From nobody Thu Apr 2 17:22:47 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 12C3A3E8C63 for ; Mon, 9 Mar 2026 16:26:05 +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=1773073568; cv=none; b=TSwBn2uWDnKiGWz7JTCTyGH50YDOGS123b5xH8xc+/Xi24AB1ATRIZxmFOvQuJBdARTKcG9qMDWKy74DZGhBpdAkI0t+ogDojnIzlL1AKqO75cVVwT/j1q84TkvQi91tC7qH0jrD+K3zMkrcD8vPqZr3n3J0NlLhtLtjGTkuFDE= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1773073568; c=relaxed/simple; bh=p5SQvu/UVANqQL8BXgDJUXlqRTupygiIt9VwpYvywMM=; h=Date:In-Reply-To:Mime-Version:References:Message-ID:Subject:From: To:Cc:Content-Type; b=sregzHmWpADrlmbVWxXEaWLOjXA7fLC2WGM/uid0DQulC0HYw/8qkqc9X7WjmUNSGYUlszw0tnxEclocqiYexznhMN8ROCzaJ2/AO7aaliEHPx6uSJpoIaUhdPF+7M8ExIodUGbZXGG1PsM92sj+quoTTDFoeCMUU/ZbqwAc5hA= 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=h/LK2X2l; 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="h/LK2X2l" Received: by mail-wm1-f73.google.com with SMTP id 5b1f17b1804b1-485390246c8so15438805e9.0 for ; Mon, 09 Mar 2026 09:26:05 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=20230601; t=1773073564; x=1773678364; 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=v7sVpz3MVsXj7CM/t7DtIsR+dSxsITBD3+AtJrGnMJ8=; b=h/LK2X2leQid4+UGp9K5OIuWUc3wfn+ohS4aKVIuKFi3qGY+yVi6CdicEu40/uXube dMtGR+YM8Jqa/YDri2pUonyLha8Gk3moQ53damFYR0tN9PEzq/DToSt3nJAweWmPuuPk pfLDGh7rKy8far8/vdyHtkRpAWfqXivtQzpeAm52IpfAsV1u++51szpWudglLh+lMFEf c9xqWMk1Fb/WAiSq8oZkJlyWVOn5iP2+eMxuNUyBm4QGc+vYfjL1no2PDgflqNRkDqVH 95Uj1GZ9ABnkccq8W5mr8HH1uXUFYrkMKGpBsQqXjuM7gG3U4nvSHjpPMXvKOmF76mwU sdSw== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1773073564; x=1773678364; 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=v7sVpz3MVsXj7CM/t7DtIsR+dSxsITBD3+AtJrGnMJ8=; b=Ye1hAwnN/Tk+ocLGEYET1TcPVdLMvR7u+J8VXkwhcVD/GpghNYmp/F19zDYTjtavJF 7tScmXiwC1HdARIqVfdVgMOxSpNxzzuOrQ72sKgaqYcG9yWkB6GvBGuftIfgMIn8oHoU ezdY/1J0F9+qv5TpVuJiklbKCmd3ek/fTQ24UR7JZbmPWTSZ2FBiN/dUw+AjMMIEvOWK kZW7YZBMnAb3whZZQtcd1mrpygZxVrVuhtTr3DkxZQEAOTGoGJVEFcgQP+PwoSDwG7A4 ZJeki9Y9d0u9QfOofnqNKOhMOHpNRsHUKmjHnpL/uyTwcSI6e0M43RW3EjzD3xvCcwgs F52Q== X-Forwarded-Encrypted: i=1; AJvYcCUG/VDcdJMDcaAiGxd85NkscLpwk5+dANEr46L6JuKnmkw5819e8A6yA+/hB/DY5HFzsCff20Ire2FodjQ=@vger.kernel.org X-Gm-Message-State: AOJu0YwTCa9sPCCXnZ4XprOBNcAH8SHR1Eh1OmKphD6yrrOW252HQV1B W/h6v8ScMp2uFX1ViX8DC558RQH7e7HC0S6xWNPJq/eMCxqRXM4fZLXRm+gt7QLG0R0ySXlWugF PQLc/KRJp2fDdNTO4hYYxzg== X-Received: from wmj24.prod.google.com ([2002:a05:600c:258:b0:485:3890:399c]) (user=vdonnefort job=prod-delivery.src-stubby-dispatcher) by 2002:a05:600c:3b0c:b0:485:17a7:b9c7 with SMTP id 5b1f17b1804b1-48526923b61mr193565395e9.10.1773073564338; Mon, 09 Mar 2026 09:26:04 -0700 (PDT) Date: Mon, 9 Mar 2026 16:24:50 +0000 In-Reply-To: <20260309162516.2623589-1-vdonnefort@google.com> Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: Mime-Version: 1.0 References: <20260309162516.2623589-1-vdonnefort@google.com> X-Mailer: git-send-email 2.53.0.473.g4a7958ca14-goog Message-ID: <20260309162516.2623589-5-vdonnefort@google.com> Subject: [PATCH v14 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. Reviewed-by: Steven Rostedt (Google) Signed-off-by: Vincent Donnefort diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 88218377fa29..fb39dd43e00b 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -5388,10 +5388,51 @@ 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; @@ -5544,7 +5585,7 @@ 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; @@ -5568,10 +5609,32 @@ __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; @@ -6155,7 +6218,7 @@ 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_obj(*iter, flags); --=20 2.53.0.473.g4a7958ca14-goog