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

Pull x86 PTI and Spectre related fixes and updates from Ingo Molnar:
 "Here's the latest set of Spectre and PTI related fixes and updates:

  Spectre:
   - Add entry code register clearing to reduce the Spectre attack
     surface
   - Update the Spectre microcode blacklist
   - Inline the KVM Spectre helpers to get close to v4.14 performance
     again.
   - Fix indirect_branch_prediction_barrier()
   - Fix/improve Spectre related kernel messages
   - Fix array_index_nospec_mask() asm constraint
   - KVM: fix two MSR handling bugs

  PTI:
   - Fix a paranoid entry PTI CR3 handling bug
   - Fix comments

  objtool:
   - Fix paranoid_entry() frame pointer warning
   - Annotate WARN()-related UD2 as reachable
   - Various fixes
   - Add Add Peter Zijlstra as objtool co-maintainer

  Misc:
   - Various x86 entry code self-test fixes
   - Improve/simplify entry code stack frame generation and handling
     after recent heavy-handed PTI and Spectre changes. (There's two
     more WIP improvements expected here.)
   - Type fix for cache entries

  There's also some low risk non-fix changes I've included in this
  branch to reduce backporting conflicts:

   - rename a confusing x86_cpu field name
   - de-obfuscate the naming of single-TLB flushing primitives"

* 'x86-pti-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (41 commits)
  x86/entry/64: Fix CR3 restore in paranoid_exit()
  x86/cpu: Change type of x86_cache_size variable to unsigned int
  x86/spectre: Fix an error message
  x86/cpu: Rename cpu_data.x86_mask to cpu_data.x86_stepping
  selftests/x86/mpx: Fix incorrect bounds with old _sigfault
  x86/mm: Rename flush_tlb_single() and flush_tlb_one() to __flush_tlb_one_[user|kernel]()
  x86/speculation: Add <asm/msr-index.h> dependency
  nospec: Move array_index_nospec() parameter checking into separate macro
  x86/speculation: Fix up array_index_nospec_mask() asm constraint
  x86/debug: Use UD2 for WARN()
  x86/debug, objtool: Annotate WARN()-related UD2 as reachable
  objtool: Fix segfault in ignore_unreachable_insn()
  selftests/x86: Disable tests requiring 32-bit support on pure 64-bit systems
  selftests/x86: Do not rely on "int $0x80" in single_step_syscall.c
  selftests/x86: Do not rely on "int $0x80" in test_mremap_vdso.c
  selftests/x86: Fix build bug caused by the 5lvl test which has been moved to the VM directory
  selftests/x86/pkeys: Remove unused functions
  selftests/x86: Clean up and document sscanf() usage
  selftests/x86: Fix vDSO selftest segfault for vsyscall=none
  x86/entry/64: Remove the unused 'icebp' macro
  ...

9 files changed, 48 insertions, 31 deletions

diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h
index 44f5d79d5105..11881726ed37 100644
--- a/arch/x86/include/asm/acpi.h
+++ b/arch/x86/include/asm/acpi.h
@@ -94,7 +94,7 @@ static inline unsigned int acpi_processor_cstate_check(unsigned int max_cstate)
 	if (boot_cpu_data.x86 == 0x0F &&
 	    boot_cpu_data.x86_vendor == X86_VENDOR_AMD &&
 	    boot_cpu_data.x86_model <= 0x05 &&
-	    boot_cpu_data.x86_mask < 0x0A)
+	    boot_cpu_data.x86_stepping < 0x0A)
 		return 1;
 	else if (boot_cpu_has(X86_BUG_AMD_APIC_C1E))
 		return 1;
diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h
index 30d406146016..e1259f043ae9 100644
--- a/arch/x86/include/asm/barrier.h
+++ b/arch/x86/include/asm/barrier.h
@@ -40,7 +40,7 @@ static inline unsigned long array_index_mask_nospec(unsigned long index,
 
 	asm ("cmp %1,%2; sbb %0,%0;"
 			:"=r" (mask)
-			:"r"(size),"r" (index)
+			:"g"(size),"r" (index)
 			:"cc");
 	return mask;
 }
diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h
index 34d99af43994..6804d6642767 100644
--- a/arch/x86/include/asm/bug.h
+++ b/arch/x86/include/asm/bug.h
@@ -5,23 +5,20 @@
 #include <linux/stringify.h>
 
 /*
- * Since some emulators terminate on UD2, we cannot use it for WARN.
- * Since various instruction decoders disagree on the length of UD1,
- * we cannot use it either. So use UD0 for WARN.
+ * Despite that some emulators terminate on UD2, we use it for WARN().
  *
- * (binutils knows about "ud1" but {en,de}codes it as 2 bytes, whereas
- *  our kernel decoder thinks it takes a ModRM byte, which seems consistent
- *  with various things like the Intel SDM instruction encoding rules)
+ * Since various instruction decoders/specs disagree on the encoding of
+ * UD0/UD1.
  */
 
-#define ASM_UD0		".byte 0x0f, 0xff"
+#define ASM_UD0		".byte 0x0f, 0xff" /* + ModRM (for Intel) */
 #define ASM_UD1		".byte 0x0f, 0xb9" /* + ModRM */
 #define ASM_UD2		".byte 0x0f, 0x0b"
 
 #define INSN_UD0	0xff0f
 #define INSN_UD2	0x0b0f
 
-#define LEN_UD0		2
+#define LEN_UD2		2
 
 #ifdef CONFIG_GENERIC_BUG
 
@@ -77,7 +74,11 @@ do {								\
 	unreachable();						\
 } while (0)
 
-#define __WARN_FLAGS(flags)	_BUG_FLAGS(ASM_UD0, BUGFLAG_WARNING|(flags))
+#define __WARN_FLAGS(flags)					\
+do {								\
+	_BUG_FLAGS(ASM_UD2, BUGFLAG_WARNING|(flags));		\
+	annotate_reachable();					\
+} while (0)
 
 #include <asm-generic/bug.h>
 
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index 4d57894635f2..76b058533e47 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -6,6 +6,7 @@
 #include <asm/alternative.h>
 #include <asm/alternative-asm.h>
 #include <asm/cpufeatures.h>
+#include <asm/msr-index.h>
 
 #ifdef __ASSEMBLY__
 
@@ -164,10 +165,15 @@ static inline void vmexit_fill_RSB(void)
 
 static inline void indirect_branch_prediction_barrier(void)
 {
-	alternative_input("",
-			  "call __ibp_barrier",
-			  X86_FEATURE_USE_IBPB,
-			  ASM_NO_INPUT_CLOBBER("eax", "ecx", "edx", "memory"));
+	asm volatile(ALTERNATIVE("",
+				 "movl %[msr], %%ecx\n\t"
+				 "movl %[val], %%eax\n\t"
+				 "movl $0, %%edx\n\t"
+				 "wrmsr",
+				 X86_FEATURE_USE_IBPB)
+		     : : [msr] "i" (MSR_IA32_PRED_CMD),
+			 [val] "i" (PRED_CMD_IBPB)
+		     : "eax", "ecx", "edx", "memory");
 }
 
 #endif /* __ASSEMBLY__ */
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 892df375b615..554841fab717 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -297,9 +297,9 @@ static inline void __flush_tlb_global(void)
 {
 	PVOP_VCALL0(pv_mmu_ops.flush_tlb_kernel);
 }
-static inline void __flush_tlb_single(unsigned long addr)
+static inline void __flush_tlb_one_user(unsigned long addr)
 {
-	PVOP_VCALL1(pv_mmu_ops.flush_tlb_single, addr);
+	PVOP_VCALL1(pv_mmu_ops.flush_tlb_one_user, addr);
 }
 
 static inline void flush_tlb_others(const struct cpumask *cpumask,
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 6ec54d01972d..f624f1f10316 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -217,7 +217,7 @@ struct pv_mmu_ops {
 	/* TLB operations */
 	void (*flush_tlb_user)(void);
 	void (*flush_tlb_kernel)(void);
-	void (*flush_tlb_single)(unsigned long addr);
+	void (*flush_tlb_one_user)(unsigned long addr);
 	void (*flush_tlb_others)(const struct cpumask *cpus,
 				 const struct flush_tlb_info *info);
 
diff --git a/arch/x86/include/asm/pgtable_32.h b/arch/x86/include/asm/pgtable_32.h
index e67c0620aec2..e55466760ff8 100644
--- a/arch/x86/include/asm/pgtable_32.h
+++ b/arch/x86/include/asm/pgtable_32.h
@@ -61,7 +61,7 @@ void paging_init(void);
 #define kpte_clear_flush(ptep, vaddr)		\
 do {						\
 	pte_clear(&init_mm, (vaddr), (ptep));	\
-	__flush_tlb_one((vaddr));		\
+	__flush_tlb_one_kernel((vaddr));		\
 } while (0)
 
 #endif /* !__ASSEMBLY__ */
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 793bae7e7ce3..1bd9ed87606f 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -91,7 +91,7 @@ struct cpuinfo_x86 {
 	__u8			x86;		/* CPU family */
 	__u8			x86_vendor;	/* CPU vendor */
 	__u8			x86_model;
-	__u8			x86_mask;
+	__u8			x86_stepping;
 #ifdef CONFIG_X86_64
 	/* Number of 4K pages in DTLB/ITLB combined(in pages): */
 	int			x86_tlbsize;
@@ -109,7 +109,7 @@ struct cpuinfo_x86 {
 	char			x86_vendor_id[16];
 	char			x86_model_id[64];
 	/* in KB - valid for CPUS which support this call: */
-	int			x86_cache_size;
+	unsigned int		x86_cache_size;
 	int			x86_cache_alignment;	/* In bytes */
 	/* Cache QoS architectural values: */
 	int			x86_cache_max_rmid;	/* max index */
@@ -977,7 +977,4 @@ bool xen_set_default_idle(void);
 
 void stop_this_cpu(void *dummy);
 void df_debug(struct pt_regs *regs, long error_code);
-
-void __ibp_barrier(void);
-
 #endif /* _ASM_X86_PROCESSOR_H */
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 2b8f18ca5874..84137c22fdfa 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -140,7 +140,7 @@ static inline unsigned long build_cr3_noflush(pgd_t *pgd, u16 asid)
 #else
 #define __flush_tlb() __native_flush_tlb()
 #define __flush_tlb_global() __native_flush_tlb_global()
-#define __flush_tlb_single(addr) __native_flush_tlb_single(addr)
+#define __flush_tlb_one_user(addr) __native_flush_tlb_one_user(addr)
 #endif
 
 static inline bool tlb_defer_switch_to_init_mm(void)
@@ -400,7 +400,7 @@ static inline void __native_flush_tlb_global(void)
 /*
  * flush one page in the user mapping
  */
-static inline void __native_flush_tlb_single(unsigned long addr)
+static inline void __native_flush_tlb_one_user(unsigned long addr)
 {
 	u32 loaded_mm_asid = this_cpu_read(cpu_tlbstate.loaded_mm_asid);
 
@@ -437,18 +437,31 @@ static inline void __flush_tlb_all(void)
 /*
  * flush one page in the kernel mapping
  */
-static inline void __flush_tlb_one(unsigned long addr)
+static inline void __flush_tlb_one_kernel(unsigned long addr)
 {
 	count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ONE);
-	__flush_tlb_single(addr);
+
+	/*
+	 * If PTI is off, then __flush_tlb_one_user() is just INVLPG or its
+	 * paravirt equivalent.  Even with PCID, this is sufficient: we only
+	 * use PCID if we also use global PTEs for the kernel mapping, and
+	 * INVLPG flushes global translations across all address spaces.
+	 *
+	 * If PTI is on, then the kernel is mapped with non-global PTEs, and
+	 * __flush_tlb_one_user() will flush the given address for the current
+	 * kernel address space and for its usermode counterpart, but it does
+	 * not flush it for other address spaces.
+	 */
+	__flush_tlb_one_user(addr);
 
 	if (!static_cpu_has(X86_FEATURE_PTI))
 		return;
 
 	/*
-	 * __flush_tlb_single() will have cleared the TLB entry for this ASID,
-	 * but since kernel space is replicated across all, we must also
-	 * invalidate all others.
+	 * See above.  We need to propagate the flush to all other address
+	 * spaces.  In principle, we only need to propagate it to kernelmode
+	 * address spaces, but the extra bookkeeping we would need is not
+	 * worth it.
 	 */
 	invalidate_other_asid();
 }