Merge branch 'x86-asm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 asm changes from Ingo Molnar:
 "There were lots of changes in this development cycle:

   - over 100 separate cleanups, restructuring changes, speedups and
     fixes in the x86 system call, irq, trap and other entry code, part
     of a heroic effort to deobfuscate a decade old spaghetti asm code
     and its C code dependencies (Denys Vlasenko, Andy Lutomirski)

   - alternatives code fixes and enhancements (Borislav Petkov)

   - simplifications and cleanups to the compat code (Brian Gerst)

   - signal handling fixes and new x86 testcases (Andy Lutomirski)

   - various other fixes and cleanups

  By their nature many of these changes are risky - we tried to test
  them well on many different x86 systems (there are no known
  regressions), and they are split up finely to help bisection - but
  there's still a fair bit of residual risk left so caveat emptor"

* 'x86-asm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (148 commits)
  perf/x86/64: Report regs_user->ax too in get_regs_user()
  perf/x86/64: Simplify regs_user->abi setting code in get_regs_user()
  perf/x86/64: Do report user_regs->cx while we are in syscall, in get_regs_user()
  perf/x86/64: Do not guess user_regs->cs, ss, sp in get_regs_user()
  x86/asm/entry/32: Tidy up JNZ instructions after TESTs
  x86/asm/entry/64: Reduce padding in execve stubs
  x86/asm/entry/64: Remove GET_THREAD_INFO() in ret_from_fork
  x86/asm/entry/64: Simplify jumps in ret_from_fork
  x86/asm/entry/64: Remove a redundant jump
  x86/asm/entry/64: Optimize [v]fork/clone stubs
  x86/asm/entry: Zero EXTRA_REGS for stub32_execve() too
  x86/asm/entry/64: Move stub_x32_execvecloser() to stub_execveat()
  x86/asm/entry/64: Use common code for rt_sigreturn() epilogue
  x86/asm/entry/64: Add forgotten CFI annotation
  x86/asm/entry/irq: Simplify interrupt dispatch table (IDT) layout
  x86/asm/entry/64: Move opportunistic sysret code to syscall code path
  x86, selftests: Add sigreturn selftest
  x86/alternatives: Guard NOPs optimization
  x86/asm/entry: Clear EXTRA_REGS for all executable formats
  x86/signal: Remove pax argument from restore_sigcontext
  ...

3 files changed, 68 insertions, 42 deletions

diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index a220239cea65..dd9e50500297 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -711,6 +711,11 @@ static void init_amd(struct cpuinfo_x86 *c)
 		set_cpu_bug(c, X86_BUG_AMD_APIC_C1E);
 
 	rdmsr_safe(MSR_AMD64_PATCH_LEVEL, &c->microcode, &dummy);
+
+	/* 3DNow or LM implies PREFETCHW */
+	if (!cpu_has(c, X86_FEATURE_3DNOWPREFETCH))
+		if (cpu_has(c, X86_FEATURE_3DNOW) || cpu_has(c, X86_FEATURE_LM))
+			set_cpu_cap(c, X86_FEATURE_3DNOWPREFETCH);
 }
 
 #ifdef CONFIG_X86_32
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 2346c95c6ab1..3f70538012e2 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -959,38 +959,37 @@ static void identify_cpu(struct cpuinfo_x86 *c)
 #endif
 }
 
-#ifdef CONFIG_X86_64
-#ifdef CONFIG_IA32_EMULATION
-/* May not be __init: called during resume */
-static void syscall32_cpu_init(void)
-{
-	/* Load these always in case some future AMD CPU supports
-	   SYSENTER from compat mode too. */
-	wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)__KERNEL_CS);
-	wrmsrl_safe(MSR_IA32_SYSENTER_ESP, 0ULL);
-	wrmsrl_safe(MSR_IA32_SYSENTER_EIP, (u64)ia32_sysenter_target);
-
-	wrmsrl(MSR_CSTAR, ia32_cstar_target);
-}
-#endif		/* CONFIG_IA32_EMULATION */
-#endif		/* CONFIG_X86_64 */
-
+/*
+ * Set up the CPU state needed to execute SYSENTER/SYSEXIT instructions
+ * on 32-bit kernels:
+ */
 #ifdef CONFIG_X86_32
 void enable_sep_cpu(void)
 {
-	int cpu = get_cpu();
-	struct tss_struct *tss = &per_cpu(init_tss, cpu);
+	struct tss_struct *tss;
+	int cpu;
 
-	if (!boot_cpu_has(X86_FEATURE_SEP)) {
-		put_cpu();
-		return;
-	}
+	cpu = get_cpu();
+	tss = &per_cpu(cpu_tss, cpu);
+
+	if (!boot_cpu_has(X86_FEATURE_SEP))
+		goto out;
+
+	/*
+	 * We cache MSR_IA32_SYSENTER_CS's value in the TSS's ss1 field --
+	 * see the big comment in struct x86_hw_tss's definition.
+	 */
 
 	tss->x86_tss.ss1 = __KERNEL_CS;
-	tss->x86_tss.sp1 = sizeof(struct tss_struct) + (unsigned long) tss;
-	wrmsr(MSR_IA32_SYSENTER_CS, __KERNEL_CS, 0);
-	wrmsr(MSR_IA32_SYSENTER_ESP, tss->x86_tss.sp1, 0);
-	wrmsr(MSR_IA32_SYSENTER_EIP, (unsigned long) ia32_sysenter_target, 0);
+	wrmsr(MSR_IA32_SYSENTER_CS, tss->x86_tss.ss1, 0);
+
+	wrmsr(MSR_IA32_SYSENTER_ESP,
+	      (unsigned long)tss + offsetofend(struct tss_struct, SYSENTER_stack),
+	      0);
+
+	wrmsr(MSR_IA32_SYSENTER_EIP, (unsigned long)ia32_sysenter_target, 0);
+
+out:
 	put_cpu();
 }
 #endif
@@ -1118,7 +1117,7 @@ static __init int setup_disablecpuid(char *arg)
 __setup("clearcpuid=", setup_disablecpuid);
 
 DEFINE_PER_CPU(unsigned long, kernel_stack) =
-	(unsigned long)&init_thread_union - KERNEL_STACK_OFFSET + THREAD_SIZE;
+	(unsigned long)&init_thread_union + THREAD_SIZE;
 EXPORT_PER_CPU_SYMBOL(kernel_stack);
 
 #ifdef CONFIG_X86_64
@@ -1130,8 +1129,8 @@ DEFINE_PER_CPU_FIRST(union irq_stack_union,
 		     irq_stack_union) __aligned(PAGE_SIZE) __visible;
 
 /*
- * The following four percpu variables are hot.  Align current_task to
- * cacheline size such that all four fall in the same cacheline.
+ * The following percpu variables are hot.  Align current_task to
+ * cacheline size such that they fall in the same cacheline.
  */
 DEFINE_PER_CPU(struct task_struct *, current_task) ____cacheline_aligned =
 	&init_task;
@@ -1171,10 +1170,23 @@ void syscall_init(void)
 	 */
 	wrmsrl(MSR_STAR,  ((u64)__USER32_CS)<<48  | ((u64)__KERNEL_CS)<<32);
 	wrmsrl(MSR_LSTAR, system_call);
-	wrmsrl(MSR_CSTAR, ignore_sysret);
 
 #ifdef CONFIG_IA32_EMULATION
-	syscall32_cpu_init();
+	wrmsrl(MSR_CSTAR, ia32_cstar_target);
+	/*
+	 * This only works on Intel CPUs.
+	 * On AMD CPUs these MSRs are 32-bit, CPU truncates MSR_IA32_SYSENTER_EIP.
+	 * This does not cause SYSENTER to jump to the wrong location, because
+	 * AMD doesn't allow SYSENTER in long mode (either 32- or 64-bit).
+	 */
+	wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)__KERNEL_CS);
+	wrmsrl_safe(MSR_IA32_SYSENTER_ESP, 0ULL);
+	wrmsrl_safe(MSR_IA32_SYSENTER_EIP, (u64)ia32_sysenter_target);
+#else
+	wrmsrl(MSR_CSTAR, ignore_sysret);
+	wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)GDT_ENTRY_INVALID_SEG);
+	wrmsrl_safe(MSR_IA32_SYSENTER_ESP, 0ULL);
+	wrmsrl_safe(MSR_IA32_SYSENTER_EIP, 0ULL);
 #endif
 
 	/* Flags to clear on syscall */
@@ -1226,6 +1238,15 @@ DEFINE_PER_CPU(int, __preempt_count) = INIT_PREEMPT_COUNT;
 EXPORT_PER_CPU_SYMBOL(__preempt_count);
 DEFINE_PER_CPU(struct task_struct *, fpu_owner_task);
 
+/*
+ * On x86_32, vm86 modifies tss.sp0, so sp0 isn't a reliable way to find
+ * the top of the kernel stack.  Use an extra percpu variable to track the
+ * top of the kernel stack directly.
+ */
+DEFINE_PER_CPU(unsigned long, cpu_current_top_of_stack) =
+	(unsigned long)&init_thread_union + THREAD_SIZE;
+EXPORT_PER_CPU_SYMBOL(cpu_current_top_of_stack);
+
 #ifdef CONFIG_CC_STACKPROTECTOR
 DEFINE_PER_CPU_ALIGNED(struct stack_canary, stack_canary);
 #endif
@@ -1307,7 +1328,7 @@ void cpu_init(void)
 	 */
 	load_ucode_ap();
 
-	t = &per_cpu(init_tss, cpu);
+	t = &per_cpu(cpu_tss, cpu);
 	oist = &per_cpu(orig_ist, cpu);
 
 #ifdef CONFIG_NUMA
@@ -1391,7 +1412,7 @@ void cpu_init(void)
 {
 	int cpu = smp_processor_id();
 	struct task_struct *curr = current;
-	struct tss_struct *t = &per_cpu(init_tss, cpu);
+	struct tss_struct *t = &per_cpu(cpu_tss, cpu);
 	struct thread_struct *thread = &curr->thread;
 
 	wait_for_master_cpu(cpu);
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index b71a7f86d68a..e2888a3ad1e3 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -2147,24 +2147,24 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
 static unsigned long code_segment_base(struct pt_regs *regs)
 {
 	/*
+	 * For IA32 we look at the GDT/LDT segment base to convert the
+	 * effective IP to a linear address.
+	 */
+
+#ifdef CONFIG_X86_32
+	/*
 	 * If we are in VM86 mode, add the segment offset to convert to a
 	 * linear address.
 	 */
 	if (regs->flags & X86_VM_MASK)
 		return 0x10 * regs->cs;
 
-	/*
-	 * For IA32 we look at the GDT/LDT segment base to convert the
-	 * effective IP to a linear address.
-	 */
-#ifdef CONFIG_X86_32
 	if (user_mode(regs) && regs->cs != __USER_CS)
 		return get_segment_base(regs->cs);
 #else
-	if (test_thread_flag(TIF_IA32)) {
-		if (user_mode(regs) && regs->cs != __USER32_CS)
-			return get_segment_base(regs->cs);
-	}
+	if (user_mode(regs) && !user_64bit_mode(regs) &&
+	    regs->cs != __USER32_CS)
+		return get_segment_base(regs->cs);
 #endif
 	return 0;
 }