From: Leon Hwang <leon.hwang@linux.dev>
To: bpf@vger.kernel.org
Cc: Alexei Starovoitov <ast@kernel.org>,
Daniel Borkmann <daniel@iogearbox.net>,
Andrii Nakryiko <andrii@kernel.org>,
Martin KaFai Lau <martin.lau@linux.dev>,
Eduard Zingerman <eddyz87@gmail.com>, 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>,
Puranjay Mohan <puranjay@kernel.org>,
Xu Kuohai <xukuohai@huaweicloud.com>,
Catalin Marinas <catalin.marinas@arm.com>,
Will Deacon <will@kernel.org>, Thomas Gleixner <tglx@kernel.org>,
Ingo Molnar <mingo@redhat.com>, Borislav Petkov <bp@alien8.de>,
Dave Hansen <dave.hansen@linux.intel.com>,
x86@kernel.org, "H . Peter Anvin" <hpa@zytor.com>,
Shuah Khan <shuah@kernel.org>, Leon Hwang <leon.hwang@linux.dev>,
Peilin Ye <yepeilin@google.com>,
Luis Gerhorst <luis.gerhorst@fau.de>,
Viktor Malik <vmalik@redhat.com>,
linux-arm-kernel@lists.infradead.org,
linux-kernel@vger.kernel.org, netdev@vger.kernel.org,
linux-kselftest@vger.kernel.org, kernel-patches-bot@fb.com
Subject: [PATCH bpf-next v2 3/6] bpf, arm64: Add 64-bit bitops kfuncs support
Date: Thu, 19 Feb 2026 22:29:25 +0800 [thread overview]
Message-ID: <20260219142933.13904-4-leon.hwang@linux.dev> (raw)
In-Reply-To: <20260219142933.13904-1-leon.hwang@linux.dev>
Implement JIT inlining of the 64-bit bitops kfuncs on arm64.
bpf_clz64(), bpf_ffs64(), bpf_fls64(), and bpf_bitrev64() are always
inlined using mandatory ARMv8 CLZ/RBIT instructions. bpf_ctz64() is
inlined via RBIT + CLZ, or via the native CTZ instruction when
FEAT_CSSC is available. bpf_rol64() and bpf_ror64() are always inlined
via RORV.
bpf_popcnt64() is not inlined as the native population count instruction
requires NEON/SIMD registers, which should not be touched from BPF
programs. It therefore falls back to a regular function call.
Signed-off-by: Leon Hwang <leon.hwang@linux.dev>
---
arch/arm64/net/bpf_jit_comp.c | 123 ++++++++++++++++++++++++++++++++++
1 file changed, 123 insertions(+)
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index 7a530ea4f5ae..f03f732063d9 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -1192,6 +1192,127 @@ static int add_exception_handler(const struct bpf_insn *insn,
return 0;
}
+static inline u32 a64_clz64(u8 rd, u8 rn)
+{
+ /*
+ * Arm Architecture Reference Manual for A-profile architecture
+ * (Document number: ARM DDI 0487)
+ *
+ * A64 Base Instruction Descriptions
+ * C6.2 Alphabetical list of A64 base instructions
+ *
+ * C6.2.91 CLZ
+ *
+ * Count leading zeros
+ *
+ * This instruction counts the number of consecutive binary zero bits,
+ * starting from the most significant bit in the source register,
+ * and places the count in the destination register.
+ */
+ /* CLZ Xd, Xn */
+ return 0xdac01000 | (rn << 5) | rd;
+}
+
+static inline u32 a64_ctz64(u8 rd, u8 rn)
+{
+ /*
+ * Arm Architecture Reference Manual for A-profile architecture
+ * (Document number: ARM DDI 0487)
+ *
+ * A64 Base Instruction Descriptions
+ * C6.2 Alphabetical list of A64 base instructions
+ *
+ * C6.2.144 CTZ
+ *
+ * Count trailing zeros
+ *
+ * This instruction counts the number of consecutive binary zero bits,
+ * starting from the least significant bit in the source register,
+ * and places the count in the destination register.
+ *
+ * This instruction requires FEAT_CSSC.
+ */
+ /* CTZ Xd, Xn */
+ return 0xdac01800 | (rn << 5) | rd;
+}
+
+static inline u32 a64_rbit64(u8 rd, u8 rn)
+{
+ /*
+ * Arm Architecture Reference Manual for A-profile architecture
+ * (Document number: ARM DDI 0487)
+ *
+ * A64 Base Instruction Descriptions
+ * C6.2 Alphabetical list of A64 base instructions
+ *
+ * C6.2.320 RBIT
+ *
+ * Reverse bits
+ *
+ * This instruction reverses the bit order in a register.
+ */
+ /* RBIT Xd, Xn */
+ return 0xdac00000 | (rn << 5) | rd;
+}
+
+static inline bool boot_cpu_supports_cssc(void)
+{
+ /*
+ * Documentation/arch/arm64/cpu-feature-registers.rst
+ *
+ * ID_AA64ISAR2_EL1 - Instruction set attribute register 2
+ *
+ * CSSC
+ */
+ return cpuid_feature_extract_unsigned_field(read_sanitised_ftr_reg(SYS_ID_AA64ISAR2_EL1),
+ ID_AA64ISAR2_EL1_CSSC_SHIFT);
+}
+
+static bool bpf_inlines_func_call(struct jit_ctx *ctx, void *func_addr)
+{
+ const u8 tmp = bpf2a64[TMP_REG_1];
+ const u8 r0 = bpf2a64[BPF_REG_0];
+ const u8 r1 = bpf2a64[BPF_REG_1];
+ const u8 r2 = bpf2a64[BPF_REG_2];
+ bool inlined = true;
+
+ if (func_addr == bpf_clz64) {
+ emit(a64_clz64(r0, r1), ctx);
+ } else if (func_addr == bpf_ctz64 || func_addr == bpf_ffs64) {
+ if (boot_cpu_supports_cssc()) {
+ emit(a64_ctz64(r0, r1), ctx);
+ } else {
+ emit(a64_rbit64(tmp, r1), ctx);
+ emit(a64_clz64(r0, tmp), ctx);
+ }
+ } else if (func_addr == bpf_fls64) {
+ emit(a64_clz64(tmp, r1), ctx);
+ emit(A64_NEG(1, tmp, tmp), ctx);
+ emit(A64_ADD_I(1, r0, tmp, 64), ctx);
+ } else if (func_addr == bpf_bitrev64) {
+ emit(a64_rbit64(r0, r1), ctx);
+ } else if (func_addr == bpf_rol64) {
+ emit(A64_NEG(1, tmp, r2), ctx);
+ emit(A64_DATA2(1, r0, r1, tmp, RORV), ctx);
+ } else if (func_addr == bpf_ror64) {
+ emit(A64_DATA2(1, r0, r1, r2, RORV), ctx);
+ } else {
+ inlined = false;
+ }
+
+ return inlined;
+}
+
+bool bpf_jit_inlines_kfunc_call(void *func_addr)
+{
+ if (func_addr == bpf_clz64 || func_addr == bpf_ctz64 ||
+ func_addr == bpf_ffs64 || func_addr == bpf_fls64 ||
+ func_addr == bpf_rol64 || func_addr == bpf_ror64 ||
+ func_addr == bpf_bitrev64)
+ return true;
+ return false;
+}
+
/* JITs an eBPF instruction.
* Returns:
* 0 - successfully JITed an 8-byte eBPF instruction.
@@ -1598,6 +1719,8 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
&func_addr, &func_addr_fixed);
if (ret < 0)
return ret;
+ if (bpf_inlines_func_call(ctx, (void *) func_addr))
+ break;
emit_call(func_addr, ctx);
/*
* Call to arch_bpf_timed_may_goto() is emitted by the
--
2.52.0
next prev parent reply other threads:[~2026-02-19 14:31 UTC|newest]
Thread overview: 25+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-02-19 14:29 [PATCH bpf-next v2 0/6] bpf: Introduce 64-bit bitops kfuncs Leon Hwang
2026-02-19 14:29 ` [PATCH bpf-next v2 1/6] " Leon Hwang
2026-02-19 17:50 ` Alexei Starovoitov
2026-02-20 15:34 ` Leon Hwang
2026-02-19 14:29 ` [PATCH bpf-next v2 2/6] bpf, x86: Add 64-bit bitops kfuncs support for x86_64 Leon Hwang
2026-02-19 17:47 ` Alexei Starovoitov
2026-02-20 15:54 ` Leon Hwang
2026-02-20 17:50 ` Alexei Starovoitov
2026-02-21 12:45 ` Leon Hwang
2026-02-21 16:51 ` Alexei Starovoitov
2026-02-23 16:35 ` Leon Hwang
2026-02-19 22:05 ` kernel test robot
2026-02-20 14:12 ` Leon Hwang
2026-02-20 11:59 ` kernel test robot
2026-02-19 14:29 ` Leon Hwang [this message]
2026-02-19 15:10 ` [PATCH bpf-next v2 3/6] bpf, arm64: Add 64-bit bitops kfuncs support Puranjay Mohan
2026-02-19 15:20 ` Puranjay Mohan
2026-02-19 15:25 ` Puranjay Mohan
2026-02-19 15:36 ` Leon Hwang
2026-02-19 14:29 ` [PATCH bpf-next v2 4/6] selftests/bpf: Add tests for 64-bit bitops kfuncs Leon Hwang
2026-02-19 14:29 ` [PATCH bpf-next v2 5/6] selftests/bpf: Add __cpu_feature annotation for CPU-feature-gated tests Leon Hwang
2026-02-19 14:29 ` [PATCH bpf-next v2 6/6] selftests/bpf: Add JIT disassembly tests for 64-bit bitops kfuncs Leon Hwang
-- strict thread matches above, loose matches on Subject: below --
2026-02-20 18:57 [PATCH bpf-next v2 1/6] bpf: Introduce " kernel test robot
2026-02-21 9:58 ` Dan Carpenter
2026-02-21 12:50 ` Leon Hwang
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=20260219142933.13904-4-leon.hwang@linux.dev \
--to=leon.hwang@linux.dev \
--cc=andrii@kernel.org \
--cc=ast@kernel.org \
--cc=bp@alien8.de \
--cc=bpf@vger.kernel.org \
--cc=catalin.marinas@arm.com \
--cc=daniel@iogearbox.net \
--cc=dave.hansen@linux.intel.com \
--cc=eddyz87@gmail.com \
--cc=haoluo@google.com \
--cc=hpa@zytor.com \
--cc=john.fastabend@gmail.com \
--cc=jolsa@kernel.org \
--cc=kernel-patches-bot@fb.com \
--cc=kpsingh@kernel.org \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-kselftest@vger.kernel.org \
--cc=luis.gerhorst@fau.de \
--cc=martin.lau@linux.dev \
--cc=mingo@redhat.com \
--cc=netdev@vger.kernel.org \
--cc=puranjay@kernel.org \
--cc=sdf@fomichev.me \
--cc=shuah@kernel.org \
--cc=song@kernel.org \
--cc=tglx@kernel.org \
--cc=vmalik@redhat.com \
--cc=will@kernel.org \
--cc=x86@kernel.org \
--cc=xukuohai@huaweicloud.com \
--cc=yepeilin@google.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.