Merge remote-tracking branch 'stable-rc/linux-4.4.y' into 4.4.113-rc1-hikey-20180123-0014.4.113-rc1-hikey-20180123-001

34 files changed, 713 insertions, 59 deletions

diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 39280b72f27a..22a4688dc0c8 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -2452,6 +2452,11 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 
 	nohugeiomap	[KNL,x86] Disable kernel huge I/O mappings.
 
+	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.
@@ -3594,6 +3599,29 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 	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/Makefile b/Makefile
index 07070a1e6292..207a70dab753 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 VERSION = 4
 PATCHLEVEL = 4
-SUBLEVEL = 112
-EXTRAVERSION =
+SUBLEVEL = 113
+EXTRAVERSION = -rc1
 NAME = Blurry Fish Butt
 
 # *DOCUMENTATION*
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 0ef2cdd11616..75d0053b495a 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -379,6 +379,19 @@ 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.
+
 if X86_32
 config X86_EXTENDED_PLATFORM
 	bool "Support for extended (non-PC) x86 platforms"
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 4086abca0b32..1f9caa041bf7 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -189,6 +189,14 @@ KBUILD_CFLAGS += -fno-asynchronous-unwind-tables
 KBUILD_CFLAGS += $(mflags-y)
 KBUILD_AFLAGS += $(mflags-y)
 
+# 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
+    endif
+endif
+
 archscripts: scripts_basic
 	$(Q)$(MAKE) $(build)=arch/x86/tools relocs
 
diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S
index 6bd2c6c95373..3f93dedb5a4d 100644
--- a/arch/x86/crypto/aesni-intel_asm.S
+++ b/arch/x86/crypto/aesni-intel_asm.S
@@ -31,6 +31,7 @@
 
 #include <linux/linkage.h>
 #include <asm/inst.h>
+#include <asm/nospec-branch.h>
 
 /*
  * The following macros are used to move an (un)aligned 16 byte value to/from
@@ -2714,7 +2715,7 @@ ENTRY(aesni_xts_crypt8)
 	pxor INC, STATE4
 	movdqu IV, 0x30(OUTP)
 
-	call *%r11
+	CALL_NOSPEC %r11
 
 	movdqu 0x00(OUTP), INC
 	pxor INC, STATE1
@@ -2759,7 +2760,7 @@ 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 ce71f9212409..5881756f78a2 100644
--- a/arch/x86/crypto/camellia-aesni-avx-asm_64.S
+++ b/arch/x86/crypto/camellia-aesni-avx-asm_64.S
@@ -16,6 +16,7 @@
  */
 
 #include <linux/linkage.h>
+#include <asm/nospec-branch.h>
 
 #define CAMELLIA_TABLE_BYTE_LEN 272
 
@@ -1210,7 +1211,7 @@ 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 0e0b8863a34b..0d45b04b490a 100644
--- a/arch/x86/crypto/camellia-aesni-avx2-asm_64.S
+++ b/arch/x86/crypto/camellia-aesni-avx2-asm_64.S
@@ -11,6 +11,7 @@
  */
 
 #include <linux/linkage.h>
+#include <asm/nospec-branch.h>
 
 #define CAMELLIA_TABLE_BYTE_LEN 272
 
@@ -1323,7 +1324,7 @@ 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 4fe27e074194..48767520cbe0 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
 	offset=crc_array-jump_table
 	lea     offset(bufp, len, 1), bufp
-	jmp     *bufp
+	JMP_NOSPEC bufp
 
 	################################################################
 	## 2a) PROCESS FULL BLOCKS:
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index ae678ad128a9..0789e93218db 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -44,6 +44,7 @@
 #include <asm/alternative-asm.h>
 #include <asm/asm.h>
 #include <asm/smap.h>
+#include <asm/nospec-branch.h>
 
 	.section .entry.text, "ax"
 
@@ -226,7 +227,7 @@ ENTRY(ret_from_kernel_thread)
 	pushl	$0x0202				# Reset kernel eflags
 	popfl
 	movl	PT_EBP(%esp), %eax
-	call	*PT_EBX(%esp)
+	CALL_NOSPEC PT_EBX(%esp)
 	movl	$0, PT_EAX(%esp)
 
 	/*
@@ -861,7 +862,8 @@ trace:
 	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
@@ -896,7 +898,7 @@ return_to_handler:
 	movl	%eax, %ecx
 	popl	%edx
 	popl	%eax
-	jmp	*%ecx
+	JMP_NOSPEC %ecx
 #endif
 
 #ifdef CONFIG_TRACING
@@ -938,7 +940,7 @@ error_code:
 	movl	%ecx, %es
 	TRACE_IRQS_OFF
 	movl	%esp, %eax			# pt_regs pointer
-	call	*%edi
+	CALL_NOSPEC %edi
 	jmp	ret_from_exception
 END(page_fault)
 
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 952b23b5d4e9..81b1cd533965 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -36,6 +36,7 @@
 #include <asm/smap.h>
 #include <asm/pgtable_types.h>
 #include <asm/kaiser.h>
+#include <asm/nospec-branch.h>
 #include <linux/err.h>
 
 /* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this.  */
@@ -184,7 +185,13 @@ entry_SYSCALL_64_fastpath:
 #endif
 	ja	1f				/* return -ENOSYS (already in pt_regs->ax) */
 	movq	%r10, %rcx
+#ifdef CONFIG_RETPOLINE
+	movq	sys_call_table(, %rax, 8), %rax
+	call	__x86_indirect_thunk_rax
+#else
 	call	*sys_call_table(, %rax, 8)
+#endif
+
 	movq	%rax, RAX(%rsp)
 1:
 /*
@@ -276,7 +283,12 @@ tracesys_phase2:
 #endif
 	ja	1f				/* return -ENOSYS (already in pt_regs->ax) */
 	movq	%r10, %rcx			/* fixup for C */
+#ifdef CONFIG_RETPOLINE
+	movq	sys_call_table(, %rax, 8), %rax
+	call	__x86_indirect_thunk_rax
+#else
 	call	*sys_call_table(, %rax, 8)
+#endif
 	movq	%rax, RAX(%rsp)
 1:
 	/* Use IRET because user could have changed pt_regs->foo */
@@ -491,7 +503,7 @@ ENTRY(ret_from_fork)
 	 * nb: we depend on RESTORE_EXTRA_REGS above
 	 */
 	movq	%rbp, %rdi
-	call	*%rbx
+	CALL_NOSPEC %rbx
 	movl	$0, RAX(%rsp)
 	RESTORE_EXTRA_REGS
 	jmp	int_ret_from_sys_call
diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index d1cf17173b1b..215ea9214215 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -1,6 +1,8 @@
 #ifndef _ASM_X86_ALTERNATIVE_H
 #define _ASM_X86_ALTERNATIVE_H
 
+#ifndef __ASSEMBLY__
+
 #include <linux/types.h>
 #include <linux/stddef.h>
 #include <linux/stringify.h>
@@ -271,4 +273,6 @@ extern void *text_poke(void *addr, const void *opcode, size_t len);
 extern int poke_int3_handler(struct pt_regs *regs);
 extern void *text_poke_bp(void *addr, const void *opcode, size_t len, void *handler);
 
+#endif /* __ASSEMBLY__ */
+
 #endif /* _ASM_X86_ALTERNATIVE_H */
diff --git a/arch/x86/include/asm/asm-prototypes.h b/arch/x86/include/asm/asm-prototypes.h
new file mode 100644
index 000000000000..b15aa4083dfd
--- /dev/null
+++ b/arch/x86/include/asm/asm-prototypes.h
@@ -0,0 +1,41 @@
+#include <asm/ftrace.h>
+#include <asm/uaccess.h>
+#include <asm/string.h>
+#include <asm/page.h>
+#include <asm/checksum.h>
+
+#include <asm-generic/asm-prototypes.h>
+
+#include <asm/page.h>
+#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/asm.h b/arch/x86/include/asm/asm.h
index 189679aba703..b9c6c7a6f5a6 100644
--- a/arch/x86/include/asm/asm.h
+++ b/arch/x86/include/asm/asm.h
@@ -105,4 +105,15 @@
 /* For C file, we already have NOKPROBE_SYMBOL macro */
 #endif
 
+#ifndef __ASSEMBLY__
+/*
+ * This output constraint should be used for any inline asm which has a "call"
+ * instruction.  Otherwise the asm may be inserted before the frame pointer
+ * gets set up by the containing function.  If you forget to do this, objtool
+ * may print a "call without frame pointer save/setup" warning.
+ */
+register unsigned long current_stack_pointer asm(_ASM_SP);
+#define ASM_CALL_CONSTRAINT "+r" (current_stack_pointer)
+#endif
+
 #endif /* _ASM_X86_ASM_H */
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 142028afd049..0fbc98568018 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -200,6 +200,8 @@
 #define X86_FEATURE_HWP_PKG_REQ ( 7*32+14) /* Intel HWP_PKG_REQ */
 #define X86_FEATURE_INTEL_PT	( 7*32+15) /* Intel Processor Trace */
 
+#define X86_FEATURE_RETPOLINE	( 7*32+29) /* Generic Retpoline mitigation for Spectre variant 2 */
+#define X86_FEATURE_RETPOLINE_AMD ( 7*32+30) /* AMD Retpoline mitigation for Spectre variant 2 */
 /* Because the ALTERNATIVE scheme is for members of the X86_FEATURE club... */
 #define X86_FEATURE_KAISER	( 7*32+31) /* CONFIG_PAGE_TABLE_ISOLATION w/o nokaiser */
 
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 37db36fddc88..b8911aecf035 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -330,6 +330,9 @@
 #define FAM10H_MMIO_CONF_BASE_MASK	0xfffffffULL
 #define FAM10H_MMIO_CONF_BASE_SHIFT	20
 #define MSR_FAM10H_NODE_ID		0xc001100c
+#define MSR_F10H_DECFG			0xc0011029
+#define MSR_F10H_DECFG_LFENCE_SERIALIZE_BIT	1
+#define MSR_F10H_DECFG_LFENCE_SERIALIZE		BIT_ULL(MSR_F10H_DECFG_LFENCE_SERIALIZE_BIT)
 
 /* K8 MSRs */
 #define MSR_K8_TOP_MEM1			0xc001001a
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
new file mode 100644
index 000000000000..1afd04eb5fb7
--- /dev/null
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -0,0 +1,190 @@
+/* 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/cpufeature.h>
+
+/*
+ * 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.
+ *
+ * This is required in various cases for retpoline and IBRS-based
+ * mitigations for the Spectre variant 2 vulnerability. Sometimes to
+ * eliminate potentially bogus entries from the RSB, and sometimes
+ * purely to ensure that it doesn't get empty, which on some CPUs would
+ * allow predictions from other (unwanted!) sources to be used.
+ *
+ * We define a CPP macro such that it can be used from both .S files and
+ * inline assembly. It's possible to do a .macro and then include that
+ * from C via asm(".include <asm/nospec-branch.h>") but let's not go there.
+ */
+
+#define RSB_CLEAR_LOOPS		32	/* To forcibly overwrite all entries */
+#define RSB_FILL_LOOPS		16	/* To avoid underflow */
+
+/*
+ * Google experimented with loop-unrolling and this turned out to be
+ * the optimal version — two calls, each with their own speculation
+ * trap should their return address end up getting used, in a loop.
+ */
+#define __FILL_RETURN_BUFFER(reg, nr, sp)	\
+	mov	$(nr/2), reg;			\
+771:						\
+	call	772f;				\
+773:	/* speculation trap */			\
+	pause;					\
+	jmp	773b;				\
+772:						\
+	call	774f;				\
+775:	/* speculation trap */			\
+	pause;					\
+	jmp	775b;				\
+774:						\
+	dec	reg;				\
+	jnz	771b;				\
+	add	$(BITS_PER_LONG/8) * nr, sp;
+
+#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
+
+ /*
+  * A simpler FILL_RETURN_BUFFER macro. Don't make people use the CPP
+  * monstrosity above, manually.
+  */
+.macro FILL_RETURN_BUFFER reg:req nr:req ftr:req
+#ifdef CONFIG_RETPOLINE
+	ALTERNATIVE "jmp .Lskip_rsb_\@",				\
+		__stringify(__FILL_RETURN_BUFFER(\reg,\nr,%_ASM_SP))	\
+		\ftr
+.Lskip_rsb_\@:
+#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    904f;\n"					\
+	"       .align 16\n"					\
+	"901:	call   903f;\n"					\
+	"902:	pause;\n"					\
+	"       jmp    902b;\n"					\
+	"       .align 16\n"					\
+	"903:	addl   $4, %%esp;\n"				\
+	"       pushl  %[thunk_target];\n"			\
+	"       ret;\n"						\
+	"       .align 16\n"					\
+	"904:	call   901b;\n",				\
+	X86_FEATURE_RETPOLINE)
+
+# define THUNK_TARGET(addr) [thunk_target] "rm" (addr)
+#else /* No retpoline for C / inline asm */
+# define CALL_NOSPEC "call *%[thunk_target]\n"
+# 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,
+};
+
+/*
+ * On VMEXIT we must ensure that no RSB predictions learned in the guest
+ * can be followed in the host, by overwriting the RSB completely. Both
+ * retpoline and IBRS mitigations for Spectre v2 need this; only on future
+ * CPUs with IBRS_ATT *might* it be avoided.
+ */
+static inline void vmexit_fill_RSB(void)
+{
+#ifdef CONFIG_RETPOLINE
+	unsigned long loops = RSB_CLEAR_LOOPS / 2;
+
+	asm volatile (ALTERNATIVE("jmp 910f",
+				  __stringify(__FILL_RETURN_BUFFER(%0, RSB_CLEAR_LOOPS, %1)),
+				  X86_FEATURE_RETPOLINE)
+		      "910:"
+		      : "=&r" (loops), ASM_CALL_CONSTRAINT
+		      : "r" (loops) : "memory" );
+#endif
+}
+#endif /* __ASSEMBLY__ */
+#endif /* __NOSPEC_BRANCH_H__ */
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index c7b551028740..9b028204685d 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -166,17 +166,6 @@ static inline struct thread_info *current_thread_info(void)
 	return (struct thread_info *)(current_top_of_stack() - THREAD_SIZE);
 }
 
-static inline unsigned long current_stack_pointer(void)
-{
-	unsigned long sp;
-#ifdef CONFIG_X86_64
-	asm("mov %%rsp,%0" : "=g" (sp));
-#else
-	asm("mov %%esp,%0" : "=g" (sp));
-#endif
-	return sp;
-}
-
 #else /* !__ASSEMBLY__ */
 
 #ifdef CONFIG_X86_64
diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h
index 85133b2b8e99..0977e7607046 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>
@@ -215,9 +216,9 @@ 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();
 
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index e2defc7593a4..4bf9e77f3e05 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -746,8 +746,32 @@ static void init_amd(struct cpuinfo_x86 *c)
 		set_cpu_cap(c, X86_FEATURE_K8);
 
 	if (cpu_has_xmm2) {
-		/* MFENCE stops RDTSC speculation */
-		set_cpu_cap(c, X86_FEATURE_MFENCE_RDTSC);
+		unsigned long long val;
+		int ret;
+
+		/*
+		 * A serializing LFENCE has less overhead than MFENCE, so
+		 * use it for execution serialization.  On families which
+		 * don't have that MSR, LFENCE is already serializing.
+		 * msr_set_bit() uses the safe accessors, too, even if the MSR
+		 * is not present.
+		 */
+		msr_set_bit(MSR_F10H_DECFG,
+			    MSR_F10H_DECFG_LFENCE_SERIALIZE_BIT);
+
+		/*
+		 * Verify that the MSR write was successful (could be running
+		 * under a hypervisor) and only then assume that LFENCE is
+		 * serializing.
+		 */
+		ret = rdmsrl_safe(MSR_F10H_DECFG, &val);
+		if (!ret && (val & MSR_F10H_DECFG_LFENCE_SERIALIZE)) {
+			/* A serializing LFENCE stops RDTSC speculation */
+			set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC);
+		} else {
+			/* MFENCE stops RDTSC speculation */
+			set_cpu_cap(c, X86_FEATURE_MFENCE_RDTSC);
+		}
 	}
 
 	/*
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index cd46f9039119..49d25ddf0e9f 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -10,6 +10,9 @@
 #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>
@@ -20,16 +23,10 @@
 #include <asm/pgtable.h>
 #include <asm/cacheflush.h>
 
+static void __init spectre_v2_select_mitigation(void);
+
 void __init check_bugs(void)
 {
-#ifdef CONFIG_X86_32
-	/*
-	 * Regardless of whether PCID is enumerated, the SDM says
-	 * that it can't be enabled in 32-bit mode.
-	 */
-	setup_clear_cpu_cap(X86_FEATURE_PCID);
-#endif
-
 	identify_boot_cpu();
 
 	if (!IS_ENABLED(CONFIG_SMP)) {
@@ -37,6 +34,9 @@ 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.
@@ -69,6 +69,153 @@ 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)
@@ -93,6 +240,7 @@ 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 dc4dfad66a70..0531c1707b40 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -838,6 +838,14 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
 	setup_force_cpu_bug(X86_BUG_SPECTRE_V2);
 
 	fpu__init_system(c);
+
+#ifdef CONFIG_X86_32
+	/*
+	 * Regardless of whether PCID is enumerated, the SDM says
+	 * that it can't be enabled in 32-bit mode.
+	 */
+	setup_clear_cpu_cap(X86_FEATURE_PCID);
+#endif
 }
 
 void __init early_cpu_init(void)
diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index 38da8f29a9c8..528b7aa1780d 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
 
@@ -55,17 +56,17 @@ 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");
 }
 
 static inline void *current_stack(void)
 {
-	return (void *)(current_stack_pointer() & ~(THREAD_SIZE - 1));
+	return (void *)(current_stack_pointer & ~(THREAD_SIZE - 1));
 }
 
 static inline int execute_on_irq_stack(int overflow, struct irq_desc *desc)
@@ -89,17 +90,17 @@ static inline int execute_on_irq_stack(int overflow, struct irq_desc *desc)
 
 	/* Save the next esp at the bottom of the stack */
 	prev_esp = (u32 *)irqstk;
-	*prev_esp = current_stack_pointer();
+	*prev_esp = current_stack_pointer;
 
 	if (unlikely(overflow))
 		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;
 }
@@ -142,7 +143,7 @@ void do_softirq_own_stack(void)
 
 	/* Push the previous esp onto the stack */
 	prev_esp = (u32 *)irqstk;
-	*prev_esp = current_stack_pointer();
+	*prev_esp = current_stack_pointer;
 
 	call_on_stack(__do_softirq, isp);
 }
diff --git a/arch/x86/kernel/mcount_64.S b/arch/x86/kernel/mcount_64.S
index 5d9afbcb6074..09284cfab86f 100644
--- a/arch/x86/kernel/mcount_64.S
+++ b/arch/x86/kernel/mcount_64.S
@@ -7,7 +7,7 @@
 #include <linux/linkage.h>
 #include <asm/ptrace.h>
 #include <asm/ftrace.h>
-
+#include <asm/nospec-branch.h>
 
 	.code64
 	.section .entry.text, "ax"
@@ -285,8 +285,9 @@ 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 +330,5 @@ GLOBAL(return_to_handler)
 	movq 8(%rsp), %rdx
 	movq (%rsp), %rax
 	addq $24, %rsp
-	jmp *%rdi
+	JMP_NOSPEC %rdi
 #endif
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 679302c312f8..22b81f35c500 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -166,7 +166,7 @@ void ist_begin_non_atomic(struct pt_regs *regs)
 	 * from double_fault.
 	 */
 	BUG_ON((unsigned long)(current_top_of_stack() -
-			       current_stack_pointer()) >= THREAD_SIZE);
+			       current_stack_pointer) >= THREAD_SIZE);
 
 	preempt_enable_no_resched();
 }
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 900ffb6c28b5..2038e5bacce6 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -37,6 +37,7 @@
 #include <asm/desc.h>
 #include <asm/debugreg.h>
 #include <asm/kvm_para.h>
+#include <asm/nospec-branch.h>
 
 #include <asm/virtext.h>
 #include "trace.h"
@@ -3904,6 +3905,9 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
 #endif
 		);
 
+	/* Eliminate branch target predictions from guest mode */
+	vmexit_fill_RSB();
+
 #ifdef CONFIG_X86_64
 	wrmsrl(MSR_GS_BASE, svm->host.gs_base);
 #else
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index c26255f19603..75d60e40c389 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -47,6 +47,7 @@
 #include <asm/kexec.h>
 #include <asm/apic.h>
 #include <asm/irq_remapping.h>
+#include <asm/nospec-branch.h>
 
 #include "trace.h"
 #include "pmu.h"
@@ -8701,6 +8702,9 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 #endif
 	      );
 
+	/* Eliminate branch target predictions from guest mode */
+	vmexit_fill_RSB();
+
 	/* MSR_IA32_DEBUGCTLMSR is zeroed on vmexit. Restore it if needed */
 	if (debugctlmsr)
 		update_debugctlmsr(debugctlmsr);
diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile
index f2587888d987..12a34d15b648 100644
--- a/arch/x86/lib/Makefile
+++ b/arch/x86/lib/Makefile
@@ -21,6 +21,7 @@ lib-y += usercopy_$(BITS).o usercopy.o getuser.o putuser.o
 lib-y += memcpy_$(BITS).o
 lib-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem.o
 lib-$(CONFIG_INSTRUCTION_DECODER) += insn.o inat.o
+lib-$(CONFIG_RETPOLINE) += retpoline.o
 
 obj-y += msr.o msr-reg.o msr-reg-export.o
 
diff --git a/arch/x86/lib/checksum_32.S b/arch/x86/lib/checksum_32.S
index c1e623209853..90353a26ed95 100644
--- a/arch/x86/lib/checksum_32.S
+++ b/arch/x86/lib/checksum_32.S
@@ -28,7 +28,8 @@
 #include <linux/linkage.h>
 #include <asm/errno.h>
 #include <asm/asm.h>
-				
+#include <asm/nospec-branch.h>
+
 /*
  * computes a partial checksum, e.g. for TCP/UDP fragments
  */
@@ -155,7 +156,7 @@ 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
@@ -437,7 +438,7 @@ 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)
diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S
new file mode 100644
index 000000000000..019a03599bb0
--- /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/cpufeature.h>
+#include <asm/alternative-asm.h>
+#include <asm-generic/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
diff --git a/drivers/hv/hv.c b/drivers/hv/hv.c
index 8ce1f2e22912..d415a804fd26 100644
--- a/drivers/hv/hv.c
+++ b/drivers/hv/hv.c
@@ -31,6 +31,7 @@
 #include <linux/clockchips.h>
 #include <asm/hyperv.h>
 #include <asm/mshyperv.h>
+#include <asm/nospec-branch.h>
 #include "hyperv_vmbus.h"
 
 /* The one and only */
@@ -103,9 +104,10 @@ static u64 do_hypercall(u64 control, void *input, void *output)
 		return (u64)ULLONG_MAX;
 
 	__asm__ __volatile__("mov %0, %%r8" : : "r" (output_address) : "r8");
-	__asm__ __volatile__("call *%3" : "=a" (hv_status) :
+	__asm__ __volatile__(CALL_NOSPEC :
+			     "=a" (hv_status) :
 			     "c" (control), "d" (input_address),
-			     "m" (hypercall_page));
+			     THUNK_TARGET(hypercall_page));
 
 	return hv_status;
 
@@ -123,11 +125,12 @@ static u64 do_hypercall(u64 control, void *input, void *output)
 	if (!hypercall_page)
 		return (u64)ULLONG_MAX;
 
-	__asm__ __volatile__ ("call *%8" : "=d"(hv_status_hi),
+	__asm__ __volatile__ (CALL_NOSPEC : "=d"(hv_status_hi),
 			      "=a"(hv_status_lo) : "d" (control_hi),
 			      "a" (control_lo), "b" (input_address_hi),
 			      "c" (input_address_lo), "D"(output_address_hi),
-			      "S"(output_address_lo), "m" (hypercall_page));
+			      "S"(output_address_lo),
+			      THUNK_TARGET(hypercall_page));
 
 	return hv_status_lo | ((u64)hv_status_hi << 32);
 #endif /* !x86_64 */
diff --git a/include/asm-generic/asm-prototypes.h b/include/asm-generic/asm-prototypes.h
new file mode 100644
index 000000000000..df13637e4017
--- /dev/null
+++ b/include/asm-generic/asm-prototypes.h
@@ -0,0 +1,7 @@
+#include <linux/bitops.h>
+extern void *__memset(void *, int, __kernel_size_t);
+extern void *__memcpy(void *, const void *, __kernel_size_t);
+extern void *__memmove(void *, const void *, __kernel_size_t);
+extern void *memset(void *, int, __kernel_size_t);
+extern void *memcpy(void *, const void *, __kernel_size_t);
+extern void *memmove(void *, const void *, __kernel_size_t);
diff --git a/include/asm-generic/export.h b/include/asm-generic/export.h
new file mode 100644
index 000000000000..43199a049da5
--- /dev/null
+++ b/include/asm-generic/export.h
@@ -0,0 +1,94 @@
+#ifndef __ASM_GENERIC_EXPORT_H
+#define __ASM_GENERIC_EXPORT_H
+
+#ifndef KSYM_FUNC
+#define KSYM_FUNC(x) x
+#endif
+#ifdef CONFIG_64BIT
+#define __put .quad
+#ifndef KSYM_ALIGN
+#define KSYM_ALIGN 8
+#endif
+#ifndef KCRC_ALIGN
+#define KCRC_ALIGN 8
+#endif
+#else
+#define __put .long
+#ifndef KSYM_ALIGN
+#define KSYM_ALIGN 4
+#endif
+#ifndef KCRC_ALIGN
+#define KCRC_ALIGN 4
+#endif
+#endif
+
+#ifdef CONFIG_HAVE_UNDERSCORE_SYMBOL_PREFIX
+#define KSYM(name) _##name
+#else
+#define KSYM(name) name
+#endif
+
+/*
+ * note on .section use: @progbits vs %progbits nastiness doesn't matter,
+ * since we immediately emit into those sections anyway.
+ */
+.macro ___EXPORT_SYMBOL name,val,sec
+#ifdef CONFIG_MODULES
+	.globl KSYM(__ksymtab_\name)
+	.section ___ksymtab\sec+\name,"a"
+	.balign KSYM_ALIGN
+KSYM(__ksymtab_\name):
+	__put \val, KSYM(__kstrtab_\name)
+	.previous
+	.section __ksymtab_strings,"a"
+KSYM(__kstrtab_\name):
+#ifdef CONFIG_HAVE_UNDERSCORE_SYMBOL_PREFIX
+	.asciz "_\name"
+#else
+	.asciz "\name"
+#endif
+	.previous
+#ifdef CONFIG_MODVERSIONS
+	.section ___kcrctab\sec+\name,"a"
+	.balign KCRC_ALIGN
+KSYM(__kcrctab_\name):
+	__put KSYM(__crc_\name)
+	.weak KSYM(__crc_\name)
+	.previous
+#endif
+#endif
+.endm
+#undef __put
+
+#if defined(__KSYM_DEPS__)
+
+#define __EXPORT_SYMBOL(sym, val, sec)	=== __KSYM_##sym ===
+
+#elif defined(CONFIG_TRIM_UNUSED_KSYMS)
+
+#include <linux/kconfig.h>
+#include <generated/autoksyms.h>
+
+#define __EXPORT_SYMBOL(sym, val, sec)				\
+	__cond_export_sym(sym, val, sec, config_enabled(__KSYM_##sym))
+#define __cond_export_sym(sym, val, sec, conf)			\
+	___cond_export_sym(sym, val, sec, conf)
+#define ___cond_export_sym(sym, val, sec, enabled)		\
+	__cond_export_sym_##enabled(sym, val, sec)
+#define __cond_export_sym_1(sym, val, sec) ___EXPORT_SYMBOL sym, val, sec
+#define __cond_export_sym_0(sym, val, sec) /* nothing */
+
+#else
+#define __EXPORT_SYMBOL(sym, val, sec) ___EXPORT_SYMBOL sym, val, sec
+#endif
+
+#define EXPORT_SYMBOL(name)					\
+	__EXPORT_SYMBOL(name, KSYM_FUNC(KSYM(name)),)
+#define EXPORT_SYMBOL_GPL(name) 				\
+	__EXPORT_SYMBOL(name, KSYM_FUNC(KSYM(name)), _gpl)
+#define EXPORT_DATA_SYMBOL(name)				\
+	__EXPORT_SYMBOL(name, KSYM(name),)
+#define EXPORT_DATA_SYMBOL_GPL(name)				\
+	__EXPORT_SYMBOL(name, KSYM(name),_gpl)
+
+#endif
diff --git a/include/linux/kconfig.h b/include/linux/kconfig.h
index b33c7797eb57..a94b5bf57f51 100644
--- a/include/linux/kconfig.h
+++ b/include/linux/kconfig.h
@@ -17,10 +17,11 @@
  * the last step cherry picks the 2nd arg, we get a zero.
  */
 #define __ARG_PLACEHOLDER_1 0,
-#define config_enabled(cfg) _config_enabled(cfg)
-#define _config_enabled(value) __config_enabled(__ARG_PLACEHOLDER_##value)
-#define __config_enabled(arg1_or_junk) ___config_enabled(arg1_or_junk 1, 0)
-#define ___config_enabled(__ignored, val, ...) val
+#define config_enabled(cfg)		___is_defined(cfg)
+#define __is_defined(x)			___is_defined(x)
+#define ___is_defined(val)		____is_defined(__ARG_PLACEHOLDER_##val)
+#define ____is_defined(arg1_or_junk)	__take_second_arg(arg1_or_junk 1, 0)
+#define __take_second_arg(__ignored, val, ...) val
 
 /*
  * IS_BUILTIN(CONFIG_FOO) evaluates to 1 if CONFIG_FOO is set to 'y', 0
@@ -42,7 +43,7 @@
  * built-in code when CONFIG_FOO is set to 'm'.
  */
 #define IS_REACHABLE(option) (config_enabled(option) || \
-		 (config_enabled(option##_MODULE) && config_enabled(MODULE)))
+		 (config_enabled(option##_MODULE) && __is_defined(MODULE)))
 
 /*
  * IS_ENABLED(CONFIG_FOO) evaluates to 1 if CONFIG_FOO is set to 'y' or 'm',
diff --git a/kernel/gcov/Kconfig b/kernel/gcov/Kconfig
index c92e44855ddd..1276aabaab55 100644
--- a/kernel/gcov/Kconfig
+++ b/kernel/gcov/Kconfig
@@ -37,6 +37,7 @@ config ARCH_HAS_GCOV_PROFILE_ALL
 
 config GCOV_PROFILE_ALL
 	bool "Profile entire Kernel"
+	depends on !COMPILE_TEST
 	depends on GCOV_KERNEL
 	depends on ARCH_HAS_GCOV_PROFILE_ALL
 	default n