Merge branch 'linus' into x86/urgent

Pick up Linus's latest, to fix a bug.

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

25 files changed, 284 insertions, 205 deletions

diff --git a/arch/x86/include/asm/Kbuild b/arch/x86/include/asm/Kbuild
index a8fee078b92f..4acddc43ee0c 100644
--- a/arch/x86/include/asm/Kbuild
+++ b/arch/x86/include/asm/Kbuild
@@ -5,4 +5,5 @@ genhdr-y += unistd_64.h
 genhdr-y += unistd_x32.h
 
 generic-y += clkdev.h
+generic-y += cputime.h
 generic-y += mcs_spinlock.h
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index bc507d7640f8..63211ef5046a 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -37,7 +37,7 @@
 #define X86_FEATURE_PAT		(0*32+16) /* Page Attribute Table */
 #define X86_FEATURE_PSE36	(0*32+17) /* 36-bit PSEs */
 #define X86_FEATURE_PN		(0*32+18) /* Processor serial number */
-#define X86_FEATURE_CLFLSH	(0*32+19) /* "clflush" CLFLUSH instruction */
+#define X86_FEATURE_CLFLUSH	(0*32+19) /* CLFLUSH instruction */
 #define X86_FEATURE_DS		(0*32+21) /* "dts" Debug Store */
 #define X86_FEATURE_ACPI	(0*32+22) /* ACPI via MSR */
 #define X86_FEATURE_MMX		(0*32+23) /* Multimedia Extensions */
@@ -318,7 +318,7 @@ extern const char * const x86_power_flags[32];
 #define cpu_has_pmm_enabled	boot_cpu_has(X86_FEATURE_PMM_EN)
 #define cpu_has_ds		boot_cpu_has(X86_FEATURE_DS)
 #define cpu_has_pebs		boot_cpu_has(X86_FEATURE_PEBS)
-#define cpu_has_clflush		boot_cpu_has(X86_FEATURE_CLFLSH)
+#define cpu_has_clflush		boot_cpu_has(X86_FEATURE_CLFLUSH)
 #define cpu_has_bts		boot_cpu_has(X86_FEATURE_BTS)
 #define cpu_has_gbpages		boot_cpu_has(X86_FEATURE_GBPAGES)
 #define cpu_has_arch_perfmon	boot_cpu_has(X86_FEATURE_ARCH_PERFMON)
diff --git a/arch/x86/include/asm/cputime.h b/arch/x86/include/asm/cputime.h
deleted file mode 100644
index 6d68ad7e0ea3..000000000000
--- a/arch/x86/include/asm/cputime.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/cputime.h>
diff --git a/arch/x86/include/asm/floppy.h b/arch/x86/include/asm/floppy.h
index d3d74698dce9..1c7eefe32502 100644
--- a/arch/x86/include/asm/floppy.h
+++ b/arch/x86/include/asm/floppy.h
@@ -145,10 +145,10 @@ static int fd_request_irq(void)
 {
 	if (can_use_virtual_dma)
 		return request_irq(FLOPPY_IRQ, floppy_hardint,
-				   IRQF_DISABLED, "floppy", NULL);
+				   0, "floppy", NULL);
 	else
 		return request_irq(FLOPPY_IRQ, floppy_interrupt,
-				   IRQF_DISABLED, "floppy", NULL);
+				   0, "floppy", NULL);
 }
 
 static unsigned long dma_mem_alloc(unsigned long size)
diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h
index ab0ae1aa6d0a..230853da4ec0 100644
--- a/arch/x86/include/asm/hardirq.h
+++ b/arch/x86/include/asm/hardirq.h
@@ -33,6 +33,9 @@ typedef struct {
 #ifdef CONFIG_X86_MCE_THRESHOLD
 	unsigned int irq_threshold_count;
 #endif
+#if IS_ENABLED(CONFIG_HYPERV) || defined(CONFIG_XEN)
+	unsigned int irq_hv_callback_count;
+#endif
 } ____cacheline_aligned irq_cpustat_t;
 
 DECLARE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index cd9c41938b8a..c163215abb9a 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -2,6 +2,7 @@
 #define _ASM_X86_MSHYPER_H
 
 #include <linux/types.h>
+#include <linux/interrupt.h>
 #include <asm/hyperv.h>
 
 struct ms_hyperv_info {
@@ -16,6 +17,7 @@ void hyperv_callback_vector(void);
 #define trace_hyperv_callback_vector hyperv_callback_vector
 #endif
 void hyperv_vector_handler(struct pt_regs *regs);
-void hv_register_vmbus_handler(int irq, irq_handler_t handler);
+void hv_setup_vmbus_irq(void (*handler)(void));
+void hv_remove_vmbus_irq(void);
 
 #endif
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index fdedd38fd0fc..a4ea02351f4d 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -449,6 +449,15 @@ struct stack_canary {
 };
 DECLARE_PER_CPU_ALIGNED(struct stack_canary, stack_canary);
 #endif
+/*
+ * per-CPU IRQ handling stacks
+ */
+struct irq_stack {
+	u32                     stack[THREAD_SIZE/sizeof(u32)];
+} __aligned(THREAD_SIZE);
+
+DECLARE_PER_CPU(struct irq_stack *, hardirq_stack);
+DECLARE_PER_CPU(struct irq_stack *, softirq_stack);
 #endif	/* X86_64 */
 
 extern unsigned int xstate_size;
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index e1940c06ed02..47e5de25ba79 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -9,6 +9,7 @@
 
 #include <linux/compiler.h>
 #include <asm/page.h>
+#include <asm/percpu.h>
 #include <asm/types.h>
 
 /*
@@ -32,12 +33,6 @@ struct thread_info {
 	mm_segment_t		addr_limit;
 	struct restart_block    restart_block;
 	void __user		*sysenter_return;
-#ifdef CONFIG_X86_32
-	unsigned long           previous_esp;   /* ESP of the previous stack in
-						   case of nested (IRQ) stacks
-						*/
-	__u8			supervisor_stack[0];
-#endif
 	unsigned int		sig_on_uaccess_error:1;
 	unsigned int		uaccess_err:1;	/* uaccess failed */
 };
@@ -153,9 +148,9 @@ struct thread_info {
 #define _TIF_WORK_CTXSW_PREV (_TIF_WORK_CTXSW|_TIF_USER_RETURN_NOTIFY)
 #define _TIF_WORK_CTXSW_NEXT (_TIF_WORK_CTXSW)
 
-#ifdef CONFIG_X86_32
+#define STACK_WARN		(THREAD_SIZE/8)
+#define KERNEL_STACK_OFFSET	(5*(BITS_PER_LONG/8))
 
-#define STACK_WARN	(THREAD_SIZE/8)
 /*
  * macros/functions for gaining access to the thread information structure
  *
@@ -163,42 +158,6 @@ struct thread_info {
  */
 #ifndef __ASSEMBLY__
 
-#define current_stack_pointer ({		\
-	unsigned long sp;			\
-	asm("mov %%esp,%0" : "=g" (sp));	\
-	sp;					\
-})
-
-/* how to get the thread information struct from C */
-static inline struct thread_info *current_thread_info(void)
-{
-	return (struct thread_info *)
-		(current_stack_pointer & ~(THREAD_SIZE - 1));
-}
-
-#else /* !__ASSEMBLY__ */
-
-/* how to get the thread information struct from ASM */
-#define GET_THREAD_INFO(reg)	 \
-	movl $-THREAD_SIZE, reg; \
-	andl %esp, reg
-
-/* use this one if reg already contains %esp */
-#define GET_THREAD_INFO_WITH_ESP(reg) \
-	andl $-THREAD_SIZE, reg
-
-#endif
-
-#else /* X86_32 */
-
-#include <asm/percpu.h>
-#define KERNEL_STACK_OFFSET (5*8)
-
-/*
- * macros/functions for gaining access to the thread information structure
- * preempt_count needs to be 1 initially, until the scheduler is functional.
- */
-#ifndef __ASSEMBLY__
 DECLARE_PER_CPU(unsigned long, kernel_stack);
 
 static inline struct thread_info *current_thread_info(void)
@@ -213,8 +172,8 @@ static inline struct thread_info *current_thread_info(void)
 
 /* how to get the thread information struct from ASM */
 #define GET_THREAD_INFO(reg) \
-	movq PER_CPU_VAR(kernel_stack),reg ; \
-	subq $(THREAD_SIZE-KERNEL_STACK_OFFSET),reg
+	_ASM_MOV PER_CPU_VAR(kernel_stack),reg ; \
+	_ASM_SUB $(THREAD_SIZE-KERNEL_STACK_OFFSET),reg ;
 
 /*
  * Same if PER_CPU_VAR(kernel_stack) is, perhaps with some offset, already in
@@ -224,8 +183,6 @@ static inline struct thread_info *current_thread_info(void)
 
 #endif
 
-#endif /* !X86_32 */
-
 /*
  * Thread-synchronous status.
  *
diff --git a/arch/x86/include/asm/unistd.h b/arch/x86/include/asm/unistd.h
index c2a48139c340..3f556c6a0157 100644
--- a/arch/x86/include/asm/unistd.h
+++ b/arch/x86/include/asm/unistd.h
@@ -23,6 +23,9 @@
 #  include <asm/unistd_64.h>
 #  include <asm/unistd_64_x32.h>
 #  define __ARCH_WANT_COMPAT_SYS_TIME
+#  define __ARCH_WANT_COMPAT_SYS_GETDENTS64
+#  define __ARCH_WANT_COMPAT_SYS_PREADV64
+#  define __ARCH_WANT_COMPAT_SYS_PWRITEV64
 
 # endif
 
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 8e28bf2fc3ef..a135239badb7 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1025,7 +1025,8 @@ __setup("show_msr=", setup_show_msr);
 
 static __init int setup_noclflush(char *arg)
 {
-	setup_clear_cpu_cap(X86_FEATURE_CLFLSH);
+	setup_clear_cpu_cap(X86_FEATURE_CLFLUSH);
+	setup_clear_cpu_cap(X86_FEATURE_CLFLUSHOPT);
 	return 1;
 }
 __setup("noclflush", setup_noclflush);
@@ -1078,6 +1079,10 @@ static __init int setup_disablecpuid(char *arg)
 }
 __setup("clearcpuid=", setup_disablecpuid);
 
+DEFINE_PER_CPU(unsigned long, kernel_stack) =
+	(unsigned long)&init_thread_union - KERNEL_STACK_OFFSET + THREAD_SIZE;
+EXPORT_PER_CPU_SYMBOL(kernel_stack);
+
 #ifdef CONFIG_X86_64
 struct desc_ptr idt_descr = { NR_VECTORS * 16 - 1, (unsigned long) idt_table };
 struct desc_ptr debug_idt_descr = { NR_VECTORS * 16 - 1,
@@ -1094,10 +1099,6 @@ DEFINE_PER_CPU(struct task_struct *, current_task) ____cacheline_aligned =
 	&init_task;
 EXPORT_PER_CPU_SYMBOL(current_task);
 
-DEFINE_PER_CPU(unsigned long, kernel_stack) =
-	(unsigned long)&init_thread_union - KERNEL_STACK_OFFSET + THREAD_SIZE;
-EXPORT_PER_CPU_SYMBOL(kernel_stack);
-
 DEFINE_PER_CPU(char *, irq_stack_ptr) =
 	init_per_cpu_var(irq_stack_union.irq_stack) + IRQ_STACK_SIZE - 64;
 
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index 832d05a914ba..76f98fe5b35c 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -17,6 +17,7 @@
 #include <linux/hardirq.h>
 #include <linux/efi.h>
 #include <linux/interrupt.h>
+#include <linux/irq.h>
 #include <asm/processor.h>
 #include <asm/hypervisor.h>
 #include <asm/hyperv.h>
@@ -31,6 +32,45 @@
 struct ms_hyperv_info ms_hyperv;
 EXPORT_SYMBOL_GPL(ms_hyperv);
 
+#if IS_ENABLED(CONFIG_HYPERV)
+static void (*vmbus_handler)(void);
+
+void hyperv_vector_handler(struct pt_regs *regs)
+{
+	struct pt_regs *old_regs = set_irq_regs(regs);
+
+	irq_enter();
+	exit_idle();
+
+	inc_irq_stat(irq_hv_callback_count);
+	if (vmbus_handler)
+		vmbus_handler();
+
+	irq_exit();
+	set_irq_regs(old_regs);
+}
+
+void hv_setup_vmbus_irq(void (*handler)(void))
+{
+	vmbus_handler = handler;
+	/*
+	 * Setup the IDT for hypervisor callback. Prevent reallocation
+	 * at module reload.
+	 */
+	if (!test_bit(HYPERVISOR_CALLBACK_VECTOR, used_vectors))
+		alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR,
+				hyperv_callback_vector);
+}
+
+void hv_remove_vmbus_irq(void)
+{
+	/* We have no way to deallocate the interrupt gate */
+	vmbus_handler = NULL;
+}
+EXPORT_SYMBOL_GPL(hv_setup_vmbus_irq);
+EXPORT_SYMBOL_GPL(hv_remove_vmbus_irq);
+#endif
+
 static uint32_t  __init ms_hyperv_platform(void)
 {
 	u32 eax;
@@ -119,41 +159,3 @@ const __refconst struct hypervisor_x86 x86_hyper_ms_hyperv = {
 	.init_platform		= ms_hyperv_init_platform,
 };
 EXPORT_SYMBOL(x86_hyper_ms_hyperv);
-
-#if IS_ENABLED(CONFIG_HYPERV)
-static int vmbus_irq = -1;
-static irq_handler_t vmbus_isr;
-
-void hv_register_vmbus_handler(int irq, irq_handler_t handler)
-{
-	/*
-	 * Setup the IDT for hypervisor callback.
-	 */
-	alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR, hyperv_callback_vector);
-
-	vmbus_irq = irq;
-	vmbus_isr = handler;
-}
-
-void hyperv_vector_handler(struct pt_regs *regs)
-{
-	struct pt_regs *old_regs = set_irq_regs(regs);
-	struct irq_desc *desc;
-
-	irq_enter();
-	exit_idle();
-
-	desc = irq_to_desc(vmbus_irq);
-
-	if (desc)
-		generic_handle_irq_desc(vmbus_irq, desc);
-
-	irq_exit();
-	set_irq_regs(old_regs);
-}
-#else
-void hv_register_vmbus_handler(int irq, irq_handler_t handler)
-{
-}
-#endif
-EXPORT_SYMBOL_GPL(hv_register_vmbus_handler);
diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c
index a21d49c071db..5abd4cd4230c 100644
--- a/arch/x86/kernel/dumpstack_32.c
+++ b/arch/x86/kernel/dumpstack_32.c
@@ -16,12 +16,35 @@
 
 #include <asm/stacktrace.h>
 
+static void *is_irq_stack(void *p, void *irq)
+{
+	if (p < irq || p >= (irq + THREAD_SIZE))
+		return NULL;
+	return irq + THREAD_SIZE;
+}
+
+
+static void *is_hardirq_stack(unsigned long *stack, int cpu)
+{
+	void *irq = per_cpu(hardirq_stack, cpu);
+
+	return is_irq_stack(stack, irq);
+}
+
+static void *is_softirq_stack(unsigned long *stack, int cpu)
+{
+	void *irq = per_cpu(softirq_stack, cpu);
+
+	return is_irq_stack(stack, irq);
+}
 
 void dump_trace(struct task_struct *task, struct pt_regs *regs,
 		unsigned long *stack, unsigned long bp,
 		const struct stacktrace_ops *ops, void *data)
 {
+	const unsigned cpu = get_cpu();
 	int graph = 0;
+	u32 *prev_esp;
 
 	if (!task)
 		task = current;
@@ -39,18 +62,31 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
 
 	for (;;) {
 		struct thread_info *context;
+		void *end_stack;
+
+		end_stack = is_hardirq_stack(stack, cpu);
+		if (!end_stack)
+			end_stack = is_softirq_stack(stack, cpu);
 
-		context = (struct thread_info *)
-			((unsigned long)stack & (~(THREAD_SIZE - 1)));
-		bp = ops->walk_stack(context, stack, bp, ops, data, NULL, &graph);
+		context = task_thread_info(task);
+		bp = ops->walk_stack(context, stack, bp, ops, data,
+				     end_stack, &graph);
 
-		stack = (unsigned long *)context->previous_esp;
+		/* Stop if not on irq stack */
+		if (!end_stack)
+			break;
+
+		/* The previous esp is saved on the bottom of the stack */
+		prev_esp = (u32 *)(end_stack - THREAD_SIZE);
+		stack = (unsigned long *)*prev_esp;
 		if (!stack)
 			break;
+
 		if (ops->stack(data, "IRQ") < 0)
 			break;
 		touch_nmi_watchdog();
 	}
+	put_cpu();
 }
 EXPORT_SYMBOL(dump_trace);
 
diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index addb207dab92..346b1df2412e 100644
--- a/arch/x86/kernel/dumpstack_64.c
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -104,6 +104,45 @@ in_irq_stack(unsigned long *stack, unsigned long *irq_stack,
 	return (stack >= irq_stack && stack < irq_stack_end);
 }
 
+static const unsigned long irq_stack_size =
+	(IRQ_STACK_SIZE - 64) / sizeof(unsigned long);
+
+enum stack_type {
+	STACK_IS_UNKNOWN,
+	STACK_IS_NORMAL,
+	STACK_IS_EXCEPTION,
+	STACK_IS_IRQ,
+};
+
+static enum stack_type
+analyze_stack(int cpu, struct task_struct *task,
+	      unsigned long *stack, unsigned long **stack_end, char **id)
+{
+	unsigned long *irq_stack;
+	unsigned long addr;
+	unsigned used = 0;
+
+	addr = ((unsigned long)stack & (~(THREAD_SIZE - 1)));
+	if ((unsigned long)task_stack_page(task) == addr)
+		return STACK_IS_NORMAL;
+
+	*stack_end = in_exception_stack(cpu, (unsigned long)stack,
+					 &used, id);
+	if (*stack_end)
+		return STACK_IS_EXCEPTION;
+
+	*stack_end = (unsigned long *)per_cpu(irq_stack_ptr, cpu);
+	if (!*stack_end)
+		return STACK_IS_UNKNOWN;
+
+	irq_stack = *stack_end - irq_stack_size;
+
+	if (in_irq_stack(stack, irq_stack, *stack_end))
+		return STACK_IS_IRQ;
+
+	return STACK_IS_UNKNOWN;
+}
+
 /*
  * x86-64 can have up to three kernel stacks:
  * process stack
@@ -116,12 +155,11 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
 		const struct stacktrace_ops *ops, void *data)
 {
 	const unsigned cpu = get_cpu();
-	unsigned long *irq_stack_end =
-		(unsigned long *)per_cpu(irq_stack_ptr, cpu);
-	unsigned used = 0;
 	struct thread_info *tinfo;
-	int graph = 0;
+	unsigned long *irq_stack;
 	unsigned long dummy;
+	int graph = 0;
+	int done = 0;
 
 	if (!task)
 		task = current;
@@ -143,49 +181,60 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
 	 * exceptions
 	 */
 	tinfo = task_thread_info(task);
-	for (;;) {
+	while (!done) {
+		unsigned long *stack_end;
+		enum stack_type stype;
 		char *id;
-		unsigned long *estack_end;
-		estack_end = in_exception_stack(cpu, (unsigned long)stack,
-						&used, &id);
 
-		if (estack_end) {
+		stype = analyze_stack(cpu, task, stack, &stack_end, &id);
+
+		/* Default finish unless specified to continue */
+		done = 1;
+
+		switch (stype) {
+
+		/* Break out early if we are on the thread stack */
+		case STACK_IS_NORMAL:
+			break;
+
+		case STACK_IS_EXCEPTION:
+
 			if (ops->stack(data, id) < 0)
 				break;
 
 			bp = ops->walk_stack(tinfo, stack, bp, ops,
-					     data, estack_end, &graph);
+					     data, stack_end, &graph);
 			ops->stack(data, "<EOE>");
 			/*
 			 * We link to the next stack via the
 			 * second-to-last pointer (index -2 to end) in the
 			 * exception stack:
 			 */
-			stack = (unsigned long *) estack_end[-2];
-			continue;
-		}
-		if (irq_stack_end) {
-			unsigned long *irq_stack;
-			irq_stack = irq_stack_end -
-				(IRQ_STACK_SIZE - 64) / sizeof(*irq_stack);
-
-			if (in_irq_stack(stack, irq_stack, irq_stack_end)) {
-				if (ops->stack(data, "IRQ") < 0)
-					break;
-				bp = ops->walk_stack(tinfo, stack, bp,
-					ops, data, irq_stack_end, &graph);
-				/*
-				 * We link to the next stack (which would be
-				 * the process stack normally) the last
-				 * pointer (index -1 to end) in the IRQ stack:
-				 */
-				stack = (unsigned long *) (irq_stack_end[-1]);
-				irq_stack_end = NULL;
-				ops->stack(data, "EOI");
-				continue;
-			}
+			stack = (unsigned long *) stack_end[-2];
+			done = 0;
+			break;
+
+		case STACK_IS_IRQ:
+
+			if (ops->stack(data, "IRQ") < 0)
+				break;
+			bp = ops->walk_stack(tinfo, stack, bp,
+				     ops, data, stack_end, &graph);
+			/*
+			 * We link to the next stack (which would be
+			 * the process stack normally) the last
+			 * pointer (index -1 to end) in the IRQ stack:
+			 */
+			stack = (unsigned long *) (stack_end[-1]);
+			irq_stack = stack_end - irq_stack_size;
+			ops->stack(data, "EOI");
+			done = 0;
+			break;
+
+		case STACK_IS_UNKNOWN:
+			ops->stack(data, "UNK");
+			break;
 		}
-		break;
 	}
 
 	/*
diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c
index bc4a088f9023..6d7d5a1260a6 100644
--- a/arch/x86/kernel/early-quirks.c
+++ b/arch/x86/kernel/early-quirks.c
@@ -203,18 +203,15 @@ static void __init intel_remapping_check(int num, int slot, int func)
 	revision = read_pci_config_byte(num, slot, func, PCI_REVISION_ID);
 
 	/*
- 	 * Revision 13 of all triggering devices id in this quirk have
-	 * a problem draining interrupts when irq remapping is enabled,
-	 * and should be flagged as broken.  Additionally revisions 0x12
-	 * and 0x22 of device id 0x3405 has this problem.
+	 * Revision <= 13 of all triggering devices id in this quirk
+	 * have a problem draining interrupts when irq remapping is
+	 * enabled, and should be flagged as broken. Additionally
+	 * revision 0x22 of device id 0x3405 has this problem.
 	 */
-	if (revision == 0x13)
+	if (revision <= 0x13)
 		set_irq_remapping_broken();
-	else if ((device == 0x3405) &&
-	    ((revision == 0x12) ||
-	     (revision == 0x22)))
+	else if (device == 0x3405 && revision == 0x22)
 		set_irq_remapping_broken();
-
 }
 
 /*
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index da85a8e830a1..014618dbaa7b 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -521,7 +521,7 @@ static int hpet_setup_irq(struct hpet_dev *dev)
 {
 
 	if (request_irq(dev->irq, hpet_interrupt_handler,
-			IRQF_TIMER | IRQF_DISABLED | IRQF_NOBALANCING,
+			IRQF_TIMER | IRQF_NOBALANCING,
 			dev->name, dev))
 		return -1;
 
@@ -699,7 +699,7 @@ static int hpet_cpuhp_notify(struct notifier_block *n,
 		/* FIXME: add schedule_work_on() */
 		schedule_delayed_work_on(cpu, &work.work, 0);
 		wait_for_completion(&work.complete);
-		destroy_timer_on_stack(&work.work.timer);
+		destroy_delayed_work_on_stack(&work.work);
 		break;
 	case CPU_DEAD:
 		if (hdev) {
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index d99f31d9a750..42805fac0092 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -125,6 +125,12 @@ int arch_show_interrupts(struct seq_file *p, int prec)
 		seq_printf(p, "%10u ", per_cpu(mce_poll_count, j));
 	seq_printf(p, "  Machine check polls\n");
 #endif
+#if defined(CONFIG_HYPERV) || defined(CONFIG_XEN)
+	seq_printf(p, "%*s: ", prec, "THR");
+	for_each_online_cpu(j)
+		seq_printf(p, "%10u ", irq_stats(j)->irq_hv_callback_count);
+	seq_printf(p, "  Hypervisor callback interrupts\n");
+#endif
 	seq_printf(p, "%*s: %10u\n", prec, "ERR", atomic_read(&irq_err_count));
 #if defined(CONFIG_X86_IO_APIC)
 	seq_printf(p, "%*s: %10u\n", prec, "MIS", atomic_read(&irq_mis_count));
diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index d7fcbedc9c43..63ce838e5a54 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -55,16 +55,8 @@ static inline int check_stack_overflow(void) { return 0; }
 static inline void print_stack_overflow(void) { }
 #endif
 
-/*
- * per-CPU IRQ handling contexts (thread information and stack)
- */
-union irq_ctx {
-	struct thread_info      tinfo;
-	u32                     stack[THREAD_SIZE/sizeof(u32)];
-} __attribute__((aligned(THREAD_SIZE)));
-
-static DEFINE_PER_CPU(union irq_ctx *, hardirq_ctx);
-static DEFINE_PER_CPU(union irq_ctx *, softirq_ctx);
+DEFINE_PER_CPU(struct irq_stack *, hardirq_stack);
+DEFINE_PER_CPU(struct irq_stack *, softirq_stack);
 
 static void call_on_stack(void *func, void *stack)
 {
@@ -77,14 +69,26 @@ static void call_on_stack(void *func, void *stack)
 		     : "memory", "cc", "edx", "ecx", "eax");
 }
 
+/* how to get the current stack pointer from C */
+#define current_stack_pointer ({		\
+	unsigned long sp;			\
+	asm("mov %%esp,%0" : "=g" (sp));	\
+	sp;					\
+})
+
+static inline void *current_stack(void)
+{
+	return (void *)(current_stack_pointer & ~(THREAD_SIZE - 1));
+}
+
 static inline int
 execute_on_irq_stack(int overflow, struct irq_desc *desc, int irq)
 {
-	union irq_ctx *curctx, *irqctx;
-	u32 *isp, arg1, arg2;
+	struct irq_stack *curstk, *irqstk;
+	u32 *isp, *prev_esp, arg1, arg2;
 
-	curctx = (union irq_ctx *) current_thread_info();
-	irqctx = __this_cpu_read(hardirq_ctx);
+	curstk = (struct irq_stack *) current_stack();
+	irqstk = __this_cpu_read(hardirq_stack);
 
 	/*
 	 * this is where we switch to the IRQ stack. However, if we are
@@ -92,13 +96,14 @@ execute_on_irq_stack(int overflow, struct irq_desc *desc, int irq)
 	 * handler) we can't do that and just have to keep using the
 	 * current stack (which is the irq stack already after all)
 	 */
-	if (unlikely(curctx == irqctx))
+	if (unlikely(curstk == irqstk))
 		return 0;
 
-	/* build the stack frame on the IRQ stack */
-	isp = (u32 *) ((char *)irqctx + sizeof(*irqctx));
-	irqctx->tinfo.task = curctx->tinfo.task;
-	irqctx->tinfo.previous_esp = current_stack_pointer;
+	isp = (u32 *) ((char *)irqstk + sizeof(*irqstk));
+
+	/* Save the next esp at the bottom of the stack */
+	prev_esp = (u32 *)irqstk;
+	*prev_esp = current_stack_pointer;
 
 	if (unlikely(overflow))
 		call_on_stack(print_stack_overflow, isp);
@@ -118,46 +123,40 @@ execute_on_irq_stack(int overflow, struct irq_desc *desc, int irq)
  */
 void irq_ctx_init(int cpu)
 {
-	union irq_ctx *irqctx;
+	struct irq_stack *irqstk;
 
-	if (per_cpu(hardirq_ctx, cpu))
+	if (per_cpu(hardirq_stack, cpu))
 		return;
 
-	irqctx = page_address(alloc_pages_node(cpu_to_node(cpu),
+	irqstk = page_address(alloc_pages_node(cpu_to_node(cpu),
 					       THREADINFO_GFP,
 					       THREAD_SIZE_ORDER));
-	memset(&irqctx->tinfo, 0, sizeof(struct thread_info));
-	irqctx->tinfo.cpu		= cpu;
-	irqctx->tinfo.addr_limit	= MAKE_MM_SEG(0);
-
-	per_cpu(hardirq_ctx, cpu) = irqctx;
+	per_cpu(hardirq_stack, cpu) = irqstk;
 
-	irqctx = page_address(alloc_pages_node(cpu_to_node(cpu),
+	irqstk = page_address(alloc_pages_node(cpu_to_node(cpu),
 					       THREADINFO_GFP,
 					       THREAD_SIZE_ORDER));
-	memset(&irqctx->tinfo, 0, sizeof(struct thread_info));
-	irqctx->tinfo.cpu		= cpu;
-	irqctx->tinfo.addr_limit	= MAKE_MM_SEG(0);
-
-	per_cpu(softirq_ctx, cpu) = irqctx;
+	per_cpu(softirq_stack, cpu) = irqstk;
 
 	printk(KERN_DEBUG "CPU %u irqstacks, hard=%p soft=%p\n",
-	       cpu, per_cpu(hardirq_ctx, cpu),  per_cpu(softirq_ctx, cpu));
+	       cpu, per_cpu(hardirq_stack, cpu),  per_cpu(softirq_stack, cpu));
 }
 
 void do_softirq_own_stack(void)
 {
-	struct thread_info *curctx;
-	union irq_ctx *irqctx;
-	u32 *isp;
+	struct thread_info *curstk;
+	struct irq_stack *irqstk;
+	u32 *isp, *prev_esp;
 
-	curctx = current_thread_info();
-	irqctx = __this_cpu_read(softirq_ctx);
-	irqctx->tinfo.task = curctx->task;
-	irqctx->tinfo.previous_esp = current_stack_pointer;
+	curstk = current_stack();
+	irqstk = __this_cpu_read(softirq_stack);
 
 	/* build the stack frame on the softirq stack */
-	isp = (u32 *) ((char *)irqctx + sizeof(*irqctx));
+	isp = (u32 *) ((char *)irqstk + sizeof(*irqstk));
+
+	/* Push the previous esp onto the stack */
+	prev_esp = (u32 *)irqstk;
+	*prev_esp = current_stack_pointer;
 
 	call_on_stack(__do_softirq, isp);
 }
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 0de43e98ce08..7bc86bbe7485 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -314,6 +314,10 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	 */
 	arch_end_context_switch(next_p);
 
+	this_cpu_write(kernel_stack,
+		  (unsigned long)task_stack_page(next_p) +
+		  THREAD_SIZE - KERNEL_STACK_OFFSET);
+
 	/*
 	 * Restore %gs if needed (which is common)
 	 */
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index 7461f50d5bb1..678c0ada3b3c 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -184,14 +184,14 @@ 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;
+	u32 *prev_esp;
 
 	if (context == (sp & ~(THREAD_SIZE - 1)))
 		return sp;
 
-	tinfo = (struct thread_info *)context;
-	if (tinfo->previous_esp)
-		return tinfo->previous_esp;
+	prev_esp = (u32 *)(context);
+	if (prev_esp)
+		return (unsigned long)prev_esp;
 
 	return (unsigned long)regs;
 }
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index c752cb43e52f..654b46574b91 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -464,9 +464,12 @@ void __attribute__((weak)) mach_reboot_fixups(void)
  * 2) If still alive, write to the keyboard controller
  * 3) If still alive, write to the ACPI reboot register again
  * 4) If still alive, write to the keyboard controller again
+ * 5) If still alive, call the EFI runtime service to reboot
+ * 6) If still alive, write to the PCI IO port 0xCF9 to reboot
+ * 7) If still alive, inform BIOS to do a proper reboot
  *
  * If the machine is still alive at this stage, it gives up. We default to
- * following the same pattern, except that if we're still alive after (4) we'll
+ * following the same pattern, except that if we're still alive after (7) we'll
  * try to force a triple fault and then cycle between hitting the keyboard
  * controller and doing that
  */
@@ -502,7 +505,7 @@ static void native_machine_emergency_restart(void)
 				attempt = 1;
 				reboot_type = BOOT_ACPI;
 			} else {
-				reboot_type = BOOT_TRIPLE;
+				reboot_type = BOOT_EFI;
 			}
 			break;
 
@@ -510,13 +513,15 @@ static void native_machine_emergency_restart(void)
 			load_idt(&no_idt);
 			__asm__ __volatile__("int3");
 
+			/* We're probably dead after this, but... */
 			reboot_type = BOOT_KBD;
 			break;
 
 		case BOOT_BIOS:
 			machine_real_restart(MRR_BIOS);
 
-			reboot_type = BOOT_KBD;
+			/* We're probably dead after this, but... */
+			reboot_type = BOOT_TRIPLE;
 			break;
 
 		case BOOT_ACPI:
@@ -530,7 +535,7 @@ static void native_machine_emergency_restart(void)
 						 EFI_RESET_WARM :
 						 EFI_RESET_COLD,
 						 EFI_SUCCESS, 0, NULL);
-			reboot_type = BOOT_KBD;
+			reboot_type = BOOT_CF9_COND;
 			break;
 
 		case BOOT_CF9:
@@ -548,7 +553,7 @@ static void native_machine_emergency_restart(void)
 				outb(cf9|reboot_code, 0xcf9);
 				udelay(50);
 			}
-			reboot_type = BOOT_KBD;
+			reboot_type = BOOT_BIOS;
 			break;
 		}
 	}
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 60179ec39d4c..34826934d4a7 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -766,10 +766,10 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle)
 #else
 	clear_tsk_thread_flag(idle, TIF_FORK);
 	initial_gs = per_cpu_offset(cpu);
+#endif
 	per_cpu(kernel_stack, cpu) =
 		(unsigned long)task_stack_page(idle) -
 		KERNEL_STACK_OFFSET + THREAD_SIZE;
-#endif
 	early_gdt_descr.address = (unsigned long)get_cpu_gdt_table(cpu);
 	initial_code = (unsigned long)start_secondary;
 	stack_start  = idle->thread.sp;
@@ -1387,7 +1387,7 @@ static inline void mwait_play_dead(void)
 
 	if (!this_cpu_has(X86_FEATURE_MWAIT))
 		return;
-	if (!this_cpu_has(X86_FEATURE_CLFLSH))
+	if (!this_cpu_has(X86_FEATURE_CLFLUSH))
 		return;
 	if (__this_cpu_read(cpu_info.cpuid_level) < CPUID_MWAIT_LEAF)
 		return;
diff --git a/arch/x86/kernel/time.c b/arch/x86/kernel/time.c
index 6ec91c00d84d..bf7ef5ce29df 100644
--- a/arch/x86/kernel/time.c
+++ b/arch/x86/kernel/time.c
@@ -62,7 +62,7 @@ static irqreturn_t timer_interrupt(int irq, void *dev_id)
 
 static struct irqaction irq0  = {
 	.handler = timer_interrupt,
-	.flags = IRQF_DISABLED | IRQF_NOBALANCING | IRQF_IRQPOLL | IRQF_TIMER,
+	.flags = IRQF_NOBALANCING | IRQF_IRQPOLL | IRQF_TIMER,
 	.name = "timer"
 };
 
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index c6976257eff5..e5503d8aec1d 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -263,7 +263,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 		F(TSC) | F(MSR) | F(PAE) | F(MCE) |
 		F(CX8) | F(APIC) | 0 /* Reserved */ | F(SEP) |
 		F(MTRR) | F(PGE) | F(MCA) | F(CMOV) |
-		F(PAT) | F(PSE36) | 0 /* PSN */ | F(CLFLSH) |
+		F(PAT) | F(PSE36) | 0 /* PSN */ | F(CLFLUSH) |
 		0 /* Reserved, DS, ACPI */ | F(MMX) |
 		F(FXSR) | F(XMM) | F(XMM2) | F(SELFSNOOP) |
 		0 /* HTT, TM, Reserved, PBE */;
diff --git a/arch/x86/mm/srat.c b/arch/x86/mm/srat.c
index 1953e9c9391a..66338a60aa6e 100644
--- a/arch/x86/mm/srat.c
+++ b/arch/x86/mm/srat.c
@@ -52,12 +52,18 @@ void __init acpi_numa_slit_init(struct acpi_table_slit *slit)
 	int i, j;
 
 	for (i = 0; i < slit->locality_count; i++) {
-		if (pxm_to_node(i) == NUMA_NO_NODE)
+		const int from_node = pxm_to_node(i);
+
+		if (from_node == NUMA_NO_NODE)
 			continue;
+
 		for (j = 0; j < slit->locality_count; j++) {
-			if (pxm_to_node(j) == NUMA_NO_NODE)
+			const int to_node = pxm_to_node(j);
+
+			if (to_node == NUMA_NO_NODE)
 				continue;
-			numa_set_distance(pxm_to_node(i), pxm_to_node(j),
+
+			numa_set_distance(from_node, to_node,
 				slit->entry[slit->locality_count * i + j]);
 		}
 	}
diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c
index 581521c843a5..4d3acc34a998 100644
--- a/arch/x86/xen/spinlock.c
+++ b/arch/x86/xen/spinlock.c
@@ -183,7 +183,7 @@ __visible void xen_lock_spinning(struct arch_spinlock *lock, __ticket_t want)
 
 	local_irq_save(flags);
 
-	kstat_incr_irqs_this_cpu(irq, irq_to_desc(irq));
+	kstat_incr_irq_this_cpu(irq);
 out:
 	cpumask_clear_cpu(cpu, &waiting_cpus);
 	w->lock = NULL;