Merge branch 'linus' into irq/core

Reason: Get upstream fixes integrated before further modifications.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

20 files changed, 192 insertions, 87 deletions

diff --git a/arch/x86/ia32/ia32_aout.c b/arch/x86/ia32/ia32_aout.c
index fd843877e841..39e49091f648 100644
--- a/arch/x86/ia32/ia32_aout.c
+++ b/arch/x86/ia32/ia32_aout.c
@@ -315,6 +315,13 @@ static int load_aout_binary(struct linux_binprm *bprm, struct pt_regs *regs)
 	current->mm->free_area_cache = TASK_UNMAPPED_BASE;
 	current->mm->cached_hole_size = 0;
 
+	retval = setup_arg_pages(bprm, IA32_STACK_TOP, EXSTACK_DEFAULT);
+	if (retval < 0) {
+		/* Someone check-me: is this error path enough? */
+		send_sig(SIGKILL, current, 0);
+		return retval;
+	}
+
 	install_exec_creds(bprm);
 	current->flags &= ~PF_FORKNOEXEC;
 
@@ -410,13 +417,6 @@ beyond_if:
 
 	set_brk(current->mm->start_brk, current->mm->brk);
 
-	retval = setup_arg_pages(bprm, IA32_STACK_TOP, EXSTACK_DEFAULT);
-	if (retval < 0) {
-		/* Someone check-me: is this error path enough? */
-		send_sig(SIGKILL, current, 0);
-		return retval;
-	}
-
 	current->mm->start_stack =
 		(unsigned long)create_aout_tables((char __user *)bprm->p, bprm);
 	/* start thread */
diff --git a/arch/x86/include/asm/i387.h b/arch/x86/include/asm/i387.h
index a850b4d8d14d..247904945d3f 100644
--- a/arch/x86/include/asm/i387.h
+++ b/arch/x86/include/asm/i387.h
@@ -29,10 +29,11 @@ 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 void __math_state_restore(struct task_struct *);
 extern void math_state_restore(void);
 extern int dump_fpu(struct pt_regs *, struct user_i387_struct *);
 
+DECLARE_PER_CPU(struct task_struct *, fpu_owner_task);
+
 extern user_regset_active_fn fpregs_active, xfpregs_active;
 extern user_regset_get_fn fpregs_get, xfpregs_get, fpregs_soft_get,
 				xstateregs_get;
@@ -269,6 +270,16 @@ static inline int fpu_restore_checking(struct fpu *fpu)
 
 static inline int restore_fpu_checking(struct task_struct *tsk)
 {
+	/* 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. "m" 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" (tsk->thread.fpu.has_fpu));
+
 	return fpu_restore_checking(&tsk->thread.fpu);
 }
 
@@ -279,19 +290,21 @@ static inline int restore_fpu_checking(struct task_struct *tsk)
  */
 static inline int __thread_has_fpu(struct task_struct *tsk)
 {
-	return tsk->thread.has_fpu;
+	return tsk->thread.fpu.has_fpu;
 }
 
 /* Must be paired with an 'stts' after! */
 static inline void __thread_clear_has_fpu(struct task_struct *tsk)
 {
-	tsk->thread.has_fpu = 0;
+	tsk->thread.fpu.has_fpu = 0;
+	percpu_write(fpu_owner_task, NULL);
 }
 
 /* Must be paired with a 'clts' before! */
 static inline void __thread_set_has_fpu(struct task_struct *tsk)
 {
-	tsk->thread.has_fpu = 1;
+	tsk->thread.fpu.has_fpu = 1;
+	percpu_write(fpu_owner_task, tsk);
 }
 
 /*
@@ -336,30 +349,36 @@ typedef struct { int preload; } fpu_switch_t;
  * 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 int fpu_lazy_restore(struct task_struct *new, unsigned int cpu)
+{
+	return new == percpu_read_stable(fpu_owner_task) &&
+		cpu == new->thread.fpu.last_cpu;
+}
 
-static inline fpu_switch_t switch_fpu_prepare(struct task_struct *old, struct task_struct *new)
+static inline fpu_switch_t switch_fpu_prepare(struct task_struct *old, struct task_struct *new, int cpu)
 {
 	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++;
+		if (!__save_init_fpu(old))
+			cpu = ~0;
+		old->thread.fpu.last_cpu = cpu;
+		old->thread.fpu.has_fpu = 0;	/* But leave fpu_owner_task! */
 
 		/* Don't change CR0.TS if we just switch! */
 		if (fpu.preload) {
+			new->fpu_counter++;
 			__thread_set_has_fpu(new);
 			prefetch(new->thread.fpu.state);
 		} else
 			stts();
 	} else {
 		old->fpu_counter = 0;
+		old->thread.fpu.last_cpu = ~0;
 		if (fpu.preload) {
-			if (fpu_lazy_restore(new))
+			new->fpu_counter++;
+			if (fpu_lazy_restore(new, cpu))
 				fpu.preload = 0;
 			else
 				prefetch(new->thread.fpu.state);
@@ -377,8 +396,10 @@ static inline fpu_switch_t switch_fpu_prepare(struct task_struct *old, struct ta
  */
 static inline void switch_fpu_finish(struct task_struct *new, fpu_switch_t fpu)
 {
-	if (fpu.preload)
-		__math_state_restore(new);
+	if (fpu.preload) {
+		if (unlikely(restore_fpu_checking(new)))
+			__thread_fpu_end(new);
+	}
 }
 
 /*
@@ -451,8 +472,10 @@ static inline void kernel_fpu_begin(void)
 		__save_init_fpu(me);
 		__thread_clear_has_fpu(me);
 		/* We do 'stts()' in kernel_fpu_end() */
-	} else
+	} else {
+		percpu_write(fpu_owner_task, NULL);
 		clts();
+	}
 }
 
 static inline void kernel_fpu_end(void)
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 096c975e099f..461ce432b1c2 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -242,4 +242,12 @@ static inline void perf_get_x86_pmu_capability(struct x86_pmu_capability *cap)
 static inline void perf_events_lapic_init(void)	{ }
 #endif
 
+#if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_AMD)
+ extern void amd_pmu_enable_virt(void);
+ extern void amd_pmu_disable_virt(void);
+#else
+ static inline void amd_pmu_enable_virt(void) { }
+ static inline void amd_pmu_disable_virt(void) { }
+#endif
+
 #endif /* _ASM_X86_PERF_EVENT_H */
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index f7c89e231c6c..58545c97d071 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -374,6 +374,8 @@ union thread_xstate {
 };
 
 struct fpu {
+	unsigned int last_cpu;
+	unsigned int has_fpu;
 	union thread_xstate *state;
 };
 
@@ -454,7 +456,6 @@ 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/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index d43cad74f166..c0f7d68d318f 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1044,6 +1044,9 @@ DEFINE_PER_CPU(char *, irq_stack_ptr) =
 
 DEFINE_PER_CPU(unsigned int, irq_count) = -1;
 
+DEFINE_PER_CPU(struct task_struct *, fpu_owner_task);
+EXPORT_PER_CPU_SYMBOL(fpu_owner_task);
+
 /*
  * Special IST stacks which the CPU switches to when it calls
  * an IST-marked descriptor entry. Up to 7 stacks (hardware
@@ -1111,6 +1114,8 @@ void debug_stack_reset(void)
 
 DEFINE_PER_CPU(struct task_struct *, current_task) = &init_task;
 EXPORT_PER_CPU_SYMBOL(current_task);
+DEFINE_PER_CPU(struct task_struct *, fpu_owner_task);
+EXPORT_PER_CPU_SYMBOL(fpu_owner_task);
 
 #ifdef CONFIG_CC_STACKPROTECTOR
 DEFINE_PER_CPU_ALIGNED(struct stack_canary, stack_canary);
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index 6b45e5e7a901..73d08ed98a64 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -326,8 +326,7 @@ static void __cpuinit amd_calc_l3_indices(struct amd_northbridge *nb)
 	l3->indices = (max(max3(sc0, sc1, sc2), sc3) << 10) - 1;
 }
 
-static void __cpuinit amd_init_l3_cache(struct _cpuid4_info_regs *this_leaf,
-					int index)
+static void __cpuinit amd_init_l3_cache(struct _cpuid4_info_regs *this_leaf, int index)
 {
 	int node;
 
@@ -725,14 +724,16 @@ static DEFINE_PER_CPU(struct _cpuid4_info *, ici_cpuid4_info);
 #define CPUID4_INFO_IDX(x, y)	(&((per_cpu(ici_cpuid4_info, x))[y]))
 
 #ifdef CONFIG_SMP
-static void __cpuinit cache_shared_cpu_map_setup(unsigned int cpu, int index)
+
+static int __cpuinit cache_shared_amd_cpu_map_setup(unsigned int cpu, int index)
 {
-	struct _cpuid4_info	*this_leaf, *sibling_leaf;
-	unsigned long num_threads_sharing;
-	int index_msb, i, sibling;
+	struct _cpuid4_info *this_leaf;
+	int ret, i, sibling;
 	struct cpuinfo_x86 *c = &cpu_data(cpu);
 
-	if ((index == 3) && (c->x86_vendor == X86_VENDOR_AMD)) {
+	ret = 0;
+	if (index == 3) {
+		ret = 1;
 		for_each_cpu(i, cpu_llc_shared_mask(cpu)) {
 			if (!per_cpu(ici_cpuid4_info, i))
 				continue;
@@ -743,8 +744,35 @@ static void __cpuinit cache_shared_cpu_map_setup(unsigned int cpu, int index)
 				set_bit(sibling, this_leaf->shared_cpu_map);
 			}
 		}
-		return;
+	} else if ((c->x86 == 0x15) && ((index == 1) || (index == 2))) {
+		ret = 1;
+		for_each_cpu(i, cpu_sibling_mask(cpu)) {
+			if (!per_cpu(ici_cpuid4_info, i))
+				continue;
+			this_leaf = CPUID4_INFO_IDX(i, index);
+			for_each_cpu(sibling, cpu_sibling_mask(cpu)) {
+				if (!cpu_online(sibling))
+					continue;
+				set_bit(sibling, this_leaf->shared_cpu_map);
+			}
+		}
 	}
+
+	return ret;
+}
+
+static void __cpuinit cache_shared_cpu_map_setup(unsigned int cpu, int index)
+{
+	struct _cpuid4_info *this_leaf, *sibling_leaf;
+	unsigned long num_threads_sharing;
+	int index_msb, i;
+	struct cpuinfo_x86 *c = &cpu_data(cpu);
+
+	if (c->x86_vendor == X86_VENDOR_AMD) {
+		if (cache_shared_amd_cpu_map_setup(cpu, index))
+			return;
+	}
+
 	this_leaf = CPUID4_INFO_IDX(cpu, index);
 	num_threads_sharing = 1 + this_leaf->base.eax.split.num_threads_sharing;
 
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index 786e76a86322..e4eeaaf58a47 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -528,6 +528,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank)
 
 	sprintf(name, "threshold_bank%i", bank);
 
+#ifdef CONFIG_SMP
 	if (cpu_data(cpu).cpu_core_id && shared_bank[bank]) {	/* symlink */
 		i = cpumask_first(cpu_llc_shared_mask(cpu));
 
@@ -553,6 +554,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank)
 
 		goto out;
 	}
+#endif
 
 	b = kzalloc(sizeof(struct threshold_bank), GFP_KERNEL);
 	if (!b) {
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 8944062f46e2..c30c807ddc72 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -147,7 +147,9 @@ struct cpu_hw_events {
 	/*
 	 * AMD specific bits
 	 */
-	struct amd_nb		*amd_nb;
+	struct amd_nb			*amd_nb;
+	/* Inverted mask of bits to clear in the perf_ctr ctrl registers */
+	u64				perf_ctr_virt_mask;
 
 	void				*kfree_on_online;
 };
@@ -417,9 +419,11 @@ void x86_pmu_disable_all(void);
 static inline void __x86_pmu_enable_event(struct hw_perf_event *hwc,
 					  u64 enable_mask)
 {
+	u64 disable_mask = __this_cpu_read(cpu_hw_events.perf_ctr_virt_mask);
+
 	if (hwc->extra_reg.reg)
 		wrmsrl(hwc->extra_reg.reg, hwc->extra_reg.config);
-	wrmsrl(hwc->config_base, hwc->config | enable_mask);
+	wrmsrl(hwc->config_base, (hwc->config | enable_mask) & ~disable_mask);
 }
 
 void x86_pmu_enable_all(int added);
diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c
index 0397b23be8e9..67250a52430b 100644
--- a/arch/x86/kernel/cpu/perf_event_amd.c
+++ b/arch/x86/kernel/cpu/perf_event_amd.c
@@ -1,4 +1,5 @@
 #include <linux/perf_event.h>
+#include <linux/export.h>
 #include <linux/types.h>
 #include <linux/init.h>
 #include <linux/slab.h>
@@ -357,7 +358,9 @@ static void amd_pmu_cpu_starting(int cpu)
 	struct amd_nb *nb;
 	int i, nb_id;
 
-	if (boot_cpu_data.x86_max_cores < 2)
+	cpuc->perf_ctr_virt_mask = AMD_PERFMON_EVENTSEL_HOSTONLY;
+
+	if (boot_cpu_data.x86_max_cores < 2 || boot_cpu_data.x86 == 0x15)
 		return;
 
 	nb_id = amd_get_nb_id(cpu);
@@ -587,9 +590,9 @@ static __initconst const struct x86_pmu amd_pmu_f15h = {
 	.put_event_constraints	= amd_put_event_constraints,
 
 	.cpu_prepare		= amd_pmu_cpu_prepare,
-	.cpu_starting		= amd_pmu_cpu_starting,
 	.cpu_dead		= amd_pmu_cpu_dead,
 #endif
+	.cpu_starting		= amd_pmu_cpu_starting,
 };
 
 __init int amd_pmu_init(void)
@@ -621,3 +624,33 @@ __init int amd_pmu_init(void)
 
 	return 0;
 }
+
+void amd_pmu_enable_virt(void)
+{
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+
+	cpuc->perf_ctr_virt_mask = 0;
+
+	/* Reload all events */
+	x86_pmu_disable_all();
+	x86_pmu_enable_all(0);
+}
+EXPORT_SYMBOL_GPL(amd_pmu_enable_virt);
+
+void amd_pmu_disable_virt(void)
+{
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+
+	/*
+	 * We only mask out the Host-only bit so that host-only counting works
+	 * when SVM is disabled. If someone sets up a guest-only counter when
+	 * SVM is disabled the Guest-only bits still gets set and the counter
+	 * will not count anything.
+	 */
+	cpuc->perf_ctr_virt_mask = AMD_PERFMON_EVENTSEL_HOSTONLY;
+
+	/* Reload all events */
+	x86_pmu_disable_all();
+	x86_pmu_enable_all(0);
+}
+EXPORT_SYMBOL_GPL(amd_pmu_disable_virt);
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 3fe8239fd8fb..1333d9851778 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -1532,10 +1532,17 @@ ENTRY(nmi)
 	pushq_cfi %rdx
 
 	/*
+	 * If %cs was not the kernel segment, then the NMI triggered in user
+	 * space, which means it is definitely not nested.
+	 */
+	cmpl $__KERNEL_CS, 16(%rsp)
+	jne first_nmi
+
+	/*
 	 * Check the special variable on the stack to see if NMIs are
 	 * executing.
 	 */
-	cmp $1, -8(%rsp)
+	cmpl $1, -8(%rsp)
 	je nested_nmi
 
 	/*
diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c
index ac0417be9131..73465aab28f8 100644
--- a/arch/x86/kernel/microcode_amd.c
+++ b/arch/x86/kernel/microcode_amd.c
@@ -360,7 +360,6 @@ out:
 static enum ucode_state
 request_microcode_user(int cpu, const void __user *buf, size_t size)
 {
-	pr_info("AMD microcode update via /dev/cpu/microcode not supported\n");
 	return UCODE_ERROR;
 }
 
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 80bfe1ab0031..c08d1ff12b7c 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -214,6 +214,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp,
 
 	task_user_gs(p) = get_user_gs(regs);
 
+	p->fpu_counter = 0;
 	p->thread.io_bitmap_ptr = NULL;
 	tsk = current;
 	err = -ENOMEM;
@@ -303,7 +304,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 
 	/* never put a printk in __switch_to... printk() calls wake_up*() indirectly */
 
-	fpu = switch_fpu_prepare(prev_p, next_p);
+	fpu = switch_fpu_prepare(prev_p, next_p, cpu);
 
 	/*
 	 * Reload esp0.
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 1fd94bc4279d..cfa5c90c01db 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -286,6 +286,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp,
 
 	set_tsk_thread_flag(p, TIF_FORK);
 
+	p->fpu_counter = 0;
 	p->thread.io_bitmap_ptr = NULL;
 
 	savesegment(gs, p->thread.gsindex);
@@ -388,7 +389,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	unsigned fsindex, gsindex;
 	fpu_switch_t fpu;
 
-	fpu = switch_fpu_prepare(prev_p, next_p);
+	fpu = switch_fpu_prepare(prev_p, next_p, cpu);
 
 	/*
 	 * Reload esp0, LDT and the page table pointer:
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 77da5b475ad2..4bbe04d96744 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -571,37 +571,6 @@ asmlinkage void __attribute__((weak)) smp_threshold_interrupt(void)
 }
 
 /*
- * 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(struct task_struct *tsk)
-{
-	/* 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))) {
-		__thread_fpu_end(tsk);
-		force_sig(SIGSEGV, tsk);
-		return;
-	}
-}
-
-/*
  * 'math_state_restore()' saves the current math information in the
  * old math state array, and gets the new ones from the current task
  *
@@ -631,7 +600,14 @@ void math_state_restore(void)
 	}
 
 	__thread_fpu_begin(tsk);
-	__math_state_restore(tsk);
+	/*
+	 * Paranoid restore. send a SIGSEGV if we fail to restore the state.
+	 */
+	if (unlikely(restore_fpu_checking(tsk))) {
+		__thread_fpu_end(tsk);
+		force_sig(SIGSEGV, tsk);
+		return;
+	}
 
 	tsk->fpu_counter++;
 }
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 5fa553babe56..e385214711cb 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -29,6 +29,7 @@
 #include <linux/ftrace_event.h>
 #include <linux/slab.h>
 
+#include <asm/perf_event.h>
 #include <asm/tlbflush.h>
 #include <asm/desc.h>
 #include <asm/kvm_para.h>
@@ -575,6 +576,8 @@ static void svm_hardware_disable(void *garbage)
 		wrmsrl(MSR_AMD64_TSC_RATIO, TSC_RATIO_DEFAULT);
 
 	cpu_svm_disable();
+
+	amd_pmu_disable_virt();
 }
 
 static int svm_hardware_enable(void *garbage)
@@ -622,6 +625,8 @@ static int svm_hardware_enable(void *garbage)
 
 	svm_init_erratum_383();
 
+	amd_pmu_enable_virt();
+
 	return 0;
 }
 
diff --git a/arch/x86/lib/delay.c b/arch/x86/lib/delay.c
index fc45ba887d05..e395693abdb1 100644
--- a/arch/x86/lib/delay.c
+++ b/arch/x86/lib/delay.c
@@ -48,9 +48,9 @@ static void delay_loop(unsigned long loops)
 }
 
 /* TSC based delay: */
-static void delay_tsc(unsigned long loops)
+static void delay_tsc(unsigned long __loops)
 {
-	unsigned long bclock, now;
+	u32 bclock, now, loops = __loops;
 	int cpu;
 
 	preempt_disable();
diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c
index f581a18c0d4d..8ecbb4bba4b3 100644
--- a/arch/x86/mm/hugetlbpage.c
+++ b/arch/x86/mm/hugetlbpage.c
@@ -333,13 +333,15 @@ try_again:
 		 * Lookup failure means no vma is above this address,
 		 * i.e. return with success:
 		 */
-		if (!(vma = find_vma_prev(mm, addr, &prev_vma)))
+		vma = find_vma(mm, addr);
+		if (!vma)
 			return addr;
 
 		/*
 		 * new region fits between prev_vma->vm_end and
 		 * vma->vm_start, use it:
 		 */
+		prev_vma = vma->vm_prev;
 		if (addr + len <= vma->vm_start &&
 		            (!prev_vma || (addr >= prev_vma->vm_end))) {
 			/* remember the address as a hint for next time */
diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c
index a312e76063a7..49a5cb55429b 100644
--- a/arch/x86/pci/acpi.c
+++ b/arch/x86/pci/acpi.c
@@ -60,6 +60,16 @@ static const struct dmi_system_id pci_use_crs_table[] __initconst = {
 			DMI_MATCH(DMI_BIOS_VENDOR, "American Megatrends Inc."),
 		},
 	},
+	/* https://bugzilla.kernel.org/show_bug.cgi?id=42619 */
+	{
+		.callback = set_use_crs,
+		.ident = "MSI MS-7253",
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "MICRO-STAR INTERNATIONAL CO., LTD"),
+			DMI_MATCH(DMI_BOARD_NAME, "MS-7253"),
+			DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix Technologies, LTD"),
+		},
+	},
 
 	/* Now for the blacklist.. */
 
@@ -282,9 +292,6 @@ static void add_resources(struct pci_root_info *info)
 	int i;
 	struct resource *res, *root, *conflict;
 
-	if (!pci_use_crs)
-		return;
-
 	coalesce_windows(info, IORESOURCE_MEM);
 	coalesce_windows(info, IORESOURCE_IO);
 
@@ -336,8 +343,13 @@ get_current_resources(struct acpi_device *device, int busnum,
 	acpi_walk_resources(device->handle, METHOD_NAME__CRS, setup_resource,
 				&info);
 
-	add_resources(&info);
-	return;
+	if (pci_use_crs) {
+		add_resources(&info);
+
+		return;
+	}
+
+	kfree(info.name);
 
 name_alloc_fail:
 	kfree(info.res);
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 12eb07bfb267..4172af8ceeb3 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -1141,7 +1141,9 @@ asmlinkage void __init xen_start_kernel(void)
 
 	/* Prevent unwanted bits from being set in PTEs. */
 	__supported_pte_mask &= ~_PAGE_GLOBAL;
+#if 0
 	if (!xen_initial_domain())
+#endif
 		__supported_pte_mask &= ~(_PAGE_PWT | _PAGE_PCD);
 
 	__supported_pte_mask |= _PAGE_IOMAP;
@@ -1204,10 +1206,6 @@ asmlinkage void __init xen_start_kernel(void)
 
 	pgd = (pgd_t *)xen_start_info->pt_base;
 
-	if (!xen_initial_domain())
-		__supported_pte_mask &= ~(_PAGE_PWT | _PAGE_PCD);
-
-	__supported_pte_mask |= _PAGE_IOMAP;
 	/* Don't do the full vcpu_info placement stuff until we have a
 	   possible map and a non-dummy shared_info. */
 	per_cpu(xen_vcpu, 0) = &HYPERVISOR_shared_info->vcpu_info[0];
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 58a0e46c404d..95c1cf60c669 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -415,13 +415,13 @@ static pteval_t iomap_pte(pteval_t val)
 static pteval_t xen_pte_val(pte_t pte)
 {
 	pteval_t pteval = pte.pte;
-
+#if 0
 	/* If this is a WC pte, convert back from Xen WC to Linux WC */
 	if ((pteval & (_PAGE_PAT | _PAGE_PCD | _PAGE_PWT)) == _PAGE_PAT) {
 		WARN_ON(!pat_enabled);
 		pteval = (pteval & ~_PAGE_PAT) | _PAGE_PWT;
 	}
-
+#endif
 	if (xen_initial_domain() && (pteval & _PAGE_IOMAP))
 		return pteval;
 
@@ -463,7 +463,7 @@ void xen_set_pat(u64 pat)
 static pte_t xen_make_pte(pteval_t pte)
 {
 	phys_addr_t addr = (pte & PTE_PFN_MASK);
-
+#if 0
 	/* If Linux is trying to set a WC pte, then map to the Xen WC.
 	 * If _PAGE_PAT is set, then it probably means it is really
 	 * _PAGE_PSE, so avoid fiddling with the PAT mapping and hope
@@ -476,7 +476,7 @@ static pte_t xen_make_pte(pteval_t pte)
 		if ((pte & (_PAGE_PCD | _PAGE_PWT)) == _PAGE_PWT)
 			pte = (pte & ~(_PAGE_PCD | _PAGE_PWT)) | _PAGE_PAT;
 	}
-
+#endif
 	/*
 	 * Unprivileged domains are allowed to do IOMAPpings for
 	 * PCI passthrough, but not map ISA space.  The ISA