Merge tag 'irqchip-fixes-4.0' of git://git.infradead.org/users/jcooper/linux

Pull irqchip fixes from Jason Cooper:
 "armada-370-xp:
   - Chained per-cpu interrupts

  gic{,-v3,v3-its}"
   - Various fixes for safer operation"

* tag 'irqchip-fixes-4.0' of git://git.infradead.org/users/jcooper/linux:
  irqchip: gicv3-its: Support safe initialization
  irqchip: gicv3-its: Define macros for GITS_CTLR fields
  irqchip: gicv3-its: Add limitation to page order
  irqchip: gicv3-its: Use 64KB page as default granule
  irqchip: gicv3-its: Zero itt before handling to hardware
  irqchip: gic-v3: Fix out of bounds access to cpu_logical_map
  irqchip: gic: Fix unsafe locking reported by lockdep
  irqchip: gicv3-its: Fix unsafe locking reported by lockdep
  irqchip: gicv3-its: Iterate over PCI aliases to generate ITS configuration
  irqchip: gicv3-its: Allocate enough memory for the full range of DeviceID
  irqchip: gicv3-its: Fix ITS CPU init
  irqchip: armada-370-xp: Fix chained per-cpu interrupts

5 files changed, 166 insertions, 39 deletions

diff --git a/drivers/irqchip/irq-armada-370-xp.c b/drivers/irqchip/irq-armada-370-xp.c
index 463c235acbdc..4387dae14e45 100644
--- a/drivers/irqchip/irq-armada-370-xp.c
+++ b/drivers/irqchip/irq-armada-370-xp.c
@@ -69,6 +69,7 @@ static void __iomem *per_cpu_int_base;
 static void __iomem *main_int_base;
 static struct irq_domain *armada_370_xp_mpic_domain;
 static u32 doorbell_mask_reg;
+static int parent_irq;
 #ifdef CONFIG_PCI_MSI
 static struct irq_domain *armada_370_xp_msi_domain;
 static DECLARE_BITMAP(msi_used, PCI_MSI_DOORBELL_NR);
@@ -356,6 +357,7 @@ static int armada_xp_mpic_secondary_init(struct notifier_block *nfb,
 {
 	if (action == CPU_STARTING || action == CPU_STARTING_FROZEN)
 		armada_xp_mpic_smp_cpu_init();
+
 	return NOTIFY_OK;
 }
 
@@ -364,6 +366,20 @@ static struct notifier_block armada_370_xp_mpic_cpu_notifier = {
 	.priority = 100,
 };
 
+static int mpic_cascaded_secondary_init(struct notifier_block *nfb,
+					unsigned long action, void *hcpu)
+{
+	if (action == CPU_STARTING || action == CPU_STARTING_FROZEN)
+		enable_percpu_irq(parent_irq, IRQ_TYPE_NONE);
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block mpic_cascaded_cpu_notifier = {
+	.notifier_call = mpic_cascaded_secondary_init,
+	.priority = 100,
+};
+
 #endif /* CONFIG_SMP */
 
 static struct irq_domain_ops armada_370_xp_mpic_irq_ops = {
@@ -539,7 +555,7 @@ static int __init armada_370_xp_mpic_of_init(struct device_node *node,
 					     struct device_node *parent)
 {
 	struct resource main_int_res, per_cpu_int_res;
-	int parent_irq, nr_irqs, i;
+	int nr_irqs, i;
 	u32 control;
 
 	BUG_ON(of_address_to_resource(node, 0, &main_int_res));
@@ -587,6 +603,9 @@ static int __init armada_370_xp_mpic_of_init(struct device_node *node,
 		register_cpu_notifier(&armada_370_xp_mpic_cpu_notifier);
 #endif
 	} else {
+#ifdef CONFIG_SMP
+		register_cpu_notifier(&mpic_cascaded_cpu_notifier);
+#endif
 		irq_set_chained_handler(parent_irq,
 					armada_370_xp_mpic_handle_cascade_irq);
 	}
diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index d8996bdf0f61..596b0a9eee99 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -416,13 +416,14 @@ static void its_send_single_command(struct its_node *its,
 {
 	struct its_cmd_block *cmd, *sync_cmd, *next_cmd;
 	struct its_collection *sync_col;
+	unsigned long flags;
 
-	raw_spin_lock(&its->lock);
+	raw_spin_lock_irqsave(&its->lock, flags);
 
 	cmd = its_allocate_entry(its);
 	if (!cmd) {		/* We're soooooo screewed... */
 		pr_err_ratelimited("ITS can't allocate, dropping command\n");
-		raw_spin_unlock(&its->lock);
+		raw_spin_unlock_irqrestore(&its->lock, flags);
 		return;
 	}
 	sync_col = builder(cmd, desc);
@@ -442,7 +443,7 @@ static void its_send_single_command(struct its_node *its,
 
 post:
 	next_cmd = its_post_commands(its);
-	raw_spin_unlock(&its->lock);
+	raw_spin_unlock_irqrestore(&its->lock, flags);
 
 	its_wait_for_range_completion(its, cmd, next_cmd);
 }
@@ -799,21 +800,43 @@ static int its_alloc_tables(struct its_node *its)
 {
 	int err;
 	int i;
-	int psz = PAGE_SIZE;
+	int psz = SZ_64K;
 	u64 shr = GITS_BASER_InnerShareable;
 
 	for (i = 0; i < GITS_BASER_NR_REGS; i++) {
 		u64 val = readq_relaxed(its->base + GITS_BASER + i * 8);
 		u64 type = GITS_BASER_TYPE(val);
 		u64 entry_size = GITS_BASER_ENTRY_SIZE(val);
+		int order = get_order(psz);
+		int alloc_size;
 		u64 tmp;
 		void *base;
 
 		if (type == GITS_BASER_TYPE_NONE)
 			continue;
 
-		/* We're lazy and only allocate a single page for now */
-		base = (void *)get_zeroed_page(GFP_KERNEL);
+		/*
+		 * Allocate as many entries as required to fit the
+		 * range of device IDs that the ITS can grok... The ID
+		 * space being incredibly sparse, this results in a
+		 * massive waste of memory.
+		 *
+		 * For other tables, only allocate a single page.
+		 */
+		if (type == GITS_BASER_TYPE_DEVICE) {
+			u64 typer = readq_relaxed(its->base + GITS_TYPER);
+			u32 ids = GITS_TYPER_DEVBITS(typer);
+
+			order = get_order((1UL << ids) * entry_size);
+			if (order >= MAX_ORDER) {
+				order = MAX_ORDER - 1;
+				pr_warn("%s: Device Table too large, reduce its page order to %u\n",
+					its->msi_chip.of_node->full_name, order);
+			}
+		}
+
+		alloc_size = (1 << order) * PAGE_SIZE;
+		base = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, order);
 		if (!base) {
 			err = -ENOMEM;
 			goto out_free;
@@ -841,7 +864,7 @@ retry_baser:
 			break;
 		}
 
-		val |= (PAGE_SIZE / psz) - 1;
+		val |= (alloc_size / psz) - 1;
 
 		writeq_relaxed(val, its->base + GITS_BASER + i * 8);
 		tmp = readq_relaxed(its->base + GITS_BASER + i * 8);
@@ -882,7 +905,7 @@ retry_baser:
 		}
 
 		pr_info("ITS: allocated %d %s @%lx (psz %dK, shr %d)\n",
-			(int)(PAGE_SIZE / entry_size),
+			(int)(alloc_size / entry_size),
 			its_base_type_string[type],
 			(unsigned long)virt_to_phys(base),
 			psz / SZ_1K, (int)shr >> GITS_BASER_SHAREABILITY_SHIFT);
@@ -1020,8 +1043,9 @@ static void its_cpu_init_collection(void)
 static struct its_device *its_find_device(struct its_node *its, u32 dev_id)
 {
 	struct its_device *its_dev = NULL, *tmp;
+	unsigned long flags;
 
-	raw_spin_lock(&its->lock);
+	raw_spin_lock_irqsave(&its->lock, flags);
 
 	list_for_each_entry(tmp, &its->its_device_list, entry) {
 		if (tmp->device_id == dev_id) {
@@ -1030,7 +1054,7 @@ static struct its_device *its_find_device(struct its_node *its, u32 dev_id)
 		}
 	}
 
-	raw_spin_unlock(&its->lock);
+	raw_spin_unlock_irqrestore(&its->lock, flags);
 
 	return its_dev;
 }
@@ -1040,6 +1064,7 @@ static struct its_device *its_create_device(struct its_node *its, u32 dev_id,
 {
 	struct its_device *dev;
 	unsigned long *lpi_map;
+	unsigned long flags;
 	void *itt;
 	int lpi_base;
 	int nr_lpis;
@@ -1056,7 +1081,7 @@ static struct its_device *its_create_device(struct its_node *its, u32 dev_id,
 	nr_ites = max(2UL, roundup_pow_of_two(nvecs));
 	sz = nr_ites * its->ite_size;
 	sz = max(sz, ITS_ITT_ALIGN) + ITS_ITT_ALIGN - 1;
-	itt = kmalloc(sz, GFP_KERNEL);
+	itt = kzalloc(sz, GFP_KERNEL);
 	lpi_map = its_lpi_alloc_chunks(nvecs, &lpi_base, &nr_lpis);
 
 	if (!dev || !itt || !lpi_map) {
@@ -1075,9 +1100,9 @@ static struct its_device *its_create_device(struct its_node *its, u32 dev_id,
 	dev->device_id = dev_id;
 	INIT_LIST_HEAD(&dev->entry);
 
-	raw_spin_lock(&its->lock);
+	raw_spin_lock_irqsave(&its->lock, flags);
 	list_add(&dev->entry, &its->its_device_list);
-	raw_spin_unlock(&its->lock);
+	raw_spin_unlock_irqrestore(&its->lock, flags);
 
 	/* Bind the device to the first possible CPU */
 	cpu = cpumask_first(cpu_online_mask);
@@ -1091,9 +1116,11 @@ static struct its_device *its_create_device(struct its_node *its, u32 dev_id,
 
 static void its_free_device(struct its_device *its_dev)
 {
-	raw_spin_lock(&its_dev->its->lock);
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&its_dev->its->lock, flags);
 	list_del(&its_dev->entry);
-	raw_spin_unlock(&its_dev->its->lock);
+	raw_spin_unlock_irqrestore(&its_dev->its->lock, flags);
 	kfree(its_dev->itt);
 	kfree(its_dev);
 }
@@ -1112,31 +1139,69 @@ static int its_alloc_device_irq(struct its_device *dev, irq_hw_number_t *hwirq)
 	return 0;
 }
 
+struct its_pci_alias {
+	struct pci_dev	*pdev;
+	u32		dev_id;
+	u32		count;
+};
+
+static int its_pci_msi_vec_count(struct pci_dev *pdev)
+{
+	int msi, msix;
+
+	msi = max(pci_msi_vec_count(pdev), 0);
+	msix = max(pci_msix_vec_count(pdev), 0);
+
+	return max(msi, msix);
+}
+
+static int its_get_pci_alias(struct pci_dev *pdev, u16 alias, void *data)
+{
+	struct its_pci_alias *dev_alias = data;
+
+	dev_alias->dev_id = alias;
+	if (pdev != dev_alias->pdev)
+		dev_alias->count += its_pci_msi_vec_count(dev_alias->pdev);
+
+	return 0;
+}
+
 static int its_msi_prepare(struct irq_domain *domain, struct device *dev,
 			   int nvec, msi_alloc_info_t *info)
 {
 	struct pci_dev *pdev;
 	struct its_node *its;
-	u32 dev_id;
 	struct its_device *its_dev;
+	struct its_pci_alias dev_alias;
 
 	if (!dev_is_pci(dev))
 		return -EINVAL;
 
 	pdev = to_pci_dev(dev);
-	dev_id = PCI_DEVID(pdev->bus->number, pdev->devfn);
+	dev_alias.pdev = pdev;
+	dev_alias.count = nvec;
+
+	pci_for_each_dma_alias(pdev, its_get_pci_alias, &dev_alias);
 	its = domain->parent->host_data;
 
-	its_dev = its_find_device(its, dev_id);
-	if (WARN_ON(its_dev))
-		return -EINVAL;
+	its_dev = its_find_device(its, dev_alias.dev_id);
+	if (its_dev) {
+		/*
+		 * We already have seen this ID, probably through
+		 * another alias (PCI bridge of some sort). No need to
+		 * create the device.
+		 */
+		dev_dbg(dev, "Reusing ITT for devID %x\n", dev_alias.dev_id);
+		goto out;
+	}
 
-	its_dev = its_create_device(its, dev_id, nvec);
+	its_dev = its_create_device(its, dev_alias.dev_id, dev_alias.count);
 	if (!its_dev)
 		return -ENOMEM;
 
-	dev_dbg(&pdev->dev, "ITT %d entries, %d bits\n", nvec, ilog2(nvec));
-
+	dev_dbg(&pdev->dev, "ITT %d entries, %d bits\n",
+		dev_alias.count, ilog2(dev_alias.count));
+out:
 	info->scratchpad[0].ptr = its_dev;
 	info->scratchpad[1].ptr = dev;
 	return 0;
@@ -1255,6 +1320,34 @@ static const struct irq_domain_ops its_domain_ops = {
 	.deactivate		= its_irq_domain_deactivate,
 };
 
+static int its_force_quiescent(void __iomem *base)
+{
+	u32 count = 1000000;	/* 1s */
+	u32 val;
+
+	val = readl_relaxed(base + GITS_CTLR);
+	if (val & GITS_CTLR_QUIESCENT)
+		return 0;
+
+	/* Disable the generation of all interrupts to this ITS */
+	val &= ~GITS_CTLR_ENABLE;
+	writel_relaxed(val, base + GITS_CTLR);
+
+	/* Poll GITS_CTLR and wait until ITS becomes quiescent */
+	while (1) {
+		val = readl_relaxed(base + GITS_CTLR);
+		if (val & GITS_CTLR_QUIESCENT)
+			return 0;
+
+		count--;
+		if (!count)
+			return -EBUSY;
+
+		cpu_relax();
+		udelay(1);
+	}
+}
+
 static int its_probe(struct device_node *node, struct irq_domain *parent)
 {
 	struct resource res;
@@ -1283,6 +1376,13 @@ static int its_probe(struct device_node *node, struct irq_domain *parent)
 		goto out_unmap;
 	}
 
+	err = its_force_quiescent(its_base);
+	if (err) {
+		pr_warn("%s: failed to quiesce, giving up\n",
+			node->full_name);
+		goto out_unmap;
+	}
+
 	pr_info("ITS: %s\n", node->full_name);
 
 	its = kzalloc(sizeof(*its), GFP_KERNEL);
@@ -1323,7 +1423,7 @@ static int its_probe(struct device_node *node, struct irq_domain *parent)
 	writeq_relaxed(baser, its->base + GITS_CBASER);
 	tmp = readq_relaxed(its->base + GITS_CBASER);
 	writeq_relaxed(0, its->base + GITS_CWRITER);
-	writel_relaxed(1, its->base + GITS_CTLR);
+	writel_relaxed(GITS_CTLR_ENABLE, its->base + GITS_CTLR);
 
 	if ((tmp ^ baser) & GITS_BASER_SHAREABILITY_MASK) {
 		pr_info("ITS: using cache flushing for cmd queue\n");
@@ -1382,12 +1482,11 @@ static bool gic_rdists_supports_plpis(void)
 
 int its_cpu_init(void)
 {
-	if (!gic_rdists_supports_plpis()) {
-		pr_info("CPU%d: LPIs not supported\n", smp_processor_id());
-		return -ENXIO;
-	}
-
 	if (!list_empty(&its_nodes)) {
+		if (!gic_rdists_supports_plpis()) {
+			pr_info("CPU%d: LPIs not supported\n", smp_processor_id());
+			return -ENXIO;
+		}
 		its_cpu_init_lpis();
 		its_cpu_init_collection();
 	}
diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c
index 1c6dea2fbc34..fd8850def1b8 100644
--- a/drivers/irqchip/irq-gic-v3.c
+++ b/drivers/irqchip/irq-gic-v3.c
@@ -466,7 +466,7 @@ static u16 gic_compute_target_list(int *base_cpu, const struct cpumask *mask,
 		tlist |= 1 << (mpidr & 0xf);
 
 		cpu = cpumask_next(cpu, mask);
-		if (cpu == nr_cpu_ids)
+		if (cpu >= nr_cpu_ids)
 			goto out;
 
 		mpidr = cpu_logical_map(cpu);
diff --git a/drivers/irqchip/irq-gic.c b/drivers/irqchip/irq-gic.c
index 4634cf7d0ec3..471e1cdc1933 100644
--- a/drivers/irqchip/irq-gic.c
+++ b/drivers/irqchip/irq-gic.c
@@ -154,23 +154,25 @@ static inline unsigned int gic_irq(struct irq_data *d)
 static void gic_mask_irq(struct irq_data *d)
 {
 	u32 mask = 1 << (gic_irq(d) % 32);
+	unsigned long flags;
 
-	raw_spin_lock(&irq_controller_lock);
+	raw_spin_lock_irqsave(&irq_controller_lock, flags);
 	writel_relaxed(mask, gic_dist_base(d) + GIC_DIST_ENABLE_CLEAR + (gic_irq(d) / 32) * 4);
 	if (gic_arch_extn.irq_mask)
 		gic_arch_extn.irq_mask(d);
-	raw_spin_unlock(&irq_controller_lock);
+	raw_spin_unlock_irqrestore(&irq_controller_lock, flags);
 }
 
 static void gic_unmask_irq(struct irq_data *d)
 {
 	u32 mask = 1 << (gic_irq(d) % 32);
+	unsigned long flags;
 
-	raw_spin_lock(&irq_controller_lock);
+	raw_spin_lock_irqsave(&irq_controller_lock, flags);
 	if (gic_arch_extn.irq_unmask)
 		gic_arch_extn.irq_unmask(d);
 	writel_relaxed(mask, gic_dist_base(d) + GIC_DIST_ENABLE_SET + (gic_irq(d) / 32) * 4);
-	raw_spin_unlock(&irq_controller_lock);
+	raw_spin_unlock_irqrestore(&irq_controller_lock, flags);
 }
 
 static void gic_eoi_irq(struct irq_data *d)
@@ -188,6 +190,7 @@ static int gic_set_type(struct irq_data *d, unsigned int type)
 {
 	void __iomem *base = gic_dist_base(d);
 	unsigned int gicirq = gic_irq(d);
+	unsigned long flags;
 	int ret;
 
 	/* Interrupt configuration for SGIs can't be changed */
@@ -199,14 +202,14 @@ static int gic_set_type(struct irq_data *d, unsigned int type)
 			    type != IRQ_TYPE_EDGE_RISING)
 		return -EINVAL;
 
-	raw_spin_lock(&irq_controller_lock);
+	raw_spin_lock_irqsave(&irq_controller_lock, flags);
 
 	if (gic_arch_extn.irq_set_type)
 		gic_arch_extn.irq_set_type(d, type);
 
 	ret = gic_configure_irq(gicirq, type, base, NULL);
 
-	raw_spin_unlock(&irq_controller_lock);
+	raw_spin_unlock_irqrestore(&irq_controller_lock, flags);
 
 	return ret;
 }
@@ -227,6 +230,7 @@ static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val,
 	void __iomem *reg = gic_dist_base(d) + GIC_DIST_TARGET + (gic_irq(d) & ~3);
 	unsigned int cpu, shift = (gic_irq(d) % 4) * 8;
 	u32 val, mask, bit;
+	unsigned long flags;
 
 	if (!force)
 		cpu = cpumask_any_and(mask_val, cpu_online_mask);
@@ -236,12 +240,12 @@ static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val,
 	if (cpu >= NR_GIC_CPU_IF || cpu >= nr_cpu_ids)
 		return -EINVAL;
 
-	raw_spin_lock(&irq_controller_lock);
+	raw_spin_lock_irqsave(&irq_controller_lock, flags);
 	mask = 0xff << shift;
 	bit = gic_cpu_map[cpu] << shift;
 	val = readl_relaxed(reg) & ~mask;
 	writel_relaxed(val | bit, reg);
-	raw_spin_unlock(&irq_controller_lock);
+	raw_spin_unlock_irqrestore(&irq_controller_lock, flags);
 
 	return IRQ_SET_MASK_OK;
 }
diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h
index 800544bc7bfd..781974afff9f 100644
--- a/include/linux/irqchip/arm-gic-v3.h
+++ b/include/linux/irqchip/arm-gic-v3.h
@@ -166,6 +166,11 @@
 
 #define GITS_TRANSLATER			0x10040
 
+#define GITS_CTLR_ENABLE		(1U << 0)
+#define GITS_CTLR_QUIESCENT		(1U << 31)
+
+#define GITS_TYPER_DEVBITS_SHIFT	13
+#define GITS_TYPER_DEVBITS(r)		((((r) >> GITS_TYPER_DEVBITS_SHIFT) & 0x1f) + 1)
 #define GITS_TYPER_PTA			(1UL << 19)
 
 #define GITS_CBASER_VALID		(1UL << 63)