From patchwork Fri Mar 17 14:33:09 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Vincent Donnefort X-Patchwork-Id: 71303 Return-Path: Delivered-To: ouuuleilei@gmail.com Received: by 2002:a5d:604a:0:0:0:0:0 with SMTP id j10csp385350wrt; Fri, 17 Mar 2023 07:57:19 -0700 (PDT) X-Google-Smtp-Source: AK7set8LPP9euTk+TMLYojJbUI7T8H7+pVKZuOoKDgNASe6nJWWzSKcw6y7a7oIkwXHXt3Vy1j7P X-Received: by 2002:a05:6a20:8e1e:b0:cd:ed5c:4ec with SMTP id y30-20020a056a208e1e00b000cded5c04ecmr13376812pzj.3.1679065039666; Fri, 17 Mar 2023 07:57:19 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1679065039; cv=none; d=google.com; s=arc-20160816; b=jka5jPqVpHDzAS+HIwNjekjtT1gFJPjYo+qhB7DG+XP5t97+eVf9HkuigHLHbPZXmx 94x0hXibQBbyz7O7zcFO1MPn2CjxiXH6Bf4jmkr8vskw8eDiXPG0dk34LJeQvnjAatxG jUbWvqkX6D0fNNXR8H4UGVjp8FWUWG/n71YLq6YULsAGtQ+qzxX/sN2AVdL/sh+jhF7O hWW06aIrV2i8WGR2I8i+Hn3O62zvp0NpJAPrLueXZrjNickNBIsJVczG+F+2q9ic3APP 9iHODduLlZ4reCanAnlQeRwwMAhfY+fyxNNKUDqbOCQiepCgv60J1TP9+fWPs36PHw7U IB/A== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=list-id:precedence:cc:to:from:subject:message-id:references :mime-version:in-reply-to:date:dkim-signature; bh=PkYhcFSA6DbfFEE6GkQuWN6B5OP9XSkOTQiYSr9a+3A=; b=yZgm6npvQ9nXuLxiDWMYMWqEJLBvk/2dY8v3d7Ll+rpSFKUmL7FCPEfODN+jEGalEb XJwtQcOReefw0TrIj7CoBp1qpa6VzOzS7OLQTTGIfrn0D7fnLzgULuC+mYoWC23qgUrk hVaBcWVie/deK+41TSls2xtaB76UN81TYqhON2C+srqN8BF/L1M8yH7T0yjoud/GZNTq ut4qKD4gII83BuaL5BH+cvL434gcZ8wu1aEzlGPU3h8P8lAFIjR0N0hUIwrTsGFOMBPm mpf/FgSo2FkovukQgZoQ/xDxm+u9g/WWgCW5jpsxfI6Scy2Z6LEjv4WsN8d5h8+7O3jG mRSA== ARC-Authentication-Results: i=1; mx.google.com; dkim=pass header.i=@google.com header.s=20210112 header.b=UyLSTmef; spf=pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) smtp.mailfrom=linux-kernel-owner@vger.kernel.org; dmarc=pass (p=REJECT sp=REJECT dis=NONE) header.from=google.com Received: from out1.vger.email (out1.vger.email. [2620:137:e000::1:20]) by mx.google.com with ESMTP id e7-20020a633707000000b005006397721fsi2470008pga.859.2023.03.17.07.57.06; Fri, 17 Mar 2023 07:57:19 -0700 (PDT) Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20; Authentication-Results: mx.google.com; dkim=pass header.i=@google.com header.s=20210112 header.b=UyLSTmef; spf=pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) smtp.mailfrom=linux-kernel-owner@vger.kernel.org; dmarc=pass (p=REJECT sp=REJECT dis=NONE) header.from=google.com Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S231229AbjCQOdk (ORCPT + 99 others); Fri, 17 Mar 2023 10:33:40 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:57178 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S230326AbjCQOdi (ORCPT ); Fri, 17 Mar 2023 10:33:38 -0400 Received: from mail-wr1-x449.google.com (mail-wr1-x449.google.com [IPv6:2a00:1450:4864:20::449]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id BCA94B482F for ; Fri, 17 Mar 2023 07:33:31 -0700 (PDT) Received: by mail-wr1-x449.google.com with SMTP id b14-20020a05600003ce00b002cfefd8e637so856739wrg.15 for ; Fri, 17 Mar 2023 07:33:31 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=20210112; t=1679063610; h=cc:to:from:subject:message-id:references:mime-version:in-reply-to :date:from:to:cc:subject:date:message-id:reply-to; bh=PkYhcFSA6DbfFEE6GkQuWN6B5OP9XSkOTQiYSr9a+3A=; b=UyLSTmefxksmvXKeAjm571K9GjoJEbu1HCK12EknPVteilSMeBKavO3LkckLFNtlCm oXiHECL+QwsC1FPST5alLNKDzYGELsOrAEFswh0wwZGy7fPiyWIvxZtxbLa0tvB1JPb7 KCNVAzwbGp14OzPjK6eE1i/r4f3uvdup+zBVPwR0ECqKinmvc1h2S8cJjJHfDB8NHy3U VIAKRaLC4nJ/Do+KeQ7i49c0RS3m7JL1uceRJ8Utdmp3UA4GOLh/4sO/Lbj4IQ5uysG8 okM0D2vwHnkEq9ZSICRxNDMDTdNovitCFrQsO6+ydH8/o6A4W/otJaiNAwY2X4yVHDPY UM4A== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20210112; t=1679063610; 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=PkYhcFSA6DbfFEE6GkQuWN6B5OP9XSkOTQiYSr9a+3A=; b=5VIy3EtTo+kYcDvNJwMf3DjSRQCgRBujsC+3uP6TDLDW5IffnhK88JEDc0k8Cvt1Dp KtKoQTv4Nphwh6cq4xDHDhoVjcDsD3UxsU6arFjao95VE4pr9g1hthECvt8IKrWLNhKN 614bG2DrNCDOv/6T7rgNFWp43KdL49a0h+DaTV9Ji/VncX66m3hNRfdpQ2PeA/wA2nng dtNb9i0XY/kIKZ/o0DqPNDOJPbTNWlHKAj15xPI4nNU/4K7sxhxzAaMQxPYBSzxrnIqj 1DPf0nB0rYxHaEvFNA4WnuxJngcWXL8f9yQo6zDvvlLWfi5chDNWbBMHo6KpFPpuUnKQ Eldg== X-Gm-Message-State: AO0yUKVeMu3xo87wOj4bkt+6Au2KDbF9C5iUFFfE6MvpP26P5yskN8VE AHzJDY9+RVnRsCQJOMMV1+lyjrt3qjpg5DyG X-Received: from vdonnefort.c.googlers.com ([fda3:e722:ac3:cc00:28:9cb1:c0a8:2eea]) (user=vdonnefort job=sendgmr) by 2002:a5d:49d0:0:b0:2cf:ec67:8f9f with SMTP id t16-20020a5d49d0000000b002cfec678f9fmr1731222wrs.13.1679063609848; Fri, 17 Mar 2023 07:33:29 -0700 (PDT) Date: Fri, 17 Mar 2023 14:33:09 +0000 In-Reply-To: <20230317143310.1604700-1-vdonnefort@google.com> Mime-Version: 1.0 References: <20230317143310.1604700-1-vdonnefort@google.com> X-Mailer: git-send-email 2.40.0.rc1.284.g88254d51c5-goog Message-ID: <20230317143310.1604700-2-vdonnefort@google.com> Subject: [PATCH 1/2] ring-buffer: Introducing ring-buffer mapping functions From: Vincent Donnefort To: rostedt@goodmis.org, mhiramat@kernel.org, linux-kernel@vger.kernel.org, linux-trace-kernel@vger.kernel.org Cc: kernel-team@android.com, Vincent Donnefort X-Spam-Status: No, score=-9.6 required=5.0 tests=BAYES_00,DKIMWL_WL_MED, DKIM_SIGNED,DKIM_VALID,DKIM_VALID_AU,DKIM_VALID_EF,RCVD_IN_DNSWL_NONE, SPF_HELO_NONE,SPF_PASS,USER_IN_DEF_DKIM_WL autolearn=ham autolearn_force=no version=3.4.6 X-Spam-Checker-Version: SpamAssassin 3.4.6 (2021-04-09) on lindbergh.monkeyblade.net Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org X-getmail-retrieved-from-mailbox: =?utf-8?q?INBOX?= X-GMAIL-THRID: =?utf-8?q?1760627302879521730?= X-GMAIL-MSGID: =?utf-8?q?1760627302879521730?= In preparation for allowing the user-space to map a ring-buffer, add a set of mapping functions: ring_buffer_{map,unmap}() ring_buffer_map_fault() And controls on the ring-buffer: ring_buffer_get_reader_page() /* swap reader and head */ ring_buffer_update_meta_page() Mapping the ring-buffer also involves: A unique ID for each page of the ring-buffer, as currently the pages are only identified through their in-kernel VA. A meta-page, where are stored statistics about the ring-buffer and a page IDs list, ordered. A field gives what page is the reader one and one to gives where the ring-buffer starts in the list of data pages. The linear mapping exposes the meta-page, and each page of the ring-buffer, ordered following their unique ID, assigned during the first mapping. Once mapped, no page can get in or out of the ring-buffer: the buffer size will remain unmodified and the splice enabling functions will in reality simply memcpy the data instead of swapping pages. Also, the meta-page being... a single page, this limits at the moment the number of pages in the ring-buffer that can be mapped: ~3MB on a 4K pages system. Signed-off-by: Vincent Donnefort diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h index 782e14f62201..4897e17ebdde 100644 --- a/include/linux/ring_buffer.h +++ b/include/linux/ring_buffer.h @@ -6,6 +6,8 @@ #include #include +#include + struct trace_buffer; struct ring_buffer_iter; @@ -211,4 +213,10 @@ int trace_rb_cpu_prepare(unsigned int cpu, struct hlist_node *node); #define trace_rb_cpu_prepare NULL #endif +int ring_buffer_map(struct trace_buffer *buffer, int cpu); +int ring_buffer_unmap(struct trace_buffer *buffer, int cpu); +struct page *ring_buffer_map_fault(struct trace_buffer *buffer, int cpu, + unsigned long pgoff); +int ring_buffer_get_reader_page(struct trace_buffer *buffer, int cpu); +int ring_buffer_update_meta_page(struct trace_buffer *buffer, int cpu); #endif /* _LINUX_RING_BUFFER_H */ diff --git a/include/uapi/linux/trace_mmap.h b/include/uapi/linux/trace_mmap.h new file mode 100644 index 000000000000..b5caed17a066 --- /dev/null +++ b/include/uapi/linux/trace_mmap.h @@ -0,0 +1,24 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _UAPI_TRACE_MMAP_H_ +#define _UAPI_TRACE_MMAP_H_ + +#include + +#include + +struct ring_buffer_meta_page { +#if __BITS_PER_LONG == 64 + __u64 entries; + __u64 overrun; +#else + __u32 entries; + __u32 overrun; +#endif + __u32 pages_touched; + __u32 reader_page; + __u32 nr_data_pages; /* doesn't take into account the reader_page */ + __u32 data_page_head; /* index of data_pages[] */ + __u32 data_pages[]; +}; + +#endif /* _UAPI_TRACE_MMAP_H_ */ diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index af50d931b020..08765310380b 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -332,6 +332,7 @@ struct buffer_page { local_t entries; /* entries on this page */ unsigned long real_end; /* real end of data */ struct buffer_data_page *page; /* Actual data page */ + u32 id; /* ID for external mapping */ }; /* @@ -529,6 +530,12 @@ struct ring_buffer_per_cpu { rb_time_t before_stamp; u64 event_stamp[MAX_NEST]; u64 read_stamp; + + int mapped; + struct mutex mapping_lock; + unsigned long *page_ids; /* ID to addr */ + struct ring_buffer_meta_page *meta_page; + /* ring buffer pages to update, > 0 to add, < 0 to remove */ long nr_pages_to_update; struct list_head new_pages; /* new pages to add */ @@ -1452,12 +1459,37 @@ static inline void rb_inc_page(struct buffer_page **bpage) *bpage = list_entry(p, struct buffer_page, list); } +static inline void +rb_meta_page_head_move(struct ring_buffer_per_cpu *cpu_buffer, unsigned long num) +{ + unsigned long head_id; + + if (!READ_ONCE(cpu_buffer->mapped)) + return; + + head_id = cpu_buffer->meta_page->data_page_head; + cpu_buffer->meta_page->data_page_head = (head_id + num) % cpu_buffer->nr_pages; +} + +static inline void +rb_meta_page_head_swap(struct ring_buffer_per_cpu *cpu_buffer) +{ + struct ring_buffer_meta_page *meta = cpu_buffer->meta_page; + + if (!READ_ONCE(cpu_buffer->mapped)) + return; + + meta->reader_page = cpu_buffer->head_page->id; + meta->data_pages[meta->data_page_head] = cpu_buffer->reader_page->id; +} + static struct buffer_page * rb_set_head_page(struct ring_buffer_per_cpu *cpu_buffer) { struct buffer_page *head; struct buffer_page *page; struct list_head *list; + unsigned long cnt = 0; int i; if (RB_WARN_ON(cpu_buffer, !cpu_buffer->head_page)) @@ -1479,9 +1511,12 @@ rb_set_head_page(struct ring_buffer_per_cpu *cpu_buffer) do { if (rb_is_head_page(page, page->list.prev)) { cpu_buffer->head_page = page; + rb_meta_page_head_move(cpu_buffer, cnt); + return page; } rb_inc_page(&page); + cnt++; } while (page != head); } @@ -1567,6 +1602,13 @@ static void rb_tail_page_update(struct ring_buffer_per_cpu *cpu_buffer, /* Again, either we update tail_page or an interrupt does */ (void)cmpxchg(&cpu_buffer->tail_page, tail_page, next_page); } + + if (READ_ONCE(cpu_buffer->mapped)) { + /* Ensure the meta_page is ready */ + smp_rmb(); + WRITE_ONCE(cpu_buffer->meta_page->pages_touched, + local_read(&cpu_buffer->pages_touched)); + } } static int rb_check_bpage(struct ring_buffer_per_cpu *cpu_buffer, @@ -1735,6 +1777,7 @@ rb_allocate_cpu_buffer(struct trace_buffer *buffer, long nr_pages, int cpu) init_irq_work(&cpu_buffer->irq_work.work, rb_wake_up_waiters); init_waitqueue_head(&cpu_buffer->irq_work.waiters); init_waitqueue_head(&cpu_buffer->irq_work.full_waiters); + mutex_init(&cpu_buffer->mapping_lock); bpage = kzalloc_node(ALIGN(sizeof(*bpage), cache_line_size()), GFP_KERNEL, cpu_to_node(cpu)); @@ -2173,7 +2216,6 @@ int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size, /* prevent another thread from changing buffer sizes */ mutex_lock(&buffer->mutex); - if (cpu_id == RING_BUFFER_ALL_CPUS) { /* * Don't succeed if resizing is disabled, as a reader might be @@ -2523,6 +2565,13 @@ rb_handle_head_page(struct ring_buffer_per_cpu *cpu_buffer, local_sub(BUF_PAGE_SIZE, &cpu_buffer->entries_bytes); local_inc(&cpu_buffer->pages_lost); + if (READ_ONCE(cpu_buffer->mapped)) { + /* Ensure the meta_page is ready */ + smp_rmb(); + WRITE_ONCE(cpu_buffer->meta_page->overrun, + local_read(&cpu_buffer->overrun)); + } + /* * The entries will be zeroed out when we move the * tail page. @@ -3179,6 +3228,14 @@ static inline void rb_event_discard(struct ring_buffer_event *event) static void rb_commit(struct ring_buffer_per_cpu *cpu_buffer) { local_inc(&cpu_buffer->entries); + + if (READ_ONCE(cpu_buffer->mapped)) { + /* Ensure the meta_page is ready */ + smp_rmb(); + WRITE_ONCE(cpu_buffer->meta_page->entries, + local_read(&cpu_buffer->entries)); + } + rb_end_commit(cpu_buffer); } @@ -3482,7 +3539,7 @@ static void check_buffer(struct ring_buffer_per_cpu *cpu_buffer, return; /* - * If this interrupted another event, + * If this interrupted another event, */ if (atomic_inc_return(this_cpu_ptr(&checking)) != 1) goto out; @@ -4643,7 +4700,9 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer) * Now make the new head point back to the reader page. */ rb_list_head(reader->list.next)->prev = &cpu_buffer->reader_page->list; + rb_meta_page_head_swap(cpu_buffer); rb_inc_page(&cpu_buffer->head_page); + rb_meta_page_head_move(cpu_buffer, 1); local_inc(&cpu_buffer->pages_read); @@ -5285,6 +5344,12 @@ rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer) cpu_buffer->lost_events = 0; cpu_buffer->last_overrun = 0; + if (READ_ONCE(cpu_buffer->mapped)) { + WRITE_ONCE(cpu_buffer->meta_page->entries, 0); + WRITE_ONCE(cpu_buffer->meta_page->pages_touched, 0); + WRITE_ONCE(cpu_buffer->meta_page->overrun, 0); + } + rb_head_page_activate(cpu_buffer); } @@ -5489,6 +5554,11 @@ int ring_buffer_swap_cpu(struct trace_buffer *buffer_a, cpu_buffer_a = buffer_a->buffers[cpu]; cpu_buffer_b = buffer_b->buffers[cpu]; + if (READ_ONCE(cpu_buffer_a->mapped) || READ_ONCE(cpu_buffer_b->mapped)) { + ret = -EBUSY; + goto out; + } + /* At least make sure the two buffers are somewhat the same */ if (cpu_buffer_a->nr_pages != cpu_buffer_b->nr_pages) goto out; @@ -5722,7 +5792,8 @@ int ring_buffer_read_page(struct trace_buffer *buffer, * Otherwise, we can simply swap the page with the one passed in. */ if (read || (len < (commit - read)) || - cpu_buffer->reader_page == cpu_buffer->commit_page) { + cpu_buffer->reader_page == cpu_buffer->commit_page || + READ_ONCE(cpu_buffer->mapped)) { struct buffer_data_page *rpage = cpu_buffer->reader_page->page; unsigned int rpos = read; unsigned int pos = 0; @@ -5839,6 +5910,263 @@ int ring_buffer_read_page(struct trace_buffer *buffer, } EXPORT_SYMBOL_GPL(ring_buffer_read_page); +#define META_PAGE_MAX_PAGES \ + ((PAGE_SIZE - (offsetof(struct ring_buffer_meta_page, data_page_head))) >> 2) + +static void rb_free_page_ids(struct ring_buffer_per_cpu *cpu_buffer) +{ + kfree(cpu_buffer->page_ids); + cpu_buffer->page_ids = NULL; +} + +static int rb_alloc_meta_page(struct ring_buffer_per_cpu *cpu_buffer) +{ + if (cpu_buffer->meta_page) + return 0; + + if (cpu_buffer->nr_pages > META_PAGE_MAX_PAGES) + return -E2BIG; + + cpu_buffer->meta_page = page_to_virt(alloc_page(GFP_USER)); + if (!cpu_buffer->meta_page) + return -ENOMEM; + + return 0; +} + +static void rb_free_meta_page(struct ring_buffer_per_cpu *cpu_buffer) +{ + free_page((unsigned long)cpu_buffer->meta_page); + cpu_buffer->meta_page = NULL; +} + +static void rb_setup_ids_meta_page(struct ring_buffer_per_cpu *cpu_buffer, + unsigned long *page_ids) +{ + struct ring_buffer_meta_page *meta = cpu_buffer->meta_page; + struct buffer_page *first_page, *bpage; + int id = 0; + + page_ids[id] = (unsigned long)cpu_buffer->reader_page->page; + cpu_buffer->reader_page->id = id++; + + first_page = bpage = rb_set_head_page(cpu_buffer); + do { + if (id > META_PAGE_MAX_PAGES) { + WARN_ON(1); + break; + } + + page_ids[id] = (unsigned long)bpage->page; + bpage->id = id; + meta->data_pages[id - 1] = id; + + rb_inc_page(&bpage); + id++; + } while (bpage != first_page); + + /* install page ID to kern VA translation */ + cpu_buffer->page_ids = page_ids; + + meta->entries = 0; + meta->overrun = 0; + meta->pages_touched = 0; + meta->reader_page = cpu_buffer->reader_page->id; + meta->nr_data_pages = cpu_buffer->nr_pages; + meta->data_page_head = 0; +} + +static inline struct ring_buffer_per_cpu * +rb_get_mapped_buffer(struct trace_buffer *buffer, int cpu) +{ + struct ring_buffer_per_cpu *cpu_buffer; + + if (!cpumask_test_cpu(cpu, buffer->cpumask)) + return ERR_PTR(-EINVAL); + + cpu_buffer = buffer->buffers[cpu]; + + mutex_lock(&cpu_buffer->mapping_lock); + + if (!cpu_buffer->mapped) { + mutex_unlock(&cpu_buffer->mapping_lock); + return ERR_PTR(-ENODEV); + } + + return cpu_buffer; +} + +static inline void rb_put_mapped_buffer(struct ring_buffer_per_cpu *cpu_buffer) +{ + mutex_unlock(&cpu_buffer->mapping_lock); +} + +int ring_buffer_map(struct trace_buffer *buffer, int cpu) +{ + struct ring_buffer_per_cpu *cpu_buffer; + unsigned long flags, *page_ids; + int err = 0; + + if (!cpumask_test_cpu(cpu, buffer->cpumask)) + return -EINVAL; + + cpu_buffer = buffer->buffers[cpu]; + + mutex_lock(&cpu_buffer->mapping_lock); + + if (cpu_buffer->mapped) { + WRITE_ONCE(cpu_buffer->mapped, cpu_buffer->mapped + 1); + goto unlock; + } + + /* prevent another thread from changing buffer sizes */ + mutex_lock(&buffer->mutex); + atomic_inc(&cpu_buffer->resize_disabled); + mutex_unlock(&buffer->mutex); + + err = rb_alloc_meta_page(cpu_buffer); + if (err) { + atomic_dec(&cpu_buffer->resize_disabled); + goto unlock; + } + + /* page_ids include the reader page while nr_pages does not */ + page_ids = kzalloc(sizeof(*page_ids) * (cpu_buffer->nr_pages + 1), + GFP_KERNEL); + if (!page_ids) { + rb_free_meta_page(cpu_buffer); + atomic_dec(&cpu_buffer->resize_disabled); + err = -ENOMEM; + goto unlock; + } + + /* + * Lock all readers to block any page swap until the page IDs are + * assigned. + */ + raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); + + rb_setup_ids_meta_page(cpu_buffer, page_ids); + /* + * Ensure the writer will observe the meta-page before + * cpu_buffer->mapped. + */ + smp_wmb(); + WRITE_ONCE(cpu_buffer->mapped, 1); + + /* Init meta_page values unless the writer did it already */ + cmpxchg(&cpu_buffer->meta_page->entries, 0, + local_read(&cpu_buffer->entries)); + cmpxchg(&cpu_buffer->meta_page->overrun, 0, + local_read(&cpu_buffer->overrun)); + cmpxchg(&cpu_buffer->meta_page->pages_touched, 0, + local_read(&cpu_buffer->pages_touched)); + + raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); +unlock: + mutex_unlock(&cpu_buffer->mapping_lock); + + return err; +} + +int ring_buffer_unmap(struct trace_buffer *buffer, int cpu) +{ + struct ring_buffer_per_cpu *cpu_buffer; + int err = 0; + + if (!cpumask_test_cpu(cpu, buffer->cpumask)) + return -EINVAL; + + cpu_buffer = buffer->buffers[cpu]; + + mutex_lock(&cpu_buffer->mapping_lock); + + if (!cpu_buffer->mapped) { + err = -ENODEV; + goto unlock; + } + + WRITE_ONCE(cpu_buffer->mapped, cpu_buffer->mapped - 1); + if (!cpu_buffer->mapped) { + /* Wait the writer and readers to observe !mapped */ + synchronize_rcu(); + + rb_free_page_ids(cpu_buffer); + rb_free_meta_page(cpu_buffer); + atomic_dec(&cpu_buffer->resize_disabled); + } + +unlock: + mutex_unlock(&cpu_buffer->mapping_lock); + + return err; +} + +/* + * +--------------+ + * | meta page | pgoff=0 + * +--------------+ + * | data page1 | pgoff=1 page_ids=0 + * +--------------+ + * | data page2 | pgoff=2 page_ids=1 + * ... + */ +struct page *ring_buffer_map_fault(struct trace_buffer *buffer, int cpu, + unsigned long pgoff) +{ + struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu]; + + if (!pgoff) + return virt_to_page(cpu_buffer->meta_page); + + pgoff--; + if (pgoff > cpu_buffer->nr_pages) + return NULL; + + return virt_to_page(cpu_buffer->page_ids[pgoff]); +} + +int ring_buffer_get_reader_page(struct trace_buffer *buffer, int cpu) +{ + struct ring_buffer_per_cpu *cpu_buffer; + struct buffer_page *reader; + unsigned long flags; + + cpu_buffer = rb_get_mapped_buffer(buffer, cpu); + if (IS_ERR(cpu_buffer)) + return (int)PTR_ERR(cpu_buffer); + + raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); + reader = cpu_buffer->reader_page; + reader->read = rb_page_size(reader); + if (!rb_per_cpu_empty(cpu_buffer)) + WARN_ON(!rb_get_reader_page(cpu_buffer)); + raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); + + rb_put_mapped_buffer(cpu_buffer); + + return 0; +} + +int ring_buffer_update_meta_page(struct trace_buffer *buffer, int cpu) +{ + struct ring_buffer_per_cpu *cpu_buffer; + unsigned long flags; + + cpu_buffer = rb_get_mapped_buffer(buffer, cpu); + if (IS_ERR(cpu_buffer)) + return PTR_ERR(cpu_buffer); + + /* Update the head page if the writer moved it */ + raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); + rb_set_head_page(cpu_buffer); + raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); + + rb_put_mapped_buffer(cpu_buffer); + + return 0; +} + /* * We only allocate new buffers, never free them if the CPU goes down. * If we were to free the buffer, then the user would lose any trace that was in From patchwork Fri Mar 17 14:33:10 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Vincent Donnefort X-Patchwork-Id: 71299 Return-Path: Delivered-To: ouuuleilei@gmail.com Received: by 2002:a5d:604a:0:0:0:0:0 with SMTP id j10csp380021wrt; Fri, 17 Mar 2023 07:44:50 -0700 (PDT) X-Google-Smtp-Source: AK7set/RV61tOjH1vzI1TF+mdfnwhSMJXNd2/8P5Wclm0HiwnZZ5LuPdAZcNnyMakQjg9RL5pao5 X-Received: by 2002:a05:6a00:3186:b0:5a9:cebd:7b79 with SMTP id bj6-20020a056a00318600b005a9cebd7b79mr7019767pfb.0.1679064290459; Fri, 17 Mar 2023 07:44:50 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1679064290; cv=none; d=google.com; s=arc-20160816; b=hDSeXgAiZZQXMb7JWgzkYvOecuUQ2R3I/fTDjftU/y3nyrFwLMG/vDwIY8bZjmj7HH mvb+i08ImJ+Ye4DIz1LtgStDkoAEXv7guys3LPS+FDKl21AIWtdfs6dWQXWPLZjZ+00R SiaKtKE6luN/h1YanZeSpzG+lgd7J3frcSqS1yRIqyAllQO0j9ikE08bTfnliaoOVK0Q 2O6zADyFfNjWUpod/DcPnMNZiStq7AnpvP8fz2d74eJDeXRpdQko8UcNb1JRJdWtjSZk dEfNbqSkEovsGHX3I0jnxAWUxk6V2kgvs3l9BQ6mVsfFC0718iqOEdY8CqwlfbfeUOPq wSPA== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=list-id:precedence:cc:to:from:subject:message-id:references :mime-version:in-reply-to:date:dkim-signature; bh=pr8i0Eumz09pFpMEBVzLFDV1F++dQdI0hyhxEAp2n3w=; b=JvdpyT3ny+dhYlFJaqCGpxDAEmTjQpEiKjeYQPFZ3XkhkpiGXDpbObF+H8soxuYnoa dfAd9sxspYxhxJMr6nQMwAicQWrzggnnP5Ej2R9ttqv9wkTIrE++Tws/5DkaDKuMKo75 zAf0veYvQ3eNke38eHPvIZQVwQQPrJ/HeX00tRTFyZ6F+HSo8GgeveCsocD5beISfZMg ELWirMpaKeQTWszPdCpYczB7GwjnQONatmqsxi4txP6hC4YxNNxtKG2k355XNSWfXSss 2hANqOEXnvlXlx4RZIBkuF+q8Rab7qSXU5ybrtHXUuNuYrnTQM6o+sBV1YrbTSLNwG+7 rgFw== ARC-Authentication-Results: i=1; mx.google.com; dkim=pass header.i=@google.com header.s=20210112 header.b=KFFpGv1i; spf=pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) smtp.mailfrom=linux-kernel-owner@vger.kernel.org; dmarc=pass (p=REJECT sp=REJECT dis=NONE) header.from=google.com Received: from out1.vger.email (out1.vger.email. [2620:137:e000::1:20]) by mx.google.com with ESMTP id h11-20020a63574b000000b0050be69d0a83si2248580pgm.701.2023.03.17.07.44.34; Fri, 17 Mar 2023 07:44:50 -0700 (PDT) Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20; Authentication-Results: mx.google.com; dkim=pass header.i=@google.com header.s=20210112 header.b=KFFpGv1i; spf=pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) smtp.mailfrom=linux-kernel-owner@vger.kernel.org; dmarc=pass (p=REJECT sp=REJECT dis=NONE) header.from=google.com Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S231152AbjCQOdp (ORCPT + 99 others); Fri, 17 Mar 2023 10:33:45 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:57190 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S231144AbjCQOdi (ORCPT ); Fri, 17 Mar 2023 10:33:38 -0400 Received: from mail-wr1-x449.google.com (mail-wr1-x449.google.com [IPv6:2a00:1450:4864:20::449]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 9F83FE4C5A for ; Fri, 17 Mar 2023 07:33:33 -0700 (PDT) Received: by mail-wr1-x449.google.com with SMTP id o13-20020adfa10d000000b002d34203df59so385250wro.9 for ; Fri, 17 Mar 2023 07:33:33 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=20210112; t=1679063612; h=cc:to:from:subject:message-id:references:mime-version:in-reply-to :date:from:to:cc:subject:date:message-id:reply-to; bh=pr8i0Eumz09pFpMEBVzLFDV1F++dQdI0hyhxEAp2n3w=; b=KFFpGv1i3Q3hEABcr9gwon1e9ZOOii+a9nok8Xz6VJHQXlZj8a4ilUYyQ7HMnuhkCI sXZLVNB42WAB9R7e4mMHVa9IZOWnDXuNH+2j9OKDAHzVLPmvvD6GIRnvO3NL+LPmoXb7 CuYqX6HtBJEl7yOy8tE3CbgH2a9QuAhgQH0TMKy6gIwD8vuHiQY14lGwrbFvySHqxjcW UHWAke4bMF7QCgim7nTrat4IpktRIS4roz/VIcQX5Tyx5Mc3q8mmJStRrFEcodzEy9VI XUqcI0Leb2W5ruN5ngLNBSm4rP1RDU/TYfcc9QEzXLb0+IXTjftKOL6d3GVh+lQTWdfp ZTSQ== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20210112; t=1679063612; 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=pr8i0Eumz09pFpMEBVzLFDV1F++dQdI0hyhxEAp2n3w=; b=5+fYIZX3nwu9Kisyap9AcS55z411c1WvNxVWw7R6H9FuX+h/jrUOxWAYTELCGMXPuV HbOTR6fbTBvJaMcVgAjc+D8akY7DBBc2AJUSw2SNKPRd1U5meTFIlSOrk3S5X2eYPPWd mADfhCtIlURzVuEXIe4XL0E+oBbFxEgVNmrN6RmBRCTWL8qpaohpQJI77duEO+YqSrE4 EfvQA5QIuBXgW3rdhwV6opqPM40nrQ9w6M6VAG1ou6iKYcTFqP37B24GtVLuvtJhXeG9 yp9leE3Rv3j4sMJQWNJIXKsXQcepU840S/dArRSfnLjafBpHKCh9dtrTHdipj6yjNyOZ XYng== X-Gm-Message-State: AO0yUKWo543mhSJx9JO7ag994GpXGn9kmcWpEa0CxZCekeCHWIZ4kstw L4dHThwTYxEOK4gTXfHQNjbwiFpz9TjZtDGL X-Received: from vdonnefort.c.googlers.com ([fda3:e722:ac3:cc00:28:9cb1:c0a8:2eea]) (user=vdonnefort job=sendgmr) by 2002:adf:efc1:0:b0:2cf:e74f:c5b1 with SMTP id i1-20020adfefc1000000b002cfe74fc5b1mr653973wrp.7.1679063612090; Fri, 17 Mar 2023 07:33:32 -0700 (PDT) Date: Fri, 17 Mar 2023 14:33:10 +0000 In-Reply-To: <20230317143310.1604700-1-vdonnefort@google.com> Mime-Version: 1.0 References: <20230317143310.1604700-1-vdonnefort@google.com> X-Mailer: git-send-email 2.40.0.rc1.284.g88254d51c5-goog Message-ID: <20230317143310.1604700-3-vdonnefort@google.com> Subject: [PATCH 2/2] tracing: Allow user-space mapping of the ring-buffer From: Vincent Donnefort To: rostedt@goodmis.org, mhiramat@kernel.org, linux-kernel@vger.kernel.org, linux-trace-kernel@vger.kernel.org Cc: kernel-team@android.com, Vincent Donnefort X-Spam-Status: No, score=-9.6 required=5.0 tests=BAYES_00,DKIMWL_WL_MED, DKIM_SIGNED,DKIM_VALID,DKIM_VALID_AU,DKIM_VALID_EF,RCVD_IN_DNSWL_NONE, SPF_HELO_NONE,SPF_PASS,USER_IN_DEF_DKIM_WL autolearn=ham autolearn_force=no version=3.4.6 X-Spam-Checker-Version: SpamAssassin 3.4.6 (2021-04-09) on lindbergh.monkeyblade.net Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org X-getmail-retrieved-from-mailbox: =?utf-8?q?INBOX?= X-GMAIL-THRID: =?utf-8?q?1760626517726944860?= X-GMAIL-MSGID: =?utf-8?q?1760626517726944860?= Currently, user-space extracts data from the ring-buffer via splice, which is handy for storage or network sharing. However, due to splice limitations, it is imposible to do real-time analysis without a copy. A solution for that problem is to let the user-space map the ring-buffer directly. The mapping exposed via the per-CPU file trace_pipe_raw. The first page is the meta-page and is followed by each page of the ring-buffer, ordered by their unique page ID. It is therefore easy to translate a page-ID to an offset in the mapping. * Meta-page -- include/uapi/linux/trace_mmap.h for a description * Page ID 0 * Page ID 1 ... The mapper must then do what use to be the kernel jobs: swap the reader with the head. This is done with a newly introduced ioctl: TRACE_MMAP_IOCTL_GET_READER_PAGE. Entries, pages_touched and overrun fields are automatically updated by the writer. Only readers keep the head page field updated. An additional ioctl TRACE_MMAP_IOCTL_UPDATE_META_PAGE allows to query that update, enabling non-consuming read from userspace. Signed-off-by: Vincent Donnefort diff --git a/include/uapi/linux/trace_mmap.h b/include/uapi/linux/trace_mmap.h index b5caed17a066..24bcec754a35 100644 --- a/include/uapi/linux/trace_mmap.h +++ b/include/uapi/linux/trace_mmap.h @@ -21,4 +21,7 @@ struct ring_buffer_meta_page { __u32 data_pages[]; }; +#define TRACE_MMAP_IOCTL_GET_READER_PAGE _IO('T', 0x1) +#define TRACE_MMAP_IOCTL_UPDATE_META_PAGE _IO('T', 0x2) + #endif /* _UAPI_TRACE_MMAP_H_ */ diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 45551c7b4c36..51d06a2a7545 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -6399,7 +6399,7 @@ static void tracing_set_nop(struct trace_array *tr) { if (tr->current_trace == &nop_trace) return; - + tr->current_trace->enabled--; if (tr->current_trace->reset) @@ -8432,15 +8432,27 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, return ret; } -/* An ioctl call with cmd 0 to the ring buffer file will wake up all waiters */ static long tracing_buffers_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { struct ftrace_buffer_info *info = file->private_data; struct trace_iterator *iter = &info->iter; + switch (cmd) { + case TRACE_MMAP_IOCTL_GET_READER_PAGE: + return ring_buffer_get_reader_page(iter->array_buffer->buffer, + iter->cpu_file); + case TRACE_MMAP_IOCTL_UPDATE_META_PAGE: + return ring_buffer_update_meta_page(iter->array_buffer->buffer, + iter->cpu_file); + } + if (cmd) - return -ENOIOCTLCMD; + return -ENOTTY; + /* + * An ioctl call with cmd 0 to the ring buffer file will wake up all + * waiters + */ mutex_lock(&trace_types_lock); iter->wait_index++; @@ -8453,6 +8465,60 @@ static long tracing_buffers_ioctl(struct file *file, unsigned int cmd, unsigned return 0; } +static vm_fault_t tracing_buffers_mmap_fault(struct vm_fault *vmf) +{ + struct ftrace_buffer_info *info = vmf->vma->vm_file->private_data; + struct trace_iterator *iter = &info->iter; + vm_fault_t ret = VM_FAULT_SIGBUS; + struct page *page; + + page = ring_buffer_map_fault(iter->array_buffer->buffer, iter->cpu_file, + vmf->pgoff); + if (!page) + return ret; + + get_page(page); + vmf->page = page; + + return 0; +} + +static void tracing_buffers_mmap_close(struct vm_area_struct *vma) +{ + struct ftrace_buffer_info *info = vma->vm_file->private_data; + struct trace_iterator *iter = &info->iter; + + ring_buffer_unmap(iter->array_buffer->buffer, iter->cpu_file); +} + +static void tracing_buffers_mmap_open(struct vm_area_struct *vma) +{ + struct ftrace_buffer_info *info = vma->vm_file->private_data; + struct trace_iterator *iter = &info->iter; + + WARN_ON(ring_buffer_map(iter->array_buffer->buffer, iter->cpu_file)); +} + +static const struct vm_operations_struct tracing_buffers_vmops = { + .open = tracing_buffers_mmap_open, + .close = tracing_buffers_mmap_close, + .fault = tracing_buffers_mmap_fault, +}; + +static int tracing_buffers_mmap(struct file *filp, struct vm_area_struct *vma) +{ + struct ftrace_buffer_info *info = filp->private_data; + struct trace_iterator *iter = &info->iter; + + if (vma->vm_flags & VM_WRITE) + return -EPERM; + + vm_flags_mod(vma, VM_DONTCOPY | VM_DONTDUMP, VM_MAYWRITE); + vma->vm_ops = &tracing_buffers_vmops; + + return ring_buffer_map(iter->array_buffer->buffer, iter->cpu_file); +} + static const struct file_operations tracing_buffers_fops = { .open = tracing_buffers_open, .read = tracing_buffers_read, @@ -8461,6 +8527,7 @@ static const struct file_operations tracing_buffers_fops = { .splice_read = tracing_buffers_splice_read, .unlocked_ioctl = tracing_buffers_ioctl, .llseek = no_llseek, + .mmap = tracing_buffers_mmap, }; static ssize_t