Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Conflicts:
	drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c

Minor conflict between the BCM_CNIC define removal in net-next
and a bug fix added to net.  Based upon a conflict resolution
patch posted by Stephen Rothwell.

Signed-off-by: David S. Miller <davem@davemloft.net>

31 files changed, 432 insertions, 191 deletions

diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c
index 7c04d0d..1b9c22b 100644
--- a/arch/x86/crypto/aesni-intel_glue.c
+++ b/arch/x86/crypto/aesni-intel_glue.c
@@ -515,6 +515,11 @@ static int xts_aesni_setkey(struct crypto_tfm *tfm, const u8 *key,
 }
 
 
+static void aesni_xts_tweak(void *ctx, u8 *out, const u8 *in)
+{
+	aesni_enc(ctx, out, in);
+}
+
 static int xts_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
 		       struct scatterlist *src, unsigned int nbytes)
 {
@@ -525,7 +530,7 @@ static int xts_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
 		.tbuflen = sizeof(buf),
 
 		.tweak_ctx = aes_ctx(ctx->raw_tweak_ctx),
-		.tweak_fn = XTS_TWEAK_CAST(aesni_enc),
+		.tweak_fn = aesni_xts_tweak,
 		.crypt_ctx = aes_ctx(ctx->raw_crypt_ctx),
 		.crypt_fn = lrw_xts_encrypt_callback,
 	};
@@ -550,7 +555,7 @@ static int xts_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
 		.tbuflen = sizeof(buf),
 
 		.tweak_ctx = aes_ctx(ctx->raw_tweak_ctx),
-		.tweak_fn = XTS_TWEAK_CAST(aesni_enc),
+		.tweak_fn = aesni_xts_tweak,
 		.crypt_ctx = aes_ctx(ctx->raw_crypt_ctx),
 		.crypt_fn = lrw_xts_decrypt_callback,
 	};
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index c9dcc18..6e8fdf5 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -35,7 +35,7 @@ extern unsigned long asmlinkage efi_call_phys(void *, ...);
 #define efi_call_virt6(f, a1, a2, a3, a4, a5, a6)	\
 	efi_call_virt(f, a1, a2, a3, a4, a5, a6)
 
-#define efi_ioremap(addr, size, type)		ioremap_cache(addr, size)
+#define efi_ioremap(addr, size, type, attr)	ioremap_cache(addr, size)
 
 #else /* !CONFIG_X86_32 */
 
@@ -89,7 +89,7 @@ extern u64 efi_call6(void *fp, u64 arg1, u64 arg2, u64 arg3,
 		  (u64)(a3), (u64)(a4), (u64)(a5), (u64)(a6))
 
 extern void __iomem *efi_ioremap(unsigned long addr, unsigned long size,
-				 u32 type);
+				 u32 type, u64 attribute);
 
 #endif /* CONFIG_X86_32 */
 
@@ -98,6 +98,8 @@ extern void efi_set_executable(efi_memory_desc_t *md, bool executable);
 extern int efi_memblock_x86_reserve_range(void);
 extern void efi_call_phys_prelog(void);
 extern void efi_call_phys_epilog(void);
+extern void efi_unmap_memmap(void);
+extern void efi_memory_uc(u64 addr, unsigned long size);
 
 #ifndef CONFIG_EFI
 /*
diff --git a/arch/x86/include/asm/xen/hypervisor.h b/arch/x86/include/asm/xen/hypervisor.h
index 66d0fff..125f344 100644
--- a/arch/x86/include/asm/xen/hypervisor.h
+++ b/arch/x86/include/asm/xen/hypervisor.h
@@ -33,7 +33,6 @@
 #ifndef _ASM_X86_XEN_HYPERVISOR_H
 #define _ASM_X86_XEN_HYPERVISOR_H
 
-/* arch/i386/kernel/setup.c */
 extern struct shared_info *HYPERVISOR_shared_info;
 extern struct start_info *xen_start_info;
 
diff --git a/arch/x86/include/asm/xen/interface.h b/arch/x86/include/asm/xen/interface.h
index 6d2f75a..54d52ff 100644
--- a/arch/x86/include/asm/xen/interface.h
+++ b/arch/x86/include/asm/xen/interface.h
@@ -51,14 +51,14 @@
  * with Xen so that on ARM we can have one ABI that works for 32 and 64
  * bit guests. */
 typedef unsigned long xen_pfn_t;
+#define PRI_xen_pfn "lx"
 typedef unsigned long xen_ulong_t;
+#define PRI_xen_ulong "lx"
 /* Guest handles for primitive C types. */
 __DEFINE_GUEST_HANDLE(uchar, unsigned char);
 __DEFINE_GUEST_HANDLE(uint,  unsigned int);
-__DEFINE_GUEST_HANDLE(ulong, unsigned long);
 DEFINE_GUEST_HANDLE(char);
 DEFINE_GUEST_HANDLE(int);
-DEFINE_GUEST_HANDLE(long);
 DEFINE_GUEST_HANDLE(void);
 DEFINE_GUEST_HANDLE(uint64_t);
 DEFINE_GUEST_HANDLE(uint32_t);
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index c265593..1817fa9 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -2257,6 +2257,9 @@ asmlinkage void smp_irq_move_cleanup_interrupt(void)
 			continue;
 
 		cfg = irq_cfg(irq);
+		if (!cfg)
+			continue;
+
 		raw_spin_lock(&desc->lock);
 
 		/*
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index 9a7c90d..93c5451 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -991,7 +991,7 @@ static struct attribute ** __cpuinit amd_l3_attrs(void)
 	if (attrs)
 		return attrs;
 
-	n = sizeof (default_attrs) / sizeof (struct attribute *);
+	n = ARRAY_SIZE(default_attrs);
 
 	if (amd_nb_has_feature(AMD_NB_L3_INDEX_DISABLE))
 		n += 2;
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 29e87d3..46cbf86 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -2209,11 +2209,6 @@ static struct dev_ext_attribute dev_attr_cmci_disabled = {
 	&mce_cmci_disabled
 };
 
-static struct dev_ext_attribute dev_attr_bios_cmci_threshold = {
-	__ATTR(bios_cmci_threshold, 0444, device_show_int, NULL),
-	&mce_bios_cmci_threshold
-};
-
 static struct device_attribute *mce_device_attrs[] = {
 	&dev_attr_tolerant.attr,
 	&dev_attr_check_interval.attr,
@@ -2222,7 +2217,6 @@ static struct device_attribute *mce_device_attrs[] = {
 	&dev_attr_dont_log_ce.attr,
 	&dev_attr_ignore_ce.attr,
 	&dev_attr_cmci_disabled.attr,
-	&dev_attr_bios_cmci_threshold.attr,
 	NULL
 };
 
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index c4e916d..698b6ec 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -576,12 +576,10 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank)
 	int err = 0;
 
 	if (shared_bank[bank]) {
-
 		nb = node_to_amd_nb(amd_get_nb_id(cpu));
-		WARN_ON(!nb);
 
 		/* threshold descriptor already initialized on this node? */
-		if (nb->bank4) {
+		if (nb && nb->bank4) {
 			/* yes, use it */
 			b = nb->bank4;
 			err = kobject_add(b->kobj, &dev->kobj, name);
@@ -615,8 +613,10 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank)
 		atomic_set(&b->cpus, 1);
 
 		/* nb is already initialized, see above */
-		WARN_ON(nb->bank4);
-		nb->bank4 = b;
+		if (nb) {
+			WARN_ON(nb->bank4);
+			nb->bank4 = b;
+		}
 	}
 
 	err = allocate_threshold_blocks(cpu, bank, 0,
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 915b876..4a3374e 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -208,12 +208,14 @@ static bool check_hw_exists(void)
 	}
 
 	/*
-	 * Now write a value and read it back to see if it matches,
-	 * this is needed to detect certain hardware emulators (qemu/kvm)
-	 * that don't trap on the MSR access and always return 0s.
+	 * Read the current value, change it and read it back to see if it
+	 * matches, this is needed to detect certain hardware emulators
+	 * (qemu/kvm) that don't trap on the MSR access and always return 0s.
 	 */
-	val = 0xabcdUL;
 	reg = x86_pmu_event_addr(0);
+	if (rdmsrl_safe(reg, &val))
+		goto msr_fail;
+	val ^= 0xffffUL;
 	ret = wrmsrl_safe(reg, val);
 	ret |= rdmsrl_safe(reg, &val_new);
 	if (ret || val != val_new)
@@ -338,6 +340,9 @@ int x86_setup_perfctr(struct perf_event *event)
 		/* BTS is currently only allowed for user-mode. */
 		if (!attr->exclude_kernel)
 			return -EOPNOTSUPP;
+
+		if (!attr->exclude_guest)
+			return -EOPNOTSUPP;
 	}
 
 	hwc->config |= config;
@@ -380,6 +385,9 @@ int x86_pmu_hw_config(struct perf_event *event)
 	if (event->attr.precise_ip) {
 		int precise = 0;
 
+		if (!event->attr.exclude_guest)
+			return -EOPNOTSUPP;
+
 		/* Support for constant skid */
 		if (x86_pmu.pebs_active && !x86_pmu.pebs_broken) {
 			precise++;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
index 99d96a4..3cf3d97 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -118,22 +118,24 @@ static void snbep_uncore_pci_disable_box(struct intel_uncore_box *box)
 {
 	struct pci_dev *pdev = box->pci_dev;
 	int box_ctl = uncore_pci_box_ctl(box);
-	u32 config;
+	u32 config = 0;
 
-	pci_read_config_dword(pdev, box_ctl, &config);
-	config |= SNBEP_PMON_BOX_CTL_FRZ;
-	pci_write_config_dword(pdev, box_ctl, config);
+	if (!pci_read_config_dword(pdev, box_ctl, &config)) {
+		config |= SNBEP_PMON_BOX_CTL_FRZ;
+		pci_write_config_dword(pdev, box_ctl, config);
+	}
 }
 
 static void snbep_uncore_pci_enable_box(struct intel_uncore_box *box)
 {
 	struct pci_dev *pdev = box->pci_dev;
 	int box_ctl = uncore_pci_box_ctl(box);
-	u32 config;
+	u32 config = 0;
 
-	pci_read_config_dword(pdev, box_ctl, &config);
-	config &= ~SNBEP_PMON_BOX_CTL_FRZ;
-	pci_write_config_dword(pdev, box_ctl, config);
+	if (!pci_read_config_dword(pdev, box_ctl, &config)) {
+		config &= ~SNBEP_PMON_BOX_CTL_FRZ;
+		pci_write_config_dword(pdev, box_ctl, config);
+	}
 }
 
 static void snbep_uncore_pci_enable_event(struct intel_uncore_box *box, struct perf_event *event)
@@ -156,7 +158,7 @@ static u64 snbep_uncore_pci_read_counter(struct intel_uncore_box *box, struct pe
 {
 	struct pci_dev *pdev = box->pci_dev;
 	struct hw_perf_event *hwc = &event->hw;
-	u64 count;
+	u64 count = 0;
 
 	pci_read_config_dword(pdev, hwc->event_base, (u32 *)&count);
 	pci_read_config_dword(pdev, hwc->event_base + 4, (u32 *)&count + 1);
@@ -603,11 +605,12 @@ static struct pci_driver snbep_uncore_pci_driver = {
 /*
  * build pci bus to socket mapping
  */
-static void snbep_pci2phy_map_init(void)
+static int snbep_pci2phy_map_init(void)
 {
 	struct pci_dev *ubox_dev = NULL;
 	int i, bus, nodeid;
-	u32 config;
+	int err = 0;
+	u32 config = 0;
 
 	while (1) {
 		/* find the UBOX device */
@@ -618,10 +621,14 @@ static void snbep_pci2phy_map_init(void)
 			break;
 		bus = ubox_dev->bus->number;
 		/* get the Node ID of the local register */
-		pci_read_config_dword(ubox_dev, 0x40, &config);
+		err = pci_read_config_dword(ubox_dev, 0x40, &config);
+		if (err)
+			break;
 		nodeid = config;
 		/* get the Node ID mapping */
-		pci_read_config_dword(ubox_dev, 0x54, &config);
+		err = pci_read_config_dword(ubox_dev, 0x54, &config);
+		if (err)
+			break;
 		/*
 		 * every three bits in the Node ID mapping register maps
 		 * to a particular node.
@@ -633,7 +640,11 @@ static void snbep_pci2phy_map_init(void)
 			}
 		}
 	};
-	return;
+
+	if (ubox_dev)
+		pci_dev_put(ubox_dev);
+
+	return err ? pcibios_err_to_errno(err) : 0;
 }
 /* end of Sandy Bridge-EP uncore support */
 
@@ -1547,7 +1558,6 @@ void nhmex_rbox_alter_er(struct intel_uncore_box *box, struct perf_event *event)
 {
 	struct hw_perf_event *hwc = &event->hw;
 	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
-	int port;
 
 	/* adjust the main event selector and extra register index */
 	if (reg1->idx % 2) {
@@ -1559,7 +1569,6 @@ void nhmex_rbox_alter_er(struct intel_uncore_box *box, struct perf_event *event)
 	}
 
 	/* adjust extra register config */
-	port = reg1->idx / 6 + box->pmu->pmu_idx * 4;
 	switch (reg1->idx % 6) {
 	case 2:
 		/* shift the 8~15 bits to the 0~7 bits */
@@ -2578,9 +2587,11 @@ static int __init uncore_pci_init(void)
 
 	switch (boot_cpu_data.x86_model) {
 	case 45: /* Sandy Bridge-EP */
+		ret = snbep_pci2phy_map_init();
+		if (ret)
+			return ret;
 		pci_uncores = snbep_pci_uncores;
 		uncore_pci_driver = &snbep_uncore_pci_driver;
-		snbep_pci2phy_map_init();
 		break;
 	default:
 		return 0;
@@ -2926,6 +2937,9 @@ static int __init intel_uncore_init(void)
 	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
 		return -ENODEV;
 
+	if (cpu_has_hypervisor)
+		return -ENODEV;
+
 	ret = uncore_pci_init();
 	if (ret)
 		goto fail;
diff --git a/arch/x86/kernel/cpu/perf_event_knc.c b/arch/x86/kernel/cpu/perf_event_knc.c
index 7c46bfd..4b7731b 100644
--- a/arch/x86/kernel/cpu/perf_event_knc.c
+++ b/arch/x86/kernel/cpu/perf_event_knc.c
@@ -3,6 +3,8 @@
 #include <linux/perf_event.h>
 #include <linux/types.h>
 
+#include <asm/hardirq.h>
+
 #include "perf_event.h"
 
 static const u64 knc_perfmon_event_map[] =
@@ -173,30 +175,100 @@ static void knc_pmu_enable_all(int added)
 static inline void
 knc_pmu_disable_event(struct perf_event *event)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 	u64 val;
 
 	val = hwc->config;
-	if (cpuc->enabled)
-		val &= ~ARCH_PERFMON_EVENTSEL_ENABLE;
+	val &= ~ARCH_PERFMON_EVENTSEL_ENABLE;
 
 	(void)wrmsrl_safe(hwc->config_base + hwc->idx, val);
 }
 
 static void knc_pmu_enable_event(struct perf_event *event)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 	u64 val;
 
 	val = hwc->config;
-	if (cpuc->enabled)
-		val |= ARCH_PERFMON_EVENTSEL_ENABLE;
+	val |= ARCH_PERFMON_EVENTSEL_ENABLE;
 
 	(void)wrmsrl_safe(hwc->config_base + hwc->idx, val);
 }
 
+static inline u64 knc_pmu_get_status(void)
+{
+	u64 status;
+
+	rdmsrl(MSR_KNC_IA32_PERF_GLOBAL_STATUS, status);
+
+	return status;
+}
+
+static inline void knc_pmu_ack_status(u64 ack)
+{
+	wrmsrl(MSR_KNC_IA32_PERF_GLOBAL_OVF_CONTROL, ack);
+}
+
+static int knc_pmu_handle_irq(struct pt_regs *regs)
+{
+	struct perf_sample_data data;
+	struct cpu_hw_events *cpuc;
+	int handled = 0;
+	int bit, loops;
+	u64 status;
+
+	cpuc = &__get_cpu_var(cpu_hw_events);
+
+	knc_pmu_disable_all();
+
+	status = knc_pmu_get_status();
+	if (!status) {
+		knc_pmu_enable_all(0);
+		return handled;
+	}
+
+	loops = 0;
+again:
+	knc_pmu_ack_status(status);
+	if (++loops > 100) {
+		WARN_ONCE(1, "perf: irq loop stuck!\n");
+		perf_event_print_debug();
+		goto done;
+	}
+
+	inc_irq_stat(apic_perf_irqs);
+
+	for_each_set_bit(bit, (unsigned long *)&status, X86_PMC_IDX_MAX) {
+		struct perf_event *event = cpuc->events[bit];
+
+		handled++;
+
+		if (!test_bit(bit, cpuc->active_mask))
+			continue;
+
+		if (!intel_pmu_save_and_restart(event))
+			continue;
+
+		perf_sample_data_init(&data, 0, event->hw.last_period);
+
+		if (perf_event_overflow(event, &data, regs))
+			x86_pmu_stop(event, 0);
+	}
+
+	/*
+	 * Repeat if there is more work to be done:
+	 */
+	status = knc_pmu_get_status();
+	if (status)
+		goto again;
+
+done:
+	knc_pmu_enable_all(0);
+
+	return handled;
+}
+
+
 PMU_FORMAT_ATTR(event,	"config:0-7"	);
 PMU_FORMAT_ATTR(umask,	"config:8-15"	);
 PMU_FORMAT_ATTR(edge,	"config:18"	);
@@ -214,7 +286,7 @@ static struct attribute *intel_knc_formats_attr[] = {
 
 static __initconst struct x86_pmu knc_pmu = {
 	.name			= "knc",
-	.handle_irq		= x86_pmu_handle_irq,
+	.handle_irq		= knc_pmu_handle_irq,
 	.disable_all		= knc_pmu_disable_all,
 	.enable_all		= knc_pmu_enable_all,
 	.enable			= knc_pmu_enable_event,
@@ -226,12 +298,11 @@ static __initconst struct x86_pmu knc_pmu = {
 	.event_map		= knc_pmu_event_map,
 	.max_events             = ARRAY_SIZE(knc_perfmon_event_map),
 	.apic			= 1,
-	.max_period		= (1ULL << 31) - 1,
+	.max_period		= (1ULL << 39) - 1,
 	.version		= 0,
 	.num_counters		= 2,
-	/* in theory 40 bits, early silicon is buggy though */
-	.cntval_bits		= 32,
-	.cntval_mask		= (1ULL << 32) - 1,
+	.cntval_bits		= 40,
+	.cntval_mask		= (1ULL << 40) - 1,
 	.get_event_constraints	= x86_get_event_constraints,
 	.event_constraints	= knc_event_constraints,
 	.format_attrs		= intel_knc_formats_attr,
diff --git a/arch/x86/kernel/cpu/perf_event_p6.c b/arch/x86/kernel/cpu/perf_event_p6.c
index e4dd0f7..7d0270b 100644
--- a/arch/x86/kernel/cpu/perf_event_p6.c
+++ b/arch/x86/kernel/cpu/perf_event_p6.c
@@ -8,13 +8,106 @@
  */
 static const u64 p6_perfmon_event_map[] =
 {
-  [PERF_COUNT_HW_CPU_CYCLES]		= 0x0079,
-  [PERF_COUNT_HW_INSTRUCTIONS]		= 0x00c0,
-  [PERF_COUNT_HW_CACHE_REFERENCES]	= 0x0f2e,
-  [PERF_COUNT_HW_CACHE_MISSES]		= 0x012e,
-  [PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= 0x00c4,
-  [PERF_COUNT_HW_BRANCH_MISSES]		= 0x00c5,
-  [PERF_COUNT_HW_BUS_CYCLES]		= 0x0062,
+  [PERF_COUNT_HW_CPU_CYCLES]		= 0x0079,	/* CPU_CLK_UNHALTED */
+  [PERF_COUNT_HW_INSTRUCTIONS]		= 0x00c0,	/* INST_RETIRED     */
+  [PERF_COUNT_HW_CACHE_REFERENCES]	= 0x0f2e,	/* L2_RQSTS:M:E:S:I */
+  [PERF_COUNT_HW_CACHE_MISSES]		= 0x012e,	/* L2_RQSTS:I       */
+  [PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= 0x00c4,	/* BR_INST_RETIRED  */
+  [PERF_COUNT_HW_BRANCH_MISSES]		= 0x00c5,	/* BR_MISS_PRED_RETIRED */
+  [PERF_COUNT_HW_BUS_CYCLES]		= 0x0062,	/* BUS_DRDY_CLOCKS  */
+  [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x00a2,	/* RESOURCE_STALLS  */
+
+};
+
+static __initconst u64 p6_hw_cache_event_ids
+				[PERF_COUNT_HW_CACHE_MAX]
+				[PERF_COUNT_HW_CACHE_OP_MAX]
+				[PERF_COUNT_HW_CACHE_RESULT_MAX] =
+{
+ [ C(L1D) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0043,	/* DATA_MEM_REFS       */
+                [ C(RESULT_MISS)   ] = 0x0045,	/* DCU_LINES_IN        */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0,
+		[ C(RESULT_MISS)   ] = 0x0f29,	/* L2_LD:M:E:S:I       */
+	},
+        [ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0,
+		[ C(RESULT_MISS)   ] = 0,
+        },
+ },
+ [ C(L1I ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0080,	/* IFU_IFETCH         */
+		[ C(RESULT_MISS)   ] = 0x0f28,	/* L2_IFETCH:M:E:S:I  */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0,
+		[ C(RESULT_MISS)   ] = 0,
+	},
+ },
+ [ C(LL  ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0,
+		[ C(RESULT_MISS)   ] = 0,
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0,
+		[ C(RESULT_MISS)   ] = 0x0025,	/* L2_M_LINES_INM     */
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0,
+		[ C(RESULT_MISS)   ] = 0,
+	},
+ },
+ [ C(DTLB) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0043,	/* DATA_MEM_REFS      */
+		[ C(RESULT_MISS)   ] = 0,
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0,
+		[ C(RESULT_MISS)   ] = 0,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0,
+		[ C(RESULT_MISS)   ] = 0,
+	},
+ },
+ [ C(ITLB) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0080,	/* IFU_IFETCH         */
+		[ C(RESULT_MISS)   ] = 0x0085,	/* ITLB_MISS          */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+ },
+ [ C(BPU ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x00c4,	/* BR_INST_RETIRED      */
+		[ C(RESULT_MISS)   ] = 0x00c5,	/* BR_MISS_PRED_RETIRED */
+        },
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+ },
 };
 
 static u64 p6_pmu_event_map(int hw_event)
@@ -34,7 +127,7 @@ static struct event_constraint p6_event_constraints[] =
 {
 	INTEL_EVENT_CONSTRAINT(0xc1, 0x1),	/* FLOPS */
 	INTEL_EVENT_CONSTRAINT(0x10, 0x1),	/* FP_COMP_OPS_EXE */
-	INTEL_EVENT_CONSTRAINT(0x11, 0x1),	/* FP_ASSIST */
+	INTEL_EVENT_CONSTRAINT(0x11, 0x2),	/* FP_ASSIST */
 	INTEL_EVENT_CONSTRAINT(0x12, 0x2),	/* MUL */
 	INTEL_EVENT_CONSTRAINT(0x13, 0x2),	/* DIV */
 	INTEL_EVENT_CONSTRAINT(0x14, 0x1),	/* CYCLES_DIV_BUSY */
@@ -64,25 +157,25 @@ static void p6_pmu_enable_all(int added)
 static inline void
 p6_pmu_disable_event(struct perf_event *event)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 	u64 val = P6_NOP_EVENT;
 
-	if (cpuc->enabled)
-		val |= ARCH_PERFMON_EVENTSEL_ENABLE;
-
 	(void)wrmsrl_safe(hwc->config_base, val);
 }
 
 static void p6_pmu_enable_event(struct perf_event *event)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 	u64 val;
 
 	val = hwc->config;
-	if (cpuc->enabled)
-		val |= ARCH_PERFMON_EVENTSEL_ENABLE;
+
+	/*
+	 * p6 only has a global event enable, set on PerfEvtSel0
+	 * We "disable" events by programming P6_NOP_EVENT
+	 * and we rely on p6_pmu_enable_all() being called
+	 * to actually enable the events.
+	 */
 
 	(void)wrmsrl_safe(hwc->config_base, val);
 }
@@ -158,5 +251,9 @@ __init int p6_pmu_init(void)
 
 	x86_pmu = p6_pmu;
 
+	memcpy(hw_cache_event_ids, p6_hw_cache_event_ids,
+		sizeof(hw_cache_event_ids));
+
+
 	return 0;
 }
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index ed858e9..df06ade 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -1077,6 +1077,9 @@ void __init memblock_x86_fill(void)
 		memblock_add(ei->addr, ei->size);
 	}
 
+	/* throw away partial pages */
+	memblock_trim_memory(PAGE_SIZE);
+
 	memblock_dump_all();
 }
 
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index a1193ae..88b725a 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -1035,7 +1035,7 @@ ENTRY(xen_sysenter_target)
 
 ENTRY(xen_hypervisor_callback)
 	CFI_STARTPROC
-	pushl_cfi $0
+	pushl_cfi $-1 /* orig_ax = -1 => not a system call */
 	SAVE_ALL
 	TRACE_IRQS_OFF
 
@@ -1077,14 +1077,16 @@ ENTRY(xen_failsafe_callback)
 2:	mov 8(%esp),%es
 3:	mov 12(%esp),%fs
 4:	mov 16(%esp),%gs
+	/* EAX == 0 => Category 1 (Bad segment)
+	   EAX != 0 => Category 2 (Bad IRET) */
 	testl %eax,%eax
 	popl_cfi %eax
 	lea 16(%esp),%esp
 	CFI_ADJUST_CFA_OFFSET -16
 	jz 5f
 	addl $16,%esp
-	jmp iret_exc		# EAX != 0 => Category 2 (Bad IRET)
-5:	pushl_cfi $0		# EAX == 0 => Category 1 (Bad segment)
+	jmp iret_exc
+5:	pushl_cfi $-1 /* orig_ax = -1 => not a system call */
 	SAVE_ALL
 	jmp ret_from_exception
 	CFI_ENDPROC
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 0c58952..b51b2c7 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -1435,7 +1435,7 @@ ENTRY(xen_failsafe_callback)
 	CFI_RESTORE r11
 	addq $0x30,%rsp
 	CFI_ADJUST_CFA_OFFSET -0x30
-	pushq_cfi $0
+	pushq_cfi $-1 /* orig_ax = -1 => not a system call */
 	SAVE_ALL
 	jmp error_exit
 	CFI_ENDPROC
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index b3e5e51..4180a87 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -247,7 +247,10 @@ do_async_page_fault(struct pt_regs *regs, unsigned long error_code)
 		break;
 	case KVM_PV_REASON_PAGE_NOT_PRESENT:
 		/* page is swapped out by the host. */
+		rcu_irq_enter();
+		exit_idle();
 		kvm_async_pf_task_wait((u32)read_cr2());
+		rcu_irq_exit();
 		break;
 	case KVM_PV_REASON_PAGE_READY:
 		rcu_irq_enter();
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 52190a9..4e8ba39 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -358,14 +358,6 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "VGN-Z540N"),
 		},
 	},
-	{	/* Handle problems with rebooting on CompuLab SBC-FITPC2 */
-		.callback = set_bios_reboot,
-		.ident = "CompuLab SBC-FITPC2",
-		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "CompuLab"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "SBC-FITPC2"),
-		},
-	},
 	{	/* Handle problems with rebooting on ASUS P4S800 */
 		.callback = set_bios_reboot,
 		.ident = "ASUS P4S800",
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index a2bb18e..ca45696 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -920,8 +920,22 @@ void __init setup_arch(char **cmdline_p)
 
 #ifdef CONFIG_X86_64
 	if (max_pfn > max_low_pfn) {
-		max_pfn_mapped = init_memory_mapping(1UL<<32,
-						     max_pfn<<PAGE_SHIFT);
+		int i;
+		unsigned long start, end;
+		unsigned long start_pfn, end_pfn;
+
+		for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn,
+							 NULL) {
+
+			end = PFN_PHYS(end_pfn);
+			if (end <= (1UL<<32))
+				continue;
+
+			start = PFN_PHYS(start_pfn);
+			max_pfn_mapped = init_memory_mapping(
+						max((1UL<<32), start), end);
+		}
+
 		/* can we preseve max_low_pfn ?*/
 		max_low_pfn = max_pfn;
 	}
@@ -1035,6 +1049,18 @@ void __init setup_arch(char **cmdline_p)
 	arch_init_ideal_nops();
 
 	register_refined_jiffies(CLOCK_TICK_RATE);
+
+#ifdef CONFIG_EFI
+	/* Once setup is done above, disable efi_enabled on mismatched
+	 * firmware/kernel archtectures since there is no support for
+	 * runtime services.
+	 */
+	if (efi_enabled && IS_ENABLED(CONFIG_X86_64) != efi_64bit) {
+		pr_info("efi: Setup done, disabling due to 32/64-bit mismatch\n");
+		efi_unmap_memmap();
+		efi_enabled = 0;
+	}
+#endif
 }
 
 #ifdef CONFIG_X86_32
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index 29ad351..70b27ee 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -824,10 +824,8 @@ do_notify_resume(struct pt_regs *regs, void *unused, __u32 thread_info_flags)
 		mce_notify_process();
 #endif /* CONFIG_X86_64 && CONFIG_X86_MCE */
 
-	if (thread_info_flags & _TIF_UPROBE) {
-		clear_thread_flag(TIF_UPROBE);
+	if (thread_info_flags & _TIF_UPROBE)
 		uprobe_notify_resume(regs);
-	}
 
 	/* deal with pending signal delivery */
 	if (thread_info_flags & _TIF_SIGPENDING)
diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c
index 9538f00..aafa555 100644
--- a/arch/x86/kernel/uprobes.c
+++ b/arch/x86/kernel/uprobes.c
@@ -651,31 +651,19 @@ void arch_uprobe_abort_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
 
 /*
  * Skip these instructions as per the currently known x86 ISA.
- * 0x66* { 0x90 | 0x0f 0x1f | 0x0f 0x19 | 0x87 0xc0 }
+ * rep=0x66*; nop=0x90
  */
 static bool __skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs)
 {
 	int i;
 
 	for (i = 0; i < MAX_UINSN_BYTES; i++) {
-		if ((auprobe->insn[i] == 0x66))
+		if (auprobe->insn[i] == 0x66)
 			continue;
 
 		if (auprobe->insn[i] == 0x90)
 			return true;
 
-		if (i == (MAX_UINSN_BYTES - 1))
-			break;
-
-		if ((auprobe->insn[i] == 0x0f) && (auprobe->insn[i+1] == 0x1f))
-			return true;
-
-		if ((auprobe->insn[i] == 0x0f) && (auprobe->insn[i+1] == 0x19))
-			return true;
-
-		if ((auprobe->insn[i] == 0x87) && (auprobe->insn[i+1] == 0xc0))
-			return true;
-
 		break;
 	}
 	return false;
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index c6e6b72..43e9fad 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1311,7 +1311,7 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value)
 	vcpu->arch.apic_base = value;
 	if (apic_x2apic_mode(apic)) {
 		u32 id = kvm_apic_id(apic);
-		u32 ldr = ((id & ~0xf) << 16) | (1 << (id & 0xf));
+		u32 ldr = ((id >> 4) << 16) | (1 << (id & 0xf));
 		kvm_apic_set_ldr(apic, ldr);
 	}
 	apic->base_address = apic->vcpu->arch.apic_base &
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index d289fee..6f85fe0 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -2497,8 +2497,7 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 		}
 	}
 
-	if (!is_error_pfn(pfn))
-		kvm_release_pfn_clean(pfn);
+	kvm_release_pfn_clean(pfn);
 }
 
 static void nonpaging_new_cr3(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 1eefebe..224a7e7 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3779,7 +3779,7 @@ static int write_exit_mmio(struct kvm_vcpu *vcpu, gpa_t gpa,
 {
 	struct kvm_mmio_fragment *frag = &vcpu->mmio_fragments[0];
 
-	memcpy(vcpu->run->mmio.data, frag->data, frag->len);
+	memcpy(vcpu->run->mmio.data, frag->data, min(8u, frag->len));
 	return X86EMUL_CONTINUE;
 }
 
@@ -3832,18 +3832,11 @@ mmio:
 	bytes -= handled;
 	val += handled;
 
-	while (bytes) {
-		unsigned now = min(bytes, 8U);
-
-		frag = &vcpu->mmio_fragments[vcpu->mmio_nr_fragments++];
-		frag->gpa = gpa;
-		frag->data = val;
-		frag->len = now;
-
-		gpa += now;
-		val += now;
-		bytes -= now;
-	}
+	WARN_ON(vcpu->mmio_nr_fragments >= KVM_MAX_MMIO_FRAGMENTS);
+	frag = &vcpu->mmio_fragments[vcpu->mmio_nr_fragments++];
+	frag->gpa = gpa;
+	frag->data = val;
+	frag->len = bytes;
 	return X86EMUL_CONTINUE;
 }
 
@@ -3890,7 +3883,7 @@ int emulator_read_write(struct x86_emulate_ctxt *ctxt, unsigned long addr,
 	vcpu->mmio_needed = 1;
 	vcpu->mmio_cur_fragment = 0;
 
-	vcpu->run->mmio.len = vcpu->mmio_fragments[0].len;
+	vcpu->run->mmio.len = min(8u, vcpu->mmio_fragments[0].len);
 	vcpu->run->mmio.is_write = vcpu->mmio_is_write = ops->write;
 	vcpu->run->exit_reason = KVM_EXIT_MMIO;
 	vcpu->run->mmio.phys_addr = gpa;
@@ -5522,28 +5515,44 @@ static int complete_emulated_pio(struct kvm_vcpu *vcpu)
  *
  * read:
  *   for each fragment
- *     write gpa, len
- *     exit
- *     copy data
+ *     for each mmio piece in the fragment
+ *       write gpa, len
+ *       exit
+ *       copy data
  *   execute insn
  *
  * write:
  *   for each fragment
- *      write gpa, len
- *      copy data
- *      exit
+ *     for each mmio piece in the fragment
+ *       write gpa, len
+ *       copy data
+ *       exit
  */
 static int complete_emulated_mmio(struct kvm_vcpu *vcpu)
 {
 	struct kvm_run *run = vcpu->run;
 	struct kvm_mmio_fragment *frag;
+	unsigned len;
 
 	BUG_ON(!vcpu->mmio_needed);
 
 	/* Complete previous fragment */
-	frag = &vcpu->mmio_fragments[vcpu->mmio_cur_fragment++];
+	frag = &vcpu->mmio_fragments[vcpu->mmio_cur_fragment];
+	len = min(8u, frag->len);
 	if (!vcpu->mmio_is_write)
-		memcpy(frag->data, run->mmio.data, frag->len);
+		memcpy(frag->data, run->mmio.data, len);
+
+	if (frag->len <= 8) {
+		/* Switch to the next fragment. */
+		frag++;
+		vcpu->mmio_cur_fragment++;
+	} else {
+		/* Go forward to the next mmio piece. */
+		frag->data += len;
+		frag->gpa += len;
+		frag->len -= len;
+	}
+
 	if (vcpu->mmio_cur_fragment == vcpu->mmio_nr_fragments) {
 		vcpu->mmio_needed = 0;
 		if (vcpu->mmio_is_write)
@@ -5551,13 +5560,12 @@ static int complete_emulated_mmio(struct kvm_vcpu *vcpu)
 		vcpu->mmio_read_completed = 1;
 		return complete_emulated_io(vcpu);
 	}
-	/* Initiate next fragment */
-	++frag;
+
 	run->exit_reason = KVM_EXIT_MMIO;
 	run->mmio.phys_addr = frag->gpa;
 	if (vcpu->mmio_is_write)
-		memcpy(run->mmio.data, frag->data, frag->len);
-	run->mmio.len = frag->len;
+		memcpy(run->mmio.data, frag->data, min(8u, frag->len));
+	run->mmio.len = min(8u, frag->len);
 	run->mmio.is_write = vcpu->mmio_is_write;
 	vcpu->arch.complete_userspace_io = complete_emulated_mmio;
 	return 0;
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index ab1f6a9..d7aea41 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -35,40 +35,44 @@ struct map_range {
 	unsigned page_size_mask;
 };
 
-static void __init find_early_table_space(struct map_range *mr, unsigned long end,
-					  int use_pse, int use_gbpages)
+/*
+ * First calculate space needed for kernel direct mapping page tables to cover
+ * mr[0].start to mr[nr_range - 1].end, while accounting for possible 2M and 1GB
+ * pages. Then find enough contiguous space for those page tables.
+ */
+static void __init find_early_table_space(struct map_range *mr, int nr_range)
 {
-	unsigned long puds, pmds, ptes, tables, start = 0, good_end = end;
+	int i;
+	unsigned long puds = 0, pmds = 0, ptes = 0, tables;
+	unsigned long start = 0, good_end;
 	phys_addr_t base;
 
-	puds = (end + PUD_SIZE - 1) >> PUD_SHIFT;
-	tables = roundup(puds * sizeof(pud_t), PAGE_SIZE);
-
-	if (use_gbpages) {
-		unsigned long extra;
-
-		extra = end - ((end>>PUD_SHIFT) << PUD_SHIFT);
-		pmds = (extra + PMD_SIZE - 1) >> PMD_SHIFT;
-	} else
-		pmds = (end + PMD_SIZE - 1) >> PMD_SHIFT;
+	for (i = 0; i < nr_range; i++) {
+		unsigned long range, extra;
 
-	tables += roundup(pmds * sizeof(pmd_t), PAGE_SIZE);
+		range = mr[i].end - mr[i].start;
+		puds += (range + PUD_SIZE - 1) >> PUD_SHIFT;
 
-	if (use_pse) {
-		unsigned long extra;
+		if (mr[i].page_size_mask & (1 << PG_LEVEL_1G)) {
+			extra = range - ((range >> PUD_SHIFT) << PUD_SHIFT);
+			pmds += (extra + PMD_SIZE - 1) >> PMD_SHIFT;
+		} else {
+			pmds += (range + PMD_SIZE - 1) >> PMD_SHIFT;
+		}
 
-		extra = end - ((end>>PMD_SHIFT) << PMD_SHIFT);
+		if (mr[i].page_size_mask & (1 << PG_LEVEL_2M)) {
+			extra = range - ((range >> PMD_SHIFT) << PMD_SHIFT);
 #ifdef CONFIG_X86_32
-		extra += PMD_SIZE;
+			extra += PMD_SIZE;
 #endif
-		/* The first 2/4M doesn't use large pages. */
-		if (mr->start < PMD_SIZE)
-			extra += mr->end - mr->start;
-
-		ptes = (extra + PAGE_SIZE - 1) >> PAGE_SHIFT;
-	} else
-		ptes = (end + PAGE_SIZE - 1) >> PAGE_SHIFT;
+			ptes += (extra + PAGE_SIZE - 1) >> PAGE_SHIFT;
+		} else {
+			ptes += (range + PAGE_SIZE - 1) >> PAGE_SHIFT;
+		}
+	}
 
+	tables = roundup(puds * sizeof(pud_t), PAGE_SIZE);
+	tables += roundup(pmds * sizeof(pmd_t), PAGE_SIZE);
 	tables += roundup(ptes * sizeof(pte_t), PAGE_SIZE);
 
 #ifdef CONFIG_X86_32
@@ -86,7 +90,7 @@ static void __init find_early_table_space(struct map_range *mr, unsigned long en
 	pgt_buf_top = pgt_buf_start + (tables >> PAGE_SHIFT);
 
 	printk(KERN_DEBUG "kernel direct mapping tables up to %#lx @ [mem %#010lx-%#010lx]\n",
-		end - 1, pgt_buf_start << PAGE_SHIFT,
+		mr[nr_range - 1].end - 1, pgt_buf_start << PAGE_SHIFT,
 		(pgt_buf_top << PAGE_SHIFT) - 1);
 }
 
@@ -267,7 +271,7 @@ unsigned long __init_refok init_memory_mapping(unsigned long start,
 	 * nodes are discovered.
 	 */
 	if (!after_bootmem)
-		find_early_table_space(&mr[0], end, use_pse, use_gbpages);
+		find_early_table_space(mr, nr_range);
 
 	for (i = 0; i < nr_range; i++)
 		ret = kernel_physical_mapping_init(mr[i].start, mr[i].end,
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 2b6b4a3..3baff25 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -386,7 +386,8 @@ phys_pte_init(pte_t *pte_page, unsigned long addr, unsigned long end,
 		 * these mappings are more intelligent.
 		 */
 		if (pte_val(*pte)) {
-			pages++;
+			if (!after_bootmem)
+				pages++;
 			continue;
 		}
 
@@ -451,6 +452,8 @@ phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end,
 			 * attributes.
 			 */
 			if (page_size_mask & (1 << PG_LEVEL_2M)) {
+				if (!after_bootmem)
+					pages++;
 				last_map_addr = next;
 				continue;
 			}
@@ -526,6 +529,8 @@ phys_pud_init(pud_t *pud_page, unsigned long addr, unsigned long end,
 			 * attributes.
 			 */
 			if (page_size_mask & (1 << PG_LEVEL_1G)) {
+				if (!after_bootmem)
+					pages++;
 				last_map_addr = next;
 				continue;
 			}
diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c
index 26b8a85..48768df 100644
--- a/arch/x86/oprofile/nmi_int.c
+++ b/arch/x86/oprofile/nmi_int.c
@@ -55,7 +55,7 @@ u64 op_x86_get_ctrl(struct op_x86_model_spec const *model,
 	val |= counter_config->extra;
 	event &= model->event_mask ? model->event_mask : 0xFF;
 	val |= event & 0xFF;
-	val |= (event & 0x0F00) << 24;
+	val |= (u64)(event & 0x0F00) << 24;
 
 	return val;
 }
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index aded2a9..ad443914 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -70,11 +70,15 @@ EXPORT_SYMBOL(efi);
 struct efi_memory_map memmap;
 
 bool efi_64bit;
-static bool efi_native;
 
 static struct efi efi_phys __initdata;
 static efi_system_table_t efi_systab __initdata;
 
+static inline bool efi_is_native(void)
+{
+	return IS_ENABLED(CONFIG_X86_64) == efi_64bit;
+}
+
 static int __init setup_noefi(char *arg)
 {
 	efi_enabled = 0;
@@ -420,7 +424,7 @@ void __init efi_reserve_boot_services(void)
 	}
 }
 
-static void __init efi_unmap_memmap(void)
+void __init efi_unmap_memmap(void)
 {
 	if (memmap.map) {
 		early_iounmap(memmap.map, memmap.nr_map * memmap.desc_size);
@@ -432,7 +436,7 @@ void __init efi_free_boot_services(void)
 {
 	void *p;
 
-	if (!efi_native)
+	if (!efi_is_native())
 		return;
 
 	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
@@ -684,12 +688,10 @@ void __init efi_init(void)
 		return;
 	}
 	efi_phys.systab = (efi_system_table_t *)boot_params.efi_info.efi_systab;
-	efi_native = !efi_64bit;
 #else
 	efi_phys.systab = (efi_system_table_t *)
 			  (boot_params.efi_info.efi_systab |
 			  ((__u64)boot_params.efi_info.efi_systab_hi<<32));
-	efi_native = efi_64bit;
 #endif
 
 	if (efi_systab_init(efi_phys.systab)) {
@@ -723,7 +725,7 @@ void __init efi_init(void)
 	 * that doesn't match the kernel 32/64-bit mode.
 	 */
 
-	if (!efi_native)
+	if (!efi_is_native())
 		pr_info("No EFI runtime due to 32/64-bit mismatch with kernel\n");
 	else if (efi_runtime_init()) {
 		efi_enabled = 0;
@@ -735,7 +737,7 @@ void __init efi_init(void)
 		return;
 	}
 #ifdef CONFIG_X86_32
-	if (efi_native) {
+	if (efi_is_native()) {
 		x86_platform.get_wallclock = efi_get_time;
 		x86_platform.set_wallclock = efi_set_rtc_mmss;
 	}
@@ -810,6 +812,16 @@ void __iomem *efi_lookup_mapped_addr(u64 phys_addr)
 	return NULL;
 }
 
+void efi_memory_uc(u64 addr, unsigned long size)
+{
+	unsigned long page_shift = 1UL << EFI_PAGE_SHIFT;
+	u64 npages;
+
+	npages = round_up(size, page_shift) / page_shift;
+	memrange_efi_to_native(&addr, &npages);
+	set_memory_uc(addr, npages);
+}
+
 /*
  * This function will switch the EFI runtime services to virtual mode.
  * Essentially, look through the EFI memmap and map every region that
@@ -823,7 +835,7 @@ void __init efi_enter_virtual_mode(void)
 	efi_memory_desc_t *md, *prev_md = NULL;
 	efi_status_t status;
 	unsigned long size;
-	u64 end, systab, addr, npages, end_pfn;
+	u64 end, systab, end_pfn;
 	void *p, *va, *new_memmap = NULL;
 	int count = 0;
 
@@ -834,7 +846,7 @@ void __init efi_enter_virtual_mode(void)
 	 * non-native EFI
 	 */
 
-	if (!efi_native) {
+	if (!efi_is_native()) {
 		efi_unmap_memmap();
 		return;
 	}
@@ -879,10 +891,14 @@ void __init efi_enter_virtual_mode(void)
 		end_pfn = PFN_UP(end);
 		if (end_pfn <= max_low_pfn_mapped
 		    || (end_pfn > (1UL << (32 - PAGE_SHIFT))
-			&& end_pfn <= max_pfn_mapped))
+			&& end_pfn <= max_pfn_mapped)) {
 			va = __va(md->phys_addr);
-		else
-			va = efi_ioremap(md->phys_addr, size, md->type);
+
+			if (!(md->attribute & EFI_MEMORY_WB))
+				efi_memory_uc((u64)(unsigned long)va, size);
+		} else
+			va = efi_ioremap(md->phys_addr, size,
+					 md->type, md->attribute);
 
 		md->virt_addr = (u64) (unsigned long) va;
 
@@ -892,13 +908,6 @@ void __init efi_enter_virtual_mode(void)
 			continue;
 		}
 
-		if (!(md->attribute & EFI_MEMORY_WB)) {
-			addr = md->virt_addr;
-			npages = md->num_pages;
-			memrange_efi_to_native(&addr, &npages);
-			set_memory_uc(addr, npages);
-		}
-
 		systab = (u64) (unsigned long) efi_phys.systab;
 		if (md->phys_addr <= systab && systab < end) {
 			systab += md->virt_addr - md->phys_addr;
diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index ac3aa54..95fd505 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -82,7 +82,7 @@ void __init efi_call_phys_epilog(void)
 }
 
 void __iomem *__init efi_ioremap(unsigned long phys_addr, unsigned long size,
-				 u32 type)
+				 u32 type, u64 attribute)
 {
 	unsigned long last_map_pfn;
 
@@ -92,8 +92,11 @@ void __iomem *__init efi_ioremap(unsigned long phys_addr, unsigned long size,
 	last_map_pfn = init_memory_mapping(phys_addr, phys_addr + size);
 	if ((last_map_pfn << PAGE_SHIFT) < phys_addr + size) {
 		unsigned long top = last_map_pfn << PAGE_SHIFT;
-		efi_ioremap(top, size - (top - phys_addr), type);
+		efi_ioremap(top, size - (top - phys_addr), type, attribute);
 	}
 
+	if (!(attribute & EFI_MEMORY_WB))
+		efi_memory_uc((u64)(unsigned long)__va(phys_addr), size);
+
 	return (void __iomem *)__va(phys_addr);
 }
diff --git a/arch/x86/realmode/rm/wakeup_asm.S b/arch/x86/realmode/rm/wakeup_asm.S
index e56479e..9e7e147 100644
--- a/arch/x86/realmode/rm/wakeup_asm.S
+++ b/arch/x86/realmode/rm/wakeup_asm.S
@@ -74,18 +74,9 @@ ENTRY(wakeup_start)
 
 	lidtl	wakeup_idt
 
-	/* Clear the EFLAGS but remember if we have EFLAGS.ID */
-	movl $X86_EFLAGS_ID, %ecx
-	pushl %ecx
-	popfl
-	pushfl
-	popl %edi
+	/* Clear the EFLAGS */
 	pushl $0
 	popfl
-	pushfl
-	popl %edx
-	xorl %edx, %edi
-	andl %ecx, %edi		/* %edi is zero iff CPUID & %cr4 are missing */
 
 	/* Check header signature... */
 	movl	signature, %eax
@@ -120,12 +111,12 @@ ENTRY(wakeup_start)
 	movl	%eax, %cr3
 
 	btl	$WAKEUP_BEHAVIOR_RESTORE_CR4, %edi
-	jz	1f
+	jnc	1f
 	movl	pmode_cr4, %eax
 	movl	%eax, %cr4
 1:
 	btl	$WAKEUP_BEHAVIOR_RESTORE_EFER, %edi
-	jz	1f
+	jnc	1f
 	movl	pmode_efer, %eax
 	movl	pmode_efer + 4, %edx
 	movl	$MSR_EFER, %ecx
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index e3497f2..586d838 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -81,8 +81,6 @@
 #include "smp.h"
 #include "multicalls.h"
 
-#include <xen/events.h>
-
 EXPORT_SYMBOL_GPL(hypercall_page);
 
 DEFINE_PER_CPU(struct vcpu_info *, xen_vcpu);
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 6226c99..dcf5f2d 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -1288,6 +1288,25 @@ unsigned long xen_read_cr2_direct(void)
 	return this_cpu_read(xen_vcpu_info.arch.cr2);
 }
 
+void xen_flush_tlb_all(void)
+{
+	struct mmuext_op *op;
+	struct multicall_space mcs;
+
+	trace_xen_mmu_flush_tlb_all(0);
+
+	preempt_disable();
+
+	mcs = xen_mc_entry(sizeof(*op));
+
+	op = mcs.args;
+	op->cmd = MMUEXT_TLB_FLUSH_ALL;
+	MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF);
+
+	xen_mc_issue(PARAVIRT_LAZY_MMU);
+
+	preempt_enable();
+}
 static void xen_flush_tlb(void)
 {
 	struct mmuext_op *op;
@@ -2518,7 +2537,7 @@ int xen_remap_domain_mfn_range(struct vm_area_struct *vma,
 	err = 0;
 out:
 
-	flush_tlb_all();
+	xen_flush_tlb_all();
 
 	return err;
 }