Merge tag 'x86_paravirt_for_v6.8' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 paravirt updates from Borislav Petkov:

 - Replace the paravirt patching functionality using the alternatives
   infrastructure and remove the former

 - Misc other improvements

* tag 'x86_paravirt_for_v6.8' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/alternative: Correct feature bit debug output
  x86/paravirt: Remove no longer needed paravirt patching code
  x86/paravirt: Switch mixed paravirt/alternative calls to alternatives
  x86/alternative: Add indirect call patching
  x86/paravirt: Move some functions and defines to alternative.c
  x86/paravirt: Introduce ALT_NOT_XEN
  x86/paravirt: Make the struct paravirt_patch_site packed
  x86/paravirt: Use relative reference for the original instruction offset

5 files changed, 79 insertions, 133 deletions

diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index 65f79092c9d9..fcd20c6dc7f9 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -10,6 +10,9 @@
 
 #define ALT_FLAG_NOT		(1 << 0)
 #define ALT_NOT(feature)	((ALT_FLAG_NOT << ALT_FLAGS_SHIFT) | (feature))
+#define ALT_FLAG_DIRECT_CALL	(1 << 1)
+#define ALT_DIRECT_CALL(feature) ((ALT_FLAG_DIRECT_CALL << ALT_FLAGS_SHIFT) | (feature))
+#define ALT_CALL_ALWAYS		ALT_DIRECT_CALL(X86_FEATURE_ALWAYS)
 
 #ifndef __ASSEMBLY__
 
@@ -86,6 +89,8 @@ struct alt_instr {
 	u8  replacementlen;	/* length of new instruction */
 } __packed;
 
+extern struct alt_instr __alt_instructions[], __alt_instructions_end[];
+
 /*
  * Debug flag that can be tested to see whether alternative
  * instructions were patched in already:
@@ -101,11 +106,10 @@ extern void apply_fineibt(s32 *start_retpoline, s32 *end_retpoine,
 			  s32 *start_cfi, s32 *end_cfi);
 
 struct module;
-struct paravirt_patch_site;
 
 struct callthunk_sites {
 	s32				*call_start, *call_end;
-	struct paravirt_patch_site	*pv_start, *pv_end;
+	struct alt_instr		*alt_start, *alt_end;
 };
 
 #ifdef CONFIG_CALL_THUNKS
@@ -150,6 +154,8 @@ static inline int alternatives_text_reserved(void *start, void *end)
 }
 #endif	/* CONFIG_SMP */
 
+#define ALT_CALL_INSTR		"call BUG_func"
+
 #define b_replacement(num)	"664"#num
 #define e_replacement(num)	"665"#num
 
@@ -330,6 +336,22 @@ static inline int alternatives_text_reserved(void *start, void *end)
  */
 #define ASM_NO_INPUT_CLOBBER(clbr...) "i" (0) : clbr
 
+/* Macro for creating assembler functions avoiding any C magic. */
+#define DEFINE_ASM_FUNC(func, instr, sec)		\
+	asm (".pushsection " #sec ", \"ax\"\n"		\
+	     ".global " #func "\n\t"			\
+	     ".type " #func ", @function\n\t"		\
+	     ASM_FUNC_ALIGN "\n"			\
+	     #func ":\n\t"				\
+	     ASM_ENDBR					\
+	     instr "\n\t"				\
+	     ASM_RET					\
+	     ".size " #func ", . - " #func "\n\t"	\
+	     ".popsection")
+
+void BUG_func(void);
+void nop_func(void);
+
 #else /* __ASSEMBLY__ */
 
 #ifdef CONFIG_SMP
@@ -370,6 +392,10 @@ static inline int alternatives_text_reserved(void *start, void *end)
 	.byte \alt_len
 .endm
 
+.macro ALT_CALL_INSTR
+	call BUG_func
+.endm
+
 /*
  * Define an alternative between two instructions. If @feature is
  * present, early code in apply_alternatives() replaces @oldinstr with
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 6c8ff12140ae..8bcf7584e7dd 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -142,8 +142,7 @@ static inline void write_cr0(unsigned long x)
 static __always_inline unsigned long read_cr2(void)
 {
 	return PVOP_ALT_CALLEE0(unsigned long, mmu.read_cr2,
-				"mov %%cr2, %%rax;",
-				ALT_NOT(X86_FEATURE_XENPV));
+				"mov %%cr2, %%rax;", ALT_NOT_XEN);
 }
 
 static __always_inline void write_cr2(unsigned long x)
@@ -154,13 +153,12 @@ static __always_inline void write_cr2(unsigned long x)
 static inline unsigned long __read_cr3(void)
 {
 	return PVOP_ALT_CALL0(unsigned long, mmu.read_cr3,
-			      "mov %%cr3, %%rax;", ALT_NOT(X86_FEATURE_XENPV));
+			      "mov %%cr3, %%rax;", ALT_NOT_XEN);
 }
 
 static inline void write_cr3(unsigned long x)
 {
-	PVOP_ALT_VCALL1(mmu.write_cr3, x,
-			"mov %%rdi, %%cr3", ALT_NOT(X86_FEATURE_XENPV));
+	PVOP_ALT_VCALL1(mmu.write_cr3, x, "mov %%rdi, %%cr3", ALT_NOT_XEN);
 }
 
 static inline void __write_cr4(unsigned long x)
@@ -182,7 +180,7 @@ extern noinstr void pv_native_wbinvd(void);
 
 static __always_inline void wbinvd(void)
 {
-	PVOP_ALT_VCALL0(cpu.wbinvd, "wbinvd", ALT_NOT(X86_FEATURE_XENPV));
+	PVOP_ALT_VCALL0(cpu.wbinvd, "wbinvd", ALT_NOT_XEN);
 }
 
 static inline u64 paravirt_read_msr(unsigned msr)
@@ -390,27 +388,25 @@ static inline void paravirt_release_p4d(unsigned long pfn)
 static inline pte_t __pte(pteval_t val)
 {
 	return (pte_t) { PVOP_ALT_CALLEE1(pteval_t, mmu.make_pte, val,
-					  "mov %%rdi, %%rax",
-					  ALT_NOT(X86_FEATURE_XENPV)) };
+					  "mov %%rdi, %%rax", ALT_NOT_XEN) };
 }
 
 static inline pteval_t pte_val(pte_t pte)
 {
 	return PVOP_ALT_CALLEE1(pteval_t, mmu.pte_val, pte.pte,
-				"mov %%rdi, %%rax", ALT_NOT(X86_FEATURE_XENPV));
+				"mov %%rdi, %%rax", ALT_NOT_XEN);
 }
 
 static inline pgd_t __pgd(pgdval_t val)
 {
 	return (pgd_t) { PVOP_ALT_CALLEE1(pgdval_t, mmu.make_pgd, val,
-					  "mov %%rdi, %%rax",
-					  ALT_NOT(X86_FEATURE_XENPV)) };
+					  "mov %%rdi, %%rax", ALT_NOT_XEN) };
 }
 
 static inline pgdval_t pgd_val(pgd_t pgd)
 {
 	return PVOP_ALT_CALLEE1(pgdval_t, mmu.pgd_val, pgd.pgd,
-				"mov %%rdi, %%rax", ALT_NOT(X86_FEATURE_XENPV));
+				"mov %%rdi, %%rax", ALT_NOT_XEN);
 }
 
 #define  __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION
@@ -444,14 +440,13 @@ static inline void set_pmd(pmd_t *pmdp, pmd_t pmd)
 static inline pmd_t __pmd(pmdval_t val)
 {
 	return (pmd_t) { PVOP_ALT_CALLEE1(pmdval_t, mmu.make_pmd, val,
-					  "mov %%rdi, %%rax",
-					  ALT_NOT(X86_FEATURE_XENPV)) };
+					  "mov %%rdi, %%rax", ALT_NOT_XEN) };
 }
 
 static inline pmdval_t pmd_val(pmd_t pmd)
 {
 	return PVOP_ALT_CALLEE1(pmdval_t, mmu.pmd_val, pmd.pmd,
-				"mov %%rdi, %%rax", ALT_NOT(X86_FEATURE_XENPV));
+				"mov %%rdi, %%rax", ALT_NOT_XEN);
 }
 
 static inline void set_pud(pud_t *pudp, pud_t pud)
@@ -464,7 +459,7 @@ static inline pud_t __pud(pudval_t val)
 	pudval_t ret;
 
 	ret = PVOP_ALT_CALLEE1(pudval_t, mmu.make_pud, val,
-			       "mov %%rdi, %%rax", ALT_NOT(X86_FEATURE_XENPV));
+			       "mov %%rdi, %%rax", ALT_NOT_XEN);
 
 	return (pud_t) { ret };
 }
@@ -472,7 +467,7 @@ static inline pud_t __pud(pudval_t val)
 static inline pudval_t pud_val(pud_t pud)
 {
 	return PVOP_ALT_CALLEE1(pudval_t, mmu.pud_val, pud.pud,
-				"mov %%rdi, %%rax", ALT_NOT(X86_FEATURE_XENPV));
+				"mov %%rdi, %%rax", ALT_NOT_XEN);
 }
 
 static inline void pud_clear(pud_t *pudp)
@@ -492,8 +487,7 @@ static inline void set_p4d(p4d_t *p4dp, p4d_t p4d)
 static inline p4d_t __p4d(p4dval_t val)
 {
 	p4dval_t ret = PVOP_ALT_CALLEE1(p4dval_t, mmu.make_p4d, val,
-					"mov %%rdi, %%rax",
-					ALT_NOT(X86_FEATURE_XENPV));
+					"mov %%rdi, %%rax", ALT_NOT_XEN);
 
 	return (p4d_t) { ret };
 }
@@ -501,7 +495,7 @@ static inline p4d_t __p4d(p4dval_t val)
 static inline p4dval_t p4d_val(p4d_t p4d)
 {
 	return PVOP_ALT_CALLEE1(p4dval_t, mmu.p4d_val, p4d.p4d,
-				"mov %%rdi, %%rax", ALT_NOT(X86_FEATURE_XENPV));
+				"mov %%rdi, %%rax", ALT_NOT_XEN);
 }
 
 static inline void __set_pgd(pgd_t *pgdp, pgd_t pgd)
@@ -687,17 +681,17 @@ bool __raw_callee_save___native_vcpu_is_preempted(long cpu);
 static __always_inline unsigned long arch_local_save_flags(void)
 {
 	return PVOP_ALT_CALLEE0(unsigned long, irq.save_fl, "pushf; pop %%rax;",
-				ALT_NOT(X86_FEATURE_XENPV));
+				ALT_NOT_XEN);
 }
 
 static __always_inline void arch_local_irq_disable(void)
 {
-	PVOP_ALT_VCALLEE0(irq.irq_disable, "cli;", ALT_NOT(X86_FEATURE_XENPV));
+	PVOP_ALT_VCALLEE0(irq.irq_disable, "cli;", ALT_NOT_XEN);
 }
 
 static __always_inline void arch_local_irq_enable(void)
 {
-	PVOP_ALT_VCALLEE0(irq.irq_enable, "sti;", ALT_NOT(X86_FEATURE_XENPV));
+	PVOP_ALT_VCALLEE0(irq.irq_enable, "sti;", ALT_NOT_XEN);
 }
 
 static __always_inline unsigned long arch_local_irq_save(void)
@@ -726,52 +720,25 @@ static __always_inline unsigned long arch_local_irq_save(void)
 #undef PVOP_VCALL4
 #undef PVOP_CALL4
 
-#define DEFINE_PARAVIRT_ASM(func, instr, sec)		\
-	asm (".pushsection " #sec ", \"ax\"\n"		\
-	     ".global " #func "\n\t"			\
-	     ".type " #func ", @function\n\t"		\
-	     ASM_FUNC_ALIGN "\n"			\
-	     #func ":\n\t"				\
-	     ASM_ENDBR					\
-	     instr "\n\t"				\
-	     ASM_RET					\
-	     ".size " #func ", . - " #func "\n\t"	\
-	     ".popsection")
-
 extern void default_banner(void);
 void native_pv_lock_init(void) __init;
 
 #else  /* __ASSEMBLY__ */
 
-#define _PVSITE(ptype, ops, word, algn)		\
-771:;						\
-	ops;					\
-772:;						\
-	.pushsection .parainstructions,"a";	\
-	 .align	algn;				\
-	 word 771b;				\
-	 .byte ptype;				\
-	 .byte 772b-771b;			\
-	 _ASM_ALIGN;				\
-	.popsection
-
-
 #ifdef CONFIG_X86_64
 #ifdef CONFIG_PARAVIRT_XXL
+#ifdef CONFIG_DEBUG_ENTRY
 
-#define PARA_PATCH(off)		((off) / 8)
-#define PARA_SITE(ptype, ops)	_PVSITE(ptype, ops, .quad, 8)
 #define PARA_INDIRECT(addr)	*addr(%rip)
 
-#ifdef CONFIG_DEBUG_ENTRY
 .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);)
+	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)
+#define SAVE_FLAGS ALTERNATIVE_2 "PARA_IRQ_save_fl;",			\
+				 "ALT_CALL_INSTR;", ALT_CALL_ALWAYS,	\
+				 "pushf; pop %rax;", ALT_NOT_XEN
 #endif
 #endif /* CONFIG_PARAVIRT_XXL */
 #endif	/* CONFIG_X86_64 */
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 772d03487520..d8e85d2cf8d5 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -2,15 +2,6 @@
 #ifndef _ASM_X86_PARAVIRT_TYPES_H
 #define _ASM_X86_PARAVIRT_TYPES_H
 
-#ifndef __ASSEMBLY__
-/* These all sit in the .parainstructions section to tell us what to patch. */
-struct paravirt_patch_site {
-	u8 *instr;		/* original instructions */
-	u8 type;		/* type of this instruction */
-	u8 len;			/* length of original instruction */
-};
-#endif
-
 #ifdef CONFIG_PARAVIRT
 
 #ifndef __ASSEMBLY__
@@ -250,43 +241,11 @@ struct paravirt_patch_template {
 extern struct pv_info pv_info;
 extern struct paravirt_patch_template pv_ops;
 
-#define PARAVIRT_PATCH(x)					\
-	(offsetof(struct paravirt_patch_template, x) / sizeof(void *))
-
-#define paravirt_type(op)				\
-	[paravirt_typenum] "i" (PARAVIRT_PATCH(op)),	\
-	[paravirt_opptr] "m" (pv_ops.op)
-/*
- * Generate some code, and mark it as patchable by the
- * apply_paravirt() alternate instruction patcher.
- */
-#define _paravirt_alt(insn_string, type)		\
-	"771:\n\t" insn_string "\n" "772:\n"		\
-	".pushsection .parainstructions,\"a\"\n"	\
-	_ASM_ALIGN "\n"					\
-	_ASM_PTR " 771b\n"				\
-	"  .byte " type "\n"				\
-	"  .byte 772b-771b\n"				\
-	_ASM_ALIGN "\n"					\
-	".popsection\n"
-
-/* Generate patchable code, with the default asm parameters. */
-#define paravirt_alt(insn_string)					\
-	_paravirt_alt(insn_string, "%c[paravirt_typenum]")
-
-/* Simple instruction patching code. */
-#define NATIVE_LABEL(a,x,b) "\n\t.globl " a #x "_" #b "\n" a #x "_" #b ":\n\t"
-
-unsigned int paravirt_patch(u8 type, void *insn_buff, unsigned long addr, unsigned int len);
+#define paravirt_ptr(op)	[paravirt_opptr] "m" (pv_ops.op)
 
 int paravirt_disable_iospace(void);
 
-/*
- * This generates an indirect call based on the operation type number.
- * The type number, computed in PARAVIRT_PATCH, is derived from the
- * offset into the paravirt_patch_template structure, and can therefore be
- * freely converted back into a structure offset.
- */
+/* This generates an indirect call based on the operation type number. */
 #define PARAVIRT_CALL					\
 	ANNOTATE_RETPOLINE_SAFE				\
 	"call *%[paravirt_opptr];"
@@ -319,12 +278,6 @@ int paravirt_disable_iospace(void);
  * However, x86_64 also has to clobber all caller saved registers, which
  * unfortunately, are quite a bit (r8 - r11)
  *
- * The call instruction itself is marked by placing its start address
- * and size into the .parainstructions section, so that
- * apply_paravirt() in arch/i386/kernel/alternative.c can do the
- * appropriate patching under the control of the backend pv_init_ops
- * implementation.
- *
  * Unfortunately there's no way to get gcc to generate the args setup
  * for the call, and then allow the call itself to be generated by an
  * inline asm.  Because of this, we must do the complete arg setup and
@@ -423,14 +376,27 @@ int paravirt_disable_iospace(void);
 		__mask & __eax;						\
 	})
 
-
+/*
+ * Use alternative patching for paravirt calls:
+ * - For replacing an indirect call with a direct one, use the "normal"
+ *   ALTERNATIVE() macro with the indirect call as the initial code sequence,
+ *   which will be replaced with the related direct call by using the
+ *   ALT_FLAG_DIRECT_CALL special case and the "always on" feature.
+ * - In case the replacement is either a direct call or a short code sequence
+ *   depending on a feature bit, the ALTERNATIVE_2() macro is being used.
+ *   The indirect call is the initial code sequence again, while the special
+ *   code sequence is selected with the specified feature bit. In case the
+ *   feature is not active, the direct call is used as above via the
+ *   ALT_FLAG_DIRECT_CALL special case and the "always on" feature.
+ */
 #define ____PVOP_CALL(ret, op, call_clbr, extra_clbr, ...)	\
 	({								\
 		PVOP_CALL_ARGS;						\
 		PVOP_TEST_NULL(op);					\
-		asm volatile(paravirt_alt(PARAVIRT_CALL)		\
+		asm volatile(ALTERNATIVE(PARAVIRT_CALL, ALT_CALL_INSTR,	\
+				ALT_CALL_ALWAYS)			\
 			     : call_clbr, ASM_CALL_CONSTRAINT		\
-			     : paravirt_type(op),			\
+			     : paravirt_ptr(op),			\
 			       ##__VA_ARGS__				\
 			     : "memory", "cc" extra_clbr);		\
 		ret;							\
@@ -441,10 +407,11 @@ int paravirt_disable_iospace(void);
 	({								\
 		PVOP_CALL_ARGS;						\
 		PVOP_TEST_NULL(op);					\
-		asm volatile(ALTERNATIVE(paravirt_alt(PARAVIRT_CALL),	\
-					 alt, cond)			\
+		asm volatile(ALTERNATIVE_2(PARAVIRT_CALL,		\
+				 ALT_CALL_INSTR, ALT_CALL_ALWAYS,	\
+				 alt, cond)				\
 			     : call_clbr, ASM_CALL_CONSTRAINT		\
-			     : paravirt_type(op),			\
+			     : paravirt_ptr(op),			\
 			       ##__VA_ARGS__				\
 			     : "memory", "cc" extra_clbr);		\
 		ret;							\
@@ -542,8 +509,6 @@ int paravirt_disable_iospace(void);
 	__PVOP_VCALL(op, PVOP_CALL_ARG1(arg1), PVOP_CALL_ARG2(arg2),	\
 		     PVOP_CALL_ARG3(arg3), PVOP_CALL_ARG4(arg4))
 
-void _paravirt_nop(void);
-void paravirt_BUG(void);
 unsigned long paravirt_ret0(void);
 #ifdef CONFIG_PARAVIRT_XXL
 u64 _paravirt_ident_64(u64);
@@ -553,11 +518,11 @@ void pv_native_irq_enable(void);
 unsigned long pv_native_read_cr2(void);
 #endif
 
-#define paravirt_nop	((void *)_paravirt_nop)
-
-extern struct paravirt_patch_site __parainstructions[],
-	__parainstructions_end[];
+#define paravirt_nop	((void *)nop_func)
 
 #endif	/* __ASSEMBLY__ */
+
+#define ALT_NOT_XEN	ALT_NOT(X86_FEATURE_XENPV)
+
 #endif  /* CONFIG_PARAVIRT */
 #endif	/* _ASM_X86_PARAVIRT_TYPES_H */
diff --git a/arch/x86/include/asm/qspinlock_paravirt.h b/arch/x86/include/asm/qspinlock_paravirt.h
index 85b6e3609cb9..ef9697f20129 100644
--- a/arch/x86/include/asm/qspinlock_paravirt.h
+++ b/arch/x86/include/asm/qspinlock_paravirt.h
@@ -56,8 +56,8 @@ __PV_CALLEE_SAVE_REGS_THUNK(__pv_queued_spin_unlock_slowpath, ".spinlock.text");
 	"pop    %rdx\n\t"						\
 	FRAME_END
 
-DEFINE_PARAVIRT_ASM(__raw_callee_save___pv_queued_spin_unlock,
-		    PV_UNLOCK_ASM, .spinlock.text);
+DEFINE_ASM_FUNC(__raw_callee_save___pv_queued_spin_unlock,
+		PV_UNLOCK_ASM, .spinlock.text);
 
 #else /* CONFIG_64BIT */
 
diff --git a/arch/x86/include/asm/text-patching.h b/arch/x86/include/asm/text-patching.h
index 29832c338cdc..0b70653a98c1 100644
--- a/arch/x86/include/asm/text-patching.h
+++ b/arch/x86/include/asm/text-patching.h
@@ -6,18 +6,6 @@
 #include <linux/stddef.h>
 #include <asm/ptrace.h>
 
-struct paravirt_patch_site;
-#ifdef CONFIG_PARAVIRT
-void apply_paravirt(struct paravirt_patch_site *start,
-		    struct paravirt_patch_site *end);
-#else
-static inline void apply_paravirt(struct paravirt_patch_site *start,
-				  struct paravirt_patch_site *end)
-{}
-#define __parainstructions	NULL
-#define __parainstructions_end	NULL
-#endif
-
 /*
  * Currently, the max observed size in the kernel code is
  * JUMP_LABEL_NOP_SIZE/RELATIVEJUMP_SIZE, which are 5.