[PATCH v3 55/59] x86/bpf: Emit call depth accounting if required

From: Peter Zijlstra
Date: Thu Sep 15 2022 - 07:44:26 EST


From: Thomas Gleixner <tglx@xxxxxxxxxxxxx>

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@xxxxxxxxxxxxx>
Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Cc: Alexei Starovoitov <ast@xxxxxxxxxx>
Cc: Daniel Borkmann <daniel@xxxxxxxxxxxxx>
---
arch/x86/include/asm/alternative.h | 6 ++++++
arch/x86/kernel/callthunks.c | 19 +++++++++++++++++++
arch/x86/net/bpf_jit_comp.c | 32 +++++++++++++++++++++++---------
3 files changed, 48 insertions(+), 9 deletions(-)

--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -93,6 +93,7 @@ extern void callthunks_patch_module_call
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
{
return false;
}
+static __always_inline int x86_call_depth_emit_accounting(u8 **pprog,
+ void *func)
+{
+ return 0;
+}
#endif

#ifdef CONFIG_SMP
--- a/arch/x86/kernel/callthunks.c
+++ b/arch/x86/kernel/callthunks.c
@@ -305,6 +305,25 @@ 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)
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -340,6 +340,13 @@ static int emit_call(u8 **pprog, void *f
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);
@@ -1434,19 +1441,26 @@ 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)
@@ -1823,7 +1837,7 @@ static int invoke_bpf_prog(const struct
/* 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);
@@ -1844,7 +1858,7 @@ static int invoke_bpf_prog(const struct
(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;

/*
@@ -1868,7 +1882,7 @@ static int invoke_bpf_prog(const struct
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;
@@ -2109,7 +2123,7 @@ int arch_prepare_bpf_trampoline(struct b
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;
}
@@ -2141,7 +2155,7 @@ int arch_prepare_bpf_trampoline(struct b
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;
}
@@ -2185,7 +2199,7 @@ int arch_prepare_bpf_trampoline(struct b
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;
}