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 5F61DC5518F for ; Tue, 4 Aug 2026 17:06:41 +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=9XAN2iNoVkyTD9lmxopZurAC5iGPnQ4x7OILOQSA2BM=; b=SIp667mRwCQ7VW sg1CYIPG88fImxgRV8+bt44O4EQ/8RCW9X73e6iecknD39oMANKP3J/32QBqNw1t/zZWMXP+xDrXh MIuaWL8iIpugzasozjpjDP+JTt6Xy7D02CPmD5vsnj5PrqaKi3SwsUOK5p8dy1I1uxIoAsimSC0MO JPdlCj27Xt+sIYZmpUmKnKKzJ/oNcVRwi33On4Cl7scUpKMta7EsK3+hA45s6Pa3xXlz98ildEz0U d71L+oJb4i1Yu1OBXI/Fie4p6/WWV9lMiYgKmcHUH8AKf7Yxe8pTPiXByqKt0YJT4YQPhCXCjaCs+ GaxYkgRhqZ9LWhifyV0w==; Received: from localhost ([::1] helo=bombadil.infradead.org) by bombadil.infradead.org with esmtp (Exim 4.99.1 #2 (Red Hat Linux)) id 1wrIb0-00000002QoK-0Z06; Tue, 04 Aug 2026 17:06:30 +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 1wrIav-00000002QiE-47Lh for linux-arm-kernel@lists.infradead.org; Tue, 04 Aug 2026 17:06:29 +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 6C7C91684; Tue, 4 Aug 2026 10:06:20 -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 3255E3F632; Tue, 4 Aug 2026 10:06:19 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=simple/simple; d=arm.com; s=foss; t=1785863184; bh=dT2LShAFYi+TzXy+o7lT54zkHpATAsSwWxj310ErEGU=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=DCCt0LsQ4aRQvWVapU+NS18pM+Ho7eqdW0BwGpSEySNwOOhX7Erfl4LyasvKJ76K+ bwT6txqswOL1ly2lq4MJkeq6hCa4xG/gc5JuCmTep/Pwi6vpkN47ijwP5f4xEqaZB+ DxLkhJ4a5VRZjTIbHZL2SlICnZi9hADnuasx2Fgs= From: Mark Rutland To: linux-arm-kernel@lists.infradead.org Subject: [PATCH v2 16/20] arm64: percpu: Implement preemptible return RMW ops Date: Tue, 4 Aug 2026 18:04:59 +0100 Message-Id: <20260804170503.3513916-17-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_100626_187792_4718D12D X-CRM114-Status: UNSURE ( 9.86 ) X-CRM114-Notice: Please train this message. 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 return a value. Test case: | u64 outline_this_cpu_add_return_u64(u64 __percpu *p, u64 v) | { | return this_cpu_add_return(*p, v); | } Generated code before this patch (v7.2-rc4): | : | paciasp | stp x29, x30, [sp, #-32]! | mrs x3, sp_el0 | mov x29, sp | ldr w2, [x3, #8] | add w2, w2, #0x1 | str w2, [x3, #8] | mov x2, x0 | mrs x4, tpidr_el1 | add x2, x2, x4 | 1: ldxr x0, [x2] | add x0, x0, x1 | stxr w5, x0, [x2] | cbnz w5, 1b | ldr x1, [x3, #8] | sub x1, x1, #0x1 | str w1, [x3, #8] | cbz x1, 2f | ldr x1, [x3, #8] | cbnz x1, 3f | 2: str x0, [sp, #24] | bl 0 | ldr x0, [sp, #24] | 3: ldp x29, x30, [sp], #32 | autiasp | ret Generated code after this patch: | : | mrs x3, sp_el0 | mov w5, #0x10a0 | strh w5, [x3, #20] | mrs x5, tpidr_el1 | add x4, x0, x5 | 1: ldxr x2, [x4] | add x2, x2, x1 | stxr w6, x2, [x4] | cbnz w6, 1b | strh wzr, [x3, #20] | mov x0, x2 | 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 | 36 ++++++++++++++++++++++----------- 1 file changed, 24 insertions(+), 12 deletions(-) diff --git a/arch/arm64/include/asm/percpu.h b/arch/arm64/include/asm/percpu.h index 505926363d754..8e0862704095e 100644 --- a/arch/arm64/include/asm/percpu.h +++ b/arch/arm64/include/asm/percpu.h @@ -201,24 +201,36 @@ __percpu_##name##_case_##sz(void __percpu *pcp, unsigned long val) \ #define __PERCPU_RET_OP_CASE(w, sfx, name, sz, op_llsc, op_lse) \ static inline u##sz \ -__percpu_##name##_return_case_##sz(void *ptr, unsigned long val) \ +__percpu_##name##_return_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 ret; \ \ - 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 "[ret], %[ptr]\n" \ + "1: ldxr" #sfx "\t%" #w "[ret], [%[addr]]\n" \ #op_llsc "\t%" #w "[ret], %" #w "[ret], %" #w "[val]\n" \ - " stxr" #sfx "\t%w[loop], %" #w "[ret], %[ptr]\n" \ + " stxr" #sfx "\t%w[loop], %" #w "[ret], [%[addr]]\n" \ " cbnz %w[loop], 1b", \ /* LSE atomics */ \ - #op_lse "\t%" #w "[val], %" #w "[ret], %[ptr]\n" \ + #op_lse "\t%" #w "[val], %" #w "[ret], [%[addr]]\n" \ #op_llsc "\t%" #w "[ret], %" #w "[ret], %" #w "[val]\n" \ __nops(2)) \ - : [loop] "=&r" (loop), [ret] "=&r" (ret), \ - [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), \ + [ret] "=&r" (ret) \ + : [pcp] "r" (pcp), \ + [val] "r" ((u##sz)(val)) \ + : "memory" \ + ); \ \ return ret; \ } @@ -322,13 +334,13 @@ PERCPU_RET_OP(add, add, ldadd) _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) + _pcp_wrap_return(__percpu_add_return_case_8, pcp, val) #define this_cpu_add_return_2(pcp, val) \ - _pcp_protect_return(__percpu_add_return_case_16, pcp, val) + _pcp_wrap_return(__percpu_add_return_case_16, pcp, val) #define this_cpu_add_return_4(pcp, val) \ - _pcp_protect_return(__percpu_add_return_case_32, pcp, val) + _pcp_wrap_return(__percpu_add_return_case_32, pcp, val) #define this_cpu_add_return_8(pcp, val) \ - _pcp_protect_return(__percpu_add_return_case_64, pcp, val) + _pcp_wrap_return(__percpu_add_return_case_64, pcp, val) #define this_cpu_and_1(pcp, val) \ _pcp_wrap(__percpu_andnot_case_8, pcp, ~(u8)(val)) -- 2.30.2