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

Pull x86 fixes from Thomas Gleixner:
 "Speculation:

   - Make the microcode check more robust

   - Make the L1TF memory limit depend on the internal cache physical
     address space and not on the CPUID advertised physical address
     space, which might be significantly smaller. This avoids disabling
     L1TF on machines which utilize the full physical address space.

   - Fix the GDT mapping for EFI calls on 32bit PTI

   - Fix the MCE nospec implementation to prevent #GP

  Fixes and robustness:

   - Use the proper operand order for LSL in the VDSO

   - Prevent NMI uaccess race against CR3 switching

   - Add a lockdep check to verify that text_mutex is held in
     text_poke() functions

   - Repair the fallout of giving native_restore_fl() a prototype

   - Prevent kernel memory dumps based on usermode RIP

   - Wipe KASAN shadow stack before rewinding the stack to prevent false
     positives

   - Move the AMS GOTO enforcement to the actual build stage to allow
     user API header extraction without a compiler

   - Fix a section mismatch introduced by the on demand VDSO mapping
     change

  Miscellaneous:

   - Trivial typo, GCC quirk removal and CC_SET/OUT() cleanups"

* 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/pti: Fix section mismatch warning/error
  x86/vdso: Fix lsl operand order
  x86/mce: Fix set_mce_nospec() to avoid #GP fault
  x86/efi: Load fixmap GDT in efi_call_phys_epilog()
  x86/nmi: Fix NMI uaccess race against CR3 switching
  x86: Allow generating user-space headers without a compiler
  x86/dumpstack: Don't dump kernel memory based on usermode RIP
  x86/asm: Use CC_SET()/CC_OUT() in __gen_sigismember()
  x86/alternatives: Lockdep-enforce text_mutex in text_poke*()
  x86/entry/64: Wipe KASAN stack shadow before rewind_stack_do_exit()
  x86/irqflags: Mark native_restore_fl extern inline
  x86/build: Remove jump label quirk for GCC older than 4.5.2
  x86/Kconfig: Fix trivial typo
  x86/speculation/l1tf: Increase l1tf memory limit for Nehalem+
  x86/spectre: Add missing family 6 check to microcode check

6 files changed, 51 insertions, 7 deletions

diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h
index c14f2a74b2be..15450a675031 100644
--- a/arch/x86/include/asm/irqflags.h
+++ b/arch/x86/include/asm/irqflags.h
@@ -33,7 +33,8 @@ extern inline unsigned long native_save_fl(void)
 	return flags;
 }
 
-static inline void native_restore_fl(unsigned long flags)
+extern inline void native_restore_fl(unsigned long flags);
+extern inline void native_restore_fl(unsigned long flags)
 {
 	asm volatile("push %0 ; popf"
 		     : /* no output */
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index c24297268ebc..d53c54b842da 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -132,6 +132,8 @@ struct cpuinfo_x86 {
 	/* Index into per_cpu list: */
 	u16			cpu_index;
 	u32			microcode;
+	/* Address space bits used by the cache internally */
+	u8			x86_cache_bits;
 	unsigned		initialized : 1;
 } __randomize_layout;
 
@@ -183,7 +185,7 @@ extern void cpu_detect(struct cpuinfo_x86 *c);
 
 static inline unsigned long long l1tf_pfn_limit(void)
 {
-	return BIT_ULL(boot_cpu_data.x86_phys_bits - 1 - PAGE_SHIFT);
+	return BIT_ULL(boot_cpu_data.x86_cache_bits - 1 - PAGE_SHIFT);
 }
 
 extern void early_cpu_init(void);
diff --git a/arch/x86/include/asm/signal.h b/arch/x86/include/asm/signal.h
index 5f9012ff52ed..33d3c88a7225 100644
--- a/arch/x86/include/asm/signal.h
+++ b/arch/x86/include/asm/signal.h
@@ -39,6 +39,7 @@ extern void do_signal(struct pt_regs *regs);
 
 #define __ARCH_HAS_SA_RESTORER
 
+#include <asm/asm.h>
 #include <uapi/asm/sigcontext.h>
 
 #ifdef __i386__
@@ -86,9 +87,9 @@ static inline int __const_sigismember(sigset_t *set, int _sig)
 
 static inline int __gen_sigismember(sigset_t *set, int _sig)
 {
-	unsigned char ret;
-	asm("btl %2,%1\n\tsetc %0"
-	    : "=qm"(ret) : "m"(*set), "Ir"(_sig-1) : "cc");
+	bool ret;
+	asm("btl %2,%1" CC_SET(c)
+	    : CC_OUT(c) (ret) : "m"(*set), "Ir"(_sig-1));
 	return ret;
 }
 
diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h
index b6dc698f992a..f335aad404a4 100644
--- a/arch/x86/include/asm/stacktrace.h
+++ b/arch/x86/include/asm/stacktrace.h
@@ -111,6 +111,6 @@ static inline unsigned long caller_frame_pointer(void)
 	return (unsigned long)frame;
 }
 
-void show_opcodes(u8 *rip, const char *loglvl);
+void show_opcodes(struct pt_regs *regs, const char *loglvl);
 void show_ip(struct pt_regs *regs, const char *loglvl);
 #endif /* _ASM_X86_STACKTRACE_H */
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 29c9da6c62fc..58ce5288878e 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -175,8 +175,16 @@ struct tlb_state {
 	 * are on.  This means that it may not match current->active_mm,
 	 * which will contain the previous user mm when we're in lazy TLB
 	 * mode even if we've already switched back to swapper_pg_dir.
+	 *
+	 * During switch_mm_irqs_off(), loaded_mm will be set to
+	 * LOADED_MM_SWITCHING during the brief interrupts-off window
+	 * when CR3 and loaded_mm would otherwise be inconsistent.  This
+	 * is for nmi_uaccess_okay()'s benefit.
 	 */
 	struct mm_struct *loaded_mm;
+
+#define LOADED_MM_SWITCHING ((struct mm_struct *)1)
+
 	u16 loaded_mm_asid;
 	u16 next_asid;
 	/* last user mm's ctx id */
@@ -246,6 +254,38 @@ struct tlb_state {
 };
 DECLARE_PER_CPU_SHARED_ALIGNED(struct tlb_state, cpu_tlbstate);
 
+/*
+ * Blindly accessing user memory from NMI context can be dangerous
+ * if we're in the middle of switching the current user task or
+ * switching the loaded mm.  It can also be dangerous if we
+ * interrupted some kernel code that was temporarily using a
+ * different mm.
+ */
+static inline bool nmi_uaccess_okay(void)
+{
+	struct mm_struct *loaded_mm = this_cpu_read(cpu_tlbstate.loaded_mm);
+	struct mm_struct *current_mm = current->mm;
+
+	VM_WARN_ON_ONCE(!loaded_mm);
+
+	/*
+	 * The condition we want to check is
+	 * current_mm->pgd == __va(read_cr3_pa()).  This may be slow, though,
+	 * if we're running in a VM with shadow paging, and nmi_uaccess_okay()
+	 * is supposed to be reasonably fast.
+	 *
+	 * Instead, we check the almost equivalent but somewhat conservative
+	 * condition below, and we rely on the fact that switch_mm_irqs_off()
+	 * sets loaded_mm to LOADED_MM_SWITCHING before writing to CR3.
+	 */
+	if (loaded_mm != current_mm)
+		return false;
+
+	VM_WARN_ON_ONCE(current_mm->pgd != __va(read_cr3_pa()));
+
+	return true;
+}
+
 /* Initialize cr4 shadow for this CPU. */
 static inline void cr4_init_shadow(void)
 {
diff --git a/arch/x86/include/asm/vgtod.h b/arch/x86/include/asm/vgtod.h
index fb856c9f0449..53748541c487 100644
--- a/arch/x86/include/asm/vgtod.h
+++ b/arch/x86/include/asm/vgtod.h
@@ -93,7 +93,7 @@ static inline unsigned int __getcpu(void)
 	 *
 	 * If RDPID is available, use it.
 	 */
-	alternative_io ("lsl %[p],%[seg]",
+	alternative_io ("lsl %[seg],%[p]",
 			".byte 0xf3,0x0f,0xc7,0xf8", /* RDPID %eax/rax */
 			X86_FEATURE_RDPID,
 			[p] "=a" (p), [seg] "r" (__PER_CPU_SEG));