From: Kui-Feng Lee <kuifeng@fb.com>
To: <bpf@vger.kernel.org>, <ast@kernel.org>, <daniel@iogearbox.net>,
<andrii@kernel.org>, <kernel-team@fb.com>
Cc: Kui-Feng Lee <kuifeng@fb.com>
Subject: [PATCH bpf-next v4 2/5] bpf, x86: Create bpf_tramp_run_ctx on the caller thread's stack
Date: Mon, 11 Apr 2022 10:34:26 -0700 [thread overview]
Message-ID: <20220411173429.4139609-3-kuifeng@fb.com> (raw)
In-Reply-To: <20220411173429.4139609-1-kuifeng@fb.com>
BPF trampolines will create a bpf_tramp_run_ctx, a bpf_run_ctx, on
stacks and set/reset the current bpf_run_ctx before/after calling a
bpf_prog.
Signed-off-by: Kui-Feng Lee <kuifeng@fb.com>
---
arch/x86/net/bpf_jit_comp.c | 55 +++++++++++++++++++++++++++++++++++++
include/linux/bpf.h | 17 +++++++++---
kernel/bpf/syscall.c | 4 +--
kernel/bpf/trampoline.c | 23 +++++++++++++---
4 files changed, 89 insertions(+), 10 deletions(-)
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 4dcc0b1ac770..0f521be68f7b 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -1766,10 +1766,26 @@ static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog,
{
u8 *prog = *pprog;
u8 *jmp_insn;
+ int ctx_cookie_off = offsetof(struct bpf_tramp_run_ctx, bpf_cookie);
struct bpf_prog *p = l->link.prog;
+ /* mov rdi, 0 */
+ emit_mov_imm64(&prog, BPF_REG_1, 0, 0);
+
+ /* Prepare struct bpf_tramp_run_ctx.
+ *
+ * bpf_tramp_run_ctx is already preserved by
+ * arch_prepare_bpf_trampoline().
+ *
+ * mov QWORD PTR [rsp + ctx_cookie_off], rdi
+ */
+ EMIT4(0x48, 0x89, 0x7C, 0x24); EMIT1(ctx_cookie_off);
+
/* arg1: mov rdi, progs[i] */
emit_mov_imm64(&prog, BPF_REG_1, (long) p >> 32, (u32) (long) p);
+ /* arg2: mov rsi, rsp (struct bpf_run_ctx *) */
+ EMIT3(0x48, 0x89, 0xE6);
+
if (emit_call(&prog,
p->aux->sleepable ? __bpf_prog_enter_sleepable :
__bpf_prog_enter, prog))
@@ -1815,6 +1831,8 @@ static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog,
emit_mov_imm64(&prog, BPF_REG_1, (long) p >> 32, (u32) (long) p);
/* arg2: mov rsi, rbx <- start time in nsec */
emit_mov_reg(&prog, true, BPF_REG_2, BPF_REG_6);
+ /* arg3: mov rdx, rsp (struct bpf_run_ctx *) */
+ EMIT3(0x48, 0x89, 0xE2);
if (emit_call(&prog,
p->aux->sleepable ? __bpf_prog_exit_sleepable :
__bpf_prog_exit, prog))
@@ -2079,6 +2097,16 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
}
}
+ if (nr_args < 3 && (fentry->nr_links || fexit->nr_links || fmod_ret->nr_links))
+ EMIT1(0x52); /* push rdx */
+
+ if (fentry->nr_links || fexit->nr_links || fmod_ret->nr_links) {
+ /* Prepare struct bpf_tramp_run_ctx.
+ * sub rsp, sizeof(struct bpf_tramp_run_ctx)
+ */
+ EMIT4(0x48, 0x83, 0xEC, sizeof(struct bpf_tramp_run_ctx));
+ }
+
if (fentry->nr_links)
if (invoke_bpf(m, &prog, fentry, regs_off,
flags & BPF_TRAMP_F_RET_FENTRY_RET))
@@ -2098,6 +2126,15 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
}
if (flags & BPF_TRAMP_F_CALL_ORIG) {
+ /* pop struct bpf_tramp_run_ctx
+ * add rsp, sizeof(struct bpf_tramp_run_ctx)
+ */
+ if (fentry->nr_links || fexit->nr_links || fmod_ret->nr_links)
+ EMIT4(0x48, 0x83, 0xC4, sizeof(struct bpf_tramp_run_ctx));
+
+ if (nr_args < 3 && (fentry->nr_links || fexit->nr_links || fmod_ret->nr_links))
+ EMIT1(0x5A); /* pop rdx */
+
restore_regs(m, &prog, nr_args, regs_off);
/* call original function */
@@ -2110,6 +2147,15 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
im->ip_after_call = prog;
memcpy(prog, x86_nops[5], X86_PATCH_SIZE);
prog += X86_PATCH_SIZE;
+
+ if (nr_args < 3 && (fentry->nr_links || fexit->nr_links || fmod_ret->nr_links))
+ EMIT1(0x52); /* push rdx */
+
+ /* Prepare struct bpf_tramp_run_ctx.
+ * sub rsp, sizeof(struct bpf_tramp_run_ctx)
+ */
+ if (fentry->nr_links || fexit->nr_links || fmod_ret->nr_links)
+ EMIT4(0x48, 0x83, 0xEC, sizeof(struct bpf_tramp_run_ctx));
}
if (fmod_ret->nr_links) {
@@ -2133,6 +2179,15 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
goto cleanup;
}
+ /* pop struct bpf_tramp_run_ctx
+ * add rsp, sizeof(struct bpf_tramp_run_ctx)
+ */
+ if (fentry->nr_links || fexit->nr_links || fmod_ret->nr_links)
+ EMIT4(0x48, 0x83, 0xC4, sizeof(struct bpf_tramp_run_ctx));
+
+ if (nr_args < 3 && (fentry->nr_links || fexit->nr_links || fmod_ret->nr_links))
+ EMIT1(0x5A); /* pop rdx */
+
if (flags & BPF_TRAMP_F_RESTORE_REGS)
restore_regs(m, &prog, nr_args, regs_off);
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index a1a3722d11b0..a94891bfab7f 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -681,6 +681,8 @@ struct bpf_tramp_links {
int nr_links;
};
+struct bpf_tramp_run_ctx;
+
/* Different use cases for BPF trampoline:
* 1. replace nop at the function entry (kprobe equivalent)
* flags = BPF_TRAMP_F_RESTORE_REGS
@@ -707,10 +709,11 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *tr, void *image, void *i
struct bpf_tramp_links *tlinks,
void *orig_call);
/* these two functions are called from generated trampoline */
-u64 notrace __bpf_prog_enter(struct bpf_prog *prog);
-void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start);
-u64 notrace __bpf_prog_enter_sleepable(struct bpf_prog *prog);
-void notrace __bpf_prog_exit_sleepable(struct bpf_prog *prog, u64 start);
+u64 notrace __bpf_prog_enter(struct bpf_prog *prog, struct bpf_tramp_run_ctx *run_ctx);
+void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start, struct bpf_tramp_run_ctx *run_ctx);
+u64 notrace __bpf_prog_enter_sleepable(struct bpf_prog *prog, struct bpf_tramp_run_ctx *run_ctx);
+void notrace __bpf_prog_exit_sleepable(struct bpf_prog *prog, u64 start,
+ struct bpf_tramp_run_ctx *run_ctx);
void notrace __bpf_tramp_enter(struct bpf_tramp_image *tr);
void notrace __bpf_tramp_exit(struct bpf_tramp_image *tr);
@@ -1304,6 +1307,12 @@ struct bpf_trace_run_ctx {
u64 bpf_cookie;
};
+struct bpf_tramp_run_ctx {
+ struct bpf_run_ctx run_ctx;
+ u64 bpf_cookie;
+ struct bpf_run_ctx *saved_run_ctx;
+};
+
static inline struct bpf_run_ctx *bpf_set_run_ctx(struct bpf_run_ctx *new_ctx)
{
struct bpf_run_ctx *old_ctx = NULL;
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 3078c0c9317f..e8f06311a0b5 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -4802,13 +4802,13 @@ BPF_CALL_3(bpf_sys_bpf, int, cmd, union bpf_attr *, attr, u32, attr_size)
return -EINVAL;
}
- if (!__bpf_prog_enter_sleepable(prog)) {
+ if (!__bpf_prog_enter_sleepable(prog, NULL)) {
/* recursion detected */
bpf_prog_put(prog);
return -EBUSY;
}
attr->test.retval = bpf_prog_run(prog, (void *) (long) attr->test.ctx_in);
- __bpf_prog_exit_sleepable(prog, 0 /* bpf_prog_run does runtime stats */);
+ __bpf_prog_exit_sleepable(prog, 0 /* bpf_prog_run does runtime stats */, NULL);
bpf_prog_put(prog);
return 0;
#endif
diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c
index d5e6bc5517cb..0c32828c2698 100644
--- a/kernel/bpf/trampoline.c
+++ b/kernel/bpf/trampoline.c
@@ -568,11 +568,15 @@ static void notrace inc_misses_counter(struct bpf_prog *prog)
* [2..MAX_U64] - execute bpf prog and record execution time.
* This is start time.
*/
-u64 notrace __bpf_prog_enter(struct bpf_prog *prog)
+u64 notrace __bpf_prog_enter(struct bpf_prog *prog, struct bpf_tramp_run_ctx *run_ctx)
__acquires(RCU)
{
rcu_read_lock();
migrate_disable();
+
+ if (run_ctx)
+ run_ctx->saved_run_ctx = bpf_set_run_ctx(&run_ctx->run_ctx);
+
if (unlikely(__this_cpu_inc_return(*(prog->active)) != 1)) {
inc_misses_counter(prog);
return 0;
@@ -602,20 +606,27 @@ static void notrace update_prog_stats(struct bpf_prog *prog,
}
}
-void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start)
+void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start, struct bpf_tramp_run_ctx *run_ctx)
__releases(RCU)
{
+ if (run_ctx)
+ bpf_reset_run_ctx(run_ctx->saved_run_ctx);
+
update_prog_stats(prog, start);
__this_cpu_dec(*(prog->active));
migrate_enable();
rcu_read_unlock();
}
-u64 notrace __bpf_prog_enter_sleepable(struct bpf_prog *prog)
+u64 notrace __bpf_prog_enter_sleepable(struct bpf_prog *prog, struct bpf_tramp_run_ctx *run_ctx)
{
rcu_read_lock_trace();
migrate_disable();
might_fault();
+
+ if (run_ctx)
+ run_ctx->saved_run_ctx = bpf_set_run_ctx(&run_ctx->run_ctx);
+
if (unlikely(__this_cpu_inc_return(*(prog->active)) != 1)) {
inc_misses_counter(prog);
return 0;
@@ -623,8 +634,12 @@ u64 notrace __bpf_prog_enter_sleepable(struct bpf_prog *prog)
return bpf_prog_start_time();
}
-void notrace __bpf_prog_exit_sleepable(struct bpf_prog *prog, u64 start)
+void notrace __bpf_prog_exit_sleepable(struct bpf_prog *prog, u64 start,
+ struct bpf_tramp_run_ctx *run_ctx)
{
+ if (run_ctx)
+ bpf_reset_run_ctx(run_ctx->saved_run_ctx);
+
update_prog_stats(prog, start);
__this_cpu_dec(*(prog->active));
migrate_enable();
--
2.30.2
next prev parent reply other threads:[~2022-04-11 17:35 UTC|newest]
Thread overview: 9+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-04-11 17:34 [PATCH bpf-next v4 0/5] Attach a cookie to a tracing program Kui-Feng Lee
2022-04-11 17:34 ` [PATCH bpf-next v4 1/5] bpf, x86: Generate trampolines from bpf_tramp_links Kui-Feng Lee
2022-04-11 22:57 ` kernel test robot
2022-04-11 17:34 ` Kui-Feng Lee [this message]
2022-04-11 21:25 ` [PATCH bpf-next v4 2/5] bpf, x86: Create bpf_tramp_run_ctx on the caller thread's stack Alexei Starovoitov
2022-04-12 5:06 ` Kui-Feng Lee
2022-04-11 17:34 ` [PATCH bpf-next v4 3/5] bpf, x86: Attach a cookie to fentry/fexit/fmod_ret Kui-Feng Lee
2022-04-11 17:34 ` [PATCH bpf-next v4 4/5] lib/bpf: Assign cookies to links in libbpf Kui-Feng Lee
2022-04-11 17:34 ` [PATCH bpf-next v4 5/5] selftest/bpf: The test cses of BPF cookie for fentry/fexit/fmod_ret Kui-Feng Lee
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=20220411173429.4139609-3-kuifeng@fb.com \
--to=kuifeng@fb.com \
--cc=andrii@kernel.org \
--cc=ast@kernel.org \
--cc=bpf@vger.kernel.org \
--cc=daniel@iogearbox.net \
--cc=kernel-team@fb.com \
/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