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()

10 files changed, 302 insertions, 389 deletions

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 @@ static inline void write_cr2(unsigned long x)
 
 static inline unsigned long __read_cr3(void)
 {
-	return PVOP_CALL0(unsigned long, mmu.read_cr3);
+	return PVOP_ALT_CALL0(unsigned long, mmu.read_cr3,
+			      "mov %%cr3, %%rax;", ALT_NOT(X86_FEATURE_XENPV));
 }
 
 static inline void write_cr3(unsigned long x)
 {
-	PVOP_VCALL1(mmu.write_cr3, x);
+	PVOP_ALT_VCALL1(mmu.write_cr3, x,
+			"mov %%rdi, %%cr3", ALT_NOT(X86_FEATURE_XENPV));
 }
 
 static inline void __write_cr4(unsigned long x)
@@ -157,7 +174,7 @@ static inline void halt(void)
 
 static inline void wbinvd(void)
 {
-	PVOP_VCALL0(cpu.wbinvd);
+	PVOP_ALT_VCALL0(cpu.wbinvd, "wbinvd", ALT_NOT(X86_FEATURE_XENPV));
 }
 
 static inline u64 paravirt_read_msr(unsigned msr)
@@ -371,22 +388,28 @@ static inline void paravirt_release_p4d(unsigned long pfn)
 
 static inline pte_t __pte(pteval_t val)
 {
-	return (pte_t) { PVOP_CALLEE1(pteval_t, mmu.make_pte, val) };
+	return (pte_t) { PVOP_ALT_CALLEE1(pteval_t, mmu.make_pte, val,
+					  "mov %%rdi, %%rax",
+					  ALT_NOT(X86_FEATURE_XENPV)) };
 }
 
 static inline pteval_t pte_val(pte_t pte)
 {
-	return PVOP_CALLEE1(pteval_t, mmu.pte_val, pte.pte);
+	return PVOP_ALT_CALLEE1(pteval_t, mmu.pte_val, pte.pte,
+				"mov %%rdi, %%rax", ALT_NOT(X86_FEATURE_XENPV));
 }
 
 static inline pgd_t __pgd(pgdval_t val)
 {
-	return (pgd_t) { PVOP_CALLEE1(pgdval_t, mmu.make_pgd, val) };
+	return (pgd_t) { PVOP_ALT_CALLEE1(pgdval_t, mmu.make_pgd, val,
+					  "mov %%rdi, %%rax",
+					  ALT_NOT(X86_FEATURE_XENPV)) };
 }
 
 static inline pgdval_t pgd_val(pgd_t pgd)
 {
-	return PVOP_CALLEE1(pgdval_t, mmu.pgd_val, pgd.pgd);
+	return PVOP_ALT_CALLEE1(pgdval_t, mmu.pgd_val, pgd.pgd,
+				"mov %%rdi, %%rax", ALT_NOT(X86_FEATURE_XENPV));
 }
 
 #define  __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION
@@ -419,12 +442,15 @@ static inline void set_pmd(pmd_t *pmdp, pmd_t pmd)
 
 static inline pmd_t __pmd(pmdval_t val)
 {
-	return (pmd_t) { PVOP_CALLEE1(pmdval_t, mmu.make_pmd, val) };
+	return (pmd_t) { PVOP_ALT_CALLEE1(pmdval_t, mmu.make_pmd, val,
+					  "mov %%rdi, %%rax",
+					  ALT_NOT(X86_FEATURE_XENPV)) };
 }
 
 static inline pmdval_t pmd_val(pmd_t pmd)
 {
-	return PVOP_CALLEE1(pmdval_t, mmu.pmd_val, pmd.pmd);
+	return PVOP_ALT_CALLEE1(pmdval_t, mmu.pmd_val, pmd.pmd,
+				"mov %%rdi, %%rax", ALT_NOT(X86_FEATURE_XENPV));
 }
 
 static inline void set_pud(pud_t *pudp, pud_t pud)
@@ -436,14 +462,16 @@ static inline pud_t __pud(pudval_t val)
 {
 	pudval_t ret;
 
-	ret = PVOP_CALLEE1(pudval_t, mmu.make_pud, val);
+	ret = PVOP_ALT_CALLEE1(pudval_t, mmu.make_pud, val,
+			       "mov %%rdi, %%rax", ALT_NOT(X86_FEATURE_XENPV));
 
 	return (pud_t) { ret };
 }
 
 static inline pudval_t pud_val(pud_t pud)
 {
-	return PVOP_CALLEE1(pudval_t, mmu.pud_val, pud.pud);
+	return PVOP_ALT_CALLEE1(pudval_t, mmu.pud_val, pud.pud,
+				"mov %%rdi, %%rax", ALT_NOT(X86_FEATURE_XENPV));
 }
 
 static inline void pud_clear(pud_t *pudp)
@@ -462,14 +490,17 @@ static inline void set_p4d(p4d_t *p4dp, p4d_t p4d)
 
 static inline p4d_t __p4d(p4dval_t val)
 {
-	p4dval_t ret = PVOP_CALLEE1(p4dval_t, mmu.make_p4d, val);
+	p4dval_t ret = PVOP_ALT_CALLEE1(p4dval_t, mmu.make_p4d, val,
+					"mov %%rdi, %%rax",
+					ALT_NOT(X86_FEATURE_XENPV));
 
 	return (p4d_t) { ret };
 }
 
 static inline p4dval_t p4d_val(p4d_t p4d)
 {
-	return PVOP_CALLEE1(p4dval_t, mmu.p4d_val, p4d.p4d);
+	return PVOP_ALT_CALLEE1(p4dval_t, mmu.p4d_val, p4d.p4d,
+				"mov %%rdi, %%rax", ALT_NOT(X86_FEATURE_XENPV));
 }
 
 static inline void __set_pgd(pgd_t *pgdp, pgd_t pgd)
@@ -556,7 +587,9 @@ static __always_inline void pv_queued_spin_lock_slowpath(struct qspinlock *lock,
 
 static __always_inline void pv_queued_spin_unlock(struct qspinlock *lock)
 {
-	PVOP_VCALLEE1(lock.queued_spin_unlock, lock);
+	PVOP_ALT_VCALLEE1(lock.queued_spin_unlock, lock,
+			  "movb $0, (%%" _ASM_ARG1 ");",
+			  ALT_NOT(X86_FEATURE_PVUNLOCK));
 }
 
 static __always_inline void pv_wait(u8 *ptr, u8 val)
@@ -571,7 +604,9 @@ static __always_inline void pv_kick(int cpu)
 
 static __always_inline bool pv_vcpu_is_preempted(long cpu)
 {
-	return PVOP_CALLEE1(bool, lock.vcpu_is_preempted, cpu);
+	return PVOP_ALT_CALLEE1(bool, lock.vcpu_is_preempted, cpu,
+				"xor %%" _ASM_AX ", %%" _ASM_AX ";",
+				ALT_NOT(X86_FEATURE_VCPUPREEMPT));
 }
 
 void __raw_callee_save___native_queued_spin_unlock(struct qspinlock *lock);
@@ -645,17 +680,18 @@ bool __raw_callee_save___native_vcpu_is_preempted(long cpu);
 #ifdef CONFIG_PARAVIRT_XXL
 static inline notrace unsigned long arch_local_save_flags(void)
 {
-	return PVOP_CALLEE0(unsigned long, irq.save_fl);
+	return PVOP_ALT_CALLEE0(unsigned long, irq.save_fl, "pushf; pop %%rax;",
+				ALT_NOT(X86_FEATURE_XENPV));
 }
 
 static inline notrace void arch_local_irq_disable(void)
 {
-	PVOP_VCALLEE0(irq.irq_disable);
+	PVOP_ALT_VCALLEE0(irq.irq_disable, "cli;", ALT_NOT(X86_FEATURE_XENPV));
 }
 
 static inline notrace void arch_local_irq_enable(void)
 {
-	PVOP_VCALLEE0(irq.irq_enable);
+	PVOP_ALT_VCALLEE0(irq.irq_enable, "sti;", ALT_NOT(X86_FEATURE_XENPV));
 }
 
 static inline notrace unsigned long arch_local_irq_save(void)
@@ -700,84 +736,27 @@ extern void default_banner(void);
 	.popsection
 
 
-#define COND_PUSH(set, mask, reg)			\
-	.if ((~(set)) & mask); push %reg; .endif
-#define COND_POP(set, mask, reg)			\
-	.if ((~(set)) & mask); pop %reg; .endif
-
 #ifdef CONFIG_X86_64
-
-#define PV_SAVE_REGS(set)			\
-	COND_PUSH(set, CLBR_RAX, rax);		\
-	COND_PUSH(set, CLBR_RCX, rcx);		\
-	COND_PUSH(set, CLBR_RDX, rdx);		\
-	COND_PUSH(set, CLBR_RSI, rsi);		\
-	COND_PUSH(set, CLBR_RDI, rdi);		\
-	COND_PUSH(set, CLBR_R8, r8);		\
-	COND_PUSH(set, CLBR_R9, r9);		\
-	COND_PUSH(set, CLBR_R10, r10);		\
-	COND_PUSH(set, CLBR_R11, r11)
-#define PV_RESTORE_REGS(set)			\
-	COND_POP(set, CLBR_R11, r11);		\
-	COND_POP(set, CLBR_R10, r10);		\
-	COND_POP(set, CLBR_R9, r9);		\
-	COND_POP(set, CLBR_R8, r8);		\
-	COND_POP(set, CLBR_RDI, rdi);		\
-	COND_POP(set, CLBR_RSI, rsi);		\
-	COND_POP(set, CLBR_RDX, rdx);		\
-	COND_POP(set, CLBR_RCX, rcx);		\
-	COND_POP(set, CLBR_RAX, rax)
+#ifdef CONFIG_PARAVIRT_XXL
 
 #define PARA_PATCH(off)		((off) / 8)
 #define PARA_SITE(ptype, ops)	_PVSITE(ptype, ops, .quad, 8)
 #define PARA_INDIRECT(addr)	*addr(%rip)
-#else
-#define PV_SAVE_REGS(set)			\
-	COND_PUSH(set, CLBR_EAX, eax);		\
-	COND_PUSH(set, CLBR_EDI, edi);		\
-	COND_PUSH(set, CLBR_ECX, ecx);		\
-	COND_PUSH(set, CLBR_EDX, edx)
-#define PV_RESTORE_REGS(set)			\
-	COND_POP(set, CLBR_EDX, edx);		\
-	COND_POP(set, CLBR_ECX, ecx);		\
-	COND_POP(set, CLBR_EDI, edi);		\
-	COND_POP(set, CLBR_EAX, eax)
-
-#define PARA_PATCH(off)		((off) / 4)
-#define PARA_SITE(ptype, ops)	_PVSITE(ptype, ops, .long, 4)
-#define PARA_INDIRECT(addr)	*%cs:addr
-#endif
 
-#ifdef CONFIG_PARAVIRT_XXL
 #define INTERRUPT_RETURN						\
-	PARA_SITE(PARA_PATCH(PV_CPU_iret),				\
-		  ANNOTATE_RETPOLINE_SAFE;				\
-		  jmp PARA_INDIRECT(pv_ops+PV_CPU_iret);)
-
-#define DISABLE_INTERRUPTS(clobbers)					\
-	PARA_SITE(PARA_PATCH(PV_IRQ_irq_disable),			\
-		  PV_SAVE_REGS(clobbers | CLBR_CALLEE_SAVE);		\
-		  ANNOTATE_RETPOLINE_SAFE;				\
-		  call PARA_INDIRECT(pv_ops+PV_IRQ_irq_disable);	\
-		  PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);)
-
-#define ENABLE_INTERRUPTS(clobbers)					\
-	PARA_SITE(PARA_PATCH(PV_IRQ_irq_enable),			\
-		  PV_SAVE_REGS(clobbers | CLBR_CALLEE_SAVE);		\
-		  ANNOTATE_RETPOLINE_SAFE;				\
-		  call PARA_INDIRECT(pv_ops+PV_IRQ_irq_enable);		\
-		  PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);)
-#endif
+	ANNOTATE_RETPOLINE_SAFE;					\
+	ALTERNATIVE_TERNARY("jmp *paravirt_iret(%rip);",		\
+		X86_FEATURE_XENPV, "jmp xen_iret;", "jmp native_iret;")
 
-#ifdef CONFIG_X86_64
-#ifdef CONFIG_PARAVIRT_XXL
 #ifdef CONFIG_DEBUG_ENTRY
-#define SAVE_FLAGS(clobbers)                                        \
-	PARA_SITE(PARA_PATCH(PV_IRQ_save_fl),			    \
-		  PV_SAVE_REGS(clobbers | CLBR_CALLEE_SAVE);        \
-		  ANNOTATE_RETPOLINE_SAFE;			    \
-		  call PARA_INDIRECT(pv_ops+PV_IRQ_save_fl);	    \
-		  PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);)
+.macro PARA_IRQ_save_fl
+	PARA_SITE(PARA_PATCH(PV_IRQ_save_fl),
+		  ANNOTATE_RETPOLINE_SAFE;
+		  call PARA_INDIRECT(pv_ops+PV_IRQ_save_fl);)
+.endm
+
+#define SAVE_FLAGS	ALTERNATIVE "PARA_IRQ_save_fl;", "pushf; pop %rax;", \
+				    ALT_NOT(X86_FEATURE_XENPV)
 #endif
 #endif /* CONFIG_PARAVIRT_XXL */
 #endif	/* CONFIG_X86_64 */
@@ -800,5 +779,11 @@ static inline void paravirt_arch_exit_mmap(struct mm_struct *mm)
 {
 }
 #endif
+
+#ifndef CONFIG_PARAVIRT_SPINLOCKS
+static inline void paravirt_set_cap(void)
+{
+}
+#endif
 #endif /* __ASSEMBLY__ */
 #endif /* _ASM_X86_PARAVIRT_H */
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index de87087d3bde..9d1ddb7b4350 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -3,7 +3,6 @@
 #define _ASM_X86_PARAVIRT_TYPES_H
 
 /* Bitmask of what can be clobbered: usually at least eax. */
-#define CLBR_NONE 0
 #define CLBR_EAX  (1 << 0)
 #define CLBR_ECX  (1 << 1)
 #define CLBR_EDX  (1 << 2)
@@ -15,7 +14,6 @@
 
 #define CLBR_ARG_REGS	(CLBR_EAX | CLBR_EDX | CLBR_ECX)
 #define CLBR_RET_REG	(CLBR_EAX | CLBR_EDX)
-#define CLBR_SCRATCH	(0)
 #else
 #define CLBR_RAX  CLBR_EAX
 #define CLBR_RCX  CLBR_ECX
@@ -32,12 +30,9 @@
 #define CLBR_ARG_REGS	(CLBR_RDI | CLBR_RSI | CLBR_RDX | \
 			 CLBR_RCX | CLBR_R8 | CLBR_R9)
 #define CLBR_RET_REG	(CLBR_RAX)
-#define CLBR_SCRATCH	(CLBR_R10 | CLBR_R11)
 
 #endif /* X86_64 */
 
-#define CLBR_CALLEE_SAVE ((CLBR_ARG_REGS | CLBR_SCRATCH) & ~CLBR_RET_REG)
-
 #ifndef __ASSEMBLY__
 
 #include <asm/desc_defs.h>
@@ -73,19 +68,6 @@ struct pv_info {
 	const char *name;
 };
 
-struct pv_init_ops {
-	/*
-	 * Patch may replace one of the defined code sequences with
-	 * arbitrary code, subject to the same register constraints.
-	 * This generally means the code is not free to clobber any
-	 * registers other than EAX.  The patch function should return
-	 * the number of bytes of code generated, as we nop pad the
-	 * rest in generic code.
-	 */
-	unsigned (*patch)(u8 type, void *insn_buff,
-			  unsigned long addr, unsigned len);
-} __no_randomize_layout;
-
 #ifdef CONFIG_PARAVIRT_XXL
 struct pv_lazy_ops {
 	/* Set deferred update mode, used for batching operations. */
@@ -95,11 +77,6 @@ struct pv_lazy_ops {
 } __no_randomize_layout;
 #endif
 
-struct pv_time_ops {
-	unsigned long long (*sched_clock)(void);
-	unsigned long long (*steal_clock)(int cpu);
-} __no_randomize_layout;
-
 struct pv_cpu_ops {
 	/* hooks for various privileged instructions */
 	void (*io_delay)(void);
@@ -156,10 +133,6 @@ struct pv_cpu_ops {
 
 	u64 (*read_pmc)(int counter);
 
-	/* Normal iret.  Jump to this with the standard iret stack
-	   frame set up. */
-	void (*iret)(void);
-
 	void (*start_context_switch)(struct task_struct *prev);
 	void (*end_context_switch)(struct task_struct *next);
 #endif
@@ -290,8 +263,6 @@ struct pv_lock_ops {
  * number for each function using the offset which we use to indicate
  * what to patch. */
 struct paravirt_patch_template {
-	struct pv_init_ops	init;
-	struct pv_time_ops	time;
 	struct pv_cpu_ops	cpu;
 	struct pv_irq_ops	irq;
 	struct pv_mmu_ops	mmu;
@@ -300,6 +271,7 @@ struct paravirt_patch_template {
 
 extern struct pv_info pv_info;
 extern struct paravirt_patch_template pv_ops;
+extern void (*paravirt_iret)(void);
 
 #define PARAVIRT_PATCH(x)					\
 	(offsetof(struct paravirt_patch_template, x) / sizeof(void *))
@@ -331,11 +303,7 @@ extern struct paravirt_patch_template pv_ops;
 /* Simple instruction patching code. */
 #define NATIVE_LABEL(a,x,b) "\n\t.globl " a #x "_" #b "\n" a #x "_" #b ":\n\t"
 
-unsigned paravirt_patch_ident_64(void *insn_buff, unsigned len);
-unsigned paravirt_patch_default(u8 type, void *insn_buff, unsigned long addr, unsigned len);
-unsigned paravirt_patch_insns(void *insn_buff, unsigned len, const char *start, const char *end);
-
-unsigned native_patch(u8 type, void *insn_buff, unsigned long addr, unsigned len);
+unsigned int paravirt_patch(u8 type, void *insn_buff, unsigned long addr, unsigned int len);
 
 int paravirt_disable_iospace(void);
 
@@ -414,11 +382,9 @@ int paravirt_disable_iospace(void);
  * makes sure the incoming and outgoing types are always correct.
  */
 #ifdef CONFIG_X86_32
-#define PVOP_VCALL_ARGS							\
+#define PVOP_CALL_ARGS							\
 	unsigned long __eax = __eax, __edx = __edx, __ecx = __ecx;
 
-#define PVOP_CALL_ARGS			PVOP_VCALL_ARGS
-
 #define PVOP_CALL_ARG1(x)		"a" ((unsigned long)(x))
 #define PVOP_CALL_ARG2(x)		"d" ((unsigned long)(x))
 #define PVOP_CALL_ARG3(x)		"c" ((unsigned long)(x))
@@ -434,12 +400,10 @@ int paravirt_disable_iospace(void);
 #define VEXTRA_CLOBBERS
 #else  /* CONFIG_X86_64 */
 /* [re]ax isn't an arg, but the return val */
-#define PVOP_VCALL_ARGS						\
+#define PVOP_CALL_ARGS						\
 	unsigned long __edi = __edi, __esi = __esi,		\
 		__edx = __edx, __ecx = __ecx, __eax = __eax;
 
-#define PVOP_CALL_ARGS		PVOP_VCALL_ARGS
-
 #define PVOP_CALL_ARG1(x)		"D" ((unsigned long)(x))
 #define PVOP_CALL_ARG2(x)		"S" ((unsigned long)(x))
 #define PVOP_CALL_ARG3(x)		"d" ((unsigned long)(x))
@@ -464,152 +428,138 @@ int paravirt_disable_iospace(void);
 #define PVOP_TEST_NULL(op)	((void)pv_ops.op)
 #endif
 
-#define PVOP_RETMASK(rettype)						\
+#define PVOP_RETVAL(rettype)						\
 	({	unsigned long __mask = ~0UL;				\
+		BUILD_BUG_ON(sizeof(rettype) > sizeof(unsigned long));	\
 		switch (sizeof(rettype)) {				\
 		case 1: __mask =       0xffUL; break;			\
 		case 2: __mask =     0xffffUL; break;			\
 		case 4: __mask = 0xffffffffUL; break;			\
 		default: break;						\
 		}							\
-		__mask;							\
+		__mask & __eax;						\
 	})
 
 
-#define ____PVOP_CALL(rettype, op, clbr, call_clbr, extra_clbr,		\
-		      pre, post, ...)					\
+#define ____PVOP_CALL(ret, op, clbr, call_clbr, extra_clbr, ...)	\
 	({								\
-		rettype __ret;						\
 		PVOP_CALL_ARGS;						\
 		PVOP_TEST_NULL(op);					\
-		/* This is 32-bit specific, but is okay in 64-bit */	\
-		/* since this condition will never hold */		\
-		if (sizeof(rettype) > sizeof(unsigned long)) {		\
-			asm volatile(pre				\
-				     paravirt_alt(PARAVIRT_CALL)	\
-				     post				\
-				     : call_clbr, ASM_CALL_CONSTRAINT	\
-				     : paravirt_type(op),		\
-				       paravirt_clobber(clbr),		\
-				       ##__VA_ARGS__			\
-				     : "memory", "cc" extra_clbr);	\
-			__ret = (rettype)((((u64)__edx) << 32) | __eax); \
-		} else {						\
-			asm volatile(pre				\
-				     paravirt_alt(PARAVIRT_CALL)	\
-				     post				\
-				     : call_clbr, ASM_CALL_CONSTRAINT	\
-				     : paravirt_type(op),		\
-				       paravirt_clobber(clbr),		\
-				       ##__VA_ARGS__			\
-				     : "memory", "cc" extra_clbr);	\
-			__ret = (rettype)(__eax & PVOP_RETMASK(rettype));	\
-		}							\
-		__ret;							\
+		asm volatile(paravirt_alt(PARAVIRT_CALL)		\
+			     : call_clbr, ASM_CALL_CONSTRAINT		\
+			     : paravirt_type(op),			\
+			       paravirt_clobber(clbr),			\
+			       ##__VA_ARGS__				\
+			     : "memory", "cc" extra_clbr);		\
+		ret;							\
 	})
 
-#define __PVOP_CALL(rettype, op, pre, post, ...)			\
-	____PVOP_CALL(rettype, op, CLBR_ANY, PVOP_CALL_CLOBBERS,	\
-		      EXTRA_CLOBBERS, pre, post, ##__VA_ARGS__)
-
-#define __PVOP_CALLEESAVE(rettype, op, pre, post, ...)			\
-	____PVOP_CALL(rettype, op.func, CLBR_RET_REG,			\
-		      PVOP_CALLEE_CLOBBERS, ,				\
-		      pre, post, ##__VA_ARGS__)
-
-
-#define ____PVOP_VCALL(op, clbr, call_clbr, extra_clbr, pre, post, ...)	\
+#define ____PVOP_ALT_CALL(ret, op, alt, cond, clbr, call_clbr,		\
+			  extra_clbr, ...)				\
 	({								\
-		PVOP_VCALL_ARGS;					\
+		PVOP_CALL_ARGS;						\
 		PVOP_TEST_NULL(op);					\
-		asm volatile(pre					\
-			     paravirt_alt(PARAVIRT_CALL)		\
-			     post					\
+		asm volatile(ALTERNATIVE(paravirt_alt(PARAVIRT_CALL),	\
+					 alt, cond)			\
 			     : call_clbr, ASM_CALL_CONSTRAINT		\
 			     : paravirt_type(op),			\
 			       paravirt_clobber(clbr),			\
 			       ##__VA_ARGS__				\
 			     : "memory", "cc" extra_clbr);		\
+		ret;							\
 	})
 
-#define __PVOP_VCALL(op, pre, post, ...)				\
-	____PVOP_VCALL(op, CLBR_ANY, PVOP_VCALL_CLOBBERS,		\
-		       VEXTRA_CLOBBERS,					\
-		       pre, post, ##__VA_ARGS__)
+#define __PVOP_CALL(rettype, op, ...)					\
+	____PVOP_CALL(PVOP_RETVAL(rettype), op, CLBR_ANY,		\
+		      PVOP_CALL_CLOBBERS, EXTRA_CLOBBERS, ##__VA_ARGS__)
+
+#define __PVOP_ALT_CALL(rettype, op, alt, cond, ...)			\
+	____PVOP_ALT_CALL(PVOP_RETVAL(rettype), op, alt, cond, CLBR_ANY,\
+			  PVOP_CALL_CLOBBERS, EXTRA_CLOBBERS,		\
+			  ##__VA_ARGS__)
+
+#define __PVOP_CALLEESAVE(rettype, op, ...)				\
+	____PVOP_CALL(PVOP_RETVAL(rettype), op.func, CLBR_RET_REG,	\
+		      PVOP_CALLEE_CLOBBERS, , ##__VA_ARGS__)
+
+#define __PVOP_ALT_CALLEESAVE(rettype, op, alt, cond, ...)		\
+	____PVOP_ALT_CALL(PVOP_RETVAL(rettype), op.func, alt, cond,	\
+			  CLBR_RET_REG, PVOP_CALLEE_CLOBBERS, , ##__VA_ARGS__)
+
+
+#define __PVOP_VCALL(op, ...)						\
+	(void)____PVOP_CALL(, op, CLBR_ANY, PVOP_VCALL_CLOBBERS,	\
+		       VEXTRA_CLOBBERS, ##__VA_ARGS__)
+
+#define __PVOP_ALT_VCALL(op, alt, cond, ...)				\
+	(void)____PVOP_ALT_CALL(, op, alt, cond, CLBR_ANY,		\
+				PVOP_VCALL_CLOBBERS, VEXTRA_CLOBBERS,	\
+				##__VA_ARGS__)
 
-#define __PVOP_VCALLEESAVE(op, pre, post, ...)				\
-	____PVOP_VCALL(op.func, CLBR_RET_REG,				\
-		      PVOP_VCALLEE_CLOBBERS, ,				\
-		      pre, post, ##__VA_ARGS__)
+#define __PVOP_VCALLEESAVE(op, ...)					\
+	(void)____PVOP_CALL(, op.func, CLBR_RET_REG,			\
+			    PVOP_VCALLEE_CLOBBERS, , ##__VA_ARGS__)
 
+#define __PVOP_ALT_VCALLEESAVE(op, alt, cond, ...)			\
+	(void)____PVOP_ALT_CALL(, op.func, alt, cond, CLBR_RET_REG,	\
+				PVOP_VCALLEE_CLOBBERS, , ##__VA_ARGS__)
 
 
 #define PVOP_CALL0(rettype, op)						\
-	__PVOP_CALL(rettype, op, "", "")
+	__PVOP_CALL(rettype, op)
 #define PVOP_VCALL0(op)							\
-	__PVOP_VCALL(op, "", "")
+	__PVOP_VCALL(op)
+#define PVOP_ALT_CALL0(rettype, op, alt, cond)				\
+	__PVOP_ALT_CALL(rettype, op, alt, cond)
+#define PVOP_ALT_VCALL0(op, alt, cond)					\
+	__PVOP_ALT_VCALL(op, alt, cond)
 
 #define PVOP_CALLEE0(rettype, op)					\
-	__PVOP_CALLEESAVE(rettype, op, "", "")
+	__PVOP_CALLEESAVE(rettype, op)
 #define PVOP_VCALLEE0(op)						\
-	__PVOP_VCALLEESAVE(op, "", "")
+	__PVOP_VCALLEESAVE(op)
+#define PVOP_ALT_CALLEE0(rettype, op, alt, cond)			\
+	__PVOP_ALT_CALLEESAVE(rettype, op, alt, cond)
+#define PVOP_ALT_VCALLEE0(op, alt, cond)				\
+	__PVOP_ALT_VCALLEESAVE(op, alt, cond)
 
 
 #define PVOP_CALL1(rettype, op, arg1)					\
-	__PVOP_CALL(rettype, op, "", "", PVOP_CALL_ARG1(arg1))
+	__PVOP_CALL(rettype, op, PVOP_CALL_ARG1(arg1))
 #define PVOP_VCALL1(op, arg1)						\
-	__PVOP_VCALL(op, "", "", PVOP_CALL_ARG1(arg1))
+	__PVOP_VCALL(op, PVOP_CALL_ARG1(arg1))
+#define PVOP_ALT_VCALL1(op, arg1, alt, cond)				\
+	__PVOP_ALT_VCALL(op, alt, cond, PVOP_CALL_ARG1(arg1))
 
 #define PVOP_CALLEE1(rettype, op, arg1)					\
-	__PVOP_CALLEESAVE(rettype, op, "", "", PVOP_CALL_ARG1(arg1))
+	__PVOP_CALLEESAVE(rettype, op, PVOP_CALL_ARG1(arg1))
 #define PVOP_VCALLEE1(op, arg1)						\
-	__PVOP_VCALLEESAVE(op, "", "", PVOP_CALL_ARG1(arg1))
+	__PVOP_VCALLEESAVE(op, PVOP_CALL_ARG1(arg1))
+#define PVOP_ALT_CALLEE1(rettype, op, arg1, alt, cond)			\
+	__PVOP_ALT_CALLEESAVE(rettype, op, alt, cond, PVOP_CALL_ARG1(arg1))
+#define PVOP_ALT_VCALLEE1(op, arg1, alt, cond)				\
+	__PVOP_ALT_VCALLEESAVE(op, alt, cond, PVOP_CALL_ARG1(arg1))
 
 
 #define PVOP_CALL2(rettype, op, arg1, arg2)				\
-	__PVOP_CALL(rettype, op, "", "", PVOP_CALL_ARG1(arg1),		\
-		    PVOP_CALL_ARG2(arg2))
+	__PVOP_CALL(rettype, op, PVOP_CALL_ARG1(arg1), PVOP_CALL_ARG2(arg2))
 #define PVOP_VCALL2(op, arg1, arg2)					\
-	__PVOP_VCALL(op, "", "", PVOP_CALL_ARG1(arg1),			\
-		     PVOP_CALL_ARG2(arg2))
-
-#define PVOP_CALLEE2(rettype, op, arg1, arg2)				\
-	__PVOP_CALLEESAVE(rettype, op, "", "", PVOP_CALL_ARG1(arg1),	\
-			  PVOP_CALL_ARG2(arg2))
-#define PVOP_VCALLEE2(op, arg1, arg2)					\
-	__PVOP_VCALLEESAVE(op, "", "", PVOP_CALL_ARG1(arg1),		\
-			   PVOP_CALL_ARG2(arg2))
-
+	__PVOP_VCALL(op, PVOP_CALL_ARG1(arg1), PVOP_CALL_ARG2(arg2))
 
 #define PVOP_CALL3(rettype, op, arg1, arg2, arg3)			\
-	__PVOP_CALL(rettype, op, "", "", PVOP_CALL_ARG1(arg1),		\
+	__PVOP_CALL(rettype, op, PVOP_CALL_ARG1(arg1),			\
 		    PVOP_CALL_ARG2(arg2), PVOP_CALL_ARG3(arg3))
 #define PVOP_VCALL3(op, arg1, arg2, arg3)				\
-	__PVOP_VCALL(op, "", "", PVOP_CALL_ARG1(arg1),			\
+	__PVOP_VCALL(op, PVOP_CALL_ARG1(arg1),				\
 		     PVOP_CALL_ARG2(arg2), PVOP_CALL_ARG3(arg3))
 
-/* This is the only difference in x86_64. We can make it much simpler */
-#ifdef CONFIG_X86_32
 #define PVOP_CALL4(rettype, op, arg1, arg2, arg3, arg4)			\
 	__PVOP_CALL(rettype, op,					\
-		    "push %[_arg4];", "lea 4(%%esp),%%esp;",		\
-		    PVOP_CALL_ARG1(arg1), PVOP_CALL_ARG2(arg2),		\
-		    PVOP_CALL_ARG3(arg3), [_arg4] "mr" ((u32)(arg4)))
-#define PVOP_VCALL4(op, arg1, arg2, arg3, arg4)				\
-	__PVOP_VCALL(op,						\
-		    "push %[_arg4];", "lea 4(%%esp),%%esp;",		\
-		    "0" ((u32)(arg1)), "1" ((u32)(arg2)),		\
-		    "2" ((u32)(arg3)), [_arg4] "mr" ((u32)(arg4)))
-#else
-#define PVOP_CALL4(rettype, op, arg1, arg2, arg3, arg4)			\
-	__PVOP_CALL(rettype, op, "", "",				\
 		    PVOP_CALL_ARG1(arg1), PVOP_CALL_ARG2(arg2),		\
 		    PVOP_CALL_ARG3(arg3), PVOP_CALL_ARG4(arg4))
 #define PVOP_VCALL4(op, arg1, arg2, arg3, arg4)				\
-	__PVOP_VCALL(op, "", "",					\
-		     PVOP_CALL_ARG1(arg1), PVOP_CALL_ARG2(arg2),	\
+	__PVOP_VCALL(op, PVOP_CALL_ARG1(arg1), PVOP_CALL_ARG2(arg2),	\
 		     PVOP_CALL_ARG3(arg3), PVOP_CALL_ARG4(arg4))
-#endif
 
 /* Lazy mode for batching updates / context switch */
 enum paravirt_lazy_mode {
diff --git a/arch/x86/include/asm/smap.h b/arch/x86/include/asm/smap.h
index 0bc9b0895f33..d17b39893b79 100644
--- a/arch/x86/include/asm/smap.h
+++ b/arch/x86/include/asm/smap.h
@@ -11,6 +11,7 @@
 
 #include <asm/nops.h>
 #include <asm/cpufeatures.h>
+#include <asm/alternative.h>
 
 /* "Raw" instruction opcodes */
 #define __ASM_CLAC	".byte 0x0f,0x01,0xca"
@@ -18,8 +19,6 @@
 
 #ifdef __ASSEMBLY__
 
-#include <asm/alternative-asm.h>
-
 #ifdef CONFIG_X86_SMAP
 
 #define ASM_CLAC \
@@ -37,8 +36,6 @@
 
 #else /* __ASSEMBLY__ */
 
-#include <asm/alternative.h>
-
 #ifdef CONFIG_X86_SMAP
 
 static __always_inline void clac(void)