From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from bombadil.infradead.org (bombadil.infradead.org [198.137.202.133]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.lore.kernel.org (Postfix) with ESMTPS id 2445EC55184 for ; Tue, 4 Aug 2026 17:06:35 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; q=dns/txt; c=relaxed/relaxed; d=lists.infradead.org; s=bombadil.20210309; h=Sender:Cc:List-Subscribe: List-Help:List-Post:List-Archive:List-Unsubscribe:List-Id: Content-Transfer-Encoding:MIME-Version:References:In-Reply-To:Message-Id:Date :Subject:To:From:Reply-To:Content-Type:Content-ID:Content-Description: Resent-Date:Resent-From:Resent-Sender:Resent-To:Resent-Cc:Resent-Message-ID: List-Owner; bh=Qbp8l/2tSvToZc1+r6ipKGDHRbDUhaArC2dVdoXVdMY=; b=q31Jmco1hgnHfj MwCXi4B0raoXCRCHjBKcc0NpR+8r7ZK9UOHlp0UG1Ym6E3K0yLKZw5r0OZ/DfiJhyW5JHQHPTQX7q keAe6c44xdJ3e6TQRBDqannJROfJ8l/G7C5syO6urRaadSR5unWRgZfInrGhS0xSM+Ow/309pPmOO quqPOVnX223ZnraG0kjGTHNBBhtvIX73pDONOc3sXef9jgcD6bGeB/scrujN7JnwbWibiGLvgAg6g K77/61W6w2zzZa0vyE3JFHw4SYusQBZ78cuFc+bX1zPceA300l9728XgHVmPUBkFpzpPDOp6CTKCg rhGXTvBMlR2L9HC9Vlqg==; Received: from localhost ([::1] helo=bombadil.infradead.org) by bombadil.infradead.org with esmtp (Exim 4.99.1 #2 (Red Hat Linux)) id 1wrIat-00000002Qee-2RR9; Tue, 04 Aug 2026 17:06:23 +0000 Received: from foss.arm.com ([217.140.110.172]) by bombadil.infradead.org with esmtp (Exim 4.99.1 #2 (Red Hat Linux)) id 1wrIaq-00000002QaU-3E0x for linux-arm-kernel@lists.infradead.org; Tue, 04 Aug 2026 17:06:21 +0000 Received: from usa-sjc-imap-foss1.foss.arm.com (unknown [10.121.207.14]) by usa-sjc-mx-foss1.foss.arm.com (Postfix) with ESMTP id B84A9165C; Tue, 4 Aug 2026 10:06:15 -0700 (PDT) Received: from lakrids.cambridge.arm.com (usa-sjc-imap-foss1.foss.arm.com [10.121.207.14]) by usa-sjc-imap-foss1.foss.arm.com (Postfix) with ESMTPA id A21923F632; Tue, 4 Aug 2026 10:06:15 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=simple/simple; d=arm.com; s=foss; t=1785863179; bh=SeiVEo1xT8j9kMtAH9m6doXyPF9bcq7jLl9HLRgB+C8=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=kOOlf8zNqPdTlheksjlrN0XL0BM6fYQrw8IupkVs8zegLeLWJnWZczz6L5+fAKcuA PIMBVp6RgC7csIMp5g3QEqHKea9K7yB7az0DauSpMQ1naTw/yi7hzqwf/RYCe8Bua1 G8lIaRvuPwD3gi/JEcZd8ItPx26IhgKABy0SKgLU= From: Mark Rutland To: linux-arm-kernel@lists.infradead.org Subject: [PATCH v2 15/20] arm64: percpu: Implement preemptible void RMW ops Date: Tue, 4 Aug 2026 18:04:58 +0100 Message-Id: <20260804170503.3513916-16-mark.rutland@arm.com> X-Mailer: git-send-email 2.30.2 In-Reply-To: <20260804170503.3513916-1-mark.rutland@arm.com> References: <20260804170503.3513916-1-mark.rutland@arm.com> MIME-Version: 1.0 Content-Transfer-Encoding: 8bit X-CRM114-Version: 20100106-BlameMichelson ( TRE 0.9.0 (BSD) ) MR-646709E3 X-CRM114-CacheID: sfid-20260804_100620_888826_F93277E2 X-CRM114-Status: GOOD ( 10.51 ) X-BeenThere: linux-arm-kernel@lists.infradead.org X-Mailman-Version: 2.1.34 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: mark.rutland@arm.com, vladimir.murzin@arm.com, ryan.roberts@arm.com, peterz@infradead.org, catalin.marinas@arm.com, david.laight.linux@gmail.com, stable@vger.kernel.org, ruanjinjie@huawei.com, james.morse@arm.com, yang@os.amperecomputing.com, cl@gentwo.org, maz@kernel.org, david@kernel.org, ljs@kernel.org, will@kernel.org, ardb@kernel.org Sender: "linux-arm-kernel" Errors-To: linux-arm-kernel-bounces+linux-arm-kernel=archiver.kernel.org@lists.infradead.org Use the PCPU GPR infrastructure to implement all of the RMW ops which do not return a value. Test case: | void outline_this_cpu_add_u64(u64 __percpu *p, u64 v) | { | this_cpu_add(*p, v); | } Generated code before this patch (v7.2-rc4): | : | paciasp | stp x29, x30, [sp, #-16]! | mrs x2, sp_el0 | mov x29, sp | ldr w3, [x2, #8] | add w3, w3, #0x1 | str w3, [x2, #8] | mrs x3, tpidr_el1 | add x0, x0, x3 | 1: ldxr x5, [x0] | add x5, x5, x1 | stxr w4, x5, [x0] | cbnz w4, 1b | ldr x0, [x2, #8] | sub x0, x0, #0x1 | str w0, [x2, #8] | cbz x0, 2f | ldr x0, [x2, #8] | cbnz x0, 3f | 2: bl preempt_schedule_notrace | 3: ldp x29, x30, [sp], #16 | autiasp | ret Generated code after this patch: | : | mrs x2, sp_el0 | mov w4, #0xc80 | strh w4, [x2, #20] | mrs x4, tpidr_el1 | add x3, x0, x4 | 1: ldxr x6, [x3] | add x6, x6, x1 | stxr w5, x6, [x3] | cbnz w5, 1b | strh wzr, [x2, #20] | ret Signed-off-by: Mark Rutland Cc: Ada Couprie Diaz Cc: Ard Biesheuvel Cc: Catalin Marinas Cc: James Morse Cc: Jinjie Ruan Cc: Marc Zyngier Cc: Peter Zijlstra Cc: Vladimir Murzin Cc: Will Deacon Cc: Yang Shi --- arch/arm64/include/asm/percpu.h | 52 ++++++++++++++++++++------------- 1 file changed, 32 insertions(+), 20 deletions(-) diff --git a/arch/arm64/include/asm/percpu.h b/arch/arm64/include/asm/percpu.h index a094c137d797f..505926363d754 100644 --- a/arch/arm64/include/asm/percpu.h +++ b/arch/arm64/include/asm/percpu.h @@ -168,23 +168,35 @@ static inline void __percpu_write_##sz(void __percpu *pcp, u##sz val) \ #define __PERCPU_OP_CASE(w, sfx, name, sz, op_llsc, op_lse) \ static inline void \ -__percpu_##name##_case_##sz(void *ptr, unsigned long val) \ +__percpu_##name##_case_##sz(void __percpu *pcp, unsigned long val) \ { \ + u16 *gprs = ¤t_thread_info()->pcpu_gprs; \ + unsigned long addr; \ + unsigned long off; \ unsigned int loop; \ u##sz tmp; \ \ - asm volatile (ARM64_LSE_ATOMIC_INSN( \ + asm volatile ( \ + __PCPU_GPRS_BEGIN("%[gprs]", "%[pcp]", "%[off]", "%[addr]") \ + ARM64_LSE_ATOMIC_INSN( \ /* LL/SC */ \ - "1: ldxr" #sfx "\t%" #w "[tmp], %[ptr]\n" \ + "1: ldxr" #sfx "\t%" #w "[tmp], [%[addr]]\n" \ #op_llsc "\t%" #w "[tmp], %" #w "[tmp], %" #w "[val]\n" \ - " stxr" #sfx "\t%w[loop], %" #w "[tmp], %[ptr]\n" \ + " stxr" #sfx "\t%w[loop], %" #w "[tmp], [%[addr]]\n" \ " cbnz %w[loop], 1b", \ /* LSE atomics */ \ - #op_lse "\t%" #w "[val], %" #w "[tmp], %[ptr]\n" \ + #op_lse "\t%" #w "[val], %" #w "[tmp], [%[addr]]\n" \ __nops(3)) \ - : [loop] "=&r" (loop), [tmp] "=&r" (tmp), \ - [ptr] "+Q"(*(u##sz *)ptr) \ - : [val] "r" ((u##sz)(val))); \ + __PCPU_GPRS_END("%[gprs]") \ + : [gprs] "=Qo" (*gprs), \ + [addr] "=&r" (addr), \ + [off] "=&r" (off), \ + [loop] "=&r" (loop), \ + [tmp] "=&r" (tmp) \ + : [pcp] "r" (pcp), \ + [val] "r" ((u##sz)(val)) \ + : "memory" \ + ); \ } #define __PERCPU_RET_OP_CASE(w, sfx, name, sz, op_llsc, op_lse) \ @@ -301,13 +313,13 @@ PERCPU_RET_OP(add, add, ldadd) _pcp_wrap(__percpu_write_64, pcp, (unsigned long)(val)) #define this_cpu_add_1(pcp, val) \ - _pcp_protect(__percpu_add_case_8, pcp, val) + _pcp_wrap(__percpu_add_case_8, pcp, val) #define this_cpu_add_2(pcp, val) \ - _pcp_protect(__percpu_add_case_16, pcp, val) + _pcp_wrap(__percpu_add_case_16, pcp, val) #define this_cpu_add_4(pcp, val) \ - _pcp_protect(__percpu_add_case_32, pcp, val) + _pcp_wrap(__percpu_add_case_32, pcp, val) #define this_cpu_add_8(pcp, val) \ - _pcp_protect(__percpu_add_case_64, pcp, val) + _pcp_wrap(__percpu_add_case_64, pcp, val) #define this_cpu_add_return_1(pcp, val) \ _pcp_protect_return(__percpu_add_return_case_8, pcp, val) @@ -319,22 +331,22 @@ PERCPU_RET_OP(add, add, ldadd) _pcp_protect_return(__percpu_add_return_case_64, pcp, val) #define this_cpu_and_1(pcp, val) \ - _pcp_protect(__percpu_andnot_case_8, pcp, ~(u8)(val)) + _pcp_wrap(__percpu_andnot_case_8, pcp, ~(u8)(val)) #define this_cpu_and_2(pcp, val) \ - _pcp_protect(__percpu_andnot_case_16, pcp, ~(u16)(val)) + _pcp_wrap(__percpu_andnot_case_16, pcp, ~(u16)(val)) #define this_cpu_and_4(pcp, val) \ - _pcp_protect(__percpu_andnot_case_32, pcp, ~(u32)(val)) + _pcp_wrap(__percpu_andnot_case_32, pcp, ~(u32)(val)) #define this_cpu_and_8(pcp, val) \ - _pcp_protect(__percpu_andnot_case_64, pcp, ~(u64)(val)) + _pcp_wrap(__percpu_andnot_case_64, pcp, ~(u64)(val)) #define this_cpu_or_1(pcp, val) \ - _pcp_protect(__percpu_or_case_8, pcp, val) + _pcp_wrap(__percpu_or_case_8, pcp, val) #define this_cpu_or_2(pcp, val) \ - _pcp_protect(__percpu_or_case_16, pcp, val) + _pcp_wrap(__percpu_or_case_16, pcp, val) #define this_cpu_or_4(pcp, val) \ - _pcp_protect(__percpu_or_case_32, pcp, val) + _pcp_wrap(__percpu_or_case_32, pcp, val) #define this_cpu_or_8(pcp, val) \ - _pcp_protect(__percpu_or_case_64, pcp, val) + _pcp_wrap(__percpu_or_case_64, pcp, val) #define this_cpu_xchg_1(pcp, val) \ _pcp_protect_return(xchg_relaxed, pcp, val) -- 2.30.2