET
+
+	nop
+	nop
+	nop
+	nop
+
+;
+; Cacheline start (32-byte cacheline)
+;
+	nop
+	nop
+	nop
+	extrd,u		arg1,63,6,%r1	; setup shift amount by bits to move 
+
+	mtsar		%r1
+	shladd		arg0,2,%r0,%r1	; %r1 = 4 * RDR number
+	blr  		%r1,%r0		; branch to 8-instruction sequence
+	nop
+
+;
+; Cacheline start (32-byte cacheline)
+;
+
+	;
+	; RDR 0 sequence
+	;
+	SFDIAG		(0)
+	ssm		    0,0
+	MFDIAG_1	(28)
+	shrpd		ret0,%r0,%sar,%r1
+	MTDIAG_1	(1)			; mtdiag %dr1, %r1 
+	STDIAG		(0)
+	ssm		    0,0
+	b,n         perf_rdr_shift_in_W_leave
+
+	;
+	; RDR 1 sequence
+	;
+	sync
+	ssm		    0,0
+	SFDIAG		(1)
+	ssm		    0,0
+	MFDIAG_1	(28)
+	ssm		    0,0
+	b,n         perf_rdr_shift_in_W_leave
+	nop
+
+	;
+	; RDR 2 read sequence
+	;
+	SFDIAG		(2)
+	ssm		    0,0
+	MFDIAG_1	(28)
+	shrpd		ret0,%r0,%sar,%r1
+	MTDIAG_1	(1)
+	STDIAG		(2)
+	ssm		    0,0
+	b,n         perf_rdr_shift_in_W_leave
+
+	;
+	; RDR 3 read sequence
+	;
+	b,n         perf_rdr_shift_in_W_leave
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+
+	;
+	; RDR 4 read sequence
+	;
+	sync
+	ssm		0,0
+	SFDIAG		(4)
+	ssm		0,0
+	MFDIAG_1	(28)
+	b,n         perf_rdr_shift_in_W_leave
+	ssm		0,0
+	nop
+
+	; 
+	; RDR 5 read sequence
+	;
+	sync
+	ssm		0,0
+	SFDIAG		(5)
+	ssm		0,0
+	MFDIAG_1	(28)
+	b,n         perf_rdr_shift_in_W_leave
+	ssm		0,0
+	nop
+
+	;
+	; RDR 6 read sequence
+	;
+	sync
+	ssm		0,0
+	SFDIAG		(6)
+	ssm		0,0
+	MFDIAG_1	(28)
+	b,n         perf_rdr_shift_in_W_leave
+	ssm		0,0
+	nop
+
+	;
+	; RDR 7 read sequence
+	;
+	b,n         perf_rdr_shift_in_W_leave
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+
+	;
+	; RDR 8 read sequence
+	;
+	b,n         perf_rdr_shift_in_W_leave
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+
+	;
+	; RDR 9 read sequence
+	;
+	b,n         perf_rdr_shift_in_W_leave
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+
+	;
+	; RDR 10 read sequence
+	;
+	SFDIAG		(10)
+	ssm		0,0
+	MFDIAG_1	(28)
+	shrpd		ret0,%r0,%sar,%r1
+	MTDIAG_1	(1)
+	STDIAG		(10)
+	ssm		0,0
+	b,n         perf_rdr_shift_in_W_leave
+
+	;
+	; RDR 11 read sequence
+	;
+	SFDIAG		(11)
+	ssm		0,0
+	MFDIAG_1	(28)
+	shrpd		ret0,%r0,%sar,%r1
+	MTDIAG_1	(1)
+	STDIAG		(11)
+	ssm		0,0
+	b,n         perf_rdr_shift_in_W_leave
+
+	;
+	; RDR 12 read sequence
+	;
+	b,n         perf_rdr_shift_in_W_leave
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+
+	;
+	; RDR 13 read sequence
+	;
+	sync
+	ssm		0,0
+	SFDIAG		(13)
+	ssm		0,0
+	MFDIAG_1	(28)
+	b,n         perf_rdr_shift_in_W_leave
+	ssm		0,0
+	nop
+
+	;
+	; RDR 14 read sequence
+	;
+	SFDIAG		(14)
+	ssm		0,0
+	MFDIAG_1	(28)
+	shrpd		ret0,%r0,%sar,%r1
+	MTDIAG_1	(1)
+	STDIAG		(14)
+	ssm		0,0
+	b,n         perf_rdr_shift_in_W_leave
+
+	;
+	; RDR 15 read sequence
+	;
+	sync
+	ssm		0,0
+	SFDIAG		(15)
+	ssm		0,0
+	MFDIAG_1	(28)
+	ssm		0,0
+	b,n         perf_rdr_shift_in_W_leave
+	nop
+
+	;
+	; RDR 16 read sequence
+	;
+	sync
+	ssm		0,0
+	SFDIAG		(16)
+	ssm		0,0
+	MFDIAG_1	(28)
+	b,n         perf_rdr_shift_in_W_leave
+	ssm		0,0
+	nop
+
+	;
+	; RDR 17 read sequence
+	;
+	SFDIAG		(17)
+	ssm		0,0
+	MFDIAG_1	(28)
+	shrpd		ret0,%r0,%sar,%r1
+	MTDIAG_1	(1)
+	STDIAG		(17)
+	ssm		0,0
+	b,n         perf_rdr_shift_in_W_leave
+
+	;
+	; RDR 18 read sequence
+	;
+	SFDIAG		(18)
+	ssm		0,0
+	MFDIAG_1	(28)
+	shrpd		ret0,%r0,%sar,%r1
+	MTDIAG_1	(1)
+	STDIAG		(18)
+	ssm		0,0
+	b,n         perf_rdr_shift_in_W_leave
+
+	;
+	; RDR 19 read sequence
+	;
+	b,n         perf_rdr_shift_in_W_leave
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+
+	;
+	; RDR 20 read sequence
+	;
+	sync
+	ssm		0,0
+	SFDIAG		(20)
+	ssm		0,0
+	MFDIAG_1	(28)
+	b,n         perf_rdr_shift_in_W_leave
+	ssm		0,0
+	nop
+
+	;
+	; RDR 21 read sequence
+	;
+	sync
+	ssm		0,0
+	SFDIAG		(21)
+	ssm		0,0
+	MFDIAG_1	(28)
+	b,n         perf_rdr_shift_in_W_leave
+	ssm		0,0
+	nop
+
+	;
+	; RDR 22 read sequence
+	;
+	sync
+	ssm		0,0
+	SFDIAG		(22)
+	ssm		0,0
+	MFDIAG_1	(28)
+	b,n         perf_rdr_shift_in_W_leave
+	ssm		0,0
+	nop
+
+	;
+	; RDR 23 read sequence
+	;
+	sync
+	ssm		0,0
+	SFDIAG		(23)
+	ssm		0,0
+	MFDIAG_1	(28)
+	b,n         perf_rdr_shift_in_W_leave
+	ssm		0,0
+	nop
+
+	;
+	; RDR 24 read sequence
+	;
+	sync
+	ssm		0,0
+	SFDIAG		(24)
+	ssm		0,0
+	MFDIAG_1	(28)
+	b,n         perf_rdr_shift_in_W_leave
+	ssm		0,0
+	nop
+
+	;
+	; RDR 25 read sequence
+	;
+	sync
+	ssm		0,0
+	SFDIAG		(25)
+	ssm		0,0
+	MFDIAG_1	(28)
+	b,n         perf_rdr_shift_in_W_leave
+	ssm		0,0
+	nop
+
+	;
+	; RDR 26 read sequence
+	;
+	SFDIAG		(26)
+	ssm		0,0
+	MFDIAG_1	(28)
+	shrpd		ret0,%r0,%sar,%r1
+	MTDIAG_1	(1)
+	STDIAG		(26)
+	ssm		0,0
+	b,n         perf_rdr_shift_in_W_leave
+
+	;
+	; RDR 27 read sequence
+	;
+	SFDIAG		(27)
+	ssm		0,0
+	MFDIAG_1	(28)
+	shrpd		ret0,%r0,%sar,%r1
+	MTDIAG_1	(1)
+	STDIAG		(27)
+	ssm		0,0
+	b,n         perf_rdr_shift_in_W_leave
+
+	;
+	; RDR 28 read sequence
+	;
+	sync
+	ssm		0,0
+	SFDIAG		(28)
+	ssm		0,0
+	MFDIAG_1	(28)
+	b,n         perf_rdr_shift_in_W_leave
+	ssm		0,0
+	nop
+
+	;
+	; RDR 29 read sequence
+	;
+	sync
+	ssm		0,0
+	SFDIAG		(29)
+	ssm		0,0
+	MFDIAG_1	(28)
+	b,n         perf_rdr_shift_in_W_leave
+	ssm		0,0
+	nop
+
+	;
+	; RDR 30 read sequence
+	;
+	SFDIAG		(30)
+	ssm		0,0
+	MFDIAG_1	(28)
+	shrpd		ret0,%r0,%sar,%r1
+	MTDIAG_1	(1)
+	STDIAG		(30)
+	ssm		0,0
+	b,n         perf_rdr_shift_in_W_leave
+
+	;
+	; RDR 31 read sequence
+	;
+	sync
+	ssm		0,0
+	SFDIAG		(31)
+	ssm		0,0
+	MFDIAG_1	(28)
+	nop
+	ssm		0,0
+	nop
+
+	;
+	; Fallthrough
+	;
+
+perf_rdr_shift_in_W_leave:
+	bve		    (%r2)
+	.exit
+	MTDIAG_2	(24)			; restore DR2
+	.procend
+ENDPROC(perf_rdr_shift_in_W)
+
+
+;***********************************************************************
+;*
+;* Name: perf_rdr_shift_out_W
+;*
+;* Description:
+;*	This routine moves data to the RDR's.  The double-word that
+;*	arg1 points to is loaded and moved into the staging register.
+;*	Then the STDIAG instruction for the RDR # in arg0 is called
+;*	to move the data to the RDR.
+;*
+;* Arguments:
+;*	arg0 = rdr number
+;*	arg1 = 64-bit value to write
+;*	%r24 - DR2 | DR2_SLOW_RET
+;*	%r23 - original DR2 value
+;*
+;* Returns:
+;*	None
+;*
+;* Register usage:
+;*
+;***********************************************************************
+
+ENTRY(perf_rdr_shift_out_W)
+	.proc
+	.callinfo frame=0,NO_CALLS
+	.entry
+;
+; NOTE: The PCX-W ERS states that DR2_SLOW_RET must be set before any
+; shifting is done, from or to, the remote diagnose registers.
+;
+
+	depdi,z		1,DR2_SLOW_RET,1,%r24
+	MFDIAG_2	(23)
+	or		%r24,%r23,%r24
+	MTDIAG_2	(24)		; set DR2_SLOW_RET
+	MTDIAG_1	(25)		; data to the staging register
+	shladd		arg0,2,%r0,%r1	; %r1 = 4 * RDR number
+	blr		    %r1,%r0	; branch to 8-instruction sequence
+	nop
+
+	;
+	; RDR 0 write sequence
+	;
+	sync				; RDR 0 write sequence
+	ssm		0,0
+	STDIAG		(0)
+	ssm		0,0
+	b,n         perf_rdr_shift_out_W_leave
+	nop
+	ssm		0,0
+	nop
+
+	;
+	; RDR 1 write sequence
+	;
+	sync
+	ssm		0,0
+	STDIAG		(1)
+	ssm		0,0
+	b,n         perf_rdr_shift_out_W_leave
+	nop
+	ssm		0,0
+	nop
+
+	;
+	; RDR 2 write sequence
+	;
+	sync
+	ssm		0,0
+	STDIAG		(2)
+	ssm		0,0
+	b,n         perf_rdr_shift_out_W_leave
+	nop
+	ssm		0,0
+	nop
+
+	;
+	; RDR 3 write sequence
+	;
+	sync
+	ssm		0,0
+	STDIAG		(3)
+	ssm		0,0
+	b,n         perf_rdr_shift_out_W_leave
+	nop
+	ssm		0,0
+	nop
+
+	;
+	; RDR 4 write sequence
+	;
+	sync
+	ssm		0,0
+	STDIAG		(4)
+	ssm		0,0
+	b,n         perf_rdr_shift_out_W_leave
+	nop
+	ssm		0,0
+	nop
+
+	;
+	; RDR 5 write sequence
+	;
+	sync
+	ssm		0,0
+	STDIAG		(5)
+	ssm		0,0
+	b,n         perf_rdr_shift_out_W_leave
+	nop
+	ssm		0,0
+	nop
+
+	;
+	; RDR 6 write sequence
+	;
+	sync
+	ssm		0,0
+	STDIAG		(6)
+	ssm		0,0
+	b,n         perf_rdr_shift_out_W_leave
+	nop
+	ssm		0,0
+	nop
+
+	;
+	; RDR 7 write sequence
+	;
+	sync
+	ssm		0,0
+	STDIAG		(7)
+	ssm		0,0
+	b,n         perf_rdr_shift_out_W_leave
+	nop
+	ssm		0,0
+	nop
+
+	;
+	; RDR 8 write sequence
+	;
+	sync
+	ssm		0,0
+	STDIAG		(8)
+	ssm		0,0
+	b,n         perf_rdr_shift_out_W_leave
+	nop
+	ssm		0,0
+	nop
+
+	;
+	; RDR 9 write sequence
+	;
+	sync
+	ssm		0,0
+	STDIAG		(9)
+	ssm		0,0
+	b,n         perf_rdr_shift_out_W_leave
+	nop
+	ssm		0,0
+	nop
+
+	;
+	; RDR 10 write sequence
+	;
+	sync
+	ssm		0,0
+	STDIAG		(10)
+	STDIAG		(26)
+	ssm		0,0
+	b,n         perf_rdr_shift_out_W_leave
+	ssm		0,0
+	nop
+
+	;
+	; RDR 11 write sequence
+	;
+	sync
+	ssm		0,0
+	STDIAG		(11)
+	STDIAG		(27)
+	ssm		0,0
+	b,n         perf_rdr_shift_out_W_leave
+	ssm		0,0
+	nop
+
+	;
+	; RDR 12 write sequence
+	;
+	sync
+	ssm		0,0
+	STDIAG		(12)
+	ssm		0,0
+	b,n         perf_rdr_shift_out_W_leave
+	nop
+	ssm		0,0
+	nop
+
+	;
+	; RDR 13 write sequence
+	;
+	sync
+	ssm		0,0
+	STDIAG		(13)
+	ssm		0,0
+	b,n         perf_rdr_shift_out_W_leave
+	nop
+	ssm		0,0
+	nop
+
+	;
+	; RDR 14 write sequence
+	;
+	sync
+	ssm		0,0
+	STDIAG		(14)
+	ssm		0,0
+	b,n         perf_rdr_shift_out_W_leave
+	nop
+	ssm		0,0
+	nop
+
+	;
+	; RDR 15 write sequence
+	;
+	sync
+	ssm		0,0
+	STDIAG		(15)
+	ssm		0,0
+	b,n         perf_rdr_shift_out_W_leave
+	nop
+	ssm		0,0
+	nop
+
+	;
+	; RDR 16 write sequence
+	;
+	sync
+	ssm		0,0
+	STDIAG		(16)
+	ssm		0,0
+	b,n         perf_rdr_shift_out_W_leave
+	nop
+	ssm		0,0
+	nop
+
+	;
+	; RDR 17 write sequence
+	;
+	sync
+	ssm		0,0
+	STDIAG		(17)
+	ssm		0,0
+	b,n         perf_rdr_shift_out_W_leave
+	nop
+	ssm		0,0
+	nop
+
+	;
+	; RDR 18 write sequence
+	;
+	sync
+	ssm		0,0
+	STDIAG		(18)
+	ssm		0,0
+	b,n         perf_rdr_shift_out_W_leave
+	nop
+	ssm		0,0
+	nop
+
+	;
+	; RDR 19 write sequence
+	;
+	sync
+	ssm		0,0
+	STDIAG		(19)
+	ssm		0,0
+	b,n         perf_rdr_shift_out_W_leave
+	nop
+	ssm		0,0
+	nop
+
+	;
+	; RDR 20 write sequence
+	;
+	sync
+	ssm		0,0
+	STDIAG		(20)
+	ssm		0,0
+	b,n         perf_rdr_shift_out_W_leave
+	nop
+	ssm		0,0
+	nop
+
+	;
+	; RDR 21 write sequence
+	;
+	sync
+	ssm		0,0
+	STDIAG		(21)
+	ssm		0,0
+	b,n         perf_rdr_shift_out_W_leave
+	nop
+	ssm		0,0
+	nop
+
+	;
+	; RDR 22 write sequence
+	;
+	sync
+	ssm		0,0
+	STDIAG		(22)
+	ssm		0,0
+	b,n         perf_rdr_shift_out_W_leave
+	nop
+	ssm		0,0
+	nop
+
+	;
+	; RDR 23 write sequence
+	;
+	sync
+	ssm		0,0
+	STDIAG		(23)
+	ssm		0,0
+	b,n         perf_rdr_shift_out_W_leave
+	nop
+	ssm		0,0
+	nop
+
+	;
+	; RDR 24 write sequence
+	;
+	sync
+	ssm		0,0
+	STDIAG		(24)
+	ssm		0,0
+	b,n         perf_rdr_shift_out_W_leave
+	nop
+	ssm		0,0
+	nop
+
+	;
+	; RDR 25 write sequence
+	;
+	sync
+	ssm		0,0
+	STDIAG		(25)
+	ssm		0,0
+	b,n         perf_rdr_shift_out_W_leave
+	nop
+	ssm		0,0
+	nop
+
+	;
+	; RDR 26 write sequence
+	;
+	sync
+	ssm		0,0
+	STDIAG		(10)
+	STDIAG		(26)
+	ssm		0,0
+	b,n         perf_rdr_shift_out_W_leave
+	ssm		0,0
+	nop
+
+	;
+	; RDR 27 write sequence
+	;
+	sync
+	ssm		0,0
+	STDIAG		(11)
+	STDIAG		(27)
+	ssm		0,0
+	b,n         perf_rdr_shift_out_W_leave
+	ssm		0,0
+	nop
+
+	;
+	; RDR 28 write sequence
+	;
+	sync
+	ssm		0,0
+	STDIAG		(28)
+	ssm		0,0
+	b,n         perf_rdr_shift_out_W_leave
+	nop
+	ssm		0,0
+	nop
+
+	;
+	; RDR 29 write sequence
+	;
+	sync
+	ssm		0,0
+	STDIAG		(29)
+	ssm		0,0
+	b,n         perf_rdr_shift_out_W_leave
+	nop
+	ssm		0,0
+	nop
+
+	;
+	; RDR 30 write sequence
+	;
+	sync
+	ssm		0,0
+	STDIAG		(30)
+	ssm		0,0
+	b,n         perf_rdr_shift_out_W_leave
+	nop
+	ssm		0,0
+	nop
+
+	;
+	; RDR 31 write sequence
+	;
+	sync
+	ssm		0,0
+	STDIAG		(31)
+	ssm		0,0
+	b,n         perf_rdr_shift_out_W_leave
+	nop
+	ssm		0,0
+	nop
+
+perf_rdr_shift_out_W_leave:
+	bve		(%r2)
+	.exit
+	MTDIAG_2	(23)			; restore DR2
+	.procend
+ENDPROC(perf_rdr_shift_out_W)
+
+
+;***********************************************************************
+;*
+;* Name: rdr_shift_in_U
+;*
+;* Description:
+;*	This routine shifts data in from the RDR in arg0 and returns
+;*	the result in ret0.  If the RDR is <= 64 bits in length, it
+;*	is shifted shifted backup immediately.  This is to compensate
+;*	for RDR10 which has bits that preclude PDC stack operations
+;*	when they are in the wrong state.
+;*
+;* Arguments:
+;*	arg0 : rdr to be read
+;*	arg1 : bit length of rdr
+;*
+;* Returns:
+;*	ret0 = next 64 bits of rdr data from staging register
+;*
+;* Register usage:
+;*	arg0 : rdr to be read						                        
+;*	arg1 : bit length of rdr					                        
+;*	%r24 - original DR2 value
+;*	%r23 - DR2 | DR2_SLOW_RET
+;*	%r1  - scratch
+;*
+;***********************************************************************
+
+ENTRY(perf_rdr_shift_in_U)
+	.proc
+	.callinfo frame=0,NO_CALLS
+	.entry
+
+; read(shift in) the RDR.
+;
+; NOTE: The PCX-U ERS states that DR2_SLOW_RET must be set before any
+; shifting is done, from or to, remote diagnose registers.
+
+	depdi,z		1,DR2_SLOW_RET,1,%r29
+	MFDIAG_2	(24)
+	or			%r24,%r29,%r29
+	MTDIAG_2	(29)			; set DR2_SLOW_RET
+
+	nop
+	nop
+	nop
+	nop
+
+;
+; Start of next 32-byte cacheline
+;
+	nop
+	nop
+	nop
+	extrd,u		arg1,63,6,%r1
+
+	mtsar		%r1
+	shladd		arg0,2,%r0,%r1	; %r1 = 4 * RDR number
+	blr 		%r1,%r0		; branch to 8-instruction sequence
+	nop
+
+;
+; Start of next 32-byte cacheline
+;
+	SFDIAG		(0)		; RDR 0 read sequence
+	ssm		0,0
+	MFDIAG_1	(28)
+	shrpd		ret0,%r0,%sar,%r1
+	MTDIAG_1	(1)
+	STDIAG		(0)
+	ssm		0,0
+	b,n         perf_rdr_shift_in_U_leave
+
+	SFDIAG		(1)		; RDR 1 read sequence
+	ssm		0,0
+	MFDIAG_1	(28)
+	shrpd		ret0,%r0,%sar,%r1
+	MTDIAG_1	(1)
+	STDIAG		(1)
+	ssm		0,0
+	b,n         perf_rdr_shift_in_U_leave
+
+	sync				; RDR 2 read sequence
+	ssm		0,0
+	SFDIAG		(4)
+	ssm		0,0
+	MFDIAG_1	(28)
+	b,n         perf_rdr_shift_in_U_leave
+	ssm		0,0
+	nop
+
+	sync				; RDR 3 read sequence
+	ssm		0,0
+	SFDIAG		(3)
+	ssm		0,0
+	MFDIAG_1	(28)
+	b,n         perf_rdr_shift_in_U_leave
+	ssm		0,0
+	nop
+
+	sync				; RDR 4 read sequence
+	ssm		0,0
+	SFDIAG		(4)
+	ssm		0,0
+	MFDIAG_1	(28)
+	b,n         perf_rdr_shift_in_U_leave
+	ssm		0,0
+	nop
+
+	sync				; RDR 5 read sequence
+	ssm		0,0
+	SFDIAG		(5)
+	ssm		0,0
+	MFDIAG_1	(28)
+	b,n         perf_rdr_shift_in_U_leave
+	ssm		0,0
+	nop
+
+	sync				; RDR 6 read sequence
+	ssm		0,0
+	SFDIAG		(6)
+	ssm		0,0
+	MFDIAG_1	(28)
+	b,n         perf_rdr_shift_in_U_leave
+	ssm		0,0
+	nop
+
+	sync				; RDR 7 read sequence
+	ssm		0,0
+	SFDIAG		(7)
+	ssm		0,0
+	MFDIAG_1	(28)
+	b,n         perf_rdr_shift_in_U_leave
+	ssm		0,0
+	nop
+
+	b,n         perf_rdr_shift_in_U_leave
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+
+	SFDIAG		(9)		; RDR 9 read sequence
+	ssm		0,0
+	MFDIAG_1	(28)
+	shrpd		ret0,%r0,%sar,%r1
+	MTDIAG_1	(1)
+	STDIAG		(9)
+	ssm		0,0
+	b,n         perf_rdr_shift_in_U_leave
+
+	SFDIAG		(10)		; RDR 10 read sequence
+	ssm		0,0
+	MFDIAG_1	(28)
+	shrpd		ret0,%r0,%sar,%r1
+	MTDIAG_1	(1)
+	STDIAG		(10)
+	ssm		0,0
+	b,n         perf_rdr_shift_in_U_leave
+
+	SFDIAG		(11)		; RDR 11 read sequence
+	ssm		0,0
+	MFDIAG_1	(28)
+	shrpd		ret0,%r0,%sar,%r1
+	MTDIAG_1	(1)
+	STDIAG		(11)
+	ssm		0,0
+	b,n         perf_rdr_shift_in_U_leave
+
+	SFDIAG		(12)		; RDR 12 read sequence
+	ssm		0,0
+	MFDIAG_1	(28)
+	shrpd		ret0,%r0,%sar,%r1
+	MTDIAG_1	(1)
+	STDIAG		(12)
+	ssm		0,0
+	b,n         perf_rdr_shift_in_U_leave
+
+	SFDIAG		(13)		; RDR 13 read sequence
+	ssm		0,0
+	MFDIAG_1	(28)
+	shrpd		ret0,%r0,%sar,%r1
+	MTDIAG_1	(1)
+	STDIAG		(13)
+	ssm		0,0
+	b,n         perf_rdr_shift_in_U_leave
+
+	SFDIAG		(14)		; RDR 14 read sequence
+	ssm		0,0
+	MFDIAG_1	(28)
+	shrpd		ret0,%r0,%sar,%r1
+	MTDIAG_1	(1)
+	STDIAG		(14)
+	ssm		0,0
+	b,n         perf_rdr_shift_in_U_leave
+
+	SFDIAG		(15)		; RDR 15 read sequence
+	ssm		0,0
+	MFDIAG_1	(28)
+	shrpd		ret0,%r0,%sar,%r1
+	MTDIAG_1	(1)
+	STDIAG		(15)
+	ssm		0,0
+	b,n         perf_rdr_shift_in_U_leave
+
+	sync				; RDR 16 read sequence
+	ssm		0,0
+	SFDIAG		(16)
+	ssm		0,0
+	MFDIAG_1	(28)
+	b,n         perf_rdr_shift_in_U_leave
+	ssm		0,0
+	nop
+
+	SFDIAG		(17)		; RDR 17 read sequence
+	ssm		0,0
+	MFDIAG_1	(28)
+	shrpd		ret0,%r0,%sar,%r1
+	MTDIAG_1	(1)
+	STDIAG		(17)
+	ssm		0,0
+	b,n         perf_rdr_shift_in_U_leave
+
+	SFDIAG		(18)		; RDR 18 read sequence
+	ssm		0,0
+	MFDIAG_1	(28)
+	shrpd		ret0,%r0,%sar,%r1
+	MTDIAG_1	(1)
+	STDIAG		(18)
+	ssm		0,0
+	b,n         perf_rdr_shift_in_U_leave
+
+	b,n         perf_rdr_shift_in_U_leave
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+
+	sync				; RDR 20 read sequence
+	ssm		0,0
+	SFDIAG		(20)
+	ssm		0,0
+	MFDIAG_1	(28)
+	b,n         perf_rdr_shift_in_U_leave
+	ssm		0,0
+	nop
+
+	sync				; RDR 21 read sequence
+	ssm		0,0
+	SFDIAG		(21)
+	ssm		0,0
+	MFDIAG_1	(28)
+	b,n         perf_rdr_shift_in_U_leave
+	ssm		0,0
+	nop
+
+	sync				; RDR 22 read sequence
+	ssm		0,0
+	SFDIAG		(22)
+	ssm		0,0
+	MFDIAG_1	(28)
+	b,n         perf_rdr_shift_in_U_leave
+	ssm		0,0
+	nop
+
+	sync				; RDR 23 read sequence
+	ssm		0,0
+	SFDIAG		(23)
+	ssm		0,0
+	MFDIAG_1	(28)
+	b,n         perf_rdr_shift_in_U_leave
+	ssm		0,0
+	nop
+
+	sync				; RDR 24 read sequence
+	ssm		0,0
+	SFDIAG		(24)
+	ssm		0,0
+	MFDIAG_1	(28)
+	b,n         perf_rdr_shift_in_U_leave
+	ssm		0,0
+	nop
+
+	sync				; RDR 25 read sequence
+	ssm		0,0
+	SFDIAG		(25)
+	ssm		0,0
+	MFDIAG_1	(28)
+	b,n         perf_rdr_shift_in_U_leave
+	ssm		0,0
+	nop
+
+	SFDIAG		(26)		; RDR 26 read sequence
+	ssm		0,0
+	MFDIAG_1	(28)
+	shrpd		ret0,%r0,%sar,%r1
+	MTDIAG_1	(1)
+	STDIAG		(26)
+	ssm		0,0
+	b,n         perf_rdr_shift_in_U_leave
+
+	SFDIAG		(27)		; RDR 27 read sequence
+	ssm		0,0
+	MFDIAG_1	(28)
+	shrpd		ret0,%r0,%sar,%r1
+	MTDIAG_1	(1)
+	STDIAG		(27)
+	ssm		0,0
+	b,n         perf_rdr_shift_in_U_leave
+
+	sync				; RDR 28 read sequence
+	ssm		0,0
+	SFDIAG		(28)
+	ssm		0,0
+	MFDIAG_1	(28)
+	b,n         perf_rdr_shift_in_U_leave
+	ssm		0,0
+	nop
+
+	b,n         perf_rdr_shift_in_U_leave
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+
+	SFDIAG		(30)		; RDR 30 read sequence
+	ssm		0,0
+	MFDIAG_1	(28)
+	shrpd		ret0,%r0,%sar,%r1
+	MTDIAG_1	(1)
+	STDIAG		(30)
+	ssm		0,0
+	b,n         perf_rdr_shift_in_U_leave
+
+	SFDIAG		(31)		; RDR 31 read sequence
+	ssm		0,0
+	MFDIAG_1	(28)
+	shrpd		ret0,%r0,%sar,%r1
+	MTDIAG_1	(1)
+	STDIAG		(31)
+	ssm		0,0
+	b,n         perf_rdr_shift_in_U_leave
+	nop
+
+perf_rdr_shift_in_U_leave:
+	bve		    (%r2)
+	.exit
+	MTDIAG_2	(24)			; restore DR2
+	.procend
+ENDPROC(perf_rdr_shift_in_U)
+
+;***********************************************************************
+;*
+;* Name: rdr_shift_out_U
+;*
+;* Description:
+;*	This routine moves data to the RDR's.  The double-word that
+;*	arg1 points to is loaded and moved into the staging register.
+;*	Then the STDIAG instruction for the RDR # in arg0 is called
+;*	to move the data to the RDR.
+;*
+;* Arguments:
+;*	arg0 = rdr target
+;*	arg1 = buffer pointer
+;*
+;* Returns:
+;*	None
+;*
+;* Register usage:
+;*	arg0 = rdr target
+;*	arg1 = buffer pointer
+;*	%r24 - DR2 | DR2_SLOW_RET
+;*	%r23 - original DR2 value
+;*
+;***********************************************************************
+
+ENTRY(perf_rdr_shift_out_U)
+	.proc
+	.callinfo frame=0,NO_CALLS
+	.entry
+
+;
+; NOTE: The PCX-U ERS states that DR2_SLOW_RET must be set before any
+; shifting is done, from or to, the remote diagnose registers.
+;
+
+	depdi,z		1,DR2_SLOW_RET,1,%r24
+	MFDIAG_2	(23)
+	or		%r24,%r23,%r24
+	MTDIAG_2	(24)		; set DR2_SLOW_RET
+
+	MTDIAG_1	(25)		; data to the staging register
+	shladd		arg0,2,%r0,%r1	; %r1 = 4 * RDR number
+	blr		%r1,%r0		; branch to 8-instruction sequence
+	nop
+
+;
+; 32-byte cachline aligned
+;
+
+	sync				; RDR 0 write sequence
+	ssm		0,0
+	STDIAG		(0)
+	ssm		0,0
+	b,n         perf_rdr_shift_out_U_leave
+	nop
+	ssm		0,0
+	nop
+
+	sync				; RDR 1 write sequence
+	ssm		0,0
+	STDIAG		(1)
+	ssm		0,0
+	b,n         perf_rdr_shift_out_U_leave
+	nop
+	ssm		0,0
+	nop
+
+	sync				; RDR 2 write sequence
+	ssm		0,0
+	STDIAG		(2)
+	ssm		0,0
+	b,n         perf_rdr_shift_out_U_leave
+	nop
+	ssm		0,0
+	nop
+
+	sync				; RDR 3 write sequence
+	ssm		0,0
+	STDIAG		(3)
+	ssm		0,0
+	b,n         perf_rdr_shift_out_U_leave
+	nop
+	ssm		0,0
+	nop
+
+	sync				; RDR 4 write sequence
+	ssm		0,0
+	STDIAG		(4)
+	ssm		0,0
+	b,n         perf_rdr_shift_out_U_leave
+	nop
+	ssm		0,0
+	nop
+
+	sync				; RDR 5 write sequence
+	ssm		0,0
+	STDIAG		(5)
+	ssm		0,0
+	b,n         perf_rdr_shift_out_U_leave
+	nop
+	ssm		0,0
+	nop
+
+	sync				; RDR 6 write sequence
+	ssm		0,0
+	STDIAG		(6)
+	ssm		0,0
+	b,n         perf_rdr_shift_out_U_leave
+	nop
+	ssm		0,0
+	nop
+
+	sync				; RDR 7 write sequence
+	ssm		0,0
+	STDIAG		(7)
+	ssm		0,0
+	b,n         perf_rdr_shift_out_U_leave
+	nop
+	ssm		0,0
+	nop
+
+	sync				; RDR 8 write sequence
+	ssm		0,0
+	STDIAG		(8)
+	ssm		0,0
+	b,n         perf_rdr_shift_out_U_leave
+	nop
+	ssm		0,0
+	nop
+
+	sync				; RDR 9 write sequence
+	ssm		0,0
+	STDIAG		(9)
+	ssm		0,0
+	b,n         perf_rdr_shift_out_U_leave
+	nop
+	ssm		0,0
+	nop
+
+	sync				; RDR 10 write sequence
+	ssm		0,0
+	STDIAG		(10)
+	ssm		0,0
+	b,n         perf_rdr_shift_out_U_leave
+	nop
+	ssm		0,0
+	nop
+
+	sync				; RDR 11 write sequence
+	ssm		0,0
+	STDIAG		(11)
+	ssm		0,0
+	b,n         perf_rdr_shift_out_U_leave
+	nop
+	ssm		0,0
+	nop
+
+	sync				; RDR 12 write sequence
+	ssm		0,0
+	STDIAG		(12)
+	ssm		0,0
+	b,n         perf_rdr_shift_out_U_leave
+	nop
+	ssm		0,0
+	nop
+
+	sync				; RDR 13 write sequence
+	ssm		0,0
+	STDIAG		(13)
+	ssm		0,0
+	b,n         perf_rdr_shift_out_U_leave
+	nop
+	ssm		0,0
+	nop
+
+	sync				; RDR 14 write sequence
+	ssm		0,0
+	STDIAG		(14)
+	ssm		0,0
+	b,n         perf_rdr_shift_out_U_leave
+	nop
+	ssm		0,0
+	nop
+
+	sync				; RDR 15 write sequence
+	ssm		0,0
+	STDIAG		(15)
+	ssm		0,0
+	b,n         perf_rdr_shift_out_U_leave
+	nop
+	ssm		0,0
+	nop
+
+	sync				; RDR 16 write sequence
+	ssm		0,0
+	STDIAG		(16)
+	ssm		0,0
+	b,n         perf_rdr_shift_out_U_leave
+	nop
+	ssm		0,0
+	nop
+
+	sync				; RDR 17 write sequence
+	ssm		0,0
+	STDIAG		(17)
+	ssm		0,0
+	b,n         perf_rdr_shift_out_U_leave
+	nop
+	ssm		0,0
+	nop
+
+	sync				; RDR 18 write sequence
+	ssm		0,0
+	STDIAG		(18)
+	ssm		0,0
+	b,n         perf_rdr_shift_out_U_leave
+	nop
+	ssm		0,0
+	nop
+
+	sync				; RDR 19 write sequence
+	ssm		0,0
+	STDIAG		(19)
+	ssm		0,0
+	b,n         perf_rdr_shift_out_U_leave
+	nop
+	ssm		0,0
+	nop
+
+	sync				; RDR 20 write sequence
+	ssm		0,0
+	STDIAG		(20)
+	ssm		0,0
+	b,n         perf_rdr_shift_out_U_leave
+	nop
+	ssm		0,0
+	nop
+
+	sync				; RDR 21 write sequence
+	ssm		0,0
+	STDIAG		(21)
+	ssm		0,0
+	b,n         perf_rdr_shift_out_U_leave
+	nop
+	ssm		0,0
+	nop
+
+	sync				; RDR 22 write sequence
+	ssm		0,0
+	STDIAG		(22)
+	ssm		0,0
+	b,n         perf_rdr_shift_out_U_leave
+	nop
+	ssm		0,0
+	nop
+
+	sync				; RDR 23 write sequence
+	ssm		0,0
+	STDIAG		(23)
+	ssm		0,0
+	b,n         perf_rdr_shift_out_U_leave
+	nop
+	ssm		0,0
+	nop
+
+	sync				; RDR 24 write sequence
+	ssm		0,0
+	STDIAG		(24)
+	ssm		0,0
+	b,n         perf_rdr_shift_out_U_leave
+	nop
+	ssm		0,0
+	nop
+
+	sync				; RDR 25 write sequence
+	ssm		0,0
+	STDIAG		(25)
+	ssm		0,0
+	b,n         perf_rdr_shift_out_U_leave
+	nop
+	ssm		0,0
+	nop
+
+	sync				; RDR 26 write sequence
+	ssm		0,0
+	STDIAG		(26)
+	ssm		0,0
+	b,n         perf_rdr_shift_out_U_leave
+	nop
+	ssm		0,0
+	nop
+
+	sync				; RDR 27 write sequence
+	ssm		0,0
+	STDIAG		(27)
+	ssm		0,0
+	b,n         perf_rdr_shift_out_U_leave
+	nop
+	ssm		0,0
+	nop
+
+	sync				; RDR 28 write sequence
+	ssm		0,0
+	STDIAG		(28)
+	ssm		0,0
+	b,n         perf_rdr_shift_out_U_leave
+	nop
+	ssm		0,0
+	nop
+
+	sync				; RDR 29 write sequence
+	ssm		0,0
+	STDIAG		(29)
+	ssm		0,0
+	b,n         perf_rdr_shift_out_U_leave
+	nop
+	ssm		0,0
+	nop
+
+	sync				; RDR 30 write sequence
+	ssm		0,0
+	STDIAG		(30)
+	ssm		0,0
+	b,n         perf_rdr_shift_out_U_leave
+	nop
+	ssm		0,0
+	nop
+
+	sync				; RDR 31 write sequence
+	ssm		0,0
+	STDIAG		(31)
+	ssm		0,0
+	b,n         perf_rdr_shift_out_U_leave
+	nop
+	ssm		0,0
+	nop
+
+perf_rdr_shift_out_U_leave:
+	bve		(%r2)
+	.exit
+	MTDIAG_2	(23)			; restore DR2
+	.procend
+ENDPROC(perf_rdr_shift_out_U)
+