4 files changed, 36 insertions, 15 deletions

diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c
index 1d647104bccc..446703eeee7a 100644
--- a/drivers/iommu/arm-smmu-v3.c
+++ b/drivers/iommu/arm-smmu-v3.c
@@ -24,6 +24,7 @@
 #include <linux/acpi_iort.h>
 #include <linux/bitfield.h>
 #include <linux/bitops.h>
+#include <linux/crash_dump.h>
 #include <linux/delay.h>
 #include <linux/dma-iommu.h>
 #include <linux/err.h>
@@ -366,7 +367,7 @@
 #define MSI_IOVA_BASE			0x8000000
 #define MSI_IOVA_LENGTH			0x100000
 
-static bool disable_bypass;
+static bool disable_bypass = 1;
 module_param_named(disable_bypass, disable_bypass, bool, S_IRUGO);
 MODULE_PARM_DESC(disable_bypass,
 	"Disable bypass streams such that incoming transactions from devices that are not attached to an iommu domain will report an abort back to the device and will not be allowed to pass through the SMMU.");
@@ -1301,6 +1302,7 @@ static irqreturn_t arm_smmu_priq_thread(int irq, void *dev)
 
 	/* Sync our overflow flag, as we believe we're up to speed */
 	q->cons = Q_OVF(q, q->prod) | Q_WRP(q, q->cons) | Q_IDX(q, q->cons);
+	writel(q->cons, q->cons_reg);
 	return IRQ_HANDLED;
 }
 
@@ -2211,8 +2213,12 @@ static int arm_smmu_update_gbpa(struct arm_smmu_device *smmu, u32 set, u32 clr)
 	reg &= ~clr;
 	reg |= set;
 	writel_relaxed(reg | GBPA_UPDATE, gbpa);
-	return readl_relaxed_poll_timeout(gbpa, reg, !(reg & GBPA_UPDATE),
-					  1, ARM_SMMU_POLL_TIMEOUT_US);
+	ret = readl_relaxed_poll_timeout(gbpa, reg, !(reg & GBPA_UPDATE),
+					 1, ARM_SMMU_POLL_TIMEOUT_US);
+
+	if (ret)
+		dev_err(smmu->dev, "GBPA not responding to update\n");
+	return ret;
 }
 
 static void arm_smmu_free_msis(void *data)
@@ -2392,8 +2398,15 @@ static int arm_smmu_device_reset(struct arm_smmu_device *smmu, bool bypass)
 
 	/* Clear CR0 and sync (disables SMMU and queue processing) */
 	reg = readl_relaxed(smmu->base + ARM_SMMU_CR0);
-	if (reg & CR0_SMMUEN)
+	if (reg & CR0_SMMUEN) {
+		if (is_kdump_kernel()) {
+			arm_smmu_update_gbpa(smmu, GBPA_ABORT, 0);
+			arm_smmu_device_disable(smmu);
+			return -EBUSY;
+		}
+
 		dev_warn(smmu->dev, "SMMU currently enabled! Resetting...\n");
+	}
 
 	ret = arm_smmu_device_disable(smmu);
 	if (ret)
@@ -2491,10 +2504,8 @@ static int arm_smmu_device_reset(struct arm_smmu_device *smmu, bool bypass)
 		enables |= CR0_SMMUEN;
 	} else {
 		ret = arm_smmu_update_gbpa(smmu, 0, GBPA_ABORT);
-		if (ret) {
-			dev_err(smmu->dev, "GBPA not responding to update\n");
+		if (ret)
 			return ret;
-		}
 	}
 	ret = arm_smmu_write_reg_sync(smmu, enables, ARM_SMMU_CR0,
 				      ARM_SMMU_CR0ACK);
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index f7a96bcf94a6..5349e22b5c78 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -2103,12 +2103,16 @@ static int arm_smmu_device_probe(struct platform_device *pdev)
 	if (err)
 		return err;
 
-	if (smmu->version == ARM_SMMU_V2 &&
-	    smmu->num_context_banks != smmu->num_context_irqs) {
-		dev_err(dev,
-			"found only %d context interrupt(s) but %d required\n",
-			smmu->num_context_irqs, smmu->num_context_banks);
-		return -ENODEV;
+	if (smmu->version == ARM_SMMU_V2) {
+		if (smmu->num_context_banks > smmu->num_context_irqs) {
+			dev_err(dev,
+			      "found only %d context irq(s) but %d required\n",
+			      smmu->num_context_irqs, smmu->num_context_banks);
+			return -ENODEV;
+		}
+
+		/* Ignore superfluous interrupts */
+		smmu->num_context_irqs = smmu->num_context_banks;
 	}
 
 	for (i = 0; i < smmu->num_global_irqs; ++i) {
diff --git a/drivers/iommu/io-pgtable-arm-v7s.c b/drivers/iommu/io-pgtable-arm-v7s.c
index 50e3a9fcf43e..b5948ba6b3b3 100644
--- a/drivers/iommu/io-pgtable-arm-v7s.c
+++ b/drivers/iommu/io-pgtable-arm-v7s.c
@@ -192,6 +192,7 @@ static void *__arm_v7s_alloc_table(int lvl, gfp_t gfp,
 {
 	struct io_pgtable_cfg *cfg = &data->iop.cfg;
 	struct device *dev = cfg->iommu_dev;
+	phys_addr_t phys;
 	dma_addr_t dma;
 	size_t size = ARM_V7S_TABLE_SIZE(lvl);
 	void *table = NULL;
@@ -200,6 +201,10 @@ static void *__arm_v7s_alloc_table(int lvl, gfp_t gfp,
 		table = (void *)__get_dma_pages(__GFP_ZERO, get_order(size));
 	else if (lvl == 2)
 		table = kmem_cache_zalloc(data->l2_tables, gfp | GFP_DMA);
+	phys = virt_to_phys(table);
+	if (phys != (arm_v7s_iopte)phys)
+		/* Doesn't fit in PTE */
+		goto out_free;
 	if (table && !(cfg->quirks & IO_PGTABLE_QUIRK_NO_DMA)) {
 		dma = dma_map_single(dev, table, size, DMA_TO_DEVICE);
 		if (dma_mapping_error(dev, dma))
@@ -209,7 +214,7 @@ static void *__arm_v7s_alloc_table(int lvl, gfp_t gfp,
 		 * address directly, so if the DMA layer suggests otherwise by
 		 * translating or truncating them, that bodes very badly...
 		 */
-		if (dma != virt_to_phys(table))
+		if (dma != phys)
 			goto out_unmap;
 	}
 	kmemleak_ignore(table);
diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
index 010a254305dd..88641b4560bc 100644
--- a/drivers/iommu/io-pgtable-arm.c
+++ b/drivers/iommu/io-pgtable-arm.c
@@ -237,7 +237,8 @@ static void *__arm_lpae_alloc_pages(size_t size, gfp_t gfp,
 	void *pages;
 
 	VM_BUG_ON((gfp & __GFP_HIGHMEM));
-	p = alloc_pages_node(dev_to_node(dev), gfp | __GFP_ZERO, order);
+	p = alloc_pages_node(dev ? dev_to_node(dev) : NUMA_NO_NODE,
+			     gfp | __GFP_ZERO, order);
 	if (!p)
 		return NULL;