Merge tag 'irq-core-2024-09-16' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull irq updates from Thomas Gleixner:
 "Core:

   - Remove a global lock in the affinity setting code

     The lock protects a cpumask for intermediate results and the lock
     causes a bottleneck on simultaneous start of multiple virtual
     machines. Replace the lock and the static cpumask with a per CPU
     cpumask which is nicely serialized by raw spinlock held when
     executing this code.

   - Provide support for giving a suffix to interrupt domain names.

     That's required to support devices with subfunctions so that the
     domain names are distinct even if they originate from the same
     device node.

   - The usual set of cleanups and enhancements all over the place

  Drivers:

   - Support for longarch AVEC interrupt chip

   - Refurbishment of the Armada driver so it can be extended for new
     variants.

   - The usual set of cleanups and enhancements all over the place"

* tag 'irq-core-2024-09-16' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (73 commits)
  genirq: Use cpumask_intersects()
  genirq/cpuhotplug: Use cpumask_intersects()
  irqchip/apple-aic: Only access system registers on SoCs which provide them
  irqchip/apple-aic: Add a new "Global fast IPIs only" feature level
  irqchip/apple-aic: Skip unnecessary enabling of use_fast_ipi
  dt-bindings: apple,aic: Document A7-A11 compatibles
  irqdomain: Use IS_ERR_OR_NULL() in irq_domain_trim_hierarchy()
  genirq/msi: Use kmemdup_array() instead of kmemdup()
  genirq/proc: Change the return value for set affinity permission error
  genirq/proc: Use irq_move_pending() in show_irq_affinity()
  genirq/proc: Correctly set file permissions for affinity control files
  genirq: Get rid of global lock in irq_do_set_affinity()
  genirq: Fix typo in struct comment
  irqchip/loongarch-avec: Add AVEC irqchip support
  irqchip/loongson-pch-msi: Prepare get_pch_msi_handle() for AVECINTC
  irqchip/loongson-eiointc: Rename CPUHP_AP_IRQ_LOONGARCH_STARTING
  LoongArch: Architectural preparation for AVEC irqchip
  LoongArch: Move irqchip function prototypes to irq-loongson.h
  irqchip/loongson-pch-msi: Switch to MSI parent domains
  softirq: Remove unused 'action' parameter from action callback
  ...

1 files changed, 39 insertions, 20 deletions

diff --git a/drivers/irqchip/irq-apple-aic.c b/drivers/irqchip/irq-apple-aic.c
index 5c534d9fd2b0..da5250f0155c 100644
--- a/drivers/irqchip/irq-apple-aic.c
+++ b/drivers/irqchip/irq-apple-aic.c
@@ -234,7 +234,10 @@ enum fiq_hwirq {
 	AIC_NR_FIQ
 };
 
+/* True if UNCORE/UNCORE2 and Sn_... IPI registers are present and used (A11+) */
 static DEFINE_STATIC_KEY_TRUE(use_fast_ipi);
+/* True if SYS_IMP_APL_IPI_RR_LOCAL_EL1 exists for local fast IPIs (M1+) */
+static DEFINE_STATIC_KEY_TRUE(use_local_fast_ipi);
 
 struct aic_info {
 	int version;
@@ -252,6 +255,7 @@ struct aic_info {
 
 	/* Features */
 	bool fast_ipi;
+	bool local_fast_ipi;
 };
 
 static const struct aic_info aic1_info __initconst = {
@@ -270,17 +274,32 @@ static const struct aic_info aic1_fipi_info __initconst = {
 	.fast_ipi	= true,
 };
 
+static const struct aic_info aic1_local_fipi_info __initconst = {
+	.version	= 1,
+
+	.event		= AIC_EVENT,
+	.target_cpu	= AIC_TARGET_CPU,
+
+	.fast_ipi	= true,
+	.local_fast_ipi = true,
+};
+
 static const struct aic_info aic2_info __initconst = {
 	.version	= 2,
 
 	.irq_cfg	= AIC2_IRQ_CFG,
 
 	.fast_ipi	= true,
+	.local_fast_ipi = true,
 };
 
 static const struct of_device_id aic_info_match[] = {
 	{
 		.compatible = "apple,t8103-aic",
+		.data = &aic1_local_fipi_info,
+	},
+	{
+		.compatible = "apple,t8015-aic",
 		.data = &aic1_fipi_info,
 	},
 	{
@@ -532,14 +551,9 @@ static void __exception_irq_entry aic_handle_fiq(struct pt_regs *regs)
 	 * we check for everything here, even things we don't support yet.
 	 */
 
-	if (read_sysreg_s(SYS_IMP_APL_IPI_SR_EL1) & IPI_SR_PENDING) {
-		if (static_branch_likely(&use_fast_ipi)) {
-			aic_handle_ipi(regs);
-		} else {
-			pr_err_ratelimited("Fast IPI fired. Acking.\n");
-			write_sysreg_s(IPI_SR_PENDING, SYS_IMP_APL_IPI_SR_EL1);
-		}
-	}
+	if (static_branch_likely(&use_fast_ipi) &&
+	    (read_sysreg_s(SYS_IMP_APL_IPI_SR_EL1) & IPI_SR_PENDING))
+		aic_handle_ipi(regs);
 
 	if (TIMER_FIRING(read_sysreg(cntp_ctl_el0)))
 		generic_handle_domain_irq(aic_irqc->hw_domain,
@@ -574,8 +588,9 @@ static void __exception_irq_entry aic_handle_fiq(struct pt_regs *regs)
 					  AIC_FIQ_HWIRQ(irq));
 	}
 
-	if (FIELD_GET(UPMCR0_IMODE, read_sysreg_s(SYS_IMP_APL_UPMCR0_EL1)) == UPMCR0_IMODE_FIQ &&
-			(read_sysreg_s(SYS_IMP_APL_UPMSR_EL1) & UPMSR_IACT)) {
+	if (static_branch_likely(&use_fast_ipi) &&
+	    (FIELD_GET(UPMCR0_IMODE, read_sysreg_s(SYS_IMP_APL_UPMCR0_EL1)) == UPMCR0_IMODE_FIQ) &&
+	    (read_sysreg_s(SYS_IMP_APL_UPMSR_EL1) & UPMSR_IACT)) {
 		/* Same story with uncore PMCs */
 		pr_err_ratelimited("Uncore PMC FIQ fired. Masking.\n");
 		sysreg_clear_set_s(SYS_IMP_APL_UPMCR0_EL1, UPMCR0_IMODE,
@@ -750,12 +765,12 @@ static void aic_ipi_send_fast(int cpu)
 	u64 cluster = MPIDR_CLUSTER(mpidr);
 	u64 idx = MPIDR_CPU(mpidr);
 
-	if (MPIDR_CLUSTER(my_mpidr) == cluster)
-		write_sysreg_s(FIELD_PREP(IPI_RR_CPU, idx),
-			       SYS_IMP_APL_IPI_RR_LOCAL_EL1);
-	else
+	if (static_branch_likely(&use_local_fast_ipi) && MPIDR_CLUSTER(my_mpidr) == cluster) {
+		write_sysreg_s(FIELD_PREP(IPI_RR_CPU, idx), SYS_IMP_APL_IPI_RR_LOCAL_EL1);
+	} else {
 		write_sysreg_s(FIELD_PREP(IPI_RR_CPU, idx) | FIELD_PREP(IPI_RR_CLUSTER, cluster),
 			       SYS_IMP_APL_IPI_RR_GLOBAL_EL1);
+	}
 	isb();
 }
 
@@ -811,7 +826,8 @@ static int aic_init_cpu(unsigned int cpu)
 	/* Mask all hard-wired per-CPU IRQ/FIQ sources */
 
 	/* Pending Fast IPI FIQs */
-	write_sysreg_s(IPI_SR_PENDING, SYS_IMP_APL_IPI_SR_EL1);
+	if (static_branch_likely(&use_fast_ipi))
+		write_sysreg_s(IPI_SR_PENDING, SYS_IMP_APL_IPI_SR_EL1);
 
 	/* Timer FIQs */
 	sysreg_clear_set(cntp_ctl_el0, 0, ARCH_TIMER_CTRL_IT_MASK);
@@ -832,8 +848,10 @@ static int aic_init_cpu(unsigned int cpu)
 			   FIELD_PREP(PMCR0_IMODE, PMCR0_IMODE_OFF));
 
 	/* Uncore PMC FIQ */
-	sysreg_clear_set_s(SYS_IMP_APL_UPMCR0_EL1, UPMCR0_IMODE,
-			   FIELD_PREP(UPMCR0_IMODE, UPMCR0_IMODE_OFF));
+	if (static_branch_likely(&use_fast_ipi)) {
+		sysreg_clear_set_s(SYS_IMP_APL_UPMCR0_EL1, UPMCR0_IMODE,
+				   FIELD_PREP(UPMCR0_IMODE, UPMCR0_IMODE_OFF));
+	}
 
 	/* Commit all of the above */
 	isb();
@@ -987,11 +1005,12 @@ static int __init aic_of_ic_init(struct device_node *node, struct device_node *p
 	off += sizeof(u32) * (irqc->max_irq >> 5); /* MASK_CLR */
 	off += sizeof(u32) * (irqc->max_irq >> 5); /* HW_STATE */
 
-	if (irqc->info.fast_ipi)
-		static_branch_enable(&use_fast_ipi);
-	else
+	if (!irqc->info.fast_ipi)
 		static_branch_disable(&use_fast_ipi);
 
+	if (!irqc->info.local_fast_ipi)
+		static_branch_disable(&use_local_fast_ipi);
+
 	irqc->info.die_stride = off - start_off;
 
 	irqc->hw_domain = irq_domain_create_tree(of_node_to_fwnode(node),