24 files changed, 143 insertions, 95 deletions

diff --git a/arch/x86/kernel/asm-offsets_32.c b/arch/x86/kernel/asm-offsets_32.c
index a33d5301799..8ea040124f7 100644
--- a/arch/x86/kernel/asm-offsets_32.c
+++ b/arch/x86/kernel/asm-offsets_32.c
@@ -128,13 +128,11 @@ void foo(void)
 	OFFSET(XEN_vcpu_info_pending, vcpu_info, evtchn_upcall_pending);
 #endif
 
-#ifdef CONFIG_LGUEST_GUEST
+#if defined(CONFIG_LGUEST) || defined(CONFIG_LGUEST_GUEST) || defined(CONFIG_LGUEST_MODULE)
 	BLANK();
 	OFFSET(LGUEST_DATA_irq_enabled, lguest_data, irq_enabled);
 	OFFSET(LGUEST_DATA_pgdir, lguest_data, pgdir);
-#endif
 
-#ifdef CONFIG_LGUEST
 	BLANK();
 	OFFSET(LGUEST_PAGES_host_gdt_desc, lguest_pages, state.host_gdt_desc);
 	OFFSET(LGUEST_PAGES_host_idt_desc, lguest_pages, state.host_idt_desc);
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index f86a3c4a266..a38aafaefc2 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -504,7 +504,7 @@ void __cpuinit identify_cpu(struct cpuinfo_x86 *c)
 
 	/* Clear all flags overriden by options */
 	for (i = 0; i < NCAPINTS; i++)
-		c->x86_capability[i] ^= cleared_cpu_caps[i];
+		c->x86_capability[i] &= ~cleared_cpu_caps[i];
 
 	/* Init Machine Check Exception if available. */
 	mcheck_init(c);
diff --git a/arch/x86/kernel/cpu/cpufreq/e_powersaver.c b/arch/x86/kernel/cpu/cpufreq/e_powersaver.c
index 39f8cb18296..c2f930d8664 100644
--- a/arch/x86/kernel/cpu/cpufreq/e_powersaver.c
+++ b/arch/x86/kernel/cpu/cpufreq/e_powersaver.c
@@ -55,7 +55,6 @@ static int eps_set_state(struct eps_cpu_data *centaur,
 {
 	struct cpufreq_freqs freqs;
 	u32 lo, hi;
-	u8 current_multiplier, current_voltage;
 	int err = 0;
 	int i;
 
@@ -95,6 +94,10 @@ postchange:
 	rdmsr(MSR_IA32_PERF_STATUS, lo, hi);
 	freqs.new = centaur->fsb * ((lo >> 8) & 0xff);
 
+#ifdef DEBUG
+	{
+	u8 current_multiplier, current_voltage;
+
 	/* Print voltage and multiplier */
 	rdmsr(MSR_IA32_PERF_STATUS, lo, hi);
 	current_voltage = lo & 0xff;
@@ -103,7 +106,8 @@ postchange:
 	current_multiplier = (lo >> 8) & 0xff;
 	printk(KERN_INFO "eps: Current multiplier = %d\n",
 		current_multiplier);
-
+	}
+#endif
 	cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE);
 	return err;
 }
diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c
index b6e136f23d3..be83336fddb 100644
--- a/arch/x86/kernel/cpu/mtrr/main.c
+++ b/arch/x86/kernel/cpu/mtrr/main.c
@@ -43,6 +43,7 @@
 #include <asm/uaccess.h>
 #include <asm/processor.h>
 #include <asm/msr.h>
+#include <asm/kvm_para.h>
 #include "mtrr.h"
 
 u32 num_var_ranges = 0;
@@ -649,6 +650,7 @@ static __init int amd_special_default_mtrr(void)
 
 /**
  * mtrr_trim_uncached_memory - trim RAM not covered by MTRRs
+ * @end_pfn: ending page frame number
  *
  * Some buggy BIOSes don't setup the MTRRs properly for systems with certain
  * memory configurations.  This routine checks that the highest MTRR matches
@@ -688,8 +690,11 @@ int __init mtrr_trim_uncached_memory(unsigned long end_pfn)
 
 	/* kvm/qemu doesn't have mtrr set right, don't trim them all */
 	if (!highest_pfn) {
-		printk(KERN_WARNING "WARNING: strange, CPU MTRRs all blank?\n");
-		WARN_ON(1);
+		if (!kvm_para_available()) {
+			printk(KERN_WARNING
+				"WARNING: strange, CPU MTRRs all blank?\n");
+			WARN_ON(1);
+		}
 		return 0;
 	}
 
diff --git a/arch/x86/kernel/cpu/transmeta.c b/arch/x86/kernel/cpu/transmeta.c
index 200fb3f9ebf..e8b422c1c51 100644
--- a/arch/x86/kernel/cpu/transmeta.c
+++ b/arch/x86/kernel/cpu/transmeta.c
@@ -76,13 +76,6 @@ static void __cpuinit init_transmeta(struct cpuinfo_x86 *c)
 	/* All Transmeta CPUs have a constant TSC */
 	set_bit(X86_FEATURE_CONSTANT_TSC, c->x86_capability);
 	
-	/* If we can run i686 user-space code, call us an i686 */
-#define USER686 ((1 << X86_FEATURE_TSC)|\
-		 (1 << X86_FEATURE_CX8)|\
-		 (1 << X86_FEATURE_CMOV))
-        if (c->x86 == 5 && (c->x86_capability[0] & USER686) == USER686)
-		c->x86 = 6;
-
 #ifdef CONFIG_SYSCTL
 	/* randomize_va_space slows us down enormously;
 	   it probably triggers retranslation of x86->native bytecode */
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 2ad9a1bc6a7..c20c9e7e08d 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -453,6 +453,7 @@ ENTRY(stub_execve)
 	CFI_REGISTER rip, r11
 	SAVE_REST
 	FIXUP_TOP_OF_STACK %r11
+	movq %rsp, %rcx
 	call sys_execve
 	RESTORE_TOP_OF_STACK %r11
 	movq %rax,RAX(%rsp)
@@ -1036,15 +1037,16 @@ ENDPROC(child_rip)
  *	rdi: name, rsi: argv, rdx: envp
  *
  * We want to fallback into:
- *	extern long sys_execve(char *name, char **argv,char **envp, struct pt_regs regs)
+ *	extern long sys_execve(char *name, char **argv,char **envp, struct pt_regs *regs)
  *
  * do_sys_execve asm fallback arguments:
- *	rdi: name, rsi: argv, rdx: envp, fake frame on the stack
+ *	rdi: name, rsi: argv, rdx: envp, rcx: fake frame on the stack
  */
 ENTRY(kernel_execve)
 	CFI_STARTPROC
 	FAKE_STACK_FRAME $0
 	SAVE_ALL	
+	movq %rsp,%rcx
 	call sys_execve
 	movq %rax, RAX(%rsp)	
 	RESTORE_REST
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index 25eb98540a4..fd8ca53943a 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -606,7 +606,7 @@ ENTRY(_stext)
 .section ".bss.page_aligned","wa"
 	.align PAGE_SIZE_asm
 #ifdef CONFIG_X86_PAE
-ENTRY(swapper_pg_pmd)
+swapper_pg_pmd:
 	.fill 1024*KPMDS,4,0
 #else
 ENTRY(swapper_pg_dir)
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index eb415043a92..a007454133a 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -379,18 +379,24 @@ NEXT_PAGE(level2_ident_pgt)
 	/* Since I easily can, map the first 1G.
 	 * Don't set NX because code runs from these pages.
 	 */
-	PMDS(0x0000000000000000, __PAGE_KERNEL_LARGE_EXEC, PTRS_PER_PMD)
+	PMDS(0, __PAGE_KERNEL_LARGE_EXEC, PTRS_PER_PMD)
 
 NEXT_PAGE(level2_kernel_pgt)
-	/* 40MB kernel mapping. The kernel code cannot be bigger than that.
-	   When you change this change KERNEL_TEXT_SIZE in page.h too. */
-	/* (2^48-(2*1024*1024*1024)-((2^39)*511)-((2^30)*510)) = 0 */
-	PMDS(0x0000000000000000, __PAGE_KERNEL_LARGE_EXEC|_PAGE_GLOBAL, KERNEL_TEXT_SIZE/PMD_SIZE)
-	/* Module mapping starts here */
-	.fill	(PTRS_PER_PMD - (KERNEL_TEXT_SIZE/PMD_SIZE)),8,0
+	/*
+	 * 128 MB kernel mapping. We spend a full page on this pagetable
+	 * anyway.
+	 *
+	 * The kernel code+data+bss must not be bigger than that.
+	 *
+	 * (NOTE: at +128MB starts the module area, see MODULES_VADDR.
+	 *  If you want to increase this then increase MODULES_VADDR
+	 *  too.)
+	 */
+	PMDS(0, __PAGE_KERNEL_LARGE_EXEC|_PAGE_GLOBAL,
+		KERNEL_IMAGE_SIZE/PMD_SIZE)
 
 NEXT_PAGE(level2_spare_pgt)
-	.fill   512,8,0
+	.fill   512, 8, 0
 
 #undef PMDS
 #undef NEXT_PAGE
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index 429d084e014..235fd6c7750 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -368,8 +368,8 @@ static int hpet_clocksource_register(void)
 	return 0;
 }
 
-/*
- * Try to setup the HPET timer
+/**
+ * hpet_enable - Try to setup the HPET timer. Returns 1 on success.
  */
 int __init hpet_enable(void)
 {
diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c
index 763dfc40723..d2e39e69aaf 100644
--- a/arch/x86/kernel/i387.c
+++ b/arch/x86/kernel/i387.c
@@ -132,7 +132,7 @@ int xfpregs_get(struct task_struct *target, const struct user_regset *regset,
 	if (!cpu_has_fxsr)
 		return -ENODEV;
 
-	unlazy_fpu(target);
+	init_fpu(target);
 
 	return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
 				   &target->thread.i387.fxsave, 0, -1);
@@ -147,7 +147,7 @@ int xfpregs_set(struct task_struct *target, const struct user_regset *regset,
 	if (!cpu_has_fxsr)
 		return -ENODEV;
 
-	unlazy_fpu(target);
+	init_fpu(target);
 	set_stopped_child_used_math(target);
 
 	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
@@ -261,7 +261,7 @@ static void convert_from_fxsr(struct user_i387_ia32_struct *env,
 	}
 #else
 	env->fip = fxsave->fip;
-	env->fcs = fxsave->fcs;
+	env->fcs = (u16) fxsave->fcs | ((u32) fxsave->fop << 16);
 	env->foo = fxsave->foo;
 	env->fos = fxsave->fos;
 #endif
@@ -307,7 +307,7 @@ int fpregs_get(struct task_struct *target, const struct user_regset *regset,
 	if (!HAVE_HWFP)
 		return fpregs_soft_get(target, regset, pos, count, kbuf, ubuf);
 
-	unlazy_fpu(target);
+	init_fpu(target);
 
 	if (!cpu_has_fxsr)
 		return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
@@ -332,7 +332,7 @@ int fpregs_set(struct task_struct *target, const struct user_regset *regset,
 	if (!HAVE_HWFP)
 		return fpregs_soft_set(target, regset, pos, count, kbuf, ubuf);
 
-	unlazy_fpu(target);
+	init_fpu(target);
 	set_stopped_child_used_math(target);
 
 	if (!cpu_has_fxsr)
diff --git a/arch/x86/kernel/init_task.c b/arch/x86/kernel/init_task.c
index 5b3ce793436..3d01e47777d 100644
--- a/arch/x86/kernel/init_task.c
+++ b/arch/x86/kernel/init_task.c
@@ -15,6 +15,7 @@ static struct files_struct init_files = INIT_FILES;
 static struct signal_struct init_signals = INIT_SIGNALS(init_signals);
 static struct sighand_struct init_sighand = INIT_SIGHAND(init_sighand);
 struct mm_struct init_mm = INIT_MM(init_mm);
+EXPORT_UNUSED_SYMBOL(init_mm); /* will be removed in 2.6.26 */
 
 /*
  * Initial thread structure.
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index a7d50a547dc..be3c7a299f0 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -603,11 +603,13 @@ __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p,
 	}
 #endif
 
+#ifdef X86_BTS
 	if (test_tsk_thread_flag(prev_p, TIF_BTS_TRACE_TS))
 		ptrace_bts_take_timestamp(prev_p, BTS_TASK_DEPARTS);
 
 	if (test_tsk_thread_flag(next_p, TIF_BTS_TRACE_TS))
 		ptrace_bts_take_timestamp(next_p, BTS_TASK_ARRIVES);
+#endif
 
 
 	if (!test_tsk_thread_flag(next_p, TIF_IO_BITMAP)) {
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index b0cc8f0136d..3baf9b9f4c8 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -604,11 +604,13 @@ static inline void __switch_to_xtra(struct task_struct *prev_p,
 		memset(tss->io_bitmap, 0xff, prev->io_bitmap_max);
 	}
 
+#ifdef X86_BTS
 	if (test_tsk_thread_flag(prev_p, TIF_BTS_TRACE_TS))
 		ptrace_bts_take_timestamp(prev_p, BTS_TASK_DEPARTS);
 
 	if (test_tsk_thread_flag(next_p, TIF_BTS_TRACE_TS))
 		ptrace_bts_take_timestamp(next_p, BTS_TASK_ARRIVES);
+#endif
 }
 
 /*
@@ -730,16 +732,16 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
  */
 asmlinkage
 long sys_execve(char __user *name, char __user * __user *argv,
-		char __user * __user *envp, struct pt_regs regs)
+		char __user * __user *envp, struct pt_regs *regs)
 {
 	long error;
 	char * filename;
 
 	filename = getname(name);
 	error = PTR_ERR(filename);
-	if (IS_ERR(filename)) 
+	if (IS_ERR(filename))
 		return error;
-	error = do_execve(filename, argv, envp, &regs); 
+	error = do_execve(filename, argv, envp, regs);
 	putname(filename);
 	return error;
 }
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index d862e396b09..d5904eef1d3 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -323,6 +323,16 @@ static int putreg(struct task_struct *child,
 		return set_flags(child, value);
 
 #ifdef CONFIG_X86_64
+	/*
+	 * Orig_ax is really just a flag with small positive and
+	 * negative values, so make sure to always sign-extend it
+	 * from 32 bits so that it works correctly regardless of
+	 * whether we come from a 32-bit environment or not.
+	 */
+	case offsetof(struct user_regs_struct, orig_ax):
+		value = (long) (s32) value;
+		break;
+
 	case offsetof(struct user_regs_struct,fs_base):
 		if (value >= TASK_SIZE_OF(child))
 			return -EIO;
@@ -544,6 +554,8 @@ static int ptrace_set_debugreg(struct task_struct *child,
 	return 0;
 }
 
+#ifdef X86_BTS
+
 static int ptrace_bts_get_size(struct task_struct *child)
 {
 	if (!child->thread.ds_area_msr)
@@ -826,6 +838,7 @@ void ptrace_bts_take_timestamp(struct task_struct *tsk,
 
 	ptrace_bts_write_record(tsk, &rec);
 }
+#endif /* X86_BTS */
 
 /*
  * Called by kernel/ptrace.c when detaching..
@@ -839,7 +852,9 @@ void ptrace_disable(struct task_struct *child)
 	clear_tsk_thread_flag(child, TIF_SYSCALL_EMU);
 #endif
 	if (child->thread.ds_area_msr) {
+#ifdef X86_BTS
 		ptrace_bts_realloc(child, 0, 0);
+#endif
 		child->thread.debugctlmsr &= ~ds_debugctl_mask();
 		if (!child->thread.debugctlmsr)
 			clear_tsk_thread_flag(child, TIF_DEBUGCTLMSR);
@@ -961,6 +976,10 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data)
 		break;
 #endif
 
+	/*
+	 * These bits need more cooking - not enabled yet:
+	 */
+#ifdef X86_BTS
 	case PTRACE_BTS_CONFIG:
 		ret = ptrace_bts_config
 			(child, data, (struct ptrace_bts_config __user *)addr);
@@ -988,6 +1007,7 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data)
 		ret = ptrace_bts_drain
 			(child, data, (struct bts_struct __user *) addr);
 		break;
+#endif
 
 	default:
 		ret = ptrace_request(child, request, addr, data);
@@ -1035,10 +1055,17 @@ static int putreg32(struct task_struct *child, unsigned regno, u32 value)
 	R32(esi, si);
 	R32(ebp, bp);
 	R32(eax, ax);
-	R32(orig_eax, orig_ax);
 	R32(eip, ip);
 	R32(esp, sp);
 
+	case offsetof(struct user32, regs.orig_eax):
+		/*
+		 * Sign-extend the value so that orig_eax = -1
+		 * causes (long)orig_ax < 0 tests to fire correctly.
+		 */
+		regs->orig_ax = (long) (s32) value;
+		break;
+
 	case offsetof(struct user32, regs.eflags):
 		return set_flags(child, value);
 
@@ -1226,12 +1253,14 @@ asmlinkage long sys32_ptrace(long request, u32 pid, u32 addr, u32 data)
 	case PTRACE_SETOPTIONS:
 	case PTRACE_SET_THREAD_AREA:
 	case PTRACE_GET_THREAD_AREA:
+#ifdef X86_BTS
 	case PTRACE_BTS_CONFIG:
 	case PTRACE_BTS_STATUS:
 	case PTRACE_BTS_SIZE:
 	case PTRACE_BTS_GET:
 	case PTRACE_BTS_CLEAR:
 	case PTRACE_BTS_DRAIN:
+#endif
 		return sys_ptrace(request, pid, addr, data);
 
 	default:
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 7fd6ac43e4a..55ceb8cdef7 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -326,6 +326,10 @@ static inline void kb_wait(void)
 	}
 }
 
+void __attribute__((weak)) mach_reboot_fixups(void)
+{
+}
+
 static void native_machine_emergency_restart(void)
 {
 	int i;
@@ -337,6 +341,8 @@ static void native_machine_emergency_restart(void)
 		/* Could also try the reset bit in the Hammer NB */
 		switch (reboot_type) {
 		case BOOT_KBD:
+			mach_reboot_fixups(); /* for board specific fixups */
+
 			for (i = 0; i < 10; i++) {
 				kb_wait();
 				udelay(50);
diff --git a/arch/x86/kernel/setup_64.c b/arch/x86/kernel/setup_64.c
index 6fd804f0782..7637dc91c79 100644
--- a/arch/x86/kernel/setup_64.c
+++ b/arch/x86/kernel/setup_64.c
@@ -1021,7 +1021,7 @@ void __cpuinit identify_cpu(struct cpuinfo_x86 *c)
 
 	/* Clear all flags overriden by options */
 	for (i = 0; i < NCAPINTS; i++)
-		c->x86_capability[i] ^= cleared_cpu_caps[i];
+		c->x86_capability[i] &= ~cleared_cpu_caps[i];
 
 #ifdef CONFIG_X86_MCE
 	mcheck_init(c);
diff --git a/arch/x86/kernel/signal_32.c b/arch/x86/kernel/signal_32.c
index caee1f002fe..0157a6f0f41 100644
--- a/arch/x86/kernel/signal_32.c
+++ b/arch/x86/kernel/signal_32.c
@@ -407,7 +407,7 @@ static int setup_frame(int sig, struct k_sigaction *ka,
 	 * The tracer may want to single-step inside the
 	 * handler too.
 	 */
-	regs->flags &= ~TF_MASK;
+	regs->flags &= ~(TF_MASK | X86_EFLAGS_DF);
 	if (test_thread_flag(TIF_SINGLESTEP))
 		ptrace_notify(SIGTRAP);
 
@@ -500,7 +500,7 @@ static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
 	 * The tracer may want to single-step inside the
 	 * handler too.
 	 */
-	regs->flags &= ~TF_MASK;
+	regs->flags &= ~(TF_MASK | X86_EFLAGS_DF);
 	if (test_thread_flag(TIF_SINGLESTEP))
 		ptrace_notify(SIGTRAP);
 
diff --git a/arch/x86/kernel/signal_64.c b/arch/x86/kernel/signal_64.c
index 7347bb14e30..1c83e5124c6 100644
--- a/arch/x86/kernel/signal_64.c
+++ b/arch/x86/kernel/signal_64.c
@@ -295,7 +295,7 @@ static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
 	   see include/asm-x86_64/uaccess.h for details. */
 	set_fs(USER_DS);
 
-	regs->flags &= ~X86_EFLAGS_TF;
+	regs->flags &= ~(X86_EFLAGS_TF | X86_EFLAGS_DF);
 	if (test_thread_flag(TIF_SINGLESTEP))
 		ptrace_notify(SIGTRAP);
 #ifdef DEBUG_SIG
@@ -311,6 +311,35 @@ give_sigsegv:
 }
 
 /*
+ * Return -1L or the syscall number that @regs is executing.
+ */
+static long current_syscall(struct pt_regs *regs)
+{
+	/*
+	 * We always sign-extend a -1 value being set here,
+	 * so this is always either -1L or a syscall number.
+	 */
+	return regs->orig_ax;
+}
+
+/*
+ * Return a value that is -EFOO if the system call in @regs->orig_ax
+ * returned an error.  This only works for @regs from @current.
+ */
+static long current_syscall_ret(struct pt_regs *regs)
+{
+#ifdef CONFIG_IA32_EMULATION
+	if (test_thread_flag(TIF_IA32))
+		/*
+		 * Sign-extend the value so (int)-EFOO becomes (long)-EFOO
+		 * and will match correctly in comparisons.
+		 */
+		return (int) regs->ax;
+#endif
+	return regs->ax;
+}
+
+/*
  * OK, we're invoking a handler
  */	
 
@@ -327,9 +356,9 @@ handle_signal(unsigned long sig, siginfo_t *info, struct k_sigaction *ka,
 #endif
 
 	/* Are we from a system call? */
-	if ((long)regs->orig_ax >= 0) {
+	if (current_syscall(regs) >= 0) {
 		/* If so, check system call restarting.. */
-		switch (regs->ax) {
+		switch (current_syscall_ret(regs)) {
 		        case -ERESTART_RESTARTBLOCK:
 			case -ERESTARTNOHAND:
 				regs->ax = -EINTR;
@@ -426,10 +455,9 @@ static void do_signal(struct pt_regs *regs)
 	}
 
 	/* Did we come from a system call? */
-	if ((long)regs->orig_ax >= 0) {
+	if (current_syscall(regs) >= 0) {
 		/* Restart the system call - no handlers present */
-		long res = regs->ax;
-		switch (res) {
+		switch (current_syscall_ret(regs)) {
 		case -ERESTARTNOHAND:
 		case -ERESTARTSYS:
 		case -ERESTARTNOINTR:
diff --git a/arch/x86/kernel/smpboot_64.c b/arch/x86/kernel/smpboot_64.c
index d53bd6fcb42..0880f2c388a 100644
--- a/arch/x86/kernel/smpboot_64.c
+++ b/arch/x86/kernel/smpboot_64.c
@@ -554,10 +554,10 @@ static int __cpuinit do_boot_cpu(int cpu, int apicid)
 	int timeout;
 	unsigned long start_rip;
 	struct create_idle c_idle = {
-		.work = __WORK_INITIALIZER(c_idle.work, do_fork_idle),
 		.cpu = cpu,
 		.done = COMPLETION_INITIALIZER_ONSTACK(c_idle.done),
 	};
+	INIT_WORK(&c_idle.work, do_fork_idle);
 
 	/* allocate memory for gdts of secondary cpus. Hotplug is considered */
 	if (!cpu_gdt_descr[cpu].address &&
diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c
index 02f0f61f5b1..c28c342c162 100644
--- a/arch/x86/kernel/stacktrace.c
+++ b/arch/x86/kernel/stacktrace.c
@@ -25,6 +25,8 @@ static int save_stack_stack(void *data, char *name)
 static void save_stack_address(void *data, unsigned long addr, int reliable)
 {
 	struct stack_trace *trace = data;
+	if (!reliable)
+		return;
 	if (trace->skip > 0) {
 		trace->skip--;
 		return;
@@ -37,6 +39,8 @@ static void
 save_stack_address_nosched(void *data, unsigned long addr, int reliable)
 {
 	struct stack_trace *trace = (struct stack_trace *)data;
+	if (!reliable)
+		return;
 	if (in_sched_functions(addr))
 		return;
 	if (trace->skip > 0) {
diff --git a/arch/x86/kernel/step.c b/arch/x86/kernel/step.c
index 2ef1a5f8d67..9d406cdc847 100644
--- a/arch/x86/kernel/step.c
+++ b/arch/x86/kernel/step.c
@@ -166,7 +166,7 @@ static void enable_step(struct task_struct *child, bool block)
 				  child->thread.debugctlmsr | DEBUGCTLMSR_BTF);
 	} else {
 	    write_debugctlmsr(child,
-			      child->thread.debugctlmsr & ~TIF_DEBUGCTLMSR);
+			      child->thread.debugctlmsr & ~DEBUGCTLMSR_BTF);
 
 	    if (!child->thread.debugctlmsr)
 		    clear_tsk_thread_flag(child, TIF_DEBUGCTLMSR);
@@ -189,7 +189,7 @@ void user_disable_single_step(struct task_struct *child)
 	 * Make sure block stepping (BTF) is disabled.
 	 */
 	write_debugctlmsr(child,
-			  child->thread.debugctlmsr & ~TIF_DEBUGCTLMSR);
+			  child->thread.debugctlmsr & ~DEBUGCTLMSR_BTF);
 
 	if (!child->thread.debugctlmsr)
 		clear_tsk_thread_flag(child, TIF_DEBUGCTLMSR);
diff --git a/arch/x86/kernel/tls.c b/arch/x86/kernel/tls.c
index 6dfd4e76661..022bcaa3b42 100644
--- a/arch/x86/kernel/tls.c
+++ b/arch/x86/kernel/tls.c
@@ -91,7 +91,9 @@ int do_set_thread_area(struct task_struct *p, int idx,
 
 asmlinkage int sys_set_thread_area(struct user_desc __user *u_info)
 {
-	return do_set_thread_area(current, -1, u_info, 1);
+	int ret = do_set_thread_area(current, -1, u_info, 1);
+	prevent_tail_call(ret);
+	return ret;
 }
 
 
@@ -139,7 +141,9 @@ int do_get_thread_area(struct task_struct *p, int idx,
 
 asmlinkage int sys_get_thread_area(struct user_desc __user *u_info)
 {
-	return do_get_thread_area(current, -1, u_info);
+	int ret = do_get_thread_area(current, -1, u_info);
+	prevent_tail_call(ret);
+	return ret;
 }
 
 int regset_tls_active(struct task_struct *target,
diff --git a/arch/x86/kernel/tsc_32.c b/arch/x86/kernel/tsc_32.c
index 43517e324be..f14cfd9d1f9 100644
--- a/arch/x86/kernel/tsc_32.c
+++ b/arch/x86/kernel/tsc_32.c
@@ -28,7 +28,8 @@ EXPORT_SYMBOL_GPL(tsc_khz);
 static int __init tsc_setup(char *str)
 {
 	printk(KERN_WARNING "notsc: Kernel compiled with CONFIG_X86_TSC, "
-				"cannot disable TSC.\n");
+				"cannot disable TSC completely.\n");
+	mark_tsc_unstable("user disabled TSC");
 	return 1;
 }
 #else
diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c
index 3f824277458..edff4c98548 100644
--- a/arch/x86/kernel/vsyscall_64.c
+++ b/arch/x86/kernel/vsyscall_64.c
@@ -44,11 +44,6 @@
 
 #define __vsyscall(nr) __attribute__ ((unused,__section__(".vsyscall_" #nr)))
 #define __syscall_clobber "r11","cx","memory"
-#define __pa_vsymbol(x)			\
-	({unsigned long v;  		\
-	extern char __vsyscall_0; 	\
-	  asm("" : "=r" (v) : "0" (x)); \
-	  ((v - VSYSCALL_START) + __pa_symbol(&__vsyscall_0)); })
 
 /*
  * vsyscall_gtod_data contains data that is :
@@ -102,7 +97,7 @@ static __always_inline void do_get_tz(struct timezone * tz)
 static __always_inline int gettimeofday(struct timeval *tv, struct timezone *tz)
 {
 	int ret;
-	asm volatile("vsysc2: syscall"
+	asm volatile("syscall"
 		: "=a" (ret)
 		: "0" (__NR_gettimeofday),"D" (tv),"S" (tz)
 		: __syscall_clobber );
@@ -112,7 +107,7 @@ static __always_inline int gettimeofday(struct timeval *tv, struct timezone *tz)
 static __always_inline long time_syscall(long *t)
 {
 	long secs;
-	asm volatile("vsysc1: syscall"
+	asm volatile("syscall"
 		: "=a" (secs)
 		: "0" (__NR_time),"D" (t) : __syscall_clobber);
 	return secs;
@@ -228,42 +223,11 @@ long __vsyscall(3) venosys_1(void)
 
 #ifdef CONFIG_SYSCTL
 
-#define SYSCALL 0x050f
-#define NOP2    0x9090
-
-/*
- * NOP out syscall in vsyscall page when not needed.
- */
-static int vsyscall_sysctl_change(ctl_table *ctl, int write, struct file * filp,
-                        void __user *buffer, size_t *lenp, loff_t *ppos)
+static int
+vsyscall_sysctl_change(ctl_table *ctl, int write, struct file * filp,
+		       void __user *buffer, size_t *lenp, loff_t *ppos)
 {
-	extern u16 vsysc1, vsysc2;
-	u16 __iomem *map1;
-	u16 __iomem *map2;
-	int ret = proc_dointvec(ctl, write, filp, buffer, lenp, ppos);
-	if (!write)
-		return ret;
-	/* gcc has some trouble with __va(__pa()), so just do it this
-	   way. */
-	map1 = ioremap(__pa_vsymbol(&vsysc1), 2);
-	if (!map1)
-		return -ENOMEM;
-	map2 = ioremap(__pa_vsymbol(&vsysc2), 2);
-	if (!map2) {
-		ret = -ENOMEM;
-		goto out;
-	}
-	if (!vsyscall_gtod_data.sysctl_enabled) {
-		writew(SYSCALL, map1);
-		writew(SYSCALL, map2);
-	} else {
-		writew(NOP2, map1);
-		writew(NOP2, map2);
-	}
-	iounmap(map2);
-out:
-	iounmap(map1);
-	return ret;
+	return proc_dointvec(ctl, write, filp, buffer, lenp, ppos);
 }
 
 static ctl_table kernel_table2[] = {
@@ -279,7 +243,6 @@ static ctl_table kernel_root_table2[] = {
 	  .child = kernel_table2 },
 	{}
 };
-
 #endif
 
 /* Assume __initcall executes before all user space. Hopefully kmod