linux-kernel - [PATCH 2/3] powerpc/ebpf32: Rework 64 bits shifts to avoid tests and branches

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

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <03167350b05b2fe8b741e53363ee37709d0f878d.1618227846.git.christophe.leroy@csgroup.eu>
Date:   Mon, 12 Apr 2021 11:44:17 +0000 (UTC)
From:   Christophe Leroy <christophe.leroy@...roup.eu>
To:     Benjamin Herrenschmidt <benh@...nel.crashing.org>,
        Paul Mackerras <paulus@...ba.org>,
        Michael Ellerman <mpe@...erman.id.au>, ast@...nel.org,
        daniel@...earbox.net, andrii@...nel.org, kafai@...com,
        songliubraving@...com, yhs@...com, john.fastabend@...il.com,
        kpsingh@...omium.org, naveen.n.rao@...ux.ibm.com,
        sandipan@...ux.ibm.com
Cc:     linux-kernel@...r.kernel.org, linuxppc-dev@...ts.ozlabs.org,
        netdev@...r.kernel.org, bpf@...r.kernel.org
Subject: [PATCH 2/3] powerpc/ebpf32: Rework 64 bits shifts to avoid tests and
 branches

Re-implement BPF_ALU64 | BPF_{LSH/RSH/ARSH} | BPF_X with branchless
implementation copied from misc_32.S.

Signed-off-by: Christophe Leroy <christophe.leroy@...roup.eu>
---
 arch/powerpc/net/bpf_jit_comp32.c | 39 +++++++++++++++----------------
 1 file changed, 19 insertions(+), 20 deletions(-)

diff --git a/arch/powerpc/net/bpf_jit_comp32.c b/arch/powerpc/net/bpf_jit_comp32.c
index ca6fe1583460..ef21b09df76e 100644
--- a/arch/powerpc/net/bpf_jit_comp32.c
+++ b/arch/powerpc/net/bpf_jit_comp32.c
@@ -548,16 +548,15 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *
 			EMIT(PPC_RAW_SLW(dst_reg, dst_reg, src_reg));
 			break;
 		case BPF_ALU64 | BPF_LSH | BPF_X: /* dst <<= src; */
-			EMIT(PPC_RAW_ADDIC_DOT(__REG_R0, src_reg, -32));
-			PPC_BCC_SHORT(COND_LT, (ctx->idx + 4) * 4);
-			EMIT(PPC_RAW_SLW(dst_reg_h, dst_reg, __REG_R0));
-			EMIT(PPC_RAW_LI(dst_reg, 0));
-			PPC_JMP((ctx->idx + 6) * 4);
+			bpf_set_seen_register(ctx, tmp_reg);
 			EMIT(PPC_RAW_SUBFIC(__REG_R0, src_reg, 32));
 			EMIT(PPC_RAW_SLW(dst_reg_h, dst_reg_h, src_reg));
+			EMIT(PPC_RAW_ADDI(tmp_reg, src_reg, 32));
 			EMIT(PPC_RAW_SRW(__REG_R0, dst_reg, __REG_R0));
-			EMIT(PPC_RAW_SLW(dst_reg, dst_reg, src_reg));
+			EMIT(PPC_RAW_SLW(tmp_reg, dst_reg, tmp_reg));
 			EMIT(PPC_RAW_OR(dst_reg_h, dst_reg_h, __REG_R0));
+			EMIT(PPC_RAW_SLW(dst_reg, dst_reg, src_reg));
+			EMIT(PPC_RAW_OR(dst_reg_h, dst_reg_h, tmp_reg));
 			break;
 		case BPF_ALU | BPF_LSH | BPF_K: /* (u32) dst <<= (u32) imm */
 			if (!imm)
@@ -585,16 +584,15 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *
 			EMIT(PPC_RAW_SRW(dst_reg, dst_reg, src_reg));
 			break;
 		case BPF_ALU64 | BPF_RSH | BPF_X: /* dst >>= src */
-			EMIT(PPC_RAW_ADDIC_DOT(__REG_R0, src_reg, -32));
-			PPC_BCC_SHORT(COND_LT, (ctx->idx + 4) * 4);
-			EMIT(PPC_RAW_SRW(dst_reg, dst_reg_h, __REG_R0));
-			EMIT(PPC_RAW_LI(dst_reg_h, 0));
-			PPC_JMP((ctx->idx + 6) * 4);
-			EMIT(PPC_RAW_SUBFIC(0, src_reg, 32));
+			bpf_set_seen_register(ctx, tmp_reg);
+			EMIT(PPC_RAW_SUBFIC(__REG_R0, src_reg, 32));
 			EMIT(PPC_RAW_SRW(dst_reg, dst_reg, src_reg));
+			EMIT(PPC_RAW_ADDI(tmp_reg, src_reg, 32));
 			EMIT(PPC_RAW_SLW(__REG_R0, dst_reg_h, __REG_R0));
-			EMIT(PPC_RAW_SRW(dst_reg_h, dst_reg_h, src_reg));
+			EMIT(PPC_RAW_SRW(tmp_reg, dst_reg_h, tmp_reg));
 			EMIT(PPC_RAW_OR(dst_reg, dst_reg, __REG_R0));
+			EMIT(PPC_RAW_SRW(dst_reg_h, dst_reg_h, src_reg));
+			EMIT(PPC_RAW_OR(dst_reg, dst_reg, tmp_reg));
 			break;
 		case BPF_ALU | BPF_RSH | BPF_K: /* (u32) dst >>= (u32) imm */
 			if (!imm)
@@ -622,16 +620,17 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *
 			EMIT(PPC_RAW_SRAW(dst_reg_h, dst_reg, src_reg));
 			break;
 		case BPF_ALU64 | BPF_ARSH | BPF_X: /* (s64) dst >>= src */
-			EMIT(PPC_RAW_ADDIC_DOT(__REG_R0, src_reg, -32));
-			PPC_BCC_SHORT(COND_LT, (ctx->idx + 4) * 4);
-			EMIT(PPC_RAW_SRAW(dst_reg, dst_reg_h, __REG_R0));
-			EMIT(PPC_RAW_SRAWI(dst_reg_h, dst_reg_h, 31));
-			PPC_JMP((ctx->idx + 6) * 4);
-			EMIT(PPC_RAW_SUBFIC(0, src_reg, 32));
+			bpf_set_seen_register(ctx, tmp_reg);
+			EMIT(PPC_RAW_SUBFIC(__REG_R0, src_reg, 32));
 			EMIT(PPC_RAW_SRW(dst_reg, dst_reg, src_reg));
 			EMIT(PPC_RAW_SLW(__REG_R0, dst_reg_h, __REG_R0));
-			EMIT(PPC_RAW_SRAW(dst_reg_h, dst_reg_h, src_reg));
+			EMIT(PPC_RAW_ADDI(tmp_reg, src_reg, 32));
 			EMIT(PPC_RAW_OR(dst_reg, dst_reg, __REG_R0));
+			EMIT(PPC_RAW_RLWINM(__REG_R0, tmp_reg, 0, 26, 26));
+			EMIT(PPC_RAW_SRAW(tmp_reg, dst_reg_h, tmp_reg));
+			EMIT(PPC_RAW_SRAW(dst_reg_h, dst_reg_h, src_reg));
+			EMIT(PPC_RAW_SLW(tmp_reg, tmp_reg, __REG_R0));
+			EMIT(PPC_RAW_OR(dst_reg, dst_reg, tmp_reg));
 			break;
 		case BPF_ALU | BPF_ARSH | BPF_K: /* (s32) dst >>= imm */
 			if (!imm)
-- 
2.25.0