[PATCH bpf-next 1/5] bpf, riscv: Fix stack-passed arguments for indirect trampolines

[Pu Lehui]

From: Kumar Kartikeya Dwivedi <memxor at gmail.com>

store_args() reads stack-passed arguments relative to FP assuming the
trampoline was entered through the fentry call from a traced function. In
that path, the trampoline pushes the parent frame before establishing its
final FP, so the incoming stack arguments start at FP + 16.

An indirect trampoline for a struct_ops callback is called through a
function pointer. Its prologue allocates only the trampoline frame and sets
FP to the incoming SP. The RISC-V ABI places the first stack argument at
that incoming SP, so the arguments start at FP, not FP + 16. Every
stack-passed argument of a callback with more than eight argument slots is
therefore read two slots late.

Pass the prologue-dependent offset to store_args(), using zero for a direct
struct_ops trampoline and 16 for the fentry path.

Fixes: 6801b0aef79d ("riscv, bpf: Add 12-argument support for RV64 bpf trampoline")
Cc: Björn Töpel <bjorn at kernel.org>
Cc: Pu Lehui <pulehui at huawei.com>
Signed-off-by: Kumar Kartikeya Dwivedi <memxor at gmail.com>
Reviewed-by: Pu Lehui <pulehui at huawei.com>
---
 arch/riscv/net/bpf_jit_comp64.c | 14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)

diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c
index ed0a6f871dea..b5fa6338e5eb 100644
--- a/arch/riscv/net/bpf_jit_comp64.c
+++ b/arch/riscv/net/bpf_jit_comp64.c
@@ -895,7 +895,8 @@ int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type old_t,
 	return ret;
 }
 
-static void store_args(int nr_arg_slots, int args_off, struct rv_jit_context *ctx)
+static void store_args(int nr_arg_slots, int args_off, int stack_args_off,
+		       struct rv_jit_context *ctx)
 {
 	int i;
 
@@ -903,8 +904,8 @@ static void store_args(int nr_arg_slots, int args_off, struct rv_jit_context *ct
 		if (i < RV_MAX_REG_ARGS) {
 			emit_sd(RV_REG_FP, -args_off, RV_REG_A0 + i, ctx);
 		} else {
-			/* skip slots for T0 and FP of traced function */
-			emit_ld(RV_REG_T1, 16 + (i - RV_MAX_REG_ARGS) * 8, RV_REG_FP, ctx);
+			emit_ld(RV_REG_T1, stack_args_off +
+				(i - RV_MAX_REG_ARGS) * 8, RV_REG_FP, ctx);
 			emit_sd(RV_REG_FP, -args_off, RV_REG_T1, ctx);
 		}
 		args_off -= 8;
@@ -1190,7 +1191,12 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im,
 	func_meta = nr_arg_slots;
 	emit_store_stack_imm64(RV_REG_T1, -func_meta_off, func_meta, ctx);
 
-	store_args(nr_arg_slots, args_off, ctx);
+	/*
+	 * A direct struct_ops call has its first stack argument at the incoming
+	 * SP, which the trampoline keeps as FP. The fentry path pushes the
+	 * parent frame first, so its incoming stack arguments start at FP + 16.
+	 */
+	store_args(nr_arg_slots, args_off, is_struct_ops ? 0 : 16, ctx);
 
 	if (bpf_fsession_cnt(tnodes)) {
 		/* clear all session cookies' value */
-- 
2.34.1