From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from smtp.kernel.org (aws-us-west-2-korg-mail-alma10-1.taild15c8.ts.net [100.103.45.18]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 164DD3B52EF; Fri, 2 Oct 2026 10:22:05 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=100.103.45.18 ARC-Seal:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1790936527; cv=none; b=Nl7n/AWZ0c/NifxUb95Nl19gbr7eOtUujaX0uJkfeCcj99ZzwfoNfb3MUsY2dWXPTJdy0R0T1eazowbfM4Wgc6UTAR9/11eG1KRP0NCvcdaF4g0ROFIJ9AWcAUT3JrP//ssDeBUnUe8la1y2m7aXFZ7UswhJHSkCK0VrKO95rpI= ARC-Message-Signature:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1790936527; c=relaxed/simple; bh=1/jV/DYFh6nfJjFWVdERFwhIgob38Jou7XJO721gAz0=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=KhgHdgIFdgrKxXiBjMK983xMZjeat21hXHKn5kQJwn02x5z7rto65G2+gDyD2vVhoLDcijqrxKYNQcAM1caUa9uXCWZb1T2hK5Enmf8yS2kEqRJ6j0wUChRC6OsUqI5qJz9wM+jJpbdMyRkoWOrk7SqRA7QM3OYqAHYtS6j79dI= ARC-Authentication-Results:i=1; smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b=D07SU6Ca; arc=none smtp.client-ip=100.103.45.18 Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b="D07SU6Ca" Received: by smtp.kernel.org (Postfix) with ESMTPSA id BC9161F000FF; Fri, 2 Oct 2026 10:21:56 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=kernel.org; s=k20260515; t=1790936525; bh=2kP2SZcWPJ768aWyS0vyXzgJo6Adw6WVYJKQWTRUmM0=; h=From:To:Cc:Subject:Date:In-Reply-To:References; b=D07SU6Ca1PXHJAzaD3YWk1Avq59c2aAWl00rw3yaADF5KV9F3EX/jMy/q7S5BtYiA pTyCGZm0ux2o+JlQOK4erReGHGbfscJiKjmRLPX5J7i34Oo1r1WqNdxv1J5r2uVP97 BS2qxH+DfPxJ7vbZfw3pS9Jwb9Znmp+CYrgKBt+WugZpQ2X2WGEVMBNB33bRcv2TVW 1HnqyBTSEvPhPPZpsV5fgUeBOucRXzyiF1ei7UeRUOMaGPMmdV6AtQR0nzAGdS5W8z A+XwgpStVdt/MaeUz++hQQoAVLihFOwwVElNPCYjnysShwG+rYzTRnkZlaGoJMBNlb 8kVQXFAJOhhdA== From: Arnaldo Carvalho de Melo To: Namhyung Kim Cc: Ingo Molnar , Thomas Gleixner , James Clark , Jiri Olsa , Ian Rogers , Adrian Hunter , Clark Williams , linux-kernel@vger.kernel.org, linux-perf-users@vger.kernel.org, Arnaldo Carvalho de Melo Subject: [PATCH v8 4/9] perf mutex: Add DO_ONCE() for one-time initialization Date: Fri, 2 Oct 2026 12:21:05 +0200 Message-ID: <20261002102110.27587-5-acme@kernel.org> X-Mailer: git-send-email 2.54.0 In-Reply-To: <20261002102110.27587-1-acme@kernel.org> References: <20261002102110.27587-1-acme@kernel.org> Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: 8bit From: Arnaldo Carvalho de Melo For lazy init that more than one thread can race into, without pthread_once() so that it stays within perf's locking primitives and clang's -Wthread-safety keeps an eye on the mutexes involved. Mirrors the kernel's include/linux/once.h DO_ONCE(), dropping its static key fast path, unnecessary at these cold init paths: a per call site static bool plus a statically initialized mutex, double checked. As there, code reachable from more than one call site must go through a common helper. The lockless fast path reads ___done with __atomic_load_n(..., __ATOMIC_ACQUIRE), paired with the __atomic_store_n(..., __ATOMIC_RELEASE) store after fn(), so that its side effects are visible to threads that take the fast path; the __atomic builtins over the smp_load_acquire()/smp_store_release() variants because ThreadSanitizer understands the builtins, avoiding reports on ___done and on what fn() initialized. Assisted-by: LLM Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/mutex.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) diff --git a/tools/perf/util/mutex.h b/tools/perf/util/mutex.h index b85a80ad60386aed..ef1ab6dd8c09556f 100644 --- a/tools/perf/util/mutex.h +++ b/tools/perf/util/mutex.h @@ -95,6 +95,30 @@ struct LOCKABLE mutex { /* Statically initialized mutex, for the file scope ones. */ #define DEFINE_MUTEX(name) struct mutex name = { .lock = PTHREAD_MUTEX_INITIALIZER } +/* + * Runs fn() exactly once however many threads race to it, the rest wait + * for it to finish; per call site state, so multiple sites wanting the + * same once use a common helper, as in the kernel's DO_ONCE(). + */ +#define DO_ONCE(fn, ...) \ + ({ \ + static bool ___done; \ + static DEFINE_MUTEX(___once_lock); \ + bool ___ret = false; \ + \ + if (!__atomic_load_n(&___done, __ATOMIC_ACQUIRE)) { \ + mutex_lock(&___once_lock); \ + if (!___done) { \ + fn(__VA_ARGS__); \ + __atomic_store_n(&___done, true, \ + __ATOMIC_RELEASE); \ + ___ret = true; \ + } \ + mutex_unlock(&___once_lock); \ + } \ + ___ret; \ + }) + /* A wrapper around the condition variable implementation. */ struct cond { pthread_cond_t cond; -- 2.55.0