Merge branch 'for-4.16/nfit' into libnvdimm-for-next

56 files changed, 873 insertions, 210 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index d4fc98c50378..20da391b5f32 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -55,7 +55,6 @@ config X86
 	select ARCH_HAS_GCOV_PROFILE_ALL
 	select ARCH_HAS_KCOV			if X86_64
 	select ARCH_HAS_PMEM_API		if X86_64
-	# Causing hangs/crashes, see the commit that added this change for details.
 	select ARCH_HAS_REFCOUNT
 	select ARCH_HAS_UACCESS_FLUSHCACHE	if X86_64
 	select ARCH_HAS_SET_MEMORY
@@ -89,6 +88,7 @@ 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
@@ -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 3e73bc255e4e..fad55160dcb9 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -230,6 +230,14 @@ 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
+    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 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:
diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h
index 45a63e00a6af..3f48f695d5e6 100644
--- a/arch/x86/entry/calling.h
+++ b/arch/x86/entry/calling.h
@@ -198,8 +198,11 @@ For 32-bit we have the following conventions - kernel is built with
  * PAGE_TABLE_ISOLATION PGDs are 8k.  Flip bit 12 to switch between the two
  * halves:
  */
-#define PTI_SWITCH_PGTABLES_MASK	(1<<PAGE_SHIFT)
-#define PTI_SWITCH_MASK		(PTI_SWITCH_PGTABLES_MASK|(1<<X86_CR3_PTI_SWITCH_BIT))
+#define PTI_USER_PGTABLE_BIT		PAGE_SHIFT
+#define PTI_USER_PGTABLE_MASK		(1 << PTI_USER_PGTABLE_BIT)
+#define PTI_USER_PCID_BIT		X86_CR3_PTI_PCID_USER_BIT
+#define PTI_USER_PCID_MASK		(1 << PTI_USER_PCID_BIT)
+#define PTI_USER_PGTABLE_AND_PCID_MASK  (PTI_USER_PCID_MASK | PTI_USER_PGTABLE_MASK)
 
 .macro SET_NOFLUSH_BIT	reg:req
 	bts	$X86_CR3_PCID_NOFLUSH_BIT, \reg
@@ -208,7 +211,7 @@ For 32-bit we have the following conventions - kernel is built with
 .macro ADJUST_KERNEL_CR3 reg:req
 	ALTERNATIVE "", "SET_NOFLUSH_BIT \reg", X86_FEATURE_PCID
 	/* Clear PCID and "PAGE_TABLE_ISOLATION bit", point CR3 at kernel pagetables: */
-	andq    $(~PTI_SWITCH_MASK), \reg
+	andq    $(~PTI_USER_PGTABLE_AND_PCID_MASK), \reg
 .endm
 
 .macro SWITCH_TO_KERNEL_CR3 scratch_reg:req
@@ -239,15 +242,19 @@ For 32-bit we have the following conventions - kernel is built with
 	/* Flush needed, clear the bit */
 	btr	\scratch_reg, THIS_CPU_user_pcid_flush_mask
 	movq	\scratch_reg2, \scratch_reg
-	jmp	.Lwrcr3_\@
+	jmp	.Lwrcr3_pcid_\@
 
 .Lnoflush_\@:
 	movq	\scratch_reg2, \scratch_reg
 	SET_NOFLUSH_BIT \scratch_reg
 
+.Lwrcr3_pcid_\@:
+	/* Flip the ASID to the user version */
+	orq	$(PTI_USER_PCID_MASK), \scratch_reg
+
 .Lwrcr3_\@:
-	/* Flip the PGD and ASID to the user version */
-	orq     $(PTI_SWITCH_MASK), \scratch_reg
+	/* Flip the PGD to the user version */
+	orq     $(PTI_USER_PGTABLE_MASK), \scratch_reg
 	mov	\scratch_reg, %cr3
 .Lend_\@:
 .endm
@@ -263,17 +270,12 @@ For 32-bit we have the following conventions - kernel is built with
 	movq	%cr3, \scratch_reg
 	movq	\scratch_reg, \save_reg
 	/*
-	 * Is the "switch mask" all zero?  That means that both of
-	 * these are zero:
-	 *
-	 *	1. The user/kernel PCID bit, and
-	 *	2. The user/kernel "bit" that points CR3 to the
-	 *	   bottom half of the 8k PGD
-	 *
-	 * That indicates a kernel CR3 value, not a user CR3.
+	 * Test the user pagetable bit. If set, then the user page tables
+	 * are active. If clear CR3 already has the kernel page table
+	 * active.
 	 */
-	testq	$(PTI_SWITCH_MASK), \scratch_reg
-	jz	.Ldone_\@
+	bt	$PTI_USER_PGTABLE_BIT, \scratch_reg
+	jnc	.Ldone_\@
 
 	ADJUST_KERNEL_CR3 \scratch_reg
 	movq	\scratch_reg, %cr3
@@ -290,7 +292,7 @@ For 32-bit we have the following conventions - kernel is built with
 	 * KERNEL pages can always resume with NOFLUSH as we do
 	 * explicit flushes.
 	 */
-	bt	$X86_CR3_PTI_SWITCH_BIT, \save_reg
+	bt	$PTI_USER_PGTABLE_BIT, \save_reg
 	jnc	.Lnoflush_\@
 
 	/*
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 f048e384ff54..4f8e1d35a97c 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"
@@ -191,7 +192,7 @@ ENTRY(entry_SYSCALL_64_trampoline)
 	 */
 	pushq	%rdi
 	movq	$entry_SYSCALL_64_stage2, %rdi
-	jmp	*%rdi
+	JMP_NOSPEC %rdi
 END(entry_SYSCALL_64_trampoline)
 
 	.popsection
@@ -270,7 +271,12 @@ 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)
@@ -442,7 +448,7 @@ 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
@@ -521,7 +527,7 @@ 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()
diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S
index 40f17009ec20..98d5358e4041 100644
--- a/arch/x86/entry/entry_64_compat.S
+++ b/arch/x86/entry/entry_64_compat.S
@@ -190,8 +190,13 @@ ENTRY(entry_SYSCALL_compat)
 	/* Interrupts are off on entry. */
 	swapgs
 
-	/* Stash user ESP and switch to the kernel stack. */
+	/* Stash user ESP */
 	movl	%esp, %r8d
+
+	/* Use %rsp as scratch reg. User ESP is stashed in r8 */
+	SWITCH_TO_KERNEL_CR3 scratch_reg=%rsp
+
+	/* Switch to the kernel stack */
 	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp
 
 	/* Construct struct pt_regs on stack */
@@ -220,12 +225,6 @@ GLOBAL(entry_SYSCALL_compat_after_hwframe)
 	pushq   $0			/* pt_regs->r15 = 0 */
 
 	/*
-	 * We just saved %rdi so it is safe to clobber.  It is not
-	 * preserved during the C calls inside TRACE_IRQS_OFF anyway.
-	 */
-	SWITCH_TO_KERNEL_CR3 scratch_reg=%rdi
-
-	/*
 	 * User mode is traced as though IRQs are on, and SYSENTER
 	 * turned them off.
 	 */
diff --git a/arch/x86/events/intel/bts.c b/arch/x86/events/intel/bts.c
index 141e07b06216..24ffa1e88cf9 100644
--- a/arch/x86/events/intel/bts.c
+++ b/arch/x86/events/intel/bts.c
@@ -582,6 +582,24 @@ static __init int bts_init(void)
 	if (!boot_cpu_has(X86_FEATURE_DTES64) || !x86_pmu.bts)
 		return -ENODEV;
 
+	if (boot_cpu_has(X86_FEATURE_PTI)) {
+		/*
+		 * BTS hardware writes through a virtual memory map we must
+		 * either use the kernel physical map, or the user mapping of
+		 * the AUX buffer.
+		 *
+		 * However, since this driver supports per-CPU and per-task inherit
+		 * we cannot use the user mapping since it will not be availble
+		 * if we're not running the owning process.
+		 *
+		 * With PTI we can't use the kernal map either, because its not
+		 * there when we run userspace.
+		 *
+		 * For now, disable this driver when using PTI.
+		 */
+		return -ENODEV;
+	}
+
 	bts_pmu.capabilities	= PERF_PMU_CAP_AUX_NO_SG | PERF_PMU_CAP_ITRACE |
 				  PERF_PMU_CAP_EXCLUSIVE;
 	bts_pmu.task_ctx_nr	= perf_sw_context;
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 8f0aace08b87..8156e47da7ba 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -5,6 +5,7 @@
 
 #include <asm/cpu_entry_area.h>
 #include <asm/perf_event.h>
+#include <asm/tlbflush.h>
 #include <asm/insn.h>
 
 #include "../perf_event.h"
@@ -283,20 +284,35 @@ static DEFINE_PER_CPU(void *, insn_buffer);
 
 static void ds_update_cea(void *cea, void *addr, size_t size, pgprot_t prot)
 {
+	unsigned long start = (unsigned long)cea;
 	phys_addr_t pa;
 	size_t msz = 0;
 
 	pa = virt_to_phys(addr);
+
+	preempt_disable();
 	for (; msz < size; msz += PAGE_SIZE, pa += PAGE_SIZE, cea += PAGE_SIZE)
 		cea_set_pte(cea, pa, prot);
+
+	/*
+	 * This is a cross-CPU update of the cpu_entry_area, we must shoot down
+	 * all TLB entries for it.
+	 */
+	flush_tlb_kernel_range(start, start + size);
+	preempt_enable();
 }
 
 static void ds_clear_cea(void *cea, size_t size)
 {
+	unsigned long start = (unsigned long)cea;
 	size_t msz = 0;
 
+	preempt_disable();
 	for (; msz < size; msz += PAGE_SIZE, cea += PAGE_SIZE)
 		cea_set_pte(cea, 0, PAGE_NONE);
+
+	flush_tlb_kernel_range(start, start + size);
+	preempt_enable();
 }
 
 static void *dsalloc_pages(size_t size, gfp_t flags, int cpu)
diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h
index 8d0ec9df1cbe..44f5d79d5105 100644
--- a/arch/x86/include/asm/acpi.h
+++ b/arch/x86/include/asm/acpi.h
@@ -49,7 +49,7 @@ extern int acpi_fix_pin2_polarity;
 extern int acpi_disable_cmcff;
 
 extern u8 acpi_sci_flags;
-extern int acpi_sci_override_gsi;
+extern u32 acpi_sci_override_gsi;
 void acpi_pic_sci_set_trigger(unsigned int, u16);
 
 struct device;
diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index dbfd0854651f..cf5961ca8677 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -140,7 +140,7 @@ static inline int alternatives_text_reserved(void *start, void *end)
 	".popsection\n"							\
 	".pushsection .altinstr_replacement, \"ax\"\n"			\
 	ALTINSTR_REPLACEMENT(newinstr, feature, 1)			\
-	".popsection"
+	".popsection\n"
 
 #define ALTERNATIVE_2(oldinstr, newinstr1, feature1, newinstr2, feature2)\
 	OLDINSTR_2(oldinstr, 1, 2)					\
@@ -151,7 +151,7 @@ static inline int alternatives_text_reserved(void *start, void *end)
 	".pushsection .altinstr_replacement, \"ax\"\n"			\
 	ALTINSTR_REPLACEMENT(newinstr1, feature1, 1)			\
 	ALTINSTR_REPLACEMENT(newinstr2, feature2, 2)			\
-	".popsection"
+	".popsection\n"
 
 /*
  * Alternative instructions for different CPU types or capabilities.
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 07cdd1715705..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 */
@@ -341,6 +343,8 @@
 #define X86_BUG_SWAPGS_FENCE		X86_BUG(11) /* SWAPGS without input dep on GS */
 #define X86_BUG_MONITOR			X86_BUG(12) /* IPI required to wake up remote CPU */
 #define X86_BUG_AMD_E400		X86_BUG(13) /* CPU is among the affected by Erratum 400 */
-#define X86_BUG_CPU_INSECURE		X86_BUG(14) /* CPU is insecure and needs kernel page table isolation */
+#define X86_BUG_CPU_MELTDOWN		X86_BUG(14) /* CPU is affected by meltdown attack and needs kernel page table isolation */
+#define X86_BUG_SPECTRE_V1		X86_BUG(15) /* CPU is affected by Spectre variant 1 attack with conditional branches */
+#define X86_BUG_SPECTRE_V2		X86_BUG(16) /* CPU is affected by Spectre variant 2 attack with indirect branches */
 
 #endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index 5400add2885b..8bf450b13d9f 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
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 34c4922bbc3f..e7b983a35506 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -355,6 +355,9 @@
 #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_DEC