Merge branch 'topic/asoc' into for-linus

29 files changed, 499 insertions, 177 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 864cc6e6ac8e..5bed94e189fa 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -360,7 +360,6 @@ config X86_NUMACHIP
 	depends on NUMA
 	depends on SMP
 	depends on X86_X2APIC
-	depends on !EDAC_AMD64
 	---help---
 	  Adds support for Numascale NumaChip large-SMP systems. Needed to
 	  enable more than ~168 cores.
diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c
index 3a19d04cebeb..7116dcba0c9e 100644
--- a/arch/x86/boot/compressed/misc.c
+++ b/arch/x86/boot/compressed/misc.c
@@ -321,6 +321,8 @@ static void parse_elf(void *output)
 		default: /* Ignore other PT_* */ break;
 		}
 	}
+
+	free(phdrs);
 }
 
 asmlinkage void decompress_kernel(void *rmode, memptr heap,
diff --git a/arch/x86/include/asm/cmpxchg.h b/arch/x86/include/asm/cmpxchg.h
index 0c9fa2745f13..b3b733262909 100644
--- a/arch/x86/include/asm/cmpxchg.h
+++ b/arch/x86/include/asm/cmpxchg.h
@@ -145,13 +145,13 @@ extern void __add_wrong_size(void)
 
 #ifdef __HAVE_ARCH_CMPXCHG
 #define cmpxchg(ptr, old, new)						\
-	__cmpxchg((ptr), (old), (new), sizeof(*ptr))
+	__cmpxchg(ptr, old, new, sizeof(*(ptr)))
 
 #define sync_cmpxchg(ptr, old, new)					\
-	__sync_cmpxchg((ptr), (old), (new), sizeof(*ptr))
+	__sync_cmpxchg(ptr, old, new, sizeof(*(ptr)))
 
 #define cmpxchg_local(ptr, old, new)					\
-	__cmpxchg_local((ptr), (old), (new), sizeof(*ptr))
+	__cmpxchg_local(ptr, old, new, sizeof(*(ptr)))
 #endif
 
 /*
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 17c5d4bdee5e..8d67d428b0f9 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -159,6 +159,7 @@
 #define X86_FEATURE_WDT		(6*32+13) /* Watchdog timer */
 #define X86_FEATURE_LWP		(6*32+15) /* Light Weight Profiling */
 #define X86_FEATURE_FMA4	(6*32+16) /* 4 operands MAC instructions */
+#define X86_FEATURE_TCE		(6*32+17) /* translation cache extension */
 #define X86_FEATURE_NODEID_MSR	(6*32+19) /* NodeId MSR */
 #define X86_FEATURE_TBM		(6*32+21) /* trailing bit manipulations */
 #define X86_FEATURE_TOPOEXT	(6*32+22) /* topology extensions CPUID leafs */
diff --git a/arch/x86/include/asm/i387.h b/arch/x86/include/asm/i387.h
index 6919e936345b..a850b4d8d14d 100644
--- a/arch/x86/include/asm/i387.h
+++ b/arch/x86/include/asm/i387.h
@@ -29,8 +29,8 @@ extern unsigned int sig_xstate_size;
 extern void fpu_init(void);
 extern void mxcsr_feature_mask_init(void);
 extern int init_fpu(struct task_struct *child);
-extern asmlinkage void math_state_restore(void);
-extern void __math_state_restore(void);
+extern void __math_state_restore(struct task_struct *);
+extern void math_state_restore(void);
 extern int dump_fpu(struct pt_regs *, struct user_i387_struct *);
 
 extern user_regset_active_fn fpregs_active, xfpregs_active;
@@ -212,19 +212,11 @@ static inline void fpu_fxsave(struct fpu *fpu)
 
 #endif	/* CONFIG_X86_64 */
 
-/* We need a safe address that is cheap to find and that is already
-   in L1 during context switch. The best choices are unfortunately
-   different for UP and SMP */
-#ifdef CONFIG_SMP
-#define safe_address (__per_cpu_offset[0])
-#else
-#define safe_address (__get_cpu_var(kernel_cpustat).cpustat[CPUTIME_USER])
-#endif
-
 /*
- * These must be called with preempt disabled
+ * These must be called with preempt disabled. Returns
+ * 'true' if the FPU state is still intact.
  */
-static inline void fpu_save_init(struct fpu *fpu)
+static inline int fpu_save_init(struct fpu *fpu)
 {
 	if (use_xsave()) {
 		fpu_xsave(fpu);
@@ -233,33 +225,33 @@ static inline void fpu_save_init(struct fpu *fpu)
 		 * xsave header may indicate the init state of the FP.
 		 */
 		if (!(fpu->state->xsave.xsave_hdr.xstate_bv & XSTATE_FP))
-			return;
+			return 1;
 	} else if (use_fxsr()) {
 		fpu_fxsave(fpu);
 	} else {
 		asm volatile("fnsave %[fx]; fwait"
 			     : [fx] "=m" (fpu->state->fsave));
-		return;
+		return 0;
 	}
 
-	if (unlikely(fpu->state->fxsave.swd & X87_FSW_ES))
+	/*
+	 * If exceptions are pending, we need to clear them so
+	 * that we don't randomly get exceptions later.
+	 *
+	 * FIXME! Is this perhaps only true for the old-style
+	 * irq13 case? Maybe we could leave the x87 state
+	 * intact otherwise?
+	 */
+	if (unlikely(fpu->state->fxsave.swd & X87_FSW_ES)) {
 		asm volatile("fnclex");
-
-	/* AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception
-	   is pending.  Clear the x87 state here by setting it to fixed
-	   values. safe_address is a random variable that should be in L1 */
-	alternative_input(
-		ASM_NOP8 ASM_NOP2,
-		"emms\n\t"	  	/* clear stack tags */
-		"fildl %P[addr]",	/* set F?P to defined value */
-		X86_FEATURE_FXSAVE_LEAK,
-		[addr] "m" (safe_address));
+		return 0;
+	}
+	return 1;
 }
 
-static inline void __save_init_fpu(struct task_struct *tsk)
+static inline int __save_init_fpu(struct task_struct *tsk)
 {
-	fpu_save_init(&tsk->thread.fpu);
-	task_thread_info(tsk)->status &= ~TS_USEDFPU;
+	return fpu_save_init(&tsk->thread.fpu);
 }
 
 static inline int fpu_fxrstor_checking(struct fpu *fpu)
@@ -281,39 +273,185 @@ static inline int restore_fpu_checking(struct task_struct *tsk)
 }
 
 /*
- * Signal frame handlers...
+ * Software FPU state helpers. Careful: these need to
+ * be preemption protection *and* they need to be
+ * properly paired with the CR0.TS changes!
  */
-extern int save_i387_xstate(void __user *buf);
-extern int restore_i387_xstate(void __user *buf);
+static inline int __thread_has_fpu(struct task_struct *tsk)
+{
+	return tsk->thread.has_fpu;
+}
 
-static inline void __unlazy_fpu(struct task_struct *tsk)
+/* Must be paired with an 'stts' after! */
+static inline void __thread_clear_has_fpu(struct task_struct *tsk)
 {
-	if (task_thread_info(tsk)->status & TS_USEDFPU) {
-		__save_init_fpu(tsk);
-		stts();
-	} else
-		tsk->fpu_counter = 0;
+	tsk->thread.has_fpu = 0;
+}
+
+/* Must be paired with a 'clts' before! */
+static inline void __thread_set_has_fpu(struct task_struct *tsk)
+{
+	tsk->thread.has_fpu = 1;
 }
 
+/*
+ * Encapsulate the CR0.TS handling together with the
+ * software flag.
+ *
+ * These generally need preemption protection to work,
+ * do try to avoid using these on their own.
+ */
+static inline void __thread_fpu_end(struct task_struct *tsk)
+{
+	__thread_clear_has_fpu(tsk);
+	stts();
+}
+
+static inline void __thread_fpu_begin(struct task_struct *tsk)
+{
+	clts();
+	__thread_set_has_fpu(tsk);
+}
+
+/*
+ * FPU state switching for scheduling.
+ *
+ * This is a two-stage process:
+ *
+ *  - switch_fpu_prepare() saves the old state and
+ *    sets the new state of the CR0.TS bit. This is
+ *    done within the context of the old process.
+ *
+ *  - switch_fpu_finish() restores the new state as
+ *    necessary.
+ */
+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.
+ *
+ * We don't do that yet, so "fpu_lazy_restore()" always returns
+ * false, but some day..
+ */
+#define fpu_lazy_restore(tsk) (0)
+#define fpu_lazy_state_intact(tsk) do { } while (0)
+
+static inline fpu_switch_t switch_fpu_prepare(struct task_struct *old, struct task_struct *new)
+{
+	fpu_switch_t fpu;
+
+	fpu.preload = tsk_used_math(new) && new->fpu_counter > 5;
+	if (__thread_has_fpu(old)) {
+		if (__save_init_fpu(old))
+			fpu_lazy_state_intact(old);
+		__thread_clear_has_fpu(old);
+		old->fpu_counter++;
+
+		/* Don't change CR0.TS if we just switch! */
+		if (fpu.preload) {
+			__thread_set_has_fpu(new);
+			prefetch(new->thread.fpu.state);
+		} else
+			stts();
+	} else {
+		old->fpu_counter = 0;
+		if (fpu.preload) {
+			if (fpu_lazy_restore(new))
+				fpu.preload = 0;
+			else
+				prefetch(new->thread.fpu.state);
+			__thread_fpu_begin(new);
+		}
+	}
+	return fpu;
+}
+
+/*
+ * By the time this gets called, we've already cleared CR0.TS and
+ * given the process the FPU if we are going to preload the FPU
+ * state - all we need to do is to conditionally restore the register
+ * state itself.
+ */
+static inline void switch_fpu_finish(struct task_struct *new, fpu_switch_t fpu)
+{
+	if (fpu.preload)
+		__math_state_restore(new);
+}
+
+/*
+ * Signal frame handlers...
+ */
+extern int save_i387_xstate(void __user *buf);
+extern int restore_i387_xstate(void __user *buf);
+
 static inline void __clear_fpu(struct task_struct *tsk)
 {
-	if (task_thread_info(tsk)->status & TS_USEDFPU) {
+	if (__thread_has_fpu(tsk)) {
 		/* Ignore delayed exceptions from user space */
 		asm volatile("1: fwait\n"
 			     "2:\n"
 			     _ASM_EXTABLE(1b, 2b));
-		task_thread_info(tsk)->status &= ~TS_USEDFPU;
-		stts();
+		__thread_fpu_end(tsk);
 	}
 }
 
+/*
+ * Were we in an interrupt that interrupted kernel mode?
+ *
+ * We can do a kernel_fpu_begin/end() pair *ONLY* if that
+ * pair does nothing at all: the thread must not have fpu (so
+ * that we don't try to save the FPU state), and TS must
+ * be set (so that the clts/stts pair does nothing that is
+ * visible in the interrupted kernel thread).
+ */
+static inline bool interrupted_kernel_fpu_idle(void)
+{
+	return !__thread_has_fpu(current) &&
+		(read_cr0() & X86_CR0_TS);
+}
+
+/*
+ * Were we in user mode (or vm86 mode) when we were
+ * interrupted?
+ *
+ * Doing kernel_fpu_begin/end() is ok if we are running
+ * in an interrupt context from user mode - we'll just
+ * save the FPU state as required.
+ */
+static inline bool interrupted_user_mode(void)
+{
+	struct pt_regs *regs = get_irq_regs();
+	return regs && user_mode_vm(regs);
+}
+
+/*
+ * Can we use the FPU in kernel mode with the
+ * whole "kernel_fpu_begin/end()" sequence?
+ *
+ * It's always ok in process context (ie "not interrupt")
+ * but it is sometimes ok even from an irq.
+ */
+static inline bool irq_fpu_usable(void)
+{
+	return !in_interrupt() ||
+		interrupted_user_mode() ||
+		interrupted_kernel_fpu_idle();
+}
+
 static inline void kernel_fpu_begin(void)
 {
-	struct thread_info *me = current_thread_info();
+	struct task_struct *me = current;
+
+	WARN_ON_ONCE(!irq_fpu_usable());
 	preempt_disable();
-	if (me->status & TS_USEDFPU)
-		__save_init_fpu(me->task);
-	else
+	if (__thread_has_fpu(me)) {
+		__save_init_fpu(me);
+		__thread_clear_has_fpu(me);
+		/* We do 'stts()' in kernel_fpu_end() */
+	} else
 		clts();
 }
 
@@ -323,14 +461,6 @@ static inline void kernel_fpu_end(void)
 	preempt_enable();
 }
 
-static inline bool irq_fpu_usable(void)
-{
-	struct pt_regs *regs;
-
-	return !in_interrupt() || !(regs = get_irq_regs()) || \
-		user_mode(regs) || (read_cr0() & X86_CR0_TS);
-}
-
 /*
  * Some instructions like VIA's padlock instructions generate a spurious
  * DNA fault but don't modify SSE registers. And these instructions
@@ -363,20 +493,64 @@ static inline void irq_ts_restore(int TS_state)
 }
 
 /*
+ * The question "does this thread have fpu access?"
+ * is slightly racy, since preemption could come in
+ * and revoke it immediately after the test.
+ *
+ * However, even in that very unlikely scenario,
+ * we can just assume we have FPU access - typically
+ * to save the FP state - we'll just take a #NM
+ * fault and get the FPU access back.
+ *
+ * The actual user_fpu_begin/end() functions
+ * need to be preemption-safe, though.
+ *
+ * NOTE! user_fpu_end() must be used only after you
+ * have saved the FP state, and user_fpu_begin() must
+ * be used only immediately before restoring it.
+ * These functions do not do any save/restore on
+ * their own.
+ */
+static inline int user_has_fpu(void)
+{
+	return __thread_has_fpu(current);
+}
+
+static inline void user_fpu_end(void)
+{
+	preempt_disable();
+	__thread_fpu_end(current);
+	preempt_enable();
+}
+
+static inline void user_fpu_begin(void)
+{
+	preempt_disable();
+	if (!user_has_fpu())
+		__thread_fpu_begin(current);
+	preempt_enable();
+}
+
+/*
  * These disable preemption on their own and are safe
  */
 static inline void save_init_fpu(struct task_struct *tsk)
 {
+	WARN_ON_ONCE(!__thread_has_fpu(tsk));
 	preempt_disable();
 	__save_init_fpu(tsk);
-	stts();
+	__thread_fpu_end(tsk);
 	preempt_enable();
 }
 
 static inline void unlazy_fpu(struct task_struct *tsk)
 {
 	preempt_disable();
-	__unlazy_fpu(tsk);
+	if (__thread_has_fpu(tsk)) {
+		__save_init_fpu(tsk);
+		__thread_fpu_end(tsk);
+	} else
+		tsk->fpu_counter = 0;
 	preempt_enable();
 }
 
diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h
index ab4092e3214e..7b9cfc4878af 100644
--- a/arch/x86/include/asm/kvm_emulate.h
+++ b/arch/x86/include/asm/kvm_emulate.h
@@ -190,6 +190,9 @@ struct x86_emulate_ops {
 	int (*intercept)(struct x86_emulate_ctxt *ctxt,
 			 struct x86_instruction_info *info,
 			 enum x86_intercept_stage stage);
+
+	bool (*get_cpuid)(struct x86_emulate_ctxt *ctxt,
+			 u32 *eax, u32 *ebx, u32 *ecx, u32 *edx);
 };
 
 typedef u32 __attribute__((vector_size(16))) sse128_t;
@@ -298,6 +301,19 @@ struct x86_emulate_ctxt {
 #define X86EMUL_MODE_PROT     (X86EMUL_MODE_PROT16|X86EMUL_MODE_PROT32| \
 			       X86EMUL_MODE_PROT64)
 
+/* CPUID vendors */
+#define X86EMUL_CPUID_VENDOR_AuthenticAMD_ebx 0x68747541
+#define X86EMUL_CPUID_VENDOR_AuthenticAMD_ecx 0x444d4163
+#define X86EMUL_CPUID_VENDOR_AuthenticAMD_edx 0x69746e65
+
+#define X86EMUL_CPUID_VENDOR_AMDisbetterI_ebx 0x69444d41
+#define X86EMUL_CPUID_VENDOR_AMDisbetterI_ecx 0x21726574
+#define X86EMUL_CPUID_VENDOR_AMDisbetterI_edx 0x74656273
+
+#define X86EMUL_CPUID_VENDOR_GenuineIntel_ebx 0x756e6547
+#define X86EMUL_CPUID_VENDOR_GenuineIntel_ecx 0x6c65746e
+#define X86EMUL_CPUID_VENDOR_GenuineIntel_edx 0x49656e69
+
 enum x86_intercept_stage {
 	X86_ICTP_NONE = 0,   /* Allow zero-init to not match anything */
 	X86_ICPT_PRE_EXCEPT,
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index aa9088c26931..f7c89e231c6c 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -454,6 +454,7 @@ struct thread_struct {
 	unsigned long		trap_no;
 	unsigned long		error_code;
 	/* floating point and extended processor state */
+	unsigned long		has_fpu;
 	struct fpu		fpu;
 #ifdef CONFIG_X86_32
 	/* Virtual 86 mode info */
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index bc817cd8b443..cfd8144d5527 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -247,8 +247,6 @@ static inline struct thread_info *current_thread_info(void)
  * ever touches our thread-synchronous status, so we don't
  * have to worry about atomic accesses.
  */
-#define TS_USEDFPU		0x0001	/* FPU was used by this task
-					   this quantum (SMP) */
 #define TS_COMPAT		0x0002	/* 32bit syscall active (64BIT)*/
 #define TS_POLLING		0x0004	/* idle task polling need_resched,
 					   skip sending interrupt */
diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h
index 54a13aaebc40..21f7385badb8 100644
--- a/arch/x86/include/asm/uv/uv_hub.h
+++ b/arch/x86/include/asm/uv/uv_hub.h
@@ -318,13 +318,13 @@ uv_gpa_in_mmr_space(unsigned long gpa)
 /* UV global physical address --> socket phys RAM */
 static inline unsigned long uv_gpa_to_soc_phys_ram(unsigned long gpa)
 {
-	unsigned long paddr = gpa & uv_hub_info->gpa_mask;
+	unsigned long paddr;
 	unsigned long remap_base = uv_hub_info->lowmem_remap_base;
 	unsigned long remap_top =  uv_hub_info->lowmem_remap_top;
 
 	gpa = ((gpa << uv_hub_info->m_shift) >> uv_hub_info->m_shift) |
 		((gpa >> uv_hub_info->n_lshift) << uv_hub_info->m_val);
-	gpa = gpa & uv_hub_info->gpa_mask;
+	paddr = gpa & uv_hub_info->gpa_mask;
 	if (paddr >= remap_base && paddr < remap_base + remap_top)
 		paddr -= remap_base;
 	return paddr;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index 73da6b64f5b7..d6bd49faa40c 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -439,7 +439,6 @@ void intel_pmu_pebs_enable(struct perf_event *event)
 	hwc->config &= ~ARCH_PERFMON_EVENTSEL_INT;
 
 	cpuc->pebs_enabled |= 1ULL << hwc->idx;
-	WARN_ON_ONCE(cpuc->enabled);
 
 	if (x86_pmu.intel_cap.pebs_trap && event->attr.precise_ip > 1)
 		intel_pmu_lbr_enable(event);
diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
index 3fab3de3ce96..47a7e63bfe54 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
@@ -72,8 +72,6 @@ void intel_pmu_lbr_enable(struct perf_event *event)
 	if (!x86_pmu.lbr_nr)
 		return;
 
-	WARN_ON_ONCE(cpuc->enabled);
-
 	/*
 	 * Reset the LBR stack if we changed task context to
 	 * avoid data leaks.
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index 1aae78f775fc..4025fe4f928f 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -252,7 +252,8 @@ int __kprobes __die(const char *str, struct pt_regs *regs, long err)
 	unsigned short ss;
 	unsigned long sp;
 #endif
-	printk(KERN_EMERG "%s: %04lx [#%d] ", str, err & 0xffff, ++die_counter);
+	printk(KERN_DEFAULT
+	       "%s: %04lx [#%d] ", str, err & 0xffff, ++die_counter);
 #ifdef CONFIG_PREEMPT
 	printk("PREEMPT ");
 #endif
diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index 6d728d9284bd..17107bd6e1f0 100644
--- a/arch/x86/kernel/dumpstack_64.c
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -129,7 +129,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
 	if (!stack) {
 		if (regs)
 			stack = (unsigned long *)regs->sp;
-		else if (task && task != current)
+		else if (task != current)
 			stack = (unsigned long *)task->thread.sp;
 		else
 			stack = &dummy;
@@ -269,11 +269,11 @@ void show_registers(struct pt_regs *regs)
 		unsigned char c;
 		u8 *ip;
 
-		printk(KERN_EMERG "Stack:\n");
+		printk(KERN_DEFAULT "Stack:\n");
 		show_stack_log_lvl(NULL, regs, (unsigned long *)sp,
-				   0, KERN_EMERG);
+				   0, KERN_DEFAULT);
 
-		printk(KERN_EMERG "Code: ");
+		printk(KERN_DEFAULT "Code: ");
 
 		ip = (u8 *)regs->ip - code_prologue;
 		if (ip < (u8 *)PAGE_OFFSET || probe_kernel_address(ip, c)) {
diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c
index fe86493f3ed1..ac0417be9131 100644
--- a/arch/x86/kernel/microcode_amd.c
+++ b/arch/x86/kernel/microcode_amd.c
@@ -311,13 +311,33 @@ out:
 	return state;
 }
 
+/*
+ * AMD microcode firmware naming convention, up to family 15h they are in
+ * the legacy file:
+ *
+ *    amd-ucode/microcode_amd.bin
+ *
+ * This legacy file is always smaller than 2K in size.
+ *
+ * Starting at family 15h they are in family specific firmware files:
+ *
+ *    amd-ucode/microcode_amd_fam15h.bin
+ *    amd-ucode/microcode_amd_fam16h.bin
+ *    ...
+ *
+ * These might be larger than 2K.
+ */
 static enum ucode_state request_microcode_amd(int cpu, struct device *device)
 {
-	const char *fw_name = "amd-ucode/microcode_amd.bin";
+	char fw_name[36] = "amd-ucode/microcode_amd.bin";
 	const struct firmware *fw;
 	enum ucode_state ret = UCODE_NFOUND;
+	struct cpuinfo_x86 *c = &cpu_data(cpu);
+
+	if (c->x86 >= 0x15)
+		snprintf(fw_name, sizeof(fw_name), "amd-ucode/microcode_amd_fam%.2xh.bin", c->x86);
 
-	if (request_firmware(&fw, fw_name, device)) {
+	if (request_firmware(&fw, (const char *)fw_name, device)) {
 		pr_err("failed to load file %s\n", fw_name);
 		goto out;
 	}
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 485204f58cda..80bfe1ab0031 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -299,22 +299,11 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 				 *next = &next_p->thread;
 	int cpu = smp_processor_id();
 	struct tss_struct *tss = &per_cpu(init_tss, cpu);
-	bool preload_fpu;
+	fpu_switch_t fpu;
 
 	/* never put a printk in __switch_to... printk() calls wake_up*() indirectly */
 
-	/*
-	 * If the task has used fpu the last 5 timeslices, just do a full
-	 * restore of the math state immediately to avoid the trap; the
-	 * chances of needing FPU soon are obviously high now
-	 */
-	preload_fpu = tsk_used_math(next_p) && next_p->fpu_counter > 5;
-
-	__unlazy_fpu(prev_p);
-
-	/* we're going to use this soon, after a few expensive things */
-	if (preload_fpu)
-		prefetch(next->fpu.state);
+	fpu = switch_fpu_prepare(prev_p, next_p);
 
 	/*
 	 * Reload esp0.
@@ -354,11 +343,6 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 		     task_thread_info(next_p)->flags & _TIF_WORK_CTXSW_NEXT))
 		__switch_to_xtra(prev_p, next_p, tss);
 
-	/* If we're going to preload the fpu context, make sure clts
-	   is run while we're batching the cpu state updates. */
-	if (preload_fpu)
-		clts();
-
 	/*
 	 * Leave lazy mode, flushing any hypercalls made here.
 	 * This must be done before restoring TLS segments so
@@ -368,15 +352,14 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	 */
 	arch_end_context_switch(next_p);
 
-	if (preload_fpu)
-		__math_state_restore();
-
 	/*
 	 * Restore %gs if needed (which is common)
 	 */
 	if (prev->gs | next->gs)
 		lazy_load_gs(next->gs);
 
+	switch_fpu_finish(next_p, fpu);
+
 	percpu_write(current_task, next_p);
 
 	return prev_p;
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 9b9fe4a85c87..1fd94bc4279d 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -386,18 +386,9 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	int cpu = smp_processor_id();
 	struct tss_struct *tss = &per_cpu(init_tss, cpu);
 	unsigned fsindex, gsindex;
-	bool preload_fpu;
+	fpu_switch_t fpu;
 
-	/*
-	 * If the task has used fpu the last 5 timeslices, just do a full
-	 * restore of the math state immediately to avoid the trap; the
-	 * chances of needing FPU soon are obviously high now
-	 */
-	preload_fpu = tsk_used_math(next_p) && next_p->fpu_counter > 5;
-
-	/* we're going to use this soon, after a few expensive things */
-	if (preload_fpu)
-		prefetch(next->fpu.state);
+	fpu = switch_fpu_prepare(prev_p, next_p);
 
 	/*
 	 * Reload esp0, LDT and the page table pointer:
@@ -427,13 +418,6 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 
 	load_TLS(next, cpu);
 
-	/* Must be after DS reload */
-	__unlazy_fpu(prev_p);
-
-	/* Make sure cpu is ready for new context */
-	if (preload_fpu)
-		clts();
-
 	/*
 	 * Leave lazy mode, flushing any hypercalls made here.
 	 * This must be done before restoring TLS segments so
@@ -474,6 +458,8 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 		wrmsrl(MSR_KERNEL_GS_BASE, next->gs);
 	prev->gsindex = gsindex;
 
+	switch_fpu_finish(next_p, fpu);
+
 	/*
 	 * Switch the PDA and FPU contexts.
 	 */
@@ -492,13 +478,6 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 		     task_thread_info(prev_p)->flags & _TIF_WORK_CTXSW_PREV))
 		__switch_to_xtra(prev_p, next_p, tss);
 
-	/*
-	 * Preload the FPU context, now that we've determined that the
-	 * task is likely to be using it. 
-	 */
-	if (preload_fpu)
-		__math_state_restore();
-
 	return prev_p;
 }
 
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 37a458b521a6..d840e69a853c 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -39,6 +39,14 @@ static int reboot_mode;
 enum reboot_type reboot_type = BOOT_ACPI;
 int reboot_force;
 
+/* This variable is used privately to keep track of whether or not
+ * reboot_type is still set to its default value (i.e., reboot= hasn't
+ * been set on the command line).  This is needed so that we can
+ * suppress DMI scanning for reboot quirks.  Without it, it's
+ * impossible to override a faulty reboot quirk without recompiling.
+ */
+static int reboot_default = 1;
+
 #if defined(CONFIG_X86_32) && defined(CONFIG_SMP)
 static int reboot_cpu = -1;
 #endif
@@ -67,6 +75,12 @@ bool port_cf9_safe = false;
 static int __init reboot_setup(char *str)
 {
 	for (;;) {
+		/* Having anything passed on the command line via
+		 * reboot= will cause us to disable DMI checking
+		 * below.
+		 */
+		reboot_default = 0;
+
 		switch (*str) {
 		case 'w':
 			reboot_mode = 0x1234;
@@ -295,14 +309,6 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = {
 			DMI_MATCH(DMI_BOARD_NAME, "P4S800"),
 		},
 	},
-	{	/* Handle problems with rebooting on VersaLogic Menlow boards */
-		.callback = set_bios_reboot,
-		.ident = "VersaLogic Menlow based board",
-		.matches = {
-			DMI_MATCH(DMI_BOARD_VENDOR, "VersaLogic Corporation"),
-			DMI_MATCH(DMI_BOARD_NAME, "VersaLogic Menlow board"),
-		},
-	},
 	{ /* Handle reboot issue on Acer Aspire one */
 		.callback = set_kbd_reboot,
 		.ident = "Acer Aspire One A110",
@@ -316,7 +322,12 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = {
 
 static int __init reboot_init(void)
 {
-	dmi_check_system(reboot_dmi_table);
+	/* Only do the DMI check if reboot_type hasn't been overridden
+	 * on the command line
+	 */
+	if (reboot_default) {
+		dmi_check_system(reboot_dmi_table);
+	}
 	return 0;
 }
 core_initcall(reboot_init);
@@ -465,7 +476,12 @@ static struct dmi_system_id __initdata pci_reboot_dmi_table[] = {
 
 static int __init pci_reboot_init(void)
 {
-	dmi_check_system(pci_reboot_dmi_table);
+	/* Only do the DMI check if reboot_type hasn't been overridden
+	 * on the command line
+	 */
+	if (reboot_default) {
+		dmi_check_system(pci_reboot_dmi_table);
+	}
 	return 0;
 }
 core_initcall(pci_reboot_init);
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 482ec3af2067..77da5b475ad2 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -571,25 +571,34 @@ asmlinkage void __attribute__((weak)) smp_threshold_interrupt(void)
 }
 
 /*
- * __math_state_restore assumes that cr0.TS is already clear and the
- * fpu state is all ready for use.  Used during context switch.
+ * This gets called with the process already owning the
+ * FPU state, and with CR0.TS cleared. It just needs to
+ * restore the FPU register state.
  */
-void __math_state_restore(void)
+void __math_state_restore(struct task_struct *tsk)
 {
-	struct thread_info *thread = current_thread_info();
-	struct task_struct *tsk = thread->task;
+	/* We need a safe address that is cheap to find and that is already
+	   in L1. We've just brought in "tsk->thread.has_fpu", so use that */
+#define safe_address (tsk->thread.has_fpu)
+
+	/* AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception
+	   is pending.  Clear the x87 state here by setting it to fixed
+	   values. safe_address is a random variable that should be in L1 */
+	alternative_input(
+		ASM_NOP8 ASM_NOP2,
+		"emms\n\t"	  	/* clear stack tags */
+		"fildl %P[addr]",	/* set F?P to defined value */
+		X86_FEATURE_FXSAVE_LEAK,
+		[addr] "m" (safe_address));
 
 	/*
 	 * Paranoid restore. send a SIGSEGV if we fail to restore the state.
 	 */
 	if (unlikely(restore_fpu_checking(tsk))) {
-		stts();
+		__thread_fpu_end(tsk);
 		force_sig(SIGSEGV, tsk);
 		return;
 	}
-
-	thread->status |= TS_USEDFPU;	/* So we fnsave on switch_to() */
-	tsk->fpu_counter++;
 }
 
 /*
@@ -599,13 +608,12 @@ void __math_state_restore(void)
  * Careful.. There are problems with IBM-designed IRQ13 behaviour.
  * Don't touch unless you *really* know how it works.
  *
- * Must be called with kernel preemption disabled (in this case,
- * local interrupts are disabled at the call-site in entry.S).
+ * Must be called with kernel preemption disabled (eg with local
+ * local interrupts as in the case of do_device_not_available).
  */
-asmlinkage void math_state_restore(void)
+void math_state_restore(void)
 {
-	struct thread_info *thread = current_thread_info();
-	struct task_struct *tsk = thread->task;
+	struct task_struct *tsk = current;
 
 	if (!tsk_used_math(tsk)) {
 		local_irq_enable();
@@ -622,9 +630,10 @@ asmlinkage void math_state_restore(void)
 		local_irq_disable();
 	}
 
-	clts();				/* Allow maths ops (or we recurse) */
+	__thread_fpu_begin(tsk);
+	__math_state_restore(tsk);
 
-	__math_state_restore();
+	tsk->fpu_counter++;
 }
 EXPORT_SYMBOL_GPL(math_state_restore);
 
diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c
index a3911343976b..711091114119 100644
--- a/arch/x86/kernel/xsave.c
+++ b/arch/x86/kernel/xsave.c
@@ -47,7 +47,7 @@ void __sanitize_i387_state(struct task_struct *tsk)
 	if (!fx)
 		return;
 
-	BUG_ON(task_thread_info(tsk)->status & TS_USEDFPU);
+	BUG_ON(__thread_has_fpu(tsk));
 
 	xstate_bv = tsk->thread.fpu.state->xsave.xsave_hdr.xstate_bv;
 
@@ -168,7 +168,7 @@ int save_i387_xstate(void __user *buf)
 	if (!used_math())
 		return 0;
 
-	if (task_thread_info(tsk)->status & TS_USEDFPU) {
+	if (user_has_fpu()) {
 		if (use_xsave())
 			err = xsave_user(buf);
 		else
@@ -176,8 +176,7 @@ int save_i387_xstate(void __user *buf)
 
 		if (err)
 			return err;
-		task_thread_info(tsk)->status &= ~TS_USEDFPU;
-		stts();
+		user_fpu_end();
 	} else {
 		sanitize_i387_state(tsk);
 		if (__copy_to_user(buf, &tsk->thread.fpu.state->fxsave,
@@ -292,10 +291,7 @@ int restore_i387_xstate(void __user *buf)
 			return err;
 	}
 
-	if (!(task_thread_info(current)->status & TS_USEDFPU)) {
-		clts();
-		task_thread_info(current)->status |= TS_USEDFPU;
-	}
+	user_fpu_begin();
 	if (use_xsave())
 		err = restore_user_xstate(buf);
 	else
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 05a562b85025..0982507b962a 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -1891,6 +1891,51 @@ setup_syscalls_segments(struct x86_emulate_ctxt *ctxt,
 	ss->p = 1;
 }
 
+static bool em_syscall_is_enabled(struct x86_emulate_ctxt *ctxt)
+{
+	struct x86_emulate_ops *ops = ctxt->ops;
+	u32 eax, ebx, ecx, edx;
+
+	/*
+	 * syscall should always be enabled in longmode - so only become
+	 * vendor specific (cpuid) if other modes are active...
+	 */
+	if (ctxt->mode == X86EMUL_MODE_PROT64)
+		return true;
+
+	eax = 0x00000000;
+	ecx = 0x00000000;
+	if (ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx)) {
+		/*
+		 * Intel ("GenuineIntel")
+		 * remark: Intel CPUs only support "syscall" in 64bit
+		 * longmode. Also an 64bit guest with a
+		 * 32bit compat-app running will #UD !! While this
+		 * behaviour can be fixed (by emulating) into AMD
+		 * response - CPUs of AMD can't behave like Intel.
+		 */
+		if (ebx == X86EMUL_CPUID_VENDOR_GenuineIntel_ebx &&
+		    ecx == X86EMUL_CPUID_VENDOR_GenuineIntel_ecx &&
+		    edx == X86EMUL_CPUID_VENDOR_GenuineIntel_edx)
+			return false;
+
+		/* AMD ("AuthenticAMD") */
+		if (ebx == X86EMUL_CPUID_VENDOR_AuthenticAMD_ebx &&
+		    ecx == X86EMUL_CPUID_VENDOR_AuthenticAMD_ecx &&
+		    edx == X86EMUL_CPUID_VENDOR_AuthenticAMD_edx)
+			return true;
+
+		/* AMD ("AMDisbetter!") */
+		if (ebx == X86EMUL_CPUID_VENDOR_AMDisbetterI_ebx &&
+		    ecx == X86EMUL_CPUID_VENDOR_AMDisbetterI_ecx &&
+		    edx == X86EMUL_CPUID_VENDOR_AMDisbetterI_edx)
+			return true;
+	}
+
+	/* default: (not Intel, not AMD), apply Intel's stricter rules... */
+	return false;
+}
+
 static int em_syscall(struct x86_emulate_ctxt *ctxt)
 {
 	struct x86_emulate_ops *ops = ctxt->ops;
@@ -1904,9 +1949,15 @@ static int em_syscall(struct x86_emulate_ctxt *ctxt)
 	    ctxt->mode == X86EMUL_MODE_VM86)
 		return emulate_ud(ctxt);
 
+	if (!(em_syscall_is_enabled(ctxt)))
+		return emulate_ud(ctxt);
+
 	ops->get_msr(ctxt, MSR_EFER, &efer);
 	setup_syscalls_segments(ctxt, &cs, &ss);
 
+	if (!(efer & EFER_SCE))
+		return emulate_ud(ctxt);
+
 	ops->get_msr(ctxt, MSR_STAR, &msr_data);
 	msr_data >>= 32;
 	cs_sel = (u16)(msr_data & 0xfffc);
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index d29216c462b3..3b4c8d8ad906 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -1457,7 +1457,7 @@ static void __vmx_load_host_state(struct vcpu_vmx *vmx)
 #ifdef CONFIG_X86_64
 	wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_host_kernel_gs_base);
 #endif
-	if (current_thread_info()->status & TS_USEDFPU)
+	if (__thread_has_fpu(current))
 		clts();
 	load_gdt(&__get_cpu_var(host_gdt));
 }
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 14d6cadc4ba6..9cbfc0698118 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1495,6 +1495,8 @@ static void record_steal_time(struct kvm_vcpu *vcpu)
 
 int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 {
+	bool pr = false;
+
 	switch (msr) {
 	case MSR_EFER:
 		return set_efer(vcpu, data);
@@ -1635,6 +1637,18 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 		pr_unimpl(vcpu, "unimplemented perfctr wrmsr: "
 			"0x%x data 0x%llx\n", msr, data);
 		break;
+	case MSR_P6_PERFCTR0:
+	case MSR_P6_PERFCTR1:
+		pr = true;
+	case MSR_P6_EVNTSEL0:
+	case MSR_P6_EVNTSEL1:
+		if (kvm_pmu_msr(vcpu, msr))
+			return kvm_pmu_set_msr(vcpu, msr, data);
+
+		if (pr || data != 0)
+			pr_unimpl(vcpu, "disabled perfctr wrmsr: "
+				"0x%x data 0x%llx\n", msr, data);
+		break;
 	case MSR_K7_CLK_CTL:
 		/*
 		 * Ignore all writes to this no longer documented MSR.
@@ -1835,6 +1849,14 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
 	case MSR_FAM10H_MMIO_CONF_BASE:
 		data = 0;
 		break;
+	case MSR_P6_PERFCTR0:
+	case MSR_P6_PERFCTR1:
+	case MSR_P6_EVNTSEL0:
+	case MSR_P6_EVNTSEL1:
+		if (kvm_pmu_msr(vcpu, msr))
+			return kvm_pmu_get_msr(vcpu, msr, pdata);
+		data = 0;
+		break;
 	case MSR_IA32_UCODE_REV:
 		data = 0x100000000ULL;
 		break;
@@ -4180,6 +4202,28 @@ static int emulator_intercept(struct x86_emulate_ctxt *ctxt,
 	return kvm_x86_ops->check_intercept(emul_to_vcpu(ctxt), info, stage);
 }
 
+static bool emulator_get_cpuid(struct x86_emulate_ctxt *ctxt,
+			       u32 *eax, u32 *ebx, u32 *ecx, u32 *edx)
+{
+	struct kvm_cpuid_entry2 *cpuid = NULL;
+
+	if (eax && ecx)
+		cpuid = kvm_find_cpuid_entry(emul_to_vcpu(ctxt),
+					    *eax, *ecx);
+
+	if (cpuid) {
+		*eax = cpuid->eax;
+		*ecx = cpuid->ecx;
+		if (ebx)
+			*ebx = cpuid->ebx;
+		if (edx)
+			*edx = cpuid->edx;
+		return true;
+	}
+
+	return false;
+}
+
 static struct x86_emulate_ops emulate_ops = {
 	.read_std            = kvm_read_guest_virt_system,
 	.write_std           = kvm_write_guest_virt_system,
@@ -4211,6 +4255,7 @@ static struct x86_emulate_ops emulate_ops = {
 	.get_fpu             = emulator_get_fpu,
 	.put_fpu             = emulator_put_fpu,
 	.intercept           = emulator_intercept,
+	.get_cpuid           = emulator_get_cpuid,
 };
 
 static void cache_all_regs(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 9d74824a708d..f0b4caf85c1a 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -673,7 +673,7 @@ no_context(struct pt_regs *regs, unsigned long error_code,
 
 	stackend = end_of_stack(tsk);
 	if (tsk != &init_task && *stackend != STACK_END_MAGIC)
-		printk(KERN_ALERT "Thread overran stack, or stack corrupted\n");
+		printk(KERN_EMERG "Thread overran stack, or stack corrupted\n");
 
 	tsk->thread.cr2		= address;
 	tsk->thread.trap_no	= 14;
@@ -684,7 +684,7 @@ no_context(struct pt_regs *regs, unsigned long error_code,
 		sig = 0;
 
 	/* Executive summary in case the body of the oops scrolled away */
-	printk(KERN_EMERG "CR2: %016lx\n", address);
+	printk(KERN_DEFAULT "CR2: %016lx\n", address);
 
 	oops_end(flags, regs, sig);
 }
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 7b65f752c5f8..7c1b765ecc59 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -151,17 +151,18 @@ void bpf_jit_compile(struct sk_filter *fp)
 	cleanup_addr = proglen; /* epilogue address */
 
 	for (pass = 0; pass < 10; pass++) {
+		u8 seen_or_pass0 = (pass == 0) ? (SEEN_XREG | SEEN_DATAREF | SEEN_MEM) : seen;
 		/* no prologue/epilogue for trivial filters (RET something) */
 		proglen = 0;
 		prog = temp;
 
-		if (seen) {
+		if (seen_or_pass0) {
 			EMIT4(0x55, 0x48, 0x89, 0xe5); /* push %rbp; mov %rsp,%rbp */
 			EMIT4(0x48, 0x83, 0xec, 96);	/* subq  $96,%rsp	*/
 			/* note : must save %rbx in case bpf_error is hit */
-			if (seen & (SEEN_XREG | SEEN_DATAREF))
+			if (seen_or_pass0 & (SEEN_XREG | SEEN_DATAREF))
 				EMIT4(0x48, 0x89, 0x5d, 0xf8); /* mov %rbx, -8(%rbp) */
-			if (seen & SEEN_XREG)
+			if (seen_or_pass0 & SEEN_XREG)
 				CLEAR_X(); /* make sure we dont leek kernel memory */
 
 			/*
@@ -170,7 +171,7 @@ void bpf_jit_compile(struct sk_filter *fp)
 			 *  r9 = skb->len - skb->data_len
 			 *  r8 = skb->data
 			 */
-			if (seen & SEEN_DATAREF) {
+			if (seen_or_pass0 & SEEN_DATAREF) {
 				if (offsetof(struct sk_buff, len) <= 127)
 					/* mov    off8(%rdi),%r9d */
 					EMIT4(0x44, 0x8b, 0x4f, offsetof(struct sk_buff, len));
@@ -260,9 +261,14 @@ void bpf_jit_compile(struct sk_filter *fp)
 			case BPF_S_ALU_DIV_X: /* A /= X; */
 				seen |= SEEN_XREG;
 				EMIT2(0x85, 0xdb);	/* test %ebx,%ebx */
-				if (pc_ret0 != -1)
-					EMIT_COND_JMP(X86_JE, addrs[pc_ret0] - (addrs[i] - 4));
-				else {
+				if (pc_ret0 > 0) {
+					/* addrs[pc_ret0 - 1] is start address of target
+					 * (addrs[i] - 4) is the address following this jmp
+					 * ("xor %edx,%edx; div %ebx" being 4 bytes long)
+					 */
+					EMIT_COND_JMP(X86_JE, addrs[pc_ret0 - 1] -
+								(addrs[i] - 4));
+				} else {
 					EMIT_COND_JMP(X86_JNE, 2 + 5);
 					CLEAR_A();
 					EMIT1_off32(0xe9, cleanup_addr - (addrs[i] - 4)); /* jmp .+off32 */
@@ -335,12 +341,12 @@ void bpf_jit_compile(struct sk_filter *fp)
 				}
 				/* fallinto */
 			case BPF_S_RET_A:
-				if (seen) {
+				if (seen_or_pass0) {
 					if (i != flen - 1) {
 						EMIT_JMP(cleanup_addr - addrs[i]);
 						break;
 					}
-					if (seen & SEEN_XREG)
+					if (seen_or_pass0 & SEEN_XREG)
 						EMIT4(0x48, 0x8b, 0x5d, 0xf8);  /* mov  -8(%rbp),%rbx */
 					EMIT1(0xc9);		/* leaveq */
 				}
@@ -483,8 +489,9 @@ common_load:			seen |= SEEN_DATAREF;
 				goto common_load;
 			case BPF_S_LDX_B_MSH:
 				if ((int)K < 0) {
-					if (pc_ret0 != -1) {
-						EMIT_JMP(addrs[pc_ret0] - addrs[i]);
+					if (pc_ret0 > 0) {
+						/* addrs[pc_ret0 - 1] is the start address */
+						EMIT_JMP(addrs[pc_ret0 - 1] - addrs[i]);
 						break;
 					}
 					CLEAR_A();
@@ -599,13 +606,14 @@ cond_branch:			f_offset = addrs[i + filter[i].jf] - addrs[i];
 		 * use it to give the cleanup instruction(s) addr
 		 */
 		cleanup_addr = proglen - 1; /* ret */
-		if (seen)
+		if (seen_or_pass0)
 			cleanup_addr -= 1; /* leaveq */
-		if (seen & SEEN_XREG)
+		if (seen_or_pass0 & SEEN_XREG)
 			cleanup_addr -= 4; /* mov  -8(%rbp),%rbx */
 
 		if (image) {
-			WARN_ON(proglen != oldproglen);
+			if (proglen != oldproglen)
+				pr_err("bpb_jit_compile proglen=%u != oldproglen=%u\n", proglen, oldproglen);
 			break;
 		}
 		if (proglen == oldproglen) {
diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c
index 492ade8c978e..d99346ea8fdb 100644
--- a/arch/x86/pci/xen.c
+++ b/arch/x86/pci/xen.c
@@ -374,7 +374,7 @@ int __init pci_xen_init(void)
 
 int __init pci_xen_hvm_init(void)
 {
-	if (!xen_feature(XENFEAT_hvm_pirqs))
+	if (!xen_have_vector_callback || !xen_feature(XENFEAT_hvm_pirqs))
 		return 0;
 
 #ifdef CONFIG_ACPI
diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c
index 9be4cff00a2d..3ae0e61abd23 100644
--- a/arch/x86/platform/uv/tlb_uv.c
+++ b/arch/x86/platform/uv/tlb_uv.c
@@ -1851,6 +1851,8 @@ static void __init init_per_cpu_tunables(void)
 		bcp->cong_reps			= congested_reps;
 		bcp->cong_period		= congested_period;
 		bcp->clocks_per_100_usec =	usec_2_cycles(100);
+		spin_lock_init(&bcp->queue_lock);
+		spin_lock_init(&bcp->uvhub_lock);
 	}
 }
 
diff --git a/arch/x86/platform/uv/uv_irq.c b/arch/x86/platform/uv/uv_irq.c
index 374a05d8ad22..f25c2765a5c9 100644
--- a/arch/x86/platform/uv/uv_irq.c
+++ b/arch/x86/platform/uv/uv_irq.c
@@ -25,7 +25,7 @@ struct uv_irq_2_mmr_pnode{
 	int			irq;
 };
 
-static spinlock_t		uv_irq_lock;
+static DEFINE_SPINLOCK(uv_irq_lock);
 static struct rb_root		uv_irq_root;
 
 static int uv_set_irq_affinity(struct irq_data *, const struct cpumask *, bool);
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index 041d4fe9dfe4..501d4e0244ba 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -409,6 +409,13 @@ static void __cpuinit xen_play_dead(void) /* used only with HOTPLUG_CPU */
 	play_dead_common();
 	HYPERVISOR_vcpu_op(VCPUOP_down, smp_processor_id(), NULL);
 	cpu_bringup();
+	/*
+	 * Balance out the preempt calls - as we are running in cpu_idle
+	 * loop which has been called at bootup from cpu_bringup_and_idle.
+	 * The cpucpu_bringup_and_idle called cpu_bringup which made a
+	 * preempt_disable() So this preempt_enable will balance it out.
+	 */
+	preempt_enable();
 }
 
 #else /* !CONFIG_HOTPLUG_CPU */
diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c
index cc9b1e182fcf..d69cc6c3f808 100644
--- a/arch/x86/xen/spinlock.c
+++ b/arch/x86/xen/spinlock.c
@@ -116,9 +116,26 @@ static inline void spin_time_accum_blocked(u64 start)
 }
 #endif  /* CONFIG_XEN_DEBUG_FS */
 
+/*
+ * Size struct xen_spinlock so it's the same as arch_spinlock_t.
+ */
+#if NR_CPUS < 256
+typedef u8 xen_spinners_t;
+# define inc_spinners(xl) \
+	asm(LOCK_PREFIX " incb %0" : "+m" ((xl)->spinners) : : "memory");
+# define dec_spinners(xl) \
+	asm(LOCK_PREFIX " decb %0" : "+m" ((xl)->spinners) : : "memory");
+#else
+typedef u16 xen_spinners_t;
+# define inc_spinners(xl) \
+	asm(LOCK_PREFIX " incw %0" : "+m" ((xl)->spinners) : : "memory");
+# define dec_spinners(xl) \
+	asm(LOCK_PREFIX " decw %0" : "+m" ((xl)->spinners) : : "memory");
+#endif
+
 struct xen_spinlock {
 	unsigned char lock;		/* 0 -> free; 1 -> locked */
-	unsigned short spinners;	/* count of waiting cpus */
+	xen_spinners_t spinners;	/* count of waiting cpus */
 };
 
 static int xen_spin_is_locked(struct arch_spinlock *lock)
@@ -164,8 +181,7 @@ static inline struct xen_spinlock *spinning_lock(struct xen_spinlock *xl)
 
 	wmb();			/* set lock of interest before count */
 
-	asm(LOCK_PREFIX " incw %0"
-	    : "+m" (xl->spinners) : : "memory");
+	inc_spinners(xl);
 
 	return prev;
 }
@@ -176,8 +192,7 @@ static inline struct xen_spinlock *spinning_lock(struct xen_spinlock *xl)
  */
 static inline void unspinning_lock(struct xen_spinlock *xl, struct xen_spinlock *prev)
 {
-	asm(LOCK_PREFIX " decw %0"
-	    : "+m" (xl->spinners) : : "memory");
+	dec_spinners(xl);
 	wmb();			/* decrement count before restoring lock */
 	__this_cpu_write(lock_spinners, prev);
 }
@@ -373,6 +388,8 @@ void xen_uninit_lock_cpu(int cpu)
 
 void __init xen_init_spinlocks(void)
 {
+	BUILD_BUG_ON(sizeof(struct xen_spinlock) > sizeof(arch_spinlock_t));
+
 	pv_lock_ops.spin_is_locked = xen_spin_is_locked;
 	pv_lock_ops.spin_is_contended = xen_spin_is_contended;
 	pv_lock_ops.spin_lock = xen_spin_lock;