From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-18.7 required=3.0 tests=BAYES_00,DKIM_SIGNED, DKIM_VALID,DKIM_VALID_AU,HEADER_FROM_DIFFERENT_DOMAINS,INCLUDES_CR_TRAILER, INCLUDES_PATCH,MAILING_LIST_MULTI,SPF_HELO_NONE,SPF_PASS,URIBL_BLOCKED, USER_AGENT_GIT autolearn=unavailable autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 930D3C2BB9A for ; Thu, 10 Dec 2020 16:32:57 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 507C523DB3 for ; Thu, 10 Dec 2020 16:32:57 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S2389221AbgLJQEu (ORCPT ); Thu, 10 Dec 2020 11:04:50 -0500 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:47086 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S2387918AbgLJQEl (ORCPT ); Thu, 10 Dec 2020 11:04:41 -0500 Received: from mail-wm1-x344.google.com (mail-wm1-x344.google.com [IPv6:2a00:1450:4864:20::344]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 44270C0613D6 for ; Thu, 10 Dec 2020 08:04:01 -0800 (PST) Received: by mail-wm1-x344.google.com with SMTP id v14so5104285wml.1 for ; Thu, 10 Dec 2020 08:04:01 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google; h=from:to:cc:subject:date:message-id:mime-version :content-transfer-encoding; bh=Hh8PxAhln6PiY96SsIvH4Jb4HnhnMqeMZCUSPG8j+s0=; b=DLZ928rqaeb/lsTz6CetglcHdGdiZkSKcNbL+S0gXsaCg1O7UdHDnhC/o64G2rrVYd K3heFF0KQl/eEspEWJJvlkIdqSFxbIeRzDTpk9PVoMOR24vo0uTw58xd71nL3srbmzv1 8TJOoxrvfbWu0J8wZGvX2E/JiRZTdgLa+jhq71FCJoDLykcycr246iElt6AiPtk6yLZ2 5KPwJ90ogvnpan9yngc2YYi6VIr1+OESuqABEZeVIXtiUU3fLkqGq1dbTmGC/B2cUD7x s+YfUc5Kt1KAut4BzM/AVJJdR8UXi7j2vuXku9o2jBm5c+GCdiKuMfzfKqk+s5XeNRUh C27A== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:from:to:cc:subject:date:message-id:mime-version :content-transfer-encoding; bh=Hh8PxAhln6PiY96SsIvH4Jb4HnhnMqeMZCUSPG8j+s0=; b=SecvmZ0n7VyRC8qLEi5iRMf/yqzjWLfKidrxDFqiz2rDdaHDpkLDtUz9KlDh5T1KPg AdmqzaxC7/ulKV9Zk+dOwxL2zmNEIHSlrMmZ6htv+BVnJ4KfnxNVdVp7u/sqyYE0mT3Z rgYLca9tU6eEnvFEKd6qyNUMfNXoCFMUlL/pzFwS+oTN3FnumE4ya2QjZPRVed4xVvnL eHKCenC4r0CX2h9XG5sYbB3tYy/6DLKYKsd5ZEYGDEeyJG/XCTHjX6jfI4NNItT64OdC S4Wrhe1/v4mGD88azp23ZKd7jLUz6nzjxWC7zATYWSSoiMbOYf+HOTUyvOq++gU2EZuT eHuA== X-Gm-Message-State: AOAM5301uscbF1g8G28QNPgkhvcStB9LM/ObDa5W8VJir2rsT1P3zoyD +FvgEcHY03KKWMh1KNEqZ4X67g== X-Google-Smtp-Source: ABdhPJwlL+iccy5h+6abVXgzPBfF873S9rja/ooxjbuBYTgwfozKKRBiUTpSGG43GvEvWnRDaZvTIw== X-Received: by 2002:a1c:e10b:: with SMTP id y11mr9199667wmg.65.1607616239854; Thu, 10 Dec 2020 08:03:59 -0800 (PST) Received: from localhost.localdomain ([212.45.67.2]) by smtp.googlemail.com with ESMTPSA id d17sm9274768wro.62.2020.12.10.08.03.58 (version=TLS1_2 cipher=ECDHE-ECDSA-AES128-GCM-SHA256 bits=128/128); Thu, 10 Dec 2020 08:03:59 -0800 (PST) From: Georgi Djakov To: akpm@linux-foundation.org Cc: linux-mm@kvack.org, vbabka@suse.cz, corbet@lwn.net, linux-doc@vger.kernel.org, linux-kernel@vger.kernel.org, lmark@codeaurora.org, georgi.djakov@linaro.org Subject: [PATCH v3] mm/page_owner: Record timestamp and pid Date: Thu, 10 Dec 2020 18:03:57 +0200 Message-Id: <20201210160357.27779-1-georgi.djakov@linaro.org> X-Mailer: git-send-email 2.29.0 MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Precedence: bulk List-ID: X-Mailing-List: linux-doc@vger.kernel.org From: Liam Mark Collect the time for each allocation recorded in page owner so that allocation "surges" can be measured. Record the pid for each allocation recorded in page owner so that the source of allocation "surges" can be better identified. The above is very useful when doing memory analysis. On a crash for example, we can get this information from kdump (or ramdump) and parse it to figure out memory allocation problems. Please note that on x86_64 this increases the size of struct page_owner from 16 bytes to 32. Vlastimil: it's not a functionality intended for production, so unless somebody says they need to enable page_owner for debugging and this increase prevents them from fitting into available memory, let's not complicate things with making this optional. Signed-off-by: Liam Mark Signed-off-by: Georgi Djakov Acked-by: Vlastimil Babka Cc: Jonathan Corbet --- v3: - Fix the warnings in the documentation (reported in linux-next) and make Sphinx happy: Documentation/vm/page_owner.rst:44: WARNING: Literal block ends without a blank line; unexpected unindent. Documentation/vm/page_owner.rst:49: WARNING: Literal block ends without a blank line; unexpected unindent. v2: https://lore.kernel.org/r/20201209125153.10533-1-georgi.djakov@linaro.org - Improve the commit message (Andrew and Vlastimil) - Update page_owner.rst with more recent object size information (Andrew) - Use pid_t for the pid (Andrew) - Print the info also in __dump_page_owner() (Vlastimil) v1: https://lore.kernel.org/r/20201112184106.733-1-georgi.djakov@linaro.org Documentation/vm/page_owner.rst | 12 ++++++------ mm/page_owner.c | 17 +++++++++++++---- 2 files changed, 19 insertions(+), 10 deletions(-) diff --git a/Documentation/vm/page_owner.rst b/Documentation/vm/page_owner.rst index 02deac76673f..4e67c2e9bbed 100644 --- a/Documentation/vm/page_owner.rst +++ b/Documentation/vm/page_owner.rst @@ -41,17 +41,17 @@ size change due to this facility. - Without page owner:: text data bss dec hex filename - 40662 1493 644 42799 a72f mm/page_alloc.o + 48392 2333 644 51369 c8a9 mm/page_alloc.o - With page owner:: text data bss dec hex filename - 40892 1493 644 43029 a815 mm/page_alloc.o - 1427 24 8 1459 5b3 mm/page_ext.o - 2722 50 0 2772 ad4 mm/page_owner.o + 48800 2445 644 51889 cab1 mm/page_alloc.o + 6574 108 29 6711 1a37 mm/page_owner.o + 1025 8 8 1041 411 mm/page_ext.o -Although, roughly, 4 KB code is added in total, page_alloc.o increase by -230 bytes and only half of it is in hotpath. Building the kernel with +Although, roughly, 8 KB code is added in total, page_alloc.o increase by +520 bytes and less than half of it is in hotpath. Building the kernel with page owner and turning it on if needed would be great option to debug kernel memory problem. diff --git a/mm/page_owner.c b/mm/page_owner.c index b735a8eafcdb..af464bb7fbe7 100644 --- a/mm/page_owner.c +++ b/mm/page_owner.c @@ -10,6 +10,7 @@ #include #include #include +#include #include "internal.h" @@ -25,6 +26,8 @@ struct page_owner { gfp_t gfp_mask; depot_stack_handle_t handle; depot_stack_handle_t free_handle; + u64 ts_nsec; + pid_t pid; }; static bool page_owner_enabled = false; @@ -172,6 +175,8 @@ static inline void __set_page_owner_handle(struct page *page, page_owner->order = order; page_owner->gfp_mask = gfp_mask; page_owner->last_migrate_reason = -1; + page_owner->pid = current->pid; + page_owner->ts_nsec = local_clock(); __set_bit(PAGE_EXT_OWNER, &page_ext->flags); __set_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags); @@ -236,6 +241,8 @@ void __copy_page_owner(struct page *oldpage, struct page *newpage) new_page_owner->last_migrate_reason = old_page_owner->last_migrate_reason; new_page_owner->handle = old_page_owner->handle; + new_page_owner->pid = old_page_owner->pid; + new_page_owner->ts_nsec = old_page_owner->ts_nsec; /* * We don't clear the bit on the oldpage as it's going to be freed @@ -349,9 +356,10 @@ print_page_owner(char __user *buf, size_t count, unsigned long pfn, return -ENOMEM; ret = snprintf(kbuf, count, - "Page allocated via order %u, mask %#x(%pGg)\n", + "Page allocated via order %u, mask %#x(%pGg), pid %d, ts %llu ns\n", page_owner->order, page_owner->gfp_mask, - &page_owner->gfp_mask); + &page_owner->gfp_mask, page_owner->pid, + page_owner->ts_nsec); if (ret >= count) goto err; @@ -427,8 +435,9 @@ void __dump_page_owner(struct page *page) else pr_alert("page_owner tracks the page as freed\n"); - pr_alert("page last allocated via order %u, migratetype %s, gfp_mask %#x(%pGg)\n", - page_owner->order, migratetype_names[mt], gfp_mask, &gfp_mask); + pr_alert("page last allocated via order %u, migratetype %s, gfp_mask %#x(%pGg), pid %d, ts %llu\n", + page_owner->order, migratetype_names[mt], gfp_mask, &gfp_mask, + page_owner->pid, page_owner->ts_nsec); handle = READ_ONCE(page_owner->handle); if (!handle) {