Merge commit 'v3.0' into x86/vdso

35 files changed, 328 insertions, 119 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index c1e41bccdcb..c05810c0d09 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1174,7 +1174,7 @@ comment "NUMA (Summit) requires SMP, 64GB highmem support, ACPI"
 config AMD_NUMA
 	def_bool y
 	prompt "Old style AMD Opteron NUMA detection"
-	depends on NUMA && PCI
+	depends on X86_64 && NUMA && PCI
 	---help---
 	  Enable AMD NUMA node topology detection.  You should say Y here if
 	  you have a multi processor AMD system. This uses an old method to
diff --git a/arch/x86/include/asm/apb_timer.h b/arch/x86/include/asm/apb_timer.h
index 2fefa501d3b..af60d8a2e28 100644
--- a/arch/x86/include/asm/apb_timer.h
+++ b/arch/x86/include/asm/apb_timer.h
@@ -62,7 +62,7 @@ extern int sfi_mtimer_num;
 #else /* CONFIG_APB_TIMER */
 
 static inline unsigned long apbt_quick_calibrate(void) {return 0; }
-static inline void apbt_time_init(void) {return 0; }
+static inline void apbt_time_init(void) { }
 
 #endif
 #endif /* ASM_X86_APBT_H */
diff --git a/arch/x86/include/asm/memblock.h b/arch/x86/include/asm/memblock.h
index 19ae14ba697..0cd3800f33b 100644
--- a/arch/x86/include/asm/memblock.h
+++ b/arch/x86/include/asm/memblock.h
@@ -4,7 +4,6 @@
 #define ARCH_DISCARD_MEMBLOCK
 
 u64 memblock_x86_find_in_range_size(u64 start, u64 *sizep, u64 align);
-void memblock_x86_to_bootmem(u64 start, u64 end);
 
 void memblock_x86_reserve_range(u64 start, u64 end, char *name);
 void memblock_x86_free_range(u64 start, u64 end);
@@ -19,5 +18,6 @@ u64 memblock_x86_hole_size(u64 start, u64 end);
 u64 memblock_x86_find_in_range_node(int nid, u64 start, u64 end, u64 size, u64 align);
 u64 memblock_x86_free_memory_in_range(u64 addr, u64 limit);
 u64 memblock_x86_memory_in_range(u64 addr, u64 limit);
+bool memblock_x86_check_reserved_size(u64 *addrp, u64 *sizep, u64 align);
 
 #endif
diff --git a/arch/x86/include/asm/mmzone_32.h b/arch/x86/include/asm/mmzone_32.h
index 5e83a416eca..ffa037f28d3 100644
--- a/arch/x86/include/asm/mmzone_32.h
+++ b/arch/x86/include/asm/mmzone_32.h
@@ -48,17 +48,6 @@ static inline int pfn_to_nid(unsigned long pfn)
 #endif
 }
 
-/*
- * Following are macros that each numa implmentation must define.
- */
-
-#define node_start_pfn(nid)	(NODE_DATA(nid)->node_start_pfn)
-#define node_end_pfn(nid)						\
-({									\
-	pg_data_t *__pgdat = NODE_DATA(nid);				\
-	__pgdat->node_start_pfn + __pgdat->node_spanned_pages;		\
-})
-
 static inline int pfn_valid(int pfn)
 {
 	int nid = pfn_to_nid(pfn);
@@ -68,6 +57,8 @@ static inline int pfn_valid(int pfn)
 	return 0;
 }
 
+#define early_pfn_valid(pfn)	pfn_valid((pfn))
+
 #endif /* CONFIG_DISCONTIGMEM */
 
 #ifdef CONFIG_NEED_MULTIPLE_NODES
diff --git a/arch/x86/include/asm/mmzone_64.h b/arch/x86/include/asm/mmzone_64.h
index b3f88d7867c..129d9aa3ceb 100644
--- a/arch/x86/include/asm/mmzone_64.h
+++ b/arch/x86/include/asm/mmzone_64.h
@@ -13,8 +13,5 @@ extern struct pglist_data *node_data[];
 
 #define NODE_DATA(nid)		(node_data[nid])
 
-#define node_start_pfn(nid)	(NODE_DATA(nid)->node_start_pfn)
-#define node_end_pfn(nid)       (NODE_DATA(nid)->node_start_pfn +	\
-				 NODE_DATA(nid)->node_spanned_pages)
 #endif
 #endif /* _ASM_X86_MMZONE_64_H */
diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h
index 31d84acc151..a518c0a4504 100644
--- a/arch/x86/include/asm/pvclock.h
+++ b/arch/x86/include/asm/pvclock.h
@@ -22,6 +22,8 @@ static inline u64 pvclock_scale_delta(u64 delta, u32 mul_frac, int shift)
 	u64 product;
 #ifdef __i386__
 	u32 tmp1, tmp2;
+#else
+	ulong tmp;
 #endif
 
 	if (shift < 0)
@@ -42,8 +44,11 @@ static inline u64 pvclock_scale_delta(u64 delta, u32 mul_frac, int shift)
 		: "a" ((u32)delta), "1" ((u32)(delta >> 32)), "2" (mul_frac) );
 #elif defined(__x86_64__)
 	__asm__ (
-		"mul %%rdx ; shrd $32,%%rdx,%%rax"
-		: "=a" (product) : "0" (delta), "d" ((u64)mul_frac) );
+		"mul %[mul_frac] ; shrd $32, %[hi], %[lo]"
+		: [lo]"=a"(product),
+		  [hi]"=d"(tmp)
+		: "0"(delta),
+		  [mul_frac]"rm"((u64)mul_frac));
 #else
 #error implement me!
 #endif
diff --git a/arch/x86/kernel/acpi/realmode/wakeup.S b/arch/x86/kernel/acpi/realmode/wakeup.S
index ead21b66311..b4fd836e405 100644
--- a/arch/x86/kernel/acpi/realmode/wakeup.S
+++ b/arch/x86/kernel/acpi/realmode/wakeup.S
@@ -28,6 +28,8 @@ pmode_cr3:	.long	0	/* Saved %cr3 */
 pmode_cr4:	.long	0	/* Saved %cr4 */
 pmode_efer:	.quad	0	/* Saved EFER */
 pmode_gdt:	.quad	0
+pmode_misc_en:	.quad	0	/* Saved MISC_ENABLE MSR */
+pmode_behavior:	.long	0	/* Wakeup behavior flags */
 realmode_flags:	.long	0
 real_magic:	.long	0
 trampoline_segment:	.word 0
@@ -91,6 +93,18 @@ wakeup_code:
 	/* Call the C code */
 	calll	main
 
+	/* Restore MISC_ENABLE before entering protected mode, in case
+	   BIOS decided to clear XD_DISABLE during S3. */
+	movl	pmode_behavior, %eax
+	btl	$WAKEUP_BEHAVIOR_RESTORE_MISC_ENABLE, %eax
+	jnc	1f
+
+	movl	pmode_misc_en, %eax
+	movl	pmode_misc_en + 4, %edx
+	movl	$MSR_IA32_MISC_ENABLE, %ecx
+	wrmsr
+1:
+
 	/* Do any other stuff... */
 
 #ifndef CONFIG_64BIT
diff --git a/arch/x86/kernel/acpi/realmode/wakeup.h b/arch/x86/kernel/acpi/realmode/wakeup.h
index e1828c07e79..97a29e1430e 100644
--- a/arch/x86/kernel/acpi/realmode/wakeup.h
+++ b/arch/x86/kernel/acpi/realmode/wakeup.h
@@ -21,6 +21,9 @@ struct wakeup_header {
 	u32 pmode_efer_low;	/* Protected mode EFER */
 	u32 pmode_efer_high;
 	u64 pmode_gdt;
+	u32 pmode_misc_en_low;	/* Protected mode MISC_ENABLE */
+	u32 pmode_misc_en_high;
+	u32 pmode_behavior;	/* Wakeup routine behavior flags */
 	u32 realmode_flags;
 	u32 real_magic;
 	u16 trampoline_segment;	/* segment with trampoline code, 64-bit only */
@@ -39,4 +42,7 @@ extern struct wakeup_header wakeup_header;
 #define WAKEUP_HEADER_SIGNATURE 0x51ee1111
 #define WAKEUP_END_SIGNATURE	0x65a22c82
 
+/* Wakeup behavior bits */
+#define WAKEUP_BEHAVIOR_RESTORE_MISC_ENABLE     0
+
 #endif /* ARCH_X86_KERNEL_ACPI_RM_WAKEUP_H */
diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c
index 18a857ba7a2..103b6ab368d 100644
--- a/arch/x86/kernel/acpi/sleep.c
+++ b/arch/x86/kernel/acpi/sleep.c
@@ -77,6 +77,12 @@ int acpi_suspend_lowlevel(void)
 
 	header->pmode_cr0 = read_cr0();
 	header->pmode_cr4 = read_cr4_safe();
+	header->pmode_behavior = 0;
+	if (!rdmsr_safe(MSR_IA32_MISC_ENABLE,
+			&header->pmode_misc_en_low,
+			&header->pmode_misc_en_high))
+		header->pmode_behavior |=
+			(1 << WAKEUP_BEHAVIOR_RESTORE_MISC_ENABLE);
 	header->realmode_flags = acpi_realmode_flags;
 	header->real_magic = 0x12345678;
 
diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c
index cd8cbeb5fa3..7c3a95e54ec 100644
--- a/arch/x86/kernel/amd_iommu.c
+++ b/arch/x86/kernel/amd_iommu.c
@@ -30,6 +30,7 @@
 #include <asm/proto.h>
 #include <asm/iommu.h>
 #include <asm/gart.h>
+#include <asm/dma.h>
 #include <asm/amd_iommu_proto.h>
 #include <asm/amd_iommu_types.h>
 #include <asm/amd_iommu.h>
@@ -154,6 +155,10 @@ static int iommu_init_device(struct device *dev)
 	pdev = pci_get_bus_and_slot(PCI_BUS(alias), alias & 0xff);
 	if (pdev)
 		dev_data->alias = &pdev->dev;
+	else {
+		kfree(dev_data);
+		return -ENOTSUPP;
+	}
 
 	atomic_set(&dev_data->bind, 0);
 
@@ -163,6 +168,20 @@ static int iommu_init_device(struct device *dev)
 	return 0;
 }
 
+static void iommu_ignore_device(struct device *dev)
+{
+	u16 devid, alias;
+
+	devid = get_device_id(dev);
+	alias = amd_iommu_alias_table[devid];
+
+	memset(&amd_iommu_dev_table[devid], 0, sizeof(struct dev_table_entry));
+	memset(&amd_iommu_dev_table[alias], 0, sizeof(struct dev_table_entry));
+
+	amd_iommu_rlookup_table[devid] = NULL;
+	amd_iommu_rlookup_table[alias] = NULL;
+}
+
 static void iommu_uninit_device(struct device *dev)
 {
 	kfree(dev->archdata.iommu);
@@ -192,7 +211,9 @@ int __init amd_iommu_init_devices(void)
 			continue;
 
 		ret = iommu_init_device(&pdev->dev);
-		if (ret)
+		if (ret == -ENOTSUPP)
+			iommu_ignore_device(&pdev->dev);
+		else if (ret)
 			goto out_free;
 	}
 
@@ -2383,6 +2404,23 @@ static struct dma_map_ops amd_iommu_dma_ops = {
 	.dma_supported = amd_iommu_dma_supported,
 };
 
+static unsigned device_dma_ops_init(void)
+{
+	struct pci_dev *pdev = NULL;
+	unsigned unhandled = 0;
+
+	for_each_pci_dev(pdev) {
+		if (!check_device(&pdev->dev)) {
+			unhandled += 1;
+			continue;
+		}
+
+		pdev->dev.archdata.dma_ops = &amd_iommu_dma_ops;
+	}
+
+	return unhandled;
+}
+
 /*
  * The function which clues the AMD IOMMU driver into dma_ops.
  */
@@ -2395,7 +2433,7 @@ void __init amd_iommu_init_api(void)
 int __init amd_iommu_init_dma_ops(void)
 {
 	struct amd_iommu *iommu;
-	int ret;
+	int ret, unhandled;
 
 	/*
 	 * first allocate a default protection domain for every IOMMU we
@@ -2421,7 +2459,11 @@ int __init amd_iommu_init_dma_ops(void)
 	swiotlb = 0;
 
 	/* Make the driver finally visible to the drivers */
-	dma_ops = &amd_iommu_dma_ops;
+	unhandled = device_dma_ops_init();
+	if (unhandled && max_pfn > MAX_DMA32_PFN) {
+		/* There are unhandled devices - initialize swiotlb for them */
+		swiotlb = 1;
+	}
 
 	amd_iommu_stats_init();
 
diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c
index 9179c21120a..bfc8453bd98 100644
--- a/arch/x86/kernel/amd_iommu_init.c
+++ b/arch/x86/kernel/amd_iommu_init.c
@@ -731,8 +731,8 @@ static void __init init_iommu_from_acpi(struct amd_iommu *iommu,
 {
 	u8 *p = (u8 *)h;
 	u8 *end = p, flags = 0;
-	u16 dev_i, devid = 0, devid_start = 0, devid_to = 0;
-	u32 ext_flags = 0;
+	u16 devid = 0, devid_start = 0, devid_to = 0;
+	u32 dev_i, ext_flags = 0;
 	bool alias = false;
 	struct ivhd_entry *e;
 
@@ -887,7 +887,7 @@ static void __init init_iommu_from_acpi(struct amd_iommu *iommu,
 /* Initializes the device->iommu mapping for the driver */
 static int __init init_iommu_devices(struct amd_iommu *iommu)
 {
-	u16 i;
+	u32 i;
 
 	for (i = iommu->first_device; i <= iommu->last_device; ++i)
 		set_iommu_for_device(iommu, i);
@@ -1177,7 +1177,7 @@ static int __init init_memory_definitions(struct acpi_table_header *table)
  */
 static void init_device_table(void)
 {
-	u16 devid;
+	u32 devid;
 
 	for (devid = 0; devid <= amd_iommu_last_bdf; ++devid) {
 		set_dev_entry_bit(devid, DEV_ENTRY_VALID);
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index b961af86bfe..b9338b8cf42 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -390,7 +390,8 @@ static unsigned int reserve_eilvt_offset(int offset, unsigned int new)
 
 /*
  * If mask=1, the LVT entry does not generate interrupts while mask=0
- * enables the vector. See also the BKDGs.
+ * enables the vector. See also the BKDGs. Must be called with
+ * preemption disabled.
  */
 
 int setup_APIC_eilvt(u8 offset, u8 vector, u8 msg_type, u8 mask)
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index b511a011b7d..adc66c3a1fe 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -632,14 +632,14 @@ late_initcall(uv_init_heartbeat);
 
 /* Direct Legacy VGA I/O traffic to designated IOH */
 int uv_set_vga_state(struct pci_dev *pdev, bool decode,
-		      unsigned int command_bits, bool change_bridge)
+		      unsigned int command_bits, u32 flags)
 {
 	int domain, bus, rc;
 
-	PR_DEVEL("devfn %x decode %d cmd %x chg_brdg %d\n",
-			pdev->devfn, decode, command_bits, change_bridge);
+	PR_DEVEL("devfn %x decode %d cmd %x flags %d\n",
+			pdev->devfn, decode, command_bits, flags);
 
-	if (!change_bridge)
+	if (!(flags & PCI_VGA_STATE_CHANGE_BRIDGE))
 		return 0;
 
 	if ((command_bits & PCI_COMMAND_IO) == 0)
diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c
index 690bc846183..9aeb78a23de 100644
--- a/arch/x86/kernel/devicetree.c
+++ b/arch/x86/kernel/devicetree.c
@@ -13,6 +13,7 @@
 #include <linux/slab.h>
 #include <linux/pci.h>
 #include <linux/of_pci.h>
+#include <linux/initrd.h>
 
 #include <asm/hpet.h>
 #include <asm/irq_controller.h>
@@ -98,6 +99,16 @@ void * __init early_init_dt_alloc_memory_arch(u64 size, u64 align)
 	return __alloc_bootmem(size, align, __pa(MAX_DMA_ADDRESS));
 }
 
+#ifdef CONFIG_BLK_DEV_INITRD
+void __init early_init_dt_setup_initrd_arch(unsigned long start,
+					    unsigned long end)
+{
+	initrd_start = (unsigned long)__va(start);
+	initrd_end = (unsigned long)__va(end);
+	initrd_below_start_ok = 1;
+}
+#endif
+
 void __init add_dtb(u64 data)
 {
 	initial_dtb = data + offsetof(struct setup_data, data);
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 2e4928d45a2..e1ba8cb24e4 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -337,7 +337,7 @@ EXPORT_SYMBOL(boot_option_idle_override);
  * Powermanagement idle function, if any..
  */
 void (*pm_idle)(void);
-#if defined(CONFIG_APM_MODULE) && defined(CONFIG_APM_CPU_IDLE)
+#ifdef CONFIG_APM_MODULE
 EXPORT_SYMBOL(pm_idle);
 #endif
 
@@ -399,7 +399,7 @@ void default_idle(void)
 		cpu_relax();
 	}
 }
-#if defined(CONFIG_APM_MODULE) && defined(CONFIG_APM_CPU_IDLE)
+#ifdef CONFIG_APM_MODULE
 EXPORT_SYMBOL(default_idle);
 #endif
 
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 8d128783af4..a3d0dc59067 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -245,7 +245,6 @@ start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp)
 {
 	set_user_gs(regs, 0);
 	regs->fs		= 0;
-	set_fs(USER_DS);
 	regs->ds		= __USER_DS;
 	regs->es		= __USER_DS;
 	regs->ss		= __USER_DS;
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 6c9dd922ac0..ca6f7ab8df3 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -338,7 +338,6 @@ start_thread_common(struct pt_regs *regs, unsigned long new_ip,
 	regs->cs		= _cs;
 	regs->ss		= _ss;
 	regs->flags		= X86_EFLAGS_IF;
-	set_fs(USER_DS);
 	/*
 	 * Free the old FP and other extended state
 	 */
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 0c016f72769..9242436e993 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -294,6 +294,14 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = {
 			DMI_MATCH(DMI_BOARD_NAME, "VersaLogic Menlow board"),
 		},
 	},
+	{ /* Handle reboot issue on Acer Aspire one */
+		.callback = set_bios_reboot,
+		.ident = "Acer Aspire One A110",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "AOA110"),
+		},
+	},
 	{ }
 };
 
@@ -411,6 +419,30 @@ static struct dmi_system_id __initdata pci_reboot_dmi_table[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "iMac9,1"),
 		},
 	},
+	{	/* Handle problems with rebooting on the Latitude E6320. */
+		.callback = set_pci_reboot,
+		.ident = "Dell Latitude E6320",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Latitude E6320"),
+		},
+	},
+	{	/* Handle problems with rebooting on the Latitude E5420. */
+		.callback = set_pci_reboot,
+		.ident = "Dell Latitude E5420",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Latitude E5420"),
+		},
+	},
+	{	/* Handle problems with rebooting on the Latitude E6420. */
+		.callback = set_pci_reboot,
+		.ident = "Dell Latitude E6420",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Latitude E6420"),
+		},
+	},
 	{ }
 };
 
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 33a0c11797d..9fd3137230d 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -285,6 +285,19 @@ notrace static void __cpuinit start_secondary(void *unused)
 	per_cpu(cpu_state, smp_processor_id()) = CPU_ONLINE;
 	x86_platform.nmi_init();
 
+	/*
+	 * Wait until the cpu which brought this one up marked it
+	 * online before enabling interrupts. If we don't do that then
+	 * we can end up waking up the softirq thread before this cpu
+	 * reached the active state, which makes the scheduler unhappy
+	 * and schedule the softirq thread on the wrong cpu. This is
+	 * only observable with forced threaded interrupts, but in
+	 * theory it could also happen w/o them. It's just way harder
+	 * to achieve.
+	 */
+	while (!cpumask_test_cpu(smp_processor_id(), cpu_active_mask))
+		cpu_relax();
+
 	/* enable local interrupts */
 	local_irq_enable();
 
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index d6e2477feb1..adc98675cda 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -47,38 +47,40 @@
 #define DstDI       (5<<1)	/* Destination is in ES:(E)DI */
 #define DstMem64    (6<<1)	/* 64bit memory operand */
 #define DstImmUByte (7<<1)	/* 8-bit unsigned immediate operand */
-#define DstMask     (7<<1)
+#define DstDX       (8<<1)	/* Destination is in DX register */
+#define DstMask     (0xf<<1)
 /* Source operand type. */
-#define SrcNone     (0<<4)	/* No source operand. */
-#define SrcReg      (1<<4)	/* Register operand. */
-#define SrcMem      (2<<4)	/* Memory operand. */
-#define SrcMem16    (3<<4)	/* Memory operand (16-bit). */
-#define SrcMem32    (4<<4)	/* Memory operand (32-bit). */
-#define SrcImm      (5<<4)	/* Immediate operand. */
-#define SrcImmByte  (6<<4)	/* 8-bit sign-extended immediate operand. */
-#define SrcOne      (7<<4)	/* Implied '1' */
-#define SrcImmUByte (8<<4)      /* 8-bit unsigned immediate operand. */
-#define SrcImmU     (9<<4)      /* Immediate operand, unsigned */
-#define SrcSI       (0xa<<4)	/* Source is in the DS:RSI */
-#define SrcImmFAddr (0xb<<4)	/* Source is immediate far address */
-#define SrcMemFAddr (0xc<<4)	/* Source is far address in memory */
-#define SrcAcc      (0xd<<4)	/* Source Accumulator */
-#define SrcImmU16   (0xe<<4)    /* Immediate operand, unsigned, 16 bits */
-#define SrcMask     (0xf<<4)
+#define SrcNone     (0<<5)	/* No source operand. */
+#define SrcReg      (1<<5)	/* Register operand. */
+#define SrcMem      (2<<5)	/* Memory operand. */
+#define SrcMem16    (3<<5)	/* Memory operand (16-bit). */
+#define SrcMem32    (4<<5)	/* Memory operand (32-bit). */
+#define SrcImm      (5<<5)	/* Immediate operand. */
+#define SrcImmByte  (6<<5)	/* 8-bit sign-extended immediate operand. */
+#define SrcOne      (7<<5)	/* Implied '1' */
+#define SrcImmUByte (8<<5)      /* 8-bit unsigned immediate operand. */
+#define SrcImmU     (9<<5)      /* Immediate operand, unsigned */
+#define SrcSI       (0xa<<5)	/* Source is in the DS:RSI */
+#define SrcImmFAddr (0xb<<5)	/* Source is immediate far address */
+#define SrcMemFAddr (0xc<<5)	/* Source is far address in memory */
+#define SrcAcc      (0xd<<5)	/* Source Accumulator */
+#define SrcImmU16   (0xe<<5)    /* Immediate operand, unsigned, 16 bits */
+#define SrcDX       (0xf<<5)	/* Source is in DX register */
+#define SrcMask     (0xf<<5)
 /* Generic ModRM decode. */
-#define ModRM       (1<<8)
+#define ModRM       (1<<9)
 /* Destination is only written; never read. */
-#define Mov         (1<<9)
-#define BitOp       (1<<10)
-#define MemAbs      (1<<11)      /* Memory operand is absolute displacement */
-#define String      (1<<12)     /* String instruction (rep capable) */
-#define Stack       (1<<13)     /* Stack instruction (push/pop) */
-#define GroupMask   (7<<14)     /* Opcode uses one of the group mechanisms */
-#define Group       (1<<14)     /* Bits 3:5 of modrm byte extend opcode */
-#define GroupDual   (2<<14)     /* Alternate decoding of mod == 3 */
-#define Prefix      (3<<14)     /* Instruction varies with 66/f2/f3 prefix */
-#define RMExt       (4<<14)     /* Opcode extension in ModRM r/m if mod == 3 */
-#define Sse         (1<<17)     /* SSE Vector instruction */
+#define Mov         (1<<10)
+#define BitOp       (1<<11)
+#define MemAbs      (1<<12)      /* Memory operand is absolute displacement */
+#define String      (1<<13)     /* String instruction (rep capable) */
+#define Stack       (1<<14)     /* Stack instruction (push/pop) */
+#define GroupMask   (7<<15)     /* Opcode uses one of the group mechanisms */
+#define Group       (1<<15)     /* Bits 3:5 of modrm byte extend opcode */
+#define GroupDual   (2<<15)     /* Alternate decoding of mod == 3 */
+#define Prefix      (3<<15)     /* Instruction varies with 66/f2/f3 prefix */
+#define RMExt       (4<<15)     /* Opcode extension in ModRM r/m if mod == 3 */
+#define Sse         (1<<18)     /* SSE Vector instruction */
 /* Misc flags */
 #define Prot        (1<<21) /* instruction generates #UD if not in prot-mode */
 #define VendorSpecific (1<<22) /* Vendor specific instruction */
@@ -3154,8 +3156,8 @@ static struct opcode opcode_table[256] = {
 	I(DstReg | SrcMem | ModRM | Src2Imm, em_imul_3op),
 	I(SrcImmByte | Mov | Stack, em_push),
 	I(DstReg | SrcMem | ModRM | Src2ImmByte, em_imul_3op),
-	D2bvIP(DstDI | Mov | String, ins, check_perm_in), /* insb, insw/insd */
-	D2bvIP(SrcSI | ImplicitOps | String, outs, check_perm_out), /* outsb, outsw/outsd */
+	D2bvIP(DstDI | SrcDX | Mov | String, ins, check_perm_in), /* insb, insw/insd */
+	D2bvIP(SrcSI | DstDX | String, outs, check_perm_out), /* outsb, outsw/outsd */
 	/* 0x70 - 0x7F */
 	X16(D(SrcImmByte)),
 	/* 0x80 - 0x87 */
@@ -3212,8 +3214,8 @@ static struct opcode opcode_table[256] = {
 	/* 0xE8 - 0xEF */
 	D(SrcImm | Stack), D(SrcImm | ImplicitOps),
 	D(SrcImmFAddr | No64), D(SrcImmByte | ImplicitOps),
-	D2bvIP(SrcNone | DstAcc,     in,  check_perm_in),
-	D2bvIP(SrcAcc | ImplicitOps, out, check_perm_out),
+	D2bvIP(SrcDX | DstAcc, in,  check_perm_in),
+	D2bvIP(SrcAcc | DstDX, out, check_perm_out),
 	/* 0xF0 - 0xF7 */
 	N, DI(ImplicitOps, icebp), N, N,
 	DI(ImplicitOps | Priv, hlt), D(ImplicitOps),
@@ -3370,7 +3372,7 @@ x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len)
 	int def_op_bytes, def_ad_bytes, goffset, simd_prefix;
 	bool op_prefix = false;
 	struct opcode opcode;
-	struct operand memop = { .type = OP_NONE };
+	struct operand memop = { .type = OP_NONE }, *memopp = NULL;
 
 	c->eip = ctxt->eip;
 	c->fetch.start = c->eip;
@@ -3545,9 +3547,6 @@ done_prefixes:
 	if (memop.type == OP_MEM && c->ad_bytes != 8)
 		memop.addr.mem.ea = (u32)memop.addr.mem.ea;
 
-	if (memop.type == OP_MEM && c->rip_relative)
-		memop.addr.mem.ea += c->eip;
-
 	/*
 	 * Decode and fetch the source operand: register, memory
 	 * or immediate.
@@ -3569,6 +3568,7 @@ done_prefixes:
 							   c->op_bytes;
 	srcmem_common:
 		c->src = memop;
+		memopp = &c->src;
 		break;
 	case SrcImmU16:
 		rc = decode_imm(ctxt, &c->src, 2, false);
@@ -3613,6 +3613,12 @@ done_prefixes:
 		memop.bytes = c->op_bytes + 2;
 		goto srcmem_common;
 		break;
+	case SrcDX:
+		c->src.type = OP_REG;
+		c->src.bytes = 2;
+		c->src.addr.reg = &c->regs[VCPU_REGS_RDX];
+		fetch_register_operand(&c->src);
+		break;
 	}
 
 	if (rc != X86EMUL_CONTINUE)
@@ -3659,6 +3665,7 @@ done_prefixes:
 	case DstMem:
 	case DstMem64:
 		c->dst = memop;
+		memopp = &c->dst;
 		if ((c->d & DstMask) == DstMem64)
 			c->dst.bytes = 8;
 		else
@@ -3682,14 +3689,23 @@ done_prefixes:
 		c->dst.addr.mem.seg = VCPU_SREG_ES;
 		c->dst.val = 0;
 		break;
+	case DstDX:
+		c->dst.type = OP_REG;
+		c->dst.bytes = 2;
+		c->dst.addr.reg = &c->regs[VCPU_REGS_RDX];
+		fetch_register_operand(&c->dst);
+		break;
 	case ImplicitOps:
 		/* Special instructions do their own operand decoding. */
 	default:
 		c->dst.type = OP_NONE; /* Disable writeback. */
-		return 0;
+		break;
 	}
 
 done:
+	if (memopp && memopp->type == OP_MEM && c->rip_relative)
+		memopp->addr.mem.ea += c->eip;
+
 	return (rc == X86EMUL_UNHANDLEABLE) ? EMULATION_FAILED : EMULATION_OK;
 }
 
@@ -4027,7 +4043,6 @@ special_insn:
 		break;
 	case 0xec: /* in al,dx */
 	case 0xed: /* in (e/r)ax,dx */
-		c->src.val = c->regs[VCPU_REGS_RDX];
 	do_io_in:
 		if (!pio_in_emulated(ctxt, ops, c->dst.bytes, c->src.val,
 				     &c->dst.val))
@@ -4035,7 +4050,6 @@ special_insn:
 		break;
 	case 0xee: /* out dx,al */
 	case 0xef: /* out dx,(e/r)ax */
-		c->dst.val = c->regs[VCPU_REGS_RDX];
 	do_io_out:
 		ops->pio_out_emulated(ctxt, c->src.bytes, c->dst.val,
 				      &c->src.val, 1);
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index bd14bb4c859..aee38623b76 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -565,7 +565,7 @@ gfn_to_memslot_dirty_bitmap(struct kvm_vcpu *vcpu, gfn_t gfn,
 
 static bool mapping_level_dirty_bitmap(struct kvm_vcpu *vcpu, gfn_t large_gfn)
 {
-	return gfn_to_memslot_dirty_bitmap(vcpu, large_gfn, true);
+	return !gfn_to_memslot_dirty_bitmap(vcpu, large_gfn, true);
 }
 
 static int mapping_level(struct kvm_vcpu *vcpu, gfn_t large_gfn)
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index 6c4dc010c4c..9d03ad4dd5e 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -121,7 +121,7 @@ static int FNAME(walk_addr_generic)(struct guest_walker *walker,
 				    gva_t addr, u32 access)
 {
 	pt_element_t pte;
-	pt_element_t __user *ptep_user;
+	pt_element_t __user *uninitialized_var(ptep_user);
 	gfn_t table_gfn;
 	unsigned index, pt_access, uninitialized_var(pte_access);
 	gpa_t pte_gpa;
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 4c3fa0f6746..d48ec60ea42 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2047,7 +2