17 files changed, 122 insertions, 141 deletions

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/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/e820.c b/arch/x86/kernel/e820.c
index 174d938d576b..62d61e9976eb 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -703,7 +703,7 @@ void __init e820_mark_nosave_regions(unsigned long limit_pfn)
 }
 #endif
 
-#ifdef CONFIG_HIBERNATION
+#ifdef CONFIG_ACPI
 /**
  * Mark ACPI NVS memory region, so that we can save/restore it during
  * hibernation and the subsequent resume.
@@ -716,7 +716,7 @@ static int __init e820_mark_nvs_memory(void)
 		struct e820entry *ei = &e820.map[i];
 
 		if (ei->type == E820_NVS)
-			suspend_nvs_register(ei->addr, ei->size);
+			acpi_nvs_register(ei->addr, ei->size);
 	}
 
 	return 0;
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index 4af9fd2450a5..79d97e68f042 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -42,6 +42,7 @@
  */
 
 #include <linux/linkage.h>
+#include <linux/err.h>
 #include <asm/thread_info.h>
 #include <asm/irqflags.h>
 #include <asm/errno.h>
@@ -453,7 +454,7 @@ sysenter_audit:
 	movl %ebx,%ecx			/* 3rd arg: 1st syscall arg */
 	movl %eax,%edx			/* 2nd arg: syscall number */
 	movl $AUDIT_ARCH_I386,%eax	/* 1st arg: audit arch */
-	call audit_syscall_entry
+	call __audit_syscall_entry
 	pushl_cfi %ebx
 	movl PT_EAX(%esp),%eax		/* reload syscall number */
 	jmp sysenter_do_call
@@ -464,11 +465,10 @@ sysexit_audit:
 	TRACE_IRQS_ON
 	ENABLE_INTERRUPTS(CLBR_ANY)
 	movl %eax,%edx		/* second arg, syscall return value */
-	cmpl $0,%eax		/* is it < 0? */
-	setl %al		/* 1 if so, 0 if not */
+	cmpl $-MAX_ERRNO,%eax	/* is it an error ? */
+	setbe %al		/* 1 if so, 0 if not */
 	movzbl %al,%eax		/* zero-extend that */
-	inc %eax /* first arg, 0->1(AUDITSC_SUCCESS), 1->2(AUDITSC_FAILURE) */
-	call audit_syscall_exit
+	call __audit_syscall_exit
 	DISABLE_INTERRUPTS(CLBR_ANY)
 	TRACE_IRQS_OFF
 	movl TI_flags(%ebp), %ecx
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 940ba711fc28..3fe8239fd8fb 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -55,6 +55,7 @@
 #include <asm/paravirt.h>
 #include <asm/ftrace.h>
 #include <asm/percpu.h>
+#include <linux/err.h>
 
 /* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this.  */
 #include <linux/elf-em.h>
@@ -548,7 +549,7 @@ badsys:
 #ifdef CONFIG_AUDITSYSCALL
 	/*
 	 * Fast path for syscall audit without full syscall trace.
-	 * We just call audit_syscall_entry() directly, and then
+	 * We just call __audit_syscall_entry() directly, and then
 	 * jump back to the normal fast path.
 	 */
 auditsys:
@@ -558,22 +559,21 @@ auditsys:
 	movq %rdi,%rdx			/* 3rd arg: 1st syscall arg */
 	movq %rax,%rsi			/* 2nd arg: syscall number */
 	movl $AUDIT_ARCH_X86_64,%edi	/* 1st arg: audit arch */
-	call audit_syscall_entry
+	call __audit_syscall_entry
 	LOAD_ARGS 0		/* reload call-clobbered registers */
 	jmp system_call_fastpath
 
 	/*
-	 * Return fast path for syscall audit.  Call audit_syscall_exit()
+	 * Return fast path for syscall audit.  Call __audit_syscall_exit()
 	 * directly and then jump back to the fast path with TIF_SYSCALL_AUDIT
 	 * masked off.
 	 */
 sysret_audit:
 	movq RAX-ARGOFFSET(%rsp),%rsi	/* second arg, syscall return value */
-	cmpq $0,%rsi		/* is it < 0? */
-	setl %al		/* 1 if so, 0 if not */
+	cmpq $-MAX_ERRNO,%rsi	/* is it < -MAX_ERRNO? */
+	setbe %al		/* 1 if so, 0 if not */
 	movzbl %al,%edi		/* zero-extend that into %edi */
-	inc %edi /* first arg, 0->1(AUDITSC_SUCCESS), 1->2(AUDITSC_FAILURE) */
-	call audit_syscall_exit
+	call __audit_syscall_exit
 	movl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT),%edi
 	jmp sysret_check
 #endif	/* CONFIG_AUDITSYSCALL */
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..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;
@@ -299,22 +300,11 @@ __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, cpu);
 
 	/*
 	 * Reload esp0.
@@ -354,11 +344,6 @@ __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 +353,14 @@ __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..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);
@@ -386,18 +387,9 @@ __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, cpu);
 
 	/*
 	 * Reload esp0, LDT and the page table pointer:
@@ -427,13 +419,6 @@ __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 +459,8 @@ __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 +479,6 @@ __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/ptrace.c b/arch/x86/kernel/ptrace.c
index 89a04c7b5bb6..50267386b766 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -1392,20 +1392,18 @@ long syscall_trace_enter(struct pt_regs *regs)
 	if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
 		trace_sys_enter(regs, regs->orig_ax);
 
-	if (unlikely(current->audit_context)) {
-		if (IS_IA32)
-			audit_syscall_entry(AUDIT_ARCH_I386,
-					    regs->orig_ax,
-					    regs->bx, regs->cx,
-					    regs->dx, regs->si);
+	if (IS_IA32)
+		audit_syscall_entry(AUDIT_ARCH_I386,
+				    regs->orig_ax,
+				    regs->bx, regs->cx,
+				    regs->dx, regs->si);
 #ifdef CONFIG_X86_64
-		else
-			audit_syscall_entry(AUDIT_ARCH_X86_64,
-					    regs->orig_ax,
-					    regs->di, regs->si,
-					    regs->dx, regs->r10);
+	else
+		audit_syscall_entry(AUDIT_ARCH_X86_64,
+				    regs->orig_ax,
+				    regs->di, regs->si,
+				    regs->dx, regs->r10);
 #endif
-	}
 
 	return ret ?: regs->orig_ax;
 }
@@ -1414,8 +1412,7 @@ void syscall_trace_leave(struct pt_regs *regs)
 {
 	bool step;
 
-	if (unlikely(current->audit_context))
-		audit_syscall_exit(AUDITSC_RESULT(regs->ax), regs->ax);
+	audit_syscall_exit(regs);
 
 	if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
 		trace_sys_exit(regs, regs->ax);
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..4bbe04d96744 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -571,41 +571,18 @@ 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.
- */
-void __math_state_restore(void)
-{
-	struct thread_info *thread = current_thread_info();
-	struct task_struct *tsk = thread->task;
-
-	/*
-	 * Paranoid restore. send a SIGSEGV if we fail to restore the state.
-	 */
-	if (unlikely(restore_fpu_checking(tsk))) {
-		stts();
-		force_sig(SIGSEGV, tsk);
-		return;
-	}
-
-	thread->status |= TS_USEDFPU;	/* So we fnsave on switch_to() */
-	tsk->fpu_counter++;
-}
-
-/*
  * 'math_state_restore()' saves the current math information in the
  * old math state array, and gets the new ones from the current task
  *
  * 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 +599,17 @@ asmlinkage void math_state_restore(void)
 		local_irq_disable();
 	}
 
-	clts();				/* Allow maths ops (or we recurse) */
+	__thread_fpu_begin(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;
+	}
 
-	__math_state_restore();
+	tsk->fpu_counter++;
 }
 EXPORT_SYMBOL_GPL(math_state_restore);
 
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index c0dd5b603749..a62c201c97ec 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -290,14 +290,15 @@ static inline int pit_verify_msb(unsigned char val)
 static inline int pit_expect_msb(unsigned char val, u64 *tscp, unsigned long *deltap)
 {
 	int count;
-	u64 tsc = 0;
+	u64 tsc = 0, prev_tsc = 0;
 
 	for (count = 0; count < 50000; count++) {
 		if (!pit_verify_msb(val))
 			break;
+		prev_tsc = tsc;
 		tsc = get_cycles();
 	}
-	*deltap = get_cycles() - tsc;
+	*deltap = get_cycles() - prev_tsc;
 	*tscp = tsc;
 
 	/*
@@ -311,9 +312,9 @@ static inline int pit_expect_msb(unsigned char val, u64 *tscp, unsigned long *de
  * How many MSB values do we want to see? We aim for
  * a maximum error rate of 500ppm (in practice the
  * real error is much smaller), but refuse to spend
- * more than 25ms on it.
+ * more than 50ms on it.
  */
-#define MAX_QUICK_PIT_MS 25
+#define MAX_QUICK_PIT_MS 50
 #define MAX_QUICK_PIT_ITERATIONS (MAX_QUICK_PIT_MS * PIT_TICK_RATE / 1000 / 256)
 
 static unsigned long quick_pit_calibrate(void)
@@ -383,15 +384,12 @@ success:
 	 *
 	 * As a result, we can depend on there not being
 	 * any odd delays anywhere, and the TSC reads are
-	 * reliable (within the error). We also adjust the
-	 * delta to the middle of the error bars, just
-	 * because it looks nicer.
+	 * reliable (within the error).
 	 *
 	 * kHz = ticks / time-in-seconds / 1000;
 	 * kHz = (t2 - t1) / (I * 256 / PIT_TICK_RATE) / 1000
 	 * kHz = ((t2 - t1) * PIT_TICK_RATE) / (I * 256 * 1000)
 	 */
-	delta += (long)(d2 - d1)/2;
 	delta *= PIT_TICK_RATE;
 	do_div(delta, i*256*1000);
 	printk("Fast TSC calibration using PIT\n");
diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c
index 863f8753ab0a..b466cab5ba15 100644
--- a/arch/x86/kernel/vm86_32.c
+++ b/arch/x86/kernel/vm86_32.c
@@ -335,9 +335,11 @@ static void do_sys_vm86(struct kernel_vm86_struct *info, struct task_struct *tsk
 	if (info->flags & VM86_SCREEN_BITMAP)
 		mark_screen_rdonly(tsk->mm);
 
-	/*call audit_syscall_exit since we do not exit via the normal paths */
+	/*call __audit_syscall_exit since we do not exit via the normal paths */
+#ifdef CONFIG_AUDITSYSCALL
 	if (unlikely(current->audit_context))
-		audit_syscall_exit(AUDITSC_RESULT(0), 0);
+		__audit_syscall_exit(1, 0);
+#endif
 
 	__asm__ __volatile__(
 		"movl %0,%%esp\n\t"
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