noinline void __set_page_owner(struct page *page, unsigned int order,
gfp_t gfp_mask)
{
struct page_ext *page_ext = lookup_page_ext(page);
depot_stack_handle_t handle;
if (unlikely(!page_ext))
return;
handle = save_stack(gfp_mask);
__set_page_owner_handle(page_ext, handle, order, gfp_mask);
}
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;
int pageblock_mt, page_mt;
char *kbuf;
unsigned long entries[PAGE_OWNER_STACK_DEPTH];
struct stack_trace trace = {
.nr_entries = 0,
.entries = entries,
.max_entries = PAGE_OWNER_STACK_DEPTH,
.skip = 0
};
kbuf = kmalloc(count, GFP_KERNEL);
if (!kbuf)
return -ENOMEM;
ret = snprintf(kbuf, count,
"Page allocated via order %u, mask %#x(%pGg)\n",
page_owner->order, page_owner->gfp_mask,
&page_owner->gfp_mask);
if (ret >= count)
goto err;
/* Print information relevant to grouping pages by mobility */
pageblock_mt = get_pageblock_migratetype(page);
page_mt = gfpflags_to_migratetype(page_owner->gfp_mask);
ret += snprintf(kbuf + ret, count - ret,
"PFN %lu type %s Block %lu type %s Flags %#lx(%pGp)\n",
pfn,
migratetype_names[page_mt],
pfn >> pageblock_order,
migratetype_names[pageblock_mt],
page->flags, &page->flags);
if (ret >= count)
goto err;
depot_fetch_stack(handle, &trace);
ret += snprint_stack_trace(kbuf + ret, count - ret, &trace, 0);
if (ret >= count)
goto err;
if (page_owner->last_migrate_reason != -1) {
ret += snprintf(kbuf + ret, count - ret,
"Page has been migrated, last migrate reason: %s\n",
migrate_reason_names[page_owner->last_migrate_reason]);
if (ret >= count)
goto err;
}
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(struct page *page)
{
struct page_ext *page_ext = lookup_page_ext(page);
struct page_owner *page_owner;
unsigned long entries[PAGE_OWNER_STACK_DEPTH];
struct stack_trace trace = {
.nr_entries = 0,
.entries = entries,
.max_entries = PAGE_OWNER_STACK_DEPTH,
.skip = 0
};
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 = gfpflags_to_migratetype(gfp_mask);
if (!test_bit(PAGE_EXT_OWNER, &page_ext->flags)) {
pr_alert("page_owner info is not active (free page?)\n");
return;
}
handle = READ_ONCE(page_owner->handle);
if (!handle) {
pr_alert("page_owner info is not active (free page?)\n");
return;
}
depot_fetch_stack(handle, &trace);
pr_alert("page allocated via order %u, migratetype %s, gfp_mask %#x(%pGg)\n",
page_owner->order, migratetype_names[mt], gfp_mask, &gfp_mask);
print_stack_trace(&trace, 0);
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]);
}
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;
pfn = min_low_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++;
drain_all_pages(NULL);
/* Find an allocated page */
for (; pfn < max_pfn; pfn++) {
/*
* 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;
}
/* Check for holes within a MAX_ORDER area */
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;
}
page_ext = lookup_page_ext(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))
continue;
page_owner = get_page_owner(page_ext);
/*
* Access to page_ext->handle isn't synchronous so we should
* be careful to access it.
*/
handle = READ_ONCE(page_owner->handle);
if (!handle)
continue;
/* Record the next PFN to read in the file offset */
*ppos = (pfn - min_low_pfn) + 1;
return print_page_owner(buf, count, pfn, page,
page_owner, handle);
}
return 0;
}
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 = ALIGN(pfn + 1, pageblock_nr_pages);
block_end_pfn = min(block_end_pfn, end_pfn);
for (; pfn < block_end_pfn; pfn++) {
struct page *page;
struct page_ext *page_ext;
if (!pfn_valid_within(pfn))
continue;
page = pfn_to_page(pfn);
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 = page_order_unsafe(page);
if (order > 0 && order < MAX_ORDER)
pfn += (1UL << order) - 1;
continue;
}
if (PageReserved(page))
continue;
page_ext = lookup_page_ext(page);
if (unlikely(!page_ext))
continue;
/* Maybe overlapping zone */
if (test_bit(PAGE_EXT_OWNER, &page_ext->flags))
continue;
/* Found early allocated page */
__set_page_owner_handle(page_ext, early_handle, 0, 0);
count++;
}
cond_resched();
}
pr_info("Node %d, zone %8s: page owner found early allocated %lu pages\n",
pgdat->node_id, zone->name, count);
}
static noinline depot_stack_handle_t save_stack(gfp_t flags)
{
unsigned long entries[PAGE_OWNER_STACK_DEPTH];
struct stack_trace trace = {
.nr_entries = 0,
.entries = entries,
.max_entries = PAGE_OWNER_STACK_DEPTH,
.skip = 2
};
depot_stack_handle_t handle;
save_stack_trace(&trace);
if (trace.nr_entries != 0 &&
trace.entries[trace.nr_entries-1] == ULONG_MAX)
trace.nr_entries--;
/*
* We need to check recursion here because our request to stackdepot
* could trigger memory allocation to save new entry. New memory
* allocation would reach here and call depot_save_stack() again
* if we don't catch it. There is still not enough memory in stackdepot
* so it would try to allocate memory again and loop forever.
*/
if (check_recursive_alloc(&trace, _RET_IP_))
return dummy_handle;
handle = depot_save_stack(&trace, flags);
if (!handle)
handle = failure_handle;
return handle;
}
static inline void __set_page_owner_handle(struct page_ext *page_ext,
depot_stack_handle_t handle, unsigned int order, gfp_t gfp_mask)
{
struct page_owner *page_owner;
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 = -1;
__set_bit(PAGE_EXT_OWNER, &page_ext->flags);
}
noinline void __set_page_owner(struct page *page, unsigned int order,
gfp_t gfp_mask)
{
struct page_ext *page_ext = lookup_page_ext(page);
depot_stack_handle_t handle;
if (unlikely(!page_ext))
return;
handle = save_stack(gfp_mask);
__set_page_owner_handle(page_ext, handle, order, gfp_mask);
}
void __set_page_owner_migrate_reason(struct page *page, int reason)
{
struct page_ext *page_ext = lookup_page_ext(page);
struct page_owner *page_owner;
if (unlikely(!page_ext))
return;
page_owner = get_page_owner(page_ext);
page_owner->last_migrate_reason = reason;
}
void __split_page_owner(struct page *page, unsigned int order)
{
int i;
struct page_ext *page_ext = lookup_page_ext(page);
struct page_owner *page_owner;
if (unlikely(!page_ext))
return;
page_owner = get_page_owner(page_ext);
page_owner->order = 0;
for (i = 1; i < (1 << order); i++)
__copy_page_owner(page, page + i);
}
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 = ALIGN(pfn + 1, pageblock_nr_pages);
block_end_pfn = min(block_end_pfn, end_pfn);
for (; pfn < block_end_pfn; pfn++) {
struct page *page;
struct page_ext *page_ext;
if (!pfn_valid_within(pfn))
continue;
page = pfn_to_page(pfn);
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 = page_order_unsafe(page);
if (order > 0 && order < MAX_ORDER)
pfn += (1UL << order) - 1;
continue;
}
if (PageReserved(page))
continue;
page_ext = lookup_page_ext(page);
if (unlikely(!page_ext))
continue;
/* Maybe overlapping zone */
if (test_bit(PAGE_EXT_OWNER, &page_ext->flags))
continue;
/* Found early allocated page */
__set_page_owner_handle(page_ext, early_handle, 0, 0);
count++;
}
cond_resched();
}
pr_info("Node %d, zone %8s: page owner found early allocated %lu pages\n",
pgdat->node_id, zone->name, count);
}