From nobody Mon Feb 9 16:52:36 2026 Received: from mail-wm1-f74.google.com (mail-wm1-f74.google.com [209.85.128.74]) (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 E4D0F2FD68A for ; Fri, 30 Jan 2026 13:30:11 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=209.85.128.74 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1769779813; cv=none; b=hGTNoMMaLnoi8VUGz64HSgqB2MCfNCH9kFYG2Zmnj5YR19eBjsSTC8Hzs+at4+PfxtGojMuOOnkDelDKZhu5p3ofe+G3uKqaM2o35YbcVKZF/FfjsWROXguMLbkGzf6aVhKyhnM13rvBg2vem3qz1QmKjKRTUzi2wAursZfadps= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1769779813; c=relaxed/simple; bh=N+0RvBUJ08uz7gY4C8XhNnF6MHXEg5OROSx72CVegc8=; h=Date:In-Reply-To:Mime-Version:References:Message-ID:Subject:From: To:Cc:Content-Type; b=Y5x0Kz6PfkIaSVHjIVhR4wiiaee2sGUQk2yQmgs6JNopUHQN/BfkVfw7h0iZvl234tsMgqrx24eghc148Bi+/UQCI6x2Ft1tWnjDmeXLAk9sysfMF703C/Gm3GSa8nqwnYG+u3chCkRIXDZIVEEqTWNw9o0SLLdQTu+tv9pSUOo= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=reject dis=none) header.from=google.com; spf=pass smtp.mailfrom=flex--elver.bounces.google.com; dkim=pass (2048-bit key) header.d=google.com header.i=@google.com header.b=CrWts64V; arc=none smtp.client-ip=209.85.128.74 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=reject dis=none) header.from=google.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=flex--elver.bounces.google.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=google.com header.i=@google.com header.b="CrWts64V" Received: by mail-wm1-f74.google.com with SMTP id 5b1f17b1804b1-4806fce5ab1so12721475e9.2 for ; Fri, 30 Jan 2026 05:30:11 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=20230601; t=1769779810; x=1770384610; darn=vger.kernel.org; h=cc:to:from:subject:message-id:references:mime-version:in-reply-to :date:from:to:cc:subject:date:message-id:reply-to; bh=scSVMH9or2TMfZesMIFkbkxALtorvxefZYfnvMnEqKA=; b=CrWts64VZJgm0kzxO2nxJv9/1VtuOxgxvZ4808HOro7Fy4o8qGcs1kDkMkkgU7gAkT AxCjj1QMjnMtIFSYSYSs44Woqfk7YSgVEzYa2dPTh8NlJTOeas6UeeWZia1mPRLIW0aX Itj/UG9twZj7mdj4xUjWB7iPAmzHH4NYt47aXgpMREQKmEYKGqKhF8wh7BNDLJhIwA4+ Xb9rNzf9D4yqLyLX88LWKGqZwdd+JoGfpKAxcPauuPAB9HJvM7CHofPBALDMtrzxupXG ZYkTpwgU1YgNi5HNOHos/Bf4FOOIzKT90t7RKvgKCnQZXzJKRJuaovoXpqVxGqOTncVF 8iEA== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1769779810; x=1770384610; h=cc:to:from:subject:message-id:references:mime-version:in-reply-to :date:x-gm-message-state:from:to:cc:subject:date:message-id:reply-to; bh=scSVMH9or2TMfZesMIFkbkxALtorvxefZYfnvMnEqKA=; b=EqoIt2F97rxOT3Cc96tDLSJvyZGqbx0G8X+VWJOCCsuDNxa17poOjc1cMFgnernTMU F0g2rg4Ep/IxavA5Gl8DCkJvUsI+fnAq59Pw8kV41kNW6Oiu0/yu6Ja4Th5bIWapPAC8 8HE8S1TZluC0MeLx0qhZQ8UDY1vs0tyNOCkYP3z1l5uK9Rv0uf0NSVZEHCDHPxr/nly/ 1DRdSR1a1HZY+FsXH6CoPMW0aZI5lADx8tmJiLNpwGsJZg1tqsOD+hCSMBdCaFRytwCP IqWAvYwCaR4nITFFyb8Wrhk+YMZjRDabA6rLf83Kzi/68frt/QBMksA5yQoq7IuWDx+G 416A== X-Forwarded-Encrypted: i=1; AJvYcCUKS0KGLobJCn0U9DAfoWzeVS/gKLR33n/PenvgQYQaj4489yg3Q+3I+qpuwUKGRcbbxs792GUqa8l9V2c=@vger.kernel.org X-Gm-Message-State: AOJu0Yzl62yFWYnR9ZD1SKjLfYKTs/KhIiy49ZLcGTVAykfcpo84tAHG EVnAYBdYoenBW5n4fJJdkmykbT8A/SaQe6+4cCcu6/pA1eR32sT2XVC7CGR5YKmS7Px+Xq0ecF7 YOQ== X-Received: from wmpx5.prod.google.com ([2002:a05:600c:1885:b0:480:4a03:7b7f]) (user=elver job=prod-delivery.src-stubby-dispatcher) by 2002:a05:600c:4507:b0:475:dcbb:7903 with SMTP id 5b1f17b1804b1-482db45ea8emr33261705e9.9.1769779810315; Fri, 30 Jan 2026 05:30:10 -0800 (PST) Date: Fri, 30 Jan 2026 14:28:25 +0100 In-Reply-To: <20260130132951.2714396-1-elver@google.com> Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: Mime-Version: 1.0 References: <20260130132951.2714396-1-elver@google.com> X-Mailer: git-send-email 2.53.0.rc1.225.gd81095ad13-goog Message-ID: <20260130132951.2714396-3-elver@google.com> Subject: [PATCH v3 2/3] arm64: Optimize __READ_ONCE() with CONFIG_LTO=y From: Marco Elver To: elver@google.com, Peter Zijlstra , Will Deacon Cc: Ingo Molnar , Thomas Gleixner , Boqun Feng , Waiman Long , Bart Van Assche , llvm@lists.linux.dev, David Laight , Catalin Marinas , Arnd Bergmann , linux-arm-kernel@lists.infradead.org, linux-kernel@vger.kernel.org Content-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset="utf-8" Rework arm64 LTO __READ_ONCE() to improve code generation as follows: 1. Replace _Generic-based __unqual_scalar_typeof() with more complete __rwonce_typeof_unqual(). This strips qualifiers from all types, not just integer types, which is required to be able to assign (must be non-const) to __u.__val in the non-atomic case (required for #2). Once our minimum compiler versions are bumped, this just becomes TYPEOF_UNQUAL() (or typeof_unqual() should we decide to adopt C23 naming). Sadly the fallback version of __rwonce_typeof_unqual() cannot be used as a general TYPEOF_UNQUAL() fallback (see code comments). One subtle point here is that non-integer types of __val could be const or volatile within the union with the old __unqual_scalar_typeof(), if the passed variable is const or volatile. This would then result in a forced load from the stack if __u.__val is volatile; in the case of const, it does look odd if the underlying storage changes, but the compiler is told said member is "const" -- it smells like UB. 2. Eliminate the atomic flag and ternary conditional expression. Move the fallback volatile load into the default case of the switch, ensuring __u is unconditionally initialized across all paths. The statement expression now unconditionally returns __u.__val. This refactoring appears to help the compiler improve (or fix) code generation. With a defconfig + LTO + debug options builds, we observe different codegen for the following functions: btrfs_reclaim_sweep (708 -> 1032 bytes) btrfs_sinfo_bg_reclaim_threshold_store (200 -> 204 bytes) check_mem_access (3652 -> 3692 bytes) [inlined bpf_map_is_rdonly] console_flush_all (1268 -> 1264 bytes) console_lock_spinning_disable_and_check (180 -> 176 bytes) igb_add_filter (640 -> 636 bytes) igb_config_tx_modes (2404 -> 2400 bytes) kvm_vcpu_on_spin (480 -> 476 bytes) map_freeze (376 -> 380 bytes) netlink_bind (1664 -> 1656 bytes) nmi_cpu_backtrace (404 -> 400 bytes) set_rps_cpu (516 -> 520 bytes) swap_cluster_readahead (944 -> 932 bytes) tcp_accecn_third_ack (328 -> 336 bytes) tcp_create_openreq_child (1764 -> 1772 bytes) tcp_data_queue (5784 -> 5892 bytes) tcp_ecn_rcv_synack (620 -> 628 bytes) xen_manage_runstate_time (944 -> 896 bytes) xen_steal_clock (340 -> 296 bytes) Increase of some functions are due to more aggressive inlining due to better codegen (in this build, e.g. bpf_map_is_rdonly is no longer present due to being inlined completely). Signed-off-by: Marco Elver Reviewed-by: David Laight @gmail.com --- v3: * Comment. v2: * Add __rwonce_typeof_unqual() as fallback for old compilers. --- arch/arm64/include/asm/rwonce.h | 21 +++++++++++++++++---- 1 file changed, 17 insertions(+), 4 deletions(-) diff --git a/arch/arm64/include/asm/rwonce.h b/arch/arm64/include/asm/rwonc= e.h index fc0fb42b0b64..42c9e8429274 100644 --- a/arch/arm64/include/asm/rwonce.h +++ b/arch/arm64/include/asm/rwonce.h @@ -19,6 +19,20 @@ "ldapr" #sfx "\t" #regs, \ ARM64_HAS_LDAPR) =20 +#ifdef USE_TYPEOF_UNQUAL +#define __rwonce_typeof_unqual(x) TYPEOF_UNQUAL(x) +#else +/* + * Fallback for older compilers (Clang < 19). + * + * Uses the fact that, for all supported Clang versions, 'auto' correctly = drops + * qualifiers. Unlike typeof_unqual(), the type must be completely defined= , i.e. + * no forward-declared struct pointer dereferences. The array-to-pointer = decay + * case does not matter for usage in READ_ONCE() either. + */ +#define __rwonce_typeof_unqual(x) typeof(({ auto ____t =3D (x); ____t; })) +#endif + /* * When building with LTO, there is an increased risk of the compiler * converting an address dependency headed by a READ_ONCE() invocation @@ -32,8 +46,7 @@ #define __READ_ONCE(x) \ ({ \ typeof(&(x)) __x =3D &(x); \ - int atomic =3D 1; \ - union { __unqual_scalar_typeof(*__x) __val; char __c[1]; } __u; \ + union { __rwonce_typeof_unqual(*__x) __val; char __c[1]; } __u; \ switch (sizeof(x)) { \ case 1: \ asm volatile(__LOAD_RCPC(b, %w0, %1) \ @@ -56,9 +69,9 @@ : "Q" (*__x) : "memory"); \ break; \ default: \ - atomic =3D 0; \ + __u.__val =3D *(volatile typeof(*__x) *)__x; \ } \ - atomic ? (typeof(*__x))__u.__val : (*(volatile typeof(*__x) *)__x);\ + __u.__val; \ }) =20 #endif /* !BUILD_VDSO */ --=20 2.53.0.rc1.225.gd81095ad13-goog