path: root/retpoline.patch

From 61dc0f555b5c761cdafb0ba5bd41ecf22d68a4c4 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Sun, 7 Jan 2018 22:48:01 +0100
Subject: [PATCH] x86/cpu: Implement CPU vulnerabilites sysfs functions

Implement the CPU vulnerabilty show functions for meltdown, spectre_v1 and
spectre_v2.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Linus Torvalds <torvalds@linuxfoundation.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: David Woodhouse <dwmw@amazon.co.uk>
Link: https://lkml.kernel.org/r/20180107214913.177414879@linutronix.de
---
 arch/x86/Kconfig           |  1 +
 arch/x86/kernel/cpu/bugs.c | 29 +++++++++++++++++++++++++++++
 2 files changed, 30 insertions(+)

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index cd5199de231e..e23d21ac745a 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -89,6 +89,7 @@ config X86
 	select GENERIC_CLOCKEVENTS_MIN_ADJUST
 	select GENERIC_CMOS_UPDATE
 	select GENERIC_CPU_AUTOPROBE
+	select GENERIC_CPU_VULNERABILITIES
 	select GENERIC_EARLY_IOREMAP
 	select GENERIC_FIND_FIRST_BIT
 	select GENERIC_IOMAP
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index ba0b2424c9b0..76ad6cb44b40 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -10,6 +10,7 @@
  */
 #include <linux/init.h>
 #include <linux/utsname.h>
+#include <linux/cpu.h>
 #include <asm/bugs.h>
 #include <asm/processor.h>
 #include <asm/processor-flags.h>
@@ -60,3 +61,31 @@ void __init check_bugs(void)
 		set_memory_4k((unsigned long)__va(0), 1);
 #endif
 }
+
+#ifdef CONFIG_SYSFS
+ssize_t cpu_show_meltdown(struct device *dev,
+			  struct device_attribute *attr, char *buf)
+{
+	if (!boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN))
+		return sprintf(buf, "Not affected\n");
+	if (boot_cpu_has(X86_FEATURE_PTI))
+		return sprintf(buf, "Mitigation: PTI\n");
+	return sprintf(buf, "Vulnerable\n");
+}
+
+ssize_t cpu_show_spectre_v1(struct device *dev,
+			    struct device_attribute *attr, char *buf)
+{
+	if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V1))
+		return sprintf(buf, "Not affected\n");
+	return sprintf(buf, "Vulnerable\n");
+}
+
+ssize_t cpu_show_spectre_v2(struct device *dev,
+			    struct device_attribute *attr, char *buf)
+{
+	if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2))
+		return sprintf(buf, "Not affected\n");
+	return sprintf(buf, "Vulnerable\n");
+}
+#endif
-- 
2.14.3

From d46717c610dcfa2cba5c87500c928993371ef1ad Mon Sep 17 00:00:00 2001
From: David Woodhouse <dwmw@amazon.co.uk>
Date: Tue, 9 Jan 2018 14:43:07 +0000
Subject: [PATCH 01/10] x86/retpoline: Add initial retpoline support

Enable the use of -mindirect-branch=thunk-extern in newer GCC, and provide
the corresponding thunks. Provide assembler macros for invoking the thunks
in the same way that GCC does, from native and inline assembler.

This adds X86_FEATURE_RETPOLINE and sets it by default on all CPUs. In
some circumstances, IBRS microcode features may be used instead, and the
retpoline can be disabled.

On AMD CPUs if lfence is serialising, the retpoline can be dramatically
simplified to a simple "lfence; jmp *\reg". A future patch, after it has
been verified that lfence really is serialising in all circumstances, can
enable this by setting the X86_FEATURE_RETPOLINE_AMD feature bit in addition
to X86_FEATURE_RETPOLINE.

Do not align the retpoline in the altinstr section, because there is no
guarantee that it stays aligned when it's copied over the oldinstr during
alternative patching.

[ Andi Kleen: Rename the macros, add CONFIG_RETPOLINE option, export thunks]
[ tglx: Put actual function CALL/JMP in front of the macros, convert to
  	symbolic labels ]

Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Arjan van de Ven <arjan@linux.intel.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
Cc: gnomes@lxorguk.ukuu.org.uk
Cc: Rik van Riel <riel@redhat.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Jiri Kosina <jikos@kernel.org>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Kees Cook <keescook@google.com>
Cc: Tim Chen <tim.c.chen@linux.intel.com>
Cc: Greg Kroah-Hartman <gregkh@linux-foundation.org>
Cc: Paul Turner <pjt@google.com>
Link: https://lkml.kernel.org/r/1515508997-6154-2-git-send-email-dwmw@amazon.co.uk
---
 arch/x86/Kconfig                      |  13 ++++
 arch/x86/Makefile                     |  10 ++++
 arch/x86/include/asm/asm-prototypes.h |  25 ++++++++
 arch/x86/include/asm/cpufeatures.h    |   2 +
 arch/x86/include/asm/nospec-branch.h  | 109 ++++++++++++++++++++++++++++++++++
 arch/x86/kernel/cpu/common.c          |   4 ++
 arch/x86/lib/Makefile                 |   1 +
 arch/x86/lib/retpoline.S              |  48 +++++++++++++++
 8 files changed, 212 insertions(+)
 create mode 100644 arch/x86/include/asm/nospec-branch.h
 create mode 100644 arch/x86/lib/retpoline.S

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index e23d21ac745a..d1819161cc6c 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -429,6 +429,19 @@ config GOLDFISH
        def_bool y
        depends on X86_GOLDFISH

+config RETPOLINE
+	bool "Avoid speculative indirect branches in kernel"
+	default y
+	help
+	  Compile kernel with the retpoline compiler options to guard against
+	  kernel-to-user data leaks by avoiding speculative indirect
+	  branches. Requires a compiler with -mindirect-branch=thunk-extern
+	  support for full protection. The kernel may run slower.
+
+	  Without compiler support, at least indirect branches in assembler
+	  code are eliminated. Since this includes the syscall entry path,
+	  it is not entirely pointless.
+
 config INTEL_RDT
 	bool "Intel Resource Director Technology support"
 	default n
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index a20eacd9c7e9..974c61864978 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -235,6 +235,16 @@ KBUILD_CFLAGS += -Wno-sign-compare
 #
 KBUILD_CFLAGS += -fno-asynchronous-unwind-tables

+# Avoid indirect branches in kernel to deal with Spectre
+ifdef CONFIG_RETPOLINE
+    RETPOLINE_CFLAGS += $(call cc-option,-mindirect-branch=thunk-extern -mindirect-branch-register)
+    ifneq ($(RETPOLINE_CFLAGS),)
+        KBUILD_CFLAGS += $(RETPOLINE_CFLAGS) -DRETPOLINE
+    else
+        $(warning CONFIG_RETPOLINE=y, but not supported by the compiler. Toolchain update recommended.)
+    endif
+endif
+
 archscripts: scripts_basic
 	$(Q)$(MAKE) $(build)=arch/x86/tools relocs

diff --git a/arch/x86/include/asm/asm-prototypes.h b/arch/x86/include/asm/asm-prototypes.h
index ff700d81e91e..0927cdc4f946 100644
--- a/arch/x86/include/asm/asm-prototypes.h
+++ b/arch/x86/include/asm/asm-prototypes.h
@@ -11,7 +11,32 @@
 #include <asm/pgtable.h>
 #include <asm/special_insns.h>
 #include <asm/preempt.h>
+#include <asm/asm.h>

 #ifndef CONFIG_X86_CMPXCHG64
 extern void cmpxchg8b_emu(void);
 #endif
+
+#ifdef CONFIG_RETPOLINE
+#ifdef CONFIG_X86_32
+#define INDIRECT_THUNK(reg) extern asmlinkage void __x86_indirect_thunk_e ## reg(void);
+#else
+#define INDIRECT_THUNK(reg) extern asmlinkage void __x86_indirect_thunk_r ## reg(void);
+INDIRECT_THUNK(8)
+INDIRECT_THUNK(9)
+INDIRECT_THUNK(10)
+INDIRECT_THUNK(11)
+INDIRECT_THUNK(12)
+INDIRECT_THUNK(13)
+INDIRECT_THUNK(14)
+INDIRECT_THUNK(15)
+#endif
+INDIRECT_THUNK(ax)
+INDIRECT_THUNK(bx)
+INDIRECT_THUNK(cx)
+INDIRECT_THUNK(dx)
+INDIRECT_THUNK(si)
+INDIRECT_THUNK(di)
+INDIRECT_THUNK(bp)
+INDIRECT_THUNK(sp)
+#endif /* CONFIG_RETPOLINE */
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 1641c2f96363..f275447862f4 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -203,6 +203,8 @@
 #define X86_FEATURE_PROC_FEEDBACK	( 7*32+ 9) /* AMD ProcFeedbackInterface */
 #define X86_FEATURE_SME			( 7*32+10) /* AMD Secure Memory Encryption */
 #define X86_FEATURE_PTI			( 7*32+11) /* Kernel Page Table Isolation enabled */
+#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 */
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
new file mode 100644
index 000000000000..7f58713b27c4
--- /dev/null
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -0,0 +1,109 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __NOSPEC_BRANCH_H__
+#define __NOSPEC_BRANCH_H__
+
+#include <asm/alternative.h>
+#include <asm/alternative-asm.h>
+#include <asm/cpufeatures.h>
+
+#ifdef __ASSEMBLY__
+
+/*
+ * These are the bare retpoline primitives for indirect jmp and call.
+ * Do not use these directly; they only exist to make the ALTERNATIVE
+ * invocation below less ugly.
+ */
+.macro RETPOLINE_JMP reg:req
+	call	.Ldo_rop_\@
+.Lspec_trap_\@:
+	pause
+	jmp	.Lspec_trap_\@
+.Ldo_rop_\@:
+	mov	\reg, (%_ASM_SP)
+	ret
+.endm
+
+/*
+ * This is a wrapper around RETPOLINE_JMP so the called function in reg
+ * returns to the instruction after the macro.
+ */
+.macro RETPOLINE_CALL reg:req
+	jmp	.Ldo_call_\@
+.Ldo_retpoline_jmp_\@:
+	RETPOLINE_JMP \reg
+.Ldo_call_\@:
+	call	.Ldo_retpoline_jmp_\@
+.endm
+
+/*
+ * JMP_NOSPEC and CALL_NOSPEC macros can be used instead of a simple
+ * indirect jmp/call which may be susceptible to the Spectre variant 2
+ * attack.
+ */
+.macro JMP_NOSPEC reg:req
+#ifdef CONFIG_RETPOLINE
+	ALTERNATIVE_2 __stringify(jmp *\reg),				\
+		__stringify(RETPOLINE_JMP \reg), X86_FEATURE_RETPOLINE,	\
+		__stringify(lfence; jmp *\reg), X86_FEATURE_RETPOLINE_AMD
+#else
+	jmp	*\reg
+#endif
+.endm
+
+.macro CALL_NOSPEC reg:req
+#ifdef CONFIG_RETPOLINE
+	ALTERNATIVE_2 __stringify(call *\reg),				\
+		__stringify(RETPOLINE_CALL \reg), X86_FEATURE_RETPOLINE,\
+		__stringify(lfence; call *\reg), X86_FEATURE_RETPOLINE_AMD
+#else
+	call	*\reg
+#endif
+.endm
+
+#else /* __ASSEMBLY__ */
+
+#if defined(CONFIG_X86_64) && defined(RETPOLINE)
+/*
+ * Since the inline asm uses the %V modifier which is only in newer GCC,
+ * the 64-bit one is dependent on RETPOLINE not CONFIG_RETPOLINE.
+ */
+# define CALL_NOSPEC ALTERNATIVE(				\
+	"call *%[thunk_target]\n",				\
+	"call __x86_indirect_thunk_%V[thunk_target]\n",		\
+	X86_FEATURE_RETPOLINE)
+# define THUNK_TARGET(addr) [thunk_target] "r" (addr)
+#elif defined(CONFIG_X86_32) && defined(CONFIG_RETPOLINE)
+/*
+ * For i386 we use the original ret-equivalent retpoline, because
+ * otherwise we'll run out of registers. We don't care about CET
+ * here, anyway.
+ */
+# define CALL_NOSPEC ALTERNATIVE(				\
+	"call	*%[thunk_target]\n",				\
+	""							\
+	"       jmp    do_call%=;\n"				\
+	"       .align 16\n"					\
+	"do_retpoline%=:\n"					\
+	"	call   do_rop%=;\n"				\
+	"spec_trap%=:\n"					\
+	"	pause;\n"					\
+	"       jmp    spec_trap%=;\n"				\
+	"       .align 16\n"					\
+	"do_rop%=:\n"						\
+	"	addl   $4, %%esp;\n"				\
+	"       pushl  %[thunk_target];\n"			\
+	"       ret;\n"						\
+	"       .align 16\n"					\
+	"do_call%=:\n"						\
+	"	call   do_retpoline%=;\n",			\
+	X86_FEATURE_RETPOLINE)
+
+# define THUNK_TARGET(addr) [thunk_target] "rm" (addr)
+#else /* No retpoline */
+# define CALL_NOSPEC "call *%[thunk_target]\n"
+# define THUNK_TARGET(addr) [thunk_target] "rm" (addr)
+#endif
+
+#endif /* __ASSEMBLY__ */
+#endif /* __NOSPEC_BRANCH_H__ */
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 372ba3fb400f..7a671d1ae3cb 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -905,6 +905,10 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
 	setup_force_cpu_bug(X86_BUG_SPECTRE_V1);
 	setup_force_cpu_bug(X86_BUG_SPECTRE_V2);

+#ifdef CONFIG_RETPOLINE
+	setup_force_cpu_cap(X86_FEATURE_RETPOLINE);
+#endif
+
 	fpu__init_system(c);

 #ifdef CONFIG_X86_32
diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile
index 457f681ef379..d435c89875c1 100644
--- a/arch/x86/lib/Makefile
+++ b/arch/x86/lib/Makefile
@@ -26,6 +26,7 @@ lib-y += memcpy_$(BITS).o
 lib-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem.o
 lib-$(CONFIG_INSTRUCTION_DECODER) += insn.o inat.o insn-eval.o
 lib-$(CONFIG_RANDOMIZE_BASE) += kaslr.o
+lib-$(CONFIG_RETPOLINE) += retpoline.o

 obj-y += msr.o msr-reg.o msr-reg-export.o hweight.o

diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S
new file mode 100644
index 000000000000..cb45c6cb465f
--- /dev/null
+++ b/arch/x86/lib/retpoline.S
@@ -0,0 +1,48 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#include <linux/stringify.h>
+#include <linux/linkage.h>
+#include <asm/dwarf2.h>
+#include <asm/cpufeatures.h>
+#include <asm/alternative-asm.h>
+#include <asm/export.h>
+#include <asm/nospec-branch.h>
+
+.macro THUNK reg
+	.section .text.__x86.indirect_thunk.\reg
+
+ENTRY(__x86_indirect_thunk_\reg)
+	CFI_STARTPROC
+	JMP_NOSPEC %\reg
+	CFI_ENDPROC
+ENDPROC(__x86_indirect_thunk_\reg)
+.endm
+
+/*
+ * Despite being an assembler file we can't just use .irp here
+ * because __KSYM_DEPS__ only uses the C preprocessor and would
+ * only see one instance of "__x86_indirect_thunk_\reg" rather
+ * than one per register with the correct names. So we do it
+ * the simple and nasty way...
+ */
+#define EXPORT_THUNK(reg) EXPORT_SYMBOL(__x86_indirect_thunk_ ## reg)
+#define GENERATE_THUNK(reg) THUNK reg ; EXPORT_THUNK(reg)
+
+GENERATE_THUNK(_ASM_AX)
+GENERATE_THUNK(_ASM_BX)
+GENERATE_THUNK(_ASM_CX)
+GENERATE_THUNK(_ASM_DX)
+GENERATE_THUNK(_ASM_SI)
+GENERATE_THUNK(_ASM_DI)
+GENERATE_THUNK(_ASM_BP)
+GENERATE_THUNK(_ASM_SP)
+#ifdef CONFIG_64BIT
+GENERATE_THUNK(r8)
+GENERATE_THUNK(r9)
+GENERATE_THUNK(r10)
+GENERATE_THUNK(r11)
+GENERATE_THUNK(r12)
+GENERATE_THUNK(r13)
+GENERATE_THUNK(r14)
+GENERATE_THUNK(r15)
+#endif
-- 
2.14.3

From 59b6e22f92f9a86dbd0798db72adc97bdb831f86 Mon Sep 17 00:00:00 2001
From: Andi Kleen <ak@linux.intel.com>
Date: Tue, 9 Jan 2018 14:43:08 +0000
Subject: [PATCH 02/10] x86/retpoline: Temporarily disable objtool when
 CONFIG_RETPOLINE=y

objtool's assembler currently cannot deal with the code generated by the
retpoline compiler and throws hundreds of warnings, mostly because it sees
calls that don't have a symbolic target.

Exclude all the options that rely on objtool when RETPOLINE is active.

This mainly means that the kernel has to fallback to use the frame pointer
unwinder and livepatch is not supported.

Josh is looking into resolving the issue.

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Arjan van de Ven <arjan@linux.intel.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
Cc: gnomes@lxorguk.ukuu.org.uk
Cc: Rik van Riel <riel@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Jiri Kosina <jikos@kernel.org>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Kees Cook <keescook@google.com>
Cc: Tim Chen <tim.c.chen@linux.intel.com>
Cc: Greg Kroah-Hartman <gregkh@linux-foundation.org>
Cc: Paul Turner <pjt@google.com>
Link: https://lkml.kernel.org/r/1515508997-6154-3-git-send-email-dwmw@amazon.co.uk
---
 arch/x86/Kconfig       | 4 ++--
 arch/x86/Kconfig.debug | 6 +++---
 2 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index d1819161cc6c..abeac4b80b74 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -172,8 +172,8 @@ config X86
 	select HAVE_PERF_USER_STACK_DUMP
 	select HAVE_RCU_TABLE_FREE
 	select HAVE_REGS_AND_STACK_ACCESS_API
-	select HAVE_RELIABLE_STACKTRACE		if X86_64 && UNWINDER_FRAME_POINTER && STACK_VALIDATION
-	select HAVE_STACK_VALIDATION		if X86_64
+	select HAVE_RELIABLE_STACKTRACE		if X86_64 && UNWINDER_FRAME_POINTER && STACK_VALIDATION && !RETPOLINE
+	select HAVE_STACK_VALIDATION		if X86_64 && !RETPOLINE
 	select HAVE_SYSCALL_TRACEPOINTS
 	select HAVE_UNSTABLE_SCHED_CLOCK
 	select HAVE_USER_RETURN_NOTIFIER
diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug
index 6293a8768a91..9f3928d744bc 100644
--- a/arch/x86/Kconfig.debug
+++ b/arch/x86/Kconfig.debug
@@ -359,8 +359,8 @@ config PUNIT_ATOM_DEBUG

 choice
 	prompt "Choose kernel unwinder"
-	default UNWINDER_ORC if X86_64
-	default UNWINDER_FRAME_POINTER if X86_32
+	default UNWINDER_ORC if X86_64 && !RETPOLINE
+	default UNWINDER_FRAME_POINTER if X86_32 || RETPOLINE
 	---help---
 	  This determines which method will be used for unwinding kernel stack
 	  traces for panics, oopses, bugs, warnings, perf, /proc/<pid>/stack,
@@ -368,7 +368,7 @@ choice

 config UNWINDER_ORC
 	bool "ORC unwinder"
-	depends on X86_64
+	depends on X86_64 && !RETPOLINE
 	select STACK_VALIDATION
 	---help---
 	  This option enables the ORC (Oops Rewind Capability) unwinder for
-- 
2.14.3

From 86d057614112971f7d5bbac45f67869adca79852 Mon Sep 17 00:00:00 2001
From: David Woodhouse <dwmw@amazon.co.uk>
Date: Tue, 9 Jan 2018 14:43:09 +0000
Subject: [PATCH 03/10] x86/spectre: Add boot time option to select Spectre v2
 mitigation

Add a spectre_v2= option to select the mitigation used for the indirect
branch speculation vulnerability.

Currently, the only option available is retpoline, in its various forms.
This will be expanded to cover the new IBRS/IBPB microcode features.

The RETPOLINE_AMD feature relies on a serializing LFENCE for speculation
control. For AMD hardware, only set RETPOLINE_AMD if LFENCE is a
serializing instruction, which is indicated by the LFENCE_RDTSC feature.

[ tglx: Folded back the LFENCE/AMD fixes and reworked it so IBRS
  	integration becomes simple ]

Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: gnomes@lxorguk.ukuu.org.uk
Cc: Rik van Riel <riel@redhat.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Jiri Kosina <jikos@kernel.org>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Kees Cook <keescook@google.com>
Cc: Tim Chen <tim.c.chen@linux.intel.com>
Cc: Greg Kroah-Hartman <gregkh@linux-foundation.org>
Cc: Paul Turner <pjt@google.com>
Cc: Tom Lendacky <thomas.lendacky@amd.com>
Link: https://lkml.kernel.org/r/1515508997-6154-4-git-send-email-dwmw@amazon.co.uk
---
 Documentation/admin-guide/kernel-parameters.txt |  28 +++++
 arch/x86/include/asm/nospec-branch.h            |  10 ++
 arch/x86/kernel/cpu/bugs.c                      | 158 +++++++++++++++++++++++-
 arch/x86/kernel/cpu/common.c                    |   4 -
 4 files changed, 195 insertions(+), 5 deletions(-)

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 905991745d26..8122b5f98ea1 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -2599,6 +2599,11 @@
 	nosmt		[KNL,S390] Disable symmetric multithreading (SMT).
 			Equivalent to smt=1.

+	nospectre_v2	[X86] Disable all mitigations for the Spectre variant 2
+			(indirect branch prediction) vulnerability. System may
+			allow data leaks with this option, which is equivalent
+			to spectre_v2=off.
+
 	noxsave		[BUGS=X86] Disables x86 extended register state save
 			and restore using xsave. The kernel will fallback to
 			enabling legacy floating-point and sse state.
@@ -3908,6 +3913,29 @@
 	sonypi.*=	[HW] Sony Programmable I/O Control Device driver
 			See Documentation/laptops/sonypi.txt

+	spectre_v2=	[X86] Control mitigation of Spectre variant 2
+			(indirect branch speculation) vulnerability.
+
+			on   - unconditionally enable
+			off  - unconditionally disable
+			auto - kernel detects whether your CPU model is
+			       vulnerable
+
+			Selecting 'on' will, and 'auto' may, choose a
+			mitigation method at run time according to the
+			CPU, the available microcode, the setting of the
+			CONFIG_RETPOLINE configuration option, and the
+			compiler with which the kernel was built.
+
+			Specific mitigations can also be selected manually:
+
+			retpoline	  - replace indirect branches
+			retpoline,generic - google's original retpoline
+			retpoline,amd     - AMD-specific minimal thunk
+
+			Not specifying this option is equivalent to
+			spectre_v2=auto.
+
 	spia_io_base=	[HW,MTD]
 	spia_fio_base=
 	spia_pedr=
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index 7f58713b27c4..7d70ea977fbe 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -105,5 +105,15 @@
 # define THUNK_TARGET(addr) [thunk_target] "rm" (addr)
 #endif

+/* The Spectre V2 mitigation variants */
+enum spectre_v2_mitigation {
+	SPECTRE_V2_NONE,
+	SPECTRE_V2_RETPOLINE_MINIMAL,
+	SPECTRE_V2_RETPOLINE_MINIMAL_AMD,
+	SPECTRE_V2_RETPOLINE_GENERIC,
+	SPECTRE_V2_RETPOLINE_AMD,
+	SPECTRE_V2_IBRS,
+};
+
 #endif /* __ASSEMBLY__ */
 #endif /* __NOSPEC_BRANCH_H__ */
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 76ad6cb44b40..e4dc26185aa7 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -11,6 +11,9 @@
 #include <linux/init.h>
 #include <linux/utsname.h>
 #include <linux/cpu.h>
+
+#include <asm/nospec-branch.h>
+#include <asm/cmdline.h>
 #include <asm/bugs.h>
 #include <asm/processor.h>
 #include <asm/processor-flags.h>
@@ -21,6 +24,8 @@
 #include <asm/pgtable.h>
 #include <asm/set_memory.h>

+static void __init spectre_v2_select_mitigation(void);
+
 void __init check_bugs(void)
 {
 	identify_boot_cpu();
@@ -30,6 +35,9 @@ void __init check_bugs(void)
 		print_cpu_info(&boot_cpu_data);
 	}

+	/* Select the proper spectre mitigation before patching alternatives */
+	spectre_v2_select_mitigation();
+
 #ifdef CONFIG_X86_32
 	/*
 	 * Check whether we are able to run this kernel safely on SMP.
@@ -62,6 +70,153 @@ void __init check_bugs(void)
 #endif
 }

+/* The kernel command line selection */
+enum spectre_v2_mitigation_cmd {
+	SPECTRE_V2_CMD_NONE,
+	SPECTRE_V2_CMD_AUTO,
+	SPECTRE_V2_CMD_FORCE,
+	SPECTRE_V2_CMD_RETPOLINE,
+	SPECTRE_V2_CMD_RETPOLINE_GENERIC,
+	SPECTRE_V2_CMD_RETPOLINE_AMD,
+};
+
+static const char *spectre_v2_strings[] = {
+	[SPECTRE_V2_NONE]			= "Vulnerable",
+	[SPECTRE_V2_RETPOLINE_MINIMAL]		= "Vulnerable: Minimal generic ASM retpoline",
+	[SPECTRE_V2_RETPOLINE_MINIMAL_AMD]	= "Vulnerable: Minimal AMD ASM retpoline",
+	[SPECTRE_V2_RETPOLINE_GENERIC]		= "Mitigation: Full generic retpoline",
+	[SPECTRE_V2_RETPOLINE_AMD]		= "Mitigation: Full AMD retpoline",
+};
+
+#undef pr_fmt
+#define pr_fmt(fmt)     "Spectre V2 mitigation: " fmt
+
+static enum spectre_v2_mitigation spectre_v2_enabled = SPECTRE_V2_NONE;
+
+static void __init spec2_print_if_insecure(const char *reason)
+{
+	if (boot_cpu_has_bug(X86_BUG_SPECTRE_V2))
+		pr_info("%s\n", reason);
+}
+
+static void __init spec2_print_if_secure(const char *reason)
+{
+	if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2))
+		pr_info("%s\n", reason);
+}
+
+static inline bool retp_compiler(void)
+{
+	return __is_defined(RETPOLINE);
+}
+
+static inline bool match_option(const char *arg, int arglen, const char *opt)
+{
+	int len = strlen(opt);
+
+	return len == arglen && !strncmp(arg, opt, len);
+}
+
+static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void)
+{
+	char arg[20];
+	int ret;
+
+	ret = cmdline_find_option(boot_command_line, "spectre_v2", arg,
+				  sizeof(arg));
+	if (ret > 0)  {
+		if (match_option(arg, ret, "off")) {
+			goto disable;
+		} else if (match_option(arg, ret, "on")) {
+			spec2_print_if_secure("force enabled on command line.");
+			return SPECTRE_V2_CMD_FORCE;
+		} else if (match_option(arg, ret, "retpoline")) {
+			spec2_print_if_insecure("retpoline selected on command line.");
+			return SPECTRE_V2_CMD_RETPOLINE;
+		} else if (match_option(arg, ret, "retpoline,amd")) {
+			if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD) {
+				pr_err("retpoline,amd selected but CPU is not AMD. Switching to AUTO select\n");
+				return SPECTRE_V2_CMD_AUTO;
+			}
+			spec2_print_if_insecure("AMD retpoline selected on command line.");
+			return SPECTRE_V2_CMD_RETPOLINE_AMD;
+		} else if (match_option(arg, ret, "retpoline,generic")) {
+			spec2_print_if_insecure("generic retpoline selected on command line.");
+			return SPECTRE_V2_CMD_RETPOLINE_GENERIC;
+		} else if (match_option(arg, ret, "auto")) {
+			return SPECTRE_V2_CMD_AUTO;
+		}
+	}
+
+	if (!cmdline_find_option_bool(boot_command_line, "nospectre_v2"))
+		return SPECTRE_V2_CMD_AUTO;
+disable:
+	spec2_print_if_insecure("disabled on command line.");
+	return SPECTRE_V2_CMD_NONE;
+}
+
+static void __init spectre_v2_select_mitigation(void)
+{
+	enum spectre_v2_mitigation_cmd cmd = spectre_v2_parse_cmdline();
+	enum spectre_v2_mitigation mode = SPECTRE_V2_NONE;
+
+	/*
+	 * If the CPU is not affected and the command line mode is NONE or AUTO
+	 * then nothing to do.
+	 */
+	if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2) &&
+	    (cmd == SPECTRE_V2_CMD_NONE || cmd == SPECTRE_V2_CMD_AUTO))
+		return;
+
+	switch (cmd) {
+	case SPECTRE_V2_CMD_NONE:
+		return;
+
+	case SPECTRE_V2_CMD_FORCE:
+		/* FALLTRHU */
+	case SPECTRE_V2_CMD_AUTO:
+		goto retpoline_auto;
+
+	case SPECTRE_V2_CMD_RETPOLINE_AMD:
+		if (IS_ENABLED(CONFIG_RETPOLINE))
+			goto retpoline_amd;
+		break;
+	case SPECTRE_V2_CMD_RETPOLINE_GENERIC:
+		if (IS_ENABLED(CONFIG_RETPOLINE))
+			goto retpoline_generic;
+		break;
+	case SPECTRE_V2_CMD_RETPOLINE:
+		if (IS_ENABLED(CONFIG_RETPOLINE))
+			goto retpoline_auto;
+		break;
+	}
+	pr_err("kernel not compiled with retpoline; no mitigation available!");
+	return;
+
+retpoline_auto:
+	if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) {
+	retpoline_amd:
+		if (!boot_cpu_has(X86_FEATURE_LFENCE_RDTSC)) {
+			pr_err("LFENCE not serializing. Switching to generic retpoline\n");
+			goto retpoline_generic;
+		}
+		mode = retp_compiler() ? SPECTRE_V2_RETPOLINE_AMD :
+					 SPECTRE_V2_RETPOLINE_MINIMAL_AMD;
+		setup_force_cpu_cap(X86_FEATURE_RETPOLINE_AMD);
+		setup_force_cpu_cap(X86_FEATURE_RETPOLINE);
+	} else {
+	retpoline_generic:
+		mode = retp_compiler() ? SPECTRE_V2_RETPOLINE_GENERIC :
+					 SPECTRE_V2_RETPOLINE_MINIMAL;
+		setup_force_cpu_cap(X86_FEATURE_RETPOLINE);
+	}
+
+	spectre_v2_enabled = mode;
+	pr_info("%s\n", spectre_v2_strings[mode]);
+}
+
+#undef pr_fmt
+
 #ifdef CONFIG_SYSFS
 ssize_t cpu_show_meltdown(struct device *dev,
 			  struct device_attribute *attr, char *buf)
@@ -86,6 +241,7 @@ ssize_t cpu_show_spectre_v2(struct device *dev,
 {
 	if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2))
 		return sprintf(buf, "Not affected\n");
-	return sprintf(buf, "Vulnerable\n");
+
+	return sprintf(buf, "%s\n", spectre_v2_strings[spectre_v2_enabled]);
 }
 #endif
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 7a671d1ae3cb..372ba3fb400f 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -905,10 +905,6 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
 	setup_force_cpu_bug(X86_BUG_SPECTRE_V1);
 	setup_force_cpu_bug(X86_BUG_SPECTRE_V2);

-#ifdef CONFIG_RETPOLINE
-	setup_force_cpu_cap(X86_FEATURE_RETPOLINE);
-#endif
-
 	fpu__init_system(c);

 #ifdef CONFIG_X86_32
-- 
2.14.3

From b3a96862283e68914d1f74f160ab980dacf811ee Mon Sep 17 00:00:00 2001
From: David Woodhouse <dwmw@amazon.co.uk>
Date: Tue, 9 Jan 2018 14:43:10 +0000
Subject: [PATCH 04/10] x86/retpoline/crypto: Convert crypto assembler indirect
 jumps

Convert all indirect jumps in crypto assembler code to use non-speculative
sequences when CONFIG_RETPOLINE is enabled.

Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Arjan van de Ven <arjan@linux.intel.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
Cc: gnomes@lxorguk.ukuu.org.uk
Cc: Rik van Riel <riel@redhat.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Jiri Kosina <jikos@kernel.org>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Kees Cook <keescook@google.com>
Cc: Tim Chen <tim.c.chen@linux.intel.com>
Cc: Greg Kroah-Hartman <gregkh@linux-foundation.org>
Cc: Paul Turner <pjt@google.com>
Link: https://lkml.kernel.org/r/1515508997-6154-5-git-send-email-dwmw@amazon.co.uk
---
 arch/x86/crypto/aesni-intel_asm.S            | 5 +++--
 arch/x86/crypto/camellia-aesni-avx-asm_64.S  | 3 ++-
 arch/x86/crypto/camellia-aesni-avx2-asm_64.S | 3 ++-
 arch/x86/crypto/crc32c-pcl-intel-asm_64.S    | 3 ++-
 4 files changed, 9 insertions(+), 5 deletions(-)

diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S
index 16627fec80b2..3d09e3aca18d 100644
--- a/arch/x86/crypto/aesni-intel_asm.S
+++ b/arch/x86/crypto/aesni-intel_asm.S
@@ -32,6 +32,7 @@
 #include <linux/linkage.h>
 #include <asm/inst.h>
 #include <asm/frame.h>
+#include <asm/nospec-branch.h>

 /*
  * The following macros are used to move an (un)aligned 16 byte value to/from
@@ -2884,7 +2885,7 @@ ENTRY(aesni_xts_crypt8)
 	pxor INC, STATE4
 	movdqu IV, 0x30(OUTP)

-	call *%r11
+	CALL_NOSPEC %r11

 	movdqu 0x00(OUTP), INC
 	pxor INC, STATE1
@@ -2929,7 +2930,7 @@ ENTRY(aesni_xts_crypt8)
 	_aesni_gf128mul_x_ble()
 	movups IV, (IVP)

-	call *%r11
+	CALL_NOSPEC %r11

 	movdqu 0x40(OUTP), INC
 	pxor INC, STATE1
diff --git a/arch/x86/crypto/camellia-aesni-avx-asm_64.S b/arch/x86/crypto/camellia-aesni-avx-asm_64.S
index f7c495e2863c..a14af6eb09cb 100644
--- a/arch/x86/crypto/camellia-aesni-avx-asm_64.S
+++ b/arch/x86/crypto/camellia-aesni-avx-asm_64.S
@@ -17,6 +17,7 @@

 #include <linux/linkage.h>
 #include <asm/frame.h>
+#include <asm/nospec-branch.h>

 #define CAMELLIA_TABLE_BYTE_LEN 272

@@ -1227,7 +1228,7 @@ camellia_xts_crypt_16way:
 	vpxor 14 * 16(%rax), %xmm15, %xmm14;
 	vpxor 15 * 16(%rax), %xmm15, %xmm15;

-	call *%r9;
+	CALL_NOSPEC %r9;

 	addq $(16 * 16), %rsp;

diff --git a/arch/x86/crypto/camellia-aesni-avx2-asm_64.S b/arch/x86/crypto/camellia-aesni-avx2-asm_64.S
index eee5b3982cfd..b66bbfa62f50 100644
--- a/arch/x86/crypto/camellia-aesni-avx2-asm_64.S
+++ b/arch/x86/crypto/camellia-aesni-avx2-asm_64.S
@@ -12,6 +12,7 @@

 #include <linux/linkage.h>
 #include <asm/frame.h>
+#include <asm/nospec-branch.h>

 #define CAMELLIA_TABLE_BYTE_LEN 272

@@ -1343,7 +1344,7 @@ camellia_xts_crypt_32way:
 	vpxor 14 * 32(%rax), %ymm15, %ymm14;
 	vpxor 15 * 32(%rax), %ymm15, %ymm15;

-	call *%r9;
+	CALL_NOSPEC %r9;

 	addq $(16 * 32), %rsp;

diff --git a/arch/x86/crypto/crc32c-pcl-intel-asm_64.S b/arch/x86/crypto/crc32c-pcl-intel-asm_64.S
index 7a7de27c6f41..d9b734d0c8cc 100644
--- a/arch/x86/crypto/crc32c-pcl-intel-asm_64.S
+++ b/arch/x86/crypto/crc32c-pcl-intel-asm_64.S
@@ -45,6 +45,7 @@

 #include <asm/inst.h>
 #include <linux/linkage.h>
+#include <asm/nospec-branch.h>

 ## ISCSI CRC 32 Implementation with crc32 and pclmulqdq Instruction

@@ -172,7 +173,7 @@ continue_block:
 	movzxw  (bufp, %rax, 2), len
 	lea	crc_array(%rip), bufp
 	lea     (bufp, len, 1), bufp
-	jmp     *bufp
+	JMP_NOSPEC bufp

 	################################################################
 	## 2a) PROCESS FULL BLOCKS:
-- 
2.14.3

From 2558106c7a47e16968a10fa66eea78a096fabfe6 Mon Sep 17 00:00:00 2001
From: David Woodhouse <dwmw@amazon.co.uk>
Date: Tue, 9 Jan 2018 14:43:11 +0000
Subject: [PATCH 05/10] x86/retpoline/entry: Convert entry assembler indirect
 jumps

Convert indirect jumps in core 32/64bit entry assembler code to use
non-speculative sequences when CONFIG_RETPOLINE is enabled.

Don't use CALL_NOSPEC in entry_SYSCALL_64_fastpath because the return
address after the 'call' instruction must be *precisely* at the
.Lentry_SYSCALL_64_after_fastpath label for stub_ptregs_64 to work,
and the use of alternatives will mess that up unless we play horrid
games to prepend with NOPs and make the variants the same length. It's
not worth it; in the case where we ALTERNATIVE out the retpoline, the
first instruction at __x86.indirect_thunk.rax is going to be a bare
jmp *%rax anyway.

Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Arjan van de Ven <arjan@linux.intel.com>
Cc: gnomes@lxorguk.ukuu.org.uk
Cc: Rik van Riel <riel@redhat.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Jiri Kosina <jikos@kernel.org>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Kees Cook <keescook@google.com>
Cc: Tim Chen <tim.c.chen@linux.intel.com>
Cc: Greg Kroah-Hartman <gregkh@linux-foundation.org>
Cc: Paul Turner <pjt@google.com>
Link: https://lkml.kernel.org/r/1515508997-6154-6-git-send-email-dwmw@amazon.co.uk
---
 arch/x86/entry/entry_32.S |  5 +++--
 arch/x86/entry/entry_64.S | 12 +++++++++---
 2 files changed, 12 insertions(+), 5 deletions(-)

diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index ace8f321a5a1..a1f28a54f23a 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -44,6 +44,7 @@
 #include <asm/asm.h>
 #include <asm/smap.h>
 #include <asm/frame.h>
+#include <asm/nospec-branch.h>

 	.section .entry.text, "ax"

@@ -290,7 +291,7 @@ ENTRY(ret_from_fork)

 	/* kernel thread */
 1:	movl	%edi, %eax
-	call	*%ebx
+	CALL_NOSPEC %ebx
 	/*
 	 * A kernel thread is allowed to return here after successfully
 	 * calling do_execve().  Exit to userspace to complete the execve()
@@ -919,7 +920,7 @@ common_exception:
 	movl	%ecx, %es
 	TRACE_IRQS_OFF
 	movl	%esp, %eax			# pt_regs pointer
-	call	*%edi
+	CALL_NOSPEC %edi
 	jmp	ret_from_exception
 END(common_exception)

diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index ed31d00dc5ee..59874bc1aed2 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -37,6 +37,7 @@
 #include <asm/pgtable_types.h>
 #include <asm/export.h>
 #include <asm/frame.h>
+#include <asm/nospec-branch.h>
 #include <linux/err.h>

 #include "calling.h"
@@ -187,7 +188,7 @@ ENTRY(entry_SYSCALL_64_trampoline)
 	 */
 	pushq	%rdi
 	movq	$entry_SYSCALL_64_stage2, %rdi
-	jmp	*%rdi
+	JMP_NOSPEC %rdi
 END(entry_SYSCALL_64_trampoline)

 	.popsection
@@ -266,7 +267,12 @@ entry_SYSCALL_64_fastpath:
 	 * It might end up jumping to the slow path.  If it jumps, RAX
 	 * and all argument registers are clobbered.
 	 */
+#ifdef CONFIG_RETPOLINE
+	movq	sys_call_table(, %rax, 8), %rax
+	call	__x86_indirect_thunk_rax
+#else
 	call	*sys_call_table(, %rax, 8)
+#endif
 .Lentry_SYSCALL_64_after_fastpath_call:

 	movq	%rax, RAX(%rsp)
@@ -438,7 +444,7 @@ ENTRY(stub_ptregs_64)
 	jmp	entry_SYSCALL64_slow_path

 1:
-	jmp	*%rax				/* Called from C */
+	JMP_NOSPEC %rax				/* Called from C */
 END(stub_ptregs_64)

 .macro ptregs_stub func
@@ -517,7 +523,7 @@ ENTRY(ret_from_fork)
 1:
 	/* kernel thread */
 	movq	%r12, %rdi
-	call	*%rbx
+	CALL_NOSPEC %rbx
 	/*
 	 * A kernel thread is allowed to return here after successfully
 	 * calling do_execve().  Exit to userspace to complete the execve()
-- 
2.14.3

From 42f7c812022441ffba2d5ccca3acf6380201f19e Mon Sep 17 00:00:00 2001
From: David Woodhouse <dwmw@amazon.co.uk>
Date: Tue, 9 Jan 2018 14:43:12 +0000
Subject: [PATCH 06/10] x86/retpoline/ftrace: Convert ftrace assembler indirect
 jumps

Convert all indirect jumps in ftrace assembler code to use non-speculative
sequences when CONFIG_RETPOLINE is enabled.

Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Arjan van de Ven <arjan@linux.intel.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
Cc: gnomes@lxorguk.ukuu.org.uk
Cc: Rik van Riel <riel@redhat.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Jiri Kosina <jikos@kernel.org>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Kees Cook <keescook@google.com>
Cc: Tim Chen <tim.c.chen@linux.intel.com>
Cc: Greg Kroah-Hartman <gregkh@linux-foundation.org>
Cc: Paul Turner <pjt@google.com>
Link: https://lkml.kernel.org/r/1515508997-6154-7-git-send-email-dwmw@amazon.co.uk
---
 arch/x86/kernel/ftrace_32.S | 6 ++++--
 arch/x86/kernel/ftrace_64.S | 8 ++++----
 2 files changed, 8 insertions(+), 6 deletions(-)

diff --git a/arch/x86/kernel/ftrace_32.S b/arch/x86/kernel/ftrace_32.S
index b6c6468e10bc..4c8440de3355 100644
--- a/arch/x86/kernel/ftrace_32.S
+++ b/arch/x86/kernel/ftrace_32.S
@@ -8,6 +8,7 @@
 #include <asm/segment.h>
 #include <asm/export.h>
 #include <asm/ftrace.h>
+#include <asm/nospec-branch.h>

 #ifdef CC_USING_FENTRY
 # define function_hook	__fentry__
@@ -197,7 +198,8 @@ ftrace_stub:
 	movl	0x4(%ebp), %edx
 	subl	$MCOUNT_INSN_SIZE, %eax

-	call	*ftrace_trace_function
+	movl	ftrace_trace_function, %ecx
+	CALL_NOSPEC %ecx

 	popl	%edx
 	popl	%ecx
@@ -241,5 +243,5 @@ return_to_handler:
 	movl	%eax, %ecx
 	popl	%edx
 	popl	%eax
-	jmp	*%ecx
+	JMP_NOSPEC %ecx
 #endif
diff --git a/arch/x86/kernel/ftrace_64.S b/arch/x86/kernel/ftrace_64.S
index c832291d948a..7cb8ba08beb9 100644
--- a/arch/x86/kernel/ftrace_64.S
+++ b/arch/x86/kernel/ftrace_64.S
@@ -7,7 +7,7 @@
 #include <asm/ptrace.h>
 #include <asm/ftrace.h>
 #include <asm/export.h>
-
+#include <asm/nospec-branch.h>

 	.code64
 	.section .entry.text, "ax"
@@ -286,8 +286,8 @@ trace:
 	 * ip and parent ip are used and the list function is called when
 	 * function tracing is enabled.
 	 */
-	call   *ftrace_trace_function
-
+	movq ftrace_trace_function, %r8
+	CALL_NOSPEC %r8
 	restore_mcount_regs

 	jmp fgraph_trace
@@ -329,5 +329,5 @@ GLOBAL(return_to_handler)
 	movq 8(%rsp), %rdx
 	movq (%rsp), %rax
 	addq $24, %rsp
-	jmp *%rdi
+	JMP_NOSPEC %rdi
 #endif
-- 
2.14.3

From f14fd95d2f3e611619756ea3c008aee3b4bd4978 Mon Sep 17 00:00:00 2001
From: David Woodhouse <dwmw@amazon.co.uk>
Date: Tue, 9 Jan 2018 14:43:13 +0000
Subject: [PATCH 07/10] x86/retpoline/hyperv: Convert assembler indirect jumps

Convert all indirect jumps in hyperv inline asm code to use non-speculative
sequences when CONFIG_RETPOLINE is enabled.

Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Arjan van de Ven <arjan@linux.intel.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
Cc: gnomes@lxorguk.ukuu.org.uk
Cc: Rik van Riel <riel@redhat.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Jiri Kosina <jikos@kernel.org>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Kees Cook <keescook@google.com>
Cc: Tim Chen <tim.c.chen@linux.intel.com>
Cc: Greg Kroah-Hartman <gregkh@linux-foundation.org>
Cc: Paul Turner <pjt@google.com>
Link: https://lkml.kernel.org/r/1515508997-6154-8-git-send-email-dwmw@amazon.co.uk
---
 arch/x86/include/asm/mshyperv.h | 18 ++++++++++--------
 1 file changed, 10 insertions(+), 8 deletions(-)

diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index 581bb54dd464..5119e4b555cc 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -7,6 +7,7 @@
 #include <linux/nmi.h>
 #include <asm/io.h>
 #include <asm/hyperv.h>
+#include <asm/nospec-branch.h>

 /*
  * The below CPUID leaves are present if VersionAndFeatures.HypervisorPresent
@@ -186,10 +187,11 @@ static inline u64 hv_do_hypercall(u64 control, void *input, void *output)
 		return U64_MAX;

 	__asm__ __volatile__("mov %4, %%r8\n"
-			     "call *%5"
+			     CALL_NOSPEC
 			     : "=a" (hv_status), ASM_CALL_CONSTRAINT,
 			       "+c" (control), "+d" (input_address)
-			     :  "r" (output_address), "m" (hv_hypercall_pg)
+			     :  "r" (output_address),
+				THUNK_TARGET(hv_hypercall_pg)
 			     : "cc", "memory", "r8", "r9", "r10", "r11");
 #else
 	u32 input_address_hi = upper_32_bits(input_address);
@@ -200,13 +202,13 @@ static inline u64 hv_do_hypercall(u64 control, void *input, void *output)
 	if (!hv_hypercall_pg)
 		return U64_MAX;

-	__asm__ __volatile__("call *%7"
+	__asm__ __volatile__(CALL_NOSPEC
 			     : "=A" (hv_status),
 			       "+c" (input_address_lo), ASM_CALL_CONSTRAINT
 			     : "A" (control),
 			       "b" (input_address_hi),
 			       "D"(output_address_hi), "S"(output_address_lo),
-			       "m" (hv_hypercall_pg)
+			       THUNK_TARGET(hv_hypercall_pg)
 			     : "cc", "memory");
 #endif /* !x86_64 */
 	return hv_status;
@@ -227,10 +229,10 @@ static inline u64 hv_do_fast_hypercall8(u16 code, u64 input1)

 #ifdef CONFIG_X86_64
 	{
-		__asm__ __volatile__("call *%4"
+		__asm__ __volatile__(CALL_NOSPEC
 				     : "=a" (hv_status), ASM_CALL_CONSTRAINT,
 				       "+c" (control), "+d" (input1)
-				     : "m" (hv_hypercall_pg)
+				     : THUNK_TARGET(hv_hypercall_pg)
 				     : "cc", "r8", "r9", "r10", "r11");
 	}
 #else
@@ -238,13 +240,13 @@ static inline u64 hv_do_fast_hypercall8(u16 code, u64 input1)
 		u32 input1_hi = upper_32_bits(input1);
 		u32 input1_lo = lower_32_bits(input1);

-		__asm__ __volatile__ ("call *%5"
+		__asm__ __volatile__ (CALL_NOSPEC
 				      : "=A"(hv_status),
 					"+c"(input1_lo),
 					ASM_CALL_CONSTRAINT
 				      :	"A" (control),
 					"b" (input1_hi),
-					"m" (hv_hypercall_pg)
+					THUNK_TARGET(hv_hypercall_pg)
 				      : "cc", "edi", "esi");
 	}
 #endif
-- 
2.14.3

From b569cb1e72bda00e7e6245519fe7d0d0ab13898e Mon Sep 17 00:00:00 2001
From: David Woodhouse <dwmw@amazon.co.uk>
Date: Tue, 9 Jan 2018 14:43:14 +0000
Subject: [PATCH 08/10] x86/retpoline/xen: Convert Xen hypercall indirect jumps

Convert indirect call in Xen hypercall to use non-speculative sequence,
when CONFIG_RETPOLINE is enabled.

Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Juergen Gross <jgross@suse.com>
Acked-by: Arjan van de Ven <arjan@linux.intel.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
Cc: gnomes@lxorguk.ukuu.org.uk
Cc: Rik van Riel <riel@redhat.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Jiri Kosina <jikos@kernel.org>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Kees Cook <keescook@google.com>
Cc: Tim Chen <tim.c.chen@linux.intel.com>
Cc: Greg Kroah-Hartman <gregkh@linux-foundation.org>
Cc: Paul Turner <pjt@google.com>
Link: https://lkml.kernel.org/r/1515508997-6154-9-git-send-email-dwmw@amazon.co.uk
---
 arch/x86/include/asm/xen/hypercall.h | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h
index 7cb282e9e587..bfd882617613 100644
--- a/arch/x86/include/asm/xen/hypercall.h
+++ b/arch/x86/include/asm/xen/hypercall.h
@@ -44,6 +44,7 @@
 #include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/smap.h>
+#include <asm/nospec-branch.h>

 #include <xen/interface/xen.h>
 #include <xen/interface/sched.h>
@@ -217,9 +218,9 @@ privcmd_call(unsigned call,
 	__HYPERCALL_5ARG(a1, a2, a3, a4, a5);

 	stac();
-	asm volatile("call *%[call]"
+	asm volatile(CALL_NOSPEC
 		     : __HYPERCALL_5PARAM
-		     : [call] "a" (&hypercall_page[call])
+		     : [thunk_target] "a" (&hypercall_page[call])
 		     : __HYPERCALL_CLOBBER5);
 	clac();

-- 
2.14.3

From 96f71b3a482e918991d165eb7a6b42eb9a9ef735 Mon Sep 17 00:00:00 2001
From: David Woodhouse <dwmw@amazon.co.uk>
Date: Tue, 9 Jan 2018 14:43:15 +0000
Subject: [PATCH 09/10] x86/retpoline/checksum32: Convert assembler indirect
 jumps

Convert all indirect jumps in 32bit checksum assembler code to use
non-speculative sequences when CONFIG_RETPOLINE is enabled.

Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Arjan van de Ven <arjan@linux.intel.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
Cc: gnomes@lxorguk.ukuu.org.uk
Cc: Rik van Riel <riel@redhat.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Jiri Kosina <jikos@kernel.org>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Kees Cook <keescook@google.com>
Cc: Tim Chen <tim.c.chen@linux.intel.com>
Cc: Greg Kroah-Hartman <gregkh@linux-foundation.org>
Cc: Paul Turner <pjt@google.com>
Link: https://lkml.kernel.org/r/1515508997-6154-10-git-send-email-dwmw@amazon.co.uk
---
 arch/x86/lib/checksum_32.S | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/arch/x86/lib/checksum_32.S b/arch/x86/lib/checksum_32.S
index 4d34bb548b41..46e71a74e612 100644
--- a/arch/x86/lib/checksum_32.S
+++ b/arch/x86/lib/checksum_32.S
@@ -29,7 +29,8 @@
 #include <asm/errno.h>
 #include <asm/asm.h>
 #include <asm/export.h>
-				
+#include <asm/nospec-branch.h>
+
 /*
  * computes a partial checksum, e.g. for TCP/UDP fragments
  */
@@ -156,7 +157,7 @@ ENTRY(csum_partial)
 	negl %ebx
 	lea 45f(%ebx,%ebx,2), %ebx
 	testl %esi, %esi
-	jmp *%ebx
+	JMP_NOSPEC %ebx

 	# Handle 2-byte-aligned regions
 20:	addw (%esi), %ax
@@ -439,7 +440,7 @@ ENTRY(csum_partial_copy_generic)
 	andl $-32,%edx
 	lea 3f(%ebx,%ebx), %ebx
 	testl %esi, %esi 
-	jmp *%ebx
+	JMP_NOSPEC %ebx
 1:	addl $64,%esi
 	addl $64,%edi 
 	SRC(movb -32(%edx),%bl)	; SRC(movb (%edx),%bl)
-- 
2.14.3

From 9080a45e302772c068f73bc24b3304a416fe2daf Mon Sep 17 00:00:00 2001
From: Andi Kleen <ak@linux.intel.com>
Date: Tue, 9 Jan 2018 14:43:16 +0000
Subject: [PATCH 10/10] x86/retpoline/irq32: Convert assembler indirect jumps

Convert all indirect jumps in 32bit irq inline asm code to use non
speculative sequences.

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Arjan van de Ven <arjan@linux.intel.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
Cc: gnomes@lxorguk.ukuu.org.uk
Cc: Rik van Riel <riel@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Jiri Kosina <jikos@kernel.org>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Kees Cook <keescook@google.com>
Cc: Tim Chen <tim.c.chen@linux.intel.com>
Cc: Greg Kroah-Hartman <gregkh@linux-foundation.org>
Cc: Paul Turner <pjt@google.com>
Link: https://lkml.kernel.org/r/1515508997-6154-11-git-send-email-dwmw@amazon.co.uk
---
 arch/x86/kernel/irq_32.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index a83b3346a0e1..c1bdbd3d3232 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -20,6 +20,7 @@
 #include <linux/mm.h>

 #include <asm/apic.h>
+#include <asm/nospec-branch.h>

 #ifdef CONFIG_DEBUG_STACKOVERFLOW

@@ -55,11 +56,11 @@ DEFINE_PER_CPU(struct irq_stack *, softirq_stack);
 static void call_on_stack(void *func, void *stack)
 {
 	asm volatile("xchgl	%%ebx,%%esp	\n"
-		     "call	*%%edi		\n"
+		     CALL_NOSPEC
 		     "movl	%%ebx,%%esp	\n"
 		     : "=b" (stack)
 		     : "0" (stack),
-		       "D"(func)
+		       [thunk_target] "D"(func)
 		     : "memory", "cc", "edx", "ecx", "eax");
 }

@@ -95,11 +96,11 @@ static inline int execute_on_irq_stack(int overflow, struct irq_desc *desc)
 		call_on_stack(print_stack_overflow, isp);

 	asm volatile("xchgl	%%ebx,%%esp	\n"
-		     "call	*%%edi		\n"
+		     CALL_NOSPEC
 		     "movl	%%ebx,%%esp	\n"
 		     : "=a" (arg1), "=b" (isp)
 		     :  "0" (desc),   "1" (isp),
-			"D" (desc->handle_irq)
+			[thunk_target] "D" (desc->handle_irq)
 		     : "memory", "cc", "ecx");
 	return 1;
 }
-- 
2.14.3