Received-SPF: pass (google.com: domain of linux-kernel+bounces-133008-linux.lists.archive=gmail.com@vger.kernel.org designates 147.75.80.249 as permitted sender) client-ip=147.75.80.249;
From: Puranjay Mohan <puranjay12@gmail.com>
To: 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@google.com>,
	Hao Luo <haoluo@google.com>,
	Jiri Olsa <jolsa@kernel.org>,
	=?UTF-8?q?Bj=C3=B6rn=20T=C3=B6pel?= <bjorn@kernel.org>,
	Paul Walmsley <paul.walmsley@sifive.com>,
	Palmer Dabbelt <palmer@dabbelt.com>,
	Albert Ou <aou@eecs.berkeley.edu>,
	bpf@vger.kernel.org,
	linux-riscv@lists.infradead.org,
	linux-kernel@vger.kernel.org,
	Pu Lehui <pulehui@huawei.com>
Cc: puranjay12@gmail.com
Subject: [PATCH bpf-next] riscv, bpf: add internal-only MOV instruction to resolve per-CPU addrs
Date: Fri,  5 Apr 2024 12:43:48 +0000
Message-Id: <20240405124348.27644-1-puranjay12@gmail.com>
Precedence: bulk
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Support an instruction for resolving absolute addresses of per-CPU
data from their per-CPU offsets. This instruction is internal-only and
users are not allowed to use them directly. They will only be used for
internal inlining optimizations for now between BPF verifier and BPF
JITs.

RISC-V uses generic per-cpu implementation where the offsets for CPUs
are kept in an array called __per_cpu_offset[cpu_number]. RISCV stores
the address of the task_struct in TP register. The first element in
tast_struct is struct thread_info, and we can get the cpu number by
reading from the TP register + offsetof(struct thread_info, cpu).

Once we have the cpu number in a register we read the offset for that
cpu from address: &__per_cpu_offset + cpu_number << 3. Then we add this
offset to the destination register.

To measure the improvement from this change, the benchmark in [1] was
used on Qemu:

Before:
glob-arr-inc   :    1.127 ± 0.013M/s
arr-inc        :    1.121 ± 0.004M/s
hash-inc       :    0.681 ± 0.052M/s

After:
glob-arr-inc   :    1.138 ± 0.011M/s
arr-inc        :    1.366 ± 0.006M/s
hash-inc       :    0.676 ± 0.001M/s

[1] https://github.com/anakryiko/linux/commit/8dec900975ef

Signed-off-by: Puranjay Mohan <puranjay12@gmail.com>
---
 arch/riscv/net/bpf_jit_comp64.c | 24 ++++++++++++++++++++++++
 1 file changed, 24 insertions(+)

diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c
index 15e482f2c657..e95bd1d459a4 100644
--- a/arch/riscv/net/bpf_jit_comp64.c
+++ b/arch/riscv/net/bpf_jit_comp64.c
@@ -12,6 +12,7 @@
 #include <linux/stop_machine.h>
 #include <asm/patch.h>
 #include <asm/cfi.h>
+#include <asm/percpu.h>
 #include "bpf_jit.h"
 
 #define RV_FENTRY_NINSNS 2
@@ -1089,6 +1090,24 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 			emit_or(RV_REG_T1, rd, RV_REG_T1, ctx);
 			emit_mv(rd, RV_REG_T1, ctx);
 			break;
+		} else if (insn_is_mov_percpu_addr(insn)) {
+			if (rd != rs)
+				emit_mv(rd, rs, ctx);
+#ifdef CONFIG_SMP
+				/* Load current CPU number in T1 */
+				emit_ld(RV_REG_T1, offsetof(struct thread_info, cpu), RV_REG_TP,
+					ctx);
+				/* << 3 because offsets are 8 bytes */
+				emit_slli(RV_REG_T1, RV_REG_T1, 3, ctx);
+				/* Load address of __per_cpu_offset array in T2 */
+				emit_imm(RV_REG_T2, (u64)&__per_cpu_offset, ctx);
+				/* Add offset of current CPU to  __per_cpu_offset */
+				emit_add(RV_REG_T1, RV_REG_T2, RV_REG_T1, ctx);
+				/* Load __per_cpu_offset[cpu] in T1 */
+				emit_ld(RV_REG_T1, 0, RV_REG_T1, ctx);
+				/* Add the offset to Rd */
+				emit_add(rd, rd, RV_REG_T1, ctx);
+#endif
 		}
 		if (imm == 1) {
 			/* Special mov32 for zext */
@@ -2038,3 +2057,8 @@ bool bpf_jit_supports_arena(void)
 {
 	return true;
 }
+
+bool bpf_jit_supports_percpu_insn(void)
+{
+	return true;
+}
-- 
2.40.1