irqchip fixes for 6.5, take #1

- Work around an erratum on GIC700, where a race between a CPU
   handling a wake-up interrupt, a change of affinity, and another
   CPU going to sleep can result in a lack of wake-up event on the
   next interrupt.
 
 - Fix the locking required on a VPE for GICv4
 
 - Enable Rockchip 3588001 erratum workaround for RK3588S
 
 - Fix the irq-bcm6345-l1 assumtions of the boot CPU always be
   the first CPU in the system
 -----BEGIN PGP SIGNATURE-----
 
 iQJDBAABCgAtFiEEn9UcU+C1Yxj9lZw9I9DQutE9ekMFAmS1HZsPHG1hekBrZXJu
 ZWwub3JnAAoJECPQ0LrRPXpDwRUQAI/DDQqQH/1fCoE+LtcA4jNjOUva2NYyRjH2
 1qYRPgj39yiIKAPCWLKnIG28bY/zZC2RrhfSiswjQQLp80xaRwh08Q9ctWIfpkFi
 3K9QAoihYZuKt2DwezNIZapiKyN7m5NjPS7vdociwJ1yLnVp/LM6racRBz3uBAJB
 ijFHMC2i560EEpWtHdWrVSCkaryd/IMITy+AQUl/b9TbIXMM/SN2KurGp6fPhIiF
 FMDCgA7pl0BwaaJ88FJWUwlkJyFho4ERUJJKmxGqDrO8tXRRDJpLI/ZlT6jLeXCf
 dtIgbGYGQe7DZ2eUVw9YVmBA54oh6pgZ5p7xDphsGMXeQUWR29xWF4itxmq6jJOF
 HIwMLCHGpdHtxaUia/dwhykGEnT1gH13hAULRjAtf3kR5mmbNVA618lHSeFC3zcx
 2yeel4CoJ3hRTlilMAHQFjW+V481s+MhKuEUSJACgDYblQxQmyM82Qq+ZuG6g5ah
 IF0DNLsxvFDF1WIw9U30bM7DI4XtF9fs/rdKGh5tiSQQXSXz9N0Rw2cmuxyxNqRR
 effQyMpOqZUUCas/xOsF2JF4pQPy0nFmHBVSXylLF597omZKmxR6NS+sKJCieJS6
 JTDCfA1zDZfRh4KhqiWmh2e+iKmGc3jc1XHFXj5EzWUYOu/ohm+y5P7Ger4krZEx
 aXxnbgnE
 =hS3u
 -----END PGP SIGNATURE-----

Merge tag 'irqchip-fixes-6.5-1' of git://git.kernel.org/pub/scm/linux/kernel/git/maz/arm-platforms into irq/urgent

Pull irqchip fixes from Marc Zyngier:

  - Work around an erratum on GIC700, where a race between a CPU
    handling a wake-up interrupt, a change of affinity, and another
    CPU going to sleep can result in a lack of wake-up event on the
    next interrupt.

  - Fix the locking required on a VPE for GICv4

  - Enable Rockchip 3588001 erratum workaround for RK3588S

  - Fix the irq-bcm6345-l1 assumtions of the boot CPU always be
    the first CPU in the system

Link: https://lore.kernel.org/lkml/20230717113857.304919-1-maz@kernel.org

Documentation/arm64/silicon-errata.rst

@@ -141,6 +141,9 @@ stable kernels.
 | ARM            | MMU-500         | #841119,826419  | N/A                         |
 +----------------+-----------------+-----------------+-----------------------------+
 +----------------+-----------------+-----------------+-----------------------------+
+| ARM            | GIC-700         | #2941627        | ARM64_ERRATUM_2941627       |
++----------------+-----------------+-----------------+-----------------------------+
++----------------+-----------------+-----------------+-----------------------------+
 | Broadcom       | Brahma-B53      | N/A             | ARM64_ERRATUM_845719        |
 +----------------+-----------------+-----------------+-----------------------------+
 | Broadcom       | Brahma-B53      | N/A             | ARM64_ERRATUM_843419        |

drivers/irqchip/irq-bcm6345-l1.c

@@ -82,6 +82,7 @@ struct bcm6345_l1_chip {
 };
 
 struct bcm6345_l1_cpu {
+	struct bcm6345_l1_chip	*intc;
 	void __iomem		*map_base;
 	unsigned int		parent_irq;
 	u32			enable_cache[];
@@ -115,17 +116,11 @@ static inline unsigned int cpu_for_irq(struct bcm6345_l1_chip *intc,
 
 static void bcm6345_l1_irq_handle(struct irq_desc *desc)
 {
-	struct bcm6345_l1_chip *intc = irq_desc_get_handler_data(desc);
-	struct bcm6345_l1_cpu *cpu;
+	struct bcm6345_l1_cpu *cpu = irq_desc_get_handler_data(desc);
+	struct bcm6345_l1_chip *intc = cpu->intc;
 	struct irq_chip *chip = irq_desc_get_chip(desc);
 	unsigned int idx;
 
-#ifdef CONFIG_SMP
-	cpu = intc->cpus[cpu_logical_map(smp_processor_id())];
-#else
-	cpu = intc->cpus[0];
-#endif
-
 	chained_irq_enter(chip, desc);
 
 	for (idx = 0; idx < intc->n_words; idx++) {
@@ -253,6 +248,7 @@ static int __init bcm6345_l1_init_one(struct device_node *dn,
 	if (!cpu)
 		return -ENOMEM;
 
+	cpu->intc = intc;
 	cpu->map_base = ioremap(res.start, sz);
 	if (!cpu->map_base)
 		return -ENOMEM;
@@ -271,7 +267,7 @@ static int __init bcm6345_l1_init_one(struct device_node *dn,
 		return -EINVAL;
 	}
 	irq_set_chained_handler_and_data(cpu->parent_irq,
-						bcm6345_l1_irq_handle, intc);
+						bcm6345_l1_irq_handle, cpu);
 
 	return 0;
 }

drivers/irqchip/irq-gic-v3-its.c

@@ -273,13 +273,23 @@ static void vpe_to_cpuid_unlock(struct its_vpe *vpe, unsigned long flags)
 	raw_spin_unlock_irqrestore(&vpe->vpe_lock, flags);
 }
 
+static struct irq_chip its_vpe_irq_chip;
+
 static int irq_to_cpuid_lock(struct irq_data *d, unsigned long *flags)
 {
-	struct its_vlpi_map *map = get_vlpi_map(d);
+	struct its_vpe *vpe = NULL;
 	int cpu;
 
-	if (map) {
-		cpu = vpe_to_cpuid_lock(map->vpe, flags);
+	if (d->chip == &its_vpe_irq_chip) {
+		vpe = irq_data_get_irq_chip_data(d);
+	} else {
+		struct its_vlpi_map *map = get_vlpi_map(d);
+		if (map)
+			vpe = map->vpe;
+	}
+
+	if (vpe) {
+		cpu = vpe_to_cpuid_lock(vpe, flags);
 	} else {
 		/* Physical LPIs are already locked via the irq_desc lock */
 		struct its_device *its_dev = irq_data_get_irq_chip_data(d);
@@ -293,10 +303,18 @@ static int irq_to_cpuid_lock(struct irq_data *d, unsigned long *flags)
 
 static void irq_to_cpuid_unlock(struct irq_data *d, unsigned long flags)
 {
-	struct its_vlpi_map *map = get_vlpi_map(d);
+	struct its_vpe *vpe = NULL;
 
-	if (map)
-		vpe_to_cpuid_unlock(map->vpe, flags);
+	if (d->chip == &its_vpe_irq_chip) {
+		vpe = irq_data_get_irq_chip_data(d);
+	} else {
+		struct its_vlpi_map *map = get_vlpi_map(d);
+		if (map)
+			vpe = map->vpe;
+	}
+
+	if (vpe)
+		vpe_to_cpuid_unlock(vpe, flags);
 }
 
 static struct its_collection *valid_col(struct its_collection *col)
@@ -1433,13 +1451,28 @@ static void wait_for_syncr(void __iomem *rdbase)
 		cpu_relax();
 }
 
+static void __direct_lpi_inv(struct irq_data *d, u64 val)
+{
+	void __iomem *rdbase;
+	unsigned long flags;
+	int cpu;
+
+	/* Target the redistributor this LPI is currently routed to */
+	cpu = irq_to_cpuid_lock(d, &flags);
+	raw_spin_lock(&gic_data_rdist_cpu(cpu)->rd_lock);
+
+	rdbase = per_cpu_ptr(gic_rdists->rdist, cpu)->rd_base;
+	gic_write_lpir(val, rdbase + GICR_INVLPIR);
+	wait_for_syncr(rdbase);
+
+	raw_spin_unlock(&gic_data_rdist_cpu(cpu)->rd_lock);
+	irq_to_cpuid_unlock(d, flags);
+}
+
 static void direct_lpi_inv(struct irq_data *d)
 {
 	struct its_vlpi_map *map = get_vlpi_map(d);
-	void __iomem *rdbase;
-	unsigned long flags;
 	u64 val;
-	int cpu;
 
 	if (map) {
 		struct its_device *its_dev = irq_data_get_irq_chip_data(d);
@@ -1453,15 +1486,7 @@ static void direct_lpi_inv(struct irq_data *d)
 		val = d->hwirq;
 	}
 
-	/* Target the redistributor this LPI is currently routed to */
-	cpu = irq_to_cpuid_lock(d, &flags);
-	raw_spin_lock(&gic_data_rdist_cpu(cpu)->rd_lock);
-	rdbase = per_cpu_ptr(gic_rdists->rdist, cpu)->rd_base;
-	gic_write_lpir(val, rdbase + GICR_INVLPIR);
-
-	wait_for_syncr(rdbase);
-	raw_spin_unlock(&gic_data_rdist_cpu(cpu)->rd_lock);
-	irq_to_cpuid_unlock(d, flags);
+	__direct_lpi_inv(d, val);
 }
 
 static void lpi_update_config(struct irq_data *d, u8 clr, u8 set)
@@ -3953,18 +3978,10 @@ static void its_vpe_send_inv(struct irq_data *d)
 {
 	struct its_vpe *vpe = irq_data_get_irq_chip_data(d);
 
-	if (gic_rdists->has_direct_lpi) {
-		void __iomem *rdbase;
-
-		/* Target the redistributor this VPE is currently known on */
-		raw_spin_lock(&gic_data_rdist_cpu(vpe->col_idx)->rd_lock);
-		rdbase = per_cpu_ptr(gic_rdists->rdist, vpe->col_idx)->rd_base;
-		gic_write_lpir(d->parent_data->hwirq, rdbase + GICR_INVLPIR);
-		wait_for_syncr(rdbase);
-		raw_spin_unlock(&gic_data_rdist_cpu(vpe->col_idx)->rd_lock);
-	} else {
+	if (gic_rdists->has_direct_lpi)
+		__direct_lpi_inv(d, d->parent_data->hwirq);
+	else
 		its_vpe_send_cmd(vpe, its_send_inv);
-	}
 }
 
 static void its_vpe_mask_irq(struct irq_data *d)
@@ -4727,7 +4744,8 @@ static bool __maybe_unused its_enable_rk3588001(void *data)
 {
 	struct its_node *its = data;
 
-	if (!of_machine_is_compatible("rockchip,rk3588"))
+	if (!of_machine_is_compatible("rockchip,rk3588") &&
+	    !of_machine_is_compatible("rockchip,rk3588s"))
 		return false;
 
 	its->flags |= ITS_FLAGS_FORCE_NON_SHAREABLE;

drivers/irqchip/irq-gic-v3.c

@@ -69,6 +69,8 @@ struct gic_chip_data {
 static void __iomem *t241_dist_base_alias[T241_CHIPS_MAX] __read_mostly;
 static DEFINE_STATIC_KEY_FALSE(gic_nvidia_t241_erratum);
 
+static DEFINE_STATIC_KEY_FALSE(gic_arm64_2941627_erratum);
+
 static struct gic_chip_data gic_data __read_mostly;
 static DEFINE_STATIC_KEY_TRUE(supports_deactivate_key);
 
@@ -592,10 +594,39 @@ static void gic_irq_nmi_teardown(struct irq_data *d)
 	gic_irq_set_prio(d, GICD_INT_DEF_PRI);
 }
 
+static bool gic_arm64_erratum_2941627_needed(struct irq_data *d)
+{
+	enum gic_intid_range range;
+
+	if (!static_branch_unlikely(&gic_arm64_2941627_erratum))
+		return false;
+
+	range = get_intid_range(d);
+
+	/*
+	 * The workaround is needed if the IRQ is an SPI and
+	 * the target cpu is different from the one we are
+	 * executing on.
+	 */
+	return (range == SPI_RANGE || range == ESPI_RANGE) &&
+		!cpumask_test_cpu(raw_smp_processor_id(),
+				  irq_data_get_effective_affinity_mask(d));
+}
+
 static void gic_eoi_irq(struct irq_data *d)
 {
 	write_gicreg(gic_irq(d), ICC_EOIR1_EL1);
 	isb();
+
+	if (gic_arm64_erratum_2941627_needed(d)) {
+		/*
+		 * Make sure the GIC stream deactivate packet
+		 * issued by ICC_EOIR1_EL1 has completed before
+		 * deactivating through GICD_IACTIVER.
+		 */
+		dsb(sy);
+		gic_poke_irq(d, GICD_ICACTIVER);
+	}
 }
 
 static void gic_eoimode1_eoi_irq(struct irq_data *d)
@@ -606,7 +637,11 @@ static void gic_eoimode1_eoi_irq(struct irq_data *d)
 	 */
 	if (gic_irq(d) >= 8192 || irqd_is_forwarded_to_vcpu(d))
 		return;
-	gic_write_dir(gic_irq(d));
+
+	if (!gic_arm64_erratum_2941627_needed(d))
+		gic_write_dir(gic_irq(d));
+	else
+		gic_poke_irq(d, GICD_ICACTIVER);
 }
 
 static int gic_set_type(struct irq_data *d, unsigned int type)
@@ -1816,6 +1851,12 @@ static bool gic_enable_quirk_asr8601(void *data)
 	return true;
 }
 
+static bool gic_enable_quirk_arm64_2941627(void *data)
+{
+	static_branch_enable(&gic_arm64_2941627_erratum);
+	return true;
+}
+
 static const struct gic_quirk gic_quirks[] = {
 	{
 		.desc	= "GICv3: Qualcomm MSM8996 broken firmware",
@@ -1863,6 +1904,25 @@ static const struct gic_quirk gic_quirks[] = {
 		.mask	= 0xffffffff,
 		.init	= gic_enable_quirk_nvidia_t241,
 	},
+	{
+		/*
+		 * GIC-700: 2941627 workaround - IP variant [0,1]
+		 *
+		 */
+		.desc	= "GICv3: ARM64 erratum 2941627",
+		.iidr	= 0x0400043b,
+		.mask	= 0xff0e0fff,
+		.init	= gic_enable_quirk_arm64_2941627,
+	},
+	{
+		/*
+		 * GIC-700: 2941627 workaround - IP variant [2]
+		 */
+		.desc	= "GICv3: ARM64 erratum 2941627",
+		.iidr	= 0x0402043b,
+		.mask	= 0xff0f0fff,
+		.init	= gic_enable_quirk_arm64_2941627,
+	},
 	{
 	}
 };