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

Pull x86 pti bits and fixes from Thomas Gleixner:
 "This last update contains:

   - An objtool fix to prevent a segfault with the gold linker by
     changing the invocation order. That's not just for gold, it's a
     general robustness improvement.

   - An improved error message for objtool which spares tearing hairs.

   - Make KASAN fail loudly if there is not enough memory instead of
     oopsing at some random place later

   - RSB fill on context switch to prevent RSB underflow and speculation
     through other units.

   - Make the retpoline/RSB functionality work reliably for both Intel
     and AMD

   - Add retpoline to the module version magic so mismatch can be
     detected

   - A small (non-fix) update for cpufeatures which prevents cpu feature
     clashing for the upcoming extra mitigation bits to ease
     backporting"

* 'x86-pti-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  module: Add retpoline tag to VERMAGIC
  x86/cpufeature: Move processor tracing out of scattered features
  objtool: Improve error message for bad file argument
  objtool: Fix seg fault with gold linker
  x86/retpoline: Add LFENCE to the retpoline/RSB filling RSB macros
  x86/retpoline: Fill RSB on context switch for affected CPUs
  x86/kasan: Panic if there is not enough memory to boot

10 files changed, 99 insertions, 19 deletions

diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index a1f28a54f23a..60c4c342316c 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -244,6 +244,17 @@ ENTRY(__switch_to_asm)
 	movl	%ebx, PER_CPU_VAR(stack_canary)+stack_canary_offset
 #endif
 
+#ifdef CONFIG_RETPOLINE
+	/*
+	 * When switching from a shallower to a deeper call stack
+	 * the RSB may either underflow or use entries populated
+	 * with userspace addresses. On CPUs where those concerns
+	 * exist, overwrite the RSB with entries which capture
+	 * speculative execution to prevent attack.
+	 */
+	FILL_RETURN_BUFFER %ebx, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW
+#endif
+
 	/* restore callee-saved registers */
 	popl	%esi
 	popl	%edi
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 4f8e1d35a97c..aa15b4c0e3d1 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -491,6 +491,17 @@ ENTRY(__switch_to_asm)
 	movq	%rbx, PER_CPU_VAR(irq_stack_union)+stack_canary_offset
 #endif
 
+#ifdef CONFIG_RETPOLINE
+	/*
+	 * When switching from a shallower to a deeper call stack
+	 * the RSB may either underflow or use entries populated
+	 * with userspace addresses. On CPUs where those concerns
+	 * exist, overwrite the RSB with entries which capture
+	 * speculative execution to prevent attack.
+	 */
+	FILL_RETURN_BUFFER %r12, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW
+#endif
+
 	/* restore callee-saved registers */
 	popq	%r15
 	popq	%r14
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index f275447862f4..25b9375c1484 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -206,11 +206,11 @@
 #define X86_FEATURE_RETPOLINE		( 7*32+12) /* Generic Retpoline mitigation for Spectre variant 2 */
 #define X86_FEATURE_RETPOLINE_AMD	( 7*32+13) /* AMD Retpoline mitigation for Spectre variant 2 */
 #define X86_FEATURE_INTEL_PPIN		( 7*32+14) /* Intel Processor Inventory Number */
-#define X86_FEATURE_INTEL_PT		( 7*32+15) /* Intel Processor Trace */
 #define X86_FEATURE_AVX512_4VNNIW	( 7*32+16) /* AVX-512 Neural Network Instructions */
 #define X86_FEATURE_AVX512_4FMAPS	( 7*32+17) /* AVX-512 Multiply Accumulation Single precision */
 
 #define X86_FEATURE_MBA			( 7*32+18) /* Memory Bandwidth Allocation */
+#define X86_FEATURE_RSB_CTXSW		( 7*32+19) /* Fill RSB on context switches */
 
 /* Virtualization flags: Linux defined, word 8 */
 #define X86_FEATURE_TPR_SHADOW		( 8*32+ 0) /* Intel TPR Shadow */
@@ -245,6 +245,7 @@
 #define X86_FEATURE_AVX512IFMA		( 9*32+21) /* AVX-512 Integer Fused Multiply-Add instructions */
 #define X86_FEATURE_CLFLUSHOPT		( 9*32+23) /* CLFLUSHOPT instruction */
 #define X86_FEATURE_CLWB		( 9*32+24) /* CLWB instruction */
+#define X86_FEATURE_INTEL_PT		( 9*32+25) /* Intel Processor Trace */
 #define X86_FEATURE_AVX512PF		( 9*32+26) /* AVX-512 Prefetch */
 #define X86_FEATURE_AVX512ER		( 9*32+27) /* AVX-512 Exponential and Reciprocal */
 #define X86_FEATURE_AVX512CD		( 9*32+28) /* AVX-512 Conflict Detection */
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index 402a11c803c3..7b45d8424150 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -11,7 +11,7 @@
  * Fill the CPU return stack buffer.
  *
  * Each entry in the RSB, if used for a speculative 'ret', contains an
- * infinite 'pause; jmp' loop to capture speculative execution.
+ * infinite 'pause; lfence; jmp' loop to capture speculative execution.
  *
  * This is required in various cases for retpoline and IBRS-based
  * mitigations for the Spectre variant 2 vulnerability. Sometimes to
@@ -38,11 +38,13 @@
 	call	772f;				\
 773:	/* speculation trap */			\
 	pause;					\
+	lfence;					\
 	jmp	773b;				\
 772:						\
 	call	774f;				\
 775:	/* speculation trap */			\
 	pause;					\
+	lfence;					\
 	jmp	775b;				\
 774:						\
 	dec	reg;				\
@@ -73,6 +75,7 @@
 	call	.Ldo_rop_\@
 .Lspec_trap_\@:
 	pause
+	lfence
 	jmp	.Lspec_trap_\@
 .Ldo_rop_\@:
 	mov	\reg, (%_ASM_SP)
@@ -165,6 +168,7 @@
 	"       .align 16\n"					\
 	"901:	call   903f;\n"					\
 	"902:	pause;\n"					\
+	"    	lfence;\n"					\
 	"       jmp    902b;\n"					\
 	"       .align 16\n"					\
 	"903:	addl   $4, %%esp;\n"				\
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index e4dc26185aa7..390b3dc3d438 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -23,6 +23,7 @@
 #include <asm/alternative.h>
 #include <asm/pgtable.h>
 #include <asm/set_memory.h>
+#include <asm/intel-family.h>
 
 static void __init spectre_v2_select_mitigation(void);
 
@@ -155,6 +156,23 @@ disable:
 	return SPECTRE_V2_CMD_NONE;
 }
 
+/* Check for Skylake-like CPUs (for RSB handling) */
+static bool __init is_skylake_era(void)
+{
+	if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL &&
+	    boot_cpu_data.x86 == 6) {
+		switch (boot_cpu_data.x86_model) {
+		case INTEL_FAM6_SKYLAKE_MOBILE:
+		case INTEL_FAM6_SKYLAKE_DESKTOP:
+		case INTEL_FAM6_SKYLAKE_X:
+		case INTEL_FAM6_KABYLAKE_MOBILE:
+		case INTEL_FAM6_KABYLAKE_DESKTOP:
+			return true;
+		}
+	}
+	return false;
+}
+
 static void __init spectre_v2_select_mitigation(void)
 {
 	enum spectre_v2_mitigation_cmd cmd = spectre_v2_parse_cmdline();
@@ -213,6 +231,24 @@ retpoline_auto:
 
 	spectre_v2_enabled = mode;
 	pr_info("%s\n", spectre_v2_strings[mode]);
+
+	/*
+	 * If neither SMEP or KPTI are available, there is a risk of
+	 * hitting userspace addresses in the RSB after a context switch
+	 * from a shallow call stack to a deeper one. To prevent this fill
+	 * the entire RSB, even when using IBRS.
+	 *
+	 * Skylake era CPUs have a separate issue with *underflow* of the
+	 * RSB, when they will predict 'ret' targets from the generic BTB.
+	 * The proper mitigation for this is IBRS. If IBRS is not supported
+	 * or deactivated in favour of retpolines the RSB fill on context
+	 * switch is required.
+	 */
+	if ((!boot_cpu_has(X86_FEATURE_PTI) &&
+	     !boot_cpu_has(X86_FEATURE_SMEP)) || is_skylake_era()) {
+		setup_force_cpu_cap(X86_FEATURE_RSB_CTXSW);
+		pr_info("Filling RSB on context switch\n");
+	}
 }
 
 #undef pr_fmt
diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c
index 05459ad3db46..d0e69769abfd 100644
--- a/arch/x86/kernel/cpu/scattered.c
+++ b/arch/x86/kernel/cpu/scattered.c
@@ -21,7 +21,6 @@ struct cpuid_bit {
 static const struct cpuid_bit cpuid_bits[] = {
 	{ X86_FEATURE_APERFMPERF,       CPUID_ECX,  0, 0x00000006, 0 },
 	{ X86_FEATURE_EPB,		CPUID_ECX,  3, 0x00000006, 0 },
-	{ X86_FEATURE_INTEL_PT,		CPUID_EBX, 25, 0x00000007, 0 },
 	{ X86_FEATURE_AVX512_4VNNIW,    CPUID_EDX,  2, 0x00000007, 0 },
 	{ X86_FEATURE_AVX512_4FMAPS,    CPUID_EDX,  3, 0x00000007, 0 },
 	{ X86_FEATURE_CAT_L3,		CPUID_EBX,  1, 0x00000010, 0 },
diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c
index 47388f0c0e59..af6f2f9c6a26 100644
--- a/arch/x86/mm/kasan_init_64.c
+++ b/arch/x86/mm/kasan_init_64.c
@@ -21,10 +21,14 @@ extern struct range pfn_mapped[E820_MAX_ENTRIES];
 
 static p4d_t tmp_p4d_table[PTRS_PER_P4D] __initdata __aligned(PAGE_SIZE);
 
-static __init void *early_alloc(size_t size, int nid)
+static __init void *early_alloc(size_t size, int nid, bool panic)
 {
-	return memblock_virt_alloc_try_nid_nopanic(size, size,
-		__pa(MAX_DMA_ADDRESS), BOOTMEM_ALLOC_ACCESSIBLE, nid);
+	if (panic)
+		return memblock_virt_alloc_try_nid(size, size,
+			__pa(MAX_DMA_ADDRESS), BOOTMEM_ALLOC_ACCESSIBLE, nid);
+	else
+		return memblock_virt_alloc_try_nid_nopanic(size, size,
+			__pa(MAX_DMA_ADDRESS), BOOTMEM_ALLOC_ACCESSIBLE, nid);
 }
 
 static void __init kasan_populate_pmd(pmd_t *pmd, unsigned long addr,
@@ -38,14 +42,14 @@ static void __init kasan_populate_pmd(pmd_t *pmd, unsigned long addr,
 		if (boot_cpu_has(X86_FEATURE_PSE) &&
 		    ((end - addr) == PMD_SIZE) &&
 		    IS_ALIGNED(addr, PMD_SIZE)) {
-			p = early_alloc(PMD_SIZE, nid);
+			p = early_alloc(PMD_SIZE, nid, false);
 			if (p && pmd_set_huge(pmd, __pa(p), PAGE_KERNEL))
 				return;
 			else if (p)
 				memblock_free(__pa(p), PMD_SIZE);
 		}
 
-		p = early_alloc(PAGE_SIZE, nid);
+		p = early_alloc(PAGE_SIZE, nid, true);
 		pmd_populate_kernel(&init_mm, pmd, p);
 	}
 
@@ -57,7 +61,7 @@ static void __init kasan_populate_pmd(pmd_t *pmd, unsigned long addr,
 		if (!pte_none(*pte))
 			continue;
 
-		p = early_alloc(PAGE_SIZE, nid);
+		p = early_alloc(PAGE_SIZE, nid, true);
 		entry = pfn_pte(PFN_DOWN(__pa(p)), PAGE_KERNEL);
 		set_pte_at(&init_mm, addr, pte, entry);
 	} while (pte++, addr += PAGE_SIZE, addr != end);
@@ -75,14 +79,14 @@ static void __init kasan_populate_pud(pud_t *pud, unsigned long addr,
 		if (boot_cpu_has(X86_FEATURE_GBPAGES) &&
 		    ((end - addr) == PUD_SIZE) &&
 		    IS_ALIGNED(addr, PUD_SIZE)) {
-			p = early_alloc(PUD_SIZE, nid);
+			p = early_alloc(PUD_SIZE, nid, false);
 			if (p && pud_set_huge(pud, __pa(p), PAGE_KERNEL))
 				return;
 			else if (p)
 				memblock_free(__pa(p), PUD_SIZE);
 		}
 
-		p = early_alloc(PAGE_SIZE, nid);
+		p = early_alloc(PAGE_SIZE, nid, true);
 		pud_populate(&init_mm, pud, p);
 	}
 
@@ -101,7 +105,7 @@ static void __init kasan_populate_p4d(p4d_t *p4d, unsigned long addr,
 	unsigned long next;
 
 	if (p4d_none(*p4d)) {
-		void *p = early_alloc(PAGE_SIZE, nid);
+		void *p = early_alloc(PAGE_SIZE, nid, true);
 
 		p4d_populate(&init_mm, p4d, p);
 	}
@@ -122,7 +126,7 @@ static void __init kasan_populate_pgd(pgd_t *pgd, unsigned long addr,
 	unsigned long next;
 
 	if (pgd_none(*pgd)) {
-		p = early_alloc(PAGE_SIZE, nid);
+		p = early_alloc(PAGE_SIZE, nid, true);
 		pgd_populate(&init_mm, pgd, p);
 	}
 
diff --git a/include/linux/vermagic.h b/include/linux/vermagic.h
index bae807eb2933..853291714ae0 100644
--- a/include/linux/vermagic.h
+++ b/include/linux/vermagic.h
@@ -31,11 +31,17 @@
 #else
 #define MODULE_RANDSTRUCT_PLUGIN
 #endif
+#ifdef RETPOLINE
+#define MODULE_VERMAGIC_RETPOLINE "retpoline "
+#else
+#define MODULE_VERMAGIC_RETPOLINE ""
+#endif
 
 #define VERMAGIC_STRING 						\
 	UTS_RELEASE " "							\
 	MODULE_VERMAGIC_SMP MODULE_VERMAGIC_PREEMPT 			\
 	MODULE_VERMAGIC_MODULE_UNLOAD MODULE_VERMAGIC_MODVERSIONS	\
 	MODULE_ARCH_VERMAGIC						\
-	MODULE_RANDSTRUCT_PLUGIN
+	MODULE_RANDSTRUCT_PLUGIN					\
+	MODULE_VERMAGIC_RETPOLINE
 
diff --git a/scripts/Makefile.build b/scripts/Makefile.build
index cb8997ed0149..47cddf32aeba 100644
--- a/scripts/Makefile.build
+++ b/scripts/Makefile.build
@@ -265,12 +265,18 @@ else
 objtool_args += $(call cc-ifversion, -lt, 0405, --no-unreachable)
 endif
 
+ifdef CONFIG_MODVERSIONS
+objtool_o = $(@D)/.tmp_$(@F)
+else
+objtool_o = $(@)
+endif
+
 # 'OBJECT_FILES_NON_STANDARD := y': skip objtool checking for a directory
 # 'OBJECT_FILES_NON_STANDARD_foo.o := 'y': skip objtool checking for a file
 # 'OBJECT_FILES_NON_STANDARD_foo.o := 'n': override directory skip for a file
 cmd_objtool = $(if $(patsubst y%,, \
 	$(OBJECT_FILES_NON_STANDARD_$(basetarget).o)$(OBJECT_FILES_NON_STANDARD)n), \
-	$(__objtool_obj) $(objtool_args) "$(@)";)
+	$(__objtool_obj) $(objtool_args) "$(objtool_o)";)
 objtool_obj = $(if $(patsubst y%,, \
 	$(OBJECT_FILES_NON_STANDARD_$(basetarget).o)$(OBJECT_FILES_NON_STANDARD)n), \
 	$(__objtool_obj))
@@ -286,16 +292,16 @@ objtool_dep = $(objtool_obj)					\
 define rule_cc_o_c
 	$(call echo-cmd,checksrc) $(cmd_checksrc)			  \
 	$(call cmd_and_fixdep,cc_o_c)					  \
-	$(cmd_modversions_c)						  \
 	$(cmd_checkdoc)							  \
 	$(call echo-cmd,objtool) $(cmd_objtool)				  \
+	$(cmd_modversions_c)						  \
 	$(call echo-cmd,record_mcount) $(cmd_record_mcount)
 endef
 
 define rule_as_o_S
 	$(call cmd_and_fixdep,as_o_S)					  \
-	$(cmd_modversions_S)						  \
-	$(call echo-cmd,objtool) $(cmd_objtool)
+	$(call echo-cmd,objtool) $(cmd_objtool)				  \
+	$(cmd_modversions_S)
 endef
 
 # List module undefined symbols (or empty line if not enabled)
diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c
index 24460155c82c..c1c338661699 100644
--- a/tools/objtool/elf.c
+++ b/tools/objtool/elf.c
@@ -26,6 +26,7 @@
 #include <stdlib.h>
 #include <string.h>
 #include <unistd.h>
+#include <errno.h>
 
 #include "elf.h"
 #include "warn.h"
@@ -358,7 +359,8 @@ struct elf *elf_open(const char *name, int flags)
 
 	elf->fd = open(name, flags);
 	if (elf->fd == -1) {
-		perror("open");
+		fprintf(stderr, "objtool: Can't open '%s': %s\n",
+			name, strerror(errno));
 		goto err;
 	}