Merge tag 'objtool-core-2021-10-31' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull objtool updates from Thomas Gleixner:

 - Improve retpoline code patching by separating it from alternatives
   which reduces memory footprint and allows to do better optimizations
   in the actual runtime patching.

 - Add proper retpoline support for x86/BPF

 - Address noinstr warnings in x86/kvm, lockdep and paravirtualization
   code

 - Add support to handle pv_opsindirect calls in the noinstr analysis

 - Classify symbols upfront and cache the result to avoid redundant
   str*cmp() invocations.

 - Add a CFI hash to reduce memory consumption which also reduces
   runtime on a allyesconfig by ~50%

 - Adjust XEN code to make objtool handling more robust and as a side
   effect to prevent text fragmentation due to placement of the
   hypercall page.

* tag 'objtool-core-2021-10-31' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (41 commits)
  bpf,x86: Respect X86_FEATURE_RETPOLINE*
  bpf,x86: Simplify computing label offsets
  x86,bugs: Unconditionally allow spectre_v2=retpoline,amd
  x86/alternative: Add debug prints to apply_retpolines()
  x86/alternative: Try inline spectre_v2=retpoline,amd
  x86/alternative: Handle Jcc __x86_indirect_thunk_\reg
  x86/alternative: Implement .retpoline_sites support
  x86/retpoline: Create a retpoline thunk array
  x86/retpoline: Move the retpoline thunk declarations to nospec-branch.h
  x86/asm: Fixup odd GEN-for-each-reg.h usage
  x86/asm: Fix register order
  x86/retpoline: Remove unused replacement symbols
  objtool,x86: Replace alternatives with .retpoline_sites
  objtool: Shrink struct instruction
  objtool: Explicitly avoid self modifying code in .altinstr_replacement
  objtool: Classify symbols
  objtool: Support pv_opsindirect calls for noinstr
  x86/xen: Rework the xen_{cpu,irq,mmu}_opsarrays
  x86/xen: Mark xen_force_evtchn_callback() noinstr
  x86/xen: Make irq_disable() noinstr
  ...

26 files changed, 550 insertions, 429 deletions

diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c
index a149a5e9a16a..54447690de11 100644
--- a/arch/um/kernel/um_arch.c
+++ b/arch/um/kernel/um_arch.c
@@ -421,6 +421,10 @@ void __init check_bugs(void)
 	os_check_bugs();
 }
 
+void apply_retpolines(s32 *start, s32 *end)
+{
+}
+
 void apply_alternatives(struct alt_instr *start, struct alt_instr *end)
 {
 }
diff --git a/arch/x86/include/asm/GEN-for-each-reg.h b/arch/x86/include/asm/GEN-for-each-reg.h
index 1b07fb102c4e..07949102a08d 100644
--- a/arch/x86/include/asm/GEN-for-each-reg.h
+++ b/arch/x86/include/asm/GEN-for-each-reg.h
@@ -1,11 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * These are in machine order; things rely on that.
+ */
 #ifdef CONFIG_64BIT
 GEN(rax)
-GEN(rbx)
 GEN(rcx)
 GEN(rdx)
+GEN(rbx)
+GEN(rsp)
+GEN(rbp)
 GEN(rsi)
 GEN(rdi)
-GEN(rbp)
 GEN(r8)
 GEN(r9)
 GEN(r10)
@@ -16,10 +21,11 @@ GEN(r14)
 GEN(r15)
 #else
 GEN(eax)
-GEN(ebx)
 GEN(ecx)
 GEN(edx)
+GEN(ebx)
+GEN(esp)
+GEN(ebp)
 GEN(esi)
 GEN(edi)
-GEN(ebp)
 #endif
diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index a3c2315aca12..58eee6402832 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -75,6 +75,7 @@ extern int alternatives_patched;
 
 extern void alternative_instructions(void);
 extern void apply_alternatives(struct alt_instr *start, struct alt_instr *end);
+extern void apply_retpolines(s32 *start, s32 *end);
 
 struct module;
 
diff --git a/arch/x86/include/asm/asm-prototypes.h b/arch/x86/include/asm/asm-prototypes.h
index 4cb726c71ed8..8f80de627c60 100644
--- a/arch/x86/include/asm/asm-prototypes.h
+++ b/arch/x86/include/asm/asm-prototypes.h
@@ -17,21 +17,3 @@
 extern void cmpxchg8b_emu(void);
 #endif
 
-#ifdef CONFIG_RETPOLINE
-
-#undef GEN
-#define GEN(reg) \
-	extern asmlinkage void __x86_indirect_thunk_ ## reg (void);
-#include <asm/GEN-for-each-reg.h>
-
-#undef GEN
-#define GEN(reg) \
-	extern asmlinkage void __x86_indirect_alt_call_ ## reg (void);
-#include <asm/GEN-for-each-reg.h>
-
-#undef GEN
-#define GEN(reg) \
-	extern asmlinkage void __x86_indirect_alt_jmp_ ## reg (void);
-#include <asm/GEN-for-each-reg.h>
-
-#endif /* CONFIG_RETPOLINE */
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index ec2d5c8c6694..cc74dc584836 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -5,12 +5,15 @@
 
 #include <linux/static_key.h>
 #include <linux/objtool.h>
+#include <linux/linkage.h>
 
 #include <asm/alternative.h>
 #include <asm/cpufeatures.h>
 #include <asm/msr-index.h>
 #include <asm/unwind_hints.h>
 
+#define RETPOLINE_THUNK_SIZE	32
+
 /*
  * Fill the CPU return stack buffer.
  *
@@ -118,6 +121,16 @@
 	".popsection\n\t"
 
 #ifdef CONFIG_RETPOLINE
+
+typedef u8 retpoline_thunk_t[RETPOLINE_THUNK_SIZE];
+
+#define GEN(reg) \
+	extern retpoline_thunk_t __x86_indirect_thunk_ ## reg;
+#include <asm/GEN-for-each-reg.h>
+#undef GEN
+
+extern retpoline_thunk_t __x86_indirect_thunk_array[];
+
 #ifdef CONFIG_X86_64
 
 /*
@@ -303,63 +316,4 @@ static inline void mds_idle_clear_cpu_buffers(void)
 
 #endif /* __ASSEMBLY__ */
 
-/*
- * Below is used in the eBPF JIT compiler and emits the byte sequence
- * for the following assembly:
- *
- * With retpolines configured:
- *
- *    callq do_rop
- *  spec_trap:
- *    pause
- *    lfence
- *    jmp spec_trap
- *  do_rop:
- *    mov %rcx,(%rsp) for x86_64
- *    mov %edx,(%esp) for x86_32
- *    retq
- *
- * Without retpolines configured:
- *
- *    jmp *%rcx for x86_64
- *    jmp *%edx for x86_32
- */
-#ifdef CONFIG_RETPOLINE
-# ifdef CONFIG_X86_64
-#  define RETPOLINE_RCX_BPF_JIT_SIZE	17
-#  define RETPOLINE_RCX_BPF_JIT()				\
-do {								\
-	EMIT1_off32(0xE8, 7);	 /* callq do_rop */		\
-	/* spec_trap: */					\
-	EMIT2(0xF3, 0x90);       /* pause */			\
-	EMIT3(0x0F, 0xAE, 0xE8); /* lfence */			\
-	EMIT2(0xEB, 0xF9);       /* jmp spec_trap */		\
-	/* do_rop: */						\
-	EMIT4(0x48, 0x89, 0x0C, 0x24); /* mov %rcx,(%rsp) */	\
-	EMIT1(0xC3);             /* retq */			\
-} while (0)
-# else /* !CONFIG_X86_64 */
-#  define RETPOLINE_EDX_BPF_JIT()				\
-do {								\
-	EMIT1_off32(0xE8, 7);	 /* call do_rop */		\
-	/* spec_trap: */					\
-	EMIT2(0xF3, 0x90);       /* pause */			\
-	EMIT3(0x0F, 0xAE, 0xE8); /* lfence */			\
-	EMIT2(0xEB, 0xF9);       /* jmp spec_trap */		\
-	/* do_rop: */						\
-	EMIT3(0x89, 0x14, 0x24); /* mov %edx,(%esp) */		\
-	EMIT1(0xC3);             /* ret */			\
-} while (0)
-# endif
-#else /* !CONFIG_RETPOLINE */
-# ifdef CONFIG_X86_64
-#  define RETPOLINE_RCX_BPF_JIT_SIZE	2
-#  define RETPOLINE_RCX_BPF_JIT()				\
-	EMIT2(0xFF, 0xE1);       /* jmp *%rcx */
-# else /* !CONFIG_X86_64 */
-#  define RETPOLINE_EDX_BPF_JIT()				\
-	EMIT2(0xFF, 0xE2)        /* jmp *%edx */
-# endif
-#endif
-
 #endif /* _ASM_X86_NOSPEC_BRANCH_H_ */
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index da3a1ac82be5..cebec95a7124 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -52,11 +52,11 @@ void __init paravirt_set_cap(void);
 /* The paravirtualized I/O functions */
 static inline void slow_down_io(void)
 {
-	pv_ops.cpu.io_delay();
+	PVOP_VCALL0(cpu.io_delay);
 #ifdef REALLY_SLOW_IO
-	pv_ops.cpu.io_delay();
-	pv_ops.cpu.io_delay();
-	pv_ops.cpu.io_delay();
+	PVOP_VCALL0(cpu.io_delay);
+	PVOP_VCALL0(cpu.io_delay);
+	PVOP_VCALL0(cpu.io_delay);
 #endif
 }
 
@@ -113,12 +113,12 @@ static inline void __cpuid(unsigned int *eax, unsigned int *ebx,
 /*
  * These special macros can be used to get or set a debugging register
  */
-static inline unsigned long paravirt_get_debugreg(int reg)
+static __always_inline unsigned long paravirt_get_debugreg(int reg)
 {
 	return PVOP_CALL1(unsigned long, cpu.get_debugreg, reg);
 }
 #define get_debugreg(var, reg) var = paravirt_get_debugreg(reg)
-static inline void set_debugreg(unsigned long val, int reg)
+static __always_inline void set_debugreg(unsigned long val, int reg)
 {
 	PVOP_VCALL2(cpu.set_debugreg, reg, val);
 }
@@ -133,14 +133,14 @@ static inline void write_cr0(unsigned long x)
 	PVOP_VCALL1(cpu.write_cr0, x);
 }
 
-static inline unsigned long read_cr2(void)
+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));
 }
 
-static inline void write_cr2(unsigned long x)
+static __always_inline void write_cr2(unsigned long x)
 {
 	PVOP_VCALL1(mmu.write_cr2, x);
 }
@@ -653,10 +653,10 @@ bool __raw_callee_save___native_vcpu_is_preempted(long cpu);
  * functions.
  */
 #define PV_THUNK_NAME(func) "__raw_callee_save_" #func
-#define PV_CALLEE_SAVE_REGS_THUNK(func)					\
+#define __PV_CALLEE_SAVE_REGS_THUNK(func, section)			\
 	extern typeof(func) __raw_callee_save_##func;			\
 									\
-	asm(".pushsection .text;"					\
+	asm(".pushsection " section ", \"ax\";"				\
 	    ".globl " PV_THUNK_NAME(func) ";"				\
 	    ".type " PV_THUNK_NAME(func) ", @function;"			\
 	    PV_THUNK_NAME(func) ":"					\
@@ -669,6 +669,9 @@ bool __raw_callee_save___native_vcpu_is_preempted(long cpu);
 	    ".size " PV_THUNK_NAME(func) ", .-" PV_THUNK_NAME(func) ";"	\
 	    ".popsection")
 
+#define PV_CALLEE_SAVE_REGS_THUNK(func)			\
+	__PV_CALLEE_SAVE_REGS_THUNK(func, ".text")
+
 /* Get a reference to a callee-save function */
 #define PV_CALLEE_SAVE(func)						\
 	((struct paravirt_callee_save) { __raw_callee_save_##func })
@@ -678,23 +681,23 @@ bool __raw_callee_save___native_vcpu_is_preempted(long cpu);
 	((struct paravirt_callee_save) { func })
 
 #ifdef CONFIG_PARAVIRT_XXL
-static inline notrace unsigned long arch_local_save_flags(void)
+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));
 }
 
-static inline notrace void arch_local_irq_disable(void)
+static __always_inline void arch_local_irq_disable(void)
 {
 	PVOP_ALT_VCALLEE0(irq.irq_disable, "cli;", ALT_NOT(X86_FEATURE_XENPV));
 }
 
-static inline notrace void arch_local_irq_enable(void)
+static __always_inline void arch_local_irq_enable(void)
 {
 	PVOP_ALT_VCALLEE0(irq.irq_enable, "sti;", ALT_NOT(X86_FEATURE_XENPV));
 }
 
-static inline notrace unsigned long arch_local_irq_save(void)
+static __always_inline unsigned long arch_local_irq_save(void)
 {
 	unsigned long f;
 
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index b94f615600d5..703663175a5a 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -181,7 +181,7 @@ static inline bool any_64bit_mode(struct pt_regs *regs)
 #define current_user_stack_pointer()	current_pt_regs()->sp
 #define compat_user_stack_pointer()	current_pt_regs()->sp
 
-static inline bool ip_within_syscall_gap(struct pt_regs *regs)
+static __always_inline bool ip_within_syscall_gap(struct pt_regs *regs)
 {
 	bool ret = (regs->ip >= (unsigned long)entry_SYSCALL_64 &&
 		    regs->ip <  (unsigned long)entry_SYSCALL_64_safe_stack);
diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h
index 454b20815f35..4a7ff8b0db20 100644
--- a/arch/x86/include/asm/xen/hypercall.h
+++ b/arch/x86/include/asm/xen/hypercall.h
@@ -308,13 +308,13 @@ HYPERVISOR_platform_op(struct xen_platform_op *op)
 	return _hypercall1(int, platform_op, op);
 }
 
-static inline int
+static __always_inline int
 HYPERVISOR_set_debugreg(int reg, unsigned long value)
 {
 	return _hypercall2(int, set_debugreg, reg, value);
 }
 
-static inline unsigned long
+static __always_inline unsigned long
 HYPERVISOR_get_debugreg(int reg)
 {
 	return _hypercall1(unsigned long, get_debugreg, reg);
@@ -358,7 +358,7 @@ HYPERVISOR_event_channel_op(int cmd, void *arg)
 	return _hypercall2(int, event_channel_op, cmd, arg);
 }
 
-static inline int
+static __always_inline int
 HYPERVISOR_xen_version(int cmd, void *arg)
 {
 	return _hypercall2(int, xen_version, cmd, arg);
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index e9da3dc71254..23fb4d51a5da 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -29,6 +29,7 @@
 #include <asm/io.h>
 #include <asm/fixmap.h>
 #include <asm/paravirt.h>
+#include <asm/asm-prototypes.h>
 
 int __read_mostly alternatives_patched;
 
@@ -113,6 +114,7 @@ static void __init_or_module add_nops(void *insns, unsigned int len)
 	}
 }
 
+extern s32 __retpoline_sites[], __retpoline_sites_end[];
 extern struct alt_instr __alt_instructions[], __alt_instructions_end[];
 extern s32 __smp_locks[], __smp_locks_end[];
 void text_poke_early(void *addr, const void *opcode, size_t len);
@@ -221,7 +223,7 @@ static __always_inline int optimize_nops_range(u8 *instr, u8 instrlen, int off)
  * "noinline" to cause control flow change and thus invalidate I$ and
  * cause refetch after modification.
  */
-static void __init_or_module noinline optimize_nops(struct alt_instr *a, u8 *instr)
+static void __init_or_module noinline optimize_nops(u8 *instr, size_t len)
 {
 	struct insn insn;
 	int i = 0;
@@ -239,11 +241,11 @@ static void __init_or_module noinline optimize_nops(struct alt_instr *a, u8 *ins
 		 * optimized.
 		 */
 		if (insn.length == 1 && insn.opcode.bytes[0] == 0x90)
-			i += optimize_nops_range(instr, a->instrlen, i);
+			i += optimize_nops_range(instr, len, i);
 		else
 			i += insn.length;
 
-		if (i >= a->instrlen)
+		if (i >= len)
 			return;
 	}
 }
@@ -331,10 +333,185 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start,
 		text_poke_early(instr, insn_buff, insn_buff_sz);
 
 next:
-		optimize_nops(a, instr);
+		optimize_nops(instr, a->instrlen);
 	}
 }
 
+#if defined(CONFIG_RETPOLINE) && defined(CONFIG_STACK_VALIDATION)
+
+/*
+ * CALL/JMP *%\reg
+ */
+static int emit_indirect(int op, int reg, u8 *bytes)
+{
+	int i = 0;
+	u8 modrm;
+
+	switch (op) {
+	case CALL_INSN_OPCODE:
+		modrm = 0x10; /* Reg = 2; CALL r/m */
+		break;
+
+	case JMP32_INSN_OPCODE:
+		modrm = 0x20; /* Reg = 4; JMP r/m */
+		break;
+
+	default:
+		WARN_ON_ONCE(1);
+		return -1;
+	}
+
+	if (reg >= 8) {
+		bytes[i++] = 0x41; /* REX.B prefix */
+		reg -= 8;
+	}
+
+	modrm |= 0xc0; /* Mod = 3 */
+	modrm += reg;
+
+	bytes[i++] = 0xff; /* opcode */
+	bytes[i++] = modrm;
+
+	return i;
+}
+
+/*
+ * Rewrite the compiler generated retpoline thunk calls.
+ *
+ * For spectre_v2=off (!X86_FEATURE_RETPOLINE), rewrite them into immediate
+ * indirect instructions, avoiding the extra indirection.
+ *
+ * For example, convert:
+ *
+ *   CALL __x86_indirect_thunk_\reg
+ *
+ * into:
+ *
+ *   CALL *%\reg
+ *
+ * It also tries to inline spectre_v2=retpoline,amd when size permits.
+ */
+static int patch_retpoline(void *addr, struct insn *insn, u8 *bytes)
+{
+	retpoline_thunk_t *target;
+	int reg, ret, i = 0;
+	u8 op, cc;
+
+	target = addr + insn->length + insn->immediate.value;
+	reg = target - __x86_indirect_thunk_array;
+
+	if (WARN_ON_ONCE(reg & ~0xf))
+		return -1;
+
+	/* If anyone ever does: CALL/JMP *%rsp, we're in deep trouble. */
+	BUG_ON(reg == 4);
+
+	if (cpu_feature_enabled(X86_FEATURE_RETPOLINE) &&
+	    !cpu_feature_enabled(X86_FEATURE_RETPOLINE_AMD))
+		return -1;
+
+	op = insn->opcode.bytes[0];
+
+	/*
+	 * Convert:
+	 *
+	 *   Jcc.d32 __x86_indirect_thunk_\reg
+	 *
+	 * into:
+	 *
+	 *   Jncc.d8 1f
+	 *   [ LFENCE ]
+	 *   JMP *%\reg
+	 *   [ NOP ]
+	 * 1:
+	 */
+	/* Jcc.d32 second opcode byte is in the range: 0x80-0x8f */
+	if (op == 0x0f && (insn->opcode.bytes[1] & 0xf0) == 0x80) {
+		cc = insn->opcode.bytes[1] & 0xf;
+		cc ^= 1; /* invert condition */
+
+		bytes[i++] = 0x70 + cc;        /* Jcc.d8 */
+		bytes[i++] = insn->length - 2; /* sizeof(Jcc.d8) == 2 */
+
+		/* Continue as if: JMP.d32 __x86_indirect_thunk_\reg */
+		op = JMP32_INSN_OPCODE;
+	}
+
+	/*
+	 * For RETPOLINE_AMD: prepend the indirect CALL/JMP with an LFENCE.
+	 */
+	if (cpu_feature_enabled(X86_FEATURE_RETPOLINE_AMD)) {
+		bytes[i++] = 0x0f;
+		bytes[i++] = 0xae;
+		bytes[i++] = 0xe8; /* LFENCE */
+	}
+
+	ret = emit_indirect(op, reg, bytes + i);
+	if (ret < 0)
+		return ret;
+	i += ret;
+
+	for (; i < insn->length;)
+		bytes[i++] = BYTES_NOP1;
+
+	return i;
+}
+
+/*
+ * Generated by 'objtool --retpoline'.
+ */
+void __init_or_module noinline apply_retpolines(s32 *start, s32 *end)
+{
+	s32 *s;
+
+	for (s = start; s < end; s++) {
+		void *addr = (void *)s + *s;
+		struct insn insn;
+		int len, ret;
+		u8 bytes[16];
+		u8 op1, op2;
+
+		ret = insn_decode_kernel(&insn, addr);
+		if (WARN_ON_ONCE(ret < 0))
+			continue;
+
+		op1 = insn.opcode.bytes[0];
+		op2 = insn.opcode.bytes[1];
+
+		switch (op1) {
+		case CALL_INSN_OPCODE:
+		case JMP32_INSN_OPCODE:
+			break;
+
+		case 0x0f: /* escape */
+			if (op2 >= 0x80 && op2 <= 0x8f)
+				break;
+			fallthrough;
+		default:
+			WARN_ON_ONCE(1);
+			continue;
+		}
+
+		DPRINTK("retpoline at: %pS (%px) len: %d to: %pS",
+			addr, addr, insn.length,
+			addr + insn.length + insn.immediate.value);
+
+		len = patch_retpoline(addr, &insn, bytes);
+		if (len == insn.length) {
+			optimize_nops(bytes, len);
+			DUMP_BYTES(((u8*)addr),  len, "%px: orig: ", addr);
+			DUMP_BYTES(((u8*)bytes), len, "%px: repl: ", addr);
+			text_poke_early(addr, bytes, len);
+		}
+	}
+}
+
+#else /* !RETPOLINES || !CONFIG_STACK_VALIDATION */
+
+void __init_or_module noinline apply_retpolines(s32 *start, s32 *end) { }
+
+#endif /* CONFIG_RETPOLINE && CONFIG_STACK_VALIDATION */
+
 #ifdef CONFIG_SMP
 static void alternatives_smp_lock(const s32 *start, const s32 *end,
 				  u8 *text, u8 *text_end)
@@ -643,6 +820,12 @@ void __init alternative_instructions(void)
 	apply_paravirt(__parainstructions, __parainstructions_end);
 
 	/*
+	 * Rewrite the retpolines, must be done before alternatives since
+	 * those can rewrite the retpoline thunks.
+	 */
+	apply_retpolines(__retpoline_sites, __retpoline_sites_end);
+
+	/*
 	 * Then patch alternatives, such that those paravirt calls that are in
 	 * alternatives can be overwritten by their immediate fragments.
 	 */
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index ecfca3bbcd96..ba43597f1027 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -882,13 +882,6 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void)
 		return SPECTRE_V2_CMD_AUTO;
 	}
 
-	if (cmd == SPECTRE_V2_CMD_RETPOLINE_AMD &&
-	    boot_cpu_data.x86_vendor != X86_VENDOR_HYGON &&
-	    boot_cpu_data.x86_vendor != X86_VENDOR_AMD) {
-		pr_err("retpoline,amd selected but CPU is not AMD. Switching to AUTO select\n");
-		return SPECTRE_V2_CMD_AUTO;
-	}
-
 	spec_v2_print_cond(mitigation_options[i].option,
 			   mitigation_options[i].secure);
 	return cmd;
diff --git a/arch/x86/kernel/irqflags.S b/arch/x86/kernel/irqflags.S
index 8ef35063964b..760e1f293093 100644
--- a/arch/x86/kernel/irqflags.S
+++ b/arch/x86/kernel/irqflags.S
@@ -7,9 +7,11 @@
 /*
  * unsigned long native_save_fl(void)
  */
+.pushsection .noinstr.text, "ax"
 SYM_FUNC_START(native_save_fl)
 	pushf
 	pop %_ASM_AX
 	ret
 SYM_FUNC_END(native_save_fl)
+.popsection
 EXPORT_SYMBOL(native_save_fl)
diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c
index 5e9a34b5bd74..169fb6f4cd2e 100644
--- a/arch/x86/kernel/module.c
+++ b/arch/x86/kernel/module.c
@@ -251,7 +251,8 @@ int module_finalize(const Elf_Ehdr *hdr,
 		    struct module *me)
 {
 	const Elf_Shdr *s, *text = NULL, *alt = NULL, *locks = NULL,
-		*para = NULL, *orc = NULL, *orc_ip = NULL;
+		*para = NULL, *orc = NULL, *orc_ip = NULL,
+		*retpolines = NULL;
 	char *secstrings = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset;
 
 	for (s = sechdrs; s < sechdrs + hdr->e_shnum; s++) {
@@ -267,8 +268,14 @@ int module_finalize(const Elf_Ehdr *hdr,
 			orc = s;
 		if (!strcmp(".orc_unwind_ip", secstrings + s->sh_name))
 			orc_ip = s;
+		if (!strcmp(".retpoline_sites", secstrings + s->sh_name))
+			retpolines = s;
 	}
 
+	if (retpolines) {
+		void *rseg = (void *)retpolines->sh_addr;
+		apply_retpolines(rseg, rseg + retpolines->sh_size);
+	}
 	if (alt) {
 		/* patch .altinstructions */
 		void *aseg = (void *)alt->sh_addr;
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 04cafc057bed..ebc45360ffd4 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -218,6 +218,36 @@ void paravirt_end_context_switch(struct task_struct *next)
 	if (test_and_clear_ti_thread_flag(task_thread_info(next), TIF_LAZY_MMU_UPDATES))
 		arch_enter_lazy_mmu_mode();
 }
+
+static noinstr unsigned long pv_native_read_cr2(void)
+{
+	return native_read_cr2();
+}
+
+static noinstr void pv_native_write_cr2(unsigned long val)
+{
+	native_write_cr2(val);
+}
+
+static noinstr unsigned long pv_native_get_debugreg(int regno)
+{
+	return native_get_debugreg(regno);
+}
+
+static noinstr void pv_native_set_debugreg(int regno, unsigned long val)
+{
+	native_set_debugreg(regno, val);
+}
+
+static noinstr void pv_native_irq_enable(void)
+{
+	native_irq_enable();
+}
+
+static noinstr void pv_native_irq_disable(void)
+{
+	native_irq_disable();
+}
 #endif
 
 enum paravirt_lazy_mode paravirt_get_lazy_mode(void)
@@ -244,8 +274,8 @@ struct paravirt_patch_template pv_ops = {
 
 #ifdef CONFIG_PARAVIRT_XXL
 	.cpu.cpuid		= native_cpuid,
-	.cpu.get_debugreg	= native_get_debugreg,
-	.cpu.set_debugreg	= native_set_debugreg,
+	.cpu.get_debugreg	= pv_native_get_debugreg,
+	.cpu.set_debugreg	= pv_native_set_debugreg,
 	.cpu.read_cr0		= native_read_cr0,
 	.cpu.write_cr0		= native_write_cr0,
 	.cpu.write_cr4		= native_write_cr4,
@@ -281,8 +311,8 @@ struct paravirt_patch_template pv_ops = {
 
 	/* Irq ops. */
 	.irq.save_fl		= __PV_IS_CALLEE_SAVE(native_save_fl),
-	.irq.irq_disable	= __PV_IS_CALLEE_SAVE(native_irq_disable),
-	.irq.irq_enable		= __PV_IS_CALLEE_SAVE(native_irq_enable),
+	.irq.irq_disable	= __PV_IS_CALLEE_SAVE(pv_native_irq_disable),
+	.irq.irq_enable		= __PV_IS_CALLEE_SAVE(pv_native_irq_enable),
 	.irq.safe_halt		= native_safe_halt,
 	.irq.halt		= native_halt,
 #endif /* CONFIG_PARAVIRT_XXL */
@@ -298,8 +328,8 @@ struct paravirt_patch_template pv_ops = {
 	.mmu.exit_mmap		= paravirt_nop,
 
 #ifdef CONFIG_PARAVIRT_XXL
-	.mmu.read_cr2		= __PV_IS_CALLEE_SAVE(native_read_cr2),
-	.mmu.write_cr2		= native_write_cr2,
+	.mmu.read_cr2		= __PV_IS_CALLEE_SAVE(pv_native_read_cr2),
+	.mmu.write_cr2		= pv_native_write_cr2,
 	.mmu.read_cr3		= __native_read_cr3,
 	.mmu.write_cr3		= native_write_cr3,
 
@@ -371,9 +401,6 @@ struct paravirt_patch_template pv_ops = {
 };
 
 #ifdef CONFIG_PARAVIRT_XXL
-/* At this point, native_get/set_debugreg has real function entries */
-NOKPROBE_SYMBOL(native_get_debugreg);
-NOKPROBE_SYMBOL(native_set_debugreg);
 NOKPROBE_SYMBOL(native_load_idt);
 
 void (*paravirt_iret)(void) = native_iret;
diff --git a/arch/x86/kernel/sev-shared.c b/arch/x86/kernel/sev-shared.c
index bf1033a62e48..ff1e82ff52d9 100644
--- a/arch/x86/kernel/sev-shared.c
+++ b/arch/x86/kernel/sev-shared.c
@@ -64,7 +64,7 @@ static bool sev_es_negotiate_protocol(void)
 static __always_inline void vc_ghcb_invalidate(struct ghcb *ghcb)
 {
 	ghcb->save.sw_exit_code = 0;
-	memset(ghcb->save.valid_bitmap, 0, sizeof(ghcb->save.valid_bitmap));
+	__builtin_memset(ghcb->save.valid_bitmap, 0, sizeof(ghcb->save.valid_bitmap));
 }
 
 static bool vc_decoding_needed(unsigned long exit_code)
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index efd9e9ea17f2..3d6dc12d198f 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -272,6 +272,20 @@ SECTIONS
 		__parainstructions_end = .;
 	}
 
+#ifdef CONFIG_RETPOLINE
+	/*
+	 * List of instructions that call/jmp/jcc to retpoline thunks
+	 * __x86_indirect_thunk_*(). These instructions can be patched along
+	 * with alternatives, after which the section can be freed.
+	 */
+	. = ALIGN(8);
+	.retpoline_sites : AT(ADDR(.retpoline_sites) - LOAD_OFFSET) {
+		__retpoline_sites = .;
+		*(.retpoline_sites)
+		__retpoline_sites_end = .;
+	}
+#endif
+
 	/*
 	 * struct alt_inst entries. From the header (alternative.h):
 	 * "Alternative instructions for different CPU types or capabilities"
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index 5d30db599e10..e63ac08115cf 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -218,12 +218,12 @@ DECLARE_PER_CPU(struct svm_cpu_data *, svm_data);
 
 void recalc_intercepts(struct vcpu_svm *svm);
 
-static inline struct kvm_svm *to_kvm_svm(struct kvm *kvm)
+static __always_inline struct kvm_svm *to_kvm_svm(struct kvm *kvm)
 {
 	return container_of(kvm, struct kvm_svm, kvm);
 }
 
-static inline bool sev_guest(struct kvm *kvm)
+static __always_inline bool sev_guest(struct kvm *kvm)
 {
 #ifdef CONFIG_KVM_AMD_SEV
 	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
@@ -234,7 +234,7 @@ static inline bool sev_guest(struct kvm *kvm)
 #endif
 }
 
-static inline bool sev_es_guest(struct kvm *kvm)
+static __always_inline bool sev_es_guest(struct kvm *kvm)
 {
 #ifdef CONFIG_KVM_AMD_SEV
 	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
@@ -271,7 +271,7 @@ static inline bool vmcb_is_dirty(struct vmcb *vmcb, int bit)
         return !test_bit(bit, (unsigned long *)&vmcb->control.clean);
 }
 
-static inline struct vcpu_svm *to_svm(struct kvm_vcpu *vcpu)
+static __always_inline struct vcpu_svm *to_svm(struct kvm_vcpu *vcpu)
 {
 	return container_of(vcpu, struct vcpu_svm, vcpu);
 }
diff --git a/arch/x86/kvm/svm/svm_ops.h b/arch/x86/kvm/svm/svm_ops.h
index 22e2b019de37..9430d6437c9f 100644
--- a/arch/x86/kvm/svm/svm_ops.h
+++ b/arch/x86/kvm/svm/svm_ops.h
@@ -56,12 +56,12 @@ static inline void invlpga(unsigned long addr, u32 asid)
  * VMSAVE, VMLOAD, etc... is still controlled by the effective address size,
  * hence 'unsigned long' instead of 'hpa_t'.
  */
-static inline void vmsave(unsigned long pa)
+static __always_inline void vmsave(unsigned long pa)
 {
 	svm_asm1(vmsave, "a" (pa), "memory");
 }
 
-static inline void vmload(unsigned long pa)
+static __always_inline void vmload(unsigned long pa)
 {
 	svm_asm1(vmload, "a" (pa), "memory");
 }
diff --git a/arch/x86/kvm/vmx/evmcs.h b/arch/x86/kvm/vmx/evmcs.h
index 152ab0aa82cf..16731d2cf231 100644
--- a/arch/x86/kvm/vmx/evmcs.h
+++ b/arch/x86/kvm/vmx/evmcs.h
@@ -93,7 +93,7 @@ static __always_inline int get_evmcs_offset(unsigned long field,
 	return evmcs_field->offset;
 }
 
-static inline void evmcs_write64(unsigned long field, u64 value)
+static __always_inline void evmcs_write64(unsigned long field, u64 value)
 {
 	u16 clean_field;
 	int offset = get_evmcs_offset(field, &clean_field);
@@ -183,7 +183,7 @@ static inline void evmcs_load(u64 phys_addr)
 
 __init void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf);
 #else /* !IS_ENABLED(CONFIG_HYPERV) */
-static inline void evmcs_write64(unsigned long field, u64 value) {}
+static __always_inline void evmcs_write64(unsigned long field, u64 value) {}
 static inline void evmcs_write32(unsigned long field, u32 value) {}
 static inline void evmcs_write16(unsigned long field, u16 value) {}
 static inline u64 evmcs_read64(unsigned long field) { return 0; }
diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S
index ec9922cba30a..cf0b39f97adc 100644
--- a/arch/x86/lib/retpoline.S
+++ b/arch/x86/lib/retpoline.S
@@ -28,46 +28,14 @@
 
 .macro THUNK reg
 
-	.align 32
-
-SYM_FUNC_START(__x86_indirect_thunk_\reg)
+	.align RETPOLINE_THUNK_SIZE
+SYM_INNER_LABEL(__x86_indirect_thunk_\reg, SYM_L_GLOBAL)
+	UNWIND_HINT_EMPTY
 
 	ALTERNATIVE_2 __stringify(ANNOTATE_RETPOLINE_SAFE; jmp *%\reg), \
 		      __stringify(RETPOLINE \reg), X86_FEATURE_RETPOLINE, \
 		      __stringify(lfence; ANNOTATE_RETPOLINE_SAFE; jmp *%\reg), X86_FEATURE_RETPOLINE_AMD
 
-SYM_FUNC_END(__x86_indirect_thunk_\reg)
-
-.endm
-
-/*
- * This generates .altinstr_replacement symbols for use by objtool. They,
- * however, must not actually live in .altinstr_replacement since that will be
- * discarded after init, but module alternatives will also reference these
- * symbols.
- *
- * Their names matches the "__x86_indirect_" prefix to mark them as retpolines.
- */
-.macro ALT_THUNK reg
-
-	.align 1
-
-SYM_FUNC_START_NOALIGN(__x86_indirect_alt_call_\reg)
-	ANNOTATE_RETPOLINE_SAFE
-1:	call	*%\reg
-2:	.skip	5-(2b-1b), 0x90
-SYM_FUNC_END(__x86_indirect_alt_call_\reg)
-
-STACK_FRAME_NON_STANDARD(__x86_indirect_alt_call_\reg)
-
-SYM_FUNC_START_NOALIGN(__x86_indirect_alt_jmp_\reg)
-	ANNOTATE_RETPOLINE_SAFE
-1:	jmp	*%\reg
-2:	.skip	5-(2b-1b), 0x90
-SYM_FUNC_END(__x86_indirect_alt_jmp_\reg)
-
-STACK_FRAME_NON_STANDARD(__x86_indirect_alt_jmp_\reg)
-
 .endm
 
 /*
@@ -85,22 +53,16 @@ STACK_FRAME_NON_STANDARD(__x86_indirect_alt_jmp_\reg)
 #define __EXPORT_THUNK(sym)	_ASM_NOKPROBE(sym); EXPORT_SYMBOL(sym)
 #define EXPORT_THUNK(reg)	__EXPORT_THUNK(__x86_indirect_thunk_ ## reg)
 
-#undef GEN
+	.align RETPOLINE_THUNK_SIZE
+SYM_CODE_START(__x86_indirect_thunk_array)
+
 #define GEN(reg) THUNK reg
 #include <asm/GEN-for-each-reg.h>
-
 #undef GEN
-#define GEN(reg) EXPORT_THUNK(reg)
-#include <asm/GEN-for-each-reg.h>
 
-#undef GEN
-#define GEN(reg) ALT_THUNK reg
-#include <asm/GEN-for-each-reg.h>
+	.align RETPOLINE_THUNK_SIZE
+SYM_CODE_END(__x86_indirect_thunk_array)
 
-#undef GEN
-#define GEN(reg) __EXPORT_THUNK(__x86_indirect_alt_call_ ## reg)
+#define GEN(reg) EXPORT_THUNK(reg)
 #include <asm/GEN-for-each-reg.h>
-
 #undef GEN
-#define GEN(reg) __EXPORT_THUNK(__x86_indirect_alt_jmp_ ## reg)
-#include <asm/GEN-for-each-reg.h>
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 9ea57389c554..39c802525fce 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -15,7 +15,6 @@
 #include <asm/set_memory.h>
 #include <asm/nospec-branch.h>
 #include <asm/text-patching.h>
-#include <asm/asm-prototypes.h>
 
 static u8 *emit_code(u8 *ptr, u32 bytes, unsigned int len)
 {
@@ -225,6 +224,14 @@ static void jit_fill_hole(void *area, unsigned int size)
 
 struct jit_context {
 	int cleanup_addr; /* Epilogue code offset */
+
+	/*
+	 * Program specific offsets of labels in the code; these rely on the
+	 * JIT doing at least 2 passes, recording the position on the first
+	 * pass, only to generate the correct offset on the second pass.
+	 */
+	int tail_call_direct_label;
+	int tail_call_indirect_label;
 };
 
 /* Maximum number of bytes emitted while JITing one eBPF insn */
@@ -380,20 +387,23 @@ int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
 	return __bpf_arch_text_poke(ip, t, old_addr, new_addr, true);
 }
 
-static int get_pop_bytes(bool *callee_regs_used)
+#define EMIT_LFENCE()	EMIT3(0x0F, 0xAE, 0xE8)
+
+static void emit_indirect_jump(u8 **pprog, int reg, u8 *ip)
 {
-	int bytes = 0;
+	u8 *prog = *pprog;
 
-	if (callee_regs_used[3])
-		bytes += 2;
-	if (callee_regs_used[2])
-		bytes += 2;
-	if (callee_regs_used[1])
-		bytes += 2;
-	if (callee_regs_used[0])
-		bytes += 1;
+#ifdef CONFIG_RETPOLINE
+	if (cpu_feature_enabled(X86_FEATURE_RETPOLINE_AMD)) {
+		EMIT_LFENCE();
+		EMIT2(0xFF, 0xE0 + reg);
+	} else if (cpu_feature_enabled(X86_FEATURE_RETPOLINE)) {
+		emit_jump(&prog, &__x86_indirect_thunk_array[reg], ip);
+	} else
+#endif
+	EMIT2(0xFF, 0xE0 + reg);
 
-	return bytes;
+	*pprog = prog;
 }
 
 /*
@@ -411,29 +421,12 @@ static int get_pop_bytes(bool *callee_regs_used)
  * out:
  */
 static void emit_bpf_tail_call_indirect(u8 **pprog, bool *callee_regs_used,
-					u32 stack_depth)
+					u32 stack_depth, u8 *ip,
+					struct jit_context *ctx)
 {
 	int tcc_off = -4 - round_up(stack_depth, 8);
-	u8 *prog = *pprog;
-	int pop_bytes = 0;
-	int off1 = 42;
-	int off2 = 31;
-	int off3 = 9;
-
-	/* count the additional bytes used for popping callee regs from stack
-	 * that need to be taken into account for each of the offsets that
-	 * are used for bailing out of the tail call
-	 */
-	pop_bytes = get_pop_bytes(callee_regs_used);
-	off1 += pop_bytes;
-	off2 += pop_bytes;
-	off3 += pop_bytes;
-
-	if (stack_depth) {
-		off1 += 7;
-		off2 += 7;
-		off3 += 7;
-	}
+	u8 *prog = *pprog, *start = *pprog;
+	int offset;
 
 	/*
 	 * rdi - pointer to ctx
@@ -448,8 +441,9 @@ static void emit_bpf_tail_call_indirect(u8 **pprog, bool *callee_regs_used,
 	EMIT2(0x89, 0xD2);                        /* mov edx, edx */
 	EMIT3(0x39, 0x56,                         /* cmp dword ptr [rsi + 16], edx */
 	      offsetof(struct bpf_array, map.max_entries));
-#define OFFSET1 (off1 + RETPOLINE_RCX_BPF_JIT_SIZE) /* Number of bytes to jump */
-	EMIT2(X86_JBE, OFFSET1);                  /* jbe out */
+
+	offset = ctx->tail_call_indirect_label - (prog + 2 - start);
+	EMIT2(X86_JBE, offset);                   /* jbe out */
 
 	/*
 	 * if (tail_call_cnt > MAX_TAIL_CALL_CNT)
@@ -457,8 +451,9 @@ static void emit_bpf_tail_call_indirect(u8 **pprog, bool *callee_regs_used,
 	 */
 	EMIT2_off32(0x8B, 0x85, tcc_off);         /* mov eax, dword ptr [rbp - tcc_off] */
 	EMIT3(0x83, 0xF8, MAX_TAIL_CALL_CNT);     /* cmp eax, MAX_TAIL_CALL_CNT */
-#define OFFSET2 (off2 + RETPOLINE_RCX_BPF_JIT_SIZE)
-	EMIT2(X86_JA, OFFSET2);                   /* ja out */
+
+	offset = ctx->tail_call_indirect_label - (prog + 2 - start);
+	EMIT2(X86_JA, offset);                    /* ja out */
 	EMIT3(0x83, 0xC0, 0x01);                  /* add eax, 1 */
 	EMIT2_off32(0x89, 0x85, tcc_off);         /* mov dword ptr [rbp - tcc_off], eax */
 
@@ -471,12 +466,11 @@ static void emit_bpf_tail_call_indirect(u8 **pprog, bool *callee_regs_used,
 	 *	goto out;
 	 */
 	EMIT3(0x48, 0x85, 0xC9);                  /* test rcx,rcx */
-#define OFFSET3 (off3 + RETPOLINE_RCX_BPF_JIT_SIZE)
-	EMIT2(X86_JE, OFFSET3);                   /* je out */
 
-	*pprog = prog;
-	pop_callee_regs(pprog, callee_regs_used);
-	prog = *pprog;
+	offset = ctx->tail_call_indirect_label - (prog + 2 - start);
+	EMIT2(X86_JE, offset);                    /* je out */
+
+	pop_callee_regs(&prog, callee_regs_used);
 
 	EMIT1(0x58);                              /* pop rax */
 	if (stack_depth)
@@ -493,41 +487,21 @@ static void emit_bpf_tail_call_indirect(u8 **pprog, bool *callee_regs_used,
 	 * rdi == ctx (1st arg)
 	 * rcx == prog->bpf_func + X86_TAIL_CALL_OFFSET
 	 */
-	RETPOLINE_RCX_BPF_JIT();
+	emit_indirect_jump(&prog, 1 /* rcx */, ip + (prog - start));
 
 	/* out: */
+	ctx->tail_call_indirect_label = prog - start;
 	*pprog = prog;
 }
 
 static void emit_bpf_tail_call_direct(struct bpf_jit_poke_descriptor *poke,
-				      u8 **pprog, int addr, u8 *image,
-				      bool *callee_regs_used, u32 stack_depth)
+				      u8 **pprog, u8 *ip,
+				      bool *callee_regs_used, u32 stack_depth,
+				      struct jit_context *ctx)
 {
 	int tcc_off = -4 - round_up(stack_depth, 8);
-	u8 *prog = *pprog;
-	int pop_bytes = 0;
-	int off1 = 20;
-	int poke_off;
-
-	/* count the additional bytes used for popping callee regs to stack
-	 * that need to be taken into account for jump offset that is used for
-	 * bailing out from of the tail call when limit is reached
-	 */
-	pop_bytes = get_pop_bytes(callee_regs_used);
-	off1 += pop_bytes;
-
-	/*
-	 * total bytes for:
-	 * - nop5/ jmpq $off
-	 * - pop callee regs
-	 * - sub rsp, $val if depth > 0
-	 * - pop rax
-	 */
-	poke_off = X86_PATCH_SIZE + pop_bytes + 1;
-	if (stack_depth) {
-		poke_off += 7;
-		off1 += 7;
-	}
+	u8 *prog = *pprog, *start = *pprog;
+	int offset;
 
 	/*
 	 * if (tail_call_cnt > MAX_TAIL_CALL_CNT)
@@ -535,28 +509,30 @@ static void emit_bpf_tail_call_direct(struct bpf_jit_poke_descriptor *poke,
 	 */
 	EMIT2_off32(0x8B, 0x85, tcc_off);             /* mov eax, dword ptr [rbp - tcc_off] */
 	EMIT3(0x83, 0xF8, MAX_TAIL_CALL_CNT);         /* cmp eax, MAX_TAIL_CALL_CNT */
-	EMIT2(X86_JA, off1);                          /* ja out */
+
+	offset = ctx->tail_call_direct_label - (prog + 2 - start);
+	EMIT2(X86_JA, offset);                        /* ja out */
 	EMIT3(0x83, 0xC0, 0x01);                      /* add eax, 1 */
 	EMIT2_off32(0x89, 0x85, tcc_off);             /* mov dword ptr [rbp - tcc_off], eax */
 
-	poke->tailcall_bypass = image + (addr - poke_off - X86_PATCH_SIZE);
+	poke->tailcall_bypass = ip + (prog - start);
 	poke->adj_off = X86_TAIL_CALL_OFFSET;
-	poke->tailcall_target = image + (addr - X86_PATCH_SIZE);
+	poke->tailcall_target = ip + ctx->tail_call_direct_label - X86_PATCH_SIZE;
 	poke->bypass_addr = (u8 *)poke->tailcall_target + X86_PATCH_SIZE;
 
 	emit_jump(&prog, (u8 *)poke->tailcall_target + X86_PATCH_SIZE,
 		  poke->tailcall_bypass);
 
-	*pprog = prog;
-	pop_callee_regs(pprog, callee_regs_used);
-	prog = *pprog;
+	pop_callee_regs(&prog, callee_regs_used);
 	EMIT1(0x58);                                  /* pop rax */
 	if (stack_depth)
 		EMIT3_off32(0x48, 0x81, 0xC4, round_up(stack_depth, 8));
 
 	memcpy(prog, x86_nops[5], X86_PATCH_SIZE);
 	prog += X86_PATCH_SIZE;
+
 	/* out: */
+	ctx->tail_call_direct_label = prog - start;
 
 	*pprog = prog;
 }
@@ -1222,8 +1198,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 			/* speculation barrier */
 		case BPF_ST | BPF_NOSPEC:
 			if (boot_cpu_has(X86_FEATURE_XMM2))
-				/* Emit 'lfence' */
-				EMIT3(0x0F, 0xAE, 0xE8);
+				EMIT_LFENCE();
 			break;
 
 			/* ST: *(u8*)(dst_reg + off) = imm */
@@ -1412,13 +1387,16 @@ st:			if (is_imm8(insn->off))
 		case BPF_JMP | BPF_TAIL_CALL:
 			if (imm32)
 				emit_bpf_tail_call_direct(&bpf_prog->aux->poke_tab[imm32 - 1],
-							  &prog, addrs[i], image,
+							  &prog, image + addrs[i - 1],
 							  callee_regs_used,
-							  bpf_prog->aux->stack_depth);
+							  bpf_prog->aux->stack_depth,
+							  ctx);
 			else
 				emit_bpf_tail_call_indirect(&prog,
 							    callee_regs_used,
-							    bpf_prog->aux->stack_depth);
+							    bpf_prog->aux->stack_depth,
+							    image + addrs[i - 1],
+							    ctx);
 			break;
 
 			/* cond jump */
@@ -2124,24 +2102,6 @@ cleanup:
 	return ret;
 }
 
-static int emit_fallback_jump(u8 **pprog)
-{
-	u8 *prog = *pprog;
-	int err = 0;
-
-#ifdef CONFIG_RETPOLINE
-	/* Note that this assumes the the compiler uses external
-	 * thunks for indirect calls. Both clang and GCC use the same
-	 * naming convention for external thunks.
-	 */
-	err = emit_jump(&prog, __x86_indirect_thunk_rdx, prog);
-#else
-	EMIT2(0xFF, 0xE2);	/* jmp rdx */
-#endif
-	*pprog = prog;
-	return err;
-}
-
 static int emit_bpf_dispatcher(u8 **pprog, int a, int b, s64 *progs)
 {
 	u8 *jg_reloc, *prog = *pprog;
@@ -2163,9 +2123,7 @@ static int emit_bpf_dispatcher(u8 **pprog, int a, int b, s64 *progs)
 		if (err)
 			return err;
 
-		err = emit_fallback_jump(&prog);	/* jmp thunk/indirect */
-		if (err)
-			return err;
+		emit_indirect_jump(&prog, 2 /* rdx */, prog);
 
 		*pprog = prog;
 		return 0;
diff --git a/arch/x86/net/bpf_jit_comp32.c b/arch/x86/net/bpf_jit_comp32.c
index 3bfda5f502cb..da9b7cfa4632 100644
--- a/arch/x86/net/bpf_jit_comp32.c
+++ b/arch/x86/net/bpf_jit_comp32.c
@@ -15,6 +15,7 @@
 #include <asm/cacheflush.h>
 #include <asm/set_memory.h>
 #include <asm/nospec-branch.h>
+#include <asm/asm-prototypes.h>
 #include <linux/bpf.h>
 
 /*
@@ -1267,6 +1268,21 @@ static void emit_epilogue(u8 **pprog, u32 stack_depth)
 	*pprog = prog;
 }
 
+static int emit_jmp_edx(u8 **pprog, u8 *ip)
+{
+	u8 *prog = *pprog;
+	int cnt = 0;
+
+#ifdef CONFIG_RETPOLINE
+	EMIT1_off32(0xE9, (u8 *)__x86_indirect_thunk_edx - (ip + 5));
+#else
+	EMIT2(0xFF, 0xE2);
+#endif
+	*pprog = prog;
+
+	return cnt;
+}
+
 /*
  * Generate the following code:
  * ... bpf_tail_call(void *ctx, struct bpf_array *array, u64 index) ...
@@ -1280,7 +1296,7 @@ static void emit_epilogue(u8 **pprog, u32 stack_depth)
  *   goto *(prog->bpf_func + prologue_size);
  * out:
  */
-static void emit_bpf_tail_call(u8 **pprog)
+static void emit_bpf_tail_call(u8 **pprog, u8 *ip)
 {
 	u8 *prog = *pprog;
 	int cnt = 0;
@@ -1362,7 +1378,7 @@ static void emit_bpf_tail_call(u8 **pprog)
 	 * eax == ctx (1st arg)
 	 * edx == prog->bpf_func + prologue_size
 	 */
-	RETPOLINE_EDX_BPF_JIT();
+	cnt += emit_jmp_edx(&prog, ip + cnt);
 
 	if (jmp_label1 == -1)
 		jmp_label1 = cnt;
@@ -2122,7 +2138,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 			break;
 		}
 		case BPF_JMP | BPF_TAIL_CALL:
-			emit_bpf_tail_call(&prog);
+			emit_bpf_tail_call(&prog, image + addrs[i - 1]);
 			break;
 
 		/* cond jump */
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index a7b7d674f500..4f63117f09bb 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -283,12 +283,12 @@ static void __init xen_init_capabilities(void)
 	}
 }
 
-static void xen_set_debugreg(int reg, unsigned long val)
+static noinstr void xen_set_debugreg(int reg, unsigned long val)
 {
 	HYPERVISOR_set_debugreg(reg, val);
 }
 
-static unsigned long xen_get_debugreg(int reg)
+static noinstr unsigned long xen_get_debugreg(int reg)
 {
 	return HYPERVISOR_get_debugreg(reg);
 }
@@ -1025,52 +1025,54 @@ static const struct pv_info xen_info __initconst = {
 	.name = "Xen",
 };
 
-static const struct pv_cpu_ops xen_cpu_ops __initconst = {
-	.cpuid = xen_cpuid,
+static const typeof(pv_ops) xen_cpu_ops __initconst = {
+	.cpu = {
+		.cpuid = xen_cpuid,
 
-	.set_debugreg = xen_set_debugreg,
-	.get_debugreg = xen_get_debugreg,
+		.set_debugreg = xen_set_debugreg,
+		.get_debugreg = xen_get_debugreg,
 
-	.read_cr0 = xen_read_cr0,
-	.write_cr0 = xen_write_cr0,
+		.read_cr0 = xen_read_cr0,
+		.write_cr0 = xen_write_cr0,
 
-	.write_cr4 = xen_write_cr4,
+		.write_cr4 = xen_write_cr4,
 
-	.wbinvd = native_wbinvd,
+		.wbinvd = native_wbinvd,
 
-	.read_msr = xen_read_msr,
-	.write_msr = xen_write_msr,
+		.read_msr = xen_read_msr,
+		.write_msr = xen_write_msr,
 
-	.read_msr_safe = xen_read_msr_safe,
-	.write_msr_safe = xen_write_msr_safe,
+		.read_msr_safe = xen_read_msr_safe,
+		.write_msr_safe = xen_write_msr_safe,
 
-	.read_pmc = xen_read_pmc,
+		.read_pmc = xen_read_pmc,
 
-	.load_tr_desc = paravirt_nop,
-	.set_ldt = xen_set_ldt,
-	.load_gdt = xen_load_gdt,
-	.load_idt = xen_load_idt,
-	.load_tls = xen_load_tls,
-	.load_gs_index = xen_load_gs_index,
+		.load_tr_desc = paravirt_nop,
+		.set_ldt = xen_set_ldt,
+		.load_gdt = xen_load_gdt,
+		.load_idt = xen_load_idt,
+		.load_tls = xen_load_tls,
+		.load_gs_index = xen_load_gs_index,
 
-	.alloc_ldt = xen_alloc_ldt,
-	.free_ldt = xen_free_ldt,
+		.alloc_ldt = xen_alloc_ldt,
+		.free_ldt = xen_free_ldt,
 
-	.store_tr = xen_store_tr,
+		.store_tr = xen_store_tr,
 
-	.write_ldt_entry = xen_write_ldt_entry,
-	.write_gdt_entry = xen_write_gdt_entry,
-	.write_idt_entry = xen_write_idt_entry,
-	.load_sp0 = xen_load_sp0,
+		.write_ldt_entry = xen_write_ldt_entry,
+		.write_gdt_entry = xen_write_gdt_entry,
+		.write_idt_entry = xen_write_idt_entry,
+		.load_sp0 = xen_load_sp0,
 
 #ifdef CONFIG_X86_IOPL_IOPERM
-	.invalidate_io_bitmap = xen_invalidate_io_bitmap,
-	.update_io_bitmap = xen_update_io_bitmap,
+		.invalidate_io_bitmap = xen_invalidate_io_bitmap,
+		.update_io_bitmap = xen_update_io_bitmap,
 #endif
-	.io_delay = xen_io_delay,
+		.io_delay = xen_io_delay,
 
-	.start_context_switch = paravirt_start_context_switch,
-	.end_context_switch = xen_end_context_switch,
+		.start_context_switch = paravirt_start_context_switch,
+		.end_context_switch = xen_end_context_switch,
+	},
 };
 
 static void xen_restart(char *msg)
@@ -1211,7 +1213,7 @@ asmlinkage __visible void __init xen_start_kernel(void)
 
 	/* Install Xen paravirt ops */
 	pv_info = xen_info;
-	pv_ops.cpu = xen_cpu_ops;
+	pv_ops.cpu = xen_cpu_ops.cpu;
 	paravirt_iret = xen_iret;
 	xen_init_irq_ops();
 
diff --git a/arch/x86/xen/irq.c b/arch/x86/xen/irq.c
index dfa091d79c2e..4fe387e520af 100644
--- a/arch/x86/xen/irq.c
+++ b/arch/x86/xen/irq.c
@@ -19,12 +19,12 @@
  * callback mask. We do this in a very simple manner, by making a call
  * down into Xen. The pending flag will be checked by Xen on return.
  */
-void xen_force_evtchn_callback(void)
+noinstr void xen_force_evtchn_callback(void)
 {
 	(void)HYPERVISOR_xen_version(0, NULL);
 }
 
-asmlinkage __visible unsigned long xen_save_fl(void)
+asmlinkage __visible noinstr unsigned long xen_save_fl(void)
 {
 	struct vcpu_info *vcpu;
 	unsigned long flags;
@@ -40,9 +40,9 @@ asmlinkage __visible unsigned long xen_save_fl(void)
 	*/
 	return (-flags) & X86_EFLAGS_IF;
 }
-PV_CALLEE_SAVE_REGS_THUNK(xen_save_fl);
+__PV_CALLEE_SAVE_REGS_THUNK(xen_save_fl, ".noinstr.text");
 
-asmlinkage __visible void xen_irq_disable(void)
+asmlinkage __visible noinstr void xen_irq_disable(void)
 {
 	/* There's a one instruction preempt window here.  We need to
 	   make sure we're don't switch CPUs between getting the vcpu
@@ -51,9 +51,9 @@ asmlinkage __visible void xen_irq_disable(void)
 	this_cpu_read(xen_vcpu)->evtchn_upcall_mask = 1;
 	preempt_enable_no_resched();
 }
-PV_CALLEE_SAVE_REGS_THUNK(xen_irq_disable);
+__PV_CALLEE_SAVE_REGS_THUNK(xen_irq_disable, ".noinstr.text");
 
-asmlinkage __visible void xen_irq_enable(void)
+asmlinkage __visible noinstr void xen_irq_enable(void)
 {
 	struct vcpu_info *vcpu;
 
@@ -76,7 +76,7 @@ asmlinkage __visible void xen_irq_enable(void)
 
 	preempt_enable();
 }
-PV_CALLEE_SAVE_REGS_THUNK(xen_irq_enable);
+__PV_CALLEE_SAVE_REGS_THUNK(xen_irq_enable, ".noinstr.text");
 
 static void xen_safe_halt(void)
 {
@@ -94,17 +94,20 @@ static void xen_halt(void)
 		xen_safe_halt();
 }
 
-static const struct pv_irq_ops xen_irq_ops __initconst = {
-	.save_fl = PV_CALLEE_SAVE(xen_save_fl),
-	.irq_disable = PV_CALLEE_SAVE(xen_irq_disable),
-	.irq_enable = PV_CALLEE_SAVE(xen_irq_enable),
+static const typeof(pv_ops) xen_irq_ops __initconst = {
+	.irq = {
 
-	.safe_halt = xen_safe_halt,
-	.halt = xen_halt,
+		.save_fl = PV_CALLEE_SAVE(xen_save_fl),
+		.irq_disable = PV_CALLEE_SAVE(xen_irq_disable),
+		.irq_enable = PV_CALLEE_SAVE(xen_irq_enable),
+
+		.safe_halt = xen_safe_halt,
+		.halt = xen_halt,
+	},
 };
 
 void __init xen_init_irq_ops(void)
 {
-	pv_ops.irq = xen_irq_ops;
+	pv_ops.irq = xen_irq_ops.irq;
 	x86_init.irqs.intr_init = xen_init_IRQ;
 }
diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c
index 3359c23573c5..1ce436eeda15 100644
--- a/arch/x86/xen/mmu_pv.c
+++ b/arch/x86/xen/mmu_pv.c
@@ -1204,7 +1204,8 @@ static void __init xen_pagetable_init(void)
 	xen_remap_memory();
 	xen_setup_mfn_list_list();
 }
-static void xen_write_cr2(unsigned long cr2)
+
+static noinstr void xen_write_cr2(unsigned long cr2)
 {
 	this_cpu_read(xen_vcpu)->arch.cr2 = cr2;
 }
@@ -2078,67 +2079,69 @@ static void xen_leave_lazy_mmu(void)
 	preempt_enable();
 }
 
-static const struct pv_mmu_ops xen_mmu_ops __initconst = {
-	.read_cr2 = __PV_IS_CALLEE_SAVE(xen_read_cr2),
-	.write_cr2 = xen_write_cr2,
+static const typeof(pv_ops) xen_mmu_ops __initconst = {
+	.mmu = {
+		.read_cr2 = __PV_IS_CALLEE_SAVE(xen_read_cr2),
+		.write_cr2 = xen_write_cr2,
 
-	.read_cr3 = xen_read_cr3,
-	.write_cr3 = xen_write_cr3_init,
+		.read_cr3 = xen_read_cr3,
+		.write_cr3 = xen_write_cr3_init,
 
-	.flush_tlb_user = xen_flush_tlb,
-	.flush_tlb_kernel = xen_flush_tlb,
-	.flush_tlb_one_user = xen_flush_tlb_one_user,
-	.flush_tlb_multi = xen_flush_tlb_multi,
-	.tlb_remove_table = tlb_remove_table,
+		.flush_tlb_user = xen_flush_tlb,
+		.flush_tlb_kernel = xen_flush_tlb,
+		.flush_tlb_one_user = xen_flush_tlb_one_user,
+		.flush_tlb_multi = xen_flush_tlb_multi,
+		.tlb_remove_table = tlb_remove_table,
 
-	.pgd_alloc = xen_pgd_alloc,
-	.pgd_free = xen_pgd_free,
+		.pgd_alloc = xen_pgd_alloc,
+		.pgd_free = xen_pgd_free,
 
-	.alloc_pte = xen_alloc_pte_init,
-	.release_pte = xen_release_pte_init,
-	.alloc_pmd = xen_alloc_pmd_init,
-	.release_pmd = xen_release_pmd_init,
+		.alloc_pte = xen_alloc_pte_init,
+		.release_pte = xen_release_pte_init,
+		.alloc_pmd = xen_alloc_pmd_init,
+		.release_pmd = xen_release_pmd_init,
 
-	.set_pte = xen_set_pte_init,
-	.set_pmd = xen_set_pmd_hyper,
+		.set_pte = xen_set_pte_init,
+		.set_pmd = xen_set_pmd_hyper,
 
-	.ptep_modify_prot_start = xen_ptep_modify_prot_start,
-	.ptep_modify_prot_commit = xen_ptep_modify_prot_commit,
+		.ptep_modify_prot_start = xen_ptep_modify_prot_start,
+		.ptep_modify_prot_commit = xen_ptep_modify_prot_commit,
 
-	.pte_val = PV_CALLEE_SAVE(xen_pte_val),
-	.pgd_val = PV_CALLEE_SAVE(xen_pgd_val),
+		.pte_val = PV_CALLEE_SAVE(xen_pte_val),
+		.pgd_val = PV_CALLEE_SAVE(xen_pgd_val),
 
-	.make_pte = PV_CALLEE_SAVE(xen_make_pte_init),
-	.make_pgd = PV_CALLEE_SAVE(xen_make_pgd),
+		.make_pte = PV_CALLEE_SAVE(xen_make_pte_init),
+		.make_pgd = PV_CALLEE_SAVE(xen_make_pgd),
 
-	.set_pud = xen_set_pud_hyper,
+		.set_pud = xen_set_pud_hyper,
 
-	.make_pmd = PV_CALLEE_SAVE(xen_make_pmd),
-	.pmd_val = PV_CALLEE_SAVE(xen_pmd_val),
+		.make_pmd = PV_CALLEE_SAVE(xen_make_pmd),
+		.pmd_val = PV_CALLEE_SAVE(xen_pmd_val),
 
-	.pud_val = PV_CALLEE_SAVE(xen_pud_val),
-	.make_pud = PV_CALLEE_SAVE(xen_make_pud),
-	.set_p4d = xen_set_p4d_hyper,
+		.pud_val = PV_CALLEE_SAVE(xen_pud_val),
+		.make_pud = PV_CALLEE_SAVE(xen_make_pud),
+		.set_p4d = xen_set_p4d_hyper,
 
-	.alloc_pud = xen_alloc_pmd_init,
-	.release_pud = xen_release_pmd_init,
+		.alloc_pud = xen_alloc_pmd_init,
+		.release_pud = xen_release_pmd_init,
 
 #if CONFIG_PGTABLE_LEVELS >= 5
-	.p4d_val = PV_CALLEE_SAVE(xen_p4d_val),
-	.make_p4d = PV_CALLEE_SAVE(xen_make_p4d),
+		.p4d_val = PV_CALLEE_SAVE(xen_p4d_val),
+		.make_p4d = PV_CALLEE_SAVE(xen_make_p4d),
 #endif
 
-	.activate_mm = xen_activate_mm,
-	.dup_mmap = xen_dup_mmap,
-	.exit_mmap = xen_exit_mmap,
+		.activate_mm = xen_activate_mm,
+		.dup_mmap = xen_dup_mmap,
+		.exit_mmap = xen_exit_mmap,
 
-	.lazy_mode = {
-		.enter = paravirt_enter_lazy_mmu,
-		.leave = xen_leave_lazy_mmu,
-		.flush = paravirt_flush_lazy_mmu,
-	},
+		.lazy_mode = {
+			.enter = paravirt_enter_lazy_mmu,
+			.leave = xen_leave_lazy_mmu,
+			.flush = paravirt_flush_lazy_mmu,
+		},
 
-	.set_fixmap = xen_set_fixmap,
+		.set_fixmap = xen_set_fixmap,
+	},
 };
 
 void __init xen_init_mmu_ops(void)
@@ -2146,7 +2149,7 @@ void __init xen_init_mmu_ops(void)
 	x86_init.paging.pagetable_init = xen_pagetable_init;
 	x86_init.hyper.init_after_bootmem = xen_after_bootmem;
 
-	pv_ops.mmu = xen_mmu_ops;
+	pv_ops.mmu = xen_mmu_ops.mmu;
 
 	memset(dummy_mapping, 0xff, PAGE_SIZE);
 }
diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S
index 1e626444712b..220dd9678494 100644
--- a/arch/x86/xen/xen-asm.S
+++ b/arch/x86/xen/xen-asm.S
@@ -21,6 +21,45 @@
 #include <linux/init.h>
 #include <linux/linkage.h>
 
+.pushsection .noinstr.text, "ax"
+/*
+ * Disabling events is simply a matter of making the event mask
+ * non-zero.
+ */
+SYM_FUNC_START(xen_irq_disable_direct)
+	movb $1, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_mask
+	ret
+SYM_FUNC_END(xen_irq_disable_direct)
+
+/*
+ * Force an event check by making a hypercall, but preserve regs
+ * before making the call.
+ */
+SYM_FUNC_START(check_events)
+	FRAME_BEGIN
+	push %rax
+	push %rcx
+	push %rdx
+	push %rsi
+	push %rdi
+	push %r8
+	push %r9
+	push %r10
+	push %r11
+	call xen_force_evtchn_callback
+	pop %r11
+	pop %r10
+	pop %r9
+	pop %r8
+	pop %rdi
+	pop %rsi
+	pop %rdx
+	pop %rcx
+	pop %rax
+	FRAME_END
+	ret
+SYM_FUNC_END(check_events)
+
 /*
  * Enable events.  This clears the event mask and tests the pending
  * event status with one and operation.  If there are pending events,
@@ -47,16 +86,6 @@ SYM_FUNC_START(xen_irq_enable_direct)
 	ret
 SYM_FUNC_END(xen_irq_enable_direct)
 
-
-/*
- * Disabling events is simply a matter of making the event mask
- * non-zero.
- */
-SYM_FUNC_START(xen_irq_disable_direct)
-	movb $1, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_mask
-	ret
-SYM_FUNC_END(xen_irq_disable_direct)
-
 /*
  * (xen_)save_fl is used to get the current interrupt enable status.
  * Callers expect the status to be in X86_EFLAGS_IF, and other bits
@@ -73,35 +102,6 @@ SYM_FUNC_START(xen_save_fl_direct)
 	ret
 SYM_FUNC_END(xen_save_fl_direct)
 
-/*
- * Force an event check by making a hypercall, but preserve regs
- * before making the call.
- */
-SYM_FUNC_START(check_events)
-	FRAME_BEGIN
-	push %rax
-	push %rcx
-	push %rdx
-	push %rsi
-	push %rdi
-	push %r8
-	push %r9
-	push %r10
-	push %r11
-	call xen_force_evtchn_callback
-	pop %r11
-	pop %r10
-	pop %r9
-	pop %r8
-	pop %rdi
-	pop %rsi
-	pop %rdx
-	pop %rcx
-	pop %rax
-	FRAME_END
-	ret
-SYM_FUNC_END(check_events)
-
 SYM_FUNC_START(xen_read_cr2)
 	FRAME_BEGIN
 	_ASM_MOV PER_CPU_VAR(xen_vcpu), %_ASM_AX
@@ -116,6 +116,7 @@ SYM_FUNC_START(xen_read_cr2_direct)
 	FRAME_END
 	ret
 SYM_FUNC_END(xen_read_cr2_direct);
+.popsection
 
 .macro xen_pv_trap name
 SYM_CODE_START(xen_\name)
diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S
index cb6538ae2fe0..9e27b86a0c31 100644
--- a/arch/x86/xen/xen-head.S
+++ b/arch/x86/xen/xen-head.S
@@ -20,6 +20,23 @@
 #include <xen/interface/xen-mca.h>
 #include <asm/xen/interface.h>
 
+.pushsection .noinstr.text, "ax"
+	.balign PAGE_SIZE
+SYM_CODE_START(hypercall_page)
+	.rept (PAGE_SIZE / 32)
+		UNWIND_HINT_FUNC
+		.skip 31, 0x90
+		ret
+	.endr
+
+#define HYPERCALL(n) \
+	.equ xen_hypercall_##n, hypercall_page + __HYPERVISOR_##n * 32; \
+	.type xen_hypercall_##n, @function; .size xen_hypercall_##n, 32
+#include <asm/xen-hypercalls.h>
+#undef HYPERCALL
+SYM_CODE_END(hypercall_page)
+.popsection
+
 #ifdef CONFIG_XEN_PV
 	__INIT
 SYM_CODE_START(startup_xen)
@@ -64,23 +81,6 @@ SYM_CODE_END(asm_cpu_bringup_and_idle)
 #endif
 #endif
 
-.pushsection .text
-	.balign PAGE_SIZE
-SYM_CODE_START(hypercall_page)
-	.rept (PAGE_SIZE / 32)
-		UNWIND_HINT_FUNC
-		.skip 31, 0x90
-		ret
-	.endr
-
-#define HYPERCALL(n) \
-	.equ xen_hypercall_##n, hypercall_page + __HYPERVISOR_##n * 32; \
-	.type xen_hypercall_##n, @function; .size xen_hypercall_##n, 32
-#include <asm/xen-hypercalls.h>
-#undef HYPERCALL
-SYM_CODE_END(hypercall_page)
-.popsection
-
 	ELFNOTE(Xen, XEN_ELFNOTE_GUEST_OS,       .asciz "linux")
 	ELFNOTE(Xen, XEN_ELFNOTE_GUEST_VERSION,  .asciz "2.6")
 	ELFNOTE(Xen, XEN_ELFNOTE_XEN_VERSION,    .asciz "xen-3.0")