mm/page_owner: print largest memory consumer when OOM panic occurs

Message ID	20191223113326.13828-1-miles.chen@mediatek.com (mailing list archive)
State	New, archived
Headers	show Return-Path: <SRS0=jhCc=2N=kvack.org=owner-linux-mm@kernel.org> DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org 7794620828 From: Miles Chen <miles.chen@mediatek.com> To: Andrew Morton <akpm@linux-foundation.org> CC: Michal Hocko <mhocko@suse.com>, <linux-kernel@vger.kernel.org>, <linux-mm@kvack.org>, <linux-mediatek@lists.infradead.org>, <wsd_upstream@mediatek.com>, Miles Chen <miles.chen@mediatek.com> Subject: [PATCH] mm/page_owner: print largest memory consumer when OOM panic occurs Date: Mon, 23 Dec 2019 19:33:26 +0800 Message-ID: <20191223113326.13828-1-miles.chen@mediatek.com> MIME-Version: 1.0 Content-Type: text/plain Content-Transfer-Encoding: base64 Sender: owner-linux-mm@kvack.org Precedence: bulk
Series	mm/page_owner: print largest memory consumer when OOM panic occurs \| expand mm/page_owner: print largest memory consumer when OOM panic occurs

diff --git a/include/linux/oom.h b/include/linux/oom.h index c696c265f019..fe3c923ac8f3 100644 --- a/include/linux/oom.h +++ b/include/linux/oom.h @@ -121,6 +121,7 @@ extern bool oom_killer_disable(signed long timeout); extern void oom_killer_enable(void); extern struct task_struct *find_lock_task_mm(struct task_struct *p); +extern void report_largest_page_consumer(void); /* sysctls */ extern int sysctl_oom_dump_tasks; diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 71e3acea7817..9b069b5a4aff 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -42,6 +42,7 @@ #include <linux/kthread.h> #include <linux/init.h> #include <linux/mmu_notifier.h> +#include <linux/once.h> #include <asm/tlb.h> #include "internal.h" @@ -1099,6 +1100,9 @@ bool out_of_memory(struct oom_control *oc) if (!oc->chosen) { dump_header(oc, NULL); pr_warn("Out of memory and no killable processes...\n"); +#ifdef CONFIG_PAGE_OWNER + DO_ONCE(report_largest_page_consumer); +#endif /* * If we got here due to an actual allocation at the * system level, we cannot survive this and will enter diff --git a/mm/page_owner.c b/mm/page_owner.c index 18ecde9f45b2..b23e5fe35dad 100644 --- a/mm/page_owner.c +++ b/mm/page_owner.c @@ -10,6 +10,8 @@ #include <linux/migrate.h> #include <linux/stackdepot.h> #include <linux/seq_file.h> +#include <linux/stacktrace.h> +#include <linux/hashtable.h> #include "internal.h" @@ -19,12 +21,16 @@ */ #define PAGE_OWNER_STACK_DEPTH (16) +#define OOM_HANDLE_HASH_BITS 10 + struct page_owner { unsigned short order; short last_migrate_reason; gfp_t gfp_mask; depot_stack_handle_t handle; depot_stack_handle_t free_handle; + struct hlist_node node; + unsigned long page_count; /* number of pages points to this handle */ }; static bool page_owner_enabled = false; @@ -33,6 +39,8 @@ DEFINE_STATIC_KEY_FALSE(page_owner_inited); static depot_stack_handle_t dummy_handle; static depot_stack_handle_t failure_handle; static depot_stack_handle_t early_handle; +static DEFINE_HASHTABLE(oom_handle_hash, OOM_HANDLE_HASH_BITS); +static struct page_owner *most_referenced_page_owner; static void init_early_allocated_pages(void); @@ -48,6 +56,57 @@ static int __init early_page_owner_param(char *buf) } early_param("page_owner", early_page_owner_param); +static struct hlist_head *get_bucket(depot_stack_handle_t handle) +{ + unsigned long hash; + + hash = hash_long(handle, OOM_HANDLE_HASH_BITS); + return &oom_handle_hash[hash]; +} + +/* + * lookup a page_owner in the hash bucket + */ +static struct page_owner *lookup_page_owner(depot_stack_handle_t handle, + struct hlist_head *b) +{ + struct page_owner *page_owner; + + hlist_for_each_entry(page_owner, b, node) { + if (page_owner->handle == handle) + return page_owner; + } + + return NULL; +} + +/* + * Increase the page_owner->page_count in the handle_hash by (1 << order) + */ +static void increase_handle_count(struct page_owner *page_owner) +{ + struct hlist_head *bucket; + struct page_owner *owner; + + bucket = get_bucket(page_owner->handle); + + owner = lookup_page_owner(page_owner->handle, bucket); + + if (!owner) { + owner = page_owner; + hlist_add_head(&page_owner->node, bucket); + } + + /* increase page counter */ + owner->page_count += (1 << owner->order); + + /* update most_referenced_page_owner */ + if (!most_referenced_page_owner) + most_referenced_page_owner = owner; + if (most_referenced_page_owner->page_count < owner->page_count) + most_referenced_page_owner = owner; +} + static bool need_page_owner(void) { return page_owner_enabled; @@ -172,6 +231,7 @@ 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->page_count = 0; __set_bit(PAGE_EXT_OWNER, &page_ext->flags); __set_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags); @@ -216,6 +276,7 @@ void __split_page_owner(struct page *page, unsigned int order) for (i = 0; i < (1 << order); i++) { page_owner = get_page_owner(page_ext); page_owner->order = 0; + page_owner->page_count = 0; page_ext = page_ext_next(page_ext); } } @@ -236,6 +297,7 @@ 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->page_count = new_page_owner->page_count; /* * We don't clear the bit on the oldpage as it's going to be freed @@ -615,6 +677,79 @@ static void init_pages_in_zone(pg_data_t *pgdat, struct zone *zone) pgdat->node_id, zone->name, count); } +static void __report_largest_page_consumer(struct page_owner *page_owner) +{ + unsigned long *entries = NULL; + unsigned int nr_entries; + + nr_entries = stack_depot_fetch(page_owner->handle, &entries); + pr_info("OOM: largest memory consumer: %lu pages are allocated from:\n", + page_owner->page_count); + stack_trace_print(entries, nr_entries, 0); +} + +void report_largest_page_consumer(void) +{ + unsigned long pfn; + struct page *page; + struct page_ext *page_ext; + struct page_owner *page_owner; + depot_stack_handle_t handle; + + pfn = min_low_pfn; + + if (!static_branch_unlikely(&page_owner_inited)) + return; + + /* Find a valid PFN or the start of a MAX_ORDER_NR_PAGES area */ + while (!pfn_valid(pfn) && (pfn & (MAX_ORDER_NR_PAGES - 1)) != 0) + pfn++; + + /* Find an allocated page */ + for (; pfn < max_pfn; pfn++) { + if ((pfn & (MAX_ORDER_NR_PAGES - 1)) == 0 && !pfn_valid(pfn)) { + pfn += MAX_ORDER_NR_PAGES - 1; + continue; + } + + if (!pfn_valid_within(pfn)) + continue; + + page = pfn_to_page(pfn); + if (PageBuddy(page)) { + unsigned long freepage_order = page_order_unsafe(page); + + if (freepage_order < MAX_ORDER) + pfn += (1UL << freepage_order) - 1; + continue; + } + + if (PageReserved(page)) + continue; + + page_ext = lookup_page_ext(page); + if (unlikely(!page_ext)) + continue; + + if (!test_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags)) + continue; + + page_owner = get_page_owner(page_ext); + + if (!IS_ALIGNED(pfn, 1 << page_owner->order)) + continue; + + handle = READ_ONCE(page_owner->handle); + if (!handle) + continue; + + increase_handle_count(page_owner); + } + + __report_largest_page_consumer(most_referenced_page_owner); +} + + static void init_zones_in_node(pg_data_t *pgdat) { struct zone *zone;

mm/page_owner: print largest memory consumer when OOM panic occurs

Commit Message

Comments

Patch