| 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: <20200508181547.24783-3-luke.r.nels@gmail.com>
Date: Fri, 8 May 2020 11:15:45 -0700
From: Luke Nelson <lukenels@...washington.edu>
To: bpf@...r.kernel.org
Cc: Luke Nelson <luke.r.nels@...il.com>, Xi Wang <xi.wang@...il.com>,
Catalin Marinas <catalin.marinas@....com>,
Will Deacon <will@...nel.org>,
Daniel Borkmann <daniel@...earbox.net>,
Alexei Starovoitov <ast@...nel.org>,
Zi Shen Lim <zlim.lnx@...il.com>,
Martin KaFai Lau <kafai@...com>,
Song Liu <songliubraving@...com>, Yonghong Song <yhs@...com>,
Andrii Nakryiko <andriin@...com>,
John Fastabend <john.fastabend@...il.com>,
KP Singh <kpsingh@...omium.org>,
Mark Rutland <mark.rutland@....com>,
Ard Biesheuvel <ardb@...nel.org>, Torsten Duwe <duwe@...e.de>,
Greg Kroah-Hartman <gregkh@...uxfoundation.org>,
Enrico Weigelt <info@...ux.net>,
Thomas Gleixner <tglx@...utronix.de>,
Christoffer Dall <christoffer.dall@...aro.org>,
Marc Zyngier <maz@...nel.org>,
linux-arm-kernel@...ts.infradead.org, linux-kernel@...r.kernel.org,
netdev@...r.kernel.org, clang-built-linux@...glegroups.com
Subject: [PATCH bpf-next v2 2/3] bpf, arm64: Optimize AND,OR,XOR,JSET BPF_K using arm64 logical immediates
The current code for BPF_{AND,OR,XOR,JSET} BPF_K loads the immediate to
a temporary register before use.
This patch changes the code to avoid using a temporary register
when the BPF immediate is encodable using an arm64 logical immediate
instruction. If the encoding fails (due to the immediate not being
encodable), it falls back to using a temporary register.
Example of generated code for BPF_ALU32_IMM(BPF_AND, R0, 0x80000001):
without optimization:
24: mov w10, #0x8000ffff
28: movk w10, #0x1
2c: and w7, w7, w10
with optimization:
24: and w7, w7, #0x80000001
Since the encoding process is quite complex, the JIT reuses existing
functionality in arch/arm64/kernel/insn.c for encoding logical immediates
rather than duplicate it in the JIT.
Co-developed-by: Xi Wang <xi.wang@...il.com>
Signed-off-by: Xi Wang <xi.wang@...il.com>
Signed-off-by: Luke Nelson <luke.r.nels@...il.com>
Acked-by: Daniel Borkmann <daniel@...earbox.net>
---
arch/arm64/net/bpf_jit.h | 14 +++++++++++++
arch/arm64/net/bpf_jit_comp.c | 37 +++++++++++++++++++++++++++--------
2 files changed, 43 insertions(+), 8 deletions(-)
diff --git a/arch/arm64/net/bpf_jit.h b/arch/arm64/net/bpf_jit.h
index eb73f9f72c46..f36a779949e6 100644
--- a/arch/arm64/net/bpf_jit.h
+++ b/arch/arm64/net/bpf_jit.h
@@ -189,4 +189,18 @@
/* Rn & Rm; set condition flags */
#define A64_TST(sf, Rn, Rm) A64_ANDS(sf, A64_ZR, Rn, Rm)
+/* Logical (immediate) */
+#define A64_LOGIC_IMM(sf, Rd, Rn, imm, type) ({ \
+ u64 imm64 = (sf) ? (u64)imm : (u64)(u32)imm; \
+ aarch64_insn_gen_logical_immediate(AARCH64_INSN_LOGIC_##type, \
+ A64_VARIANT(sf), Rn, Rd, imm64); \
+})
+/* Rd = Rn OP imm */
+#define A64_AND_I(sf, Rd, Rn, imm) A64_LOGIC_IMM(sf, Rd, Rn, imm, AND)
+#define A64_ORR_I(sf, Rd, Rn, imm) A64_LOGIC_IMM(sf, Rd, Rn, imm, ORR)
+#define A64_EOR_I(sf, Rd, Rn, imm) A64_LOGIC_IMM(sf, Rd, Rn, imm, EOR)
+#define A64_ANDS_I(sf, Rd, Rn, imm) A64_LOGIC_IMM(sf, Rd, Rn, imm, AND_SETFLAGS)
+/* Rn & imm; set condition flags */
+#define A64_TST_I(sf, Rn, imm) A64_ANDS_I(sf, A64_ZR, Rn, imm)
+
#endif /* _BPF_JIT_H */
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index cdc79de0c794..083e5d8a5e2c 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -356,6 +356,7 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
const bool isdw = BPF_SIZE(code) == BPF_DW;
u8 jmp_cond, reg;
s32 jmp_offset;
+ u32 a64_insn;
#define check_imm(bits, imm) do { \
if ((((imm) > 0) && ((imm) >> (bits))) || \
@@ -488,18 +489,33 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
break;
case BPF_ALU | BPF_AND | BPF_K:
case BPF_ALU64 | BPF_AND | BPF_K:
- emit_a64_mov_i(is64, tmp, imm, ctx);
- emit(A64_AND(is64, dst, dst, tmp), ctx);
+ a64_insn = A64_AND_I(is64, dst, dst, imm);
+ if (a64_insn != AARCH64_BREAK_FAULT) {
+ emit(a64_insn, ctx);
+ } else {
+ emit_a64_mov_i(is64, tmp, imm, ctx);
+ emit(A64_AND(is64, dst, dst, tmp), ctx);
+ }
break;
case BPF_ALU | BPF_OR | BPF_K:
case BPF_ALU64 | BPF_OR | BPF_K:
- emit_a64_mov_i(is64, tmp, imm, ctx);
- emit(A64_ORR(is64, dst, dst, tmp), ctx);
+ a64_insn = A64_ORR_I(is64, dst, dst, imm);
+ if (a64_insn != AARCH64_BREAK_FAULT) {
+ emit(a64_insn, ctx);
+ } else {
+ emit_a64_mov_i(is64, tmp, imm, ctx);
+ emit(A64_ORR(is64, dst, dst, tmp), ctx);
+ }
break;
case BPF_ALU | BPF_XOR | BPF_K:
case BPF_ALU64 | BPF_XOR | BPF_K:
- emit_a64_mov_i(is64, tmp, imm, ctx);
- emit(A64_EOR(is64, dst, dst, tmp), ctx);
+ a64_insn = A64_EOR_I(is64, dst, dst, imm);
+ if (a64_insn != AARCH64_BREAK_FAULT) {
+ emit(a64_insn, ctx);
+ } else {
+ emit_a64_mov_i(is64, tmp, imm, ctx);
+ emit(A64_EOR(is64, dst, dst, tmp), ctx);
+ }
break;
case BPF_ALU | BPF_MUL | BPF_K:
case BPF_ALU64 | BPF_MUL | BPF_K:
@@ -628,8 +644,13 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
goto emit_cond_jmp;
case BPF_JMP | BPF_JSET | BPF_K:
case BPF_JMP32 | BPF_JSET | BPF_K:
- emit_a64_mov_i(is64, tmp, imm, ctx);
- emit(A64_TST(is64, dst, tmp), ctx);
+ a64_insn = A64_TST_I(is64, dst, imm);
+ if (a64_insn != AARCH64_BREAK_FAULT) {
+ emit(a64_insn, ctx);
+ } else {
+ emit_a64_mov_i(is64, tmp, imm, ctx);
+ emit(A64_TST(is64, dst, tmp), ctx);
+ }
goto emit_cond_jmp;
/* function call */
case BPF_JMP | BPF_CALL:
--
2.17.1
Powered by blists - more mailing lists