From patchwork Mon Aug 26 16:06:52 2019 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Tejun Heo X-Patchwork-Id: 11115013 Return-Path: Received: from mail.kernel.org (pdx-korg-mail-1.web.codeaurora.org [172.30.200.123]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id E65F8184E for ; Mon, 26 Aug 2019 16:07:31 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by mail.kernel.org (Postfix) with ESMTP id B8DFE2187F for ; Mon, 26 Aug 2019 16:07:31 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=default; t=1566835651; bh=v6adb07fgKTpxyfblv9LM8Id3Y7Bpl/Uvyroh0v+vVQ=; h=From:To:Cc:Subject:Date:In-Reply-To:References:List-ID:From; b=2TDZyJmNVM6MBqCqCDrZCeSAwYVtTh7kSfEQgX6pulz+JH5aBbwYnx2JgrCEomLRO krz7F1jBE6TdNelBlF0+yOcuBh8BMQY/naQYU1MW1VgzicBode8RpjpY4IgH3vUwex 3f9Z4tqXlYJv9CBOrMUta1lg13JNQJtybk0p2bdA= Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1732497AbfHZQHI (ORCPT ); Mon, 26 Aug 2019 12:07:08 -0400 Received: from mail-qk1-f194.google.com ([209.85.222.194]:40594 "EHLO mail-qk1-f194.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1729338AbfHZQHH (ORCPT ); Mon, 26 Aug 2019 12:07:07 -0400 Received: by mail-qk1-f194.google.com with SMTP id s145so14445798qke.7; Mon, 26 Aug 2019 09:07:06 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20161025; h=sender:from:to:cc:subject:date:message-id:in-reply-to:references; bh=VLHZ6ZNZgqY5/GiQqVLdmuLaStLAgiw+ZiX1K52HrY4=; b=sNwCMXNqcvEyA4KghlQTGzgEiPrT39GgcA2FeeuElZKbfhHirdQcRItctuijuXXqOq kytMlb6po4B16uaQagwe48+I9ETxfswFZRqdvHwf/nJPr0VxltfNOfbOm3qUiHNDy0o+ Vb/zF0BsMWZ/8iEhiNJIH8d8bYf5FlD8PT2vThdCDoX76yUthkG/kml9sRZe4ubIcTIF K5gPNKO3yvicvLQJ/RMICafnmg94MSCTsyHfDXelWtzsBERuEqohmd+/N5d+f0sIiBec 3BI8y4q4wS3W3ITTG7UpWqM7DxxS0a4Hmk1tuYbee9Hh4moHaIRq/pqif4gBMk6aRXHo E6fA== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:sender:from:to:cc:subject:date:message-id :in-reply-to:references; bh=VLHZ6ZNZgqY5/GiQqVLdmuLaStLAgiw+ZiX1K52HrY4=; b=i59/8GUbaOlxmpPtDwX9OlJrmMYn3wLmdUDZ/7e7syLQEbll3v8kkMsXmvcD1KNltN E4sDq5Gv13NhwVvJivgYw9xSniePAg9K+oDrpZjrdFllwyImgWNyU4ZPcAZLIHrJ0bDn rr5CHUIws9lfUuay+gAOMNM3xKkf73J+DECUFjDPtqXJD6muaDFIxm2xjEkMLI4WSdMF w7Icd4OAHCGzksefj3anW8ZNZKfiZOkAkaGGw6FvTnMEsu2F7mfs8fmRuyfBRccqzYu+ D2PKcmrtTrp7o/155tGudv5xg91EweyOFPe2yQJo9cCIgcQ1vvBSK7Me8bVOa2F1vUn3 dcMA== X-Gm-Message-State: APjAAAVxMYbB+ND1sQnqcO5KLL3SWNlkh9jVzVaqUSHS1Jwxs5Kvu7Ly vLUNdr+ZXrYDyzmWoc4V5TY= X-Google-Smtp-Source: APXvYqwlluVR2FGCz1GaYgZtKsTrXxdhegOASK8N9AFXHtVRxexC+pNnumgVk+Ouc0c5UQRW6sJBeQ== X-Received: by 2002:a37:454:: with SMTP id 81mr16595509qke.153.1566835626129; Mon, 26 Aug 2019 09:07:06 -0700 (PDT) Received: from localhost ([2620:10d:c091:500::d081]) by smtp.gmail.com with ESMTPSA id 20sm6237089qkg.59.2019.08.26.09.07.05 (version=TLS1_2 cipher=ECDHE-RSA-AES128-GCM-SHA256 bits=128/128); Mon, 26 Aug 2019 09:07:05 -0700 (PDT) From: Tejun Heo To: axboe@kernel.dk, jack@suse.cz, hannes@cmpxchg.org, mhocko@kernel.org, vdavydov.dev@gmail.com Cc: cgroups@vger.kernel.org, linux-mm@kvack.org, linux-block@vger.kernel.org, linux-kernel@vger.kernel.org, kernel-team@fb.com, guro@fb.com, akpm@linux-foundation.org, Tejun Heo Subject: [PATCH 1/5] writeback: Generalize and expose wb_completion Date: Mon, 26 Aug 2019 09:06:52 -0700 Message-Id: <20190826160656.870307-2-tj@kernel.org> X-Mailer: git-send-email 2.17.1 In-Reply-To: <20190826160656.870307-1-tj@kernel.org> References: <20190826160656.870307-1-tj@kernel.org> Sender: linux-block-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-block@vger.kernel.org wb_completion is used to track writeback completions. We want to use it from memcg side for foreign inode flushes. This patch updates it to remember the target waitq instead of assuming bdi->wb_waitq and expose it outside of fs-writeback.c. Signed-off-by: Tejun Heo Reviewed-by: Jan Kara --- fs/fs-writeback.c | 47 ++++++++++---------------------- include/linux/backing-dev-defs.h | 20 ++++++++++++++ include/linux/backing-dev.h | 2 ++ 3 files changed, 36 insertions(+), 33 deletions(-) diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index fddd8abd839a..9442f1fd6460 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -36,10 +36,6 @@ */ #define MIN_WRITEBACK_PAGES (4096UL >> (PAGE_SHIFT - 10)) -struct wb_completion { - atomic_t cnt; -}; - /* * Passed into wb_writeback(), essentially a subset of writeback_control */ @@ -60,19 +56,6 @@ struct wb_writeback_work { struct wb_completion *done; /* set if the caller waits */ }; -/* - * If one wants to wait for one or more wb_writeback_works, each work's - * ->done should be set to a wb_completion defined using the following - * macro. Once all work items are issued with wb_queue_work(), the caller - * can wait for the completion of all using wb_wait_for_completion(). Work - * items which are waited upon aren't freed automatically on completion. - */ -#define DEFINE_WB_COMPLETION_ONSTACK(cmpl) \ - struct wb_completion cmpl = { \ - .cnt = ATOMIC_INIT(1), \ - } - - /* * If an inode is constantly having its pages dirtied, but then the * updates stop dirtytime_expire_interval seconds in the past, it's @@ -182,7 +165,7 @@ static void finish_writeback_work(struct bdi_writeback *wb, if (work->auto_free) kfree(work); if (done && atomic_dec_and_test(&done->cnt)) - wake_up_all(&wb->bdi->wb_waitq); + wake_up_all(done->waitq); } static void wb_queue_work(struct bdi_writeback *wb, @@ -206,20 +189,18 @@ static void wb_queue_work(struct bdi_writeback *wb, /** * wb_wait_for_completion - wait for completion of bdi_writeback_works - * @bdi: bdi work items were issued to * @done: target wb_completion * * Wait for one or more work items issued to @bdi with their ->done field - * set to @done, which should have been defined with - * DEFINE_WB_COMPLETION_ONSTACK(). This function returns after all such - * work items are completed. Work items which are waited upon aren't freed + * set to @done, which should have been initialized with + * DEFINE_WB_COMPLETION(). This function returns after all such work items + * are completed. Work items which are waited upon aren't freed * automatically on completion. */ -static void wb_wait_for_completion(struct backing_dev_info *bdi, - struct wb_completion *done) +void wb_wait_for_completion(struct wb_completion *done) { atomic_dec(&done->cnt); /* put down the initial count */ - wait_event(bdi->wb_waitq, !atomic_read(&done->cnt)); + wait_event(*done->waitq, !atomic_read(&done->cnt)); } #ifdef CONFIG_CGROUP_WRITEBACK @@ -854,7 +835,7 @@ static void bdi_split_work_to_wbs(struct backing_dev_info *bdi, restart: rcu_read_lock(); list_for_each_entry_continue_rcu(wb, &bdi->wb_list, bdi_node) { - DEFINE_WB_COMPLETION_ONSTACK(fallback_work_done); + DEFINE_WB_COMPLETION(fallback_work_done, bdi); struct wb_writeback_work fallback_work; struct wb_writeback_work *work; long nr_pages; @@ -901,7 +882,7 @@ static void bdi_split_work_to_wbs(struct backing_dev_info *bdi, last_wb = wb; rcu_read_unlock(); - wb_wait_for_completion(bdi, &fallback_work_done); + wb_wait_for_completion(&fallback_work_done); goto restart; } rcu_read_unlock(); @@ -2373,7 +2354,8 @@ static void wait_sb_inodes(struct super_block *sb) static void __writeback_inodes_sb_nr(struct super_block *sb, unsigned long nr, enum wb_reason reason, bool skip_if_busy) { - DEFINE_WB_COMPLETION_ONSTACK(done); + struct backing_dev_info *bdi = sb->s_bdi; + DEFINE_WB_COMPLETION(done, bdi); struct wb_writeback_work work = { .sb = sb, .sync_mode = WB_SYNC_NONE, @@ -2382,14 +2364,13 @@ static void __writeback_inodes_sb_nr(struct super_block *sb, unsigned long nr, .nr_pages = nr, .reason = reason, }; - struct backing_dev_info *bdi = sb->s_bdi; if (!bdi_has_dirty_io(bdi) || bdi == &noop_backing_dev_info) return; WARN_ON(!rwsem_is_locked(&sb->s_umount)); bdi_split_work_to_wbs(sb->s_bdi, &work, skip_if_busy); - wb_wait_for_completion(bdi, &done); + wb_wait_for_completion(&done); } /** @@ -2451,7 +2432,8 @@ EXPORT_SYMBOL(try_to_writeback_inodes_sb); */ void sync_inodes_sb(struct super_block *sb) { - DEFINE_WB_COMPLETION_ONSTACK(done); + struct backing_dev_info *bdi = sb->s_bdi; + DEFINE_WB_COMPLETION(done, bdi); struct wb_writeback_work work = { .sb = sb, .sync_mode = WB_SYNC_ALL, @@ -2461,7 +2443,6 @@ void sync_inodes_sb(struct super_block *sb) .reason = WB_REASON_SYNC, .for_sync = 1, }; - struct backing_dev_info *bdi = sb->s_bdi; /* * Can't skip on !bdi_has_dirty() because we should wait for !dirty @@ -2475,7 +2456,7 @@ void sync_inodes_sb(struct super_block *sb) /* protect against inode wb switch, see inode_switch_wbs_work_fn() */ bdi_down_write_wb_switch_rwsem(bdi); bdi_split_work_to_wbs(bdi, &work, false); - wb_wait_for_completion(bdi, &done); + wb_wait_for_completion(&done); bdi_up_write_wb_switch_rwsem(bdi); wait_sb_inodes(sb); diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h index 6a1a8a314d85..8fb740178d5d 100644 --- a/include/linux/backing-dev-defs.h +++ b/include/linux/backing-dev-defs.h @@ -67,6 +67,26 @@ enum wb_reason { WB_REASON_MAX, }; +struct wb_completion { + atomic_t cnt; + wait_queue_head_t *waitq; +}; + +#define __WB_COMPLETION_INIT(_waitq) \ + (struct wb_completion){ .cnt = ATOMIC_INIT(1), .waitq = (_waitq) } + +/* + * If one wants to wait for one or more wb_writeback_works, each work's + * ->done should be set to a wb_completion defined using the following + * macro. Once all work items are issued with wb_queue_work(), the caller + * can wait for the completion of all using wb_wait_for_completion(). Work + * items which are waited upon aren't freed automatically on completion. + */ +#define WB_COMPLETION_INIT(bdi) __WB_COMPLETION_INIT(&(bdi)->wb_waitq) + +#define DEFINE_WB_COMPLETION(cmpl, bdi) \ + struct wb_completion cmpl = WB_COMPLETION_INIT(bdi) + /* * For cgroup writeback, multiple wb's may map to the same blkcg. Those * wb's can operate mostly independently but should share the congested diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 35b31d176f74..02650b1253a2 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -44,6 +44,8 @@ void wb_start_background_writeback(struct bdi_writeback *wb); void wb_workfn(struct work_struct *work); void wb_wakeup_delayed(struct bdi_writeback *wb); +void wb_wait_for_completion(struct wb_completion *done); + extern spinlock_t bdi_lock; extern struct list_head bdi_list; From patchwork Mon Aug 26 16:06:53 2019 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Tejun Heo X-Patchwork-Id: 11115011 Return-Path: Received: from mail.kernel.org (pdx-korg-mail-1.web.codeaurora.org [172.30.200.123]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id 5F6271395 for ; Mon, 26 Aug 2019 16:07:31 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by mail.kernel.org (Postfix) with ESMTP id 3C81421881 for ; Mon, 26 Aug 2019 16:07:31 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=default; t=1566835651; bh=d76APXROQP42ZcDoR+W8ITdMwQ9mySrz4LUyUBz1r7g=; h=From:To:Cc:Subject:Date:In-Reply-To:References:List-ID:From; b=n/xw8qeYi58PcLTnYSem4bBXlfnnI92f0zTX9eSTa79xV3IjpWMgsy0EE03u2B2Zg 3ofyol9dkUooAq3srZuv/OLn22K+TikYqohaEk3SwyG1YPjWZ5kbNhzfzoE78RGsXR Itm6vEapSiUpvX0dv7t7F/I1m7XNFrHbJrQdeCv4= Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1732534AbfHZQHK (ORCPT ); Mon, 26 Aug 2019 12:07:10 -0400 Received: from mail-qt1-f194.google.com ([209.85.160.194]:44548 "EHLO mail-qt1-f194.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1732544AbfHZQHJ (ORCPT ); Mon, 26 Aug 2019 12:07:09 -0400 Received: by mail-qt1-f194.google.com with SMTP id 44so18344419qtg.11; Mon, 26 Aug 2019 09:07:08 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20161025; h=sender:from:to:cc:subject:date:message-id:in-reply-to:references; bh=3O1Xq487diyfXoEMJTs1w0KreVNXXWibqp67Mw7HjBc=; b=SEjLWoYq0fP4psa2uBCCNXgApcuu8+EjDA3JSX8B878dJyhaBo4676Upvh2awIl1by hWUw2nMIRbQ1IepCNcoN4rtxFcmV3OkbYrB/HUNC7W42vZhjFKqslqo5N3geJADazT89 Isqm1ZYiEe8QZuRhdh1ET/XGlhWk9J7KMO1YGG1t1ghRvhMJsLk+xmyE9v1w3D2LDiym IXtA59EQycyV6DncujF5KbNoD9r9BWPpOqPvy/gANx21ZEGvUODp6cDqXEZENy+s9LJU ja/E0xCD8Mk5t3kLAMXsrtNXnfgzHlhuPrnw8C99C/D4DoCJOjrcRw9QKiy5r/thHfhw 3SSg== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:sender:from:to:cc:subject:date:message-id :in-reply-to:references; bh=3O1Xq487diyfXoEMJTs1w0KreVNXXWibqp67Mw7HjBc=; b=gwlnkljsUyqOmMcvQMu+H1/G6EZDbezEaWJXSS9tbTWLZMqAys/n7y4L1mtJKPfeki iPer+U1NujA2wusn90DJhkjE5I++J6HqhVtUFPRf3phYvd1gVU+5ZuQzeDxyJDMucdVB m2csAbdEsP8XBp6EPRQnEMC0jwuorS8HXdrxhnVPuXfrkzMhf4t8SWI3N9kXsyd2racs mwniy5FulMsyPtLPXuk8hof/uNzP3t3//zawzuC/KdU937LfPznASZDXFK7uygy1aJPB LI3AhF8pQv2vLS4pbRV99O0eoIrzYIC1jpxvepSWgHJ0occJGJzuSxGOQ21Orppmwnmr 7QKw== X-Gm-Message-State: APjAAAUO5TeeU1ofxVp31KR67OPwCCs5IKLMTgAYPSPq1JFwxqiuAjGw s6hAMPPstTOZNgAy/i6RauI= X-Google-Smtp-Source: APXvYqz6TmAInj6KM5R4Rc8P00hmyrxHa998IOH+1NeZV/9zlWFa2x+f6QG1y0uMpFPaYhkDibImdg== X-Received: by 2002:ac8:4504:: with SMTP id q4mr18060803qtn.286.1566835628343; Mon, 26 Aug 2019 09:07:08 -0700 (PDT) Received: from localhost ([2620:10d:c091:500::d081]) by smtp.gmail.com with ESMTPSA id r15sm6633892qtp.94.2019.08.26.09.07.07 (version=TLS1_2 cipher=ECDHE-RSA-AES128-GCM-SHA256 bits=128/128); Mon, 26 Aug 2019 09:07:07 -0700 (PDT) From: Tejun Heo To: axboe@kernel.dk, jack@suse.cz, hannes@cmpxchg.org, mhocko@kernel.org, vdavydov.dev@gmail.com Cc: cgroups@vger.kernel.org, linux-mm@kvack.org, linux-block@vger.kernel.org, linux-kernel@vger.kernel.org, kernel-team@fb.com, guro@fb.com, akpm@linux-foundation.org, Tejun Heo Subject: [PATCH 2/5] bdi: Add bdi->id Date: Mon, 26 Aug 2019 09:06:53 -0700 Message-Id: <20190826160656.870307-3-tj@kernel.org> X-Mailer: git-send-email 2.17.1 In-Reply-To: <20190826160656.870307-1-tj@kernel.org> References: <20190826160656.870307-1-tj@kernel.org> Sender: linux-block-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-block@vger.kernel.org There currently is no way to universally identify and lookup a bdi without holding a reference and pointer to it. This patch adds an non-recycling bdi->id and implements bdi_get_by_id() which looks up bdis by their ids. This will be used by memcg foreign inode flushing. I left bdi_list alone for simplicity and because while rb_tree does support rcu assignment it doesn't seem to guarantee lossless walk when walk is racing aginst tree rebalance operations. Signed-off-by: Tejun Heo Reviewed-by: Jan Kara --- include/linux/backing-dev-defs.h | 2 + include/linux/backing-dev.h | 1 + mm/backing-dev.c | 65 +++++++++++++++++++++++++++++++- 3 files changed, 66 insertions(+), 2 deletions(-) diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h index 8fb740178d5d..1075f2552cfc 100644 --- a/include/linux/backing-dev-defs.h +++ b/include/linux/backing-dev-defs.h @@ -185,6 +185,8 @@ struct bdi_writeback { }; struct backing_dev_info { + u64 id; + struct rb_node rb_node; /* keyed by ->id */ struct list_head bdi_list; unsigned long ra_pages; /* max readahead in PAGE_SIZE units */ unsigned long io_pages; /* max allowed IO size */ diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 02650b1253a2..84cdcfbc763f 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -24,6 +24,7 @@ static inline struct backing_dev_info *bdi_get(struct backing_dev_info *bdi) return bdi; } +struct backing_dev_info *bdi_get_by_id(u64 id); void bdi_put(struct backing_dev_info *bdi); __printf(2, 3) diff --git a/mm/backing-dev.c b/mm/backing-dev.c index e8e89158adec..612aa7c5ddbd 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0-only #include +#include #include #include #include @@ -22,10 +23,12 @@ EXPORT_SYMBOL_GPL(noop_backing_dev_info); static struct class *bdi_class; /* - * bdi_lock protects updates to bdi_list. bdi_list has RCU reader side - * locking. + * bdi_lock protects bdi_tree and updates to bdi_list. bdi_list has RCU + * reader side locking. */ DEFINE_SPINLOCK(bdi_lock); +static u64 bdi_id_cursor; +static struct rb_root bdi_tree = RB_ROOT; LIST_HEAD(bdi_list); /* bdi_wq serves all asynchronous writeback tasks */ @@ -859,9 +862,58 @@ struct backing_dev_info *bdi_alloc_node(gfp_t gfp_mask, int node_id) } EXPORT_SYMBOL(bdi_alloc_node); +static struct rb_node **bdi_lookup_rb_node(u64 id, struct rb_node **parentp) +{ + struct rb_node **p = &bdi_tree.rb_node; + struct rb_node *parent = NULL; + struct backing_dev_info *bdi; + + lockdep_assert_held(&bdi_lock); + + while (*p) { + parent = *p; + bdi = rb_entry(parent, struct backing_dev_info, rb_node); + + if (bdi->id > id) + p = &(*p)->rb_left; + else if (bdi->id < id) + p = &(*p)->rb_right; + else + break; + } + + if (parentp) + *parentp = parent; + return p; +} + +/** + * bdi_get_by_id - lookup and get bdi from its id + * @id: bdi id to lookup + * + * Find bdi matching @id and get it. Returns NULL if the matching bdi + * doesn't exist or is already unregistered. + */ +struct backing_dev_info *bdi_get_by_id(u64 id) +{ + struct backing_dev_info *bdi = NULL; + struct rb_node **p; + + spin_lock_bh(&bdi_lock); + p = bdi_lookup_rb_node(id, NULL); + if (*p) { + bdi = rb_entry(*p, struct backing_dev_info, rb_node); + bdi_get(bdi); + } + spin_unlock_bh(&bdi_lock); + + return bdi; +} + int bdi_register_va(struct backing_dev_info *bdi, const char *fmt, va_list args) { struct device *dev; + struct rb_node *parent, **p; if (bdi->dev) /* The driver needs to use separate queues per device */ return 0; @@ -877,7 +929,15 @@ int bdi_register_va(struct backing_dev_info *bdi, const char *fmt, va_list args) set_bit(WB_registered, &bdi->wb.state); spin_lock_bh(&bdi_lock); + + bdi->id = ++bdi_id_cursor; + + p = bdi_lookup_rb_node(bdi->id, &parent); + rb_link_node(&bdi->rb_node, parent, p); + rb_insert_color(&bdi->rb_node, &bdi_tree); + list_add_tail_rcu(&bdi->bdi_list, &bdi_list); + spin_unlock_bh(&bdi_lock); trace_writeback_bdi_register(bdi); @@ -918,6 +978,7 @@ EXPORT_SYMBOL(bdi_register_owner); static void bdi_remove_from_list(struct backing_dev_info *bdi) { spin_lock_bh(&bdi_lock); + rb_erase(&bdi->rb_node, &bdi_tree); list_del_rcu(&bdi->bdi_list); spin_unlock_bh(&bdi_lock); From patchwork Mon Aug 26 16:06:54 2019 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Tejun Heo X-Patchwork-Id: 11115009 Return-Path: Received: from mail.kernel.org (pdx-korg-mail-1.web.codeaurora.org [172.30.200.123]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id 4E0DA1800 for ; Mon, 26 Aug 2019 16:07:30 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by mail.kernel.org (Postfix) with ESMTP id 2CB472187F for ; Mon, 26 Aug 2019 16:07:30 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=default; t=1566835650; bh=75sevnElSVQkSWHj0jk5tjITBnjjmYiMrbnKf2uzbbU=; h=From:To:Cc:Subject:Date:In-Reply-To:References:List-ID:From; b=cbKLaX43CLhK/XBj2urX364jWt3HJJ71UOBXSvOAmPtO38GFKB7dWsdAvM4VjUZW2 BEX3p8dg6RCrWcHrTNpn76PeGgenryu85mMSWuShwxGxmnq5i0v58RIO4sBR8Ack8w H9Su+wTymWjtBG1WjwyhTuI4Ylxr2CPDljp44oiI= Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1732640AbfHZQHM (ORCPT ); Mon, 26 Aug 2019 12:07:12 -0400 Received: from mail-qt1-f193.google.com ([209.85.160.193]:38970 "EHLO mail-qt1-f193.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1732612AbfHZQHL (ORCPT ); Mon, 26 Aug 2019 12:07:11 -0400 Received: by mail-qt1-f193.google.com with SMTP id l9so18371244qtu.6; Mon, 26 Aug 2019 09:07:11 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20161025; h=sender:from:to:cc:subject:date:message-id:in-reply-to:references; bh=sbi9AtPpKs90xX0XCzYWXMGLwoRRPZP34bqUM0NUXLs=; b=gX5n0n0Iya2r+6HfxSBgduwjqnM9PRtJlmoEm5ghngBsve/UtQYFYtPDwNviTIYOMH yLHoMeNJ+DWQ0bdNx4cvSVgcN681dV36+OkH/g1jKJgRguOi7VsP0NlyTZAz7cNUZOE6 zqnuyTGB/QvBuFExLTGnei+AosOZ6sQ0y8LkGtkVWGqoLaIqdMokGxmf43BnVYTMWOsm TfgrfDI+kUfbZopDzIk1PUoIxNGEh7GWOOExZRBb6f7AdZPpR69VNoZkY4jlUDeGLJQo pcOBl6W9Exf/K3YN+IZmyKLnwa/O+zqQugMqiuDEyPBkAwPlHoZuAITEWOR87u2+0DCW ok0w== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:sender:from:to:cc:subject:date:message-id :in-reply-to:references; bh=sbi9AtPpKs90xX0XCzYWXMGLwoRRPZP34bqUM0NUXLs=; b=lAu9S9iex0vX+b+i6BGbhCh4rCDjb43qIoeBVZA0tbOjfj9vr7MNd+YwOwUVM+3D41 a+zUZF1tLNpg9fHAP4GFK5BhpDv9XOQlzIBq7p48d3Wpf+PFOjU6/3+w8r3Kv2vMq+JG blol3er/fN5nVDAtoCLtcSbQDrbPcv4LuOHHpZ5cfDL299hxyOZpg9s+BeBNyEM0Zl60 aj0SN8Ve3bnRDLy0VipTz1b0OgcIHH7yTQEmMGt9iQDX0J4t0FXNWTvF1cee4rUEdud7 Yd1Pp99OZnjfU7JBoSoxf0iSkeniqtgwPI82tFPH0mieM3PKz5WX8ZsLSYXpCXzwLqP9 WtHQ== X-Gm-Message-State: APjAAAWoMp9YiSRWdG7FmtrDlswnL6gZa+W1wRtHZUDG+2Ms+Nf8WIxN 9O1K00hRYQ1w8Wq97WVAuQ0= X-Google-Smtp-Source: APXvYqwfRmoFj279L2wsJx3QYrn8JRDZ4xVVrNIXLn3zjcDpszmBL7Yzn1lB3z9lIiUyrSDzWNyx1Q== X-Received: by 2002:ac8:4789:: with SMTP id k9mr18184801qtq.41.1566835630468; Mon, 26 Aug 2019 09:07:10 -0700 (PDT) Received: from localhost ([2620:10d:c091:500::d081]) by smtp.gmail.com with ESMTPSA id 131sm6410446qkn.7.2019.08.26.09.07.09 (version=TLS1_2 cipher=ECDHE-RSA-AES128-GCM-SHA256 bits=128/128); Mon, 26 Aug 2019 09:07:09 -0700 (PDT) From: Tejun Heo To: axboe@kernel.dk, jack@suse.cz, hannes@cmpxchg.org, mhocko@kernel.org, vdavydov.dev@gmail.com Cc: cgroups@vger.kernel.org, linux-mm@kvack.org, linux-block@vger.kernel.org, linux-kernel@vger.kernel.org, kernel-team@fb.com, guro@fb.com, akpm@linux-foundation.org, Tejun Heo Subject: [PATCH 3/5] writeback: Separate out wb_get_lookup() from wb_get_create() Date: Mon, 26 Aug 2019 09:06:54 -0700 Message-Id: <20190826160656.870307-4-tj@kernel.org> X-Mailer: git-send-email 2.17.1 In-Reply-To: <20190826160656.870307-1-tj@kernel.org> References: <20190826160656.870307-1-tj@kernel.org> Sender: linux-block-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-block@vger.kernel.org Separate out wb_get_lookup() which doesn't try to create one if there isn't already one from wb_get_create(). This will be used by later patches. Signed-off-by: Tejun Heo Reviewed-by: Jan Kara --- include/linux/backing-dev.h | 2 ++ mm/backing-dev.c | 55 +++++++++++++++++++++++++------------ 2 files changed, 39 insertions(+), 18 deletions(-) diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 84cdcfbc763f..97967ce06de3 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -230,6 +230,8 @@ static inline int bdi_sched_wait(void *word) struct bdi_writeback_congested * wb_congested_get_create(struct backing_dev_info *bdi, int blkcg_id, gfp_t gfp); void wb_congested_put(struct bdi_writeback_congested *congested); +struct bdi_writeback *wb_get_lookup(struct backing_dev_info *bdi, + struct cgroup_subsys_state *memcg_css); struct bdi_writeback *wb_get_create(struct backing_dev_info *bdi, struct cgroup_subsys_state *memcg_css, gfp_t gfp); diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 612aa7c5ddbd..d9daa3e422d0 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -618,13 +618,12 @@ static int cgwb_create(struct backing_dev_info *bdi, } /** - * wb_get_create - get wb for a given memcg, create if necessary + * wb_get_lookup - get wb for a given memcg * @bdi: target bdi * @memcg_css: cgroup_subsys_state of the target memcg (must have positive ref) - * @gfp: allocation mask to use * - * Try to get the wb for @memcg_css on @bdi. If it doesn't exist, try to - * create one. The returned wb has its refcount incremented. + * Try to get the wb for @memcg_css on @bdi. The returned wb has its + * refcount incremented. * * This function uses css_get() on @memcg_css and thus expects its refcnt * to be positive on invocation. IOW, rcu_read_lock() protection on @@ -641,6 +640,39 @@ static int cgwb_create(struct backing_dev_info *bdi, * each lookup. On mismatch, the existing wb is discarded and a new one is * created. */ +struct bdi_writeback *wb_get_lookup(struct backing_dev_info *bdi, + struct cgroup_subsys_state *memcg_css) +{ + struct bdi_writeback *wb; + + if (!memcg_css->parent) + return &bdi->wb; + + rcu_read_lock(); + wb = radix_tree_lookup(&bdi->cgwb_tree, memcg_css->id); + if (wb) { + struct cgroup_subsys_state *blkcg_css; + + /* see whether the blkcg association has changed */ + blkcg_css = cgroup_get_e_css(memcg_css->cgroup, &io_cgrp_subsys); + if (unlikely(wb->blkcg_css != blkcg_css || !wb_tryget(wb))) + wb = NULL; + css_put(blkcg_css); + } + rcu_read_unlock(); + + return wb; +} + +/** + * wb_get_create - get wb for a given memcg, create if necessary + * @bdi: target bdi + * @memcg_css: cgroup_subsys_state of the target memcg (must have positive ref) + * @gfp: allocation mask to use + * + * Try to get the wb for @memcg_css on @bdi. If it doesn't exist, try to + * create one. See wb_get_lookup() for more details. + */ struct bdi_writeback *wb_get_create(struct backing_dev_info *bdi, struct cgroup_subsys_state *memcg_css, gfp_t gfp) @@ -653,20 +685,7 @@ struct bdi_writeback *wb_get_create(struct backing_dev_info *bdi, return &bdi->wb; do { - rcu_read_lock(); - wb = radix_tree_lookup(&bdi->cgwb_tree, memcg_css->id); - if (wb) { - struct cgroup_subsys_state *blkcg_css; - - /* see whether the blkcg association has changed */ - blkcg_css = cgroup_get_e_css(memcg_css->cgroup, - &io_cgrp_subsys); - if (unlikely(wb->blkcg_css != blkcg_css || - !wb_tryget(wb))) - wb = NULL; - css_put(blkcg_css); - } - rcu_read_unlock(); + wb = wb_get_lookup(bdi, memcg_css); } while (!wb && !cgwb_create(bdi, memcg_css, gfp)); return wb; From patchwork Mon Aug 26 16:06:55 2019 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Tejun Heo X-Patchwork-Id: 11115007 Return-Path: Received: from mail.kernel.org (pdx-korg-mail-1.web.codeaurora.org [172.30.200.123]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id E97111800 for ; Mon, 26 Aug 2019 16:07:28 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by mail.kernel.org (Postfix) with ESMTP id C7F242173E for ; Mon, 26 Aug 2019 16:07:28 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=default; t=1566835648; bh=2OpxsVIxbXRnTlOxFICabZyuHeHsnYorJgAjEaLfZ2A=; h=From:To:Cc:Subject:Date:In-Reply-To:References:List-ID:From; b=Uv4XLAi4w/U0aNm2+YvBM2NC4Q56ZDgt6xvi4CivbAK9LdEe4hD4+6rB+MYQW2+Lg fda1SnHbPKUF1xetG3XrfuKAbNcDNCAag/RhsZTTrDaw0GAmNCQwZ63d375GzBdufy VdNzUIe4Jl1lTlgGJzCVWgjI+Jr8eru10V9gJwqg= Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1732680AbfHZQHP (ORCPT ); Mon, 26 Aug 2019 12:07:15 -0400 Received: from mail-qt1-f196.google.com ([209.85.160.196]:38977 "EHLO mail-qt1-f196.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1732660AbfHZQHO (ORCPT ); Mon, 26 Aug 2019 12:07:14 -0400 Received: by mail-qt1-f196.google.com with SMTP id l9so18371360qtu.6; Mon, 26 Aug 2019 09:07:13 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20161025; h=sender:from:to:cc:subject:date:message-id:in-reply-to:references; bh=E6MTfC4z3G0quoIF3DBw3b87rQV2WqMBkOF2p8Csnt4=; b=f7PWgdQaNS08y3O69h2TR6wz4T9l5sgzCskuEu75Rl4PPIoqtP1eKAL8MIWvGgBGtD b9nHdxjt/X7Yhwz4de8X2WBOiT4ZepZsWVsoCYdmY2fMXZfNCQehm+t0G3Ku1Ww+4huv PQ6z8migaaxzUVn9akM/4OyyWFicteYTGNjr2o9iivqYNfvwcZBbtk9hiqePLSyjKXxt 0RoWxaEApyGfC0uS3sh3e33KjgJQNMv299LqP+PaH6YtTg+QfOuubHX1AmqbNWUaATVV gLgNdO4IRMKOeIBRyMaFmxRomthURawpH6qAf1+ZHXC5o5v4K5s/VBLoljkuFuy5JFa0 OhGA== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:sender:from:to:cc:subject:date:message-id :in-reply-to:references; bh=E6MTfC4z3G0quoIF3DBw3b87rQV2WqMBkOF2p8Csnt4=; b=Hw3arEJfQ5aQlKBAoP5REXoYtB+NbVM++wFd6h1iqTTgE5qpUDvfleoDoxo27qDOKr Nz4UuR+U61aTOAZPE8vpVJfvgobiWMEJzWUwc/SvmVxxvmpNIu6HN6+l5qEJygOsx/0u beFT8VWMcsNy6owYwxikAt1baNoT/wYFI9bxn8NTYpdgwUG3Kb0hIA9U1rlXNEqdAKgE /mjuG9vetNkLFQTnXiovjj19GHylASB/wKazS3nx7USeI6G2bwlzE9FYltuSCk44xoRB uUWK3pnBr58MEiMEfPMjDePZ6fX45b16ddZvoHme5b6VpXorRCyj465SNvUxpL/nobPW e0Dg== X-Gm-Message-State: APjAAAWyHT73xvIKcku3fORdFedmAZI0p3bysYQeFxfFCefbni+X26cv Chg+Qrzo1Eik3C97TPN1k60= X-Google-Smtp-Source: APXvYqyW96+ohk8RXKdmfLCDzQI/qpRQjuN30ZN6OCty725+J7I96Alv2wMPQnmck7YKVxCLnF1bgg== X-Received: by 2002:ad4:4752:: with SMTP id c18mr16324758qvx.69.1566835632574; Mon, 26 Aug 2019 09:07:12 -0700 (PDT) Received: from localhost ([2620:10d:c091:500::d081]) by smtp.gmail.com with ESMTPSA id t5sm6637934qkt.93.2019.08.26.09.07.11 (version=TLS1_2 cipher=ECDHE-RSA-AES128-GCM-SHA256 bits=128/128); Mon, 26 Aug 2019 09:07:11 -0700 (PDT) From: Tejun Heo To: axboe@kernel.dk, jack@suse.cz, hannes@cmpxchg.org, mhocko@kernel.org, vdavydov.dev@gmail.com Cc: cgroups@vger.kernel.org, linux-mm@kvack.org, linux-block@vger.kernel.org, linux-kernel@vger.kernel.org, kernel-team@fb.com, guro@fb.com, akpm@linux-foundation.org, Tejun Heo Subject: [PATCH 4/5] writeback, memcg: Implement cgroup_writeback_by_id() Date: Mon, 26 Aug 2019 09:06:55 -0700 Message-Id: <20190826160656.870307-5-tj@kernel.org> X-Mailer: git-send-email 2.17.1 In-Reply-To: <20190826160656.870307-1-tj@kernel.org> References: <20190826160656.870307-1-tj@kernel.org> Sender: linux-block-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-block@vger.kernel.org Implement cgroup_writeback_by_id() which initiates cgroup writeback from bdi and memcg IDs. This will be used by memcg foreign inode flushing. v2: Use wb_get_lookup() instead of wb_get_create() to avoid creating spurious wbs. v3: Interpret 0 @nr as 1.25 * nr_dirty to implement best-effort flushing while avoding possible livelocks. Signed-off-by: Tejun Heo Reviewed-by: Jan Kara --- fs/fs-writeback.c | 83 +++++++++++++++++++++++++++++++++++++++ include/linux/writeback.h | 2 + 2 files changed, 85 insertions(+) diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 9442f1fd6460..658dc16c9e6d 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -891,6 +891,89 @@ static void bdi_split_work_to_wbs(struct backing_dev_info *bdi, wb_put(last_wb); } +/** + * cgroup_writeback_by_id - initiate cgroup writeback from bdi and memcg IDs + * @bdi_id: target bdi id + * @memcg_id: target memcg css id + * @nr_pages: number of pages to write, 0 for best-effort dirty flushing + * @reason: reason why some writeback work initiated + * @done: target wb_completion + * + * Initiate flush of the bdi_writeback identified by @bdi_id and @memcg_id + * with the specified parameters. + */ +int cgroup_writeback_by_id(u64 bdi_id, int memcg_id, unsigned long nr, + enum wb_reason reason, struct wb_completion *done) +{ + struct backing_dev_info *bdi; + struct cgroup_subsys_state *memcg_css; + struct bdi_writeback *wb; + struct wb_writeback_work *work; + int ret; + + /* lookup bdi and memcg */ + bdi = bdi_get_by_id(bdi_id); + if (!bdi) + return -ENOENT; + + rcu_read_lock(); + memcg_css = css_from_id(memcg_id, &memory_cgrp_subsys); + if (memcg_css && !css_tryget(memcg_css)) + memcg_css = NULL; + rcu_read_unlock(); + if (!memcg_css) { + ret = -ENOENT; + goto out_bdi_put; + } + + /* + * And find the associated wb. If the wb isn't there already + * there's nothing to flush, don't create one. + */ + wb = wb_get_lookup(bdi, memcg_css); + if (!wb) { + ret = -ENOENT; + goto out_css_put; + } + + /* + * If @nr is zero, the caller is attempting to write out most of + * the currently dirty pages. Let's take the current dirty page + * count and inflate it by 25% which should be large enough to + * flush out most dirty pages while avoiding getting livelocked by + * concurrent dirtiers. + */ + if (!nr) { + unsigned long filepages, headroom, dirty, writeback; + + mem_cgroup_wb_stats(wb, &filepages, &headroom, &dirty, + &writeback); + nr = dirty * 10 / 8; + } + + /* issue the writeback work */ + work = kzalloc(sizeof(*work), GFP_NOWAIT | __GFP_NOWARN); + if (work) { + work->nr_pages = nr; + work->sync_mode = WB_SYNC_NONE; + work->range_cyclic = 1; + work->reason = reason; + work->done = done; + work->auto_free = 1; + wb_queue_work(wb, work); + ret = 0; + } else { + ret = -ENOMEM; + } + + wb_put(wb); +out_css_put: + css_put(memcg_css); +out_bdi_put: + bdi_put(bdi); + return ret; +} + /** * cgroup_writeback_umount - flush inode wb switches for umount * diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 8945aac31392..a19d845dd7eb 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -217,6 +217,8 @@ void wbc_attach_and_unlock_inode(struct writeback_control *wbc, void wbc_detach_inode(struct writeback_control *wbc); void wbc_account_cgroup_owner(struct writeback_control *wbc, struct page *page, size_t bytes); +int cgroup_writeback_by_id(u64 bdi_id, int memcg_id, unsigned long nr_pages, + enum wb_reason reason, struct wb_completion *done); void cgroup_writeback_umount(void); /** From patchwork Mon Aug 26 16:06:56 2019 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Tejun Heo X-Patchwork-Id: 11115005 Return-Path: Received: from mail.kernel.org (pdx-korg-mail-1.web.codeaurora.org [172.30.200.123]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id 0C5C11395 for ; Mon, 26 Aug 2019 16:07:28 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by mail.kernel.org (Postfix) with ESMTP id C218F21881 for ; Mon, 26 Aug 2019 16:07:27 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=default; t=1566835647; bh=8YdbcHdvSVKWt/B0xp4xlCRpgwxWio9UcnI2k9j5S3k=; h=From:To:Cc:Subject:Date:In-Reply-To:References:List-ID:From; b=Zx3Sbu9eSppQHd4P4AF0dlVnJG71hKGCIlHFfEax8bOEvNUFSPIVOwM5EBGoFKcdt 1UAhjau0fnthe2fvxo8fJ45fs8P4UwhxIfAzhIpd+6t/Ii4s1O4yrnlCVbkVJ3kvKe HjgEMtaMSysE3Wsubig35JrmxWuyaZKS887PguY0= Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1732700AbfHZQHR (ORCPT ); Mon, 26 Aug 2019 12:07:17 -0400 Received: from mail-qt1-f194.google.com ([209.85.160.194]:41585 "EHLO mail-qt1-f194.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1732672AbfHZQHQ (ORCPT ); Mon, 26 Aug 2019 12:07:16 -0400 Received: by mail-qt1-f194.google.com with SMTP id i4so18346811qtj.8; Mon, 26 Aug 2019 09:07:15 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20161025; h=sender:from:to:cc:subject:date:message-id:in-reply-to:references; bh=P2T/Id7H98NPxI/zlZfODmmmsoETa1Oiptdb28tCBNM=; b=PsT/XOrmLiw3ws7kz0Xbpm3bYDmBCvqDttzevHIuMFhUJsX6d0YWfdEkaL3siqA3S2 Ra12wfcA98qt1G2FzFG5zr/ydgY9ffvjaI9tKcGou1jAw7i8QCm9NaGsvlNr6UDW5aQQ VviuhQYJS0F8i7RImys70rLnpxOWODTfAMZYGteRaqpqw0LdBEO5ZukPhjsB9zsJ8tgB n0B9a0B3az/fA82eEu+YoWxOmZtSNJAAH1ApKoQWxfyEU4bLJtMFfM+4gACb5ie/scl2 HogBUZ6jUu9HFrToSedWqcuIS6sKueBE0s2bKhTV8MeU9oSM3JUsXjkuz+uu2WPY+qUA ZFXQ== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:sender:from:to:cc:subject:date:message-id :in-reply-to:references; bh=P2T/Id7H98NPxI/zlZfODmmmsoETa1Oiptdb28tCBNM=; b=FOnQRmyqvSiXmkNdfGfRDMhjVqx05+ZHBMle7MAvN+SXelPa/IuS4ehZoVetl/AwJ/ 0ZZcUpYqpxfyosE4A2cveCMgnOaHsb73ZJnasjlFuAw6lWJCcInh7pKs5fulD4kfrL9n 5yg1jgxpwrWkjamFTcz2SCn8P0btwrE7Er0cQ5RqncWoHMuqTOB5rJkutVwiAfd2GoFH kbJJXuDpC6ZL/77cjQI/vMnmHjGafnc6Gx4aUNflOv7+5hyuRTy/ewcggeKe7M6iAyQ8 XiX2e8ZXBt0hNtjdpz2ySDYhoVzsLcX+jF0mz/0Gjr/hfdC6SB61RtXLwYqmAlhoeVaL pXqA== X-Gm-Message-State: APjAAAVpqVtZYtEJJ7e5xifXLPBX1+sMSY85rMg9552drRRZVfnqUW9Q r8yeVPq1B5TIil0hhyEaltk= X-Google-Smtp-Source: APXvYqyYVShATPBrqxyY5iobSwQI2qxjIz5V2Uz3BuQGZY7a6ryn+bvgcqDoY3PprObD0QetQV7JkA== X-Received: by 2002:ac8:5491:: with SMTP id h17mr17958515qtq.227.1566835634583; Mon, 26 Aug 2019 09:07:14 -0700 (PDT) Received: from localhost ([2620:10d:c091:500::d081]) by smtp.gmail.com with ESMTPSA id k12sm11558qkj.4.2019.08.26.09.07.13 (version=TLS1_2 cipher=ECDHE-RSA-AES128-GCM-SHA256 bits=128/128); Mon, 26 Aug 2019 09:07:14 -0700 (PDT) From: Tejun Heo To: axboe@kernel.dk, jack@suse.cz, hannes@cmpxchg.org, mhocko@kernel.org, vdavydov.dev@gmail.com Cc: cgroups@vger.kernel.org, linux-mm@kvack.org, linux-block@vger.kernel.org, linux-kernel@vger.kernel.org, kernel-team@fb.com, guro@fb.com, akpm@linux-foundation.org, Tejun Heo Subject: [PATCH 5/5] writeback, memcg: Implement foreign dirty flushing Date: Mon, 26 Aug 2019 09:06:56 -0700 Message-Id: <20190826160656.870307-6-tj@kernel.org> X-Mailer: git-send-email 2.17.1 In-Reply-To: <20190826160656.870307-1-tj@kernel.org> References: <20190826160656.870307-1-tj@kernel.org> Sender: linux-block-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-block@vger.kernel.org There's an inherent mismatch between memcg and writeback. The former trackes ownership per-page while the latter per-inode. This was a deliberate design decision because honoring per-page ownership in the writeback path is complicated, may lead to higher CPU and IO overheads and deemed unnecessary given that write-sharing an inode across different cgroups isn't a common use-case. Combined with inode majority-writer ownership switching, this works well enough in most cases but there are some pathological cases. For example, let's say there are two cgroups A and B which keep writing to different but confined parts of the same inode. B owns the inode and A's memory is limited far below B's. A's dirty ratio can rise enough to trigger balance_dirty_pages() sleeps but B's can be low enough to avoid triggering background writeback. A will be slowed down without a way to make writeback of the dirty pages happen. This patch implements foreign dirty recording and foreign mechanism so that when a memcg encounters a condition as above it can trigger flushes on bdi_writebacks which can clean its pages. Please see the comment on top of mem_cgroup_track_foreign_dirty_slowpath() for details. A reproducer follows. write-range.c:: #include #include #include #include #include static const char *usage = "write-range FILE START SIZE\n"; int main(int argc, char **argv) { int fd; unsigned long start, size, end, pos; char *endp; char buf[4096]; if (argc < 4) { fprintf(stderr, usage); return 1; } fd = open(argv[1], O_WRONLY); if (fd < 0) { perror("open"); return 1; } start = strtoul(argv[2], &endp, 0); if (*endp != '\0') { fprintf(stderr, usage); return 1; } size = strtoul(argv[3], &endp, 0); if (*endp != '\0') { fprintf(stderr, usage); return 1; } end = start + size; while (1) { for (pos = start; pos < end; ) { long bread, bwritten = 0; if (lseek(fd, pos, SEEK_SET) < 0) { perror("lseek"); return 1; } bread = read(0, buf, sizeof(buf) < end - pos ? sizeof(buf) : end - pos); if (bread < 0) { perror("read"); return 1; } if (bread == 0) return 0; while (bwritten < bread) { long this; this = write(fd, buf + bwritten, bread - bwritten); if (this < 0) { perror("write"); return 1; } bwritten += this; pos += bwritten; } } } } repro.sh:: #!/bin/bash set -e set -x sysctl -w vm.dirty_expire_centisecs=300000 sysctl -w vm.dirty_writeback_centisecs=300000 sysctl -w vm.dirtytime_expire_seconds=300000 echo 3 > /proc/sys/vm/drop_caches TEST=/sys/fs/cgroup/test A=$TEST/A B=$TEST/B mkdir -p $A $B echo "+memory +io" > $TEST/cgroup.subtree_control echo $((1<<30)) > $A/memory.high echo $((32<<30)) > $B/memory.high rm -f testfile touch testfile fallocate -l 4G testfile echo "Starting B" (echo $BASHPID > $B/cgroup.procs pv -q --rate-limit 70M < /dev/urandom | ./write-range testfile $((2<<30)) $((2<<30))) & echo "Waiting 10s to ensure B claims the testfile inode" sleep 5 sync sleep 5 sync echo "Starting A" (echo $BASHPID > $A/cgroup.procs pv < /dev/urandom | ./write-range testfile 0 $((2<<30))) v2: Added comments explaining why the specific intervals are being used. v3: Use 0 @nr when calling cgroup_writeback_by_id() to use best-effort flushing while avoding possible livelocks. v4: Use get_jiffies_64() and time_before/after64() instead of raw jiffies_64 and arthimetic comparisons as suggested by Jan. Signed-off-by: Tejun Heo Reviewed-by: Jan Kara --- include/linux/backing-dev-defs.h | 1 + include/linux/memcontrol.h | 39 +++++++++ mm/memcontrol.c | 134 +++++++++++++++++++++++++++++++ mm/page-writeback.c | 4 + 4 files changed, 178 insertions(+) diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h index 1075f2552cfc..4fc87dee005a 100644 --- a/include/linux/backing-dev-defs.h +++ b/include/linux/backing-dev-defs.h @@ -63,6 +63,7 @@ enum wb_reason { * so it has a mismatch name. */ WB_REASON_FORKER_THREAD, + WB_REASON_FOREIGN_FLUSH, WB_REASON_MAX, }; diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 2cd4359cb38c..ad8f1a397ae4 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -183,6 +183,23 @@ struct memcg_padding { #define MEMCG_PADDING(name) #endif +/* + * Remember four most recent foreign writebacks with dirty pages in this + * cgroup. Inode sharing is expected to be uncommon and, even if we miss + * one in a given round, we're likely to catch it later if it keeps + * foreign-dirtying, so a fairly low count should be enough. + * + * See mem_cgroup_track_foreign_dirty_slowpath() for details. + */ +#define MEMCG_CGWB_FRN_CNT 4 + +struct memcg_cgwb_frn { + u64 bdi_id; /* bdi->id of the foreign inode */ + int memcg_id; /* memcg->css.id of foreign inode */ + u64 at; /* jiffies_64 at the time of dirtying */ + struct wb_completion done; /* tracks in-flight foreign writebacks */ +}; + /* * The memory controller data structure. The memory controller controls both * page cache and RSS per cgroup. We would eventually like to provide @@ -307,6 +324,7 @@ struct mem_cgroup { #ifdef CONFIG_CGROUP_WRITEBACK struct list_head cgwb_list; struct wb_domain cgwb_domain; + struct memcg_cgwb_frn cgwb_frn[MEMCG_CGWB_FRN_CNT]; #endif /* List of events which userspace want to receive */ @@ -1237,6 +1255,18 @@ void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages, unsigned long *pheadroom, unsigned long *pdirty, unsigned long *pwriteback); +void mem_cgroup_track_foreign_dirty_slowpath(struct page *page, + struct bdi_writeback *wb); + +static inline void mem_cgroup_track_foreign_dirty(struct page *page, + struct bdi_writeback *wb) +{ + if (unlikely(&page->mem_cgroup->css != wb->memcg_css)) + mem_cgroup_track_foreign_dirty_slowpath(page, wb); +} + +void mem_cgroup_flush_foreign(struct bdi_writeback *wb); + #else /* CONFIG_CGROUP_WRITEBACK */ static inline struct wb_domain *mem_cgroup_wb_domain(struct bdi_writeback *wb) @@ -1252,6 +1282,15 @@ static inline void mem_cgroup_wb_stats(struct bdi_writeback *wb, { } +static inline void mem_cgroup_track_foreign_dirty(struct page *page, + struct bdi_writeback *wb) +{ +} + +static inline void mem_cgroup_flush_foreign(struct bdi_writeback *wb) +{ +} + #endif /* CONFIG_CGROUP_WRITEBACK */ struct sock; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 26e2999af608..eb626a290d93 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -87,6 +87,10 @@ int do_swap_account __read_mostly; #define do_swap_account 0 #endif +#ifdef CONFIG_CGROUP_WRITEBACK +static DECLARE_WAIT_QUEUE_HEAD(memcg_cgwb_frn_waitq); +#endif + /* Whether legacy memory+swap accounting is active */ static bool do_memsw_account(void) { @@ -4238,6 +4242,127 @@ void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages, } } +/* + * Foreign dirty flushing + * + * There's an inherent mismatch between memcg and writeback. The former + * trackes ownership per-page while the latter per-inode. This was a + * deliberate design decision because honoring per-page ownership in the + * writeback path is complicated, may lead to higher CPU and IO overheads + * and deemed unnecessary given that write-sharing an inode across + * different cgroups isn't a common use-case. + * + * Combined with inode majority-writer ownership switching, this works well + * enough in most cases but there are some pathological cases. For + * example, let's say there are two cgroups A and B which keep writing to + * different but confined parts of the same inode. B owns the inode and + * A's memory is limited far below B's. A's dirty ratio can rise enough to + * trigger balance_dirty_pages() sleeps but B's can be low enough to avoid + * triggering background writeback. A will be slowed down without a way to + * make writeback of the dirty pages happen. + * + * Conditions like the above can lead to a cgroup getting repatedly and + * severely throttled after making some progress after each + * dirty_expire_interval while the underyling IO device is almost + * completely idle. + * + * Solving this problem completely requires matching the ownership tracking + * granularities between memcg and writeback in either direction. However, + * the more egregious behaviors can be avoided by simply remembering the + * most recent foreign dirtying events and initiating remote flushes on + * them when local writeback isn't enough to keep the memory clean enough. + * + * The following two functions implement such mechanism. When a foreign + * page - a page whose memcg and writeback ownerships don't match - is + * dirtied, mem_cgroup_track_foreign_dirty() records the inode owning + * bdi_writeback on the page owning memcg. When balance_dirty_pages() + * decides that the memcg needs to sleep due to high dirty ratio, it calls + * mem_cgroup_flush_foreign() which queues writeback on the recorded + * foreign bdi_writebacks which haven't expired. Both the numbers of + * recorded bdi_writebacks and concurrent in-flight foreign writebacks are + * limited to MEMCG_CGWB_FRN_CNT. + * + * The mechanism only remembers IDs and doesn't hold any object references. + * As being wrong occasionally doesn't matter, updates and accesses to the + * records are lockless and racy. + */ +void mem_cgroup_track_foreign_dirty_slowpath(struct page *page, + struct bdi_writeback *wb) +{ + struct mem_cgroup *memcg = page->mem_cgroup; + struct memcg_cgwb_frn *frn; + u64 now = get_jiffies_64(); + u64 oldest_at = now; + int oldest = -1; + int i; + + /* + * Pick the slot to use. If there is already a slot for @wb, keep + * using it. If not replace the oldest one which isn't being + * written out. + */ + for (i = 0; i < MEMCG_CGWB_FRN_CNT; i++) { + frn = &memcg->cgwb_frn[i]; + if (frn->bdi_id == wb->bdi->id && + frn->memcg_id == wb->memcg_css->id) + break; + if (time_before64(frn->at, oldest_at) && + atomic_read(&frn->done.cnt) == 1) { + oldest = i; + oldest_at = frn->at; + } + } + + if (i < MEMCG_CGWB_FRN_CNT) { + /* + * Re-using an existing one. Update timestamp lazily to + * avoid making the cacheline hot. We want them to be + * reasonably up-to-date and significantly shorter than + * dirty_expire_interval as that's what expires the record. + * Use the shorter of 1s and dirty_expire_interval / 8. + */ + unsigned long update_intv = + min_t(unsigned long, HZ, + msecs_to_jiffies(dirty_expire_interval * 10) / 8); + + if (time_before64(frn->at, now - update_intv)) + frn->at = now; + } else if (oldest >= 0) { + /* replace the oldest free one */ + frn = &memcg->cgwb_frn[oldest]; + frn->bdi_id = wb->bdi->id; + frn->memcg_id = wb->memcg_css->id; + frn->at = now; + } +} + +/* issue foreign writeback flushes for recorded foreign dirtying events */ +void mem_cgroup_flush_foreign(struct bdi_writeback *wb) +{ + struct mem_cgroup *memcg = mem_cgroup_from_css(wb->memcg_css); + unsigned long intv = msecs_to_jiffies(dirty_expire_interval * 10); + u64 now = jiffies_64; + int i; + + for (i = 0; i < MEMCG_CGWB_FRN_CNT; i++) { + struct memcg_cgwb_frn *frn = &memcg->cgwb_frn[i]; + + /* + * If the record is older than dirty_expire_interval, + * writeback on it has already started. No need to kick it + * off again. Also, don't start a new one if there's + * already one in flight. + */ + if (time_after64(frn->at, now - intv) && + atomic_read(&frn->done.cnt) == 1) { + frn->at = 0; + cgroup_writeback_by_id(frn->bdi_id, frn->memcg_id, 0, + WB_REASON_FOREIGN_FLUSH, + &frn->done); + } + } +} + #else /* CONFIG_CGROUP_WRITEBACK */ static int memcg_wb_domain_init(struct mem_cgroup *memcg, gfp_t gfp) @@ -4760,6 +4885,7 @@ static struct mem_cgroup *mem_cgroup_alloc(void) struct mem_cgroup *memcg; unsigned int size; int node; + int __maybe_unused i; size = sizeof(struct mem_cgroup); size += nr_node_ids * sizeof(struct mem_cgroup_per_node *); @@ -4803,6 +4929,9 @@ static struct mem_cgroup *mem_cgroup_alloc(void) #endif #ifdef CONFIG_CGROUP_WRITEBACK INIT_LIST_HEAD(&memcg->cgwb_list); + for (i = 0; i < MEMCG_CGWB_FRN_CNT; i++) + memcg->cgwb_frn[i].done = + __WB_COMPLETION_INIT(&memcg_cgwb_frn_waitq); #endif idr_replace(&mem_cgroup_idr, memcg, memcg->id.id); return memcg; @@ -4932,7 +5061,12 @@ static void mem_cgroup_css_released(struct cgroup_subsys_state *css) static void mem_cgroup_css_free(struct cgroup_subsys_state *css) { struct mem_cgroup *memcg = mem_cgroup_from_css(css); + int __maybe_unused i; +#ifdef CONFIG_CGROUP_WRITEBACK + for (i = 0; i < MEMCG_CGWB_FRN_CNT; i++) + wb_wait_for_completion(&memcg->cgwb_frn[i].done); +#endif if (cgroup_subsys_on_dfl(memory_cgrp_subsys) && !cgroup_memory_nosocket) static_branch_dec(&memcg_sockets_enabled_key); diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 1804f64ff43c..50055d2e4ea8 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -1667,6 +1667,8 @@ static void balance_dirty_pages(struct bdi_writeback *wb, if (unlikely(!writeback_in_progress(wb))) wb_start_background_writeback(wb); + mem_cgroup_flush_foreign(wb); + /* * Calculate global domain's pos_ratio and select the * global dtc by default. @@ -2427,6 +2429,8 @@ void account_page_dirtied(struct page *page, struct address_space *mapping) task_io_account_write(PAGE_SIZE); current->nr_dirtied++; this_cpu_inc(bdp_ratelimits); + + mem_cgroup_track_foreign_dirty(page, wb); } }