From nobody Wed Dec 17 08:03:43 2025 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 060C330DEB1 for ; Tue, 2 Dec 2025 09:36:36 +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=1764668198; cv=none; b=XR+xQNGzI0zZvcRBjcJaqJm5BVnOAPm9jsp+qBgG+bGKmy1VpzXvW1U+PsOlQ72Q54ZjmLDBqDS0XGiUpdkdb6eY7pRfgmG/5P6xkCr+ZqbMhRqsCVYX+YpyJY3lwg3UjMG7AgAcS0sFPapD6aFlb48SYPj66M5JnEIWaeHvEjA= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1764668198; c=relaxed/simple; bh=+eDwcR/MyK6osxWUTRUN9JKU08z2QxE7z4o2fObuxeQ=; h=Date:In-Reply-To:Mime-Version:References:Message-ID:Subject:From: To:Cc:Content-Type; b=tTfz0P7k+s7/1YGokCa6dmF7V20y+ISEbe/c27LenkLY/baS8CXhY0XrLfnXqem59f1Q+Q4BMMQOwlWgWiehoSrgNvn8cfn4nXgXbozzo26ie72EUkXcrCSXfw1zYYux82/ZdHzMXKnlOmk7TUPth8suOu4NBI9rGuW1C5asNxQ= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=reject dis=none) header.from=google.com; spf=pass smtp.mailfrom=flex--vdonnefort.bounces.google.com; dkim=pass (2048-bit key) header.d=google.com header.i=@google.com header.b=FIYCThBg; 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--vdonnefort.bounces.google.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=google.com header.i=@google.com header.b="FIYCThBg" Received: by mail-wm1-f73.google.com with SMTP id 5b1f17b1804b1-477bf8c1413so32282475e9.1 for ; Tue, 02 Dec 2025 01:36:36 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=20230601; t=1764668195; x=1765272995; 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=mmnmPnoKS58rysqE29lUfzlQEDVMTKJ+Y24/6OpLVn4=; b=FIYCThBgmYkz5Hk4zCBEpV6fJO9uyFUITCnSSfOZP10b/8Wf82+deAsFIouSMHtIRL vWnMS7ozQe2GZJjXhhBF1Ig/Ee+v+DC2nMmKC2rCtUtPrdzYh3uCPjQiVUn3qer3a+qx Jvv+jcXUFTc+zlDeX7bc9bR2KY3BZ3U6m+JN9h4TQ398PUs0gilx0Za7hxmInWo+Qdfz +sotiHCxeM7I8lQJvUn+y9Edew27H3ZrqAc7fnCVGTIl+l28Cmz2jiybhlKKOQ2HDiDt yS9s74BouzfbcfTpVJGjYzOCBt9ddQ+SUZhq1FQnykCAvnk3fuiV2Kr0i7eK2+Z5uvyq 6fYw== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1764668195; x=1765272995; 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=mmnmPnoKS58rysqE29lUfzlQEDVMTKJ+Y24/6OpLVn4=; b=ogZbnL9xjhNOlZGVLfd0/3r+9FUk4GoPC0LUqtcOK0xZD44ck7XJep2FPYsabnxeoT hOyjODwSPyMf0jWxMOwkAF3bOBcgJUI+a1X8gI6egiIdgWBzgrjePcvI/yhFLK5JYR4A JX5TJpGIouvW30J99PbYnI05xa9zGOiu5Of8BvUZCMmNQjD5S+1BQCvt+1RrTJktBY7G xYCfDcL+r0RhPU2hash9qWqPJv1hN4zfizI76LVowkwhWC8uJzLXFQsQCsCofNYsERyS kq5ne6SlKiFGfC0zLK1CFSgUsnfqAUtHZDrTBcvUIcTvE1u+a7aWGua8DKpDFypqLi4t F3nQ== X-Forwarded-Encrypted: i=1; AJvYcCXUe34Xck1pPcIfCxefryiE1NWyQAh8ZqiZSrcE9AZR0BKolTqozq8wFqa0Gf2jRqhr7BU3/k4KPGAKoBY=@vger.kernel.org X-Gm-Message-State: AOJu0YzMO8Sn39zMwKJXGp7QwjenJbDDsba0vdcD1HJArYcI1s3sjltV v4RDQC9IrgQctx2HrJNCYODhGfkW/Psrpazg1CUgR1FzA+K2TrmKenDamB1HdeThlsC6pxGR5Xa D682IOhkAVkK3w5gu8Gto5Q== X-Google-Smtp-Source: AGHT+IHxpU2RjXgPE3dFyHp+bs/wQ2ZJ3c3K0tGZhcA9ODepkf14EOjrYCgHkcicrP7QgAeOjeYJEOgEjUddT/jk X-Received: from wmdn1.prod.google.com ([2002:a05:600c:2941:b0:477:103e:8e30]) (user=vdonnefort job=prod-delivery.src-stubby-dispatcher) by 2002:a05:600c:1f0f:b0:471:14af:c715 with SMTP id 5b1f17b1804b1-477c0165bb8mr406176625e9.3.1764668195451; Tue, 02 Dec 2025 01:36:35 -0800 (PST) Date: Tue, 2 Dec 2025 09:35:57 +0000 In-Reply-To: <20251202093623.2337860-1-vdonnefort@google.com> Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: Mime-Version: 1.0 References: <20251202093623.2337860-1-vdonnefort@google.com> X-Mailer: git-send-email 2.52.0.107.ga0afd4fd5b-goog Message-ID: <20251202093623.2337860-5-vdonnefort@google.com> Subject: [PATCH v9 04/30] ring-buffer: Add non-consuming read for ring-buffer remotes From: Vincent Donnefort To: rostedt@goodmis.org, mhiramat@kernel.org, mathieu.desnoyers@efficios.com, linux-trace-kernel@vger.kernel.org, maz@kernel.org, oliver.upton@linux.dev, joey.gouly@arm.com, suzuki.poulose@arm.com, yuzenghui@huawei.com Cc: kvmarm@lists.linux.dev, linux-arm-kernel@lists.infradead.org, jstultz@google.com, qperret@google.com, will@kernel.org, aneesh.kumar@kernel.org, kernel-team@android.com, linux-kernel@vger.kernel.org, Vincent Donnefort Content-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset="utf-8" Hopefully, the remote will only swap pages on the kernel instruction (via the swap_reader_page() callback). This means we know at what point the ring-buffer geometry has changed. It is therefore possible to rearrange the kernel view of that ring-buffer to allow non-consuming read. Signed-off-by: Vincent Donnefort diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 9c6c8e206e04..cb674a9fc359 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -5347,10 +5347,51 @@ static bool rb_read_remote_meta_page(struct ring_bu= ffer_per_cpu *cpu_buffer) return rb_num_of_entries(cpu_buffer); } =20 +static void rb_update_remote_head(struct ring_buffer_per_cpu *cpu_buffer) +{ + struct buffer_page *next, *orig; + int retry =3D 3; + + orig =3D next =3D cpu_buffer->head_page; + rb_inc_page(&next); + + /* Run after the writer */ + while (cpu_buffer->head_page->page->time_stamp > next->page->time_stamp) { + rb_inc_page(&next); + + rb_list_head_clear(cpu_buffer->head_page->list.prev); + rb_inc_page(&cpu_buffer->head_page); + rb_set_list_to_head(cpu_buffer->head_page->list.prev); + + if (cpu_buffer->head_page =3D=3D orig) { + if (WARN_ON_ONCE(!(--retry))) + return; + } + } + + orig =3D cpu_buffer->commit_page =3D cpu_buffer->head_page; + retry =3D 3; + + while (cpu_buffer->commit_page->page->time_stamp < next->page->time_stamp= ) { + rb_inc_page(&next); + rb_inc_page(&cpu_buffer->commit_page); + + if (cpu_buffer->commit_page =3D=3D orig) { + if (WARN_ON_ONCE(!(--retry))) + return; + } + } +} + static void rb_iter_reset(struct ring_buffer_iter *iter) { struct ring_buffer_per_cpu *cpu_buffer =3D iter->cpu_buffer; =20 + if (cpu_buffer->remote) { + rb_read_remote_meta_page(cpu_buffer); + rb_update_remote_head(cpu_buffer); + } + /* Iterator usage is expected to have record disabled */ iter->head_page =3D cpu_buffer->reader_page; iter->head =3D cpu_buffer->reader_page->read; @@ -5503,7 +5544,7 @@ rb_update_iter_read_stamp(struct ring_buffer_iter *it= er, static struct buffer_page * __rb_get_reader_page_from_remote(struct ring_buffer_per_cpu *cpu_buffer) { - struct buffer_page *new_reader, *prev_reader; + struct buffer_page *new_reader, *prev_reader, *prev_head, *new_head, *las= t; =20 if (!rb_read_remote_meta_page(cpu_buffer)) return NULL; @@ -5527,10 +5568,32 @@ __rb_get_reader_page_from_remote(struct ring_buffer= _per_cpu *cpu_buffer) =20 WARN_ON_ONCE(prev_reader =3D=3D new_reader); =20 - cpu_buffer->reader_page->page =3D new_reader->page; - cpu_buffer->reader_page->id =3D new_reader->id; - cpu_buffer->reader_page->read =3D 0; - cpu_buffer->read_stamp =3D cpu_buffer->reader_page->page->time_stamp; + prev_head =3D new_reader; /* New reader was also the previous head */ + new_head =3D prev_head; + rb_inc_page(&new_head); + last =3D prev_head; + rb_dec_page(&last); + + /* Clear the old HEAD flag */ + rb_list_head_clear(cpu_buffer->head_page->list.prev); + + prev_reader->list.next =3D prev_head->list.next; + prev_reader->list.prev =3D prev_head->list.prev; + + /* Swap prev_reader with new_reader */ + last->list.next =3D &prev_reader->list; + new_head->list.prev =3D &prev_reader->list; + + new_reader->list.prev =3D &new_reader->list; + new_reader->list.next =3D &new_head->list; + + /* Reactivate the HEAD flag */ + rb_set_list_to_head(&last->list); + + cpu_buffer->head_page =3D new_head; + cpu_buffer->reader_page =3D new_reader; + cpu_buffer->pages =3D &new_head->list; + cpu_buffer->read_stamp =3D new_reader->page->time_stamp; cpu_buffer->lost_events =3D cpu_buffer->meta_page->reader.lost_events; =20 return rb_page_size(cpu_buffer->reader_page) ? cpu_buffer->reader_page : = NULL; @@ -6114,7 +6177,7 @@ ring_buffer_read_start(struct trace_buffer *buffer, i= nt cpu, gfp_t flags) struct ring_buffer_per_cpu *cpu_buffer; struct ring_buffer_iter *iter; =20 - if (!cpumask_test_cpu(cpu, buffer->cpumask) || buffer->remote) + if (!cpumask_test_cpu(cpu, buffer->cpumask)) return NULL; =20 iter =3D kzalloc(sizeof(*iter), flags); --=20 2.52.0.107.ga0afd4fd5b-goog