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, 495 insertions, 0 deletions

diff --git a/arch/powerpc/kernel/irq_64.c b/arch/powerpc/kernel/irq_64.c
new file mode 100644
index 000000000..eb2b380e5
--- /dev/null
+++ b/arch/powerpc/kernel/irq_64.c
@@ -0,0 +1,495 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ *  Derived from arch/i386/kernel/irq.c
+ *    Copyright (C) 1992 Linus Torvalds
+ *  Adapted from arch/i386 by Gary Thomas
+ *    Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
+ *  Updated and modified by Cort Dougan <cort@fsmlabs.com>
+ *    Copyright (C) 1996-2001 Cort Dougan
+ *  Adapted for Power Macintosh by Paul Mackerras
+ *    Copyright (C) 1996 Paul Mackerras (paulus@cs.anu.edu.au)
+ *
+ * This file contains the code used by various IRQ handling routines:
+ * asking for different IRQ's should be done through these routines
+ * instead of just grabbing them. Thus setups with different IRQ numbers
+ * shouldn't result in any weird surprises, and installing new handlers
+ * should be easier.
+ */
+
+#undef DEBUG
+
+#include <linux/export.h>
+#include <linux/threads.h>
+#include <linux/kernel_stat.h>
+#include <linux/signal.h>
+#include <linux/sched.h>
+#include <linux/ptrace.h>
+#include <linux/ioport.h>
+#include <linux/interrupt.h>
+#include <linux/timex.h>
+#include <linux/init.h>
+#include <linux/slab.h>
+#include <linux/delay.h>
+#include <linux/irq.h>
+#include <linux/seq_file.h>
+#include <linux/cpumask.h>
+#include <linux/profile.h>
+#include <linux/bitops.h>
+#include <linux/list.h>
+#include <linux/radix-tree.h>
+#include <linux/mutex.h>
+#include <linux/pci.h>
+#include <linux/debugfs.h>
+#include <linux/of.h>
+#include <linux/of_irq.h>
+#include <linux/vmalloc.h>
+#include <linux/pgtable.h>
+#include <linux/static_call.h>
+
+#include <linux/uaccess.h>
+#include <asm/interrupt.h>
+#include <asm/io.h>
+#include <asm/irq.h>
+#include <asm/cache.h>
+#include <asm/ptrace.h>
+#include <asm/machdep.h>
+#include <asm/udbg.h>
+#include <asm/smp.h>
+#include <asm/hw_irq.h>
+#include <asm/softirq_stack.h>
+#include <asm/ppc_asm.h>
+
+#include <asm/paca.h>
+#include <asm/firmware.h>
+#include <asm/lv1call.h>
+#include <asm/dbell.h>
+#include <asm/trace.h>
+#include <asm/cpu_has_feature.h>
+
+int distribute_irqs = 1;
+
+static inline void next_interrupt(struct pt_regs *regs)
+{
+	/*
+	 * Softirq processing can enable/disable irqs, which will leave
+	 * MSR[EE] enabled and the soft mask set to IRQS_DISABLED. Fix
+	 * this up.
+	 */
+	if (!(local_paca->irq_happened & PACA_IRQ_HARD_DIS))
+		hard_irq_disable();
+	else
+		irq_soft_mask_set(IRQS_ALL_DISABLED);
+
+	/*
+	 * We are responding to the next interrupt, so interrupt-off
+	 * latencies should be reset here.
+	 */
+	trace_hardirqs_on();
+	trace_hardirqs_off();
+}
+
+static inline bool irq_happened_test_and_clear(u8 irq)
+{
+	if (local_paca->irq_happened & irq) {
+		local_paca->irq_happened &= ~irq;
+		return true;
+	}
+	return false;
+}
+
+void replay_soft_interrupts(void)
+{
+	struct pt_regs regs;
+
+	/*
+	 * Be careful here, calling these interrupt handlers can cause
+	 * softirqs to be raised, which they may run when calling irq_exit,
+	 * which will cause local_irq_enable() to be run, which can then
+	 * recurse into this function. Don't keep any state across
+	 * interrupt handler calls which may change underneath us.
+	 *
+	 * Softirqs can not be disabled over replay to stop this recursion
+	 * because interrupts taken in idle code may require RCU softirq
+	 * to run in the irq RCU tracking context. This is a hard problem
+	 * to fix without changes to the softirq or idle layer.
+	 *
+	 * We use local_paca rather than get_paca() to avoid all the
+	 * debug_smp_processor_id() business in this low level function.
+	 */
+
+	if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) {
+		WARN_ON_ONCE(mfmsr() & MSR_EE);
+		WARN_ON(!(local_paca->irq_happened & PACA_IRQ_HARD_DIS));
+	}
+
+	ppc_save_regs(&regs);
+	regs.softe = IRQS_ENABLED;
+	regs.msr |= MSR_EE;
+
+again:
+	/*
+	 * Force the delivery of pending soft-disabled interrupts on PS3.
+	 * Any HV call will have this side effect.
+	 */
+	if (firmware_has_feature(FW_FEATURE_PS3_LV1)) {
+		u64 tmp, tmp2;
+		lv1_get_version_info(&tmp, &tmp2);
+	}
+
+	/*
+	 * Check if an hypervisor Maintenance interrupt happened.
+	 * This is a higher priority interrupt than the others, so
+	 * replay it first.
+	 */
+	if (IS_ENABLED(CONFIG_PPC_BOOK3S) &&
+	    irq_happened_test_and_clear(PACA_IRQ_HMI)) {
+		regs.trap = INTERRUPT_HMI;
+		handle_hmi_exception(&regs);
+		next_interrupt(&regs);
+	}
+
+	if (irq_happened_test_and_clear(PACA_IRQ_DEC)) {
+		regs.trap = INTERRUPT_DECREMENTER;
+		timer_interrupt(&regs);
+		next_interrupt(&regs);
+	}
+
+	if (irq_happened_test_and_clear(PACA_IRQ_EE)) {
+		regs.trap = INTERRUPT_EXTERNAL;
+		do_IRQ(&regs);
+		next_interrupt(&regs);
+	}
+
+	if (IS_ENABLED(CONFIG_PPC_DOORBELL) &&
+	    irq_happened_test_and_clear(PACA_IRQ_DBELL)) {
+		regs.trap = INTERRUPT_DOORBELL;
+		doorbell_exception(&regs);
+		next_interrupt(&regs);
+	}
+
+	/* Book3E does not support soft-masking PMI interrupts */
+	if (IS_ENABLED(CONFIG_PPC_BOOK3S) &&
+	    irq_happened_test_and_clear(PACA_IRQ_PMI)) {
+		regs.trap = INTERRUPT_PERFMON;
+		performance_monitor_exception(&regs);
+		next_interrupt(&regs);
+	}
+
+	/*
+	 * Softirq processing can enable and disable interrupts, which can
+	 * result in new irqs becoming pending. Must keep looping until we
+	 * have cleared out all pending interrupts.
+	 */
+	if (local_paca->irq_happened & ~PACA_IRQ_HARD_DIS)
+		goto again;
+}
+
+#if defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_PPC_KUAP)
+static inline void replay_soft_interrupts_irqrestore(void)
+{
+	unsigned long kuap_state = get_kuap();
+
+	/*
+	 * Check if anything calls local_irq_enable/restore() when KUAP is
+	 * disabled (user access enabled). We handle that case here by saving
+	 * and re-locking AMR but we shouldn't get here in the first place,
+	 * hence the warning.
+	 */
+	kuap_assert_locked();
+
+	if (kuap_state != AMR_KUAP_BLOCKED)
+		set_kuap(AMR_KUAP_BLOCKED);
+
+	replay_soft_interrupts();
+
+	if (kuap_state != AMR_KUAP_BLOCKED)
+		set_kuap(kuap_state);
+}
+#else
+#define replay_soft_interrupts_irqrestore() replay_soft_interrupts()
+#endif
+
+notrace void arch_local_irq_restore(unsigned long mask)
+{
+	unsigned char irq_happened;
+
+	/* Write the new soft-enabled value if it is a disable */
+	if (mask) {
+		irq_soft_mask_set(mask);
+		return;
+	}
+
+	if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG))
+		WARN_ON_ONCE(in_nmi() || in_hardirq());
+
+	/*
+	 * After the stb, interrupts are unmasked and there are no interrupts
+	 * pending replay. The restart sequence makes this atomic with
+	 * respect to soft-masked interrupts. If this was just a simple code
+	 * sequence, a soft-masked interrupt could become pending right after
+	 * the comparison and before the stb.
+	 *
+	 * This allows interrupts to be unmasked without hard disabling, and
+	 * also without new hard interrupts coming in ahead of pending ones.
+	 */
+	asm_volatile_goto(
+"1:					\n"
+"		lbz	9,%0(13)	\n"
+"		cmpwi	9,0		\n"
+"		bne	%l[happened]	\n"
+"		stb	9,%1(13)	\n"
+"2:					\n"
+		RESTART_TABLE(1b, 2b, 1b)
+	: : "i" (offsetof(struct paca_struct, irq_happened)),
+	    "i" (offsetof(struct paca_struct, irq_soft_mask))
+	: "cr0", "r9"
+	: happened);
+
+	if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG))
+		WARN_ON_ONCE(!(mfmsr() & MSR_EE));
+
+	return;
+
+happened:
+	irq_happened = READ_ONCE(local_paca->irq_happened);
+	if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG))
+		WARN_ON_ONCE(!irq_happened);
+
+	if (irq_happened == PACA_IRQ_HARD_DIS) {
+		if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG))
+			WARN_ON_ONCE(mfmsr() & MSR_EE);
+		irq_soft_mask_set(IRQS_ENABLED);
+		local_paca->irq_happened = 0;
+		__hard_irq_enable();
+		return;
+	}
+
+	/* Have interrupts to replay, need to hard disable first */
+	if (!(irq_happened & PACA_IRQ_HARD_DIS)) {
+		if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) {
+			if (!(mfmsr() & MSR_EE)) {
+				/*
+				 * An interrupt could have come in and cleared
+				 * MSR[EE] and set IRQ_HARD_DIS, so check
+				 * IRQ_HARD_DIS again and warn if it is still
+				 * clear.
+				 */
+				irq_happened = READ_ONCE(local_paca->irq_happened);
+				WARN_ON_ONCE(!(irq_happened & PACA_IRQ_HARD_DIS));
+			}
+		}
+		__hard_irq_disable();
+		local_paca->irq_happened |= PACA_IRQ_HARD_DIS;
+	} else {
+		if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) {
+			if (WARN_ON_ONCE(mfmsr() & MSR_EE))
+				__hard_irq_disable();
+		}
+	}
+
+	/*
+	 * Disable preempt here, so that the below preempt_enable will
+	 * perform resched if required (a replayed interrupt may set
+	 * need_resched).
+	 */
+	preempt_disable();
+	irq_soft_mask_set(IRQS_ALL_DISABLED);
+	trace_hardirqs_off();
+
+	replay_soft_interrupts_irqrestore();
+
+	trace_hardirqs_on();
+	irq_soft_mask_set(IRQS_ENABLED);
+	if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG))
+		WARN_ON(local_paca->irq_happened != PACA_IRQ_HARD_DIS);
+	local_paca->irq_happened = 0;
+	__hard_irq_enable();
+	preempt_enable();
+}
+EXPORT_SYMBOL(arch_local_irq_restore);
+
+/*
+ * This is a helper to use when about to go into idle low-power
+ * when the latter has the side effect of re-enabling interrupts
+ * (such as calling H_CEDE under pHyp).
+ *
+ * You call this function with interrupts soft-disabled (this is
+ * already the case when ppc_md.power_save is called). The function
+ * will return whether to enter power save or just return.
+ *
+ * In the former case, it will have notified lockdep of interrupts
+ * being re-enabled and generally sanitized the lazy irq state,
+ * and in the latter case it will leave with interrupts hard
+ * disabled and marked as such, so the local_irq_enable() call
+ * in arch_cpu_idle() will properly re-enable everything.
+ */
+bool prep_irq_for_idle(void)
+{
+	/*
+	 * First we need to hard disable to ensure no interrupt
+	 * occurs before we effectively enter the low power state
+	 */
+	__hard_irq_disable();
+	local_paca->irq_happened |= PACA_IRQ_HARD_DIS;
+
+	/*
+	 * If anything happened while we were soft-disabled,
+	 * we return now and do not enter the low power state.
+	 */
+	if (lazy_irq_pending())
+		return false;
+
+	/* Tell lockdep we are about to re-enable */
+	trace_hardirqs_on();
+
+	/*
+	 * Mark interrupts as soft-enabled and clear the
+	 * PACA_IRQ_HARD_DIS from the pending mask since we
+	 * are about to hard enable as well as a side effect
+	 * of entering the low power state.
+	 */
+	local_paca->irq_happened &= ~PACA_IRQ_HARD_DIS;
+	irq_soft_mask_set(IRQS_ENABLED);
+
+	/* Tell the caller to enter the low power state */
+	return true;
+}
+
+#ifdef CONFIG_PPC_BOOK3S
+/*
+ * This is for idle sequences that return with IRQs off, but the
+ * idle state itself wakes on interrupt. Tell the irq tracer that
+ * IRQs are enabled for the duration of idle so it does not get long
+ * off times. Must be paired with fini_irq_for_idle_irqsoff.
+ */
+bool prep_irq_for_idle_irqsoff(void)
+{
+	WARN_ON(!irqs_disabled());
+
+	/*
+	 * First we need to hard disable to ensure no interrupt
+	 * occurs before we effectively enter the low power state
+	 */
+	__hard_irq_disable();
+	local_paca->irq_happened |= PACA_IRQ_HARD_DIS;
+
+	/*
+	 * If anything happened while we were soft-disabled,
+	 * we return now and do not enter the low power state.
+	 */
+	if (lazy_irq_pending())
+		return false;
+
+	/* Tell lockdep we are about to re-enable */
+	trace_hardirqs_on();
+
+	return true;
+}
+
+/*
+ * Take the SRR1 wakeup reason, index into this table to find the
+ * appropriate irq_happened bit.
+ *
+ * Sytem reset exceptions taken in idle state also come through here,
+ * but they are NMI interrupts so do not need to wait for IRQs to be
+ * restored, and should be taken as early as practical. These are marked
+ * with 0xff in the table. The Power ISA specifies 0100b as the system
+ * reset interrupt reason.
+ */
+#define IRQ_SYSTEM_RESET	0xff
+
+static const u8 srr1_to_lazyirq[0x10] = {
+	0, 0, 0,
+	PACA_IRQ_DBELL,
+	IRQ_SYSTEM_RESET,
+	PACA_IRQ_DBELL,
+	PACA_IRQ_DEC,
+	0,
+	PACA_IRQ_EE,
+	PACA_IRQ_EE,
+	PACA_IRQ_HMI,
+	0, 0, 0, 0, 0 };
+
+void replay_system_reset(void)
+{
+	struct pt_regs regs;
+
+	ppc_save_regs(&regs);
+	regs.trap = 0x100;
+	get_paca()->in_nmi = 1;
+	system_reset_exception(&regs);
+	get_paca()->in_nmi = 0;
+}
+EXPORT_SYMBOL_GPL(replay_system_reset);
+
+void irq_set_pending_from_srr1(unsigned long srr1)
+{
+	unsigned int idx = (srr1 & SRR1_WAKEMASK_P8) >> 18;
+	u8 reason = srr1_to_lazyirq[idx];
+
+	/*
+	 * Take the system reset now, which is immediately after registers
+	 * are restored from idle. It's an NMI, so interrupts need not be
+	 * re-enabled before it is taken.
+	 */
+	if (unlikely(reason == IRQ_SYSTEM_RESET)) {
+		replay_system_reset();
+		return;
+	}
+
+	if (reason == PACA_IRQ_DBELL) {
+		/*
+		 * When doorbell triggers a system reset wakeup, the message
+		 * is not cleared, so if the doorbell interrupt is replayed
+		 * and the IPI handled, the doorbell interrupt would still
+		 * fire when EE is enabled.
+		 *
+		 * To avoid taking the superfluous doorbell interrupt,
+		 * execute a msgclr here before the interrupt is replayed.
+		 */
+		ppc_msgclr(PPC_DBELL_MSGTYPE);
+	}
+
+	/*
+	 * The 0 index (SRR1[42:45]=b0000) must always evaluate to 0,
+	 * so this can be called unconditionally with the SRR1 wake
+	 * reason as returned by the idle code, which uses 0 to mean no
+	 * interrupt.
+	 *
+	 * If a future CPU was to designate this as an interrupt reason,
+	 * then a new index for no interrupt must be assigned.
+	 */
+	local_paca->irq_happened |= reason;
+}
+#endif /* CONFIG_PPC_BOOK3S */
+
+/*
+ * Force a replay of the external interrupt handler on this CPU.
+ */
+void force_external_irq_replay(void)
+{
+	/*
+	 * This must only be called with interrupts soft-disabled,
+	 * the replay will happen when re-enabling.
+	 */
+	WARN_ON(!arch_irqs_disabled());
+
+	/*
+	 * Interrupts must always be hard disabled before irq_happened is
+	 * modified (to prevent lost update in case of interrupt between
+	 * load and store).
+	 */
+	__hard_irq_disable();
+	local_paca->irq_happened |= PACA_IRQ_HARD_DIS;
+
+	/* Indicate in the PACA that we have an interrupt to replay */
+	local_paca->irq_happened |= PACA_IRQ_EE;
+}
+
+static int __init setup_noirqdistrib(char *str)
+{
+	distribute_irqs = 0;
+	return 1;
+}
+
+__setup("noirqdistrib", setup_noirqdistrib);