Merge tag 'x86_alternatives_for_v5.13' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 alternatives/paravirt updates from Borislav Petkov:
 "First big cleanup to the paravirt infra to use alternatives and thus
  eliminate custom code patching.

  For that, the alternatives infrastructure is extended to accomodate
  paravirt's needs and, as a result, a lot of paravirt patching code
  goes away, leading to a sizeable cleanup and simplification.

  Work by Juergen Gross"

* tag 'x86_alternatives_for_v5.13' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/paravirt: Have only one paravirt patch function
  x86/paravirt: Switch functions with custom code to ALTERNATIVE
  x86/paravirt: Add new PVOP_ALT* macros to support pvops in ALTERNATIVEs
  x86/paravirt: Switch iret pvops to ALTERNATIVE
  x86/paravirt: Simplify paravirt macros
  x86/paravirt: Remove no longer needed 32-bit pvops cruft
  x86/paravirt: Add new features for paravirt patching
  x86/alternative: Use ALTERNATIVE_TERNARY() in _static_cpu_has()
  x86/alternative: Support ALTERNATIVE_TERNARY
  x86/alternative: Support not-feature
  x86/paravirt: Switch time pvops functions to use static_call()
  static_call: Add function to query current function
  static_call: Move struct static_call_key definition to static_call_types.h
  x86/alternative: Merge include files
  x86/alternative: Drop unused feature parameter from ALTINSTR_REPLACEMENT()

42 files changed, 482 insertions, 638 deletions

diff --git a/arch/arm/include/asm/paravirt.h b/arch/arm/include/asm/paravirt.h
index cdbf02d9c1d4..95d5b0d625cd 100644
--- a/arch/arm/include/asm/paravirt.h
+++ b/arch/arm/include/asm/paravirt.h
@@ -3,23 +3,19 @@
 #define _ASM_ARM_PARAVIRT_H
 
 #ifdef CONFIG_PARAVIRT
+#include <linux/static_call_types.h>
+
 struct static_key;
 extern struct static_key paravirt_steal_enabled;
 extern struct static_key paravirt_steal_rq_enabled;
 
-struct pv_time_ops {
-	unsigned long long (*steal_clock)(int cpu);
-};
-
-struct paravirt_patch_template {
-	struct pv_time_ops time;
-};
+u64 dummy_steal_clock(int cpu);
 
-extern struct paravirt_patch_template pv_ops;
+DECLARE_STATIC_CALL(pv_steal_clock, dummy_steal_clock);
 
 static inline u64 paravirt_steal_clock(int cpu)
 {
-	return pv_ops.time.steal_clock(cpu);
+	return static_call(pv_steal_clock)(cpu);
 }
 #endif
 
diff --git a/arch/arm/kernel/paravirt.c b/arch/arm/kernel/paravirt.c
index 4cfed91fe256..7dd9806369fb 100644
--- a/arch/arm/kernel/paravirt.c
+++ b/arch/arm/kernel/paravirt.c
@@ -9,10 +9,15 @@
 #include <linux/export.h>
 #include <linux/jump_label.h>
 #include <linux/types.h>
+#include <linux/static_call.h>
 #include <asm/paravirt.h>
 
 struct static_key paravirt_steal_enabled;
 struct static_key paravirt_steal_rq_enabled;
 
-struct paravirt_patch_template pv_ops;
-EXPORT_SYMBOL_GPL(pv_ops);
+static u64 native_steal_clock(int cpu)
+{
+	return 0;
+}
+
+DEFINE_STATIC_CALL(pv_steal_clock, native_steal_clock);
diff --git a/arch/arm64/include/asm/paravirt.h b/arch/arm64/include/asm/paravirt.h
index cf3a0fd7c1a7..9aa193e0e8f2 100644
--- a/arch/arm64/include/asm/paravirt.h
+++ b/arch/arm64/include/asm/paravirt.h
@@ -3,23 +3,19 @@
 #define _ASM_ARM64_PARAVIRT_H
 
 #ifdef CONFIG_PARAVIRT
+#include <linux/static_call_types.h>
+
 struct static_key;
 extern struct static_key paravirt_steal_enabled;
 extern struct static_key paravirt_steal_rq_enabled;
 
-struct pv_time_ops {
-	unsigned long long (*steal_clock)(int cpu);
-};
-
-struct paravirt_patch_template {
-	struct pv_time_ops time;
-};
+u64 dummy_steal_clock(int cpu);
 
-extern struct paravirt_patch_template pv_ops;
+DECLARE_STATIC_CALL(pv_steal_clock, dummy_steal_clock);
 
 static inline u64 paravirt_steal_clock(int cpu)
 {
-	return pv_ops.time.steal_clock(cpu);
+	return static_call(pv_steal_clock)(cpu);
 }
 
 int __init pv_time_init(void);
diff --git a/arch/arm64/kernel/paravirt.c b/arch/arm64/kernel/paravirt.c
index c07d7a034941..75fed4460407 100644
--- a/arch/arm64/kernel/paravirt.c
+++ b/arch/arm64/kernel/paravirt.c
@@ -18,6 +18,7 @@
 #include <linux/reboot.h>
 #include <linux/slab.h>
 #include <linux/types.h>
+#include <linux/static_call.h>
 
 #include <asm/paravirt.h>
 #include <asm/pvclock-abi.h>
@@ -26,8 +27,12 @@
 struct static_key paravirt_steal_enabled;
 struct static_key paravirt_steal_rq_enabled;
 
-struct paravirt_patch_template pv_ops;
-EXPORT_SYMBOL_GPL(pv_ops);
+static u64 native_steal_clock(int cpu)
+{
+	return 0;
+}
+
+DEFINE_STATIC_CALL(pv_steal_clock, native_steal_clock);
 
 struct pv_time_stolen_time_region {
 	struct pvclock_vcpu_stolen_time *kaddr;
@@ -45,7 +50,7 @@ static int __init parse_no_stealacc(char *arg)
 early_param("no-steal-acc", parse_no_stealacc);
 
 /* return stolen time in ns by asking the hypervisor */
-static u64 pv_steal_clock(int cpu)
+static u64 para_steal_clock(int cpu)
 {
 	struct pv_time_stolen_time_region *reg;
 
@@ -150,7 +155,7 @@ int __init pv_time_init(void)
 	if (ret)
 		return ret;
 
-	pv_ops.time.steal_clock = pv_steal_clock;
+	static_call_update(pv_steal_clock, para_steal_clock);
 
 	static_key_slow_inc(&paravirt_steal_enabled);
 	if (steal_acc)
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 2792879d398e..107acc403b3b 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -777,6 +777,7 @@ if HYPERVISOR_GUEST
 
 config PARAVIRT
 	bool "Enable paravirtualization code"
+	depends on HAVE_STATIC_CALL
 	help
 	  This changes the kernel so it can modify itself when it is run
 	  under a hypervisor, potentially improving performance significantly
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index df8c017e6161..96f084868ec7 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -40,7 +40,7 @@
 #include <asm/processor-flags.h>
 #include <asm/irq_vectors.h>
 #include <asm/cpufeatures.h>
-#include <asm/alternative-asm.h>
+#include <asm/alternative.h>
 #include <asm/asm.h>
 #include <asm/smap.h>
 #include <asm/frame.h>
@@ -430,7 +430,7 @@
 	 * will soon execute iret and the tracer was already set to
 	 * the irqstate after the IRET:
 	 */
-	DISABLE_INTERRUPTS(CLBR_ANY)
+	cli
 	lss	(%esp), %esp			/* switch to espfix segment */
 .Lend_\@:
 #endif /* CONFIG_X86_ESPFIX32 */
@@ -1077,7 +1077,7 @@ restore_all_switch_stack:
 	 * when returning from IPI handler and when returning from
 	 * scheduler to user-space.
 	 */
-	INTERRUPT_RETURN
+	iret
 
 .section .fixup, "ax"
 SYM_CODE_START(asm_iret_error)
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 400908dff42e..12e2e3cd58be 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -305,7 +305,7 @@ SYM_CODE_END(ret_from_fork)
 .macro DEBUG_ENTRY_ASSERT_IRQS_OFF
 #ifdef CONFIG_DEBUG_ENTRY
 	pushq %rax
-	SAVE_FLAGS(CLBR_RAX)
+	SAVE_FLAGS
 	testl $X86_EFLAGS_IF, %eax
 	jz .Lokay_\@
 	ud2
diff --git a/arch/x86/entry/vdso/vdso32/system_call.S b/arch/x86/entry/vdso/vdso32/system_call.S
index de1fff7188aa..d6a6080bade0 100644
--- a/arch/x86/entry/vdso/vdso32/system_call.S
+++ b/arch/x86/entry/vdso/vdso32/system_call.S
@@ -6,7 +6,7 @@
 #include <linux/linkage.h>
 #include <asm/dwarf2.h>
 #include <asm/cpufeatures.h>
-#include <asm/alternative-asm.h>
+#include <asm/alternative.h>
 
 	.text
 	.globl __kernel_vsyscall
diff --git a/arch/x86/include/asm/alternative-asm.h b/arch/x86/include/asm/alternative-asm.h
deleted file mode 100644
index 464034db299f..000000000000
--- a/arch/x86/include/asm/alternative-asm.h
+++ /dev/null
@@ -1,114 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_X86_ALTERNATIVE_ASM_H
-#define _ASM_X86_ALTERNATIVE_ASM_H
-
-#ifdef __ASSEMBLY__
-
-#include <asm/asm.h>
-
-#ifdef CONFIG_SMP
-	.macro LOCK_PREFIX
-672:	lock
-	.pushsection .smp_locks,"a"
-	.balign 4
-	.long 672b - .
-	.popsection
-	.endm
-#else
-	.macro LOCK_PREFIX
-	.endm
-#endif
-
-/*
- * objtool annotation to ignore the alternatives and only consider the original
- * instruction(s).
- */
-.macro ANNOTATE_IGNORE_ALTERNATIVE
-	.Lannotate_\@:
-	.pushsection .discard.ignore_alts
-	.long .Lannotate_\@ - .
-	.popsection
-.endm
-
-/*
- * Issue one struct alt_instr descriptor entry (need to put it into
- * the section .altinstructions, see below). This entry contains
- * enough information for the alternatives patching code to patch an
- * instruction. See apply_alternatives().
- */
-.macro altinstruction_entry orig alt feature orig_len alt_len pad_len
-	.long \orig - .
-	.long \alt - .
-	.word \feature
-	.byte \orig_len
-	.byte \alt_len
-	.byte \pad_len
-.endm
-
-/*
- * Define an alternative between two instructions. If @feature is
- * present, early code in apply_alternatives() replaces @oldinstr with
- * @newinstr. ".skip" directive takes care of proper instruction padding
- * in case @newinstr is longer than @oldinstr.
- */
-.macro ALTERNATIVE oldinstr, newinstr, feature
-140:
-	\oldinstr
-141:
-	.skip -(((144f-143f)-(141b-140b)) > 0) * ((144f-143f)-(141b-140b)),0x90
-142:
-
-	.pushsection .altinstructions,"a"
-	altinstruction_entry 140b,143f,\feature,142b-140b,144f-143f,142b-141b
-	.popsection
-
-	.pushsection .altinstr_replacement,"ax"
-143:
-	\newinstr
-144:
-	.popsection
-.endm
-
-#define old_len			141b-140b
-#define new_len1		144f-143f
-#define new_len2		145f-144f
-
-/*
- * gas compatible max based on the idea from:
- * http://graphics.stanford.edu/~seander/bithacks.html#IntegerMinOrMax
- *
- * The additional "-" is needed because gas uses a "true" value of -1.
- */
-#define alt_max_short(a, b)	((a) ^ (((a) ^ (b)) & -(-((a) < (b)))))
-
-
-/*
- * Same as ALTERNATIVE macro above but for two alternatives. If CPU
- * has @feature1, it replaces @oldinstr with @newinstr1. If CPU has
- * @feature2, it replaces @oldinstr with @feature2.
- */
-.macro ALTERNATIVE_2 oldinstr, newinstr1, feature1, newinstr2, feature2
-140:
-	\oldinstr
-141:
-	.skip -((alt_max_short(new_len1, new_len2) - (old_len)) > 0) * \
-		(alt_max_short(new_len1, new_len2) - (old_len)),0x90
-142:
-
-	.pushsection .altinstructions,"a"
-	altinstruction_entry 140b,143f,\feature1,142b-140b,144f-143f,142b-141b
-	altinstruction_entry 140b,144f,\feature2,142b-140b,145f-144f,142b-141b
-	.popsection
-
-	.pushsection .altinstr_replacement,"ax"
-143:
-	\newinstr1
-144:
-	\newinstr2
-145:
-	.popsection
-.endm
-
-#endif  /*  __ASSEMBLY__  */
-
-#endif /* _ASM_X86_ALTERNATIVE_ASM_H */
diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index 13adca37c99a..17b36090d448 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -2,13 +2,17 @@
 #ifndef _ASM_X86_ALTERNATIVE_H
 #define _ASM_X86_ALTERNATIVE_H
 
-#ifndef __ASSEMBLY__
-
 #include <linux/types.h>
-#include <linux/stddef.h>
 #include <linux/stringify.h>
 #include <asm/asm.h>
 
+#define ALTINSTR_FLAG_INV	(1 << 15)
+#define ALT_NOT(feat)		((feat) | ALTINSTR_FLAG_INV)
+
+#ifndef __ASSEMBLY__
+
+#include <linux/stddef.h>
+
 /*
  * Alternative inline assembly for SMP.
  *
@@ -150,7 +154,7 @@ static inline int alternatives_text_reserved(void *start, void *end)
 	" .byte " alt_rlen(num) "\n"			/* replacement len */ \
 	" .byte " alt_pad_len "\n"			/* pad len */
 
-#define ALTINSTR_REPLACEMENT(newinstr, feature, num)	/* replacement */	\
+#define ALTINSTR_REPLACEMENT(newinstr, num)		/* replacement */	\
 	"# ALT: replacement " #num "\n"						\
 	b_replacement(num)":\n\t" newinstr "\n" e_replacement(num) ":\n"
 
@@ -161,7 +165,7 @@ static inline int alternatives_text_reserved(void *start, void *end)
 	ALTINSTR_ENTRY(feature, 1)					\
 	".popsection\n"							\
 	".pushsection .altinstr_replacement, \"ax\"\n"			\
-	ALTINSTR_REPLACEMENT(newinstr, feature, 1)			\
+	ALTINSTR_REPLACEMENT(newinstr, 1)				\
 	".popsection\n"
 
 #define ALTERNATIVE_2(oldinstr, newinstr1, feature1, newinstr2, feature2)\
@@ -171,10 +175,15 @@ static inline int alternatives_text_reserved(void *start, void *end)
 	ALTINSTR_ENTRY(feature2, 2)					\
 	".popsection\n"							\
 	".pushsection .altinstr_replacement, \"ax\"\n"			\
-	ALTINSTR_REPLACEMENT(newinstr1, feature1, 1)			\
-	ALTINSTR_REPLACEMENT(newinstr2, feature2, 2)			\
+	ALTINSTR_REPLACEMENT(newinstr1, 1)				\
+	ALTINSTR_REPLACEMENT(newinstr2, 2)				\
 	".popsection\n"
 
+/* If @feature is set, patch in @newinstr_yes, otherwise @newinstr_no. */
+#define ALTERNATIVE_TERNARY(oldinstr, feature, newinstr_yes, newinstr_no) \
+	ALTERNATIVE_2(oldinstr, newinstr_no, X86_FEATURE_ALWAYS,	\
+		      newinstr_yes, feature)
+
 #define ALTERNATIVE_3(oldinsn, newinsn1, feat1, newinsn2, feat2, newinsn3, feat3) \
 	OLDINSTR_3(oldinsn, 1, 2, 3)						\
 	".pushsection .altinstructions,\"a\"\n"					\
@@ -183,9 +192,9 @@ static inline int alternatives_text_reserved(void *start, void *end)
 	ALTINSTR_ENTRY(feat3, 3)						\
 	".popsection\n"								\
 	".pushsection .altinstr_replacement, \"ax\"\n"				\
-	ALTINSTR_REPLACEMENT(newinsn1, feat1, 1)				\
-	ALTINSTR_REPLACEMENT(newinsn2, feat2, 2)				\
-	ALTINSTR_REPLACEMENT(newinsn3, feat3, 3)				\
+	ALTINSTR_REPLACEMENT(newinsn1, 1)					\
+	ALTINSTR_REPLACEMENT(newinsn2, 2)					\
+	ALTINSTR_REPLACEMENT(newinsn3, 3)					\
 	".popsection\n"
 
 /*
@@ -206,6 +215,9 @@ static inline int alternatives_text_reserved(void *start, void *end)
 #define alternative_2(oldinstr, newinstr1, feature1, newinstr2, feature2) \
 	asm_inline volatile(ALTERNATIVE_2(oldinstr, newinstr1, feature1, newinstr2, feature2) ::: "memory")
 
+#define alternative_ternary(oldinstr, feature, newinstr_yes, newinstr_no) \
+	asm_inline volatile(ALTERNATIVE_TERNARY(oldinstr, feature, newinstr_yes, newinstr_no) ::: "memory")
+
 /*
  * Alternative inline assembly with input.
  *
@@ -271,6 +283,116 @@ static inline int alternatives_text_reserved(void *start, void *end)
  */
 #define ASM_NO_INPUT_CLOBBER(clbr...) "i" (0) : clbr
 
+#else /* __ASSEMBLY__ */
+
+#ifdef CONFIG_SMP
+	.macro LOCK_PREFIX
+672:	lock
+	.pushsection .smp_locks,"a"
+	.balign 4
+	.long 672b - .
+	.popsection
+	.endm
+#else
+	.macro LOCK_PREFIX
+	.endm
+#endif
+
+/*
+ * objtool annotation to ignore the alternatives and only consider the original
+ * instruction(s).
+ */
+.macro ANNOTATE_IGNORE_ALTERNATIVE
+	.Lannotate_\@:
+	.pushsection .discard.ignore_alts
+	.long .Lannotate_\@ - .
+	.popsection
+.endm
+
+/*
+ * Issue one struct alt_instr descriptor entry (need to put it into
+ * the section .altinstructions, see below). This entry contains
+ * enough information for the alternatives patching code to patch an
+ * instruction. See apply_alternatives().
+ */
+.macro altinstruction_entry orig alt feature orig_len alt_len pad_len
+	.long \orig - .
+	.long \alt - .
+	.word \feature
+	.byte \orig_len
+	.byte \alt_len
+	.byte \pad_len
+.endm
+
+/*
+ * Define an alternative between two instructions. If @feature is
+ * present, early code in apply_alternatives() replaces @oldinstr with
+ * @newinstr. ".skip" directive takes care of proper instruction padding
+ * in case @newinstr is longer than @oldinstr.
+ */
+.macro ALTERNATIVE oldinstr, newinstr, feature
+140:
+	\oldinstr
+141:
+	.skip -(((144f-143f)-(141b-140b)) > 0) * ((144f-143f)-(141b-140b)),0x90
+142:
+
+	.pushsection .altinstructions,"a"
+	altinstruction_entry 140b,143f,\feature,142b-140b,144f-143f,142b-141b
+	.popsection
+
+	.pushsection .altinstr_replacement,"ax"
+143:
+	\newinstr
+144:
+	.popsection
+.endm
+
+#define old_len			141b-140b
+#define new_len1		144f-143f
+#define new_len2		145f-144f
+
+/*
+ * gas compatible max based on the idea from:
+ * http://graphics.stanford.edu/~seander/bithacks.html#IntegerMinOrMax
+ *
+ * The additional "-" is needed because gas uses a "true" value of -1.
+ */
+#define alt_max_short(a, b)	((a) ^ (((a) ^ (b)) & -(-((a) < (b)))))
+
+
+/*
+ * Same as ALTERNATIVE macro above but for two alternatives. If CPU
+ * has @feature1, it replaces @oldinstr with @newinstr1. If CPU has
+ * @feature2, it replaces @oldinstr with @feature2.
+ */
+.macro ALTERNATIVE_2 oldinstr, newinstr1, feature1, newinstr2, feature2
+140:
+	\oldinstr
+141:
+	.skip -((alt_max_short(new_len1, new_len2) - (old_len)) > 0) * \
+		(alt_max_short(new_len1, new_len2) - (old_len)),0x90
+142:
+
+	.pushsection .altinstructions,"a"
+	altinstruction_entry 140b,143f,\feature1,142b-140b,144f-143f,142b-141b
+	altinstruction_entry 140b,144f,\feature2,142b-140b,145f-144f,142b-141b
+	.popsection
+
+	.pushsection .altinstr_replacement,"ax"
+143:
+	\newinstr1
+144:
+	\newinstr2
+145:
+	.popsection
+.endm
+
+/* If @feature is set, patch in @newinstr_yes, otherwise @newinstr_no. */
+#define ALTERNATIVE_TERNARY(oldinstr, feature, newinstr_yes, newinstr_no) \
+	ALTERNATIVE_2 oldinstr, newinstr_no, X86_FEATURE_ALWAYS,	\
+	newinstr_yes, feature
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* _ASM_X86_ALTERNATIVE_H */
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 1728d4ce5730..16a51e7288d5 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -8,6 +8,7 @@
 
 #include <asm/asm.h>
 #include <linux/bitops.h>
+#include <asm/alternative.h>
 
 enum cpuid_leafs
 {
@@ -175,39 +176,15 @@ extern void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit);
  */
 static __always_inline bool _static_cpu_has(u16 bit)
 {
-	asm_volatile_goto("1: jmp 6f\n"
-		 "2:\n"
-		 ".skip -(((5f-4f) - (2b-1b)) > 0) * "
-			 "((5f-4f) - (2b-1b)),0x90\n"
-		 "3:\n"
-		 ".section .altinstructions,\"a\"\n"
-		 " .long 1b - .\n"		/* src offset */
-		 " .long 4f - .\n"		/* repl offset */
-		 " .word %P[always]\n"		/* always replace */
-		 " .byte 3b - 1b\n"		/* src len */
-		 " .byte 5f - 4f\n"		/* repl len */
-		 " .byte 3b - 2b\n"		/* pad len */
-		 ".previous\n"
-		 ".section .altinstr_replacement,\"ax\"\n"
-		 "4: jmp %l[t_no]\n"
-		 "5:\n"
-		 ".previous\n"
-		 ".section .altinstructions,\"a\"\n"
-		 " .long 1b - .\n"		/* src offset */
-		 " .long 0\n"			/* no replacement */
-		 " .word %P[feature]\n"		/* feature bit */
-		 " .byte 3b - 1b\n"		/* src len */
-		 " .byte 0\n"			/* repl len */
-		 " .byte 0\n"			/* pad len */
-		 ".previous\n"
-		 ".section .altinstr_aux,\"ax\"\n"
-		 "6:\n"
-		 " testb %[bitnum],%[cap_byte]\n"
-		 " jnz %l[t_yes]\n"
-		 " jmp %l[t_no]\n"
-		 ".previous\n"
+	asm_volatile_goto(
+		ALTERNATIVE_TERNARY("jmp 6f", %P[feature], "", "jmp %l[t_no]")
+		".section .altinstr_aux,\"ax\"\n"
+		"6:\n"
+		" testb %[bitnum],%[cap_byte]\n"
+		" jnz %l[t_yes]\n"
+		" jmp %l[t_no]\n"
+		".previous\n"
 		 : : [feature]  "i" (bit),
-		     [always]   "i" (X86_FEATURE_ALWAYS),
 		     [bitnum]   "i" (1 << (bit & 7)),
 		     [cap_byte] "m" (((const char *)boot_cpu_data.x86_capability)[bit >> 3])
 		 : : t_yes, t_no);
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index cc96e26d69f7..b440c950246d 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -236,6 +236,8 @@
 #define X86_FEATURE_EPT_AD		( 8*32+17) /* Intel Extended Page Table access-dirty bit */
 #define X86_FEATURE_VMCALL		( 8*32+18) /* "" Hypervisor supports the VMCALL instruction */
 #define X86_FEATURE_VMW_VMMCALL		( 8*32+19) /* "" VMware prefers VMMCALL hypercall instruction */
+#define X86_FEATURE_PVUNLOCK		( 8*32+20) /* "" PV unlock function */
+#define X86_FEATURE_VCPUPREEMPT		( 8*32+21) /* "" PV vcpu_is_preempted function */
 
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (EBX), word 9 */
 #define X86_FEATURE_FSGSBASE		( 9*32+ 0) /* RDFSBASE, WRFSBASE, RDGSBASE, WRGSBASE instructions*/
diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h
index 144d70ea4393..c5ce9845c999 100644
--- a/arch/x86/include/asm/irqflags.h
+++ b/arch/x86/include/asm/irqflags.h
@@ -109,18 +109,13 @@ static __always_inline unsigned long arch_local_irq_save(void)
 }
 #else
 
-#define ENABLE_INTERRUPTS(x)	sti
-#define DISABLE_INTERRUPTS(x)	cli
-
 #ifdef CONFIG_X86_64
 #ifdef CONFIG_DEBUG_ENTRY
-#define SAVE_FLAGS(x)		pushfq; popq %rax
+#define SAVE_FLAGS		pushfq; popq %rax
 #endif
 
 #define INTERRUPT_RETURN	jmp native_iret
 
-#else
-#define INTERRUPT_RETURN		iret
 #endif
 
 #endif /* __ASSEMBLY__ */
diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index ccf60a809a17..e7be720062a8 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -63,7 +63,7 @@ typedef int (*hyperv_fill_flush_list_func)(
 static __always_inline void hv_setup_sched_clock(void *sched_clock)
 {
 #ifdef CONFIG_PARAVIRT
-	pv_ops.time.sched_clock = sched_clock;
+	paravirt_set_sched_clock(sched_clock);
 #endif
 }
 
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index cb9ad6b73973..529f8e9380d8 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -7,7 +7,6 @@
 #include <linux/objtool.h>
 
 #include <asm/alternative.h>
-#include <asm/alternative-asm.h>
 #include <asm/cpufeatures.h>
 #include <asm/msr-index.h>
 #include <asm/unwind_hints.h>
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 4abf110e2243..43992e5c52c2 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -15,11 +15,20 @@
 #include <linux/bug.h>
 #include <linux/types.h>
 #include <linux/cpumask.h>
+#include <linux/static_call_types.h>
 #include <asm/frame.h>
 
-static inline unsigned long long paravirt_sched_clock(void)
+u64 dummy_steal_clock(int cpu);
+u64 dummy_sched_clock(void);
+
+DECLARE_STATIC_CALL(pv_steal_clock, dummy_steal_clock);
+DECLARE_STATIC_CALL(pv_sched_clock, dummy_sched_clock);
+
+void paravirt_set_sched_clock(u64 (*func)(void));
+
+static inline u64 paravirt_sched_clock(void)
 {
-	return PVOP_CALL0(unsigned long long, time.sched_clock);
+	return static_call(pv_sched_clock)();
 }
 
 struct static_key;
@@ -33,9 +42,13 @@ bool pv_is_native_vcpu_is_preempted(void);
 
 static inline u64 paravirt_steal_clock(int cpu)
 {
-	return PVOP_CALL1(u64, time.steal_clock, cpu);
+	return static_call(pv_steal_clock)(cpu);
 }
 
+#ifdef CONFIG_PARAVIRT_SPINLOCKS
+void __init paravirt_set_cap(void);
+#endif
+
 /* The paravirtualized I/O functions */
 static inline void slow_down_io(void)
 {
@@ -122,7 +135,9 @@ static inline void write_cr0(unsigned long x)
 
 static inline unsigned long read_cr2(void)
 {
-	return PVOP_CALLEE0(unsigned long, mmu.read_cr2);
+	return PVOP_ALT_CALLEE0(unsigned long, mmu.read_cr2,
+				"mov %%cr2, %%rax;",
+				ALT_NOT(X86_FEATURE_XENPV));
 }
 
 static inline void write_cr2(unsigned long x)
@@ -132,12 +147,14 @