Merge tag 'iommu-updates-v3.12' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu

Pull IOMMU Updates from Joerg Roedel:
 "This round the updates contain:

   - A new driver for the Freescale PAMU IOMMU from Varun Sethi.

     This driver has cooked for a while and required changes to the
     IOMMU-API and infrastructure that were already merged before.

   - Updates for the ARM-SMMU driver from Will Deacon

   - Various fixes, the most important one is probably a fix from Alex
     Williamson for a memory leak in the VT-d page-table freeing code

  In summary not all that much.  The biggest part in the diffstat is the
  new PAMU driver"

* tag 'iommu-updates-v3.12' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu:
  intel-iommu: Fix leaks in pagetable freeing
  iommu/amd: Fix resource leak in iommu_init_device()
  iommu/amd: Clean up unnecessary MSI/MSI-X capability find
  iommu/arm-smmu: Simplify VMID and ASID allocation
  iommu/arm-smmu: Don't use VMIDs for stage-1 translations
  iommu/arm-smmu: Tighten up global fault reporting
  iommu/arm-smmu: Remove broken big-endian check
  iommu/fsl: Remove unnecessary 'fsl-pamu' prefixes
  iommu/fsl: Fix whitespace problems noticed by git-am
  iommu/fsl: Freescale PAMU driver and iommu implementation.
  iommu/fsl: Add additional iommu attributes required by the PAMU driver.
  powerpc: Add iommu domain pointer to device archdata
  iommu/exynos: Remove dead code (set_prefbuf)

1 files changed, 56 insertions, 37 deletions

diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index ebd0a4cff049..f417e89e1e7e 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -56,9 +56,6 @@
 /* Maximum number of mapping groups per SMMU */
 #define ARM_SMMU_MAX_SMRS		128
 
-/* Number of VMIDs per SMMU */
-#define ARM_SMMU_NUM_VMIDS		256
-
 /* SMMU global address space */
 #define ARM_SMMU_GR0(smmu)		((smmu)->base)
 #define ARM_SMMU_GR1(smmu)		((smmu)->base + (smmu)->pagesize)
@@ -87,6 +84,7 @@
 #define ARM_SMMU_PTE_AP_UNPRIV		(((pteval_t)1) << 6)
 #define ARM_SMMU_PTE_AP_RDONLY		(((pteval_t)2) << 6)
 #define ARM_SMMU_PTE_ATTRINDX_SHIFT	2
+#define ARM_SMMU_PTE_nG			(((pteval_t)1) << 11)
 
 /* Stage-2 PTE */
 #define ARM_SMMU_PTE_HAP_FAULT		(((pteval_t)0) << 6)
@@ -223,6 +221,7 @@
 #define ARM_SMMU_CB_FAR_LO		0x60
 #define ARM_SMMU_CB_FAR_HI		0x64
 #define ARM_SMMU_CB_FSYNR0		0x68
+#define ARM_SMMU_CB_S1_TLBIASID		0x610
 
 #define SCTLR_S1_ASIDPNE		(1 << 12)
 #define SCTLR_CFCFG			(1 << 7)
@@ -282,6 +281,8 @@
 #define TTBCR2_ADDR_44			4
 #define TTBCR2_ADDR_48			5
 
+#define TTBRn_HI_ASID_SHIFT		16
+
 #define MAIR_ATTR_SHIFT(n)		((n) << 3)
 #define MAIR_ATTR_MASK			0xff
 #define MAIR_ATTR_DEVICE		0x04
@@ -305,7 +306,7 @@
 #define FSR_IGN				(FSR_AFF | FSR_ASF | FSR_TLBMCF |	\
 					 FSR_TLBLKF)
 #define FSR_FAULT			(FSR_MULTI | FSR_SS | FSR_UUT |		\
-					 FSR_EF | FSR_PF | FSR_TF)
+					 FSR_EF | FSR_PF | FSR_TF | FSR_IGN)
 
 #define FSYNR0_WNR			(1 << 4)
 
@@ -365,21 +366,21 @@ struct arm_smmu_device {
 	u32				num_context_irqs;
 	unsigned int			*irqs;
 
-	DECLARE_BITMAP(vmid_map, ARM_SMMU_NUM_VMIDS);
-
 	struct list_head		list;
 	struct rb_root			masters;
 };
 
 struct arm_smmu_cfg {
 	struct arm_smmu_device		*smmu;
-	u8				vmid;
 	u8				cbndx;
 	u8				irptndx;
 	u32				cbar;
 	pgd_t				*pgd;
 };
 
+#define ARM_SMMU_CB_ASID(cfg)		((cfg)->cbndx)
+#define ARM_SMMU_CB_VMID(cfg)		((cfg)->cbndx + 1)
+
 struct arm_smmu_domain {
 	/*
 	 * A domain can span across multiple, chained SMMUs and requires
@@ -533,6 +534,25 @@ static void arm_smmu_tlb_sync(struct arm_smmu_device *smmu)
 	}
 }
 
+static void arm_smmu_tlb_inv_context(struct arm_smmu_cfg *cfg)
+{
+	struct arm_smmu_device *smmu = cfg->smmu;
+	void __iomem *base = ARM_SMMU_GR0(smmu);
+	bool stage1 = cfg->cbar != CBAR_TYPE_S2_TRANS;
+
+	if (stage1) {
+		base = ARM_SMMU_CB_BASE(smmu) + ARM_SMMU_CB(smmu, cfg->cbndx);
+		writel_relaxed(ARM_SMMU_CB_ASID(cfg),
+			       base + ARM_SMMU_CB_S1_TLBIASID);
+	} else {
+		base = ARM_SMMU_GR0(smmu);
+		writel_relaxed(ARM_SMMU_CB_VMID(cfg),
+			       base + ARM_SMMU_GR0_TLBIVMID);
+	}
+
+	arm_smmu_tlb_sync(smmu);
+}
+
 static irqreturn_t arm_smmu_context_fault(int irq, void *dev)
 {
 	int flags, ret;
@@ -590,6 +610,9 @@ static irqreturn_t arm_smmu_global_fault(int irq, void *dev)
 	void __iomem *gr0_base = ARM_SMMU_GR0(smmu);
 
 	gfsr = readl_relaxed(gr0_base + ARM_SMMU_GR0_sGFSR);
+	if (!gfsr)
+		return IRQ_NONE;
+
 	gfsynr0 = readl_relaxed(gr0_base + ARM_SMMU_GR0_sGFSYNR0);
 	gfsynr1 = readl_relaxed(gr0_base + ARM_SMMU_GR0_sGFSYNR1);
 	gfsynr2 = readl_relaxed(gr0_base + ARM_SMMU_GR0_sGFSYNR2);
@@ -601,7 +624,7 @@ static irqreturn_t arm_smmu_global_fault(int irq, void *dev)
 		gfsr, gfsynr0, gfsynr1, gfsynr2);
 
 	writel(gfsr, gr0_base + ARM_SMMU_GR0_sGFSR);
-	return IRQ_NONE;
+	return IRQ_HANDLED;
 }
 
 static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain)
@@ -618,14 +641,15 @@ static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain)
 	cb_base = ARM_SMMU_CB_BASE(smmu) + ARM_SMMU_CB(smmu, root_cfg->cbndx);
 
 	/* CBAR */
-	reg = root_cfg->cbar |
-	      (root_cfg->vmid << CBAR_VMID_SHIFT);
+	reg = root_cfg->cbar;
 	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
+		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) {
@@ -687,15 +711,11 @@ static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain)
 
 	/* TTBR0 */
 	reg = __pa(root_cfg->pgd);
-#ifndef __BIG_ENDIAN
 	writel_relaxed(reg, cb_base + ARM_SMMU_CB_TTBR0_LO);
 	reg = (phys_addr_t)__pa(root_cfg->pgd) >> 32;
+	if (stage1)
+		reg |= ARM_SMMU_CB_ASID(root_cfg) << TTBRn_HI_ASID_SHIFT;
 	writel_relaxed(reg, cb_base + ARM_SMMU_CB_TTBR0_HI);
-#else
-	writel_relaxed(reg, cb_base + ARM_SMMU_CB_TTBR0_HI);
-	reg = (phys_addr_t)__pa(root_cfg->pgd) >> 32;
-	writel_relaxed(reg, cb_base + ARM_SMMU_CB_TTBR0_LO);
-#endif
 
 	/*
 	 * TTBCR
@@ -750,10 +770,6 @@ static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain)
 		writel_relaxed(reg, cb_base + ARM_SMMU_CB_S1_MAIR0);
 	}
 
-	/* Nuke the TLB */
-	writel_relaxed(root_cfg->vmid, gr0_base + ARM_SMMU_GR0_TLBIVMID);
-	arm_smmu_tlb_sync(smmu);
-
 	/* SCTLR */
 	reg = SCTLR_CFCFG | SCTLR_CFIE | SCTLR_CFRE | SCTLR_M | SCTLR_EAE_SBOP;
 	if (stage1)
@@ -790,11 +806,6 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain,
 		return -ENODEV;
 	}
 
-	ret = __arm_smmu_alloc_bitmap(smmu->vmid_map, 0, ARM_SMMU_NUM_VMIDS);
-	if (IS_ERR_VALUE(ret))
-		return ret;
-
-	root_cfg->vmid = ret;
 	if (smmu->features & ARM_SMMU_FEAT_TRANS_NESTED) {
 		/*
 		 * We will likely want to change this if/when KVM gets
@@ -813,10 +824,9 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain,
 	ret = __arm_smmu_alloc_bitmap(smmu->context_map, start,
 				      smmu->num_context_banks);
 	if (IS_ERR_VALUE(ret))
-		goto out_free_vmid;
+		return ret;
 
 	root_cfg->cbndx = ret;
-
 	if (smmu->version == 1) {
 		root_cfg->irptndx = atomic_inc_return(&smmu->irptndx);
 		root_cfg->irptndx %= smmu->num_context_irqs;
@@ -840,8 +850,6 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain,
 
 out_free_context:
 	__arm_smmu_free_bitmap(smmu->context_map, root_cfg->cbndx);
-out_free_vmid:
-	__arm_smmu_free_bitmap(smmu->vmid_map, root_cfg->vmid);
 	return ret;
 }
 
@@ -850,17 +858,22 @@ static void arm_smmu_destroy_domain_context(struct iommu_domain *domain)
 	struct arm_smmu_domain *smmu_domain = domain->priv;
 	struct arm_smmu_cfg *root_cfg = &smmu_domain->root_cfg;
 	struct arm_smmu_device *smmu = root_cfg->smmu;
+	void __iomem *cb_base;
 	int irq;
 
 	if (!smmu)
 		return;
 
+	/* Disable the context bank and nuke the TLB before freeing it. */
+	cb_base = ARM_SMMU_CB_BASE(smmu) + ARM_SMMU_CB(smmu, root_cfg->cbndx);
+	writel_relaxed(0, cb_base + ARM_SMMU_CB_SCTLR);
+	arm_smmu_tlb_inv_context(root_cfg);
+
 	if (root_cfg->irptndx != -1) {
 		irq = smmu->irqs[smmu->num_global_irqs + root_cfg->irptndx];
 		free_irq(irq, domain);
 	}
 
-	__arm_smmu_free_bitmap(smmu->vmid_map, root_cfg->vmid);
 	__arm_smmu_free_bitmap(smmu->context_map, root_cfg->cbndx);
 }
 
@@ -959,6 +972,11 @@ static void arm_smmu_free_pgtables(struct arm_smmu_domain *smmu_domain)
 static void arm_smmu_domain_destroy(struct iommu_domain *domain)
 {
 	struct arm_smmu_domain *smmu_domain = domain->priv;
+
+	/*
+	 * Free the domain resources. We assume that all devices have
+	 * already been detached.
+	 */
 	arm_smmu_destroy_domain_context(domain);
 	arm_smmu_free_pgtables(smmu_domain);
 	kfree(smmu_domain);
@@ -1199,7 +1217,7 @@ static int arm_smmu_alloc_init_pte(struct arm_smmu_device *smmu, pmd_t *pmd,
 	}
 
 	if (stage == 1) {
-		pteval |= ARM_SMMU_PTE_AP_UNPRIV;
+		pteval |= ARM_SMMU_PTE_AP_UNPRIV | ARM_SMMU_PTE_nG;
 		if (!(flags & IOMMU_WRITE) && (flags & IOMMU_READ))
 			pteval |= ARM_SMMU_PTE_AP_RDONLY;
 
@@ -1415,13 +1433,9 @@ static size_t arm_smmu_unmap(struct iommu_domain *domain, unsigned long iova,
 {
 	int ret;
 	struct arm_smmu_domain *smmu_domain = domain->priv;
-	struct arm_smmu_cfg *root_cfg = &smmu_domain->root_cfg;
-	struct arm_smmu_device *smmu = root_cfg->smmu;
-	void __iomem *gr0_base = ARM_SMMU_GR0(smmu);
 
 	ret = arm_smmu_handle_mapping(smmu_domain, iova, 0, size, 0);
-	writel_relaxed(root_cfg->vmid, gr0_base + ARM_SMMU_GR0_TLBIVMID);
-	arm_smmu_tlb_sync(smmu);
+	arm_smmu_tlb_inv_context(&smmu_domain->root_cfg);
 	return ret ? ret : size;
 }
 
@@ -1544,6 +1558,7 @@ static struct iommu_ops arm_smmu_ops = {
 static void arm_smmu_device_reset(struct arm_smmu_device *smmu)
 {
 	void __iomem *gr0_base = ARM_SMMU_GR0(smmu);
+	void __iomem *sctlr_base = ARM_SMMU_CB_BASE(smmu) + ARM_SMMU_CB_SCTLR;
 	int i = 0;
 	u32 scr0 = readl_relaxed(gr0_base + ARM_SMMU_GR0_sCR0);
 
@@ -1553,6 +1568,10 @@ static void arm_smmu_device_reset(struct arm_smmu_device *smmu)
 		writel_relaxed(S2CR_TYPE_BYPASS, gr0_base + ARM_SMMU_GR0_S2CR(i));
 	}
 
+	/* Make sure all context banks are disabled */
+	for (i = 0; i < smmu->num_context_banks; ++i)
+		writel_relaxed(0, sctlr_base + ARM_SMMU_CB(smmu, i));
+
 	/* Invalidate the TLB, just in case */
 	writel_relaxed(0, gr0_base + ARM_SMMU_GR0_STLBIALL);
 	writel_relaxed(0, gr0_base + ARM_SMMU_GR0_TLBIALLH);
@@ -1906,7 +1925,7 @@ static int arm_smmu_device_remove(struct platform_device *pdev)
 		of_node_put(master->of_node);
 	}
 
-	if (!bitmap_empty(smmu->vmid_map, ARM_SMMU_NUM_VMIDS))
+	if (!bitmap_empty(smmu->context_map, ARM_SMMU_MAX_CBS))
 		dev_err(dev, "removing device with active domains!\n");
 
 	for (i = 0; i < smmu->num_global_irqs; ++i)