From nobody Sun Feb 8 14:51:46 2026 Received: from mail-ed1-f52.google.com (mail-ed1-f52.google.com [209.85.208.52]) (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 E45CFE571 for ; Wed, 25 Dec 2024 08:24:19 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=209.85.208.52 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1735115061; cv=none; b=I5Ma7UFk8sm03B2uIb3V4y9H/ZoZ25j9FJAS96qkZUr92+OmchpH2NR9aVcllMJP59ia6BTwnNnzkQMUqsErqNmodxE4fIH/AzUpQzY1ejeELZzmkMv9k9U6Jcd3e4M3JdOB8qE88ZUGtDRSzSTU5ZgzELqW+WIGFHKxH3A3QG0= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1735115061; c=relaxed/simple; bh=6JUZ4o4vvoR9I2lUCVPf7QNwM/zBu0g8jvYrv5zFujc=; h=From:To:Cc:Subject:Date:Message-Id:MIME-Version; b=AnhOkRsPADyV8v1pblsZu3N2FalT+bvVFRCKj/COfv2ktoOKkzC6TnkjMXhoXXzv0CsUnTOn9othxFZ6UJvqpix0znQobT2r8AksBy9oW/GWQQz90+X+CtHDwvJ1qNUa6BbcXdXnK0JnpT42C+/8M1TaE6OVLabsr6UNVuGYOw0= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=gmail.com; spf=pass smtp.mailfrom=gmail.com; dkim=pass (2048-bit key) header.d=gmail.com header.i=@gmail.com header.b=bGtFbscD; arc=none smtp.client-ip=209.85.208.52 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=gmail.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=gmail.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=gmail.com header.i=@gmail.com header.b="bGtFbscD" Received: by mail-ed1-f52.google.com with SMTP id 4fb4d7f45d1cf-5d3e829ff44so12192503a12.0 for ; Wed, 25 Dec 2024 00:24:19 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20230601; t=1735115058; x=1735719858; darn=vger.kernel.org; h=content-transfer-encoding:mime-version:message-id:date:subject:cc :to:from:from:to:cc:subject:date:message-id:reply-to; bh=BWMFPl6BBjVV6yqTNgiJ5wMWW3VBFJzmfcK7dXSbSG4=; b=bGtFbscDrZ2g76JYRg9Q9xEf+Fy0/qWH0uV/DuF77UjGKAf+Pwm0oewlB7kHh0wPR6 xeXSv1lZniCuWbffNTLlIZTfo9TWolFP1S1tvtpCLdxdbgTWRFqof3Hm3Wd49QVi7ink y7hC35KpXmDZFj1x0vxkByFiLAVJOZhyfmfVlTxvdkTLr2daJs4F96wFDAOIQIaM7ulE OeAhrQ24j3daDft+fhKySwNBifelEupn4WY13oM7CjyVtaa6ZxSdOAtRXqrSuO/PsOem J9i00/yqiyLyIce1ua94VWtSplum1h4eey0qcCi0ULHV1zFvBsF315MUCCK4F6zxFkBM zbKA== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1735115058; x=1735719858; h=content-transfer-encoding:mime-version:message-id:date:subject:cc :to:from:x-gm-message-state:from:to:cc:subject:date:message-id :reply-to; bh=BWMFPl6BBjVV6yqTNgiJ5wMWW3VBFJzmfcK7dXSbSG4=; b=E5dnB3CkF6gEOZ8skNoX6m9lr/Zjs4VfLCL2aVAWxrDsviUP55Z9eTDudG9MzDKCfg G6ME89O7tJ48mbVqMLfLFCQlt/b0f4QnA2YLOhDlMKHAQoYNNCwx4RTUdQA50wGknI/h AfGUXbyy93x1VspA8WjUqvAYbtrpLjTU2geWD0SKS0xVFQq0ifUq/ijgcl6AUQEZPDj7 b3psRbc30fZ+oHIOMHvX3F/GQrzXa8VVsT41LsJZd5+vZZdrM82xMW1Qw0L8D28nj9QZ d/T/wUDtuXn2X+M4/G4vw+GIweRbtMEm0mguPRn3To8Rk0qGm1VfFVDJFk0BtJYpT6fO PIEg== X-Forwarded-Encrypted: i=1; AJvYcCWiYSFML18dXdB2x8RlehXTDrN7nAUVAuk6u96crSSv5pxPsPnM6yQ3QKP/4UbNW6atbl4w8f78tlDOp3E=@vger.kernel.org X-Gm-Message-State: AOJu0YxYm6SZd5mcgyQEyLNh7bLp6zUFylsIGvxYjZuFd6C7zCHq8n34 q/9OFNl8DkDXaOYtvn7XFJTVLMVCt8SAWjqpU2aDin06WSCygfgt X-Gm-Gg: ASbGnctiS11mRIAsQGMaUvJph3Z4doAEKaigBdkN96oKVtt03hnpQBxlyNxJ28s7vIl tJyXiAHly8a/z92aaFoBbdUWtKH5OeuLaRA8VuEh2HBgLUzpaGKnt8lb7E+lkMNowMAvuTsgn26 eOkcLwGx/oi8HsfjHBpR9GfpESstKjry+mv8II9RyMOIp3B/5tXsUqO7es0+UjTf6JTLaVWJyqR Jw7nhjx1Xp44dyD3FpkY6dGwUaGgb6SyBqcjZYX+QNv+ZkhqqN7tc4IQGRdXfTVWH61iBXPPPXg hAAcQ7j70qlKAQc= X-Google-Smtp-Source: AGHT+IEUvxRI41Vqedig7jcxV57lOBqo0tPtLsvO/mSofwkkDHvbsY/WaSCcBxQjgK/6iuQThoWdlw== X-Received: by 2002:a17:906:36ce:b0:aae:bb48:211e with SMTP id a640c23a62f3a-aaebb482becmr962797366b.27.1735115057817; Wed, 25 Dec 2024 00:24:17 -0800 (PST) Received: from localhost.localdomain ([109.245.38.221]) by smtp.gmail.com with ESMTPSA id a640c23a62f3a-aac0f06629esm769283766b.189.2024.12.25.00.24.13 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Wed, 25 Dec 2024 00:24:15 -0800 (PST) From: Aleksandar Rikalo To: linux-riscv@lists.infradead.org Cc: Paul Walmsley , Palmer Dabbelt , Albert Ou , Will Deacon , Peter Zijlstra , Boqun Feng , Mark Rutland , Yury Norov , Rasmus Villemoes , Andrea Parri , Leonardo Bras , Guo Ren , Samuel Holland , Eric Chan , Aleksandar Rikalo , linux-kernel@vger.kernel.org, Djordje Todorovic Subject: [PATCH v2] riscv: Use Zalrsc extension to implement atomic functions Date: Wed, 25 Dec 2024 09:24:12 +0100 Message-Id: <20241225082412.36727-1-arikalo@gmail.com> X-Mailer: git-send-email 2.25.1 Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset="utf-8" From: Chao-ying Fu Use only LR/SC instructions to implement atomic functions. Add config RISCV_AMO_USE_ZALRSC. Signed-off-by: Chao-ying Fu Signed-off-by: Aleksandar Rikalo --- arch/riscv/Kconfig | 11 +++++++ arch/riscv/include/asm/atomic.h | 52 +++++++++++++++++++++++++++++++- arch/riscv/include/asm/bitops.h | 45 +++++++++++++++++++++++++++ arch/riscv/include/asm/cmpxchg.h | 16 ++++++++++ arch/riscv/include/asm/futex.h | 46 ++++++++++++++++++++++++++++ 5 files changed, 169 insertions(+), 1 deletion(-) diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index cc63aef41e94..9fb020b49408 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -715,6 +715,17 @@ config RISCV_ISA_ZACAS =20 If you don't know what to do here, say Y. =20 +config RISCV_AMO_USE_ZALRSC + bool "Use Zalrsc extension to implement atomic functions" + help + Kernel uses only LR/SC instructions to implement atomic functions. + + It makes sense to enable this option if your platform only + implements the Zalrsc extension (a subset of the A extension), + and not the complete A extension. + + If you don't know what to do here, say N. + config TOOLCHAIN_HAS_ZBB bool default y diff --git a/arch/riscv/include/asm/atomic.h b/arch/riscv/include/asm/atomi= c.h index 5b96c2f61adb..88f62e33a545 100644 --- a/arch/riscv/include/asm/atomic.h +++ b/arch/riscv/include/asm/atomic.h @@ -50,6 +50,7 @@ static __always_inline void arch_atomic64_set(atomic64_t = *v, s64 i) * have the AQ or RL bits set. These don't return anything, so there's on= ly * one version to worry about. */ +#ifndef RISCV_AMO_USE_ZALRSC #define ATOMIC_OP(op, asm_op, I, asm_type, c_type, prefix) \ static __always_inline \ void arch_atomic##prefix##_##op(c_type i, atomic##prefix##_t *v) \ @@ -59,7 +60,23 @@ void arch_atomic##prefix##_##op(c_type i, atomic##prefix= ##_t *v) \ : "+A" (v->counter) \ : "r" (I) \ : "memory"); \ -} \ +} +#else +#define ATOMIC_OP(op, asm_op, I, asm_type, c_type, prefix) \ +static __always_inline \ +void arch_atomic##prefix##_##op(c_type i, atomic##prefix##_t *v) \ +{ \ + register c_type ret, temp; \ + __asm__ __volatile__ ( \ + "1: lr." #asm_type " %1, %0\n" \ + " " #asm_op " %2, %1, %3\n" \ + " sc." #asm_type " %2, %2, %0\n" \ + " bnez %2, 1b\n" \ + : "+A" (v->counter), "=3D&r" (ret), "=3D&r" (temp) \ + : "r" (I) \ + : "memory"); \ +} +#endif =20 #ifdef CONFIG_GENERIC_ATOMIC64 #define ATOMIC_OPS(op, asm_op, I) \ @@ -84,6 +101,7 @@ ATOMIC_OPS(xor, xor, i) * There's two flavors of these: the arithmatic ops have both fetch and re= turn * versions, while the logical ops only have fetch versions. */ +#ifndef RISCV_AMO_USE_ZALRSC #define ATOMIC_FETCH_OP(op, asm_op, I, asm_type, c_type, prefix) \ static __always_inline \ c_type arch_atomic##prefix##_fetch_##op##_relaxed(c_type i, \ @@ -108,6 +126,38 @@ c_type arch_atomic##prefix##_fetch_##op(c_type i, atom= ic##prefix##_t *v) \ : "memory"); \ return ret; \ } +#else +#define ATOMIC_FETCH_OP(op, asm_op, I, asm_type, c_type, prefix) \ +static __always_inline \ +c_type arch_atomic##prefix##_fetch_##op##_relaxed(c_type i, \ + atomic##prefix##_t *v) \ +{ \ + register c_type ret, temp; \ + __asm__ __volatile__ ( \ + "1: lr." #asm_type " %1, %0\n" \ + " " #asm_op " %2, %1, %3\n" \ + " sc." #asm_type " %2, %2, %0\n" \ + " bnez %2, 1b\n" \ + : "+A" (v->counter), "=3D&r" (ret), "=3D&r" (temp) \ + : "r" (I) \ + : "memory"); \ + return ret; \ +} \ +static __always_inline \ +c_type arch_atomic##prefix##_fetch_##op(c_type i, atomic##prefix##_t *v) \ +{ \ + register c_type ret, temp; \ + __asm__ __volatile__ ( \ + "1: lr." #asm_type ".aqrl %1, %0\n" \ + " " #asm_op " %2, %1, %3\n" \ + " sc." #asm_type ".aqrl %2, %2, %0\n" \ + " bnez %2, 1b\n" \ + : "+A" (v->counter), "=3D&r" (ret), "=3D&r" (temp) \ + : "r" (I) \ + : "memory"); \ + return ret; \ +} +#endif =20 #define ATOMIC_OP_RETURN(op, asm_op, c_op, I, asm_type, c_type, prefix) \ static __always_inline \ diff --git a/arch/riscv/include/asm/bitops.h b/arch/riscv/include/asm/bitop= s.h index fae152ea0508..0051de1cf471 100644 --- a/arch/riscv/include/asm/bitops.h +++ b/arch/riscv/include/asm/bitops.h @@ -187,12 +187,17 @@ static __always_inline int variable_fls(unsigned int = x) =20 #if (BITS_PER_LONG =3D=3D 64) #define __AMO(op) "amo" #op ".d" +#define __LR "lr.d" +#define __SC "sc.d" #elif (BITS_PER_LONG =3D=3D 32) #define __AMO(op) "amo" #op ".w" +#define __LR "lr.w" +#define __SC "sc.w" #else #error "Unexpected BITS_PER_LONG" #endif =20 +#ifndef RISCV_AMO_USE_ZALRSC #define __test_and_op_bit_ord(op, mod, nr, addr, ord) \ ({ \ unsigned long __res, __mask; \ @@ -211,6 +216,33 @@ static __always_inline int variable_fls(unsigned int x) : "+A" (addr[BIT_WORD(nr)]) \ : "r" (mod(BIT_MASK(nr))) \ : "memory"); +#else +#define __test_and_op_bit_ord(op, mod, nr, addr, ord) \ +({ \ + unsigned long __res, __mask, __temp; \ + __mask =3D BIT_MASK(nr); \ + __asm__ __volatile__ ( \ + "1: " __LR #ord " %0, %1\n" \ + #op " %2, %0, %3\n" \ + __SC #ord " %2, %2, %1\n" \ + "bnez %2, 1b\n" \ + : "=3D&r" (__res), "+A" (addr[BIT_WORD(nr)]), "=3D&r" (__temp) \ + : "r" (mod(__mask)) \ + : "memory"); \ + ((__res & __mask) !=3D 0); \ +}) + +#define __op_bit_ord(op, mod, nr, addr, ord) \ + unsigned long __res, __temp; \ + __asm__ __volatile__ ( \ + "1: " __LR #ord " %0, %1\n" \ + #op " %2, %0, %3\n" \ + __SC #ord " %2, %2, %1\n" \ + "bnez %2, 1b\n" \ + : "=3D&r" (__res), "+A" (addr[BIT_WORD(nr)]), "=3D&r" (__temp) \ + : "r" (mod(BIT_MASK(nr))) \ + : "memory") +#endif =20 #define __test_and_op_bit(op, mod, nr, addr) \ __test_and_op_bit_ord(op, mod, nr, addr, .aqrl) @@ -354,12 +386,25 @@ static inline void arch___clear_bit_unlock( static inline bool arch_xor_unlock_is_negative_byte(unsigned long mask, volatile unsigned long *addr) { +#ifndef RISCV_AMO_USE_ZALRSC unsigned long res; __asm__ __volatile__ ( __AMO(xor) ".rl %0, %2, %1" : "=3Dr" (res), "+A" (*addr) : "r" (__NOP(mask)) : "memory"); +#else + unsigned long res, temp; + + __asm__ __volatile__ ( + "1: " __LR ".rl %0, %1\n" + "xor %2, %0, %3\n" + __SC ".rl %2, %2, %1\n" + "bnez %2, 1b\n" + : "=3D&r" (res), "+A" (*addr), "=3D&r" (temp) + : "r" (__NOP(mask)) + : "memory"); +#endif return (res & BIT(7)) !=3D 0; } =20 diff --git a/arch/riscv/include/asm/cmpxchg.h b/arch/riscv/include/asm/cmpx= chg.h index 4cadc56220fe..aba60f427060 100644 --- a/arch/riscv/include/asm/cmpxchg.h +++ b/arch/riscv/include/asm/cmpxchg.h @@ -51,6 +51,7 @@ } \ }) =20 +#ifndef RISCV_AMO_USE_ZALRSC #define __arch_xchg(sfx, prepend, append, r, p, n) \ ({ \ __asm__ __volatile__ ( \ @@ -61,6 +62,21 @@ : "r" (n) \ : "memory"); \ }) +#else +#define __arch_xchg(sfx, prepend, append, r, p, n) \ +({ \ + __typeof__(*(__ptr)) temp; \ + __asm__ __volatile__ ( \ + prepend \ + "1: lr" sfx " %0, %1\n" \ + " sc" sfx " %2, %3, %1\n" \ + " bnez %2, 1b\n" \ + append \ + : "=3D&r" (r), "+A" (*(p)), "=3D&r" (temp) \ + : "r" (n) \ + : "memory"); \ +}) +#endif =20 #define _arch_xchg(ptr, new, sc_sfx, swap_sfx, prepend, \ sc_append, swap_append) \ diff --git a/arch/riscv/include/asm/futex.h b/arch/riscv/include/asm/futex.h index fc8130f995c1..dc63065e707e 100644 --- a/arch/riscv/include/asm/futex.h +++ b/arch/riscv/include/asm/futex.h @@ -19,6 +19,7 @@ #define __disable_user_access() do { } while (0) #endif =20 +#ifndef RISCV_AMO_USE_ZALRSC #define __futex_atomic_op(insn, ret, oldval, uaddr, oparg) \ { \ __enable_user_access(); \ @@ -32,16 +33,39 @@ : "memory"); \ __disable_user_access(); \ } +#else +#define __futex_atomic_op(insn, ret, oldval, uaddr, oparg) \ +{ \ + __enable_user_access(); \ + __asm__ __volatile__ ( \ + "1: lr.w.aqrl %[ov], %[u]\n" \ + " " insn "\n" \ + " sc.w.aqrl %[t], %[t], %[u]\n" \ + " bnez %[t], 1b\n" \ + "2:\n" \ + _ASM_EXTABLE_UACCESS_ERR(1b, 2b, %[r]) \ + : [r] "+r" (ret), [ov] "=3D&r" (oldval), \ + [t] "=3D&r" (temp), [u] "+m" (*uaddr) \ + : [op] "Jr" (oparg) \ + : "memory"); \ + __disable_user_access(); \ +} +#endif =20 static inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uadd= r) { +#ifndef RISCV_AMO_USE_ZALRSC int oldval =3D 0, ret =3D 0; +#else + int oldval =3D 0, ret =3D 0, temp =3D 0; +#endif =20 if (!access_ok(uaddr, sizeof(u32))) return -EFAULT; =20 switch (op) { +#ifndef RISCV_AMO_USE_ZALRSC case FUTEX_OP_SET: __futex_atomic_op("amoswap.w.aqrl %[ov],%z[op],%[u]", ret, oldval, uaddr, oparg); @@ -62,6 +86,28 @@ arch_futex_atomic_op_inuser(int op, int oparg, int *oval= , u32 __user *uaddr) __futex_atomic_op("amoxor.w.aqrl %[ov],%z[op],%[u]", ret, oldval, uaddr, oparg); break; +#else + case FUTEX_OP_SET: + __futex_atomic_op("mv %[t], %z[op]", + ret, oldval, uaddr, oparg); + break; + case FUTEX_OP_ADD: + __futex_atomic_op("add %[t], %[ov], %z[op]", + ret, oldval, uaddr, oparg); + break; + case FUTEX_OP_OR: + __futex_atomic_op("or %[t], %[ov], %z[op]", + ret, oldval, uaddr, oparg); + break; + case FUTEX_OP_ANDN: + __futex_atomic_op("and %[t], %[ov], %z[op]", + ret, oldval, uaddr, ~oparg); + break; + case FUTEX_OP_XOR: + __futex_atomic_op("xor %[t], %[ov], %z[op]", + ret, oldval, uaddr, oparg); + break; +#endif default: ret =3D -ENOSYS; } --=20 2.25.1