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, 683 insertions, 0 deletions

diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c
new file mode 100644
index 000000000..91c2b8124
--- /dev/null
+++ b/arch/sparc/kernel/process_64.c
@@ -0,0 +1,683 @@
+// SPDX-License-Identifier: GPL-2.0
+/*  arch/sparc64/kernel/process.c
+ *
+ *  Copyright (C) 1995, 1996, 2008 David S. Miller (davem@davemloft.net)
+ *  Copyright (C) 1996       Eddie C. Dost   (ecd@skynet.be)
+ *  Copyright (C) 1997, 1998 Jakub Jelinek   (jj@sunsite.mff.cuni.cz)
+ */
+
+/*
+ * This file handles the architecture-dependent parts of process handling..
+ */
+#include <linux/errno.h>
+#include <linux/export.h>
+#include <linux/sched.h>
+#include <linux/sched/debug.h>
+#include <linux/sched/task.h>
+#include <linux/sched/task_stack.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/fs.h>
+#include <linux/smp.h>
+#include <linux/stddef.h>
+#include <linux/ptrace.h>
+#include <linux/slab.h>
+#include <linux/user.h>
+#include <linux/delay.h>
+#include <linux/compat.h>
+#include <linux/tick.h>
+#include <linux/init.h>
+#include <linux/cpu.h>
+#include <linux/perf_event.h>
+#include <linux/elfcore.h>
+#include <linux/sysrq.h>
+#include <linux/nmi.h>
+#include <linux/context_tracking.h>
+#include <linux/signal.h>
+
+#include <linux/uaccess.h>
+#include <asm/page.h>
+#include <asm/pgalloc.h>
+#include <asm/processor.h>
+#include <asm/pstate.h>
+#include <asm/elf.h>
+#include <asm/fpumacro.h>
+#include <asm/head.h>
+#include <asm/cpudata.h>
+#include <asm/mmu_context.h>
+#include <asm/unistd.h>
+#include <asm/hypervisor.h>
+#include <asm/syscalls.h>
+#include <asm/irq_regs.h>
+#include <asm/smp.h>
+#include <asm/pcr.h>
+
+#include "kstack.h"
+
+/* Idle loop support on sparc64. */
+void arch_cpu_idle(void)
+{
+	if (tlb_type != hypervisor) {
+		touch_nmi_watchdog();
+	} else {
+		unsigned long pstate;
+
+		raw_local_irq_enable();
+
+                /* The sun4v sleeping code requires that we have PSTATE.IE cleared over
+                 * the cpu sleep hypervisor call.
+                 */
+		__asm__ __volatile__(
+			"rdpr %%pstate, %0\n\t"
+			"andn %0, %1, %0\n\t"
+			"wrpr %0, %%g0, %%pstate"
+			: "=&r" (pstate)
+			: "i" (PSTATE_IE));
+
+		if (!need_resched() && !cpu_is_offline(smp_processor_id())) {
+			sun4v_cpu_yield();
+			/* If resumed by cpu_poke then we need to explicitly
+			 * call scheduler_ipi().
+			 */
+			scheduler_poke();
+		}
+
+		/* Re-enable interrupts. */
+		__asm__ __volatile__(
+			"rdpr %%pstate, %0\n\t"
+			"or %0, %1, %0\n\t"
+			"wrpr %0, %%g0, %%pstate"
+			: "=&r" (pstate)
+			: "i" (PSTATE_IE));
+
+		raw_local_irq_disable();
+	}
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+void arch_cpu_idle_dead(void)
+{
+	sched_preempt_enable_no_resched();
+	cpu_play_dead();
+}
+#endif
+
+#ifdef CONFIG_COMPAT
+static void show_regwindow32(struct pt_regs *regs)
+{
+	struct reg_window32 __user *rw;
+	struct reg_window32 r_w;
+	
+	__asm__ __volatile__ ("flushw");
+	rw = compat_ptr((unsigned int)regs->u_regs[14]);
+	if (copy_from_user (&r_w, rw, sizeof(r_w))) {
+		return;
+	}
+
+	printk("l0: %08x l1: %08x l2: %08x l3: %08x "
+	       "l4: %08x l5: %08x l6: %08x l7: %08x\n",
+	       r_w.locals[0], r_w.locals[1], r_w.locals[2], r_w.locals[3],
+	       r_w.locals[4], r_w.locals[5], r_w.locals[6], r_w.locals[7]);
+	printk("i0: %08x i1: %08x i2: %08x i3: %08x "
+	       "i4: %08x i5: %08x i6: %08x i7: %08x\n",
+	       r_w.ins[0], r_w.ins[1], r_w.ins[2], r_w.ins[3],
+	       r_w.ins[4], r_w.ins[5], r_w.ins[6], r_w.ins[7]);
+}
+#else
+#define show_regwindow32(regs)	do { } while (0)
+#endif
+
+static void show_regwindow(struct pt_regs *regs)
+{
+	struct reg_window __user *rw;
+	struct reg_window *rwk;
+	struct reg_window r_w;
+
+	if ((regs->tstate & TSTATE_PRIV) || !(test_thread_flag(TIF_32BIT))) {
+		__asm__ __volatile__ ("flushw");
+		rw = (struct reg_window __user *)
+			(regs->u_regs[14] + STACK_BIAS);
+		rwk = (struct reg_window *)
+			(regs->u_regs[14] + STACK_BIAS);
+		if (!(regs->tstate & TSTATE_PRIV)) {
+			if (copy_from_user (&r_w, rw, sizeof(r_w))) {
+				return;
+			}
+			rwk = &r_w;
+		}
+	} else {
+		show_regwindow32(regs);
+		return;
+	}
+	printk("l0: %016lx l1: %016lx l2: %016lx l3: %016lx\n",
+	       rwk->locals[0], rwk->locals[1], rwk->locals[2], rwk->locals[3]);
+	printk("l4: %016lx l5: %016lx l6: %016lx l7: %016lx\n",
+	       rwk->locals[4], rwk->locals[5], rwk->locals[6], rwk->locals[7]);
+	printk("i0: %016lx i1: %016lx i2: %016lx i3: %016lx\n",
+	       rwk->ins[0], rwk->ins[1], rwk->ins[2], rwk->ins[3]);
+	printk("i4: %016lx i5: %016lx i6: %016lx i7: %016lx\n",
+	       rwk->ins[4], rwk->ins[5], rwk->ins[6], rwk->ins[7]);
+	if (regs->tstate & TSTATE_PRIV)
+		printk("I7: <%pS>\n", (void *) rwk->ins[7]);
+}
+
+void show_regs(struct pt_regs *regs)
+{
+	show_regs_print_info(KERN_DEFAULT);
+
+	printk("TSTATE: %016lx TPC: %016lx TNPC: %016lx Y: %08x    %s\n", regs->tstate,
+	       regs->tpc, regs->tnpc, regs->y, print_tainted());
+	printk("TPC: <%pS>\n", (void *) regs->tpc);
+	printk("g0: %016lx g1: %016lx g2: %016lx g3: %016lx\n",
+	       regs->u_regs[0], regs->u_regs[1], regs->u_regs[2],
+	       regs->u_regs[3]);
+	printk("g4: %016lx g5: %016lx g6: %016lx g7: %016lx\n",
+	       regs->u_regs[4], regs->u_regs[5], regs->u_regs[6],
+	       regs->u_regs[7]);
+	printk("o0: %016lx o1: %016lx o2: %016lx o3: %016lx\n",
+	       regs->u_regs[8], regs->u_regs[9], regs->u_regs[10],
+	       regs->u_regs[11]);
+	printk("o4: %016lx o5: %016lx sp: %016lx ret_pc: %016lx\n",
+	       regs->u_regs[12], regs->u_regs[13], regs->u_regs[14],
+	       regs->u_regs[15]);
+	printk("RPC: <%pS>\n", (void *) regs->u_regs[15]);
+	show_regwindow(regs);
+	show_stack(current, (unsigned long *)regs->u_regs[UREG_FP], KERN_DEFAULT);
+}
+
+union global_cpu_snapshot global_cpu_snapshot[NR_CPUS];
+static DEFINE_SPINLOCK(global_cpu_snapshot_lock);
+
+static void __global_reg_self(struct thread_info *tp, struct pt_regs *regs,
+			      int this_cpu)
+{
+	struct global_reg_snapshot *rp;
+
+	flushw_all();
+
+	rp = &global_cpu_snapshot[this_cpu].reg;
+
+	rp->tstate = regs->tstate;
+	rp->tpc = regs->tpc;
+	rp->tnpc = regs->tnpc;
+	rp->o7 = regs->u_regs[UREG_I7];
+
+	if (regs->tstate & TSTATE_PRIV) {
+		struct reg_window *rw;
+
+		rw = (struct reg_window *)
+			(regs->u_regs[UREG_FP] + STACK_BIAS);
+		if (kstack_valid(tp, (unsigned long) rw)) {
+			rp->i7 = rw->ins[7];
+			rw = (struct reg_window *)
+				(rw->ins[6] + STACK_BIAS);
+			if (kstack_valid(tp, (unsigned long) rw))
+				rp->rpc = rw->ins[7];
+		}
+	} else {
+		rp->i7 = 0;
+		rp->rpc = 0;
+	}
+	rp->thread = tp;
+}
+
+/* In order to avoid hangs we do not try to synchronize with the
+ * global register dump client cpus.  The last store they make is to
+ * the thread pointer, so do a short poll waiting for that to become
+ * non-NULL.
+ */
+static void __global_reg_poll(struct global_reg_snapshot *gp)
+{
+	int limit = 0;
+
+	while (!gp->thread && ++limit < 100) {
+		barrier();
+		udelay(1);
+	}
+}
+
+void arch_trigger_cpumask_backtrace(const cpumask_t *mask, bool exclude_self)
+{
+	struct thread_info *tp = current_thread_info();
+	struct pt_regs *regs = get_irq_regs();
+	unsigned long flags;
+	int this_cpu, cpu;
+
+	if (!regs)
+		regs = tp->kregs;
+
+	spin_lock_irqsave(&global_cpu_snapshot_lock, flags);
+
+	this_cpu = raw_smp_processor_id();
+
+	memset(global_cpu_snapshot, 0, sizeof(global_cpu_snapshot));
+
+	if (cpumask_test_cpu(this_cpu, mask) && !exclude_self)
+		__global_reg_self(tp, regs, this_cpu);
+
+	smp_fetch_global_regs();
+
+	for_each_cpu(cpu, mask) {
+		struct global_reg_snapshot *gp;
+
+		if (exclude_self && cpu == this_cpu)
+			continue;
+
+		gp = &global_cpu_snapshot[cpu].reg;
+
+		__global_reg_poll(gp);
+
+		tp = gp->thread;
+		printk("%c CPU[%3d]: TSTATE[%016lx] TPC[%016lx] TNPC[%016lx] TASK[%s:%d]\n",
+		       (cpu == this_cpu ? '*' : ' '), cpu,
+		       gp->tstate, gp->tpc, gp->tnpc,
+		       ((tp && tp->task) ? tp->task->comm : "NULL"),
+		       ((tp && tp->task) ? tp->task->pid : -1));
+
+		if (gp->tstate & TSTATE_PRIV) {
+			printk("             TPC[%pS] O7[%pS] I7[%pS] RPC[%pS]\n",
+			       (void *) gp->tpc,
+			       (void *) gp->o7,
+			       (void *) gp->i7,
+			       (void *) gp->rpc);
+		} else {
+			printk("             TPC[%lx] O7[%lx] I7[%lx] RPC[%lx]\n",
+			       gp->tpc, gp->o7, gp->i7, gp->rpc);
+		}
+
+		touch_nmi_watchdog();
+	}
+
+	memset(global_cpu_snapshot, 0, sizeof(global_cpu_snapshot));
+
+	spin_unlock_irqrestore(&global_cpu_snapshot_lock, flags);
+}
+
+#ifdef CONFIG_MAGIC_SYSRQ
+
+static void sysrq_handle_globreg(int key)
+{
+	trigger_all_cpu_backtrace();
+}
+
+static const struct sysrq_key_op sparc_globalreg_op = {
+	.handler	= sysrq_handle_globreg,
+	.help_msg	= "global-regs(y)",
+	.action_msg	= "Show Global CPU Regs",
+};
+
+static void __global_pmu_self(int this_cpu)
+{
+	struct global_pmu_snapshot *pp;
+	int i, num;
+
+	if (!pcr_ops)
+		return;
+
+	pp = &global_cpu_snapshot[this_cpu].pmu;
+
+	num = 1;
+	if (tlb_type == hypervisor &&
+	    sun4v_chip_type >= SUN4V_CHIP_NIAGARA4)
+		num = 4;
+
+	for (i = 0; i < num; i++) {
+		pp->pcr[i] = pcr_ops->read_pcr(i);
+		pp->pic[i] = pcr_ops->read_pic(i);
+	}
+}
+
+static void __global_pmu_poll(struct global_pmu_snapshot *pp)
+{
+	int limit = 0;
+
+	while (!pp->pcr[0] && ++limit < 100) {
+		barrier();
+		udelay(1);
+	}
+}
+
+static void pmu_snapshot_all_cpus(void)
+{
+	unsigned long flags;
+	int this_cpu, cpu;
+
+	spin_lock_irqsave(&global_cpu_snapshot_lock, flags);
+
+	memset(global_cpu_snapshot, 0, sizeof(global_cpu_snapshot));
+
+	this_cpu = raw_smp_processor_id();
+
+	__global_pmu_self(this_cpu);
+
+	smp_fetch_global_pmu();
+
+	for_each_online_cpu(cpu) {
+		struct global_pmu_snapshot *pp = &global_cpu_snapshot[cpu].pmu;
+
+		__global_pmu_poll(pp);
+
+		printk("%c CPU[%3d]: PCR[%08lx:%08lx:%08lx:%08lx] PIC[%08lx:%08lx:%08lx:%08lx]\n",
+		       (cpu == this_cpu ? '*' : ' '), cpu,
+		       pp->pcr[0], pp->pcr[1], pp->pcr[2], pp->pcr[3],
+		       pp->pic[0], pp->pic[1], pp->pic[2], pp->pic[3]);
+
+		touch_nmi_watchdog();
+	}
+
+	memset(global_cpu_snapshot, 0, sizeof(global_cpu_snapshot));
+
+	spin_unlock_irqrestore(&global_cpu_snapshot_lock, flags);
+}
+
+static void sysrq_handle_globpmu(int key)
+{
+	pmu_snapshot_all_cpus();
+}
+
+static const struct sysrq_key_op sparc_globalpmu_op = {
+	.handler	= sysrq_handle_globpmu,
+	.help_msg	= "global-pmu(x)",
+	.action_msg	= "Show Global PMU Regs",
+};
+
+static int __init sparc_sysrq_init(void)
+{
+	int ret = register_sysrq_key('y', &sparc_globalreg_op);
+
+	if (!ret)
+		ret = register_sysrq_key('x', &sparc_globalpmu_op);
+	return ret;
+}
+
+core_initcall(sparc_sysrq_init);
+
+#endif
+
+/* Free current thread data structures etc.. */
+void exit_thread(struct task_struct *tsk)
+{
+	struct thread_info *t = task_thread_info(tsk);
+
+	if (t->utraps) {
+		if (t->utraps[0] < 2)
+			kfree (t->utraps);
+		else
+			t->utraps[0]--;
+	}
+}
+
+void flush_thread(void)
+{
+	struct thread_info *t = current_thread_info();
+	struct mm_struct *mm;
+
+	mm = t->task->mm;
+	if (mm)
+		tsb_context_switch(mm);
+
+	set_thread_wsaved(0);
+
+	/* Clear FPU register state. */
+	t->fpsaved[0] = 0;
+}
+
+/* It's a bit more tricky when 64-bit tasks are involved... */
+static unsigned long clone_stackframe(unsigned long csp, unsigned long psp)
+{
+	bool stack_64bit = test_thread_64bit_stack(psp);
+	unsigned long fp, distance, rval;
+
+	if (stack_64bit) {
+		csp += STACK_BIAS;
+		psp += STACK_BIAS;
+		__get_user(fp, &(((struct reg_window __user *)psp)->ins[6]));
+		fp += STACK_BIAS;
+		if (test_thread_flag(TIF_32BIT))
+			fp &= 0xffffffff;
+	} else
+		__get_user(fp, &(((struct reg_window32 __user *)psp)->ins[6]));
+
+	/* Now align the stack as this is mandatory in the Sparc ABI
+	 * due to how register windows work.  This hides the
+	 * restriction from thread libraries etc.
+	 */
+	csp &= ~15UL;
+
+	distance = fp - psp;
+	rval = (csp - distance);
+	if (raw_copy_in_user((void __user *)rval, (void __user *)psp, distance))
+		rval = 0;
+	else if (!stack_64bit) {
+		if (put_user(((u32)csp),
+			     &(((struct reg_window32 __user *)rval)->ins[6])))
+			rval = 0;
+	} else {
+		if (put_user(((u64)csp - STACK_BIAS),
+			     &(((struct reg_window __user *)rval)->ins[6])))
+			rval = 0;
+		else
+			rval = rval - STACK_BIAS;
+	}
+
+	return rval;
+}
+
+/* Standard stuff. */
+static inline void shift_window_buffer(int first_win, int last_win,
+				       struct thread_info *t)
+{
+	int i;
+
+	for (i = first_win; i < last_win; i++) {
+		t->rwbuf_stkptrs[i] = t->rwbuf_stkptrs[i+1];
+		memcpy(&t->reg_window[i], &t->reg_window[i+1],
+		       sizeof(struct reg_window));
+	}
+}
+
+void synchronize_user_stack(void)
+{
+	struct thread_info *t = current_thread_info();
+	unsigned long window;
+
+	flush_user_windows();
+	if ((window = get_thread_wsaved()) != 0) {
+		window -= 1;
+		do {
+			struct reg_window *rwin = &t->reg_window[window];
+			int winsize = sizeof(struct reg_window);
+			unsigned long sp;
+
+			sp = t->rwbuf_stkptrs[window];
+
+			if (test_thread_64bit_stack(sp))
+				sp += STACK_BIAS;
+			else
+				winsize = sizeof(struct reg_window32);
+
+			if (!copy_to_user((char __user *)sp, rwin, winsize)) {
+				shift_window_buffer(window, get_thread_wsaved() - 1, t);
+				set_thread_wsaved(get_thread_wsaved() - 1);
+			}
+		} while (window--);
+	}
+}
+
+static void stack_unaligned(unsigned long sp)
+{
+	force_sig_fault(SIGBUS, BUS_ADRALN, (void __user *) sp);
+}
+
+static const char uwfault32[] = KERN_INFO \
+	"%s[%d]: bad register window fault: SP %08lx (orig_sp %08lx) TPC %08lx O7 %08lx\n";
+static const char uwfault64[] = KERN_INFO \
+	"%s[%d]: bad register window fault: SP %016lx (orig_sp %016lx) TPC %08lx O7 %016lx\n";
+
+void fault_in_user_windows(struct pt_regs *regs)
+{
+	struct thread_info *t = current_thread_info();
+	unsigned long window;
+
+	flush_user_windows();
+	window = get_thread_wsaved();
+
+	if (likely(window != 0)) {
+		window -= 1;
+		do {
+			struct reg_window *rwin = &t->reg_window[window];
+			int winsize = sizeof(struct reg_window);
+			unsigned long sp, orig_sp;
+
+			orig_sp = sp = t->rwbuf_stkptrs[window];
+
+			if (test_thread_64bit_stack(sp))
+				sp += STACK_BIAS;
+			else
+				winsize = sizeof(struct reg_window32);
+
+			if (unlikely(sp & 0x7UL))
+				stack_unaligned(sp);
+
+			if (unlikely(copy_to_user((char __user *)sp,
+						  rwin, winsize))) {
+				if (show_unhandled_signals)
+					printk_ratelimited(is_compat_task() ?
+							   uwfault32 : uwfault64,
+							   current->comm, current->pid,
+							   sp, orig_sp,
+							   regs->tpc,
+							   regs->u_regs[UREG_I7]);
+				goto barf;
+			}
+		} while (window--);
+	}
+	set_thread_wsaved(0);
+	return;
+
+barf:
+	set_thread_wsaved(window + 1);
+	force_sig(SIGSEGV);
+}
+
+/* Copy a Sparc thread.  The fork() return value conventions
+ * under SunOS are nothing short of bletcherous:
+ * Parent -->  %o0 == childs  pid, %o1 == 0
+ * Child  -->  %o0 == parents pid, %o1 == 1
+ */
+int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
+{
+	unsigned long clone_flags = args->flags;
+	unsigned long sp = args->stack;
+	unsigned long tls = args->tls;
+	struct thread_info *t = task_thread_info(p);
+	struct pt_regs *regs = current_pt_regs();
+	struct sparc_stackf *parent_sf;
+	unsigned long child_stack_sz;
+	char *child_trap_frame;
+
+	/* Calculate offset to stack_frame & pt_regs */
+	child_stack_sz = (STACKFRAME_SZ + TRACEREG_SZ);
+	child_trap_frame = (task_stack_page(p) +
+			    (THREAD_SIZE - child_stack_sz));
+
+	t->new_child = 1;
+	t->ksp = ((unsigned long) child_trap_frame) - STACK_BIAS;
+	t->kregs = (struct pt_regs *) (child_trap_frame +
+				       sizeof(struct sparc_stackf));
+	t->fpsaved[0] = 0;
+
+	if (unlikely(args->fn)) {
+		memset(child_trap_frame, 0, child_stack_sz);
+		__thread_flag_byte_ptr(t)[TI_FLAG_BYTE_CWP] = 
+			(current_pt_regs()->tstate + 1) & TSTATE_CWP;
+		t->kregs->u_regs[UREG_G1] = (unsigned long) args->fn;
+		t->kregs->u_regs[UREG_G2] = (unsigned long) args->fn_arg;
+		return 0;
+	}
+
+	parent_sf = ((struct sparc_stackf *) regs) - 1;
+	memcpy(child_trap_frame, parent_sf, child_stack_sz);
+	if (t->flags & _TIF_32BIT) {
+		sp &= 0x00000000ffffffffUL;
+		regs->u_regs[UREG_FP] &= 0x00000000ffffffffUL;
+	}
+	t->kregs->u_regs[UREG_FP] = sp;
+	__thread_flag_byte_ptr(t)[TI_FLAG_BYTE_CWP] = 
+		(regs->tstate + 1) & TSTATE_CWP;
+	if (sp != regs->u_regs[UREG_FP]) {
+		unsigned long csp;
+
+		csp = clone_stackframe(sp, regs->u_regs[UREG_FP]);
+		if (!csp)
+			return -EFAULT;
+		t->kregs->u_regs[UREG_FP] = csp;
+	}
+	if (t->utraps)
+		t->utraps[0]++;
+
+	/* Set the return value for the child. */
+	t->kregs->u_regs[UREG_I0] = current->pid;
+	t->kregs->u_regs[UREG_I1] = 1;
+
+	/* Set the second return value for the parent. */
+	regs->u_regs[UREG_I1] = 0;
+
+	if (clone_flags & CLONE_SETTLS)
+		t->kregs->u_regs[UREG_G7] = tls;
+
+	return 0;
+}
+
+/* TIF_MCDPER in thread info flags for current task is updated lazily upon
+ * a context switch. Update this flag in current task's thread flags
+ * before dup so the dup'd task will inherit the current TIF_MCDPER flag.
+ */
+int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
+{
+	if (adi_capable()) {
+		register unsigned long tmp_mcdper;
+
+		__asm__ __volatile__(
+			".word 0x83438000\n\t"	/* rd  %mcdper, %g1 */
+			"mov %%g1, %0\n\t"
+			: "=r" (tmp_mcdper)
+			:
+			: "g1");
+		if (tmp_mcdper)
+			set_thread_flag(TIF_MCDPER);
+		else
+			clear_thread_flag(TIF_MCDPER);
+	}
+
+	*dst = *src;
+	return 0;
+}
+
+unsigned long __get_wchan(struct task_struct *task)
+{
+	unsigned long pc, fp, bias = 0;
+	struct thread_info *tp;
+	struct reg_window *rw;
+        unsigned long ret = 0;
+	int count = 0; 
+
+	tp = task_thread_info(task);
+	bias = STACK_BIAS;
+	fp = task_thread_info(task)->ksp + bias;
+
+	do {
+		if (!kstack_valid(tp, fp))
+			break;
+		rw = (struct reg_window *) fp;
+		pc = rw->ins[7];
+		if (!in_sched_functions(pc)) {
+			ret = pc;
+			goto out;
+		}
+		fp = rw->ins[6] + bias;
+	} while (++count < 16);
+
+out:
+	return ret;
+}