iommu/amd: Convert dev_table_entry to u64

Convert the contents of 'struct dev_table_entry' to u64 to
allow updating the DTE wit 64bit writes as required by the
spec.

Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index 4ee277a..661e2bb 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -365,8 +365,8 @@
 {
 	int i;
 
-	for (i = 0; i < 8; ++i)
-		pr_err("AMD-Vi: DTE[%d]: %08x\n", i,
+	for (i = 0; i < 4; ++i)
+		pr_err("AMD-Vi: DTE[%d]: %016llx\n", i,
 			amd_iommu_dev_table[devid].data[i]);
 }
 
@@ -1583,19 +1583,22 @@
 static void set_dte_entry(u16 devid, struct protection_domain *domain, bool ats)
 {
 	u64 pte_root = virt_to_phys(domain->pt_root);
-	u32 flags = 0;
+	u64 flags = 0;
 
 	pte_root |= (domain->mode & DEV_ENTRY_MODE_MASK)
 		    << DEV_ENTRY_MODE_SHIFT;
 	pte_root |= IOMMU_PTE_IR | IOMMU_PTE_IW | IOMMU_PTE_P | IOMMU_PTE_TV;
 
+	flags = amd_iommu_dev_table[devid].data[1];
+
 	if (ats)
 		flags |= DTE_FLAG_IOTLB;
 
-	amd_iommu_dev_table[devid].data[3] |= flags;
-	amd_iommu_dev_table[devid].data[2]  = domain->id;
-	amd_iommu_dev_table[devid].data[1]  = upper_32_bits(pte_root);
-	amd_iommu_dev_table[devid].data[0]  = lower_32_bits(pte_root);
+	flags &= ~(0xffffUL);
+	flags |= domain->id;
+
+	amd_iommu_dev_table[devid].data[1]  = flags;
+	amd_iommu_dev_table[devid].data[0]  = pte_root;
 }
 
 static void clear_dte_entry(u16 devid)
@@ -1603,7 +1606,6 @@
 	/* remove entry from the device table seen by the hardware */
 	amd_iommu_dev_table[devid].data[0] = IOMMU_PTE_P | IOMMU_PTE_TV;
 	amd_iommu_dev_table[devid].data[1] = 0;
-	amd_iommu_dev_table[devid].data[2] = 0;
 
 	amd_iommu_apply_erratum_63(devid);
 }
diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c
index 82d2410..17e0f77 100644
--- a/drivers/iommu/amd_iommu_init.c
+++ b/drivers/iommu/amd_iommu_init.c
@@ -584,18 +584,18 @@
 /* sets a specific bit in the device table entry. */
 static void set_dev_entry_bit(u16 devid, u8 bit)
 {
-	int i = (bit >> 5) & 0x07;
-	int _bit = bit & 0x1f;
+	int i = (bit >> 6) & 0x03;
+	int _bit = bit & 0x3f;
 
-	amd_iommu_dev_table[devid].data[i] |= (1 << _bit);
+	amd_iommu_dev_table[devid].data[i] |= (1UL << _bit);
 }
 
 static int get_dev_entry_bit(u16 devid, u8 bit)
 {
-	int i = (bit >> 5) & 0x07;
-	int _bit = bit & 0x1f;
+	int i = (bit >> 6) & 0x03;
+	int _bit = bit & 0x3f;
 
-	return (amd_iommu_dev_table[devid].data[i] & (1 << _bit)) >> _bit;
+	return (amd_iommu_dev_table[devid].data[i] & (1UL << _bit)) >> _bit;
 }
 
 
diff --git a/drivers/iommu/amd_iommu_types.h b/drivers/iommu/amd_iommu_types.h
index 5b9c507..f8dd9ae 100644
--- a/drivers/iommu/amd_iommu_types.h
+++ b/drivers/iommu/amd_iommu_types.h
@@ -230,7 +230,7 @@
 #define IOMMU_PTE_IR (1ULL << 61)
 #define IOMMU_PTE_IW (1ULL << 62)
 
-#define DTE_FLAG_IOTLB	0x01
+#define DTE_FLAG_IOTLB	(0x01UL << 32)
 
 #define IOMMU_PAGE_MASK (((1ULL << 52) - 1) & ~0xfffULL)
 #define IOMMU_PTE_PRESENT(pte) ((pte) & IOMMU_PTE_P)
@@ -484,7 +484,7 @@
  * Structure defining one entry in the device table
  */
 struct dev_table_entry {
-	u32 data[8];
+	u64 data[4];
 };
 
 /*