Merge tag 'iommu-fixes-v3.14-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu

Pull IOMMU fixes from Joerg Roedel:
 "The fixes are only for the ARM-SMMU driver.  Here is the summary from
  Will Deacon:

   - Andreas Herrmann took the driver for a run with a real SATA
     controller, which caused the new mutex-based locking to explode
     since we require mappings in atomic context

   - Yifan fixed an issue with the page table creation, which then
     caused breakages with the way in which we flush descriptors out to
     the table walker

   - I ran the driver on a system where the SMMU is hooked into a
     coherent interconnect for table walks, and noticed a shareability
     mismatch between the CPU and the SMMU

  These issues are all fixed here and have been tested on both arm and
  arm64 based systems.

  Besides that I put a fix on-top to make the spinlock irq-safe, so that
  the code-paths can be used in the DMA-API"

* tag 'iommu-fixes-v3.14-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu:
  arm/smmu: Use irqsafe spinlock for domain lock
  iommu/arm-smmu: fix compilation issue when !CONFIG_ARM_AMBA
  iommu/arm-smmu: set CBARn.BPSHCFG to NSH for s1-s2-bypass contexts
  iommu/arm-smmu: fix table flushing during initial allocations
  iommu/arm-smmu: really fix page table locking
  iommu/arm-smmu: fix pud/pmd entry fill sequence

1 files changed, 63 insertions, 42 deletions

diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index 8911850..1d9ab39 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -79,7 +79,6 @@
 
 #define ARM_SMMU_PTE_CONT_SIZE		(PAGE_SIZE * ARM_SMMU_PTE_CONT_ENTRIES)
 #define ARM_SMMU_PTE_CONT_MASK		(~(ARM_SMMU_PTE_CONT_SIZE - 1))
-#define ARM_SMMU_PTE_HWTABLE_SIZE	(PTRS_PER_PTE * sizeof(pte_t))
 
 /* Stage-1 PTE */
 #define ARM_SMMU_PTE_AP_UNPRIV		(((pteval_t)1) << 6)
@@ -191,6 +190,9 @@
 #define ARM_SMMU_GR1_CBAR(n)		(0x0 + ((n) << 2))
 #define CBAR_VMID_SHIFT			0
 #define CBAR_VMID_MASK			0xff
+#define CBAR_S1_BPSHCFG_SHIFT		8
+#define CBAR_S1_BPSHCFG_MASK		3
+#define CBAR_S1_BPSHCFG_NSH		3
 #define CBAR_S1_MEMATTR_SHIFT		12
 #define CBAR_S1_MEMATTR_MASK		0xf
 #define CBAR_S1_MEMATTR_WB		0xf
@@ -393,7 +395,7 @@ struct arm_smmu_domain {
 	struct arm_smmu_cfg		root_cfg;
 	phys_addr_t			output_mask;
 
-	struct mutex			lock;
+	spinlock_t			lock;
 };
 
 static DEFINE_SPINLOCK(arm_smmu_devices_lock);
@@ -632,6 +634,28 @@ static irqreturn_t arm_smmu_global_fault(int irq, void *dev)
 	return IRQ_HANDLED;
 }
 
+static void arm_smmu_flush_pgtable(struct arm_smmu_device *smmu, void *addr,
+				   size_t size)
+{
+	unsigned long offset = (unsigned long)addr & ~PAGE_MASK;
+
+
+	/* Ensure new page tables are visible to the hardware walker */
+	if (smmu->features & ARM_SMMU_FEAT_COHERENT_WALK) {
+		dsb();
+	} else {
+		/*
+		 * If the SMMU can't walk tables in the CPU caches, treat them
+		 * like non-coherent DMA since we need to flush the new entries
+		 * all the way out to memory. There's no possibility of
+		 * recursion here as the SMMU table walker will not be wired
+		 * through another SMMU.
+		 */
+		dma_map_page(smmu->dev, virt_to_page(addr), offset, size,
+				DMA_TO_DEVICE);
+	}
+}
+
 static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain)
 {
 	u32 reg;
@@ -650,11 +674,16 @@ static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain)
 	if (smmu->version == 1)
 	      reg |= root_cfg->irptndx << CBAR_IRPTNDX_SHIFT;
 
-	/* Use the weakest memory type, so it is overridden by the pte */
-	if (stage1)
-		reg |= (CBAR_S1_MEMATTR_WB << CBAR_S1_MEMATTR_SHIFT);
-	else
+	/*
+	 * Use the weakest shareability/memory types, so they are
+	 * overridden by the ttbcr/pte.
+	 */
+	if (stage1) {
+		reg |= (CBAR_S1_BPSHCFG_NSH << CBAR_S1_BPSHCFG_SHIFT) |
+			(CBAR_S1_MEMATTR_WB << CBAR_S1_MEMATTR_SHIFT);
+	} else {
 		reg |= ARM_SMMU_CB_VMID(root_cfg) << CBAR_VMID_SHIFT;
+	}
 	writel_relaxed(reg, gr1_base + ARM_SMMU_GR1_CBAR(root_cfg->cbndx));
 
 	if (smmu->version > 1) {
@@ -715,6 +744,8 @@ static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain)
 	}
 
 	/* TTBR0 */
+	arm_smmu_flush_pgtable(smmu, root_cfg->pgd,
+			       PTRS_PER_PGD * sizeof(pgd_t));
 	reg = __pa(root_cfg->pgd);
 	writel_relaxed(reg, cb_base + ARM_SMMU_CB_TTBR0_LO);
 	reg = (phys_addr_t)__pa(root_cfg->pgd) >> 32;
@@ -901,7 +932,7 @@ static int arm_smmu_domain_init(struct iommu_domain *domain)
 		goto out_free_domain;
 	smmu_domain->root_cfg.pgd = pgd;
 
-	mutex_init(&smmu_domain->lock);
+	spin_lock_init(&smmu_domain->lock);
 	domain->priv = smmu_domain;
 	return 0;
 
@@ -1128,6 +1159,7 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
 	struct arm_smmu_domain *smmu_domain = domain->priv;
 	struct arm_smmu_device *device_smmu = dev->archdata.iommu;
 	struct arm_smmu_master *master;
+	unsigned long flags;
 
 	if (!device_smmu) {
 		dev_err(dev, "cannot attach to SMMU, is it on the same bus?\n");
@@ -1138,7 +1170,7 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
 	 * Sanity check the domain. We don't currently support domains
 	 * that cross between different SMMU chains.
 	 */
-	mutex_lock(&smmu_domain->lock);
+	spin_lock_irqsave(&smmu_domain->lock, flags);
 	if (!smmu_domain->leaf_smmu) {
 		/* Now that we have a master, we can finalise the domain */
 		ret = arm_smmu_init_domain_context(domain, dev);
@@ -1153,7 +1185,7 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
 			dev_name(device_smmu->dev));
 		goto err_unlock;
 	}
-	mutex_unlock(&smmu_domain->lock);
+	spin_unlock_irqrestore(&smmu_domain->lock, flags);
 
 	/* Looks ok, so add the device to the domain */
 	master = find_smmu_master(smmu_domain->leaf_smmu, dev->of_node);
@@ -1163,7 +1195,7 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
 	return arm_smmu_domain_add_master(smmu_domain, master);
 
 err_unlock:
-	mutex_unlock(&smmu_domain->lock);
+	spin_unlock_irqrestore(&smmu_domain->lock, flags);
 	return ret;
 }
 
@@ -1177,23 +1209,6 @@ static void arm_smmu_detach_dev(struct iommu_domain *domain, struct device *dev)
 		arm_smmu_domain_remove_master(smmu_domain, master);
 }
 
-static void arm_smmu_flush_pgtable(struct arm_smmu_device *smmu, void *addr,
-				   size_t size)
-{
-	unsigned long offset = (unsigned long)addr & ~PAGE_MASK;
-
-	/*
-	 * If the SMMU can't walk tables in the CPU caches, treat them
-	 * like non-coherent DMA since we need to flush the new entries
-	 * all the way out to memory. There's no possibility of recursion
-	 * here as the SMMU table walker will not be wired through another
-	 * SMMU.
-	 */
-	if (!(smmu->features & ARM_SMMU_FEAT_COHERENT_WALK))
-		dma_map_page(smmu->dev, virt_to_page(addr), offset, size,
-			     DMA_TO_DEVICE);
-}
-
 static bool arm_smmu_pte_is_contiguous_range(unsigned long addr,
 					     unsigned long end)
 {
@@ -1210,12 +1225,11 @@ static int arm_smmu_alloc_init_pte(struct arm_smmu_device *smmu, pmd_t *pmd,
 
 	if (pmd_none(*pmd)) {
 		/* Allocate a new set of tables */
-		pgtable_t table = alloc_page(PGALLOC_GFP);
+		pgtable_t table = alloc_page(GFP_ATOMIC|__GFP_ZERO);
 		if (!table)
 			return -ENOMEM;
 
-		arm_smmu_flush_pgtable(smmu, page_address(table),
-				       ARM_SMMU_PTE_HWTABLE_SIZE);
+		arm_smmu_flush_pgtable(smmu, page_address(table), PAGE_SIZE);
 		if (!pgtable_page_ctor(table)) {
 			__free_page(table);
 			return -ENOMEM;
@@ -1317,9 +1331,15 @@ static int arm_smmu_alloc_init_pmd(struct arm_smmu_device *smmu, pud_t *pud,
 
 #ifndef __PAGETABLE_PMD_FOLDED
 	if (pud_none(*pud)) {
-		pmd = pmd_alloc_one(NULL, addr);
+		pmd = (pmd_t *)get_zeroed_page(GFP_ATOMIC);
 		if (!pmd)
 			return -ENOMEM;
+
+		arm_smmu_flush_pgtable(smmu, pmd, PAGE_SIZE);
+		pud_populate(NULL, pud, pmd);
+		arm_smmu_flush_pgtable(smmu, pud, sizeof(*pud));
+
+		pmd += pmd_index(addr);
 	} else
 #endif
 		pmd = pmd_offset(pud, addr);
@@ -1328,8 +1348,6 @@ static int arm_smmu_alloc_init_pmd(struct arm_smmu_device *smmu, pud_t *pud,
 		next = pmd_addr_end(addr, end);
 		ret = arm_smmu_alloc_init_pte(smmu, pmd, addr, end, pfn,
 					      flags, stage);
-		pud_populate(NULL, pud, pmd);
-		arm_smmu_flush_pgtable(smmu, pud, sizeof(*pud));
 		phys += next - addr;
 	} while (pmd++, addr = next, addr < end);
 
@@ -1346,9 +1364,15 @@ static int arm_smmu_alloc_init_pud(struct arm_smmu_device *smmu, pgd_t *pgd,
 
 #ifndef __PAGETABLE_PUD_FOLDED
 	if (pgd_none(*pgd)) {
-		pud = pud_alloc_one(NULL, addr);
+		pud = (pud_t *)get_zeroed_page(GFP_ATOMIC);
 		if (!pud)
 			return -ENOMEM;
+
+		arm_smmu_flush_pgtable(smmu, pud, PAGE_SIZE);
+		pgd_populate(NULL, pgd, pud);
+		arm_smmu_flush_pgtable(smmu, pgd, sizeof(*pgd));
+
+		pud += pud_index(addr);
 	} else
 #endif
 		pud = pud_offset(pgd, addr);
@@ -1357,8 +1381,6 @@ static int arm_smmu_alloc_init_pud(struct arm_smmu_device *smmu, pgd_t *pgd,
 		next = pud_addr_end(addr, end);
 		ret = arm_smmu_alloc_init_pmd(smmu, pud, addr, next, phys,
 					      flags, stage);
-		pgd_populate(NULL, pud, pgd);
-		arm_smmu_flush_pgtable(smmu, pgd, sizeof(*pgd));
 		phys += next - addr;
 	} while (pud++, addr = next, addr < end);
 
@@ -1375,6 +1397,7 @@ static int arm_smmu_handle_mapping(struct arm_smmu_domain *smmu_domain,
 	struct arm_smmu_cfg *root_cfg = &smmu_domain->root_cfg;
 	pgd_t *pgd = root_cfg->pgd;
 	struct arm_smmu_device *smmu = root_cfg->smmu;
+	unsigned long irqflags;
 
 	if (root_cfg->cbar == CBAR_TYPE_S2_TRANS) {
 		stage = 2;
@@ -1397,7 +1420,7 @@ static int arm_smmu_handle_mapping(struct arm_smmu_domain *smmu_domain,
 	if (paddr & ~output_mask)
 		return -ERANGE;
 
-	mutex_lock(&smmu_domain->lock);
+	spin_lock_irqsave(&smmu_domain->lock, irqflags);
 	pgd += pgd_index(iova);
 	end = iova + size;
 	do {
@@ -1413,11 +1436,7 @@ static int arm_smmu_handle_mapping(struct arm_smmu_domain *smmu_domain,
 	} while (pgd++, iova != end);
 
 out_unlock:
-	mutex_unlock(&smmu_domain->lock);
-
-	/* Ensure new page tables are visible to the hardware walker */
-	if (smmu->features & ARM_SMMU_FEAT_COHERENT_WALK)
-		dsb();
+	spin_unlock_irqrestore(&smmu_domain->lock, irqflags);
 
 	return ret;
 }
@@ -1987,8 +2006,10 @@ static int __init arm_smmu_init(void)
 	if (!iommu_present(&platform_bus_type))
 		bus_set_iommu(&platform_bus_type, &arm_smmu_ops);
 
+#ifdef CONFIG_ARM_AMBA
 	if (!iommu_present(&amba_bustype))
 		bus_set_iommu(&amba_bustype, &arm_smmu_ops);
+#endif
 
 	return 0;
 }