@@ -1602,6 +1602,9 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
rn = arm_bpf_get_reg32(src_lo, tmp2[1], ctx);
emit_ldx_r(dst, rn, off, ctx, BPF_SIZE(code));
break;
+ /* speculation barrier */
+ case BPF_ST | BPF_NOSPEC:
+ break;
/* ST: *(size *)(dst + off) = imm */
case BPF_ST | BPF_MEM | BPF_W:
case BPF_ST | BPF_MEM | BPF_H:
@@ -701,6 +701,19 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
}
break;
+ /* speculation barrier */
+ case BPF_ST | BPF_NOSPEC:
+ /*
+ * Nothing required here.
+ *
+ * In case of arm64, we rely on the firmware mitigation of
+ * Speculative Store Bypass as controlled via the ssbd kernel
+ * parameter. Whenever the mitigation is enabled, it works
+ * for all of the kernel code with no need to provide any
+ * additional instructions.
+ */
+ break;
+
/* ST: *(size *)(dst + off) = imm */
case BPF_ST | BPF_MEM | BPF_W:
case BPF_ST | BPF_MEM | BPF_H:
@@ -1355,6 +1355,9 @@ static int build_one_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
}
break;
+ case BPF_ST | BPF_NOSPEC: /* speculation barrier */
+ break;
+
case BPF_ST | BPF_B | BPF_MEM:
case BPF_ST | BPF_H | BPF_MEM:
case BPF_ST | BPF_W | BPF_MEM:
@@ -644,6 +644,12 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
}
break;
+ /*
+ * BPF_ST NOSPEC (speculation barrier)
+ */
+ case BPF_ST | BPF_NOSPEC:
+ break;
+
/*
* BPF_ST(X)
*/
@@ -1313,6 +1313,10 @@ static int emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
emit(rv_ld(rd, 0, RV_REG_T1), ctx);
break;
+ /* speculation barrier */
+ case BPF_ST | BPF_NOSPEC:
+ break;
+
/* ST: *(size *)(dst + off) = imm */
case BPF_ST | BPF_MEM | BPF_B:
emit_imm(RV_REG_T1, imm, ctx);
@@ -913,6 +913,11 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp,
break;
}
break;
+ /*
+ * BPF_NOSPEC (speculation barrier)
+ */
+ case BPF_ST | BPF_NOSPEC:
+ break;
/*
* BPF_ST(X)
*/
@@ -1287,6 +1287,9 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
return 1;
break;
}
+ /* speculation barrier */
+ case BPF_ST | BPF_NOSPEC:
+ break;
/* ST: *(size *)(dst + off) = imm */
case BPF_ST | BPF_MEM | BPF_W:
case BPF_ST | BPF_MEM | BPF_H:
@@ -728,6 +728,13 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
}
break;
+ /* speculation barrier */
+ case BPF_ST | BPF_NOSPEC:
+ if (boot_cpu_has(X86_FEATURE_XMM2))
+ /* Emit 'lfence' */
+ EMIT3(0x0F, 0xAE, 0xE8);
+ break;
+
/* ST: *(u8*)(dst_reg + off) = imm */
case BPF_ST | BPF_MEM | BPF_B:
if (is_ereg(dst_reg))
@@ -1705,6 +1705,12 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
i++;
break;
}
+ /* speculation barrier */
+ case BPF_ST | BPF_NOSPEC:
+ if (boot_cpu_has(X86_FEATURE_XMM2))
+ /* Emit 'lfence' */
+ EMIT3(0x0F, 0xAE, 0xE8);
+ break;
/* ST: *(u8*)(dst_reg + off) = imm */
case BPF_ST | BPF_MEM | BPF_H:
case BPF_ST | BPF_MEM | BPF_B:
@@ -68,6 +68,11 @@ struct ctl_table_header;
/* unused opcode to mark call to interpreter with arguments */
#define BPF_CALL_ARGS 0xe0
+/* unused opcode to mark speculation barrier for mitigating
+ * Speculative Store Bypass
+ */
+#define BPF_NOSPEC 0xc0
+
/* As per nm, we expose JITed images as text (code) section for
* kallsyms. That way, tools like perf can find it to match
* addresses.
@@ -368,6 +373,16 @@ static inline bool insn_is_zext(const struct bpf_insn *insn)
.off = 0, \
.imm = 0 })
+/* Speculation barrier */
+
+#define BPF_ST_NOSPEC() \
+ ((struct bpf_insn) { \
+ .code = BPF_ST | BPF_NOSPEC, \
+ .dst_reg = 0, \
+ .src_reg = 0, \
+ .off = 0, \
+ .imm = 0 })
+
/* Internal classic blocks for direct assignment */
#define __BPF_STMT(CODE, K) \
@@ -31,6 +31,7 @@
#include <linux/rcupdate.h>
#include <linux/perf_event.h>
+#include <asm/barrier.h>
#include <asm/unaligned.h>
/* Registers */
@@ -1310,6 +1311,7 @@ static u64 ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn, u64 *stack)
/* Non-UAPI available opcodes. */
[BPF_JMP | BPF_CALL_ARGS] = &&JMP_CALL_ARGS,
[BPF_JMP | BPF_TAIL_CALL] = &&JMP_TAIL_CALL,
+ [BPF_ST | BPF_NOSPEC] = &&ST_NOSPEC,
};
#undef BPF_INSN_3_LBL
#undef BPF_INSN_2_LBL
@@ -1550,7 +1552,21 @@ static u64 ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn, u64 *stack)
COND_JMP(s, JSGE, >=)
COND_JMP(s, JSLE, <=)
#undef COND_JMP
- /* STX and ST and LDX*/
+ /* ST, STX and LDX*/
+ ST_NOSPEC:
+ /* Speculation barrier for mitigating Speculative Store Bypass.
+ * In case of arm64, we rely on the firmware mitigation as
+ * controlled via the ssbd kernel parameter. Whenever the
+ * mitigation is enabled, it works for all of the kernel code
+ * with no need to provide any additional instructions here.
+ * In case of x86, we use 'lfence' insn for mitigation. We
+ * reuse preexisting logic from Spectre v1 mitigation that
+ * happens to produce the required code on x86 for v4 as well.
+ */
+#ifdef CONFIG_X86
+ barrier_nospec();
+#endif
+ CONT;
#define LDST(SIZEOP, SIZE) \
STX_MEM_##SIZEOP: \
*(SIZE *)(unsigned long) (DST + insn->off) = SRC; \
@@ -162,15 +162,17 @@ void print_bpf_insn(const struct bpf_insn_cbs *cbs,
else
verbose(cbs->private_data, "BUG_%02x\n", insn->code);
} else if (class == BPF_ST) {
- if (BPF_MODE(insn->code) != BPF_MEM) {
+ if (BPF_MODE(insn->code) == BPF_MEM) {
+ verbose(cbs->private_data, "(%02x) *(%s *)(r%d %+d) = %d\n",
+ insn->code,
+ bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
+ insn->dst_reg,
+ insn->off, insn->imm);
+ } else if (BPF_MODE(insn->code) == 0xc0 /* BPF_NOSPEC, no UAPI */) {
+ verbose(cbs->private_data, "(%02x) nospec\n", insn->code);
+ } else {
verbose(cbs->private_data, "BUG_st_%02x\n", insn->code);
- return;
}
- verbose(cbs->private_data, "(%02x) *(%s *)(r%d %+d) = %d\n",
- insn->code,
- bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
- insn->dst_reg,
- insn->off, insn->imm);
} else if (class == BPF_LDX) {
if (BPF_MODE(insn->code) != BPF_MEM) {
verbose(cbs->private_data, "BUG_ldx_%02x\n", insn->code);