From nobody Thu Apr 2 19:00:21 2026 Received: from mail-wm1-f73.google.com (mail-wm1-f73.google.com [209.85.128.73]) (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 0BA9022156B for ; Mon, 16 Feb 2026 14:50:37 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=209.85.128.73 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1771253440; cv=none; b=UIZzmk86u+1XCzVNPItOS+h1lipFFSIbejy2gYesqXulh+P2OiE3HQHQUXdBhl+27cT5YxfNt69Y3r0JhGGZqJbdeb1KoomBBo4StbyLB0h6hLOFC6lvi5Vc/NA/n0xIQjnMJX1CXW1IwlpKwDFesZjfDT86G1KLHD5kMPgJFnc= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1771253440; c=relaxed/simple; bh=ZUPsEyOe5JsqQojpLzkrHOX340UlsnpEJtleUHPh+3Q=; h=Date:In-Reply-To:Mime-Version:References:Message-ID:Subject:From: To:Cc:Content-Type; b=ixAUOmZ64SiTIGoVdB52dJ8cyO+Tq2yp6J8hGY//Q2Uq6GD0hQaBA06U5nbQTuFTLdHMnIOp4qgaHgWiLsbr3FlcvHVorxt7mcnH9oRBj+xRg29SrL3taQ6buKTKHyhLrRz8vbyZ8w05DC7ySY+BnT0/mobzEfciOlCmhlqLTJo= 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=YEYGX0Ij; arc=none smtp.client-ip=209.85.128.73 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="YEYGX0Ij" Received: by mail-wm1-f73.google.com with SMTP id 5b1f17b1804b1-4837b7903f3so22497245e9.2 for ; Mon, 16 Feb 2026 06:50:37 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=20230601; t=1771253436; x=1771858236; 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=a9bx2SVNA6p6zRS/D5nNjpug9N+EIaRo9Qayx0T8s/E=; b=YEYGX0IjfVq9/h5q5GKvsDtlo4OObyQYImYyhPfecswdNacBCMIW2H8P8C54JGB27/ K+OoovnSiyV2rweQ3i+KnJCCNcKqI4CY7hCkUMh0nXtY3A030Z44BbTWZxUQWx40oWQb DvYfrUX9Z7MS3fNP1dw1RRfwGLHfs+ZLbnizs93Ye7WhkSjZP6u5kdcHfgDRc//ZnrRD cnxYgV8oJL9M70CaEPe3cjwIV6YCFWqmpC8VmULm2Na5onoARXomQOlGjfY61wzIZdZ0 HuqdWBnR2qXdA6iLw7bhvplLQHeYf+ltSVJWUfpickQnhUa5OdjqIEM6gOxVuhB377jT fDsg== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1771253436; x=1771858236; 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=a9bx2SVNA6p6zRS/D5nNjpug9N+EIaRo9Qayx0T8s/E=; b=QJl7aEnpOzqF34MYxh7gnFkC2x/msUR80t7uRBlIl5FG7fNkZNHiN7lWLEf/Xv297M SG432yV4raNE/BY6rZ0Ny02yyRynGQdqr1/Y6etqbd1da2Bu0hZqj0yzpFpss3Ss40oF SwiKgsGcbZgGIXsh/AUIBogay2nqggkJ0tRpu5UsoMky8o6c4FW35lzX1DYLN7wngpsx 4J6/k5PHrEMGjQU3dM3gVDrn7MBFzPXgVZeBfeAMVz/lIILe3hGVV3obUVobpmsS/wsz 353TCPof7bWl53FoJJtjJ+HUI18rOjcW/soqMUzO7ll4LWaH5ExfRoVKbNHyoRetmyPr 4exQ== X-Forwarded-Encrypted: i=1; AJvYcCUxFWt1juCnkCcE5u2krKaC+1qD47abe79vvDPeUJZ8mhcOxfgeLsjnwGjb8DLEDe8e/DUuergQhT4RtgE=@vger.kernel.org X-Gm-Message-State: AOJu0YzUMEL8BNUD9muaaqfufu3fOlbPFPWr8fRu/dcgIKyJjmBvSOVL 91JkinQ4JiHkrrG6ceuN18RzdoE4YI+gQ2WB8pGtxByxvAIvgdSFPu7qWBeCQZQqgPhBbjP5gbC 4kA== X-Received: from wmbfj12.prod.google.com ([2002:a05:600c:c8c:b0:480:69c2:3949]) (user=elver job=prod-delivery.src-stubby-dispatcher) by 2002:a05:600c:1f8d:b0:47e:e87b:af8 with SMTP id 5b1f17b1804b1-48373a5ba01mr192805505e9.21.1771253436108; Mon, 16 Feb 2026 06:50:36 -0800 (PST) Date: Mon, 16 Feb 2026 15:16:22 +0100 In-Reply-To: <20260216142436.2207937-2-elver@google.com> Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: Mime-Version: 1.0 References: <20260216142436.2207937-2-elver@google.com> X-Mailer: git-send-email 2.53.0.335.g19a08e0c02-goog Message-ID: <20260216142436.2207937-3-elver@google.com> Subject: [PATCH v4 1/2] 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 , Al Viro , Catalin Marinas , Nathan Chancellor , 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). 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). NOTE: The return-value-of-function-drops-qualifiers hack was first suggested by Al Viro in [1], which notes some of its limitations which make it unsuitable for a general __unqual_scalar_typeof() replacement. Notably, array types are not supported, and GCC 8.1-8.3 still fail. Why should we use it here? READ_ONCE() does not support reading whole arrays, and the GCC version problem only affects 3 minor releases of a very ancient still-supported GCC version; not only that, this arm64 READ_ONCE() version is currently only activated by LTO builds, which to-date are *only supported by Clang*! Link: https://lore.kernel.org/all/20260111182010.GH3634291@ZenIV/ [1] Signed-off-by: Marco Elver --- v4: * Use the return-value-of-function-drops-qualifiers hack to paint the bikeshed. v3: * Comment. v2: * Add __rwonce_typeof_unqual() as fallback for old compilers. --- arch/arm64/include/asm/rwonce.h | 18 ++++++++++++++---- 1 file changed, 14 insertions(+), 4 deletions(-) diff --git a/arch/arm64/include/asm/rwonce.h b/arch/arm64/include/asm/rwonc= e.h index fc0fb42b0b64..9fd24cef3376 100644 --- a/arch/arm64/include/asm/rwonce.h +++ b/arch/arm64/include/asm/rwonce.h @@ -19,6 +19,17 @@ "ldapr" #sfx "\t" #regs, \ ARM64_HAS_LDAPR) =20 +/* + * Replace this with typeof_unqual() when minimum compiler versions are + * increased to GCC 14 and Clang 19. For the time being, we need this + * workaround, which relies on function return values dropping qualifiers. + */ +#define __rwonce_typeof_unqual(x) typeof(({ \ + __diag_push() \ + __diag_ignore_all("-Wignored-qualifiers", "") \ + ((typeof(x)(*)(void))0)(); \ + __diag_pop() })) + /* * When building with LTO, there is an increased risk of the compiler * converting an address dependency headed by a READ_ONCE() invocation @@ -32,8 +43,7 @@ #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 +66,9 @@ : "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 2.53.0.335.g19a08e0c02-goog