1 files changed, 114 insertions, 63 deletions

diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index 16acce0f102d..ada585bfa451 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -41,12 +41,14 @@
 #include <asm/exception.h>
 
 #include "irq-gic-common.h"
-#include "irq-msi-lib.h"
+#include "irq-gic-its-msi-parent.h"
+#include <linux/irqchip/irq-msi-lib.h>
 
 #define ITS_FLAGS_CMDQ_NEEDS_FLUSHING		(1ULL << 0)
 #define ITS_FLAGS_WORKAROUND_CAVIUM_22375	(1ULL << 1)
 #define ITS_FLAGS_WORKAROUND_CAVIUM_23144	(1ULL << 2)
 #define ITS_FLAGS_FORCE_NON_SHAREABLE		(1ULL << 3)
+#define ITS_FLAGS_WORKAROUND_HISILICON_162100801	(1ULL << 4)
 
 #define RD_LOCAL_LPI_ENABLED                    BIT(0)
 #define RD_LOCAL_PENDTABLE_PREALLOCATED         BIT(1)
@@ -64,6 +66,7 @@ static u32 lpi_id_bits;
 #define LPI_PENDBASE_SZ		ALIGN(BIT(LPI_NRBITS) / 8, SZ_64K)
 
 static u8 __ro_after_init lpi_prop_prio;
+static struct its_node *find_4_1_its(void);
 
 /*
  * Collection structure - just an ID, and a redistributor address to
@@ -123,6 +126,8 @@ struct its_node {
 	int			vlpi_redist_offset;
 };
 
+static DEFINE_PER_CPU(struct its_node *, local_4_1_its);
+
 #define is_v4(its)		(!!((its)->typer & GITS_TYPER_VLPIS))
 #define is_v4_1(its)		(!!((its)->typer & GITS_TYPER_VMAPP))
 #define device_ids(its)		(FIELD_GET(GITS_TYPER_DEVBITS, (its)->typer) + 1)
@@ -203,13 +208,15 @@ static DEFINE_IDA(its_vpeid_ida);
 #define gic_data_rdist_rd_base()	(gic_data_rdist()->rd_base)
 #define gic_data_rdist_vlpi_base()	(gic_data_rdist_rd_base() + SZ_128K)
 
+static gfp_t gfp_flags_quirk;
+
 static struct page *its_alloc_pages_node(int node, gfp_t gfp,
 					 unsigned int order)
 {
 	struct page *page;
 	int ret = 0;
 
-	page = alloc_pages_node(node, gfp, order);
+	page = alloc_pages_node(node, gfp | gfp_flags_quirk, order);
 
 	if (!page)
 		return NULL;
@@ -1807,17 +1814,10 @@ static u64 its_irq_get_msi_base(struct its_device *its_dev)
 static void its_irq_compose_msi_msg(struct irq_data *d, struct msi_msg *msg)
 {
 	struct its_device *its_dev = irq_data_get_irq_chip_data(d);
-	struct its_node *its;
-	u64 addr;
 
-	its = its_dev->its;
-	addr = its->get_msi_base(its_dev);
-
-	msg->address_lo		= lower_32_bits(addr);
-	msg->address_hi		= upper_32_bits(addr);
-	msg->data		= its_get_event_id(d);
-
-	iommu_dma_compose_msi_msg(irq_data_get_msi_desc(d), msg);
+	msg->data = its_get_event_id(d);
+	msi_msg_set_addr(irq_data_get_msi_desc(d), msg,
+			 its_dev->its->get_msi_base(its_dev));
 }
 
 static int its_irq_set_irqchip_state(struct irq_data *d,
@@ -2043,7 +2043,7 @@ static int its_irq_set_vcpu_affinity(struct irq_data *d, void *vcpu_info)
 	if (!is_v4(its_dev->its))
 		return -EINVAL;
 
-	guard(raw_spinlock_irq)(&its_dev->event_map.vlpi_lock);
+	guard(raw_spinlock)(&its_dev->event_map.vlpi_lock);
 
 	/* Unmap request? */
 	if (!info)
@@ -2781,6 +2781,7 @@ static u64 inherit_vpe_l1_table_from_its(void)
 		}
 		val |= FIELD_PREP(GICR_VPROPBASER_4_1_SIZE, GITS_BASER_NR_PAGES(baser) - 1);
 
+		*this_cpu_ptr(&local_4_1_its) = its;
 		return val;
 	}
 
@@ -2818,6 +2819,7 @@ static u64 inherit_vpe_l1_table_from_rd(cpumask_t **mask)
 		gic_data_rdist()->vpe_l1_base = gic_data_rdist_cpu(cpu)->vpe_l1_base;
 		*mask = gic_data_rdist_cpu(cpu)->vpe_table_mask;
 
+		*this_cpu_ptr(&local_4_1_its) = *per_cpu_ptr(&local_4_1_its, cpu);
 		return val;
 	}
 
@@ -3623,8 +3625,33 @@ out:
 	return err;
 }
 
+static void its_msi_teardown(struct irq_domain *domain, msi_alloc_info_t *info)
+{
+	struct its_device *its_dev = info->scratchpad[0].ptr;
+
+	guard(mutex)(&its_dev->its->dev_alloc_lock);
+
+	/* If the device is shared, keep everything around */
+	if (its_dev->shared)
+		return;
+
+	/* LPIs should have been already unmapped at this stage */
+	if (WARN_ON_ONCE(!bitmap_empty(its_dev->event_map.lpi_map,
+				       its_dev->event_map.nr_lpis)))
+		return;
+
+	its_lpi_free(its_dev->event_map.lpi_map,
+		     its_dev->event_map.lpi_base,
+		     its_dev->event_map.nr_lpis);
+
+	/* Unmap device/itt, and get rid of the tracking */
+	its_send_mapd(its_dev, 0);
+	its_free_device(its_dev);
+}
+
 static struct msi_domain_ops its_msi_domain_ops = {
 	.msi_prepare	= its_msi_prepare,
+	.msi_teardown	= its_msi_teardown,
 };
 
 static int its_irq_gic_domain_alloc(struct irq_domain *domain,
@@ -3725,7 +3752,6 @@ static void its_irq_domain_free(struct irq_domain *domain, unsigned int virq,
 {
 	struct irq_data *d = irq_domain_get_irq_data(domain, virq);
 	struct its_device *its_dev = irq_data_get_irq_chip_data(d);
-	struct its_node *its = its_dev->its;
 	int i;
 
 	bitmap_release_region(its_dev->event_map.lpi_map,
@@ -3739,26 +3765,6 @@ static void its_irq_domain_free(struct irq_domain *domain, unsigned int virq,
 		irq_domain_reset_irq_data(data);
 	}
 
-	mutex_lock(&its->dev_alloc_lock);
-
-	/*
-	 * If all interrupts have been freed, start mopping the
-	 * floor. This is conditioned on the device not being shared.
-	 */
-	if (!its_dev->shared &&
-	    bitmap_empty(its_dev->event_map.lpi_map,
-			 its_dev->event_map.nr_lpis)) {
-		its_lpi_free(its_dev->event_map.lpi_map,
-			     its_dev->event_map.lpi_base,
-			     its_dev->event_map.nr_lpis);
-
-		/* Unmap device/itt */
-		its_send_mapd(its_dev, 0);
-		its_free_device(its_dev);
-	}
-
-	mutex_unlock(&its->dev_alloc_lock);
-
 	irq_domain_free_irqs_parent(domain, virq, nr_irqs);
 }
 
@@ -3883,6 +3889,20 @@ static void its_vpe_db_proxy_move(struct its_vpe *vpe, int from, int to)
 	raw_spin_unlock_irqrestore(&vpe_proxy.lock, flags);
 }
 
+static void its_vpe_4_1_invall_locked(int cpu, struct its_vpe *vpe)
+{
+	void __iomem *rdbase;
+	u64 val;
+
+	val  = GICR_INVALLR_V;
+	val |= FIELD_PREP(GICR_INVALLR_VPEID, vpe->vpe_id);
+
+	guard(raw_spinlock)(&gic_data_rdist_cpu(cpu)->rd_lock);
+	rdbase = per_cpu_ptr(gic_rdists->rdist, cpu)->rd_base;
+	gic_write_lpir(val, rdbase + GICR_INVALLR);
+	wait_for_syncr(rdbase);
+}
+
 static int its_vpe_set_affinity(struct irq_data *d,
 				const struct cpumask *mask_val,
 				bool force)
@@ -3890,6 +3910,7 @@ static int its_vpe_set_affinity(struct irq_data *d,
 	struct its_vpe *vpe = irq_data_get_irq_chip_data(d);
 	unsigned int from, cpu = nr_cpu_ids;
 	struct cpumask *table_mask;
+	struct its_node *its;
 	unsigned long flags;
 
 	/*
@@ -3952,6 +3973,11 @@ static int its_vpe_set_affinity(struct irq_data *d,
 	vpe->col_idx = cpu;
 
 	its_send_vmovp(vpe);
+
+	its = find_4_1_its();
+	if (its && its->flags & ITS_FLAGS_WORKAROUND_HISILICON_162100801)
+		its_vpe_4_1_invall_locked(cpu, vpe);
+
 	its_vpe_db_proxy_move(vpe, from, cpu);
 
 out:
@@ -4163,7 +4189,7 @@ static struct irq_chip its_vpe_irq_chip = {
 
 static struct its_node *find_4_1_its(void)
 {
-	static struct its_node *its = NULL;
+	struct its_node *its = *this_cpu_ptr(&local_4_1_its);
 
 	if (!its) {
 		list_for_each_entry(its, &its_nodes, entry) {
@@ -4259,22 +4285,12 @@ static void its_vpe_4_1_deschedule(struct its_vpe *vpe,
 
 static void its_vpe_4_1_invall(struct its_vpe *vpe)
 {
-	void __iomem *rdbase;
 	unsigned long flags;
-	u64 val;
 	int cpu;
 
-	val  = GICR_INVALLR_V;
-	val |= FIELD_PREP(GICR_INVALLR_VPEID, vpe->vpe_id);
-
 	/* Target the redistributor this vPE is currently known on */
 	cpu = vpe_to_cpuid_lock(vpe, &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_INVALLR);
-
-	wait_for_syncr(rdbase);
-	raw_spin_unlock(&gic_data_rdist_cpu(cpu)->rd_lock);
+	its_vpe_4_1_invall_locked(cpu, vpe);
 	vpe_to_cpuid_unlock(vpe, flags);
 }
 
@@ -4867,6 +4883,25 @@ static bool its_set_non_coherent(void *data)
 	return true;
 }
 
+static bool __maybe_unused its_enable_quirk_hip09_162100801(void *data)
+{
+	struct its_node *its = data;
+
+	its->flags |= ITS_FLAGS_WORKAROUND_HISILICON_162100801;
+	return true;
+}
+
+static bool __maybe_unused its_enable_rk3568002(void *data)
+{
+	if (!of_machine_is_compatible("rockchip,rk3566") &&
+	    !of_machine_is_compatible("rockchip,rk3568"))
+		return false;
+
+	gfp_flags_quirk |= GFP_DMA32;
+
+	return true;
+}
+
 static const struct gic_quirk its_quirks[] = {
 #ifdef CONFIG_CAVIUM_ERRATUM_22375
 	{
@@ -4913,6 +4948,14 @@ static const struct gic_quirk its_quirks[] = {
 		.init	= its_enable_quirk_hip07_161600802,
 	},
 #endif
+#ifdef CONFIG_HISILICON_ERRATUM_162100801
+	{
+		.desc	= "ITS: Hip09 erratum 162100801",
+		.iidr	= 0x00051736,
+		.mask	= 0xffffffff,
+		.init	= its_enable_quirk_hip09_162100801,
+	},
+#endif
 #ifdef CONFIG_ROCKCHIP_ERRATUM_3588001
 	{
 		.desc   = "ITS: Rockchip erratum RK3588001",
@@ -4926,6 +4969,14 @@ static const struct gic_quirk its_quirks[] = {
 		.property = "dma-noncoherent",
 		.init   = its_set_non_coherent,
 	},
+#ifdef CONFIG_ROCKCHIP_ERRATUM_3568002
+	{
+		.desc   = "ITS: Rockchip erratum RK3568002",
+		.iidr   = 0x0201743b,
+		.mask   = 0xffffffff,
+		.init   = its_enable_rk3568002,
+	},
+#endif
 	{
 	}
 };
@@ -4941,7 +4992,7 @@ static void its_enable_quirks(struct its_node *its)
 				     its_quirks, its);
 }
 
-static int its_save_disable(void)
+static int its_save_disable(void *data)
 {
 	struct its_node *its;
 	int err = 0;
@@ -4977,7 +5028,7 @@ err:
 	return err;
 }
 
-static void its_restore_enable(void)
+static void its_restore_enable(void *data)
 {
 	struct its_node *its;
 	int ret;
@@ -5037,11 +5088,15 @@ static void its_restore_enable(void)
 	raw_spin_unlock(&its_lock);
 }
 
-static struct syscore_ops its_syscore_ops = {
+static const struct syscore_ops its_syscore_ops = {
 	.suspend = its_save_disable,
 	.resume = its_restore_enable,
 };
 
+static struct syscore its_syscore = {
+	.ops = &its_syscore_ops,
+};
+
 static void __init __iomem *its_map_one(struct resource *res, int *err)
 {
 	void __iomem *its_base;
@@ -5076,7 +5131,12 @@ out_unmap:
 
 static int its_init_domain(struct its_node *its)
 {
-	struct irq_domain *inner_domain;
+	struct irq_domain_info dom_info = {
+		.fwnode		= its->fwnode_handle,
+		.ops		= &its_domain_ops,
+		.domain_flags	= its->msi_domain_flags,
+		.parent		= its_parent,
+	};
 	struct msi_domain_info *info;
 
 	info = kzalloc(sizeof(*info), GFP_KERNEL);
@@ -5085,21 +5145,12 @@ static int its_init_domain(struct its_node *its)
 
 	info->ops = &its_msi_domain_ops;
 	info->data = its;
+	dom_info.host_data = info;
 
-	inner_domain = irq_domain_create_hierarchy(its_parent,
-						   its->msi_domain_flags, 0,
-						   its->fwnode_handle, &its_domain_ops,
-						   info);
-	if (!inner_domain) {
+	if (!msi_create_parent_irq_domain(&dom_info, &gic_v3_its_msi_parent_ops)) {
 		kfree(info);
 		return -ENOMEM;
 	}
-
-	irq_domain_update_bus_token(inner_domain, DOMAIN_BUS_NEXUS);
-
-	inner_domain->msi_parent_ops = &gic_v3_its_msi_parent_ops;
-	inner_domain->flags |= IRQ_DOMAIN_FLAG_MSI_PARENT;
-
 	return 0;
 }
 
@@ -5476,7 +5527,7 @@ static struct its_node __init *its_node_init(struct resource *res,
 	its->base = its_base;
 	its->phys_base = res->start;
 	its->get_msi_base = its_irq_get_msi_base;
-	its->msi_domain_flags = IRQ_DOMAIN_FLAG_ISOLATED_MSI;
+	its->msi_domain_flags = IRQ_DOMAIN_FLAG_ISOLATED_MSI | IRQ_DOMAIN_FLAG_MSI_IMMUTABLE;
 
 	its->numa_node = numa_node;
 	its->fwnode_handle = handle;
@@ -5817,7 +5868,7 @@ int __init its_init(struct fwnode_handle *handle, struct rdists *rdists,
 		}
 	}
 
-	register_syscore_ops(&its_syscore_ops);
+	register_syscore(&its_syscore);
 
 	return 0;
 }