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

Pull x86 fixes from Ingo Molnar:
 "There's a number of fixes:

   - a round of fixes for CPUID-less legacy CPUs
   - a number of microcode loader fixes
   - i8042 detection robustization fixes
   - stack dump/unwinder fixes
   - x86 SoC platform driver fixes
   - a GCC 7 warning fix
   - virtualization related fixes"

* 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (24 commits)
  Revert "x86/unwind: Detect bad stack return address"
  x86/paravirt: Mark unused patch_default label
  x86/microcode/AMD: Reload proper initrd start address
  x86/platform/intel/quark: Add printf attribute to imr_self_test_result()
  x86/platform/intel-mid: Switch MPU3050 driver to IIO
  x86/alternatives: Do not use sync_core() to serialize I$
  x86/topology: Document cpu_llc_id
  x86/hyperv: Handle unknown NMIs on one CPU when unknown_nmi_panic
  x86/asm: Rewrite sync_core() to use IRET-to-self
  x86/microcode/intel: Replace sync_core() with native_cpuid()
  Revert "x86/boot: Fail the boot if !M486 and CPUID is missing"
  x86/asm/32: Make sync_core() handle missing CPUID on all 32-bit kernels
  x86/cpu: Probe CPUID leaf 6 even when cpuid_level == 6
  x86/tools: Fix gcc-7 warning in relocs.c
  x86/unwind: Dump stack data on warnings
  x86/unwind: Adjust last frame check for aligned function stacks
  x86/init: Fix a couple of comment typos
  x86/init: Remove i8042_detect() from platform ops
  Input: i8042 - Trust firmware a bit more when probing on X86
  x86/init: Add i8042 state to the platform data
  ...

1 files changed, 58 insertions, 22 deletions

diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 6aa741fbe1df..eaf100508c36 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -602,33 +602,69 @@ static __always_inline void cpu_relax(void)
 	rep_nop();
 }
 
-/* Stop speculative execution and prefetching of modified code. */
+/*
+ * This function forces the icache and prefetched instruction stream to
+ * catch up with reality in two very specific cases:
+ *
+ *  a) Text was modified using one virtual address and is about to be executed
+ *     from the same physical page at a different virtual address.
+ *
+ *  b) Text was modified on a different CPU, may subsequently be
+ *     executed on this CPU, and you want to make sure the new version
+ *     gets executed.  This generally means you're calling this in a IPI.
+ *
+ * If you're calling this for a different reason, you're probably doing
+ * it wrong.
+ */
 static inline void sync_core(void)
 {
-	int tmp;
-
-#ifdef CONFIG_M486
 	/*
-	 * Do a CPUID if available, otherwise do a jump.  The jump
-	 * can conveniently enough be the jump around CPUID.
+	 * There are quite a few ways to do this.  IRET-to-self is nice
+	 * because it works on every CPU, at any CPL (so it's compatible
+	 * with paravirtualization), and it never exits to a hypervisor.
+	 * The only down sides are that it's a bit slow (it seems to be
+	 * a bit more than 2x slower than the fastest options) and that
+	 * it unmasks NMIs.  The "push %cs" is needed because, in
+	 * paravirtual environments, __KERNEL_CS may not be a valid CS
+	 * value when we do IRET directly.
+	 *
+	 * In case NMI unmasking or performance ever becomes a problem,
+	 * the next best option appears to be MOV-to-CR2 and an
+	 * unconditional jump.  That sequence also works on all CPUs,
+	 * but it will fault at CPL3 (i.e. Xen PV and lguest).
+	 *
+	 * CPUID is the conventional way, but it's nasty: it doesn't
+	 * exist on some 486-like CPUs, and it usually exits to a
+	 * hypervisor.
+	 *
+	 * Like all of Linux's memory ordering operations, this is a
+	 * compiler barrier as well.
 	 */
-	asm volatile("cmpl %2,%1\n\t"
-		     "jl 1f\n\t"
-		     "cpuid\n"
-		     "1:"
-		     : "=a" (tmp)
-		     : "rm" (boot_cpu_data.cpuid_level), "ri" (0), "0" (1)
-		     : "ebx", "ecx", "edx", "memory");
+	register void *__sp asm(_ASM_SP);
+
+#ifdef CONFIG_X86_32
+	asm volatile (
+		"pushfl\n\t"
+		"pushl %%cs\n\t"
+		"pushl $1f\n\t"
+		"iret\n\t"
+		"1:"
+		: "+r" (__sp) : : "memory");
 #else
-	/*
-	 * CPUID is a barrier to speculative execution.
-	 * Prefetched instructions are automatically
-	 * invalidated when modified.
-	 */
-	asm volatile("cpuid"
-		     : "=a" (tmp)
-		     : "0" (1)
-		     : "ebx", "ecx", "edx", "memory");
+	unsigned int tmp;
+
+	asm volatile (
+		"mov %%ss, %0\n\t"
+		"pushq %q0\n\t"
+		"pushq %%rsp\n\t"
+		"addq $8, (%%rsp)\n\t"
+		"pushfq\n\t"
+		"mov %%cs, %0\n\t"
+		"pushq %q0\n\t"
+		"pushq $1f\n\t"
+		"iretq\n\t"
+		"1:"
+		: "=&r" (tmp), "+r" (__sp) : : "cc", "memory");
 #endif
 }