Merge tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux

Pull arm64 updates from Catalin Marinas:
 "No major architecture features this time around, just some new HWCAP
  definitions, support for the Ampere SoC PMUs and a few fixes/cleanups.

  The bulk of the changes is reworking of the CPU capability checking
  code (cpus_have_cap() etc).

   - Major refactoring of the CPU capability detection logic resulting
     in the removal of the cpus_have_const_cap() function and migrating
     the code to "alternative" branches where possible

   - Backtrace/kgdb: use IPIs and pseudo-NMI

   - Perf and PMU:

      - Add support for Ampere SoC PMUs

      - Multi-DTC improvements for larger CMN configurations with
        multiple Debug & Trace Controllers

      - Rework the Arm CoreSight PMU driver to allow separate
        registration of vendor backend modules

      - Fixes: add missing MODULE_DEVICE_TABLE to the amlogic perf
        driver; use device_get_match_data() in the xgene driver; fix
        NULL pointer dereference in the hisi driver caused by calling
        cpuhp_state_remove_instance(); use-after-free in the hisi driver

   - HWCAP updates:

      - FEAT_SVE_B16B16 (BFloat16)

      - FEAT_LRCPC3 (release consistency model)

      - FEAT_LSE128 (128-bit atomic instructions)

   - SVE: remove a couple of pseudo registers from the cpufeature code.
     There is logic in place already to detect mismatched SVE features

   - Miscellaneous:

      - Reduce the default swiotlb size (currently 64MB) if no ZONE_DMA
        bouncing is needed. The buffer is still required for small
        kmalloc() buffers

      - Fix module PLT counting with !RANDOMIZE_BASE

      - Restrict CPU_BIG_ENDIAN to LLVM IAS 15.x or newer move
        synchronisation code out of the set_ptes() loop

      - More compact cpufeature displaying enabled cores

      - Kselftest updates for the new CPU features"

 * tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (83 commits)
  arm64: Restrict CPU_BIG_ENDIAN to GNU as or LLVM IAS 15.x or newer
  arm64: module: Fix PLT counting when CONFIG_RANDOMIZE_BASE=n
  arm64, irqchip/gic-v3, ACPI: Move MADT GICC enabled check into a helper
  perf: hisi: Fix use-after-free when register pmu fails
  drivers/perf: hisi_pcie: Initialize event->cpu only on success
  drivers/perf: hisi_pcie: Check the type first in pmu::event_init()
  arm64: cpufeature: Change DBM to display enabled cores
  arm64: cpufeature: Display the set of cores with a feature
  perf/arm-cmn: Enable per-DTC counter allocation
  perf/arm-cmn: Rework DTC counters (again)
  perf/arm-cmn: Fix DTC domain detection
  drivers: perf: arm_pmuv3: Drop some unused arguments from armv8_pmu_init()
  drivers: perf: arm_pmuv3: Read PMMIR_EL1 unconditionally
  drivers/perf: hisi: use cpuhp_state_remove_instance_nocalls() for hisi_hns3_pmu uninit process
  clocksource/drivers/arm_arch_timer: limit XGene-1 workaround
  arm64: Remove system_uses_lse_atomics()
  arm64: Mark the 'addr' argument to set_ptes() and __set_pte_at() as unused
  drivers/perf: xgene: Use device_get_match_data()
  perf/amlogic: add missing MODULE_DEVICE_TABLE
  arm64/mm: Hoist synchronization out of set_ptes() loop
  ...

1 files changed, 46 insertions, 36 deletions

diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c
index f59ac9586b7b..68d11ccee441 100644
--- a/drivers/irqchip/irq-gic-v3.c
+++ b/drivers/irqchip/irq-gic-v3.c
@@ -79,6 +79,13 @@ static DEFINE_STATIC_KEY_TRUE(supports_deactivate_key);
 #define GIC_ESPI_NR	GICD_TYPER_ESPIS(gic_data.rdists.gicd_typer)
 
 /*
+ * There are 16 SGIs, though we only actually use 8 in Linux. The other 8 SGIs
+ * are potentially stolen by the secure side. Some code, especially code dealing
+ * with hwirq IDs, is simplified by accounting for all 16.
+ */
+#define SGI_NR		16
+
+/*
  * The behaviours of RPR and PMR registers differ depending on the value of
  * SCR_EL3.FIQ, and the behaviour of non-secure priority registers of the
  * distributor and redistributors depends on whether security is enabled in the
@@ -99,7 +106,7 @@ static DEFINE_STATIC_KEY_TRUE(supports_deactivate_key);
  * - Figure 4-7 Secure read of the priority field for a Non-secure Group 1
  *   interrupt.
  */
-static DEFINE_STATIC_KEY_FALSE(supports_pseudo_nmis);
+DEFINE_STATIC_KEY_FALSE(supports_pseudo_nmis);
 
 DEFINE_STATIC_KEY_FALSE(gic_nonsecure_priorities);
 EXPORT_SYMBOL(gic_nonsecure_priorities);
@@ -125,8 +132,8 @@ EXPORT_SYMBOL(gic_nonsecure_priorities);
 		__priority;						\
 	})
 
-/* ppi_nmi_refs[n] == number of cpus having ppi[n + 16] set as NMI */
-static refcount_t *ppi_nmi_refs;
+/* rdist_nmi_refs[n] == number of cpus having the rdist interrupt n set as NMI */
+static refcount_t *rdist_nmi_refs;
 
 static struct gic_kvm_info gic_v3_kvm_info __initdata;
 static DEFINE_PER_CPU(bool, has_rss);
@@ -270,17 +277,6 @@ static void gic_redist_wait_for_rwp(void)
 	gic_do_wait_for_rwp(gic_data_rdist_rd_base(), GICR_CTLR_RWP);
 }
 
-#ifdef CONFIG_ARM64
-
-static u64 __maybe_unused gic_read_iar(void)
-{
-	if (cpus_have_const_cap(ARM64_WORKAROUND_CAVIUM_23154))
-		return gic_read_iar_cavium_thunderx();
-	else
-		return gic_read_iar_common();
-}
-#endif
-
 static void gic_enable_redist(bool enable)
 {
 	void __iomem *rbase;
@@ -519,9 +515,22 @@ static u32 __gic_get_ppi_index(irq_hw_number_t hwirq)
 	}
 }
 
-static u32 gic_get_ppi_index(struct irq_data *d)
+static u32 __gic_get_rdist_index(irq_hw_number_t hwirq)
+{
+	switch (__get_intid_range(hwirq)) {
+	case SGI_RANGE:
+	case PPI_RANGE:
+		return hwirq;
+	case EPPI_RANGE:
+		return hwirq - EPPI_BASE_INTID + 32;
+	default:
+		unreachable();
+	}
+}
+
+static u32 gic_get_rdist_index(struct irq_data *d)
 {
-	return __gic_get_ppi_index(d->hwirq);
+	return __gic_get_rdist_index(d->hwirq);
 }
 
 static int gic_irq_nmi_setup(struct irq_data *d)
@@ -545,11 +554,14 @@ static int gic_irq_nmi_setup(struct irq_data *d)
 
 	/* desc lock should already be held */
 	if (gic_irq_in_rdist(d)) {
-		u32 idx = gic_get_ppi_index(d);
+		u32 idx = gic_get_rdist_index(d);
 
-		/* Setting up PPI as NMI, only switch handler for first NMI */
-		if (!refcount_inc_not_zero(&ppi_nmi_refs[idx])) {
-			refcount_set(&ppi_nmi_refs[idx], 1);
+		/*
+		 * Setting up a percpu interrupt as NMI, only switch handler
+		 * for first NMI
+		 */
+		if (!refcount_inc_not_zero(&rdist_nmi_refs[idx])) {
+			refcount_set(&rdist_nmi_refs[idx], 1);
 			desc->handle_irq = handle_percpu_devid_fasteoi_nmi;
 		}
 	} else {
@@ -582,10 +594,10 @@ static void gic_irq_nmi_teardown(struct irq_data *d)
 
 	/* desc lock should already be held */
 	if (gic_irq_in_rdist(d)) {
-		u32 idx = gic_get_ppi_index(d);
+		u32 idx = gic_get_rdist_index(d);
 
 		/* Tearing down NMI, only switch handler for last NMI */
-		if (refcount_dec_and_test(&ppi_nmi_refs[idx]))
+		if (refcount_dec_and_test(&rdist_nmi_refs[idx]))
 			desc->handle_irq = handle_percpu_devid_irq;
 	} else {
 		desc->handle_irq = handle_fasteoi_irq;
@@ -1279,10 +1291,10 @@ static void gic_cpu_init(void)
 	rbase = gic_data_rdist_sgi_base();
 
 	/* Configure SGIs/PPIs as non-secure Group-1 */
-	for (i = 0; i < gic_data.ppi_nr + 16; i += 32)
+	for (i = 0; i < gic_data.ppi_nr + SGI_NR; i += 32)
 		writel_relaxed(~0, rbase + GICR_IGROUPR0 + i / 8);
 
-	gic_cpu_config(rbase, gic_data.ppi_nr + 16, gic_redist_wait_for_rwp);
+	gic_cpu_config(rbase, gic_data.ppi_nr + SGI_NR, gic_redist_wait_for_rwp);
 
 	/* initialise system registers */
 	gic_cpu_sys_reg_init();
@@ -1952,12 +1964,13 @@ static void gic_enable_nmi_support(void)
 		return;
 	}
 
-	ppi_nmi_refs = kcalloc(gic_data.ppi_nr, sizeof(*ppi_nmi_refs), GFP_KERNEL);
-	if (!ppi_nmi_refs)
+	rdist_nmi_refs = kcalloc(gic_data.ppi_nr + SGI_NR,
+				 sizeof(*rdist_nmi_refs), GFP_KERNEL);
+	if (!rdist_nmi_refs)
 		return;
 
-	for (i = 0; i < gic_data.ppi_nr; i++)
-		refcount_set(&ppi_nmi_refs[i], 0);
+	for (i = 0; i < gic_data.ppi_nr + SGI_NR; i++)
+		refcount_set(&rdist_nmi_refs[i], 0);
 
 	pr_info("Pseudo-NMIs enabled using %s ICC_PMR_EL1 synchronisation\n",
 		gic_has_relaxed_pmr_sync() ? "relaxed" : "forced");
@@ -2074,6 +2087,7 @@ static int __init gic_init_bases(phys_addr_t dist_phys_base,
 
 	gic_dist_init();
 	gic_cpu_init();
+	gic_enable_nmi_support();
 	gic_smp_init();
 	gic_cpu_pm_init();
 
@@ -2086,8 +2100,6 @@ static int __init gic_init_bases(phys_addr_t dist_phys_base,
 			gicv2m_init(handle, gic_data.domain);
 	}
 
-	gic_enable_nmi_support();
-
 	return 0;
 
 out_free:
@@ -2380,8 +2392,7 @@ gic_acpi_parse_madt_gicc(union acpi_subtable_headers *header,
 	u32 size = reg == GIC_PIDR2_ARCH_GICv4 ? SZ_64K * 4 : SZ_64K * 2;
 	void __iomem *redist_base;
 
-	/* GICC entry which has !ACPI_MADT_ENABLED is not unusable so skip */
-	if (!(gicc->flags & ACPI_MADT_ENABLED))
+	if (!acpi_gicc_is_usable(gicc))
 		return 0;
 
 	redist_base = ioremap(gicc->gicr_base_address, size);
@@ -2431,7 +2442,7 @@ static int __init gic_acpi_match_gicc(union acpi_subtable_headers *header,
 	 * If GICC is enabled and has valid gicr base address, then it means
 	 * GICR base is presented via GICC
 	 */
-	if ((gicc->flags & ACPI_MADT_ENABLED) && gicc->gicr_base_address) {
+	if (acpi_gicc_is_usable(gicc) && gicc->gicr_base_address) {
 		acpi_data.enabled_rdists++;
 		return 0;
 	}
@@ -2440,7 +2451,7 @@ static int __init gic_acpi_match_gicc(union acpi_subtable_headers *header,
 	 * It's perfectly valid firmware can pass disabled GICC entry, driver
 	 * should not treat as errors, skip the entry instead of probe fail.
 	 */
-	if (!(gicc->flags & ACPI_MADT_ENABLED))
+	if (!acpi_gicc_is_usable(gicc))
 		return 0;
 
 	return -ENODEV;
@@ -2499,8 +2510,7 @@ static int __init gic_acpi_parse_virt_madt_gicc(union acpi_subtable_headers *hea
 	int maint_irq_mode;
 	static int first_madt = true;
 
-	/* Skip unusable CPUs */
-	if (!(gicc->flags & ACPI_MADT_ENABLED))
+	if (!acpi_gicc_is_usable(gicc))
 		return 0;
 
 	maint_irq_mode = (gicc->flags & ACPI_MADT_VGIC_IRQ_MODE) ?