From: Peilin Ye <yepeilin@google.com>
To: bpf@vger.kernel.org, linux-arm-kernel@lists.infradead.org
Cc: Peilin Ye <yepeilin@google.com>,
bpf@ietf.org, Alexei Starovoitov <ast@kernel.org>,
Xu Kuohai <xukuohai@huaweicloud.com>,
Eduard Zingerman <eddyz87@gmail.com>,
David Vernet <void@manifault.com>,
Daniel Borkmann <daniel@iogearbox.net>,
Andrii Nakryiko <andrii@kernel.org>,
Martin KaFai Lau <martin.lau@linux.dev>,
Song Liu <song@kernel.org>,
Yonghong Song <yonghong.song@linux.dev>,
John Fastabend <john.fastabend@gmail.com>,
KP Singh <kpsingh@kernel.org>,
Stanislav Fomichev <sdf@fomichev.me>, Hao Luo <haoluo@google.com>,
Jiri Olsa <jolsa@kernel.org>, Jonathan Corbet <corbet@lwn.net>,
"Paul E. McKenney" <paulmck@kernel.org>,
Puranjay Mohan <puranjay@kernel.org>,
Ilya Leoshkevich <iii@linux.ibm.com>,
Heiko Carstens <hca@linux.ibm.com>,
Vasily Gorbik <gor@linux.ibm.com>,
Catalin Marinas <catalin.marinas@arm.com>,
Will Deacon <will@kernel.org>, Quentin Monnet <qmo@kernel.org>,
Mykola Lysenko <mykolal@fb.com>, Shuah Khan <shuah@kernel.org>,
Ihor Solodrai <ihor.solodrai@linux.dev>,
Yingchi Long <longyingchi24s@ict.ac.cn>,
Josh Don <joshdon@google.com>, Barret Rhoden <brho@google.com>,
Neel Natu <neelnatu@google.com>,
Benjamin Segall <bsegall@google.com>,
linux-kernel@vger.kernel.org
Subject: [PATCH bpf-next v4 07/10] bpf, arm64: Support load-acquire and store-release instructions
Date: Mon, 3 Mar 2025 05:37:57 +0000 [thread overview]
Message-ID: <3dcd54003b8dbb9ed74beb0535fee704db421515.1740978603.git.yepeilin@google.com> (raw)
In-Reply-To: <cover.1740978603.git.yepeilin@google.com>
Support BPF load-acquire (BPF_LOAD_ACQ) and store-release
(BPF_STORE_REL) instructions in the arm64 JIT compiler. For example
(assuming little-endian):
db 10 00 00 00 01 00 00 r0 = load_acquire((u64 *)(r1 + 0x0))
95 00 00 00 00 00 00 00 exit
opcode (0xdb): BPF_ATOMIC | BPF_DW | BPF_STX
imm (0x00000100): BPF_LOAD_ACQ
The JIT compiler would emit an LDAR instruction for the above, e.g.:
ldar x7, [x0]
Similarly, consider the following 16-bit store-release:
cb 21 00 00 10 01 00 00 store_release((u16 *)(r1 + 0x0), w2)
95 00 00 00 00 00 00 00 exit
opcode (0xcb): BPF_ATOMIC | BPF_H | BPF_STX
imm (0x00000110): BPF_STORE_REL
An STLRH instruction would be emitted, e.g.:
stlrh w1, [x0]
For a complete mapping:
load-acquire 8-bit LDARB
(BPF_LOAD_ACQ) 16-bit LDARH
32-bit LDAR (32-bit)
64-bit LDAR (64-bit)
store-release 8-bit STLRB
(BPF_STORE_REL) 16-bit STLRH
32-bit STLR (32-bit)
64-bit STLR (64-bit)
Arena accesses are supported.
bpf_jit_supports_insn(..., /*in_arena=*/true) always returns true for
BPF_LOAD_ACQ and BPF_STORE_REL instructions, as they don't depend on
ARM64_HAS_LSE_ATOMICS.
Acked-by: Xu Kuohai <xukuohai@huawei.com>
Signed-off-by: Peilin Ye <yepeilin@google.com>
---
arch/arm64/net/bpf_jit.h | 20 ++++++++
arch/arm64/net/bpf_jit_comp.c | 90 ++++++++++++++++++++++++++++++++---
2 files changed, 104 insertions(+), 6 deletions(-)
diff --git a/arch/arm64/net/bpf_jit.h b/arch/arm64/net/bpf_jit.h
index b22ab2f97a30..a3b0e693a125 100644
--- a/arch/arm64/net/bpf_jit.h
+++ b/arch/arm64/net/bpf_jit.h
@@ -119,6 +119,26 @@
aarch64_insn_gen_load_store_ex(Rt, Rn, Rs, A64_SIZE(sf), \
AARCH64_INSN_LDST_STORE_REL_EX)
+/* Load-acquire & store-release */
+#define A64_LDAR(Rt, Rn, size) \
+ aarch64_insn_gen_load_acq_store_rel(Rt, Rn, AARCH64_INSN_SIZE_##size, \
+ AARCH64_INSN_LDST_LOAD_ACQ)
+#define A64_STLR(Rt, Rn, size) \
+ aarch64_insn_gen_load_acq_store_rel(Rt, Rn, AARCH64_INSN_SIZE_##size, \
+ AARCH64_INSN_LDST_STORE_REL)
+
+/* Rt = [Rn] (load acquire) */
+#define A64_LDARB(Wt, Xn) A64_LDAR(Wt, Xn, 8)
+#define A64_LDARH(Wt, Xn) A64_LDAR(Wt, Xn, 16)
+#define A64_LDAR32(Wt, Xn) A64_LDAR(Wt, Xn, 32)
+#define A64_LDAR64(Xt, Xn) A64_LDAR(Xt, Xn, 64)
+
+/* [Rn] = Rt (store release) */
+#define A64_STLRB(Wt, Xn) A64_STLR(Wt, Xn, 8)
+#define A64_STLRH(Wt, Xn) A64_STLR(Wt, Xn, 16)
+#define A64_STLR32(Wt, Xn) A64_STLR(Wt, Xn, 32)
+#define A64_STLR64(Xt, Xn) A64_STLR(Xt, Xn, 64)
+
/*
* LSE atomics
*
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index bdda5a77bb16..70d7c89d3ac9 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -647,6 +647,81 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx)
return 0;
}
+static int emit_atomic_ld_st(const struct bpf_insn *insn, struct jit_ctx *ctx)
+{
+ const s32 imm = insn->imm;
+ const s16 off = insn->off;
+ const u8 code = insn->code;
+ const bool arena = BPF_MODE(code) == BPF_PROBE_ATOMIC;
+ const u8 arena_vm_base = bpf2a64[ARENA_VM_START];
+ const u8 dst = bpf2a64[insn->dst_reg];
+ const u8 src = bpf2a64[insn->src_reg];
+ const u8 tmp = bpf2a64[TMP_REG_1];
+ u8 reg;
+
+ switch (imm) {
+ case BPF_LOAD_ACQ:
+ reg = src;
+ break;
+ case BPF_STORE_REL:
+ reg = dst;
+ break;
+ default:
+ pr_err_once("unknown atomic load/store op code %02x\n", imm);
+ return -EINVAL;
+ }
+
+ if (off) {
+ emit_a64_add_i(1, tmp, reg, tmp, off, ctx);
+ reg = tmp;
+ }
+ if (arena) {
+ emit(A64_ADD(1, tmp, reg, arena_vm_base), ctx);
+ reg = tmp;
+ }
+
+ switch (imm) {
+ case BPF_LOAD_ACQ:
+ switch (BPF_SIZE(code)) {
+ case BPF_B:
+ emit(A64_LDARB(dst, reg), ctx);
+ break;
+ case BPF_H:
+ emit(A64_LDARH(dst, reg), ctx);
+ break;
+ case BPF_W:
+ emit(A64_LDAR32(dst, reg), ctx);
+ break;
+ case BPF_DW:
+ emit(A64_LDAR64(dst, reg), ctx);
+ break;
+ }
+ break;
+ case BPF_STORE_REL:
+ switch (BPF_SIZE(code)) {
+ case BPF_B:
+ emit(A64_STLRB(src, reg), ctx);
+ break;
+ case BPF_H:
+ emit(A64_STLRH(src, reg), ctx);
+ break;
+ case BPF_W:
+ emit(A64_STLR32(src, reg), ctx);
+ break;
+ case BPF_DW:
+ emit(A64_STLR64(src, reg), ctx);
+ break;
+ }
+ break;
+ default:
+ pr_err_once("unexpected atomic load/store op code %02x\n",
+ imm);
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
#ifdef CONFIG_ARM64_LSE_ATOMICS
static int emit_lse_atomic(const struct bpf_insn *insn, struct jit_ctx *ctx)
{
@@ -1641,11 +1716,17 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
return ret;
break;
+ case BPF_STX | BPF_ATOMIC | BPF_B:
+ case BPF_STX | BPF_ATOMIC | BPF_H:
case BPF_STX | BPF_ATOMIC | BPF_W:
case BPF_STX | BPF_ATOMIC | BPF_DW:
+ case BPF_STX | BPF_PROBE_ATOMIC | BPF_B:
+ case BPF_STX | BPF_PROBE_ATOMIC | BPF_H:
case BPF_STX | BPF_PROBE_ATOMIC | BPF_W:
case BPF_STX | BPF_PROBE_ATOMIC | BPF_DW:
- if (cpus_have_cap(ARM64_HAS_LSE_ATOMICS))
+ if (bpf_atomic_is_load_store(insn))
+ ret = emit_atomic_ld_st(insn, ctx);
+ else if (cpus_have_cap(ARM64_HAS_LSE_ATOMICS))
ret = emit_lse_atomic(insn, ctx);
else
ret = emit_ll_sc_atomic(insn, ctx);
@@ -2667,13 +2748,10 @@ bool bpf_jit_supports_insn(struct bpf_insn *insn, bool in_arena)
if (!in_arena)
return true;
switch (insn->code) {
- case BPF_STX | BPF_ATOMIC | BPF_B:
- case BPF_STX | BPF_ATOMIC | BPF_H:
case BPF_STX | BPF_ATOMIC | BPF_W:
case BPF_STX | BPF_ATOMIC | BPF_DW:
- if (bpf_atomic_is_load_store(insn))
- return false;
- if (!cpus_have_cap(ARM64_HAS_LSE_ATOMICS))
+ if (!bpf_atomic_is_load_store(insn) &&
+ !cpus_have_cap(ARM64_HAS_LSE_ATOMICS))
return false;
}
return true;
--
2.48.1.711.g2feabab25a-goog
next prev parent reply other threads:[~2025-03-03 5:38 UTC|newest]
Thread overview: 17+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-03-03 5:36 [PATCH bpf-next v4 00/10] Introduce load-acquire and store-release BPF instructions Peilin Ye
2025-03-03 5:37 ` [PATCH bpf-next v4 01/10] bpf/verifier: Factor out atomic_ptr_type_ok() Peilin Ye
2025-03-03 5:37 ` [PATCH bpf-next v4 02/10] bpf/verifier: Factor out check_atomic_rmw() Peilin Ye
2025-03-03 5:37 ` [PATCH bpf-next v4 03/10] bpf/verifier: Factor out check_load_mem() and check_store_reg() Peilin Ye
2025-03-03 18:52 ` Alexei Starovoitov
2025-03-03 22:20 ` Peilin Ye
2025-03-03 5:37 ` [PATCH bpf-next v4 04/10] bpf: Introduce load-acquire and store-release instructions Peilin Ye
2025-03-03 5:37 ` [PATCH bpf-next v4 05/10] arm64: insn: Add BIT(23) to {load,store}_ex's mask Peilin Ye
2025-03-03 5:37 ` [PATCH bpf-next v4 06/10] arm64: insn: Add load-acquire and store-release instructions Peilin Ye
2025-03-03 5:37 ` Peilin Ye [this message]
2025-03-03 5:38 ` [PATCH bpf-next v4 08/10] bpf, x86: Support " Peilin Ye
2025-03-03 5:46 ` Peilin Ye
2025-03-03 5:38 ` [PATCH bpf-next v4 09/10] selftests/bpf: Add selftests for " Peilin Ye
2025-03-03 5:38 ` [PATCH bpf-next v4 10/10] bpf, docs: Update instruction-set.rst " Peilin Ye
2025-03-03 19:14 ` Alexei Starovoitov
2025-03-03 21:31 ` Peilin Ye
2025-03-03 19:00 ` [PATCH bpf-next v4 00/10] Introduce load-acquire and store-release BPF instructions patchwork-bot+netdevbpf
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=3dcd54003b8dbb9ed74beb0535fee704db421515.1740978603.git.yepeilin@google.com \
--to=yepeilin@google.com \
--cc=andrii@kernel.org \
--cc=ast@kernel.org \
--cc=bpf@ietf.org \
--cc=bpf@vger.kernel.org \
--cc=brho@google.com \
--cc=bsegall@google.com \
--cc=catalin.marinas@arm.com \
--cc=corbet@lwn.net \
--cc=daniel@iogearbox.net \
--cc=eddyz87@gmail.com \
--cc=gor@linux.ibm.com \
--cc=haoluo@google.com \
--cc=hca@linux.ibm.com \
--cc=ihor.solodrai@linux.dev \
--cc=iii@linux.ibm.com \
--cc=john.fastabend@gmail.com \
--cc=jolsa@kernel.org \
--cc=joshdon@google.com \
--cc=kpsingh@kernel.org \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=longyingchi24s@ict.ac.cn \
--cc=martin.lau@linux.dev \
--cc=mykolal@fb.com \
--cc=neelnatu@google.com \
--cc=paulmck@kernel.org \
--cc=puranjay@kernel.org \
--cc=qmo@kernel.org \
--cc=sdf@fomichev.me \
--cc=shuah@kernel.org \
--cc=song@kernel.org \
--cc=void@manifault.com \
--cc=will@kernel.org \
--cc=xukuohai@huaweicloud.com \
--cc=yonghong.song@linux.dev \
/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
all inboxes | Powered by JetHome®