From nobody Thu Jan 30 18:48:46 2025 Received: from mail-pj1-f53.google.com (mail-pj1-f53.google.com [209.85.216.53]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 8A889158A09 for ; Tue, 28 Jan 2025 20:06:31 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=209.85.216.53 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1738094794; cv=none; b=m6aj2Yi9+z/pgL6CWuBxQtsdRTBarA9jwUFtl7mfYlcCF3YkRqCWeYRt1LlcSgh5IKkpPg++CM1J80qzPF+QyRZZ78F1R09U6FbVaNCZxkrPRcJ18eicdZ82ClMfF35LUVtYLxMDkFL6yUvl6+OaIvCR1Lpv26QVL2t1oMUxONc= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1738094794; c=relaxed/simple; bh=OlyyFFGJKKb9rmkiPSLFyPA1bfvLaKaSmOAiI/T1Czo=; h=From:Date:Subject:MIME-Version:Content-Type:Message-Id:To:Cc; b=Xt7VsbVLW/OCmKiv/TwQsMrzy1tCUoBp4SnBm1sIGuLNtxTOxhYj22ZeoX96/M1mnqzlTdTGSDK+mW6pS4hqI5fyytTzTgnkmWcz+1g57GCsV5ZOvkI59PEecSRFFTaySzbGxdZePFJGpr9Z4FIFVoetBDsO/wGbymNx6CIBeWQ= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=none (p=none dis=none) header.from=rivosinc.com; spf=pass smtp.mailfrom=rivosinc.com; dkim=pass (2048-bit key) header.d=rivosinc-com.20230601.gappssmtp.com header.i=@rivosinc-com.20230601.gappssmtp.com header.b=DL9Cm/mh; arc=none smtp.client-ip=209.85.216.53 Authentication-Results: smtp.subspace.kernel.org; dmarc=none (p=none dis=none) header.from=rivosinc.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=rivosinc.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=rivosinc-com.20230601.gappssmtp.com header.i=@rivosinc-com.20230601.gappssmtp.com header.b="DL9Cm/mh" Received: by mail-pj1-f53.google.com with SMTP id 98e67ed59e1d1-2ef714374c0so56851a91.0 for ; Tue, 28 Jan 2025 12:06:31 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=rivosinc-com.20230601.gappssmtp.com; s=20230601; t=1738094790; x=1738699590; darn=vger.kernel.org; h=cc:to:message-id:content-transfer-encoding:mime-version:subject :date:from:from:to:cc:subject:date:message-id:reply-to; bh=lDyVQTBA7PUUvWjbd4Ge36IvAZ5YSvfp1xVWyK0ZYTw=; b=DL9Cm/mhqNtMwtN86S/JekHgfHgSRNcQOhq//gZfUJ8ChMKD7Z3zy3UyEKe9z9eTbS CQiqXXpe5zVCI/yD2BMwBbiXhyCQA5Idd+MvpYvbANdOJEvFlwZiinoWhOtA8g1qtJkE PQ7tbt0P/tbfd1KwWHgIai9Bm7Ay+HI5+rfd5Mh02Vmf1A4tKXeNYdn+Qs39mYrG5v9H 8vDQBtxUzDvX6qx9cJ2hygRA53o0JMMfOLIwZsaKxuF0W/uUKuE7ujufaSP7NcsnwFeb Mt5GPM0u3DKVMNYK8txy3jUjag69iNcqBljvkYMbEB2lFIK2iSHHzck9li68qUsBOStW SHXA== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1738094790; x=1738699590; h=cc:to:message-id:content-transfer-encoding:mime-version:subject :date:from:x-gm-message-state:from:to:cc:subject:date:message-id :reply-to; bh=lDyVQTBA7PUUvWjbd4Ge36IvAZ5YSvfp1xVWyK0ZYTw=; b=ncZAeVaVEY1V2vb75vmpCubUAXBMaJdcVdyvoIB4WNdt501uNFoxqSgxDbQW1JDzAm /zH/tDczt2lcn6JYff/ZtpCjt8JARnjn5cFP76UpvtjSbTF5GbfR2FVmlxUrSB8CwjYF 7gaJQyWRNOJSsiYLh5E7L/jCLxWZLTZ43O4+J+Jxu16rCvUxS8JOu/hO4C9FndWWSyDR JHMa+lYBywnI1APwmO7X21PckIKKpW6X6sr/2iUPHmZ5jIw0Cu0RMAcjrLOfzTOI3cjQ k++PYCaDOpAYmGgiT4w6PBgPejN0Lfvo50lrfUMqeiB181P5fZkvrEW20JjXWZ+ORwsk 5mjA== X-Forwarded-Encrypted: i=1; AJvYcCXG7Ox/zQhqiy/+zR63WTaWWTnOSFZLD+qSigIPn/N/dTfHBHLkaMWHfRsHpRZUcO75OY2NfM/k2+KM+R0=@vger.kernel.org X-Gm-Message-State: AOJu0YxanJ0p/dbC9kaO6tBvhKHOyH7gjK+J5yUhvKfdakBLeINpTe/f G8EzUgiar/MxxOo+UVCWVuVAdOCbW6r3S3hsj2vvRp3c1Hc5b3Q0L6UkkdK/AcrJnO/nZD5eYc4 k X-Gm-Gg: ASbGncv3btgb/gd90ckUUSIPQo7aZ2uhy7VEJ8/1sgHptdK+wVTDDDZKfAp28kzC+8m e8mTpzgITXA67yxppxICcZsINDL14ZgTZafQ3KAce8u/ZIgW60alqOsxhJg3L/UCNWygwQ6CTBS SINHOUvRg/RWsCFKBxSy3ntWOdrrNIX2Hou8xVIKbHHg6mksGTeZ/F0of5wtJPuHWISd26LLeHa bmP40FHUxkLlyITGqAPHih4eW7qIUmqZLtc4x3soBlDbAPbpBUo6SPn5a0C10SROJRP7srvyw34 cHu88yQOUnHvApjAbaFwQ/QcH2rcTp0= X-Google-Smtp-Source: AGHT+IGfiwM1GiaWLFVTL0UIxryEtvd5zmHJnKcWdmv6nkOF5WgHkws+kt9CR76TSVgPA0My70uS/g== X-Received: by 2002:a17:90b:3d43:b0:2f5:63a:44f8 with SMTP id 98e67ed59e1d1-2f82bff716emr7570879a91.8.1738094790475; Tue, 28 Jan 2025 12:06:30 -0800 (PST) Received: from charlie.ba.rivosinc.com ([64.71.180.162]) by smtp.gmail.com with ESMTPSA id 98e67ed59e1d1-2f7ffa8318asm9775224a91.47.2025.01.28.12.06.29 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Tue, 28 Jan 2025 12:06:29 -0800 (PST) From: Charlie Jenkins Date: Tue, 28 Jan 2025 12:06:08 -0800 Subject: [PATCH v3] riscv: Add runtime constant support Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable Message-Id: <20250128-runtime_const_riscv-v3-1-11922989e2d3@rivosinc.com> X-B4-Tracking: v=1; b=H4sIAK84mWcC/43NTQ7CIBCG4as0rMXwI1JceQ9jGkqndhYFA5Vom t5d2sSNceHy/ZJ5ZiYJIkIip2omETImDL6E3FXEDdbfgGJXmggmFONC0vjwE47QuODT1ERMLtO j62p1ABA116Rc3iP0+NzUy7X0gGkK8bU9yXxdP57+6WVOOdVGtUxIsIK154g5JPRu78JIVjKLP xhRGKMsaNcbbaX5YpZleQO0cuACAAEAAA== X-Change-ID: 20250123-runtime_const_riscv-6cd854ee2817 To: Paul Walmsley , Palmer Dabbelt , Ard Biesheuvel , Ben Dooks , Pasha Bouzarjomehri Cc: linux-riscv@lists.infradead.org, linux-kernel@vger.kernel.org, Charlie Jenkins X-Mailer: b4 0.14.2 X-Developer-Signature: v=1; a=openpgp-sha256; l=8001; i=charlie@rivosinc.com; h=from:subject:message-id; bh=OlyyFFGJKKb9rmkiPSLFyPA1bfvLaKaSmOAiI/T1Czo=; b=owGbwMvMwCXWx5hUnlvL8Y3xtFoSQ/pMi/0bmH/VL/vocLqh5eee87Nt1fdtfcbxrExQ7aWPZ NxXaSHxjlIWBjEuBlkxRRaeaw3MrXf0y46Klk2AmcPKBDKEgYtTACbyag8jw/fCaXXGbPt+bt5w 5fKSxJON7t1K7DEXzF9uinHqCzrMIcjwP1Xx+N5THBvvSZ1lm+r8333Wt0fqSud5ZZ4Zbm1nPpT zlQ8A X-Developer-Key: i=charlie@rivosinc.com; a=openpgp; fpr=7D834FF11B1D8387E61C776FFB10D1F27D6B1354 Implement the runtime constant infrastructure for riscv. Use this infrastructure to generate constants to be used by the d_hash() function. This is the riscv variant of commit 94a2bc0f611c ("arm64: add 'runtime constant' support") and commit e3c92e81711d ("runtime constants: add x86 architecture support"). Signed-off-by: Charlie Jenkins --- Ard brought this to my attention in this patch [1]. [1] https://lore.kernel.org/lkml/CAMj1kXE4DJnwFejNWQu784GvyJO=3DaGNrzuLjSxi= owX_e7nW8QA@mail.gmail.com/ --- Changes in v3: - Leverage "pack" instruction for runtime_const_ptr() to reduce hot path by 3 instructions if Zbkb is supported. Suggested by Pasha Bouzarjomehri = (pasha@rivosinc.com) - Link to v2: https://lore.kernel.org/r/20250127-runtime_const_riscv-v2-1-9= 5ae7cf97a39@rivosinc.com Changes in v2: - Treat instructions as __le32 and do proper conversions (Ben) - Link to v1: https://lore.kernel.org/r/20250127-runtime_const_riscv-v1-1-7= 95b023ea20b@rivosinc.com --- arch/riscv/include/asm/runtime-const.h | 194 +++++++++++++++++++++++++++++= ++++ arch/riscv/kernel/vmlinux.lds.S | 3 + 2 files changed, 197 insertions(+) diff --git a/arch/riscv/include/asm/runtime-const.h b/arch/riscv/include/as= m/runtime-const.h new file mode 100644 index 0000000000000000000000000000000000000000..0ecbe6967013900781b0b1048d4= 622f676b64076 --- /dev/null +++ b/arch/riscv/include/asm/runtime-const.h @@ -0,0 +1,194 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_RISCV_RUNTIME_CONST_H +#define _ASM_RISCV_RUNTIME_CONST_H + +#include +#include +#include +#include + +#ifdef CONFIG_32BIT +#define runtime_const_ptr(sym) \ +({ \ + typeof(sym) __ret, __tmp; \ + asm_inline("1:\t" \ + ".option push" \ + ".option norvc" \ + "lui %[__ret],0x89abd\n\t" \ + "addi %[__ret],-0x211\n\t" \ + ".option pop" \ + ".pushsection runtime_ptr_" #sym ",\"a\"\n\t" \ + ".long 1b - .\n\t" \ + ".popsection" \ + : [__ret] "=3Dr" (__ret)); \ + __ret; \ +}) +#else +/* + * Loading 64-bit constants into a register from immediates is a non-trivi= al + * task on riscv64. To get it somewhat performant, load 32 bits into two + * different registers and then combine the results. + * + * If the processor supports the Zbkb extension, we can combine the final + * "slli,slli,srli,add" into the single "pack" instruction. If the process= or + * doesn't support Zbkb but does support the Zbb extension, we can + * combine the final "slli,srli,add" into one instruction "add.uw". + */ +#define runtime_const_ptr(sym) \ +({ \ + typeof(sym) __ret, __tmp; \ + asm_inline("1:\t" \ + ".option push\n\t" \ + ".option norvc\n\t" \ + "lui %[__ret],0x89abd\n\t" \ + "lui %[__tmp],0x1234\n\t" \ + "addiw %[__ret],%[__ret],-0x211\n\t" \ + "addiw %[__tmp],%[__tmp],0x567\n\t" \ + ALTERNATIVE_2( \ + "slli %[__tmp],%[__tmp],32\n\t" \ + "slli %[__ret],%[__ret],32\n\t" \ + "srli %[__ret],%[__ret],32\n\t" \ + "add %[__ret],%[__ret],%[__tmp]\n\t", \ + ".option push\n\t" \ + ".option arch,+zba\n\t" \ + "slli %[__tmp],%[__tmp],32\n\t" \ + "add.uw %[__ret],%[__ret],%[__tmp]\n\t" \ + "nop\n\t" \ + "nop\n\t" \ + ".option pop\n\t", \ + 0, RISCV_ISA_EXT_ZBA, 1, \ + ".option push\n\t" \ + ".option arch,+zbkb\n\t" \ + "pack %[__ret],%[__ret],%[__tmp]\n\t" \ + "nop\n\t" \ + "nop\n\t" \ + "nop\n\t" \ + ".option pop\n\t", \ + 0, RISCV_ISA_EXT_ZBKB, 1 \ + ) \ + ".option pop\n\t" \ + ".pushsection runtime_ptr_" #sym ",\"a\"\n\t" \ + ".long 1b - .\n\t" \ + ".popsection" \ + : [__ret] "=3Dr" (__ret), [__tmp] "=3Dr" (__tmp)); \ + __ret; \ +}) +#endif + +#ifdef CONFIG_32BIT +#define SRLI "srli " +#else +#define SRLI "srliw " +#endif + +#define runtime_const_shift_right_32(val, sym) \ +({ \ + u32 __ret; \ + asm_inline("1:\t" \ + ".option push\n\t" \ + ".option norvc\n\t" \ + SRLI "%[__ret],%[__val],12\n\t" \ + ".option pop\n\t" \ + ".pushsection runtime_shift_" #sym ",\"a\"\n\t" \ + ".long 1b - .\n\t" \ + ".popsection" \ + : [__ret] "=3Dr" (__ret) \ + : [__val] "r" (val)); \ + __ret; \ +}) + +#define runtime_const_init(type, sym) do { \ + extern s32 __start_runtime_##type##_##sym[]; \ + extern s32 __stop_runtime_##type##_##sym[]; \ + \ + runtime_const_fixup(__runtime_fixup_##type, \ + (unsigned long)(sym), \ + __start_runtime_##type##_##sym, \ + __stop_runtime_##type##_##sym); \ +} while (0) + +static inline void __runtime_fixup_caches(void *where, unsigned int insns) +{ + /* On riscv there are currently only cache-wide flushes so va is ignored.= */ + __always_unused uintptr_t va =3D (uintptr_t)where; + + flush_icache_range(va, va + 4*insns); +} + +/* + * The 32-bit immediate is stored in a lui+addi pairing. + * lui holds the upper 20 bits of the immediate in the first 20 bits of th= e instruction. + * addi holds the lower 12 bits of the immediate in the first 12 bits of t= he instruction. + */ +static inline void __runtime_fixup_32(u32 *lui, u32 *addi, unsigned int va= l) +{ + unsigned int lower_immediate, upper_immediate; + u32 lui_insn =3D le32_to_cpu(*lui); + u32 addi_insn =3D le32_to_cpu(*addi); + __le32 addi_res, lui_res; + + lower_immediate =3D sign_extend32(val, 11); + upper_immediate =3D (val - lower_immediate); + + if (upper_immediate & 0xfffff000) { + /* replace upper 20 bits of lui with upper immediate */ + lui_insn &=3D 0x00000fff; + lui_insn |=3D upper_immediate & 0xfffff000; + } else { + /* replace lui with nop if immediate is small enough to fit in addi */ + lui_insn =3D 0x00000013; + } + + if (lower_immediate & 0x00000fff) { + /* replace upper 12 bits of addi with lower 12 bits of val */ + addi_insn &=3D 0x000fffff; + addi_insn |=3D (lower_immediate & 0x00000fff) << 20; + } else { + /* replace addi with nop if lower_immediate is empty */ + addi_insn =3D 0x00000013; + } + + addi_res =3D cpu_to_le32(addi_insn); + lui_res =3D cpu_to_le32(lui_insn); + patch_insn_write(addi, &addi_res, sizeof(addi_res)); + patch_insn_write(lui, &lui_res, sizeof(lui_res)); +} + +static inline void __runtime_fixup_ptr(void *where, unsigned long val) +{ + if (IS_ENABLED(CONFIG_32BIT)) { + __runtime_fixup_32(where, where + 4, val); + __runtime_fixup_caches(where, 2); + } else { + __runtime_fixup_32(where, where + 8, val); + __runtime_fixup_32(where + 4, where + 12, val >> 32); + __runtime_fixup_caches(where, 4); + } +} + +/* + * Replace the least significant 5 bits of the srli/srliw immediate that is + * located at bits 20-24 + */ +static inline void __runtime_fixup_shift(void *where, unsigned long val) +{ + u32 insn =3D le32_to_cpu(*(__le32 *)where); + __le32 res; + + insn &=3D 0xfe0fffff; + insn |=3D (val & 0b11111) << 20; + + res =3D cpu_to_le32(insn); + patch_text_nosync(where, &res, sizeof(insn)); +} + +static inline void runtime_const_fixup(void (*fn)(void *, unsigned long), + unsigned long val, s32 *start, s32 *end) +{ + while (start < end) { + fn(*start + (void *)start, val); + start++; + } +} + +#endif /* _ASM_RISCV_RUNTIME_CONST_H */ diff --git a/arch/riscv/kernel/vmlinux.lds.S b/arch/riscv/kernel/vmlinux.ld= s.S index 002ca58dd998cb78b662837b5ebac988fb6c77bb..61bd5ba6680a786bf1db7dc37bf= 1acda0639b5c7 100644 --- a/arch/riscv/kernel/vmlinux.lds.S +++ b/arch/riscv/kernel/vmlinux.lds.S @@ -97,6 +97,9 @@ SECTIONS { EXIT_DATA } + + RUNTIME_CONST_VARIABLES + PERCPU_SECTION(L1_CACHE_BYTES) =20 .rel.dyn : { --- base-commit: ffd294d346d185b70e28b1a28abe367bbfe53c04 change-id: 20250123-runtime_const_riscv-6cd854ee2817 --=20 - Charlie