arm64: bpf: Annotate JITed code for BTI

In order to extend the protection offered by BTI to all code executing in
kernel mode we need to annotate JITed BPF code appropriately for BTI. To
do this we need to add a landing pad to the start of each BPF function and
also immediately after the function prologue if we are emitting a function
which can be tail called. Jumps within BPF functions are all to immediate
offsets and therefore do not require landing pads.
Signed-off-by: Mark Brown <broonie@kernel.org>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Link: https://lore.kernel.org/r/20200506195138.22086-6-broonie@kernel.orgSigned-off-by: Will Deacon <will@kernel.org>

arch/arm64/net/bpf_jit.h

@@ -189,4 +189,12 @@
 /* Rn & Rm; set condition flags */
 #define A64_TST(sf, Rn, Rm) A64_ANDS(sf, A64_ZR, Rn, Rm)
 
+/* HINTs */
+#define A64_HINT(x) aarch64_insn_gen_hint(x)
+
+/* BTI */
+#define A64_BTI_C  A64_HINT(AARCH64_INSN_HINT_BTIC)
+#define A64_BTI_J  A64_HINT(AARCH64_INSN_HINT_BTIJ)
+#define A64_BTI_JC A64_HINT(AARCH64_INSN_HINT_BTIJC)
+
 #endif /* _BPF_JIT_H */

arch/arm64/net/bpf_jit_comp.c

@@ -171,7 +171,11 @@ static inline int epilogue_offset(const struct jit_ctx *ctx)
 #define STACK_ALIGN(sz) (((sz) + 15) & ~15)
 
 /* Tail call offset to jump into */
+#if IS_ENABLED(CONFIG_ARM64_BTI_KERNEL)
+#define PROLOGUE_OFFSET 8
+#else
 #define PROLOGUE_OFFSET 7
+#endif
 
 static int build_prologue(struct jit_ctx *ctx, bool ebpf_from_cbpf)
 {
@@ -208,6 +212,10 @@ static int build_prologue(struct jit_ctx *ctx, bool ebpf_from_cbpf)
 	 *
 	 */
 
+	/* BTI landing pad */
+	if (IS_ENABLED(CONFIG_ARM64_BTI_KERNEL))
+		emit(A64_BTI_C, ctx);
+
 	/* Save FP and LR registers to stay align with ARM64 AAPCS */
 	emit(A64_PUSH(A64_FP, A64_LR, A64_SP), ctx);
 	emit(A64_MOV(1, A64_FP, A64_SP), ctx);
@@ -230,6 +238,10 @@ static int build_prologue(struct jit_ctx *ctx, bool ebpf_from_cbpf)
 				    cur_offset, PROLOGUE_OFFSET);
 			return -1;
 		}
+
+		/* BTI landing pad for the tail call, done with a BR */
+		if (IS_ENABLED(CONFIG_ARM64_BTI_KERNEL))
+			emit(A64_BTI_J, ctx);
 	}
 
 	ctx->stack_size = STACK_ALIGN(prog->aux->stack_depth);