Merge tag 'iommu-updates-v3.20' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu

Pull IOMMU updates from Joerg Roedel:
 "This time with:

   - Generic page-table framework for ARM IOMMUs using the LPAE
     page-table format, ARM-SMMU and Renesas IPMMU make use of it
     already.

   - Break out the IO virtual address allocator from the Intel IOMMU so
     that it can be used by other DMA-API implementations too.  The
     first user will be the ARM64 common DMA-API implementation for
     IOMMUs

   - Device tree support for Renesas IPMMU

   - Various fixes and cleanups all over the place"

* tag 'iommu-updates-v3.20' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu: (36 commits)
  iommu/amd: Convert non-returned local variable to boolean when relevant
  iommu: Update my email address
  iommu/amd: Use wait_event in put_pasid_state_wait
  iommu/amd: Fix amd_iommu_free_device()
  iommu/arm-smmu: Avoid build warning
  iommu/fsl: Various cleanups
  iommu/fsl: Use %pa to print phys_addr_t
  iommu/omap: Print phys_addr_t using %pa
  iommu: Make more drivers depend on COMPILE_TEST
  iommu/ipmmu-vmsa: Fix IOMMU lookup when multiple IOMMUs are registered
  iommu: Disable on !MMU builds
  iommu/fsl: Remove unused fsl_of_pamu_ids[]
  iommu/fsl: Fix section mismatch
  iommu/ipmmu-vmsa: Use the ARM LPAE page table allocator
  iommu: Fix trace_map() to report original iova and original size
  iommu/arm-smmu: add support for iova_to_phys through ATS1PR
  iopoll: Introduce memory-mapped IO polling macros
  iommu/arm-smmu: don't touch the secure STLBIALL register
  iommu/arm-smmu: make use of generic LPAE allocator
  iommu: io-pgtable-arm: add non-secure quirk
  ...

Documentation/devicetree/bindings/iommu/renesas,ipmmu-vmsa.txt

+* Renesas VMSA-Compatible IOMMU
+
+The IPMMU is an IOMMU implementation compatible with the ARM VMSA page tables.
+It provides address translation for bus masters outside of the CPU, each
+connected to the IPMMU through a port called micro-TLB.
+
+
+Required Properties:
+
+  - compatible: Must contain "renesas,ipmmu-vmsa".
+  - reg: Base address and size of the IPMMU registers.
+  - interrupts: Specifiers for the MMU fault interrupts. For instances that
+    support secure mode two interrupts must be specified, for non-secure and
+    secure mode, in that order. For instances that don't support secure mode a
+    single interrupt must be specified.
+
+  - #iommu-cells: Must be 1.
+
+Each bus master connected to an IPMMU must reference the IPMMU in its device
+node with the following property:
+
+  - iommus: A reference to the IPMMU in two cells. The first cell is a phandle
+    to the IPMMU and the second cell the number of the micro-TLB that the
+    device is connected to.
+
+
+Example: R8A7791 IPMMU-MX and VSP1-D0 bus master
+
+	ipmmu_mx: mmu@fe951000 {
+		compatible = "renasas,ipmmu-vmsa";
+		reg = <0 0xfe951000 0 0x1000>;
+		interrupts = <0 222 IRQ_TYPE_LEVEL_HIGH>,
+			     <0 221 IRQ_TYPE_LEVEL_HIGH>;
+		#iommu-cells = <1>;
+	};
+
+	vsp1@fe928000 {
+		...
+		iommus = <&ipmmu_mx 13>;
+		...
+	};

MAINTAINERS

@@ -1606,6 +1606,7 @@ M:	Will Deacon <will.deacon@arm.com>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
 F:	drivers/iommu/arm-smmu.c
+F:	drivers/iommu/io-pgtable-arm.c
 
 ARM64 PORT (AARCH64 ARCHITECTURE)
 M:	Catalin Marinas <catalin.marinas@arm.com>

arch/arm64/Kconfig

@@ -350,7 +350,6 @@ config ARM64_VA_BITS_42
 
 config ARM64_VA_BITS_48
 	bool "48-bit"
-	depends on !ARM_SMMU
 
 endchoice
 

drivers/iommu/Kconfig

@@ -4,6 +4,7 @@ config IOMMU_API
 
 menuconfig IOMMU_SUPPORT
 	bool "IOMMU Hardware Support"
+	depends on MMU
 	default y
 	---help---
 	  Say Y here if you want to compile device drivers for IO Memory
@@ -13,13 +14,43 @@ menuconfig IOMMU_SUPPORT
 
 if IOMMU_SUPPORT
 
+menu "Generic IOMMU Pagetable Support"
+
+# Selected by the actual pagetable implementations
+config IOMMU_IO_PGTABLE
+	bool
+
+config IOMMU_IO_PGTABLE_LPAE
+	bool "ARMv7/v8 Long Descriptor Format"
+	select IOMMU_IO_PGTABLE
+	help
+	  Enable support for the ARM long descriptor pagetable format.
+	  This allocator supports 4K/2M/1G, 16K/32M and 64K/512M page
+	  sizes at both stage-1 and stage-2, as well as address spaces
+	  up to 48-bits in size.
+
+config IOMMU_IO_PGTABLE_LPAE_SELFTEST
+	bool "LPAE selftests"
+	depends on IOMMU_IO_PGTABLE_LPAE
+	help
+	  Enable self-tests for LPAE page table allocator. This performs
+	  a series of page-table consistency checks during boot.
+
+	  If unsure, say N here.
+
+endmenu
+
+config IOMMU_IOVA
+	bool
+
 config OF_IOMMU
        def_bool y
        depends on OF && IOMMU_API
 
 config FSL_PAMU
 	bool "Freescale IOMMU support"
-	depends on PPC_E500MC
+	depends on PPC32
+	depends on PPC_E500MC || COMPILE_TEST
 	select IOMMU_API
 	select GENERIC_ALLOCATOR
 	help
@@ -30,7 +61,8 @@ config FSL_PAMU
 # MSM IOMMU support
 config MSM_IOMMU
 	bool "MSM IOMMU Support"
-	depends on ARCH_MSM8X60 || ARCH_MSM8960
+	depends on ARM
+	depends on ARCH_MSM8X60 || ARCH_MSM8960 || COMPILE_TEST
 	select IOMMU_API
 	help
 	  Support for the IOMMUs found on certain Qualcomm SOCs.
@@ -91,6 +123,7 @@ config INTEL_IOMMU
 	bool "Support for Intel IOMMU using DMA Remapping Devices"
 	depends on PCI_MSI && ACPI && (X86 || IA64_GENERIC)
 	select IOMMU_API
+	select IOMMU_IOVA
 	select DMAR_TABLE
 	help
 	  DMA remapping (DMAR) devices support enables independent address
@@ -140,7 +173,8 @@ config IRQ_REMAP
 # OMAP IOMMU support
 config OMAP_IOMMU
 	bool "OMAP IOMMU Support"
-	depends on ARCH_OMAP2PLUS
+	depends on ARM && MMU
+	depends on ARCH_OMAP2PLUS || COMPILE_TEST
 	select IOMMU_API
 
 config OMAP_IOMMU_DEBUG
@@ -187,7 +221,7 @@ config TEGRA_IOMMU_SMMU
 
 config EXYNOS_IOMMU
 	bool "Exynos IOMMU Support"
-	depends on ARCH_EXYNOS && ARM
+	depends on ARCH_EXYNOS && ARM && MMU
 	select IOMMU_API
 	select ARM_DMA_USE_IOMMU
 	help
@@ -216,7 +250,7 @@ config SHMOBILE_IPMMU_TLB
 config SHMOBILE_IOMMU
 	bool "IOMMU for Renesas IPMMU/IPMMUI"
 	default n
-	depends on ARM
+	depends on ARM && MMU
 	depends on ARCH_SHMOBILE || COMPILE_TEST
 	select IOMMU_API
 	select ARM_DMA_USE_IOMMU
@@ -287,6 +321,7 @@ config IPMMU_VMSA
 	depends on ARM_LPAE
 	depends on ARCH_SHMOBILE || COMPILE_TEST
 	select IOMMU_API
+	select IOMMU_IO_PGTABLE_LPAE
 	select ARM_DMA_USE_IOMMU
 	help
 	  Support for the Renesas VMSA-compatible IPMMU Renesas found in the
@@ -304,13 +339,13 @@ config SPAPR_TCE_IOMMU
 
 config ARM_SMMU
 	bool "ARM Ltd. System MMU (SMMU) Support"
-	depends on ARM64 || (ARM_LPAE && OF)
+	depends on (ARM64 || ARM) && MMU
 	select IOMMU_API
+	select IOMMU_IO_PGTABLE_LPAE
 	select ARM_DMA_USE_IOMMU if ARM
 	help
 	  Support for implementations of the ARM System MMU architecture
-	  versions 1 and 2. The driver supports both v7l and v8l table
-	  formats with 4k and 64k page sizes.
+	  versions 1 and 2.
 
 	  Say Y here if your SoC includes an IOMMU device implementing
 	  the ARM SMMU architecture.

drivers/iommu/Makefile

 obj-$(CONFIG_IOMMU_API) += iommu.o
 obj-$(CONFIG_IOMMU_API) += iommu-traces.o
 obj-$(CONFIG_IOMMU_API) += iommu-sysfs.o
+obj-$(CONFIG_IOMMU_IO_PGTABLE) += io-pgtable.o
+obj-$(CONFIG_IOMMU_IO_PGTABLE_LPAE) += io-pgtable-arm.o
+obj-$(CONFIG_IOMMU_IOVA) += iova.o
 obj-$(CONFIG_OF_IOMMU)	+= of_iommu.o
 obj-$(CONFIG_MSM_IOMMU) += msm_iommu.o msm_iommu_dev.o
 obj-$(CONFIG_AMD_IOMMU) += amd_iommu.o amd_iommu_init.o
 obj-$(CONFIG_AMD_IOMMU_V2) += amd_iommu_v2.o
 obj-$(CONFIG_ARM_SMMU) += arm-smmu.o
 obj-$(CONFIG_DMAR_TABLE) += dmar.o
-obj-$(CONFIG_INTEL_IOMMU) += iova.o intel-iommu.o
+obj-$(CONFIG_INTEL_IOMMU) += intel-iommu.o
 obj-$(CONFIG_IPMMU_VMSA) += ipmmu-vmsa.o
 obj-$(CONFIG_IRQ_REMAP) += intel_irq_remapping.o irq_remapping.o
 obj-$(CONFIG_OMAP_IOMMU) += omap-iommu.o

drivers/iommu/amd_iommu.c

 /*
  * Copyright (C) 2007-2010 Advanced Micro Devices, Inc.
- * Author: Joerg Roedel <joerg.roedel@amd.com>
+ * Author: Joerg Roedel <jroedel@suse.de>
  *         Leo Duran <leo.duran@amd.com>
  *
  * This program is free software; you can redistribute it and/or modify it
@@ -843,10 +843,10 @@ static void build_inv_iommu_pages(struct iommu_cmd *cmd, u64 address,
 				  size_t size, u16 domid, int pde)
 {
 	u64 pages;
-	int s;
+	bool s;
 
 	pages = iommu_num_pages(address, size, PAGE_SIZE);
-	s     = 0;
+	s     = false;
 
 	if (pages > 1) {
 		/*
@@ -854,7 +854,7 @@ static void build_inv_iommu_pages(struct iommu_cmd *cmd, u64 address,
 		 * TLB entries for this domain
 		 */
 		address = CMD_INV_IOMMU_ALL_PAGES_ADDRESS;
-		s = 1;
+		s = true;
 	}
 
 	address &= PAGE_MASK;
@@ -874,10 +874,10 @@ static void build_inv_iotlb_pages(struct iommu_cmd *cmd, u16 devid, int qdep,
 				  u64 address, size_t size)
 {
 	u64 pages;
-	int s;
+	bool s;
 
 	pages = iommu_num_pages(address, size, PAGE_SIZE);
-	s     = 0;
+	s     = false;
 
 	if (pages > 1) {
 		/*
@@ -885,7 +885,7 @@ static void build_inv_iotlb_pages(struct iommu_cmd *cmd, u16 devid, int qdep,
 		 * TLB entries for this domain
 		 */
 		address = CMD_INV_IOMMU_ALL_PAGES_ADDRESS;
-		s = 1;
+		s = true;
 	}
 
 	address &= PAGE_MASK;

drivers/iommu/amd_iommu_init.c

 /*
  * Copyright (C) 2007-2010 Advanced Micro Devices, Inc.
- * Author: Joerg Roedel <joerg.roedel@amd.com>
+ * Author: Joerg Roedel <jroedel@suse.de>
  *         Leo Duran <leo.duran@amd.com>
  *
  * This program is free software; you can redistribute it and/or modify it

drivers/iommu/amd_iommu_proto.h

 /*
  * Copyright (C) 2009-2010 Advanced Micro Devices, Inc.
- * Author: Joerg Roedel <joerg.roedel@amd.com>
+ * Author: Joerg Roedel <jroedel@suse.de>
  *
  * 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

drivers/iommu/amd_iommu_types.h

 /*
  * Copyright (C) 2007-2010 Advanced Micro Devices, Inc.
- * Author: Joerg Roedel <joerg.roedel@amd.com>
+ * Author: Joerg Roedel <jroedel@suse.de>
  *         Leo Duran <leo.duran@amd.com>
  *
  * This program is free software; you can redistribute it and/or modify it

drivers/iommu/amd_iommu_v2.c

 /*
  * Copyright (C) 2010-2012 Advanced Micro Devices, Inc.
- * Author: Joerg Roedel <joerg.roedel@amd.com>
+ * Author: Joerg Roedel <jroedel@suse.de>
  *
  * 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
@@ -31,7 +31,7 @@
 #include "amd_iommu_proto.h"
 
 MODULE_LICENSE("GPL v2");
-MODULE_AUTHOR("Joerg Roedel <joerg.roedel@amd.com>");
+MODULE_AUTHOR("Joerg Roedel <jroedel@suse.de>");
 
 #define MAX_DEVICES		0x10000
 #define PRI_QUEUE_SIZE		512
@@ -151,18 +151,6 @@ static void put_device_state(struct device_state *dev_state)
 		wake_up(&dev_state->wq);
 }
 
-static void put_device_state_wait(struct device_state *dev_state)
-{
-	DEFINE_WAIT(wait);
-
-	prepare_to_wait(&dev_state->wq, &wait, TASK_UNINTERRUPTIBLE);
-	if (!atomic_dec_and_test(&dev_state->count))
-		schedule();
-	finish_wait(&dev_state->wq, &wait);
-
-	free_device_state(dev_state);
-}
-
 /* Must be called under dev_state->lock */
 static struct pasid_state **__get_pasid_state_ptr(struct device_state *dev_state,
 						  int pasid, bool alloc)
@@ -278,14 +266,7 @@ static void put_pasid_state(struct pasid_state *pasid_state)
 
 static void put_pasid_state_wait(struct pasid_state *pasid_state)
 {
-	DEFINE_WAIT(wait);
-
-	prepare_to_wait(&pasid_state->wq, &wait, TASK_UNINTERRUPTIBLE);
-
-	if (!atomic_dec_and_test(&pasid_state->count))
-		schedule();
-
-	finish_wait(&pasid_state->wq, &wait);
+	wait_event(pasid_state->wq, !atomic_read(&pasid_state->count));
 	free_pasid_state(pasid_state);
 }
 
@@ -851,7 +832,13 @@ void amd_iommu_free_device(struct pci_dev *pdev)
 	/* Get rid of any remaining pasid states */
 	free_pasid_states(dev_state);
 
-	put_device_state_wait(dev_state);
+	put_device_state(dev_state);
+	/*
+	 * Wait until the last reference is dropped before freeing
+	 * the device state.
+	 */
+	wait_event(dev_state->wq, !atomic_read(&dev_state->count));
+	free_device_state(dev_state);
 }
 EXPORT_SYMBOL(amd_iommu_free_device);
 
@@ -921,7 +908,7 @@ static int __init amd_iommu_v2_init(void)
 {
 	int ret;
 
-	pr_info("AMD IOMMUv2 driver by Joerg Roedel <joerg.roedel@amd.com>\n");
+	pr_info("AMD IOMMUv2 driver by Joerg Roedel <jroedel@suse.de>\n");
 
 	if (!amd_iommu_v2_supported()) {
 		pr_info("AMD IOMMUv2 functionality not available on this system\n");

drivers/iommu/fsl_pamu.h

@@ -19,13 +19,15 @@
 #ifndef __FSL_PAMU_H
 #define __FSL_PAMU_H
 
+#include <linux/iommu.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))
+#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 */
@@ -198,8 +200,7 @@ struct pamu_mmap_regs {
 #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_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
@@ -219,7 +220,7 @@ struct pamu_mmap_regs {
 #define PAACE_TCEF_FORMAT0_8B   0x00
 #define PAACE_TCEF_FORMAT1_RSVD 0x01
 /*
- * Hard coded value for the PAACT size to accomodate
+ * Hard coded value for the PAACT size to accommodate
  * maximum LIODN value generated by u-boot.
  */
 #define PAACE_NUMBER_ENTRIES    0x500
@@ -332,7 +333,7 @@ struct paace {
 #define NUM_MOE 128
 struct ome {
 	u8 moe[NUM_MOE];
-} __attribute__((packed));
+} __packed;
 
 #define PAACT_SIZE              (sizeof(struct paace) * PAACE_NUMBER_ENTRIES)
 #define SPAACT_SIZE              (sizeof(struct paace) * SPAACE_NUMBER_ENTRIES)

drivers/iommu/intel-iommu.c

@@ -71,6 +71,9 @@
 				__DOMAIN_MAX_PFN(gaw), (unsigned long)-1))
 #define DOMAIN_MAX_ADDR(gaw)	(((uint64_t)__DOMAIN_MAX_PFN(gaw)) << VTD_PAGE_SHIFT)
 
+/* IO virtual address start page frame number */
+#define IOVA_START_PFN		(1)
+
 #define IOVA_PFN(addr)		((addr) >> PAGE_SHIFT)
 #define DMA_32BIT_PFN		IOVA_PFN(DMA_BIT_MASK(32))
 #define DMA_64BIT_PFN		IOVA_PFN(DMA_BIT_MASK(64))
@@ -485,7 +488,6 @@ __setup("intel_iommu=", intel_iommu_setup);
 
 static struct kmem_cache *iommu_domain_cache;
 static struct kmem_cache *iommu_devinfo_cache;
-static struct kmem_cache *iommu_iova_cache;
 
 static inline void *alloc_pgtable_page(int node)
 {
@@ -523,16 +525,6 @@ static inline void free_devinfo_mem(void *vaddr)
 	kmem_cache_free(iommu_devinfo_cache, vaddr);
 }
 
-struct iova *alloc_iova_mem(void)
-{
-	return kmem_cache_alloc(iommu_iova_cache, GFP_ATOMIC);
-}
-
-void free_iova_mem(struct iova *iova)
-{
-	kmem_cache_free(iommu_iova_cache, iova);
-}
-
 static inline int domain_type_is_vm(struct dmar_domain *domain)
 {
 	return domain->flags & DOMAIN_FLAG_VIRTUAL_MACHINE;
@@ -1643,7 +1635,8 @@ static int dmar_init_reserved_ranges(void)
 	struct iova *iova;
 	int i;
 
-	init_iova_domain(&reserved_iova_list, DMA_32BIT_PFN);
+	init_iova_domain(&reserved_iova_list, VTD_PAGE_SIZE, IOVA_START_PFN,
+			DMA_32BIT_PFN);
 
 	lockdep_set_class(&reserved_iova_list.iova_rbtree_lock,
 		&reserved_rbtree_key);
@@ -1701,7 +1694,8 @@ static int domain_init(struct dmar_domain *domain, int guest_width)
 	int adjust_width, agaw;
 	unsigned long sagaw;
 
-	init_iova_domain(&domain->iovad, DMA_32BIT_PFN);
+	init_iova_domain(&domain->iovad, VTD_PAGE_SIZE, IOVA_START_PFN,
+			DMA_32BIT_PFN);
 	domain_reserve_special_ranges(domain);
 
 	/* calculate AGAW */
@@ -3427,23 +3421,6 @@ static inline int iommu_devinfo_cache_init(void)
 	return ret;
 }
 
-static inline int iommu_iova_cache_init(void)
-{
-	int ret = 0;
-
-	iommu_iova_cache = kmem_cache_create("iommu_iova",
-					 sizeof(struct iova),
-					 0,
-					 SLAB_HWCACHE_ALIGN,
-					 NULL);
-	if (!iommu_iova_cache) {
-		printk(KERN_ERR "Couldn't create iova cache\n");
-		ret = -ENOMEM;
-	}
-
-	return ret;
-}
-
 static int __init iommu_init_mempool(void)
 {
 	int ret;
@@ -3461,7 +3438,7 @@ static int __init iommu_init_mempool(void)
 
 	kmem_cache_destroy(iommu_domain_cache);
 domain_error:
-	kmem_cache_destroy(iommu_iova_cache);
+	iommu_iova_cache_destroy();
 
 	return -ENOMEM;
 }
@@ -3470,8 +3447,7 @@ static void __init iommu_exit_mempool(void)
 {
 	kmem_cache_destroy(iommu_devinfo_cache);
 	kmem_cache_destroy(iommu_domain_cache);
-	kmem_cache_destroy(iommu_iova_cache);
-
+	iommu_iova_cache_destroy();
 }
 
 static void quirk_ioat_snb_local_iommu(struct pci_dev *pdev)
@@ -4342,7 +4318,8 @@ static int md_domain_init(struct dmar_domain *domain, int guest_width)
 {
 	int adjust_width;
 
-	init_iova_domain(&domain->iovad, DMA_32BIT_PFN);
+	init_iova_domain(&domain->iovad, VTD_PAGE_SIZE, IOVA_START_PFN,
+			DMA_32BIT_PFN);
 	domain_reserve_special_ranges(domain);
 
 	/* calculate AGAW */

drivers/iommu/io-pgtable.c

+/*
+ * Generic page table allocator for IOMMUs.
+ *
+ * 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, see <http://www.gnu.org/licenses/>.
+ *
+ * Copyright (C) 2014 ARM Limited
+ *
+ * Author: Will Deacon <will.deacon@arm.com>
+ */
+
+#include <linux/bug.h>
+#include <linux/kernel.h>
+#include <linux/types.h>
+
+#include "io-pgtable.h"
+
+extern struct io_pgtable_init_fns io_pgtable_arm_32_lpae_s1_init_fns;
+extern struct io_pgtable_init_fns io_pgtable_arm_32_lpae_s2_init_fns;
+extern struct io_pgtable_init_fns io_pgtable_arm_64_lpae_s1_init_fns;
+extern struct io_pgtable_init_fns io_pgtable_arm_64_lpae_s2_init_fns;
+
+static const struct io_pgtable_init_fns *
+io_pgtable_init_table[IO_PGTABLE_NUM_FMTS] =
+{
+#ifdef CONFIG_IOMMU_IO_PGTABLE_LPAE
+	[ARM_32_LPAE_S1] = &io_pgtable_arm_32_lpae_s1_init_fns,
+	[ARM_32_LPAE_S2] = &io_pgtable_arm_32_lpae_s2_init_fns,
+	[ARM_64_LPAE_S1] = &io_pgtable_arm_64_lpae_s1_init_fns,
+	[ARM_64_LPAE_S2] = &io_pgtable_arm_64_lpae_s2_init_fns,
+#endif
+};
+
+struct io_pgtable_ops *alloc_io_pgtable_ops(enum io_pgtable_fmt fmt,
+					    struct io_pgtable_cfg *cfg,
+					    void *cookie)
+{
+	struct io_pgtable *iop;
+	const struct io_pgtable_init_fns *fns;
+
+	if (fmt >= IO_PGTABLE_NUM_FMTS)
+		return NULL;
+
+	fns = io_pgtable_init_table[fmt];
+	if (!fns)
+		return NULL;
+
+	iop = fns->alloc(cfg, cookie);
+	if (!iop)
+		return NULL;
+
+	iop->fmt	= fmt;
+	iop->cookie	= cookie;
+	iop->cfg	= *cfg;
+
+	return &iop->ops;
+}
+
+/*
+ * It is the IOMMU driver's responsibility to ensure that the page table
+ * is no longer accessible to the walker by this point.
+ */
+void free_io_pgtable_ops(struct io_pgtable_ops *ops)
+{
+	struct io_pgtable *iop;
+
+	if (!ops)
+		return;
+
+	iop = container_of(ops, struct io_pgtable, ops);
+	iop->cfg.tlb->tlb_flush_all(iop->cookie);
+	io_pgtable_init_table[iop->fmt]->free(iop);
+}

drivers/iommu/io-pgtable.h

+#ifndef __IO_PGTABLE_H
+#define __IO_PGTABLE_H
+
+/*
+ * Public API for use by IOMMU drivers
+ */
+enum io_pgtable_fmt {
+	ARM_32_LPAE_S1,
+	ARM_32_LPAE_S2,
+	ARM_64_LPAE_S1,
+	ARM_64_LPAE_S2,
+	IO_PGTABLE_NUM_FMTS,
+};
+
+/**
+ * struct iommu_gather_ops - IOMMU callbacks for TLB and page table management.
+ *
+ * @tlb_flush_all: Synchronously invalidate the entire TLB context.
+ * @tlb_add_flush: Queue up a TLB invalidation for a virtual address range.
+ * @tlb_sync:      Ensure any queue TLB invalidation has taken effect.
+ * @flush_pgtable: Ensure page table updates are visible to the IOMMU.
+ *
+ * Note that these can all be called in atomic context and must therefore
+ * not block.
+ */
+struct iommu_gather_ops {
+	void (*tlb_flush_all)(void *cookie);
+	void (*tlb_add_flush)(unsigned long iova, size_t size, bool leaf,
+			      void *cookie);
+	void (*tlb_sync)(void *cookie);
+	void (*flush_pgtable)(void *ptr, size_t size, void *cookie);
+};
+
+/**
+ * struct io_pgtable_cfg - Configuration data for a set of page tables.
+ *
+ * @quirks:        A bitmap of hardware quirks that require some special
+ *                 action by the low-level page table allocator.
+ * @pgsize_bitmap: A bitmap of page sizes supported by this set of page
+ *                 tables.
+ * @ias:           Input address (iova) size, in bits.
+ * @oas:           Output address (paddr) size, in bits.
+ * @tlb:           TLB management callbacks for this set of tables.
+ */
+struct io_pgtable_cfg {
+	#define IO_PGTABLE_QUIRK_ARM_NS	(1 << 0)	/* Set NS bit in PTEs */
+	int				quirks;
+	unsigned long			pgsize_bitmap;
+	unsigned int			ias;
+	unsigned int			oas;
+	const struct iommu_gather_ops	*tlb;
+
+	/* Low-level data specific to the table format */
+	union {
+		struct {
+			u64	ttbr[2];
+			u64	tcr;
+			u64	mair[2];
+		} arm_lpae_s1_cfg;
+
+		struct {
+			u64	vttbr;
+			u64	vtcr;
+		} arm_lpae_s2_cfg;
+	};
+};
+
+/**
+ * struct io_pgtable_ops - Page table manipulation API for IOMMU drivers.
+ *
+ * @map:          Map a physically contiguous memory region.
+ * @unmap:        Unmap a physically contiguous memory region.
+ * @iova_to_phys: Translate iova to physical address.
+ *
+ * These functions map directly onto the iommu_ops member functions with
+ * the same names.
+ */
+struct io_pgtable_ops {
+	int (*map)(struct io_pgtable_ops *ops, unsigned long iova,
+		   phys_addr_t paddr, size_t size, int prot);
+	int (*unmap)(struct io_pgtable_ops *ops, unsigned long iova,
+		     size_t size);
+	phys_addr_t (*iova_to_phys)(struct io_pgtable_ops *ops,
+				    unsigned long iova);
+};
+
+/**
+ * alloc_io_pgtable_ops() - Allocate a page table allocator for use by an IOMMU.
+ *
+ * @fmt:    The page table format.
+ * @cfg:    The page table configuration. This will be modified to represent
+ *          the configuration actually provided by the allocator (e.g. the
+ *          pgsize_bitmap may be restricted).
+ * @cookie: An opaque token provided by the IOMMU driver and passed back to
+ *          the callback routines in cfg->tlb.
+ */
+struct io_pgtable_ops *alloc_io_pgtable_ops(enum io_pgtable_fmt fmt,
+					    struct io_pgtable_cfg *cfg,
+					    void *cookie);
+
+/**
+ * free_io_pgtable_ops() - Free an io_pgtable_ops structure. The caller
+ *                         *must* ensure that the page table is no longer
+ *                         live, but the TLB can be dirty.
+ *
+ * @ops: The ops returned from alloc_io_pgtable_ops.
+ */
+void free_io_pgtable_ops(struct io_pgtable_ops *ops);
+
+
+/*
+ * Internal structures for page table allocator implementations.
+ */
+
+/**
+ * struct io_pgtable - Internal structure describing a set of page tables.
+ *
+ * @fmt:    The page table format.
+ * @cookie: An opaque token provided by the IOMMU driver and passed back to
+ *          any callback routines.
+ * @cfg:    A copy of the page table configuration.
+ * @ops:    The page table operations in use for this set of page tables.
+ */
+struct io_pgtable {
+	enum io_pgtable_fmt	fmt;
+	void			*cookie;
+	struct io_pgtable_cfg	cfg;
+	struct io_pgtable_ops	ops;
+};
+
+/**
+ * struct io_pgtable_init_fns - Alloc/free a set of page tables for a
+ *                              particular format.
+ *
+ * @alloc: Allocate a set of page tables described by cfg.
+ * @free:  Free the page tables associated with iop.
+ */
+struct io_pgtable_init_fns {
+	struct io_pgtable *(*alloc)(struct io_pgtable_cfg *cfg, void *cookie);
+	void (*free)(struct io_pgtable *iop);
+};
+
+#endif /* __IO_PGTABLE_H */

drivers/iommu/iommu.c

 /*
  * Copyright (C) 2007-2008 Advanced Micro Devices, Inc.
- * Author: Joerg Roedel <joerg.roedel@amd.com>
+ * Author: Joerg Roedel <jroedel@suse.de>
  *
  * 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
@@ -1084,7 +1084,7 @@ int iommu_map(struct iommu_domain *domain, unsigned long iova,
 	if (ret)
 		iommu_unmap(domain, orig_iova, orig_size - size);
 	else
-		trace_map(iova, paddr, size);
+		trace_map(orig_iova, paddr, orig_size);
 
 	return ret;
 }
@@ -1094,6 +1094,7 @@ size_t iommu_unmap(struct iommu_domain *domain, unsigned long iova, size_t size)
 {
 	size_t unmapped_page, unmapped = 0;
 	unsigned int min_pagesz;
+	unsigned long orig_iova = iova;
 
 	if (unlikely(domain->ops->unmap == NULL ||
 		     domain->ops->pgsize_bitmap == 0UL))
@@ -1133,7 +1134,7 @@ size_t iommu_unmap(struct iommu_domain *domain, unsigned long iova, size_t size)
 		unmapped += unmapped_page;
 	}
 
-	trace_unmap(iova, 0, size);
+	trace_unmap(orig_iova, size, unmapped);
 	return unmapped;
 }
 EXPORT_SYMBOL_GPL(iommu_unmap);

drivers/iommu/iova.c

@@ -18,13 +18,58 @@
  */
 
 #include <linux/iova.h>
+#include <linux/slab.h>
+
+static struct kmem_cache *iommu_iova_cache;
+
+int iommu_iova_cache_init(void)
+{
+	int ret = 0;
+
+	iommu_iova_cache = kmem_cache_create("iommu_iova",
+					 sizeof(struct iova),
+					 0,
+					 SLAB_HWCACHE_ALIGN,
+					 NULL);
+	if (!iommu_iova_cache) {
+		pr_err("Couldn't create iova cache\n");
+		ret = -ENOMEM;
+	}
+
+	return ret;
+}
+
+void iommu_iova_cache_destroy(void)
+{
+	kmem_cache_destroy(iommu_iova_cache);
+}
+
+struct iova *alloc_iova_mem(void)
+{
+	return kmem_cache_alloc(iommu_iova_cache, GFP_ATOMIC);
+}
+
+void free_iova_mem(struct iova *iova)
+{
+	kmem_cache_free(iommu_iova_cache, iova);
+}
 
 void
-init_iova_domain(struct iova_domain *iovad, unsigned long pfn_32bit)
+init_iova_domain(struct iova_domain *iovad, unsigned long granule,
+	unsigned long start_pfn, unsigned long pfn_32bit)
 {
+	/*
+	 * IOVA granularity will normally be equal to the smallest
+	 * supported IOMMU page size; both *must* be capable of
+	 * representing individual CPU pages exactly.
+	 */
+	BUG_ON((granule > PAGE_SIZE) || !is_power_of_2(granule));
+
 	spin_lock_init(&iovad->iova_rbtree_lock);
 	iovad->rbroot = RB_ROOT;
 	iovad->cached32_node = NULL;
+	iovad->granule = granule;
+	iovad->start_pfn = start_pfn;
 	iovad->dma_32bit_pfn = pfn_32bit;
 }
 
@@ -127,7 +172,7 @@ static int __alloc_and_insert_iova_range(struct iova_domain *iovad,
 	if (!curr) {
 		if (size_aligned)
 			pad_size = iova_get_pad_size(size, limit_pfn);
-		if ((IOVA_START_PFN + size + pad_size) > limit_pfn) {
+		if ((iovad->start_pfn + size + pad_size) > limit_pfn) {
 			spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
 			return -ENOMEM;
 		}
@@ -202,8 +247,8 @@ iova_insert_rbtree(struct rb_root *root, struct iova *iova)
  * @size: - size of page frames to allocate
  * @limit_pfn: - max limit address
  * @size_aligned: - set if size_aligned address range is required
- * This function allocates an iova in the range limit_pfn to IOVA_START_PFN
- * looking from limit_pfn instead from IOVA_START_PFN. If the size_aligned
+ * This function allocates an iova in the range iovad->start_pfn to limit_pfn,
+ * searching top-down from limit_pfn to iovad->start_pfn. If the size_aligned
  * flag is set then the allocated address iova->pfn_lo will be naturally
  * aligned on roundup_power_of_two(size).
  */

drivers/iommu/irq_remapping.h

 /*
  * Copyright (C) 2012 Advanced Micro Devices, Inc.
- * Author: Joerg Roedel <joerg.roedel@amd.com>
+ * Author: Joerg Roedel <jroedel@suse.de>
  *
  * 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

drivers/iommu/omap-iommu.c

@@ -1126,7 +1126,7 @@ static int omap_iommu_map(struct iommu_domain *domain, unsigned long da,
 		return -EINVAL;
 	}
 
-	dev_dbg(dev, "mapping da 0x%lx to pa 0x%x size 0x%x\n", da, pa, bytes);
+	dev_dbg(dev, "mapping da 0x%lx to pa %pa size 0x%x\n", da, &pa, bytes);
 
 	iotlb_init_entry(&e, da, pa, omap_pgsz);
 

include/linux/iopoll.h

+/*
+ * Copyright (c) 2012-2014 The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only 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.
+ *
+ */
+
+#ifndef _LINUX_IOPOLL_H
+#define _LINUX_IOPOLL_H
+
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/hrtimer.h>
+#include <linux/delay.h>
+#include <linux/errno.h>
+#include <linux/io.h>
+
+/**
+ * readx_poll_timeout - Periodically poll an address until a condition is met or a timeout occurs
+ * @op: accessor function (takes @addr as its only argument)
+ * @addr: Address to poll
+ * @val: Variable to read the value into
+ * @cond: Break condition (usually involving @val)
+ * @sleep_us: Maximum time to sleep between reads in us (0
+ *            tight-loops).  Should be less than ~20ms since usleep_range
+ *            is used (see Documentation/timers/timers-howto.txt).
+ * @timeout_us: Timeout in us, 0 means never timeout
+ *
+ * Returns 0 on success and -ETIMEDOUT upon a timeout. In either
+ * case, the last read value at @addr is stored in @val. Must not
+ * be called from atomic context if sleep_us or timeout_us are used.
+ *
+ * When available, you'll probably want to use one of the specialized
+ * macros defined below rather than this macro directly.
+ */
+#define readx_poll_timeout(op, addr, val, cond, sleep_us, timeout_us)	\
+({ \
+	ktime_t timeout = ktime_add_us(ktime_get(), timeout_us); \
+	might_sleep_if(sleep_us); \
+	for (;;) { \
+		(val) = op(addr); \
+		if (cond) \
+			break; \
+		if (timeout_us && ktime_compare(ktime_get(), timeout) > 0) { \
+			(val) = op(addr); \
+			break; \
+		} \
+		if (sleep_us) \
+			usleep_range((sleep_us >> 2) + 1, sleep_us); \
+	} \
+	(cond) ? 0 : -ETIMEDOUT; \
+})
+
+/**
+ * readx_poll_timeout_atomic - Periodically poll an address until a condition is met or a timeout occurs
+ * @op: accessor function (takes @addr as its only argument)
+ * @addr: Address to poll
+ * @val: Variable to read the value into
+ * @cond: Break condition (usually involving @val)
+ * @delay_us: Time to udelay between reads in us (0 tight-loops).  Should
+ *            be less than ~10us since udelay is used (see
+ *            Documentation/timers/timers-howto.txt).
+ * @timeout_us: Timeout in us, 0 means never timeout
+ *
+ * Returns 0 on success and -ETIMEDOUT upon a timeout. In either
+ * case, the last read value at @addr is stored in @val.
+ *
+ * When available, you'll probably want to use one of the specialized
+ * macros defined below rather than this macro directly.
+ */
+#define readx_poll_timeout_atomic(op, addr, val, cond, delay_us, timeout_us) \
+({ \
+	ktime_t timeout = ktime_add_us(ktime_get(), timeout_us); \
+	for (;;) { \
+		(val) = op(addr); \
+		if (cond) \
+			break; \
+		if (timeout_us && ktime_compare(ktime_get(), timeout) > 0) { \
+			(val) = op(addr); \
+			break; \
+		} \
+		if (delay_us) \
+			udelay(delay_us);	\
+	} \
+	(cond) ? 0 : -ETIMEDOUT; \
+})
+
+
+#define readb_poll_timeout(addr, val, cond, delay_us, timeout_us) \
+	readx_poll_timeout(readb, addr, val, cond, delay_us, timeout_us)
+
+#define readb_poll_timeout_atomic(addr, val, cond, delay_us, timeout_us) \
+	readx_poll_timeout_atomic(readb, addr, val, cond, delay_us, timeout_us)
+
+#define readw_poll_timeout(addr, val, cond, delay_us, timeout_us) \
+	readx_poll_timeout(readw, addr, val, cond, delay_us, timeout_us)
+
+#define readw_poll_timeout_atomic(addr, val, cond, delay_us, timeout_us) \
+	readx_poll_timeout_atomic(readw, addr, val, cond, delay_us, timeout_us)
+
+#define readl_poll_timeout(addr, val, cond, delay_us, timeout_us) \
+	readx_poll_timeout(readl, addr, val, cond, delay_us, timeout_us)
+
+#define readl_poll_timeout_atomic(addr, val, cond, delay_us, timeout_us) \
+	readx_poll_timeout_atomic(readl, addr, val, cond, delay_us, timeout_us)
+
+#define readq_poll_timeout(addr, val, cond, delay_us, timeout_us) \
+	readx_poll_timeout(readq, addr, val, cond, delay_us, timeout_us)
+
+#define readq_poll_timeout_atomic(addr, val, cond, delay_us, timeout_us) \
+	readx_poll_timeout_atomic(readq, addr, val, cond, delay_us, timeout_us)
+
+#define readb_relaxed_poll_timeout(addr, val, cond, delay_us, timeout_us) \
+	readx_poll_timeout(readb_relaxed, addr, val, cond, delay_us, timeout_us)
+
+#define readb_relaxed_poll_timeout_atomic(addr, val, cond, delay_us, timeout_us) \
+	readx_poll_timeout_atomic(readb_relaxed, addr, val, cond, delay_us, timeout_us)
+
+#define readw_relaxed_poll_timeout(addr, val, cond, delay_us, timeout_us) \
+	readx_poll_timeout(readw_relaxed, addr, val, cond, delay_us, timeout_us)
+
+#define readw_relaxed_poll_timeout_atomic(addr, val, cond, delay_us, timeout_us) \
+	readx_poll_timeout_atomic(readw_relaxed, addr, val, cond, delay_us, timeout_us)
+
+#define readl_relaxed_poll_timeout(addr, val, cond, delay_us, timeout_us) \
+	readx_poll_timeout(readl_relaxed, addr, val, cond, delay_us, timeout_us)
+
+#define readl_relaxed_poll_timeout_atomic(addr, val, cond, delay_us, timeout_us) \
+	readx_poll_timeout_atomic(readl_relaxed, addr, val, cond, delay_us, timeout_us)
+
+#define readq_relaxed_poll_timeout(addr, val, cond, delay_us, timeout_us) \
+	readx_poll_timeout(readq_relaxed, addr, val, cond, delay_us, timeout_us)
+
+#define readq_relaxed_poll_timeout_atomic(addr, val, cond, delay_us, timeout_us) \
+	readx_poll_timeout_atomic(readq_relaxed, addr, val, cond, delay_us, timeout_us)
+
+#endif /* _LINUX_IOPOLL_H */

include/linux/platform_data/ipmmu-vmsa.h

-/*
- * IPMMU VMSA Platform Data
- *
- * Copyright (C) 2014 Renesas Electronics Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; version 2 of the License.
- */
-
-#ifndef __IPMMU_VMSA_H__
-#define __IPMMU_VMSA_H__
-
-struct ipmmu_vmsa_master {
-	const char *name;
-	unsigned int utlb;
-};
-
-struct ipmmu_vmsa_platform_data {
-	const struct ipmmu_vmsa_master *masters;
-	unsigned int num_masters;
-};
-
-#endif /* __IPMMU_VMSA_H__ */