linux-kernel - [PATCH bpf-next] bpf, x86: inline bpf_get_current_task() for x86

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [day] [month] [year] [list]

Message-ID: <20251225104459.204104-1-dongml2@chinatelecom.cn>
Date: Thu, 25 Dec 2025 18:44:59 +0800
From: Menglong Dong <menglong8.dong@...il.com>
To: ast@...nel.org
Cc: davem@...emloft.net,
	dsahern@...nel.org,
	daniel@...earbox.net,
	andrii@...nel.org,
	martin.lau@...ux.dev,
	eddyz87@...il.com,
	song@...nel.org,
	yonghong.song@...ux.dev,
	john.fastabend@...il.com,
	kpsingh@...nel.org,
	sdf@...ichev.me,
	haoluo@...gle.com,
	jolsa@...nel.org,
	tglx@...utronix.de,
	mingo@...hat.com,
	bp@...en8.de,
	dave.hansen@...ux.intel.com,
	jiang.biao@...ux.dev,
	x86@...nel.org,
	hpa@...or.com,
	netdev@...r.kernel.org,
	bpf@...r.kernel.org,
	linux-kernel@...r.kernel.org
Subject: [PATCH bpf-next] bpf, x86: inline bpf_get_current_task() for x86_64

Inline bpf_get_current_task() and bpf_get_current_task_btf() for x86_64
to obtain better performance. The instruction we use here is:

  65 48 8B 04 25 [offset] // mov rax, gs:[offset]

Not sure if there is any side effect here.

Signed-off-by: Menglong Dong <dongml2@...natelecom.cn>
---
 arch/x86/net/bpf_jit_comp.c | 33 +++++++++++++++++++++++++++++++++
 1 file changed, 33 insertions(+)

diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index b69dc7194e2c..7f38481816f0 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -1300,6 +1300,19 @@ static void emit_st_r12(u8 **pprog, u32 size, u32 dst_reg, int off, int imm)
 	emit_st_index(pprog, size, dst_reg, X86_REG_R12, off, imm);
 }
 
+static void emit_ldx_percpu_r0(u8 **pprog, const void __percpu *ptr)
+{
+	u8 *prog = *pprog;
+
+	/* mov rax, gs:[offset] */
+	EMIT2(0x65, 0x48);
+	EMIT2(0x8B, 0x04);
+	EMIT1(0x25);
+	EMIT((u32)(unsigned long)ptr, 4);
+
+	*pprog = prog;
+}
+
 static int emit_atomic_rmw(u8 **pprog, u32 atomic_op,
 			   u32 dst_reg, u32 src_reg, s16 off, u8 bpf_size)
 {
@@ -2435,6 +2448,15 @@ st:			if (is_imm8(insn->off))
 		case BPF_JMP | BPF_CALL: {
 			u8 *ip = image + addrs[i - 1];
 
+			if (insn->src_reg == 0 && (insn->imm == BPF_FUNC_get_current_task ||
+						   insn->imm == BPF_FUNC_get_current_task_btf)) {
+				if (IS_ENABLED(CONFIG_USE_X86_SEG_SUPPORT))
+					emit_ldx_percpu_r0(&prog, &const_current_task);
+				else
+					emit_ldx_percpu_r0(&prog, &current_task);
+				break;
+			}
+
 			func = (u8 *) __bpf_call_base + imm32;
 			if (src_reg == BPF_PSEUDO_CALL && tail_call_reachable) {
 				LOAD_TAIL_CALL_CNT_PTR(stack_depth);
@@ -4067,3 +4089,14 @@ bool bpf_jit_supports_timed_may_goto(void)
 {
 	return true;
 }
+
+bool bpf_jit_inlines_helper_call(s32 imm)
+{
+	switch (imm) {
+	case BPF_FUNC_get_current_task:
+	case BPF_FUNC_get_current_task_btf:
+		return true;
+	default:
+		return false;
+	}
+}
-- 
2.52.0