x86/bpf: Emit call depth accounting if required

Ensure that calls in BPF jitted programs are emitting call depth accounting
when enabled to keep the call/return balanced. The return thunk jump is
already injected due to the earlier retbleed mitigations.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20220915111148.615413406@infradead.org

arch/x86/include/asm/alternative.h

@@ -93,6 +93,7 @@ extern void callthunks_patch_module_calls(struct callthunk_sites *sites,
 					  struct module *mod);
 extern void *callthunks_translate_call_dest(void *dest);
 extern bool is_callthunk(void *addr);
+extern int x86_call_depth_emit_accounting(u8 **pprog, void *func);
 #else
 static __always_inline void callthunks_patch_builtin_calls(void) {}
 static __always_inline void
@@ -106,6 +107,11 @@ static __always_inline bool is_callthunk(void *addr)
 {
 	return false;
 }
+static __always_inline int x86_call_depth_emit_accounting(u8 **pprog,
+							  void *func)
+{
+	return 0;
+}
 #endif
 
 #ifdef CONFIG_SMP

arch/x86/kernel/callthunks.c

@@ -306,6 +306,25 @@ bool is_callthunk(void *addr)
 	return !bcmp((void *)(dest - tmpl_size), tmpl, tmpl_size);
 }
 
+#ifdef CONFIG_BPF_JIT
+int x86_call_depth_emit_accounting(u8 **pprog, void *func)
+{
+	unsigned int tmpl_size = SKL_TMPL_SIZE;
+	void *tmpl = skl_call_thunk_template;
+
+	if (!thunks_initialized)
+		return 0;
+
+	/* Is function call target a thunk? */
+	if (is_callthunk(func))
+		return 0;
+
+	memcpy(*pprog, tmpl, tmpl_size);
+	*pprog += tmpl_size;
+	return tmpl_size;
+}
+#endif
+
 #ifdef CONFIG_MODULES
 void noinline callthunks_patch_module_calls(struct callthunk_sites *cs,
 					    struct module *mod)

arch/x86/net/bpf_jit_comp.c

@@ -340,6 +340,13 @@ static int emit_call(u8 **pprog, void *func, void *ip)
 	return emit_patch(pprog, func, ip, 0xE8);
 }
 
+static int emit_rsb_call(u8 **pprog, void *func, void *ip)
+{
+	OPTIMIZER_HIDE_VAR(func);
+	x86_call_depth_emit_accounting(pprog, func);
+	return emit_patch(pprog, func, ip, 0xE8);
+}
+
 static int emit_jump(u8 **pprog, void *func, void *ip)
 {
 	return emit_patch(pprog, func, ip, 0xE9);
@@ -1436,19 +1443,26 @@ st:			if (is_imm8(insn->off))
 			break;
 
 			/* call */
-		case BPF_JMP | BPF_CALL:
+		case BPF_JMP | BPF_CALL: {
+			int offs;
+
 			func = (u8 *) __bpf_call_base + imm32;
 			if (tail_call_reachable) {
 				/* mov rax, qword ptr [rbp - rounded_stack_depth - 8] */
 				EMIT3_off32(0x48, 0x8B, 0x85,
 					    -round_up(bpf_prog->aux->stack_depth, 8) - 8);
-				if (!imm32 || emit_call(&prog, func, image + addrs[i - 1] + 7))
+				if (!imm32)
 					return -EINVAL;
+				offs = 7 + x86_call_depth_emit_accounting(&prog, func);
 			} else {
-				if (!imm32 || emit_call(&prog, func, image + addrs[i - 1]))
+				if (!imm32)
 					return -EINVAL;
+				offs = x86_call_depth_emit_accounting(&prog, func);
 			}
+			if (emit_call(&prog, func, image + addrs[i - 1] + offs))
+				return -EINVAL;
 			break;
+		}
 
 		case BPF_JMP | BPF_TAIL_CALL:
 			if (imm32)
@@ -1854,7 +1868,7 @@ static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog,
 	/* arg2: lea rsi, [rbp - ctx_cookie_off] */
 	EMIT4(0x48, 0x8D, 0x75, -run_ctx_off);
 
-	if (emit_call(&prog, enter, prog))
+	if (emit_rsb_call(&prog, enter, prog))
 		return -EINVAL;
 	/* remember prog start time returned by __bpf_prog_enter */
 	emit_mov_reg(&prog, true, BPF_REG_6, BPF_REG_0);
@@ -1875,7 +1889,7 @@ static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog,
 			       (long) p->insnsi >> 32,
 			       (u32) (long) p->insnsi);
 	/* call JITed bpf program or interpreter */
-	if (emit_call(&prog, p->bpf_func, prog))
+	if (emit_rsb_call(&prog, p->bpf_func, prog))
 		return -EINVAL;
 
 	/*
@@ -1899,7 +1913,7 @@ static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog,
 	emit_mov_reg(&prog, true, BPF_REG_2, BPF_REG_6);
 	/* arg3: lea rdx, [rbp - run_ctx_off] */
 	EMIT4(0x48, 0x8D, 0x55, -run_ctx_off);
-	if (emit_call(&prog, exit, prog))
+	if (emit_rsb_call(&prog, exit, prog))
 		return -EINVAL;
 
 	*pprog = prog;
@@ -2147,7 +2161,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
 	if (flags & BPF_TRAMP_F_CALL_ORIG) {
 		/* arg1: mov rdi, im */
 		emit_mov_imm64(&prog, BPF_REG_1, (long) im >> 32, (u32) (long) im);
-		if (emit_call(&prog, __bpf_tramp_enter, prog)) {
+		if (emit_rsb_call(&prog, __bpf_tramp_enter, prog)) {
 			ret = -EINVAL;
 			goto cleanup;
 		}
@@ -2179,7 +2193,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
 			EMIT2(0xff, 0xd0); /* call *rax */
 		} else {
 			/* call original function */
-			if (emit_call(&prog, orig_call, prog)) {
+			if (emit_rsb_call(&prog, orig_call, prog)) {
 				ret = -EINVAL;
 				goto cleanup;
 			}
@@ -2223,7 +2237,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
 		im->ip_epilogue = prog;
 		/* arg1: mov rdi, im */
 		emit_mov_imm64(&prog, BPF_REG_1, (long) im >> 32, (u32) (long) im);
-		if (emit_call(&prog, __bpf_tramp_exit, prog)) {
+		if (emit_rsb_call(&prog, __bpf_tramp_exit, prog)) {
 			ret = -EINVAL;
 			goto cleanup;
 		}