From: Yonghong Song <yonghong.song@linux.dev>
To: bpf@vger.kernel.org
Cc: Alexei Starovoitov <ast@kernel.org>,
Andrii Nakryiko <andrii@kernel.org>,
Daniel Borkmann <daniel@iogearbox.net>,
kernel-team@fb.com, Martin KaFai Lau <martin.lau@kernel.org>,
Tejun Heo <tj@kernel.org>
Subject: [PATCH bpf-next v7 6/9] bpf, x86: Support private stack in jit
Date: Tue, 29 Oct 2024 15:17:07 -0700 [thread overview]
Message-ID: <20241029221707.266393-1-yonghong.song@linux.dev> (raw)
In-Reply-To: <20241029221637.264348-1-yonghong.song@linux.dev>
Support private stack in jit. The x86 register 9 (X86_REG_R9) is used to
replace bpf frame register (BPF_REG_10). The private stack is used per
subprog if it is enabled by verifier. The X86_REG_R9 is saved and
restored around every func call (not including tailcall) to maintain
correctness of X86_REG_R9.
Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
---
arch/x86/net/bpf_jit_comp.c | 61 +++++++++++++++++++++++++++++++++++++
1 file changed, 61 insertions(+)
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 181d9f04418f..4ee69071c26d 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -325,6 +325,22 @@ struct jit_context {
/* Number of bytes that will be skipped on tailcall */
#define X86_TAIL_CALL_OFFSET (12 + ENDBR_INSN_SIZE)
+static void push_r9(u8 **pprog)
+{
+ u8 *prog = *pprog;
+
+ EMIT2(0x41, 0x51); /* push r9 */
+ *pprog = prog;
+}
+
+static void pop_r9(u8 **pprog)
+{
+ u8 *prog = *pprog;
+
+ EMIT2(0x41, 0x59); /* pop r9 */
+ *pprog = prog;
+}
+
static void push_r12(u8 **pprog)
{
u8 *prog = *pprog;
@@ -1404,6 +1420,24 @@ static void emit_shiftx(u8 **pprog, u32 dst_reg, u8 src_reg, bool is64, u8 op)
*pprog = prog;
}
+static void emit_priv_frame_ptr(u8 **pprog, void __percpu *priv_frame_ptr)
+{
+ u8 *prog = *pprog;
+
+ /* movabs r9, priv_frame_ptr */
+ emit_mov_imm64(&prog, X86_REG_R9, (__force long) priv_frame_ptr >> 32,
+ (u32) (__force long) priv_frame_ptr);
+
+#ifdef CONFIG_SMP
+ /* add <r9>, gs:[<off>] */
+ EMIT2(0x65, 0x4c);
+ EMIT3(0x03, 0x0c, 0x25);
+ EMIT((u32)(unsigned long)&this_cpu_off, 4);
+#endif
+
+ *pprog = prog;
+}
+
#define INSN_SZ_DIFF (((addrs[i] - addrs[i - 1]) - (prog - temp)))
#define __LOAD_TCC_PTR(off) \
@@ -1421,6 +1455,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image
int insn_cnt = bpf_prog->len;
bool seen_exit = false;
u8 temp[BPF_MAX_INSN_SIZE + BPF_INSN_SAFETY];
+ void __percpu *priv_frame_ptr = NULL;
u64 arena_vm_start, user_vm_start;
int i, excnt = 0;
int ilen, proglen = 0;
@@ -1429,6 +1464,10 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image
int err;
stack_depth = bpf_prog->aux->stack_depth;
+ if (bpf_prog->aux->priv_stack_ptr) {
+ priv_frame_ptr = bpf_prog->aux->priv_stack_ptr + round_up(stack_depth, 8);
+ stack_depth = 0;
+ }
arena_vm_start = bpf_arena_get_kern_vm_start(bpf_prog->aux->arena);
user_vm_start = bpf_arena_get_user_vm_start(bpf_prog->aux->arena);
@@ -1457,6 +1496,9 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image
emit_mov_imm64(&prog, X86_REG_R12,
arena_vm_start >> 32, (u32) arena_vm_start);
+ if (priv_frame_ptr)
+ emit_priv_frame_ptr(&prog, priv_frame_ptr);
+
ilen = prog - temp;
if (rw_image)
memcpy(rw_image + proglen, temp, ilen);
@@ -1476,6 +1518,14 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image
u8 *func;
int nops;
+ if (priv_frame_ptr) {
+ if (src_reg == BPF_REG_FP)
+ src_reg = X86_REG_R9;
+
+ if (dst_reg == BPF_REG_FP)
+ dst_reg = X86_REG_R9;
+ }
+
switch (insn->code) {
/* ALU */
case BPF_ALU | BPF_ADD | BPF_X:
@@ -2136,9 +2186,15 @@ st: if (is_imm8(insn->off))
}
if (!imm32)
return -EINVAL;
+ if (priv_frame_ptr) {
+ push_r9(&prog);
+ ip += 2;
+ }
ip += x86_call_depth_emit_accounting(&prog, func, ip);
if (emit_call(&prog, func, ip))
return -EINVAL;
+ if (priv_frame_ptr)
+ pop_r9(&prog);
break;
}
@@ -3563,6 +3619,11 @@ bool bpf_jit_supports_exceptions(void)
return IS_ENABLED(CONFIG_UNWINDER_ORC);
}
+bool bpf_jit_supports_private_stack(void)
+{
+ return true;
+}
+
void arch_bpf_stack_walk(bool (*consume_fn)(void *cookie, u64 ip, u64 sp, u64 bp), void *cookie)
{
#if defined(CONFIG_UNWINDER_ORC)
--
2.43.5
next prev parent reply other threads:[~2024-10-29 22:20 UTC|newest]
Thread overview: 13+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-10-29 22:16 [PATCH bpf-next v7 0/9] bpf: Support private stack for bpf progs Yonghong Song
2024-10-29 22:16 ` [PATCH bpf-next v7 1/9] bpf: Check stack depth limit after visiting all subprogs Yonghong Song
2024-10-29 22:16 ` [PATCH bpf-next v7 2/9] bpf: Allow private stack to have each subprog having stack size of 512 bytes Yonghong Song
2024-10-29 22:16 ` [PATCH bpf-next v7 3/9] bpf: Check potential private stack recursion for progs with async callback Yonghong Song
2024-10-29 22:16 ` [PATCH bpf-next v7 4/9] bpf: Allocate private stack for eligible main prog or subprogs Yonghong Song
2024-10-29 22:17 ` [PATCH bpf-next v7 5/9] bpf, x86: Avoid repeated usage of bpf_prog->aux->stack_depth Yonghong Song
2024-10-29 22:17 ` Yonghong Song [this message]
2024-10-29 22:17 ` [PATCH bpf-next v7 7/9] selftests/bpf: Add tracing prog private stack tests Yonghong Song
2024-10-29 22:17 ` [PATCH bpf-next v7 8/9] bpf: Support private stack for struct_ops progs Yonghong Song
2024-10-30 23:14 ` Tejun Heo
2024-10-29 22:17 ` [PATCH bpf-next v7 9/9] selftests/bpf: Add struct_ops prog private stack tests Yonghong Song
2024-10-30 23:29 ` Tejun Heo
2024-10-31 19:37 ` Yonghong Song
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20241029221707.266393-1-yonghong.song@linux.dev \
--to=yonghong.song@linux.dev \
--cc=andrii@kernel.org \
--cc=ast@kernel.org \
--cc=bpf@vger.kernel.org \
--cc=daniel@iogearbox.net \
--cc=kernel-team@fb.com \
--cc=martin.lau@kernel.org \
--cc=tj@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox