Contributors: 54
| Author |
Tokens |
Token Proportion |
Commits |
Commit Proportion |
| JoonSoo Kim |
1421 |
35.74% |
10 |
8.93% |
| Oscar Salvador |
1113 |
27.99% |
11 |
9.82% |
| Vlastimil Babka |
429 |
10.79% |
14 |
12.50% |
| Waiman Long |
223 |
5.61% |
3 |
2.68% |
| Charan Teja Reddy |
139 |
3.50% |
1 |
0.89% |
| Yang Shi |
77 |
1.94% |
1 |
0.89% |
| Kassey Li |
64 |
1.61% |
2 |
1.79% |
| Linus Torvalds (pre-git) |
45 |
1.13% |
6 |
5.36% |
| Liam Mark |
39 |
0.98% |
1 |
0.89% |
| Thomas Gleixner |
37 |
0.93% |
1 |
0.89% |
| Kamezawa Hiroyuki |
33 |
0.83% |
2 |
1.79% |
| Stanislaw Gruszka |
28 |
0.70% |
1 |
0.89% |
| Barry Song |
26 |
0.65% |
1 |
0.89% |
| Andrew Morton |
25 |
0.63% |
2 |
1.79% |
| Yixuan Cao |
24 |
0.60% |
2 |
1.79% |
| Mel Gorman |
23 |
0.58% |
3 |
2.68% |
| Georgi Djakov |
20 |
0.50% |
1 |
0.89% |
| Matthew Wilcox |
17 |
0.43% |
3 |
2.68% |
| Vinayak Menon |
15 |
0.38% |
1 |
0.89% |
| Linus Torvalds |
14 |
0.35% |
4 |
3.57% |
| Sergei Trofimovich |
14 |
0.35% |
2 |
1.79% |
| Christoph Hellwig |
12 |
0.30% |
1 |
0.89% |
| Miles Chen |
11 |
0.28% |
1 |
0.89% |
| Sudip Mukherjee |
11 |
0.28% |
1 |
0.89% |
| Zi Yan |
10 |
0.25% |
1 |
0.89% |
| Christoph Lameter |
9 |
0.23% |
3 |
2.68% |
| Qian Cai |
9 |
0.23% |
1 |
0.89% |
| Nicholas Piggin |
9 |
0.23% |
2 |
1.79% |
| Dave Hansen |
6 |
0.15% |
1 |
0.89% |
| Mike Rapoport |
6 |
0.15% |
2 |
1.79% |
| Kirill A. Shutemov |
6 |
0.15% |
2 |
1.79% |
| Khan, Imran |
6 |
0.15% |
2 |
1.79% |
| HyeonggonYoo |
6 |
0.15% |
1 |
0.89% |
| Pavel Tatashin |
5 |
0.13% |
1 |
0.89% |
| KeMeng Shi |
5 |
0.13% |
1 |
0.89% |
| Sasikantha babu |
4 |
0.10% |
1 |
0.89% |
| Ayush Mittal |
4 |
0.10% |
1 |
0.89% |
| Miaohe Lin |
3 |
0.08% |
1 |
0.89% |
| David Chinner |
3 |
0.08% |
1 |
0.89% |
| Greg Kroah-Hartman |
3 |
0.08% |
2 |
1.79% |
| Sergei Rogachev |
3 |
0.08% |
1 |
0.89% |
| Wei Yang |
3 |
0.08% |
1 |
0.89% |
| Kefeng Wang |
2 |
0.05% |
1 |
0.89% |
| Arjan van de Ven |
2 |
0.05% |
1 |
0.89% |
| Maninder Singh |
2 |
0.05% |
1 |
0.89% |
| Ting Liu |
2 |
0.05% |
1 |
0.89% |
| Paul Gortmaker |
1 |
0.03% |
1 |
0.89% |
| Joe Perches |
1 |
0.03% |
1 |
0.89% |
| Andrey Konovalov |
1 |
0.03% |
1 |
0.89% |
| Suren Baghdasaryan |
1 |
0.03% |
1 |
0.89% |
| Prakash Gupta |
1 |
0.03% |
1 |
0.89% |
| Dou Liyang |
1 |
0.03% |
1 |
0.89% |
| Fanjun Kong |
1 |
0.03% |
1 |
0.89% |
| Audra Mitchell |
1 |
0.03% |
1 |
0.89% |
| Total |
3976 |
|
112 |
|
// SPDX-License-Identifier: GPL-2.0
#include <linux/debugfs.h>
#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/uaccess.h>
#include <linux/memblock.h>
#include <linux/stacktrace.h>
#include <linux/page_owner.h>
#include <linux/jump_label.h>
#include <linux/migrate.h>
#include <linux/stackdepot.h>
#include <linux/seq_file.h>
#include <linux/memcontrol.h>
#include <linux/sched/clock.h>
#include "internal.h"
/*
* TODO: teach PAGE_OWNER_STACK_DEPTH (__dump_page_owner and save_stack)
* to use off stack temporal storage
*/
#define PAGE_OWNER_STACK_DEPTH (16)
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;
u64 ts_nsec;
u64 free_ts_nsec;
char comm[TASK_COMM_LEN];
pid_t pid;
pid_t tgid;
pid_t free_pid;
pid_t free_tgid;
};
struct stack {
struct stack_record *stack_record;
struct stack *next;
};
static struct stack dummy_stack;
static struct stack failure_stack;
static struct stack *stack_list;
static DEFINE_SPINLOCK(stack_list_lock);
static bool page_owner_enabled __initdata;
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 void init_early_allocated_pages(void);
static inline void set_current_in_page_owner(void)
{
/*
* Avoid recursion.
*
* We might need to allocate more memory from page_owner code, so make
* sure to signal it in order to avoid recursion.
*/
current->in_page_owner = 1;
}
static inline void unset_current_in_page_owner(void)
{
current->in_page_owner = 0;
}
static int __init early_page_owner_param(char *buf)
{
int ret = kstrtobool(buf, &page_owner_enabled);
if (page_owner_enabled)
stack_depot_request_early_init();
return ret;
}
early_param("page_owner", early_page_owner_param);
static __init bool need_page_owner(void)
{
return page_owner_enabled;
}
static __always_inline depot_stack_handle_t create_dummy_stack(void)
{
unsigned long entries[4];
unsigned int nr_entries;
nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 0);
return stack_depot_save(entries, nr_entries, GFP_KERNEL);
}
static noinline void register_dummy_stack(void)
{
dummy_handle = create_dummy_stack();
}
static noinline void register_failure_stack(void)
{
failure_handle = create_dummy_stack();
}
static noinline void register_early_stack(void)
{
early_handle = create_dummy_stack();
}
static __init void init_page_owner(void)
{
if (!page_owner_enabled)
return;
register_dummy_stack();
register_failure_stack();
register_early_stack();
init_early_allocated_pages();
/* Initialize dummy and failure stacks and link them to stack_list */
dummy_stack.stack_record = __stack_depot_get_stack_record(dummy_handle);
failure_stack.stack_record = __stack_depot_get_stack_record(failure_handle);
if (dummy_stack.stack_record)
refcount_set(&dummy_stack.stack_record->count, 1);
if (failure_stack.stack_record)
refcount_set(&failure_stack.stack_record->count, 1);
dummy_stack.next = &failure_stack;
stack_list = &dummy_stack;
static_branch_enable(&page_owner_inited);
}
struct page_ext_operations page_owner_ops = {
.size = sizeof(struct page_owner),
.need = need_page_owner,
.init = init_page_owner,
.need_shared_flags = true,
};
static inline struct page_owner *get_page_owner(struct page_ext *page_ext)
{
return page_ext_data(page_ext, &page_owner_ops);
}
static noinline depot_stack_handle_t save_stack(gfp_t flags)
{
unsigned long entries[PAGE_OWNER_STACK_DEPTH];
depot_stack_handle_t handle;
unsigned int nr_entries;
if (current->in_page_owner)
return dummy_handle;
set_current_in_page_owner();
nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 2);
handle = stack_depot_save(entries, nr_entries, flags);
if (!handle)
handle = failure_handle;
unset_current_in_page_owner();
return handle;
}
static void add_stack_record_to_list(struct stack_record *stack_record,
gfp_t gfp_mask)
{
unsigned long flags;
struct stack *stack;
set_current_in_page_owner();
stack = kmalloc(sizeof(*stack), gfp_nested_mask(gfp_mask));
if (!stack) {
unset_current_in_page_owner();
return;
}
unset_current_in_page_owner();
stack->stack_record = stack_record;
stack->next = NULL;
spin_lock_irqsave(&stack_list_lock, flags);
stack->next = stack_list;
/*
* This pairs with smp_load_acquire() from function
* stack_start(). This guarantees that stack_start()
* will see an updated stack_list before starting to
* traverse the list.
*/
smp_store_release(&stack_list, stack);
spin_unlock_irqrestore(&stack_list_lock, flags);
}
static void inc_stack_record_count(depot_stack_handle_t handle, gfp_t gfp_mask,
int nr_base_pages)
{
struct stack_record *stack_record = __stack_depot_get_stack_record(handle);
if (!stack_record)
return;
/*
* New stack_record's that do not use STACK_DEPOT_FLAG_GET start
* with REFCOUNT_SATURATED to catch spurious increments of their
* refcount.
* Since we do not use STACK_DEPOT_FLAG_GET API, let us
* set a refcount of 1 ourselves.
*/
if (refcount_read(&stack_record->count) == REFCOUNT_SATURATED) {
int old = REFCOUNT_SATURATED;
if (atomic_try_cmpxchg_relaxed(&stack_record->count.refs, &old, 1))
/* Add the new stack_record to our list */
add_stack_record_to_list(stack_record, gfp_mask);
}
refcount_add(nr_base_pages, &stack_record->count);
}
static void dec_stack_record_count(depot_stack_handle_t handle,
int nr_base_pages)
{
struct stack_record *stack_record = __stack_depot_get_stack_record(handle);
if (!stack_record)
return;
if (refcount_sub_and_test(nr_base_pages, &stack_record->count))
pr_warn("%s: refcount went to 0 for %u handle\n", __func__,
handle);
}
static inline void __update_page_owner_handle(struct page_ext *page_ext,
depot_stack_handle_t handle,
unsigned short order,
gfp_t gfp_mask,
short last_migrate_reason, u64 ts_nsec,
pid_t pid, pid_t tgid, char *comm)
{
int i;
struct page_owner *page_owner;
for (i = 0; i < (1 << order); i++) {
page_owner = get_page_owner(page_ext);
page_owner->handle = handle;
page_owner->order = order;
page_owner->gfp_mask = gfp_mask;
page_owner->last_migrate_reason = last_migrate_reason;
page_owner->pid = pid;
page_owner->tgid = tgid;
page_owner->ts_nsec = ts_nsec;
strscpy(page_owner->comm, comm,
sizeof(page_owner->comm));
__set_bit(PAGE_EXT_OWNER, &page_ext->flags);
__set_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags);
page_ext = page_ext_next(page_ext);
}
}
static inline void __update_page_owner_free_handle(struct page_ext *page_ext,
depot_stack_handle_t handle,
unsigned short order,
pid_t pid, pid_t tgid,
u64 free_ts_nsec)
{
int i;
struct page_owner *page_owner;
for (i = 0; i < (1 << order); i++) {
page_owner = get_page_owner(page_ext);
/* Only __reset_page_owner() wants to clear the bit */
if (handle) {
__clear_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags);
page_owner->free_handle = handle;
}
page_owner->free_ts_nsec = free_ts_nsec;
page_owner->free_pid = current->pid;
page_owner->free_tgid = current->tgid;
page_ext = page_ext_next(page_ext);
}
}
void __reset_page_owner(struct page *page, unsigned short order)
{
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 = local_clock();
page_ext = page_ext_get(page);
if (unlikely(!page_ext))
return;
page_owner = get_page_owner(page_ext);
alloc_handle = page_owner->handle;
handle = save_stack(GFP_NOWAIT | __GFP_NOWARN);
__update_page_owner_free_handle(page_ext, handle, order, current->pid,
current->tgid, free_ts_nsec);
page_ext_put(page_ext);
if (alloc_handle != early_handle)
/*
* early_handle is being set as a handle for all those
* early allocated pages. See init_pages_in_zone().
* Since their refcount is not being incremented because
* the machinery is not ready yet, we cannot decrement
* their refcount either.
*/
dec_stack_record_count(alloc_handle, 1 << order);
}
noinline void __set_page_owner(struct page *page, unsigned short order,
gfp_t gfp_mask)
{
struct page_ext *page_ext;
u64 ts_nsec = local_clock();
depot_stack_handle_t handle;
handle = save_stack(gfp_mask);
page_ext = page_ext_get(page);
if (unlikely(!page_ext))
return;
__update_page_owner_handle(page_ext, handle, order, gfp_mask, -1,
ts_nsec, current->pid, current->tgid,
current->comm);
page_ext_put(page_ext);
inc_stack_record_count(handle, gfp_mask, 1 << order);
}
void __set_page_owner_migrate_reason(struct page *page, int reason)
{
struct page_ext *page_ext = page_ext_get(page);
struct page_owner *page_owner;
if (unlikely(!page_ext))
return;
page_owner = get_page_owner(page_ext);
page_owner->last_migrate_reason = reason;
page_ext_put(page_ext);
}
void __split_page_owner(struct page *page, int old_order, int new_order)
{
int i;
struct page_ext *page_ext = page_ext_get(page);
struct page_owner *page_owner;
if (unlikely(!page_ext))
return;
for (i = 0; i < (1 << old_order); i++) {
page_owner = get_page_owner(page_ext);
page_owner->order = new_order;
page_ext = page_ext_next(page_ext);
}
page_ext_put(page_ext);
}
void __folio_copy_owner(struct folio *newfolio, struct folio *old)
{
int i;
struct page_ext *old_ext;
struct page_ext *new_ext;
struct page_owner *old_page_owner;
struct page_owner *new_page_owner;
depot_stack_handle_t migrate_handle;
old_ext = page_ext_get(&old->page);
if (unlikely(!old_ext))
return;
new_ext = page_ext_get(&newfolio->page);
if (unlikely(!new_ext)) {
page_ext_put(old_ext);
return;
}
old_page_owner = get_page_owner(old_ext);
new_page_owner = get_page_owner(new_ext);
migrate_handle = new_page_owner->handle;
__update_page_owner_handle(new_ext, old_page_owner->handle,
old_page_owner->order, old_page_owner->gfp_mask,
old_page_owner->last_migrate_reason,
old_page_owner->ts_nsec, old_page_owner->pid,
old_page_owner->tgid, old_page_owner->comm);
/*
* Do not proactively clear PAGE_EXT_OWNER{_ALLOCATED} bits as the folio
* will be freed after migration. Keep them until then as they may be
* useful.
*/
__update_page_owner_free_handle(new_ext, 0, old_page_owner->order,
old_page_owner->free_pid,
old_page_owner->free_tgid,
old_page_owner->free_ts_nsec);
/*
* We linked the original stack to the new folio, we need to do the same
* for the new one and the old folio otherwise there will be an imbalance
* when subtracting those pages from the stack.
*/
for (i = 0; i < (1 << new_page_owner->order); i++) {
old_page_owner->handle = migrate_handle;
old_ext = page_ext_next(old_ext);
old_page_owner = get_page_owner(old_ext);
}
page_ext_put(new_ext);
page_ext_put(old_ext);
}
void pagetypeinfo_showmixedcount_print(struct seq_file *m,
pg_data_t *pgdat, struct zone *zone)
{
struct page *page;
struct page_ext *page_ext;
struct page_owner *page_owner;
unsigned long pfn, block_end_pfn;
unsigned long end_pfn = zone_end_pfn(zone);
unsigned long count[MIGRATE_TYPES] = { 0, };
int pageblock_mt, page_mt;
int i;
/* Scan block by block. First and last block may be incomplete */
pfn = zone->zone_start_pfn;
/*
* Walk the zone in pageblock_nr_pages steps. If a page block spans
* a zone boundary, it will be double counted between zones. This does
* not matter as the mixed block count will still be correct
*/
for (; pfn < end_pfn; ) {
page = pfn_to_online_page(pfn);
if (!page) {
pfn = ALIGN(pfn + 1, MAX_ORDER_NR_PAGES);
continue;
}
block_end_pfn = pageblock_end_pfn(pfn);
block_end_pfn = min(block_end_pfn, end_pfn);
pageblock_mt = get_pageblock_migratetype(page);
for (; pfn < block_end_pfn; pfn++) {
/* The pageblock is online, no need to recheck. */
page = pfn_to_page(pfn);
if (page_zone(page) != zone)
continue;
if (PageBuddy(page)) {
unsigned long freepage_order;
freepage_order = buddy_order_unsafe(page);
if (freepage_order <= MAX_PAGE_ORDER)
pfn += (1UL << freepage_order) - 1;
continue;
}
if (PageReserved(page))
continue;
page_ext = page_ext_get(page);
if (unlikely(!page_ext))
continue;
if (!test_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags))
goto ext_put_continue;
page_owner = get_page_owner(page_ext);
page_mt = gfp_migratetype(page_owner->gfp_mask);
if (pageblock_mt != page_mt) {
if (is_migrate_cma(pageblock_mt))
count[MIGRATE_MOVABLE]++;
else
count[pageblock_mt]++;
pfn = block_end_pfn;
page_ext_put(page_ext);
break;
}
pfn += (1UL << page_owner->order) - 1;
ext_put_continue:
page_ext_put(page_ext);
}
}
/* Print counts */
seq_printf(m, "Node %d, zone %8s ", pgdat->node_id, zone->name);
for (i = 0; i < MIGRATE_TYPES; i++)
seq_printf(m, "%12lu ", count[i]);
seq_putc(m, '\n');
}
/*
* Looking for memcg information and print it out
*/
static inline int print_page_owner_memcg(char *kbuf, size_t count, int ret,
struct page *page)
{
#ifdef CONFIG_MEMCG
unsigned long memcg_data;
struct mem_cgroup *memcg;
bool online;
char name[80];
rcu_read_lock();
memcg_data = READ_ONCE(page->memcg_data);
if (!memcg_data)
goto out_unlock;
if (memcg_data & MEMCG_DATA_OBJEXTS)
ret += scnprintf(kbuf + ret, count - ret,
"Slab cache page\n");
memcg = page_memcg_check(page);
if (!memcg)
goto out_unlock;
online = (memcg->css.flags & CSS_ONLINE);
cgroup_name(memcg->css.cgroup, name, sizeof(name));
ret += scnprintf(kbuf + ret, count - ret,
"Charged %sto %smemcg %s\n",
PageMemcgKmem(page) ? "(via objcg) " : "",
online ? "" : "offline ",
name);
out_unlock:
rcu_read_unlock();
#endif /* CONFIG_MEMCG */
return ret;
}
static ssize_t
print_page_owner(char __user *buf, size_t count, unsigned long pfn,
struct page *page, struct page_owner *page_owner,
depot_stack_handle_t handle)
{
int ret, pageblock_mt, page_mt;
char *kbuf;
count = min_t(size_t, count, PAGE_SIZE);
kbuf = kmalloc(count, GFP_KERNEL);
if (!kbuf)
return -ENOMEM;
ret = scnprintf(kbuf, count,
"Page allocated via order %u, mask %#x(%pGg), pid %d, tgid %d (%s), ts %llu ns\n",
page_owner->order, page_owner->gfp_mask,
&page_owner->gfp_mask, page_owner->pid,
page_owner->tgid, page_owner->comm,
page_owner->ts_nsec);
/* Print information relevant to grouping pages by mobility */
pageblock_mt = get_pageblock_migratetype(page);
page_mt = gfp_migratetype(page_owner->gfp_mask);
ret += scnprintf(kbuf + ret, count - ret,
"PFN 0x%lx type %s Block %lu type %s Flags %pGp\n",
pfn,
migratetype_names[page_mt],
pfn >> pageblock_order,
migratetype_names[pageblock_mt],
&page->flags);
ret += stack_depot_snprint(handle, kbuf + ret, count - ret, 0);
if (ret >= count)
goto err;
if (page_owner->last_migrate_reason != -1) {
ret += scnprintf(kbuf + ret, count - ret,
"Page has been migrated, last migrate reason: %s\n",
migrate_reason_names[page_owner->last_migrate_reason]);
}
ret = print_page_owner_memcg(kbuf, count, ret, page);
ret += snprintf(kbuf + ret, count - ret, "\n");
if (ret >= count)
goto err;
if (copy_to_user(buf, kbuf, ret))
ret = -EFAULT;
kfree(kbuf);
return ret;
err:
kfree(kbuf);
return -ENOMEM;
}
void __dump_page_owner(const struct page *page)
{
struct page_ext *page_ext = page_ext_get((void *)page);
struct page_owner *page_owner;
depot_stack_handle_t handle;
gfp_t gfp_mask;
int mt;
if (unlikely(!page_ext)) {
pr_alert("There is not page extension available.\n");
return;
}
page_owner = get_page_owner(page_ext);
gfp_mask = page_owner->gfp_mask;
mt = gfp_migratetype(gfp_mask);
if (!test_bit(PAGE_EXT_OWNER, &page_ext->flags)) {
pr_alert("page_owner info is not present (never set?)\n");
page_ext_put(page_ext);
return;
}
if (test_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags))
pr_alert("page_owner tracks the page as allocated\n");
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), pid %d, tgid %d (%s), ts %llu, free_ts %llu\n",
page_owner->order, migratetype_names[mt], gfp_mask, &gfp_mask,
page_owner->pid, page_owner->tgid, page_owner->comm,
page_owner->ts_nsec, page_owner->free_ts_nsec);
handle = READ_ONCE(page_owner->handle);
if (!handle)
pr_alert("page_owner allocation stack trace missing\n");
else
stack_depot_print(handle);
handle = READ_ONCE(page_owner->free_handle);
if (!handle) {
pr_alert("page_owner free stack trace missing\n");
} else {
pr_alert("page last free pid %d tgid %d stack trace:\n",
page_owner->free_pid, page_owner->free_tgid);
stack_depot_print(handle);
}
if (page_owner->last_migrate_reason != -1)
pr_alert("page has been migrated, last migrate reason: %s\n",
migrate_reason_names[page_owner->last_migrate_reason]);
page_ext_put(page_ext);
}
static ssize_t
read_page_owner(struct file *file, char __user *buf, size_t count, loff_t *ppos)
{
unsigned long pfn;
struct page *page;
struct page_ext *page_ext;
struct page_owner *page_owner;
depot_stack_handle_t handle;
if (!static_branch_unlikely(&page_owner_inited))
return -EINVAL;
page = NULL;
if (*ppos == 0)
pfn = min_low_pfn;
else
pfn = *ppos;
/* 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++) {
/*
* This temporary page_owner is required so
* that we can avoid the context switches while holding
* the rcu lock and copying the page owner information to
* user through copy_to_user() or GFP_KERNEL allocations.
*/
struct page_owner page_owner_tmp;
/*
* If the new page is in a new MAX_ORDER_NR_PAGES area,
* validate the area as existing, skip it if not
*/
if ((pfn & (MAX_ORDER_NR_PAGES - 1)) == 0 && !pfn_valid(pfn)) {
pfn += MAX_ORDER_NR_PAGES - 1;
continue;
}
page = pfn_to_page(pfn);
if (PageBuddy(page)) {
unsigned long freepage_order = buddy_order_unsafe(page);
if (freepage_order <= MAX_PAGE_ORDER)
pfn += (1UL << freepage_order) - 1;
continue;
}
page_ext = page_ext_get(page);
if (unlikely(!page_ext))
continue;
/*
* Some pages could be missed by concurrent allocation or free,
* because we don't hold the zone lock.
*/
if (!test_bit(PAGE_EXT_OWNER, &page_ext->flags))
goto ext_put_continue;
/*
* Although we do have the info about past allocation of free
* pages, it's not relevant for current memory usage.
*/
if (!test_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags))
goto ext_put_continue;
page_owner = get_page_owner(page_ext);
/*
* Don't print "tail" pages of high-order allocations as that
* would inflate the stats.
*/
if (!IS_ALIGNED(pfn, 1 << page_owner->order))
goto ext_put_continue;
/*
* Access to page_ext->handle isn't synchronous so we should
* be careful to access it.
*/
handle = READ_ONCE(page_owner->handle);
if (!handle)
goto ext_put_continue;
/* Record the next PFN to read in the file offset */
*ppos = pfn + 1;
page_owner_tmp = *page_owner;
page_ext_put(page_ext);
return print_page_owner(buf, count, pfn, page,
&page_owner_tmp, handle);
ext_put_continue:
page_ext_put(page_ext);
}
return 0;
}
static loff_t lseek_page_owner(struct file *file, loff_t offset, int orig)
{
switch (orig) {
case SEEK_SET:
file->f_pos = offset;
break;
case SEEK_CUR:
file->f_pos += offset;
break;
default:
return -EINVAL;
}
return file->f_pos;
}
static void init_pages_in_zone(pg_data_t *pgdat, struct zone *zone)
{
unsigned long pfn = zone->zone_start_pfn;
unsigned long end_pfn = zone_end_pfn(zone);
unsigned long count = 0;
/*
* Walk the zone in pageblock_nr_pages steps. If a page block spans
* a zone boundary, it will be double counted between zones. This does
* not matter as the mixed block count will still be correct
*/
for (; pfn < end_pfn; ) {
unsigned long block_end_pfn;
if (!pfn_valid(pfn)) {
pfn = ALIGN(pfn + 1, MAX_ORDER_NR_PAGES);
continue;
}
block_end_pfn = pageblock_end_pfn(pfn);
block_end_pfn = min(block_end_pfn, end_pfn);
for (; pfn < block_end_pfn; pfn++) {
struct page *page = pfn_to_page(pfn);
struct page_ext *page_ext;
if (page_zone(page) != zone)
continue;
/*
* To avoid having to grab zone->lock, be a little
* careful when reading buddy page order. The only
* danger is that we skip too much and potentially miss
* some early allocated pages, which is better than
* heavy lock contention.
*/
if (PageBuddy(page)) {
unsigned long order = buddy_order_unsafe(page);
if (order > 0 && order <= MAX_PAGE_ORDER)
pfn += (1UL << order) - 1;
continue;
}
if (PageReserved(page))
continue;
page_ext = page_ext_get(page);
if (unlikely(!page_ext))
continue;
/* Maybe overlapping zone */
if (test_bit(PAGE_EXT_OWNER, &page_ext->flags))
goto ext_put_continue;
/* Found early allocated page */
__update_page_owner_handle(page_ext, early_handle, 0, 0,
-1, local_clock(), current->pid,
current->tgid, current->comm);
count++;
ext_put_continue:
page_ext_put(page_ext);
}
cond_resched();
}
pr_info("Node %d, zone %8s: page owner found early allocated %lu pages\n",
pgdat->node_id, zone->name, count);
}
static void init_zones_in_node(pg_data_t *pgdat)
{
struct zone *zone;
struct zone *node_zones = pgdat->node_zones;
for (zone = node_zones; zone - node_zones < MAX_NR_ZONES; ++zone) {
if (!populated_zone(zone))
continue;
init_pages_in_zone(pgdat, zone);
}
}
static void init_early_allocated_pages(void)
{
pg_data_t *pgdat;
for_each_online_pgdat(pgdat)
init_zones_in_node(pgdat);
}
static const struct file_operations proc_page_owner_operations = {
.read = read_page_owner,
.llseek = lseek_page_owner,
};
static void *stack_start(struct seq_file *m, loff_t *ppos)
{
struct stack *stack;
if (*ppos == -1UL)
return NULL;
if (!*ppos) {
/*
* This pairs with smp_store_release() from function
* add_stack_record_to_list(), so we get a consistent
* value of stack_list.
*/
stack = smp_load_acquire(&stack_list);
m->private = stack;
} else {
stack = m->private;
}
return stack;
}
static void *stack_next(struct seq_file *m, void *v, loff_t *ppos)
{
struct stack *stack = v;
stack = stack->next;
*ppos = stack ? *ppos + 1 : -1UL;
m->private = stack;
return stack;
}
static unsigned long page_owner_pages_threshold;
static int stack_print(struct seq_file *m, void *v)
{
int i, nr_base_pages;
struct stack *stack = v;
unsigned long *entries;
unsigned long nr_entries;
struct stack_record *stack_record = stack->stack_record;
if (!stack->stack_record)
return 0;
nr_entries = stack_record->size;
entries = stack_record->entries;
nr_base_pages = refcount_read(&stack_record->count) - 1;
if (nr_base_pages < 1 || nr_base_pages < page_owner_pages_threshold)
return 0;
for (i = 0; i < nr_entries; i++)
seq_printf(m, " %pS\n", (void *)entries[i]);
seq_printf(m, "nr_base_pages: %d\n\n", nr_base_pages);
return 0;
}
static void stack_stop(struct seq_file *m, void *v)
{
}
static const struct seq_operations page_owner_stack_op = {
.start = stack_start,
.next = stack_next,
.stop = stack_stop,
.show = stack_print
};
static int page_owner_stack_open(struct inode *inode, struct file *file)
{
return seq_open_private(file, &page_owner_stack_op, 0);
}
static const struct file_operations page_owner_stack_operations = {
.open = page_owner_stack_open,
.read = seq_read,
.llseek = seq_lseek,
.release = seq_release,
};
static int page_owner_threshold_get(void *data, u64 *val)
{
*val = READ_ONCE(page_owner_pages_threshold);
return 0;
}
static int page_owner_threshold_set(void *data, u64 val)
{
WRITE_ONCE(page_owner_pages_threshold, val);
return 0;
}
DEFINE_SIMPLE_ATTRIBUTE(proc_page_owner_threshold, &page_owner_threshold_get,
&page_owner_threshold_set, "%llu");
static int __init pageowner_init(void)
{
struct dentry *dir;
if (!static_branch_unlikely(&page_owner_inited)) {
pr_info("page_owner is disabled\n");
return 0;
}
debugfs_create_file("page_owner", 0400, NULL, NULL,
&proc_page_owner_operations);
dir = debugfs_create_dir("page_owner_stacks", NULL);
debugfs_create_file("show_stacks", 0400, dir, NULL,
&page_owner_stack_operations);
debugfs_create_file("count_threshold", 0600, dir, NULL,
&proc_page_owner_threshold);
return 0;
}
late_initcall(pageowner_init)