[PATCH 2/3] LoongArch: BPF: Add fsession support for trampolines

[Hengqi Chen <hengqi.chen@gmail.com>]

Implement BPF_TRACE_FSESSION support in LoongArch BPF JIT.
The logic here is almost identical to what has been done in
RISC-V JIT.

The key changes are:
  - Allocate stack space for function meta and session cookies
  - Introduce invoke_bpf() as a wrapper around invoke_bpf_prog()
    that populates session cookies before each invocation
  - Implement bpf_jit_supports_fsession() callback

Signed-off-by: Hengqi Chen <hengqi.chen@gmail.com>
---
 arch/loongarch/net/bpf_jit.c | 78 +++++++++++++++++++++++++++++++-----
 1 file changed, 67 insertions(+), 11 deletions(-)

diff --git a/arch/loongarch/net/bpf_jit.c b/arch/loongarch/net/bpf_jit.c
index e3deb0da6a50..16da53f80266 100644
--- a/arch/loongarch/net/bpf_jit.c
+++ b/arch/loongarch/net/bpf_jit.c
@@ -1549,6 +1549,31 @@ static int invoke_bpf_prog(struct jit_ctx *ctx, struct bpf_tramp_link *l,
 	return ret;
 }
 
+static int invoke_bpf(struct jit_ctx *ctx, struct bpf_tramp_links *tl,
+		      int args_off, int retval_off, int run_ctx_off,
+		      int func_meta_off, bool save_ret, u64 func_meta,
+		      int cookie_off)
+{
+	int i, cur_cookie = (cookie_off - args_off) / 8;
+
+	for (i = 0; i < tl->nr_links; i++) {
+		int err;
+
+		if (bpf_prog_calls_session_cookie(tl->links[i])) {
+			u64 meta = func_meta | ((u64)cur_cookie << BPF_TRAMP_COOKIE_INDEX_SHIFT);
+
+			emit_store_stack_imm64(ctx, LOONGARCH_GPR_T1, -func_meta_off, meta);
+			cur_cookie--;
+		}
+		err = invoke_bpf_prog(ctx, tl->links[i], args_off, retval_off,
+				      run_ctx_off, save_ret);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
 static void invoke_bpf_mod_ret(struct jit_ctx *ctx, struct bpf_tramp_links *tl,
 			       int args_off, int retval_off, int run_ctx_off, u32 **branches)
 {
@@ -1610,13 +1635,15 @@ static int __arch_prepare_bpf_trampoline(struct jit_ctx *ctx, struct bpf_tramp_i
 {
 	int i, ret, save_ret;
 	int stack_size, nargs;
-	int retval_off, args_off, nargs_off, ip_off, run_ctx_off, sreg_off, tcc_ptr_off;
+	int retval_off, args_off, func_meta_off, ip_off, run_ctx_off, sreg_off, tcc_ptr_off;
+	int cookie_off, cookie_cnt;
 	bool is_struct_ops = flags & BPF_TRAMP_F_INDIRECT;
 	void *orig_call = func_addr;
 	struct bpf_tramp_links *fentry = &tlinks[BPF_TRAMP_FENTRY];
 	struct bpf_tramp_links *fexit = &tlinks[BPF_TRAMP_FEXIT];
 	struct bpf_tramp_links *fmod_ret = &tlinks[BPF_TRAMP_MODIFY_RETURN];
 	u32 **branches = NULL;
+	u64 func_meta;
 
 	/*
 	 * FP + 8       [ RA to parent func ] return address to parent
@@ -1634,10 +1661,14 @@ static int __arch_prepare_bpf_trampoline(struct jit_ctx *ctx, struct bpf_tramp_i
 	 *                  [ ...               ]
 	 * FP - args_off    [ arg1              ]
 	 *
-	 * FP - nargs_off   [ regs count        ]
+	 * FP - func_meta_off [ regs count, etc ]
 	 *
 	 * FP - ip_off      [ traced func   ] BPF_TRAMP_F_IP_ARG
 	 *
+	 *                  [ stack cookie N    ]
+	 *                  [ ...               ]
+	 * FP - cookie_off  [ stack cookie 1    ]
+	 *
 	 * FP - run_ctx_off [ bpf_tramp_run_ctx ]
 	 *
 	 * FP - sreg_off    [ callee saved reg  ]
@@ -1671,9 +1702,9 @@ static int __arch_prepare_bpf_trampoline(struct jit_ctx *ctx, struct bpf_tramp_i
 	stack_size += nargs * 8;
 	args_off = stack_size;
 
-	/* Room of trampoline frame to store args number */
+	/* function metadata, such as regs count */
 	stack_size += 8;
-	nargs_off = stack_size;
+	func_meta_off = stack_size;
 
 	/* Room of trampoline frame to store ip address */
 	if (flags & BPF_TRAMP_F_IP_ARG) {
@@ -1681,6 +1712,11 @@ static int __arch_prepare_bpf_trampoline(struct jit_ctx *ctx, struct bpf_tramp_i
 		ip_off = stack_size;
 	}
 
+	cookie_cnt = bpf_fsession_cookie_cnt(tlinks);
+	/* room for session cookies */
+	stack_size += cookie_cnt * 8;
+	cookie_off = stack_size;
+
 	/* Room of trampoline frame to store struct bpf_tramp_run_ctx */
 	stack_size += round_up(sizeof(struct bpf_tramp_run_ctx), 8);
 	run_ctx_off = stack_size;
@@ -1734,11 +1770,19 @@ static int __arch_prepare_bpf_trampoline(struct jit_ctx *ctx, struct bpf_tramp_i
 	if (flags & BPF_TRAMP_F_IP_ARG)
 		emit_store_stack_imm64(ctx, LOONGARCH_GPR_T1, -ip_off, (u64)func_addr);
 
-	/* store nargs number */
-	emit_store_stack_imm64(ctx, LOONGARCH_GPR_T1, -nargs_off, nargs);
+	func_meta = nargs;
+	emit_store_stack_imm64(ctx, LOONGARCH_GPR_T1, -func_meta_off, func_meta);
 
 	store_args(ctx, nargs, args_off);
 
+	if (bpf_fsession_cnt(tlinks)) {
+		/* clear all session cookies' value */
+		for (i = 0; i < cookie_cnt; i++)
+			emit_insn(ctx, std, LOONGARCH_GPR_ZERO, LOONGARCH_GPR_FP, -cookie_off + 8 * i);
+		/* clear return value to make sure fentry always get 0 */
+		emit_insn(ctx, std, LOONGARCH_GPR_ZERO, LOONGARCH_GPR_FP, -retval_off);
+	}
+
 	/* To traced function */
 	/* Ftrace jump skips 2 NOP instructions */
 	if (is_kernel_text((unsigned long)orig_call) ||
@@ -1755,9 +1799,10 @@ static int __arch_prepare_bpf_trampoline(struct jit_ctx *ctx, struct bpf_tramp_i
 			return ret;
 	}
 
-	for (i = 0; i < fentry->nr_links; i++) {
-		ret = invoke_bpf_prog(ctx, fentry->links[i], args_off, retval_off,
-				      run_ctx_off, flags & BPF_TRAMP_F_RET_FENTRY_RET);
+	if (fentry->nr_links) {
+		ret = invoke_bpf(ctx, fentry, args_off, retval_off, run_ctx_off,
+				 func_meta_off, flags & BPF_TRAMP_F_RET_FENTRY_RET,
+				 func_meta, cookie_off);
 		if (ret)
 			return ret;
 	}
@@ -1791,8 +1836,14 @@ static int __arch_prepare_bpf_trampoline(struct jit_ctx *ctx, struct bpf_tramp_i
 		*branches[i] = larch_insn_gen_bne(LOONGARCH_GPR_T1, LOONGARCH_GPR_ZERO, offset);
 	}
 
-	for (i = 0; i < fexit->nr_links; i++) {
-		ret = invoke_bpf_prog(ctx, fexit->links[i], args_off, retval_off, run_ctx_off, false);
+	/* set "is_return" flag for fsession */
+	func_meta |= (1ULL << BPF_TRAMP_IS_RETURN_SHIFT);
+	if (bpf_fsession_cnt(tlinks))
+		emit_store_stack_imm64(ctx, LOONGARCH_GPR_T1, -func_meta_off, func_meta);
+
+	if (fexit->nr_links) {
+		ret = invoke_bpf(ctx, fexit, args_off, retval_off, run_ctx_off,
+				 func_meta_off, false, func_meta, cookie_off);
 		if (ret)
 			goto out;
 	}
@@ -2132,3 +2183,8 @@ bool bpf_jit_supports_subprog_tailcalls(void)
 {
 	return true;
 }
+
+bool bpf_jit_supports_fsession(void)
+{
+	return true;
+}
-- 
2.43.5