Merge branch 'linus' into perf/core

Conflicts:
	tools/perf/Makefile
	tools/perf/builtin-test.c
	tools/perf/perf.h
	tools/perf/tests/parse-events.c
	tools/perf/util/evsel.h

Signed-off-by: Ingo Molnar <mingo@kernel.org>

34 files changed, 548 insertions, 195 deletions

diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c
index c760e073963e..e87b0cac14b5 100644
--- a/arch/x86/boot/compressed/eboot.c
+++ b/arch/x86/boot/compressed/eboot.c
@@ -12,6 +12,8 @@
 #include <asm/setup.h>
 #include <asm/desc.h>
 
+#undef memcpy			/* Use memcpy from misc.c */
+
 #include "eboot.h"
 
 static efi_system_table_t *sys_table;
diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S
index 2a017441b8b2..8c132a625b94 100644
--- a/arch/x86/boot/header.S
+++ b/arch/x86/boot/header.S
@@ -476,6 +476,3 @@ die:
 setup_corrupt:
 	.byte	7
 	.string	"No setup signature found...\n"
-
-	.data
-dummy:	.long	0
diff --git a/arch/x86/include/asm/Kbuild b/arch/x86/include/asm/Kbuild
index 66e5f0ef0523..79fd8a3418f9 100644
--- a/arch/x86/include/asm/Kbuild
+++ b/arch/x86/include/asm/Kbuild
@@ -12,6 +12,7 @@ header-y += mce.h
 header-y += msr-index.h
 header-y += msr.h
 header-y += mtrr.h
+header-y += perf_regs.h
 header-y += posix_types_32.h
 header-y += posix_types_64.h
 header-y += posix_types_x32.h
@@ -19,8 +20,10 @@ header-y += prctl.h
 header-y += processor-flags.h
 header-y += ptrace-abi.h
 header-y += sigcontext32.h
+header-y += svm.h
 header-y += ucontext.h
 header-y += vm86.h
+header-y += vmx.h
 header-y += vsyscall.h
 
 genhdr-y += unistd_32.h
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index c9dcc181d4d1..6e8fdf5ad113 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/fpu-internal.h b/arch/x86/include/asm/fpu-internal.h
index 831dbb9c6c02..41ab26ea6564 100644
--- a/arch/x86/include/asm/fpu-internal.h
+++ b/arch/x86/include/asm/fpu-internal.h
@@ -399,14 +399,17 @@ static inline void drop_init_fpu(struct task_struct *tsk)
 typedef struct { int preload; } fpu_switch_t;
 
 /*
- * FIXME! We could do a totally lazy restore, but we need to
- * add a per-cpu "this was the task that last touched the FPU
- * on this CPU" variable, and the task needs to have a "I last
- * touched the FPU on this CPU" and check them.
+ * Must be run with preemption disabled: this clears the fpu_owner_task,
+ * on this CPU.
  *
- * We don't do that yet, so "fpu_lazy_restore()" always returns
- * false, but some day..
+ * This will disable any lazy FPU state restore of the current FPU state,
+ * but if the current thread owns the FPU, it will still be saved by.
  */
+static inline void __cpu_disable_lazy_restore(unsigned int cpu)
+{
+	per_cpu(fpu_owner_task, cpu) = NULL;
+}
+
 static inline int fpu_lazy_restore(struct task_struct *new, unsigned int cpu)
 {
 	return new == this_cpu_read_stable(fpu_owner_task) &&
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index dcfde52979c3..19f16ebaf4fa 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -205,21 +205,14 @@ static inline bool user_64bit_mode(struct pt_regs *regs)
 }
 #endif
 
-/*
- * X86_32 CPUs don't save ss and esp if the CPU is already in kernel mode
- * when it traps.  The previous stack will be directly underneath the saved
- * registers, and 'sp/ss' won't even have been saved. Thus the '&regs->sp'.
- *
- * This is valid only for kernel mode traps.
- */
-static inline unsigned long kernel_stack_pointer(struct pt_regs *regs)
-{
 #ifdef CONFIG_X86_32
-	return (unsigned long)(&regs->sp);
+extern unsigned long kernel_stack_pointer(struct pt_regs *regs);
 #else
+static inline unsigned long kernel_stack_pointer(struct pt_regs *regs)
+{
 	return regs->sp;
-#endif
 }
+#endif
 
 #define GET_IP(regs) ((regs)->ip)
 #define GET_FP(regs) ((regs)->bp)
diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h
index 59c226d120cd..c20d1ce62dc6 100644
--- a/arch/x86/include/asm/xen/hypercall.h
+++ b/arch/x86/include/asm/xen/hypercall.h
@@ -359,18 +359,14 @@ HYPERVISOR_update_va_mapping(unsigned long va, pte_t new_val,
 		return _hypercall4(int, update_va_mapping, va,
 				   new_val.pte, new_val.pte >> 32, flags);
 }
+extern int __must_check xen_event_channel_op_compat(int, void *);
 
 static inline int
 HYPERVISOR_event_channel_op(int cmd, void *arg)
 {
 	int rc = _hypercall2(int, event_channel_op, cmd, arg);
-	if (unlikely(rc == -ENOSYS)) {
-		struct evtchn_op op;
-		op.cmd = cmd;
-		memcpy(&op.u, arg, sizeof(op.u));
-		rc = _hypercall1(int, event_channel_op_compat, &op);
-		memcpy(arg, &op.u, sizeof(op.u));
-	}
+	if (unlikely(rc == -ENOSYS))
+		rc = xen_event_channel_op_compat(cmd, arg);
 	return rc;
 }
 
@@ -386,17 +382,14 @@ HYPERVISOR_console_io(int cmd, int count, char *str)
 	return _hypercall3(int, console_io, cmd, count, str);
 }
 
+extern int __must_check HYPERVISOR_physdev_op_compat(int, void *);
+
 static inline int
 HYPERVISOR_physdev_op(int cmd, void *arg)
 {
 	int rc = _hypercall2(int, physdev_op, cmd, arg);
-	if (unlikely(rc == -ENOSYS)) {
-		struct physdev_op op;
-		op.cmd = cmd;
-		memcpy(&op.u, arg, sizeof(op.u));
-		rc = _hypercall1(int, physdev_op_compat, &op);
-		memcpy(arg, &op.u, sizeof(op.u));
-	}
+	if (unlikely(rc == -ENOSYS))
+		rc = HYPERVISOR_physdev_op_compat(cmd, arg);
 	return rc;
 }
 
diff --git a/arch/x86/include/asm/xen/hypervisor.h b/arch/x86/include/asm/xen/hypervisor.h
index 66d0fff1ee84..125f344f06a9 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/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index c265593ec2cd..1817fa911024 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/amd.c b/arch/x86/kernel/cpu/amd.c
index f7e98a2c0d12..1b7d1656a042 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -631,6 +631,20 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
 		}
 	}
 
+	/*
+	 * The way access filter has a performance penalty on some workloads.
+	 * Disable it on the affected CPUs.
+	 */
+	if ((c->x86 == 0x15) &&
+	    (c->x86_model >= 0x02) && (c->x86_model < 0x20)) {
+		u64 val;
+
+		if (!rdmsrl_safe(0xc0011021, &val) && !(val & 0x1E)) {
+			val |= 0x1E;
+			wrmsrl_safe(0xc0011021, val);
+		}
+	}
+
 	cpu_detect_cache_sizes(c);
 
 	/* Multi core CPU? */
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index 698b6ec12e0f..1ac581f38dfa 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -6,7 +6,7 @@
  *
  *  Written by Jacob Shin - AMD, Inc.
  *
- *  Support: borislav.petkov@amd.com
+ *  Maintained by: Borislav Petkov <bp@alien8.de>
  *
  *  April 2006
  *     - added support for AMD Family 0x10 processors
diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c
index 5f88abf07e9c..4f9a3cbfc4a3 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_intel.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c
@@ -285,34 +285,39 @@ void cmci_clear(void)
 	raw_spin_unlock_irqrestore(&cmci_discover_lock, flags);
 }
 
+static long cmci_rediscover_work_func(void *arg)
+{
+	int banks;
+
+	/* Recheck banks in case CPUs don't all have the same */
+	if (cmci_supported(&banks))
+		cmci_discover(banks);
+
+	return 0;
+}
+
 /*
  * After a CPU went down cycle through all the others and rediscover
  * Must run in process context.
  */
 void cmci_rediscover(int dying)
 {
-	int banks;
-	int cpu;
-	cpumask_var_t old;
+	int cpu, banks;
 
 	if (!cmci_supported(&banks))
 		return;
-	if (!alloc_cpumask_var(&old, GFP_KERNEL))
-		return;
-	cpumask_copy(old, &current->cpus_allowed);
 
 	for_each_online_cpu(cpu) {
 		if (cpu == dying)
 			continue;
-		if (set_cpus_allowed_ptr(current, cpumask_of(cpu)))
+
+		if (cpu == smp_processor_id()) {
+			cmci_rediscover_work_func(NULL);
 			continue;
-		/* Recheck banks in case CPUs don't all have the same */
-		if (cmci_supported(&banks))
-			cmci_discover(banks);
-	}
+		}
 
-	set_cpus_allowed_ptr(current, old);
-	free_cpumask_var(old);
+		work_on_cpu(cpu, cmci_rediscover_work_func, NULL);
+	}
 }
 
 /*
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
index 5df8d32ba91e..3cf3d97cce3a 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;
diff --git a/arch/x86/kernel/cpu/perf_event_knc.c b/arch/x86/kernel/cpu/perf_event_knc.c
index 7c46bfdbc373..4b7731bf23a8 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 900b76b5d6ef..f2af39f5dc3d 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);
 }
@@ -160,5 +253,9 @@ __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 ed858e9e9a74..df06ade26bef 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_64.S b/arch/x86/kernel/entry_64.S
index b51b2c7ee51f..1328fe49a3f1 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -995,8 +995,8 @@ END(interrupt)
 	 */
 	.p2align CONFIG_X86_L1_CACHE_SHIFT
 common_interrupt:
-	ASM_CLAC
 	XCPT_FRAME
+	ASM_CLAC
 	addq $-0x80,(%rsp)		/* Adjust vector to [-256,-1] range */
 	interrupt do_IRQ
 	/* 0(%rsp): old_rsp-ARGOFFSET */
@@ -1135,8 +1135,8 @@ END(common_interrupt)
  */
 .macro apicinterrupt num sym do_sym
 ENTRY(\sym)
-	ASM_CLAC
 	INTR_FRAME
+	ASM_CLAC
 	pushq_cfi $~(\num)
 .Lcommon_\sym:
 	interrupt \do_sym
@@ -1190,8 +1190,8 @@ apicinterrupt IRQ_WORK_VECTOR \
  */
 .macro zeroentry sym do_sym
 ENTRY(\sym)
-	ASM_CLAC
 	INTR_FRAME
+	ASM_CLAC
 	PARAVIRT_ADJUST_EXCEPTION_FRAME
 	pushq_cfi $-1		/* ORIG_RAX: no syscall to restart */
 	subq $ORIG_RAX-R15, %rsp
@@ -1208,8 +1208,8 @@ END(\sym)
 
 .macro paranoidzeroentry sym do_sym
 ENTRY(\sym)
-	ASM_CLAC
 	INTR_FRAME
+	ASM_CLAC
 	PARAVIRT_ADJUST_EXCEPTION_FRAME
 	pushq_cfi $-1		/* ORIG_RAX: no syscall to restart */
 	subq $ORIG_RAX-R15, %rsp
@@ -1227,8 +1227,8 @@ END(\sym)
 #define INIT_TSS_IST(x) PER_CPU_VAR(init_tss) + (TSS_ist + ((x) - 1) * 8)
 .macro paranoidzeroentry_ist sym do_sym ist
 ENTRY(\sym)
-	ASM_CLAC
 	INTR_FRAME
+	ASM_CLAC
 	PARAVIRT_ADJUST_EXCEPTION_FRAME
 	pushq_cfi $-1		/* ORIG_RAX: no syscall to restart */
 	subq $ORIG_RAX-R15, %rsp
@@ -1247,8 +1247,8 @@ END(\sym)
 
 .macro errorentry sym do_sym
 ENTRY(\sym)
-	ASM_CLAC
 	XCPT_FRAME
+	ASM_CLAC
 	PARAVIRT_ADJUST_EXCEPTION_FRAME
 	subq $ORIG_RAX-R15, %rsp
 	CFI_ADJUST_CFA_OFFSET ORIG_RAX-R15
@@ -1266,8 +1266,8 @@ END(\sym)
 	/* error code is on the stack already */
 .macro paranoiderrorentry sym do_sym
 ENTRY(\sym)
-	ASM_CLAC
 	XCPT_FRAME
+	ASM_CLAC
 	PARAVIRT_ADJUST_EXCEPTION_FRAME
 	subq $ORIG_RAX-R15, %rsp
 	CFI_ADJUST_CFA_OFFSET ORIG_RAX-R15
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index 957a47aec64e..4dac2f68ed4a 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -292,8 +292,8 @@ default_entry:
  *	be using the global pages. 
  *
  *	NOTE! If we are on a 486 we may have no cr4 at all!
- *	Specifically, cr4 exists if and only if CPUID exists,
- *	which in turn exists if and only if EFLAGS.ID exists.
+ *	Specifically, cr4 exists if and only if CPUID exists
+ *	and has flags other than the FPU flag set.
  */
 	movl $X86_EFLAGS_ID,%ecx
 	pushl %ecx
@@ -308,6 +308,11 @@ default_entry:
 	testl %ecx,%eax
 	jz 6f			# No ID flag = no CPUID = no CR4
 
+	movl $1,%eax
+	cpuid
+	andl $~1,%edx		# Ignore CPUID.FPU
+	jz 6f			# No flags or only CPUID.FPU = no CR4
+
 	movl pa(mmu_cr4_features),%eax
 	movl %eax,%cr4
 
diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c
index 7720ff5a9ee2..efdec7cd8e01 100644
--- a/arch/x86/kernel/microcode_amd.c
+++ b/arch/x86/kernel/microcode_amd.c
@@ -8,8 +8,8 @@
  *  Tigran Aivazian <tigran@aivazian.fsnet.co.uk>
  *
  *  Maintainers:
- *  Andreas Herrmann <andreas.herrmann3@amd.com>
- *  Borislav Petkov <borislav.petkov@amd.com>
+ *  Andreas Herrmann <herrmann.der.user@googlemail.com>
+ *  Borislav Petkov <bp@alien8.de>
  *
  *  This driver allows to upgrade microcode on F10h AMD
  *  CPUs and later.
@@ -190,6 +190,7 @@ static unsigned int verify_patch_size(int cpu, u32 patch_size,
 #define F1XH_MPB_MAX_SIZE 2048
 #define F14H_MPB_MAX_SIZE 1824
 #define F15H_MPB_MAX_SIZE 4096
+#define F16H_MPB_MAX_SIZE 3458
 
 	switch (c->x86) {
 	case 0x14:
@@ -198,6 +199,9 @@ static unsigned int verify_patch_size(int cpu, u32 patch_size,
 	case 0x15:
 		max_size = F15H_MPB_MAX_SIZE;
 		break;
+	case 0x16:
+		max_size = F16H_MPB_MAX_SIZE;
+		break;
 	default:
 		max_size = F1XH_MPB_MAX_SIZE;
 		break;
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index b00b33a18390..974b67e46dd0 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -22,6 +22,7 @@
 #include <linux/perf_event.h>
 #include <linux/hw_breakpoint.h>
 #include <linux/rcupdate.h>
+#include <linux/module.h>
 
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
@@ -166,6 +167,35 @@ static inline bool invalid_selector(u16 value)
 
 #define FLAG_MASK		FLAG_MASK_32
 
+/*
+ * X86_32 CPUs don't save ss and esp if the CPU is already in kernel mode
+ * when it traps.  The previous stack will be directly underneath the saved
+ * registers, and 'sp/ss' won't even have been saved. Thus the '&regs->sp'.
+ *
+ * Now, if the stack is empty, '&regs->sp' is out of range. In this
+ * case we try to take the previous stack. To always return a non-null
+ * stack pointer we fall back to regs as stack if no previous stack
+ * exists.
+ *
+ * This is valid only for kernel mode traps.
+ */
+unsigned long kernel_stack_pointer(struct pt_regs *regs)
+{
+	unsigned long context = (unsigned long)regs & ~(THREAD_SIZE - 1);
+	unsigned long sp = (unsigned long)&regs->sp;
+	struct thread_info *tinfo;
+
+	if (context == (sp & ~(THREAD_SIZE - 1)))
+		return sp;
+
+	tinfo = (struct thread_info *)context;
+	if (tinfo->previous_esp)
+		return tinfo->previous_esp;
+
+	return (unsigned long)regs;
+}
+EXPORT_SYMBOL_GPL(kernel_stack_pointer);
+
 static unsigned long *pt_regs_access(struct pt_regs *regs, unsigned long regno)
 {
 	BUILD_BUG_ON(offsetof(struct pt_regs, bx) != 0);
@@ -1511,6 +1541,13 @@ void syscall_trace_leave(struct pt_regs *regs)
 {
 	bool step;
 
+	/*
+	 * We may come here right after calling schedule_user()
+	 * or do_notify_resume(), in which case we can be in RCU
+	 * user mode.
+	 */
+	rcu_user_exit();
+
 	audit_syscall_exit(regs);
 
 	if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 468e98dfd44e..ca45696f30fb 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -921,18 +921,19 @@ void __init setup_arch(char **cmdline_p)
 #ifdef CONFIG_X86_64
 	if (max_pfn > max_low_pfn) {
 		int i;
-		for (i = 0; i < e820.nr_map; i++) {
-			struct e820entry *ei = &e820.map[i];
+		unsigned long start, end;
+		unsigned long start_pfn, end_pfn;
 
-			if (ei->addr + ei->size <= 1UL << 32)
-				continue;
+		for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn,
+							 NULL) {
 
-			if (ei->type == E820_RESERVED)
+			end = PFN_PHYS(end_pfn);
+			if (end <= (1UL<<32))
 				continue;
 
+			start = PFN_PHYS(start_pfn);
 			max_pfn_mapped = init_memory_mapping(
-				ei->addr < 1UL << 32 ? 1UL << 32 : ei->addr,
-				ei->addr + ei->size);
+						max((1UL<<32), start), end);
 		}
 
 		/* can we preseve max_low_pfn ?*/
@@ -1048,6 +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/smpboot.c b/arch/x86/kernel/smpboot.c
index c80a33bc528b..f3e2ec878b8c 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -68,6 +68,8 @@
 #include <asm/mwait.h>
 #include <asm/apic.h>
 #include <asm/io_apic.h>
+#include <asm/i387.h>
+#include <asm/fpu-internal.h>
 #include <asm/setup.h>
 #include <asm/uv/uv.h>
 #include <linux/mc146818rtc.h>
@@ -818,6 +820,9 @@ int __cpuinit native_cpu_up(unsigned int cpu, struct task_struct *tidle)
 
 	per_cpu(cpu_state, cpu) = CPU_UP_PREPARE;
 
+	/* the FPU context is blank, nobody can own it */
+	__cpu_disable_lazy_restore(cpu);
+
 	err = do_boot_cpu(apicid, cpu, tidle);
 	if (err) {
 		pr_debug("do_boot_cpu failed %d\n", err);
diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h
index a10e46016851..58fc51488828 100644
--- a/arch/x86/kvm/cpuid.h
+++ b/arch/x86/kvm/cpuid.h
@@ -24,6 +24,9 @@ static inline bool guest_cpuid_has_xsave(struct kvm_vcpu *vcpu)
 {
 	struct kvm_cpuid_entry2 *best;
 
+	if (!static_cpu_has(X86_FEATURE_XSAVE))
+		return 0;
+
 	best = kvm_find_cpuid_entry(vcpu, 1, 0);
 	return best && (best->ecx & bit(X86_FEATURE_XSAVE));
 }
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 39171cb307ea..bba39bfa1c4b 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -426,8 +426,7 @@ static void invalidate_registers(struct x86_emulate_ctxt *ctxt)
 			_ASM_EXTABLE(1b, 3b)				\
 			: "=m" ((ctxt)->eflags), "=&r" (_tmp),		\
 			  "+a" (*rax), "+d" (*rdx), "+qm"(_ex)		\
-			: "i" (EFLAGS_MASK), "m" ((ctxt)->src.val),	\
-			  "a" (*rax), "d" (*rdx));			\
+			: "i" (EFLAGS_MASK), "m" ((ctxt)->src.val));	\
 	} while (0)
 
 /* instruction has only one source operand, destination is implicit (e.g. mul, div, imul, idiv) */
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index ad6b1dd06f8b..f85815945fc6 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -6549,19 +6549,22 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu)
 		}
 	}
 
-	exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL);
 	/* Exposing INVPCID only when PCID is exposed */
 	best = kvm_find_cpuid_entry(vcpu, 0x7, 0);
 	if (vmx_invpcid_supported() &&
 	    best && (best->ebx & bit(X86_FEATURE_INVPCID)) &&
 	    guest_cpuid_has_pcid(vcpu)) {
+		exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL);
 		exec_control |= SECONDARY_EXEC_ENABLE_INVPCID;
 		vmcs_write32(SECONDARY_VM_EXEC_CONTROL,
 			     exec_control);
 	} else {
-		exec_control &= ~SECONDARY_EXEC_ENABLE_INVPCID;
-		vmcs_write32(SECONDARY_VM_EXEC_CONTROL,
-			     exec_control);
+		if (cpu_has_secondary_exec_ctrls()) {
+			exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL);
+			exec_control &= ~SECONDARY_EXEC_ENABLE_INVPCID;
+			vmcs_write32(SECONDARY_VM_EXEC_CONTROL,
+				     exec_control);
+		}
 		if (best)
 			best->ebx &= ~bit(X86_FEATURE_INVPCID);
 	}
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 1eefebe5d727..4f7641756be2 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;
@@ -5773,6 +5781,9 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 	int pending_vec, max_bits, idx;
 	struct desc_ptr dt;
 
+	if (!guest_cpuid_has_xsave(vcpu) && (sregs->cr4 & X86_CR4_OSXSAVE))
+		return -EINVAL;
+
 	dt.size = sregs->idt.limit;
 	dt.address = sregs->idt.base;
 	kvm_x86_ops->set_idt(vcpu, &dt);
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index ab1f6a93b527..d7aea41563b3 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 2b6b4a3c8beb..3baff255adac 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/mm/tlb.c b/arch/x86/mm/tlb.c
index 0777f042e400..60f926cd8b0e 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -197,7 +197,7 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
 	}
 
 	if (end == TLB_FLUSH_ALL || tlb_flushall_shift == -1
-					|| vmflag == VM_HUGETLB) {
+					|| vmflag & VM_HUGETLB) {
 		local_flush_tlb();
 		goto flush_all;
 	}
diff --git a/arch/x86/pci/ce4100.c b/arch/x86/pci/ce4100.c
index 41bd2a2d2c50..b914e20b5a00 100644
--- a/arch/x86/pci/ce4100.c
+++ b/arch/x86/pci/ce4100.c
@@ -115,6 +115,16 @@ static void sata_revid_read(struct sim_dev_reg *reg, u32 *value)
 	reg_read(reg, value);
 }
 
+static void reg_noirq_read(struct sim_dev_reg *reg, u32 *value)
+{
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&pci_config_lock, flags);
+	/* force interrupt pin value to 0 */
+	*value = reg->sim_reg.value & 0xfff00ff;
+	raw_spin_unlock_irqrestore(&pci_config_lock, flags);
+}
+
 static struct sim_dev_reg bus1_fixups[] = {
 	DEFINE_REG(2, 0, 0x10, (16*MB), reg_init, reg_read, reg_write)
 	DEFINE_REG(2, 0, 0x14, (256), reg_init, reg_read, reg_write)
@@ -144,6 +154,7 @@ static struct sim_dev_reg bus1_fixups[] = {
 	DEFINE_REG(11, 5, 0x10, (64*KB), reg_init, reg_read, reg_write)
 	DEFINE_REG(11, 6, 0x10, (256), reg_init, reg_read, reg_write)
 	DEFINE_REG(11, 7, 0x10, (64*KB), reg_init, reg_read, reg_write)
+	DEFINE_REG(11, 7, 0x3c, 256, reg_init, reg_noirq_read, reg_write)
 	DEFINE_REG(12, 0, 0x10, (128*KB), reg_init, reg_read, reg_write)
 	DEFINE_REG(12, 0, 0x14, (256), reg_init, reg_read, reg_write)
 	DEFINE_REG(12, 1, 0x10, (1024), reg_init, reg_read, reg_write)
@@ -161,8 +172,10 @@ static struct sim_dev_reg bus1_fixups[] = {
 	DEFINE_REG(16, 0, 0x10, (64*KB), reg_init, reg_read, reg_write)
 	DEFINE_REG(16, 0, 0x14, (64*MB), reg_init, reg_read, reg_write)
 	DEFINE_REG(16, 0, 0x18, (64*MB), reg_init, reg_read, reg_write)
+	DEFINE_REG(16, 0, 0x3c, 256, reg_init, reg_noirq_read, reg_write)
 	DEFINE_REG(17, 0, 0x10, (128*KB), reg_init, reg_read, reg_write)
 	DEFINE_REG(18, 0, 0x10, (1*KB), reg_init, reg_read, reg_write)
+	DEFINE_REG(18, 0, 0x3c, 256, reg_init, reg_noirq_read, reg_write)
 };
 
 static void __init init_sim_regs(void)
diff --git a/arch/x86/platform/ce4100/ce4100.c b/arch/x86/platform/ce4100/ce4100.c
index 4c61b52191eb..92525cb8e54c 100644
--- a/arch/x86/platform/ce4100/ce4100.c
+++ b/arch/x86/platform/ce4100/ce4100.c
@@ -21,12 +21,25 @@
 #include <asm/i8259.h>
 #include <asm/io.h>
 #include <asm/io_apic.h>
+#include <asm/emergency-restart.h>
 
 static int ce4100_i8042_detect(void)
 {
 	return 0;
 }
 
+/*
+ * The CE4100 platform has an internal 8051 Microcontroller which is
+ * responsible for signaling to the external Power Management Unit the
+ * intention to reset, reboot or power off the system. This 8051 device has
+ * its command register mapped at I/O port 0xcf9 and the value 0x4 is used
+ * to power off the system.
+ */
+static void ce4100_power_off(void)
+{
+	outb(0x4, 0xcf9);
+}
+
 #ifdef CONFIG_SERIAL_8250
 
 static unsigned int mem_serial_in(struct uart_port *p, int offset)
@@ -139,8 +152,19 @@ void __init x86_ce4100_early_setup(void)
 	x86_init.mpparse.find_smp_config = x86_init_noop;
 	x86_init.pci.init = ce4100_pci_init;
 
+	/*
+	 * By default, the reboot method is ACPI which is supported by the
+	 * CE4100 bootloader CEFDK using FADT.ResetReg Address and ResetValue
+	 * the bootloader will however issue a system power off instead of
+	 * reboot. By using BOOT_KBD we ensure proper system reboot as
+	 * expected.
+	 */
+	reboot_type = BOOT_KBD;
+
 #ifdef CONFIG_X86_IO_APIC
 	x86_init.pci.init_irq = sdv_pci_init;
 	x86_init.mpparse.setup_ioapic_ids = setup_ioapic_ids_from_mpc_nocheck;
 #endif
+
+	pm_power_off = ce4100_power_off;
 }
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index aded2a91162a..ad4439145f85 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 ac3aa54e2654..95fd505dfeb6 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/xen/mmu.c b/arch/x86/xen/mmu.c
index 6226c99729b9..dcf5f2dd91ec 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;
 }