This patch was posted in 2019/12/23 [1] and nacked by Qian Cai [2]
because Qian thought this approach is not a general solution and it
works only for some special cases.
Thanks for Qian's comment but I think the patch provides an important
and straightforward information that is not printed in current OOM
log - the greatest memory consumer so it looks like for some special
cases. I decide to repost this patch and see if it is possible to
reconsider this approach.
We have seen different types of OOM panics:
a) OOM panics are caused by memory fragmentation. (unable to
allocate a large contiguous memory) [3, 4].
b) Abnormal slab usage, we have to reproduce the issue with
CONFIG_KMEMLEAK.
c) A painful OOM panic: every number in OOM report looks fine but OOM
panic occurs and it is not a memory fragmentation issue. We will use
CONFIG_PAGE_OWNER and reproduce this case, but it takes a lot of
time to do reproduce the issue. (the motivation of this patch)
For (b, c), I assume that knowing the greatest memory consumer is useful,
so I applied the patch and collected internal test data since 2019/5,
the result shows that the information is useful in 8/39 OOM panic
reports.
There are already many useful numbers in the OOM kernel report, this
patch is trying to add "the greatest memory consumer" to the report.
Like Qian's comment, it is "situational" but I think it can improve the
OOM report.
Thanks again for Qian's comment. I hope I made Qian's point clear enough.
[1] https://lkml.org/lkml/2019/12/23/185
[2] https://lkml.org/lkml/2019/12/29/1023
[3] https://lkml.org/lkml/2019/11/18/11
[4] https://lkml.org/lkml/2018/11/1/1251
Motivation:
-----------
When debug with a OOM kernel panic, it is difficult to know the
memory allocated by kernel drivers by using alloc_pages() or vmalloc()
by checking the Mem-Info or Node/Zone info. For example:
Mem-Info:
active_anon:5144 inactive_anon:16120 isolated_anon:0
active_file:0 inactive_file:0 isolated_file:0
unevictable:0 dirty:0 writeback:0 unstable:0
slab_reclaimable:739 slab_unreclaimable:442469
mapped:534 shmem:21050 pagetables:21 bounce:0
free:14808 free_pcp:3389 free_cma:8128
Node 0 active_anon:20576kB inactive_anon:64480kB active_file:0kB
inactive_file:0kB unevictable:0kB isolated(anon):0kB isolated(file):0kB
mapped:2136kB dirty:0kB writeback:0kB shmem:84200kB shmem_thp: 0kB
shmem_pmdmapped: 0kB anon_thp: 0kB writeback_tmp:0kB unstable:0kB
all_unr eclaimable? yes
Node 0 DMA free:14476kB min:21512kB low:26888kB high:32264kB
reserved_highatomic:0KB active_anon:0kB inactive_anon:0kB
active_file: 0kB inactive_file:0kB unevictable:0kB writepending:0kB
present:1048576kB managed:952736kB mlocked:0kB kernel_stack:0kB
pagetables:0kB bounce:0kB free_pcp:2716kB local_pcp:0kB free_cma:0kB
The information above tells us the memory usage of the known memory
categories and we can check the abnormal large numbers. However, if a
memory leakage cannot be observed in the categories above, we need to
reproduce the issue with CONFIG_PAGE_OWNER.
It is possible to read the page owner information from coredump files.
However, coredump files may not always be available, so my approach is
to print out the greatest page consumer when OOM kernel panic occurs.
The heuristic approach assumes that the OOM kernel panic is caused by
a single backtrace. The assumption is not always true but it works in
many cases during our test.
We have tested this heuristic approach since 2019/5 on android devices.
In 39 internal OOM kernel panic reports:
31/39: can be analyzed by using existing information
8/39: need page owner formation and the heuristic approach in this patch
prints the correct backtraces of abnormal memory allocations. No need to
reproduce the issues.
Output:
-------
This output below is generated by a dummy infinite
kmalloc(2048, GFP_KERNEL) loop on QEMU with 2048MB DRAM.
[ 12.928878] OOM: greatest memory consumer: 431376 pages are allocated from:
[ 12.929112] prep_new_page+0x50/0x180
[ 12.929220] get_page_from_freelist+0x20c/0x248
[ 12.929330] __alloc_pages_nodemask+0x158/0x254
[ 12.929433] alloc_pages_current+0x104/0x190
[ 12.929526] alloc_slab_page+0x11c/0x464
[ 12.930043] allocate_slab+0x88/0x4ac
[ 12.930133] ___slab_alloc+0x1a0/0x314
[ 12.930217] kmem_cache_alloc+0x244/0x250
[ 12.930317] meminfo_proc_show+0x1c/0x20
[ 12.930412] seq_read+0x1d8/0x474
[ 12.930490] proc_reg_read+0x84/0xf0
[ 12.930572] __vfs_read+0x44/0x16c
[ 12.930646] vfs_read+0xb8/0x154
[ 12.930717] ksys_read+0x70/0xd8
[ 12.930788] __arm64_sys_read+0x18/0x20
[ 12.930874] el0_svc_common+0x98/0x150
[ 12.931668] Kernel panic - not syncing: System is deadlocked on memory
Change since v1:
Replace "largest" with "greatest"
Cc: Qian Cai <[email protected]>
Cc: Michal Hocko <[email protected]>
Signed-off-by: Miles Chen <[email protected]>
---
include/linux/oom.h | 1 +
mm/oom_kill.c | 4 ++
mm/page_owner.c | 135 ++++++++++++++++++++++++++++++++++++++++++++
3 files changed, 140 insertions(+)
diff --git a/include/linux/oom.h b/include/linux/oom.h
index c696c265f019..99f5724d21d3 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_greatest_page_consumer(void);
/* sysctls */
extern int sysctl_oom_dump_tasks;
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index dfc357614e56..90cae29d0223 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -43,6 +43,7 @@
#include <linux/kthread.h>
#include <linux/init.h>
#include <linux/mmu_notifier.h>
+#include <linux/once.h>
#include <asm/tlb.h>
#include "internal.h"
@@ -1101,6 +1102,9 @@ 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_greatest_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..e1497b9eca02 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_greatest_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: greatest memory consumer: %lu pages are allocated from:\n",
+ page_owner->page_count);
+ stack_trace_print(entries, nr_entries, 0);
+}
+
+void report_greatest_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_greatest_page_consumer(most_referenced_page_owner);
+}
+
+
static void init_zones_in_node(pg_data_t *pgdat)
{
struct zone *zone;
--
2.18.0