1 files changed, 110 insertions, 44 deletions

diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index db20e992a40f..2dd1ff0cf558 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -97,9 +97,14 @@ struct its_device;
  * The ITS structure - contains most of the infrastructure, with the
  * top-level MSI domain, the command queue, the collections, and the
  * list of devices writing to it.
+ *
+ * dev_alloc_lock has to be taken for device allocations, while the
+ * spinlock must be taken to parse data structures such as the device
+ * list.
  */
 struct its_node {
 	raw_spinlock_t		lock;
+	struct mutex		dev_alloc_lock;
 	struct list_head	entry;
 	void __iomem		*base;
 	phys_addr_t		phys_base;
@@ -156,6 +161,7 @@ struct its_device {
 	void			*itt;
 	u32			nr_ites;
 	u32			device_id;
+	bool			shared;
 };
 
 static struct {
@@ -1580,6 +1586,9 @@ static unsigned long *its_lpi_alloc(int nr_irqs, u32 *base, int *nr_ids)
 		nr_irqs /= 2;
 	} while (nr_irqs > 0);
 
+	if (!nr_irqs)
+		err = -ENOSPC;
+
 	if (err)
 		goto out;
 
@@ -1737,6 +1746,7 @@ static int its_setup_baser(struct its_node *its, struct its_baser *baser,
 	u64 type = GITS_BASER_TYPE(val);
 	u64 baser_phys, tmp;
 	u32 alloc_pages;
+	struct page *page;
 	void *base;
 
 retry_alloc_baser:
@@ -1749,10 +1759,11 @@ retry_alloc_baser:
 		order = get_order(GITS_BASER_PAGES_MAX * psz);
 	}
 
-	base = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, order);
-	if (!base)
+	page = alloc_pages_node(its->numa_node, GFP_KERNEL | __GFP_ZERO, order);
+	if (!page)
 		return -ENOMEM;
 
+	base = (void *)page_address(page);
 	baser_phys = virt_to_phys(base);
 
 	/* Check if the physical address of the memory is above 48bits */
@@ -1946,6 +1957,8 @@ static int its_alloc_tables(struct its_node *its)
 			indirect = its_parse_indirect_baser(its, baser,
 							    psz, &order,
 							    its->device_ids);
+			break;
+
 		case GITS_BASER_TYPE_VCPU:
 			indirect = its_parse_indirect_baser(its, baser,
 							    psz, &order,
@@ -2059,6 +2072,29 @@ static int __init allocate_lpi_tables(void)
 	return 0;
 }
 
+static u64 its_clear_vpend_valid(void __iomem *vlpi_base)
+{
+	u32 count = 1000000;	/* 1s! */
+	bool clean;
+	u64 val;
+
+	val = gits_read_vpendbaser(vlpi_base + GICR_VPENDBASER);
+	val &= ~GICR_VPENDBASER_Valid;
+	gits_write_vpendbaser(val, vlpi_base + GICR_VPENDBASER);
+
+	do {
+		val = gits_read_vpendbaser(vlpi_base + GICR_VPENDBASER);
+		clean = !(val & GICR_VPENDBASER_Dirty);
+		if (!clean) {
+			count--;
+			cpu_relax();
+			udelay(1);
+		}
+	} while (!clean && count);
+
+	return val;
+}
+
 static void its_cpu_init_lpis(void)
 {
 	void __iomem *rbase = gic_data_rdist_rd_base();
@@ -2144,6 +2180,30 @@ static void its_cpu_init_lpis(void)
 	val |= GICR_CTLR_ENABLE_LPIS;
 	writel_relaxed(val, rbase + GICR_CTLR);
 
+	if (gic_rdists->has_vlpis) {
+		void __iomem *vlpi_base = gic_data_rdist_vlpi_base();
+
+		/*
+		 * It's possible for CPU to receive VLPIs before it is
+		 * sheduled as a vPE, especially for the first CPU, and the
+		 * VLPI with INTID larger than 2^(IDbits+1) will be considered
+		 * as out of range and dropped by GIC.
+		 * So we initialize IDbits to known value to avoid VLPI drop.
+		 */
+		val = (LPI_NRBITS - 1) & GICR_VPROPBASER_IDBITS_MASK;
+		pr_debug("GICv4: CPU%d: Init IDbits to 0x%llx for GICR_VPROPBASER\n",
+			smp_processor_id(), val);
+		gits_write_vpropbaser(val, vlpi_base + GICR_VPROPBASER);
+
+		/*
+		 * Also clear Valid bit of GICR_VPENDBASER, in case some
+		 * ancient programming gets left in and has possibility of
+		 * corrupting memory.
+		 */
+		val = its_clear_vpend_valid(vlpi_base);
+		WARN_ON(val & GICR_VPENDBASER_Dirty);
+	}
+
 	/* Make sure the GIC has seen the above */
 	dsb(sy);
 out:
@@ -2236,7 +2296,8 @@ static struct its_baser *its_get_baser(struct its_node *its, u32 type)
 	return NULL;
 }
 
-static bool its_alloc_table_entry(struct its_baser *baser, u32 id)
+static bool its_alloc_table_entry(struct its_node *its,
+				  struct its_baser *baser, u32 id)
 {
 	struct page *page;
 	u32 esz, idx;
@@ -2256,7 +2317,8 @@ static bool its_alloc_table_entry(struct its_baser *baser, u32 id)
 
 	/* Allocate memory for 2nd level table */
 	if (!table[idx]) {
-		page = alloc_pages(GFP_KERNEL | __GFP_ZERO, get_order(baser->psz));
+		page = alloc_pages_node(its->numa_node, GFP_KERNEL | __GFP_ZERO,
+					get_order(baser->psz));
 		if (!page)
 			return false;
 
@@ -2287,7 +2349,7 @@ static bool its_alloc_device_table(struct its_node *its, u32 dev_id)
 	if (!baser)
 		return (ilog2(dev_id) < its->device_ids);
 
-	return its_alloc_table_entry(baser, dev_id);
+	return its_alloc_table_entry(its, baser, dev_id);
 }
 
 static bool its_alloc_vpe_table(u32 vpe_id)
@@ -2311,7 +2373,7 @@ static bool its_alloc_vpe_table(u32 vpe_id)
 		if (!baser)
 			return false;
 
-		if (!its_alloc_table_entry(baser, vpe_id))
+		if (!its_alloc_table_entry(its, baser, vpe_id))
 			return false;
 	}
 
@@ -2345,7 +2407,7 @@ static struct its_device *its_create_device(struct its_node *its, u32 dev_id,
 	nr_ites = max(2, nvecs);
 	sz = nr_ites * its->ite_size;
 	sz = max(sz, ITS_ITT_ALIGN) + ITS_ITT_ALIGN - 1;
-	itt = kzalloc(sz, GFP_KERNEL);
+	itt = kzalloc_node(sz, GFP_KERNEL, its->numa_node);
 	if (alloc_lpis) {
 		lpi_map = its_lpi_alloc(nvecs, &lpi_base, &nr_lpis);
 		if (lpi_map)
@@ -2399,13 +2461,14 @@ static void its_free_device(struct its_device *its_dev)
 	kfree(its_dev);
 }
 
-static int its_alloc_device_irq(struct its_device *dev, irq_hw_number_t *hwirq)
+static int its_alloc_device_irq(struct its_device *dev, int nvecs, irq_hw_number_t *hwirq)
 {
 	int idx;
 
-	idx = find_first_zero_bit(dev->event_map.lpi_map,
-				  dev->event_map.nr_lpis);
-	if (idx == dev->event_map.nr_lpis)
+	idx = bitmap_find_free_region(dev->event_map.lpi_map,
+				      dev->event_map.nr_lpis,
+				      get_count_order(nvecs));
+	if (idx < 0)
 		return -ENOSPC;
 
 	*hwirq = dev->event_map.lpi_base + idx;
@@ -2421,6 +2484,7 @@ static int its_msi_prepare(struct irq_domain *domain, struct device *dev,
 	struct its_device *its_dev;
 	struct msi_domain_info *msi_info;
 	u32 dev_id;
+	int err = 0;
 
 	/*
 	 * We ignore "dev" entierely, and rely on the dev_id that has
@@ -2443,6 +2507,7 @@ static int its_msi_prepare(struct irq_domain *domain, struct device *dev,
 		return -EINVAL;
 	}
 
+	mutex_lock(&its->dev_alloc_lock);
 	its_dev = its_find_device(its, dev_id);
 	if (its_dev) {
 		/*
@@ -2450,18 +2515,22 @@ static int its_msi_prepare(struct irq_domain *domain, struct device *dev,
 		 * another alias (PCI bridge of some sort). No need to
 		 * create the device.
 		 */
+		its_dev->shared = true;
 		pr_debug("Reusing ITT for devID %x\n", dev_id);
 		goto out;
 	}
 
 	its_dev = its_create_device(its, dev_id, nvec, true);
-	if (!its_dev)
-		return -ENOMEM;
+	if (!its_dev) {
+		err = -ENOMEM;
+		goto out;
+	}
 
 	pr_debug("ITT %d entries, %d bits\n", nvec, ilog2(nvec));
 out:
+	mutex_unlock(&its->dev_alloc_lock);
 	info->scratchpad[0].ptr = its_dev;
-	return 0;
+	return err;
 }
 
 static struct msi_domain_ops its_msi_domain_ops = {
@@ -2501,21 +2570,21 @@ static int its_irq_domain_alloc(struct irq_domain *domain, unsigned int virq,
 	int err;
 	int i;
 
-	for (i = 0; i < nr_irqs; i++) {
-		err = its_alloc_device_irq(its_dev, &hwirq);
-		if (err)
-			return err;
+	err = its_alloc_device_irq(its_dev, nr_irqs, &hwirq);
+	if (err)
+		return err;
 
-		err = its_irq_gic_domain_alloc(domain, virq + i, hwirq);
+	for (i = 0; i < nr_irqs; i++) {
+		err = its_irq_gic_domain_alloc(domain, virq + i, hwirq + i);
 		if (err)
 			return err;
 
 		irq_domain_set_hwirq_and_chip(domain, virq + i,
-					      hwirq, &its_irq_chip, its_dev);
+					      hwirq + i, &its_irq_chip, its_dev);
 		irqd_set_single_target(irq_desc_get_irq_data(irq_to_desc(virq + i)));
 		pr_debug("ID:%d pID:%d vID:%d\n",
-			 (int)(hwirq - its_dev->event_map.lpi_base),
-			 (int) hwirq, virq + i);
+			 (int)(hwirq + i - its_dev->event_map.lpi_base),
+			 (int)(hwirq + i), virq + i);
 	}
 
 	return 0;
@@ -2565,6 +2634,7 @@ 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;
 
 	for (i = 0; i < nr_irqs; i++) {
@@ -2579,8 +2649,14 @@ static void its_irq_domain_free(struct irq_domain *domain, unsigned int virq,
 		irq_domain_reset_irq_data(data);
 	}
 
-	/* If all interrupts have been freed, start mopping the floor */
-	if (bitmap_empty(its_dev->event_map.lpi_map,
+	mutex_lock(&its->dev_alloc_lock);
+
+	/*
+	 * If all interrupts have been freed, start mopping the
+	 * floor. This is conditionned 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,
@@ -2592,6 +2668,8 @@ static void its_irq_domain_free(struct irq_domain *domain, unsigned int virq,
 		its_free_device(its_dev);
 	}
 
+	mutex_unlock(&its->dev_alloc_lock);
+
 	irq_domain_free_irqs_parent(domain, virq, nr_irqs);
 }
 
@@ -2754,26 +2832,11 @@ static void its_vpe_schedule(struct its_vpe *vpe)
 static void its_vpe_deschedule(struct its_vpe *vpe)
 {
 	void __iomem *vlpi_base = gic_data_rdist_vlpi_base();
-	u32 count = 1000000;	/* 1s! */
-	bool clean;
 	u64 val;
 
-	/* We're being scheduled out */
-	val = gits_read_vpendbaser(vlpi_base + GICR_VPENDBASER);
-	val &= ~GICR_VPENDBASER_Valid;
-	gits_write_vpendbaser(val, vlpi_base + GICR_VPENDBASER);
+	val = its_clear_vpend_valid(vlpi_base);
 
-	do {
-		val = gits_read_vpendbaser(vlpi_base + GICR_VPENDBASER);
-		clean = !(val & GICR_VPENDBASER_Dirty);
-		if (!clean) {
-			count--;
-			cpu_relax();
-			udelay(1);
-		}
-	} while (!clean && count);
-
-	if (unlikely(!clean && !count)) {
+	if (unlikely(val & GICR_VPENDBASER_Dirty)) {
 		pr_err_ratelimited("ITS virtual pending table not cleaning\n");
 		vpe->idai = false;
 		vpe->pending_last = true;
@@ -3486,6 +3549,7 @@ static int __init its_probe_one(struct resource *res,
 	void __iomem *its_base;
 	u32 val, ctlr;
 	u64 baser, tmp, typer;
+	struct page *page;
 	int err;
 
 	its_base = ioremap(res->start, resource_size(res));
@@ -3516,6 +3580,7 @@ static int __init its_probe_one(struct resource *res,
 	}
 
 	raw_spin_lock_init(&its->lock);
+	mutex_init(&its->dev_alloc_lock);
 	INIT_LIST_HEAD(&its->entry);
 	INIT_LIST_HEAD(&its->its_device_list);
 	typer = gic_read_typer(its_base + GITS_TYPER);
@@ -3541,12 +3606,13 @@ static int __init its_probe_one(struct resource *res,
 
 	its->numa_node = numa_node;
 
-	its->cmd_base = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
-						get_order(ITS_CMD_QUEUE_SZ));
-	if (!its->cmd_base) {
+	page = alloc_pages_node(its->numa_node, GFP_KERNEL | __GFP_ZERO,
+				get_order(ITS_CMD_QUEUE_SZ));
+	if (!page) {
 		err = -ENOMEM;
 		goto out_free_its;
 	}
+	its->cmd_base = (void *)page_address(page);
 	its->cmd_write = its->cmd_base;
 	its->fwnode_handle = handle;
 	its->get_msi_base = its_irq_get_msi_base;