Merge branches 'arm/exynos', 'ppc/pamu', 'arm/smmu', 'x86/amd' and 'iommu/fixes' into next

arch/powerpc/include/asm/device.h

@@ -28,6 +28,9 @@ struct dev_archdata {
 		void		*iommu_table_base;
 	} dma_data;
 
+#ifdef CONFIG_IOMMU_API
+	void			*iommu_domain;
+#endif
 #ifdef CONFIG_SWIOTLB
 	dma_addr_t		max_direct_dma_addr;
 #endif

arch/powerpc/include/asm/fsl_pamu_stash.h

+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ *
+ * Copyright (C) 2013 Freescale Semiconductor, Inc.
+ *
+ */
+
+#ifndef __FSL_PAMU_STASH_H
+#define __FSL_PAMU_STASH_H
+
+/* cache stash targets */
+enum pamu_stash_target {
+	PAMU_ATTR_CACHE_L1 = 1,
+	PAMU_ATTR_CACHE_L2,
+	PAMU_ATTR_CACHE_L3,
+};
+
+/*
+ * This attribute allows configuring stashig specific parameters
+ * in the PAMU hardware.
+ */
+
+struct pamu_stash_attribute {
+	u32 	cpu;	/* cpu number */
+	u32 	cache;	/* cache to stash to: L1,L2,L3 */
+};
+
+#endif  /* __FSL_PAMU_STASH_H */

arch/powerpc/sysdev/fsl_pci.h

@@ -16,6 +16,11 @@
 
 struct platform_device;
 
+
+/* FSL PCI controller BRR1 register */
+#define PCI_FSL_BRR1      0xbf8
+#define PCI_FSL_BRR1_VER 0xffff
+
 #define PCIE_LTSSM	0x0404		/* PCIE Link Training and Status */
 #define PCIE_LTSSM_L0	0x16		/* L0 state */
 #define PCIE_IP_REV_2_2		0x02080202 /* PCIE IP block version Rev2.2 */

drivers/iommu/Kconfig

@@ -17,6 +17,16 @@ config OF_IOMMU
        def_bool y
        depends on OF
 
+config FSL_PAMU
+	bool "Freescale IOMMU support"
+	depends on PPC_E500MC
+	select IOMMU_API
+	select GENERIC_ALLOCATOR
+	help
+	  Freescale PAMU support. PAMU is the IOMMU present on Freescale QorIQ platforms.
+	  PAMU can authorize memory access, remap the memory address, and remap I/O
+	  transaction types.
+
 # MSM IOMMU support
 config MSM_IOMMU
 	bool "MSM IOMMU Support"

drivers/iommu/Makefile

@@ -16,3 +16,4 @@ obj-$(CONFIG_TEGRA_IOMMU_SMMU) += tegra-smmu.o
 obj-$(CONFIG_EXYNOS_IOMMU) += exynos-iommu.o
 obj-$(CONFIG_SHMOBILE_IOMMU) += shmobile-iommu.o
 obj-$(CONFIG_SHMOBILE_IPMMU) += shmobile-ipmmu.o
+obj-$(CONFIG_FSL_PAMU) += fsl_pamu.o fsl_pamu_domain.o

drivers/iommu/amd_iommu.c

@@ -456,8 +456,10 @@ static int iommu_init_device(struct device *dev)
 	}
 
 	ret = init_iommu_group(dev);
-	if (ret)
+	if (ret) {
+		free_dev_data(dev_data);
 		return ret;
+	}
 
 	if (pci_iommuv2_capable(pdev)) {
 		struct amd_iommu *iommu;

drivers/iommu/amd_iommu_init.c

@@ -1384,7 +1384,7 @@ static int iommu_init_msi(struct amd_iommu *iommu)
 	if (iommu->int_enabled)
 		goto enable_faults;
 
-	if (pci_find_capability(iommu->dev, PCI_CAP_ID_MSI))
+	if (iommu->dev->msi_cap)
 		ret = iommu_setup_msi(iommu);
 	else
 		ret = -ENODEV;

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)

drivers/iommu/exynos-iommu.c

@@ -247,50 +247,6 @@ static void __sysmmu_set_prefbuf(void __iomem *sfrbase, unsigned long base,
 	__raw_writel(size - 1 + base,  sfrbase + REG_PB0_EADDR + idx * 8);
 }
 
-void exynos_sysmmu_set_prefbuf(struct device *dev,
-				unsigned long base0, unsigned long size0,
-				unsigned long base1, unsigned long size1)
-{
-	struct sysmmu_drvdata *data = dev_get_drvdata(dev->archdata.iommu);
-	unsigned long flags;
-	int i;
-
-	BUG_ON((base0 + size0) <= base0);
-	BUG_ON((size1 > 0) && ((base1 + size1) <= base1));
-
-	read_lock_irqsave(&data->lock, flags);
-	if (!is_sysmmu_active(data))
-		goto finish;
-
-	for (i = 0; i < data->nsfrs; i++) {
-		if ((readl(data->sfrbases[i] + REG_MMU_VERSION) >> 28) == 3) {
-			if (!sysmmu_block(data->sfrbases[i]))
-				continue;
-
-			if (size1 == 0) {
-				if (size0 <= SZ_128K) {
-					base1 = base0;
-					size1 = size0;
-				} else {
-					size1 = size0 -
-						ALIGN(size0 / 2, SZ_64K);
-					size0 = size0 - size1;
-					base1 = base0 + size0;
-				}
-			}
-
-			__sysmmu_set_prefbuf(
-					data->sfrbases[i], base0, size0, 0);
-			__sysmmu_set_prefbuf(
-					data->sfrbases[i], base1, size1, 1);
-
-			sysmmu_unblock(data->sfrbases[i]);
-		}
-	}
-finish:
-	read_unlock_irqrestore(&data->lock, flags);
-}
-
 static void __set_fault_handler(struct sysmmu_drvdata *data,
 					sysmmu_fault_handler_t handler)
 {

drivers/iommu/fsl_pamu.h

+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ *
+ * Copyright (C) 2013 Freescale Semiconductor, Inc.
+ *
+ */
+
+#ifndef __FSL_PAMU_H
+#define __FSL_PAMU_H
+
+#include <asm/fsl_pamu_stash.h>
+
+/* Bit Field macros
+ *	v = bit field variable; m = mask, m##_SHIFT = shift, x = value to load
+ */
+#define set_bf(v, m, x)		(v = ((v) & ~(m)) | (((x) << (m##_SHIFT)) & (m)))
+#define get_bf(v, m)		(((v) & (m)) >> (m##_SHIFT))
+
+/* PAMU CCSR space */
+#define PAMU_PGC 0x00000000     /* Allows all peripheral accesses */
+#define PAMU_PE 0x40000000      /* enable PAMU                    */
+
+/* PAMU_OFFSET to the next pamu space in ccsr */
+#define PAMU_OFFSET 0x1000
+
+#define PAMU_MMAP_REGS_BASE 0
+
+struct pamu_mmap_regs {
+	u32 ppbah;
+	u32 ppbal;
+	u32 pplah;
+	u32 pplal;
+	u32 spbah;
+	u32 spbal;
+	u32 splah;
+	u32 splal;
+	u32 obah;
+	u32 obal;
+	u32 olah;
+	u32 olal;
+};
+
+/* PAMU Error Registers */
+#define PAMU_POES1 0x0040
+#define PAMU_POES2 0x0044
+#define PAMU_POEAH 0x0048
+#define PAMU_POEAL 0x004C
+#define PAMU_AVS1  0x0050
+#define PAMU_AVS1_AV    0x1
+#define PAMU_AVS1_OTV   0x6
+#define PAMU_AVS1_APV   0x78
+#define PAMU_AVS1_WAV   0x380
+#define PAMU_AVS1_LAV   0x1c00
+#define PAMU_AVS1_GCV   0x2000
+#define PAMU_AVS1_PDV   0x4000
+#define PAMU_AV_MASK    (PAMU_AVS1_AV | PAMU_AVS1_OTV | PAMU_AVS1_APV | PAMU_AVS1_WAV \
+			| PAMU_AVS1_LAV | PAMU_AVS1_GCV | PAMU_AVS1_PDV)
+#define PAMU_AVS1_LIODN_SHIFT 16
+#define PAMU_LAV_LIODN_NOT_IN_PPAACT 0x400
+
+#define PAMU_AVS2  0x0054
+#define PAMU_AVAH  0x0058
+#define PAMU_AVAL  0x005C
+#define PAMU_EECTL 0x0060
+#define PAMU_EEDIS 0x0064
+#define PAMU_EEINTEN 0x0068
+#define PAMU_EEDET 0x006C
+#define PAMU_EEATTR 0x0070
+#define PAMU_EEAHI 0x0074
+#define PAMU_EEALO 0x0078
+#define PAMU_EEDHI 0X007C
+#define PAMU_EEDLO 0x0080
+#define PAMU_EECC  0x0084
+#define PAMU_UDAD  0x0090
+
+/* PAMU Revision Registers */
+#define PAMU_PR1 0x0BF8
+#define PAMU_PR2 0x0BFC
+
+/* PAMU version mask */
+#define PAMU_PR1_MASK 0xffff
+
+/* PAMU Capabilities Registers */
+#define PAMU_PC1 0x0C00
+#define PAMU_PC2 0x0C04
+#define PAMU_PC3 0x0C08
+#define PAMU_PC4 0x0C0C
+
+/* PAMU Control Register */
+#define PAMU_PC 0x0C10
+
+/* PAMU control defs */
+#define PAMU_CONTROL 0x0C10
+#define PAMU_PC_PGC 0x80000000  /* PAMU gate closed bit */
+#define PAMU_PC_PE   0x40000000 /* PAMU enable bit */
+#define PAMU_PC_SPCC 0x00000010 /* sPAACE cache enable */
+#define PAMU_PC_PPCC 0x00000001 /* pPAACE cache enable */
+#define PAMU_PC_OCE  0x00001000 /* OMT cache enable */
+
+#define PAMU_PFA1 0x0C14
+#define PAMU_PFA2 0x0C18
+
+#define PAMU_PC2_MLIODN(X) ((X) >> 16)
+#define PAMU_PC3_MWCE(X) (((X) >> 21) & 0xf)
+
+/* PAMU Interrupt control and Status Register */
+#define PAMU_PICS 0x0C1C
+#define PAMU_ACCESS_VIOLATION_STAT   0x8
+#define PAMU_ACCESS_VIOLATION_ENABLE 0x4
+
+/* PAMU Debug Registers */
+#define PAMU_PD1 0x0F00
+#define PAMU_PD2 0x0F04
+#define PAMU_PD3 0x0F08
+#define PAMU_PD4 0x0F0C
+
+#define PAACE_AP_PERMS_DENIED  0x0
+#define PAACE_AP_PERMS_QUERY   0x1
+#define PAACE_AP_PERMS_UPDATE  0x2
+#define PAACE_AP_PERMS_ALL     0x3
+
+#define PAACE_DD_TO_HOST       0x0
+#define PAACE_DD_TO_IO         0x1
+#define PAACE_PT_PRIMARY       0x0
+#define PAACE_PT_SECONDARY     0x1
+#define PAACE_V_INVALID        0x0
+#define PAACE_V_VALID          0x1
+#define PAACE_MW_SUBWINDOWS    0x1
+
+#define PAACE_WSE_4K           0xB
+#define PAACE_WSE_8K           0xC
+#define PAACE_WSE_16K          0xD
+#define PAACE_WSE_32K          0xE
+#define PAACE_WSE_64K          0xF
+#define PAACE_WSE_128K         0x10
+#define PAACE_WSE_256K         0x11
+#define PAACE_WSE_512K         0x12
+#define PAACE_WSE_1M           0x13
+#define PAACE_WSE_2M           0x14
+#define PAACE_WSE_4M           0x15
+#define PAACE_WSE_8M           0x16
+#define PAACE_WSE_16M          0x17
+#define PAACE_WSE_32M          0x18
+#define PAACE_WSE_64M          0x19
+#define PAACE_WSE_128M         0x1A
+#define PAACE_WSE_256M         0x1B
+#define PAACE_WSE_512M         0x1C
+#define PAACE_WSE_1G           0x1D
+#define PAACE_WSE_2G           0x1E
+#define PAACE_WSE_4G           0x1F
+
+#define PAACE_DID_PCI_EXPRESS_1 0x00
+#define PAACE_DID_PCI_EXPRESS_2 0x01
+#define PAACE_DID_PCI_EXPRESS_3 0x02
+#define PAACE_DID_PCI_EXPRESS_4 0x03
+#define PAACE_DID_LOCAL_BUS     0x04
+#define PAACE_DID_SRIO          0x0C
+#define PAACE_DID_MEM_1         0x10
+#define PAACE_DID_MEM_2         0x11
+#define PAACE_DID_MEM_3         0x12
+#define PAACE_DID_MEM_4         0x13
+#define PAACE_DID_MEM_1_2       0x14
+#define PAACE_DID_MEM_3_4       0x15
+#define PAACE_DID_MEM_1_4       0x16
+#define PAACE_DID_BM_SW_PORTAL  0x18
+#define PAACE_DID_PAMU          0x1C
+#define PAACE_DID_CAAM          0x21
+#define PAACE_DID_QM_SW_PORTAL  0x3C
+#define PAACE_DID_CORE0_INST    0x80
+#define PAACE_DID_CORE0_DATA    0x81
+#define PAACE_DID_CORE1_INST    0x82
+#define PAACE_DID_CORE1_DATA    0x83
+#define PAACE_DID_CORE2_INST    0x84
+#define PAACE_DID_CORE2_DATA    0x85
+#define PAACE_DID_CORE3_INST    0x86
+#define PAACE_DID_CORE3_DATA    0x87
+#define PAACE_DID_CORE4_INST    0x88
+#define PAACE_DID_CORE4_DATA    0x89
+#define PAACE_DID_CORE5_INST    0x8A
+#define PAACE_DID_CORE5_DATA    0x8B
+#define PAACE_DID_CORE6_INST    0x8C
+#define PAACE_DID_CORE6_DATA    0x8D
+#define PAACE_DID_CORE7_INST    0x8E
+#define PAACE_DID_CORE7_DATA    0x8F
+#define PAACE_DID_BROADCAST     0xFF
+
+#define PAACE_ATM_NO_XLATE      0x00
+#define PAACE_ATM_WINDOW_XLATE  0x01
+#define PAACE_ATM_PAGE_XLATE    0x02
+#define PAACE_ATM_WIN_PG_XLATE  \
+                (PAACE_ATM_WINDOW_XLATE | PAACE_ATM_PAGE_XLATE)
+#define PAACE_OTM_NO_XLATE      0x00
+#define PAACE_OTM_IMMEDIATE     0x01
+#define PAACE_OTM_INDEXED       0x02
+#define PAACE_OTM_RESERVED      0x03
+
+#define PAACE_M_COHERENCE_REQ   0x01
+
+#define PAACE_PID_0             0x0
+#define PAACE_PID_1             0x1
+#define PAACE_PID_2             0x2
+#define PAACE_PID_3             0x3
+#define PAACE_PID_4             0x4
+#define PAACE_PID_5             0x5
+#define PAACE_PID_6             0x6
+#define PAACE_PID_7             0x7
+
+#define PAACE_TCEF_FORMAT0_8B   0x00
+#define PAACE_TCEF_FORMAT1_RSVD 0x01
+/*
+ * Hard coded value for the PAACT size to accomodate
+ * maximum LIODN value generated by u-boot.
+ */
+#define PAACE_NUMBER_ENTRIES    0x500
+/* Hard coded value for the SPAACT size */
+#define SPAACE_NUMBER_ENTRIES	0x800
+
+#define	OME_NUMBER_ENTRIES      16
+
+/* PAACE Bit Field Defines */
+#define PPAACE_AF_WBAL			0xfffff000
+#define PPAACE_AF_WBAL_SHIFT		12
+#define PPAACE_AF_WSE			0x00000fc0
+#define PPAACE_AF_WSE_SHIFT		6
+#define PPAACE_AF_MW			0x00000020
+#define PPAACE_AF_MW_SHIFT		5
+
+#define SPAACE_AF_LIODN			0xffff0000
+#define SPAACE_AF_LIODN_SHIFT		16
+
+#define PAACE_AF_AP			0x00000018
+#define PAACE_AF_AP_SHIFT		3
+#define PAACE_AF_DD			0x00000004
+#define PAACE_AF_DD_SHIFT		2
+#define PAACE_AF_PT			0x00000002
+#define PAACE_AF_PT_SHIFT		1
+#define PAACE_AF_V			0x00000001
+#define PAACE_AF_V_SHIFT		0
+
+#define PAACE_DA_HOST_CR		0x80
+#define PAACE_DA_HOST_CR_SHIFT		7
+
+#define PAACE_IA_CID			0x00FF0000
+#define PAACE_IA_CID_SHIFT		16
+#define PAACE_IA_WCE			0x000000F0
+#define PAACE_IA_WCE_SHIFT		4
+#define PAACE_IA_ATM			0x0000000C
+#define PAACE_IA_ATM_SHIFT		2
+#define PAACE_IA_OTM			0x00000003
+#define PAACE_IA_OTM_SHIFT		0
+
+#define PAACE_WIN_TWBAL			0xfffff000
+#define PAACE_WIN_TWBAL_SHIFT		12
+#define PAACE_WIN_SWSE			0x00000fc0
+#define PAACE_WIN_SWSE_SHIFT		6
+
+/* PAMU Data Structures */
+/* primary / secondary paact structure */
+struct paace {
+	/* PAACE Offset 0x00 */
+	u32 wbah;				/* only valid for Primary PAACE */
+	u32 addr_bitfields;		/* See P/S PAACE_AF_* */
+
+	/* PAACE Offset 0x08 */
+	/* Interpretation of first 32 bits dependent on DD above */
+	union {
+		struct {
+			/* Destination ID, see PAACE_DID_* defines */
+			u8 did;
+			/* Partition ID */
+			u8 pid;
+			/* Snoop ID */
+			u8 snpid;
+			/* coherency_required : 1 reserved : 7 */
+			u8 coherency_required; /* See PAACE_DA_* */
+		} to_host;
+		struct {
+			/* Destination ID, see PAACE_DID_* defines */
+			u8  did;
+			u8  reserved1;
+			u16 reserved2;
+		} to_io;
+	} domain_attr;
+
+	/* Implementation attributes + window count + address & operation translation modes */
+	u32 impl_attr;			/* See PAACE_IA_* */
+
+	/* PAACE Offset 0x10 */
+	/* Translated window base address */
+	u32 twbah;
+	u32 win_bitfields;			/* See PAACE_WIN_* */
+
+	/* PAACE Offset 0x18 */
+	/* first secondary paace entry */
+	u32 fspi;				/* only valid for Primary PAACE */
+	union {
+		struct {
+			u8 ioea;
+			u8 moea;
+			u8 ioeb;
+			u8 moeb;
+		} immed_ot;
+		struct {
+			u16 reserved;
+			u16 omi;
+		} index_ot;
+	} op_encode;
+
+	/* PAACE Offsets 0x20-0x38 */
+	u32 reserved[8];			/* not currently implemented */
+};
+
+/* OME : Operation mapping entry
+ * MOE : Mapped Operation Encodings
+ * The operation mapping table is table containing operation mapping entries (OME).
+ * The index of a particular OME is programmed in the PAACE entry for translation
+ * in bound I/O operations corresponding to an LIODN. The OMT is used for translation
+ * specifically in case of the indexed translation mode. Each OME contains a 128
+ * byte mapped operation encoding (MOE), where each byte represents an MOE.
+ */
+#define NUM_MOE 128
+struct ome {
+	u8 moe[NUM_MOE];
+} __attribute__((packed));
+
+#define PAACT_SIZE              (sizeof(struct paace) * PAACE_NUMBER_ENTRIES)
+#define SPAACT_SIZE              (sizeof(struct paace) * SPAACE_NUMBER_ENTRIES)
+#define OMT_SIZE                (sizeof(struct ome) * OME_NUMBER_ENTRIES)
+
+#define PAMU_PAGE_SHIFT 12
+#define PAMU_PAGE_SIZE  4096ULL
+
+#define IOE_READ        0x00
+#define IOE_READ_IDX    0x00
+#define IOE_WRITE       0x81
+#define IOE_WRITE_IDX   0x01
+#define IOE_EREAD0      0x82    /* Enhanced read type 0 */
+#define IOE_EREAD0_IDX  0x02    /* Enhanced read type 0 */
+#define IOE_EWRITE0     0x83    /* Enhanced write type 0 */
+#define IOE_EWRITE0_IDX 0x03    /* Enhanced write type 0 */
+#define IOE_DIRECT0     0x84    /* Directive type 0 */
+#define IOE_DIRECT0_IDX 0x04    /* Directive type 0 */
+#define IOE_EREAD1      0x85    /* Enhanced read type 1 */
+#define IOE_EREAD1_IDX  0x05    /* Enhanced read type 1 */
+#define IOE_EWRITE1     0x86    /* Enhanced write type 1 */
+#define IOE_EWRITE1_IDX 0x06    /* Enhanced write type 1 */
+#define IOE_DIRECT1     0x87    /* Directive type 1 */
+#define IOE_DIRECT1_IDX 0x07    /* Directive type 1 */
+#define IOE_RAC         0x8c    /* Read with Atomic clear */
+#define IOE_RAC_IDX     0x0c    /* Read with Atomic clear */
+#define IOE_RAS         0x8d    /* Read with Atomic set */
+#define IOE_RAS_IDX     0x0d    /* Read with Atomic set */
+#define IOE_RAD         0x8e    /* Read with Atomic decrement */
+#define IOE_RAD_IDX     0x0e    /* Read with Atomic decrement */
+#define IOE_RAI         0x8f    /* Read with Atomic increment */
+#define IOE_RAI_IDX     0x0f    /* Read with Atomic increment */
+
+#define EOE_READ        0x00
+#define EOE_WRITE       0x01
+#define EOE_RAC         0x0c    /* Read with Atomic clear */
+#define EOE_RAS         0x0d    /* Read with Atomic set */
+#define EOE_RAD         0x0e    /* Read with Atomic decrement */
+#define EOE_RAI         0x0f    /* Read with Atomic increment */
+#define EOE_LDEC        0x10    /* Load external cache */
+#define EOE_LDECL       0x11    /* Load external cache with stash lock */
+#define EOE_LDECPE      0x12    /* Load external cache with preferred exclusive */
+#define EOE_LDECPEL     0x13    /* Load external cache with preferred exclusive and lock */
+#define EOE_LDECFE      0x14    /* Load external cache with forced exclusive */
+#define EOE_LDECFEL     0x15    /* Load external cache with forced exclusive and lock */
+#define EOE_RSA         0x16    /* Read with stash allocate */
+#define EOE_RSAU        0x17    /* Read with stash allocate and unlock */
+#define EOE_READI       0x18    /* Read with invalidate */
+#define EOE_RWNITC      0x19    /* Read with no intention to cache */
+#define EOE_WCI         0x1a    /* Write cache inhibited */
+#define EOE_WWSA        0x1b    /* Write with stash allocate */
+#define EOE_WWSAL       0x1c    /* Write with stash allocate and lock */
+#define EOE_WWSAO       0x1d    /* Write with stash allocate only */
+#define EOE_WWSAOL      0x1e    /* Write with stash allocate only and lock */
+#define EOE_VALID       0x80
+
+/* Function prototypes */
+int pamu_domain_init(void);
+int pamu_enable_liodn(int liodn);
+int pamu_disable_liodn(int liodn);
+void pamu_free_subwins(int liodn);
+int pamu_config_ppaace(int liodn, phys_addr_t win_addr, phys_addr_t win_size,
+		       u32 omi, unsigned long rpn, u32 snoopid, uint32_t stashid,
+		       u32 subwin_cnt, int prot);
+int pamu_config_spaace(int liodn, u32 subwin_cnt, u32 subwin_addr,
+		       phys_addr_t subwin_size, u32 omi, unsigned long rpn,
+		       uint32_t snoopid, u32 stashid, int enable, int prot);
+
+u32 get_stash_id(u32 stash_dest_hint, u32 vcpu);
+void get_ome_index(u32 *omi_index, struct device *dev);
+int  pamu_update_paace_stash(int liodn, u32 subwin, u32 value);
+int pamu_disable_spaace(int liodn, u32 subwin);
+u32 pamu_get_max_subwin_cnt(void);
+
+#endif  /* __FSL_PAMU_H */

drivers/iommu/fsl_pamu_domain.h

+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ *
+ * Copyright (C) 2013 Freescale Semiconductor, Inc.
+ *
+ */
+
+#ifndef __FSL_PAMU_DOMAIN_H
+#define __FSL_PAMU_DOMAIN_H
+
+#include "fsl_pamu.h"
+
+struct dma_window {
+	phys_addr_t paddr;
+	u64 size;
+	int valid;
+	int prot;
+};
+
+struct fsl_dma_domain {
+	/*
+	 * Indicates the geometry size for the domain.
+	 * This would be set when the geometry is
+	 * configured for the domain.
+	 */
+	dma_addr_t			geom_size;
+	/*
+	 * Number of windows assocaited with this domain.
+	 * During domain initialization, it is set to the
+	 * the maximum number of subwindows allowed for a LIODN.
+	 * Minimum value for this is 1 indicating a single PAMU
+	 * window, without any sub windows. Value can be set/
+	 * queried by set_attr/get_attr API for DOMAIN_ATTR_WINDOWS.
+	 * Value can only be set once the geometry has been configured.
+	 */
+	u32				win_cnt;
+	/*
+	 * win_arr contains information of the configured
+	 * windows for a domain. This is allocated only
+	 * when the number of windows for the domain are
+	 * set.
+	 */
+	struct dma_window		*win_arr;
+	/* list of devices associated with the domain */
+	struct list_head		devices;
+	/* dma_domain states:
+	 * mapped - A particular mapping has been created
+	 * within the configured geometry.
+	 * enabled - DMA has been enabled for the given
+	 * domain. This translates to setting of the
+	 * valid bit for the primary PAACE in the PAMU
+	 * PAACT table. Domain geometry should be set and
+	 * it must have a valid mapping before DMA can be
+	 * enabled for it.
+	 *
+	 */
+	int				mapped;
+	int				enabled;
+	/* stash_id obtained from the stash attribute details */
+	u32				stash_id;
+	struct pamu_stash_attribute	dma_stash;
+	u32				snoop_id;
+	struct iommu_domain		*iommu_domain;
+	spinlock_t			domain_lock;
+};
+
+/* domain-device relationship */
+struct device_domain_info {
+	struct list_head link;	/* link to domain siblings */
+	struct device *dev;
+	u32 liodn;
+	struct fsl_dma_domain *domain; /* pointer to domain */
+};
+#endif  /* __FSL_PAMU_DOMAIN_H */

drivers/iommu/intel-iommu.c

@@ -890,56 +890,54 @@ static int dma_pte_clear_range(struct dmar_domain *domain,
 	return order;
 }
 
+static void dma_pte_free_level(struct dmar_domain *domain, int level,
+			       struct dma_pte *pte, unsigned long pfn,
+			       unsigned long start_pfn, unsigned long last_pfn)
+{
+	pfn = max(start_pfn, pfn);
+	pte = &pte[pfn_level_offset(pfn, level)];
+
+	do {
+		unsigned long level_pfn;
+		struct dma_pte *level_pte;
+
+		if (!dma_pte_present(pte) || dma_pte_superpage(pte))
+			goto next;
+
+		level_pfn = pfn & level_mask(level - 1);
+		level_pte = phys_to_virt(dma_pte_addr(pte));
+
+		if (level > 2)
+			dma_pte_free_level(domain, level - 1, level_pte,
+					   level_pfn, start_pfn, last_pfn);
+
+		/* If range covers entire pagetable, free it */
+		if (!(start_pfn > level_pfn ||
+		      last_pfn < level_pfn + level_size(level))) {
+			dma_clear_pte(pte);
+			domain_flush_cache(domain, pte, sizeof(*pte));
+			free_pgtable_page(level_pte);
+		}
+next:
+		pfn += level_size(level);
+	} while (!first_pte_in_page(++pte) && pfn <= last_pfn);
+}
+
 /* free page table pages. last level pte should already be cleared */
 static void dma_pte_free_pagetable(struct dmar_domain *domain,
 				   unsigned long start_pfn,
 				   unsigned long last_pfn)
 {
 	int addr_width = agaw_to_width(domain->agaw) - VTD_PAGE_SHIFT;
-	struct dma_pte *first_pte, *pte;
-	int total = agaw_to_level(domain->agaw);
-	int level;
-	unsigned long tmp;
-	int large_page = 2;
 
 	BUG_ON(addr_width < BITS_PER_LONG && start_pfn >> addr_width);
 	BUG_ON(addr_width < BITS_PER_LONG && last_pfn >> addr_width);
 	BUG_ON(start_pfn > last_pfn);
 
 	/* We don't need lock here; nobody else touches the iova range */
-	level = 2;
-	while (level <= total) {
-		tmp = align_to_level(start_pfn, level);
-
-		/* If we can't even clear one PTE at this level, we're done */
-		if (tmp + level_size(level) - 1 > last_pfn)
-			return;
-
-		do {
-			large_page = level;
-			first_pte = pte = dma_pfn_level_pte(domain, tmp, level, &large_page);
-			if (large_page > level)
-				level = large_page + 1;
-			if (!pte) {
-				tmp = align_to_level(tmp + 1, level + 1);
-				continue;
-			}
-			do {
-				if (dma_pte_present(pte)) {
-					free_pgtable_page(phys_to_virt(dma_pte_addr(pte)));
-					dma_clear_pte(pte);
-				}
-				pte++;
-				tmp += level_size(level);
-			} while (!first_pte_in_page(pte) &&
-				 tmp + level_size(level) - 1 <= last_pfn);
+	dma_pte_free_level(domain, agaw_to_level(domain->agaw),
+			   domain->pgd, 0, start_pfn, last_pfn);
 
-			domain_flush_cache(domain, first_pte,
-					   (void *)pte - (void *)first_pte);
-			
-		} while (tmp && tmp + level_size(level) - 1 <= last_pfn);
-		level++;
-	}
 	/* free pgd */
 	if (start_pfn == 0 && last_pfn == DOMAIN_MAX_PFN(domain->gaw)) {
 		free_pgtable_page(domain->pgd);

include/linux/iommu.h

@@ -58,10 +58,26 @@ struct iommu_domain {
 #define IOMMU_CAP_CACHE_COHERENCY	0x1
 #define IOMMU_CAP_INTR_REMAP		0x2	/* isolates device intrs */
 
+/*
+ * Following constraints are specifc to FSL_PAMUV1:
+ *  -aperture must be power of 2, and naturally aligned
+ *  -number of windows must be power of 2, and address space size
+ *   of each window is determined by aperture size / # of windows
+ *  -the actual size of the mapped region of a window must be power
+ *   of 2 starting with 4KB and physical address must be naturally
+ *   aligned.
+ * DOMAIN_ATTR_FSL_PAMUV1 corresponds to the above mentioned contraints.
+ * The caller can invoke iommu_domain_get_attr to check if the underlying
+ * iommu implementation supports these constraints.
+ */
+
 enum iommu_attr {
 	DOMAIN_ATTR_GEOMETRY,
 	DOMAIN_ATTR_PAGING,
 	DOMAIN_ATTR_WINDOWS,
+	DOMAIN_ATTR_FSL_PAMU_STASH,
+	DOMAIN_ATTR_FSL_PAMU_ENABLE,
+	DOMAIN_ATTR_FSL_PAMUV1,
 	DOMAIN_ATTR_MAX,
 };