From nobody Fri Dec 19 08:04:07 2025 Delivered-To: importer@patchew.org Received-SPF: pass (zoho.com: domain of gnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; envelope-from=qemu-devel-bounces+importer=patchew.org@nongnu.org; helo=lists.gnu.org; Authentication-Results: mx.zohomail.com; dkim=fail; spf=pass (zoho.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org Return-Path: Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) by mx.zohomail.com with SMTPS id 1546988609270572.1307958231064; Tue, 8 Jan 2019 15:03:29 -0800 (PST) Received: from localhost ([127.0.0.1]:47837 helo=lists.gnu.org) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1gh0PA-0005uw-49 for importer@patchew.org; Tue, 08 Jan 2019 18:03:28 -0500 Received: from eggs.gnu.org ([209.51.188.92]:57808) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1gh08m-0005sZ-Jz for qemu-devel@nongnu.org; Tue, 08 Jan 2019 17:46:34 -0500 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1gh08k-0006de-H7 for qemu-devel@nongnu.org; Tue, 08 Jan 2019 17:46:32 -0500 Received: from ozlabs.org ([2401:3900:2:1::2]:40161) by eggs.gnu.org with esmtps (TLS1.0:DHE_RSA_AES_256_CBC_SHA1:32) (Exim 4.71) (envelope-from ) id 1gh08g-0006Xy-MK; Tue, 08 Jan 2019 17:46:28 -0500 Received: by ozlabs.org (Postfix, from userid 1007) id 43Z6mt42spz9sN1; Wed, 9 Jan 2019 09:46:05 +1100 (AEDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=gibson.dropbear.id.au; s=201602; t=1546987566; bh=aKAR/Xo69oM/CrvIho8dQ3EbTLMQGem1kzNGeVHBb9Q=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=i2DARSSu3pj1MA3fcC1EbD7NXtZ3PGQ9zGzBqS523IQSY7IVpdRnPXhNf7H24mx+K eSn8sVaNFIlSns2EqyQIsg40DFELYjdso9j5YDRvNlzKrZHGEk7Sk+NfTlxyReS4Pd PiV6JhpxWpPsRQLe9a8cxl90sjw+EmUaq5TpI2Ws= From: David Gibson To: peter.maydell@linaro.org Date: Wed, 9 Jan 2019 09:45:39 +1100 Message-Id: <20190108224600.23125-9-david@gibson.dropbear.id.au> X-Mailer: git-send-email 2.20.1 In-Reply-To: <20190108224600.23125-1-david@gibson.dropbear.id.au> References: <20190108224600.23125-1-david@gibson.dropbear.id.au> MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable X-detected-operating-system: by eggs.gnu.org: Genre and OS details not recognized. X-Received-From: 2401:3900:2:1::2 Subject: [Qemu-devel] [PULL 08/29] target/ppc: introduce get_avr64() and set_avr64() helpers for VMX register access X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.21 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: Richard Henderson , Mark Cave-Ayland , qemu-devel@nongnu.org, groug@kaod.org, qemu-ppc@nongnu.org, clg@kaod.org, David Gibson Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: "Qemu-devel" X-ZohoMail-DKIM: fail (Header signature does not verify) Content-Type: text/plain; charset="utf-8" From: Mark Cave-Ayland These helpers allow us to move AVR register values to/from the specified TC= Gv_i64 argument. To prevent VMX helpers accessing the cpu_avr{l,h} arrays directly, add extr= a TCG temporaries as required. Signed-off-by: Mark Cave-Ayland Reviewed-by: Richard Henderson Acked-by: David Gibson Signed-off-by: David Gibson --- target/ppc/translate.c | 10 ++ target/ppc/translate/vmx-impl.inc.c | 147 +++++++++++++++++++++------- 2 files changed, 124 insertions(+), 33 deletions(-) diff --git a/target/ppc/translate.c b/target/ppc/translate.c index 9cecab42f3..3bb24e7310 100644 --- a/target/ppc/translate.c +++ b/target/ppc/translate.c @@ -6709,6 +6709,16 @@ static inline void set_fpr(int regno, TCGv_i64 src) tcg_gen_mov_i64(cpu_fpr[regno], src); } =20 +static inline void get_avr64(TCGv_i64 dst, int regno, bool high) +{ + tcg_gen_mov_i64(dst, (high ? cpu_avrh : cpu_avrl)[regno]); +} + +static inline void set_avr64(int regno, TCGv_i64 src, bool high) +{ + tcg_gen_mov_i64((high ? cpu_avrh : cpu_avrl)[regno], src); +} + #include "translate/fp-impl.inc.c" =20 #include "translate/vmx-impl.inc.c" diff --git a/target/ppc/translate/vmx-impl.inc.c b/target/ppc/translate/vmx= -impl.inc.c index 3cb6fc2926..5e8327e9a3 100644 --- a/target/ppc/translate/vmx-impl.inc.c +++ b/target/ppc/translate/vmx-impl.inc.c @@ -18,52 +18,66 @@ static inline TCGv_ptr gen_avr_ptr(int reg) static void glue(gen_, name)(DisasContext *ctx) = \ { = \ TCGv EA; = \ + TCGv_i64 avr; = \ if (unlikely(!ctx->altivec_enabled)) { = \ gen_exception(ctx, POWERPC_EXCP_VPU); = \ return; = \ } = \ gen_set_access_type(ctx, ACCESS_INT); = \ + avr =3D tcg_temp_new_i64(); = \ EA =3D tcg_temp_new(); = \ gen_addr_reg_index(ctx, EA); = \ tcg_gen_andi_tl(EA, EA, ~0xf); = \ /* We only need to swap high and low halves. gen_qemu_ld64_i64 does = \ necessary 64-bit byteswap already. */ = \ if (ctx->le_mode) { = \ - gen_qemu_ld64_i64(ctx, cpu_avrl[rD(ctx->opcode)], EA); = \ + gen_qemu_ld64_i64(ctx, avr, EA); = \ + set_avr64(rD(ctx->opcode), avr, false); = \ tcg_gen_addi_tl(EA, EA, 8); = \ - gen_qemu_ld64_i64(ctx, cpu_avrh[rD(ctx->opcode)], EA); = \ + gen_qemu_ld64_i64(ctx, avr, EA); = \ + set_avr64(rD(ctx->opcode), avr, true); = \ } else { = \ - gen_qemu_ld64_i64(ctx, cpu_avrh[rD(ctx->opcode)], EA); = \ + gen_qemu_ld64_i64(ctx, avr, EA); = \ + set_avr64(rD(ctx->opcode), avr, true); = \ tcg_gen_addi_tl(EA, EA, 8); = \ - gen_qemu_ld64_i64(ctx, cpu_avrl[rD(ctx->opcode)], EA); = \ + gen_qemu_ld64_i64(ctx, avr, EA); = \ + set_avr64(rD(ctx->opcode), avr, false); = \ } = \ tcg_temp_free(EA); = \ + tcg_temp_free_i64(avr); = \ } =20 #define GEN_VR_STX(name, opc2, opc3) = \ static void gen_st##name(DisasContext *ctx) = \ { = \ TCGv EA; = \ + TCGv_i64 avr; = \ if (unlikely(!ctx->altivec_enabled)) { = \ gen_exception(ctx, POWERPC_EXCP_VPU); = \ return; = \ } = \ gen_set_access_type(ctx, ACCESS_INT); = \ + avr =3D tcg_temp_new_i64(); = \ EA =3D tcg_temp_new(); = \ gen_addr_reg_index(ctx, EA); = \ tcg_gen_andi_tl(EA, EA, ~0xf); = \ /* We only need to swap high and low halves. gen_qemu_st64_i64 does = \ necessary 64-bit byteswap already. */ = \ if (ctx->le_mode) { = \ - gen_qemu_st64_i64(ctx, cpu_avrl[rD(ctx->opcode)], EA); = \ + get_avr64(avr, rD(ctx->opcode), false); = \ + gen_qemu_st64_i64(ctx, avr, EA); = \ tcg_gen_addi_tl(EA, EA, 8); = \ - gen_qemu_st64_i64(ctx, cpu_avrh[rD(ctx->opcode)], EA); = \ + get_avr64(avr, rD(ctx->opcode), true); = \ + gen_qemu_st64_i64(ctx, avr, EA); = \ } else { = \ - gen_qemu_st64_i64(ctx, cpu_avrh[rD(ctx->opcode)], EA); = \ + get_avr64(avr, rD(ctx->opcode), true); = \ + gen_qemu_st64_i64(ctx, avr, EA); = \ tcg_gen_addi_tl(EA, EA, 8); = \ - gen_qemu_st64_i64(ctx, cpu_avrl[rD(ctx->opcode)], EA); = \ + get_avr64(avr, rD(ctx->opcode), false); = \ + gen_qemu_st64_i64(ctx, avr, EA); = \ } = \ tcg_temp_free(EA); = \ + tcg_temp_free_i64(avr); = \ } =20 #define GEN_VR_LVE(name, opc2, opc3, size) \ @@ -159,15 +173,20 @@ static void gen_lvsr(DisasContext *ctx) static void gen_mfvscr(DisasContext *ctx) { TCGv_i32 t; + TCGv_i64 avr; if (unlikely(!ctx->altivec_enabled)) { gen_exception(ctx, POWERPC_EXCP_VPU); return; } - tcg_gen_movi_i64(cpu_avrh[rD(ctx->opcode)], 0); + avr =3D tcg_temp_new_i64(); + tcg_gen_movi_i64(avr, 0); + set_avr64(rD(ctx->opcode), avr, true); t =3D tcg_temp_new_i32(); tcg_gen_ld_i32(t, cpu_env, offsetof(CPUPPCState, vscr)); - tcg_gen_extu_i32_i64(cpu_avrl[rD(ctx->opcode)], t); + tcg_gen_extu_i32_i64(avr, t); + set_avr64(rD(ctx->opcode), avr, false); tcg_temp_free_i32(t); + tcg_temp_free_i64(avr); } =20 static void gen_mtvscr(DisasContext *ctx) @@ -185,9 +204,10 @@ static void gen_mtvscr(DisasContext *ctx) #define GEN_VX_VMUL10(name, add_cin, ret_carry) \ static void glue(gen_, name)(DisasContext *ctx) \ { \ - TCGv_i64 t0 =3D tcg_temp_new_i64(); \ - TCGv_i64 t1 =3D tcg_temp_new_i64(); \ - TCGv_i64 t2 =3D tcg_temp_new_i64(); \ + TCGv_i64 t0; \ + TCGv_i64 t1; \ + TCGv_i64 t2; \ + TCGv_i64 avr; \ TCGv_i64 ten, z; \ \ if (unlikely(!ctx->altivec_enabled)) { \ @@ -195,30 +215,43 @@ static void glue(gen_, name)(DisasContext *ctx) = \ return; \ } \ \ + t0 =3D tcg_temp_new_i64(); \ + t1 =3D tcg_temp_new_i64(); \ + t2 =3D tcg_temp_new_i64(); \ + avr =3D tcg_temp_new_i64(); \ ten =3D tcg_const_i64(10); \ z =3D tcg_const_i64(0); \ \ if (add_cin) { \ - tcg_gen_mulu2_i64(t0, t1, cpu_avrl[rA(ctx->opcode)], ten); \ - tcg_gen_andi_i64(t2, cpu_avrl[rB(ctx->opcode)], 0xF); \ - tcg_gen_add2_i64(cpu_avrl[rD(ctx->opcode)], t2, t0, t1, t2, z); \ + get_avr64(avr, rA(ctx->opcode), false); \ + tcg_gen_mulu2_i64(t0, t1, avr, ten); \ + get_avr64(avr, rB(ctx->opcode), false); \ + tcg_gen_andi_i64(t2, avr, 0xF); \ + tcg_gen_add2_i64(avr, t2, t0, t1, t2, z); \ + set_avr64(rD(ctx->opcode), avr, false); \ } else { \ - tcg_gen_mulu2_i64(cpu_avrl[rD(ctx->opcode)], t2, \ - cpu_avrl[rA(ctx->opcode)], ten); \ + get_avr64(avr, rA(ctx->opcode), false); \ + tcg_gen_mulu2_i64(avr, t2, avr, ten); \ + set_avr64(rD(ctx->opcode), avr, false); \ } \ \ if (ret_carry) { \ - tcg_gen_mulu2_i64(t0, t1, cpu_avrh[rA(ctx->opcode)], ten); \ - tcg_gen_add2_i64(t0, cpu_avrl[rD(ctx->opcode)], t0, t1, t2, z); \ - tcg_gen_movi_i64(cpu_avrh[rD(ctx->opcode)], 0); \ + get_avr64(avr, rA(ctx->opcode), true); \ + tcg_gen_mulu2_i64(t0, t1, avr, ten); \ + tcg_gen_add2_i64(t0, avr, t0, t1, t2, z); \ + set_avr64(rD(ctx->opcode), avr, false); \ + set_avr64(rD(ctx->opcode), z, true); \ } else { \ - tcg_gen_mul_i64(t0, cpu_avrh[rA(ctx->opcode)], ten); \ - tcg_gen_add_i64(cpu_avrh[rD(ctx->opcode)], t0, t2); \ + get_avr64(avr, rA(ctx->opcode), true); \ + tcg_gen_mul_i64(t0, avr, ten); \ + tcg_gen_add_i64(avr, t0, t2); \ + set_avr64(rD(ctx->opcode), avr, true); \ } \ \ tcg_temp_free_i64(t0); \ tcg_temp_free_i64(t1); \ tcg_temp_free_i64(t2); \ + tcg_temp_free_i64(avr); \ tcg_temp_free_i64(ten); \ tcg_temp_free_i64(z); \ } \ @@ -232,12 +265,31 @@ GEN_VX_VMUL10(vmul10ecuq, 1, 1); #define GEN_VX_LOGICAL(name, tcg_op, opc2, opc3) \ static void glue(gen_, name)(DisasContext *ctx) = \ { \ + TCGv_i64 t0; \ + TCGv_i64 t1; \ + TCGv_i64 avr; \ + \ if (unlikely(!ctx->altivec_enabled)) { \ gen_exception(ctx, POWERPC_EXCP_VPU); \ return; \ } \ - tcg_op(cpu_avrh[rD(ctx->opcode)], cpu_avrh[rA(ctx->opcode)], cpu_avrh[= rB(ctx->opcode)]); \ - tcg_op(cpu_avrl[rD(ctx->opcode)], cpu_avrl[rA(ctx->opcode)], cpu_avrl[= rB(ctx->opcode)]); \ + t0 =3D tcg_temp_new_i64(); \ + t1 =3D tcg_temp_new_i64(); \ + avr =3D tcg_temp_new_i64(); \ + \ + get_avr64(t0, rA(ctx->opcode), true); \ + get_avr64(t1, rB(ctx->opcode), true); \ + tcg_op(avr, t0, t1); \ + set_avr64(rD(ctx->opcode), avr, true); \ + \ + get_avr64(t0, rA(ctx->opcode), false); \ + get_avr64(t1, rB(ctx->opcode), false); \ + tcg_op(avr, t0, t1); \ + set_avr64(rD(ctx->opcode), avr, false); \ + \ + tcg_temp_free_i64(t0); \ + tcg_temp_free_i64(t1); \ + tcg_temp_free_i64(avr); \ } =20 GEN_VX_LOGICAL(vand, tcg_gen_and_i64, 2, 16); @@ -406,6 +458,7 @@ GEN_VXFORM(vmrglw, 6, 6); static void gen_vmrgew(DisasContext *ctx) { TCGv_i64 tmp; + TCGv_i64 avr; int VT, VA, VB; if (unlikely(!ctx->altivec_enabled)) { gen_exception(ctx, POWERPC_EXCP_VPU); @@ -415,15 +468,28 @@ static void gen_vmrgew(DisasContext *ctx) VA =3D rA(ctx->opcode); VB =3D rB(ctx->opcode); tmp =3D tcg_temp_new_i64(); - tcg_gen_shri_i64(tmp, cpu_avrh[VB], 32); - tcg_gen_deposit_i64(cpu_avrh[VT], cpu_avrh[VA], tmp, 0, 32); - tcg_gen_shri_i64(tmp, cpu_avrl[VB], 32); - tcg_gen_deposit_i64(cpu_avrl[VT], cpu_avrl[VA], tmp, 0, 32); + avr =3D tcg_temp_new_i64(); + + get_avr64(avr, VB, true); + tcg_gen_shri_i64(tmp, avr, 32); + get_avr64(avr, VA, true); + tcg_gen_deposit_i64(avr, avr, tmp, 0, 32); + set_avr64(VT, avr, true); + + get_avr64(avr, VB, false); + tcg_gen_shri_i64(tmp, avr, 32); + get_avr64(avr, VA, false); + tcg_gen_deposit_i64(avr, avr, tmp, 0, 32); + set_avr64(VT, avr, false); + tcg_temp_free_i64(tmp); + tcg_temp_free_i64(avr); } =20 static void gen_vmrgow(DisasContext *ctx) { + TCGv_i64 t0, t1; + TCGv_i64 avr; int VT, VA, VB; if (unlikely(!ctx->altivec_enabled)) { gen_exception(ctx, POWERPC_EXCP_VPU); @@ -432,9 +498,23 @@ static void gen_vmrgow(DisasContext *ctx) VT =3D rD(ctx->opcode); VA =3D rA(ctx->opcode); VB =3D rB(ctx->opcode); - - tcg_gen_deposit_i64(cpu_avrh[VT], cpu_avrh[VB], cpu_avrh[VA], 32, 32); - tcg_gen_deposit_i64(cpu_avrl[VT], cpu_avrl[VB], cpu_avrl[VA], 32, 32); + t0 =3D tcg_temp_new_i64(); + t1 =3D tcg_temp_new_i64(); + avr =3D tcg_temp_new_i64(); + + get_avr64(t0, VB, true); + get_avr64(t1, VA, true); + tcg_gen_deposit_i64(avr, t0, t1, 32, 32); + set_avr64(VT, avr, true); + + get_avr64(t0, VB, false); + get_avr64(t1, VA, false); + tcg_gen_deposit_i64(avr, t0, t1, 32, 32); + set_avr64(VT, avr, false); + + tcg_temp_free_i64(t0); + tcg_temp_free_i64(t1); + tcg_temp_free_i64(avr); } =20 GEN_VXFORM(vmuloub, 4, 0); @@ -790,7 +870,7 @@ static void glue(gen_, name)(DisasContext *ctx) = \ { \ TCGv_ptr rb, rd; \ uint8_t uimm =3D UIMM4(ctx->opcode); \ - TCGv_i32 t0 =3D tcg_temp_new_i32(); \ + TCGv_i32 t0; \ if (unlikely(!ctx->altivec_enabled)) { \ gen_exception(ctx, POWERPC_EXCP_VPU); \ return; \ @@ -798,6 +878,7 @@ static void glue(gen_, name)(DisasContext *ctx) = \ if (uimm > splat_max) { \ uimm =3D 0; \ } \ + t0 =3D tcg_temp_new_i32(); \ tcg_gen_movi_i32(t0, uimm); \ rb =3D gen_avr_ptr(rB(ctx->opcode)); \ rd =3D gen_avr_ptr(rD(ctx->opcode)); \ --=20 2.20.1