Merge branch 'next' (accumulated 3.16 merge window patches) into master

Now that 3.15 is released, this merges the 'next' branch into 'master',
bringing us to the normal situation where my 'master' branch is the
merge window.

* accumulated work in next: (6809 commits)
  ufs: sb mutex merge + mutex_destroy
  powerpc: update comments for generic idle conversion
  cris: update comments for generic idle conversion
  idle: remove cpu_idle() forward declarations
  nbd: zero from and len fields in NBD_CMD_DISCONNECT.
  mm: convert some level-less printks to pr_*
  MAINTAINERS: adi-buildroot-devel is moderated
  MAINTAINERS: add linux-api for review of API/ABI changes
  mm/kmemleak-test.c: use pr_fmt for logging
  fs/dlm/debug_fs.c: replace seq_printf by seq_puts
  fs/dlm/lockspace.c: convert simple_str to kstr
  fs/dlm/config.c: convert simple_str to kstr
  mm: mark remap_file_pages() syscall as deprecated
  mm: memcontrol: remove unnecessary memcg argument from soft limit functions
  mm: memcontrol: clean up memcg zoneinfo lookup
  mm/memblock.c: call kmemleak directly from memblock_(alloc|free)
  mm/mempool.c: update the kmemleak stack trace for mempool allocations
  lib/radix-tree.c: update the kmemleak stack trace for radix tree allocations
  mm: introduce kmemleak_update_trace()
  mm/kmemleak.c: use %u to print ->checksum
  ...

1 files changed, 622 insertions, 430 deletions

diff --git a/drivers/iommu/exynos-iommu.c b/drivers/iommu/exynos-iommu.c
index 074018979cdf..99054d2c040d 100644
--- a/drivers/iommu/exynos-iommu.c
+++ b/drivers/iommu/exynos-iommu.c
@@ -29,7 +29,8 @@
 #include <asm/cacheflush.h>
 #include <asm/pgtable.h>
 
-#include <mach/sysmmu.h>
+typedef u32 sysmmu_iova_t;
+typedef u32 sysmmu_pte_t;
 
 /* We does not consider super section mapping (16MB) */
 #define SECT_ORDER 20
@@ -44,28 +45,44 @@
 #define LPAGE_MASK (~(LPAGE_SIZE - 1))
 #define SPAGE_MASK (~(SPAGE_SIZE - 1))
 
-#define lv1ent_fault(sent) (((*(sent) & 3) == 0) || ((*(sent) & 3) == 3))
-#define lv1ent_page(sent) ((*(sent) & 3) == 1)
+#define lv1ent_fault(sent) ((*(sent) == ZERO_LV2LINK) || \
+			   ((*(sent) & 3) == 0) || ((*(sent) & 3) == 3))
+#define lv1ent_zero(sent) (*(sent) == ZERO_LV2LINK)
+#define lv1ent_page_zero(sent) ((*(sent) & 3) == 1)
+#define lv1ent_page(sent) ((*(sent) != ZERO_LV2LINK) && \
+			  ((*(sent) & 3) == 1))
 #define lv1ent_section(sent) ((*(sent) & 3) == 2)
 
 #define lv2ent_fault(pent) ((*(pent) & 3) == 0)
 #define lv2ent_small(pent) ((*(pent) & 2) == 2)
 #define lv2ent_large(pent) ((*(pent) & 3) == 1)
 
+static u32 sysmmu_page_offset(sysmmu_iova_t iova, u32 size)
+{
+	return iova & (size - 1);
+}
+
 #define section_phys(sent) (*(sent) & SECT_MASK)
-#define section_offs(iova) ((iova) & 0xFFFFF)
+#define section_offs(iova) sysmmu_page_offset((iova), SECT_SIZE)
 #define lpage_phys(pent) (*(pent) & LPAGE_MASK)
-#define lpage_offs(iova) ((iova) & 0xFFFF)
+#define lpage_offs(iova) sysmmu_page_offset((iova), LPAGE_SIZE)
 #define spage_phys(pent) (*(pent) & SPAGE_MASK)
-#define spage_offs(iova) ((iova) & 0xFFF)
-
-#define lv1ent_offset(iova) ((iova) >> SECT_ORDER)
-#define lv2ent_offset(iova) (((iova) & 0xFF000) >> SPAGE_ORDER)
+#define spage_offs(iova) sysmmu_page_offset((iova), SPAGE_SIZE)
 
 #define NUM_LV1ENTRIES 4096
-#define NUM_LV2ENTRIES 256
+#define NUM_LV2ENTRIES (SECT_SIZE / SPAGE_SIZE)
+
+static u32 lv1ent_offset(sysmmu_iova_t iova)
+{
+	return iova >> SECT_ORDER;
+}
+
+static u32 lv2ent_offset(sysmmu_iova_t iova)
+{
+	return (iova >> SPAGE_ORDER) & (NUM_LV2ENTRIES - 1);
+}
 
-#define LV2TABLE_SIZE (NUM_LV2ENTRIES * sizeof(long))
+#define LV2TABLE_SIZE (NUM_LV2ENTRIES * sizeof(sysmmu_pte_t))
 
 #define SPAGES_PER_LPAGE (LPAGE_SIZE / SPAGE_SIZE)
 
@@ -80,6 +97,13 @@
 #define CTRL_BLOCK	0x7
 #define CTRL_DISABLE	0x0
 
+#define CFG_LRU		0x1
+#define CFG_QOS(n)	((n & 0xF) << 7)
+#define CFG_MASK	0x0150FFFF /* Selecting bit 0-15, 20, 22 and 24 */
+#define CFG_ACGEN	(1 << 24) /* System MMU 3.3 only */
+#define CFG_SYSSEL	(1 << 22) /* System MMU 3.2 only */
+#define CFG_FLPDCACHE	(1 << 20) /* System MMU 3.2+ only */
+
 #define REG_MMU_CTRL		0x000
 #define REG_MMU_CFG		0x004
 #define REG_MMU_STATUS		0x008
@@ -96,19 +120,32 @@
 
 #define REG_MMU_VERSION		0x034
 
+#define MMU_MAJ_VER(val)	((val) >> 7)
+#define MMU_MIN_VER(val)	((val) & 0x7F)
+#define MMU_RAW_VER(reg)	(((reg) >> 21) & ((1 << 11) - 1)) /* 11 bits */
+
+#define MAKE_MMU_VER(maj, min)	((((maj) & 0xF) << 7) | ((min) & 0x7F))
+
 #define REG_PB0_SADDR		0x04C
 #define REG_PB0_EADDR		0x050
 #define REG_PB1_SADDR		0x054
 #define REG_PB1_EADDR		0x058
 
-static unsigned long *section_entry(unsigned long *pgtable, unsigned long iova)
+#define has_sysmmu(dev)		(dev->archdata.iommu != NULL)
+
+static struct kmem_cache *lv2table_kmem_cache;
+static sysmmu_pte_t *zero_lv2_table;
+#define ZERO_LV2LINK mk_lv1ent_page(virt_to_phys(zero_lv2_table))
+
+static sysmmu_pte_t *section_entry(sysmmu_pte_t *pgtable, sysmmu_iova_t iova)
 {
 	return pgtable + lv1ent_offset(iova);
 }
 
-static unsigned long *page_entry(unsigned long *sent, unsigned long iova)
+static sysmmu_pte_t *page_entry(sysmmu_pte_t *sent, sysmmu_iova_t iova)
 {
-	return (unsigned long *)__va(lv2table_base(sent)) + lv2ent_offset(iova);
+	return (sysmmu_pte_t *)phys_to_virt(
+				lv2table_base(sent)) + lv2ent_offset(iova);
 }
 
 enum exynos_sysmmu_inttype {
@@ -124,16 +161,6 @@ enum exynos_sysmmu_inttype {
 	SYSMMU_FAULTS_NUM
 };
 
-/*
- * @itype: type of fault.
- * @pgtable_base: the physical address of page table base. This is 0 if @itype
- *                is SYSMMU_BUSERROR.
- * @fault_addr: the device (virtual) address that the System MMU tried to
- *             translated. This is 0 if @itype is SYSMMU_BUSERROR.
- */
-typedef int (*sysmmu_fault_handler_t)(enum exynos_sysmmu_inttype itype,
-			unsigned long pgtable_base, unsigned long fault_addr);
-
 static unsigned short fault_reg_offset[SYSMMU_FAULTS_NUM] = {
 	REG_PAGE_FAULT_ADDR,
 	REG_AR_FAULT_ADDR,
@@ -157,27 +184,34 @@ static char *sysmmu_fault_name[SYSMMU_FAULTS_NUM] = {
 	"UNKNOWN FAULT"
 };
 
+/* attached to dev.archdata.iommu of the master device */
+struct exynos_iommu_owner {
+	struct list_head client; /* entry of exynos_iommu_domain.clients */
+	struct device *dev;
+	struct device *sysmmu;
+	struct iommu_domain *domain;
+	void *vmm_data;         /* IO virtual memory manager's data */
+	spinlock_t lock;        /* Lock to preserve consistency of System MMU */
+};
+
 struct exynos_iommu_domain {
 	struct list_head clients; /* list of sysmmu_drvdata.node */
-	unsigned long *pgtable; /* lv1 page table, 16KB */
+	sysmmu_pte_t *pgtable; /* lv1 page table, 16KB */
 	short *lv2entcnt; /* free lv2 entry counter for each section */
 	spinlock_t lock; /* lock for this structure */
 	spinlock_t pgtablelock; /* lock for modifying page table @ pgtable */
 };
 
 struct sysmmu_drvdata {
-	struct list_head node; /* entry of exynos_iommu_domain.clients */
 	struct device *sysmmu;	/* System MMU's device descriptor */
-	struct device *dev;	/* Owner of system MMU */
-	char *dbgname;
-	int nsfrs;
-	void __iomem **sfrbases;
-	struct clk *clk[2];
+	struct device *master;	/* Owner of system MMU */
+	void __iomem *sfrbase;
+	struct clk *clk;
+	struct clk *clk_master;
 	int activations;
-	rwlock_t lock;
+	spinlock_t lock;
 	struct iommu_domain *domain;
-	sysmmu_fault_handler_t fault_handler;
-	unsigned long pgtable;
+	phys_addr_t pgtable;
 };
 
 static bool set_sysmmu_active(struct sysmmu_drvdata *data)
@@ -204,6 +238,11 @@ static void sysmmu_unblock(void __iomem *sfrbase)
 	__raw_writel(CTRL_ENABLE, sfrbase + REG_MMU_CTRL);
 }
 
+static unsigned int __raw_sysmmu_version(struct sysmmu_drvdata *data)
+{
+	return MMU_RAW_VER(__raw_readl(data->sfrbase + REG_MMU_VERSION));
+}
+
 static bool sysmmu_block(void __iomem *sfrbase)
 {
 	int i = 120;
@@ -226,434 +265,428 @@ static void __sysmmu_tlb_invalidate(void __iomem *sfrbase)
 }
 
 static void __sysmmu_tlb_invalidate_entry(void __iomem *sfrbase,
-						unsigned long iova)
+				sysmmu_iova_t iova, unsigned int num_inv)
 {
-	__raw_writel((iova & SPAGE_MASK) | 1, sfrbase + REG_MMU_FLUSH_ENTRY);
+	unsigned int i;
+
+	for (i = 0; i < num_inv; i++) {
+		__raw_writel((iova & SPAGE_MASK) | 1,
+				sfrbase + REG_MMU_FLUSH_ENTRY);
+		iova += SPAGE_SIZE;
+	}
 }
 
 static void __sysmmu_set_ptbase(void __iomem *sfrbase,
-				       unsigned long pgd)
+				       phys_addr_t pgd)
 {
-	__raw_writel(0x1, sfrbase + REG_MMU_CFG); /* 16KB LV1, LRU */
 	__raw_writel(pgd, sfrbase + REG_PT_BASE_ADDR);
 
 	__sysmmu_tlb_invalidate(sfrbase);
 }
 
-static void __sysmmu_set_prefbuf(void __iomem *sfrbase, unsigned long base,
-						unsigned long size, int idx)
-{
-	__raw_writel(base, sfrbase + REG_PB0_SADDR + idx * 8);
-	__raw_writel(size - 1 + base,  sfrbase + REG_PB0_EADDR + idx * 8);
-}
-
-static void __set_fault_handler(struct sysmmu_drvdata *data,
-					sysmmu_fault_handler_t handler)
-{
-	unsigned long flags;
-
-	write_lock_irqsave(&data->lock, flags);
-	data->fault_handler = handler;
-	write_unlock_irqrestore(&data->lock, flags);
-}
-
-void exynos_sysmmu_set_fault_handler(struct device *dev,
-					sysmmu_fault_handler_t handler)
-{
-	struct sysmmu_drvdata *data = dev_get_drvdata(dev->archdata.iommu);
-
-	__set_fault_handler(data, handler);
-}
-
-static int default_fault_handler(enum exynos_sysmmu_inttype itype,
-		     unsigned long pgtable_base, unsigned long fault_addr)
+static void show_fault_information(const char *name,
+		enum exynos_sysmmu_inttype itype,
+		phys_addr_t pgtable_base, sysmmu_iova_t fault_addr)
 {
-	unsigned long *ent;
+	sysmmu_pte_t *ent;
 
 	if ((itype >= SYSMMU_FAULTS_NUM) || (itype < SYSMMU_PAGEFAULT))
 		itype = SYSMMU_FAULT_UNKNOWN;
 
-	pr_err("%s occurred at 0x%lx(Page table base: 0x%lx)\n",
-			sysmmu_fault_name[itype], fault_addr, pgtable_base);
+	pr_err("%s occurred at %#x by %s(Page table base: %pa)\n",
+		sysmmu_fault_name[itype], fault_addr, name, &pgtable_base);
 
-	ent = section_entry(__va(pgtable_base), fault_addr);
-	pr_err("\tLv1 entry: 0x%lx\n", *ent);
+	ent = section_entry(phys_to_virt(pgtable_base), fault_addr);
+	pr_err("\tLv1 entry: %#x\n", *ent);
 
 	if (lv1ent_page(ent)) {
 		ent = page_entry(ent, fault_addr);
-		pr_err("\t Lv2 entry: 0x%lx\n", *ent);
+		pr_err("\t Lv2 entry: %#x\n", *ent);
 	}
-
-	pr_err("Generating Kernel OOPS... because it is unrecoverable.\n");
-
-	BUG();
-
-	return 0;
 }
 
 static irqreturn_t exynos_sysmmu_irq(int irq, void *dev_id)
 {
 	/* SYSMMU is in blocked when interrupt occurred. */
 	struct sysmmu_drvdata *data = dev_id;
-	struct resource *irqres;
-	struct platform_device *pdev;
 	enum exynos_sysmmu_inttype itype;
-	unsigned long addr = -1;
-
-	int i, ret = -ENOSYS;
-
-	read_lock(&data->lock);
+	sysmmu_iova_t addr = -1;
+	int ret = -ENOSYS;
 
 	WARN_ON(!is_sysmmu_active(data));
 
-	pdev = to_platform_device(data->sysmmu);
-	for (i = 0; i < (pdev->num_resources / 2); i++) {
-		irqres = platform_get_resource(pdev, IORESOURCE_IRQ, i);
-		if (irqres && ((int)irqres->start == irq))
-			break;
-	}
+	spin_lock(&data->lock);
 
-	if (i == pdev->num_resources) {
+	if (!IS_ERR(data->clk_master))
+		clk_enable(data->clk_master);
+
+	itype = (enum exynos_sysmmu_inttype)
+		__ffs(__raw_readl(data->sfrbase + REG_INT_STATUS));
+	if (WARN_ON(!((itype >= 0) && (itype < SYSMMU_FAULT_UNKNOWN))))
 		itype = SYSMMU_FAULT_UNKNOWN;
+	else
+		addr = __raw_readl(data->sfrbase + fault_reg_offset[itype]);
+
+	if (itype == SYSMMU_FAULT_UNKNOWN) {
+		pr_err("%s: Fault is not occurred by System MMU '%s'!\n",
+			__func__, dev_name(data->sysmmu));
+		pr_err("%s: Please check if IRQ is correctly configured.\n",
+			__func__);
+		BUG();
 	} else {
-		itype = (enum exynos_sysmmu_inttype)
-			__ffs(__raw_readl(data->sfrbases[i] + REG_INT_STATUS));
-		if (WARN_ON(!((itype >= 0) && (itype < SYSMMU_FAULT_UNKNOWN))))
-			itype = SYSMMU_FAULT_UNKNOWN;
-		else
-			addr = __raw_readl(
-				data->sfrbases[i] + fault_reg_offset[itype]);
+		unsigned int base =
+				__raw_readl(data->sfrbase + REG_PT_BASE_ADDR);
+		show_fault_information(dev_name(data->sysmmu),
+					itype, base, addr);
+		if (data->domain)
+			ret = report_iommu_fault(data->domain,
+					data->master, addr, itype);
 	}
 
-	if (data->domain)
-		ret = report_iommu_fault(data->domain, data->dev,
-				addr, itype);
+	/* fault is not recovered by fault handler */
+	BUG_ON(ret != 0);
 
-	if ((ret == -ENOSYS) && data->fault_handler) {
-		unsigned long base = data->pgtable;
-		if (itype != SYSMMU_FAULT_UNKNOWN)
-			base = __raw_readl(
-					data->sfrbases[i] + REG_PT_BASE_ADDR);
-		ret = data->fault_handler(itype, base, addr);
-	}
+	__raw_writel(1 << itype, data->sfrbase + REG_INT_CLEAR);
 
-	if (!ret && (itype != SYSMMU_FAULT_UNKNOWN))
-		__raw_writel(1 << itype, data->sfrbases[i] + REG_INT_CLEAR);
-	else
-		dev_dbg(data->sysmmu, "(%s) %s is not handled.\n",
-				data->dbgname, sysmmu_fault_name[itype]);
+	sysmmu_unblock(data->sfrbase);
 
-	if (itype != SYSMMU_FAULT_UNKNOWN)
-		sysmmu_unblock(data->sfrbases[i]);
+	if (!IS_ERR(data->clk_master))
+		clk_disable(data->clk_master);
 
-	read_unlock(&data->lock);
+	spin_unlock(&data->lock);
 
 	return IRQ_HANDLED;
 }
 
-static bool __exynos_sysmmu_disable(struct sysmmu_drvdata *data)
+static void __sysmmu_disable_nocount(struct sysmmu_drvdata *data)
 {
+	if (!IS_ERR(data->clk_master))
+		clk_enable(data->clk_master);
+
+	__raw_writel(CTRL_DISABLE, data->sfrbase + REG_MMU_CTRL);
+	__raw_writel(0, data->sfrbase + REG_MMU_CFG);
+
+	clk_disable(data->clk);
+	if (!IS_ERR(data->clk_master))
+		clk_disable(data->clk_master);
+}
+
+static bool __sysmmu_disable(struct sysmmu_drvdata *data)
+{
+	bool disabled;
 	unsigned long flags;
-	bool disabled = false;
-	int i;
 
-	write_lock_irqsave(&data->lock, flags);
+	spin_lock_irqsave(&data->lock, flags);
 
-	if (!set_sysmmu_inactive(data))
-		goto finish;
+	disabled = set_sysmmu_inactive(data);
 
-	for (i = 0; i < data->nsfrs; i++)
-		__raw_writel(CTRL_DISABLE, data->sfrbases[i] + REG_MMU_CTRL);
+	if (disabled) {
+		data->pgtable = 0;
+		data->domain = NULL;
 
-	if (data->clk[1])
-		clk_disable(data->clk[1]);
-	if (data->clk[0])
-		clk_disable(data->clk[0]);
+		__sysmmu_disable_nocount(data);
 
-	disabled = true;
-	data->pgtable = 0;
-	data->domain = NULL;
-finish:
-	write_unlock_irqrestore(&data->lock, flags);
+		dev_dbg(data->sysmmu, "Disabled\n");
+	} else  {
+		dev_dbg(data->sysmmu, "%d times left to disable\n",
+					data->activations);
+	}
 
-	if (disabled)
-		dev_dbg(data->sysmmu, "(%s) Disabled\n", data->dbgname);
-	else
-		dev_dbg(data->sysmmu, "(%s) %d times left to be disabled\n",
-					data->dbgname, data->activations);
+	spin_unlock_irqrestore(&data->lock, flags);
 
 	return disabled;
 }
 
-/* __exynos_sysmmu_enable: Enables System MMU
- *
- * returns -error if an error occurred and System MMU is not enabled,
- * 0 if the System MMU has been just enabled and 1 if System MMU was already
- * enabled before.
- */
-static int __exynos_sysmmu_enable(struct sysmmu_drvdata *data,
-			unsigned long pgtable, struct iommu_domain *domain)
+static void __sysmmu_init_config(struct sysmmu_drvdata *data)
 {
-	int i, ret = 0;
-	unsigned long flags;
+	unsigned int cfg = CFG_LRU | CFG_QOS(15);
+	unsigned int ver;
+
+	ver = __raw_sysmmu_version(data);
+	if (MMU_MAJ_VER(ver) == 3) {
+		if (MMU_MIN_VER(ver) >= 2) {
+			cfg |= CFG_FLPDCACHE;
+			if (MMU_MIN_VER(ver) == 3) {
+				cfg |= CFG_ACGEN;
+				cfg &= ~CFG_LRU;
+			} else {
+				cfg |= CFG_SYSSEL;
+			}
+		}
+	}
 
-	write_lock_irqsave(&data->lock, flags);
+	__raw_writel(cfg, data->sfrbase + REG_MMU_CFG);
+}
 
-	if (!set_sysmmu_active(data)) {
-		if (WARN_ON(pgtable != data->pgtable)) {
-			ret = -EBUSY;
-			set_sysmmu_inactive(data);
-		} else {
-			ret = 1;
-		}
+static void __sysmmu_enable_nocount(struct sysmmu_drvdata *data)
+{
+	if (!IS_ERR(data->clk_master))
+		clk_enable(data->clk_master);
+	clk_enable(data->clk);
 
-		dev_dbg(data->sysmmu, "(%s) Already enabled\n", data->dbgname);
-		goto finish;
-	}
+	__raw_writel(CTRL_BLOCK, data->sfrbase + REG_MMU_CTRL);
 
-	if (data->clk[0])
-		clk_enable(data->clk[0]);
-	if (data->clk[1])
-		clk_enable(data->clk[1]);
+	__sysmmu_init_config(data);
 
-	data->pgtable = pgtable;
+	__sysmmu_set_ptbase(data->sfrbase, data->pgtable);
 
-	for (i = 0; i < data->nsfrs; i++) {
-		__sysmmu_set_ptbase(data->sfrbases[i], pgtable);
+	__raw_writel(CTRL_ENABLE, data->sfrbase + REG_MMU_CTRL);
 
-		if ((readl(data->sfrbases[i] + REG_MMU_VERSION) >> 28) == 3) {
-			/* System MMU version is 3.x */
-			__raw_writel((1 << 12) | (2 << 28),
-					data->sfrbases[i] + REG_MMU_CFG);
-			__sysmmu_set_prefbuf(data->sfrbases[i], 0, -1, 0);
-			__sysmmu_set_prefbuf(data->sfrbases[i], 0, -1, 1);
-		}
+	if (!IS_ERR(data->clk_master))
+		clk_disable(data->clk_master);
+}
 
-		__raw_writel(CTRL_ENABLE, data->sfrbases[i] + REG_MMU_CTRL);
+static int __sysmmu_enable(struct sysmmu_drvdata *data,
+			phys_addr_t pgtable, struct iommu_domain *domain)
+{
+	int ret = 0;
+	unsigned long flags;
+
+	spin_lock_irqsave(&data->lock, flags);
+	if (set_sysmmu_active(data)) {
+		data->pgtable = pgtable;
+		data->domain = domain;
+
+		__sysmmu_enable_nocount(data);
+
+		dev_dbg(data->sysmmu, "Enabled\n");
+	} else {
+		ret = (pgtable == data->pgtable) ? 1 : -EBUSY;
+
+		dev_dbg(data->sysmmu, "already enabled\n");
 	}
 
-	data->domain = domain;
+	if (WARN_ON(ret < 0))
+		set_sysmmu_inactive(data); /* decrement count */
 
-	dev_dbg(data->sysmmu, "(%s) Enabled\n", data->dbgname);
-finish:
-	write_unlock_irqrestore(&data->lock, flags);
+	spin_unlock_irqrestore(&data->lock, flags);
 
 	return ret;
 }
 
-int exynos_sysmmu_enable(struct device *dev, unsigned long pgtable)
+/* __exynos_sysmmu_enable: Enables System MMU
+ *
+ * returns -error if an error occurred and System MMU is not enabled,
+ * 0 if the System MMU has been just enabled and 1 if System MMU was already
+ * enabled before.
+ */
+static int __exynos_sysmmu_enable(struct device *dev, phys_addr_t pgtable,
+				  struct iommu_domain *domain)
 {
-	struct sysmmu_drvdata *data = dev_get_drvdata(dev->archdata.iommu);
-	int ret;
+	int ret = 0;
+	unsigned long flags;
+	struct exynos_iommu_owner *owner = dev->archdata.iommu;
+	struct sysmmu_drvdata *data;
 
-	BUG_ON(!memblock_is_memory(pgtable));
+	BUG_ON(!has_sysmmu(dev));
 
-	ret = pm_runtime_get_sync(data->sysmmu);
-	if (ret < 0) {
-		dev_dbg(data->sysmmu, "(%s) Failed to enable\n", data->dbgname);
-		return ret;
-	}
+	spin_lock_irqsave(&owner->lock, flags);
 
-	ret = __exynos_sysmmu_enable(data, pgtable, NULL);
-	if (WARN_ON(ret < 0)) {
-		pm_runtime_put(data->sysmmu);
-		dev_err(data->sysmmu,
-			"(%s) Already enabled with page table %#lx\n",
-			data->dbgname, data->pgtable);
-	} else {
-		data->dev = dev;
-	}
+	data = dev_get_drvdata(owner->sysmmu);
+
+	ret = __sysmmu_enable(data, pgtable, domain);
+	if (ret >= 0)
+		data->master = dev;
+
+	spin_unlock_irqrestore(&owner->lock, flags);
 
 	return ret;
 }
 
+int exynos_sysmmu_enable(struct device *dev, phys_addr_t pgtable)
+{
+	BUG_ON(!memblock_is_memory(pgtable));
+
+	return __exynos_sysmmu_enable(dev, pgtable, NULL);
+}
+
 static bool exynos_sysmmu_disable(struct device *dev)
 {
-	struct sysmmu_drvdata *data = dev_get_drvdata(dev->archdata.iommu);
-	bool disabled;
+	unsigned long flags;
+	bool disabled = true;
+	struct exynos_iommu_owner *owner = dev->archdata.iommu;
+	struct sysmmu_drvdata *data;
+
+	BUG_ON(!has_sysmmu(dev));
+
+	spin_lock_irqsave(&owner->lock, flags);
 
-	disabled = __exynos_sysmmu_disable(data);
-	pm_runtime_put(data->sysmmu);
+	data = dev_get_drvdata(owner->sysmmu);
+
+	disabled = __sysmmu_disable(data);
+	if (disabled)
+		data->master = NULL;
+
+	spin_unlock_irqrestore(&owner->lock, flags);
 
 	return disabled;
 }
 
-static void sysmmu_tlb_invalidate_entry(struct device *dev, unsigned long iova)
+static void __sysmmu_tlb_invalidate_flpdcache(struct sysmmu_drvdata *data,
+					      sysmmu_iova_t iova)
+{
+	if (__raw_sysmmu_version(data) == MAKE_MMU_VER(3, 3))
+		__raw_writel(iova | 0x1, data->sfrbase + REG_MMU_FLUSH_ENTRY);
+}
+
+static void sysmmu_tlb_invalidate_flpdcache(struct device *dev,
+					    sysmmu_iova_t iova)
+{
+	unsigned long flags;
+	struct exynos_iommu_owner *owner = dev->archdata.iommu;
+	struct sysmmu_drvdata *data = dev_get_drvdata(owner->sysmmu);
+
+	if (!IS_ERR(data->clk_master))
+		clk_enable(data->clk_master);
+
+	spin_lock_irqsave(&data->lock, flags);
+	if (is_sysmmu_active(data))
+		__sysmmu_tlb_invalidate_flpdcache(data, iova);
+	spin_unlock_irqrestore(&data->lock, flags);
+
+	if (!IS_ERR(data->clk_master))
+		clk_disable(data->clk_master);
+}
+
+static void sysmmu_tlb_invalidate_entry(struct device *dev, sysmmu_iova_t iova,
+					size_t size)
 {
+	struct exynos_iommu_owner *owner = dev->archdata.iommu;
 	unsigned long flags;
-	struct sysmmu_drvdata *data = dev_get_drvdata(dev->archdata.iommu);
+	struct sysmmu_drvdata *data;
 
-	read_lock_irqsave(&data->lock, flags);
+	data = dev_get_drvdata(owner->sysmmu);
 
+	spin_lock_irqsave(&data->lock, flags);
 	if (is_sysmmu_active(data)) {
-		int i;
-		for (i = 0; i < data->nsfrs; i++) {
-			if (sysmmu_block(data->sfrbases[i])) {
-				__sysmmu_tlb_invalidate_entry(
-						data->sfrbases[i], iova);
-				sysmmu_unblock(data->sfrbases[i]);
-			}
+		unsigned int num_inv = 1;
+
+		if (!IS_ERR(data->clk_master))
+			clk_enable(data->clk_master);
+
+		/*
+		 * L2TLB invalidation required
+		 * 4KB page: 1 invalidation
+		 * 64KB page: 16 invalidation
+		 * 1MB page: 64 invalidation
+		 * because it is set-associative TLB
+		 * with 8-way and 64 sets.
+		 * 1MB page can be cached in one of all sets.
+		 * 64KB page can be one of 16 consecutive sets.
+		 */
+		if (MMU_MAJ_VER(__raw_sysmmu_version(data)) == 2)
+			num_inv = min_t(unsigned int, size / PAGE_SIZE, 64);
+
+		if (sysmmu_block(data->sfrbase)) {
+			__sysmmu_tlb_invalidate_entry(
+				data->sfrbase, iova, num_inv);
+			sysmmu_unblock(data->sfrbase);
 		}
+		if (!IS_ERR(data->clk_master))
+			clk_disable(data->clk_master);
 	} else {
-		dev_dbg(data->sysmmu,
-			"(%s) Disabled. Skipping invalidating TLB.\n",
-			data->dbgname);
+		dev_dbg(dev, "disabled. Skipping TLB invalidation @ %#x\n",
+			iova);
 	}
-
-	read_unlock_irqrestore(&data->lock, flags);
+	spin_unlock_irqrestore(&data->lock, flags);
 }
 
 void exynos_sysmmu_tlb_invalidate(struct device *dev)
 {
+	struct exynos_iommu_owner *owner = dev->archdata.iommu;
 	unsigned long flags;
-	struct sysmmu_drvdata *data = dev_get_drvdata(dev->archdata.iommu);
+	struct sysmmu_drvdata *data;
 
-	read_lock_irqsave(&data->lock, flags);
+	data = dev_get_drvdata(owner->sysmmu);
 
+	spin_lock_irqsave(&data->lock, flags);
 	if (is_sysmmu_active(data)) {
-		int i;
-		for (i = 0; i < data->nsfrs; i++) {
-			if (sysmmu_block(data->sfrbases[i])) {
-				__sysmmu_tlb_invalidate(data->sfrbases[i]);
-				sysmmu_unblock(data->sfrbases[i]);
-			}
+		if (!IS_ERR(data->clk_master))
+			clk_enable(data->clk_master);
+		if (sysmmu_block(data->sfrbase)) {
+			__sysmmu_tlb_invalidate(data->sfrbase);
+			sysmmu_unblock(data->sfrbase);
 		}
+		if (!IS_ERR(data->clk_master))
+			clk_disable(data->clk_master);
 	} else {
-		dev_dbg(data->sysmmu,
-			"(%s) Disabled. Skipping invalidating TLB.\n",
-			data->dbgname);
+		dev_dbg(dev, "disabled. Skipping TLB invalidation\n");
 	}
-
-	read_unlock_irqrestore(&data->lock, flags);
+	spin_unlock_irqrestore(&data->lock, flags);
 }
 
-static int exynos_sysmmu_probe(struct platform_device *pdev)
+static int __init exynos_sysmmu_probe(struct platform_device *pdev)
 {
-	int i, ret;
-	struct device *dev;
+	int irq, ret;
+	struct device *dev = &pdev->dev;
 	struct sysmmu_drvdata *data;
+	struct resource *res;
 
-	dev = &pdev->dev;
+	data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
 
-	data = kzalloc(sizeof(*data), GFP_KERNEL);
-	if (!data) {
-		dev_dbg(dev, "Not enough memory\n");
-		ret = -ENOMEM;
-		goto err_alloc;
-	}
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	data->sfrbase = devm_ioremap_resource(dev, res);
+	if (IS_ERR(data->sfrbase))
+		return PTR_ERR(data->sfrbase);
 
-	ret = dev_set_drvdata(dev, data);
-	if (ret) {
-		dev_dbg(dev, "Unabled to initialize driver data\n");
-		goto err_init;
+	irq = platform_get_irq(pdev, 0);
+	if (irq <= 0) {
+		dev_err(dev, "Unable to find IRQ resource\n");
+		return irq;
 	}
 
-	data->nsfrs = pdev->num_resources / 2;
-	data->sfrbases = kmalloc(sizeof(*data->sfrbases) * data->nsfrs,
-								GFP_KERNEL);
-	if (data->sfrbases == NULL) {
-		dev_dbg(dev, "Not enough memory\n");
-		ret = -ENOMEM;
-		goto err_init;
-	}
-
-	for (i = 0; i < data->nsfrs; i++) {
-		struct resource *res;
-		res = platform_get_resource(pdev, IORESOURCE_MEM, i);
-		if (!res) {
-			dev_dbg(dev, "Unable to find IOMEM region\n");
-			ret = -ENOENT;
-			goto err_res;
-		}
-
-		data->sfrbases[i] = ioremap(res->start, resource_size(res));
-		if (!data->sfrbases[i]) {
-			dev_dbg(dev, "Unable to map IOMEM @ PA:%#x\n",
-							res->start);
-			ret = -ENOENT;
-			goto err_res;
-		}
+	ret = devm_request_irq(dev, irq, exynos_sysmmu_irq, 0,
+				dev_name(dev), data);
+	if (ret) {
+		dev_err(dev, "Unabled to register handler of irq %d\n", irq);
+		return ret;
 	}
 
-	for (i = 0; i < data->nsfrs; i++) {
-		ret = platform_get_irq(pdev, i);
-		if (ret <= 0) {
-			dev_dbg(dev, "Unable to find IRQ resource\n");
-			goto err_irq;
-		}
-
-		ret = request_irq(ret, exynos_sysmmu_irq, 0,
-					dev_name(dev), data);
+	data->clk = devm_clk_get(dev, "sysmmu");
+	if (IS_ERR(data->clk)) {
+		dev_err(dev, "Failed to get clock!\n");
+		return PTR_ERR(data->clk);
+	} else  {
+		ret = clk_prepare(data->clk);
 		if (ret) {
-			dev_dbg(dev, "Unabled to register interrupt handler\n");
-			goto err_irq;
+			dev_err(dev, "Failed to prepare clk\n");
+			return ret;
 		}
 	}
 
-	if (dev_get_platdata(dev)) {
-		char *deli, *beg;
-		struct sysmmu_platform_data *platdata = dev_get_platdata(dev);
-
-		beg = platdata->clockname;
-
-		for (deli = beg; (*deli != '\0') && (*deli != ','); deli++)
-			/* NOTHING */;
-
-		if (*deli == '\0')
-			deli = NULL;
-		else
-			*deli = '\0';
-
-		data->clk[0] = clk_get(dev, beg);
-		if (IS_ERR(data->clk[0])) {
-			data->clk[0] = NULL;
-			dev_dbg(dev, "No clock descriptor registered\n");
-		}
-
-		if (data->clk[0] && deli) {
-			*deli = ',';
-			data->clk[1] = clk_get(dev, deli + 1);
-			if (IS_ERR(data->clk[1]))
-				data->clk[1] = NULL;
+	data->clk_master = devm_clk_get(dev, "master");
+	if (!IS_ERR(data->clk_master)) {
+		ret = clk_prepare(data->clk_master);
+		if (ret) {
+			clk_unprepare(data->clk);
+			dev_err(dev, "Failed to prepare master's clk\n");
+			return ret;
 		}
-
-		data->dbgname = platdata->dbgname;
 	}
 
 	data->sysmmu = dev;
-	rwlock_init(&data->lock);
-	INIT_LIST_HEAD(&data->node);
+	spin_lock_init(&data->lock);
 
-	__set_fault_handler(data, &default_fault_handler);
+	platform_set_drvdata(pdev, data);
 
-	if (dev->parent)
-		pm_runtime_enable(dev);
+	pm_runtime_enable(dev);
 
-	dev_dbg(dev, "(%s) Initialized\n", data->dbgname);
 	return 0;
-err_irq:
-	while (i-- > 0) {
-		int irq;
-
-		irq = platform_get_irq(pdev, i);
-		free_irq(irq, data);
-	}
-err_res:
-	while (data->nsfrs-- > 0)
-		iounmap(data->sfrbases[data->nsfrs]);
-	kfree(data->sfrbases);
-err_init:
-	kfree(data);
-err_alloc:
-	dev_err(dev, "Failed to initialize\n");
-	return ret;
 }
 
-static struct platform_driver exynos_sysmmu_driver = {
-	.probe		= exynos_sysmmu_probe,
-	.driver		= {
+static const struct of_device_id sysmmu_of_match[] __initconst = {
+	{ .compatible	= "samsung,exynos-sysmmu", },
+	{ },
+};
+
+static struct platform_driver exynos_sysmmu_driver __refdata = {
+	.probe	= exynos_sysmmu_probe,
+	.driver	= {
 		.owner		= THIS_MODULE,
 		.name		= "exynos-sysmmu",
+		.of_match_table	= sysmmu_of_match,
 	}
 };
 
@@ -667,21 +700,32 @@ static inline void pgtable_flush(void *vastart, void *vaend)
 static int exynos_iommu_domain_init(struct iommu_domain *domain)
 {
 	struct exynos_iommu_domain *priv;
+	int i;
 
 	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
 	if (!priv)
 		return -ENOMEM;
 
-	priv->pgtable = (unsigned long *)__get_free_pages(
-						GFP_KERNEL | __GFP_ZERO, 2);
+	priv->pgtable = (sysmmu_pte_t *)__get_free_pages(GFP_KERNEL, 2);
 	if (!priv->pgtable)
 		goto err_pgtable;
 
-	priv->lv2entcnt = (short *)__get_free_pages(
-						GFP_KERNEL | __GFP_ZERO, 1);
+	priv->lv2entcnt = (short *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, 1);
 	if (!priv->lv2entcnt)
 		goto err_counter;
 
+	/* w/a of System MMU v3.3 to prevent caching 1MiB mapping */
+	for (i = 0; i < NUM_LV1ENTRIES; i += 8) {
+		priv->pgtable[i + 0] = ZERO_LV2LINK;
+		priv->pgtable[i + 1] = ZERO_LV2LINK;
+		priv->pgtable[i + 2] = ZERO_LV2LINK;
+		priv->pgtable[i + 3] = ZERO_LV2LINK;
+		priv->pgtable[i + 4] = ZERO_LV2LINK;
+		priv->pgtable[i + 5] = ZERO_LV2LINK;
+		priv->pgtable[i + 6] = ZERO_LV2LINK;
+		priv->pgtable[i + 7] = ZERO_LV2LINK;
+	}
+
 	pgtable_flush(priv->pgtable, priv->pgtable + NUM_LV1ENTRIES);
 
 	spin_lock_init(&priv->lock);
@@ -705,7 +749,7 @@ err_pgtable:
 static void exynos_iommu_domain_destroy(struct iommu_domain *domain)
 {
 	struct exynos_iommu_domain *priv = domain->priv;
-	struct sysmmu_drvdata *data;
+	struct exynos_iommu_owner *owner;
 	unsigned long flags;
 	int i;
 
@@ -713,16 +757,20 @@ static void exynos_iommu_domain_destroy(struct iommu_domain *domain)
 
 	spin_lock_irqsave(&priv->lock, flags);
 
-	list_for_each_entry(data, &priv->clients, node) {
-		while (!exynos_sysmmu_disable(data->dev))
+	list_for_each_entry(owner, &priv->clients, client) {
+		while (!exynos_sysmmu_disable(owner->dev))
 			; /* until System MMU is actually disabled */
 	}
 
+	while (!list_empty(&priv->clients))
+		list_del_init(priv->clients.next);
+
 	spin_unlock_irqrestore(&priv->lock, flags);
 
 	for (i = 0; i < NUM_LV1ENTRIES; i++)
 		if (lv1ent_page(priv->pgtable + i))
-			kfree(__va(lv2table_base(priv->pgtable + i)));
+			kmem_cache_free(lv2table_kmem_cache,
+				phys_to_virt(lv2table_base(priv->pgtable + i)));
 
 	free_pages((unsigned long)priv->pgtable, 2);
 	free_pages((unsigned long)priv->lv2entcnt, 1);
@@ -733,114 +781,134 @@ static void exynos_iommu_domain_destroy(struct iommu_domain *domain)
 static int exynos_iommu_attach_device(struct iommu_domain *domain,
 				   struct device *dev)
 {
-	struct sysmmu_drvdata *data = dev_get_drvdata(dev->archdata.iommu);
+	struct exynos_iommu_owner *owner = dev->archdata.iommu;
 	struct exynos_iommu_domain *priv = domain->priv;
+	phys_addr_t pagetable = virt_to_phys(priv->pgtable);
 	unsigned long flags;
 	int ret;
 
-	ret = pm_runtime_get_sync(data->sysmmu);
-	if (ret < 0)
-		return ret;
-
-	ret = 0;
-
 	spin_lock_irqsave(&priv->lock, flags);
 
-	ret = __exynos_sysmmu_enable(data, __pa(priv->pgtable), domain);
-
+	ret = __exynos_sysmmu_enable(dev, pagetable, domain);
 	if (ret == 0) {
-		/* 'data->node' must not be appeared in priv->clients */
-		BUG_ON(!list_empty(&data->node));
-		data->dev = dev;
-		list_add_tail(&data->node, &priv->clients);
+		list_add_tail(&owner->client, &priv->clients);
+		owner->domain = domain;
 	}
 
 	spin_unlock_irqrestore(&priv->lock, flags);
 
 	if (ret < 0) {
-		dev_err(dev, "%s: Failed to attach IOMMU with pgtable %#lx\n",
-				__func__, __pa(priv->pgtable));
-		pm_runtime_put(data->sysmmu);
-	} else if (ret > 0) {
-		dev_dbg(dev, "%s: IOMMU with pgtable 0x%lx already attached\n",
-					__func__, __pa(priv->pgtable));
-	} else {
-		dev_dbg(dev, "%s: Attached new IOMMU with pgtable 0x%lx\n",
-					__func__, __pa(priv->pgtable));
+		dev_err(dev, "%s: Failed to attach IOMMU with pgtable %pa\n",
+					__func__, &pagetable);
+		return ret;
 	}
 
+	dev_dbg(dev, "%s: Attached IOMMU with pgtable %pa %s\n",
+		__func__, &pagetable, (ret == 0) ? "" : ", again");
+
 	return ret;
 }
 
 static void exynos_iommu_detach_device(struct iommu_domain *domain,
 				    struct device *dev)
 {
-	struct sysmmu_drvdata *data = dev_get_drvdata(dev->archdata.iommu);
+	struct exynos_iommu_owner *owner;
 	struct exynos_iommu_domain *priv = domain->priv;
-	struct list_head *pos;
+	phys_addr_t pagetable = virt_to_phys(priv->pgtable);
 	unsigned long flags;
-	bool found = false;
 
 	spin_lock_irqsave(&priv->lock, flags);
 
-	list_for_each(pos, &priv->clients) {
-		if (list_entry(pos, struct sysmmu_drvdata, node) == data) {
-			found = true;
+	list_for_each_entry(owner, &priv->clients, client) {
+		if (owner == dev->archdata.iommu) {
+			if (exynos_sysmmu_disable(dev)) {
+				list_del_init(&owner->client);
+				owner->domain = NULL;
+			}
 			break;
 		}
 	}
 
-	if (!found)
-		goto finish;
-
-	if (__exynos_sysmmu_disable(data)) {
-		dev_dbg(dev, "%s: Detached IOMMU with pgtable %#lx\n",
-					__func__, __pa(priv->pgtable));
-		list_del_init(&data->node);
-
-	} else {
-		dev_dbg(dev, "%s: Detaching IOMMU with pgtable %#lx delayed",
-					__func__, __pa(priv->pgtable));
-	}
-
-finish:
 	spin_unlock_irqrestore(&priv->lock, flags);
 
-	if (found)
-		pm_runtime_put(data->sysmmu);
+	if (owner == dev->archdata.iommu)
+		dev_dbg(dev, "%s: Detached IOMMU with pgtable %pa\n",
+					__func__, &pagetable);
+	else
+		dev_err(dev, "%s: No IOMMU is attached\n", __func__);
 }
 
-static unsigned long *alloc_lv2entry(unsigned long *sent, unsigned long iova,
-					short *pgcounter)
+static sysmmu_pte_t *alloc_lv2entry(struct exynos_iommu_domain *priv,
+		sysmmu_pte_t *sent, sysmmu_iova_t iova, short *pgcounter)
 {
+	if (lv1ent_section(sent)) {
+		WARN(1, "Trying mapping on %#08x mapped with 1MiB page", iova);
+		return ERR_PTR(-EADDRINUSE);
+	}
+
 	if (lv1ent_fault(sent)) {
-		unsigned long *pent;
+		sysmmu_pte_t *pent;
+		bool need_flush_flpd_cache = lv1ent_zero(sent);
 
-		pent = kzalloc(LV2TABLE_SIZE, GFP_ATOMIC);
-		BUG_ON((unsigned long)pent & (LV2TABLE_SIZE - 1));
+		pent = kmem_cache_zalloc(lv2table_kmem_cache, GFP_ATOMIC);
+		BUG_ON((unsigned int)pent & (LV2TABLE_SIZE - 1));
 		if (!pent)
-			return NULL;
+			return ERR_PTR(-ENOMEM);
 
-		*sent = mk_lv1ent_page(__pa(pent));
+		*sent = mk_lv1ent_page(virt_to_phys(pent));
 		*pgcounter = NUM_LV2ENTRIES;
 		pgtable_flush(pent, pent + NUM_LV2ENTRIES);
 		pgtable_flush(sent, sent + 1);
+
+		/*
+		 * If pretched SLPD is a fault SLPD in zero_l2_table, FLPD cache
+		 * may caches the address of zero_l2_table. This function
+		 * replaces the zero_l2_table with new L2 page table to write
+		 * valid mappings.
+		 * Accessing the valid area may cause page fault since FLPD
+		 * cache may still caches zero_l2_table for the valid area
+		 * instead of new L2 page table that have the mapping
+		 * information of the valid area
+		 * Thus any replacement of zero_l2_table with other valid L2
+		 * page table must involve FLPD cache invalidation for System
+		 * MMU v3.3.
+		 * FLPD cache invalidation is performed with TLB invalidation
+		 * by VPN without blocking. It is safe to invalidate TLB without
+		 * blocking because the target address of TLB invalidation is
+		 * not currently mapped.
+		 */
+		if (need_flush_flpd_cache) {
+			struct exynos_iommu_owner *owner;
+
+			spin_lock(&priv->lock);
+			list_for_each_entry(owner, &priv->clients, client)
+				sysmmu_tlb_invalidate_flpdcache(
+							owner->dev, iova);
+			spin_unlock(&priv->lock);
+		}
 	}
 
 	return page_entry(sent, iova);
 }
 
-static int lv1set_section(unsigned long *sent, phys_addr_t paddr, short *pgcnt)
+static int lv1set_section(struct exynos_iommu_domain *priv,
+			  sysmmu_pte_t *sent, sysmmu_iova_t iova,
+			  phys_addr_t paddr, short *pgcnt)
 {
-	if (lv1ent_section(sent))
+	if (lv1ent_section(sent)) {
+		WARN(1, "Trying mapping on 1MiB@%#08x that is mapped",
+			iova);
 		return -EADDRINUSE;
+	}
 
 	if (lv1ent_page(sent)) {
-		if (*pgcnt != NUM_LV2ENTRIES)
+		if (*pgcnt != NUM_LV2ENTRIES) {
+			WARN(1, "Trying mapping on 1MiB@%#08x that is mapped",
+				iova);
 			return -EADDRINUSE;
+		}
 
-		kfree(page_entry(sent, 0));
-
+		kmem_cache_free(lv2table_kmem_cache, page_entry(sent, 0));
 		*pgcnt = 0;
 	}
 
@@ -848,14 +916,26 @@ static int lv1set_section(unsigned long *sent, phys_addr_t paddr, short *pgcnt)
 
 	pgtable_flush(sent, sent + 1);
 
+	spin_lock(&priv->lock);
+	if (lv1ent_page_zero(sent)) {
+		struct exynos_iommu_owner *owner;
+		/*
+		 * Flushing FLPD cache in System MMU v3.3 that may cache a FLPD
+		 * entry by speculative prefetch of SLPD which has no mapping.
+		 */
+		list_for_each_entry(owner, &priv->clients, client)
+			sysmmu_tlb_invalidate_flpdcache(owner->dev, iova);
+	}
+	spin_unlock(&priv->lock);
+
 	return 0;
 }
 
-static int lv2set_page(unsigned long *pent, phys_addr_t paddr, size_t size,
+static int lv2set_page(sysmmu_pte_t *pent, phys_addr_t paddr, size_t size,
 								short *pgcnt)
 {
 	if (size == SPAGE_SIZE) {
-		if (!lv2ent_fault(pent))
+		if (WARN_ON(!lv2ent_fault(pent)))
 			return -EADDRINUSE;
 
 		*pent = mk_lv2ent_spage(paddr);
@@ -863,9 +943,11 @@ static int lv2set_page(unsigned long *pent, phys_addr_t paddr, size_t size,
 		*pgcnt -= 1;
 	} else { /* size == LPAGE_SIZE */
 		int i;
+
 		for (i = 0; i < SPAGES_PER_LPAGE; i++, pent++) {
-			if (!lv2ent_fault(pent)) {
-				memset(pent, 0, sizeof(*pent) * i);
+			if (WARN_ON(!lv2ent_fault(pent))) {
+				if (i > 0)
+					memset(pent - i, 0, sizeof(*pent) * i);
 				return -EADDRINUSE;
 			}
 
@@ -878,11 +960,38 @@ static int lv2set_page(unsigned long *pent, phys_addr_t paddr, size_t size,
 	return 0;
 }
 
-static int exynos_iommu_map(struct iommu_domain *domain, unsigned long iova,
+/*
+ * *CAUTION* to the I/O virtual memory managers that support exynos-iommu:
+ *
+ * System MMU v3.x have an advanced logic to improve address translation
+ * performance with caching more page table entries by a page table walk.
+ * However, the logic has a bug that caching fault page table entries and System
+ * MMU reports page fault if the cached fault entry is hit even though the fault
+ * entry is updated to a valid entry after the entry is cached.
+ * To prevent caching fault page table entries which may be updated to valid
+ * entries later, the virtual memory manager should care about the w/a about the
+ * problem. The followings describe w/a.
+ *
+ * Any two consecutive I/O virtual address regions must have a hole of 128KiB
+ * in maximum to prevent misbehavior of System MMU 3.x. (w/a of h/w bug)
+ *
+ * Precisely, any start address of I/O virtual region must be aligned by
+ * the following sizes for System MMU v3.1 and v3.2.
+ * System MMU v3.1: 128KiB
+ * System MMU v3.2: 256KiB
+ *
+ * Because System MMU v3.3 caches page table entries more aggressively, it needs
+ * more w/a.
+ * - Any two consecutive I/O virtual regions must be have a hole of larger size
+ *   than or equal size to 128KiB.
+ * - Start address of an I/O virtual region must be aligned by 128KiB.
+ */
+static int exynos_iommu_map(struct iommu_domain *domain, unsigned long l_iova,
 			 phys_addr_t paddr, size_t size, int prot)
 {
 	struct exynos_iommu_domain *priv = domain->priv;
-	unsigned long *entry;
+	sysmmu_pte_t *entry;
+	sysmmu_iova_t iova = (sysmmu_iova_t)l_iova;
 	unsigned long flags;
 	int ret = -ENOMEM;
 
@@ -893,38 +1002,52 @@ static int exynos_iommu_map(struct iommu_domain *domain, unsigned long iova,
 	entry = section_entry(priv->pgtable, iova);
 
 	if (size == SECT_SIZE) {
-		ret = lv1set_section(entry, paddr,
+		ret = lv1set_section(priv, entry, iova, paddr,
 					&priv->lv2entcnt[lv1ent_offset(iova)]);
 	} else {
-		unsigned long *pent;
+		sysmmu_pte_t *pent;
 
-		pent = alloc_lv2entry(entry, iova,
+		pent = alloc_lv2entry(priv, entry, iova,
 					&priv->lv2entcnt[lv1ent_offset(iova)]);
 
-		if (!pent)
-			ret = -ENOMEM;
+		if (IS_ERR(pent))
+			ret = PTR_ERR(pent);
 		else
 			ret = lv2set_page(pent, paddr, size,
 					&priv->lv2entcnt[lv1ent_offset(iova)]);
 	}
 
-	if (ret) {
-		pr_debug("%s: Failed to map iova 0x%lx/0x%x bytes\n",
-							__func__, iova, size);
-	}
+	if (ret)
+		pr_err("%s: Failed(%d) to map %#zx bytes @ %#x\n",
+			__func__, ret, size, iova);
 
 	spin_unlock_irqrestore(&priv->pgtablelock, flags);
 
 	return ret;
 }
 
+static void exynos_iommu_tlb_invalidate_entry(struct exynos_iommu_domain *priv,
+						sysmmu_iova_t iova, size_t size)
+{
+	struct exynos_iommu_owner *owner;
+	unsigned long flags;
+
+	spin_lock_irqsave(&priv->lock, flags);
+
+	list_for_each_entry(owner, &priv->clients, client)
+		sysmmu_tlb_invalidate_entry(owner->dev, iova, size);
+
+	spin_unlock_irqrestore(&priv->lock, flags);
+}
+
 static size_t exynos_iommu_unmap(struct iommu_domain *domain,
-					       unsigned long iova, size_t size)
+					unsigned long l_iova, size_t size)
 {
 	struct exynos_iommu_domain *priv = domain->priv;
-	struct sysmmu_drvdata *data;
+	sysmmu_iova_t iova = (sysmmu_iova_t)l_iova;
+	sysmmu_pte_t *ent;
+	size_t err_pgsize;
 	unsigned long flags;
-	unsigned long *ent;
 
 	BUG_ON(priv->pgtable == NULL);
 
@@ -933,9 +1056,12 @@ static size_t exynos_iommu_unmap(struct iommu_domain *domain,
 	ent = section_entry(priv->pgtable, iova);
 
 	if (lv1ent_section(ent)) {
-		BUG_ON(size < SECT_SIZE);
+		if (WARN_ON(size < SECT_SIZE)) {
+			err_pgsize = SECT_SIZE;
+			goto err;
+		}
 
-		*ent = 0;
+		*ent = ZERO_LV2LINK; /* w/a for h/w bug in Sysmem MMU v3.3 */
 		pgtable_flush(ent, ent + 1);
 		size = SECT_SIZE;
 		goto done;
@@ -959,34 +1085,42 @@ static size_t exynos_iommu_unmap(struct iommu_domain *domain,
 	if (lv2ent_small(ent)) {
 		*ent = 0;
 		size = SPAGE_SIZE;
+		pgtable_flush(ent, ent + 1);
 		priv->lv2entcnt[lv1ent_offset(iova)] += 1;
 		goto done;
 	}
 
 	/* lv1ent_large(ent) == true here */
-	BUG_ON(size < LPAGE_SIZE);
+	if (WARN_ON(size < LPAGE_SIZE)) {
+		err_pgsize = LPAGE_SIZE;
+		goto err;
+	}
 
 	memset(ent, 0, sizeof(*ent) * SPAGES_PER_LPAGE);
+	pgtable_flush(ent, ent + SPAGES_PER_LPAGE);
 
 	size = LPAGE_SIZE;
 	priv->lv2entcnt[lv1ent_offset(iova)] += SPAGES_PER_LPAGE;
 done:
 	spin_unlock_irqrestore(&priv->pgtablelock, flags);
 
-	spin_lock_irqsave(&priv->lock, flags);
-	list_for_each_entry(data, &priv->clients, node)
-		sysmmu_tlb_invalidate_entry(data->dev, iova);
-	spin_unlock_irqrestore(&priv->lock, flags);
-
+	exynos_iommu_tlb_invalidate_entry(priv, iova, size);
 
 	return size;
+err:
+	spin_unlock_irqrestore(&priv->pgtablelock, flags);
+
+	pr_err("%s: Failed: size(%#zx) @ %#x is smaller than page size %#zx\n",
+		__func__, size, iova, err_pgsize);
+
+	return 0;
 }
 
 static phys_addr_t exynos_iommu_iova_to_phys(struct iommu_domain *domain,
 					  dma_addr_t iova)
 {
 	struct exynos_iommu_domain *priv = domain->priv;
-	unsigned long *entry;
+	sysmmu_pte_t *entry;
 	unsigned long flags;
 	phys_addr_t phys = 0;
 
@@ -1010,14 +1144,42 @@ static phys_addr_t exynos_iommu_iova_to_phys(struct iommu_domain *domain,
 	return phys;
 }
 
+static int exynos_iommu_add_device(struct device *dev)
+{
+	struct iommu_group *group;
+	int ret;
+
+	group = iommu_group_get(dev);
+
+	if (!group) {
+		group = iommu_group_alloc();
+		if (IS_ERR(group)) {
+			dev_err(dev, "Failed to allocate IOMMU group\n");
+			return PTR_ERR(group);
+		}
+	}
+
+	ret = iommu_group_add_device(group, dev);
+	iommu_group_put(group);
+
+	return ret;
+}
+
+static void exynos_iommu_remove_device(struct device *dev)
+{
+	iommu_group_remove_device(dev);
+}
+
 static struct iommu_ops exynos_iommu_ops = {
-	.domain_init = &exynos_iommu_domain_init,
-	.domain_destroy = &exynos_iommu_domain_destroy,
-	.attach_dev = &exynos_iommu_attach_device,
-	.detach_dev = &exynos_iommu_detach_device,
-	.map = &exynos_iommu_map,
-	.unmap = &exynos_iommu_unmap,
-	.iova_to_phys = &exynos_iommu_iova_to_phys,
+	.domain_init = exynos_iommu_domain_init,
+	.domain_destroy = exynos_iommu_domain_destroy,
+	.attach_dev = exynos_iommu_attach_device,
+	.detach_dev = exynos_iommu_detach_device,
+	.map = exynos_iommu_map,
+	.unmap = exynos_iommu_unmap,
+	.iova_to_phys = exynos_iommu_iova_to_phys,
+	.add_device = exynos_iommu_add_device,
+	.remove_device = exynos_iommu_remove_device,
 	.pgsize_bitmap = SECT_SIZE | LPAGE_SIZE | SPAGE_SIZE,
 };
 
@@ -1025,11 +1187,41 @@ static int __init exynos_iommu_init(void)
 {
 	int ret;
 
+	lv2table_kmem_cache = kmem_cache_create("exynos-iommu-lv2table",
+				LV2TABLE_SIZE, LV2TABLE_SIZE, 0, NULL);
+	if (!lv2table_kmem_cache) {
+		pr_err("%s: Failed to create kmem cache\n", __func__);
+		return -ENOMEM;
+	}
+
 	ret = platform_driver_register(&exynos_sysmmu_driver);
+	if (ret) {
+		pr_err("%s: Failed to register driver\n", __func__);
+		goto err_reg_driver;
+	}
 
-	if (ret == 0)
-		bus_set_iommu(&platform_bus_type, &exynos_iommu_ops);
+	zero_lv2_table = kmem_cache_zalloc(lv2table_kmem_cache, GFP_KERNEL);
+	if (zero_lv2_table == NULL) {
+		pr_err("%s: Failed to allocate zero level2 page table\n",
+			__func__);
+		ret = -ENOMEM;
+		goto err_zero_lv2;
+	}
 
+	ret = bus_set_iommu(&platform_bus_type, &exynos_iommu_ops);
+	if (ret) {
+		pr_err("%s: Failed to register exynos-iommu driver.\n",
+								__func__);
+		goto err_set_iommu;
+	}
+
+	return 0;
+err_set_iommu:
+	kmem_cache_free(lv2table_kmem_cache, zero_lv2_table);
+err_zero_lv2:
+	platform_driver_unregister(&exynos_sysmmu_driver);
+err_reg_driver:
+	kmem_cache_destroy(lv2table_kmem_cache);
 	return ret;
 }
 subsys_initcall(exynos_iommu_init);