arch/x86/include/asm/nospec-branch.h

/* SPDX-License-Identifier: GPL-2.0 */

#ifndef _ASM_X86_NOSPEC_BRANCH_H_
#define _ASM_X86_NOSPEC_BRANCH_H_

#include <linux/static_key.h>

#include <asm/alternative.h>
#include <asm/alternative-asm.h>
#include <asm/cpufeatures.h>
#include <asm/msr-index.h>

/*
 * This should be used immediately before a retpoline alternative. It tells
 * objtool where the retpolines are so that it can make sense of the control
 * flow by just reading the original instruction(s) and ignoring the
 * alternatives.
 */
#define ANNOTATE_NOSPEC_ALTERNATIVE \
	ANNOTATE_IGNORE_ALTERNATIVE

/*
 * Fill the CPU return stack buffer.
 *
 * Each entry in the RSB, if used for a speculative 'ret', contains an
 * infinite 'pause; lfence; jmp' loop to capture speculative execution.
 *
 * This is required in various cases for retpoline and IBRS-based
 * mitigations for the Spectre variant 2 vulnerability. Sometimes to
 * eliminate potentially bogus entries from the RSB, and sometimes
 * purely to ensure that it doesn't get empty, which on some CPUs would
 * allow predictions from other (unwanted!) sources to be used.
 *
 * We define a CPP macro such that it can be used from both .S files and
 * inline assembly. It's possible to do a .macro and then include that
 * from C via asm(".include <asm/nospec-branch.h>") but let's not go there.
 */

#define RSB_CLEAR_LOOPS		32	/* To forcibly overwrite all entries */
#define RSB_FILL_LOOPS		16	/* To avoid underflow */

/*
 * Google experimented with loop-unrolling and this turned out to be
 * the optimal version — two calls, each with their own speculation
 * trap should their return address end up getting used, in a loop.
 */
#define __FILL_RETURN_BUFFER(reg, nr, sp)	\
	mov	$(nr/2), reg;			\
771:						\
	call	772f;				\
773:	/* speculation trap */			\
	pause;					\
	lfence;					\
	jmp	773b;				\
772:						\
	call	774f;				\
775:	/* speculation trap */			\
	pause;					\
	lfence;					\
	jmp	775b;				\
774:						\
	dec	reg;				\
	jnz	771b;				\
	add	$(BITS_PER_LONG/8) * nr, sp;

#ifdef __ASSEMBLY__

/*
 * This should be used immediately before an indirect jump/call. It tells
 * objtool the subsequent indirect jump/call is vouched safe for retpoline
 * builds.
 */
.macro ANNOTATE_RETPOLINE_SAFE
	.Lannotate_\@:
	.pushsection .discard.retpoline_safe
	_ASM_PTR .Lannotate_\@
	.popsection
.endm

/*
 * These are the bare retpoline primitives for indirect jmp and call.
 * Do not use these directly; they only exist to make the ALTERNATIVE
 * invocation below less ugly.
 */
.macro RETPOLINE_JMP reg:req
	call	.Ldo_rop_\@
.Lspec_trap_\@:
	pause
	lfence
	jmp	.Lspec_trap_\@
.Ldo_rop_\@:
	mov	\reg, (%_ASM_SP)
	ret
.endm

/*
 * This is a wrapper around RETPOLINE_JMP so the called function in reg
 * returns to the instruction after the macro.
 */
.macro RETPOLINE_CALL reg:req
	jmp	.Ldo_call_\@
.Ldo_retpoline_jmp_\@:
	RETPOLINE_JMP \reg
.Ldo_call_\@:
	call	.Ldo_retpoline_jmp_\@
.endm

/*
 * JMP_NOSPEC and CALL_NOSPEC macros can be used instead of a simple
 * indirect jmp/call which may be susceptible to the Spectre variant 2
 * attack.
 */
.macro JMP_NOSPEC reg:req
#ifdef CONFIG_RETPOLINE
	ANNOTATE_NOSPEC_ALTERNATIVE
	ALTERNATIVE_2 __stringify(ANNOTATE_RETPOLINE_SAFE; jmp *\reg),	\
		__stringify(RETPOLINE_JMP \reg), X86_FEATURE_RETPOLINE,	\
		__stringify(lfence; ANNOTATE_RETPOLINE_SAFE; jmp *\reg), X86_FEATURE_RETPOLINE_AMD
#else
	jmp	*\reg
#endif
.endm

.macro CALL_NOSPEC reg:req
#ifdef CONFIG_RETPOLINE
	ANNOTATE_NOSPEC_ALTERNATIVE
	ALTERNATIVE_2 __stringify(ANNOTATE_RETPOLINE_SAFE; call *\reg),	\
		__stringify(RETPOLINE_CALL \reg), X86_FEATURE_RETPOLINE,\
		__stringify(lfence; ANNOTATE_RETPOLINE_SAFE; call *\reg), X86_FEATURE_RETPOLINE_AMD
#else
	call	*\reg
#endif
.endm

 /*
  * A simpler FILL_RETURN_BUFFER macro. Don't make people use the CPP
  * monstrosity above, manually.
  */
.macro FILL_RETURN_BUFFER reg:req nr:req ftr:req
#ifdef CONFIG_RETPOLINE
	ANNOTATE_NOSPEC_ALTERNATIVE
	ALTERNATIVE "jmp .Lskip_rsb_\@",				\
		__stringify(__FILL_RETURN_BUFFER(\reg,\nr,%_ASM_SP))	\
		\ftr
.Lskip_rsb_\@:
#endif
.endm

#else /* __ASSEMBLY__ */

#define ANNOTATE_RETPOLINE_SAFE					\
	"999:\n\t"						\
	".pushsection .discard.retpoline_safe\n\t"		\
	_ASM_PTR " 999b\n\t"					\
	".popsection\n\t"

#ifdef CONFIG_RETPOLINE
#ifdef CONFIG_X86_64

/*
 * Inline asm uses the %V modifier which is only in newer GCC
 * which is ensured when CONFIG_RETPOLINE is defined.
 */
# define CALL_NOSPEC						\
	ANNOTATE_NOSPEC_ALTERNATIVE				\
	ALTERNATIVE_2(						\
	ANNOTATE_RETPOLINE_SAFE					\
	"call *%[thunk_target]\n",				\
	"call __x86_indirect_thunk_%V[thunk_target]\n",		\
	X86_FEATURE_RETPOLINE,					\
	"lfence;\n"						\
	ANNOTATE_RETPOLINE_SAFE					\
	"call *%[thunk_target]\n",				\
	X86_FEATURE_RETPOLINE_AMD)
# define THUNK_TARGET(addr) [thunk_target] "r" (addr)

#else /* CONFIG_X86_32 */
/*
 * For i386 we use the original ret-equivalent retpoline, because
 * otherwise we'll run out of registers. We don't care about CET
 * here, anyway.
 */
# define CALL_NOSPEC						\
	ANNOTATE_NOSPEC_ALTERNATIVE				\
	ALTERNATIVE_2(						\
	ANNOTATE_RETPOLINE_SAFE					\
	"call *%[thunk_target]\n",				\
	"       jmp    904f;\n"					\
	"       .align 16\n"					\
	"901:	call   903f;\n"					\
	"902:	pause;\n"					\
	"    	lfence;\n"					\
	"       jmp    902b;\n"					\
	"       .align 16\n"					\
	"903:	addl   $4, %%esp;\n"				\
	"       pushl  %[thunk_target];\n"			\
	"       ret;\n"						\
	"       .align 16\n"					\
	"904:	call   901b;\n",				\
	X86_FEATURE_RETPOLINE,					\
	"lfence;\n"						\
	ANNOTATE_RETPOLINE_SAFE					\
	"call *%[thunk_target]\n",				\
	X86_FEATURE_RETPOLINE_AMD)

# define THUNK_TARGET(addr) [thunk_target] "rm" (addr)
#endif
#else /* No retpoline for C / inline asm */
# define CALL_NOSPEC "call *%[thunk_target]\n"
# define THUNK_TARGET(addr) [thunk_target] "rm" (addr)
#endif

/* The Spectre V2 mitigation variants */
enum spectre_v2_mitigation {
	SPECTRE_V2_NONE,
	SPECTRE_V2_RETPOLINE_GENERIC,
	SPECTRE_V2_RETPOLINE_AMD,
	SPECTRE_V2_IBRS_ENHANCED,
};

/* The indirect branch speculation control variants */
enum spectre_v2_user_mitigation {
	SPECTRE_V2_USER_NONE,
	SPECTRE_V2_USER_STRICT,
	SPECTRE_V2_USER_STRICT_PREFERRED,
	SPECTRE_V2_USER_PRCTL,
	SPECTRE_V2_USER_SECCOMP,
};

/* The Speculative Store Bypass disable variants */
enum ssb_mitigation {
	SPEC_STORE_BYPASS_NONE,
	SPEC_STORE_BYPASS_DISABLE,
	SPEC_STORE_BYPASS_PRCTL,
	SPEC_STORE_BYPASS_SECCOMP,
};

extern char __indirect_thunk_start[];
extern char __indirect_thunk_end[];

/*
 * On VMEXIT we must ensure that no RSB predictions learned in the guest
 * can be followed in the host, by overwriting the RSB completely. Both
 * retpoline and IBRS mitigations for Spectre v2 need this; only on future
 * CPUs with IBRS_ALL *might* it be avoided.
 */
static inline void vmexit_fill_RSB(void)
{
#ifdef CONFIG_RETPOLINE
	unsigned long loops;

	asm volatile (ANNOTATE_NOSPEC_ALTERNATIVE
		      ALTERNATIVE("jmp 910f",
				  __stringify(__FILL_RETURN_BUFFER(%0, RSB_CLEAR_LOOPS, %1)),
				  X86_FEATURE_RETPOLINE)
		      "910:"
		      : "=r" (loops), ASM_CALL_CONSTRAINT
		      : : "memory" );
#endif
}

static __always_inline
void alternative_msr_write(unsigned int msr, u64 val, unsigned int feature)
{
	asm volatile(ALTERNATIVE("", "wrmsr", %c[feature])
		: : "c" (msr),
		    "a" ((u32)val),
		    "d" ((u32)(val >> 32)),
		    [feature] "i" (feature)
		: "memory");
}

static inline void indirect_branch_prediction_barrier(void)
{
	u64 val = PRED_CMD_IBPB;

	alternative_msr_write(MSR_IA32_PRED_CMD, val, X86_FEATURE_USE_IBPB);
}

/* The Intel SPEC CTRL MSR base value cache */
extern u64 x86_spec_ctrl_base;

/*
 * With retpoline, we must use IBRS to restrict branch prediction
 * before calling into firmware.
 *
 * (Implemented as CPP macros due to header hell.)
 */
#define firmware_restrict_branch_speculation_start()			\
do {									\
	u64 val = x86_spec_ctrl_base | SPEC_CTRL_IBRS;			\
									\
	preempt_disable();						\
	alternative_msr_write(MSR_IA32_SPEC_CTRL, val,			\
			      X86_FEATURE_USE_IBRS_FW);			\
} while (0)

#define firmware_restrict_branch_speculation_end()			\
do {									\
	u64 val = x86_spec_ctrl_base;					\
									\
	alternative_msr_write(MSR_IA32_SPEC_CTRL, val,			\
			      X86_FEATURE_USE_IBRS_FW);			\
	preempt_enable();						\
} while (0)

DECLARE_STATIC_KEY_FALSE(switch_to_cond_stibp);
DECLARE_STATIC_KEY_FALSE(switch_mm_cond_ibpb);
DECLARE_STATIC_KEY_FALSE(switch_mm_always_ibpb);

#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 %rax,(%rsp) for x86_64
 *    mov %edx,(%esp) for x86_32
 *    retq
 *
 * Without retpolines configured:
 *
 *    jmp *%rax for x86_64
 *    jmp *%edx for x86_32
 */
#ifdef CONFIG_RETPOLINE
# ifdef CONFIG_X86_64
#  define RETPOLINE_RAX_BPF_JIT_SIZE	17
#  define RETPOLINE_RAX_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, 0x04, 0x24); /* mov %rax,(%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_RAX_BPF_JIT_SIZE	2
#  define RETPOLINE_RAX_BPF_JIT()				\
	EMIT2(0xFF, 0xE0);       /* jmp *%rax */
# else /* !CONFIG_X86_64 */
#  define RETPOLINE_EDX_BPF_JIT()				\
	EMIT2(0xFF, 0xE2)        /* jmp *%edx */
# endif
#endif

#endif /* _ASM_X86_NOSPEC_BRANCH_H_ */