| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <20240430175834.33152-3-puranjay@kernel.org>
Date: Tue, 30 Apr 2024 17:58:34 +0000
From: Puranjay Mohan <puranjay@...nel.org>
To: Alexei Starovoitov <ast@...nel.org>,
Daniel Borkmann <daniel@...earbox.net>,
Andrii Nakryiko <andrii@...nel.org>,
Martin KaFai Lau <martin.lau@...ux.dev>,
Eduard Zingerman <eddyz87@...il.com>,
Song Liu <song@...nel.org>,
Yonghong Song <yonghong.song@...ux.dev>,
John Fastabend <john.fastabend@...il.com>,
KP Singh <kpsingh@...nel.org>,
Stanislav Fomichev <sdf@...gle.com>,
Hao Luo <haoluo@...gle.com>,
Jiri Olsa <jolsa@...nel.org>,
Björn Töpel <bjorn@...nel.org>,
Paul Walmsley <paul.walmsley@...ive.com>,
Palmer Dabbelt <palmer@...belt.com>,
Albert Ou <aou@...s.berkeley.edu>,
bpf@...r.kernel.org,
linux-riscv@...ts.infradead.org,
linux-kernel@...r.kernel.org,
Pu Lehui <pulehui@...wei.com>
Cc: puranjay12@...il.com
Subject: [PATCH bpf-next v2 2/2] riscv, bpf: inline bpf_get_smp_processor_id()
Inline the calls to bpf_get_smp_processor_id() in the riscv bpf jit.
RISCV saves the pointer to the CPU's task_struct in the TP (thread
pointer) register. This makes it trivial to get the CPU's processor id.
As thread_info is the first member of task_struct, we can read the
processor id from TP + offsetof(struct thread_info, cpu).
RISCV64 JIT output for `call bpf_get_smp_processor_id`
======================================================
Before After
-------- -------
auipc t1,0x848c ld a5,32(tp)
jalr 604(t1)
mv a5,a0
Benchmark using [1] on Qemu.
/benchs/run_bench_trigger.sh glob-arr-inc arr-inc hash-inc
+---------------+------------------+------------------+--------------+
| Name | Before | After | % change |
|---------------+------------------+------------------+--------------|
| glob-arr-inc | 1.077 ± 0.006M/s | 1.336 ± 0.010M/s | + 24.04% |
| arr-inc | 1.078 ± 0.002M/s | 1.332 ± 0.015M/s | + 23.56% |
| hash-inc | 0.494 ± 0.004M/s | 0.653 ± 0.001M/s | + 32.18% |
+---------------+------------------+------------------+--------------+
NOTE: This benchmark includes changes from this patch and the previous
patch that implemented the per-cpu insn.
[1] https://github.com/anakryiko/linux/commit/8dec900975ef
Signed-off-by: Puranjay Mohan <puranjay@...nel.org>
---
arch/riscv/net/bpf_jit_comp64.c | 26 ++++++++++++++++++++++++++
include/linux/filter.h | 1 +
kernel/bpf/core.c | 11 +++++++++++
kernel/bpf/verifier.c | 2 ++
4 files changed, 40 insertions(+)
diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c
index 99d7006f1420..5789b7afae47 100644
--- a/arch/riscv/net/bpf_jit_comp64.c
+++ b/arch/riscv/net/bpf_jit_comp64.c
@@ -1493,6 +1493,22 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
bool fixed_addr;
u64 addr;
+ /* Inline calls to bpf_get_smp_processor_id()
+ *
+ * RV_REG_TP holds the address of the current CPU's task_struct and thread_info is
+ * at offset 0 in task_struct.
+ * Load cpu from thread_info:
+ * Set R0 to ((struct thread_info *)(RV_REG_TP))->cpu
+ *
+ * This replicates the implementation of raw_smp_processor_id() on RISCV
+ */
+ if (insn->src_reg == 0 && insn->imm == BPF_FUNC_get_smp_processor_id) {
+ /* Load current CPU number in R0 */
+ emit_ld(bpf_to_rv_reg(BPF_REG_0, ctx), offsetof(struct thread_info, cpu),
+ RV_REG_TP, ctx);
+ break;
+ }
+
mark_call(ctx);
ret = bpf_jit_get_func_addr(ctx->prog, insn, extra_pass,
&addr, &fixed_addr);
@@ -2062,3 +2078,13 @@ bool bpf_jit_supports_percpu_insn(void)
{
return true;
}
+
+bool bpf_jit_inlines_helper_call(s32 imm)
+{
+ switch (imm) {
+ case BPF_FUNC_get_smp_processor_id:
+ return true;
+ }
+
+ return false;
+}
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 7a27f19bf44d..3e19bb62ed1a 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -993,6 +993,7 @@ u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog);
void bpf_jit_compile(struct bpf_prog *prog);
bool bpf_jit_needs_zext(void);
+bool bpf_jit_inlines_helper_call(s32 imm);
bool bpf_jit_supports_subprog_tailcalls(void);
bool bpf_jit_supports_percpu_insn(void);
bool bpf_jit_supports_kfunc_call(void);
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 99b8b1c9a248..aa59af9f9bd9 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -2941,6 +2941,17 @@ bool __weak bpf_jit_needs_zext(void)
return false;
}
+/* Return true if the JIT inlines the call to the helper corresponding to
+ * the imm.
+ *
+ * The verifier will not patch the insn->imm for the call to the helper if
+ * this returns true.
+ */
+bool __weak bpf_jit_inlines_helper_call(s32 imm)
+{
+ return false;
+}
+
/* Return TRUE if the JIT backend supports mixing bpf2bpf and tailcalls. */
bool __weak bpf_jit_supports_subprog_tailcalls(void)
{
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 5d42db05315e..e78f766d7f91 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -20013,6 +20013,8 @@ static int do_misc_fixups(struct bpf_verifier_env *env)
goto next_insn;
}
+ if (bpf_jit_inlines_helper_call(insn->imm))
+ goto next_insn;
if (insn->imm == BPF_FUNC_get_route_realm)
prog->dst_needed = 1;
if (insn->imm == BPF_FUNC_get_prandom_u32)
--
2.40.1
Powered by blists - more mailing lists