From nobody Wed Dec 17 08:21:11 2025 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 795E4C7618E for ; Fri, 21 Apr 2023 10:15:01 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S231315AbjDUKO7 (ORCPT ); Fri, 21 Apr 2023 06:14:59 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:48690 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S231329AbjDUKOj (ORCPT ); Fri, 21 Apr 2023 06:14:39 -0400 Received: from smtp-out2.suse.de (smtp-out2.suse.de [195.135.220.29]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id CB320A5F0 for ; Fri, 21 Apr 2023 03:14:37 -0700 (PDT) Received: from imap2.suse-dmz.suse.de (imap2.suse-dmz.suse.de [192.168.254.74]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature ECDSA (P-521) server-digest SHA512) (No client certificate requested) by smtp-out2.suse.de (Postfix) with ESMTPS id 53B631FDDC; Fri, 21 Apr 2023 10:14:36 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=suse.de; s=susede2_rsa; t=1682072076; h=from:from:reply-to:date:date:message-id:message-id:to:to:cc:cc: mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=NhQ8pvDEDYdK4MH7I174Hpey5DF3W+He8Wm+uYrTkgw=; b=E5cBcBJ0NS1SCMaDeyEpm1IRLZaQHjgK1FAE4SYuJ40GAfoaJ6W70GfGcSsWIk3Xe1hfRe 3PR8N9XM2u1eZB8mD+cvlzlVt4WpBWIskHlztPK4Wi5JFJku1IHWSGEtjMYGHobusXWq96 vn0t7I0G5Y3PGrtKt1u1P76dOI/WrAM= DKIM-Signature: v=1; a=ed25519-sha256; c=relaxed/relaxed; d=suse.de; s=susede2_ed25519; t=1682072076; h=from:from:reply-to:date:date:message-id:message-id:to:to:cc:cc: mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=NhQ8pvDEDYdK4MH7I174Hpey5DF3W+He8Wm+uYrTkgw=; b=CWbSShbgBZJ0E617Q6QJQE0QaIJAUC+0i7cKB+O8UWP4cWLAVoqZkpEIGA61IUeWgdD4+D lQ5hqFH6RMS1NrDQ== Received: from imap2.suse-dmz.suse.de (imap2.suse-dmz.suse.de [192.168.254.74]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature ECDSA (P-521) server-digest SHA512) (No client certificate requested) by imap2.suse-dmz.suse.de (Postfix) with ESMTPS id 88D7A1390E; Fri, 21 Apr 2023 10:14:35 +0000 (UTC) Received: from dovecot-director2.suse.de ([192.168.254.65]) by imap2.suse-dmz.suse.de with ESMTPSA id 6KUrHgtiQmRNaAAAMHmgww (envelope-from ); Fri, 21 Apr 2023 10:14:35 +0000 From: Oscar Salvador To: Andrew Morton Cc: linux-kernel@vger.kernel.org, linux-mm@kvack.org, Michal Hocko , Vlastimil Babka , Eric Dumazet , Waiman Long , Suren Baghdasaryan , Marco Elver , Andrey Konovalov , Alexander Potapenko , Oscar Salvador Subject: [PATCH v4 1/3] lib/stackdepot: Add a refcount field in stack_record Date: Fri, 21 Apr 2023 12:14:13 +0200 Message-Id: <20230421101415.5734-2-osalvador@suse.de> X-Mailer: git-send-email 2.40.0 In-Reply-To: <20230421101415.5734-1-osalvador@suse.de> References: <20230421101415.5734-1-osalvador@suse.de> MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Type: text/plain; charset="utf-8" We want to filter out page_owner output and print only those stacks that have been repeated beyond a certain threshold. This gives us the chance to get rid of a lot of noise. In order to do that, we need to keep track of how many repeated stacks (for allocation) do we have, so we add a new refcount_t field in the stack_record struct. Note that this might increase the size of the struct for some architectures. E.g: x86_64 is not affected due to alignment, but x86 32bits might. The alternative would be to have some kind of struct like this: struct track_stacks { struct stack_record *stack; struct track_stacks *next; refcount_t stack_count; But ithat would imply to perform more allocations and glue everything together, which would make the code more complex, so I think that going with a new field in the struct stack_record is good enough. Note that on __set_page_owner_handle(), page_owner->handle is set, and on __reset_page_owner(), page_owner->free_handle is set. We are interested in page_owner->handle, so when __set_page_owner() gets called, we derive the stack_record struct from page_owner->handle, and we increment its refcount_t field; and when __reset_page_owner() gets called, we derive its stack_record from page_owner->handle() and we decrement its refcount_t field. Signed-off-by: Oscar Salvador --- include/linux/stackdepot.h | 8 ++++- lib/stackdepot.c | 72 ++++++++++++++++++++++++++++++++------ mm/kasan/common.c | 3 +- mm/page_owner.c | 13 ++++--- 4 files changed, 79 insertions(+), 17 deletions(-) diff --git a/include/linux/stackdepot.h b/include/linux/stackdepot.h index e58306783d8e..b94d33312839 100644 --- a/include/linux/stackdepot.h +++ b/include/linux/stackdepot.h @@ -93,7 +93,9 @@ static inline int stack_depot_early_init(void) { return 0= ; } */ depot_stack_handle_t __stack_depot_save(unsigned long *entries, unsigned int nr_entries, - gfp_t gfp_flags, bool can_alloc); + gfp_t gfp_flags, bool can_alloc, + bool counter); +void stack_depot_dec_count(depot_stack_handle_t handle); =20 /** * stack_depot_save - Save a stack trace to stack depot @@ -109,6 +111,10 @@ depot_stack_handle_t __stack_depot_save(unsigned long = *entries, */ depot_stack_handle_t stack_depot_save(unsigned long *entries, unsigned int nr_entries, gfp_t gfp_flags); +depot_stack_handle_t stack_depot_save_action(unsigned long *entries, + unsigned int nr_entries, + gfp_t gfp_flags, + bool counter); =20 /** * stack_depot_fetch - Fetch a stack trace from stack depot diff --git a/lib/stackdepot.c b/lib/stackdepot.c index 036da8e295d1..e99f4ef218ef 100644 --- a/lib/stackdepot.c +++ b/lib/stackdepot.c @@ -59,6 +59,7 @@ struct stack_record { u32 hash; /* Hash in the hash table */ u32 size; /* Number of stored frames */ union handle_parts handle; + refcount_t count; /* Number of the same repeated stacks */ unsigned long entries[]; /* Variable-sized array of frames */ }; =20 @@ -304,6 +305,7 @@ depot_alloc_stack(unsigned long *entries, int size, u32= hash, void **prealloc) stack->handle.offset =3D pool_offset >> DEPOT_STACK_ALIGN; stack->handle.valid =3D 1; stack->handle.extra =3D 0; + refcount_set(&stack->count, 1); memcpy(stack->entries, entries, flex_array_size(stack, entries, size)); pool_offset +=3D required_size; =20 @@ -349,9 +351,15 @@ static inline struct stack_record *find_stack(struct s= tack_record *bucket, return NULL; } =20 +static void stack_depot_inc_count(struct stack_record *stack) +{ + refcount_inc(&stack->count); +} + depot_stack_handle_t __stack_depot_save(unsigned long *entries, unsigned int nr_entries, - gfp_t alloc_flags, bool can_alloc) + gfp_t alloc_flags, bool can_alloc, + bool counter) { struct stack_record *found =3D NULL, **bucket; union handle_parts retval =3D { .handle =3D 0 }; @@ -436,8 +444,11 @@ depot_stack_handle_t __stack_depot_save(unsigned long = *entries, /* Stack depot didn't use this memory, free it. */ free_pages((unsigned long)prealloc, DEPOT_POOL_ORDER); } - if (found) + if (found) { retval.handle =3D found->handle.handle; + if (counter) + stack_depot_inc_count(found); + } fast_exit: return retval.handle; } @@ -447,12 +458,20 @@ depot_stack_handle_t stack_depot_save(unsigned long *= entries, unsigned int nr_entries, gfp_t alloc_flags) { - return __stack_depot_save(entries, nr_entries, alloc_flags, true); + return __stack_depot_save(entries, nr_entries, alloc_flags, true, false); } EXPORT_SYMBOL_GPL(stack_depot_save); =20 -unsigned int stack_depot_fetch(depot_stack_handle_t handle, - unsigned long **entries) +depot_stack_handle_t stack_depot_save_action(unsigned long *entries, + unsigned int nr_entries, + gfp_t alloc_flags, + bool counter) +{ + return __stack_depot_save(entries, nr_entries, alloc_flags, true, counter= ); +} +EXPORT_SYMBOL_GPL(stack_depot_save_action); + +static struct stack_record *stack_depot_getstack(depot_stack_handle_t hand= le) { union handle_parts parts =3D { .handle =3D handle }; /* @@ -464,25 +483,56 @@ unsigned int stack_depot_fetch(depot_stack_handle_t h= andle, size_t offset =3D parts.offset << DEPOT_STACK_ALIGN; struct stack_record *stack; =20 - *entries =3D NULL; - if (!handle) - return 0; + if(!handle) + return NULL; =20 if (parts.pool_index > pool_index_cached) { WARN(1, "pool index %d out of bounds (%d) for stack id %08x\n", - parts.pool_index, pool_index_cached, handle); - return 0; + parts.pool_index, pool_index_cached, handle); + return NULL; } pool =3D stack_pools[parts.pool_index]; if (!pool) - return 0; + return NULL; + stack =3D pool + offset; + return stack; +} + +unsigned int stack_depot_fetch(depot_stack_handle_t handle, + unsigned long **entries) +{ + struct stack_record *stack; + + *entries =3D NULL; + if (!handle) + return 0; + + stack =3D stack_depot_getstack(handle); + if (!stack) + return 0; =20 *entries =3D stack->entries; return stack->size; } EXPORT_SYMBOL_GPL(stack_depot_fetch); =20 +void stack_depot_dec_count(depot_stack_handle_t handle) +{ + struct stack_record *stack =3D NULL; + + stack =3D stack_depot_getstack(handle); + if (stack) { + /* + * page_owner creates some stacks via create_dummy_stack(). + * We are not interested in those, so make sure we only decrement + * "valid" stacks. + */ + if (refcount_read(&stack->count) > 1) + refcount_dec(&stack->count); + } +} + void stack_depot_print(depot_stack_handle_t stack) { unsigned long *entries; diff --git a/mm/kasan/common.c b/mm/kasan/common.c index b376a5d055e5..ea0061ea8ae9 100644 --- a/mm/kasan/common.c +++ b/mm/kasan/common.c @@ -43,7 +43,8 @@ depot_stack_handle_t kasan_save_stack(gfp_t flags, bool c= an_alloc) unsigned int nr_entries; =20 nr_entries =3D stack_trace_save(entries, ARRAY_SIZE(entries), 0); - return __stack_depot_save(entries, nr_entries, flags, can_alloc); + return __stack_depot_save(entries, nr_entries, flags, can_alloc, + false); } =20 void kasan_set_track(struct kasan_track *track, gfp_t flags) diff --git a/mm/page_owner.c b/mm/page_owner.c index 220cdeddc295..b6637524e442 100644 --- a/mm/page_owner.c +++ b/mm/page_owner.c @@ -107,7 +107,7 @@ static inline struct page_owner *get_page_owner(struct = page_ext *page_ext) return (void *)page_ext + page_owner_ops.offset; } =20 -static noinline depot_stack_handle_t save_stack(gfp_t flags) +static noinline depot_stack_handle_t save_stack(gfp_t flags, bool counter) { unsigned long entries[PAGE_OWNER_STACK_DEPTH]; depot_stack_handle_t handle; @@ -126,7 +126,7 @@ static noinline depot_stack_handle_t save_stack(gfp_t f= lags) current->in_page_owner =3D 1; =20 nr_entries =3D stack_trace_save(entries, ARRAY_SIZE(entries), 2); - handle =3D stack_depot_save(entries, nr_entries, flags); + handle =3D stack_depot_save_action(entries, nr_entries, flags, counter); if (!handle) handle =3D failure_handle; =20 @@ -139,6 +139,7 @@ void __reset_page_owner(struct page *page, unsigned sho= rt order) int i; struct page_ext *page_ext; depot_stack_handle_t handle; + depot_stack_handle_t alloc_handle; struct page_owner *page_owner; u64 free_ts_nsec =3D local_clock(); =20 @@ -146,7 +147,10 @@ void __reset_page_owner(struct page *page, unsigned sh= ort order) if (unlikely(!page_ext)) return; =20 - handle =3D save_stack(GFP_NOWAIT | __GFP_NOWARN); + page_owner =3D get_page_owner(page_ext); + alloc_handle =3D page_owner->handle; + + handle =3D save_stack(GFP_NOWAIT | __GFP_NOWARN, false); for (i =3D 0; i < (1 << order); i++) { __clear_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags); page_owner =3D get_page_owner(page_ext); @@ -155,6 +159,7 @@ void __reset_page_owner(struct page *page, unsigned sho= rt order) page_ext =3D page_ext_next(page_ext); } page_ext_put(page_ext); + stack_depot_dec_count(alloc_handle); } =20 static inline void __set_page_owner_handle(struct page_ext *page_ext, @@ -189,7 +194,7 @@ noinline void __set_page_owner(struct page *page, unsig= ned short order, struct page_ext *page_ext; depot_stack_handle_t handle; =20 - handle =3D save_stack(gfp_mask); + handle =3D save_stack(gfp_mask, true); =20 page_ext =3D page_ext_get(page); if (unlikely(!page_ext)) --=20 2.35.3 From nobody Wed Dec 17 08:21:11 2025 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id CDB00C77B75 for ; Fri, 21 Apr 2023 10:15:05 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S231434AbjDUKPE (ORCPT ); Fri, 21 Apr 2023 06:15:04 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:48722 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S231342AbjDUKOk (ORCPT ); Fri, 21 Apr 2023 06:14:40 -0400 Received: from smtp-out2.suse.de (smtp-out2.suse.de [IPv6:2001:67c:2178:6::1d]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 706FCC16B for ; Fri, 21 Apr 2023 03:14:39 -0700 (PDT) Received: from imap2.suse-dmz.suse.de (imap2.suse-dmz.suse.de [192.168.254.74]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature ECDSA (P-521) server-digest SHA512) (No client certificate requested) by smtp-out2.suse.de (Postfix) with ESMTPS id 236311FDDE; Fri, 21 Apr 2023 10:14:38 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=suse.de; s=susede2_rsa; t=1682072078; h=from:from:reply-to:date:date:message-id:message-id:to:to:cc:cc: mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=zE4KUQItN/3/UV4PaOZpW67hAUQM7k7JGXQXpSUX7jM=; b=LxPC06RfpZaf/PV59ic/kcvwI8MQ/gLjs6JkYCNJ/RNb4xRaG70GAN+PGm+8H+ryznSgpc YrF8dckTbYzILZ5H8nPsp0rNBoS1mIsN58UGleQbLSkmKQt45pkJxWA4xeNLFKhm3E6CSB bgDU8rZ29b2J1dRT10rROtiAB8ISjTE= DKIM-Signature: v=1; a=ed25519-sha256; c=relaxed/relaxed; d=suse.de; s=susede2_ed25519; t=1682072078; h=from:from:reply-to:date:date:message-id:message-id:to:to:cc:cc: mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=zE4KUQItN/3/UV4PaOZpW67hAUQM7k7JGXQXpSUX7jM=; b=TfOtgFn8V7n2eVcwCSKoDkdsIoC3KMz6ZTBfi4H+A0+FegXVYPQtLSIWwe1Nz6zW8lDvXx 1QolS+TvzBBDJnBQ== Received: from imap2.suse-dmz.suse.de (imap2.suse-dmz.suse.de [192.168.254.74]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature ECDSA (P-521) server-digest SHA512) (No client certificate requested) by imap2.suse-dmz.suse.de (Postfix) with ESMTPS id 542F01390E; Fri, 21 Apr 2023 10:14:37 +0000 (UTC) Received: from dovecot-director2.suse.de ([192.168.254.65]) by imap2.suse-dmz.suse.de with ESMTPSA id GNpvEQ1iQmRNaAAAMHmgww (envelope-from ); Fri, 21 Apr 2023 10:14:37 +0000 From: Oscar Salvador To: Andrew Morton Cc: linux-kernel@vger.kernel.org, linux-mm@kvack.org, Michal Hocko , Vlastimil Babka , Eric Dumazet , Waiman Long , Suren Baghdasaryan , Marco Elver , Andrey Konovalov , Alexander Potapenko , Oscar Salvador Subject: [PATCH v4 2/3] mm, page_owner: Add page_owner_stacks file to print out only stacks and their counte Date: Fri, 21 Apr 2023 12:14:14 +0200 Message-Id: <20230421101415.5734-3-osalvador@suse.de> X-Mailer: git-send-email 2.40.0 In-Reply-To: <20230421101415.5734-1-osalvador@suse.de> References: <20230421101415.5734-1-osalvador@suse.de> MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Type: text/plain; charset="utf-8" We might be only interested in knowing about stacks <-> count relationship, so instead of having to fiddle with page_owner output and screen through pfns, let us add a new file called 'page_owner_stacks' that does just that. By cating such file, we will get all the stacktraces followed by its counter, so we can have a more global view. Signed-off-by: Oscar Salvador #include #include +#include +#include =20 #define DEPOT_HANDLE_BITS (sizeof(depot_stack_handle_t) * 8) =20 @@ -499,6 +501,77 @@ static struct stack_record *stack_depot_getstack(depot= _stack_handle_t handle) return stack; } =20 +#ifdef CONFIG_PAGE_OWNER +void *stack_start(struct seq_file *m, loff_t *ppos) +{ + unsigned long *table =3D m->private; + struct stack_record **stacks, *stack; + + /* First time */ + if (*ppos =3D=3D 0) + *table =3D 0; + + if (*ppos =3D=3D -1UL) + return NULL; + + stacks =3D &stack_table[*table]; + stack =3D (struct stack_record *)stacks; + + return stack; +} + +void *stack_next(struct seq_file *m, void *v, loff_t *ppos) +{ + unsigned long *table =3D m->private; + unsigned long nr_table =3D *table; + struct stack_record *next =3D NULL, *stack =3D v, **stacks; + unsigned long stack_table_entries =3D stack_hash_mask + 1; + + if (!stack) { +new_table: + /* New table */ + nr_table++; + if (nr_table >=3D stack_table_entries) + goto out; + stacks =3D &stack_table[nr_table]; + stack =3D (struct stack_record *)stacks; + next =3D stack; + } else { + next =3D stack->next; + } + + if (!next) + goto new_table; + +out: + *table =3D nr_table; + *ppos =3D (nr_table >=3D stack_table_entries) ? -1UL : *ppos + 1; + return next; +} + +int stack_print(struct seq_file *m, void *v) +{ + char *buf; + int ret =3D 0; + struct stack_record *stack =3Dv; + + if (!stack->size || stack->size < 0 || + stack->size > PAGE_SIZE || stack->handle.valid !=3D 1 || + refcount_read(&stack->count) < 1) + return 0; + + buf =3D kzalloc(PAGE_SIZE, GFP_KERNEL); + ret +=3D stack_trace_snprint(buf, PAGE_SIZE, stack->entries, stack->size,= 0); + scnprintf(buf + ret, PAGE_SIZE - ret, "stack count: %d\n\n", + refcount_read(&stack->count)); + seq_printf(m, buf); + seq_puts(m, "\n\n"); + kfree(buf); + + return 0; +} +#endif + unsigned int stack_depot_fetch(depot_stack_handle_t handle, unsigned long **entries) { diff --git a/mm/page_owner.c b/mm/page_owner.c index b6637524e442..b191ad1d41f9 100644 --- a/mm/page_owner.c +++ b/mm/page_owner.c @@ -718,6 +718,31 @@ static const struct file_operations proc_page_owner_op= erations =3D { .llseek =3D lseek_page_owner, }; =20 +static void stack_stop(struct seq_file *m, void *v) +{ + return; +} + +static const struct seq_operations page_owner_stack_op =3D { + .start =3D stack_start, + .next =3D stack_next, + .stop =3D stack_stop, + .show =3D stack_print +}; + +static int page_owner_stack_open(struct inode *inode, struct file *file) +{ + return seq_open_private(file, &page_owner_stack_op, + sizeof(unsigned long)); +} + +const struct file_operations page_owner_stack_operations =3D { + .open =3D page_owner_stack_open, + .read =3D seq_read, + .llseek =3D seq_lseek, + .release =3D seq_release, +}; + static int __init pageowner_init(void) { if (!static_branch_unlikely(&page_owner_inited)) { @@ -728,6 +753,9 @@ static int __init pageowner_init(void) debugfs_create_file("page_owner", 0400, NULL, NULL, &proc_page_owner_operations); =20 + debugfs_create_file("page_owner_stacks", S_IRUSR, NULL, NULL, + &page_owner_stack_operations); + return 0; } late_initcall(pageowner_init) --=20 2.35.3 From nobody Wed Dec 17 08:21:11 2025 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id E1CB4C77B75 for ; Fri, 21 Apr 2023 10:15:09 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S231719AbjDUKPI (ORCPT ); Fri, 21 Apr 2023 06:15:08 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:48760 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S231478AbjDUKOm (ORCPT ); Fri, 21 Apr 2023 06:14:42 -0400 Received: from smtp-out2.suse.de (smtp-out2.suse.de [IPv6:2001:67c:2178:6::1d]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 6A5F1BBA4 for ; Fri, 21 Apr 2023 03:14:41 -0700 (PDT) Received: from imap2.suse-dmz.suse.de (imap2.suse-dmz.suse.de [192.168.254.74]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature ECDSA (P-521) server-digest SHA512) (No client certificate requested) by smtp-out2.suse.de (Postfix) with ESMTPS id 1AD021FDDD; Fri, 21 Apr 2023 10:14:40 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=suse.de; s=susede2_rsa; t=1682072080; h=from:from:reply-to:date:date:message-id:message-id:to:to:cc:cc: mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=MPdsIHAkF3dojDaKePRBYhF7VPy8HOJoJzQ2IPR70Ow=; b=DdqlQbKRzrk0ecb+luhX0blRgkUDuGYm7WDDLDbPi4vbYnYkhLJT1pTwGhsTuvYWAEJqri kt5QbY3sB5G4gVZ9eIoQ6+DLmEsMikliivsd9cqxZT4qwbGlwF7i+ONMsDKtZ/Y2fep0fG 7oIwPv7A4PDhJeFJjeNvR+3jlGc4xXY= DKIM-Signature: v=1; a=ed25519-sha256; c=relaxed/relaxed; d=suse.de; s=susede2_ed25519; t=1682072080; h=from:from:reply-to:date:date:message-id:message-id:to:to:cc:cc: mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=MPdsIHAkF3dojDaKePRBYhF7VPy8HOJoJzQ2IPR70Ow=; b=x4vnIpaKeT0Oe6Mjy4yVpvO3QSsS3+iLzk0GjWPcysPnP0FWH94mz8RNdbfDyx1Ki8iouK v40Oc8hZwlD9BJBA== Received: from imap2.suse-dmz.suse.de (imap2.suse-dmz.suse.de [192.168.254.74]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature ECDSA (P-521) server-digest SHA512) (No client certificate requested) by imap2.suse-dmz.suse.de (Postfix) with ESMTPS id BABC11390E; Fri, 21 Apr 2023 10:14:38 +0000 (UTC) Received: from dovecot-director2.suse.de ([192.168.254.65]) by imap2.suse-dmz.suse.de with ESMTPSA id UDFAKg5iQmRNaAAAMHmgww (envelope-from ); Fri, 21 Apr 2023 10:14:38 +0000 From: Oscar Salvador To: Andrew Morton Cc: linux-kernel@vger.kernel.org, linux-mm@kvack.org, Michal Hocko , Vlastimil Babka , Eric Dumazet , Waiman Long , Suren Baghdasaryan , Marco Elver , Andrey Konovalov , Alexander Potapenko , Oscar Salvador Subject: [PATCH v4 3/3] mm,page_owner: Filter out stacks by a threshold counter Date: Fri, 21 Apr 2023 12:14:15 +0200 Message-Id: <20230421101415.5734-4-osalvador@suse.de> X-Mailer: git-send-email 2.40.0 In-Reply-To: <20230421101415.5734-1-osalvador@suse.de> References: <20230421101415.5734-1-osalvador@suse.de> MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Type: text/plain; charset="utf-8" We want to be able to filter out the output on a threshold basis, in this way we can get rid of a lot of noise and focus only on those stacks which have an allegedly high counter. We can control the threshold value by a new file called 'page_owner_threshold', which is 0 by default. Signed-off-by: Oscar Salvador --- include/linux/stackdepot.h | 3 +++ lib/stackdepot.c | 17 ++++++++++++++++- mm/page_owner.c | 5 +++++ 3 files changed, 24 insertions(+), 1 deletion(-) diff --git a/include/linux/stackdepot.h b/include/linux/stackdepot.h index e1d05d9adcd1..c6b54199ea26 100644 --- a/include/linux/stackdepot.h +++ b/include/linux/stackdepot.h @@ -120,6 +120,9 @@ depot_stack_handle_t stack_depot_save_action(unsigned l= ong *entries, void *stack_start(struct seq_file *m, loff_t *ppos); void *stack_next(struct seq_file *m, void *v, loff_t *ppos); int stack_print(struct seq_file *m, void *v); + +int page_owner_threshold_get(void *data, u64 *val); +int page_owner_threshold_set(void *data, u64 val); #endif =20 /** diff --git a/lib/stackdepot.c b/lib/stackdepot.c index d0a4e6ac0bc9..2f1a41f0ae4f 100644 --- a/lib/stackdepot.c +++ b/lib/stackdepot.c @@ -502,6 +502,9 @@ static struct stack_record *stack_depot_getstack(depot_= stack_handle_t handle) } =20 #ifdef CONFIG_PAGE_OWNER + +static unsigned long page_owner_stack_threshold =3D 0; + void *stack_start(struct seq_file *m, loff_t *ppos) { unsigned long *table =3D m->private; @@ -557,7 +560,7 @@ int stack_print(struct seq_file *m, void *v) =20 if (!stack->size || stack->size < 0 || stack->size > PAGE_SIZE || stack->handle.valid !=3D 1 || - refcount_read(&stack->count) < 1) + refcount_read(&stack->count) < page_owner_stack_threshold) return 0; =20 buf =3D kzalloc(PAGE_SIZE, GFP_KERNEL); @@ -570,6 +573,18 @@ int stack_print(struct seq_file *m, void *v) =20 return 0; } + +int page_owner_threshold_get(void *data, u64 *val) +{ + *val =3D page_owner_stack_threshold; + return 0; +} + +int page_owner_threshold_set(void *data, u64 val) +{ + page_owner_stack_threshold =3D val; + return 0; +} #endif =20 unsigned int stack_depot_fetch(depot_stack_handle_t handle, diff --git a/mm/page_owner.c b/mm/page_owner.c index b191ad1d41f9..daec789b0b50 100644 --- a/mm/page_owner.c +++ b/mm/page_owner.c @@ -743,6 +743,9 @@ const struct file_operations page_owner_stack_operation= s =3D { .release =3D seq_release, }; =20 +DEFINE_SIMPLE_ATTRIBUTE(proc_page_owner_threshold, &page_owner_threshold_g= et, + &page_owner_threshold_set, "%lu"); + static int __init pageowner_init(void) { if (!static_branch_unlikely(&page_owner_inited)) { @@ -755,6 +758,8 @@ static int __init pageowner_init(void) =20 debugfs_create_file("page_owner_stacks", S_IRUSR, NULL, NULL, &page_owner_stack_operations); + debugfs_create_file("page_owner_threshold", 0600, NULL, NULL, + &proc_page_owner_threshold); =20 return 0; } --=20 2.35.3